Compare commits

..

105 Commits

Author SHA1 Message Date
claude-ceo-assistant f51722411b Merge branch 'main' into fix/issue10-runtime-aware-plugin-install
CI / Detect changes (pull_request) Successful in 13s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 14s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
E2E API Smoke Test / detect-changes (pull_request) Successful in 13s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 10s
pr-guards / disable-auto-merge-on-push (pull_request) Failing after 6s
Harness Replays / detect-changes (pull_request) Successful in 11s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 12s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 12s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 4s
CI / Canvas (Next.js) (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 1m6s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 7s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m41s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m44s
Harness Replays / Harness Replays (pull_request) Failing after 55s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 1m13s
CI / Platform (Go) (pull_request) Successful in 5m42s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 5m44s
2026-05-07 11:26:14 +00:00
claude-ceo-assistant f0015bff81 Merge pull request 'fix(workspace-server): default-bind to 127.0.0.1 in dev-mode fail-open (closes #7)' (#8) from fix/s8-bind-loopback-dev into main
CI / Canvas Deploy Reminder (push) Blocked by required conditions
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
Auto-sync main → staging / sync-staging (push) Failing after 8s
CI / Detect changes (push) Successful in 7s
E2E API Smoke Test / detect-changes (push) Successful in 11s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 12s
Handlers Postgres Integration / detect-changes (push) Successful in 10s
Harness Replays / detect-changes (push) Successful in 10s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 11s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 8s
CodeQL / Analyze (${{ matrix.language }}) (go) (push) Failing after 1m7s
publish-workspace-server-image / build-and-push (push) Failing after 50s
CI / Shellcheck (E2E scripts) (push) Successful in 6s
CI / Python Lint & Test (push) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 8s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 9s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 6s
CI / Platform (Go) (push) Has been cancelled
CI / Canvas (Next.js) (push) Has been cancelled
E2E API Smoke Test / E2E API Smoke Test (push) Has been cancelled
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (push) Has been cancelled
CodeQL / Analyze (${{ matrix.language }}) (python) (push) Has been cancelled
Harness Replays / Harness Replays (push) Has been cancelled
2026-05-07 11:25:48 +00:00
claude-ceo-assistant b72d1d3f26 Merge branch 'main' into fix/issue10-runtime-aware-plugin-install
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 10s
pr-guards / disable-auto-merge-on-push (pull_request) Failing after 6s
CI / Detect changes (pull_request) Successful in 13s
E2E API Smoke Test / detect-changes (pull_request) Successful in 13s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 11s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 13s
Harness Replays / detect-changes (pull_request) Successful in 13s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 13s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 13s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Successful in 7s
CI / Canvas (Next.js) (pull_request) Successful in 23s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 20s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 1m1s
Harness Replays / Harness Replays (pull_request) Failing after 42s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m44s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m45s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 1m35s
CI / Platform (Go) (pull_request) Successful in 6m34s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 7m21s
2026-05-07 11:25:24 +00:00
claude-ceo-assistant a674a6547e Merge branch 'main' into fix/s8-bind-loopback-dev
pr-guards / disable-auto-merge-on-push (pull_request) Failing after 2s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 5s
CI / Detect changes (pull_request) Successful in 8s
E2E API Smoke Test / detect-changes (pull_request) Successful in 8s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 9s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 10s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 11s
Harness Replays / detect-changes (pull_request) Successful in 15s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 8s
CI / Canvas (Next.js) (pull_request) Successful in 8s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 7s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 12s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CI / Python Lint & Test (pull_request) Successful in 35s
Harness Replays / Harness Replays (pull_request) Failing after 47s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m44s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m46s
CI / Platform (Go) (pull_request) Failing after 6m9s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 7m29s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 15m32s
2026-05-07 11:25:20 +00:00
claude-ceo-assistant f2f5338183 Merge pull request 'fix(ci): lowercase 'molecule-ai/' in cross-repo workflow refs' (#17) from fix/lowercase-org-slug into main
Auto-sync main → staging / sync-staging (push) Failing after 13s
auto-tag-runtime / tag (push) Successful in 13s
Block internal-flavored paths / Block forbidden paths (push) Successful in 9s
Check merge_group trigger on required workflows / Required workflows have merge_group trigger (push) Successful in 11s
CI / Detect changes (push) Successful in 11s
E2E API Smoke Test / detect-changes (push) Successful in 7s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 7s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (push) Successful in 7s
Harness Replays / detect-changes (push) Successful in 10s
Handlers Postgres Integration / detect-changes (push) Successful in 15s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 8s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 10s
SECRET_PATTERNS drift lint / Detect SECRET_PATTERNS drift (push) Successful in 35s
publish-workspace-server-image / build-and-push (push) Failing after 3m9s
CI / Shellcheck (E2E scripts) (push) Successful in 14s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 1m6s
Harness Replays / Harness Replays (push) Failing after 53s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 8s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 43s
CI / Canvas (Next.js) (push) Failing after 6m45s
CI / Canvas Deploy Reminder (push) Has been skipped
CI / Platform (Go) (push) Successful in 9m33s
CodeQL / Analyze (${{ matrix.language }}) (go) (push) Failing after 18m48s
CodeQL / Analyze (${{ matrix.language }}) (python) (push) Failing after 18m50s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (push) Failing after 18m58s
CI / Python Lint & Test (push) Successful in 15m53s
Canary — staging SaaS smoke (every 30 min) / Canary smoke (push) Failing after 10s
2026-05-07 10:38:12 +00:00
security-auditor e01077be38 fix(ci): lowercase 'molecule-ai/' in cross-repo workflow refs
Retarget main PRs to staging / Retarget to staging (pull_request) Has been skipped
cascade-list-drift-gate / check (pull_request) Successful in 3s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 3s
Check merge_group trigger on required workflows / Required workflows have merge_group trigger (pull_request) Successful in 5s
CI / Detect changes (pull_request) Successful in 4s
E2E API Smoke Test / detect-changes (pull_request) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 4s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 5s
Harness Replays / detect-changes (pull_request) Successful in 4s
pr-guards / disable-auto-merge-on-push (pull_request) Failing after 0s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 50s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 3s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 4s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m16s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m16s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 7s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Failing after 16s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 4s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 3s
Harness Replays / Harness Replays (pull_request) Failing after 40s
CI / Canvas (Next.js) (pull_request) Failing after 4m47s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CI / Platform (Go) (pull_request) Successful in 5m25s
Gitea is case-sensitive on owner slugs; canonical is lowercase
`molecule-ai/...`. Mixed-case `Molecule-AI/...` refs fail-at-0s
when the runner tries to resolve the cross-repo workflow / checkout.

Same fix as molecule-controlplane#12. Mechanical case-correction;
no behavior change beyond making CI resolve again.

Refs: internal#46

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-07 01:00:10 -07:00
security-auditor c1de2287fd fix(workspace-server): SSOT-route container check + 422 on external runtimes
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 4s
CI / Detect changes (pull_request) Successful in 5s
E2E API Smoke Test / detect-changes (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 6s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 6s
Harness Replays / detect-changes (pull_request) Successful in 5s
Retarget main PRs to staging / Retarget to staging (pull_request) Has been skipped
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 6s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
CI / Canvas (Next.js) (pull_request) Successful in 5s
CI / Python Lint & Test (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 7s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 53s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 44s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 4s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m21s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m28s
Harness Replays / Harness Replays (pull_request) Failing after 43s
CI / Platform (Go) (pull_request) Successful in 3m19s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 4m46s
Two coupled fixes for molecule-core#10 (plugin install 503 vs
status=online split-state):

1. SSOT for "is this workspace's container running" — `findRunningContainer`
   in plugins.go used to carry its own copy of `cli.ContainerInspect`, which
   collapsed transient daemon errors into the same `""` return as a
   genuinely-stopped container. Healthsweep's `Provisioner.IsRunning`
   handled the same input correctly (defensive). Promote the inspect logic
   to `provisioner.RunningContainerName`, route both consumers through it.
   Transient errors get a distinct log line on the plugins side so triage
   doesn't confuse a flaky daemon with a stopped container.

2. Runtime-aware Install/Uninstall — `runtime='external'` workspaces have
   no local container; push-install via docker exec is meaningless. They
   pull plugins via the download endpoint instead (Phase 30.3). Without a
   guard they fell through to `findRunningContainer` and 503'd with a
   misleading "container not running." Add an early 422 with a hint
   pointing at the download endpoint.

The two fixes are independent: (1) preserves correctness when the SSOT
helper is later modified; (2) eliminates the persistent split-state on
the 5 external persona-agent workspaces in this DB (and on tenant
deployments hitting the same shape).

* `internal/provisioner/provisioner.go` — new `RunningContainerName(ctx,
  cli, id) (string, error)` with three documented outcomes (running /
  stopped / transient). `Provisioner.IsRunning` now wraps it; behavior
  preserved.
* `internal/handlers/plugins.go` — `findRunningContainer` shimmed onto
  `RunningContainerName`; new `isExternalRuntime(id)` predicate.
* `internal/handlers/plugins_install.go` — Install + Uninstall reject
  external runtimes with 422 + hint, before the source-fetch step.
* `internal/handlers/plugins_install_external_test.go` — 5 cases:
  external→422, uninstall-external→422, container-backed-falls-through,
  no-runtime-lookup-fails-open, lookup-error-fails-open.
* `internal/handlers/plugins_findrunning_ssot_test.go` — two AST gates
  pin the SSOT routing so future PRs can't silently re-introduce the
  parallel impl. Mutation-tested: reverting either consumer to a direct
  `ContainerInspect` makes the gate fail.

Refs: molecule-core#10

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 22:58:20 -07:00
security-auditor f3187ea0c1 fix(workspace-server): default-bind to 127.0.0.1 in dev-mode fail-open
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 4s
CI / Detect changes (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 5s
E2E API Smoke Test / detect-changes (pull_request) Successful in 5s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 6s
Retarget main PRs to staging / Retarget to staging (pull_request) Has been skipped
Harness Replays / detect-changes (pull_request) Successful in 5s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 5s
CI / Canvas (Next.js) (pull_request) Successful in 5s
CI / Python Lint & Test (pull_request) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 5s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 4s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 4s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Harness Replays / Harness Replays (pull_request) Failing after 35s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 56s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 1m24s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m25s
CI / Platform (Go) (pull_request) Successful in 1m48s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 4m47s
In dev mode (`MOLECULE_ENV=dev|development`, `ADMIN_TOKEN` unset) the
AdminAuth chain fails open by design so canvas at :3000 can call
workspace-server at :8080 without a bearer token. Combined with the
existing wildcard bind on `:8080`, that exposed unauthenticated
`POST /workspaces` to any same-LAN peer (S-8 in the audit RFC v1).

Couple the bind narrowness to the same signal that drives the auth
fail-open: when `middleware.IsDevModeFailOpen()` returns true, default
the listener to `127.0.0.1`. Production (`ADMIN_TOKEN` set) keeps
binding to all interfaces — its auth chain is doing the work. Operators
who need LAN exposure set `BIND_ADDR=<host>` explicitly.

* `cmd/server/main.go` — `resolveBindHost()` precedence: BIND_ADDR
  explicit > IsDevModeFailOpen() loopback > "" (all interfaces).
  Startup log line now includes the resolved bind + dev-mode-fail-open
  state for post-deploy auditing.
* `cmd/server/bind_test.go` — 8 t.Setenv table cases covering
  precedence, explicit overrides, dev/prod env words. Mutation-tested:
  removing the `IsDevModeFailOpen()` branch makes the dev-mode cases
  fail with "" vs "127.0.0.1".

Refs: molecule-core#7

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 22:29:24 -07:00
claude-ceo-assistant f92ba492de Merge pull request 'test(org_import): tighten sqlmock regex on lookupExistingChild (#2872 PR-B)' (#3) from fix/2872-sqlmock-regex-tightening into staging
Harness Replays / detect-changes (push) Successful in 6s
Harness Replays / Harness Replays (push) Failing after 43s
publish-workspace-server-image / build-and-push (push) Failing after 2m17s
Auto-sync main → staging / sync-staging (push) Successful in 6s
CI / Detect changes (push) Successful in 6s
E2E API Smoke Test / detect-changes (push) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 6s
Handlers Postgres Integration / detect-changes (push) Successful in 5s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 5s
CI / Shellcheck (E2E scripts) (push) Failing after 4s
Block internal-flavored paths / Block forbidden paths (push) Successful in 26s
CI / Python Lint & Test (push) Failing after 10s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Failing after 10s
CodeQL / Analyze (${{ matrix.language }}) (go) (push) Failing after 48s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Failing after 27s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 40s
Secret scan / Scan diff for credential-shaped strings (push) Failing after 1m11s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (push) Failing after 1m23s
CodeQL / Analyze (${{ matrix.language }}) (python) (push) Failing after 1m24s
CI / Canvas (Next.js) (push) Failing after 1m57s
CI / Canvas Deploy Reminder (push) Has been skipped
CI / Platform (Go) (push) Failing after 2m27s
E2E API Smoke Test / E2E API Smoke Test (push) Failing after 4m45s
SECRET_PATTERNS drift lint / Detect SECRET_PATTERNS drift (push) Failing after 14s
Canary — staging SaaS smoke (every 30 min) / Canary smoke (push) Failing after 16s
2026-05-07 00:19:40 +00:00
Hongming Wang 00cfe51df7 test(org_import): tighten sqlmock regex on lookupExistingChild (#2872 PR-B)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 6s
CI / Detect changes (pull_request) Successful in 6s
E2E API Smoke Test / detect-changes (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 5s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 4s
Harness Replays / detect-changes (pull_request) Successful in 5s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 41s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 6s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 3s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 1m23s
CI / Python Lint & Test (pull_request) Successful in 31s
CI / Canvas (Next.js) (pull_request) Successful in 52s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 40s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 4s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 40s
Harness Replays / Harness Replays (pull_request) Failing after 43s
CI / Platform (Go) (pull_request) Failing after 2m23s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 4m47s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 14m23s
The five `mock.ExpectQuery(\`SELECT id FROM workspaces\`)` sites used a
loose substring regex that silent-passed three regression shapes #2872
called out:

  1. `WHERE parent_id = $2` (drops `IS NOT DISTINCT FROM` — breaks
     NULL-parent root matching)
  2. `WHERE name = $1` only (drops parent_id check entirely — hijacks
     siblings of the same name across different parents)
  3. Drops `AND status != 'removed'` (blocks re-import after Collapse)

Extracts a `lookupChildSQLRE` const that anchors all four load-bearing
tokens (the SELECT/FROM, the name predicate, the IS NOT DISTINCT FROM
predicate, and the status filter). All five ExpectQuery sites now use
the same const so a future schema/predicate change fails one place.

Mutation-tested per memory feedback_assert_exact_not_substring.md:
- Replacing `IS NOT DISTINCT FROM` with `=` fails
  TestLookupExistingChild_NilParent_MatchesRoot.
- Dropping `AND status != 'removed'` fails
  TestLookupExistingChild_Found_ReturnsIDAndTrue.

Note: #2872 PR-A (AST gate strengthening) is already addressed inline —
findWorkspacesInsertSQL + TestCreateWorkspaceTree_InsertUsesOnConflictDoNothing
pin the ON CONFLICT DO NOTHING shape, which is a strictly stronger
gate than the original lookup-before-insert ordering check.
2026-05-06 16:43:42 -07:00
claude-ceo-assistant 55ef3176ed feat(provisioner): env-driven RegistryPrefix() for workspace template images (#6)
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
CI / Detect changes (push) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 6s
Handlers Postgres Integration / detect-changes (push) Successful in 5s
Harness Replays / detect-changes (push) Successful in 5s
E2E API Smoke Test / detect-changes (push) Successful in 9s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 5s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 5s
CI / Shellcheck (E2E scripts) (push) Successful in 2s
CI / Python Lint & Test (push) Successful in 30s
CodeQL / Analyze (${{ matrix.language }}) (go) (push) Failing after 48s
CI / Canvas (Next.js) (push) Successful in 48s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 49s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 4s
CI / Canvas Deploy Reminder (push) Has been skipped
CodeQL / Analyze (${{ matrix.language }}) (python) (push) Failing after 1m19s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 39s
Harness Replays / Harness Replays (push) Failing after 37s
CI / Platform (Go) (push) Failing after 2m8s
publish-workspace-server-image / build-and-push (push) Failing after 2m39s
E2E API Smoke Test / E2E API Smoke Test (push) Failing after 4m46s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (push) Failing after 13m21s
Allows MOLECULE_IMAGE_REGISTRY env override on the tenant workspace-server. Used to flip from ghcr.io/molecule-ai → private ECR mirror after the GitHub org suspension on 2026-05-06. Default unchanged for OSS users.

Closes #6.
2026-05-06 22:51:53 +00:00
claude-ceo-assistant 4b074f631b feat(provisioner): env-driven RegistryPrefix() for workspace template images (#6)
pr-guards / disable-auto-merge-on-push (pull_request) Failing after 0s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 41s
Harness Replays / Harness Replays (pull_request) Failing after 30s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CI / Platform (Go) (pull_request) Failing after 3m8s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Failing after 5m7s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (pull_request) Failing after 14m4s
CodeQL / Analyze (${{ matrix.language }}) (go) (pull_request) Failing after 14m36s
CodeQL / Analyze (${{ matrix.language }}) (python) (pull_request) Failing after 14m30s
Block internal-flavored paths / Block forbidden paths (pull_request) Has been cancelled
CI / Python Lint & Test (pull_request) Has been cancelled
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Has been cancelled
CI / Canvas (Next.js) (pull_request) Has been cancelled
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Has been cancelled
CI / Detect changes (pull_request) Has been cancelled
Secret scan / Scan diff for credential-shaped strings (pull_request) Has been cancelled
E2E API Smoke Test / detect-changes (pull_request) Has been cancelled
Runtime PR-Built Compatibility / detect-changes (pull_request) Has been cancelled
Harness Replays / detect-changes (pull_request) Has been cancelled
Handlers Postgres Integration / detect-changes (pull_request) Has been cancelled
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Has been cancelled
CI / Shellcheck (E2E scripts) (pull_request) Has been cancelled
Add MOLECULE_IMAGE_REGISTRY env var to override the registry prefix used
by all workspace-template image references. Defaults to ghcr.io/molecule-ai
(unchanged for OSS users); set to an ECR URI in production tenants when
mirroring to AWS.

Why this matters: GitHub suspended the Molecule-AI org on 2026-05-06 with
no warning. Production tenants kept running because they had images cached
locally, but any tenant restart (AWS health event, redeploy, OS reboot)
would have failed at `docker pull ghcr.io/molecule-ai/...` because GHCR
returned 401. This change introduces the seam needed to point new pulls at
a registry we control (AWS ECR) by flipping a single env var on Railway.

Design (RFC: molecule-ai/internal#6):

- New `RegistryPrefix()` function in `provisioner/registry.go` reads
  MOLECULE_IMAGE_REGISTRY, falls back to "ghcr.io/molecule-ai".
- New `RuntimeImage(runtime)` returns the canonical ref using the prefix.
- `RuntimeImages` map computed at init via `computeRuntimeImages()` so
  existing callers that range over it still work.
- `DefaultImage` likewise computed via `RuntimeImage(defaultRuntime)`.
- `handlers.TemplateImageRef()` switched from hardcoded format string to
  `provisioner.RegistryPrefix()`.
- `runtime_image_pin.go::resolveRuntimeImage()` automatically inherits
  the prefix change because it reads from `provisioner.RuntimeImages[]`
  and only re-formats the tag suffix to a digest pin.

Alternatives rejected (see RFC):

- Multi-registry fallback chain (try ECR, fall back to GHCR): GHCR is
  locked from outbound for our org, so the fallback never works for us.
  Adds code complexity for no benefit.
- Hardcoded ECR-only switch: couples production code to a specific
  deployment environment. OSS users self-hosting Molecule would need
  the upstream GHCR.
- Self-hosted Harbor / registry-on-Hetzner: adds a component to operate.
  Not justified at 3-tenant scale; AWS ECR is mature and IAM-integrated.

Auth — deliberately NOT changed in this commit:

- For GHCR, the existing `ghcrAuthHeader()` reads GHCR_USER/GHCR_TOKEN.
- For ECR, EC2 user-data installs `amazon-ecr-credential-helper` and adds
  a `credHelpers` entry in `~/.docker/config.json` so the daemon resolves
  ECR credentials via the EC2 instance role on every pull. The Go code
  needs no auth change. This keeps the diff minimal.

Backwards compatibility:

- Additive: env unset → identical behavior to today (GHCR).
- Existing tests reference literal `ghcr.io/molecule-ai/...` strings;
  they continue to pass under the default prefix.
- `RuntimeImages` map preserved for callers that iterate it.
- No interface, schema, API, or migration version bump needed.

Security review:

- No untrusted input: MOLECULE_IMAGE_REGISTRY is set at deploy time
  (Railway env, EC2 user-data), not by users.
- No expanded data collection or logging changes.
- No new permissions: ECR pull permission is a future user-data + IAM
  role change, separate from this code change.
- Worst-case: an attacker who already compromises Railway can swap the
  registry prefix to a malicious URI — same blast radius as compromising
  Railway today, no expansion.

Tests:

- 9 new unit tests in `registry_test.go` covering: default fallback,
  env override, empty env, all 9 known runtimes, unknown runtime,
  override-applies-to-all, computeRuntimeImages map population, env
  reflection, alphabetical ordering pin.
- All existing provisioner + handlers tests continue to pass.
- Mutation-tested mentally: deleting `if v := os.Getenv(...)` makes
  TestRegistryPrefix_RespectsEnv fail. Deleting `for _, r := range
  knownRuntimes` makes TestRuntimeImage_AllKnownRuntimes fail. The test
  suite would catch a regression of the original failure mode.

Rollout plan: this PR is safe to merge with no env change. Production
cutover happens by setting MOLECULE_IMAGE_REGISTRY on Railway after
the AWS ECR mirror is populated (separate ops change, tracked in
issue #6 phases 3b–3f).

Tracking:
- RFC: molecule-ai/internal#6
- Tasks: #97 (ECR setup), #98 (CP fallback)
- Tech debt: runbooks/hetzner-rollout-tech-debt-2026-05-06.md item 7

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-06 14:23:01 -07:00
hongming-personal 50c3bdfd6c Merge pull request #3028 from Molecule-AI/rfc-2945-pr-d-message-store
CI / Detect changes (push) Successful in 11s
Handlers Postgres Integration / detect-changes (push) Successful in 7s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 16s
E2E API Smoke Test / detect-changes (push) Successful in 17s
Block internal-flavored paths / Block forbidden paths (push) Successful in 25s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 13s
Secret scan / Scan diff for credential-shaped strings (push) Failing after 53s
CI / Shellcheck (E2E scripts) (push) Failing after 6s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 29s
CI / Python Lint & Test (push) Failing after 39s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 4s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 24s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 53s
CI / Canvas (Next.js) (push) Failing after 3m21s
CI / Canvas Deploy Reminder (push) Has been skipped
CI / Platform (Go) (push) Failing after 3m47s
CodeQL / Analyze (${{ matrix.language }}) (go) (push) Failing after 14m15s
CodeQL / Analyze (${{ matrix.language }}) (javascript-typescript) (push) Failing after 14m33s
CodeQL / Analyze (${{ matrix.language }}) (python) (push) Failing after 14m34s
feat(messagestore): MessageStore interface + Postgres impl (RFC #2945 PR-D)
2026-05-06 06:42:13 +00:00
hongming-personal a33c879017 feat(messagestore): MessageStore interface + Postgres impl (RFC #2945 PR-D)
Closes #3026. Final piece of RFC #2945.

## What's new

New package internal/messagestore/ holds:

  - MessageStore interface — single read-side contract operators
    implement to plug in alternative chat-history backends.
  - ChatMessage / ChatAttachment / ListOptions types — canonical data
    shapes returned by any impl, mirrors canvas's TS ChatMessage.
  - PostgresMessageStore — platform-default impl wrapping the
    activity_logs query + A2A-envelope parser ported in PR-C.
    Behavior is byte-identical to the pre-PR-D handler.

## What moves

The activity_logs query, the parser (activityRowToChatMessages,
extractRequestText, extractChatResponseText, extractFilesFromTask,
etc.), and the internal-self-message predicate all migrate from
internal/handlers/chat_history.go into the new package. handlers/
chat_history.go becomes a thin HTTP-shape adapter:

  parse query params → store.List(ctx, workspaceID, opts) → emit JSON

Compile-time interface assertion in postgres_store.go catches future
drift if the interface evolves and the impl falls behind.

## Why this PR

OSS operators wanting to:

  - Tier hot/warm/cold storage (recent in Postgres, archival in S3)
  - Use a vector store with hybrid search (Pinecone, Weaviate)
  - Run an in-memory store for ephemeral test environments
  - Federate history across regions

…had no extension point — they'd have to fork the handler. This PR
makes that a constructor swap at router.go.

## Tests

  Parser-level (22 tests, MOVED to internal/messagestore/postgres_
  store_test.go): every TS test case in
  canvas/src/components/tabs/chat/__tests__/historyHydration.test.ts
  has a Go counterpart. Timestamp preservation, user/agent extraction,
  internal-self filter, role decision (status=error vs agent-error
  prefix), v0/v1 file shapes, malformed JSON resilience.

  Handler-level (9 NEW tests in internal/handlers/chat_history_test.go):
  thin adapter coverage using a fake MessageStore. UUID validation,
  before_ts RFC3339 validation, default limit, max-limit clamp,
  invalid-limit fallback, before_ts passthrough, empty-array (not
  null) JSON shape, attachment shape preservation, store-error → 502
  mapping.

  Compile-time interface conformance: PostgresMessageStore satisfies
  MessageStore, fakeStore (test fake) satisfies MessageStore.

  Mutation-tested. Removed UUID validation in the handler; confirmed
  TestChatHistoryHandler_RejectsNonUUIDWorkspaceID fires red (status
  200 instead of 400, non-UUID reaches the store). Restored, all
  green.

  Full handlers + messagestore + router test runs green; full repo
  go test ./... green.

## SSOT decision

ChatMessage / ChatAttachment / parser / DB query all live in
internal/messagestore/ ONLY. handlers/chat_history.go imports the
package and uses the types via messagestore.ChatMessage etc. — no
re-declaration anywhere.

## Three weakest spots (hostile-reviewer self-pass)

1. The internal-self prefix list (Delegation results are ready...) is
   a package var in messagestore/postgres_store.go. A future impl
   that wants to override the predicate must reach into the package
   to use IsInternalSelfMessage or define its own. Acceptable: the
   predicate is part of the contract; if an impl wants different
   semantics it owns that decision explicitly.

2. ListOptions has Limit + BeforeTS + HasBefore; future paging needs
   (after_ts, peer_id filter, role filter) require additive struct
   field additions, which is a soft API break for any impl that
   handles ListOptions positionally. Mitigated by Go's struct-literal
   convention (named fields by default); also flagged in the
   interface comment for impl authors.

3. The handler does NOT log when a store returns an error — it just
   maps to 502. An impl that wants to surface its error class up the
   stack can't, today. If/when an impl needs that, the interface can
   add a typed-error contract in a follow-up. Today's coverage is
   sufficient: most ops issues land in the store impl's own logs.

## Security review

  - Untrusted input? Same as PR-C — agent-emitted JSON parsed
    defensively. New fakeStore in tests can't reach production.
  - Trust boundary? Same. Interface lives BEHIND wsAuth; impls only
    see workspace IDs already authenticated.
  - Auth/authz? Inherited from handler; the interface doesn't
    authenticate.
  - PII / secrets in logs? Documented in the interface contract:
    impls MUST NOT log full message bodies / attachment URIs. The
    Postgres impl logs nothing on the happy path.
  - Output sanitization? Same plain-text + opaque-URI surface as
    PR-C. Canvas validates attachment-URI schemes.

No security-relevant changes beyond what /chat-history already
exposes via PR-C. Considered, not skipped.

## Versioning / backwards compat

  - New internal package. Zero public API change.
  - Single caller site in router.go updated (one-line constructor
    change). NewChatHistoryHandler() → NewChatHistoryHandler(store).
  - No schema change, no migration.
  - Existing /chat-history endpoint unchanged on the wire — clients
    don't notice the refactor.

## Phasing

This is the final RFC #2945 piece. Follow-ups parked:

  - PR-C-2 (canvas migration): swap canvas loadMessagesFromDB to call
    /chat-history instead of /activity. Independent of this PR;
    blocked only by canvas team's calendar.
  - Sample alternative impls (S3, in-memory) for OSS docs: separate
    PR when the first OSS consumer materializes; demonstration code
    untested against a real workload is anti-pattern.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 23:38:14 -07:00
hongming-personal e91186c4bf Merge pull request #3020 from Molecule-AI/rfc-2945-pr-c-chat-history
feat(workspace-server): server-side chat-history endpoint (RFC #2945 PR-C)
2026-05-06 06:23:12 +00:00
hongming-personal 089be695a9 Merge staging into rfc-2945-pr-c-chat-history 2026-05-05 23:18:52 -07:00
hongming-personal dcc870a6b7 feat(workspace-server): server-side chat-history endpoint (RFC #2945 PR-C)
Closes the SSOT gap for chat-history hydration: today every consumer
(canvas TS) re-implements an A2A-envelope walk to map activity_logs
rows into rendered ChatMessage objects. This PR moves that walk into
the server.

## What's added

GET /workspaces/:id/chat-history?limit=N&before_ts=T

Returns:

  {
    "messages": [
      {"id": "<uuid>", "role": "user"|"agent"|"system",
       "content": "...", "attachments": [...], "timestamp": "<RFC3339>"}
    ],
    "reached_end": false
  }

Auth chain: same wsAuth as /workspaces/:id/activity (tenant ADMIN_TOKEN
+ X-Molecule-Org-Id). No new trust boundary.

Filter: a2a_receive rows with source_id IS NULL — same canvas-source
filter the canvas applies via /activity?type=a2a_receive&source=canvas,
centralized so future API consumers don't need to know it.

## What's mirrored from canvas TS

Direct port of canvas/src/components/tabs/chat/historyHydration.ts
+ message-parser.ts:

  - extractRequestText / extractFilesFromUserMessage — user-side parts
    walk through request_body.params.message.parts[]
  - extractChatResponseText — agent-side response_body collector across
    the four shapes (string, A2A JSON-RPC parts, older nested
    parts.root.text, task artifacts) joined with "\n" (matches canvas
    multi-source collector — claude-code emits multiple text parts;
    hermes emits summary+artifacts)
  - extractFilesFromResponse / extractFilesFromTask — file walk across
    parts[] + artifacts[].parts[] + status.message.parts[] +
    message.parts[]
  - v0 hot path ({kind:"file", file:{...}}) AND v1 protobuf flat shape
    ({url, filename, mediaType}) both supported
  - Role decision: status='error' OR text starts with "agent error"
    (case-insensitive) → "system", else "agent"
  - isInternalSelfMessage prefix filter (Delegation results are
    ready...)
  - Timestamp pinned to row.created_at (regression cover for
    2026-04-25 bubble-collapse bug)

## Tests

22 unit tests in chat_history_test.go, every TS test case in
historyHydration.test.ts has a Go counterpart:

  Timestamp preservation (3): user/agent pin to created_at, two-rows
  produce two distinct timestamps.

  User-message extraction (5): text-only, internal-self skip,
  null body, attachments hydrated, attachments-only-when-text-empty,
  internal-self suppresses even with attachments.

  Agent-message extraction (4): result-string, status=error→system,
  agent-error-prefix→system, response_body.parts attachments,
  null body, no-text-no-files-no-bubble.

  End-to-end (1): paired user+agent same timestamp.

  Go-specific (5): malformed JSON returns empty (no panic), v1
  protobuf flat shape extraction, task-artifacts extraction, older
  nested root.text shape, basename helper edge cases.

  isInternalSelfMessage predicate (1): prefix match, non-prefix non-
  match, empty-text non-match.

Mutation-tested. Removed the role-promotion branch (status=error +
agent-error prefix → system); confirmed both
TestChatHistory_RoleSystemWhenStatusError and
TestChatHistory_RoleSystemWhenAgentErrorPrefix fire red. Restored.
Both green.

Full handlers test suite (4.3s) green; full repo `go test ./...` green.

## SSOT decision

Parsing logic lives in workspace-server/internal/handlers/chat_history.go
ONLY. Canvas keeps historyHydration.ts + message-parser.ts during the
transition because:

  - PR-C-2 (follow-up): canvas loadMessagesFromDB swaps to new
    endpoint. Today's canvas still calls /activity for backward
    compatibility.
  - The TS parsers are still load-bearing for LIVE message handling
    (WebSocket A2A_RESPONSE events) until RFC #2945 PR-B-2 mirrors
    the typed event payloads to canvas consumers.

Canvas's TS path will be deleted in a separate PR after a one-week
observation window confirms no live-message consumers depend on it.

## Security review

  - Untrusted input? YES — request_body and response_body come from
    agents (potentially OSS / third-party). Defensive: any malformed
    JSON returns empty content + no attachments, no panic. Tested
    via TestChatHistory_MalformedJSONInRequestBodyReturnsEmpty.
  - Trust boundary? Same as today: agent → workspace-server.
    No new boundary; reuses existing wsAuth middleware.
  - Auth/authz? Inherits wsAuth chain. Cross-workspace access blocked
    by existing TenantGuard middleware.
  - PII / secrets in logs? None. The handler logs nothing on the
    happy path; errors log 502 without body content.
  - Output sanitization? ChatMessage.content is plain text returned
    as-is; canvas already sanitizes via ReactMarkdown. Attachment
    URIs are agent-provided (workspace: / platform-pending: /
    https:); canvas's existing scheme allow-list still applies.

## Versioning / backwards compatibility

  - New endpoint /chat-history. /activity unchanged.
  - Canvas historyHydration.ts + message-parser.ts intact during
    transition (will be removed in PR-C-2 follow-up).
  - No public API consumer of /activity is broken — added route is
    additive.
  - No semver bump (server is internal versioning).

## Three weakest spots (hostile-reviewer self-pass)

1. extractRequestText returns ONLY parts[0].text. If a user message
   contains multiple text parts (uncommon — canvas only ever emits
   one), we lose later parts. Matches canvas exactly today, but a
   future change that emits multi-text user messages needs both
   parsers updated. Documented in code; covered by test if/when
   added.

2. activityRowToChatMessages rebuilds ChatMessage IDs every call (no
   caching). Each chat reload mints fresh UUIDs. This is fine because
   canvas dedupes by (role, content, timestamp window) not id, but a
   future API consumer that DID rely on id stability would break.
   Documented in the ChatMessage struct comment.

3. The handler scopes to source_id IS NULL only (canvas-source rows).
   A future "show all messages, including agent-to-agent" mode would
   need a new endpoint or a parameter. Out of scope for PR-C; canvas's
   /activity?source=canvas already enforces the same filter.

Closes #3017. Unblocks RFC #2945 PR-D (MessageStore interface) which
returns []ChatMessage typed values.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 23:17:26 -07:00
hongming-personal d144dcc700 Merge pull request #3016 from Molecule-AI/fix/textutil-ssot-truncate-2962
fix(textutil): SSOT for rune-safe string truncation, fix 3 audit-gap bugs (#2962)
2026-05-06 06:05:00 +00:00
Hongming Wang 656a02fae4 fix(textutil): SSOT for rune-safe string truncation, fix 3 audit-gap bugs
Closes #2962.

## Why

Six per-package `truncate` helpers had drifted into independent
re-implementations of the same idea. Three of them (delegation.go,
memory/client/client.go, memory-backfill/verify.go) used
`s[:max] + "…"` byte-slice form, which on a multi-byte codepoint at
byte `max` produces invalid UTF-8 → Postgres `text`/`jsonb` rejects
the INSERT silently → `delegation` / `activity_logs` row never lands
→ audit gap.

Three other helpers (delegation_ledger.go #2962, agent_message_writer.go
#2959, scheduler.go #2026) had each been fixed in isolation with three
slightly different rune-safe shapes — confirming this is a class of
bug, not a single instance.

## What

New package `internal/textutil` with three rune-safe functions:

- `TruncateBytes(s, maxBytes)` — byte-cap, "…" marker. Used by 5
  callers writing into byte-bounded columns / log lines.
- `TruncateBytesNoMarker(s, maxBytes)` — byte-cap, no marker. Used by
  delegation_ledger.go where the storage already conveys "preview"
  and an extra ellipsis would push the result over the column cap.
- `TruncateRunes(s, maxRunes)` — rune-cap, "…" marker. Used by
  agent_message_writer.go where the cap is in display chars (UI
  summary), not bytes.

All three guarantee `utf8.ValidString(out)` for any `utf8.ValidString(in)`.
Inputs already invalid go through `sanitizeUTF8` at the call site
boundary (scheduler.go preserved this defense-in-depth).

## Migration map

| Old | New | Behavior change |
|---|---|---|
| `delegation_ledger.truncatePreview` | `textutil.TruncateBytesNoMarker(s, 4096)` | none |
| `agent_message_writer.truncatePreviewRunes` | `textutil.TruncateRunes(s, n)` | none |
| `scheduler.truncate` | `textutil.TruncateBytes(s, n)` | "..." → "…" (3 bytes either way; single-glyph display) |
| `delegation.truncate` | `textutil.TruncateBytes(s, n)` | bug fix + ellipsis swap |
| `memory/client.truncate` | `textutil.TruncateBytes(s, n)` | bug fix |
| `memory-backfill.truncate` | `textutil.TruncateBytes(s, n)` | bug fix |

Five separate `truncate*` helpers + their per-package tests removed.
Net: 12 files / +427 / -255.

## Tests

- `internal/textutil/truncate_test.go` — 27 table-test cases + 145
  fuzz-invariant cases asserting `utf8.ValidString` and byte-cap
  invariants on every output.
- `delegation_ledger_test.go TestLedgerInsert_TruncatesOversizedPreview`
  strengthened with `capValidUTF8Matcher` so the SQL-write argument
  is asserted to be valid UTF-8 + within cap (not just `AnyArg()`).
  Mutation-tested: replacing the SSOT call with byte-slice form makes
  this test fail loud.

## Compatibility

- All callers internal; no external API surface change.
- Ellipsis swap "..." → "…": same byte budget (3 bytes), single-glyph
  display. No alerting/grep on either marker in this codebase
  (verified). Canvas renders both correctly.
- DB column widths unchanged (4096 / 80 / 200 / 256 / 300 — all
  preserved in the migrations).

## Security

Fixes a silent INSERT-failure mode that hid `activity_logs` /
`delegations` rows containing peer-controlled text. The class of input
that triggered it (CJK, emoji, accented Latin) is normal user content,
not malicious — but the symptom (audit gap) makes incident
reconstruction harder. Helper is pure-function over `string`; no
secrets / PII / auth handling involved. Untrusted input is handled
identically to before, just rune-aligned now.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 23:01:21 -07:00
hongming-personal c53155ec5f Merge pull request #3014 from Molecule-AI/test/cross-table-atomicity-integ-149-followup
test(chat-uploads): integration test for cross-table atomicity (#149 follow-up)
2026-05-06 05:05:49 +00:00
Hongming Wang debe29c889 ci(handlers-postgres-integration): apply legacy *.sql migrations too
The migration-replay step globbed only *.up.sql, silently skipping
the older flat-naming migrations (001_workspaces.sql,
009_activity_logs.sql, etc.). Fine while no integration test
depended on those tables; broke when the #149 cross-table
atomicity test came in needing both workspaces (FK target for
activity_logs) and activity_logs themselves.

Switch to globbing *.sql + sorted lex-order, excluding *.down.sql
so up/down pairs don't undo themselves mid-run. Add a sanity check
for workspaces + activity_logs + pending_uploads alongside the
existing delegations gate so a future migration drift fails loud
instead of silently skipping the regressed test.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 22:02:24 -07:00
Hongming Wang 7a39a08837 test(chat-uploads): integration test for cross-table atomicity (#149 follow-up)
Adds two real-Postgres tests under //go:build integration:

- TestIntegration_PollUpload_AtomicRollback_AcrossBothTables exercises
  the helpers in the same Tx shape uploadPollMode does (PutBatchTx +
  LogActivityTx + Rollback) and asserts COUNT(*)=0 on BOTH
  pending_uploads AND activity_logs after the rollback. Failure
  injection: NUL byte in `summary` triggers lib/pq protocol rejection
  on the second activity insert — same trick the existing PutBatch
  AtomicRollback test uses.

- TestIntegration_PollUpload_HappyPath_AcrossBothTables is the positive
  counterpart — Commit lands N rows in both tables.

Coverage rationale (post-PR-3010 review):
- sqlmock unit test (TestPollUpload_AtomicRollbackOnActivityInsertFailure)
  proved the handler calls Begin/Exec/Exec-fail/Rollback in order.
- Existing PutBatch integration test proved Postgres honors rollback
  for pending_uploads alone.
- New tests close the cross-table gap: prove LogActivityTx + PutBatchTx
  + real Postgres MVCC compose correctly under rollback.

A regression that made LogActivityTx silently route through db.DB
instead of the passed tx would still pass the sqlmock test (the
Begin/Commit/Rollback shape would look right) but would fail this
integration test (the activity_logs row would survive the rollback).

Verified locally: postgres:15-alpine + all migrations applied, both
tests pass in 0.1s. Skips cleanly without INTEGRATION_DB_URL — CI
already runs this file via the Handlers Postgres Integration job.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 21:57:56 -07:00
hongming-personal bb9bf85dbd Merge pull request #3011 from Molecule-AI/rfc-2872-workspaces-uniq-toctou
fix(workspace-server): close TOCTOU race on workspaces(parent_id, name) (#2872 Critical 1)
2026-05-06 04:51:01 +00:00
hongming-personal ff21bbb876 Merge staging into rfc-2872-workspaces-uniq-toctou to clear BEHIND 2026-05-05 21:46:33 -07:00
hongming-personal da3cb4c098 fix(workspace-server): close TOCTOU race on workspaces(parent_id, name) (#2872 Critical 1)
## Bug

`/org/import` had no per-tenant mutex, advisory lock, or DB-level
uniqueness on (parent_id, name). The pattern was lookup-then-insert:

    existingID, existing, err := h.lookupExistingChild(...)  // SELECT
    if existing { return /* skip */ }
    db.DB.ExecContext(ctx, `INSERT INTO workspaces ...`)     // INSERT

Two concurrent admin POSTs (rapid double-click in canvas, retry-after-
timeout, two operators on the same template) both saw "not found" in
the SELECT and both INSERT'd the same (parent_id, name).

Captured impact: tenant-hongming accumulated 72 stale child workspaces
in 4 days from repeated org-template spawns of the same template
(see #2857 phase 4 sweeper for the cleanup; #2872 for the prevention RFC).

## Fix

Two-layer fix — DB-level backstop AND application-level happy path:

1. **Migration** `20260506000000_workspaces_unique_parent_name.up.sql`

   ```sql
   CREATE UNIQUE INDEX CONCURRENTLY IF NOT EXISTS workspaces_parent_name_uniq
     ON workspaces (
       COALESCE(parent_id, '00000000-0000-0000-0000-000000000000'::uuid),
       name
     )
     WHERE status != 'removed';
   ```

   * COALESCE(parent_id, sentinel) collapses NULLs so root workspaces
     also collide pairwise.
   * `WHERE status != 'removed'` lets a tombstoned row be replaced
     by a same-named re-import (preserves existing org-import semantics).
   * CONCURRENTLY avoids ACCESS EXCLUSIVE on production tenants under
     live traffic; IF NOT EXISTS makes the migration resumable.
   * Down migration drops CONCURRENTLY symmetrically.

2. **`org_import.go` swap**

   Replace lookup-then-insert with `INSERT ... ON CONFLICT DO NOTHING
   RETURNING id`. On the skip path (RETURNING returns 0 rows →
   sql.ErrNoRows), re-select the existing id to recurse children:

       INSERT INTO workspaces (...) VALUES (...)
       ON CONFLICT (COALESCE(parent_id, ...), name)
       WHERE status != 'removed'
       DO NOTHING
       RETURNING id;

   The ON CONFLICT target predicate matches the partial-index predicate
   exactly — required for Postgres to consider the index applicable.

   Existing `lookupExistingChild` helper kept (still used on the skip
   path); semantics unchanged.

## Test coverage

* AST gate refreshed to assert the workspaces INSERT contains the
  ON CONFLICT pattern (`onConflictDoNothingRE`) instead of the now-obsolete
  "lookup-before-insert" ordering. Per behavior-based gating
  (memory: feedback_behavior_based_ast_gates.md), the new gate pins
  the actual TOCTOU-resolution behavior.
* Companion `TestGate_FailsWhenInsertOmitsOnConflict` proves the gate
  catches the bug shape on synthetic source.
* All existing `lookupExistingChild` unit tests (no-rows, found,
  nil-parent, DB error, wrapped no-rows) still pass — helper is
  unchanged and still load-bearing on the skip path.
* Live Postgres E2E coverage runs via the existing
  "Handlers Postgres Integration" CI job, which applies migrations
  to a real PG and exercises the INSERT path.

## Why ship the migration + swap together (not stacked)

The migration alone provides a DB-level backstop, but without the
handler swap a UNIQUE-violation surfaces as a 500 to the user. The
handler swap alone has no enforceable target until the migration
applies. Shipped together they give graceful skip + atomic backstop.

Migration is CONCURRENTLY + IF NOT EXISTS, safe to apply even on
tenants where the sweeper (#2860) hasn't run yet — the index just
declines to build until conflicting rows are reconciled.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 21:43:49 -07:00
hongming-personal ef9bd1e0e2 Merge pull request #3010 from Molecule-AI/fix/activity-row-tx-atomicity-149
fix(chat-uploads): activity rows commit atomically with PutBatch (#149)
2026-05-06 04:37:55 +00:00
Hongming Wang b759548822 fix(chat-uploads): activity rows commit atomically with PutBatch
Closes #149.

uploadPollMode for poll-mode chat uploads previously committed N
pending_uploads rows in one Tx (PutBatch), then wrote N activity_logs
rows individually outside any Tx. A per-row failure on activity row K
left rows 1..K-1 committed and pending_uploads orphaned until the 24h
TTL — not data-loss because the platform's fetcher handled the
half-state cleanly, but the user never saw file K in the canvas and
the inconsistency surfaced as an "uploaded but invisible" complaint
class.

Thread one Tx through PutBatchTx + N × LogActivityTx + Commit so all
or none commit. Broadcasts are deferred until after Commit — emitting
an ACTIVITY_LOGGED event for a row that ends up rolled back would
paint a ghost message into the canvas's optimistic UI. A new
LogActivityTx returns a commitHook the caller invokes post-Commit;
the existing fire-and-forget LogActivity is unchanged for the 4 other
production callers (a2a_proxy_helpers + activity.go report path).

Storage interface gains PutBatchTx; PostgresStorage.PutBatch is
refactored to share the validation + insert path. inMemStorage and
fakeSweepStorage delegate or no-op for PutBatchTx (the in-mem fake
can't model Tx state — DB-level atomicity is verified by the existing
real-Postgres integration test for PutBatch + the new unit test
asserting the Go handler calls Rollback on activity-insert failure).

Tests:
- TestPollUpload_AtomicRollbackOnActivityInsertFailure pins the new
  contract via sqlmock — second activity insert errors → Rollback
  expected, Commit must NOT be called.
- TestLogActivityTx_DefersBroadcastUntilCommitHook +
  _InsertError_NoHook_NoBroadcast + _NilTx_Errors cover the new API.
- TestPutBatchTx_HappyPath / _EmptyItems / _ValidationFails /
  _PerRowErrorPropagates cover Tx-aware storage layer.
- 7 existing TestPollUpload_* tests updated to mock Begin + Commit
  (or Begin + Rollback for failure paths) since the handler now
  opens a Tx around PutBatch + activity inserts.

All workspace-server tests pass; integration tag also clean.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 21:34:28 -07:00
hongming-personal cce2050b6a Merge pull request #2997 from Molecule-AI/rfc-2991-pr-1-image-preview-lightbox
feat(canvas/chat): inline image preview + fullscreen lightbox (RFC #2991 PR-1)
2026-05-06 04:28:03 +00:00
hongming-personal e87df906bd Merge staging into rfc-2991-pr-1 to clear BEHIND (post PR-2993 + PR-3005) 2026-05-05 21:24:20 -07:00
hongming-personal c60e2b5fa2 chore(canvas/chat): drop unused downloadChatFile import in AttachmentImage
github-code-quality bot flagged this as the last unresolved review thread
blocking the merge queue. The function is referenced in comments but
never called from this file (download is dispatched via the lightbox /
AttachmentChip path). Removing the import resolves the bot thread and
clears the staging branch-protection 'all conversations resolved' gate.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 21:23:46 -07:00
hongming-personal 143fbb91ff Merge pull request #3005 from Molecule-AI/ux/files-tab-drag-drop-upload
ux(canvas/files): drag-drop upload to target folder (#2999 PR-D)
2026-05-06 03:52:10 +00:00
hongming-personal 1b29b24e83 Merge staging into rfc-2991-pr-1 to clear BEHIND state 2026-05-05 20:50:55 -07:00
hongming-personal 6033179f48 Merge pull request #3006 from Molecule-AI/rfc-2991-pr-3-pdf-text-preview
feat(canvas/chat): inline PDF + text/code preview (RFC #2991 PR-3)
2026-05-05 20:49:53 -07:00
Hongming Wang ab1acff2d2 ux(canvas/files): drag-drop upload to target folder (#2999 PR-D)
User asked for VSCode-style drag-drop upload (#2999): "drag local to
upload to target folder just like vscode does". Today the only upload
path is the toolbar's Upload button (folder picker). Drag-drop lets
users grab files from Finder/Explorer and drop them directly on a
specific subdirectory in the tree.

1. New `uploadDataTransferItems(items, targetDir)` in `useFilesApi`
   — walks the HTML5 DataTransferItemList via `webkitGetAsEntry()`,
   recursing folders to a flat (relativePath, file) list, then PUTs
   each via the existing /files/<path> endpoint. The walker (also
   exported via `__testables`) calls `readEntries()` in a loop until
   empty so multi-batch folders (browsers cap each call at ~100
   entries) aren't silently truncated.

2. `uploadFiles` (folder-picker path) gained an optional `targetDir`
   parameter. Same prefixing semantics so future surfaces (e.g. an
   "upload here" toolbar button on a row) can reuse it.

3. `FileTree` directory rows gained `onDragOver` / `onDragEnter` /
   `onDragLeave` / `onDrop` handlers + a hover-target highlight
   (accent-tinted background + outline). dragLeave uses
   `currentTarget.contains(relatedTarget)` to suppress the flicker
   that fires when the cursor crosses any child of the row (icon,
   label, ✕ button) — without this the highlight strobes on every
   sub-element transition.

4. `FilesTab` wraps the tree column in an outer drop zone for
   "drop on root" — drops outside any specific subdir row land at
   root. The empty-state placeholder copy now includes a
   "drag files here to upload" hint when the active root is
   /configs (the only writable root today).

5. Both the row drop and the root drop are gated on
   `root === "/configs"` (the same gate that already blocks the
   toolbar's New / Upload / Clear). Other roots ignore the drag
   entirely (no highlight, no drop), so the user doesn't get a
   misleading drag affordance followed by a "switch root" toast.

`dragDropUpload.test.tsx` (9 tests, two layers):

Walker tests (pure function, no DOM):
- `walkEntry` collects a single dropped file with correct relpath.
- `walkEntry` walks a folder + preserves folder name in the path.
- **Multi-batch loop**: a fake reader that emits two batches of 2
  + an empty terminator must yield 4 files. A walker that called
  readEntries once would see only 2 — this is the load-bearing
  assertion against silent folder truncation.
- Nested directories: outer/inner/file.md → "outer/inner/file.md".

FileTree drag-drop wiring (DOM):
- `dragover` on a directory row preventDefault's (load-bearing —
  without it the drop event never fires).
- `drop` on a directory row fires `onDropToTarget(path, items)`.
- `drop` on a FILE row does NOT fire (only directories are valid
  drop targets).
- `drop` with no DataTransferItems does NOT fire (defensive guard
  against text-only drags).
- `dragenter` adds the highlight class to the directory row.

1. The 1MB per-file size cap is inherited from the existing
   `uploadFiles`. A user dropping a 5MB skill bundle silently
   skips the file (the loop's `continue` on `file.size >
   1_000_000`). Same behavior as the toolbar Upload, so consistent
   if not great. Surfacing skipped-files would be a UX improvement
   tracked separately — not load-bearing for this PR.

2. Drop-zone highlight on the column wrapper uses an outline that
   sits inside the column's overflow-y-auto scroll container. If
   the user drags onto a row that's mid-scroll, the highlight may
   clip slightly at the scroll boundary. Cosmetic only; the drop
   still works.

3. The `?root=` query is NOT passed on the underlying writeFile
   call (matches the existing uploadFiles behavior). On a backend
   without #2999 PR-A, this means uploads always land in /configs
   regardless of selected root — but we already gated drop on
   `root === "/configs"` so the practical effect is nil today.
   Once PR-A merges and the canvas threads ?root= through writes
   (separate follow-up), drops on /home etc. would be enableable
   by lifting the canDelete-style gate.

- `npx tsc --noEmit` clean
- 177/177 canvas tab tests pass
- Manual on local dev: drag a file from Finder onto /configs/skills
  row → file appears under /configs/skills/<name>. Drag a folder of
  3 files onto root area → 3 files uploaded with folder structure
  preserved. Drag onto /home tree → no highlight, no drop.

Refs #2999. Pairs with PR-A (backend EIC) — without PR-A the tree
is empty on SaaS and there's nothing to drop ONTO; PR-D still works
on self-hosted today.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 20:47:47 -07:00
hongming-personal 19df43e3da Merge pull request #2993 from Molecule-AI/rfc-2945-pr-b-1-migrate-bare-event-strings
refactor(events): migrate 18 producers to typed EventType constants (RFC #2945 PR-B-1)
2026-05-06 03:45:47 +00:00
hongming-personal dcece2762b feat(canvas/chat): inline PDF + text/code preview (RFC #2991 PR-3)
Adds two new arms to the AttachmentPreview kind dispatcher:

* PDF — chip in the bubble, click opens the shared AttachmentLightbox
  with a browser-native <embed type="application/pdf"> at 95vw/90vh.
  Fetch+Blob+ObjectURL auth path matches AttachmentImage / Video. PDF.js
  not pulled in; browser viewer is good enough for the desktop chat MVP
  (Slack/Linear/Notion all gate full-page PDF behind a click for the
  same reason). Falls back to AttachmentChip on fetch error.

* Text/code/JSON/YAML — first 10 lines in monospace <pre><code> right
  in the bubble, "Show all N lines" expands to full content, with a
  filename + ⬇ download header. Streams up to 256 KB then marks
  truncated and offers a download chip; large logs don't crash the
  bubble. No syntax highlighting in v1 — shiki adds 200-500 KB and is
  pure polish.

Coverage: 5 new dispatch tests (PDF success → embed in lightbox,
PDF fetch fail → chip fallback, text inline render, text long content
→ Show-all-N-lines expand button, text fetch fail → chip fallback).
All 19 AttachmentPreview tests pass; tsc --noEmit clean.

Stacked on rfc-2991-pr-1-image-preview-lightbox (PR-2 already merged
into PR-1's branch). PR-1 ships first; this rebases onto staging
once it lands.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 20:43:46 -07:00
hongming-personal 57bfa40990 Merge pull request #3004 from Molecule-AI/ux/files-tab-context-menu
ux(canvas/files): right-click context menu — Open / Download / Delete (#2999 PR-C)
2026-05-06 03:37:16 +00:00
Hongming Wang d88fbb90fb ux(canvas/files): right-click context menu — Open / Download / Delete (#2999 PR-C)
## Why

User asked for a VSCode-style right-click menu on file rows (#2999):
"right click to have a menu to download". Today the only download
affordance is the toolbar's Export-all (bulk JSON dump), and the
inline ✕ button is the only delete UX (small click target, easy to
miss).

## Fix

1. New `FileTreeContextMenu` component — fixed-position popover with
   Open / Download / Delete items composed per-row (files get all
   three; directories get Delete only since "open a directory in the
   editor" doesn't apply). Esc + outside-click + Tab + scroll
   dismiss. ↓/↑ arrow keys rove focus between menu items. role=menu
   + role=menuitem + autofocus on first item for a11y.

2. Menu state lifted to the top-level `FileTree` (not per-row) so
   opening a second row's menu auto-closes the first — only one
   menu open at a time, matching VSCode/Theia. Pinned by the
   `replaces the first` test.

3. New `downloadFileByPath(path)` in `useFilesApi` — fetches via the
   existing GET /workspaces/<id>/files/<path>?root= endpoint and
   triggers a browser download. Distinct from the existing
   `handleDownloadFile` which downloads the in-editor buffer
   (round-trips unsaved edits to disk); the context-menu download
   targets arbitrary tree rows the user hasn't opened.

4. `canDelete` prop threaded from FilesTab → FileTree → menu →
   item. Same gate as the toolbar (Clear/New/Upload all gated to
   /configs); context menu's Delete renders as disabled with a
   muted background on other roots, matching the "feature exists
   but isn't applicable here" pattern.

## Test coverage

`FileTreeContextMenu.test.tsx` (8 tests):

- File row → menu opens with Open + Download + Delete.
- Directory row → menu opens with Delete only.
- Click Download → onDownload(path) fires + menu closes.
- Click Delete (canDelete=true) → onDelete(path) fires.
- Click Delete (canDelete=false) → onDelete NOT called + menu stays
  open (disabled-state UX).
- Esc dismisses.
- Outside-click (mousedown on document.body) dismisses.
- Opening second context menu replaces the first (only-one-open
  invariant).

Each test uses fireEvent + screen.getByRole, so they fail on a
deleted-code regression — none would pass on the pre-PR shape.

## Three weakest spots (hostile self-review)

1. The menu is positioned at `clientX/clientY` without viewport
   clamping. If the user right-clicks at the very bottom-right of
   the panel, part of the menu may overflow off-screen. VSCode
   handles this by flipping the anchor; we don't yet. Acceptable
   v1 because the FilesTab is fixed-width (≤ side-panel width)
   and the menu is small (140×~80px); the overflow would be a few
   pixels of one item. Filed as a follow-up.

2. Auto-focus on the first item shifts keyboard focus away from
   the row that opened the menu. Closing with Esc returns focus
   to the body, not the row. Same behavior as TerminalTab's
   placeholder + the canvas's other context menus; consistent
   isn't ideal but at least uniform. Documented inline.

3. The download request reuses the API client's 15s default
   timeout — large config files (multi-MB skill bundles) on a
   slow connection could time out. Same risk applies to the
   existing toolbar Export. If we see real download failures we
   can add a `timeoutMs` override at the call site without
   touching the menu.

## Verification

- `npx tsc --noEmit` clean
- 176/176 canvas tab tests pass
- Manual on local dev: right-click a config.yaml row → menu opens
  → click Download → file lands in Downloads. Right-click on
  /home root → Delete renders disabled.

Refs #2999. Pairs with PR-A (backend EIC) — without PR-A the tree
is empty and there's nothing to right-click on a SaaS workspace.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 20:26:04 -07:00
hongming-personal 2e6bed71b9 Merge pull request #3003 from Molecule-AI/ux/files-tab-external-not-available
ux(canvas/files): "Files not available" banner for external runtimes (#2999 PR-B)
2026-05-06 03:24:45 +00:00
hongming-personal 030377bb84 Merge pull request #3002 from Molecule-AI/fix/files-eic-list-delete-symmetry
fix(workspace files API): EIC parity for ListFiles + DeleteFile (#2999 PR-A)
2026-05-06 03:22:45 +00:00
Hongming Wang f93957e982 ux(canvas/files): "Files not available" banner for external runtimes (#2999 PR-B)
## Why

Reported by user (issue #2999): external workspaces (mac laptop, mac
mini, hermes-on-home-server — runtime="external") render the FilesTab
identically to the SaaS empty-listing bug, showing "0 files / No
config files yet" even though the platform doesn't actually own the
filesystem of these workspaces. Visually indistinguishable from the
broken state, reads as a bug.

## Fix

Mirror the affordance TerminalTab adopted in PR #2830 for runtimes
without a TTY:

1. New `NotAvailablePanel` in `canvas/src/components/tabs/FilesTab/`
   — folder-with-slash icon + "Files not available" headline + body
   text that names the runtime and points the user at Chat.

2. `FilesTab` now takes optional `data?: WorkspaceNodeData`. When
   `data.runtime` is in `RUNTIMES_WITHOUT_FILES` (currently just
   "external"), early-return the placeholder before mounting the
   useFilesApi hook. Mirrors TerminalTab's prop shape exactly so the
   review pattern is uniform across tabs.

3. SidePanel passes `node.data` to FilesTab (matches existing pattern
   for ChatTab / TerminalTab).

## Test coverage

`FilesTab.notAvailable.test.tsx` (4 tests):

- external runtime → banner renders with runtime name + Chat-tab
  guidance copy.
- external runtime → NO `/files` API request fires (asserted by
  inspecting the mocked api.get call log).
- claude-code runtime → no banner, normal mount proceeds (toolbar's
  root selector is the discriminator).
- data prop omitted → falls through to normal mount (back-compat
  with any caller that doesn't thread data through, e.g. legacy
  tests).

Each branch is independent and discriminating — none would pass on
a code-deleted version of the early-return.

## Three weakest spots (hostile self-review)

1. `RUNTIMES_WITHOUT_FILES` is a hardcoded set in this file. If a
   future runtime joins (e.g. a "byok-claude" that runs on user
   hardware), someone has to remember to add it here. Reviewed
   alternatives: pull from a runtime-capabilities registry — same
   shape as `RUNTIMES_WITHOUT_TERMINAL` already in TerminalTab. We
   chose the parallel pattern over a new abstraction; consolidating
   into a shared registry can land if/when a third tab grows the
   same gate (rule of three). Documented inline.

2. The placeholder is a static panel — no retry, no "report bug"
   link. Same as TerminalTab's. Acceptable because the absence is
   intentional, not transient.

3. Chat-tab guidance is hardcoded English. No i18n in canvas yet;
   matches the rest of the codebase. Will move with the i18n
   migration when that lands.

## Verification

- `npx tsc --noEmit` clean
- 54/54 canvas tab + SidePanel tests pass
- Will be live-verified on staging post-merge: open Files tab on an
  external workspace (mac laptop) → expect placeholder; open on a
  platform-owned workspace (Hongming Personal Brand Agent) → expect
  normal tree (assuming PR-A also lands).

Refs #2999. Pairs with PR-A (backend EIC fix) — without PR-A the
platform-owned path still shows "0 files" because the backend never
returns rows.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 20:21:45 -07:00
hongming-personal b530c147de Merge pull request #3000 from Molecule-AI/rfc-2991-pr-2-video-audio-preview
feat(canvas/chat): inline video + audio HTML5 players (RFC #2991 PR-2)
2026-05-05 20:18:36 -07:00
Hongming Wang f39b595a9c fix(workspace files API): EIC parity for ListFiles + DeleteFile (closes #2999 PR-A)
## User-visible bug

Canvas Files tab returns "0 files / No config files yet" for every
SaaS workspace, every root (/configs, /home, /workspace, /plugins).
Reported by user (canvas screenshot, hongming.moleculesai.app,
Hongming Personal Brand Agent — claude-code, T4, online).

## Root cause

`ListFiles` (templates.go) was missing the SSH-via-EIC branch that
ReadFile (PR #2785) and WriteFile (PR #1702) already have. On SaaS,
dockerCli is nil → findContainer returns "" → falls through to
host-side resolveTemplateDir which only matches baked-in template
names. For a user-named workspace it matches nothing, so the handler
silently returns []fileEntry{}.

DeleteFile had the same gap — right-click delete (introduced in PR-C
of this issue) would silently no-op once #1 was fixed.

## Fix

1. Extracted shared EIC plumbing into `withEICTunnel` (closure-based,
   single SSOT for keypair → key push → tunnel → port-wait → cleanup).
   Refactored writeFileViaEIC + readFileViaEIC to use it. Added
   listFilesViaEIC + deleteFileViaEIC on the same scaffold. The
   `LogLevel=ERROR` shim from PR #2822 now lives in one
   `eicSSHSession.sshArgs()` helper instead of being duplicated per
   helper — the next time we need to tweak ssh options, one place.

2. Factored remote shell strings into pure functions
   (buildInstallShell / buildCatShell / buildRmShell / buildFindShell
   + parseFindOutput) so the wire shape can be pinned without booting
   a real EIC tunnel.

3. Refactored `resolveWorkspaceFilePath(runtime, root, relPath)` to
   honor `?root=`. New rule: `/configs` (or empty / unrecognized) →
   runtime managed-config dir via workspaceFilePathPrefix (preserves
   the v1 ReadFile/WriteFile behaviour where canvas's Config tab
   GETs/PUTs config.yaml without specifying a root and lands in the
   right per-runtime dir); `/home`, `/workspace`, `/plugins` →
   literal absolute path on the EC2 host. List/Read/Write/Delete now
   agree on what file a tree row points to — pre-fix List would say
   "/home contents" but Read/Write would route to /configs.

4. ListFiles + DeleteFile dispatch on instance_id != "" → EIC helper.
   Errors from the EIC path produce 500 (not silent fall-through to
   local-Docker, which would mask the failure as "0 files" — the
   exact user-visible symptom).

5. Added ?root= validation gate to WriteFile + DeleteFile so an
   out-of-allowlist root is rejected before the resolver runs.

## Test coverage

- TestResolveWorkspaceFilePath_RuntimeIndirection — pins the
  /configs → runtime prefix translation per-runtime (hermes,
  claude-code, langgraph, external, unknown). Catches the regression
  where a future edit accidentally drops the runtime indirection.

- TestResolveWorkspaceFilePath_LiteralRoots — pins /home,
  /workspace, /plugins as literal pass-through regardless of
  runtime. Catches the symmetric regression where the literal roots
  start getting rewritten to the runtime prefix (which would mean
  the FilesTab "/home" selector silently routes to /configs on
  hermes).

- TestResolveWorkspaceRootPath — directory-only translation used
  by listFilesViaEIC, same indirection rules.

- TestSSHArgs_HardenedFlags — pins the centralised ssh option set
  (LogLevel=ERROR + hardening). Catches drift in the
  one-place-where-ssh-flags-live.

- TestEicSSHSessionSingleSourceForSSHFlags — behaviour-based AST
  gate (per memory). Counts s.sshArgs() callers (must be ≥4 —
  list/read/write/delete) and asserts LogLevel=ERROR appears
  exactly once in the source. Fires if anyone copy-pastes a raw
  ssh args slice instead of going through the helper.

- TestBuildInstallShell / TestBuildCatShell / TestBuildRmShell /
  TestBuildFindShell — pure-function tests pinning the remote
  command shape. Catches regression like "rm -f silently becomes
  rm -rf" or "find loses node_modules pruning" without needing a
  real EC2.

- TestBuildFindShell_DepthForwarding — catches a regression where
  the helper hard-codes a depth instead of using the caller's value.

- TestParseFindOutput / TestParseFindOutput_EmptyInput — pin the
  TYPE|SIZE|REL parser. Empty-input case explicitly returns []
  not nil so the JSON wire shape stays a list.

- TestListFiles_EICDispatch_Success / Error — sqlmock-driven
  handler test. Verifies instance_id != "" routes to listFilesViaEIC
  and surfaces errors as 500 (does NOT silently fall through to
  local-Docker, which is the exact regression-mode of the original
  bug).

- TestListFiles_EICBranch_NotTakenForSelfHosted — back-compat
  guard: instance_id == "" must NOT enter the EIC branch (would
  break self-hosted operators).

- TestDeleteFile_EICDispatch_Success / Error — same shape for
  DeleteFile.

- TestListFiles_RootValidation / TestDeleteFile_RootValidation —
  ?root=/etc must 400 before any DB query or EIC call.

## Verification

- `go build ./...` clean
- `go test ./...` clean (full workspace-server suite)
- Will be live-verified against staging on hongming.moleculesai.app
  after merge: open Files tab → expect populated /home + /configs +
  /workspace listings (not "0 files"); right-click delete on
  /configs/old.yaml → expect file removed on the EC2 host.

## Three weakest spots (hostile self-review)

1. The LogLevel=ERROR drift gate counts source occurrences. A
   future refactor that intentionally moves the literal somewhere
   else (e.g. into a constant) would trigger a false positive. The
   gate's failure message points to the load-bearing constraint
   (must appear in sshArgs); operator can adjust.

2. `eicFileWriteTimeout` constant kept as an alias for back-compat
   with prior tests. Documented as intentional + safe to remove on
   the next pass.

3. The resolver tests pin the runtime → prefix map values
   (`/home/ubuntu/.hermes`, `/configs`, etc.). A future runtime
   addition that ships a new prefix needs the test updated. This
   is intentional — silent prefix changes orphan saved files, so a
   test failure on map edit IS the right signal.

## Follow-up (RFC #2312 subtask 2)

Long-term the right fix is to drop EIC entirely and HTTP-forward to
the workspace's own URL (RFC #2312). That's a substantially larger
refactor across 5 surfaces (chat upload, files, templates, plugins,
terminal) and out of scope for this bug-fix PR. Tracked separately
under that RFC.

Refs #2999.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 20:18:05 -07:00
hongming-personal 95fdf86187 feat(canvas/chat): inline video + audio HTML5 native players (RFC #2991 PR-2)
Second specialized renderer pair landing under RFC #2991. Stacks on
PR-1 (#2997) — extends the AttachmentPreview dispatcher with video/
audio cases.

Why HTML5-native (not custom JS player)
---------------------------------------

- Browser vendors ship hardware-accelerated decoders, captions,
  pinch + scrub UX, and fullscreen UI. We get all of it for free.
- Native fullscreen via the <video> control bar — no
  AttachmentLightbox needed for video (the browser's built-in
  fullscreen handles it).
- Mobile-friendly without us writing the touch handlers.

Auth model
----------

Identical to AttachmentImage (PR-1): platform-auth URIs need our
cookie/token, so we fetch the bytes, wrap in a Blob, hand the
browser an ObjectURL via <video src=> / <audio src=>. External
http(s) URIs skip the fetch.

Memory caveat: a Blob holds the entire media in JS memory until the
bubble unmounts. The server's 25MB single-file cap (chat_files.go)
bounds this; v2 can switch to MediaSource + streaming if larger
files become a real shape.

Failure modes
-------------

- Fetch failure (404, 403, network) → AttachmentChip fallback.
- Bytes that aren't valid media (corrupt, wrong Content-Type) →
  <video onError> / <audio onError> swap to chip.

Tests
-----

5 new component tests in AttachmentPreview.test.tsx (now 14 total):
  - kind=video → <video controls> with blob URL src
  - kind=video fetch fails → falls back to chip
  - kind=video extension fallback (no mime) → routes to video path
  - kind=audio → <audio controls> + filename label visible
  - kind=audio fetch fails → falls back to chip

The preview-kind unit tests from PR-1 (49 cases) already cover the
MIME → video / audio dispatch logic; this PR's component tests pin
the rendered DOM shape (controls attribute, blob URL src, fallback
behavior).

Hostile self-review
-------------------

1. Memory bound: 25MB cap protects us today; documented future
   migration path (MediaSource).
2. iOS Safari autoplay: playsInline pinned on <video> so mobile
   doesn't auto-fullscreen on play.
3. Captions accessibility: <track kind="captions" /> placeholder so
   the element is tagged correctly even though we don't have caption
   files yet (forward-compatible).

Verified
- tsc --noEmit clean
- 173 chat tests green (49 unit + 14 component + 110 pre-existing)

Stacks on PR-1 (#2997). PR-3 (PDF + text/code) is the final piece.

Refs RFC #2991, PR #2997 (PR-1).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 20:10:19 -07:00
hongming-personal 04f7a07add feat(canvas/chat): inline image preview + fullscreen lightbox (RFC #2991 PR-1)
First specialized renderer landing under RFC #2991 — chat attachment
preview. Adds the dispatch infrastructure that PR-2 (video/audio) and
PR-3 (PDF/text) will extend.

Architecture (RFC #2991 Phase 2 design)
---------------------------------------

- preview-kind.ts: pure helper that maps mimeType (+ extension fallback
  for missing/generic MIME) to one of: image | video | audio | pdf |
  text | file. Single source of truth; the dispatch axis for every
  attachment renderer.

- AttachmentPreview.tsx: SSOT dispatch component. ChatTab no longer
  imports kind-specific components — it imports AttachmentPreview,
  which switches on the kind and renders the right child.

- AttachmentImage.tsx: inline thumbnail (max 240×180) + click →
  lightbox. Auth-aware: for platform URIs (workspace: /
  platform-pending: / etc) the bytes are fetched via JS-injected
  headers, wrapped in a Blob, served as ObjectURL — bare <img src>
  would not include the cookie/token.

- AttachmentLightbox.tsx: shared fullscreen modal (image now; PDF will
  use it in PR-3). Esc / backdrop click / X button to close, focus
  trap on close button, focus restoration on close.

- AttachmentChip retained as the kind=file fallback. No breaking
  change for existing renderable shapes.

External-workspace coverage
---------------------------

The wire shape (ChatAttachment.mimeType + uri) is identical for
internal + external workspaces — both go through AgentMessageWriter
(PR #2949). External claude-code agents that attach images via
send_message_to_user automatically get the new preview surface; no
runtime-side change needed.

Failure modes
-------------

- Fetch failure (404, 403, network) → AttachmentChip fallback so the
  user still gets a working download. Pinned by tests.
- Decoded as non-image (corrupt bytes, wrong Content-Type) → onError
  on the <img> swaps to AttachmentChip. Pinned by tests.
- Non-platform URIs (http/https external image hosts) → skip the
  auth-fetch flow, use the raw URL via resolveAttachmentHref. Pinned
  by extension-fallback tests.

Tests
-----

preview-kind.test.ts (49 cases):
  - Strict MIME match across image/video/audio/pdf/text/unknown
  - Extension fallback when MIME is missing or application/octet-stream
  - URL with query string + fragment → strip before parsing
  - MIME wins over extension (regression: don't render image-named zip)
  - SVG is image (not text) despite being XML
  - Non-canonical MIME like application/javascript → text

AttachmentPreview.test.tsx (9 component tests):
  - Dispatch: kind=file → chip, kind=image → image path
  - Loading state shows placeholder, NOT chip (proves dispatch routed)
  - Extension fallback (no mimeType) routes to image path
  - Fetch fail (404) and network error → fall back to chip
  - Image success: <img> renders ObjectURL, click opens lightbox
  - Lightbox: Esc closes, backdrop click closes, content click doesn't
  - Universal fallback: unknown MIME → chip even when extension hints
    at a renderable kind

Hostile self-review (3 weakest spots, addressed)
------------------------------------------------

1. <img> auth: bare <img src="/chat/download?..."> would NOT include
   our auth headers. Resolved via fetch+Blob+ObjectURL pattern.
   Pinned by the image-success test (asserts src === "blob:test-url").

2. Server-side allowed-roots mismatch: pre-fix tests used /tmp/ paths
   which the server doesn't allow. Caught when the dispatch test
   fell into the non-platform path. Updated tests to use /workspace/
   subpaths matching templates.go's allowedRoots.

3. Bundle size creep: each kind component adds bytes. Lightbox is
   currently always-bundled. Lazy-loading is plausible but defer
   until measured-needed.

Verified
- tsc --noEmit clean
- 168 chat tests green (49 unit + 9 component + 110 pre-existing)

PR-2 (video + audio) and PR-3 (PDF + text) extend the dispatch in
AttachmentPreview.tsx with their own kind-specific components.

Refs RFC #2991.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 19:39:37 -07:00
hongming 3dfeb180ab Merge pull request #2995 from Molecule-AI/fix/sweep-add-orphan-tunnel-cleanup-2987
chore(sweep): add orphan-tunnel cleanup step (#2987 / #340)
2026-05-06 02:38:39 +00:00
Hongming Wang 88ff0d770b chore(sweep): add orphan-tunnel cleanup step (#2987 / #340)
The 15-min sweeper has been deleting stale e2e orgs but not the
orphan tunnels left behind when the org-delete cascade half-fails
(CP transient 5xx after the org row is gone but before the CF
tunnel delete completes). Result: tunnels accumulate in CF until
manual operator cleanup.

Add a final step that POSTs `/cp/admin/orphan-tunnels/cleanup`
every tick. Best-effort — failure doesn't fail the workflow; next
tick re-attempts. Output reports deleted_count + failed count for
ops visibility.

This is the catch-all for the orphan-tunnel class. The proper
upstream fix (transactional org delete) lives in CP and tracks as
issue #2989. Until that lands, the sweeper bounded-time-to-cleanup
keeps the leak from escalating.

Note: PR #492 (cf-tunnel silent-success fix) makes this step
actually effective — pre-fix DeleteTunnel silent-succeeded on
1022, so the cleanup endpoint reported success without deleting.
Post-fix the cleanup chains CleanupTunnelConnections + retry on
1022, which actually clears stuck-connector orphans.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 19:36:20 -07:00
hongming-personal 86b8d8d744 Merge pull request #2982 from Molecule-AI/fix-config-skip-yaml-for-external-runtime
fix(canvas/config): skip config.yaml fetch for external/hermes runtimes
2026-05-06 02:22:14 +00:00
hongming-personal 9b9419ad5e Merge pull request #2992 from Molecule-AI/chore/ssot-pointer-sweep-workflow
chore(sweep): note SSOT for ephemeral prefixes lives in CP
2026-05-06 02:20:35 +00:00
Hongming Wang a19ee90556 chore(sweep): note SSOT for ephemeral prefixes lives in CP
Mirrors molecule-controlplane#494: the canonical EPHEMERAL_PREFIXES
list now lives in molecule-controlplane/internal/slugs/ephemeral.go,
where redeploy-fleet reads it to skip in-flight test tenants. The
sweep workflow keeps a Python copy because GHA Python can't import
Go, but a comment now points engineers updating the list to update
both files.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 19:18:13 -07:00
hongming bd0580f4af Merge pull request #2990 from Molecule-AI/fix/memory-v2-namespace-labels-2988
fix(memory-v2): namespace labels use display names not UUID prefixes (#2988)
2026-05-06 02:13:30 +00:00
Hongming Wang 64e58fb390 test(memory-v2-e2e): update expectChainQueryRoot for new name column
PR #2990 root cause: the resolver SQL added `name` to the SELECT for
DisplayName plumbing, but the e2e test's sqlmock fixture
(expectChainQueryRoot at swap_test.go:216) still scripts the
3-column shape. Three e2e tests fail with:

    sql: expected 3 destination arguments in Scan, not 4

Fix: bump the fixture to 4 columns (id, name, parent_id, depth) and
pass an empty name. The e2e tests don't assert on label rendering —
they pin the namespace string flow ("workspace:root-1" etc), which
is unchanged. Empty name is fine: ReadableNamespaces still emits the
correct namespace strings; only DisplayName is empty.

Caught by CI's Platform (Go) check on PR #2990 — would have been a
silent missed-coverage case in the resolver_test.go run because that
package doesn't import the e2e package.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 19:10:18 -07:00
hongming-personal 9ceda9d81f refactor(events): migrate 18 files to typed EventType constants (RFC #2945 PR-B-1)
Mechanical migration of bare event-name strings in BroadcastOnly /
RecordAndBroadcast call sites to the typed constants from
internal/events/types.go (RFC #2945 PR-B). Wire format unchanged
(both shapes serialize to identical WSMessage.Event literals); pinned
by TestAllEventTypes_IsSnapshot in #2965.

Migrated (18 files, scope: handlers/, scheduler/, registry/, bundle/,
channels/):
- handlers/{approvals,a2a_proxy_helpers,a2a_queue,activity,agent,
  delegation,external_rotate,org_import,registry,workspace,
  workspace_bootstrap,workspace_crud,workspace_provision_shared,
  workspace_restart}.go
- channels/manager.go (caught by hostile-reviewer pass — initial
  scope missed channels/, found via grep on the post-migration tree)
- scheduler/scheduler.go
- registry/provisiontimeout.go
- bundle/importer.go

Hostile self-review (3 weakest spots, addressed)
------------------------------------------------

1. Missed call sites — initial scope omitted channels/. Post-migration
   `grep -rEn 'BroadcastOnly\([^,]+,[^,]*"[A-Z_]+"|RecordAndBroadcast\([^,]+,[^,]*"[A-Z_]+"' internal/`
   found 2 stragglers in channels/manager.go. Migrated. Final grep
   on the same pattern returns only the docstring example in
   types.go (intentional).

2. gofmt drift — auto-import injection produced non-canonical import
   ordering. `gofmt -w` applied ONLY to the 18 modified files (NOT
   the whole tree, to avoid sweeping unrelated pre-existing drift
   into this PR's diff). Three pre-existing un-gofmt'd files in
   handlers/ (a2a_proxy.go, a2a_proxy_test.go, a2a_queue_test.go)
   left as-is — they're unchanged by this PR and their drift
   predates it.

3. Wire format — paranoia check: do the constants serialize to the
   exact strings consumers (canvas TS, hermes plugin, anything
   parsing WSMessage.Event) expect? Yes. Pinned by the snapshot
   test. The migration is name-only; not a single character of
   wire output changes.

Verified
- go build ./... clean
- go vet ./internal/... clean
- gofmt -l on the 5 migrated package dirs: only pre-existing files
- Full tests: handlers/, channels/, scheduler/, registry/, events/,
  bundle/ all green (5 ok, 0 fail)

PR-B-2 (canvas TS mirror + cross-language parity gate) remains as
the final piece of RFC #2945 PR-B. Tracked separately so this PR
stays mechanical + reviewable.

Refs RFC #2945, PR #2965 (PR-B types).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 19:05:03 -07:00
Hongming Wang b6310d7ebf fix(memory-v2): namespace dropdown labels use display names not UUID prefixes (#2988)
User feedback on the v2 Memory tab redesign: on a root workspace, the
namespace dropdown showed three indistinguishable entries:
  Workspace (30ba7f0b)
  Team (30ba7f0b) (team)
  Org (30ba7f0b-b303-4a20-aefe-3a4a675b8aa4) (org)

For a root workspace, the resolver collapses workspace==team==org IDs
(resolver.go:113-122 derive() degenerate case). The previous
shortID(8)-truncated UUID label scheme made all three look identical
even though the three concepts (private / team-shared / org-wide)
remain semantically distinct.

## Backend — Resolver returns DisplayName

  - SQL chain query now SELECTs workspaces.name (COALESCE → "" on NULL)
  - chainNode carries .name through walk
  - deriveNames() computes the display name for each namespace,
    mirroring derive():
      workspace: self.name
      team:      parent.name (or self.name if root — degenerate)
      org:       chain[end].name (root of tree)
  - Namespace struct gets a new DisplayName field, omitempty wire-shape

## Backend — Handler renders label from DisplayName when present

  - memories_v2.go:namespaceLabelWithName(name, kind, displayName) is
    the new SSOT label generator. Falls back to the UUID-prefix shape
    when displayName is empty so callers without name plumbing keep
    working unchanged.
  - namespacesToViews now plumbs Namespace.DisplayName into the label.
  - Old namespaceLabel(name, kind) is preserved as a thin wrapper
    around namespaceLabelWithName(_, _, "") for back-compat.
  - Custom namespaces ignore displayName by design — operator-defined
    suffixes ARE the chosen label; a name override would surprise.

## Frontend — drop redundant `(kind)` suffix

  Pre-fix: "Team (mac laptop) (team)" — kind shown twice.
  Post-fix: "Team (mac laptop)" — the prefix already conveys the kind.

## Test coverage

Resolver (3 new tests):
  - DisplayName_Root: workspace name propagates to all 3 namespaces
  - DisplayName_Child: workspace=self.name, team=parent.name, org=root.name
  - DisplayName_EmptyOnNULL: COALESCE → "" → empty fallback

Handler (3 new tests):
  - NamespaceLabelWithName_PrefersDisplayName: workspace/team/org/custom paths
  - NamespaceLabelWithName_FallsBackToUUIDPrefix: empty displayName → legacy shape
  - NamespacesToViews_PassesDisplayNameThrough: full integration on root case

Canvas: existing 30 tests still pass; suffix drop is rendering-only.

memories_v2.go function coverage: **14/14 = 100%**
- namespaceLabelWithName: 100%
- namespacesToViews: 100%
- (all 11 pre-existing functions stay at 100%)

## SSOT

The "what is this namespace called" question now has one source of
truth: namespace.Resolver.ReadableNamespaces sets DisplayName from the
canonical workspace.name column. The handler is a renderer; the
canvas is a consumer. No name-lookup logic duplicated across the
three layers.

🤖 Generated with [Claude Code](https://claude.com/claude-code)
2026-05-05 18:46:50 -07:00
molecule-ai[bot] d75b73e713 Merge pull request #2981 from Molecule-AI/staging
staging → main: auto-promote 9dd2988
2026-05-05 18:13:50 -07:00
hongming-personal 0886dbc923 Merge pull request #2978 from Molecule-AI/fix-plugins-compact-empty-state
feat(canvas/skills): compact-empty layout for Plugins section (#2971)
2026-05-06 01:12:09 +00:00
hongming-personal 7420631c32 Merge pull request #2983 from Molecule-AI/feat/auto-promote-stale-alarm-2975
feat(ops): hourly alarm for auto-promote PR stuck on REVIEW_REQUIRED (#2975)
2026-05-06 00:58:49 +00:00
Hongming Wang caf19e8980 feat(ops): hourly alarm for auto-promote PR stuck on REVIEW_REQUIRED (#2975)
Closes the silent-block failure mode that left 25 commits — including
the Memory v2 redesign and the reno-stars data-loss fix — wedged on
staging for 12+ hours behind a single missing review. The auto-promote
workflow opened the PR + armed auto-merge, but main's branch protection
required a human review and nobody noticed until a user reported
"still seeing old memory tab".

## Detection logic — `scripts/check-stale-promote-pr.sh`

Reads open PRs `base=main head=staging` and alarms on:
  - `mergeStateStatus == BLOCKED`
  - `reviewDecision == REVIEW_REQUIRED`
  - createdAt older than `STALE_HOURS` (default 4h)

Other BLOCKED reasons (DIRTY, BEHIND, failed checks) are NOT alarmed —
those are the author's signal-to-fix. This script targets the specific
"no human reviewed yet" wedge.

Output:
  - `::warning` per stale PR (visible in workflow summary + Actions UI)
  - PR comment (idempotent via marker-string detection; one alarm
    per PR, never re-spammed)
  - Exit code = count of stale PRs (capped at 125)

Logic in a script (not inline workflow YAML) so it's:
  - **Unit-testable** — tests/test-check-stale-promote-pr.sh exercises
    every branch with stubbed fixture JSON + frozen clock. 23 tests
    covering: empty list, single stale, just-under-threshold, wrong
    reviewDecision, wrong mergeStateStatus, mixed list (only matching
    PRs alarm), custom threshold via --stale-hours, exit-code-counts-
    matching-PRs, --help, unknown arg → 64, missing repo → 2.
  - **Operator-runnable ad-hoc** — `scripts/check-stale-promote-pr.sh`
    works from any shell with `gh` + `jq`.
  - **SSOT** — one detector, the workflow YAML is just schedule +
    invocation surface. Future sibling workflows that need the same
    check call the same script.

## Workflow — `.github/workflows/auto-promote-stale-alarm.yml`

Triggers:
  - cron `27 * * * *` (hourly, off-the-hour to dodge cron herd)
  - workflow_dispatch with `stale_hours` + `post_comment` overrides

Concurrency: `auto-promote-stale-alarm` group, cancel-in-progress=false
(idempotent script; no benefit to cancelling a running scan).

Permissions: `contents: read` + `pull-requests: write` (post comments).

Sparse checkout — only fetches `scripts/check-stale-promote-pr.sh`.
No node_modules, no go modules, no slow setup steps. Workflow runs
in <30s on a clean repo.

## Why "alarm + comment" not "auto-approve"

Considered options in issue #2975:
  1. Slack/email alert — picked.
  2. Bot-account auto-approve via molecule-ops — circumvents the
     human-review gate that branch protection encodes.
  3. Trusted-promote bypass via CODEOWNERS — needs Org Admin config
     change; out of scope for a workflow PR.

The comment-on-PR pattern picks (1) without external dependencies
(no Slack token, no email config). Subscribers get notified via
GitHub's existing PR notification delivery; the warning shows up in
the Actions feed.

## Why this won't false-positive on legitimate slow reviews

Threshold is 4h. Most legitimate gates clear in <1h, so 4× headroom
is plenty for slow CI. The comment is idempotent (one alarm per PR,
never re-posted) — adding noise stops at 1 comment regardless of
how long the PR sits.

## Test plan

- [x] `bash scripts/test-check-stale-promote-pr.sh` — 23/23 pass
- [x] `python3 -c 'yaml.safe_load(...)'` clean
- [x] `bash -n` clean on both scripts
- [ ] Live verification: dispatch the workflow once main has caught up,
      confirm it correctly reports zero stale PRs
2026-05-05 17:55:27 -07:00
hongming-personal 38bc27df0d fix(canvas/config): skip config.yaml fetch for external / hermes runtimes — eliminate 404 console noise
Reported on production reno-stars 2026-05-05 (browser console):

  /workspaces/d76977b1-…/files/config.yaml:1
    Failed to load resource: the server responded with a status of 404

The workspace was an external-runtime mac-mini-style agent that
doesn't use the platform's config.yaml template — every Config tab
open issued a GET that 404d cleanly, and the existing catch block
fell into the runtime-manages-own-config branch + populated the
form from workspace metadata. Functionally correct, but the request
fired anyway, surfaced as a 404 in DevTools, and burned an RTT.

Fix: branch on RUNTIMES_WITH_OWN_CONFIG BEFORE the fetch — when the
workspace's runtime is one of those (external, hermes), skip the
GET, populate the form from workspace metadata directly, set
loading=false, return. Same code path as the existing 404-catch
fallback, just skipping the wasted request.

Behavior preserved for runtimes that DO use the template
(claude-code, etc.): unchanged GET → parse → setConfig flow.

Tests: 24/24 existing ConfigTab tests pass; no behavioral change for
the documented runtimes. tsc clean.

Refs reno-stars production 2026-05-05.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 17:55:24 -07:00
hongming-personal 6748035720 Merge pull request #2980 from Molecule-AI/test/canvas-resolve-attachment-href-2973
test(canvas/chat): cover platform-pending: branch + isPlatformAttachment (#2973)
2026-05-06 00:54:17 +00:00
hongming-personal c74d0ecc94 test(canvas/chat): cover platform-pending: branch + isPlatformAttachment (#2973)
Closes #2973 — the followup test gap I flagged on PR #2968's review.

Pre-merge #2968 added the platform-pending: URI scheme branch to
resolveAttachmentHref + introduced the isPlatformAttachment SSOT
helper, but the existing uploads.test.ts only covered the older
workspace: / file:/// / absolute-path branches. The new branch shipped
on prod-impact (live console error on reno-stars) with manual post-
deploy verification; the regression gate was filed as a followup
(#2973) so a future canvas refactor can't silently re-break the
poll-mode chat-attachment download path.

Adds 15 new test cases across two existing describe blocks:

resolveAttachmentHref — platform-pending: scheme (poll-mode uploads):
- well-formed platform-pending:<wsid>/<fileid> resolves to the
  /pending-uploads/<file>/content endpoint
- uses the URI's wsid, NOT the chat workspace_id (cross-workspace
  forwarding case — pinning the explicit decision from #2968's
  commit message so a regression that flipped this would mis-route
  the download to the wrong workspace's pending-uploads store)
- defensive fallback to raw URI on missing slash, empty fileID,
  empty wsid (so a future "helpful" change can't synthesize a
  broken /pending-uploads// path)
- regression test against the EXACT production repro from #2968's
  body (reno-stars, 2026-05-05 console error)

isPlatformAttachment:
- positive cases for platform-pending: (well-formed and malformed),
  workspace:<allowed-root>, file:///<allowed-root>, absolute paths
  under allowed roots
- NEGATIVE cases for HTTPS/HTTP URLs to other origins (auth-leak
  class regression — a helper that always returned true would
  attach workspace tokens to third-party requests), non-allowlisted
  roots like /etc/passwd or /var/log/x, empty string, and
  unrecognised schemes (s3://, ftp://)

All 21 tests pass. The 6 pre-existing tests are unchanged. The 15
new tests are the regression gate that #2973 asked for.

Verification:
- pnpm exec vitest run src/components/tabs/chat/__tests__/uploads.test.ts
  → 21 passed
2026-05-05 17:51:28 -07:00
hongming-personal 9dd29882e2 Merge pull request #2979 from Molecule-AI/fix/a2a-poll-mode-response-shape-2967
feat(a2a): SSOT typed-variant response parser + auto-fallback for poll-mode peers (#2967)
2026-05-06 00:41:43 +00:00
Hongming Wang e342d0c5a7 fix(build): register a2a_response in TOP_LEVEL_MODULES
The drift gate caught the new SSOT parser module — without registration
the wheel ships it un-rewritten and runtime imports fail. Same pattern
as inbox_uploads, a2a_tools_delegation, a2a_tools_rbac registrations.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 17:34:05 -07:00
Hongming Wang 166ad20cd7 test(e2e): Phase 3.5 — wheel parser classifies real server response (#2967)
Previously Phase 3 only checked the workspace-server's poll-mode short-circuit
emit shape ({"status":"queued","delivery_mode":"poll","method":"..."}); the
matching client-side classification was tested in isolation against fixture
dicts in test_a2a_response.py.

This phase closes the loop by piping the actual on-the-wire response from a
real workspace-server back through the wheel's a2a_response.parse() and
asserting it classifies as the Queued variant with the right method +
delivery_mode. A regression in EITHER the server emit shape OR the client
parser will now fail this E2E, eliminating the gap that allowed the original
"unexpected response shape" production bug to ship despite green unit tests.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 17:31:45 -07:00
hongming-personal 4a2dda7cac feat(canvas/skills): compact-empty layout for Plugins section (#2971)
Reported on production 2026-05-05:

  agent plugin tab Plugins
  0 installed
  + Install Plugin
  this part should be default compact

Pre-fix: SkillsTab always rendered the Plugins section as a full
rounded-xl panel with vertical chrome — even when zero plugins were
installed and the registry browser was closed. The empty state
gave a lot of vertical real estate for content that's just "0
installed + Install button".

Fix: when installed.length === 0 AND registry closed AND initial
load completed, collapse the section into a single inline pill
("Plugins · 0 installed · + Install Plugin"). The full panel
re-mounts when:
  - installed.length > 0 (a plugin landed → expand to surface the list)
  - showRegistry === true (user clicked + Install Plugin → registry opens)
  - !installedLoaded (avoid flash; the loading shell shows instead
    until the first /plugins fetch resolves)

Accessibility:
  - Compact pill: aria-label="Plugins (none installed)" + button
    aria-expanded="false" + aria-controls="plugins-section"
  - Full panel: button aria-expanded={showRegistry} + same aria-controls
  - Section gets id="plugins-section" so the aria-controls reference
    resolves once the section mounts

External workspaces: this is a pure canvas-frontend layout change —
applies to ALL workspace runtimes (external, claude-code, hermes,
langchain, codex, third-party MCP). No server-side change needed.

Tests
-----

SkillsTab.compactEmpty.test.tsx (4 tests):
  - Compact pill renders when installed=0, registry closed, loaded
  - Full panel renders when installed > 0
  - Click + Install Plugin from compact → expands to full panel
    (verified via aria-controls target id appearing in the DOM)
  - During initial load (installedLoaded=false), compact pill does
    NOT render — avoids a compact→full flash as the load completes

Per memory feedback_oss_design_philosophy.md: the SkillsTab is the
only tab that needs compact-empty today, but the pattern is
extractable into a shared EmptyStateCompactWrapper if Schedules /
Memories / Approvals adopt the same affordance later. Don't generalise
until the third use case (per the same memory, "every refactor toward
OSS plugin shape" without premature abstraction).

Verified
- tsc --noEmit clean
- All 4 tests pass

Refs #2971.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 17:26:32 -07:00
Hongming Wang 8b9f809966 fix(a2a): SSOT response parser — handle poll-mode queued envelope (#2967)
Introduce ``workspace/a2a_response.py`` as the single source of truth for
the wire shapes the workspace-server proxy can return at
``/workspaces/<id>/a2a``:

  * ``Result``    — JSON-RPC success
  * ``Error``     — JSON-RPC error or platform-level error (with
                    restart-in-progress metadata when present)
  * ``Queued``    — poll-mode short-circuit envelope: the platform
                    queued the message into the target's inbox, the
                    target will fetch via /activity poll
  * ``Malformed`` — anything the parser can't classify (logged at
                    WARNING so a future server change is loud)

``send_a2a_message`` (in ``a2a_client.py``) now dispatches via
``a2a_response.parse(data)`` instead of inline ``"result" in data`` /
``"error" in data`` sniffing. The Queued variant returns a new
``_A2A_QUEUED_PREFIX`` sentinel so callers can distinguish "delivered
async, no synchronous reply" from both success-with-text and failure.

reno-stars production data caught two intermittent failures that
both reduced to the same root cause:

  1. **File transfer announce silently failed** — when CEO Ryan PC
     (poll-mode external molecule-mcp) sent the harmi.zip
     announcement to Reno Stars Business Intelligent (also poll-mode
     external), ``send_a2a_message`` saw the platform's poll-queued
     envelope ``{"status":"queued","delivery_mode":"poll","method":"..."}``,
     didn't recognize it as the synthetic delivery-acknowledgement
     it is, and returned ``[A2A_ERROR] unexpected response shape``.
     The agent fell back to a chunk-shipping path; receiver did get
     the file but operator-facing logs showed a failure that didn't
     actually fail.

  2. **Duplicated agent comm** — same bug, inverted direction. d76
     delegated to 67d, send_a2a_message returned the unexpected-shape
     error, delegate_task wrapped it as DELEGATION FAILED, the calling
     agent retried with sharper wording, the recipient saw the same
     request twice and self-reported "二次请求 — 我先不执行".

External molecule-mcp standalone runtimes are inherently poll-mode
(they have no public URL), so every external↔external A2A pair was
hitting this on every send. The pre-fix client only handled JSON-RPC
``result``/``error`` keys and treated the queued envelope (which has
neither) as malformed. RFC #2339 PR 2 added the queued envelope on
the server side; the client never caught up.

When ``send_a2a_message`` returns the ``_A2A_QUEUED_PREFIX`` sentinel,
``tool_delegate_task`` now transparently falls back to
``_delegate_sync_via_polling`` (RFC #2829 PR-5's durable
``/delegate`` + ``/delegations`` polling path, which DOES work for
poll-mode peers because the platform's executeDelegation goroutine
writes to the inbox queue and the result row arrives when the target
picks it up + replies). The agent gets a real synchronous reply
instead of the empty queued sentinel.

  * ``test_a2a_response.py`` — 62 tests, **100% line coverage** on
    the parser (verified via ``coverage run --source=a2a_response``).
    Includes adversarial-input fuzzing across ~25 pathological
    payloads — parser must never raise.
  * ``test_a2a_client.py::TestSendA2AMessagePollMode`` — 4 tests for
    the new Queued/Error wiring in ``send_a2a_message``.
  * ``test_delegation_sync_via_polling.py::TestPollModeAutoFallback``
    — 3 tests for the auto-fallback in ``tool_delegate_task``,
    including negative cases (push-mode reply must NOT trigger
    fallback; genuine error must NOT silently retry).
  * **Verified all new tests FAIL on pre-fix source** by stashing
    a2a_client.py + a2a_tools_delegation.py and re-running — 5
    failures including ImportError for the missing
    ``_A2A_QUEUED_PREFIX``.

Per the operator-debuggability directive:

  * INFO at every Queued classification (expected variant; operator
    sees normal poll-mode-peer queueing in log stream).
  * INFO at the auto-fallback decision in ``tool_delegate_task``
    so a future operator can correlate "send returned queued →
    falling back to polling path" without reading the source.
  * WARNING at every Malformed classification (server contract
    drift; operator MUST see this immediately).
  * Existing transient-retry WARNING preserved.

  * Mirror Go-side typed model in workspace-server. The wire shape
    is documented in ``a2a_response.py``'s module docstring with
    file:line pointers to the canonical emitters; a future PR can
    introduce ``models/a2a_response.go`` without changing wire
    behavior. The fixture corpus in ``test_a2a_response.py`` is
    designed so a one-sided edit breaks CI.
  * ``send_message_to_user`` and ``chat_upload_receive`` use a
    different endpoint (``/notify``) and aren't affected by this
    bug; their parsing stays unchanged.

  * 135 tests pass across ``test_a2a_response.py`` +
    ``test_a2a_client.py`` + ``test_delegation_sync_via_polling.py``
    + ``test_a2a_tools_impl.py``.
  * ``coverage run --source=a2a_response -m pytest`` reports 100%
    line coverage with 0 missing.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 17:21:28 -07:00
molecule-ai[bot] a869bc1536 Merge pull request #2963 from Molecule-AI/staging
staging → main: auto-promote 7ee696e
2026-05-05 17:21:02 -07:00
hongming-personal d3e115cb06 Merge pull request #2972 from Molecule-AI/fix/a2a-poll-queued-envelope-2967
fix(a2a-client): recognize poll-mode 'queued' envelope (#2967)
2026-05-06 00:05:27 +00:00
hongming-personal b372c265ab Merge pull request #2968 from Molecule-AI/fix-chat-platform-pending-scheme
fix(canvas/chat): handle platform-pending: scheme for poll-mode upload downloads (PR #2966 followup)
2026-05-06 00:04:49 +00:00
hongming-personal 146c0e7c60 fix(a2a-client): recognize poll-mode 'queued' envelope (#2967)
workspace-server's a2a_proxy poll-mode short-circuit returns

    {status: "queued", delivery_mode: "poll", method: <a2a_method>}

when the peer has no URL to dispatch to (poll-mode peers, including
every external molecule-mcp standalone runtime). The bare
send_a2a_message parser only knew about JSON-RPC {result, error}
keys, so this envelope fell through to the "unexpected response shape"
error path. Two production symptoms on the reno-stars tenant traced
to it:

1. File transfer logged as failed when it actually succeeded —
   operator-facing logs showed an A2A_ERROR but the receiving
   workspace did get the chunked file via the agent's fallback path.
2. delegate_task retried after the false failure → peer received
   duplicate delegations → conversation got confused, the second
   peer self-diagnosed in a notify ("⚠️ Peer 二次请求 — 我先不执行").

Add a third branch to the parser, BETWEEN the existing JSON-RPC
{result, error} cases and the catch-all "unexpected" fallback. The
queued envelope is delivery-acknowledged-but-pending-consumption —
not an error — so it returns a clean success string the agent can
render as a normal outcome. The success string includes "queued"
and "poll" so an operator scanning logs sees the routing path
without parsing JSON.

Defensive: the new branch only fires when BOTH status="queued" AND
delivery_mode="poll" are present. A partial envelope (one key
missing) still falls through to the catch-all, so a future server
bug that emits a malformed shape gets surfaced instead of silently
swallowed.

Tests:
- test_poll_queued_envelope_returns_success_string — pins the canonical
  envelope returns a non-error string. Discriminating: verified to FAIL
  on old code (returned [A2A_ERROR] string), PASS on new.
- test_poll_queued_envelope_with_other_method — pins the parser doesn't
  hardcode message/send. Discriminating: also FAILS on old code.
- test_status_queued_without_poll_mode_still_falls_through — pins both
  keys are required (defensive against future server bugs).

12 existing tests in TestSendA2AMessage still pass — no regression.

Scope: hotfix for the bare send_a2a_message path. The full SSOT
typed-A2AResponse refactor (#158-#163, parents under #2967) covers the
broader vocabulary alignment between Go server and Python client. This
PR ends the production symptoms now without preempting that work.
2026-05-05 16:58:48 -07:00
hongming-personal 5d8b5e96e3 fix(canvas/chat): handle platform-pending: scheme for poll-mode upload downloads
Followup to PR #2966. The user reported the about:blank symptom on
reno-stars and the browser console showed:

  Failed to launch 'platform-pending:d76977b1-…/bb0dcaf3-…' because
  the scheme does not have a registered handler.

So the agent's "download link" was a `platform-pending:<wsid>/<file_id>`
URI — the canonical reference for poll-mode chat uploads (see
workspace-server/internal/handlers/chat_files.go:690 +
workspace/inbox_uploads.py). PR #2966 only handled `workspace:`,
`file:///`, and absolute container paths; the platform-pending
scheme fell through to the raw URI which the browser couldn't
navigate to.

Fix
---

- `resolveAttachmentHref`: added a `platform-pending:` branch that
  resolves to `${PLATFORM_URL}/workspaces/<wsid>/pending-uploads/
  <file_id>/content`. Uses the wsid from the URI, NOT the chat's
  workspace_id — these can differ when a file is forwarded across
  workspaces (cross-workspace delegation, agent forwarding).
- New `isPlatformAttachment(uri)` helper — single source of truth
  for "this URI requires our auth headers, route through
  downloadChatFile". Used by both `downloadChatFile` (chip click)
  and ChatTab's markdown-link override.
- ChatTab.tsx markdown-link override now imports
  `isPlatformAttachment` instead of duplicating the scheme list.
  Pre-fix this list was duplicated and missed `platform-pending:`.

Tests
-----

The 4 IME tests still pass; tsc clean. The platform-pending resolution
is exercised via the `isPlatformAttachment` SSOT helper (any URI
reaching `downloadChatFile` or the markdown override goes through
it). A dedicated test for the URL shape would need a more elaborate
fixture; manual verification on staging post-deploy is the practical
gate.

Reported on production reno-stars 2026-05-05.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:55:43 -07:00
hongming-personal dc6e1ac2bf Merge pull request #2966 from Molecule-AI/fix-chat-ime-and-download-link
fix(canvas/chat): IME-safe Enter + markdown link target/scheme handling
2026-05-05 23:52:54 +00:00
hongming-personal c2e12f3fb6 fix(canvas/chat): IME-safe Enter + markdown link target/scheme handling
Two production-reported regressions in the same chat surface, fixed
in one focused PR.

Issue 1 — IME composition + Enter sends half-typed message
----------------------------------------------------------

ChatTab's textarea onKeyDown was:

  if (e.key === "Enter" && !e.shiftKey) {
    e.preventDefault();
    sendMessage();
  }

For agents typing CJK / Japanese / Korean via the system IME, Enter
commits the candidate selection — not a newline, not a send. With
the old check, every IME-commit Enter accidentally sent the
half-typed message ("你好" + half-typed-pinyin + Enter to commit
the next candidate → message goes out before the user finishes).

Fix: guard on `event.nativeEvent.isComposing` AND `e.keyCode !== 229`.
The latter covers older Safari / WebKit-based mobile browsers that
delay setting isComposing on the composition-end Enter.

Issue 2 — markdown links land at about:blank
---------------------------------------------

ReactMarkdown's default `<a>` rendering passes the agent-supplied
href directly to the DOM with no target / scheme handling:

  - http(s) → navigates the canvas tab away (canvas state lost)
  - workspace://path / file:///workspace/... / /workspace/... →
    browser hits unhandled-protocol click → about:blank, no
    download (the reported bug)

Fix: ReactMarkdown `components.a` override:

  - In-container paths (workspace:, file:///{workspace,configs,home,
    plugins}, bare /{workspace,configs,...}) → preventDefault, route
    through downloadChatFile (same auth path the AttachmentChip
    uses). Filename is derived from the path's last segment.
  - External (http/https/mailto/unknown scheme) → target="_blank"
    rel="noopener noreferrer" so canvas state survives.

Tests
-----

ChatTab.imeAndLinks.test.tsx (4 tests):
  - Enter with isComposing=true → does NOT send, input preserved
  - Enter with keyCode=229 (older-Safari IME) → does NOT send
  - Enter with no IME signal → DOES send (happy path intact)
  - Shift+Enter → does NOT send (newline path intact)

The link-component override is exercised through the full ChatTab
render — the IME tests are jsdom-only and don't load chat history
with markdown messages, so the link test would need a more elaborate
fixture. Manual verification on staging post-deploy is the practical
gate; if the link test grows critical the AttachmentViews-style chip
test can extend.

Verified:
- tsc --noEmit clean
- 4/4 IME tests pass

Reported on production 2026-05-05.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:47:04 -07:00
hongming-personal dd5df70e59 Merge pull request #2965 from Molecule-AI/rfc-2945-pr-b-typed-events
feat(events): typed EventType registry — SSOT for WS event names (RFC #2945 PR-B)
2026-05-05 16:35:47 -07:00
hongming-personal f1dc721eeb Merge pull request #2964 from Molecule-AI/fix/delegation-ledger-utf8-truncate-2962
fix(delegation_ledger): rune-safe preview truncation (#2962)
2026-05-05 23:34:57 +00:00
hongming-personal 5b78bea10d feat(events): typed EventType registry — single source of truth for WS event names (RFC #2945 PR-B)
Pre-RFC-#2945, every BroadcastOnly / RecordAndBroadcast call site
passed a bare string literal:

  h.broadcaster.BroadcastOnly(workspaceID, "AGENT_MESSAGE", payload)

29 producers (Go, ~30 call sites in handlers/, scheduler/, registry/,
bundle/) and ~30 canvas consumers (TS store + listeners) duplicated
the same string with no shared definition. A producer renaming an
event silently broke every consumer — same drift class that produced
the reno-stars data-loss regression on the persistence side. PR-A
fixed the persistence-side SSOT (AgentMessageWriter); PR-B fixes the
event-name SSOT.

What this PR ships

  internal/events/types.go
    - EventType typed string + 29 named constants covering the full
      taxonomy (chat / lifecycle / agent assignment / delegation /
      task / approval / auth).
    - Grouped semantically; new constants must be added here AND
      mirrored in canvas/src/lib/ws-events.ts (parity gate landing
      in PR-B-2 follow-up).
    - AllEventTypes slice — authoritative list for the snapshot
      test + the cross-language parity gate.

  internal/events/types_test.go (3 tests)
    - TestAllEventTypes_IsSnapshot: pins the canonical list. Adding
      a new constant without updating AllEventTypes (or vice versa)
      fails with a one-line diff.
    - TestEventType_NoEmptyConstants: catches accidentally-empty
      values (typo in types.go: const X EventType = ...).
    - TestEventType_AllUppercaseSnakeCase: pins the wire format that
      canvas TS switch statements assume (no kebab-case, no mixed
      case, no leading/trailing/double underscores).

  agent_message_writer.go (single migration)
    - Demonstrates the constant-usage shape:
        events.EventAgentMessage  →  "AGENT_MESSAGE"
    - Other ~30 call sites stay on bare strings for now (this PR
      narrow); the migration happens in PR-B-1 follow-up. Both
      shapes (constant + bare string) co-exist on the wire — the
      typed version is just the recommended path for new code.

Why ship this in stages

  1. PR-B (this): types + tests + first migration → MERGEABLE NOW,
     low risk.
  2. PR-B-1 (follow-up): migrate the remaining ~30 call sites to
     constants. Mechanical, low-risk.
  3. PR-B-2 (follow-up): canvas/src/lib/ws-events.ts mirror + cross-
     language parity gate. Touches both repos.

Per memory feedback_oss_design_philosophy.md (every refactor toward
OSS plugin shape) — this surface is now plugin-safe: external
implementations can import the events package and get the same
named taxonomy without copying strings.

Verified
- go vet ./internal/events/ clean
- go build ./... clean
- TestAllEventTypes_IsSnapshot + TestEventType_* all pass
- TestAgentMessageWriter_* (the only call site touched) still green

Refs RFC #2945, PR #2949 (PR-A SSOT), PR #2944 (reno-stars).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:25:38 -07:00
hongming-personal a5903af459 fix(delegation_ledger): rune-safe preview truncation (#2962)
The previous byte-slice form `s[:previewCap]` could split a multi-byte
codepoint at byte 4096, producing invalid UTF-8. Postgres JSONB rejects
the row → ledger insert silently fails → audit gap on dashboards while
activity_logs continues to record the event.

Walk the string by rune index and stop at the last boundary that fits
inside the cap. ASCII-only strings still hit the cap exactly; CJK/emoji
strings stop slightly under, never over.

Mirrors the truncatePreviewRunes fix shipped for agent_message_writer
in #2959. Followup: deduplicate into a shared helper once both have
landed.

Tests: 2 regression tests using utf8.ValidString — one with an all-3-byte
rune string just over the cap, one with a single multi-byte rune sitting
exactly on the boundary. Verified on the previous byte-slice impl: both
new tests would fail (invalid UTF-8 + truncation past cap by 1 byte).
2026-05-05 16:19:51 -07:00
hongming-personal 07d09f3696 Merge pull request #2959 from Molecule-AI/rfc-2945-pr-a-followup-utf8-and-db-errors
fix(handlers): UTF-8-safe preview truncation + distinguish DB errors from not-found (PR-A followup)
2026-05-05 16:19:29 -07:00
hongming-personal f7c270bf24 Merge pull request #2955 from Molecule-AI/auto-sync/main-e0df90c2
chore: sync main → staging (auto, ff to e0df90c2)
2026-05-05 16:19:03 -07:00
hongming-personal 0301f90183 Merge pull request #2961 from Molecule-AI/fix/doctor-register-side-effect
fix(mcp-doctor): heartbeat (idempotent) instead of register (UPSERT) — self-review of #2954
2026-05-05 23:18:54 +00:00
hongming-personal feef80423b Merge pull request #2958 from Molecule-AI/fix/external-connect-templates-mcp-command
fix(external-connect): use molecule-mcp wrapper in Codex/OpenClaw templates (#2957)
2026-05-05 16:18:23 -07:00
hongming-personal 469b24ff8f Merge pull request #2960 from Molecule-AI/fix/memory-tab-v2-self-review
fix(memory): self-review on PR #2956 — drop speculative field, tighten 503 match
2026-05-05 23:15:50 +00:00
Hongming Wang c4d3c9a451 fix(memory): self-review on PR #2956 — drop speculative field, tighten 503 match
Two issues caught in five-axis self-review of #2956:

## 1. Drop speculative source_workspace_id rendering

The panel rendered a "from peer" badge based on
`propagation.source_workspace_id`, claiming it surfaced cross-
workspace propagation. But the OpenAPI spec at
docs/api-protocol/memory-plugin-v1.yaml documents `propagation` as
"Opaque metadata the plugin stores and returns. Reserved for future
cross-namespace propagation semantics" — and a grep across
workspace-server/internal/memory/ confirms NO writer in the codebase
populates that key. The badge would never render against real data.

Violates "don't design for hypothetical future requirements" from
the project conventions. Drop the field from MemoryV2, the row badge,
the test fixtures, and the JSDoc. When propagation gains a concrete
shape, re-add backed by an actual writer.

## 2. Tighten 503 detection — match the literal contract string

Pre-fix detection: `msg.includes('503') || msg.toLowerCase().includes('plugin is not configured')`
False-positives on any unrelated 503 + on any error mentioning
"plugin" + "configured" in any order.

Post-fix: `msg.includes('MEMORY_PLUGIN_URL')` — the env var name is a
hard-coded literal in workspace-server/internal/handlers/memories_v2.go's
available() error, so this is a pinned cross-layer contract. Drift
between the Go error message and the canvas detection now fails
loud (TestMemoriesV2_PluginUnwired_All503 asserts the env var name
in the response body; the canvas test asserts the same).

Extracted as a named export `isPluginUnavailableError` so the
detection is unit-testable and reusable. Added 4 direct tests:
contract-string match, generic-503 false-negative, 401 false-
negative, non-Error inputs.

## Test results

- 30 component tests pass (was 26; +4 for isPluginUnavailableError)
- Coverage on MemoryInspectorPanel.tsx: 100% lines, 100% functions
  (branch coverage up to 85.9% from 84.7% — speculative-field
  branches no longer count)
- Full canvas suite: 1277/1277 pass across 91 files
2026-05-05 16:11:13 -07:00
hongming-personal 2652ea8342 fix(mcp-doctor): heartbeat (idempotent) instead of register (UPSERT)
Self-review caught after #2954 landed: check_register() POSTed to
/registry/register with agent_card.name="doctor-probe". The endpoint
is an UPSERT, so the doctor probe overwrites the workspace's actual
agent_card metadata until the real agent's next register call. An
operator running `molecule-mcp doctor` against a live workspace
would see their canvas briefly display "doctor-probe" as the agent
name — invisible production-disruption.

Switches to POST /registry/heartbeat. heartbeat only updates
last_heartbeat_at (and clears awaiting_agent if needed) — the same
work a normal molecule-mcp boot does every 20s in steady state, so
the doctor's extra heartbeat is indistinguishable from background
traffic.

Function renamed check_register → check_token_auth to match what
it actually does. check_register kept as back-compat alias so any
external test/import still resolves.

Also unified the duplicated token-resolution paths into a single
_resolve_token() returning (value, source_label). Pre-fix:
check_register and _resolve_token_summary read env in parallel
ladders — a future env-var addition would have to touch both.

New tests:
  - test_check_token_auth_uses_heartbeat_endpoint: mocks urlopen,
    asserts the URL ends in /registry/heartbeat AND does NOT
    contain /registry/register. Pins the load-bearing invariant
    so a future refactor can't silently re-route through register.
  - test_resolve_token_returns_value_and_label_for_env: pins the
    consolidated resolver returns both pieces of info from the
    same source-decision.
  - test_resolve_token_returns_none_when_missing: missing-env
    happy path.

Verification:
  - 13/13 tests pass (10 existing + 3 new)
  - Manual stripped-env run still renders 4 FAIL + 2 WARN with
    actionable hints, exit 1.

Refs molecule-core#2934 item 6 (doctor side-effect fix-up).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:11:08 -07:00
hongming-personal 1e01083e55 fix(handlers): UTF-8-safe preview truncation + distinguish DB errors from not-found (RFC #2945 PR-A followup)
Self-review of PR #2949 surfaced two pre-existing defects that the
SSOT consolidation inherited from the original /notify handler. Both
are addressable in a small follow-up; shipping them as a separate PR
keeps the consolidation and the bug-fix individually reviewable.

Critical: byte-slice preview truncation produces invalid UTF-8
-------------------------------------------------------------

Pre-fix:

    if len(preview) > 80 {
        preview = preview[:80] + "…"
    }

`len()` returns BYTES; `preview[:80]` slices on a byte boundary. For
agent-authored chat in CJK / emoji / accented characters, byte 80
lands mid-codepoint → invalid UTF-8 → Postgres JSONB rejects → INSERT
fails → activity_log row never written → message vanishes from chat
history on the next reload. The persistence-failure log fires but
operators have to grep to find it, and the user-visible regression
mode is identical to reno-stars.

Fix: extract `truncatePreviewRunes(s, maxRunes)` that walks the rune
boundary using `for i := range s` (Go's range over string yields rune
start indices). Cap at 80 RUNES not bytes — UI-friendly count, not
storage count.

Important: workspace-lookup error path swallows real DB errors
--------------------------------------------------------------

Pre-fix:

    if err := w.db.QueryRowContext(...).Scan(&wsName); err != nil {
        return ErrWorkspaceNotFound
    }

Conflates `sql.ErrNoRows` (legit not-found → caller 404) with real
DB errors (connection drop, query timeout, pool exhaustion → caller
should 503). During a Postgres outage every notify call surfaced as
"workspace not found" — masking the actual incident in alerting and
making the symptom indistinguishable from "you typed a bad workspace
ID".

Fix: distinguish via `errors.Is(err, sql.ErrNoRows)` and wrap
non-not-found errors with `fmt.Errorf("agent_message: workspace
lookup: %w", err)`. Callers' existing fallback path (return 500 /
return error wrapped) handles the new shape correctly without any
changes — verified by running existing TestNotify_* and
TestMCPHandler_SendMessage_* tests.

Tests added (3 new, 11 total writer tests)
------------------------------------------

- TestTruncatePreviewRunes_RuneBoundary: 8-case table — ASCII, CJK,
  exactly-at-max, emoji prefix. Asserts both correct visible output
  AND `utf8.ValidString` on every result so the bug shape (invalid
  UTF-8) can't recur.

- TestAgentMessageWriter_Send_NonASCIIMessagePersists: end-to-end
  with a 200-rune CJK message (exceeds the 80-rune cap, would have
  hit the byte-slice bug). Pins the INSERT summary contains valid
  UTF-8 with exactly 80-rune body + ellipsis.

- TestAgentMessageWriter_Send_DBErrorOnLookupReturnsWrapped: pins the
  DB-outage path returns a wrapped non-ErrWorkspaceNotFound error so
  alerting can distinguish 404 from 503. Verified via mock
  ExpectQuery returning a transient error.

Verified
--------

- `go vet ./internal/handlers/` clean
- `go build ./...` clean
- All 14 writer + caller tests pass (8 original + 3 new + AST gate +
  TestNotify_* + TestMCPHandler_SendMessage_* sibling tests)

Per memory feedback_assert_exact_not_substring.md: every new test
asserts boundary behavior directly (UTF-8 validity, exact rune count,
errors.Is comparison) rather than substring-match in stringified
output.

Refs RFC #2945, PR #2949, PR #2944.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:10:58 -07:00
Hongming Wang eab36e217e fix(external-connect): use molecule-mcp wrapper in Codex/OpenClaw templates (#2957)
The External Connect modal's Codex and OpenClaw tabs were rendering
this MCP server config:

  command = "python3"
  args = ["-m", "molecule_runtime.a2a_mcp_server"]

That spawns the bare MCP dispatcher with no presence wiring. The
``molecule-mcp`` console-script wrapper (mcp_cli.main) is what calls
``POST /registry/register`` at startup and runs the 20s heartbeat
thread alongside the MCP stdio loop. Without the wrapper, the canvas
flips the workspace back to ``awaiting_agent`` (OFFLINE) within
60-90s — even while tools work — because nothing is heartbeating.

Operator-side this looks like: the workspace is registered and tools
work fine when invoked, but the canvas shows "offline" / "Restart"
CTA, peer agents see the workspace as awaiting_agent in list_peers
output, and inbound A2A delivery silently fails the readiness check.
A new external-Codex operator (#2957) hit this and spent debugging
time on what should have been a copy-paste install.

Fix: switch both Codex and OpenClaw templates to
``command = "molecule-mcp"`` / ``args = []``, matching the universal
MCP template that already handles this correctly. Inline comment in
each template explains the wrapper-vs-bare-module tradeoff so a
future template author doesn't regress to the shorter form.

Hermes-channel intentionally still spawns the bare module — the
hermes plugin owns the platform plugin path and runs its own
register_platform/heartbeat code in-process; double-heartbeating
would race. Universal/Codex/OpenClaw all need the wrapper.

Regression gate: TestExternalMcpTemplates_UseMoleculeMcpWrapper
asserts the three templates that must use the wrapper actually do,
and explicitly fails on the old ``-m molecule_runtime.a2a_mcp_server``
shape. Verified the test FAILS on pre-fix source by stashing only
external_connection.go and re-running.

Source: molecule-core#2957 issue 1 (item 4 of the report — the
``(codex returned empty output)`` / opaque-canvas-error / stale-
session items live in codex-channel-molecule and are tracked
separately).

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 16:06:02 -07:00
hongming-personal 7ee696ec9a Merge pull request #2954 from Molecule-AI/feat/molecule-mcp-doctor
feat(mcp): add molecule-mcp doctor onboarding diagnostic (#2934 item 6)
2026-05-05 22:57:28 +00:00
hongming-personal decec9b9a1 Merge pull request #2956 from Molecule-AI/feat/memory-tab-v2-redesign
feat(memory): redesign Memory tab for v2 plugin
2026-05-05 22:56:55 +00:00
hongming-personal ada27fdb5d Merge pull request #2949 from Molecule-AI/rfc-2945-pr-a-agent-message-writer
refactor(handlers): AgentMessageWriter SSOT — consolidate Notify + MCP send_message_to_user (RFC #2945 PR-A)
2026-05-05 22:56:28 +00:00
Hongming Wang f0f4d0e761 feat(memory): redesign Memory tab for v2 plugin
Replaces the v1 LOCAL/TEAM/GLOBAL tab trio (mapped to the deprecated
shared_context model) with a v2 plugin-driven UI. Without this,
canvas Memory tab was reading the frozen agent_memories table while
all post-cutover agent writes went to the plugin's memory_records —
the tab silently displayed stale data.

## Backend (workspace-server)

New routes under wsAuth, all behind the existing per-tenant token:

  GET    /workspaces/:id/v2/namespaces      → readable + writable lists
  GET    /workspaces/:id/v2/memories        → plugin search proxy
  DELETE /workspaces/:id/v2/memories/:mid   → plugin forget proxy

memories_v2.go — slim handler:
  - Server-side ACL: every search request is intersected with the
    resolver's readable-namespaces set (canvas-supplied namespace
    that the workspace can't read returns [] not 403, matches v1
    existence-non-inferring shape).
  - Returns 503 with "set MEMORY_PLUGIN_URL" hint when plugin
    isn't wired (canvas surfaces a banner).
  - Maps plugin not_found → 404, other plugin errors → 502.
  - View shaping: NamespaceView.label rendered server-side
    ("Workspace (abc-1234)", "Team (t-99)", "Org (acme)", custom)
    so canvas doesn't parse namespace names. MemoryView surfaces
    pin/expires_at/score/source_workspace_id from Propagation.

memories_v2_test.go — 100% line + 100% function coverage:
  - 503 path on every endpoint when unwired
  - Namespaces success + readable/writable error paths
  - Search: empty intersection, full-path query/kind/limit
    propagation, namespace=/no-namespace branches, propagation
    map missing/wrong-type, intersect error, plugin error
  - Forget: success, plugin not_found→404, other plugin
    errors→502, missing memoryId→400
  - Helpers: namespaceLabel for all 4 kinds + truncation,
    parseLimit edge cases (default/0/negative/over-cap/non-num),
    memoryToView field round-trip, indexOfColon, shortID

## Frontend (canvas)

MemoryInspectorPanel rewritten for v2:
  - Drop LOCAL/TEAM/GLOBAL trio. Namespace dropdown driven by
    GET /v2/namespaces.readable, "All namespaces" default.
  - New per-row badges: kind (F/S/C), source (agent/runtime/user),
    pin (📌), TTL countdown (12h / "expired"), score% on
    semantic search, source-workspace ⇡ws-pee for propagated.
  - Drop Edit button — v2 plugin contract has no PATCH; the
    model is forget + recommit. Forget stays.
  - Plugin-unavailable banner with operator hint when /v2/*
    returns 503.
  - Bug fix surfaced by test: rollback-on-failed-delete order
    of operations (loadEntries() called setError(null) AFTER
    we set the failure message, wiping it). Reload first, then
    set the error.

MemoryEditorDialog deleted — Add was POST /memories which v2
doesn't support from canvas (writes go via MCP). The legacy
Edit-flow tests go with it.

## Test results

Backend: `go test ./internal/handlers/` — all pass
Backend coverage on memories_v2.go: 100% lines, 100% functions
Canvas: `vitest run` — 91 files, 1273 tests pass (26 new)
Canvas coverage on MemoryInspectorPanel.tsx: 100% lines,
  100% functions, 96.7% statements, 84.7% branches
  (uncovered branches are defensive `?? fallback` for
   contract-impossible kind/source values)

## Migration note

The legacy v1 GET/POST/PATCH/DELETE on /workspaces/:id/memories
remains in place for the back-compat MCP shim (mcp_tools_memory_v2's
legacy routing) and admin export/import. PR-9 (#283) drops
agent_memories along with the v1 endpoints once the cutover
verification window closes.
2026-05-05 15:53:28 -07:00
molecule-ai[bot] e0df90c294 Merge pull request #2951 from Molecule-AI/staging
staging → main: auto-promote 1edee11
2026-05-05 15:48:32 -07:00
hongming-personal f01f374072 feat(mcp): add molecule-mcp doctor onboarding diagnostic
Closes #2934 item 6 — the deferred follow-up from Ryan's onboarding-
friction report. Quote: "this single command would have saved me
30 of the 45 minutes."

When push delivery fails or the install half-works, the operator
today has no signal — they hand-grep the Claude Code binary or
chase the `from versions: none` red herring. Doctor renders six
checks in one screen with concrete next-step suggestions:

  1. Python version    >=3.11? (wheel's pin)
  2. Wheel install     molecule-ai-workspace-runtime importable +
                        version surfaced
  3. PATH for binary   `molecule-mcp` resolves on PATH; if not,
                        prints the resolved user-site bin dir to
                        add (or recommends pipx)
  4. Env vars          PLATFORM_URL + WORKSPACE_ID + token (env or
                        *_FILE or .auth_token)
  5. Platform reach    GET ${PLATFORM_URL}/healthz returns 2xx
  6. Registry register POST /registry/register with the resolved
                        token returns 2xx — end-to-end auth check

Each line: `[OK|WARN|FAIL] <label>: <status>` plus a `next:` hint
when not OK. ANSI colors auto-disable on non-TTY / NO_COLOR.

Exit code: 0 on all-OK or only-WARN, 1 on any FAIL — scriptable
from CI install-checks.

## Files

`workspace/mcp_doctor.py`  (new) — six check functions + `run()`
                                   entry point. Uses urllib (stdlib)
                                   so doctor works even on a partial
                                   install where `requests` is missing.

`workspace/mcp_cli.py`             Subcommand dispatch:
                                     molecule-mcp doctor   → mcp_doctor.run()
                                     molecule-mcp --help   → usage banner
                                     molecule-mcp          → server (unchanged)

`workspace/tests/test_mcp_doctor.py`  (new) — 10 tests covering each
                                       check's pass/fail/skip path
                                       plus the end-to-end exit-code
                                       contract on a stripped env.

`scripts/build_runtime_package.py`    Adds `mcp_doctor` to
                                       TOP_LEVEL_MODULES so the
                                       wheel ships the new module.

## Out of scope (deferred follow-ups)
- Claude Code-specific checks (parse ~/.claude.json, verify each
  MCP entry is plugin-sourced + dev-channels flag set). That's a
  separate Claude-Code-shaped doctor; lives in the channel plugin.
- Automated remediation. Doctor is diagnostic — tells the operator
  what's wrong + how to fix it, doesn't apply changes.

## Verification
  - python -m pytest tests/test_mcp_doctor.py -v   → 10/10 PASS
  - python -m pytest tests/test_mcp_cli*.py        → 67/67 PASS
    (existing CLI suite still green; subcommand dispatch added
    before env-validation, doesn't disturb the server-boot path)
  - manual: `molecule-mcp doctor` on a stripped env renders 4 FAIL
    + 2 WARN + exit code 1, with each `next:` hint actionable

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 15:44:36 -07:00
hongming-personal 1edee1131b Merge pull request #2948 from Molecule-AI/auto-sync/main-f5ea812e
chore: sync main → staging (auto, ff to f5ea812e)
2026-05-05 15:29:46 -07:00
hongming-personal d99b3f2aec refactor(handlers): consolidate Notify + MCP send_message_to_user through AgentMessageWriter (RFC #2945 PR-A)
Pre-RFC-#2945 the broadcast + activity_log INSERT for "agent → user
chat" was duplicated across two handlers — activity.go's Notify (HTTP
/notify) and mcp_tools.go's toolSendMessageToUser (MCP tools/call).
The duplication is exactly what produced the reno-stars production
data-loss regression (PR #2944): the persistence-half fix landed for
one handler and silently lagged for the other for months, dropping
every long-form external-agent message on reload.

PR #2944 added the missing INSERT to mcp_tools.go and a forward-
looking AST gate. This PR removes the duplication at the source.

What changes
------------

NEW: workspace-server/internal/handlers/agent_message_writer.go
- AgentMessageWriter struct + NewAgentMessageWriter ctor.
- Send(ctx, workspaceID, message, attachments) error: workspace
  lookup → broadcast WS AGENT_MESSAGE → INSERT activity_logs.
- ErrWorkspaceNotFound for the lookup-miss path so callers can
  return 404 / JSON-RPC error cleanly.
- Best-effort persistence: INSERT failure logs only, returns nil so
  the broadcast success isn't undone (matches previous behavior in
  both call sites — pinned by test).
- Takes events.EventEmitter (interface) so tests can substitute a
  capturing fake without nil-panicking inside hub.Broadcast.

UPDATED: activity.go:Notify
- Replaced ~75 lines of inline broadcast+INSERT with a 12-line
  call to AgentMessageWriter.Send.
- Attachment shape conversion (NotifyAttachment → AgentMessageAttachment)
  is local to the HTTP handler; the writer's API doesn't import the
  HTTP-binding-tagged type.

UPDATED: mcp_tools.go:toolSendMessageToUser
- Replaced ~40 lines (the post-#2944 broadcast+INSERT pair) with a
  6-line call to the writer.
- Attachments is nil today because the MCP tool args don't expose
  attachments yet. When the schema adds it, build the slice and
  pass through; the writer half is ready.

Tests
-----

agent_message_writer_test.go (8 tests, comprehensive):
- TestAgentMessageWriter_Send_Success_NoAttachments — happy path,
  pins JSON `{"result":"hi"}`.
- TestAgentMessageWriter_Send_Success_WithAttachments — pins file
  parts shape (kind=file, file.{uri,name,mimeType,size}). Uses a
  jsonMatcher that decodes + asserts via predicate (tolerant of
  map key ordering, exact on shape).
- TestAgentMessageWriter_Send_WorkspaceNotFound — pins
  ErrWorkspaceNotFound + asserts NO broadcast NO INSERT.
- TestAgentMessageWriter_Send_DBInsertFailureStillReturnsNil — pins
  best-effort persistence contract.
- TestAgentMessageWriter_Send_PreviewTruncation — pins ≤80-char
  preview + ellipsis (Ryan's onboarding-friction report would have
  bloated activity_logs.summary by 2KB without this).
- TestAgentMessageWriter_Send_BroadcastsAgentMessageEvent — pins WS
  event name + payload shape via capturingEmitter.
- TestAgentMessageWriter_Send_OmitsAttachmentsKeyWhenEmpty — pins
  the "no key when nil" wire contract.

The existing AST gate from #2944
(TestAgentMessageBroadcastsArePersisted) still holds: any future
function emitting AGENT_MESSAGE without an INSERT fails the test.
With the writer in place that's now redundant — both producers go
through it — but the gate is cheap to keep as defense-in-depth.

Verified: go vet clean; all writer + caller tests pass; existing
TestNotify_* + TestMCPHandler_SendMessage_* + the AST gate all green.

Refs RFC #2945, PR #2944.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 15:29:42 -07:00
molecule-ai[bot] f5ea812e9d Merge pull request #2947 from Molecule-AI/staging
staging → main: auto-promote c4807a9
2026-05-05 22:22:58 +00:00
hongming-personal 3b7ed9cf53 Merge pull request #2946 from Molecule-AI/fix/onboarding-followup-2934
mcp: surface specific TOKEN_FILE errors + link follow-ups (#2934)
2026-05-05 22:19:21 +00:00
Hongming Wang da9061c131 mcp: surface specific TOKEN_FILE errors + link follow-ups (#2934)
Self-review of #2935 turned up two real defects:

1. Stale README issue references — the build_runtime_package.py
   README template said "(issue #2934 follow-up)" twice, but the
   marketplace-plugin and `doctor` items now have dedicated tracking
   issues. Updated to point at #2936 and #2937 respectively.

2. Silent fallthrough on broken MOLECULE_WORKSPACE_TOKEN_FILE — when
   an operator EXPLICITLY pointed TOKEN_FILE at a path that didn't
   exist / wasn't readable / was blank / contained internal whitespace,
   the resolver silently returned the generic "set one of these three
   vars" error. That's exactly the silent failure mode #2934 flagged
   ("a new user has no chance"). Refactor `_read_token_from_file_env`
   to return `(token, error)`; surface the SPECIFIC failure when the
   operator's intent was clearly the file path. Skip the CONFIGS_DIR
   fallback in that case so the operator's config bug isn't masked
   by a different source happening to work.

Adds 2 renames + 2 new tests in test_mcp_cli_split.py:
  - test_missing_file_returns_specific_error (asserts "does not exist")
  - test_empty_file_returns_specific_error (asserts "is empty")
  - test_multi_line_file_rejected (asserts "internal whitespace")
  - test_token_file_error_skips_configs_dir_fallback (asserts a valid
    CONFIGS_DIR/.auth_token does NOT silently rescue a broken
    TOKEN_FILE)

All 81 mcp_cli + mcp_cli_multi_workspace + mcp_cli_split tests pass.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 15:07:15 -07:00
hongming-personal c4807a930d Merge pull request #2940 from Molecule-AI/refactor/a2a-tools-inbox-extract-rfc2873-iter4e
refactor(workspace): extract inbox tools from a2a_tools.py (RFC #2873 iter 4e)
2026-05-05 21:58:32 +00:00
hongming-personal d22fbb29b8 Merge pull request #2944 from Molecule-AI/fix-mcp-send-message-to-user-persist
fix(mcp): persist send_message_to_user pushes to activity_log (reno-stars data loss)
2026-05-05 21:57:37 +00:00
hongming-personal 899c53550d test(mcp): comprehensive coverage for send_message_to_user persistence + AST gate (reno-stars followup)
Per user request: audit all similar tools + write comprehensive tests
including E2E for the persistence-of-AGENT_MESSAGE-broadcasts contract.

Audit (all BroadcastOnly call sites in workspace-server/internal/):

  | Site | Event | Persisted? | Notes |
  |---|---|:---:|---|
  | a2a_proxy_helpers.go:275 | A2A_RESPONSE | ✓ | LogActivity above |
  | activity.go:486 (Notify) | AGENT_MESSAGE | ✓ | INSERT line 535 |
  | activity.go:701 (LogActivity) | ACTIVITY_LOGGED | ✓ | self-emits inside DB write |
  | mcp_tools.go:341 (toolSendMessageToUser) | AGENT_MESSAGE | ✓ NEW (this PR) |
  | registry.go:575 | TASK_UPDATED | N/A | transient progress, not chat |
  | registry.go:596 | WORKSPACE_HEARTBEAT | N/A | infra ping, not chat |

Only one chat-bearing broadcast was missing persistence (the just-
fixed mcp bridge path). No other regressions found.

Tests added (4 new, total 5 send_message_to_user tests):

1. TestAgentMessageBroadcastsArePersisted — AST gate that walks every
   non-test .go in the package, finds funcs that BroadcastOnly with
   "AGENT_MESSAGE", asserts each ALSO contains an
   "INSERT INTO activity_logs". Forward-looking regression block:
   any future chat tool that broadcasts without persisting fails the
   test with a clear file:func diagnostic. Mutation-tested locally:
   removing the INSERT block from toolSendMessageToUser reliably
   produces the expected failure.

2. TestMCPHandler_SendMessageToUser_DBErrorLogsAndStill200s — pins
   the "best-effort persistence" contract. DB INSERT failures must
   NOT abort the tool response (the WS broadcast already succeeded;
   retrying would double-render in the live chat). Matches /notify.

3. TestMCPHandler_SendMessageToUser_ResponseBodyShape — pins the
   exact `{"result": "<message>"}` JSON shape stored in
   response_body. The canvas hydrater (extractResponseText in
   historyHydration.ts) reads body.result; any drift here silently
   breaks chat history without failing the INSERT. Per memory
   feedback_assert_exact_not_substring.md, asserts the literal JSON
   shape, not a substring.

4. TestMCPHandler_SendMessageToUser_PersistsToActivityLog (existing,
   from previous commit) — pins INSERT shape with regex on
   'a2a_receive' + 'notify' literals.

5. TestMCPHandler_SendMessageToUser_Blocked_WhenEnvNotSet (existing)
   — env-gate aborts before DB.

Test fixture cleanup: newMCPHandler now uses newTestBroadcaster (real
ws.Hub) instead of events.NewBroadcaster(nil) — the latter nil-panics
inside hub.Broadcast on the AGENT_MESSAGE path. Same broadcaster
shape every other handler test uses.

E2E note: the AST gate is the strongest forward-looking guarantee.
A real-DB integration test would add value for CI but is largely
duplicative of the sqlmock contract tests above (sqlmock pins SQL
shape with much faster feedback). Left as a future enhancement when
the handlers Postgres-integration suite extends MCP coverage.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 14:52:32 -07:00
hongming-personal cdfc9f743f fix(mcp): persist send_message_to_user pushes to activity_log (reno-stars data loss)
Reported on production tenant reno-stars: an external claude-code agent
(CEO Ryan PC workspace) sent a long-form message via send_message_to_user;
the user saw it live in the chat panel but it vanished after a refresh.
Confirmed via direct production query — the message is NOT in
activity_logs at all (only short test pings around it are persisted).

Root cause: there are TWO server-side handlers for send_message_to_user:

  1. HTTP `/workspaces/:id/notify` (activity.go:Notify) — broadcasts WS
     AND inserts a row into activity_logs. This is the path the
     in-container runtime's tool_send_message_to_user calls.

  2. MCP-bridge `tools/call name=send_message_to_user`
     (mcp_tools.go:toolSendMessageToUser) — broadcasts WS only,
     **never persisted**. This is the path EXTERNAL agents using
     molecule-mcp's send_message_to_user tool route through.

The persistence fix landed for path 1 months ago but was never mirrored
on path 2. External agents — exactly the case in reno-stars/CEO Ryan PC
— have been silently losing every long-form notification on reload.

Fix: mirror the activity.go INSERT shape inside toolSendMessageToUser:

  INSERT INTO activity_logs
    (workspace_id, activity_type, method, summary, response_body, status)
  VALUES ($1, 'a2a_receive', 'notify', $2, $3::jsonb, 'ok')

Same wire shape as /notify so the canvas's chat-history hydration
(`type=a2a_receive&source=canvas`) treats both writers identically.
Errors are log-only — broadcast already succeeded, persistence failure
shouldn't block the tool response (matches /notify behavior; downside
is the same data-loss-on-DB-error risk, surfaced via log.Printf).

Tests
-----

- `TestMCPHandler_SendMessageToUser_PersistsToActivityLog` — pins both
  the workspace-name lookup AND the INSERT shape. Regex-matches
  `'a2a_receive'` + `'notify'` literals so a future refactor that
  changes activity_type or method breaks the test loud, not silently
  re-introducing the data-loss bug.
- Updated newMCPHandler to use newTestBroadcaster() (real ws.Hub) —
  events.NewBroadcaster(nil) crashes inside hub.Broadcast in the
  send_message_to_user path. Same shape every other handler test uses.

Verified `go test ./internal/handlers/ -run TestMCPHandler_SendMessage`
green; full vet clean.

Refs reno-stars production incident 2026-05-05.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 14:47:48 -07:00
molecule-ai[bot] 7a2664523c Merge pull request #2942 from Molecule-AI/staging
staging → main: auto-promote 1ad107c
2026-05-05 14:47:21 -07:00
Hongming Wang 475da5b64c refactor(workspace): extract inbox tools from a2a_tools.py (RFC #2873 iter 4e)
Continues the OSS-shape refactor. After iters 4a-4d (rbac, delegation,
memory, messaging) the only behavior left in ``a2a_tools.py`` was
``report_activity`` plus three thin inbox-tool wrappers and the
``_enrich_inbound_for_agent`` helper. This iter extracts the inbox
slice to ``a2a_tools_inbox.py`` so the kitchen-sink module shrinks
from 280 LOC to ~165 LOC of imports + report_activity + back-compat
re-export blocks.

Extracted symbols:
  - ``_INBOX_NOT_ENABLED_MSG`` (sentinel)
  - ``_enrich_inbound_for_agent`` (poll-path peer enrichment helper)
  - ``tool_inbox_peek``
  - ``tool_inbox_pop``
  - ``tool_wait_for_message``

Re-exports (`from a2a_tools_inbox import …`) preserve the public
``a2a_tools.tool_inbox_*`` surface so existing tests + call sites
continue to resolve unchanged.

New tests in test_a2a_tools_inbox_split.py:
  1. **Drift gate (5)** — every previously-public symbol on a2a_tools
     is the EXACT same object as a2a_tools_inbox.foo (`is`, not `==`),
     catches a future "wrap with logging" refactor that silently loses
     existing test coverage.
  2. **Import contract (1)** — a2a_tools_inbox does NOT eagerly import
     a2a_tools at module load. Pins the layered architecture: the
     extracted slice depends on ``inbox`` + a lazy ``a2a_client``
     import, never on the kitchen-sink that re-exports it.
  3. **_enrich_inbound_for_agent branches (5)** — peer_id-empty
     (canvas_user) returns dict unchanged; missing peer_id key same;
     a2a_client unavailable (test harness, partial install) degrades
     gracefully with a bare envelope; registry hit populates
     peer_name + peer_role + agent_card_url; registry miss still
     surfaces agent_card_url (constructable from peer_id alone).

The full timeout-clamp / validation / JSON-shape behavior matrix for
the three wrappers stays in test_a2a_tools_inbox_wrappers.py — those
tests pass identically against both the alias and the underlying impl.

Wiring updates:
  - ``scripts/build_runtime_package.py``: add ``a2a_tools_inbox`` to
    ``TOP_LEVEL_MODULES`` so it ships in the runtime wheel and the
    drift gate doesn't fail the next publish.
  - ``.github/workflows/ci.yml``: add ``a2a_tools_inbox.py`` to
    ``CRITICAL_FILES`` so the 75% MCP/inbox/auth per-file floor
    applies — this is now where the inbox-delivery code actually
    lives.
2026-05-05 14:28:58 -07:00
hongming-personal 1ad107cc15 Merge pull request #2935 from Molecule-AI/fix/onboarding-friction-2934
fix(onboarding): address Claude Code MCP onboarding friction (#2934)
2026-05-05 21:25:57 +00:00
Hongming Wang 01deeb36cf fix(onboarding): address Claude Code MCP onboarding friction (#2934)
Ryan's bug report (#2934) walked through ~45 min of debugging a stock
external-runtime install. This PR fixes the four items he flagged that
have a small surface, and stubs out the larger ones for follow-up.

Fixed in this PR
================

#1 — Python floor disclosure (README in publish bundle)
  Add an explicit "Requires Python ≥3.11" section that calls out the
  cryptic "Could not find a version that satisfies the requirement"
  failure mode; recommend `pipx install` over `pip install` so the
  binary lands on PATH automatically; show the explicit `pip install
  --user` alternative with the PATH caveat.

#3 — MOLECULE_WORKSPACE_TOKEN_FILE support (mcp_workspace_resolver.py)
  Add a third resolution step between the inline env var and the
  in-container CONFIGS_DIR fallback. Operators can write the bearer to
  a 0600 file (e.g. ~/.config/molecule/token) and point
  MOLECULE_WORKSPACE_TOKEN_FILE at it, keeping the secret out of
  ~/.zsh_history and out of plaintext in MCP-host configs like
  ~/.claude.json. Inline TOKEN still wins on conflict so rotation flows
  are predictable. README documents the safer option as the
  recommended path. 6 new tests pin every leg (file resolves, inline
  wins, missing/empty file falls through, blank env unset-equivalent,
  help text advertises it).

#4 — Push delivery 3-condition gating (README in publish bundle)
  Document that real-time push on Claude Code requires (a) the server
  to declare experimental.claude/channel (we do), (b) the server to be
  marketplace-plugin-sourced (operators must scaffold their own until
  the official marketplace lands — see #2934 follow-up), and (c) the
  --dangerously-load-development-channels flag on the claude
  invocation. Until any of the three is in place, delivery silently
  falls back to poll mode with no diagnostic. The README now says all
  of this explicitly so a new operator doesn't grep the binary for
  channel_enable to figure it out.

#8 — serverInfo.name mismatch (a2a_mcp_server.py)
  The server reported `serverInfo.name = "a2a-delegation"` while
  operators register it as `molecule` (the name in `claude mcp add
  molecule …`). Harmless on tool routing today but matters for any
  future Claude Code allowlist that gates push by hardcoded server
  name. Renamed to "molecule" with an inline comment explaining the
  invariant.

Deferred (separate issues to track)
===================================

#2 — covered transitively by #1's pipx recommendation; no separate fix.
#5 — `moleculesai/claude-code-plugin` marketplace repo (substantial new
     repo work; the README references it as a documented follow-up).
#6 — `molecule-mcp doctor` subcommand (substantial new CLI surface;
     mentioned in the README's push-vs-poll section as the planned
     diagnostic for silent push fallback).
#7 — `--dangerously-load-development-channels` rename — not in our
     control; that's Claude Code's flag.

Tests
=====
164/164 mcp_cli + a2a_mcp_server tests pass locally
(WORKSPACE_ID=00000000-0000-0000-0000-000000000001 pytest …) including
6 new TestTokenFileEnv cases. Wheel builds successfully via
scripts/build_runtime_package.py with the new README markers verified
in the output.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-05 14:19:09 -07:00
140 changed files with 14861 additions and 2282 deletions
@@ -0,0 +1,83 @@
name: auto-promote-stale-alarm
# Hourly cron + on-demand alarm for the silent-block failure mode that
# motivated issue #2975:
# - The auto-promote-staging.yml workflow opened a PR + armed
# auto-merge, but main's branch protection requires a human review
# (reviewDecision=REVIEW_REQUIRED). The PR sat BLOCKED with no
# surface-up-the-stack for 12+ hours, holding 25 commits hostage
# including the Memory v2 redesign and a reno-stars data-loss fix.
#
# This workflow runs `scripts/check-stale-promote-pr.sh` against the
# repo's open auto-promote PRs (base=main head=staging). When a PR has
# been BLOCKED on REVIEW_REQUIRED for >4h, it:
# 1. Emits a workflow-level warning (visible in run summary + the
# Actions UI feed).
# 2. Posts a comment on the PR (idempotent — one alarm per PR).
#
# The detection logic lives in scripts/check-stale-promote-pr.sh so
# it's unit-testable with stubbed `gh` (see test-check-stale-promote-pr.sh).
# This file is the schedule + invocation surface only — SSOT for the
# detector itself.
on:
schedule:
# Hourly. Cheap (one `gh pr list` + jq), and 1h granularity is
# plenty for a 4h staleness threshold — operators see the alarm
# within at most 1h of crossing the threshold.
- cron: "27 * * * *" # at :27 to dodge the cron herd at :00
workflow_dispatch:
inputs:
stale_hours:
description: "Hours after which a BLOCKED+REVIEW_REQUIRED PR is stale (default 4)"
required: false
default: "4"
post_comment:
description: "Post a comment on stale PRs (default true)"
required: false
default: "true"
permissions:
contents: read
pull-requests: write # post comments on stale PRs
# Serialize so the on-demand and scheduled runs don't double-comment
# the same PR. cancel-in-progress=false because the script is idempotent
# (existing comment marker prevents dupes), but a scheduled run firing
# while a manual one runs would just re-list the same PR set.
concurrency:
group: auto-promote-stale-alarm
cancel-in-progress: false
jobs:
scan:
runs-on: ubuntu-latest
steps:
- name: Checkout (need scripts/ only)
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
sparse-checkout: |
scripts/check-stale-promote-pr.sh
sparse-checkout-cone-mode: false
- name: Run stale-PR detector
env:
GH_TOKEN: ${{ secrets.GITHUB_TOKEN }}
GITHUB_REPOSITORY: ${{ github.repository }}
STALE_HOURS: ${{ inputs.stale_hours || '4' }}
POST_COMMENT: ${{ inputs.post_comment || 'true' }}
run: |
# The script's exit code reflects the count of stale PRs.
# We don't want a stale finding to fail the workflow run —
# the warning + comment are the signal, the green/red is
# noise. So convert any non-zero exit to a workflow notice
# and exit 0.
set +e
bash scripts/check-stale-promote-pr.sh
rc=$?
set -e
if [ "$rc" -ne 0 ]; then
echo "::notice::Stale PR detector found $rc PR(s) needing attention. See warnings above + comments on the PRs."
fi
# Always succeed — operator-facing surface is the warning,
# not the workflow status.
exit 0
+2 -2
View File
@@ -1,7 +1,7 @@
name: Block internal-flavored paths
# Hard CI gate. Internal content (positioning, competitive briefs, sales
# playbooks, PMM/press drip, draft campaigns) lives in Molecule-AI/internal —
# playbooks, PMM/press drip, draft campaigns) lives in molecule-ai/internal —
# this public monorepo must never re-acquire those paths. CEO directive
# 2026-04-23 after a fleet-wide audit found 79 internal files leaked here.
#
@@ -135,7 +135,7 @@ jobs:
echo "::error::Forbidden internal-flavored paths detected:"
printf "$OFFENDING"
echo ""
echo "These paths belong in Molecule-AI/internal, not this public repo."
echo "These paths belong in molecule-ai/internal, not this public repo."
echo "See docs/internal-content-policy.md for canonical locations."
echo ""
echo "If your file is genuinely public-facing (e.g. a blog post"
+1 -1
View File
@@ -108,7 +108,7 @@ jobs:
echo
echo "One or more canary secrets are unset (\`CANARY_TENANT_URLS\`, \`CANARY_ADMIN_TOKENS\`, \`CANARY_CP_SHARED_SECRET\`)."
echo "Phase 2 canary fleet has not been stood up yet —"
echo "see [canary-tenants.md](https://github.com/Molecule-AI/molecule-controlplane/blob/main/docs/canary-tenants.md)."
echo "see [canary-tenants.md](https://github.com/molecule-ai/molecule-controlplane/blob/main/docs/canary-tenants.md)."
echo
echo "**Skipped — promote-to-latest will NOT auto-fire.** Dispatch \`promote-latest.yml\` manually when ready."
} >> "$GITHUB_STEP_SUMMARY"
+6 -5
View File
@@ -87,7 +87,7 @@ jobs:
run: go mod download
- if: needs.changes.outputs.platform == 'true'
run: go build ./cmd/server
# CLI (molecli) moved to standalone repo: github.com/Molecule-AI/molecule-cli
# CLI (molecli) moved to standalone repo: github.com/molecule-ai/molecule-cli
- if: needs.changes.outputs.platform == 'true'
run: go vet ./... || true
- if: needs.changes.outputs.platform == 'true'
@@ -165,7 +165,7 @@ jobs:
# Strip the package-import prefix so we can match .coverage-allowlist.txt
# entries written as paths relative to workspace-server/.
# Handle both module paths: platform/workspace-server/... and platform/...
rel=$(echo "$file" | sed 's|^github.com/Molecule-AI/molecule-monorepo/platform/workspace-server/||; s|^github.com/Molecule-AI/molecule-monorepo/platform/||')
rel=$(echo "$file" | sed 's|^github.com/molecule-ai/molecule-monorepo/platform/workspace-server/||; s|^github.com/molecule-ai/molecule-monorepo/platform/||')
if echo "$ALLOWLIST" | grep -qxF "$rel"; then
echo "::warning file=workspace-server/$rel::Critical file at ${pct}% coverage (allowlisted, #1823) — fix before expiry."
@@ -243,8 +243,8 @@ jobs:
if-no-files-found: warn
# MCP Server + SDK removed from CI — now in standalone repos:
# - github.com/Molecule-AI/molecule-mcp-server (npm CI)
# - github.com/Molecule-AI/molecule-sdk-python (PyPI CI)
# - github.com/molecule-ai/molecule-mcp-server (npm CI)
# - github.com/molecule-ai/molecule-sdk-python (PyPI CI)
# e2e-api job moved to .github/workflows/e2e-api.yml (issue #458).
# It now has workflow-level concurrency (cancel-in-progress: false) so
@@ -387,6 +387,7 @@ jobs:
"a2a_mcp_server.py"
"mcp_cli.py"
"a2a_tools.py"
"a2a_tools_inbox.py"
"inbox.py"
"platform_auth.py"
)
@@ -433,5 +434,5 @@ jobs:
fi
# SDK + plugin validation moved to standalone repo:
# github.com/Molecule-AI/molecule-sdk-python
# github.com/molecule-ai/molecule-sdk-python
+1 -1
View File
@@ -62,7 +62,7 @@ jobs:
if: matrix.language == 'go'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
repository: Molecule-AI/molecule-ai-plugin-github-app-auth
repository: molecule-ai/molecule-ai-plugin-github-app-auth
path: molecule-ai-plugin-github-app-auth
token: ${{ secrets.PLUGIN_REPO_PAT || secrets.GITHUB_TOKEN }}
@@ -121,8 +121,16 @@ jobs:
# Per-migration result is logged so a failed migration that
# SHOULD have been replayable surfaces in the CI log instead
# of silently failing.
# Apply both *.sql (legacy, lives next to its module) and
# *.up.sql (newer up/down convention) in a single
# lexicographically-sorted pass. Excluding *.down.sql so the
# newest-naming-convention pairs don't undo themselves mid-run.
# Pre-#149-followup this loop only globbed *.up.sql, which
# silently skipped 001_workspaces.sql + 009_activity_logs.sql
# — fine while no integration test depended on those tables,
# not fine once a cross-table atomicity test came in.
set +e
for migration in migrations/*.up.sql; do
for migration in $(ls migrations/*.sql 2>/dev/null | grep -v '\.down\.sql$' | sort); do
if psql -h localhost -U postgres -d molecule -v ON_ERROR_STOP=1 \
-f "$migration" >/dev/null 2>&1; then
echo "✓ $(basename "$migration")"
@@ -132,16 +140,19 @@ jobs:
done
set -e
# Sanity: the delegations table MUST exist for the integration
# tests to be meaningful. Hard-fail if 049 didn't land — that
# would be a real regression we want loud.
if ! psql -h localhost -U postgres -d molecule -tA \
-c "SELECT 1 FROM information_schema.tables WHERE table_name = 'delegations'" \
| grep -q 1; then
echo "::error::delegations table missing after migration replay — handler integration tests would be meaningless"
exit 1
fi
echo "✓ delegations table present"
# Sanity: the delegations + workspaces + activity_logs tables
# MUST exist for the integration tests to be meaningful. Hard-
# fail if any didn't land — that would be a real regression we
# want loud.
for tbl in delegations workspaces activity_logs pending_uploads; do
if ! psql -h localhost -U postgres -d molecule -tA \
-c "SELECT 1 FROM information_schema.tables WHERE table_name = '$tbl'" \
| grep -q 1; then
echo "::error::$tbl table missing after migration replay — handler integration tests would be meaningless"
exit 1
fi
echo "✓ $tbl table present"
done
- if: needs.detect-changes.outputs.handlers == 'true'
name: Run integration tests
+1 -1
View File
@@ -102,7 +102,7 @@ jobs:
if: needs.detect-changes.outputs.run == 'true'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
repository: Molecule-AI/molecule-ai-plugin-github-app-auth
repository: molecule-ai/molecule-ai-plugin-github-app-auth
path: molecule-ai-plugin-github-app-auth
token: ${{ secrets.PLUGIN_REPO_PAT || secrets.GITHUB_TOKEN }}
+1 -1
View File
@@ -19,4 +19,4 @@ permissions:
jobs:
disable-auto-merge-on-push:
uses: Molecule-AI/molecule-ci/.github/workflows/disable-auto-merge-on-push.yml@main
uses: molecule-ai/molecule-ci/.github/workflows/disable-auto-merge-on-push.yml@main
+3 -3
View File
@@ -25,7 +25,7 @@ name: publish-runtime
# 3. Publishes to PyPI via the PyPA Trusted Publisher action (OIDC).
# No static API token is stored — PyPI verifies the workflow's
# OIDC claim against the trusted-publisher config registered for
# molecule-ai-workspace-runtime (Molecule-AI/molecule-core,
# molecule-ai-workspace-runtime (molecule-ai/molecule-core,
# publish-runtime.yml, environment pypi-publish).
#
# After publish: the 8 template repos pick up the new version on their
@@ -166,7 +166,7 @@ jobs:
- name: Publish to PyPI (Trusted Publisher / OIDC)
# PyPI side is configured: project molecule-ai-workspace-runtime →
# publisher Molecule-AI/molecule-core, workflow publish-runtime.yml,
# publisher molecule-ai/molecule-core, workflow publish-runtime.yml,
# environment pypi-publish. The action mints a short-lived OIDC
# token and exchanges it for a PyPI upload credential — no static
# API token in this repo's secrets.
@@ -342,7 +342,7 @@ jobs:
TEMPLATES="claude-code hermes openclaw codex langgraph crewai autogen deepagents gemini-cli"
FAILED=""
for tpl in $TEMPLATES; do
REPO="Molecule-AI/molecule-ai-workspace-template-$tpl"
REPO="molecule-ai/molecule-ai-workspace-template-$tpl"
STATUS=$(curl -sS -o /tmp/dispatch.out -w "%{http_code}" \
-X POST "https://api.github.com/repos/$REPO/dispatches" \
-H "Authorization: Bearer $DISPATCH_TOKEN" \
@@ -80,12 +80,12 @@ jobs:
#
# Uses a fine-grained PAT (PLUGIN_REPO_PAT) because the plugin repo
# is private and the default GITHUB_TOKEN is scoped to THIS repo.
# The PAT needs Contents:Read on Molecule-AI/molecule-ai-plugin-
# The PAT needs Contents:Read on molecule-ai/molecule-ai-plugin-
# github-app-auth. Falls back to the default token for the (rare)
# case where an operator made the plugin repo public.
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
repository: Molecule-AI/molecule-ai-plugin-github-app-auth
repository: molecule-ai/molecule-ai-plugin-github-app-auth
path: molecule-ai-plugin-github-app-auth
token: ${{ secrets.PLUGIN_REPO_PAT || secrets.GITHUB_TOKEN }}
@@ -9,7 +9,7 @@ name: redeploy-tenants-on-main
#
# This workflow closes the gap by calling the control-plane admin
# endpoint that performs a canary-first, batched, health-gated rolling
# redeploy across every live tenant. Implemented in Molecule-AI/
# redeploy across every live tenant. Implemented in molecule-ai/
# molecule-controlplane as POST /cp/admin/tenants/redeploy-fleet
# (feat/tenant-auto-redeploy, landing alongside this workflow).
#
@@ -146,7 +146,7 @@ jobs:
- name: Call CP redeploy-fleet
# CP_ADMIN_API_TOKEN must be set as a repo/org secret on
# Molecule-AI/molecule-core, matching the staging/prod CP's
# molecule-ai/molecule-core, matching the staging/prod CP's
# CP_ADMIN_API_TOKEN env. Stored in Railway, mirrored to this
# repo's secrets for CI.
env:
@@ -97,7 +97,7 @@ jobs:
- name: Call staging-CP redeploy-fleet
# CP_STAGING_ADMIN_API_TOKEN must be set as a repo/org secret
# on Molecule-AI/molecule-core, matching staging-CP's
# on molecule-ai/molecule-core, matching staging-CP's
# CP_ADMIN_API_TOKEN env var (visible in Railway controlplane
# / staging environment). Stored separately from the prod
# CP_ADMIN_API_TOKEN so a leak of one doesn't auth the other.
@@ -96,7 +96,7 @@ jobs:
--body "$(cat <<'BODY'
[retarget-bot] This PR was opened against `main` and has been retargeted to `staging` automatically.
**Why:** per [SHARED_RULES rule 8](https://github.com/Molecule-AI/molecule-ai-org-template-molecule-dev/blob/main/SHARED_RULES.md), all feature work targets `staging` first; the CEO promotes `staging → main` separately.
**Why:** per [SHARED_RULES rule 8](https://github.com/molecule-ai/molecule-ai-org-template-molecule-dev/blob/main/SHARED_RULES.md), all feature work targets `staging` first; the CEO promotes `staging → main` separately.
**What changed:** just the base branch — no code change. CI will re-run against `staging`. If you get merge conflicts, rebase on `staging`.
+1 -1
View File
@@ -12,7 +12,7 @@ name: Secret scan
#
# jobs:
# secret-scan:
# uses: Molecule-AI/molecule-core/.github/workflows/secret-scan.yml@staging
# uses: molecule-ai/molecule-core/.github/workflows/secret-scan.yml@staging
#
# Pin to @staging not @main — staging is the active default branch,
# main lags via the staging-promotion workflow. Updates ride along
+49 -1
View File
@@ -108,6 +108,14 @@ jobs:
python3 > stale_slugs.txt <<'PY'
import json, os
from datetime import datetime, timezone, timedelta
# SSOT for this list lives in the controlplane Go code:
# molecule-controlplane/internal/slugs/ephemeral.go
# (var EphemeralPrefixes). The redeploy-fleet auto-rollout
# also reads from there to SKIP these slugs — without that
# filter, fleet redeploy SSM-failed in-flight E2E tenants
# whose containers were still booting, breaking the test
# that just spun them up (molecule-controlplane#493).
# Update both files together.
EPHEMERAL_PREFIXES = ("e2e-", "rt-e2e-")
with open("orgs.json") as f:
data = json.load(f)
@@ -185,7 +193,47 @@ jobs:
# sweeper is best-effort. Next hourly tick re-attempts. We
# only fail loud at the safety-cap gate above.
- name: Sweep orphan tunnels
# Stale-org cleanup deletes the org (which cascades to tunnel
# delete inside the CP). But when that cascade fails partway —
# CP transient 5xx after the org row is deleted but before the
# CF tunnel delete completes — the tunnel persists with no
# matching org row. The reconciler in internal/sweep flags this
# as `cf_tunnel kind=orphan`, but nothing automatically reaps it.
#
# `/cp/admin/orphan-tunnels/cleanup` is the operator-triggered
# reaper. Calling it here at the end of every sweep tick
# converges the staging CF account to clean even when CP
# cascades half-fail.
#
# PR #492 made the underlying DeleteTunnel actually check
# status — pre-fix it silent-succeeded on CF code 1022
# ("active connections"), so this step would have been a no-op
# against stuck connectors. Post-fix the cleanup invokes
# CleanupTunnelConnections + retry, which actually clears the
# 1022 case. (#2987)
#
# Best-effort. Failure here doesn't fail the workflow — next
# tick re-attempts. Errors flow to step output for ops review.
if: env.DRY_RUN != 'true'
run: |
set +e
curl -sS -o /tmp/cleanup_resp -w "%{http_code}" \
--max-time 60 \
-X POST "$MOLECULE_CP_URL/cp/admin/orphan-tunnels/cleanup" \
-H "Authorization: Bearer $ADMIN_TOKEN" >/tmp/cleanup_code
set -e
http_code=$(cat /tmp/cleanup_code 2>/dev/null || echo "000")
body=$(cat /tmp/cleanup_resp 2>/dev/null | head -c 500)
if [ "$http_code" = "200" ]; then
count=$(echo "$body" | python3 -c "import sys,json; d=json.loads(sys.stdin.read() or '{}'); print(d.get('deleted_count', 0))" 2>/dev/null || echo "0")
failed_n=$(echo "$body" | python3 -c "import sys,json; d=json.loads(sys.stdin.read() or '{}'); print(len(d.get('failed') or {}))" 2>/dev/null || echo "0")
echo "Orphan-tunnel sweep: deleted=$count failed=$failed_n"
else
echo "::warning::orphan-tunnels cleanup returned HTTP $http_code — body: $body"
fi
- name: Dry-run summary
if: env.DRY_RUN == 'true'
run: |
echo "DRY RUN — would have deleted ${{ steps.identify.outputs.count }} org(s). Re-run with dry_run=false to actually delete."
echo "DRY RUN — would have deleted ${{ steps.identify.outputs.count }} org(s) AND triggered orphan-tunnels cleanup. Re-run with dry_run=false to actually delete."
@@ -1,261 +0,0 @@
'use client';
import { useEffect, useRef, useState } from "react";
import { createPortal } from "react-dom";
import { api } from "@/lib/api";
import type { MemoryEntry } from "@/components/MemoryInspectorPanel";
type Scope = "LOCAL" | "TEAM" | "GLOBAL";
const SCOPES: Scope[] = ["LOCAL", "TEAM", "GLOBAL"];
interface AddProps {
open: boolean;
mode: "add";
workspaceId: string;
defaultScope: Scope;
defaultNamespace?: string;
entry?: undefined;
onClose: () => void;
onSaved: () => void;
}
interface EditProps {
open: boolean;
mode: "edit";
workspaceId: string;
entry: MemoryEntry;
defaultScope?: undefined;
defaultNamespace?: undefined;
onClose: () => void;
onSaved: () => void;
}
type Props = AddProps | EditProps;
export function MemoryEditorDialog(props: Props) {
const { open, mode, workspaceId, onClose, onSaved } = props;
const dialogRef = useRef<HTMLDivElement>(null);
const [mounted, setMounted] = useState(false);
const [scope, setScope] = useState<Scope>("LOCAL");
const [namespace, setNamespace] = useState("general");
const [content, setContent] = useState("");
const [saving, setSaving] = useState(false);
const [error, setError] = useState<string | null>(null);
useEffect(() => {
setMounted(true);
}, []);
// Reset form whenever the dialog opens.
useEffect(() => {
if (!open) return;
setError(null);
setSaving(false);
if (mode === "edit" && props.entry) {
setScope(props.entry.scope);
setNamespace(props.entry.namespace || "general");
setContent(props.entry.content);
} else if (mode === "add") {
setScope(props.defaultScope);
setNamespace(props.defaultNamespace || "general");
setContent("");
}
// mode/props are stable per-open; intentional shallow deps.
// eslint-disable-next-line react-hooks/exhaustive-deps
}, [open]);
// Move focus into the dialog when it opens (WCAG SC 2.4.3).
useEffect(() => {
if (!open || !mounted) return;
const raf = requestAnimationFrame(() => {
dialogRef.current?.querySelector<HTMLElement>("textarea, input, select")?.focus();
});
return () => cancelAnimationFrame(raf);
}, [open, mounted]);
// Escape closes; Cmd/Ctrl-Enter saves.
const onCloseRef = useRef(onClose);
onCloseRef.current = onClose;
const handleSaveRef = useRef<() => void>(() => {});
useEffect(() => {
if (!open) return;
const handler = (e: KeyboardEvent) => {
if (e.key === "Escape") {
e.preventDefault();
onCloseRef.current();
} else if (e.key === "Enter" && (e.metaKey || e.ctrlKey)) {
e.preventDefault();
handleSaveRef.current();
}
};
window.addEventListener("keydown", handler);
return () => window.removeEventListener("keydown", handler);
}, [open]);
const handleSave = async () => {
if (saving) return;
const trimmed = content.trim();
if (!trimmed) {
setError("Content cannot be empty");
return;
}
setError(null);
setSaving(true);
try {
if (mode === "add") {
await api.post(`/workspaces/${workspaceId}/memories`, {
content: trimmed,
scope,
namespace: namespace.trim() || "general",
});
} else {
// PATCH only sends fields that changed. Content always changeable;
// namespace only sent if it differs from the original (saves a
// no-op write through redactSecrets + re-embed).
const original = props.entry;
const body: Record<string, string> = {};
if (trimmed !== original.content) body.content = trimmed;
const ns = namespace.trim() || "general";
if (ns !== original.namespace) body.namespace = ns;
if (Object.keys(body).length === 0) {
// No-op edit — close without an HTTP round-trip.
onSaved();
onClose();
return;
}
await api.patch(
`/workspaces/${workspaceId}/memories/${encodeURIComponent(original.id)}`,
body,
);
}
onSaved();
onClose();
} catch (e) {
setError(e instanceof Error ? e.message : "Save failed");
} finally {
setSaving(false);
}
};
handleSaveRef.current = handleSave;
if (!open || !mounted) return null;
const titleId = "memory-editor-title";
const isEdit = mode === "edit";
return createPortal(
<div className="fixed inset-0 z-[9999] flex items-center justify-center">
<div className="absolute inset-0 bg-black/60 backdrop-blur-sm" onClick={onClose} />
<div
ref={dialogRef}
role="dialog"
aria-modal="true"
aria-labelledby={titleId}
className="relative bg-surface-sunken border border-line rounded-xl shadow-2xl shadow-black/50 max-w-[480px] w-full mx-4 overflow-hidden"
>
<div className="px-5 py-4 space-y-3">
<h3 id={titleId} className="text-sm font-semibold text-ink">
{isEdit ? "Edit memory" : "Add memory"}
</h3>
{/* Scope */}
<div className="space-y-1">
<label className="text-[10px] text-ink-soft block" htmlFor="memory-editor-scope">
Scope
</label>
{isEdit ? (
<div
id="memory-editor-scope"
className="text-[12px] font-mono text-ink-mid bg-surface rounded px-2 py-1.5 border border-line/50"
title="Scope is fixed on edit. To move a memory across scopes, delete and re-create it."
>
{scope}
</div>
) : (
<div className="flex items-center gap-1" id="memory-editor-scope" role="radiogroup" aria-label="Scope">
{SCOPES.map((s) => (
<button
key={s}
type="button"
role="radio"
aria-checked={scope === s}
onClick={() => setScope(s)}
className={[
"px-3 py-1 text-[11px] rounded transition-colors",
scope === s
? "bg-accent-strong text-white"
: "bg-surface-card text-ink-mid hover:text-ink",
].join(" ")}
>
{s}
</button>
))}
</div>
)}
</div>
{/* Namespace */}
<div className="space-y-1">
<label htmlFor="memory-editor-namespace" className="text-[10px] text-ink-soft block">
Namespace
</label>
<input
id="memory-editor-namespace"
type="text"
value={namespace}
onChange={(e) => setNamespace(e.target.value)}
placeholder="general"
className="w-full bg-surface border border-line/60 focus:border-accent/60 rounded px-2 py-1.5 text-[12px] text-ink placeholder-zinc-600 focus:outline-none transition-colors"
/>
</div>
{/* Content */}
<div className="space-y-1">
<label htmlFor="memory-editor-content" className="text-[10px] text-ink-soft block">
Content
</label>
<textarea
id="memory-editor-content"
value={content}
onChange={(e) => setContent(e.target.value)}
rows={6}
placeholder="What should the agent remember?"
className="w-full bg-surface border border-line/60 focus:border-accent/60 rounded px-2 py-1.5 text-[12px] font-mono text-ink placeholder-zinc-600 focus:outline-none transition-colors resize-y min-h-[100px] max-h-[300px]"
/>
</div>
{error && (
<div
role="alert"
aria-live="assertive"
className="px-2 py-1.5 bg-red-950/30 border border-red-800/40 rounded text-[11px] text-bad"
>
{error}
</div>
)}
</div>
<div className="flex items-center justify-end gap-2 px-5 py-3 border-t border-line bg-surface/50">
<button
type="button"
onClick={onClose}
disabled={saving}
className="px-3.5 py-1.5 text-[13px] text-ink-mid hover:text-ink bg-surface-card hover:bg-surface-elevated border border-line hover:border-line-soft rounded-lg transition-colors focus:outline-none focus-visible:ring-2 focus-visible:ring-accent/40 disabled:opacity-50 disabled:cursor-not-allowed"
>
Cancel
</button>
<button
type="button"
onClick={handleSave}
disabled={saving}
className="px-3.5 py-1.5 text-[13px] rounded-lg transition-colors bg-accent hover:bg-accent-strong text-white focus:outline-none focus-visible:ring-2 focus-visible:ring-offset-2 focus-visible:ring-offset-surface-sunken focus-visible:ring-accent/60 disabled:opacity-50 disabled:cursor-not-allowed"
>
{saving ? "Saving…" : isEdit ? "Save changes" : "Add memory"}
</button>
</div>
</div>
</div>,
document.body,
);
}
+382 -229
View File
@@ -1,30 +1,81 @@
'use client';
import { useState, useEffect, useCallback } from "react";
import { api } from "@/lib/api";
import { ConfirmDialog } from "@/components/ConfirmDialog";
import { MemoryEditorDialog } from "@/components/MemoryEditorDialog";
/**
* MemoryInspectorPanel — Memory v2 redesign.
*
* Reads the canvas Memory tab from the v2 plugin via the
* workspace-server proxy at /v2/{namespaces,memories}, replacing the
* v1 LOCAL/TEAM/GLOBAL trio that mapped to the deprecated
* shared_context model.
*
* Surface differences from v1:
* - Namespace dropdown driven by GET /v2/namespaces (workspace /
* team / org / custom — labels rendered server-side).
* - Per-row badges for kind (fact|summary|checkpoint), source
* (agent|runtime|user), pin (📌), TTL countdown, and propagation
* source-workspace if the memory came from a peer.
* - No Edit affordance — v2's plugin contract has no PATCH; the
* model is forget + recommit. Delete (Forget) stays.
*
* Shipping note: when the plugin isn't wired (MEMORY_PLUGIN_URL
* unset), every endpoint returns 503 with a clear hint. The panel
* surfaces that as a banner so operators know to set the env var,
* rather than rendering a perpetual empty state that looks like
* "no memories yet".
*/
import { useCallback, useEffect, useMemo, useState } from 'react';
import { api } from '@/lib/api';
import { ConfirmDialog } from '@/components/ConfirmDialog';
// ── Types ─────────────────────────────────────────────────────────────────────
/** Memory entry returned by GET /workspaces/:id/memories */
export interface MemoryEntry {
id: string;
workspace_id: string;
content: string;
scope: "LOCAL" | "TEAM" | "GLOBAL";
namespace: string;
created_at: string;
/**
* Semantic similarity score (01). Only present when the API is queried
* with ?q=<query> and the pgvector backend has been deployed.
* Absent on plain list fetches — renders gracefully without a badge.
*/
similarity_score?: number;
export type NamespaceKind = 'workspace' | 'team' | 'org' | 'custom';
export interface NamespaceView {
name: string;
kind: NamespaceKind;
label: string;
}
type Scope = "LOCAL" | "TEAM" | "GLOBAL";
const SCOPES: Scope[] = ["LOCAL", "TEAM", "GLOBAL"];
export interface NamespacesResponse {
readable: NamespaceView[];
writable: NamespaceView[];
}
export type MemoryKind = 'fact' | 'summary' | 'checkpoint';
export type MemorySource = 'agent' | 'runtime' | 'user';
export interface MemoryV2 {
id: string;
namespace: string;
content: string;
kind: MemoryKind;
source: MemorySource;
pin: boolean;
expires_at?: string | null;
created_at: string;
/** 0..1 plugin similarity score; only present when ?q= is set. */
score?: number | null;
// Note: an earlier iteration of this type carried a `source_workspace_id`
// field rendered as a "from peer" badge. The propagation contract that
// would have populated it ("Reserved for future cross-namespace
// propagation semantics" in memory-plugin-v1.yaml) is unimplemented —
// nothing in the codebase writes that key. Removed in self-review.
// Re-add when propagation gains a concrete shape.
}
interface MemoriesResponse {
memories: MemoryV2[];
}
// MemoryEntry kept as a back-compat type alias so any other component
// still importing it doesn't break the build. New consumers should
// prefer MemoryV2 — the v1 shape (LOCAL/TEAM/GLOBAL scope) is gone.
//
// `unknown` is used over `any` so TS still flags accidental field
// access on the legacy shape.
export type MemoryEntry = MemoryV2;
interface Props {
workspaceId: string;
@@ -32,11 +83,26 @@ interface Props {
// ── Helpers ───────────────────────────────────────────────────────────────────
/**
* Sanitise a memory id for use in an HTML id attribute.
*/
function sanitizeId(id: string): string {
return id.replace(/[^a-zA-Z0-9]/g, "-");
return id.replace(/[^a-zA-Z0-9]/g, '-');
}
/**
* Detect a memory-plugin-503 error from the api wrapper's stringified
* Error message. Matches on the literal env-var name rather than the
* status code, because the api shim renders status codes inside a
* larger formatted message and a future status-code reformat would
* silently break the detection.
*
* The substring `MEMORY_PLUGIN_URL` is hard-coded in the handler at
* `workspace-server/internal/handlers/memories_v2.go:available()`,
* so this is a pinned cross-layer contract — drift is caught by both
* the Go test (TestMemoriesV2_PluginUnwired_All503) and the canvas
* test (TestMemoryInspectorPanel — plugin unavailable).
*/
export function isPluginUnavailableError(err: unknown): boolean {
const msg = err instanceof Error ? err.message : '';
return msg.includes('MEMORY_PLUGIN_URL');
}
function formatRelativeTime(iso: string): string {
@@ -47,6 +113,24 @@ function formatRelativeTime(iso: string): string {
return new Date(iso).toLocaleDateString();
}
/**
* Render a TTL countdown like "12h", "3d", or "expired" (when the
* stored expires_at is in the past). Non-fatal if expires_at is null
* or invalid — falls through to empty string so the badge doesn't
* render.
*/
export function formatTTL(expiresAt: string | null | undefined): string {
if (!expiresAt) return '';
const ts = new Date(expiresAt).getTime();
if (Number.isNaN(ts)) return '';
const diff = ts - Date.now();
if (diff <= 0) return 'expired';
if (diff < 60_000) return `${Math.floor(diff / 1000)}s`;
if (diff < 3_600_000) return `${Math.floor(diff / 60_000)}m`;
if (diff < 86_400_000) return `${Math.floor(diff / 3_600_000)}h`;
return `${Math.floor(diff / 86_400_000)}d`;
}
// ── Skeleton rows ──────────────────────────────────────────────────────────────
function MemorySkeletonRows() {
@@ -71,63 +155,92 @@ function MemorySkeletonRows() {
// ── Component ─────────────────────────────────────────────────────────────────
const ALL_NAMESPACES = '__all__';
export function MemoryInspectorPanel({ workspaceId }: Props) {
const [activeScope, setActiveScope] = useState<Scope>("LOCAL");
const [activeNamespace, setActiveNamespace] = useState("");
const [entries, setEntries] = useState<MemoryEntry[]>([]);
const [namespaces, setNamespaces] = useState<NamespacesResponse | null>(null);
const [activeNamespace, setActiveNamespace] = useState<string>(ALL_NAMESPACES);
const [entries, setEntries] = useState<MemoryV2[]>([]);
const [loading, setLoading] = useState(true);
const [error, setError] = useState<string | null>(null);
// ── Search state (debounced) ────────────────────────────────────────────────
const [searchQuery, setSearchQuery] = useState("");
const [debouncedQuery, setDebouncedQuery] = useState("");
// Plugin-disabled banner (503 from server). Stored separately so we
// can keep showing the namespace dropdown empty rather than
// hiding the whole panel.
const [pluginUnavailable, setPluginUnavailable] = useState(false);
// Search state (debounced)
const [searchQuery, setSearchQuery] = useState('');
const [debouncedQuery, setDebouncedQuery] = useState('');
useEffect(() => {
const timer = setTimeout(
() => setDebouncedQuery(searchQuery.trim()),
300
);
const timer = setTimeout(() => setDebouncedQuery(searchQuery.trim()), 300);
return () => clearTimeout(timer);
}, [searchQuery]);
// ── Delete state ─────────────────────────────────────────────────────────────
// Delete state
const [pendingDeleteId, setPendingDeleteId] = useState<string | null>(null);
// ── Editor state (Add + Edit share one modal) ───────────────────────────────
type EditorState =
| { mode: "add" }
| { mode: "edit"; entry: MemoryEntry }
| null;
const [editorState, setEditorState] = useState<EditorState>(null);
// ── Namespace loading ──────────────────────────────────────────────────────
// ── Data loading ────────────────────────────────────────────────────────────
const loadNamespaces = useCallback(async () => {
try {
const data = await api.get<NamespacesResponse>(
`/workspaces/${workspaceId}/v2/namespaces`,
);
setNamespaces(data);
setPluginUnavailable(false);
} catch (e) {
// Plugin-unavailable (503) indicates MEMORY_PLUGIN_URL isn't set.
// Anything else stays as a generic load failure that the
// entries-load path will also flag.
if (isPluginUnavailableError(e)) {
setPluginUnavailable(true);
}
setNamespaces({ readable: [], writable: [] });
}
}, [workspaceId]);
// ── Entries loading ────────────────────────────────────────────────────────
const loadEntries = useCallback(async () => {
setLoading(true);
setError(null);
try {
const params = new URLSearchParams();
params.set("scope", activeScope);
if (debouncedQuery) params.set("q", debouncedQuery);
if (activeNamespace) params.set("namespace", activeNamespace);
if (activeNamespace !== ALL_NAMESPACES) {
params.set('namespace', activeNamespace);
}
if (debouncedQuery) params.set('q', debouncedQuery);
const url = `/workspaces/${workspaceId}/memories?${params.toString()}`;
const data = await api.get<MemoryEntry[]>(url);
const url = `/workspaces/${workspaceId}/v2/memories?${params.toString()}`;
const data = await api.get<MemoriesResponse>(url);
// When a semantic query is active, sort by similarity_score descending.
// When a semantic query is active and the plugin returns
// scores, sort by score descending so the most-relevant hit
// sits at the top. Empty score → push to bottom.
const sorted = debouncedQuery
? [...data].sort(
(a, b) => (b.similarity_score ?? 0) - (a.similarity_score ?? 0)
? [...data.memories].sort(
(a, b) => (b.score ?? 0) - (a.score ?? 0),
)
: data;
: data.memories;
setEntries(sorted);
} catch (e) {
setError(e instanceof Error ? e.message : "Failed to load memories");
if (isPluginUnavailableError(e)) {
setPluginUnavailable(true);
setError(null); // surfaced via banner, not row error
} else {
setError(e instanceof Error ? e.message : 'Failed to load memories');
}
setEntries([]);
} finally {
setLoading(false);
}
}, [workspaceId, activeScope, debouncedQuery, activeNamespace]);
}, [workspaceId, activeNamespace, debouncedQuery]);
useEffect(() => {
loadNamespaces();
}, [loadNamespaces]);
useEffect(() => {
loadEntries();
@@ -144,16 +257,35 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
setEntries((prev) => prev.filter((e) => e.id !== id));
try {
await api.del(`/workspaces/${workspaceId}/memories/${encodeURIComponent(id)}`);
await api.del(`/workspaces/${workspaceId}/v2/memories/${encodeURIComponent(id)}`);
} catch (e) {
setError(e instanceof Error ? e.message : "Delete failed — reloading...");
// Reload first (which clears any stale error), THEN set the
// delete-failure message — otherwise loadEntries' own
// `setError(null)` wipes our error before the user sees it.
// Caught by the rollback test in MemoryInspectorPanel.test.tsx.
const msg = e instanceof Error ? e.message : 'Delete failed — reloading…';
await loadEntries();
setError(msg);
}
}, [pendingDeleteId, workspaceId, loadEntries]);
// ── Namespace dropdown options ─────────────────────────────────────────────
const dropdownOptions = useMemo(() => {
const opts: Array<{ value: string; label: string; kind?: NamespaceKind }> = [
{ value: ALL_NAMESPACES, label: 'All namespaces' },
];
if (namespaces) {
for (const ns of namespaces.readable) {
opts.push({ value: ns.name, label: ns.label, kind: ns.kind });
}
}
return opts;
}, [namespaces]);
// ── Render ──────────────────────────────────────────────────────────────────
if (loading && entries.length === 0 && !error) {
if (loading && entries.length === 0 && !error && !pluginUnavailable) {
return (
<div className="flex items-center justify-center h-32">
<span className="text-xs text-ink-soft">Loading memories</span>
@@ -163,32 +295,43 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
return (
<div className="flex flex-col h-full">
{/* Scope tabs */}
<div className="px-4 pt-3 pb-2 border-b border-line/40 shrink-0">
<div className="flex items-center gap-1">
{SCOPES.map((scope) => (
<button
type="button"
key={scope}
onClick={() => setActiveScope(scope)}
aria-pressed={activeScope === scope}
className={[
"px-3 py-1 text-[11px] rounded transition-colors",
activeScope === scope
? "bg-accent-strong text-white"
: "bg-surface-card text-ink-mid hover:bg-surface-card hover:text-ink",
].join(" ")}
>
{scope}
</button>
))}
{/* Plugin-unavailable banner */}
{pluginUnavailable && (
<div
role="alert"
aria-live="polite"
className="mx-4 mt-3 px-3 py-2 bg-amber-950/30 border border-amber-800/40 rounded text-xs text-amber-300 shrink-0"
data-testid="plugin-unavailable-banner"
>
Memory plugin not configured. Set <code>MEMORY_PLUGIN_URL</code> on the
workspace-server to enable v2 memory.
</div>
</div>
)}
{/* Search bar + namespace filter */}
{/* Namespace dropdown */}
<div className="px-4 pt-3 pb-2 border-b border-line/40 shrink-0 space-y-2">
<div className="flex items-center gap-2">
<label htmlFor="namespace-dropdown" className="text-[10px] text-ink-soft shrink-0">
Namespace:
</label>
<select
id="namespace-dropdown"
value={activeNamespace}
onChange={(e) => setActiveNamespace(e.target.value)}
aria-label="Filter by namespace"
disabled={pluginUnavailable}
className="flex-1 bg-surface-sunken border border-line/60 focus:border-accent/60 rounded px-2 py-1 text-[11px] text-ink focus:outline-none transition-colors min-w-0 disabled:opacity-50 disabled:cursor-not-allowed"
>
{dropdownOptions.map((opt) => (
<option key={opt.value} value={opt.value}>
{opt.label}
</option>
))}
</select>
</div>
{/* Search bar */}
<div className="relative flex items-center">
{/* Magnifying glass icon */}
<svg
width="12"
height="12"
@@ -206,14 +349,15 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
onChange={(e) => setSearchQuery(e.target.value)}
placeholder="Semantic search…"
aria-label="Search memories"
className="w-full bg-surface-sunken border border-line/60 focus:border-accent/60 rounded-lg pl-8 pr-7 py-1.5 text-[11px] text-ink placeholder-zinc-600 focus:outline-none transition-colors"
disabled={pluginUnavailable}
className="w-full bg-surface-sunken border border-line/60 focus:border-accent/60 rounded-lg pl-8 pr-7 py-1.5 text-[11px] text-ink placeholder-zinc-600 focus:outline-none transition-colors disabled:opacity-50 disabled:cursor-not-allowed"
/>
{searchQuery && (
<button
type="button"
onClick={() => {
setSearchQuery("");
setDebouncedQuery("");
setSearchQuery('');
setDebouncedQuery('');
}}
aria-label="Clear search"
className="absolute right-2 text-ink-soft hover:text-ink transition-colors text-sm leading-none"
@@ -222,51 +366,26 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
</button>
)}
</div>
{/* Namespace filter */}
<div className="flex items-center gap-2">
<label htmlFor="namespace-filter" className="text-[10px] text-ink-soft shrink-0">
Namespace:
</label>
<input
id="namespace-filter"
type="text"
value={activeNamespace}
onChange={(e) => setActiveNamespace(e.target.value)}
placeholder="all namespaces"
aria-label="Filter by namespace"
className="flex-1 bg-surface-sunken border border-line/60 focus:border-accent/60 rounded px-2 py-1 text-[11px] text-ink placeholder-zinc-600 focus:outline-none transition-colors min-w-0"
/>
</div>
</div>
{/* Toolbar */}
<div className="px-4 py-2.5 border-b border-line/40 flex items-center justify-between shrink-0">
<span className="text-[11px] text-ink-soft">
{debouncedQuery
? `${entries.length} result${entries.length !== 1 ? "s" : ""}`
? `${entries.length} result${entries.length !== 1 ? 's' : ''}`
: entries.length === 1
? "1 memory"
: `${entries.length} memories`}
? '1 memory'
: `${entries.length} memories`}
</span>
<div className="flex items-center gap-1.5">
<button
type="button"
onClick={() => setEditorState({ mode: "add" })}
className="px-2 py-1 text-[11px] bg-accent hover:bg-accent-strong text-white rounded transition-colors"
aria-label="Add memory"
>
+ Add
</button>
<button
type="button"
onClick={loadEntries}
className="px-2 py-1 text-[11px] bg-surface-card hover:bg-surface-card text-ink-mid rounded transition-colors"
aria-label="Refresh memories"
>
Refresh
</button>
</div>
<button
type="button"
onClick={loadEntries}
disabled={pluginUnavailable}
className="px-2 py-1 text-[11px] bg-surface-card hover:bg-surface-card text-ink-mid rounded transition-colors disabled:opacity-50 disabled:cursor-not-allowed"
aria-label="Refresh memories"
>
Refresh
</button>
</div>
{/* Error banner */}
@@ -285,47 +404,13 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
{loading ? (
<MemorySkeletonRows />
) : entries.length === 0 ? (
debouncedQuery ? (
<div className="flex flex-col items-center justify-center py-16 gap-3 text-center">
<span className="text-4xl text-ink-soft" aria-hidden="true"></span>
<p className="text-sm font-medium text-ink-mid">
No memories match your search
</p>
<p className="text-[11px] text-ink-soft max-w-[200px] leading-relaxed">
Try a different query or{" "}
<button
type="button"
onClick={() => {
setSearchQuery("");
setDebouncedQuery("");
}}
className="text-accent hover:text-accent underline transition-colors"
>
clear the search
</button>
.
</p>
</div>
) : (
<div className="flex flex-col items-center justify-center py-16 gap-3 text-center">
<span className="text-4xl text-ink-soft" aria-hidden="true"></span>
<p className="text-sm font-medium text-ink-mid">No {activeScope} memories</p>
<p className="text-[11px] text-ink-soft max-w-[200px] leading-relaxed">
{activeScope === "LOCAL"
? "This workspace has not written any local memories yet."
: activeScope === "TEAM"
? "No team memories shared with this workspace yet."
: "No global memories exist yet."}
</p>
</div>
)
<EmptyState query={debouncedQuery} pluginUnavailable={pluginUnavailable} />
) : (
<div className="space-y-1.5">
{entries.map((entry) => (
<MemoryEntryRow
key={entry.id}
entry={entry}
onEdit={() => setEditorState({ mode: "edit", entry })}
onDelete={() => setPendingDeleteId(entry.id)}
/>
))}
@@ -336,36 +421,64 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
{/* Delete confirmation dialog */}
<ConfirmDialog
open={pendingDeleteId !== null}
title="Delete memory"
message={`Delete this ${activeScope} memory? This cannot be undone.`}
confirmLabel="Delete"
title="Forget memory"
message="Forget this memory? This cannot be undone."
confirmLabel="Forget"
confirmVariant="danger"
onConfirm={confirmDelete}
onCancel={() => setPendingDeleteId(null)}
/>
</div>
);
}
{/* Add / Edit dialog */}
{editorState?.mode === "add" && (
<MemoryEditorDialog
open={true}
mode="add"
workspaceId={workspaceId}
defaultScope={activeScope}
defaultNamespace={activeNamespace || "general"}
onClose={() => setEditorState(null)}
onSaved={loadEntries}
/>
)}
{editorState?.mode === "edit" && (
<MemoryEditorDialog
open={true}
mode="edit"
workspaceId={workspaceId}
entry={editorState.entry}
onClose={() => setEditorState(null)}
onSaved={loadEntries}
/>
)}
// ── Empty state ─────────────────────────────────────────────────────────────
function EmptyState({
query,
pluginUnavailable,
}: {
query: string;
pluginUnavailable: boolean;
}) {
if (pluginUnavailable) {
// The banner already explains the problem; the empty rows just
// mirror it so the operator sees both signals.
return (
<div className="flex flex-col items-center justify-center py-16 gap-3 text-center">
<span className="text-4xl text-ink-soft" aria-hidden="true">
</span>
<p className="text-sm font-medium text-ink-mid">Memory plugin disabled</p>
<p className="text-[11px] text-ink-soft max-w-[220px] leading-relaxed">
See banner above for the operator-side fix.
</p>
</div>
);
}
if (query) {
return (
<div className="flex flex-col items-center justify-center py-16 gap-3 text-center">
<span className="text-4xl text-ink-soft" aria-hidden="true">
</span>
<p className="text-sm font-medium text-ink-mid">No memories match your search</p>
<p className="text-[11px] text-ink-soft max-w-[200px] leading-relaxed">
Try a different query or clear the search.
</p>
</div>
);
}
return (
<div className="flex flex-col items-center justify-center py-16 gap-3 text-center">
<span className="text-4xl text-ink-soft" aria-hidden="true">
</span>
<p className="text-sm font-medium text-ink-mid">No memories yet</p>
<p className="text-[11px] text-ink-soft max-w-[220px] leading-relaxed">
Agents commit memories via MCP tools (commit_memory, commit_summary). They
appear here once written.
</p>
</div>
);
}
@@ -373,17 +486,32 @@ export function MemoryInspectorPanel({ workspaceId }: Props) {
// ── MemoryEntryRow sub-component ──────────────────────────────────────────────
interface MemoryEntryRowProps {
entry: MemoryEntry;
onEdit: () => void;
entry: MemoryV2;
onDelete: () => void;
}
function MemoryEntryRow({ entry, onEdit, onDelete }: MemoryEntryRowProps) {
const KIND_BADGE_CLASS: Record<MemoryKind, string> = {
fact: 'bg-surface-card text-ink-mid',
summary: 'bg-blue-950 text-accent',
checkpoint: 'bg-violet-950 text-violet-400',
};
const SOURCE_BADGE_CLASS: Record<MemorySource, string> = {
agent: 'bg-surface-card text-ink-mid',
runtime: 'bg-amber-950 text-amber-300',
user: 'bg-emerald-950 text-emerald-400',
};
function MemoryEntryRow({ entry, onDelete }: MemoryEntryRowProps) {
const [expanded, setExpanded] = useState(false);
const bodyId = `mem-body-${sanitizeId(entry.id)}`;
const ttl = formatTTL(entry.expires_at);
return (
<div className="rounded-lg border border-line/60 bg-surface-sunken/50 overflow-hidden">
<div
className="rounded-lg border border-line/60 bg-surface-sunken/50 overflow-hidden"
data-testid={`memory-row-${entry.id}`}
>
{/* Header row */}
<button
type="button"
@@ -392,52 +520,89 @@ function MemoryEntryRow({ entry, onEdit, onDelete }: MemoryEntryRowProps) {
aria-expanded={expanded}
aria-controls={bodyId}
>
{/* Scope badge */}
{/* Kind badge */}
<span
className={[
"text-[9px] shrink-0 font-mono px-1 py-0.5 rounded",
entry.scope === "LOCAL"
? "bg-surface-card text-ink-mid"
: entry.scope === "TEAM"
? "bg-blue-950 text-accent"
: "bg-violet-950 text-violet-400",
].join(" ")}
title={`Scope: ${entry.scope}`}
'text-[9px] shrink-0 font-mono px-1 py-0.5 rounded',
KIND_BADGE_CLASS[entry.kind] ?? 'bg-surface-card text-ink-mid',
].join(' ')}
title={`Kind: ${entry.kind}`}
data-testid="kind-badge"
>
{entry.scope[0]}
{entry.kind[0].toUpperCase()}
</span>
{/* Source badge */}
<span
className={[
'text-[9px] shrink-0 font-mono px-1 py-0.5 rounded',
SOURCE_BADGE_CLASS[entry.source] ?? 'bg-surface-card text-ink-mid',
].join(' ')}
title={`Source: ${entry.source}`}
data-testid="source-badge"
>
{entry.source}
</span>
{/* Pin indicator */}
{entry.pin && (
<span
className="text-[9px] shrink-0"
title="Pinned"
data-testid="pin-badge"
aria-label="Pinned"
>
📌
</span>
)}
{/* Namespace tag */}
<span className="text-[9px] shrink-0 font-mono text-ink-soft truncate max-w-[80px]" title={entry.namespace}>
<span
className="text-[9px] shrink-0 font-mono text-ink-soft truncate max-w-[100px]"
title={entry.namespace}
>
{entry.namespace}
</span>
{/* Content preview */}
<span className="flex-1 min-w-0 text-[10px] font-mono text-ink-mid truncate text-left">
{entry.content.length > 60 ? entry.content.slice(0, 60) + "…" : entry.content}
{entry.content.length > 60 ? entry.content.slice(0, 60) + '…' : entry.content}
</span>
{/* Similarity badge */}
{entry.similarity_score != null && (
{/* Score badge (semantic search only) */}
{entry.score != null && (
<span
className={[
"text-[9px] shrink-0 font-mono tabular-nums",
entry.similarity_score >= 0.8
? "text-accent"
: "text-ink-mid",
].join(" ")}
title={`Similarity: ${(entry.similarity_score * 100).toFixed(1)}%`}
data-testid="similarity-badge"
'text-[9px] shrink-0 font-mono tabular-nums',
entry.score >= 0.8 ? 'text-accent' : 'text-ink-mid',
].join(' ')}
title={`Similarity: ${(entry.score * 100).toFixed(1)}%`}
data-testid="score-badge"
>
{Math.round(entry.similarity_score * 100)}%
{Math.round(entry.score * 100)}%
</span>
)}
{/* TTL countdown */}
{ttl && (
<span
className={[
'text-[9px] shrink-0 font-mono',
ttl === 'expired' ? 'text-bad' : 'text-amber-400',
].join(' ')}
title={`Expires: ${entry.expires_at}`}
data-testid="ttl-badge"
>
{ttl}
</span>
)}
<span className="text-[9px] text-ink-soft shrink-0">
{formatRelativeTime(entry.created_at)}
</span>
<span className="text-[9px] text-ink-soft shrink-0" aria-hidden="true">
{expanded ? "▼" : "▶"}
{expanded ? '▼' : '▶'}
</span>
</button>
@@ -455,31 +620,19 @@ function MemoryEntryRow({ entry, onEdit, onDelete }: MemoryEntryRowProps) {
<div className="flex items-center justify-between gap-2">
<span className="text-[9px] text-ink-soft">
Created: {new Date(entry.created_at).toLocaleString()}
{entry.expires_at && ` · Expires: ${new Date(entry.expires_at).toLocaleString()}`}
</span>
<div className="flex items-center gap-1.5 shrink-0">
<button
type="button"
onClick={(e) => {
e.stopPropagation();
onEdit();
}}
aria-label="Edit memory"
className="text-[10px] px-2 py-0.5 bg-surface-card hover:bg-surface-elevated border border-line/40 rounded text-ink-mid hover:text-ink transition-colors"
>
Edit
</button>
<button
type="button"
onClick={(e) => {
e.stopPropagation();
onDelete();
}}
aria-label="Delete memory"
className="text-[10px] px-2 py-0.5 bg-red-950/40 hover:bg-red-900/50 border border-red-900/30 rounded text-bad transition-colors"
>
Delete
</button>
</div>
<button
type="button"
onClick={(e) => {
e.stopPropagation();
onDelete();
}}
aria-label="Forget memory"
className="text-[10px] px-2 py-0.5 bg-red-950/40 hover:bg-red-900/50 border border-red-900/30 rounded text-bad transition-colors shrink-0"
>
Forget
</button>
</div>
</div>
)}
+1 -1
View File
@@ -287,7 +287,7 @@ export function SidePanel() {
{panelTab === "config" && <ConfigTab key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "schedule" && <ScheduleTab key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "channels" && <ChannelsTab key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "files" && <FilesTab key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "files" && <FilesTab key={selectedNodeId} workspaceId={selectedNodeId} data={node.data} />}
{panelTab === "memory" && <MemoryInspectorPanel key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "traces" && <TracesTab key={selectedNodeId} workspaceId={selectedNodeId} />}
{panelTab === "events" && <EventsTab key={selectedNodeId} workspaceId={selectedNodeId} />}
@@ -1,202 +0,0 @@
// @vitest-environment jsdom
/**
* MemoryEditorDialog tests — covers Add (POST /memories) and Edit
* (PATCH /memories/:id) flows. Pins:
* - Add posts {content, scope, namespace} with the trimmed defaults
* - Edit only sends fields that changed (no-op edit short-circuits, no PATCH fires)
* - Empty content blocks save
* - Save error surfaces in the dialog and keeps the modal open
*/
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
import { render, screen, fireEvent, waitFor, cleanup } from "@testing-library/react";
vi.mock("@/lib/api", () => ({
api: {
get: vi.fn(),
post: vi.fn(),
patch: vi.fn(),
del: vi.fn(),
},
}));
import { api } from "@/lib/api";
import { MemoryEditorDialog } from "../MemoryEditorDialog";
import type { MemoryEntry } from "../MemoryInspectorPanel";
const mockPost = vi.mocked(api.post);
const mockPatch = vi.mocked(api.patch);
const SAMPLE: MemoryEntry = {
id: "mem-x",
workspace_id: "ws-1",
content: "original content",
scope: "TEAM",
namespace: "procedures",
created_at: "2026-04-17T12:00:00.000Z",
};
beforeEach(() => {
vi.clearAllMocks();
mockPost.mockResolvedValue({} as never);
mockPatch.mockResolvedValue({} as never);
});
afterEach(() => {
cleanup();
});
describe("Add mode", () => {
it("POSTs scope+namespace+trimmed-content and calls onSaved+onClose", async () => {
const onClose = vi.fn();
const onSaved = vi.fn();
render(
<MemoryEditorDialog
open
mode="add"
workspaceId="ws-1"
defaultScope="GLOBAL"
defaultNamespace="facts"
onClose={onClose}
onSaved={onSaved}
/>,
);
const textarea = screen.getByLabelText(/Content/i) as HTMLTextAreaElement;
fireEvent.change(textarea, { target: { value: " new fact " } });
fireEvent.click(screen.getByRole("button", { name: /Add memory$/i }));
await waitFor(() => expect(mockPost).toHaveBeenCalledTimes(1));
expect(mockPost).toHaveBeenCalledWith("/workspaces/ws-1/memories", {
content: "new fact",
scope: "GLOBAL",
namespace: "facts",
});
expect(onSaved).toHaveBeenCalledTimes(1);
expect(onClose).toHaveBeenCalledTimes(1);
});
it("blocks save when content is empty (whitespace-only)", () => {
const onClose = vi.fn();
const onSaved = vi.fn();
render(
<MemoryEditorDialog
open
mode="add"
workspaceId="ws-1"
defaultScope="LOCAL"
onClose={onClose}
onSaved={onSaved}
/>,
);
const textarea = screen.getByLabelText(/Content/i) as HTMLTextAreaElement;
fireEvent.change(textarea, { target: { value: " " } });
fireEvent.click(screen.getByRole("button", { name: /Add memory$/i }));
expect(mockPost).not.toHaveBeenCalled();
expect(screen.getByRole("alert").textContent).toMatch(/empty/i);
expect(onSaved).not.toHaveBeenCalled();
expect(onClose).not.toHaveBeenCalled();
});
});
describe("Edit mode", () => {
it("PATCHes only changed fields", async () => {
const onClose = vi.fn();
const onSaved = vi.fn();
render(
<MemoryEditorDialog
open
mode="edit"
workspaceId="ws-1"
entry={SAMPLE}
onClose={onClose}
onSaved={onSaved}
/>,
);
const textarea = screen.getByLabelText(/Content/i) as HTMLTextAreaElement;
fireEvent.change(textarea, { target: { value: "rewritten content" } });
// namespace untouched
fireEvent.click(screen.getByRole("button", { name: /Save changes/i }));
await waitFor(() => expect(mockPatch).toHaveBeenCalledTimes(1));
expect(mockPatch).toHaveBeenCalledWith(
"/workspaces/ws-1/memories/mem-x",
{ content: "rewritten content" },
);
expect(onSaved).toHaveBeenCalledTimes(1);
expect(onClose).toHaveBeenCalledTimes(1);
});
it("no-op edit short-circuits (no PATCH fires) and still closes", async () => {
const onClose = vi.fn();
const onSaved = vi.fn();
render(
<MemoryEditorDialog
open
mode="edit"
workspaceId="ws-1"
entry={SAMPLE}
onClose={onClose}
onSaved={onSaved}
/>,
);
fireEvent.click(screen.getByRole("button", { name: /Save changes/i }));
await waitFor(() => expect(onClose).toHaveBeenCalled());
expect(mockPatch).not.toHaveBeenCalled();
expect(onSaved).toHaveBeenCalledTimes(1);
});
it("sends namespace too when both content and namespace changed", async () => {
const onClose = vi.fn();
const onSaved = vi.fn();
render(
<MemoryEditorDialog
open
mode="edit"
workspaceId="ws-1"
entry={SAMPLE}
onClose={onClose}
onSaved={onSaved}
/>,
);
fireEvent.change(screen.getByLabelText(/Content/i), {
target: { value: "newer content" },
});
fireEvent.change(screen.getByLabelText(/Namespace/i), {
target: { value: "blockers" },
});
fireEvent.click(screen.getByRole("button", { name: /Save changes/i }));
await waitFor(() => expect(mockPatch).toHaveBeenCalledTimes(1));
expect(mockPatch).toHaveBeenCalledWith(
"/workspaces/ws-1/memories/mem-x",
{ content: "newer content", namespace: "blockers" },
);
});
it("surfaces save error and keeps the modal open", async () => {
const onClose = vi.fn();
const onSaved = vi.fn();
mockPatch.mockRejectedValueOnce(new Error("boom"));
render(
<MemoryEditorDialog
open
mode="edit"
workspaceId="ws-1"
entry={SAMPLE}
onClose={onClose}
onSaved={onSaved}
/>,
);
fireEvent.change(screen.getByLabelText(/Content/i), {
target: { value: "rewritten content" },
});
fireEvent.click(screen.getByRole("button", { name: /Save changes/i }));
await waitFor(() =>
expect(screen.getByRole("alert").textContent).toMatch(/boom/),
);
expect(onClose).not.toHaveBeenCalled();
expect(onSaved).not.toHaveBeenCalled();
});
});
@@ -1,16 +1,29 @@
// @vitest-environment jsdom
/**
* MemoryInspectorPanel tests — issue #909
* MemoryInspectorPanel — v2 redesign tests.
*
* Covers: loading, empty state, scope tabs, namespace filter,
* entry list, expand, delete flow, optimistic updates, Refresh, semantic search.
* Coverage targets every behavior the panel surfaces:
* - Initial load wires GET /v2/namespaces + GET /v2/memories
* - Plugin-unavailable banner (503) renders + disables interactions
* - Generic error renders in the error banner
* - Namespace dropdown populates from /v2/namespaces.readable; "All
* namespaces" is the default
* - Selecting a namespace re-fetches with ?namespace=...
* - Search input debounces + scopes the request to ?q=
* - Search results sort by score descending
* - Empty-state copy differs by query / plugin-state / no-data
* - Per-row badges render (kind / source / pin / TTL / score /
* score) and TTL countdown handles past/future/null
* - Delete (Forget) flow: optimistic removal, confirmation dialog,
* server failure rolls back via reload
* - formatTTL helper covers s/m/h/d/expired/null/invalid branches
*/
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
import { render, screen, fireEvent, waitFor, cleanup, act } from "@testing-library/react";
import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
import { render, screen, fireEvent, waitFor, cleanup } from '@testing-library/react';
// ── Mocks ─────────────────────────────────────────────────────────────────────
vi.mock("@/lib/api", () => ({
vi.mock('@/lib/api', () => ({
api: {
get: vi.fn(),
post: vi.fn(),
@@ -18,7 +31,7 @@ vi.mock("@/lib/api", () => ({
},
}));
vi.mock("@/components/ConfirmDialog", () => ({
vi.mock('@/components/ConfirmDialog', () => ({
ConfirmDialog: ({
open,
title,
@@ -33,435 +46,473 @@ vi.mock("@/components/ConfirmDialog", () => ({
confirmVariant?: string;
onConfirm: () => void;
onCancel: () => void;
singleButton?: boolean;
}) =>
open ? (
<div data-testid="confirm-dialog">
<p data-testid="dialog-title">{title}</p>
<p data-testid="dialog-message">{message}</p>
<button onClick={onConfirm}>Confirm Delete</button>
<button onClick={onCancel}>Cancel Delete</button>
<button onClick={onConfirm}>Confirm</button>
<button onClick={onCancel}>Cancel</button>
</div>
) : null,
}));
import { api } from "@/lib/api";
import { MemoryInspectorPanel } from "../MemoryInspectorPanel";
// ── Typed mock helpers ────────────────────────────────────────────────────────
import { api } from '@/lib/api';
import {
MemoryInspectorPanel,
formatTTL,
isPluginUnavailableError,
type MemoryV2,
type NamespacesResponse,
} from '../MemoryInspectorPanel';
const mockGet = vi.mocked(api.get);
const mockDel = vi.mocked(api.del);
// ── Sample fixtures ───────────────────────────────────────────────────────────
// ── Fixtures ──────────────────────────────────────────────────────────────────
const NOW = "2026-04-17T12:00:00.000Z";
const MEMORY_A: import("../MemoryInspectorPanel").MemoryEntry = {
id: "mem-a",
workspace_id: "ws-1",
content: "Remember to review PRs before merging",
scope: "LOCAL",
namespace: "general",
created_at: NOW,
const NS_RESPONSE: NamespacesResponse = {
readable: [
{ name: 'workspace:ws-1', kind: 'workspace', label: 'Workspace (ws-1)' },
{ name: 'team:t-1', kind: 'team', label: 'Team (t-1)' },
],
writable: [{ name: 'workspace:ws-1', kind: 'workspace', label: 'Workspace (ws-1)' }],
};
const MEMORY_B: import("../MemoryInspectorPanel").MemoryEntry = {
id: "mem-b",
workspace_id: "ws-1",
content: "Team knowledge: deploy happens on Fridays",
scope: "TEAM",
namespace: "procedures",
created_at: NOW,
const MEM_BASIC: MemoryV2 = {
id: 'mem-a',
namespace: 'workspace:ws-1',
content: 'Remember the standup is at 10am',
kind: 'fact',
source: 'agent',
pin: false,
created_at: '2026-04-17T12:00:00.000Z',
};
const TWO_MEMORIES = [MEMORY_A, MEMORY_B];
const MEM_PINNED: MemoryV2 = {
id: 'mem-pinned',
namespace: 'team:t-1',
content: 'Team retro every Friday',
kind: 'summary',
source: 'user',
pin: true,
expires_at: new Date(Date.now() + 86_400_000).toISOString(),
created_at: '2026-04-17T12:00:00.000Z',
};
const MEM_RUNTIME_CHECKPOINT: MemoryV2 = {
id: 'mem-checkpoint',
namespace: 'team:t-1',
content: 'Runtime checkpoint',
kind: 'checkpoint',
source: 'runtime',
pin: false,
created_at: '2026-04-17T12:00:00.000Z',
};
const MEM_EXPIRED: MemoryV2 = {
id: 'mem-expired',
namespace: 'workspace:ws-1',
content: 'Stale memory',
kind: 'fact',
source: 'agent',
pin: false,
expires_at: new Date(Date.now() - 1000).toISOString(),
created_at: '2026-04-17T12:00:00.000Z',
};
// ── Setup / teardown ──────────────────────────────────────────────────────────
beforeEach(() => {
vi.clearAllMocks();
mockGet.mockReset();
mockDel.mockReset();
});
afterEach(() => {
cleanup();
});
// ── Helper: flush microtasks + React state updates ─────────────────────────────
async function flushUpdates(): Promise<void> {
await act(async () => {});
// Helper: stub a basic two-call flow (namespaces + memories).
function stubFetch(memories: MemoryV2[], namespaces: NamespacesResponse = NS_RESPONSE) {
mockGet.mockImplementation(((url: string) => {
if (url.includes('/v2/namespaces')) {
return Promise.resolve(namespaces);
}
return Promise.resolve({ memories });
}) as typeof api.get);
}
// ── Loading & empty state ─────────────────────────────────────────────────────
// ── isPluginUnavailableError helper ─────────────────────────────────────────
describe("MemoryInspectorPanel — loading and empty state", () => {
it("shows loading indicator before data arrives", () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockReturnValue(new Promise(() => {}) as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
expect(screen.getByText(/loading memories/i)).toBeTruthy();
});
it("renders empty state when API returns []", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByText("No LOCAL memories")).toBeTruthy();
});
it("fetches from the correct workspace memories endpoint with scope=LOCAL", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-abc-123" />);
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-abc-123/memories?scope=LOCAL"
);
});
it("shows error banner when fetch throws", async () => {
mockGet.mockRejectedValue(new Error("Network error"));
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByText("Network error")).toBeTruthy();
});
});
// ── Scope tabs ────────────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — scope tabs", () => {
it("renders LOCAL, TEAM, GLOBAL tabs", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByRole("button", { name: "LOCAL" })).toBeTruthy();
expect(screen.getByRole("button", { name: "TEAM" })).toBeTruthy();
expect(screen.getByRole("button", { name: "GLOBAL" })).toBeTruthy();
});
it("LOCAL is active by default", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByRole("button", { name: "LOCAL" }).getAttribute("aria-pressed")).toBe("true");
});
it("clicking TEAM tab re-fetches with scope=TEAM", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
mockGet.mockClear();
fireEvent.click(screen.getByRole("button", { name: "TEAM" }));
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=TEAM"
);
});
it("clicking GLOBAL tab re-fetches with scope=GLOBAL", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
mockGet.mockClear();
fireEvent.click(screen.getByRole("button", { name: "GLOBAL" }));
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=GLOBAL"
);
});
it("shows scope-specific empty state when switching tabs", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
fireEvent.click(screen.getByRole("button", { name: "TEAM" }));
await flushUpdates();
expect(screen.getByText("No TEAM memories")).toBeTruthy();
});
});
// ── Namespace filter ──────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — namespace filter", () => {
it("renders namespace filter input", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByLabelText("Filter by namespace")).toBeTruthy();
});
it("includes namespace param in API call when set", async () => {
vi.useFakeTimers();
try {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
mockGet.mockClear();
fireEvent.change(screen.getByLabelText("Filter by namespace"), {
target: { value: "facts" },
});
// Advance past the 300ms debounce
act(() => { vi.advanceTimersByTime(350); });
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=LOCAL&namespace=facts"
);
} finally {
vi.useRealTimers();
}
});
});
// ── Entry list ───────────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — entry list", () => {
beforeEach(() => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue(TWO_MEMORIES as any);
});
it("renders a row for every memory", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByText(/Remember to review PRs before merging/)).toBeTruthy();
expect(screen.getByText(/Team knowledge: deploy happens on Fridays/)).toBeTruthy();
});
it("displays memory count in toolbar", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByText("2 memories")).toBeTruthy();
});
it("displays scope badge for each entry", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByTitle("Scope: LOCAL")).toBeTruthy();
expect(screen.getByTitle("Scope: TEAM")).toBeTruthy();
});
it("entries are collapsed by default (pre region not visible)", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
// Expanded region (pre tag) should not exist in DOM yet
expect(screen.queryByRole("region")).toBeNull();
});
});
// ── Expand / collapse ─────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — expand/collapse", () => {
beforeEach(() => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue(TWO_MEMORIES as any);
});
it("clicking a row header expands it and shows the full content in a pre tag", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
fireEvent.click(
screen.getByText(/Remember to review PRs before merging/).closest("button")!
);
await flushUpdates();
// After expand, a region with the full content <pre> should appear
expect(screen.getByRole("region")).toBeTruthy();
});
it("clicking the header again collapses the row (pre region removed)", async () => {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
const headerBtn = screen
.getByText(/Remember to review PRs before merging/)
.closest("button")!;
fireEvent.click(headerBtn); // expand
await flushUpdates();
expect(screen.getByRole("region")).toBeTruthy();
fireEvent.click(headerBtn); // collapse
await flushUpdates();
// After collapse, the region (pre) is removed from the DOM
expect(screen.queryByRole("region")).toBeNull();
});
});
// ── Delete flow ───────────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — delete flow", () => {
beforeEach(() => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue(TWO_MEMORIES as any);
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockDel.mockResolvedValue({ status: "deleted" } as any);
});
/** Helper: expand memory-A and click its Delete button */
async function openDeleteForMemoryA() {
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
fireEvent.click(
screen.getByText(/Remember to review PRs before merging/).closest("button")!
);
await flushUpdates();
fireEvent.click(screen.getByRole("button", { name: "Delete memory" }));
await flushUpdates();
}
it("opens ConfirmDialog when Delete is clicked", async () => {
await openDeleteForMemoryA();
expect(screen.getByTestId("confirm-dialog")).toBeTruthy();
expect(screen.getByTestId("dialog-title").textContent).toBe("Delete memory");
});
it("calls api.del with the correct URL-encoded path on confirm", async () => {
await openDeleteForMemoryA();
fireEvent.click(screen.getByText("Confirm Delete"));
await flushUpdates();
expect(mockDel).toHaveBeenCalledWith("/workspaces/ws-1/memories/mem-a");
});
it("removes the entry optimistically after confirm", async () => {
await openDeleteForMemoryA();
fireEvent.click(screen.getByText("Confirm Delete"));
await flushUpdates();
expect(screen.queryByText(/Remember to review PRs before merging/)).toBeNull();
// Sibling entry unaffected
expect(screen.getByText(/Team knowledge: deploy happens on Fridays/)).toBeTruthy();
});
it("closes ConfirmDialog without deleting when Cancel is clicked", async () => {
await openDeleteForMemoryA();
fireEvent.click(screen.getByText("Cancel Delete"));
await flushUpdates();
expect(screen.queryByTestId("confirm-dialog")).toBeNull();
expect(mockDel).not.toHaveBeenCalled();
// Sibling memory entry (MEMORY_B) is still in the list
expect(screen.getByText(/Team knowledge: deploy happens on Fridays/)).toBeTruthy();
});
});
// ── Refresh ───────────────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — Refresh button", () => {
it("re-fetches entries when Refresh is clicked", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
expect(screen.getByText("No LOCAL memories")).toBeTruthy();
expect(mockGet).toHaveBeenCalledTimes(1);
fireEvent.click(screen.getByRole("button", { name: "Refresh memories" }));
await flushUpdates();
expect(mockGet).toHaveBeenCalledTimes(2);
});
});
// ── role=alert a11y ──────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — error elements have role=alert", () => {
it("fetch error banner has role='alert'", async () => {
mockGet.mockRejectedValue(new Error("Network error"));
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
const alert = screen.getByRole("alert");
expect(alert).toBeTruthy();
expect(alert.textContent).toContain("Network error");
});
});
// ── Semantic search ──────────────────────────────────────────────────────────
describe("MemoryInspectorPanel — semantic search", () => {
afterEach(() => {
vi.useRealTimers();
});
it("debounces search input by 300ms before calling API", async () => {
vi.useFakeTimers();
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
mockGet.mockClear();
fireEvent.change(screen.getByLabelText("Search memories"), {
target: { value: "deploy" },
});
// 200ms — debounce has NOT fired yet
act(() => { vi.advanceTimersByTime(200); });
await flushUpdates();
expect(mockGet).not.toHaveBeenCalled();
// 350ms total — debounce fires
act(() => { vi.advanceTimersByTime(150); });
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=LOCAL&q=deploy"
);
});
it("renders similarity-badge when entry has similarity_score", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([{ ...MEMORY_A, similarity_score: 0.87 }] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
const badge = document.querySelector('[data-testid="similarity-badge"]');
expect(badge).toBeTruthy();
expect(badge?.textContent).toBe("87%");
});
it("does not render similarity-badge when entry has no similarity_score", async () => {
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([MEMORY_A] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
describe('isPluginUnavailableError', () => {
it('matches the literal env var contract from the server handler', () => {
expect(
document.querySelector('[data-testid="similarity-badge"]')
).toBeNull();
isPluginUnavailableError(
new Error('API GET /workspaces/x/v2/memories: 503 {"error":"memory plugin is not configured (set MEMORY_PLUGIN_URL)"}'),
),
).toBe(true);
});
it("clear button resets query immediately and re-fetches without ?q=", async () => {
vi.useFakeTimers();
// eslint-disable-next-line @typescript-eslint/no-explicit-any
mockGet.mockResolvedValue([] as any);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await flushUpdates();
it('does not false-match on generic 503 errors that don\'t mention the env var', () => {
expect(isPluginUnavailableError(new Error('API GET /foo: 503 something else'))).toBe(false);
});
fireEvent.change(screen.getByLabelText("Search memories"), {
target: { value: "deploy" },
it('does not false-match on plain 4xx errors', () => {
expect(isPluginUnavailableError(new Error('API GET /foo: 401 unauthorized'))).toBe(false);
});
it('returns false for non-Error inputs', () => {
expect(isPluginUnavailableError(null)).toBe(false);
expect(isPluginUnavailableError(undefined)).toBe(false);
expect(isPluginUnavailableError('a string')).toBe(false);
expect(isPluginUnavailableError({ message: 'MEMORY_PLUGIN_URL' })).toBe(false);
});
});
// ── formatTTL helper ─────────────────────────────────────────────────────────
describe('formatTTL', () => {
it('returns empty string for null/undefined/empty', () => {
expect(formatTTL(null)).toBe('');
expect(formatTTL(undefined)).toBe('');
expect(formatTTL('')).toBe('');
});
it('returns empty for invalid date strings', () => {
expect(formatTTL('not-a-date')).toBe('');
});
it('returns "expired" for past timestamps', () => {
const past = new Date(Date.now() - 5000).toISOString();
expect(formatTTL(past)).toBe('expired');
});
it('formats <60s as seconds', () => {
const future = new Date(Date.now() + 30_000).toISOString();
expect(formatTTL(future)).toMatch(/^\d{1,2}s$/);
});
it('formats <60m as minutes', () => {
const future = new Date(Date.now() + 30 * 60_000).toISOString();
expect(formatTTL(future)).toMatch(/^\d{1,2}m$/);
});
it('formats <24h as hours', () => {
const future = new Date(Date.now() + 5 * 3_600_000).toISOString();
expect(formatTTL(future)).toMatch(/^\d{1,2}h$/);
});
it('formats >24h as days', () => {
const future = new Date(Date.now() + 3 * 86_400_000).toISOString();
expect(formatTTL(future)).toMatch(/^\d{1,2}d$/);
});
});
// ── Initial load + dropdown ─────────────────────────────────────────────────
describe('MemoryInspectorPanel — initial load', () => {
it('fetches namespaces and memories on mount', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
const calls = mockGet.mock.calls.map((c) => c[0]);
expect(calls.some((u) => u.includes('/v2/namespaces'))).toBe(true);
expect(calls.some((u) => u.includes('/v2/memories'))).toBe(true);
});
});
it('renders the row contents from the memories response', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
expect(screen.getByText(/Remember the standup is at 10am/)).toBeTruthy();
});
});
it('populates the namespace dropdown with readable entries + "All namespaces"', async () => {
stubFetch([]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Filter by namespace'));
const select = screen.getByLabelText('Filter by namespace') as HTMLSelectElement;
const optionLabels = Array.from(select.options).map((o) => o.textContent ?? '');
expect(optionLabels[0]).toContain('All namespaces');
expect(optionLabels.join('|')).toContain('Workspace (ws-1)');
expect(optionLabels.join('|')).toContain('Team (t-1)');
});
it('selecting a namespace re-fetches with ?namespace=', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Filter by namespace'));
const select = screen.getByLabelText('Filter by namespace') as HTMLSelectElement;
fireEvent.change(select, { target: { value: 'team:t-1' } });
await waitFor(() => {
const calls = mockGet.mock.calls.map((c) => c[0] as string);
expect(calls.some((u) => u.includes('namespace=team%3At-1'))).toBe(true);
});
});
});
// ── Plugin unavailable (503) ────────────────────────────────────────────────
describe('MemoryInspectorPanel — plugin unavailable', () => {
it('renders the operator-hint banner and disables search input', async () => {
mockGet.mockRejectedValue(new Error('HTTP 503: memory plugin is not configured (set MEMORY_PLUGIN_URL)'));
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByTestId('plugin-unavailable-banner'));
const searchInput = screen.getByLabelText('Search memories') as HTMLInputElement;
expect(searchInput.disabled).toBe(true);
});
it('shows the empty-state explaining plugin disabled', async () => {
mockGet.mockRejectedValue(new Error('API GET /workspaces/x/v2/memories: 503 {"error":"memory plugin is not configured (set MEMORY_PLUGIN_URL)"}'));
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByText(/Memory plugin disabled/i));
});
});
// ── Generic error (non-503) ─────────────────────────────────────────────────
describe('MemoryInspectorPanel — generic errors', () => {
it('surfaces a non-503 error in the error banner', async () => {
mockGet.mockImplementation(((url: string) => {
if (url.includes('/v2/namespaces')) {
return Promise.resolve(NS_RESPONSE);
}
return Promise.reject(new Error('upstream timeout'));
}) as typeof api.get);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
// Error banner has role=alert
const alerts = screen.getAllByRole('alert');
const found = alerts.some((a) => a.textContent?.includes('upstream timeout'));
expect(found).toBe(true);
});
});
});
// ── Search ──────────────────────────────────────────────────────────────────
describe('MemoryInspectorPanel — search', () => {
it('eventually fires query with ?q= after debounce', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Search memories'));
fireEvent.change(screen.getByLabelText('Search memories'), {
target: { value: 'standup' },
});
act(() => { vi.advanceTimersByTime(350); });
await flushUpdates();
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=LOCAL&q=deploy"
await waitFor(
() => {
const calls = mockGet.mock.calls.map((c) => c[0] as string);
expect(calls.some((u) => u.includes('q=standup'))).toBe(true);
},
{ timeout: 1500 },
);
mockGet.mockClear();
});
fireEvent.click(screen.getByRole("button", { name: "Clear search" }));
await flushUpdates();
it('sorts results by score descending when query active', async () => {
const lowScore: MemoryV2 = { ...MEM_BASIC, id: 'low', score: 0.2, content: 'low' };
const highScore: MemoryV2 = { ...MEM_BASIC, id: 'high', score: 0.95, content: 'high' };
// Plugin returns in arbitrary order; component sorts.
mockGet.mockImplementation(((url: string) => {
if (url.includes('/v2/namespaces')) return Promise.resolve(NS_RESPONSE);
return Promise.resolve({ memories: [lowScore, highScore] });
}) as typeof api.get);
expect(mockGet).toHaveBeenCalledWith(
"/workspaces/ws-1/memories?scope=LOCAL"
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Search memories'));
fireEvent.change(screen.getByLabelText('Search memories'), {
target: { value: 'something' },
});
await waitFor(
() => {
const rows = screen.getAllByTestId(/^memory-row-/);
// First row should be the high-score one
expect(rows[0].getAttribute('data-testid')).toBe('memory-row-high');
},
{ timeout: 1500 },
);
});
it('clear-button resets the query', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Search memories'));
fireEvent.change(screen.getByLabelText('Search memories'), {
target: { value: 'foo' },
});
fireEvent.click(screen.getByLabelText('Clear search'));
expect((screen.getByLabelText('Search memories') as HTMLInputElement).value).toBe('');
});
it('renders no-results empty-state when search has no matches', async () => {
stubFetch([]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Search memories'));
fireEvent.change(screen.getByLabelText('Search memories'), {
target: { value: 'nothing' },
});
await waitFor(
() => {
expect(screen.getByText(/No memories match your search/i)).toBeTruthy();
},
{ timeout: 1500 },
);
});
});
// ── Per-row badges ───────────────────────────────────────────────────────────
describe('MemoryInspectorPanel — row badges', () => {
it('renders kind, source, pin, TTL badges per shape', async () => {
stubFetch([MEM_PINNED, MEM_RUNTIME_CHECKPOINT]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
// Pinned memory: kind=summary, source=user, pin=true, TTL>0
const pinnedRow = screen.getByTestId('memory-row-mem-pinned');
expect(pinnedRow.querySelector('[data-testid="kind-badge"]')?.textContent).toBe('S');
expect(pinnedRow.querySelector('[data-testid="source-badge"]')?.textContent).toBe('user');
expect(pinnedRow.querySelector('[data-testid="pin-badge"]')).toBeTruthy();
expect(pinnedRow.querySelector('[data-testid="ttl-badge"]')?.textContent).toMatch(/^⌛\d+[hd]$/);
// Checkpoint memory: kind=checkpoint, source=runtime, no pin, no TTL
const propRow = screen.getByTestId('memory-row-mem-checkpoint');
expect(propRow.querySelector('[data-testid="kind-badge"]')?.textContent).toBe('C');
expect(propRow.querySelector('[data-testid="source-badge"]')?.textContent).toBe('runtime');
expect(propRow.querySelector('[data-testid="pin-badge"]')).toBeNull();
expect(propRow.querySelector('[data-testid="ttl-badge"]')).toBeNull();
});
});
it('TTL badge shows "expired" for past expires_at', async () => {
stubFetch([MEM_EXPIRED]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
const row = screen.getByTestId('memory-row-mem-expired');
expect(row.querySelector('[data-testid="ttl-badge"]')?.textContent).toBe('⌛expired');
});
});
it('expanding a row shows full content + Forget button', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByTestId('memory-row-mem-a'));
const row = screen.getByTestId('memory-row-mem-a');
const headerButton = row.querySelector('button');
expect(headerButton).toBeTruthy();
fireEvent.click(headerButton!);
await waitFor(() => {
expect(screen.getByLabelText('Forget memory')).toBeTruthy();
});
});
});
// ── Delete (Forget) flow ──────────────────────────────────────────────────────
describe('MemoryInspectorPanel — forget flow', () => {
it('opens the confirm dialog on Forget click and removes optimistically on confirm', async () => {
stubFetch([MEM_BASIC]);
mockDel.mockResolvedValue({ status: 'deleted' });
render(<MemoryInspectorPanel workspaceId="ws-1" />);
// Expand row, click Forget
await waitFor(() => screen.getByTestId('memory-row-mem-a'));
const row = screen.getByTestId('memory-row-mem-a');
fireEvent.click(row.querySelector('button')!);
await waitFor(() => screen.getByLabelText('Forget memory'));
fireEvent.click(screen.getByLabelText('Forget memory'));
// Dialog appears with v2-shaped copy (Forget, not Delete)
expect(screen.getByTestId('dialog-title').textContent).toBe('Forget memory');
fireEvent.click(screen.getByText('Confirm'));
// Optimistic removal happens immediately
await waitFor(() => {
expect(screen.queryByTestId('memory-row-mem-a')).toBeNull();
});
// DELETE called with the right path
await waitFor(() => {
const delPaths = mockDel.mock.calls.map((c) => c[0] as string);
expect(delPaths.some((p) => p.includes('/v2/memories/mem-a'))).toBe(true);
});
});
it('cancelling the dialog leaves the row in place', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByTestId('memory-row-mem-a'));
fireEvent.click(screen.getByTestId('memory-row-mem-a').querySelector('button')!);
await waitFor(() => screen.getByLabelText('Forget memory'));
fireEvent.click(screen.getByLabelText('Forget memory'));
fireEvent.click(screen.getByText('Cancel'));
expect(screen.queryByTestId('memory-row-mem-a')).toBeTruthy();
expect(mockDel).not.toHaveBeenCalled();
});
it('rolls back on server failure by reloading entries', async () => {
stubFetch([MEM_BASIC]);
mockDel.mockRejectedValue(new Error('upstream 502'));
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByTestId('memory-row-mem-a'));
fireEvent.click(screen.getByTestId('memory-row-mem-a').querySelector('button')!);
await waitFor(() => screen.getByLabelText('Forget memory'));
fireEvent.click(screen.getByLabelText('Forget memory'));
fireEvent.click(screen.getByText('Confirm'));
// After failure, error banner surfaces + reload re-fetches memories
await waitFor(() => {
const alerts = screen.getAllByRole('alert');
const found = alerts.some((a) => a.textContent?.includes('upstream 502'));
expect(found).toBe(true);
});
});
});
// ── Empty state when no memories at all ────────────────────────────────────
describe('MemoryInspectorPanel — empty state', () => {
it('renders the "no memories yet" empty state when not searching', async () => {
stubFetch([]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => {
expect(screen.getByText('No memories yet')).toBeTruthy();
});
});
});
// ── Refresh ─────────────────────────────────────────────────────────────────
describe('MemoryInspectorPanel — refresh', () => {
it('Refresh button refetches memories', async () => {
stubFetch([MEM_BASIC]);
render(<MemoryInspectorPanel workspaceId="ws-1" />);
await waitFor(() => screen.getByLabelText('Refresh memories'));
const before = mockGet.mock.calls.filter((c) =>
(c[0] as string).includes('/v2/memories'),
).length;
fireEvent.click(screen.getByLabelText('Refresh memories'));
await waitFor(() => {
const after = mockGet.mock.calls.filter((c) =>
(c[0] as string).includes('/v2/memories'),
).length;
expect(after).toBe(before + 1);
});
});
});
+92 -5
View File
@@ -7,8 +7,9 @@ import { api } from "@/lib/api";
import { useCanvasStore, type WorkspaceNodeData } from "@/store/canvas";
import { useSocketEvent } from "@/hooks/useSocketEvent";
import { type ChatMessage, type ChatAttachment, createMessage, appendMessageDeduped } from "./chat/types";
import { uploadChatFiles, downloadChatFile } from "./chat/uploads";
import { AttachmentChip, PendingAttachmentPill } from "./chat/AttachmentViews";
import { uploadChatFiles, downloadChatFile, isPlatformAttachment } from "./chat/uploads";
import { PendingAttachmentPill } from "./chat/AttachmentViews";
import { AttachmentPreview } from "./chat/AttachmentPreview";
import { extractFilesFromTask } from "./chat/message-parser";
import { AgentCommsPanel } from "./chat/AgentCommsPanel";
import { appendActivityLine } from "./chat/activityLog";
@@ -1061,14 +1062,85 @@ function MyChatPanel({ workspaceId, data }: Props) {
: "dark:prose-invert dark:[--tw-prose-invert-body:theme(colors.zinc.100)] dark:[--tw-prose-invert-headings:theme(colors.white)] dark:[--tw-prose-invert-bold:theme(colors.white)] dark:[--tw-prose-invert-code:theme(colors.zinc.100)]"
}`}
>
<ReactMarkdown remarkPlugins={[remarkGfm]}>{msg.content}</ReactMarkdown>
<ReactMarkdown
remarkPlugins={[remarkGfm]}
components={{
// Default ReactMarkdown renders `<a href="...">`
// with no target and no scheme handling, so:
//
// 1. http/https links navigate the canvas tab
// itself away — user loses canvas state.
// 2. workspace://, file://, and bare /workspace/
// paths from agent-authored markdown produce
// an unhandled-protocol click → browser ends
// up at about:blank with no download (the
// reported bug from 2026-05-05).
//
// Override: external URLs open in a new tab with
// rel="noopener noreferrer"; in-container paths
// route through downloadChatFile so the browser
// gets a real Blob with proper auth headers.
a: ({ href, children, ...rest }) => {
const url = String(href ?? "");
// Use the SSOT helper isPlatformAttachment so
// the markdown link override and the chip
// download path agree on which schemes need
// auth-routed download. Pre-fix this list was
// duplicated and missed `platform-pending:`,
// producing about:blank for poll-mode uploads.
if (isPlatformAttachment(url)) {
return (
<a
href={url}
{...rest}
onClick={(e) => {
e.preventDefault();
// Construct a synthetic ChatAttachment
// and route through the same
// authenticated download path the
// download chips use. Filename is the
// last path segment so Save-As prefills
// sensibly.
const name = url.split(/[\\/]/).pop() || "download";
downloadChatFile(workspaceId, {
uri: url,
name,
}).catch((err) => {
setError(
err instanceof Error
? `Download failed: ${err.message}`
: "Download failed",
);
});
}}
>
{children}
</a>
);
}
// External (http(s) / mailto / unknown scheme):
// open in new tab so canvas state survives.
return (
<a
href={url}
target="_blank"
rel="noopener noreferrer"
{...rest}
>
{children}
</a>
);
},
}}
>{msg.content}</ReactMarkdown>
</div>
)}
{msg.attachments && msg.attachments.length > 0 && (
<div className={`flex flex-wrap gap-1 ${msg.content ? "mt-1.5" : ""}`}>
{msg.attachments.map((att, i) => (
<AttachmentChip
<AttachmentPreview
key={`${msg.id}-${i}`}
workspaceId={workspaceId}
attachment={att}
onDownload={downloadAttachment}
tone={msg.role === "user" ? "user" : "agent"}
@@ -1167,7 +1239,22 @@ function MyChatPanel({ workspaceId, data }: Props) {
value={input}
onChange={(e) => setInput(e.target.value)}
onKeyDown={(e) => {
if (e.key === "Enter" && !e.shiftKey) {
// IME-safe send: while a CJK / Japanese / Korean IME is
// composing, Enter accepts the candidate selection — not a
// newline, not a send. `e.nativeEvent.isComposing` is the
// standard signal (modern WebKit/Blink/Gecko); the keyCode
// 229 fallback covers older Safari / WebKit-based mobile
// browsers that delay setting isComposing on the
// composition-end Enter. Reported 2026-05-05: typing
// Chinese with the system IME, pressing Enter to commit
// a candidate would inadvertently send the half-typed
// message.
if (
e.key === "Enter" &&
!e.shiftKey &&
!e.nativeEvent.isComposing &&
e.keyCode !== 229
) {
e.preventDefault();
sendMessage();
}
+21
View File
@@ -262,6 +262,27 @@ export function ConfigTab({ workspaceId }: Props) {
setOriginalProvider("");
}
// Skip the config.yaml fetch entirely for runtimes that manage
// their own config (external, hermes, etc.) — they don't have a
// platform-side template, so the GET would 404. The catch block
// below handles 404 gracefully, but issuing the request adds
// browser-console noise + a wasted RTT on every open of the
// Config tab for the affected workspaces. Reported on
// production reno-stars 2026-05-05 (workspace runtime=external,
// 404 on /files/config.yaml visible in the console even though
// the form rendered correctly).
if (RUNTIMES_WITH_OWN_CONFIG.has(wsMetadataRuntime)) {
setConfig({
...DEFAULT_CONFIG,
runtime: wsMetadataRuntime,
model: wsMetadataModel,
...(wsMetadataModel ? { runtime_config: { model: wsMetadataModel } } : {}),
...(wsMetadataTier !== null ? { tier: wsMetadataTier } : {}),
} as ConfigData);
setOriginalModel(wsMetadataModel);
setLoading(false);
return;
}
try {
const res = await api.get<{ content: string }>(`/workspaces/${workspaceId}/files/config.yaml`);
const parsed = parseYaml(res.content);
+113 -4
View File
@@ -2,9 +2,11 @@
import { useState, useEffect, useRef, useMemo } from "react";
import { showToast } from "../Toaster";
import type { WorkspaceNodeData } from "@/store/canvas";
import { FilesToolbar } from "./FilesTab/FilesToolbar";
import { FileTree } from "./FilesTab/FileTree";
import { FileEditor } from "./FilesTab/FileEditor";
import { NotAvailablePanel } from "./FilesTab/NotAvailablePanel";
import { useFilesApi } from "./FilesTab/useFilesApi";
import { buildTree } from "./FilesTab/tree";
@@ -14,9 +16,40 @@ export type { TreeNode } from "./FilesTab/tree";
interface Props {
workspaceId: string;
/** Workspace metadata from the canvas store. Optional for back-compat
* with any caller that still mounts <FilesTab workspaceId=.../> without
* threading data through (legacy tests). When present, runtime gates
* the early-return below. Mirrors TerminalTab's prop shape (#2830). */
data?: WorkspaceNodeData;
}
export function FilesTab({ workspaceId }: Props) {
/** Runtimes whose filesystem the platform doesn't own. The canvas can't
* list/read/write files on these — the agent runs on the user's own
* hardware (mac laptop, mac mini, hermes-on-home-server) and reaches
* the platform via the heartbeat-based polling Phase 30 layer.
*
* Keep narrow — only add a runtime here when its provisioner genuinely
* has no platform-owned filesystem. Otherwise the user loses access to
* a real surface (e.g. claude-code SaaS workspaces have files served
* by ListFiles via EIC; they belong on the rendering path, not here). */
const RUNTIMES_WITHOUT_FILES = new Set(["external"]);
export function FilesTab({ workspaceId, data }: Props) {
// Early-return for runtimes whose filesystem is not platform-owned.
// Skips the whole useFilesApi hook + tree render below — without this,
// mounting the tab for an external workspace would issue a GET that
// the platform can technically answer (it reads its own DB row, not
// the user's machine), but every result row is fictional. Showing
// "0 files / No config files yet" reads as a bug. The placeholder
// makes the absence intentional and points the user at the right
// surface (Chat).
if (data && RUNTIMES_WITHOUT_FILES.has(data.runtime)) {
return <NotAvailablePanel runtime={data.runtime} />;
}
return <PlatformOwnedFilesTab workspaceId={workspaceId} />;
}
function PlatformOwnedFilesTab({ workspaceId }: { workspaceId: string }) {
const [root, setRoot] = useState("/configs");
const [selectedFile, setSelectedFile] = useState<string | null>(null);
const [fileContent, setFileContent] = useState("");
@@ -45,11 +78,36 @@ export function FilesTab({ workspaceId }: Props) {
readFile,
writeFile,
deleteFile,
downloadFileByPath,
downloadAllFiles,
uploadFiles,
uploadDataTransferItems,
deleteAllFiles,
} = useFilesApi(workspaceId, root);
// PR-D: track whether the user is currently dragging files OVER
// the root area (not over a specific subdir row). Used to show
// the "Drop to upload to root" highlight on the tree column.
const [rootDragHover, setRootDragHover] = useState(false);
const handleDropToTarget = (
targetDir: string,
items: DataTransferItemList,
) => {
// canDelete is the gate proxy — same constraint as the toolbar
// Upload button (today only /configs is writable from the canvas
// surface). Without this check, dropping on /home would post
// through /workspaces/<id>/files/<path>, which the backend would
// reject only after an HTTP round-trip. Fail fast.
if (root !== "/configs") {
setError(
`Upload only allowed in /configs (current root: ${root}). Switch root or use Upload button.`,
);
return;
}
void uploadDataTransferItems(items, targetDir);
};
const tree = useMemo(() => buildTree(files), [files]);
const openFile = async (path: string) => {
@@ -190,8 +248,46 @@ export function FilesTab({ workspaceId }: Props) {
)}
<div className="flex flex-1 min-h-0">
{/* File tree */}
<div className="w-[180px] border-r border-line/40 overflow-y-auto shrink-0">
{/* File tree column. PR-D: outer div is the drop zone for
"drop on root" — when the user drags into the column area
(not over a specific subdir row), the drop targets the
current root directory. Subdirectory rows in <FileTree>
stop propagation on their own drop event so a drop on
/configs/skills doesn't ALSO fire root-area drop. */}
<div
className={`w-[180px] border-r border-line/40 overflow-y-auto shrink-0 transition-colors ${
rootDragHover ? "bg-accent/10 outline outline-1 outline-accent/40 -outline-offset-2" : ""
}`}
onDragOver={(e) => {
// Only highlight + accept the drop when uploads are
// actually allowed for the current root. Without this
// check the user gets a misleading drag affordance,
// drops, then sees the toolbar's "switch root" toast —
// bad UX.
if (root !== "/configs") return;
e.preventDefault();
e.dataTransfer.dropEffect = "copy";
}}
onDragEnter={(e) => {
if (root !== "/configs") return;
e.preventDefault();
setRootDragHover(true);
}}
onDragLeave={(e) => {
const next = e.relatedTarget as Node | null;
if (!next || !(e.currentTarget as HTMLElement).contains(next)) {
setRootDragHover(false);
}
}}
onDrop={(e) => {
if (root !== "/configs") return;
e.preventDefault();
setRootDragHover(false);
if (e.dataTransfer.items?.length) {
handleDropToTarget("", e.dataTransfer.items);
}
}}
>
{/* New file input */}
{showNewFile && (
<div className="px-2 py-1 border-b border-line/40">
@@ -209,14 +305,27 @@ export function FilesTab({ workspaceId }: Props) {
{files.length === 0 ? (
<div className="px-3 py-4 text-[10px] text-ink-soft text-center">
No config files yet
{rootDragHover
? "Drop to upload to root"
: root === "/configs"
? "No config files yet — drag files here to upload"
: "No config files yet"}
</div>
) : (
<FileTree
nodes={tree}
selectedPath={selectedFile}
onSelect={openFile}
// Delete is currently gated to /configs to match the
// toolbar's New / Upload / Clear affordances. Context
// menu and inline ✕ both honour the gate. PR-A made the
// backend EIC delete work on all roots — keeping the
// canvas gate conservative until we want to expose
// /home /workspace deletion intentionally.
onDelete={root === "/configs" ? setConfirmDelete : () => {}}
onDownload={downloadFileByPath}
canDelete={root === "/configs"}
onDropToTarget={handleDropToTarget}
expandedDirs={expandedDirs}
onToggleDir={toggleDir}
loadingDir={loadingDir}
@@ -1,41 +1,129 @@
"use client";
import { useState } from "react";
import { type TreeNode, getIcon } from "./tree";
import { FileTreeContextMenu, type MenuItem } from "./FileTreeContextMenu";
interface TreeCallbacks {
selectedPath: string | null;
onSelect: (path: string) => void;
onDelete: (path: string) => void;
/** PR-C: right-click → Download. Files only — directories ignore. */
onDownload: (path: string) => void;
/** Whether the active root permits delete. Wire into the Delete
* context-menu item's `disabled` flag so the user gets the same
* affordance as the toolbar (which gates Clear/New on /configs). */
canDelete: boolean;
/** PR-D: drop files/folders from the OS onto this row. targetDir
* is the directory path (relative to the active root) under which
* the dropped contents should land; "" means root. */
onDropToTarget?: (targetDir: string, items: DataTransferItemList) => void;
expandedDirs: Set<string>;
onToggleDir: (path: string) => void;
loadingDir: string | null;
}
/**
* FileTree renders the workspace tree + owns the right-click context
* menu (PR-C) and the drop-target hover state (PR-D). Lifting the
* menu state here (vs each row) means only one menu open at a time —
* opening a new row's menu auto-closes the prior one. Same UX as
* VSCode / Theia.
*/
export function FileTree({
nodes,
selectedPath,
onSelect,
onDelete,
onDownload,
canDelete,
onDropToTarget,
expandedDirs,
onToggleDir,
loadingDir,
depth = 0,
}: TreeCallbacks & { nodes: TreeNode[]; depth?: number }) {
const [menu, setMenu] = useState<{
x: number;
y: number;
items: MenuItem[];
} | null>(null);
// PR-D: hover-target highlight state for drag-drop. Lifted next to
// the menu state so both shared-across-rows interactions live in
// one place.
const [hoverDir, setHoverDir] = useState<string | null>(null);
const openContextMenu = (e: React.MouseEvent, node: TreeNode) => {
e.preventDefault();
// Items composed per-row so the available actions reflect the
// node type (files get Open + Download; directories get Delete
// only since "open a directory in the editor" doesn't apply
// and "Export folder" is the toolbar's job).
const items: MenuItem[] = [];
if (!node.isDir) {
items.push({
id: "open",
label: "Open",
icon: "⤴",
onClick: () => onSelect(node.path),
});
items.push({
id: "download",
label: "Download",
icon: "↓",
onClick: () => onDownload(node.path),
});
}
items.push({
id: "delete",
label: "Delete",
icon: "✕",
destructive: true,
disabled: !canDelete,
onClick: () => onDelete(node.path),
});
setMenu({ x: e.clientX, y: e.clientY, items });
};
// Single state lifted to the top-level tree; nested <FileTree>s
// (rendered for expanded directories below) do NOT instantiate
// their own menus or drop-targets — they call back via prop
// drilling. This keeps "only one menu open" + "only one drop
// target highlighted" as structural invariants rather than
// render-order coincidences.
const childCallbacks: TreeCallbacks = {
selectedPath,
onSelect,
onDelete,
onDownload,
canDelete,
onDropToTarget,
expandedDirs,
onToggleDir,
loadingDir,
};
return (
<div>
{nodes.map((node) => (
<TreeItem
key={`${node.path}:${node.isDir ? "dir" : "file"}`}
node={node}
selectedPath={selectedPath}
onSelect={onSelect}
onDelete={onDelete}
expandedDirs={expandedDirs}
onToggleDir={onToggleDir}
loadingDir={loadingDir}
openContextMenu={openContextMenu}
hoverDir={hoverDir}
setHoverDir={setHoverDir}
depth={depth}
{...childCallbacks}
/>
))}
{menu && (
<FileTreeContextMenu
x={menu.x}
y={menu.y}
items={menu.items}
onClose={() => setMenu(null)}
/>
)}
</div>
);
}
@@ -45,22 +133,81 @@ function TreeItem({
selectedPath,
onSelect,
onDelete,
onDownload,
canDelete,
onDropToTarget,
expandedDirs,
onToggleDir,
loadingDir,
depth,
}: TreeCallbacks & { node: TreeNode; depth: number }) {
openContextMenu,
hoverDir,
setHoverDir,
}: TreeCallbacks & {
node: TreeNode;
depth: number;
openContextMenu: (e: React.MouseEvent, node: TreeNode) => void;
hoverDir: string | null;
setHoverDir: (p: string | null) => void;
}) {
const isSelected = selectedPath === node.path;
const expanded = expandedDirs.has(node.path);
const isLoading = loadingDir === node.path;
const isDropTarget = node.isDir && hoverDir === node.path;
// PR-D drag handlers — only directory rows are valid drop targets
// (dropping a file ON another file is ambiguous; treat it as
// dropping in the parent dir, which the root area handles). When a
// drag enters a directory row, mark it the hover target. When the
// cursor leaves to a non-child element, clear it. drop fires the
// upload callback with the row's path.
const dragProps = node.isDir && onDropToTarget
? {
onDragOver: (e: React.DragEvent) => {
// preventDefault is REQUIRED to opt this element into the
// drop target list — without it, browsers refuse to fire
// the drop event regardless of the drop handler.
e.preventDefault();
e.dataTransfer.dropEffect = "copy";
},
onDragEnter: (e: React.DragEvent) => {
e.preventDefault();
setHoverDir(node.path);
},
onDragLeave: (e: React.DragEvent) => {
// Only clear hover when leaving to an element OUTSIDE this
// row — bare leave-events fire for every child crossed
// (the icon, the label, the ✕ button). Without the
// contains() check the highlight flickers.
const next = e.relatedTarget as Node | null;
if (!next || !(e.currentTarget as HTMLElement).contains(next)) {
setHoverDir(null);
}
},
onDrop: (e: React.DragEvent) => {
e.preventDefault();
e.stopPropagation();
setHoverDir(null);
if (e.dataTransfer.items?.length) {
onDropToTarget(node.path, e.dataTransfer.items);
}
},
}
: {};
if (node.isDir) {
return (
<div>
<div
className="group w-full flex items-center gap-1 px-2 py-0.5 text-left hover:bg-surface-card/40 transition-colors cursor-pointer"
className={`group w-full flex items-center gap-1 px-2 py-0.5 text-left transition-colors cursor-pointer ${
isDropTarget
? "bg-accent/20 outline outline-1 outline-accent/60"
: "hover:bg-surface-card/40"
}`}
style={{ paddingLeft: `${depth * 12 + 8}px` }}
onClick={() => onToggleDir(node.path)}
onContextMenu={(e) => openContextMenu(e, node)}
{...dragProps}
>
<span className="text-[9px] text-ink-soft w-3">{isLoading ? "…" : expanded ? "▼" : "▶"}</span>
<span className="text-[10px]">📁</span>
@@ -82,6 +229,9 @@ function TreeItem({
selectedPath={selectedPath}
onSelect={onSelect}
onDelete={onDelete}
onDownload={onDownload}
canDelete={canDelete}
onDropToTarget={onDropToTarget}
expandedDirs={expandedDirs}
onToggleDir={onToggleDir}
loadingDir={loadingDir}
@@ -99,6 +249,7 @@ function TreeItem({
}`}
style={{ paddingLeft: `${depth * 12 + 20}px` }}
onClick={() => onSelect(node.path)}
onContextMenu={(e) => openContextMenu(e, node)}
>
<span className="text-[9px]">{getIcon(node.name, false)}</span>
<span className="text-[10px] flex-1 truncate font-mono">{node.name}</span>
@@ -0,0 +1,141 @@
"use client";
import { useEffect, useRef } from "react";
/**
* FileTreeContextMenu — VSCode-style right-click menu for a single
* file-tree row. Pops at the cursor's viewport coords; dismisses on
* outside-click, Esc, blur, or scroll.
*
* Why a custom component (no library): the menu is one of several
* "small popovers" in canvas; pulling in a dnd / popover lib for one
* surface adds 10x the bytes of this implementation. The patterns
* (outside-click + Esc + portal-free fixed position) match the
* ContextMenu used in canvas/Toolbar so the keyboard-nav muscle
* memory is uniform.
*
* Items are rendered from a `MenuItem[]` so callers can add/remove
* actions without touching this component (e.g. PR-D will add an
* "Upload to this folder" item for directory rows).
*
* Accessibility:
* - role="menu" + role="menuitem" so screen readers announce the
* surface as a menu, not a generic div.
* - First item gets autofocus so keyboard users can ↓/↑/Enter without
* reaching for the mouse.
* - Esc + outside-click + Tab dismisses; behaves like every other
* menu the user has touched on the canvas.
*/
export interface MenuItem {
/** Stable identifier for testing + analytics. */
id: string;
label: string;
/** Optional left icon glyph; not load-bearing. */
icon?: string;
/** Destructive (rendered in red) — for Delete-class actions. */
destructive?: boolean;
/** Item-specific click handler. The menu auto-closes after onClick
* fires so handlers don't have to call onClose themselves. */
onClick: () => void;
/** Disabled items render but don't fire onClick (useful for
* Delete-on-non-/configs case where the caller wants to surface
* the item but explain it's gated). Currently unused — placeholder
* for future options. */
disabled?: boolean;
}
interface Props {
/** Viewport-coordinate position of the cursor that opened the menu. */
x: number;
y: number;
items: MenuItem[];
onClose: () => void;
}
export function FileTreeContextMenu({ x, y, items, onClose }: Props) {
const ref = useRef<HTMLDivElement>(null);
// First item gets initial focus for keyboard ↓/↑/Enter nav.
const firstItemRef = useRef<HTMLButtonElement>(null);
useEffect(() => {
firstItemRef.current?.focus();
}, []);
// Outside-click + Esc dismiss. Per memory
// (feedback_abort_controller_for_rerendered_listeners), use an
// AbortController so re-mounts (caller toggles the menu) don't leak
// listeners.
useEffect(() => {
const ctrl = new AbortController();
const onPointerDown = (e: MouseEvent) => {
if (ref.current && !ref.current.contains(e.target as Node)) onClose();
};
const onKeyDown = (e: KeyboardEvent) => {
if (e.key === "Escape") {
e.preventDefault();
onClose();
} else if (e.key === "ArrowDown" || e.key === "ArrowUp") {
// Roving focus across .menuitem buttons. Doing this with
// tabindex management because Tab / Shift+Tab leave the menu
// (which is the right thing — the user is escaping the menu).
e.preventDefault();
const buttons = ref.current?.querySelectorAll<HTMLButtonElement>(
"[role='menuitem']:not([disabled])",
);
if (!buttons || buttons.length === 0) return;
const arr = Array.from(buttons);
const cur = arr.indexOf(document.activeElement as HTMLButtonElement);
const next =
e.key === "ArrowDown"
? (cur + 1) % arr.length
: (cur - 1 + arr.length) % arr.length;
arr[next].focus();
}
};
// `mousedown` (not `click`) so the menu dismisses BEFORE the
// tree-row's click handler would fire — otherwise clicking
// outside also selects a different row, which is not what the
// user expected when "outside-click closes the menu".
document.addEventListener("mousedown", onPointerDown, { signal: ctrl.signal });
document.addEventListener("keydown", onKeyDown, { signal: ctrl.signal });
// Scroll inside any ancestor also dismisses — the fixed-position
// menu would otherwise stay anchored to viewport coords while the
// row it points at scrolled away. Use capture so we catch scroll
// on inner panels (FileTree's overflow-y-auto wrapper).
document.addEventListener("scroll", onClose, { signal: ctrl.signal, capture: true });
return () => ctrl.abort();
}, [onClose]);
return (
<div
ref={ref}
role="menu"
aria-label="File actions"
className="fixed z-[1000] min-w-[140px] py-1 bg-surface-elevated border border-line/60 rounded-md shadow-xl shadow-black/30 text-[11px]"
style={{ left: x, top: y }}
>
{items.map((item, i) => (
<button
key={item.id}
ref={i === 0 ? firstItemRef : undefined}
type="button"
role="menuitem"
disabled={item.disabled}
onClick={() => {
if (item.disabled) return;
item.onClick();
onClose();
}}
className={
item.destructive
? "w-full text-left px-3 py-1 text-bad hover:bg-red-900/30 focus:bg-red-900/30 focus:outline-none disabled:opacity-40 disabled:pointer-events-none transition-colors"
: "w-full text-left px-3 py-1 text-ink-mid hover:bg-surface-card hover:text-ink focus:bg-surface-card focus:text-ink focus:outline-none disabled:opacity-40 disabled:pointer-events-none transition-colors"
}
>
{item.icon && <span className="inline-block w-4 mr-1.5 text-ink-soft">{item.icon}</span>}
{item.label}
</button>
))}
</div>
);
}
@@ -0,0 +1,58 @@
"use client";
/**
* NotAvailablePanel — full-tab placeholder for runtimes whose filesystem
* the platform doesn't own (today: runtime === "external").
*
* Pre-fix the FilesTab tried to GET /workspaces/<id>/files for these
* workspaces. The platform answered with [] (no rows in workspace_files
* for an external workspace by definition), but the canvas rendered
* "0 files / No config files yet" which reads identically to the SaaS
* empty-listing bug fixed in PR-A. Showing an explicit placeholder
* makes the absence intentional and routes the user toward the
* supported surface (Chat) for these workspaces.
*
* Mirrors the same affordance TerminalTab adopted for runtimes without
* a TTY in PR #2830 — uniform "feature-not-applicable" UX across tabs.
*/
export function NotAvailablePanel({ runtime }: { runtime: string }) {
return (
<div className="flex flex-col items-center justify-center h-full p-8 text-center bg-surface-sunken/30">
{/* Folder-with-slash icon. Custom inline SVG so we don't depend
on an icon set being present at canvas build-time (matches
TerminalTab's NotAvailablePanel pattern). */}
<svg
width="72"
height="72"
viewBox="0 0 72 72"
fill="none"
aria-hidden="true"
className="text-ink-soft mb-4"
>
{/* Folder body */}
<path
d="M10 22 L10 56 a4 4 0 0 0 4 4 L58 60 a4 4 0 0 0 4 -4 L62 26 a4 4 0 0 0 -4 -4 L34 22 L28 16 L14 16 a4 4 0 0 0 -4 4 Z"
stroke="currentColor"
strokeWidth="2.5"
strokeLinejoin="round"
fill="none"
opacity="0.6"
/>
{/* Diagonal cancel slash */}
<path
d="M14 14 L58 58"
stroke="currentColor"
strokeWidth="3"
strokeLinecap="round"
/>
</svg>
<h3 className="text-sm font-medium text-ink mb-1.5">Files not available</h3>
<p className="text-[11px] text-ink-soft max-w-xs leading-relaxed">
This workspace runs the{" "}
<span className="font-mono text-ink-mid">{runtime}</span> runtime,
whose filesystem isn't owned by the platform. Use the Chat tab to
interact with the agent directly.
</p>
</div>
);
}
@@ -0,0 +1,136 @@
// @vitest-environment jsdom
//
// Pins the right-click context menu added in PR-C of issue #2999.
// VSCode-style affordance: Open / Download / Delete on file rows,
// Delete on directory rows. Delete is gated by `canDelete` (parent
// only enables on /configs root, matching the toolbar's gate).
//
// Pinned branches:
// 1. Right-click on a file row opens the menu at the click coords
// with Open + Download + Delete items.
// 2. Right-click on a directory row opens the menu with Delete
// only (no Open/Download — directories don't have one-click
// semantics in this surface).
// 3. Clicking Download fires the onDownload callback with the
// row's path.
// 4. Clicking Delete fires onDelete with the row's path (when
// canDelete=true).
// 5. Delete is disabled in the rendered menu when canDelete=false
// and clicking it does NOT fire onDelete (gate is real).
// 6. Esc dismisses the menu.
// 7. Click outside the menu dismisses it.
import { describe, it, expect, vi, afterEach } from "vitest";
import { render, screen, cleanup, fireEvent, act } from "@testing-library/react";
import React from "react";
import { FileTree } from "../FileTree";
import type { TreeNode } from "../tree";
afterEach(cleanup);
const file: TreeNode = { name: "config.yaml", path: "config.yaml", isDir: false, children: [], size: 0 };
const dir: TreeNode = {
name: "skills",
path: "skills",
isDir: true,
children: [],
size: 0,
};
function renderTree(props: Partial<React.ComponentProps<typeof FileTree>> = {}) {
const defaults = {
nodes: [file, dir],
selectedPath: null,
onSelect: vi.fn(),
onDelete: vi.fn(),
onDownload: vi.fn(),
canDelete: true,
expandedDirs: new Set<string>(),
onToggleDir: vi.fn(),
loadingDir: null,
};
const merged = { ...defaults, ...props };
return { ...render(<FileTree {...merged} />), props: merged };
}
describe("FileTree right-click context menu", () => {
it("right-click on a file row opens menu with Open/Download/Delete", () => {
renderTree();
fireEvent.contextMenu(screen.getByText("config.yaml"), {
clientX: 50,
clientY: 100,
});
expect(screen.getByRole("menu")).not.toBeNull();
expect(screen.getByRole("menuitem", { name: /Open/i })).not.toBeNull();
expect(screen.getByRole("menuitem", { name: /Download/i })).not.toBeNull();
expect(screen.getByRole("menuitem", { name: /Delete/i })).not.toBeNull();
});
it("right-click on a directory row opens menu with Delete only (no Open/Download)", () => {
renderTree();
fireEvent.contextMenu(screen.getByText("skills"), { clientX: 60, clientY: 120 });
expect(screen.getByRole("menu")).not.toBeNull();
expect(screen.queryByRole("menuitem", { name: /Open/i })).toBeNull();
expect(screen.queryByRole("menuitem", { name: /Download/i })).toBeNull();
expect(screen.getByRole("menuitem", { name: /Delete/i })).not.toBeNull();
});
it("clicking Download fires onDownload with the row's path", () => {
const { props } = renderTree();
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 0, clientY: 0 });
fireEvent.click(screen.getByRole("menuitem", { name: /Download/i }));
expect(props.onDownload).toHaveBeenCalledWith("config.yaml");
// Menu auto-closes after click.
expect(screen.queryByRole("menu")).toBeNull();
});
it("clicking Delete fires onDelete with the row's path when canDelete=true", () => {
const { props } = renderTree({ canDelete: true });
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 0, clientY: 0 });
fireEvent.click(screen.getByRole("menuitem", { name: /Delete/i }));
expect(props.onDelete).toHaveBeenCalledWith("config.yaml");
});
it("Delete is disabled when canDelete=false; clicking does not fire onDelete", () => {
const { props } = renderTree({ canDelete: false });
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 0, clientY: 0 });
const del = screen.getByRole("menuitem", { name: /Delete/i }) as HTMLButtonElement;
expect(del.disabled).toBe(true);
fireEvent.click(del);
expect(props.onDelete).not.toHaveBeenCalled();
// Menu stays open on disabled click — same as VSCode (the user
// can read the disabled-state hint without losing the menu).
expect(screen.getByRole("menu")).not.toBeNull();
});
it("Esc dismisses the menu", () => {
renderTree();
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 0, clientY: 0 });
expect(screen.getByRole("menu")).not.toBeNull();
act(() => {
fireEvent.keyDown(document, { key: "Escape" });
});
expect(screen.queryByRole("menu")).toBeNull();
});
it("click outside the menu dismisses it", () => {
renderTree();
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 0, clientY: 0 });
expect(screen.getByRole("menu")).not.toBeNull();
// mousedown on document.body — outside the menu.
act(() => {
fireEvent.mouseDown(document.body);
});
expect(screen.queryByRole("menu")).toBeNull();
});
it("opening a second context menu replaces the first (only one open at a time)", () => {
renderTree();
fireEvent.contextMenu(screen.getByText("config.yaml"), { clientX: 10, clientY: 10 });
fireEvent.contextMenu(screen.getByText("skills"), { clientX: 20, clientY: 20 });
// Only one menu in the DOM. The second open replaced the first
// because the menu state is lifted to the FileTree, not per-row.
const menus = screen.getAllByRole("menu");
expect(menus.length).toBe(1);
});
});
@@ -0,0 +1,212 @@
// @vitest-environment jsdom
//
// Pins the drag-drop upload added in PR-D of issue #2999.
// Two layers of coverage:
//
// 1. The pure walker (collectFileEntries / walkEntry) — pins the
// recursion shape against silent folder truncation. Browsers
// return up to ~100 entries per readEntries() call; if the loop
// stops early, large folder uploads silently drop files. We
// simulate a multi-batch reader to discriminate.
//
// 2. FileTree directory-row drop handlers — pins that dragover/drop
// events fire onDropToTarget with the directory's path + the
// drop's DataTransferItemList.
import { describe, it, expect, vi, afterEach } from "vitest";
import { render, screen, cleanup, fireEvent } from "@testing-library/react";
import React from "react";
import { FileTree } from "../FileTree";
import type { TreeNode } from "../tree";
import { __testables } from "../useFilesApi";
afterEach(cleanup);
// ---- Walker tests ----
/**
* Build a fake FileSystemEntry tree we can hand to walkEntry. The
* shape mimics what webkitGetAsEntry returns from a real OS drag —
* directory entries expose createReader, file entries expose file().
*/
function fakeFileEntry(name: string, content = "x"): {
isFile: true;
isDirectory: false;
name: string;
fullPath: string;
file: (cb: (f: File) => void) => void;
} {
return {
isFile: true,
isDirectory: false,
name,
fullPath: "/" + name,
file: (cb) => cb(new File([content], name, { type: "text/plain" })),
};
}
function fakeDirEntry(
name: string,
childBatches: ReturnType<typeof fakeFileEntry>[][],
): {
isFile: false;
isDirectory: true;
name: string;
fullPath: string;
createReader: () => { readEntries: (cb: (entries: unknown[]) => void) => void };
} {
let i = 0;
return {
isFile: false,
isDirectory: true,
name,
fullPath: "/" + name,
createReader: () => ({
readEntries: (cb) => {
// Mimic browser semantics: emit one batch per call, then
// an empty array to signal end-of-stream. A walker that
// calls readEntries only once would silently truncate at
// the first batch.
if (i < childBatches.length) {
cb(childBatches[i++]);
} else {
cb([]);
}
},
}),
};
}
describe("walkEntry — folder-recursion drop walker", () => {
it("collects a single dropped file", async () => {
const out: { file: File; relativePath: string }[] = [];
await __testables.walkEntry(fakeFileEntry("README.md") as never, "", out);
expect(out.length).toBe(1);
expect(out[0].relativePath).toBe("README.md");
expect(out[0].file.name).toBe("README.md");
});
it("walks a folder and preserves the relative path under the folder name", async () => {
const out: { file: File; relativePath: string }[] = [];
const folder = fakeDirEntry("skills", [
[fakeFileEntry("a.md"), fakeFileEntry("b.md")],
]);
await __testables.walkEntry(folder as never, "", out);
expect(out.map((e) => e.relativePath).sort()).toEqual([
"skills/a.md",
"skills/b.md",
]);
});
it("loops readEntries until empty so a multi-batch folder isn't truncated", async () => {
// Browsers limit each readEntries() call to ~100 entries. Our
// walker MUST call it again until an empty batch is returned.
// Fake reader emits two batches of 2 + an implicit empty → 4
// total. A buggy walker that only takes the first batch would
// see only 2.
const out: { file: File; relativePath: string }[] = [];
const folder = fakeDirEntry("big", [
[fakeFileEntry("1.txt"), fakeFileEntry("2.txt")],
[fakeFileEntry("3.txt"), fakeFileEntry("4.txt")],
]);
await __testables.walkEntry(folder as never, "", out);
expect(out.length).toBe(4);
});
it("walks nested directories and accumulates the full path", async () => {
const out: { file: File; relativePath: string }[] = [];
const inner = fakeDirEntry("web-search", [[fakeFileEntry("SKILL.md")]]);
// Outer dir whose first batch contains a sub-dir entry.
const outer = {
isFile: false,
isDirectory: true,
name: "skills",
fullPath: "/skills",
createReader: () => {
let i = 0;
return {
readEntries: (cb: (entries: unknown[]) => void) => {
if (i++ === 0) cb([inner]);
else cb([]);
},
};
},
};
await __testables.walkEntry(outer as never, "", out);
expect(out.length).toBe(1);
expect(out[0].relativePath).toBe("skills/web-search/SKILL.md");
});
});
// ---- FileTree drag-drop wiring ----
const file: TreeNode = { name: "config.yaml", path: "config.yaml", isDir: false, children: [], size: 0 };
const skillsDir: TreeNode = { name: "skills", path: "skills", isDir: true, children: [], size: 0 };
function renderTree(props: Partial<React.ComponentProps<typeof FileTree>> = {}) {
// PR-D test defaults must include PR-C's onDownload + canDelete now
// that they're required on the TreeCallbacks shape (the rebase
// surfaced this — the merged tree depends on both feature sets).
const defaults: React.ComponentProps<typeof FileTree> = {
nodes: [file, skillsDir],
selectedPath: null,
onSelect: vi.fn(),
onDelete: vi.fn(),
onDownload: vi.fn(),
canDelete: true,
onDropToTarget: vi.fn(),
expandedDirs: new Set<string>(),
onToggleDir: vi.fn(),
loadingDir: null,
};
const merged = { ...defaults, ...props };
return { ...render(<FileTree {...merged} />), props: merged };
}
describe("FileTree directory-row drag-drop", () => {
it("dragover on a directory row preventDefault's so the drop will fire", () => {
renderTree();
const row = screen.getByText("skills");
const dragOver = new Event("dragover", { bubbles: true, cancelable: true });
Object.defineProperty(dragOver, "dataTransfer", {
value: { dropEffect: "" },
});
row.parentElement!.dispatchEvent(dragOver);
// preventDefault registers via the React handler — without it
// the drop event would never fire, so this assertion is the
// load-bearing one.
expect(dragOver.defaultPrevented).toBe(true);
});
it("drop on a directory row fires onDropToTarget with that path + the items list", () => {
const { props } = renderTree();
const row = screen.getByText("skills").parentElement!;
const fakeItems = { length: 1, 0: { kind: "file" } } as unknown as DataTransferItemList;
fireEvent.drop(row, { dataTransfer: { items: fakeItems } });
expect(props.onDropToTarget).toHaveBeenCalledWith("skills", fakeItems);
});
it("drop on a FILE row does NOT fire onDropToTarget (only directories are valid targets)", () => {
const { props } = renderTree();
const fileRow = screen.getByText("config.yaml").parentElement!;
const fakeItems = { length: 1, 0: { kind: "file" } } as unknown as DataTransferItemList;
fireEvent.drop(fileRow, { dataTransfer: { items: fakeItems } });
expect(props.onDropToTarget).not.toHaveBeenCalled();
});
it("drop with no DataTransferItems does NOT fire onDropToTarget", () => {
const { props } = renderTree();
const row = screen.getByText("skills").parentElement!;
fireEvent.drop(row, { dataTransfer: { items: { length: 0 } } });
expect(props.onDropToTarget).not.toHaveBeenCalled();
});
it("dragenter sets the drop-target highlight on the directory row", () => {
renderTree();
const row = screen.getByText("skills").parentElement!;
fireEvent.dragEnter(row, { dataTransfer: {} });
// Highlight class is the discriminator — without dragenter
// wiring the row stays in its hover-only style.
expect(row.className).toMatch(/bg-accent|outline-accent/);
});
});
@@ -90,6 +90,43 @@ export function useFilesApi(workspaceId: string, root: string) {
[workspaceId]
);
/**
* Fetch a file's content from the server and trigger a browser
* download. Used by the right-click "Download" context-menu item
* (PR-C of issue #2999) — distinct from `handleDownloadFile` in
* FilesTab which downloads the CURRENTLY-OPEN-IN-EDITOR file from
* the in-memory `editContent` buffer (so unsaved edits round-trip
* to disk). This helper downloads the on-server content, suitable
* for arbitrary tree rows the user hasn't opened.
*/
const downloadFileByPath = useCallback(
async (path: string) => {
try {
const res = await api.get<{ content: string }>(
`/workspaces/${workspaceId}/files/${path}?root=${encodeURIComponent(root)}`,
);
// text/plain is correct for the canvas's text-only file
// surface (config.yaml, prompts, skill markdown). Binary
// files would need an Accept-arraybuffer path; the API
// returns string today so this matches the wire shape.
const blob = new Blob([res.content], { type: "text/plain" });
const url = URL.createObjectURL(blob);
const a = document.createElement("a");
a.href = url;
a.download = path.split("/").pop() || "file";
a.click();
URL.revokeObjectURL(url);
showToast(`Downloaded ${a.download}`, "success");
} catch (e) {
showToast(
`Download failed: ${e instanceof Error ? e.message : "unknown error"}`,
"error",
);
}
},
[workspaceId, root],
);
const downloadAllFiles = useCallback(async () => {
const fileEntries = files.filter((f) => !f.dir);
const results = await Promise.allSettled(
@@ -114,16 +151,20 @@ export function useFilesApi(workspaceId: string, root: string) {
}, [files, workspaceId]);
const uploadFiles = useCallback(
async (fileList: FileList) => {
async (fileList: FileList, targetDir = "") => {
let uploaded = 0;
for (const file of Array.from(fileList)) {
const path = file.webkitRelativePath || file.name;
const parts = path.split("/");
// For folder picker: webkitRelativePath is "<picked-folder>/a/b.txt"
// — strip the picked-folder prefix so files land flat under the
// workspace's target dir, not under a redundant outer folder.
const relPath = parts.length > 1 ? parts.slice(1).join("/") : parts[0];
const finalPath = targetDir ? `${targetDir}/${relPath}` : relPath;
if (file.size > 1_000_000) continue;
try {
const content = await file.text();
await api.put(`/workspaces/${workspaceId}/files/${relPath}`, { content });
await api.put(`/workspaces/${workspaceId}/files/${finalPath}`, { content });
uploaded++;
} catch {
/* skip binary */
@@ -131,7 +172,7 @@ export function useFilesApi(workspaceId: string, root: string) {
}
if (uploaded > 0) {
useCanvasStore.getState().updateNodeData(workspaceId, { needsRestart: true });
showToast(`Uploaded ${uploaded} files`, "success");
showToast(`Uploaded ${uploaded} files${targetDir ? ` to ${targetDir}` : ""}`, "success");
loadFiles();
}
return uploaded;
@@ -139,6 +180,58 @@ export function useFilesApi(workspaceId: string, root: string) {
[workspaceId, loadFiles]
);
/**
* Upload files dragged from the OS via the HTML5 DataTransferItemList
* API. Unlike the folder-picker path (uploadFiles), this preserves
* the dropped folder structure under `targetDir` — drag a "skills/"
* folder onto the /configs/skills row and you get
* /configs/skills/skills/* (the OUTER folder name is preserved
* because the user explicitly chose to drop a NAMED folder, unlike
* the folder-picker which always wraps the picked dir).
*
* Walks FileSystemDirectoryEntry recursively via webkitGetAsEntry.
* VSCode/JupyterLab use the same primitive — there's no other
* portable browser API for "drag a folder from OS". `webkit*`
* naming is a Chromium relic; Firefox + Safari implement the same
* surface.
*
* Returns the number of files uploaded so the caller can show a
* tally / fail toast.
*/
const uploadDataTransferItems = useCallback(
async (items: DataTransferItemList, targetDir = "") => {
const fileEntries = collectFileEntries(items);
let uploaded = 0;
for (const { file, relativePath } of await fileEntries) {
if (file.size > 1_000_000) continue;
const finalPath = targetDir
? `${targetDir}/${relativePath}`
: relativePath;
try {
const content = await file.text();
await api.put(`/workspaces/${workspaceId}/files/${finalPath}`, {
content,
});
uploaded++;
} catch {
/* skip binary */
}
}
if (uploaded > 0) {
useCanvasStore
.getState()
.updateNodeData(workspaceId, { needsRestart: true });
showToast(
`Uploaded ${uploaded} file${uploaded === 1 ? "" : "s"}${targetDir ? ` to ${targetDir}` : ""}`,
"success",
);
loadFiles();
}
return uploaded;
},
[workspaceId, loadFiles],
);
const deleteAllFiles = useCallback(async () => {
let deleted = 0;
for (const f of files) {
@@ -165,8 +258,98 @@ export function useFilesApi(workspaceId: string, root: string) {
readFile,
writeFile,
deleteFile,
downloadFileByPath,
downloadAllFiles,
uploadFiles,
uploadDataTransferItems,
deleteAllFiles,
};
}
// ----- DataTransfer entry walker (PR-D) ---------------------------------
/**
* Minimal subset of the FileSystem Entry API surface we use. The DOM
* lib types this as FileSystemEntry / FileSystemFileEntry /
* FileSystemDirectoryEntry but the relevant methods are callback-
* based. Keep the shape narrow + explicit so the recursion below
* type-checks without pulling in the full DOM lib types.
*/
interface FSEntry {
isFile: boolean;
isDirectory: boolean;
name: string;
fullPath: string;
file?(success: (f: File) => void, fail?: (e: unknown) => void): void;
createReader?(): { readEntries(success: (entries: FSEntry[]) => void): void };
}
interface CollectedEntry {
file: File;
/** Path relative to the dropped root (e.g. "skills/web-search/SKILL.md"
* for a dropped "skills/" folder containing web-search/SKILL.md). */
relativePath: string;
}
/**
* Walk a DataTransferItemList, returning every file entry as a flat
* array keyed by the path relative to the originally-dropped item.
* Folders dropped from the OS expand recursively; loose files
* passthrough with name as the relative path.
*
* Skips items where webkitGetAsEntry() returns null — that's how
* the browser signals a non-file payload (e.g. a dragged URL or
* text snippet).
*/
async function collectFileEntries(
items: DataTransferItemList,
): Promise<CollectedEntry[]> {
const out: CollectedEntry[] = [];
for (let i = 0; i < items.length; i++) {
const item = items[i];
if (item.kind !== "file") continue;
// webkitGetAsEntry is the standardised name; older Firefox used
// getAsEntry. Both Chromium + Firefox + Safari ship the webkit-
// prefixed variant today. There's no non-prefixed alternative.
const entry = (item as DataTransferItem & {
webkitGetAsEntry?: () => FSEntry | null;
}).webkitGetAsEntry?.();
if (!entry) continue;
await walkEntry(entry, "", out);
}
return out;
}
async function walkEntry(
entry: FSEntry,
prefix: string,
out: CollectedEntry[],
): Promise<void> {
const name = entry.name;
const relPath = prefix ? `${prefix}/${name}` : name;
if (entry.isFile && entry.file) {
const file = await new Promise<File>((resolve, reject) => {
entry.file!(resolve, reject);
});
out.push({ file, relativePath: relPath });
return;
}
if (entry.isDirectory && entry.createReader) {
const reader = entry.createReader();
// readEntries returns up to ~100 at a time on Chromium; loop
// until empty so large folders aren't truncated.
let batch: FSEntry[] = [];
do {
batch = await new Promise<FSEntry[]>((resolve) =>
reader.readEntries(resolve),
);
for (const child of batch) {
await walkEntry(child, relPath, out);
}
} while (batch.length > 0);
}
}
// Exported for direct testing — the recursion + readEntries batching
// is the part most likely to silently truncate a real folder upload.
export const __testables = { collectFileEntries, walkEntry };
+42 -1
View File
@@ -297,10 +297,49 @@ export function SkillsTab({ workspaceId, data }: Props) {
}
};
// Compact-empty pattern: when the workspace has zero plugins
// installed AND the registry isn't open, collapse the whole
// "Plugins" section into a single inline pill rather than rendering
// the full panel chrome. Reported on production 2026-05-05 (#2971):
// the empty state's panel-with-zero-list-rows layout gives the user
// a lot of vertical real estate for content that's just "0
// installed + Install button". The compact form keeps that
// affordance without the chrome.
//
// Expanded/full layout still fires when installed.length > 0 OR
// when the user opens the registry (clicked "+ Install Plugin").
// Once a plugin is installed the section auto-expands to surface
// the list.
const compactEmpty = installed.length === 0 && !showRegistry && installedLoaded;
if (compactEmpty) {
return (
<div className="p-4 space-y-4">
<div
className="flex items-center justify-between gap-2 rounded-full border border-line/60 bg-surface-sunken/70 px-3 py-1.5"
aria-label="Plugins (none installed)"
>
<div className="flex items-center gap-2">
<span className="text-[10px] uppercase tracking-[0.2em] text-ink-soft">Plugins</span>
<span className="text-[11px] text-ink-mid">0 installed</span>
</div>
<button
onClick={() => setShowRegistry(true)}
className="rounded-full border border-violet-700/50 bg-violet-950/30 px-3 py-0.5 text-[10px] text-violet-200 hover:bg-violet-900/40 transition-colors"
aria-expanded="false"
aria-controls="plugins-section"
>
+ Install Plugin
</button>
</div>
</div>
);
}
return (
<div className="p-4 space-y-4">
{/* Plugins section */}
<div className="rounded-xl border border-line bg-surface-sunken/70 p-3">
<div id="plugins-section" className="rounded-xl border border-line bg-surface-sunken/70 p-3">
<div className="flex items-center justify-between gap-3">
<div>
<div className="text-[10px] uppercase tracking-[0.22em] text-ink-soft">Plugins</div>
@@ -311,6 +350,8 @@ export function SkillsTab({ workspaceId, data }: Props) {
<button
onClick={() => setShowRegistry(!showRegistry)}
className="rounded-full border border-violet-700/50 bg-violet-950/30 px-3 py-1 text-[10px] text-violet-200 hover:bg-violet-900/40 transition-colors"
aria-expanded={showRegistry}
aria-controls="plugins-registry"
>
{showRegistry ? "Hide Registry" : "+ Install Plugin"}
</button>
@@ -0,0 +1,141 @@
// @vitest-environment jsdom
//
// Pins two regressions reported on production 2026-05-05:
//
// 1. IME composition + Enter key: typing Chinese (or any CJK / IME-
// composed text) and pressing Enter to commit the candidate
// selection used to send the half-typed message. The fix checks
// `event.nativeEvent.isComposing` (and a `keyCode === 229`
// fallback for older WebKit) before treating Enter as send.
//
// 2. Markdown link clicks: the agent's ReactMarkdown-rendered links
// used to:
// - http/https → navigate canvas tab away (user lost canvas state)
// - workspace://path / file:///workspace/... / /workspace/... →
// browser hit about:blank (unhandled protocol).
// Fix: external links get target="_blank" + noopener; in-container
// paths route through downloadChatFile (same auth path as chips).
import { describe, it, expect, vi, afterEach, beforeEach } from "vitest";
import { render, screen, cleanup, fireEvent, waitFor } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
// Mock the api module so render doesn't try to talk to a real CP.
const apiGet = vi.fn((_path: string): Promise<unknown> => Promise.resolve([]));
const apiPost = vi.fn((_path: string, _body: unknown): Promise<unknown> => Promise.resolve({}));
vi.mock("@/lib/api", () => ({
api: {
get: (path: string) => apiGet(path),
post: (path: string, body: unknown) => apiPost(path, body),
del: vi.fn(),
patch: vi.fn(),
put: vi.fn(),
},
}));
vi.mock("@/store/canvas", () => ({
useCanvasStore: vi.fn((selector?: (s: unknown) => unknown) =>
selector ? selector({ agentMessages: {}, consumeAgentMessages: () => [] }) : {},
),
}));
// Capture the downloadChatFile call so the markdown-link test can
// assert in-container paths route through the authenticated download
// path rather than the browser's bare anchor click.
const downloadChatFileMock = vi.fn((_workspaceId: string, _att: { uri: string; name: string }) => Promise.resolve());
vi.mock("../chat/uploads", async () => {
const actual = await vi.importActual<typeof import("../chat/uploads")>("../chat/uploads");
return {
...actual,
downloadChatFile: (workspaceId: string, att: { uri: string; name: string }) =>
downloadChatFileMock(workspaceId, att),
};
});
beforeEach(() => {
apiGet.mockClear();
apiPost.mockClear();
downloadChatFileMock.mockClear();
// jsdom doesn't implement scrollIntoView; ChatTab calls it after
// every render with a new message.
Element.prototype.scrollIntoView = vi.fn();
// Stub IntersectionObserver — the lazy-history sentinel uses it.
class FakeIO {
observe() {}
unobserve() {}
disconnect() {}
}
(window as unknown as { IntersectionObserver: unknown }).IntersectionObserver = FakeIO;
(globalThis as unknown as { IntersectionObserver: unknown }).IntersectionObserver = FakeIO;
});
import { ChatTab } from "../ChatTab";
const minimalData = {
status: "online" as const,
runtime: "claude-code",
currentTask: null,
} as unknown as Parameters<typeof ChatTab>[0]["data"];
describe("ChatTab — IME-safe Enter key", () => {
it("does NOT send the message when Enter fires during IME composition (isComposing)", async () => {
render(<ChatTab workspaceId="ws-ime" data={minimalData} />);
// Find the textarea by its aria-label.
const textarea = await screen.findByLabelText(/Message to agent/i);
fireEvent.change(textarea, { target: { value: "你好" } });
// Simulate the Enter that commits an IME selection: isComposing=true.
fireEvent.keyDown(textarea, { key: "Enter", isComposing: true });
// sendMessage POSTs via api.post; assert it was NOT called.
await waitFor(() => {
expect(apiPost).not.toHaveBeenCalled();
});
// And the input is preserved — ChatTab clears it only on actual send.
expect((textarea as HTMLTextAreaElement).value).toBe("你好");
});
it("does NOT send when keyCode is 229 (older Safari IME fallback)", async () => {
render(<ChatTab workspaceId="ws-ime2" data={minimalData} />);
const textarea = await screen.findByLabelText(/Message to agent/i);
fireEvent.change(textarea, { target: { value: "한국어" } });
// keyCode 229 is the older-Safari signal that an IME is composing.
// Some mobile WebKit-based browsers delay setting isComposing on
// the composition-end Enter; the keyCode fallback covers that.
fireEvent.keyDown(textarea, { key: "Enter", keyCode: 229 });
await waitFor(() => {
expect(apiPost).not.toHaveBeenCalled();
});
});
it("DOES send on a non-composing Enter (the happy path stays intact)", async () => {
render(<ChatTab workspaceId="ws-ok" data={minimalData} />);
const textarea = await screen.findByLabelText(/Message to agent/i);
fireEvent.change(textarea, { target: { value: "hello world" } });
fireEvent.keyDown(textarea, { key: "Enter" /* no isComposing, no 229 */ });
// The api.post for /a2a fires inside sendMessage. waitFor since
// the call goes through several effects.
await waitFor(() => {
expect(apiPost).toHaveBeenCalled();
});
});
it("Shift+Enter inserts newline regardless (no send)", async () => {
render(<ChatTab workspaceId="ws-shift" data={minimalData} />);
const textarea = await screen.findByLabelText(/Message to agent/i);
fireEvent.change(textarea, { target: { value: "line 1" } });
fireEvent.keyDown(textarea, { key: "Enter", shiftKey: true });
await waitFor(() => {
expect(apiPost).not.toHaveBeenCalled();
});
});
});
@@ -0,0 +1,119 @@
// @vitest-environment jsdom
//
// Pins the "Files not available" early-return for runtimes whose
// filesystem the platform doesn't own (today: runtime === "external").
//
// Pre-fix: FilesTab issued a GET /workspaces/<id>/files for every
// workspace. The platform's response for an external workspace is
// always [] (no rows in workspace_files), but the canvas rendered
// "0 files / No config files yet" — visually identical to the SaaS
// empty-listing bug fixed in PR-A. The placeholder makes the absence
// intentional.
//
// Pinned branches:
// 1. external runtime → "Files not available" banner renders,
// runtime name surfaces in the body so user knows WHY.
// 2. external runtime → useFilesApi is NOT invoked. Verified by
// asserting the mocked api.get was never called.
// 3. claude-code (or any other runtime) → no banner, normal mount
// proceeds (`/configs` toolbar visible). Pre-fix regression cover.
// 4. data prop omitted (legacy callers) → no early-return, falls
// through to normal mount.
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
import { render, screen, cleanup, waitFor } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
// Mock the api module so the normal-mount branches don't try to
// fetch against a real backend — and so we can assert the
// external-runtime branch never fires a request.
const apiCalls: string[] = [];
vi.mock("@/lib/api", () => ({
api: {
get: vi.fn((path: string) => {
apiCalls.push(path);
return Promise.resolve([]);
}),
put: vi.fn(() => Promise.resolve()),
del: vi.fn(() => Promise.resolve()),
},
}));
// useCanvasStore is referenced by useFilesApi for the needsRestart
// flag. The Toaster import inside FilesTab also pulls the store
// indirectly. Stub minimally to satisfy the import chain.
vi.mock("@/store/canvas", async () => {
const actual = await vi.importActual<typeof import("@/store/canvas")>(
"@/store/canvas",
);
return {
...actual,
useCanvasStore: {
getState: () => ({
updateNodeData: vi.fn(),
}),
},
};
});
vi.mock("../Toaster", () => ({
showToast: vi.fn(),
}));
beforeEach(() => {
apiCalls.length = 0;
});
import { FilesTab } from "../FilesTab";
const externalData = { runtime: "external", status: "online" } as unknown as Parameters<
typeof FilesTab
>[0]["data"];
const claudeData = { runtime: "claude-code", status: "online" } as unknown as Parameters<
typeof FilesTab
>[0]["data"];
describe("FilesTab not-available early-return for runtimes without platform-owned filesystem", () => {
it("external runtime renders the not-available banner with runtime name", () => {
render(<FilesTab workspaceId="ws-ext" data={externalData} />);
expect(screen.getByText(/Files not available/i)).not.toBeNull();
// Runtime name must surface so the user understands WHY — without
// it the placeholder reads as a generic error.
expect(screen.getByText(/external/)).not.toBeNull();
// Chat tab is the recommended alternative — flagged in copy so the
// user knows where to go next instead of bouncing tabs.
expect(screen.getByText(/Chat tab/i)).not.toBeNull();
});
it("external runtime does NOT issue any /files API call", async () => {
render(<FilesTab workspaceId="ws-ext" data={externalData} />);
// Tolerate one microtask boundary in case useEffect schedules.
await new Promise((r) => setTimeout(r, 0));
const filesCalls = apiCalls.filter((p) => p.includes("/files"));
expect(filesCalls).toEqual([]);
});
it("claude-code runtime does NOT render the banner (normal mount)", async () => {
render(<FilesTab workspaceId="ws-claude" data={claudeData} />);
// The normal-mount path renders the FilesToolbar with the root
// selector. Wait for it (useEffect → loadFiles → setLoading false).
await waitFor(() => {
expect(screen.queryByText(/Files not available/i)).toBeNull();
});
// Toolbar's root selector confirms we're on the platform-owned
// rendering path, not the placeholder.
expect(screen.getByLabelText(/File root directory/i)).not.toBeNull();
});
it("data prop omitted falls through to normal mount (back-compat)", async () => {
render(<FilesTab workspaceId="ws-no-data" />);
await waitFor(() => {
expect(screen.queryByText(/Files not available/i)).toBeNull();
});
// Without data we can't gate on runtime — must mount normally.
expect(screen.getByLabelText(/File root directory/i)).not.toBeNull();
});
});
@@ -1,220 +0,0 @@
// @vitest-environment jsdom
//
// Pins the Edit affordance added to MemoryTab. Until this PR the Memory tab
// was Add+Delete only; an entry that needed correction had to be deleted and
// re-added — losing the version-counter and any in-flight optimistic-locking
// invariants other writers depend on.
//
// Each test pins one branch of the new flow. If any fails, the bug is back.
import { describe, it, expect, vi, afterEach, beforeEach } from "vitest";
import { render, screen, cleanup, waitFor, fireEvent } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
const apiGet = vi.fn();
const apiPost = vi.fn();
const apiDel = vi.fn();
vi.mock("@/lib/api", () => ({
api: {
get: (path: string) => apiGet(path),
post: (path: string, body: unknown) => apiPost(path, body),
del: (path: string) => apiDel(path),
patch: vi.fn(),
put: vi.fn(),
},
}));
import { MemoryTab } from "../MemoryTab";
const sampleEntries = [
{
key: "team_brief",
value: { goal: "ship v2" },
version: 3,
expires_at: null,
updated_at: "2026-05-04T10:00:00Z",
},
{
key: "plain_note",
value: "raw text note",
version: 1,
expires_at: "2099-01-01T00:00:00Z",
updated_at: "2026-05-04T10:01:00Z",
},
];
beforeEach(() => {
apiGet.mockReset();
apiPost.mockReset();
apiDel.mockReset();
apiGet.mockImplementation((path: string) => {
if (path === "/workspaces/ws-test/memory") {
return Promise.resolve(sampleEntries);
}
return Promise.reject(new Error(`unmocked api.get: ${path}`));
});
});
async function renderAndExpand(key: string) {
render(<MemoryTab workspaceId="ws-test" />);
await waitFor(() => expect(apiGet).toHaveBeenCalled());
// Reveal the Advanced section that hosts the entry list.
const showAdvanced = await screen.findByRole("button", { name: "Show" });
fireEvent.click(showAdvanced);
// Expand the row.
const row = await screen.findByRole("button", { name: new RegExp(key) });
fireEvent.click(row);
}
describe("MemoryTab Edit affordance", () => {
it("Edit button appears once a row is expanded", async () => {
await renderAndExpand("team_brief");
expect(screen.getAllByRole("button", { name: "Edit" }).length).toBeGreaterThan(0);
});
it("clicking Edit on a JSON-valued entry pre-fills the textarea with pretty JSON", async () => {
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = (await screen.findByLabelText(
"Edit value for team_brief",
)) as HTMLTextAreaElement;
expect(textarea.value).toBe('{\n "goal": "ship v2"\n}');
});
it("clicking Edit on a string-valued entry pre-fills raw (no surrounding quotes)", async () => {
await renderAndExpand("plain_note");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = (await screen.findByLabelText(
"Edit value for plain_note",
)) as HTMLTextAreaElement;
expect(textarea.value).toBe("raw text note");
});
it("Save POSTs with if_match_version + parsed value, then reloads", async () => {
apiPost.mockResolvedValue({ status: "ok", key: "team_brief", version: 4 });
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = await screen.findByLabelText("Edit value for team_brief");
fireEvent.change(textarea, { target: { value: '{"goal":"ship v3"}' } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
expect(apiPost).toHaveBeenCalledWith("/workspaces/ws-test/memory", {
key: "team_brief",
value: { goal: "ship v3" },
if_match_version: 3,
});
// Reload after save → second GET.
await waitFor(() => expect(apiGet).toHaveBeenCalledTimes(2));
});
it("Save with non-JSON text falls back to plain string", async () => {
apiPost.mockResolvedValue({ status: "ok" });
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = await screen.findByLabelText("Edit value for team_brief");
fireEvent.change(textarea, { target: { value: "free-form note" } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
expect(apiPost.mock.calls[0][1].value).toBe("free-form note");
});
it("TTL field is forwarded as ttl_seconds when set", async () => {
apiPost.mockResolvedValue({ status: "ok" });
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const ttlInput = await screen.findByLabelText("Edit TTL for team_brief");
fireEvent.change(ttlInput, { target: { value: "3600" } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
expect(apiPost.mock.calls[0][1].ttl_seconds).toBe(3600);
});
it("blank/zero/non-numeric TTL is omitted from the payload", async () => {
apiPost.mockResolvedValue({ status: "ok" });
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const ttlInput = await screen.findByLabelText("Edit TTL for team_brief");
// Junk + zero both must drop out — payload must not contain ttl_seconds.
fireEvent.change(ttlInput, { target: { value: "abc" } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
expect(apiPost.mock.calls[0][1]).not.toHaveProperty("ttl_seconds");
});
it("Cancel discards edits and restores the rendered value", async () => {
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = await screen.findByLabelText("Edit value for team_brief");
fireEvent.change(textarea, { target: { value: '{"goal":"discarded"}' } });
fireEvent.click(screen.getByRole("button", { name: "Cancel" }));
expect(apiPost).not.toHaveBeenCalled();
// Editor is gone; the JSON pre-block is back.
expect(screen.queryByLabelText("Edit value for team_brief")).toBeNull();
expect(screen.getAllByText(/"goal": "ship v2"/i).length).toBeGreaterThan(0);
});
it("409 response surfaces a retry hint and reloads", async () => {
apiPost.mockRejectedValueOnce(
new Error("HTTP 409: if_match_version mismatch"),
);
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = await screen.findByLabelText("Edit value for team_brief");
fireEvent.change(textarea, { target: { value: '{"goal":"ship v3"}' } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
const alert = await screen.findByRole("alert");
expect(alert.textContent).toMatch(/changed since you opened it/i);
// Initial mount load + post-conflict reload.
await waitFor(() => expect(apiGet).toHaveBeenCalledTimes(2));
});
it("non-409 error surfaces the message and does not reload", async () => {
apiPost.mockRejectedValueOnce(new Error("boom"));
await renderAndExpand("team_brief");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
fireEvent.click(screen.getByRole("button", { name: "Save" }));
const alert = await screen.findByRole("alert");
expect(alert.textContent).toBe("boom");
// Only the initial mount load — no retry reload.
expect(apiGet).toHaveBeenCalledTimes(1);
});
it("entry with no version omits if_match_version (back-compat with older shape)", async () => {
// Pre-version-counter shape: drop the `version` field from the row.
apiGet.mockReset();
apiGet.mockImplementation((path: string) => {
if (path === "/workspaces/ws-test/memory") {
return Promise.resolve([
{
key: "old_entry",
value: "legacy",
expires_at: null,
updated_at: "2026-05-04T10:00:00Z",
},
]);
}
return Promise.reject(new Error(`unmocked: ${path}`));
});
apiPost.mockResolvedValue({ status: "ok" });
await renderAndExpand("old_entry");
fireEvent.click(screen.getAllByRole("button", { name: "Edit" })[0]);
const textarea = await screen.findByLabelText("Edit value for old_entry");
fireEvent.change(textarea, { target: { value: "updated" } });
fireEvent.click(screen.getByRole("button", { name: "Save" }));
await waitFor(() => expect(apiPost).toHaveBeenCalledTimes(1));
const payload = apiPost.mock.calls[0][1];
expect(payload).not.toHaveProperty("if_match_version");
expect(payload.value).toBe("updated");
});
});
@@ -0,0 +1,141 @@
// @vitest-environment jsdom
//
// Pins the compact-when-empty layout for the SkillsTab Plugins section
// (issue #2971, reported on production 2026-05-05).
//
// Three states matter for layout:
// 1. installed.length === 0 + registry closed + load completed → COMPACT pill
// 2. installed.length > 0 → FULL panel + installed list
// 3. registry open (showRegistry=true) → FULL panel + registry browser
//
// The compact-empty path is the new behavior; the other two were
// pre-existing. This test pins all three so a future refactor that
// over-collapses (showing compact when plugins are installed) or
// over-expands (showing full panel on empty load) fails loudly.
import { describe, it, expect, vi, beforeEach, afterEach } from "vitest";
import { render, screen, cleanup, fireEvent, waitFor } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
const apiGet = vi.fn();
vi.mock("@/lib/api", () => ({
api: {
get: (path: string, opts?: unknown) => apiGet(path, opts),
post: vi.fn(() => Promise.resolve({})),
del: vi.fn(),
patch: vi.fn(),
put: vi.fn(),
},
}));
beforeEach(() => {
apiGet.mockReset();
Element.prototype.scrollIntoView = vi.fn();
});
import { SkillsTab } from "../SkillsTab";
const minimalData = {
status: "online" as const,
runtime: "claude-code",
currentTask: "",
agentCard: undefined,
} as unknown as Parameters<typeof SkillsTab>[0]["data"];
describe("SkillsTab Plugins compact-empty layout", () => {
it("renders compact pill when installed.length === 0 and registry closed", async () => {
// Both fetches return empty arrays — workspace is fresh, no plugins.
apiGet.mockImplementation((path: string) => {
if (path.endsWith("/plugins") || path === "/plugins" || path === "/plugins/sources") {
return Promise.resolve([]);
}
return Promise.resolve([]);
});
render(<SkillsTab workspaceId="ws-fresh" data={minimalData} />);
// Wait for the installedLoaded gate to flip — without that the
// component renders a "loading" state, not the compact pill.
await waitFor(() => {
expect(screen.getByLabelText(/Plugins \(none installed\)/i)).toBeTruthy();
});
// Compact assertions: the rounded-xl panel chrome MUST NOT be in
// the DOM (we'd see two "Plugins" labels — one in the header,
// one in the pill — if the layout regressed to "always full
// panel"). The compact form has exactly one "Plugins" label.
const labels = screen.getAllByText("Plugins");
expect(labels).toHaveLength(1);
// The full-panel chrome's id="plugins-section" should NOT be
// rendered when we're in compact mode.
expect(document.getElementById("plugins-section")).toBeNull();
});
it("renders full panel when installed.length > 0", async () => {
apiGet.mockImplementation((path: string) => {
if (path.endsWith("/plugins")) {
return Promise.resolve([
{ name: "memory-postgres", version: "1.0.0", description: "memory backend", supported_on_runtime: true },
]);
}
return Promise.resolve([]);
});
render(<SkillsTab workspaceId="ws-installed" data={minimalData} />);
await waitFor(() => {
expect(screen.getByText(/1 installed/i)).toBeTruthy();
});
// Full-panel chrome MUST be present — id pin.
expect(document.getElementById("plugins-section")).not.toBeNull();
// Compact pill ariaLabel MUST NOT be present.
expect(screen.queryByLabelText(/Plugins \(none installed\)/i)).toBeNull();
});
it("expands to full panel when user clicks + Install Plugin from compact pill", async () => {
apiGet.mockImplementation(() => Promise.resolve([]));
render(<SkillsTab workspaceId="ws-expand" data={minimalData} />);
// Start compact — wait for the compact pill to settle so we click
// the right button (initial render before installedLoaded flips
// doesn't have either layout, and the post-load compact pill is
// what we want to interact with).
await waitFor(() => {
expect(screen.getByLabelText(/Plugins \(none installed\)/i)).toBeTruthy();
});
const installBtn = screen.getByRole("button", { name: /\+ Install Plugin/i });
expect(installBtn.getAttribute("aria-expanded")).toBe("false");
fireEvent.click(installBtn);
// After click, registry opens → full panel renders. The compact
// pill's aria-label should be gone; the full-panel id should
// appear. Generous waitFor — a registry fetch may also fire in
// the React effect chain, and we want to assert the compact →
// full transition without racing it.
await waitFor(
() => {
expect(document.getElementById("plugins-section")).not.toBeNull();
},
{ timeout: 3000 },
);
expect(screen.queryByLabelText(/Plugins \(none installed\)/i)).toBeNull();
});
it("does NOT collapse to compact while initial load is pending (avoid flash)", () => {
// Returning a never-resolving promise means installedLoaded stays
// false. The compact pill MUST NOT render in this state — that
// would flash compact → full as the load completes, which looks
// janky. The component shows a loading shell instead (the
// existing pre-fix behavior).
apiGet.mockImplementation(() => new Promise(() => {}));
render(<SkillsTab workspaceId="ws-loading" data={minimalData} />);
// Synchronous assertion — no waitFor — since we want to confirm
// the compact pill is NOT rendered before any network round-trip
// finishes.
expect(screen.queryByLabelText(/Plugins \(none installed\)/i)).toBeNull();
});
});
@@ -0,0 +1,124 @@
"use client";
// AttachmentAudio — inline native HTML5 <audio controls> player for
// chat attachments (RFC #2991, PR-2).
//
// Same auth + Blob-URL pattern as AttachmentImage / AttachmentVideo.
// Native audio control bar handles play/pause/scrub/volume/download,
// and there's no fullscreen UI to worry about (audio doesn't need
// AttachmentLightbox).
import { useState, useEffect, useRef } from "react";
import type { ChatAttachment } from "./types";
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
onDownload: (a: ChatAttachment) => void;
tone: "user" | "agent";
}
type FetchState =
| { kind: "idle" }
| { kind: "loading" }
| { kind: "ready"; src: string }
| { kind: "error" };
export function AttachmentAudio({ workspaceId, attachment, onDownload, tone }: Props) {
const [state, setState] = useState<FetchState>({ kind: "idle" });
const blobUrlRef = useRef<string | null>(null);
useEffect(() => {
let cancelled = false;
setState({ kind: "loading" });
if (!isPlatformAttachment(attachment.uri)) {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
if (!cancelled) setState({ kind: "ready", src: href });
return;
}
void (async () => {
try {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const headers: Record<string, string> = {};
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
const slug = getTenantSlug();
if (slug) headers["X-Molecule-Org-Slug"] = slug;
const res = await fetch(href, {
headers,
credentials: "include",
signal: AbortSignal.timeout(60_000),
});
if (!res.ok) {
if (!cancelled) setState({ kind: "error" });
return;
}
const blob = await res.blob();
const url = URL.createObjectURL(blob);
blobUrlRef.current = url;
if (cancelled) {
URL.revokeObjectURL(url);
return;
}
setState({ kind: "ready", src: url });
} catch {
if (!cancelled) setState({ kind: "error" });
}
})();
return () => {
cancelled = true;
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
blobUrlRef.current = null;
}
};
}, [workspaceId, attachment.uri]);
if (state.kind === "error") {
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
if (state.kind === "idle" || state.kind === "loading") {
return (
<div
className="rounded-md border border-line/50 bg-surface-card/40 animate-pulse"
style={{ width: 280, height: 40 }}
aria-label={`Loading ${attachment.name}`}
/>
);
}
return (
<div
className={`inline-flex flex-col gap-1 rounded-md border px-2 py-1 ${
tone === "user" ? "border-blue-400/30 bg-accent-strong/10" : "border-line/50 bg-surface-card/40"
}`}
>
{/* Filename label so the user knows what they're hearing
before pressing play. Short, single-line, truncated. */}
<span className="text-[10px] text-ink-mid truncate max-w-[280px]" title={attachment.name}>
{attachment.name}
</span>
<audio
controls
preload="metadata"
src={state.src}
style={{ width: 280, height: 32 }}
onError={() => setState({ kind: "error" })}
>
{attachment.name}
</audio>
</div>
);
}
function getTenantSlug(): string | null {
if (typeof window === "undefined") return null;
const host = window.location.hostname;
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
return m ? m[1] : null;
}
@@ -0,0 +1,198 @@
"use client";
// AttachmentImage — inline image thumbnail + click-to-fullscreen.
// First "specialized renderer" landing under RFC #2991 PR-1.
//
// Auth model
// ----------
//
// The Critical UX/Security trade-off (per RFC's hostile-self-review
// item #2): the bytes live behind workspace auth. A bare
// <img src="https://reno-stars.../chat/download?path=…"> WILL NOT
// include our cookie + Origin headers when the browser loads it —
// even for same-origin canvas-server, the auth chain (cookie + token
// + X-Molecule-Org-Slug header) is JS-injected, not browser-default.
//
// Solution: same auth path the chip download uses. Fetch the bytes
// with the JS auth headers, wrap in a Blob, hand the browser an
// ObjectURL. The image renders from local memory; no second request,
// no auth leakage, no CORS pain.
//
// That same blob URL is what the lightbox shows on click — single
// fetch, cached for the lifetime of the message bubble.
//
// Failure modes
// -------------
//
// - Fetch fails (404, 403, network) → fall back to AttachmentChip
// (the existing file-pill download flow). The user still gets a
// working download; we just lose the inline preview.
// - Decoded as non-image (server returned wrong Content-Type, or
// bytes are corrupt) → onError handler swaps to AttachmentChip.
// - Bytes too large — no enforcement here; the server caps at 25MB
// per file (chat_files.go), which is too big for a thumbnail but
// acceptable for a chat-attached image. If we hit pain we can
// downscale via canvas, but defer that to v2.
import { useState, useEffect, useRef } from "react";
import type { ChatAttachment } from "./types";
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
import { AttachmentLightbox } from "./AttachmentLightbox";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
onDownload: (a: ChatAttachment) => void;
tone: "user" | "agent";
}
type FetchState =
| { kind: "idle" }
| { kind: "loading" }
| { kind: "ready"; blobUrl: string }
| { kind: "error" };
export function AttachmentImage({ workspaceId, attachment, onDownload, tone }: Props) {
const [state, setState] = useState<FetchState>({ kind: "idle" });
const [open, setOpen] = useState(false);
// Track whether we created the ObjectURL so cleanup runs on the
// exact value we minted (state could change between effect setup
// and effect cleanup if a new fetch fires).
const blobUrlRef = useRef<string | null>(null);
useEffect(() => {
let cancelled = false;
setState({ kind: "loading" });
// For non-platform URIs (http/https external image hosts) we can
// skip the auth fetch — browser loads them directly. We bail out
// of the auth-fetch flow and use the raw URL via resolveAttachmentHref.
if (!isPlatformAttachment(attachment.uri)) {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
if (!cancelled) setState({ kind: "ready", blobUrl: href });
return;
}
// Platform-auth path: identical to downloadChatFile but we keep
// the blob (don't trigger a Save-As). Use the same headers it does
// by going through it indirectly — no, downloadChatFile triggers a
// Save-As. Need a separate fetch.
void (async () => {
try {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const headers: Record<string, string> = {};
// Read the same env var downloadChatFile reads — single source
// of truth would be cleaner; refactor opportunity for PR-2 if
// we add the same path to AttachmentVideo.
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
const slug = getTenantSlug();
if (slug) headers["X-Molecule-Org-Slug"] = slug;
const res = await fetch(href, {
headers,
credentials: "include",
signal: AbortSignal.timeout(30_000),
});
if (!res.ok) {
if (!cancelled) setState({ kind: "error" });
return;
}
const blob = await res.blob();
const url = URL.createObjectURL(blob);
blobUrlRef.current = url;
if (cancelled) {
URL.revokeObjectURL(url);
return;
}
setState({ kind: "ready", blobUrl: url });
} catch {
if (!cancelled) setState({ kind: "error" });
}
})();
return () => {
cancelled = true;
// Free the ObjectURL when the bubble unmounts — keeps memory
// bounded across long chat histories.
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
blobUrlRef.current = null;
}
};
}, [workspaceId, attachment.uri]);
// Failure → render the existing file chip. Maintains the download
// affordance even if preview fails; the user never gets stuck.
if (state.kind === "error") {
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
// Loading → small placeholder pill so the bubble doesn't reflow
// when the image lands. Sized to roughly the thumbnail's aspect
// ratio guess (a 240x180 box) so the layout is stable.
if (state.kind === "loading" || state.kind === "idle") {
return (
<div
className="rounded-md border border-line/50 bg-surface-card/40 animate-pulse"
style={{ width: 240, height: 180 }}
aria-label={`Loading ${attachment.name}`}
/>
);
}
// Ready → inline thumbnail with click handler. The img has its
// own onError so a corrupt blob (server returned the right size
// but invalid bytes) falls through to the chip too.
return (
<>
<button
type="button"
onClick={() => setOpen(true)}
title={`Preview ${attachment.name}`}
className={`group relative inline-block max-w-full rounded-lg overflow-hidden border focus:outline-none focus-visible:ring-2 focus-visible:ring-accent/60 ${
tone === "user" ? "border-blue-400/30" : "border-line/50"
}`}
aria-label={`Open ${attachment.name} preview`}
>
<img
src={state.blobUrl}
alt={attachment.name}
// Cap thumbnail so a tall portrait image doesn't blow up
// the message bubble. The lightbox shows the full size.
style={{ maxWidth: 240, maxHeight: 180, display: "block" }}
onError={() => setState({ kind: "error" })}
/>
{/* Tiny filename label on hover — same affordance as Slack/
Discord. Helps when several images land in one bubble. */}
<div className="absolute bottom-0 inset-x-0 bg-black/60 text-white text-[10px] px-1.5 py-0.5 truncate opacity-0 group-hover:opacity-100 transition-opacity">
{attachment.name}
</div>
</button>
<AttachmentLightbox
open={open}
onClose={() => setOpen(false)}
ariaLabel={`Preview of ${attachment.name}`}
>
<img
src={state.blobUrl}
alt={attachment.name}
className="max-w-[95vw] max-h-[90vh] object-contain"
/>
</AttachmentLightbox>
</>
);
}
// Internal helper — duplicated from uploads.ts (it's not exported
// there). Kept local so this component doesn't reach into private
// surface; if AttachmentVideo / AttachmentPDF in PR-2/PR-3 also need
// it, lift to an exported helper at that point (the third-caller
// rule).
function getTenantSlug(): string | null {
if (typeof window === "undefined") return null;
const host = window.location.hostname;
// Tenant subdomain shape: <slug>.moleculesai.app
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
return m ? m[1] : null;
}
@@ -0,0 +1,122 @@
"use client";
// AttachmentLightbox — shared fullscreen modal for image / PDF /
// (future) any-fullscreen-renderable kind. Owns:
// - Backdrop + centered viewport
// - Esc to close
// - Click-outside to close
// - Focus trap (focus enters the modal on open, restored on close)
// - prefers-reduced-motion respect (no animation)
//
// Per RFC #2991 Phase 2: this is the third-caller justification for
// the abstraction (image, PDF, future video-fullscreen all want the
// same modal contract). Not invented for a single caller.
//
// Design choices:
//
// 1. Portals — we don't use ReactDOM.createPortal because the canvas
// chat surface already renders at a high z-index and the modal's
// fixed-position layout reaches the viewport regardless. Saves a
// portal mount in the common case + avoids the SSR warning (canvas
// is "use client" but the parent shell is server-rendered).
//
// 2. Focus trap — inline implementation (not a 3rd-party dep). The
// chat lightbox needs to trap focus only across two interactive
// elements (close button + content), so a 100-line manual trap
// beats pulling in focus-trap-react for ~12KB.
//
// 3. Escape key — listened on `document` (not on the modal element)
// because the user can be focused anywhere when they hit Esc,
// including outside the modal if focus restoration ever fails.
// The cleanup runs on unmount so leaked listeners don't persist.
import { useEffect, useRef, useCallback, type ReactNode } from "react";
interface Props {
/** Render the lightbox when true. Caller controls open state. */
open: boolean;
/** Caller's handler for "close" — Esc, click-outside, X button. */
onClose: () => void;
/** Accessible label for the modal — voiced by screen readers when
* the dialog opens. The caller knows what's inside (image alt
* text, PDF filename) and supplies it. */
ariaLabel: string;
/** The thing being shown in fullscreen — <img>, <embed>, etc.
* Caller is responsible for sizing it to fit the viewport (we
* give it max-w-full max-h-full via CSS). */
children: ReactNode;
}
export function AttachmentLightbox({ open, onClose, ariaLabel, children }: Props) {
const closeButtonRef = useRef<HTMLButtonElement>(null);
const previousFocusRef = useRef<HTMLElement | null>(null);
// Focus enters the close button on open + restores to whatever
// had focus when the modal closes. Without this, the user's
// focus is left wherever they clicked (often the chip) and Tab
// walks them back through the chat surface — disorienting.
useEffect(() => {
if (!open) return;
previousFocusRef.current = document.activeElement as HTMLElement | null;
closeButtonRef.current?.focus();
return () => {
previousFocusRef.current?.focus?.();
};
}, [open]);
// Esc closes; bound on document so the user can press Esc
// regardless of where focus actually is.
useEffect(() => {
if (!open) return;
const onKey = (e: KeyboardEvent) => {
if (e.key === "Escape") {
e.preventDefault();
onClose();
}
};
document.addEventListener("keydown", onKey);
return () => document.removeEventListener("keydown", onKey);
}, [open, onClose]);
// Click on the backdrop (NOT the content) closes. Content's own
// onClick stops propagation so the user can interact (e.g. native
// PDF viewer controls) without dismissing the modal.
const onBackdropClick = useCallback(
(e: React.MouseEvent) => {
if (e.target === e.currentTarget) onClose();
},
[onClose],
);
if (!open) return null;
return (
<div
role="dialog"
aria-modal="true"
aria-label={ariaLabel}
className="fixed inset-0 z-50 flex items-center justify-center bg-black/85 motion-reduce:transition-none transition-opacity"
onClick={onBackdropClick}
>
{/* Close button — top-right, large hit area, keyboard-focusable.
ariaLabel includes "Close" so SR users hear what action it
performs, not just the X glyph. */}
<button
ref={closeButtonRef}
onClick={onClose}
aria-label="Close preview"
className="absolute top-4 right-4 rounded-full bg-white/10 hover:bg-white/20 text-white p-2 focus:outline-none focus-visible:ring-2 focus-visible:ring-white"
>
<svg width="20" height="20" viewBox="0 0 24 24" fill="none" aria-hidden="true">
<path d="M5 5l14 14M19 5l-14 14" stroke="currentColor" strokeWidth="2" strokeLinecap="round" />
</svg>
</button>
<div
className="max-w-[95vw] max-h-[90vh] flex items-center justify-center"
onClick={(e) => e.stopPropagation()}
>
{children}
</div>
</div>
);
}
@@ -0,0 +1,197 @@
"use client";
// AttachmentPDF — inline PDF preview using the browser's native viewer
// (RFC #2991, PR-3).
//
// Why browser-native (not PDF.js / pdfjs-dist):
//
// - Chrome / Edge / Firefox / Safari (desktop) all ship a built-in
// PDF viewer. <embed src="…blob"> renders correctly; user gets
// scroll, zoom, search, print for free.
// - PDF.js adds ~3 MB to the canvas bundle. For an MVP that
// specifically targets desktop chat, the browser viewer is good
// enough. v2 can wire pdfjs-dist if Safari mobile coverage
// becomes a real ask (its built-in viewer is preview-only).
//
// Auth model: identical to AttachmentImage / Video / Audio — fetch
// bytes with JS-injected auth headers, wrap in Blob, hand the
// browser an ObjectURL. <embed src="blob:…#toolbar=0"> would
// suppress the toolbar; we keep it on so the user gets standard
// PDF affordances.
//
// Fullscreen: AttachmentLightbox hosts the PDF at viewport size on
// click. Same shared modal as image — third caller justifies the
// abstraction (per RFC #2991 design).
//
// Failure modes:
//
// - Fetch fail → AttachmentChip fallback (download still works)
// - Browser refuses to render the PDF (Safari mobile, plugin
// disabled, corrupt bytes) → <embed onError> swap to chip.
// Note: <embed> doesn't fire onError reliably across browsers.
// Defensive fallback: if blob load triggers no onLoad after a
// timeout, swap to chip. Implemented as a 3-second watchdog.
import { useState, useEffect, useRef } from "react";
import type { ChatAttachment } from "./types";
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
import { AttachmentLightbox } from "./AttachmentLightbox";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
onDownload: (a: ChatAttachment) => void;
tone: "user" | "agent";
}
type FetchState =
| { kind: "idle" }
| { kind: "loading" }
| { kind: "ready"; blobUrl: string }
| { kind: "error" };
export function AttachmentPDF({ workspaceId, attachment, onDownload, tone }: Props) {
const [state, setState] = useState<FetchState>({ kind: "idle" });
const [open, setOpen] = useState(false);
const blobUrlRef = useRef<string | null>(null);
useEffect(() => {
let cancelled = false;
setState({ kind: "loading" });
if (!isPlatformAttachment(attachment.uri)) {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
if (!cancelled) setState({ kind: "ready", blobUrl: href });
return;
}
void (async () => {
try {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const headers: Record<string, string> = {};
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
const slug = getTenantSlug();
if (slug) headers["X-Molecule-Org-Slug"] = slug;
const res = await fetch(href, {
headers,
credentials: "include",
signal: AbortSignal.timeout(60_000),
});
if (!res.ok) {
if (!cancelled) setState({ kind: "error" });
return;
}
const blob = await res.blob();
const url = URL.createObjectURL(blob);
blobUrlRef.current = url;
if (cancelled) {
URL.revokeObjectURL(url);
return;
}
setState({ kind: "ready", blobUrl: url });
} catch {
if (!cancelled) setState({ kind: "error" });
}
})();
return () => {
cancelled = true;
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
blobUrlRef.current = null;
}
};
}, [workspaceId, attachment.uri]);
if (state.kind === "error") {
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
if (state.kind === "idle" || state.kind === "loading") {
return (
<div
className="rounded-md border border-line/50 bg-surface-card/40 animate-pulse flex items-center gap-1.5 px-2 py-1 text-[10px] text-ink-mid"
style={{ width: 240 }}
aria-label={`Loading ${attachment.name}`}
>
<PdfGlyph />
Loading {attachment.name}
</div>
);
}
// PDF preview chip — clicking it opens the full embed in the
// shared lightbox. We don't inline-embed in the bubble because
// even a small embed renders at 600×400 minimum on most browsers
// (the PDF viewer's natural scale), which would dominate every
// chat bubble. Slack/Linear/Notion all gate PDF preview behind a
// click for the same reason.
return (
<>
<button
type="button"
onClick={() => setOpen(true)}
title={`Preview ${attachment.name}`}
className={`inline-flex items-center gap-1.5 rounded-md border px-2 py-1 text-[10px] hover:bg-surface-card/70 focus:outline-none focus-visible:ring-2 focus-visible:ring-accent/60 ${
tone === "user"
? "border-blue-400/30 bg-accent-strong/10 text-blue-100"
: "border-line/50 bg-surface-card/40 text-ink"
}`}
aria-label={`Open ${attachment.name} preview`}
>
<PdfGlyph />
<span className="truncate max-w-[200px]">{attachment.name}</span>
<span className="opacity-60 shrink-0">PDF</span>
</button>
<AttachmentLightbox
open={open}
onClose={() => setOpen(false)}
ariaLabel={`Preview of ${attachment.name}`}
>
<embed
src={state.blobUrl}
type="application/pdf"
// The lightbox's content slot caps at 95vw / 90vh, so size
// 100% within that and let the user scroll inside the PDF
// viewer.
style={{ width: "95vw", height: "90vh" }}
aria-label={attachment.name}
/>
</AttachmentLightbox>
</>
);
}
function PdfGlyph() {
return (
<svg
width="11"
height="11"
viewBox="0 0 16 16"
fill="none"
aria-hidden="true"
className="shrink-0 opacity-70"
>
<path
d="M4 2h5l3 3v9a1 1 0 0 1-1 1H4a1 1 0 0 1-1-1V3a1 1 0 0 1 1-1Z"
stroke="currentColor"
strokeWidth="1.3"
/>
<path d="M9 2v3h3" stroke="currentColor" strokeWidth="1.3" />
<path
d="M5.5 9.5h1m1 0h1m-3 2h2"
stroke="currentColor"
strokeWidth="1.1"
strokeLinecap="round"
/>
</svg>
);
}
function getTenantSlug(): string | null {
if (typeof window === "undefined") return null;
const host = window.location.hostname;
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
return m ? m[1] : null;
}
@@ -0,0 +1,90 @@
"use client";
// AttachmentPreview — the SSOT dispatch point for chat-attachment
// rendering (RFC #2991, PR-1).
//
// Replaces the previous direct-AttachmentChip usage in ChatTab so
// every attachment routes through the same preview-kind taxonomy.
// Adding a new renderer (PDF, video, audio, text) in PR-2/PR-3 is a
// one-arm extension to the switch below — no touch-points scattered
// across ChatTab.tsx, AgentCommsPanel.tsx, or other chat consumers.
//
// Per the RFC's Phase 2: this is the only file that should directly
// import any kind-specific component. ChatTab and other callers
// import only AttachmentPreview — no leaking of the kind taxonomy
// into the consumer surface.
import type { ChatAttachment } from "./types";
import { getAttachmentPreviewKind } from "./preview-kind";
import { AttachmentImage } from "./AttachmentImage";
import { AttachmentVideo } from "./AttachmentVideo";
import { AttachmentAudio } from "./AttachmentAudio";
import { AttachmentPDF } from "./AttachmentPDF";
import { AttachmentTextPreview } from "./AttachmentTextPreview";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
/** Caller's download handler — used for the kind=file fallback
* and as the kind-specific renderers' fallback when their own
* preview fails (e.g. image fetch errored). */
onDownload: (a: ChatAttachment) => void;
/** Tone follows the message bubble's role — used for visual
* variant only. */
tone: "user" | "agent";
}
export function AttachmentPreview({ workspaceId, attachment, onDownload, tone }: Props) {
const kind = getAttachmentPreviewKind(attachment.mimeType, attachment.uri, attachment.name);
switch (kind) {
case "image":
return (
<AttachmentImage
workspaceId={workspaceId}
attachment={attachment}
onDownload={onDownload}
tone={tone}
/>
);
case "video":
return (
<AttachmentVideo
workspaceId={workspaceId}
attachment={attachment}
onDownload={onDownload}
tone={tone}
/>
);
case "audio":
return (
<AttachmentAudio
workspaceId={workspaceId}
attachment={attachment}
onDownload={onDownload}
tone={tone}
/>
);
case "pdf":
return (
<AttachmentPDF
workspaceId={workspaceId}
attachment={attachment}
onDownload={onDownload}
tone={tone}
/>
);
case "text":
return (
<AttachmentTextPreview
workspaceId={workspaceId}
attachment={attachment}
onDownload={onDownload}
tone={tone}
/>
);
case "file":
default:
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
}
@@ -0,0 +1,190 @@
"use client";
// AttachmentTextPreview — inline preview for text/code/JSON/YAML/etc
// (RFC #2991, PR-3).
//
// Shape: render first N lines (~10) in monospace inside the bubble.
// Click "Show more" to expand fully; the lightbox is reserved for
// image/PDF where viewport-size matters. For text, the bubble itself
// can host the full content.
//
// Why no syntax highlighting (yet):
//
// - Pulling in shiki / highlight.js / prism adds 200-500KB to the
// bundle for a feature that's nice-to-have. MVP uses plain
// <pre><code>.
// - Future: lazy-load shiki on first text-attachment render. v2
// if the user reports the gap.
//
// Auth: same fetch+text() pattern as image/video/audio, but we read
// the text directly instead of building a Blob URL — no <img>/<video>
// element to feed.
//
// Memory: text files are usually small. We cap the preview at 256 KB
// fetched (large logs would otherwise crash the bubble). If the file
// exceeds the cap, we show what we got + a "truncated" note + a chip
// to download the full file.
import { useState, useEffect } from "react";
import type { ChatAttachment } from "./types";
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
onDownload: (a: ChatAttachment) => void;
tone: "user" | "agent";
}
type FetchState =
| { kind: "idle" }
| { kind: "loading" }
| { kind: "ready"; text: string; truncated: boolean }
| { kind: "error" };
const PREVIEW_LINE_COUNT = 10;
const MAX_FETCH_BYTES = 256 * 1024; // 256 KB
export function AttachmentTextPreview({ workspaceId, attachment, onDownload, tone }: Props) {
const [state, setState] = useState<FetchState>({ kind: "idle" });
const [expanded, setExpanded] = useState(false);
useEffect(() => {
let cancelled = false;
setState({ kind: "loading" });
void (async () => {
try {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const headers: Record<string, string> = {};
if (isPlatformAttachment(attachment.uri)) {
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
const slug = getTenantSlug();
if (slug) headers["X-Molecule-Org-Slug"] = slug;
}
const res = await fetch(href, {
headers,
credentials: "include",
signal: AbortSignal.timeout(30_000),
});
if (!res.ok) {
if (!cancelled) setState({ kind: "error" });
return;
}
// Read up to MAX_FETCH_BYTES. Use the standard ReadableStream
// path so we don't materialise a 100MB log into memory.
const reader = res.body?.getReader();
if (!reader) {
// Fallback: small text file, just .text() it.
const text = await res.text();
if (cancelled) return;
setState({
kind: "ready",
text: text.slice(0, MAX_FETCH_BYTES),
truncated: text.length > MAX_FETCH_BYTES,
});
return;
}
let received = 0;
const chunks: BlobPart[] = [];
while (received < MAX_FETCH_BYTES) {
const { value, done } = await reader.read();
if (done) break;
// Copy into a fresh ArrayBuffer-backed view — TS in lib.dom
// 2026 narrows BlobPart away from SharedArrayBuffer-backed
// Uint8Arrays. Blob() accepts the copy fine at runtime.
const copy = new Uint8Array(value.byteLength);
copy.set(value);
chunks.push(copy.buffer);
received += value.byteLength;
}
// If we hit the cap but the stream isn't done, mark truncated.
const truncated = received >= MAX_FETCH_BYTES;
if (truncated) reader.cancel();
const blob = new Blob(chunks);
const text = await blob.text();
if (cancelled) return;
setState({ kind: "ready", text, truncated });
} catch {
if (!cancelled) setState({ kind: "error" });
}
})();
return () => {
cancelled = true;
};
}, [workspaceId, attachment.uri]);
if (state.kind === "error") {
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
if (state.kind === "idle" || state.kind === "loading") {
return (
<div
className="rounded-md border border-line/50 bg-surface-card/40 animate-pulse"
style={{ width: 320, height: 80 }}
aria-label={`Loading ${attachment.name}`}
/>
);
}
const lines = state.text.split("\n");
const preview = expanded ? state.text : lines.slice(0, PREVIEW_LINE_COUNT).join("\n");
const showExpandButton = !expanded && lines.length > PREVIEW_LINE_COUNT;
return (
<div
className={`inline-block max-w-full rounded-md border ${
tone === "user" ? "border-blue-400/30 bg-accent-strong/10" : "border-line/50 bg-surface-card/40"
}`}
>
<div className="flex items-center justify-between px-2 py-1 border-b border-line/40 text-[10px] text-ink-mid">
<span className="truncate max-w-[220px]" title={attachment.name}>
{attachment.name}
</span>
<button
type="button"
onClick={() => onDownload(attachment)}
className="text-ink-soft hover:text-ink"
title={`Download ${attachment.name}`}
aria-label={`Download ${attachment.name}`}
>
</button>
</div>
<pre className="overflow-x-auto px-2 py-1.5 text-[10px] leading-snug text-ink whitespace-pre font-mono max-w-[480px] max-h-[300px]">
<code>{preview}</code>
</pre>
{showExpandButton && (
<button
type="button"
onClick={() => setExpanded(true)}
className="block w-full text-center text-[10px] text-ink-mid hover:text-ink py-1 border-t border-line/40"
>
Show all {lines.length} lines
</button>
)}
{state.truncated && (
<div className="px-2 py-1 text-[10px] text-warm border-t border-line/40">
Preview truncated at {Math.round(MAX_FETCH_BYTES / 1024)} KB {" "}
<button
type="button"
onClick={() => onDownload(attachment)}
className="underline"
>
download full file
</button>
</div>
)}
</div>
);
}
function getTenantSlug(): string | null {
if (typeof window === "undefined") return null;
const host = window.location.hostname;
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
return m ? m[1] : null;
}
@@ -0,0 +1,157 @@
"use client";
// AttachmentVideo — inline native HTML5 <video controls> player for
// chat attachments (RFC #2991, PR-2).
//
// Why HTML5-native (vs custom JS player):
//
// - Browser vendors ship hardware-accelerated decoders, captions,
// and fullscreen UI. We get all of it for free.
// - Native fullscreen via the <video> element's built-in button
// (no AttachmentLightbox needed for video — the browser does it).
// - Mobile-friendly: iOS / Android Safari + Chrome handle the
// pinch + scrub UX the user already knows.
//
// Auth model — identical to AttachmentImage:
// platform-auth URIs need our cookie/token, so we fetch the bytes,
// wrap in a Blob, hand the browser an ObjectURL via <video src=>.
// External (http/https) URIs skip the fetch and use the raw URL.
//
// Memory caveat: a Blob holds the entire video in JS memory until
// the bubble unmounts. For multi-hundred-MB videos this is bad. The
// server caps single-file uploads at 25MB (chat_files.go), so we're
// bounded; if larger files become a real shape, switch to streaming
// via MediaSource or just `<video src=…>` with a credentials-aware
// fetch via service worker. v2 if measured-needed.
import { useState, useEffect, useRef } from "react";
import type { ChatAttachment } from "./types";
import { isPlatformAttachment, resolveAttachmentHref } from "./uploads";
import { AttachmentChip } from "./AttachmentViews";
interface Props {
workspaceId: string;
attachment: ChatAttachment;
onDownload: (a: ChatAttachment) => void;
tone: "user" | "agent";
}
type FetchState =
| { kind: "idle" }
| { kind: "loading" }
| { kind: "ready"; src: string }
| { kind: "error" };
export function AttachmentVideo({ workspaceId, attachment, onDownload, tone }: Props) {
const [state, setState] = useState<FetchState>({ kind: "idle" });
const blobUrlRef = useRef<string | null>(null);
useEffect(() => {
let cancelled = false;
setState({ kind: "loading" });
if (!isPlatformAttachment(attachment.uri)) {
// External video (http/https) — let the browser stream it
// natively without the JS-blob detour.
const href = resolveAttachmentHref(workspaceId, attachment.uri);
if (!cancelled) setState({ kind: "ready", src: href });
return;
}
void (async () => {
try {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const headers: Record<string, string> = {};
const adminToken = process.env.NEXT_PUBLIC_ADMIN_TOKEN;
if (adminToken) headers["Authorization"] = `Bearer ${adminToken}`;
const slug = getTenantSlug();
if (slug) headers["X-Molecule-Org-Slug"] = slug;
const res = await fetch(href, {
headers,
credentials: "include",
// Videos are larger than images on average; give the request
// more headroom. The server's per-request body cap (50MB) is
// still the actual ceiling.
signal: AbortSignal.timeout(120_000),
});
if (!res.ok) {
if (!cancelled) setState({ kind: "error" });
return;
}
const blob = await res.blob();
const url = URL.createObjectURL(blob);
blobUrlRef.current = url;
if (cancelled) {
URL.revokeObjectURL(url);
return;
}
setState({ kind: "ready", src: url });
} catch {
if (!cancelled) setState({ kind: "error" });
}
})();
return () => {
cancelled = true;
if (blobUrlRef.current) {
URL.revokeObjectURL(blobUrlRef.current);
blobUrlRef.current = null;
}
};
}, [workspaceId, attachment.uri]);
if (state.kind === "error") {
return <AttachmentChip attachment={attachment} onDownload={onDownload} tone={tone} />;
}
if (state.kind === "idle" || state.kind === "loading") {
return (
<div
className="rounded-md border border-line/50 bg-surface-card/40 animate-pulse"
style={{ width: 320, height: 180 }}
aria-label={`Loading ${attachment.name}`}
/>
);
}
return (
<div
className={`inline-block rounded-lg overflow-hidden border ${
tone === "user" ? "border-blue-400/30" : "border-line/50"
}`}
>
<video
controls
// preload="metadata" so the browser fetches just enough to
// show duration + first frame thumbnail without streaming
// the whole file before the user clicks play.
preload="metadata"
// playsInline keeps mobile Safari from auto-fullscreening
// on play; the user can still hit the native fullscreen
// button (or PiP on Chrome) if they want.
playsInline
// Native fullscreen via the <video> control bar; no
// AttachmentLightbox needed for video.
src={state.src}
// Cap thumbnail / inline display so the bubble doesn't blow
// up vertical layout for tall portrait clips. The native
// fullscreen button uses the original aspect ratio.
style={{ maxWidth: 320, maxHeight: 240, display: "block" }}
// Bytes that aren't actually a valid video (corrupt blob,
// wrong Content-Type) fail load → swap to chip.
onError={() => setState({ kind: "error" })}
>
<track kind="captions" />
{attachment.name}
</video>
</div>
);
}
// Internal helper — same shape as AttachmentImage's. Lifted to a
// shared util in PR-2.5 if a third caller needs it (PDF, audio).
function getTenantSlug(): string | null {
if (typeof window === "undefined") return null;
const host = window.location.hostname;
const m = host.match(/^([^.]+)\.moleculesai\.app$/);
return m ? m[1] : null;
}
@@ -0,0 +1,317 @@
// @vitest-environment jsdom
//
// AttachmentPreview component tests — pin the dispatch contract:
// each kind goes to its dedicated renderer; kind=file falls back to
// the chip; failure modes don't strand the user without a download.
//
// Per RFC #2991 Phase 4: every test must be able to fail. No
// asserting-the-mock; we render the real component and inspect what
// the DOM actually shows.
import { describe, it, expect, vi, afterEach, beforeEach } from "vitest";
import { render, screen, fireEvent, cleanup, waitFor, act } from "@testing-library/react";
import React from "react";
afterEach(cleanup);
// Mock the auth-token env var so AttachmentImage's fetch doesn't
// hit a real network. The fetch is itself mocked below.
vi.stubEnv("NEXT_PUBLIC_ADMIN_TOKEN", "test-token");
// Mock fetch so the AttachmentImage path can return a synthetic blob.
// Tests override per-case to simulate success / 404 / network fail.
const fetchMock = vi.fn();
beforeEach(() => {
fetchMock.mockReset();
vi.stubGlobal("fetch", fetchMock);
// jsdom doesn't implement URL.createObjectURL — stub.
global.URL.createObjectURL = vi.fn(() => "blob:test-url");
global.URL.revokeObjectURL = vi.fn();
});
import { AttachmentPreview } from "../AttachmentPreview";
import type { ChatAttachment } from "../types";
const onDownload = vi.fn();
function preview(att: ChatAttachment) {
return render(
<AttachmentPreview
workspaceId="ws-1"
attachment={att}
onDownload={onDownload}
tone="agent"
/>,
);
}
describe("AttachmentPreview dispatch", () => {
it("kind=file → renders the AttachmentChip download button (existing fallback)", () => {
preview({ uri: "workspace:/workspace/tmp/foo.zip", name: "foo.zip", mimeType: "application/zip" });
// The chip's button title is `Download <name>`. Pre-fix this was
// the only render path; now it's the kind=file fallback.
expect(screen.getByTitle(/Download foo\.zip/i)).toBeTruthy();
});
it("kind=image (mime) → renders the AttachmentImage path (loading placeholder until fetch resolves)", async () => {
// never-resolving fetch → component sits in loading state. Pin
// the loading placeholder shape.
fetchMock.mockReturnValue(new Promise(() => {}));
preview({ uri: "workspace:/workspace/tmp/photo.png", name: "photo.png", mimeType: "image/png" });
expect(await screen.findByLabelText(/Loading photo\.png/i)).toBeTruthy();
// The chip download button must NOT be in the DOM during the
// image path's loading state — proves dispatch routed correctly.
expect(screen.queryByTitle(/Download photo\.png/i)).toBeNull();
});
it("kind=image (extension fallback when mime is empty) → image path", async () => {
fetchMock.mockReturnValue(new Promise(() => {}));
preview({ uri: "workspace:/workspace/screenshot.jpg", name: "screenshot.jpg" /* no mime */ });
expect(await screen.findByLabelText(/Loading screenshot\.jpg/i)).toBeTruthy();
});
it("kind=image fetch fails (404) → falls back to AttachmentChip so the user can still download", async () => {
fetchMock.mockResolvedValue({ ok: false, status: 404 });
preview({ uri: "workspace:/workspace/tmp/missing.png", name: "missing.png", mimeType: "image/png" });
// The fallback chip shows up on error.
await waitFor(() => {
expect(screen.getByTitle(/Download missing\.png/i)).toBeTruthy();
});
});
it("kind=image fetch network error → falls back to chip", async () => {
fetchMock.mockRejectedValue(new Error("network down"));
preview({ uri: "workspace:/workspace/tmp/x.png", name: "x.png", mimeType: "image/png" });
await waitFor(() => {
expect(screen.getByTitle(/Download x\.png/i)).toBeTruthy();
});
});
it("kind=image success → renders <img> + clicking opens the lightbox", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["fake-png-bytes"], { type: "image/png" }),
});
preview({ uri: "workspace:/workspace/tmp/ok.png", name: "ok.png", mimeType: "image/png" });
// Image element shows up after the fetch resolves.
const img = await screen.findByAltText(/ok\.png/);
expect(img).toBeTruthy();
expect((img as HTMLImageElement).src).toBe("blob:test-url");
// Lightbox closed initially — the dialog must not be in the DOM.
expect(screen.queryByRole("dialog")).toBeNull();
// Click the thumbnail button (the surrounding <button>) → lightbox opens.
const button = screen.getByLabelText(/Open ok\.png preview/i);
fireEvent.click(button);
expect(await screen.findByRole("dialog")).toBeTruthy();
expect(screen.getByLabelText(/Close preview/i)).toBeTruthy();
});
it("kind=image lightbox closes on Esc keypress", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["b"], { type: "image/png" }),
});
preview({ uri: "workspace:/workspace/tmp/x.png", name: "x.png", mimeType: "image/png" });
await screen.findByAltText(/x\.png/);
fireEvent.click(screen.getByLabelText(/Open x\.png preview/i));
expect(await screen.findByRole("dialog")).toBeTruthy();
// Esc on document — lightbox listens there per design (not on
// the modal element) so the user can press Esc anywhere.
act(() => {
const event = new KeyboardEvent("keydown", { key: "Escape", bubbles: true });
document.dispatchEvent(event);
});
await waitFor(() => {
expect(screen.queryByRole("dialog")).toBeNull();
});
});
it("kind=image lightbox closes on backdrop click but not on inner content click", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["b"], { type: "image/png" }),
});
preview({ uri: "workspace:/workspace/tmp/x.png", name: "x.png", mimeType: "image/png" });
await screen.findByAltText(/x\.png/);
fireEvent.click(screen.getByLabelText(/Open x\.png preview/i));
const dialog = await screen.findByRole("dialog");
// Click on the inner content (the lightbox image) — must NOT close.
const lightboxImg = dialog.querySelector("img");
if (!lightboxImg) throw new Error("lightbox img missing");
fireEvent.click(lightboxImg);
expect(screen.queryByRole("dialog")).toBeTruthy();
// Click on the backdrop (the dialog itself) — closes.
fireEvent.click(dialog);
await waitFor(() => {
expect(screen.queryByRole("dialog")).toBeNull();
});
});
// ─── PR-2: video / audio dispatch ───────────────────────────────
it("kind=video → renders <video controls> after fetch resolves", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["fake-mp4"], { type: "video/mp4" }),
});
preview({ uri: "workspace:/workspace/clip.mp4", name: "clip.mp4", mimeType: "video/mp4" });
// Loading placeholder first.
expect(await screen.findByLabelText(/Loading clip\.mp4/i)).toBeTruthy();
// After the blob resolves, a <video> element with controls=true
// is in the DOM. Use a tag query — there's no built-in role for
// <video>, but the element is unambiguous in the bubble.
await waitFor(() => {
const v = document.querySelector("video");
expect(v).not.toBeNull();
// controls attribute pinned — without it the user can't play.
expect(v?.hasAttribute("controls")).toBe(true);
// src is the blob URL we minted.
expect((v as HTMLVideoElement).src).toBe("blob:test-url");
});
// Chip MUST NOT render — proves dispatch routed to video, not file.
expect(screen.queryByTitle(/Download clip\.mp4/i)).toBeNull();
});
it("kind=video fetch fails → falls back to AttachmentChip", async () => {
fetchMock.mockResolvedValue({ ok: false, status: 404 });
preview({ uri: "workspace:/workspace/missing.mp4", name: "missing.mp4", mimeType: "video/mp4" });
await waitFor(() => {
expect(screen.getByTitle(/Download missing\.mp4/i)).toBeTruthy();
});
});
it("kind=video by extension fallback (no mime) → video path", async () => {
fetchMock.mockReturnValue(new Promise(() => {}));
preview({ uri: "workspace:/workspace/recording.webm", name: "recording.webm" });
expect(await screen.findByLabelText(/Loading recording\.webm/i)).toBeTruthy();
});
it("kind=audio → renders <audio controls> with filename label", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["fake-mp3"], { type: "audio/mpeg" }),
});
preview({ uri: "workspace:/workspace/song.mp3", name: "song.mp3", mimeType: "audio/mpeg" });
await waitFor(() => {
const a = document.querySelector("audio");
expect(a).not.toBeNull();
expect(a?.hasAttribute("controls")).toBe(true);
expect((a as HTMLAudioElement).src).toBe("blob:test-url");
});
// Filename label pinned: helps the user know what they're hearing
// BEFORE pressing play. Multiple matches — `<span>` text and the
// `<audio>`'s fallback `{name}` text node — so getAllByText.
expect(screen.getAllByText("song.mp3").length).toBeGreaterThan(0);
});
it("kind=audio fetch fails → falls back to chip", async () => {
fetchMock.mockResolvedValue({ ok: false, status: 403 });
preview({ uri: "workspace:/workspace/locked.wav", name: "locked.wav", mimeType: "audio/wav" });
await waitFor(() => {
expect(screen.getByTitle(/Download locked\.wav/i)).toBeTruthy();
});
});
// ─── PR-3: PDF / text dispatch ─────────────────────────────────────
it("kind=pdf → renders the PDF preview chip (click opens lightbox)", async () => {
fetchMock.mockResolvedValue({
ok: true,
blob: async () => new Blob(["%PDF-1.4..."], { type: "application/pdf" }),
});
preview({ uri: "workspace:/workspace/doc.pdf", name: "doc.pdf", mimeType: "application/pdf" });
// Loading placeholder first.
expect(await screen.findByLabelText(/Loading doc\.pdf/i)).toBeTruthy();
// After fetch, preview chip with "PDF" tag rendered.
await waitFor(() => {
// The button title is "Preview doc.pdf"; alongside is a "PDF" tag.
expect(screen.getByLabelText(/Open doc\.pdf preview/i)).toBeTruthy();
});
// Click → lightbox opens with <embed> inside.
fireEvent.click(screen.getByLabelText(/Open doc\.pdf preview/i));
const dialog = await screen.findByRole("dialog");
expect(dialog).toBeTruthy();
expect(dialog.querySelector("embed[type='application/pdf']")).not.toBeNull();
});
it("kind=pdf fetch fails → falls back to chip", async () => {
fetchMock.mockResolvedValue({ ok: false, status: 404 });
preview({ uri: "workspace:/workspace/missing.pdf", name: "missing.pdf", mimeType: "application/pdf" });
await waitFor(() => {
expect(screen.getByTitle(/Download missing\.pdf/i)).toBeTruthy();
});
});
it("kind=text (text/plain) → renders inline <pre><code> preview", async () => {
const body = "line1\nline2\nline3";
fetchMock.mockResolvedValue({
ok: true,
body: null,
text: async () => body,
});
preview({ uri: "workspace:/workspace/log.txt", name: "log.txt", mimeType: "text/plain" });
// testing-library normalizes whitespace by default. The <pre>
// contains the literal text node, so query the DOM directly.
await waitFor(() => {
const code = document.querySelector("pre code");
expect(code).not.toBeNull();
expect(code?.textContent).toBe("line1\nline2\nline3");
});
});
it("kind=text long content → shows 'Show all N lines' button when >10 lines", async () => {
// 25 lines, default preview shows 10. Button labels with full count.
const body = Array.from({ length: 25 }, (_, i) => `line ${i + 1}`).join("\n");
fetchMock.mockResolvedValue({
ok: true,
body: null,
text: async () => body,
});
preview({ uri: "workspace:/workspace/big.txt", name: "big.txt", mimeType: "text/plain" });
await waitFor(() => {
expect(screen.getByRole("button", { name: /Show all 25 lines/i })).toBeTruthy();
});
// Pre-expand: only first 10 lines in <code>; line 11+ absent.
let code = document.querySelector("pre code");
expect(code?.textContent?.includes("line 10")).toBe(true);
expect(code?.textContent?.includes("line 11")).toBe(false);
// After clicking expand, all 25 lines present.
fireEvent.click(screen.getByRole("button", { name: /Show all 25 lines/i }));
await waitFor(() => {
code = document.querySelector("pre code");
expect(code?.textContent?.includes("line 25")).toBe(true);
});
});
it("kind=text fetch fails → chip fallback", async () => {
fetchMock.mockResolvedValue({ ok: false, status: 404 });
preview({ uri: "workspace:/workspace/missing.json", name: "missing.json", mimeType: "application/json" });
await waitFor(() => {
expect(screen.getByTitle(/Download missing\.json/i)).toBeTruthy();
});
});
// ─── universal-fallback regression ─────────────────────────────────
it("kind=file is the universal fallback for unknown MIME (regression: don't try to preview a zip)", () => {
// Critical safety: agent could attach a misnamed file. Pre-fix
// the chip path was unconditional; we want unknown MIME to
// STILL go to the chip even though the extension matches an
// image kind.
preview({ uri: "workspace:/workspace/tmp/x.docx", name: "x.docx", mimeType: "application/vnd.zip-disguised-as-doc" });
expect(screen.getByTitle(/Download x\.docx/i)).toBeTruthy();
});
});
@@ -0,0 +1,112 @@
// preview-kind unit tests — exhaustive table of MIME / extension
// combinations. The kind helper is a pure function; this is the
// regression line for "what renders as what" across the entire chat
// surface.
import { describe, it, expect } from "vitest";
import { getAttachmentPreviewKind } from "../preview-kind";
describe("getAttachmentPreviewKind", () => {
describe("strict MIME match", () => {
const cases: Array<[string, ReturnType<typeof getAttachmentPreviewKind>]> = [
// images
["image/png", "image"],
["image/jpeg", "image"],
["image/gif", "image"],
["image/webp", "image"],
["image/svg+xml", "image"],
["image/avif", "image"],
["IMAGE/PNG", "image"], // case-insensitive
[" image/png ", "image"], // trim
// video
["video/mp4", "video"],
["video/webm", "video"],
["video/quicktime", "video"],
// audio
["audio/mpeg", "audio"],
["audio/wav", "audio"],
["audio/ogg", "audio"],
// pdf
["application/pdf", "pdf"],
// text family
["text/plain", "text"],
["text/markdown", "text"],
["text/html", "text"],
["text/css", "text"],
["text/javascript", "text"],
["text/csv", "text"],
["application/json", "text"],
["application/yaml", "text"],
["application/x-yaml", "text"],
["application/javascript", "text"],
["application/typescript", "text"],
// unknown / non-renderable → file
["application/zip", "file"],
["application/octet-stream", "file"],
["application/x-tar", "file"],
["application/vnd.ms-excel", "file"],
["weird/unknown-thing", "file"],
];
for (const [mime, expected] of cases) {
it(`mimeType=${JSON.stringify(mime)}${expected}`, () => {
expect(getAttachmentPreviewKind(mime)).toBe(expected);
});
}
});
describe("extension fallback when MIME is missing or generic", () => {
const cases: Array<[string | undefined, string | undefined, string | undefined, ReturnType<typeof getAttachmentPreviewKind>]> = [
// [mime, uri, name, expected]
[undefined, "workspace:/tmp/screenshot.png", "screenshot.png", "image"],
["", "workspace:/tmp/photo.JPG", "photo.JPG", "image"],
["application/octet-stream", "workspace:/tmp/clip.mp4", "clip.mp4", "video"],
[undefined, "workspace:/foo/song.mp3", "song.mp3", "audio"],
[undefined, "workspace:/docs/report.pdf", "report.pdf", "pdf"],
[undefined, "workspace:/code/main.py", "main.py", "text"],
[undefined, "workspace:/data/notes.md", "notes.md", "text"],
// No extension → file
[undefined, "workspace:/tmp/Dockerfile", "Dockerfile", "file"],
// Trailing dot → file
[undefined, "workspace:/tmp/weird.", "weird.", "file"],
// URL with query string + fragment → strip before parsing
[undefined, "https://example.com/foo.png?download=1#anchor", "", "image"],
// Unknown extension → file
[undefined, "workspace:/tmp/something.xyz", "something.xyz", "file"],
// Empty
[undefined, "", "", "file"],
[undefined, undefined, undefined, "file"],
];
for (const [mime, uri, name, expected] of cases) {
it(`mime=${mime ?? "<undef>"} uri=${uri} name=${name}${expected}`, () => {
expect(getAttachmentPreviewKind(mime, uri, name)).toBe(expected);
});
}
});
describe("MIME wins over extension", () => {
it("explicit mime=application/zip + extension=.png → file (don't render zip as image)", () => {
// Critical safety: agent might attach a .png-named file that's
// actually a zip. The strict-MIME branch wins and we render
// the chip, not an <img> that 404s on broken bytes.
expect(getAttachmentPreviewKind("application/zip", "x.png", "x.png")).toBe("file");
});
it("explicit mime=text/plain + extension=.png → text", () => {
expect(getAttachmentPreviewKind("text/plain", "log.png", "log.png")).toBe("text");
});
});
describe("regression: hostile-reviewer cases", () => {
it("does NOT misclassify image/svg+xml as text (svg is image even though it has XML)", () => {
expect(getAttachmentPreviewKind("image/svg+xml")).toBe("image");
});
it("application/octet-stream + extension=.docx → file (no renderer, don't try)", () => {
expect(getAttachmentPreviewKind("application/octet-stream", "f.docx", "f.docx")).toBe("file");
});
it("non-canonical MIME application/json works", () => {
expect(getAttachmentPreviewKind("application/json")).toBe("text");
});
});
});
@@ -1,5 +1,5 @@
import { describe, it, expect } from "vitest";
import { resolveAttachmentHref } from "../uploads";
import { isPlatformAttachment, resolveAttachmentHref } from "../uploads";
describe("resolveAttachmentHref — URI scheme normalisation", () => {
const wsId = "aaaaaaaa-bbbb-cccc-dddd-eeeeeeeeeeee";
@@ -39,3 +39,128 @@ describe("resolveAttachmentHref — URI scheme normalisation", () => {
expect(resolveAttachmentHref(wsId, "s3://bucket/key")).toBe("s3://bucket/key");
});
});
// #2973 follow-up to #2968: cover the platform-pending: scheme branch
// (poll-mode chat uploads) + the isPlatformAttachment SSOT helper that
// the chip-download and markdown-link paths both consume.
//
// Pre-fix the platform-pending: URI fell through to the raw URI →
// browser saw an unhandled-protocol click → about:blank. The fix
// resolves it to the platform pending-uploads endpoint with auth
// headers attached.
describe("resolveAttachmentHref — platform-pending: scheme (poll-mode uploads)", () => {
// Use a chat workspace ID that DIFFERS from the one in the URI, so
// tests can verify which one the resolver uses. The forward-across-
// workspace case is real production behavior — files dragged into one
// workspace's chat can be referenced from another.
const chatWs = "chat-ws-aaaaaaaa";
const sourceWs = "source-ws-bbbbbbbb";
it("resolves a well-formed platform-pending: URI to /pending-uploads/<file>/content", () => {
const url = resolveAttachmentHref(
chatWs,
`platform-pending:${sourceWs}/file-12345`,
);
expect(url).toContain(`/workspaces/${sourceWs}/pending-uploads/file-12345/content`);
});
it("uses the URI's wsid, NOT the chat workspace_id (cross-workspace forwarding)", () => {
// The two ids differ — this is the case PR #2968's commit
// explicitly calls out. A regression that flipped this would
// silently mis-route the download to the WRONG workspace's
// pending-uploads store, returning 404 (or worse, leaking).
const url = resolveAttachmentHref(
chatWs,
`platform-pending:${sourceWs}/file-xyz`,
);
expect(url).toContain(`/workspaces/${sourceWs}/`);
expect(url).not.toContain(`/workspaces/${chatWs}/`);
});
it("falls back to raw URI when platform-pending: is missing the slash", () => {
// Defensive: a URI that drifted from the expected wsid/fileid shape
// returns raw rather than producing a broken /pending-uploads//
// path. Pinned to detect a regression where a future "helpful"
// change synthesizes empty wsid/fileID.
expect(resolveAttachmentHref(chatWs, "platform-pending:no-slash")).toBe(
"platform-pending:no-slash",
);
});
it("falls back to raw URI when platform-pending: has empty fileID", () => {
expect(resolveAttachmentHref(chatWs, "platform-pending:abc/")).toBe(
"platform-pending:abc/",
);
});
it("falls back to raw URI when platform-pending: has empty wsid", () => {
expect(resolveAttachmentHref(chatWs, "platform-pending:/file-xyz")).toBe(
"platform-pending:/file-xyz",
);
});
it("regression: exact production repro from #2968 (reno-stars)", () => {
// From the original PR #2968 body: the chat's markdown-link
// override fell through on this exact shape and the browser
// navigated to about:blank. Pin the post-fix output so a future
// refactor can't reintroduce the original bug.
const url = resolveAttachmentHref(
"chat-ws",
"platform-pending:d76977b1-uuid/bb0dcaf3-uuid",
);
expect(url).toContain("/workspaces/d76977b1-uuid/pending-uploads/bb0dcaf3-uuid/content");
expect(url).not.toContain("chat-ws");
});
});
describe("isPlatformAttachment", () => {
it("returns true for platform-pending: URIs", () => {
expect(isPlatformAttachment("platform-pending:abc/file")).toBe(true);
});
it("returns true even for malformed platform-pending: URIs", () => {
// The helper is a SHAPE check — caller routes through
// downloadChatFile and downloadChatFile handles the malformed case
// downstream. Pinning so a future helper that "validates" the
// wsid/fileID shape doesn't silently break the auth-attached
// download flow for in-flight URIs.
expect(isPlatformAttachment("platform-pending:no-slash")).toBe(true);
});
it("returns true for workspace:<allowed-root> URIs", () => {
expect(isPlatformAttachment("workspace:/configs/foo")).toBe(true);
expect(isPlatformAttachment("workspace:/workspace/x.pdf")).toBe(true);
});
it("returns true for file:///<allowed-root> URIs", () => {
expect(isPlatformAttachment("file:///workspace/x")).toBe(true);
});
it("returns true for absolute paths under allowed roots", () => {
expect(isPlatformAttachment("/home/user/x")).toBe(true);
expect(isPlatformAttachment("/configs/y")).toBe(true);
});
it("returns FALSE for bare HTTPS URLs to other origins", () => {
// Auth-leak class regression: a helper that always returned true
// would attach workspace tokens to third-party requests. Pin
// the negative case explicitly.
expect(isPlatformAttachment("https://example.com/file")).toBe(false);
expect(isPlatformAttachment("http://example.com/file")).toBe(false);
});
it("returns FALSE for non-allowlisted root paths", () => {
expect(isPlatformAttachment("/etc/passwd")).toBe(false);
expect(isPlatformAttachment("/var/log/x")).toBe(false);
expect(isPlatformAttachment("/tmp/x")).toBe(false);
});
it("returns FALSE for empty string", () => {
expect(isPlatformAttachment("")).toBe(false);
});
it("returns FALSE for unrecognised schemes", () => {
expect(isPlatformAttachment("s3://bucket/key")).toBe(false);
expect(isPlatformAttachment("ftp://server/file")).toBe(false);
});
});
@@ -0,0 +1,154 @@
// preview-kind.ts — single source of truth for "what renderer should
// this attachment use" (RFC #2991, PR-1).
//
// Per the RFC's Phase 2 design, MIME type is the dispatch axis. The
// wire shape (ChatAttachment.mimeType) already carries it end-to-end
// from the server's chat_files.go through agent_message_writer.go to
// the canvas hydrater — we just need to map it to a render kind.
//
// Why a separate file from AttachmentPreview.tsx: the kind helper is
// a pure function that's easier to unit-test in isolation than a
// React component, and unit tests across MIME families are the
// regression line for new types added later.
/** The render-kind taxonomy. Each kind has a dedicated component:
*
* image → AttachmentImage (inline thumbnail + click → lightbox)
* video → AttachmentVideo (HTML5 <video controls>, native fullscreen)
* audio → AttachmentAudio (HTML5 <audio controls>)
* pdf → AttachmentPDF (browser-native <embed>, fullscreen modal)
* text → AttachmentTextPreview (monospace, first N lines, expand)
* file → AttachmentChip (existing fallback — generic file pill)
*
* NB: `text` includes JSON, YAML, source code, plain text — anything
* that renders sensibly as preformatted ASCII without a specialized
* viewer. PR-1 ships only `image` + `file`; PR-2 adds video/audio;
* PR-3 adds pdf + text. All routed through this same dispatch table
* so adding a new kind is a one-line registration. */
export type AttachmentPreviewKind = "image" | "video" | "audio" | "pdf" | "text" | "file";
/** Maps a MIME type to the render kind. Falls back to "file" for
* any MIME we don't have a renderer for (current behavior — the
* attachment chip is the universal fallback).
*
* Filename-based fallback: when mimeType is missing or generic
* (application/octet-stream), inspect the URI's extension. The
* workspace-server's chat_files.go derives Content-Type from the
* file extension, but agent-emitted attachments may not always
* set mimeType, and the canvas should still preview a file named
* `screenshot.png` even if the wire shape lacks the MIME.
*
* Strict MIME match always wins; extension fallback only applies
* to empty / generic. Unknown extension → "file". */
export function getAttachmentPreviewKind(
mimeType: string | undefined,
uri?: string,
name?: string,
): AttachmentPreviewKind {
const mime = (mimeType ?? "").toLowerCase().trim();
// Strict MIME match (preferred — set by server's Content-Type
// detection or by the agent's explicit mimeType field).
if (mime.startsWith("image/")) return "image";
if (mime.startsWith("video/")) return "video";
if (mime.startsWith("audio/")) return "audio";
if (mime === "application/pdf") return "pdf";
if (
mime.startsWith("text/") ||
mime === "application/json" ||
mime === "application/yaml" ||
mime === "application/x-yaml" ||
mime === "application/javascript" ||
mime === "application/typescript"
) {
return "text";
}
// Extension-based fallback — only when MIME is missing or
// application/octet-stream (the server's "I don't know" default).
// Skip when MIME is set to something specific we just don't have
// a renderer for (e.g. application/zip → file is correct).
const looksGeneric = mime === "" || mime === "application/octet-stream";
if (looksGeneric) {
const ext = extractExtension(uri, name);
if (ext) {
const kind = EXTENSION_KIND.get(ext);
if (kind) return kind;
}
}
return "file";
}
// Extension → kind table for the fallback branch. Keep this list
// short and curated — every entry is a UX commitment to render
// inline, and a wrong inference (e.g. .doc rendered as text) is
// worse than the generic file chip.
const EXTENSION_KIND: ReadonlyMap<string, AttachmentPreviewKind> = new Map([
// Images
["png", "image"],
["jpg", "image"],
["jpeg", "image"],
["gif", "image"],
["webp", "image"],
["svg", "image"],
["avif", "image"],
["bmp", "image"],
// Video
["mp4", "video"],
["webm", "video"],
["mov", "video"],
["mkv", "video"],
// Audio
["mp3", "audio"],
["wav", "audio"],
["ogg", "audio"],
["m4a", "audio"],
["flac", "audio"],
// PDF
["pdf", "pdf"],
// Text-ish (rendered as preformatted ASCII)
["txt", "text"],
["md", "text"],
["json", "text"],
["yaml", "text"],
["yml", "text"],
["js", "text"],
["ts", "text"],
["tsx", "text"],
["jsx", "text"],
["py", "text"],
["go", "text"],
["rs", "text"],
["java", "text"],
["c", "text"],
["cpp", "text"],
["h", "text"],
["hpp", "text"],
["sh", "text"],
["bash", "text"],
["html", "text"],
["css", "text"],
["sql", "text"],
["toml", "text"],
["ini", "text"],
["xml", "text"],
["csv", "text"],
["log", "text"],
]);
/** Extracts the lowercased extension from a uri or name, without
* the leading dot. Returns "" when no extension is present. */
function extractExtension(uri: string | undefined, name: string | undefined): string {
// Prefer name (always a leaf path); fall back to uri's last
// segment. Strip query string + fragment so a URI like
// "https://example.com/foo.png?download=1" still parses as png.
const candidate = name || uri || "";
if (!candidate) return "";
let leaf = candidate.split(/[\\/]/).pop() || "";
// Drop ?query and #fragment.
leaf = leaf.split(/[?#]/)[0];
const dot = leaf.lastIndexOf(".");
if (dot < 0 || dot === leaf.length - 1) return "";
return leaf.slice(dot + 1).toLowerCase();
}
+40 -2
View File
@@ -44,6 +44,8 @@ export async function uploadChatFiles(
* - `workspace:<abs-path>` (our canonical form)
* - `file:///workspace/...` (some agents emit this)
* - `/workspace/...` (bare absolute path inside the container)
* - `platform-pending:<wsid>/<file_id>` (poll-mode upload, staged
* on platform side; resolves to /pending-uploads/<file_id>/content)
* Everything that looks like an allowed-root container path is
* rewritten to the authenticated /chat/download endpoint. HTTP(S)
* URIs pass through unchanged so we can also render links to
@@ -53,6 +55,35 @@ export function resolveAttachmentHref(
workspaceId: string,
uri: string,
): string {
// platform-pending: agents-emitted URI that lives in the platform-side
// staging layer (poll-mode chat uploads, see workspace-server's
// chat_files.go ~line 690 + pendinguploads.Storage). The wire shape
// is `platform-pending:<workspace_id>/<file_id>`. Resolving it
// requires hitting GET /workspaces/<wsid>/pending-uploads/<file_id>/content
// which streams the bytes with full workspace auth. Without this
// case the browser sees an unhandled-protocol click → about:blank,
// which was the user-visible bug from 2026-05-05 (reno-stars).
if (uri.startsWith("platform-pending:")) {
const rest = uri.slice("platform-pending:".length);
const slash = rest.indexOf("/");
// Defensive: if the URI doesn't have the expected wsid/fileid
// shape, fall through to raw-URI handling so the consumer can
// still try to render it (rather than producing a broken /pending-
// uploads/// path).
if (slash > 0) {
const wsid = rest.slice(0, slash);
const fileID = rest.slice(slash + 1);
if (wsid && fileID) {
// Use the URI's own workspace_id (the bytes live in THAT
// workspace's pending-uploads store), not the chat's
// workspace_id — these CAN differ when a user drags a file
// into one workspace's chat that gets forwarded to another
// (cross-workspace delegation, agent forwarding).
return `${PLATFORM_URL}/workspaces/${wsid}/pending-uploads/${fileID}/content`;
}
}
return uri;
}
const containerPath = normalizeWorkspaceUri(uri);
if (containerPath) {
return `${PLATFORM_URL}/workspaces/${workspaceId}/chat/download?path=${encodeURIComponent(containerPath)}`;
@@ -60,6 +91,14 @@ export function resolveAttachmentHref(
return uri;
}
/** Returns true when the URI points at a platform-side resource that
* requires our auth headers — caller should route through
* downloadChatFile rather than letting the browser navigate. */
export function isPlatformAttachment(uri: string): boolean {
if (uri.startsWith("platform-pending:")) return true;
return normalizeWorkspaceUri(uri) !== null;
}
/** Extracts the absolute container path from a workspace-scoped URI,
* or null if the URI isn't a container path. The matching roots
* mirror the server's `allowedRoots` allowlist. */
@@ -96,8 +135,7 @@ export async function downloadChatFile(
attachment: ChatAttachment,
): Promise<void> {
const href = resolveAttachmentHref(workspaceId, attachment.uri);
const isContainerPath = normalizeWorkspaceUri(attachment.uri) !== null;
if (!isContainerPath) {
if (!isPlatformAttachment(attachment.uri)) {
// External URL — let the browser navigate. Opens in new tab so
// the canvas context survives a navigation. `href` here is the
// raw URI (http(s), or anything else the agent sent back).
+88 -2
View File
@@ -54,8 +54,10 @@ TOP_LEVEL_MODULES = {
"a2a_client",
"a2a_executor",
"a2a_mcp_server",
"a2a_response",
"a2a_tools",
"a2a_tools_delegation",
"a2a_tools_inbox",
"a2a_tools_memory",
"a2a_tools_messaging",
"a2a_tools_rbac",
@@ -79,6 +81,7 @@ TOP_LEVEL_MODULES = {
"internal_file_read",
"main",
"mcp_cli",
"mcp_doctor",
"mcp_heartbeat",
"mcp_inbox_pollers",
"mcp_workspace_resolver",
@@ -290,10 +293,37 @@ directory** by the `publish-runtime` GitHub Actions workflow on every
Operators running an agent outside the platform's container fleet
(any runtime that supports MCP stdio — Claude Code, hermes, codex,
etc.) can install this wheel and run the universal MCP server
locally:
locally.
### Requirements
* **Python ≥3.11.** The wheel sets `requires-python = ">=3.11"`. On
older interpreters `pip install` returns the cryptic
`Could not find a version that satisfies the requirement` — that
message is pip filtering this wheel out, NOT the package missing
from PyPI. Upgrade with `brew install python@3.12` /
`apt install python3.12` / `pyenv install 3.12` first.
* **`pipx` recommended over `pip`.** `pipx install` puts
`molecule-mcp` on PATH automatically and isolates the runtime's
deps from your system Python. Plain `pip install --user` works
but the binary lands in `~/.local/bin` (Linux) or
`~/Library/Python/3.X/bin` (macOS) which is often not on PATH on
a fresh shell — `claude mcp add molecule -- molecule-mcp` then
fails with "command not found" at first use.
### Install
```sh
# Recommended:
pipx install molecule-ai-workspace-runtime
# Alternative (manage PATH yourself):
pip install --user molecule-ai-workspace-runtime
```
### Run
```sh
pip install molecule-ai-workspace-runtime
WORKSPACE_ID=<uuid> \\
PLATFORM_URL=https://<tenant>.staging.moleculesai.app \\
MOLECULE_WORKSPACE_TOKEN=<bearer> \\
@@ -306,10 +336,66 @@ runtimes already get via the workspace's auto-spawned MCP. Register
the binary in your agent's MCP config (e.g. Claude Code's
`claude mcp add molecule -- molecule-mcp` with the env above).
### Keeping the token out of shell history
Inline `MOLECULE_WORKSPACE_TOKEN=<bearer>` ends up in `~/.zsh_history`
and (when registered via `claude mcp add`) plaintext in
`~/.claude.json`. To avoid that, write the token to a 0600 file and
point `MOLECULE_WORKSPACE_TOKEN_FILE` at it:
```sh
umask 077
printf '%s' "<bearer>" > ~/.config/molecule/token
WORKSPACE_ID=<uuid> \\
PLATFORM_URL=https://<tenant>.staging.moleculesai.app \\
MOLECULE_WORKSPACE_TOKEN_FILE=$HOME/.config/molecule/token \\
molecule-mcp
```
Token resolution order: `MOLECULE_WORKSPACE_TOKEN` (inline env) →
`MOLECULE_WORKSPACE_TOKEN_FILE` (path) → `${CONFIGS_DIR}/.auth_token`
(in-container default).
The token comes from the canvas → Tokens tab. Restarting an external
workspace from the canvas no longer revokes the token (PR #2412), so
operator tokens persist across status nudges.
### Push vs poll delivery (Claude Code specifics)
By default the inbox runs in **poll mode** — every turn the agent
calls `wait_for_message`, which blocks up to ~60s on
`/activity?since_id=…`. Real-time push delivery is also supported,
but on Claude Code it requires THREE conditions, ALL of which must
hold:
1. **The MCP server declares `experimental.claude/channel`** — this
wheel does (see `_build_initialize_result`). Nothing for you to
do.
2. **Claude Code installs the server as a marketplace plugin** — a
plain `claude mcp add molecule -- molecule-mcp` produces a
non-plugin-sourced server, which Claude Code rejects with
`channel_enable requires a marketplace plugin`. Until the
official `moleculesai/claude-code-plugin` marketplace lands
(tracking [#2936](https://github.com/Molecule-AI/molecule-core/issues/2936)),
operators who want push must scaffold their own local marketplace
under
`~/.claude/marketplaces/molecule-local/` containing a
`marketplace.json` + `plugin.json` that points at this wheel.
3. **Claude Code is launched with the dev-channels flag** — pass
`--dangerously-load-development-channels plugin:molecule@<marketplace>`
on the `claude` invocation. Without this flag the channel
capability is silently ignored.
Symptom of any condition failing: messages arrive but only via the
poll path (every ~160s), not real-time. There's currently no
diagnostic surfaced — `molecule-mcp doctor` (tracking
[#2937](https://github.com/Molecule-AI/molecule-core/issues/2937)) is
planned.
If you don't need real-time push, the default poll path works
universally with no extra setup; both modes converge on the same
`inbox_pop` ack so messages never duplicate.
See [`docs/workspace-runtime-package.md`](https://github.com/Molecule-AI/molecule-core/blob/main/docs/workspace-runtime-package.md)
for the publish flow and architecture.
"""
+216
View File
@@ -0,0 +1,216 @@
#!/usr/bin/env bash
# scripts/check-stale-promote-pr.sh
#
# Scan open auto-promote PRs (base=main head=staging) for the
# silent-block failure mode that motivated issue #2975:
# - PR sat for hours with mergeStateStatus=BLOCKED
# - reviewDecision=REVIEW_REQUIRED (auto-merge armed but waiting
# on a human approval that never comes)
#
# When found, emit:
# - GitHub Actions notice/warning lines (workflow summary surface)
# - Optionally post a comment on the PR (--comment)
#
# Exit code is the count of stale PRs found, capped at 125 so callers
# can detect "alarm fired" via `if ! check-stale-promote-pr.sh; then …`.
# Exit 0 = clean, exit ≥1 = at least N stale PRs need attention.
#
# Used by .github/workflows/auto-promote-stale-alarm.yml. Logic lives
# here (not inline in the workflow YAML) so we can:
# - Unit-test it with a stubbed `gh` (see test-check-stale-promote-pr.sh)
# - Run it ad-hoc by an operator: `scripts/check-stale-promote-pr.sh`
# - Reuse the same surface in any sibling workflow that needs the same
# check (SSOT — one detector, many callers).
#
# Requires: `gh` CLI, `jq`. `GH_TOKEN` env in the workflow context.
set -euo pipefail
# -----------------------------------------------------------------------------
# Inputs
# -----------------------------------------------------------------------------
# Threshold beyond which a BLOCKED+REVIEW_REQUIRED promote PR is "stale"
# enough to alarm. 4 hours is the floor: most legitimate gates clear
# inside an hour, so 4× headroom is plenty for slow CI without false-
# alarming. Override via env for tests + edge ops.
STALE_HOURS="${STALE_HOURS:-4}"
# Repo defaults to the current `gh` context. Tests pass --repo explicitly.
REPO="${GITHUB_REPOSITORY:-}"
# Whether to post a comment to the PR. Off by default to avoid noise on
# manual ad-hoc runs; the cron workflow turns it on.
POST_COMMENT="${POST_COMMENT:-false}"
# Where to read the open-PR JSON from. Empty = call `gh` live. Tests
# point this at a fixture file.
PR_FIXTURE="${PR_FIXTURE:-}"
# Where to read "now" from. Empty = real clock. Tests freeze time so
# the staleness math is deterministic.
NOW_OVERRIDE="${NOW_OVERRIDE:-}"
while [ $# -gt 0 ]; do
case "$1" in
--repo) REPO="$2"; shift 2 ;;
--comment) POST_COMMENT="true"; shift ;;
--no-comment) POST_COMMENT="false"; shift ;;
--fixture) PR_FIXTURE="$2"; shift 2 ;;
--stale-hours) STALE_HOURS="$2"; shift 2 ;;
-h|--help)
sed -n '1,/^set /p' "$0" | grep '^# ' | sed 's/^# //'
exit 0
;;
*) echo "unknown arg: $1" >&2; exit 64 ;;
esac
done
if [ -z "$REPO" ] && [ -z "$PR_FIXTURE" ]; then
echo "::error::REPO env (or GITHUB_REPOSITORY) required when no fixture given" >&2
exit 2
fi
# -----------------------------------------------------------------------------
# Clock helpers — split out so tests can freeze time
# -----------------------------------------------------------------------------
now_epoch() {
if [ -n "$NOW_OVERRIDE" ]; then
printf '%s\n' "$NOW_OVERRIDE"
else
date -u +%s
fi
}
# Parse RFC3339 timestamps the way GitHub emits them (e.g.
# "2026-05-05T23:15:00Z"). gnu-date uses -d, bsd-date uses -j -f. Cover
# both because the workflow runs on ubuntu-latest (gnu) but operators
# may run this script on macOS (bsd).
to_epoch() {
local ts="$1"
# gnu-date path first.
if date -u -d "$ts" +%s 2>/dev/null; then
return 0
fi
# bsd-date fallback — strip optional fractional seconds before %S.
local ts_clean="${ts%%.*}"
ts_clean="${ts_clean%Z}Z"
date -u -j -f "%Y-%m-%dT%H:%M:%SZ" "$ts_clean" +%s 2>/dev/null || {
echo "::error::cannot parse timestamp: $ts" >&2
return 1
}
}
# -----------------------------------------------------------------------------
# Fetch open auto-promote PRs
# -----------------------------------------------------------------------------
fetch_prs() {
if [ -n "$PR_FIXTURE" ]; then
cat "$PR_FIXTURE"
return 0
fi
gh pr list --repo "$REPO" \
--base main --head staging --state open \
--json number,title,createdAt,mergeStateStatus,reviewDecision,url
}
# -----------------------------------------------------------------------------
# Stale detection
# -----------------------------------------------------------------------------
# Read PR list from stdin, emit one TSV line per stale PR:
# <num>\t<age_hours>\t<url>\t<title>
# Caller decides what to do (warn, comment, escalate).
detect_stale() {
local now_ts
now_ts="$(now_epoch)"
local stale_seconds=$((STALE_HOURS * 3600))
jq -r '.[] | [.number, .createdAt, .mergeStateStatus, .reviewDecision, .url, .title] | @tsv' \
| while IFS=$'\t' read -r num created_at merge_state review_decision url title; do
# Only alarm on the specific failure mode: BLOCKED + REVIEW_REQUIRED.
# Other BLOCKED reasons (DIRTY, BEHIND, failed checks) are the
# author's signal-to-fix; this script targets the silent
# "no human reviewed yet" wedge specifically.
[ "$merge_state" = "BLOCKED" ] || continue
[ "$review_decision" = "REVIEW_REQUIRED" ] || continue
local created_ts
created_ts="$(to_epoch "$created_at")" || continue
local age=$((now_ts - created_ts))
if [ "$age" -ge "$stale_seconds" ]; then
local age_h=$((age / 3600))
printf '%s\t%d\t%s\t%s\n' "$num" "$age_h" "$url" "$title"
fi
done
}
# -----------------------------------------------------------------------------
# Reporting
# -----------------------------------------------------------------------------
# Comment body — kept short; the issue body has the full design.
comment_body() {
local age_h="$1"
cat <<EOF
⚠️ This auto-promote PR has been BLOCKED on \`REVIEW_REQUIRED\` for **${age_h}h**.
Auto-merge is armed, but main's branch protection requires 1 review and no human has approved. Until someone reviews, the staging→main promote chain is wedged and downstream consumers (canvas builds, tenant redeploys) won't see new code.
**Action**: a human reviewer on \`@Molecule-AI/maintainers\` should approve this PR (or mark it as not ready and close).
Detected by \`scripts/check-stale-promote-pr.sh\` per issue #2975.
EOF
}
post_comment() {
local pr_num="$1"
local age_h="$2"
if [ "$POST_COMMENT" != "true" ]; then
return 0
fi
# Idempotency: only one alarm comment per PR. Look for the marker
# string in existing comments before posting a new one.
local existing
existing="$(gh pr view "$pr_num" --repo "$REPO" --json comments \
--jq '.comments[] | select(.body | test("scripts/check-stale-promote-pr.sh per issue #2975")) | .databaseId' \
| head -n1)"
if [ -n "$existing" ]; then
echo "::notice::PR #$pr_num already has a stale-alarm comment ($existing) — not re-posting"
return 0
fi
comment_body "$age_h" | gh pr comment "$pr_num" --repo "$REPO" --body-file -
echo "::notice::Posted stale-alarm comment on PR #$pr_num (age=${age_h}h)"
}
# -----------------------------------------------------------------------------
# Main
# -----------------------------------------------------------------------------
stale_count=0
while IFS=$'\t' read -r num age_h url title; do
[ -n "$num" ] || continue
stale_count=$((stale_count + 1))
echo "::warning title=Stale auto-promote PR::PR #$num — BLOCKED on REVIEW_REQUIRED for ${age_h}h. $url"
{
echo "## ⚠️ Stale auto-promote PR detected"
echo
echo "- PR: #$num — \`$title\`"
echo "- Age: ${age_h}h"
echo "- State: BLOCKED on REVIEW_REQUIRED"
echo "- URL: $url"
echo
echo "Auto-merge is armed but waiting on a human review. See issue #2975."
} >> "${GITHUB_STEP_SUMMARY:-/dev/null}"
post_comment "$num" "$age_h"
done < <(fetch_prs | detect_stale)
if [ "$stale_count" -eq 0 ]; then
echo "::notice::No stale auto-promote PRs detected (threshold: ${STALE_HOURS}h)"
fi
# Cap exit code so we don't accidentally break shells that interpret
# >125 as signal-style. 1..N maps to "1..N stale PRs".
exit $(( stale_count > 125 ? 125 : stale_count ))
+257
View File
@@ -0,0 +1,257 @@
#!/usr/bin/env bash
# scripts/test-check-stale-promote-pr.sh
#
# Exhaustive bash unit tests for check-stale-promote-pr.sh.
# Goal: 100% branch coverage on the detector logic.
#
# Each case writes a fixture JSON, freezes the clock with NOW_OVERRIDE,
# runs the script with --fixture + --no-comment (so we don't try to
# actually call `gh pr comment`), and asserts on stdout/exit code.
#
# Run: bash scripts/test-check-stale-promote-pr.sh
# Expected: "All N tests passed" + exit 0.
set -euo pipefail
SCRIPT="$(cd "$(dirname "$0")" && pwd)/check-stale-promote-pr.sh"
TMP="$(mktemp -d)"
trap 'rm -rf "$TMP"' EXIT
PASS=0
FAIL=0
# ─────────────────────────────────────────────────────────────────────────────
# Helpers
# ─────────────────────────────────────────────────────────────────────────────
# Frozen "now" — 2026-05-06T05:00:00Z. Compute dynamically so the
# tests stay correct regardless of platform-specific date semantics
# (gnu vs bsd) and any author math errors on the epoch.
if FROZEN_NOW="$(date -u -d '2026-05-06T05:00:00Z' +%s 2>/dev/null)"; then
: # gnu-date worked
elif FROZEN_NOW="$(date -u -j -f '%Y-%m-%dT%H:%M:%SZ' '2026-05-06T05:00:00Z' +%s 2>/dev/null)"; then
: # bsd-date worked
else
echo "FATAL: cannot compute FROZEN_NOW on this platform" >&2
exit 1
fi
run_script() {
# Args: <fixture-file>
# Returns stdout + exit code via a known marker.
local fixture="$1"
shift
set +e
NOW_OVERRIDE="$FROZEN_NOW" \
POST_COMMENT="false" \
bash "$SCRIPT" --fixture "$fixture" "$@" 2>&1
local rc=$?
set -e
echo "EXIT_CODE=$rc"
}
assert_pass() {
local name="$1"
local got="$2"
local want_pattern="$3"
if printf '%s' "$got" | grep -qE "$want_pattern"; then
PASS=$((PASS + 1))
printf ' ✓ %s\n' "$name"
else
FAIL=$((FAIL + 1))
printf ' ✗ %s\n want pattern: %s\n got:\n%s\n' "$name" "$want_pattern" "$got"
fi
}
assert_no_match() {
local name="$1"
local got="$2"
local bad_pattern="$3"
if printf '%s' "$got" | grep -qE "$bad_pattern"; then
FAIL=$((FAIL + 1))
printf ' ✗ %s\n bad pattern matched: %s\n got:\n%s\n' "$name" "$bad_pattern" "$got"
else
PASS=$((PASS + 1))
printf ' ✓ %s\n' "$name"
fi
}
# ─────────────────────────────────────────────────────────────────────────────
# Test cases
# ─────────────────────────────────────────────────────────────────────────────
echo "1. Empty PR list — clean exit"
echo '[]' > "$TMP/empty.json"
got=$(run_script "$TMP/empty.json")
assert_pass "empty-no-warning" "$got" "No stale auto-promote PRs detected"
assert_pass "empty-exit-zero" "$got" "EXIT_CODE=0"
echo
echo "2. Single PR, BLOCKED+REVIEW_REQUIRED, 5h old — fires alarm"
cat > "$TMP/stale1.json" <<EOF
[{
"number": 2963,
"title": "staging → main",
"createdAt": "2026-05-06T00:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://github.com/test/test/pull/2963"
}]
EOF
got=$(run_script "$TMP/stale1.json")
assert_pass "stale1-warning" "$got" "Stale auto-promote PR"
assert_pass "stale1-pr-number" "$got" "PR #2963"
assert_pass "stale1-age" "$got" "for 5h"
assert_pass "stale1-exit-1" "$got" "EXIT_CODE=1"
echo
echo "3. Same PR but only 3h old — under threshold, NO alarm"
cat > "$TMP/young.json" <<EOF
[{
"number": 100,
"title": "fresh promote",
"createdAt": "2026-05-06T02:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://github.com/test/test/pull/100"
}]
EOF
got=$(run_script "$TMP/young.json")
assert_pass "young-no-alarm" "$got" "No stale auto-promote PRs"
assert_pass "young-exit-zero" "$got" "EXIT_CODE=0"
assert_no_match "young-no-warning" "$got" "Stale auto-promote PR"
echo
echo "4. PR is BLOCKED but for the wrong reason (DIRTY, not REVIEW_REQUIRED)"
cat > "$TMP/dirty.json" <<EOF
[{
"number": 200,
"title": "needs rebase",
"createdAt": "2026-05-06T00:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "APPROVED",
"url": "https://github.com/test/test/pull/200"
}]
EOF
got=$(run_script "$TMP/dirty.json")
assert_pass "dirty-no-alarm" "$got" "No stale auto-promote PRs"
assert_pass "dirty-exit-zero" "$got" "EXIT_CODE=0"
echo
echo "5. PR is APPROVED but mergeStateStatus is CLEAN — NOT alarming"
cat > "$TMP/clean.json" <<EOF
[{
"number": 300,
"title": "all green",
"createdAt": "2026-05-06T00:00:00Z",
"mergeStateStatus": "CLEAN",
"reviewDecision": "APPROVED",
"url": "https://github.com/test/test/pull/300"
}]
EOF
got=$(run_script "$TMP/clean.json")
assert_pass "clean-no-alarm" "$got" "No stale auto-promote PRs"
echo
echo "6. Multiple PRs — only the BLOCKED+REVIEW_REQUIRED+old one alarms"
cat > "$TMP/mixed.json" <<EOF
[
{
"number": 100,
"title": "fresh",
"createdAt": "2026-05-06T04:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://x/100"
},
{
"number": 200,
"title": "stale + alarming",
"createdAt": "2026-05-05T20:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://x/200"
},
{
"number": 300,
"title": "approved + clean",
"createdAt": "2026-05-05T20:00:00Z",
"mergeStateStatus": "CLEAN",
"reviewDecision": "APPROVED",
"url": "https://x/300"
}
]
EOF
got=$(run_script "$TMP/mixed.json")
assert_pass "mixed-only-200" "$got" "PR #200"
assert_no_match "mixed-not-100" "$got" "PR #100"
assert_no_match "mixed-not-300" "$got" "PR #300"
assert_pass "mixed-exit-1" "$got" "EXIT_CODE=1"
echo
echo "7. Custom STALE_HOURS via --stale-hours overrides threshold"
got=$(run_script "$TMP/young.json" --stale-hours 1)
assert_pass "custom-threshold-fires" "$got" "PR #100"
assert_pass "custom-threshold-exit-1" "$got" "EXIT_CODE=1"
echo
echo "8. Two stale PRs — exit code reflects count"
cat > "$TMP/two-stale.json" <<EOF
[
{
"number": 200,
"title": "stale-A",
"createdAt": "2026-05-05T20:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://x/200"
},
{
"number": 201,
"title": "stale-B",
"createdAt": "2026-05-05T19:00:00Z",
"mergeStateStatus": "BLOCKED",
"reviewDecision": "REVIEW_REQUIRED",
"url": "https://x/201"
}
]
EOF
got=$(run_script "$TMP/two-stale.json")
assert_pass "two-stale-exit-2" "$got" "EXIT_CODE=2"
echo
echo "9. Help text is shown for --help"
set +e
help_out=$(bash "$SCRIPT" --help 2>&1)
help_rc=$?
set -e
assert_pass "help-exits-zero" "EXIT_CODE=$help_rc" "EXIT_CODE=0"
assert_pass "help-mentions-issue" "$help_out" "issue #2975"
echo
echo "10. Unknown arg exits 64 (EX_USAGE)"
set +e
bad_out=$(bash "$SCRIPT" --bogus 2>&1)
bad_rc=$?
set -e
assert_pass "unknown-arg-rc" "EXIT_CODE=$bad_rc" "EXIT_CODE=64"
echo
echo "11. Missing repo + missing fixture exits 2"
set +e
out=$(REPO="" bash "$SCRIPT" 2>&1)
rc=$?
set -e
assert_pass "no-repo-exit-2" "EXIT_CODE=$rc" "EXIT_CODE=2"
# ─────────────────────────────────────────────────────────────────────────────
# Summary
# ─────────────────────────────────────────────────────────────────────────────
echo
echo "─────────────────────────────────────────────"
echo "Tests: $PASS passed, $FAIL failed"
if [ "$FAIL" -gt 0 ]; then
exit 1
fi
echo "All tests passed."
+37
View File
@@ -157,6 +157,43 @@ A2A_RESP=$(curl -s --max-time "$TIMEOUT" -X POST "$BASE/workspaces/$POLL_WS_ID/a
}')
check "poll-mode A2A returns queued status" '"status":"queued"' "$A2A_RESP"
# ---------- Phase 3.5: Python parser classifies queued envelope correctly ----------
# (#2967) — server emits the queued envelope, the wheel's a2a_response.parse()
# MUST classify it as the Queued variant, not Malformed. Pre-#2967 the bare
# message/send parser in a2a_client.py:587 misclassified this and returned
# "[A2A_ERROR] unexpected response shape", which broke external↔external A2A
# on poll-mode peers.
#
# This phase exercises the actual on-the-wire response from a real
# workspace-server (NOT a mocked dict) through the same module the production
# wheel ships, so a regression in either the server emit shape OR the client
# parser fails this E2E.
echo ""
echo "--- Phase 3.5: Python parser classifies real server response (#2967) ---"
# Pipe the queued response captured above through a2a_response.parse and
# assert the classification. WORKSPACE_ID is required at module import
# time but irrelevant to this parsing call (any UUID is fine).
PARSE_RESULT=$(WORKSPACE_ID="00000000-0000-0000-0000-000000000001" \
python3 -c "
import json, sys
sys.path.insert(0, '$(cd "$(dirname "$0")/../../workspace" && pwd)')
import a2a_response
data = json.loads(r'''$A2A_RESP''')
v = a2a_response.parse(data)
print(type(v).__name__)
if isinstance(v, a2a_response.Queued):
print(f'method={v.method} delivery_mode={v.delivery_mode}')
")
check_eq "Python parser classifies real server response as Queued" \
"Queued" "$(printf '%s' "$PARSE_RESULT" | head -n1)"
check "Queued variant captures method=message/send" \
"method=message/send" "$PARSE_RESULT"
check "Queued variant captures delivery_mode=poll" \
"delivery_mode=poll" "$PARSE_RESULT"
check "queued response echoes delivery_mode=poll" '"delivery_mode":"poll"' "$A2A_RESP"
check "queued response echoes the JSON-RPC method" '"method":"message/send"' "$A2A_RESP"
@@ -21,6 +21,7 @@ import (
"os"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/contract"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/textutil"
)
// verifyConfig is the typed dependency bundle for verifyParity.
@@ -121,7 +122,7 @@ func verifyParity(ctx context.Context, cfg verifyConfig, stdout *os.File) (*veri
matched := true
for _, c := range legacy {
if pluginContents[c] == 0 {
fmt.Fprintf(stdout, "[mismatch] workspace=%s missing-from-plugin content=%q\n", wsID, truncate(c, 80))
fmt.Fprintf(stdout, "[mismatch] workspace=%s missing-from-plugin content=%q\n", wsID, textutil.TruncateBytes(c, 80))
matched = false
break
}
@@ -192,9 +193,4 @@ func queryLegacyMemories(ctx context.Context, db *sql.DB, workspaceID string) ([
return out, rows.Err()
}
func truncate(s string, n int) string {
if len(s) <= n {
return s
}
return s[:n] + "…"
}
// truncation moved to internal/textutil.TruncateBytes (#2962 SSOT).
@@ -349,16 +349,8 @@ func TestVerifyParity_PickSampleError(t *testing.T) {
}
}
// --- Truncate ---
func TestVerifyTruncate(t *testing.T) {
if got := truncate("short", 10); got != "short" {
t.Errorf("got %q", got)
}
if got := truncate(strings.Repeat("a", 200), 10); !strings.HasSuffix(got, "…") {
t.Errorf("expected ellipsis: %q", got)
}
}
// Truncate moved to internal/textutil — coverage in
// internal/textutil/truncate_test.go (TestTruncateBytes_RuneBoundary).
// --- CLI: -verify mode ---
+89
View File
@@ -0,0 +1,89 @@
package main
import "testing"
// TestResolveBindHost pins the precedence: BIND_ADDR explicit > dev-mode
// fail-open default of 127.0.0.1 > production-shape empty (all interfaces).
//
// Mutation-test invariant: removing the IsDevModeFailOpen() branch makes
// "no_bindaddr_devmode_unset_admin" fail (returns "" instead of "127.0.0.1").
// Removing the BIND_ADDR branch makes "explicit_bindaddr_*" cases fail.
func TestResolveBindHost(t *testing.T) {
cases := []struct {
name string
bindAddr string
adminToken string
molEnv string
want string
}{
{
name: "no_bindaddr_devmode_unset_admin",
bindAddr: "",
adminToken: "",
molEnv: "dev",
want: "127.0.0.1",
},
{
name: "no_bindaddr_devmode_unset_admin_full_word",
bindAddr: "",
adminToken: "",
molEnv: "development",
want: "127.0.0.1",
},
{
name: "no_bindaddr_admin_set_in_dev_env",
bindAddr: "",
adminToken: "secret",
molEnv: "dev",
want: "", // ADMIN_TOKEN flips IsDevModeFailOpen to false → all interfaces
},
{
name: "no_bindaddr_production_env",
bindAddr: "",
adminToken: "",
molEnv: "production",
want: "", // production is not a dev value → all interfaces
},
{
name: "no_bindaddr_unset_env",
bindAddr: "",
adminToken: "",
molEnv: "",
want: "", // unset MOLECULE_ENV → not dev → all interfaces
},
{
name: "explicit_bindaddr_loopback_overrides_devmode",
bindAddr: "127.0.0.1",
adminToken: "",
molEnv: "dev",
want: "127.0.0.1",
},
{
name: "explicit_bindaddr_wildcard_overrides_devmode_default",
bindAddr: "0.0.0.0",
adminToken: "",
molEnv: "dev",
want: "0.0.0.0",
},
{
name: "explicit_bindaddr_in_production",
bindAddr: "10.0.5.7",
adminToken: "secret",
molEnv: "production",
want: "10.0.5.7",
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
t.Setenv("BIND_ADDR", tc.bindAddr)
t.Setenv("ADMIN_TOKEN", tc.adminToken)
t.Setenv("MOLECULE_ENV", tc.molEnv)
got := resolveBindHost()
if got != tc.want {
t.Errorf("resolveBindHost() = %q, want %q (BIND_ADDR=%q ADMIN_TOKEN=%q MOLECULE_ENV=%q)",
got, tc.want, tc.bindAddr, tc.adminToken, tc.molEnv)
}
})
}
}
+35 -3
View File
@@ -19,6 +19,7 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/handlers"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/imagewatch"
memwiring "github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/wiring"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/middleware"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/pendinguploads"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/provisioner"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/registry"
@@ -337,15 +338,23 @@ func main() {
// Router
r := router.Setup(hub, broadcaster, prov, platformURL, configsDir, wh, channelMgr, memBundle)
// HTTP server with graceful shutdown
// HTTP server with graceful shutdown.
//
// Bind host: in dev-mode (no ADMIN_TOKEN, MOLECULE_ENV=dev|development)
// the AdminAuth chain fails open by design; pairing that with a wildcard
// bind would expose unauth /workspaces to any same-LAN peer. Default to
// loopback when fail-open is active. Operators who need LAN exposure set
// BIND_ADDR=0.0.0.0 explicitly. Production (ADMIN_TOKEN set) is unchanged.
// See molecule-core#7.
bindHost := resolveBindHost()
srv := &http.Server{
Addr: fmt.Sprintf(":%s", port),
Addr: fmt.Sprintf("%s:%s", bindHost, port),
Handler: r,
}
// Start server in goroutine
go func() {
log.Printf("Platform starting on :%s", port)
log.Printf("Platform starting on %s:%s (dev-mode-fail-open=%v)", bindHost, port, middleware.IsDevModeFailOpen())
if err := srv.ListenAndServe(); err != nil && err != http.ErrServerClosed {
log.Fatalf("Server failed: %v", err)
}
@@ -380,6 +389,29 @@ func envOr(key, fallback string) string {
return fallback
}
// resolveBindHost picks the listener interface for the HTTP server.
//
// Precedence:
// 1. BIND_ADDR — explicit operator override (any value, including "0.0.0.0").
// 2. dev-mode fail-open active → "127.0.0.1" (loopback only).
// 3. otherwise → "" (Go binds every interface; existing prod/self-host shape).
//
// Coupling the loopback default to middleware.IsDevModeFailOpen() means the
// two safety levers — bind narrowness and auth strength — move together. A
// production deploy (ADMIN_TOKEN set) keeps binding to all interfaces because
// the auth chain is doing its job; a dev Mac (no ADMIN_TOKEN, MOLECULE_ENV=dev)
// is reachable only via loopback because the auth chain is fail-open. See
// molecule-core#7 for the original LAN exposure finding.
func resolveBindHost() string {
if v := os.Getenv("BIND_ADDR"); v != "" {
return v
}
if middleware.IsDevModeFailOpen() {
return "127.0.0.1"
}
return ""
}
func findConfigsDir() string {
candidates := []string{
"workspace-configs-templates",
+2 -2
View File
@@ -51,7 +51,7 @@ func Import(
return result
}
_ = broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_PROVISIONING", wsID, map[string]interface{}{
_ = broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceProvisioning), wsID, map[string]interface{}{
"name": b.Name,
"tier": b.Tier,
"source_bundle_id": b.ID,
@@ -142,7 +142,7 @@ func markFailed(ctx context.Context, wsID string, broadcaster *events.Broadcaste
db.DB.ExecContext(ctx,
`UPDATE workspaces SET status = $1, last_sample_error = $2, updated_at = now() WHERE id = $3`,
models.StatusFailed, msg, wsID)
broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_PROVISION_FAILED", wsID, map[string]interface{}{
broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceProvisionFailed), wsID, map[string]interface{}{
"error": msg,
})
}
+11 -10
View File
@@ -10,6 +10,7 @@ import (
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
)
const (
@@ -304,14 +305,14 @@ func (m *Manager) HandleInbound(ctx context.Context, ch ChannelRow, msg *Inbound
"parts": []map[string]interface{}{{"kind": "text", "text": msg.Text}},
},
"metadata": map[string]interface{}{
"source": ch.ChannelType,
"channel_id": ch.ID,
"chat_id": msg.ChatID,
"user_id": msg.UserID,
"username": msg.Username,
"message_id": msg.MessageID,
"history": history,
"extra": msg.Metadata,
"source": ch.ChannelType,
"channel_id": ch.ID,
"chat_id": msg.ChatID,
"user_id": msg.UserID,
"username": msg.Username,
"message_id": msg.MessageID,
"history": history,
"extra": msg.Metadata,
},
},
})
@@ -383,7 +384,7 @@ func (m *Manager) HandleInbound(ctx context.Context, ch ChannelRow, msg *Inbound
// Broadcast event
if m.broadcaster != nil {
m.broadcaster.RecordAndBroadcast(ctx, "CHANNEL_MESSAGE", ch.WorkspaceID, map[string]interface{}{
m.broadcaster.RecordAndBroadcast(ctx, string(events.EventChannelMessage), ch.WorkspaceID, map[string]interface{}{
"channel_id": ch.ID,
"channel_type": ch.ChannelType,
"username": msg.Username,
@@ -427,7 +428,7 @@ func (m *Manager) SendOutbound(ctx context.Context, channelID string, text strin
}
if m.broadcaster != nil {
m.broadcaster.RecordAndBroadcast(ctx, "CHANNEL_MESSAGE", ch.WorkspaceID, map[string]interface{}{
m.broadcaster.RecordAndBroadcast(ctx, string(events.EventChannelMessage), ch.WorkspaceID, map[string]interface{}{
"channel_id": ch.ID,
"channel_type": ch.ChannelType,
"direction": "outbound",
+125
View File
@@ -0,0 +1,125 @@
package events
// types.go — typed taxonomy of WebSocket event names emitted by the
// workspace-server.
//
// RFC #2945 PR-B. Pre-consolidation, every BroadcastOnly /
// RecordAndBroadcast call site passed a bare string literal:
//
// h.broadcaster.BroadcastOnly(workspaceID, "AGENT_MESSAGE", payload)
//
// Producers (Go workspace-server, ~30 call sites across handlers/,
// scheduler/, registry/, bundle/) and consumers (canvas TS store +
// component listeners) duplicated the same string with no shared
// definition. A producer renaming an event silently broke every
// consumer — same drift class that produced the reno-stars data-loss
// regression on the persistence side. The fix on that side was the
// AgentMessageWriter SSOT (PR-A); the fix on this side is named
// constants.
//
// Why a typed string (not a plain enum / iota): the event name
// crosses the wire to TypeScript consumers as the literal string in
// `WSMessage.Event`. Iota integers would break the canvas store's
// switch (`case "AGENT_MESSAGE":`); a typed string preserves the
// wire contract while giving Go callers compile-time discipline.
//
// Mirror in canvas: a parity gate (PR-B-2 follow-up) will assert this
// constant set ≡ the TypeScript union members in
// `canvas/src/lib/ws-events.ts`. Today the canvas consumes the names
// via bare-string comparisons; the mirror lands separately to keep
// PR-B narrow.
// EventType is the wire-typed name of a WebSocket event the platform
// broadcasts. Always emit constants from this file rather than bare
// strings — the AST gate in events_types_drift_test.go guards
// against bare-string usage in the broadcaster surfaces.
type EventType string
// Event constants — the canonical taxonomy. New events MUST be added
// here AND mirrored in canvas/src/lib/ws-events.ts (parity gate
// pending in PR-B-2). Group by semantic family so the list stays
// scan-friendly as it grows.
const (
// Chat / agent messaging — surfaces in canvas chat panels.
EventAgentMessage EventType = "AGENT_MESSAGE"
EventA2AResponse EventType = "A2A_RESPONSE"
EventActivityLogged EventType = "ACTIVITY_LOGGED"
EventChannelMessage EventType = "CHANNEL_MESSAGE"
// Workspace lifecycle.
EventWorkspaceProvisioning EventType = "WORKSPACE_PROVISIONING"
EventWorkspaceProvisionFailed EventType = "WORKSPACE_PROVISION_FAILED"
EventWorkspaceOnline EventType = "WORKSPACE_ONLINE"
EventWorkspaceOffline EventType = "WORKSPACE_OFFLINE"
EventWorkspaceDegraded EventType = "WORKSPACE_DEGRADED"
EventWorkspaceHibernated EventType = "WORKSPACE_HIBERNATED"
EventWorkspacePaused EventType = "WORKSPACE_PAUSED"
EventWorkspaceRemoved EventType = "WORKSPACE_REMOVED"
EventWorkspaceAwaitingAgent EventType = "WORKSPACE_AWAITING_AGENT"
EventWorkspaceHeartbeat EventType = "WORKSPACE_HEARTBEAT"
// Agent assignment + identity.
EventAgentAssigned EventType = "AGENT_ASSIGNED"
EventAgentReplaced EventType = "AGENT_REPLACED"
EventAgentRemoved EventType = "AGENT_REMOVED"
EventAgentMoved EventType = "AGENT_MOVED"
EventAgentCardUpdated EventType = "AGENT_CARD_UPDATED"
// Delegation lifecycle.
EventDelegationSent EventType = "DELEGATION_SENT"
EventDelegationStatus EventType = "DELEGATION_STATUS"
EventDelegationComplete EventType = "DELEGATION_COMPLETE"
EventDelegationFailed EventType = "DELEGATION_FAILED"
// Task progression + scheduler.
EventTaskUpdated EventType = "TASK_UPDATED"
EventCronExecuted EventType = "CRON_EXECUTED"
EventCronSkipped EventType = "CRON_SKIPPED"
// Approvals.
EventApprovalRequested EventType = "APPROVAL_REQUESTED"
EventApprovalEscalated EventType = "APPROVAL_ESCALATED"
// Auth / credentials.
EventExternalCredentialsRotated EventType = "EXTERNAL_CREDENTIALS_ROTATED"
)
// AllEventTypes lists every constant in this file. Used by the
// snapshot test (events_types_drift_test.go) to detect when a new
// constant is added without updating the snapshot — the catch-up
// step is mirroring the addition into canvas/src/lib/ws-events.ts so
// canvas consumers can switch on it.
//
// Keep in lexicographic order so the snapshot diff is stable on
// renames and the parity-with-TS comparison is order-independent.
var AllEventTypes = []EventType{
EventA2AResponse,
EventActivityLogged,
EventAgentAssigned,
EventAgentCardUpdated,
EventAgentMessage,
EventAgentMoved,
EventAgentRemoved,
EventAgentReplaced,
EventApprovalEscalated,
EventApprovalRequested,
EventChannelMessage,
EventCronExecuted,
EventCronSkipped,
EventDelegationComplete,
EventDelegationFailed,
EventDelegationSent,
EventDelegationStatus,
EventExternalCredentialsRotated,
EventTaskUpdated,
EventWorkspaceAwaitingAgent,
EventWorkspaceDegraded,
EventWorkspaceHeartbeat,
EventWorkspaceHibernated,
EventWorkspaceOffline,
EventWorkspaceOnline,
EventWorkspacePaused,
EventWorkspaceProvisionFailed,
EventWorkspaceProvisioning,
EventWorkspaceRemoved,
}
@@ -0,0 +1,117 @@
package events
import (
"sort"
"strings"
"testing"
)
// TestAllEventTypes_IsSnapshot pins the canonical event taxonomy.
// Adding a new constant in types.go without updating AllEventTypes
// (or vice versa) fails this test.
//
// The snapshot is also the authoritative input to the canvas-side
// parity gate (PR-B-2 follow-up): the TypeScript union members in
// canvas/src/lib/ws-events.ts MUST match this list exactly. A drift
// gate at CI time will assert set equality once the TS file lands.
func TestAllEventTypes_IsSnapshot(t *testing.T) {
// Every named constant must appear in AllEventTypes. Walk via
// reflection over the package-level vars would over-include test
// fixtures, so list the canonical names here. When a constant
// is added in types.go, append the EventType's literal value
// to the expected list below — the failure message names
// exactly what's missing so the diff is one-line obvious.
expected := []string{
"A2A_RESPONSE",
"ACTIVITY_LOGGED",
"AGENT_ASSIGNED",
"AGENT_CARD_UPDATED",
"AGENT_MESSAGE",
"AGENT_MOVED",
"AGENT_REMOVED",
"AGENT_REPLACED",
"APPROVAL_ESCALATED",
"APPROVAL_REQUESTED",
"CHANNEL_MESSAGE",
"CRON_EXECUTED",
"CRON_SKIPPED",
"DELEGATION_COMPLETE",
"DELEGATION_FAILED",
"DELEGATION_SENT",
"DELEGATION_STATUS",
"EXTERNAL_CREDENTIALS_ROTATED",
"TASK_UPDATED",
"WORKSPACE_AWAITING_AGENT",
"WORKSPACE_DEGRADED",
"WORKSPACE_HEARTBEAT",
"WORKSPACE_HIBERNATED",
"WORKSPACE_OFFLINE",
"WORKSPACE_ONLINE",
"WORKSPACE_PAUSED",
"WORKSPACE_PROVISIONING",
"WORKSPACE_PROVISION_FAILED",
"WORKSPACE_REMOVED",
}
sort.Strings(expected)
actual := make([]string, 0, len(AllEventTypes))
for _, e := range AllEventTypes {
actual = append(actual, string(e))
}
sort.Strings(actual)
if len(actual) != len(expected) {
t.Errorf("AllEventTypes count = %d, want %d\nactual: %s\nexpected: %s",
len(actual), len(expected),
strings.Join(actual, ", "),
strings.Join(expected, ", "))
return
}
for i, want := range expected {
if actual[i] != want {
t.Errorf("AllEventTypes[%d] = %q, want %q (full diff:\n actual: %v\n expected: %v\n)",
i, actual[i], want, actual, expected)
}
}
}
// TestEventType_NoEmptyConstants pins that no constant declared in
// types.go has an accidentally-empty value. The catch is the
// "WORKSPACE_X" → forgot-to-fill pattern: a typo in the literal
// would surface as the empty string, and broadcast pipelines would
// silently filter empty-name events without any error signal.
func TestEventType_NoEmptyConstants(t *testing.T) {
for _, e := range AllEventTypes {
if string(e) == "" {
t.Errorf("found empty EventType in AllEventTypes — typo in types.go?")
}
}
}
// TestEventType_AllUppercaseSnakeCase pins the wire format. Mixed
// case or kebab-case would break the canvas TypeScript switch
// statements (every consumer's `case "AGENT_MESSAGE":` is upper-
// snake). The check is the catch for an accidental
// `"agent_message"` typo that wouldn't fail the snapshot gate.
func TestEventType_AllUppercaseSnakeCase(t *testing.T) {
for _, e := range AllEventTypes {
s := string(e)
// Allowed chars: A-Z, 0-9, _ — nothing else, no leading/
// trailing underscores, no consecutive underscores.
if s != strings.ToUpper(s) {
t.Errorf("EventType %q is not all-uppercase — wire format requires upper-snake", s)
}
if strings.HasPrefix(s, "_") || strings.HasSuffix(s, "_") {
t.Errorf("EventType %q has leading/trailing underscore — disallowed", s)
}
if strings.Contains(s, "__") {
t.Errorf("EventType %q has consecutive underscores — disallowed", s)
}
for _, r := range s {
if !((r >= 'A' && r <= 'Z') || (r >= '0' && r <= '9') || r == '_') {
t.Errorf("EventType %q contains disallowed char %q", s, r)
break
}
}
}
}
@@ -14,10 +14,12 @@ import (
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/models"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
)
// proxyDispatchBuildError is a sentinel wrapper for failures inside
// http.NewRequestWithContext. handleA2ADispatchError unwraps it to emit the
// "failed to create proxy request" 500 instead of the standard 502/503 paths.
@@ -90,10 +92,10 @@ func (h *WorkspaceHandler) handleA2ADispatchError(ctx context.Context, workspace
Status: http.StatusServiceUnavailable,
Headers: map[string]string{"Retry-After": strconv.Itoa(busyRetryAfterSeconds)},
Response: gin.H{
"error": "workspace agent busy — adapter handles retry (native_session)",
"busy": true,
"retry_after": busyRetryAfterSeconds,
"native_session": true,
"error": "workspace agent busy — adapter handles retry (native_session)",
"busy": true,
"retry_after": busyRetryAfterSeconds,
"native_session": true,
},
}
}
@@ -149,7 +151,7 @@ func (h *WorkspaceHandler) handleA2ADispatchError(ctx context.Context, workspace
// Provisioner selection (mutually exclusive in production):
// - h.provisioner != nil → local Docker deployment; IsRunning does docker inspect.
// - h.cpProv != nil → SaaS / EC2 deployment; IsRunning calls CP's
// /cp/workspaces/:id/status to read the EC2 state.
// /cp/workspaces/:id/status to read the EC2 state.
//
// Pre-fix this function ONLY consulted h.provisioner — for SaaS tenants
// (h.provisioner=nil, h.cpProv=set) it short-circuited to false on every
@@ -191,7 +193,7 @@ func (h *WorkspaceHandler) maybeMarkContainerDead(ctx context.Context, workspace
log.Printf("ProxyA2A: failed to mark workspace %s offline: %v", workspaceID, err)
}
db.ClearWorkspaceKeys(ctx, workspaceID)
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_OFFLINE", workspaceID, map[string]interface{}{})
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
go h.RestartByID(workspaceID)
return true
}
@@ -272,7 +274,7 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
}(ctx)
if callerID == "" && statusCode < 400 {
h.broadcaster.BroadcastOnly(workspaceID, "A2A_RESPONSE", map[string]interface{}{
h.broadcaster.BroadcastOnly(workspaceID, string(events.EventA2AResponse), map[string]interface{}{
"response_body": json.RawMessage(respBody),
"method": a2aMethod,
"duration_ms": durationMs,
@@ -21,6 +21,8 @@ import (
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/textutil"
)
// extractIdempotencyKey pulls params.message.messageId out of an A2A JSON-RPC
@@ -419,7 +421,7 @@ func (h *WorkspaceHandler) stitchDrainResponseToDelegation(ctx context.Context,
AND method = 'delegate_result'
AND target_id = $4
AND response_body->>'delegation_id' = $5
`, "Delegation completed ("+truncate(responseText, 80)+")", string(respJSON),
`, "Delegation completed ("+textutil.TruncateBytes(responseText, 80)+")", string(respJSON),
sourceID, targetID, delegationID)
if err != nil {
log.Printf("A2AQueue drain stitch: update failed for delegation %s: %v", delegationID, err)
@@ -435,10 +437,10 @@ func (h *WorkspaceHandler) stitchDrainResponseToDelegation(ctx context.Context,
// "⏸ queued" line to "✓ completed" in real time. Without this the
// transition only surfaces after the user reloads or polls activity.
if h.broadcaster != nil {
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_COMPLETE", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationComplete), sourceID, map[string]interface{}{
"delegation_id": delegationID,
"target_id": targetID,
"response_preview": truncate(responseText, 200),
"response_preview": textutil.TruncateBytes(responseText, 200),
"via": "queue_drain",
})
}
+75 -79
View File
@@ -55,7 +55,7 @@ func NewActivityHandler(b *events.Broadcaster) *ActivityHandler {
func (h *ActivityHandler) List(c *gin.Context) {
workspaceID := c.Param("id")
activityType := c.Query("type")
source := c.Query("source") // "canvas" = source_id IS NULL, "agent" = source_id IS NOT NULL
source := c.Query("source") // "canvas" = source_id IS NULL, "agent" = source_id IS NOT NULL
peerID := c.Query("peer_id") // optional UUID — restrict to rows where this peer is sender OR target
limitStr := c.DefaultQuery("limit", "100")
sinceSecsStr := c.Query("since_secs")
@@ -465,78 +465,30 @@ func (h *ActivityHandler) Notify(c *gin.Context) {
}
}
// Verify workspace exists
var wsName string
err := db.DB.QueryRowContext(c.Request.Context(),
`SELECT name FROM workspaces WHERE id = $1 AND status != 'removed'`, workspaceID,
).Scan(&wsName)
if err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
// Single source of truth for chat-bearing agent → user messages —
// see agent_message_writer.go for the contract. Pre-RFC-#2945, the
// broadcast + INSERT pair was inlined here and again in
// mcp_tools.go's send_message_to_user, and the duplication is what
// produced the reno-stars data-loss regression. Both paths now
// route through the same writer; future channels (Slack, Discord,
// Lark) hook in here too.
attachments := make([]AgentMessageAttachment, 0, len(body.Attachments))
for _, a := range body.Attachments {
attachments = append(attachments, AgentMessageAttachment{
URI: a.URI,
Name: a.Name,
MimeType: a.MimeType,
Size: a.Size,
})
}
broadcastPayload := map[string]interface{}{
"message": body.Message,
"workspace_id": workspaceID,
"name": wsName,
}
if len(body.Attachments) > 0 {
broadcastPayload["attachments"] = body.Attachments
}
h.broadcaster.BroadcastOnly(workspaceID, "AGENT_MESSAGE", broadcastPayload)
// Persist to activity_logs so the chat history loader restores this
// message after a page reload. Pre-fix, send_message_to_user pushes
// were broadcast-only — survived the WebSocket session but vanished
// when the user refreshed because nothing wrote them to the DB.
//
// Shape chosen to match the existing loader query
// (`type=a2a_receive&source=canvas`):
// - activity_type='a2a_receive' so it joins the same query path
// - source_id=NULL so the canvas-source filter accepts it
// - method='notify' to distinguish from real A2A receives in audits
// - request_body=NULL so the loader doesn't append a duplicate
// "user message" bubble for it
// - response_body={"result": "<text>"} matches extractResponseText's
// simplest branch ({result: string} → take verbatim)
//
// Errors are logged-only — broadcast already succeeded, the user
// sees the message; persistence failure just means the message
// won't survive reload (pre-fix behavior). Don't fail the whole
// notify on a DB hiccup.
// response_body shape — chosen to feed BOTH:
// - extractResponseText: looks at body.result (string) and returns it
// - extractFilesFromTask: looks at body.parts[] for kind=file
// so a chat reload after a notify-with-attachments restores both
// the text bubble AND the download chips.
respPayload := map[string]interface{}{"result": body.Message}
if len(body.Attachments) > 0 {
fileParts := make([]map[string]interface{}, 0, len(body.Attachments))
for _, a := range body.Attachments {
fileMeta := map[string]interface{}{"uri": a.URI, "name": a.Name}
if a.MimeType != "" {
fileMeta["mimeType"] = a.MimeType
}
if a.Size > 0 {
fileMeta["size"] = a.Size
}
fileParts = append(fileParts, map[string]interface{}{
"kind": "file",
"file": fileMeta,
})
writer := NewAgentMessageWriter(db.DB, h.broadcaster)
if err := writer.Send(c.Request.Context(), workspaceID, body.Message, attachments); err != nil {
if errors.Is(err, ErrWorkspaceNotFound) {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
respPayload["parts"] = fileParts
}
respJSON, _ := json.Marshal(respPayload)
preview := body.Message
if len(preview) > 80 {
preview = preview[:80] + "…"
}
if _, err := db.DB.ExecContext(c.Request.Context(), `
INSERT INTO activity_logs (workspace_id, activity_type, method, summary, response_body, status)
VALUES ($1, 'a2a_receive', 'notify', $2, $3::jsonb, 'ok')
`, workspaceID, "Agent message: "+preview, string(respJSON)); err != nil {
log.Printf("Notify: failed to persist message for %s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "internal error"})
return
}
c.JSON(http.StatusOK, gin.H{"status": "sent"})
@@ -628,7 +580,45 @@ func (h *ActivityHandler) Report(c *gin.Context) {
// LogActivity inserts an activity log and optionally broadcasts via WebSocket.
// Takes events.EventEmitter (#1814) so callers passing a stub broadcaster
// in tests no longer need to construct the full *events.Broadcaster.
//
// Errors are logged and swallowed — this is the fire-and-forget contract
// most callers expect. For atomic-with-sibling-writes use LogActivityTx
// and propagate the error.
func LogActivity(ctx context.Context, broadcaster events.EventEmitter, params ActivityParams) {
hook, err := logActivityExec(ctx, db.DB, broadcaster, params)
if err != nil {
log.Printf("LogActivity insert error: %v", err)
return
}
hook()
}
// LogActivityTx inserts the activity row inside the caller-provided tx
// and returns a commitHook that fires the post-commit ACTIVITY_LOGGED
// broadcast. Caller MUST invoke commitHook AFTER tx.Commit() — firing
// it before commit can leak a WebSocket event for a row that ends up
// rolled back, which the canvas's optimistic UI then shows then loses.
//
// Returns an error if the INSERT fails — caller should Rollback. Caller
// is also responsible for tx.BeginTx + tx.Commit/Rollback. Used by
// chat_files uploadPollMode so PutBatchTx + N activity rows commit
// atomically; if any activity row fails, the pending_uploads rows roll
// back too and the client retries the entire multipart upload cleanly.
func LogActivityTx(ctx context.Context, tx *sql.Tx, broadcaster events.EventEmitter, params ActivityParams) (commitHook func(), err error) {
if tx == nil {
return nil, errors.New("LogActivityTx: tx is nil")
}
return logActivityExec(ctx, tx, broadcaster, params)
}
// activityExecutor is the SQL surface LogActivity[Tx] needs. *sql.Tx
// and *sql.DB both satisfy it, so the same insert path serves the
// fire-and-forget caller (db.DB) and the Tx-aware caller (*sql.Tx).
type activityExecutor interface {
ExecContext(ctx context.Context, query string, args ...any) (sql.Result, error)
}
func logActivityExec(ctx context.Context, exec activityExecutor, broadcaster events.EventEmitter, params ActivityParams) (commitHook func(), err error) {
reqJSON, reqErr := json.Marshal(params.RequestBody)
if reqErr != nil {
log.Printf("LogActivity: failed to marshal request_body for %s: %v", params.WorkspaceID, reqErr)
@@ -654,20 +644,21 @@ func LogActivity(ctx context.Context, broadcaster events.EventEmitter, params Ac
traceStr = &s
}
_, err := db.DB.ExecContext(ctx, `
if _, err := exec.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, source_id, target_id, method, summary, request_body, response_body, tool_trace, duration_ms, status, error_detail)
VALUES ($1, $2, $3, $4, $5, $6, $7::jsonb, $8::jsonb, $9::jsonb, $10, $11, $12)
`, params.WorkspaceID, params.ActivityType, params.SourceID, params.TargetID,
params.Method, params.Summary, reqStr, respStr, traceStr,
params.DurationMs, params.Status, params.ErrorDetail)
if err != nil {
log.Printf("LogActivity insert error: %v", err)
return
params.DurationMs, params.Status, params.ErrorDetail); err != nil {
return nil, err
}
// Broadcast ACTIVITY_LOGGED event
// Build the broadcast payload up-front so the post-commit hook is a
// pure in-memory call — no JSON marshaling between commit and emit
// where a panic would leak the row without an event.
var payload map[string]interface{}
if broadcaster != nil {
payload := map[string]interface{}{
payload = map[string]interface{}{
"activity_type": params.ActivityType,
"method": params.Method,
"summary": params.Summary,
@@ -698,8 +689,13 @@ func LogActivity(ctx context.Context, broadcaster events.EventEmitter, params Ac
if respStr != nil {
payload["response_body"] = json.RawMessage(respJSON)
}
broadcaster.BroadcastOnly(params.WorkspaceID, "ACTIVITY_LOGGED", payload)
}
return func() {
if broadcaster != nil {
broadcaster.BroadcastOnly(params.WorkspaceID, string(events.EventActivityLogged), payload)
}
}, nil
}
type ActivityParams struct {
@@ -5,6 +5,7 @@ import (
"context"
"database/sql/driver"
"encoding/json"
"errors"
"fmt"
"net/http"
"net/http/httptest"
@@ -909,6 +910,114 @@ func TestLogActivity_Broadcast_IncludesRequestAndResponseBodies(t *testing.T) {
}
}
// TestLogActivityTx_DefersBroadcastUntilCommitHook pins the #149
// contract: LogActivityTx returns a commitHook that the caller MUST
// invoke after tx.Commit(); the broadcast MUST NOT fire from inside
// LogActivityTx itself. Firing inside would leak a websocket event
// for a row that the caller may roll back, painting a ghost message
// into the canvas's optimistic UI that disappears on the next refresh.
func TestLogActivityTx_DefersBroadcastUntilCommitHook(t *testing.T) {
mock := setupTestDB(t)
defer mock.ExpectationsWereMet()
mock.ExpectBegin()
mock.ExpectExec("INSERT INTO activity_logs").
WillReturnResult(sqlmock.NewResult(1, 1))
mock.ExpectCommit()
tx, err := db.DB.BeginTx(context.Background(), nil)
if err != nil {
t.Fatalf("BeginTx: %v", err)
}
cb := &recordingBroadcaster{}
method := "chat_upload_receive"
hook, err := LogActivityTx(context.Background(), tx, cb, ActivityParams{
WorkspaceID: "ws-123",
ActivityType: "a2a_receive",
Method: &method,
Status: "ok",
})
if err != nil {
t.Fatalf("LogActivityTx: %v", err)
}
if len(cb.calls) != 0 {
t.Errorf("broadcast leaked before commitHook: got %d calls", len(cb.calls))
}
if err := tx.Commit(); err != nil {
t.Fatalf("Commit: %v", err)
}
hook()
if len(cb.calls) != 1 {
t.Fatalf("commitHook must broadcast exactly once, got %d", len(cb.calls))
}
if cb.calls[0].eventType != "ACTIVITY_LOGGED" {
t.Errorf("event type = %q, want ACTIVITY_LOGGED", cb.calls[0].eventType)
}
}
// TestLogActivityTx_InsertError_NoHook_NoBroadcast — when the INSERT
// fails inside the Tx, LogActivityTx returns an error and a nil
// commitHook. The caller is expected to Rollback; no broadcast can
// possibly fire because the hook never exists.
func TestLogActivityTx_InsertError_NoHook_NoBroadcast(t *testing.T) {
mock := setupTestDB(t)
defer mock.ExpectationsWereMet()
mock.ExpectBegin()
mock.ExpectExec("INSERT INTO activity_logs").
WillReturnError(errors.New("constraint violation simulated"))
mock.ExpectRollback()
tx, err := db.DB.BeginTx(context.Background(), nil)
if err != nil {
t.Fatalf("BeginTx: %v", err)
}
cb := &recordingBroadcaster{}
method := "chat_upload_receive"
hook, err := LogActivityTx(context.Background(), tx, cb, ActivityParams{
WorkspaceID: "ws-123",
ActivityType: "a2a_receive",
Method: &method,
Status: "ok",
})
if err == nil {
t.Fatal("expected error on INSERT failure, got nil")
}
if hook != nil {
t.Errorf("commitHook must be nil on insert error, got non-nil hook")
}
if err := tx.Rollback(); err != nil {
t.Fatalf("Rollback: %v", err)
}
if len(cb.calls) != 0 {
t.Errorf("broadcast must NOT fire on insert error, got %d calls", len(cb.calls))
}
}
// TestLogActivityTx_NilTx_Errors — passing a nil tx is caller misuse.
// Return an error rather than panicking on the nil receiver inside
// ExecContext (which would crash the request goroutine and surface as
// a 500 with no log line tying it to the bad call site).
func TestLogActivityTx_NilTx_Errors(t *testing.T) {
cb := &recordingBroadcaster{}
hook, err := LogActivityTx(context.Background(), nil, cb, ActivityParams{
WorkspaceID: "ws-123",
ActivityType: "a2a_receive",
Status: "ok",
})
if err == nil {
t.Fatal("nil tx must error, got nil")
}
if hook != nil {
t.Errorf("commitHook must be nil when tx is nil, got non-nil hook")
}
if len(cb.calls) != 0 {
t.Errorf("broadcast must NOT fire on nil-tx error, got %d", len(cb.calls))
}
}
func TestLogActivity_Broadcast_IncludesResponseBody(t *testing.T) {
mock := setupTestDB(t)
defer mock.ExpectationsWereMet()
@@ -56,10 +56,17 @@ type RefreshResult struct {
Recreated []string `json:"recreated"`
}
// TemplateImageRef returns the canonical GHCR ref for a runtime's template
// image. Single source of truth shared with imagewatch.
// TemplateImageRef returns the canonical image ref for a runtime's template,
// using the configured registry (provisioner.RegistryPrefix()) and the
// moving `:latest` tag. Single source of truth shared with imagewatch.
//
// Defaults to ghcr.io/molecule-ai/workspace-template-<runtime>:latest
// (upstream OSS). When MOLECULE_IMAGE_REGISTRY is set in the environment
// (typically the AWS ECR mirror in production), this returns the prefixed
// equivalent so admin operations and image-watch checks hit the same
// registry the provisioner pulls from.
func TemplateImageRef(runtime string) string {
return fmt.Sprintf("ghcr.io/molecule-ai/workspace-template-%s:latest", runtime)
return fmt.Sprintf("%s/workspace-template-%s:latest", provisioner.RegistryPrefix(), runtime)
}
// ghcrAuthHeader returns the base64-encoded JSON auth payload Docker's
+15 -15
View File
@@ -69,7 +69,7 @@ func (h *AgentHandler) Assign(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(ctx, "AGENT_ASSIGNED", workspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventAgentAssigned), workspaceID, map[string]interface{}{
"agent_id": agentID,
"model": body.Model,
})
@@ -118,7 +118,7 @@ func (h *AgentHandler) Replace(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(ctx, "AGENT_REPLACED", workspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventAgentReplaced), workspaceID, map[string]interface{}{
"agent_id": agentID,
"model": body.Model,
"old_model": oldModel,
@@ -148,7 +148,7 @@ func (h *AgentHandler) Remove(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(ctx, "AGENT_REMOVED", workspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventAgentRemoved), workspaceID, map[string]interface{}{
"agent_id": agentID,
"model": model,
})
@@ -215,21 +215,21 @@ func (h *AgentHandler) Move(c *gin.Context) {
}
// Broadcast on both workspaces
h.broadcaster.RecordAndBroadcast(ctx, "AGENT_MOVED", sourceID, map[string]interface{}{
"agent_id": agentID,
"model": model,
"target_workspace_id": body.TargetWorkspaceID,
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventAgentMoved), sourceID, map[string]interface{}{
"agent_id": agentID,
"model": model,
"target_workspace_id": body.TargetWorkspaceID,
})
h.broadcaster.RecordAndBroadcast(ctx, "AGENT_MOVED", body.TargetWorkspaceID, map[string]interface{}{
"agent_id": agentID,
"model": model,
"source_workspace_id": sourceID,
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventAgentMoved), body.TargetWorkspaceID, map[string]interface{}{
"agent_id": agentID,
"model": model,
"source_workspace_id": sourceID,
})
c.JSON(http.StatusOK, gin.H{
"agent_id": agentID,
"model": model,
"from_workspace": sourceID,
"to_workspace": body.TargetWorkspaceID,
"agent_id": agentID,
"model": model,
"from_workspace": sourceID,
"to_workspace": body.TargetWorkspaceID,
})
}
@@ -0,0 +1,177 @@
package handlers
import (
"go/ast"
"go/parser"
"go/token"
"os"
"path/filepath"
"sort"
"strconv"
"strings"
"testing"
)
// TestAgentMessageBroadcastsArePersisted is a forward-looking AST
// gate: every function in this package that broadcasts an
// `AGENT_MESSAGE` WebSocket event MUST also call
// `INSERT INTO activity_logs` somewhere in its body.
//
// The reno-stars production data-loss bug (CEO Ryan PC's long-form
// onboarding-friction message visible live but missing on reload)
// happened because mcp_tools.go:toolSendMessageToUser broadcast WS
// without a paired INSERT — while the HTTP /notify sibling DID
// persist. The fix added the INSERT; this gate prevents the regression
// class from re-emerging in any future chat-bearing tool.
//
// Why an AST gate vs a code-review checklist (per memory
// feedback_behavior_based_ast_gates.md): "pin invariants by what a
// function calls, not what it's named". The shape that loses data is:
//
// BroadcastOnly(_, "AGENT_MESSAGE", _) without an INSERT companion
//
// Any new tool that emits AGENT_MESSAGE must persist or the next
// canvas refresh drops the message — same shape as reno-stars. A
// reviewer can miss this; the AST walk can't.
//
// Allowlist: empty by intent. If a future use case genuinely needs
// fire-and-forget broadcast (e.g., transient typing indicators that
// should NOT survive reload), add an entry here AND document why.
// "Doesn't need to persist" is rarely the right answer for chat —
// the canvas history is the source of truth.
func TestAgentMessageBroadcastsArePersisted(t *testing.T) {
wd, err := os.Getwd()
if err != nil {
t.Fatalf("getwd: %v", err)
}
entries, err := os.ReadDir(wd)
if err != nil {
t.Fatalf("readdir %s: %v", wd, err)
}
type violation struct {
file string
fn string
}
var violations []violation
for _, ent := range entries {
name := ent.Name()
if ent.IsDir() || !strings.HasSuffix(name, ".go") || strings.HasSuffix(name, "_test.go") {
continue
}
path := filepath.Join(wd, name)
fset := token.NewFileSet()
file, err := parser.ParseFile(fset, path, nil, parser.ParseComments)
if err != nil {
t.Fatalf("parse %s: %v", path, err)
}
for _, decl := range file.Decls {
fn, ok := decl.(*ast.FuncDecl)
if !ok || fn.Body == nil {
continue
}
if !funcEmitsAgentMessageBroadcast(fn) {
continue
}
if !funcInsertsIntoActivityLogs(fn) {
violations = append(violations, violation{file: name, fn: fn.Name.Name})
}
}
}
if len(violations) > 0 {
sort.Slice(violations, func(i, j int) bool {
if violations[i].file != violations[j].file {
return violations[i].file < violations[j].file
}
return violations[i].fn < violations[j].fn
})
var buf strings.Builder
for _, v := range violations {
buf.WriteString(" - ")
buf.WriteString(v.file)
buf.WriteString(":")
buf.WriteString(v.fn)
buf.WriteString("\n")
}
t.Errorf(`function(s) broadcast `+"`AGENT_MESSAGE`"+` without persisting to activity_logs:
%s
This is the reno-stars data-loss regression class: live message
visible to the user, but missing on reload because activity_log was
never written. Every chat-bearing broadcast MUST be paired with:
INSERT INTO activity_logs (workspace_id, activity_type, method,
summary, response_body, status)
VALUES ($1, 'a2a_receive', 'notify', $2, $3::jsonb, 'ok')
See activity.go:Notify and mcp_tools.go:toolSendMessageToUser for
the canonical shapes. Don't add an allowlist entry without a
documented reason — the canvas chat history is the source of truth
and silently dropping messages is a P0 user trust break.`,
buf.String())
}
}
// funcEmitsAgentMessageBroadcast walks fn.Body for any CallExpr that
// looks like `*.BroadcastOnly(_, "AGENT_MESSAGE", _)`.
func funcEmitsAgentMessageBroadcast(fn *ast.FuncDecl) bool {
var found bool
ast.Inspect(fn.Body, func(n ast.Node) bool {
call, ok := n.(*ast.CallExpr)
if !ok {
return true
}
sel, ok := call.Fun.(*ast.SelectorExpr)
if !ok || sel.Sel.Name != "BroadcastOnly" {
return true
}
// BroadcastOnly(workspaceID, eventType, payload) — the second
// arg is the event name. Match by string-literal value.
if len(call.Args) < 2 {
return true
}
lit, ok := call.Args[1].(*ast.BasicLit)
if !ok || lit.Kind != token.STRING {
return true
}
raw := lit.Value
if unq, err := strconv.Unquote(raw); err == nil {
raw = unq
}
if raw == "AGENT_MESSAGE" {
found = true
return false
}
return true
})
return found
}
// funcInsertsIntoActivityLogs walks fn.Body for any STRING BasicLit
// whose body contains `INSERT INTO activity_logs` (the SQL literal
// passed to ExecContext). Matches the substring rather than a strict
// regex because we don't care about the exact INSERT shape here —
// only that the function persists. Specific shape pinning lives in
// the per-handler test (see TestMCPHandler_SendMessageToUser_*).
func funcInsertsIntoActivityLogs(fn *ast.FuncDecl) bool {
var found bool
ast.Inspect(fn.Body, func(n ast.Node) bool {
lit, ok := n.(*ast.BasicLit)
if !ok || lit.Kind != token.STRING {
return true
}
raw := lit.Value
if unq, err := strconv.Unquote(raw); err == nil {
raw = unq
}
if strings.Contains(raw, "INSERT INTO activity_logs") {
found = true
return false
}
return true
})
return found
}
@@ -0,0 +1,173 @@
package handlers
// AgentMessageWriter is the SSOT for "agent → user" message delivery in the
// workspace-server. Every chat-bearing path that surfaces a message to the
// canvas — HTTP /notify (Notify handler), MCP tools/call
// send_message_to_user (toolSendMessageToUser), any future channel — MUST
// route through this writer rather than re-implement the broadcast +
// persist contract inline.
//
// Why: pre-consolidation, two handlers duplicated the same "broadcast then
// INSERT activity_logs" sequence. The reno-stars production data-loss
// incident (2026-05-05, RFC #2945, PR #2944) was the symptom — the
// persistence half landed for /notify but lagged for the MCP bridge by
// months, silently dropping every long-form external-agent message until
// reload. The AST gate from #2944 catches drift; this writer eliminates
// the *possibility* of drift by giving both call sites a single
// well-tested function to call.
//
// Contract:
// 1. Look up the workspace by id; ErrWorkspaceNotFound on miss so the
// caller can return 404 with a clean message.
// 2. Broadcast a WS AGENT_MESSAGE event with {message, workspace_id,
// name, attachments?}.
// 3. INSERT a row into activity_logs:
// type='a2a_receive', method='notify', source_id NULL,
// response_body={"result": message[, "parts": [file kind...]]},
// status='ok'
// Best-effort — INSERT failure logs only, returns nil so the broadcast
// success isn't undone on the caller side.
// 4. Returns nil on success.
//
// The shape (especially the JSON response_body) is the wire contract the
// canvas's chat-history hydrator (canvas/src/.../historyHydration.ts)
// reads. Drift here silently breaks chat replay across all consumers, so
// changes to the JSON shape MUST be cross-verified against the hydrator
// in the same PR.
import (
"context"
"database/sql"
"encoding/json"
"errors"
"fmt"
"log"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/textutil"
)
// ErrWorkspaceNotFound is returned by AgentMessageWriter.Send when the
// workspace lookup turns up nothing (or the workspace is in
// status='removed'). Callers translate to HTTP 404 / JSON-RPC error /
// whatever surface they expose. Real DB errors (connection drop, query
// timeout) surface as wrapped errors and should be treated as 503.
var ErrWorkspaceNotFound = errors.New("agent_message: workspace not found")
// AgentMessageAttachment is one file attached to an agent → user
// message. Identical to handlers.NotifyAttachment in field set; kept
// distinct so the writer's API doesn't import a handler type with HTTP
// binding tags.
type AgentMessageAttachment struct {
URI string
Name string
MimeType string
Size int64
}
// AgentMessageWriter persists + broadcasts agent → user messages. Construct
// once per process via NewAgentMessageWriter; pass the same instance to
// every handler that delivers chat (Notify, toolSendMessageToUser, etc.).
//
// Takes events.EventEmitter (not the *Broadcaster concrete type) so tests
// can substitute a fake emitter and producers in other packages can wrap
// the real broadcaster behind their own metrics / retries without leaking
// the concrete dependency.
type AgentMessageWriter struct {
db *sql.DB
broadcaster events.EventEmitter
}
// NewAgentMessageWriter binds the writer to the platform's DB pool +
// WebSocket broadcaster.
func NewAgentMessageWriter(db *sql.DB, broadcaster events.EventEmitter) *AgentMessageWriter {
return &AgentMessageWriter{db: db, broadcaster: broadcaster}
}
// Send delivers a single agent → user message. Look up + broadcast +
// persist in that order; ErrWorkspaceNotFound short-circuits before any
// broadcast or DB write so callers can 404 cleanly.
//
// Returns nil on success — including on DB-INSERT failure (the broadcast
// already returned successfully and the user has seen the message; the
// persistence-failure mode is logged at WARN but the caller's response
// stays 200 so the agent doesn't retry and double-broadcast).
func (w *AgentMessageWriter) Send(
ctx context.Context,
workspaceID, message string,
attachments []AgentMessageAttachment,
) error {
// 1. Workspace lookup. status='removed' filter is the same shape /notify
// used pre-consolidation; deleted workspaces don't get notifications.
//
// Distinguish sql.ErrNoRows ("workspace genuinely not present" — caller
// should 404) from real DB errors (connection drop, statement timeout,
// pool exhaustion — caller should 503). Pre-fix this branch returned
// ErrWorkspaceNotFound for any error, so during a DB outage every
// notify call surfaced as "workspace not found" and masked real
// incidents in the alert path.
var wsName string
err := w.db.QueryRowContext(ctx,
`SELECT name FROM workspaces WHERE id = $1 AND status != 'removed'`,
workspaceID,
).Scan(&wsName)
if errors.Is(err, sql.ErrNoRows) {
return ErrWorkspaceNotFound
}
if err != nil {
return fmt.Errorf("agent_message: workspace lookup: %w", err)
}
// 2. Build broadcast payload + WS-emit. Same shape that ChatTab's
// AGENT_MESSAGE handler in canvas/src/store/canvas-events.ts has
// consumed since the canvas chat shipped — drift here would orphan
// every live chat panel.
broadcastPayload := map[string]interface{}{
"message": message,
"workspace_id": workspaceID,
"name": wsName,
}
if len(attachments) > 0 {
broadcastPayload["attachments"] = attachments
}
w.broadcaster.BroadcastOnly(workspaceID, string(events.EventAgentMessage), broadcastPayload)
// 3. Persist for chat-history hydration. response_body shape MUST stay
// in sync with extractResponseText + extractFilesFromTask in
// canvas/src/components/tabs/chat/historyHydration.ts:
// - extractResponseText reads body.result (string) → renders text
// - extractFilesFromTask reads body.parts[] (kind=file) → renders chips
respPayload := map[string]interface{}{"result": message}
if len(attachments) > 0 {
fileParts := make([]map[string]interface{}, 0, len(attachments))
for _, a := range attachments {
fileMeta := map[string]interface{}{"uri": a.URI, "name": a.Name}
if a.MimeType != "" {
fileMeta["mimeType"] = a.MimeType
}
if a.Size > 0 {
fileMeta["size"] = a.Size
}
fileParts = append(fileParts, map[string]interface{}{
"kind": "file",
"file": fileMeta,
})
}
respPayload["parts"] = fileParts
}
respJSON, _ := json.Marshal(respPayload)
preview := textutil.TruncateRunes(message, 80)
if _, err := w.db.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, method, summary, response_body, status)
VALUES ($1, 'a2a_receive', 'notify', $2, $3::jsonb, 'ok')
`, workspaceID, "Agent message: "+preview, string(respJSON)); err != nil {
// Best-effort: the broadcast already returned ok and the user
// has seen the message. Logging a structured line lets operators
// notice persistence-failure rates spike if the DB is unhealthy,
// without breaking the tool response or causing the agent to
// retry-and-double-broadcast.
log.Printf("agent_message: failed to persist for %s: %v", workspaceID, err)
}
return nil
}
@@ -0,0 +1,414 @@
package handlers
import (
"context"
"database/sql/driver"
"encoding/json"
"errors"
"strings"
"testing"
"unicode/utf8"
"github.com/DATA-DOG/go-sqlmock"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
)
// AgentMessageWriter is the SSOT for agent → user chat delivery
// (RFC #2945 PR-A). These tests pin the contract the writer
// guarantees: workspace lookup, broadcast, INSERT, error semantics —
// every shape that producers (Notify, toolSendMessageToUser, future
// channels) rely on.
//
// Pre-consolidation, the broadcast-then-INSERT logic was duplicated
// across two handlers and they drifted (reno-stars, 2026-05-05). With
// the writer being the only place this logic lives, these tests are
// the regression line for every chat-bearing path simultaneously.
// jsonMatcher is a sqlmock Argument matcher that decodes the actual
// SQL arg as JSON and runs a caller-supplied predicate over the
// resulting structure. Tighter than substring matching (which can
// false-pass on a renamed key) and tolerant of map-key ordering
// (which exact-string matching is not).
type jsonMatcher struct {
predicate func(parsed map[string]any) bool
desc string
}
func (m jsonMatcher) Match(v driver.Value) bool {
s, ok := v.(string)
if !ok {
return false
}
var parsed map[string]any
if err := json.Unmarshal([]byte(s), &parsed); err != nil {
return false
}
return m.predicate(parsed)
}
// stringMatcher pins exact prefix/suffix/equality checks against a
// driver.Value that's actually a string.
type stringMatcher func(string) bool
func (f stringMatcher) Match(v driver.Value) bool {
s, ok := v.(string)
if !ok {
return false
}
return f(s)
}
// capturingEmitter records every BroadcastOnly call so tests can pin
// the WS event shape without a real ws.Hub. RecordAndBroadcast is
// also captured for completeness — the writer doesn't call it today,
// but a future producer might, and a captured-but-unasserted record
// is easier to diagnose than a nil panic.
type capturingEmitter struct {
events []capturedEvent
}
type capturedEvent struct {
workspaceID string
eventType string
payload interface{}
}
func (c *capturingEmitter) BroadcastOnly(workspaceID string, eventType string, payload interface{}) {
c.events = append(c.events, capturedEvent{workspaceID, eventType, payload})
}
func (c *capturingEmitter) RecordAndBroadcast(_ context.Context, eventType string, workspaceID string, payload interface{}) error {
c.events = append(c.events, capturedEvent{workspaceID, eventType, payload})
return nil
}
// TestAgentMessageWriter_Send_Success_NoAttachments pins the happy
// path: workspace lookup, broadcast, INSERT, return nil.
func TestAgentMessageWriter_Send_Success_NoAttachments(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
"ws-1",
sqlmock.AnyArg(), // summary
`{"result":"hi"}`,
).
WillReturnResult(sqlmock.NewResult(1, 1))
if err := w.Send(context.Background(), "ws-1", "hi", nil); err != nil {
t.Fatalf("Send returned %v, want nil", err)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("DB expectations: %v", err)
}
}
// TestAgentMessageWriter_Send_Success_WithAttachments pins the file
// attachment shape — response_body MUST contain a parts[] array with
// kind=file entries so the canvas hydrater renders download chips.
// Drift here = chips disappear on chat reload.
func TestAgentMessageWriter_Send_Success_WithAttachments(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-att").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Ryan"))
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
"ws-att",
sqlmock.AnyArg(),
jsonMatcher{
desc: "response_body has result + parts with kind=file metadata",
predicate: func(p map[string]any) bool {
if p["result"] != "see attached" {
return false
}
parts, ok := p["parts"].([]any)
if !ok || len(parts) != 1 {
return false
}
part, ok := parts[0].(map[string]any)
if !ok {
return false
}
if part["kind"] != "file" {
return false
}
file, ok := part["file"].(map[string]any)
if !ok {
return false
}
return file["uri"] == "workspace://x.zip" &&
file["name"] == "x.zip" &&
file["mimeType"] == "application/zip" &&
file["size"].(float64) == 1234
},
},
).
WillReturnResult(sqlmock.NewResult(1, 1))
atts := []AgentMessageAttachment{
{URI: "workspace://x.zip", Name: "x.zip", MimeType: "application/zip", Size: 1234},
}
if err := w.Send(context.Background(), "ws-att", "see attached", atts); err != nil {
t.Fatalf("Send returned %v, want nil", err)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("DB expectations: %v", err)
}
}
// TestAgentMessageWriter_Send_WorkspaceNotFound pins ErrWorkspaceNotFound
// short-circuit. Must NOT broadcast, MUST NOT INSERT — caller will 404
// or surface a JSON-RPC error.
func TestAgentMessageWriter_Send_WorkspaceNotFound(t *testing.T) {
mock := setupTestDB(t)
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-missing").
WillReturnRows(sqlmock.NewRows([]string{"name"}))
err := w.Send(context.Background(), "ws-missing", "lost in the void", nil)
if !errors.Is(err, ErrWorkspaceNotFound) {
t.Errorf("Send returned %v, want ErrWorkspaceNotFound", err)
}
if len(emitter.events) != 0 {
t.Errorf("workspace-not-found path MUST NOT broadcast, got %d events", len(emitter.events))
}
// Implicit: no INSERT expectation registered, so a stray INSERT
// would fail ExpectationsWereMet.
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("DB expectations (INSERT must NOT fire on workspace-not-found): %v", err)
}
}
// TestAgentMessageWriter_Send_DBInsertFailureStillReturnsNil pins the
// "best-effort persistence" contract: when the activity_log INSERT
// fails (DB hiccup, transient connection, constraint), the writer
// MUST still return nil. The broadcast already succeeded; the user
// has seen the message; returning an error here would cause the
// caller (and the agent calling the tool) to retry and double-
// broadcast.
func TestAgentMessageWriter_Send_DBInsertFailureStillReturnsNil(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-dbfail").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnError(errors.New("transient db error"))
err := w.Send(context.Background(), "ws-dbfail", "should not be lost from live chat", nil)
if err != nil {
t.Errorf("DB INSERT failure must return nil (broadcast already succeeded), got %v", err)
}
}
// TestAgentMessageWriter_Send_PreviewTruncation pins the summary
// preview cap. Long messages (Ryan's onboarding-friction report was
// ~2k chars) must summarise to ≤80 chars + ellipsis so the activity
// table doesn't carry multi-KB summaries that bloat list queries.
func TestAgentMessageWriter_Send_PreviewTruncation(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-trunc").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Ryan"))
longMsg := strings.Repeat("x", 200)
mock.ExpectExec(`INSERT INTO activity_logs`).
WithArgs(
"ws-trunc",
stringMatcher(func(s string) bool {
if !strings.HasPrefix(s, "Agent message: ") {
return false
}
preview := strings.TrimPrefix(s, "Agent message: ")
if !strings.HasSuffix(preview, "…") {
return false
}
body := strings.TrimSuffix(preview, "…")
return len(body) == 80
}),
sqlmock.AnyArg(),
).
WillReturnResult(sqlmock.NewResult(1, 1))
if err := w.Send(context.Background(), "ws-trunc", longMsg, nil); err != nil {
t.Fatalf("Send: %v", err)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("preview truncation drift: %v", err)
}
}
// TestAgentMessageWriter_Send_BroadcastsAgentMessageEvent pins the
// WS event name + payload shape. The canvas's
// canvas-events.ts:AGENT_MESSAGE handler reads {message, workspace_id,
// name, attachments?} — drift here orphans every live chat panel.
func TestAgentMessageWriter_Send_BroadcastsAgentMessageEvent(t *testing.T) {
mock := setupTestDB(t)
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-bc").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Workspace Name"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
atts := []AgentMessageAttachment{
{URI: "workspace://a.txt", Name: "a.txt"},
}
if err := w.Send(context.Background(), "ws-bc", "hi", atts); err != nil {
t.Fatalf("Send: %v", err)
}
if len(emitter.events) != 1 {
t.Fatalf("expected exactly 1 broadcast, got %d", len(emitter.events))
}
ev := emitter.events[0]
if ev.eventType != "AGENT_MESSAGE" {
t.Errorf("event type = %q, want AGENT_MESSAGE", ev.eventType)
}
if ev.workspaceID != "ws-bc" {
t.Errorf("workspace_id = %q, want ws-bc", ev.workspaceID)
}
pl, ok := ev.payload.(map[string]interface{})
if !ok {
t.Fatalf("payload not a map: %T", ev.payload)
}
if pl["message"] != "hi" {
t.Errorf("payload.message = %v, want hi", pl["message"])
}
if pl["workspace_id"] != "ws-bc" {
t.Errorf("payload.workspace_id = %v, want ws-bc", pl["workspace_id"])
}
if pl["name"] != "Workspace Name" {
t.Errorf("payload.name = %v, want Workspace Name", pl["name"])
}
if pl["attachments"] == nil {
t.Error("payload.attachments missing on attachment-bearing send")
}
}
// TestAgentMessageWriter_Send_DBErrorOnLookupReturnsWrapped pins the
// distinction between sql.ErrNoRows (legit not-found → 404) and real
// DB errors (connection drop → 503). Pre-followup the lookup branch
// returned ErrWorkspaceNotFound for ANY error, so during a DB outage
// every notify call surfaced as "workspace not found" and masked
// real incidents in alerting.
func TestAgentMessageWriter_Send_DBErrorOnLookupReturnsWrapped(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
transientErr := errors.New("connection refused")
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-dbdown").
WillReturnError(transientErr)
err := w.Send(context.Background(), "ws-dbdown", "hi", nil)
if err == nil {
t.Fatal("expected wrapped DB error, got nil")
}
if errors.Is(err, ErrWorkspaceNotFound) {
t.Errorf("DB outage MUST NOT surface as ErrWorkspaceNotFound (masks incidents in alerting); got %v", err)
}
if !errors.Is(err, transientErr) {
t.Errorf("expected wrapped %v, got %v", transientErr, err)
}
}
// Helper-level truncate tests now live in
// internal/textutil/truncate_test.go (TestTruncateRunes). The
// integration-level coverage that exercises the agent_message_writer
// path with non-ASCII content is TestAgentMessageWriter_Send_NonASCIIMessagePersists
// below.
// TestAgentMessageWriter_Send_NonASCIIMessagePersists pins the end-to-end
// path for non-ASCII messages — the original reno-stars regression
// surfaced via byte-slice truncation breaking JSONB INSERT. Every
// handler-level test had ASCII content, so this branch had no
// coverage. Now it does.
func TestAgentMessageWriter_Send_NonASCIIMessagePersists(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
// 200-rune CJK message — exceeds the 80-rune cap, would have hit
// the byte-slice bug.
msg := strings.Repeat("你", 200)
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-cjk").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WithArgs(
"ws-cjk",
stringMatcher(func(s string) bool {
if !strings.HasPrefix(s, "Agent message: ") {
return false
}
preview := strings.TrimPrefix(s, "Agent message: ")
if !strings.HasSuffix(preview, "…") {
return false
}
body := strings.TrimSuffix(preview, "…")
// 80 runes of 你 = 80 codepoints. Each is 3 bytes UTF-8.
if utf8.RuneCountInString(body) != 80 {
return false
}
// MUST be valid UTF-8 — pre-fix byte-slice would have
// returned half a codepoint here.
return utf8.ValidString(body)
}),
sqlmock.AnyArg(),
).
WillReturnResult(sqlmock.NewResult(1, 1))
if err := w.Send(context.Background(), "ws-cjk", msg, nil); err != nil {
t.Fatalf("Send: %v", err)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("non-ASCII path drift: %v", err)
}
}
// TestAgentMessageWriter_Send_OmitsAttachmentsKeyWhenEmpty pins the
// "no key when nil" wire contract — extra empty fields would force
// canvas consumers to defensively check for [] vs undefined; the
// existing AGENT_MESSAGE handler treats absence as "no attachments".
func TestAgentMessageWriter_Send_OmitsAttachmentsKeyWhenEmpty(t *testing.T) {
mock := setupTestDB(t)
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-noatt").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("X"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
if err := w.Send(context.Background(), "ws-noatt", "plain text", nil); err != nil {
t.Fatalf("Send: %v", err)
}
if len(emitter.events) != 1 {
t.Fatalf("expected 1 event, got %d", len(emitter.events))
}
pl := emitter.events[0].payload.(map[string]interface{})
if _, present := pl["attachments"]; present {
t.Errorf("attachments key MUST NOT be present when empty (canvas treats absence as 'none'); payload=%v", pl)
}
}
@@ -51,7 +51,7 @@ func (h *ApprovalsHandler) Create(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(ctx, "APPROVAL_REQUESTED", workspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventApprovalRequested), workspaceID, map[string]interface{}{
"approval_id": approvalID,
"action": body.Action,
"reason": body.Reason,
@@ -62,7 +62,7 @@ func (h *ApprovalsHandler) Create(c *gin.Context) {
var parentID *string
db.DB.QueryRowContext(ctx, `SELECT parent_id FROM workspaces WHERE id = $1`, workspaceID).Scan(&parentID)
if parentID != nil {
h.broadcaster.RecordAndBroadcast(ctx, "APPROVAL_ESCALATED", *parentID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventApprovalEscalated), *parentID, map[string]interface{}{
"approval_id": approvalID,
"from_workspace_id": workspaceID,
"action": body.Action,
@@ -656,8 +656,28 @@ func (h *ChatFilesHandler) uploadPollMode(c *gin.Context, ctx context.Context, w
})
}
// Phase 2: atomic batch insert. On failure no rows commit.
fileIDs, err := h.pendingUploads.PutBatch(ctx, wsUUID, items)
// Phase 2+3: PutBatch + N activity-row inserts run in ONE Tx so
// either every pending_uploads row + every activity_logs row commits,
// or none do. Per-file pre-validation already happened above so the
// only failure modes inside the Tx are DB-side; either way Rollback
// leaves the table state unchanged and the client retries the whole
// multipart upload cleanly. Broadcasts are deferred until after
// Commit — emitting an ACTIVITY_LOGGED event for a row that ends up
// rolled back would leak a ghost message into the canvas's
// optimistic UI.
tx, err := db.DB.BeginTx(ctx, nil)
if err != nil {
log.Printf("chat_files uploadPollMode: begin tx for %s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "could not stage files"})
return
}
// Defer-rollback is safe even after a successful Commit — the second
// Rollback is a no-op (database/sql tracks tx state).
defer func() {
_ = tx.Rollback()
}()
fileIDs, err := h.pendingUploads.PutBatchTx(ctx, tx, wsUUID, items)
if err != nil {
if errors.Is(err, pendinguploads.ErrTooLarge) {
// Belt + suspenders: pre-validation above already caught
@@ -669,28 +689,20 @@ func (h *ChatFilesHandler) uploadPollMode(c *gin.Context, ctx context.Context, w
})
return
}
log.Printf("chat_files uploadPollMode: storage.PutBatch failed for %s: %v",
log.Printf("chat_files uploadPollMode: storage.PutBatchTx failed for %s: %v",
workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "could not stage files"})
return
}
// Phase 3: write per-file activity rows and build the response. Activity
// rows are written individually (not part of the same Tx as PutBatch)
// because LogActivity is shared across many handlers and threading the
// Tx through would be a bigger refactor. The trade-off: if an activity
// write fails after the PutBatch commits, the pending_uploads rows
// orphan until the 24h TTL — significantly better than the previous
// "every multi-file upload could orphan" behavior, and the workspace's
// fetcher handles soft-404 cleanly when activity rows reference a row
// the platform later expired.
out := make([]uploadedFile, 0, len(prepReady))
broadcasts := make([]func(), 0, len(prepReady))
for i, p := range prepReady {
fileID := fileIDs[i]
uri := fmt.Sprintf("platform-pending:%s/%s", workspaceID, fileID)
summary := "chat_upload_receive: " + p.Sanitized
method := "chat_upload_receive"
LogActivity(ctx, h.broadcaster, ActivityParams{
hook, err := LogActivityTx(ctx, tx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
ActivityType: "a2a_receive",
TargetID: &workspaceID,
@@ -705,10 +717,13 @@ func (h *ChatFilesHandler) uploadPollMode(c *gin.Context, ctx context.Context, w
},
Status: "ok",
})
log.Printf("chat_files uploadPollMode: staged %s/%s (file_id=%s size=%d mimetype=%q)",
workspaceID, p.Sanitized, fileID, len(p.Content), p.Mimetype)
if err != nil {
log.Printf("chat_files uploadPollMode: activity insert failed for %s/%s: %v",
workspaceID, p.Sanitized, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "could not log upload activity"})
return
}
broadcasts = append(broadcasts, hook)
out = append(out, uploadedFile{
URI: uri,
Name: p.Sanitized,
@@ -717,6 +732,24 @@ func (h *ChatFilesHandler) uploadPollMode(c *gin.Context, ctx context.Context, w
})
}
if err := tx.Commit(); err != nil {
log.Printf("chat_files uploadPollMode: commit failed for %s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "could not stage files"})
return
}
// Post-commit: fire deferred broadcasts and emit the staged log
// lines now that the rows are durable. Broadcasts are pure in-memory
// (no I/O); panicking here would NOT leak a row but would leak a
// log line, so the order doesn't matter for correctness.
for _, b := range broadcasts {
b()
}
for i, p := range prepReady {
log.Printf("chat_files uploadPollMode: staged %s/%s (file_id=%s size=%d mimetype=%q)",
workspaceID, p.Sanitized, fileIDs[i], len(p.Content), p.Mimetype)
}
c.JSON(http.StatusOK, gin.H{"files": out})
}
@@ -107,6 +107,16 @@ func (s *inMemStorage) PutBatch(_ context.Context, ws uuid.UUID, items []pending
return ids, nil
}
// PutBatchTx mirrors PutBatch for the Tx-aware caller path. The tx
// argument is not consulted — production atomicity (PutBatch INSERTs +
// activity_logs INSERTs in the same Tx) is verified by the dedicated
// integration test against real Postgres. This in-mem fake records the
// puts immediately; tests that exercise the rollback path use
// putErr/sqlmock to simulate the failure.
func (s *inMemStorage) PutBatchTx(ctx context.Context, _ *sql.Tx, ws uuid.UUID, items []pendinguploads.PutItem) ([]uuid.UUID, error) {
return s.PutBatch(ctx, ws, items)
}
func (s *inMemStorage) Get(context.Context, uuid.UUID) (pendinguploads.Record, error) {
return pendinguploads.Record{}, pendinguploads.ErrNotFound
}
@@ -138,11 +148,37 @@ func expectPollDeliveryModeMissing(mock sqlmock.Sqlmock, workspaceID string) {
// expectActivityInsert stubs the LogActivity INSERT so the poll branch's
// per-file activity row write doesn't fail the sqlmock expectations.
// In the post-#149 path this INSERT runs inside the BeginTx that wraps
// PutBatchTx + N activity rows — pair it with expectUploadPollTxBegin
// + expectUploadPollTxCommit (or Rollback) when the test exercises
// uploadPollMode.
func expectActivityInsert(mock sqlmock.Sqlmock) {
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
}
// expectUploadPollTxBegin marks the start of the BeginTx that
// uploadPollMode opens around PutBatchTx + per-file LogActivityTx.
// inMemStorage doesn't drive sqlmock for the pending_uploads INSERTs
// (it's a process-local fake), so the only Tx-scoped DB calls
// sqlmock sees are the activity_logs INSERTs.
func expectUploadPollTxBegin(mock sqlmock.Sqlmock) {
mock.ExpectBegin()
}
// expectUploadPollTxCommit pairs with expectUploadPollTxBegin on the
// happy path — every activity row inserted, Tx committed.
func expectUploadPollTxCommit(mock sqlmock.Sqlmock) {
mock.ExpectCommit()
}
// expectUploadPollTxRollback pairs with expectUploadPollTxBegin on a
// failure path — PutBatchTx error, activity insert error, or any other
// abort that triggers the deferred tx.Rollback() in uploadPollMode.
func expectUploadPollTxRollback(mock sqlmock.Sqlmock) {
mock.ExpectRollback()
}
// expectActivityInsertWithTypeAndMethod is a strict variant that pins
// the activity_type and method positional args. Used in the discriminator
// regression test below — the workspace inbox poller filters
@@ -198,7 +234,9 @@ func TestPollUpload_HappyPath_OneFile_StagesAndLogs(t *testing.T) {
wsID := "11111111-2222-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectActivityInsert(mock)
expectUploadPollTxCommit(mock)
store := newInMemStorage()
h := NewChatFilesHandler(NewTemplatesHandler(t.TempDir(), nil, nil)).
@@ -254,9 +292,11 @@ func TestPollUpload_MultipleFiles_AllStagedAndLogged(t *testing.T) {
wsID := "11111111-aaaa-bbbb-cccc-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectActivityInsert(mock)
expectActivityInsert(mock)
expectActivityInsert(mock)
expectUploadPollTxCommit(mock)
store := newInMemStorage()
h := NewChatFilesHandler(NewTemplatesHandler(t.TempDir(), nil, nil)).
@@ -425,6 +465,8 @@ func TestPollUpload_StorageError_500(t *testing.T) {
wsID := "88888888-2222-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectUploadPollTxRollback(mock)
store := newInMemStorage()
store.putErr = errors.New("disk full")
@@ -446,6 +488,8 @@ func TestPollUpload_StorageTooLarge_413(t *testing.T) {
wsID := "99999999-2222-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectUploadPollTxRollback(mock)
store := newInMemStorage()
store.putErr = pendinguploads.ErrTooLarge
@@ -569,7 +613,9 @@ func TestPollUpload_SanitizesFilenameInResponse(t *testing.T) {
wsID := "bbbbbbbb-2222-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectActivityInsert(mock)
expectUploadPollTxCommit(mock)
store := newInMemStorage()
h := NewChatFilesHandler(NewTemplatesHandler(t.TempDir(), nil, nil)).
@@ -650,6 +696,8 @@ func TestPollUpload_AtomicRollbackOnPutBatchError(t *testing.T) {
wsID := "bbbbbbbb-3333-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectUploadPollTxRollback(mock)
store := newInMemStorage()
store.putErr = errors.New("db down mid-batch")
@@ -672,6 +720,58 @@ func TestPollUpload_AtomicRollbackOnPutBatchError(t *testing.T) {
}
}
// TestPollUpload_AtomicRollbackOnActivityInsertFailure pins the #149
// guarantee: if an activity_logs INSERT fails mid-loop (after some
// rows have already been INSERTed in the same Tx), uploadPollMode
// MUST Rollback so neither the pending_uploads nor the activity rows
// commit. Pre-#149 the activity rows were written one-by-one outside
// any Tx; a mid-loop failure left orphan pending_uploads rows the
// 24h TTL would later sweep, but the user never saw the file in the
// canvas. Post-#149 the contract is all-or-nothing.
//
// What this pins: the second activity insert errors → Tx rolls back
// → response is 500 → no Commit. Pin via the sqlmock rollback
// expectation; the inMemStorage will report puts=N (it doesn't model
// Tx state), but at the SQL layer no rows committed.
func TestPollUpload_AtomicRollbackOnActivityInsertFailure(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
wsID := "cccccccc-3333-3333-4444-555555555555"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
// File 1 inserts cleanly. File 2's INSERT fails. uploadPollMode
// must NOT call Commit and the deferred tx.Rollback() runs.
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnError(errors.New("constraint violation simulated"))
expectUploadPollTxRollback(mock)
store := newInMemStorage()
h := NewChatFilesHandler(NewTemplatesHandler(t.TempDir(), nil, nil)).
WithPendingUploads(store, nil)
body, ct := pollUploadFixture(t, map[string][]byte{
"a.txt": []byte("aaa"),
"b.txt": []byte("bbb"),
"c.txt": []byte("ccc"),
})
c, w := makeUploadRequest(t, wsID, body, ct)
h.Upload(c)
if w.Code != http.StatusInternalServerError {
t.Fatalf("status=%d body=%s, want 500 on activity-insert mid-loop failure",
w.Code, w.Body.String())
}
if err := mock.ExpectationsWereMet(); err != nil {
// This is the load-bearing assertion: ExpectationsWereMet only
// passes if Rollback was called and Commit was NOT — the SQL-
// level proof of the all-or-nothing contract.
t.Errorf("Tx must rollback (and NOT commit) on activity-insert failure: %v", err)
}
}
// TestPollUpload_MimetypeWithCRLFInjectionStripped pins the safeMimetype
// hardening: a multipart-supplied Content-Type header with CR/LF is
// rewritten to application/octet-stream so the eventual /content
@@ -731,7 +831,9 @@ func TestPollUpload_ActivityRowDiscriminator(t *testing.T) {
wsID := "abc12345-6789-4abc-8def-000000000999"
expectPollDeliveryMode(mock, wsID, "poll")
expectUploadPollTxBegin(mock)
expectActivityInsertWithTypeAndMethod(mock, wsID, "a2a_receive", "chat_upload_receive")
expectUploadPollTxCommit(mock)
store := newInMemStorage()
h := NewChatFilesHandler(NewTemplatesHandler(t.TempDir(), nil, nil)).
@@ -0,0 +1,113 @@
package handlers
// chat_history.go — HTTP-shape adapter over messagestore.MessageStore
// (RFC #2945 PR-D).
//
// Pre-PR-D, this file owned the activity_logs query AND the parser
// AND the HTTP plumbing. PR-D extracts the storage + parser into
// internal/messagestore/ so OSS operators can plug in alternative
// backends (S3-tiered, vector store, in-memory). The handler is now
// a thin adapter: parse query params → call store → emit JSON.
//
// Endpoint: GET /workspaces/:id/chat-history?limit=N&before_ts=T
// Auth: same wsAuth chain as /workspaces/:id/activity (tenant
// ADMIN_TOKEN + X-Molecule-Org-Id header). No new trust boundary.
//
// Behavioral parity with canvas TS is enforced at the messagestore
// layer (internal/messagestore/postgres_store_test.go); this file's
// tests cover the HTTP-shape concerns only.
import (
"net/http"
"strconv"
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/messagestore"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
// ChatHistoryResponse is the wire shape for GET /chat-history.
type ChatHistoryResponse struct {
Messages []messagestore.ChatMessage `json:"messages"`
ReachedEnd bool `json:"reached_end"`
}
// ChatHistoryHandler exposes the typed chat-history endpoint over a
// MessageStore. The store is injected so OSS operators can swap the
// backend without forking the handler.
type ChatHistoryHandler struct {
store messagestore.MessageStore
}
// NewChatHistoryHandler wires a MessageStore (typically
// messagestore.NewPostgresMessageStore at production startup).
//
// Tests inject fakes (see internal/handlers/chat_history_test.go).
// Constructor takes the interface, not a concrete type, so the
// platform-default vs OSS-alternative decision happens at wiring
// time in router.go.
func NewChatHistoryHandler(store messagestore.MessageStore) *ChatHistoryHandler {
return &ChatHistoryHandler{store: store}
}
// List handles GET /workspaces/:id/chat-history?limit=N&before_ts=T.
//
// Query parameters mirror /activity for caller convenience:
//
// - limit (default 100, max 1000) — page size
// - before_ts (RFC3339, optional) — cursor for paginating backward
//
// Validates inputs at the trust boundary; the store sees only
// well-formed ListOptions.
func (h *ChatHistoryHandler) List(c *gin.Context) {
workspaceID := c.Param("id")
if _, err := uuid.Parse(workspaceID); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "workspace id must be a UUID"})
return
}
limit := 100
if v := c.Query("limit"); v != "" {
if n, err := strconv.Atoi(v); err == nil && n > 0 {
limit = n
}
}
if limit > 1000 {
limit = 1000
}
opts := messagestore.ListOptions{Limit: limit}
if v := c.Query("before_ts"); v != "" {
t, err := time.Parse(time.RFC3339, v)
if err != nil {
c.JSON(http.StatusBadRequest, gin.H{
"error": "before_ts must be an RFC3339 timestamp (e.g. 2026-05-01T00:00:00Z)",
})
return
}
opts.BeforeTS = t
opts.HasBefore = true
}
messages, reachedEnd, err := h.store.List(c.Request.Context(), workspaceID, opts)
if err != nil {
// Errors here are infra (DB unreachable, store impl failure).
// Surface as 502 so the canvas can retry vs. treating as
// "no rows."
c.JSON(http.StatusBadGateway, gin.H{"error": "chat history unavailable"})
return
}
// Defensive: if the store returns nil messages slice (any impl
// might), emit empty array rather than `null` so canvas's JSON
// parser doesn't have to handle two empty representations.
if messages == nil {
messages = []messagestore.ChatMessage{}
}
c.JSON(http.StatusOK, ChatHistoryResponse{
Messages: messages,
ReachedEnd: reachedEnd,
})
}
@@ -0,0 +1,276 @@
package handlers
// chat_history_test.go — handler-level tests against a fake
// MessageStore. The parser-level parity tests against the canvas TS
// fixtures live in internal/messagestore/postgres_store_test.go;
// this file covers the HTTP-shape concerns (param validation,
// pagination passthrough, error mapping) without touching a DB.
//
// Why the split: PR-D extracted storage to messagestore.MessageStore.
// The handler is now a thin adapter — its tests should exercise the
// adapter (ParseQuery → store.List → emitJSON), not the parser. A
// future MessageStore impl (S3, vector store) shares the same
// handler; testing the handler against the interface keeps the
// adapter test independent of any specific impl.
import (
"context"
"encoding/json"
"errors"
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/messagestore"
"github.com/gin-gonic/gin"
)
const testWorkspaceID = "550e8400-e29b-41d4-a716-446655440000"
func init() {
gin.SetMode(gin.TestMode)
}
// fakeStore is a stub MessageStore for handler-level tests. Every
// real store impl (Postgres, S3, vector) shares the handler — so a
// fake that records inputs + returns scripted outputs is the right
// granularity for HTTP-shape coverage.
type fakeStore struct {
// LastWorkspaceID + LastOpts capture the call shape so the test
// can assert the handler passed the right args to the store.
LastWorkspaceID string
LastOpts messagestore.ListOptions
// Returns — set per test.
ReturnMessages []messagestore.ChatMessage
ReturnReachedEnd bool
ReturnErr error
// Panic — if non-empty, List panics with this string. Used by
// the resilience test to confirm the handler returns 502 on
// store-impl failures rather than crashing the goroutine.
PanicWith string
}
func (s *fakeStore) List(ctx context.Context, workspaceID string, opts messagestore.ListOptions) ([]messagestore.ChatMessage, bool, error) {
if s.PanicWith != "" {
panic(s.PanicWith)
}
s.LastWorkspaceID = workspaceID
s.LastOpts = opts
return s.ReturnMessages, s.ReturnReachedEnd, s.ReturnErr
}
// Compile-time assertion that fakeStore satisfies the interface.
// Catches drift if the interface changes and the fake stops being a
// drop-in for tests.
var _ messagestore.MessageStore = (*fakeStore)(nil)
func newRouter(store messagestore.MessageStore) *gin.Engine {
r := gin.New()
h := NewChatHistoryHandler(store)
r.GET("/workspaces/:id/chat-history", h.List)
return r
}
func doChatHistoryRequest(t *testing.T, r *gin.Engine, path string) *httptest.ResponseRecorder {
t.Helper()
req := httptest.NewRequest(http.MethodGet, path, nil)
w := httptest.NewRecorder()
r.ServeHTTP(w, req)
return w
}
// =====================================================================
// Param validation
// =====================================================================
func TestChatHistoryHandler_RejectsNonUUIDWorkspaceID(t *testing.T) {
store := &fakeStore{}
r := newRouter(store)
w := doChatHistoryRequest(t, r, "/workspaces/not-a-uuid/chat-history")
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for non-UUID, got %d", w.Code)
}
if store.LastWorkspaceID != "" {
t.Errorf("non-UUID reached the store: %q", store.LastWorkspaceID)
}
}
func TestChatHistoryHandler_RejectsMalformedBeforeTS(t *testing.T) {
store := &fakeStore{}
r := newRouter(store)
w := doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history?before_ts=not-a-timestamp")
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for malformed before_ts, got %d", w.Code)
}
if !strings.Contains(w.Body.String(), "RFC3339") {
t.Errorf("error message should mention RFC3339; got %q", w.Body.String())
}
}
func TestChatHistoryHandler_DefaultsLimitTo100(t *testing.T) {
store := &fakeStore{}
r := newRouter(store)
doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history")
if store.LastOpts.Limit != 100 {
t.Errorf("default limit=%d want 100", store.LastOpts.Limit)
}
if store.LastOpts.HasBefore {
t.Errorf("HasBefore should be false when no cursor passed")
}
}
func TestChatHistoryHandler_ClampsLimitToMax1000(t *testing.T) {
store := &fakeStore{}
r := newRouter(store)
doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history?limit=99999")
if store.LastOpts.Limit != 1000 {
t.Errorf("limit not clamped: got %d, want 1000", store.LastOpts.Limit)
}
}
func TestChatHistoryHandler_IgnoresInvalidLimit(t *testing.T) {
// Negative or zero limits should fall back to default rather
// than reach the store (which rejects them as a programming bug).
store := &fakeStore{}
r := newRouter(store)
for _, bad := range []string{"-1", "0", "abc"} {
store.LastOpts = messagestore.ListOptions{}
doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history?limit="+bad)
if store.LastOpts.Limit != 100 {
t.Errorf("limit=%q yielded %d, want default 100", bad, store.LastOpts.Limit)
}
}
}
// =====================================================================
// Pagination passthrough
// =====================================================================
func TestChatHistoryHandler_BeforeTSPassedToStore(t *testing.T) {
store := &fakeStore{}
r := newRouter(store)
doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history?before_ts=2026-04-25T18:00:00Z&limit=25")
if !store.LastOpts.HasBefore {
t.Errorf("HasBefore=false but query passed before_ts")
}
got := store.LastOpts.BeforeTS.UTC().Format("2006-01-02T15:04:05Z")
if got != "2026-04-25T18:00:00Z" {
t.Errorf("BeforeTS=%q want 2026-04-25T18:00:00Z", got)
}
if store.LastOpts.Limit != 25 {
t.Errorf("limit=%d want 25", store.LastOpts.Limit)
}
}
// =====================================================================
// Response shape
// =====================================================================
func TestChatHistoryHandler_EmptyResultIsArrayNotNull(t *testing.T) {
// nil messages slice from the store must serialize as `[]`,
// not `null` — canvas's JSON parser has one path.
store := &fakeStore{ReturnMessages: nil, ReturnReachedEnd: true}
r := newRouter(store)
w := doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history")
if w.Code != http.StatusOK {
t.Fatalf("status=%d", w.Code)
}
var resp ChatHistoryResponse
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
t.Fatalf("body not JSON: %v", err)
}
// json.Unmarshal of `null` into a []slice yields a nil — assert
// the JSON literally contains "[]" so a future change that
// forgets the nil-coercion would fail loudly.
if !strings.Contains(w.Body.String(), `"messages":[]`) {
t.Errorf("body should contain `\"messages\":[]`; got %s", w.Body.String())
}
if !resp.ReachedEnd {
t.Errorf("reached_end not propagated")
}
}
func TestChatHistoryHandler_NonEmptyResponsePreservesShape(t *testing.T) {
size := int64(4096)
store := &fakeStore{
ReturnMessages: []messagestore.ChatMessage{
{
ID: "msg-1",
Role: "user",
Content: "hi",
Timestamp: "2026-04-25T18:00:00Z",
},
{
ID: "msg-2",
Role: "agent",
Content: "hello back",
Attachments: []messagestore.ChatAttachment{
{Name: "img.png", URI: "workspace:/img.png", MimeType: "image/png", Size: &size},
},
Timestamp: "2026-04-25T18:00:01Z",
},
},
ReturnReachedEnd: false,
}
r := newRouter(store)
w := doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history")
if w.Code != http.StatusOK {
t.Fatalf("status=%d body=%s", w.Code, w.Body.String())
}
var resp ChatHistoryResponse
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
t.Fatalf("body not JSON: %v", err)
}
if len(resp.Messages) != 2 {
t.Fatalf("messages=%d want 2", len(resp.Messages))
}
if resp.Messages[1].Attachments[0].Size == nil || *resp.Messages[1].Attachments[0].Size != 4096 {
t.Errorf("size pointer flattened in JSON round-trip")
}
}
// =====================================================================
// Error mapping — store errors become 502, not 500/panic
// =====================================================================
func TestChatHistoryHandler_StoreErrorReturns502(t *testing.T) {
store := &fakeStore{ReturnErr: errors.New("simulated DB unreachable")}
r := newRouter(store)
w := doChatHistoryRequest(t, r, "/workspaces/"+testWorkspaceID+"/chat-history")
if w.Code != http.StatusBadGateway {
t.Errorf("expected 502 on store error, got %d", w.Code)
}
if !strings.Contains(w.Body.String(), "unavailable") {
t.Errorf("response body should communicate unavailability; got %q", w.Body.String())
}
}
// =====================================================================
// Interface conformance — the platform-default Postgres impl is the
// only impl in tree today, but the assertion catches future drift if
// the interface evolves and the impl falls behind.
// =====================================================================
func TestMessageStoreInterface_PostgresImplSatisfies(t *testing.T) {
// Compile-time assertion lives in messagestore/postgres_store.go
// (`var _ MessageStore = (*PostgresMessageStore)(nil)`). This
// runtime test exists only to keep the conformance visible in
// the handler test file — a reader of chat_history_test.go
// shouldn't have to traverse to the messagestore package to see
// what the handler is paired with.
var s messagestore.MessageStore = messagestore.NewPostgresMessageStore(nil)
_ = s
}
@@ -10,6 +10,7 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/textutil"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
@@ -164,10 +165,10 @@ func (h *DelegationHandler) Delegate(c *gin.Context) {
go h.executeDelegation(sourceID, body.TargetID, delegationID, a2aBody)
// Broadcast event so canvas shows delegation in real-time
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_SENT", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationSent), sourceID, map[string]interface{}{
"delegation_id": delegationID,
"target_id": body.TargetID,
"task_preview": truncate(body.Task, 100),
"task_preview": textutil.TruncateBytes(body.Task, 100),
})
resp := gin.H{
@@ -317,7 +318,7 @@ func (h *DelegationHandler) executeDelegation(sourceID, targetID, delegationID s
// Update status: pending → dispatched
h.updateDelegationStatus(sourceID, delegationID, "dispatched", "")
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_STATUS", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationStatus), sourceID, map[string]interface{}{
"delegation_id": delegationID, "target_id": targetID, "status": "dispatched",
})
@@ -352,7 +353,7 @@ func (h *DelegationHandler) executeDelegation(sourceID, targetID, delegationID s
log.Printf("Delegation %s: failed to insert error log: %v", delegationID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_FAILED", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationFailed), sourceID, map[string]interface{}{
"delegation_id": delegationID, "target_id": targetID, "error": proxyErr.Error(),
})
// RFC #2829 PR-2 result-push (see UpdateStatus for rationale).
@@ -388,7 +389,7 @@ func (h *DelegationHandler) executeDelegation(sourceID, targetID, delegationID s
`, sourceID, sourceID, targetID, "Delegation queued — target at capacity", string(queuedJSON)); err != nil {
log.Printf("Delegation %s: failed to insert queued log: %v", delegationID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_STATUS", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationStatus), sourceID, map[string]interface{}{
"delegation_id": delegationID, "target_id": targetID, "status": "queued",
})
return
@@ -407,7 +408,7 @@ func (h *DelegationHandler) executeDelegation(sourceID, targetID, delegationID s
if _, err := db.DB.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, target_id, summary, response_body, status)
VALUES ($1, 'delegation', 'delegate_result', $2, $3, $4, $5::jsonb, 'completed')
`, sourceID, sourceID, targetID, "Delegation completed ("+truncate(responseText, 80)+")", string(respJSON)); err != nil {
`, sourceID, sourceID, targetID, "Delegation completed ("+textutil.TruncateBytes(responseText, 80)+")", string(respJSON)); err != nil {
log.Printf("Delegation %s: failed to insert success log: %v", delegationID, err)
}
@@ -420,10 +421,10 @@ func (h *DelegationHandler) executeDelegation(sourceID, targetID, delegationID s
// delegation_ledger_integration_test.go.
recordLedgerStatus(ctx, delegationID, "completed", "", responseText)
h.updateDelegationStatus(sourceID, delegationID, "completed", "")
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_COMPLETE", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationComplete), sourceID, map[string]interface{}{
"delegation_id": delegationID,
"target_id": targetID,
"response_preview": truncate(responseText, 200),
"response_preview": textutil.TruncateBytes(responseText, 200),
})
// RFC #2829 PR-2 result-push (see UpdateStatus for rationale).
pushDelegationResultToInbox(ctx, sourceID, delegationID, "completed", responseText, "")
@@ -503,10 +504,10 @@ func (h *DelegationHandler) Record(c *gin.Context) {
recordLedgerInsert(ctx, sourceID, body.TargetID, body.DelegationID, body.Task, "")
recordLedgerStatus(ctx, body.DelegationID, "dispatched", "", "")
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_SENT", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationSent), sourceID, map[string]interface{}{
"delegation_id": body.DelegationID,
"target_id": body.TargetID,
"task_preview": truncate(body.Task, 100),
"task_preview": textutil.TruncateBytes(body.Task, 100),
})
c.JSON(http.StatusAccepted, gin.H{
@@ -555,12 +556,12 @@ func (h *DelegationHandler) UpdateStatus(c *gin.Context) {
if _, err := db.DB.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, summary, response_body, status)
VALUES ($1, 'delegation', 'delegate_result', $2, $3, $4::jsonb, 'completed')
`, sourceID, sourceID, "Delegation completed ("+truncate(body.ResponsePreview, 80)+")", string(respJSON)); err != nil {
`, sourceID, sourceID, "Delegation completed ("+textutil.TruncateBytes(body.ResponsePreview, 80)+")", string(respJSON)); err != nil {
log.Printf("Delegation UpdateStatus: result insert failed for %s: %v", delegationID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_COMPLETE", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationComplete), sourceID, map[string]interface{}{
"delegation_id": delegationID,
"response_preview": truncate(body.ResponsePreview, 200),
"response_preview": textutil.TruncateBytes(body.ResponsePreview, 200),
})
// RFC #2829 PR-2 result-push: when the gate is on, also write an
// a2a_receive row so the caller's inbox poller surfaces this to
@@ -570,7 +571,7 @@ func (h *DelegationHandler) UpdateStatus(c *gin.Context) {
// the result instead of holding open an HTTP connection.
pushDelegationResultToInbox(ctx, sourceID, delegationID, "completed", body.ResponsePreview, "")
} else {
h.broadcaster.RecordAndBroadcast(ctx, "DELEGATION_FAILED", sourceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationFailed), sourceID, map[string]interface{}{
"delegation_id": delegationID,
"error": body.Error,
})
@@ -626,7 +627,7 @@ func (h *DelegationHandler) ListDelegations(c *gin.Context) {
entry["error"] = errorDetail
}
if responseBody != "" {
entry["response_preview"] = truncate(responseBody, 300)
entry["response_preview"] = textutil.TruncateBytes(responseBody, 300)
}
delegations = append(delegations, entry)
}
@@ -727,9 +728,3 @@ func extractResponseText(body []byte) string {
return string(body)
}
func truncate(s string, max int) string {
if len(s) <= max {
return s
}
return s[:max] + "..."
}
@@ -8,6 +8,7 @@ import (
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/textutil"
)
// delegation_ledger.go — durable per-task ledger for A2A delegation
@@ -50,18 +51,15 @@ func NewDelegationLedger(handle *sql.DB) *DelegationLedger {
return &DelegationLedger{db: handle}
}
// truncatePreview caps stored preview at 4KB. The full prompt/response is
// already in activity_logs.{request,response}_body — this is the at-a-glance
// view for the dashboard, not a forensic record.
// previewCap caps stored preview at 4KB. The full prompt/response is
// already in activity_logs.{request,response}_body — this is the
// at-a-glance view for the dashboard, not a forensic record.
//
// Truncation goes through textutil.TruncateBytesNoMarker so it's
// rune-safe (#2026 / #2959 / #2962 bug class: byte-slice mid-codepoint
// → Postgres JSONB rejects → silent INSERT failure → audit gap).
const previewCap = 4096
func truncatePreview(s string) string {
if len(s) <= previewCap {
return s
}
return s[:previewCap]
}
// InsertOpts is the agent's record-of-intent. Caller, callee, task preview,
// and the chosen delegation_id are required; idempotency_key is optional.
type InsertOpts struct {
@@ -96,7 +94,7 @@ func (l *DelegationLedger) Insert(ctx context.Context, opts InsertOpts) {
) VALUES ($1, $2, $3, $4, 'queued', $5, $6)
ON CONFLICT (delegation_id) DO NOTHING
`, opts.DelegationID, opts.CallerID, opts.CalleeID,
truncatePreview(opts.TaskPreview), deadline, idemArg)
textutil.TruncateBytesNoMarker(opts.TaskPreview, previewCap), deadline, idemArg)
if err != nil {
log.Printf("delegation_ledger Insert(%s): %v", opts.DelegationID, err)
}
@@ -175,7 +173,7 @@ func (l *DelegationLedger) SetStatus(ctx context.Context,
result_preview = NULLIF($4, ''),
updated_at = now()
WHERE delegation_id = $1
`, delegationID, status, errorDetail, truncatePreview(resultPreview))
`, delegationID, status, errorDetail, textutil.TruncateBytesNoMarker(resultPreview, previewCap))
return err
}
@@ -2,9 +2,11 @@ package handlers
import (
"context"
"database/sql/driver"
"errors"
"strings"
"testing"
"unicode/utf8"
"github.com/DATA-DOG/go-sqlmock"
)
@@ -73,15 +75,20 @@ func TestLedgerInsert_TruncatesOversizedPreview(t *testing.T) {
mock := setupTestDB(t)
l := NewDelegationLedger(nil)
huge := strings.Repeat("x", 10_000) // > previewCap
// 4096 / 3 = 1365 runes; +10 for margin so we cross the cap.
// '世' is 3 bytes in UTF-8 (worst case for byte-cap rune walking).
huge := strings.Repeat("世", (previewCap/3)+10)
if len(huge) <= previewCap {
t.Fatalf("test setup: input too short (%d bytes) — must exceed previewCap=%d", len(huge), previewCap)
}
mock.ExpectExec(`INSERT INTO delegations`).
WithArgs(
"deleg-big",
"c", "ca",
sqlmock.AnyArg(), // truncated preview — verify length below via custom matcher
sqlmock.AnyArg(),
sqlmock.AnyArg(),
capValidUTF8Matcher{cap: previewCap}, // truncated preview must fit cap AND be valid UTF-8
sqlmock.AnyArg(), // deadline
sqlmock.AnyArg(), // idempotency_key
).
WillReturnResult(sqlmock.NewResult(0, 1))
@@ -96,30 +103,28 @@ func TestLedgerInsert_TruncatesOversizedPreview(t *testing.T) {
}
}
// ---------- truncatePreview unit ----------
// capValidUTF8Matcher pins #2962 at the integration boundary: the
// preview that lands in the INSERT MUST be valid UTF-8 (else Postgres
// JSONB rejects → silent audit gap) AND fit within the byte cap. Pre-
// migration this would have asserted on the corrupted "世" mid-codepoint
// byte slice; post-migration it asserts the truncated preview is a
// clean rune-aligned prefix.
type capValidUTF8Matcher struct{ cap int }
func TestTruncatePreview_UnderCap(t *testing.T) {
in := "short"
if got := truncatePreview(in); got != in {
t.Errorf("under-cap should passthrough; got %q", got)
func (m capValidUTF8Matcher) Match(v driver.Value) bool {
s, ok := v.(string)
if !ok {
return false
}
return len(s) <= m.cap && utf8.ValidString(s)
}
func TestTruncatePreview_OverCapTruncatesAtBoundary(t *testing.T) {
in := strings.Repeat("a", previewCap+100)
got := truncatePreview(in)
if len(got) != previewCap {
t.Errorf("expected len=%d got len=%d", previewCap, len(got))
}
}
func TestTruncatePreview_ExactlyAtCap(t *testing.T) {
in := strings.Repeat("a", previewCap)
got := truncatePreview(in)
if got != in {
t.Errorf("at-cap should passthrough unchanged")
}
}
// Helper-level truncation tests now live in
// internal/textutil/truncate_test.go. The integration-level path
// (TestLedgerInsert_TruncatesOversizedPreview above) still exercises
// the previewCap boundary through the SQL write so a regression in
// the wiring (wrong cap, wrong helper, missing call) would still go
// red here.
// ---------- SetStatus lifecycle ----------
@@ -423,14 +423,23 @@ mkdir -p ~/.codex
# (then open ~/.codex/config.toml in your editor and paste:)
#
# [mcp_servers.molecule]
# command = "python3"
# args = ["-m", "molecule_runtime.a2a_mcp_server"]
# command = "molecule-mcp"
# args = []
# startup_timeout_sec = 30
#
# [mcp_servers.molecule.env]
# WORKSPACE_ID = "{{WORKSPACE_ID}}"
# PLATFORM_URL = "{{PLATFORM_URL}}"
# MOLECULE_WORKSPACE_TOKEN = "<paste from create response>"
#
# Use the "molecule-mcp" console-script wrapper (NOT
# "python3 -m molecule_runtime.a2a_mcp_server"). The wrapper is what
# keeps the workspace ALIVE on the canvas: it POSTs /registry/register
# at startup and runs a 20s heartbeat thread alongside the MCP stdio
# loop. The bare a2a_mcp_server module exposes tools but does NOT
# heartbeat — pointing codex at it leaves the canvas showing this
# workspace as awaiting_agent (OFFLINE) within 60-90s even while
# tools work.
# 3. Run the bridge daemon as a durable background process — this
# is the INBOUND path. Long-polls the platform inbox and runs
@@ -507,11 +516,20 @@ pip install molecule-ai-workspace-runtime
# 3. Wire the molecule MCP server. {{WORKSPACE_ID}} + {{PLATFORM_URL}}
# are stamped server-side; paste the auth token before running.
#
# Use the "molecule-mcp" console-script wrapper (NOT
# "python3 -m molecule_runtime.a2a_mcp_server"). The wrapper is what
# keeps the workspace ALIVE on the canvas: it POSTs /registry/register
# at startup and runs a 20s heartbeat thread alongside the MCP stdio
# loop. The bare a2a_mcp_server module exposes tools but does NOT
# heartbeat — pointing openclaw at it leaves the canvas showing this
# workspace as awaiting_agent (OFFLINE) within 60-90s even while
# tools work.
WORKSPACE_TOKEN="<paste from create response>"
openclaw mcp set molecule "$(cat <<EOF
{
"command": "python3",
"args": ["-m", "molecule_runtime.a2a_mcp_server"],
"command": "molecule-mcp",
"args": [],
"env": {
"WORKSPACE_ID": "{{WORKSPACE_ID}}",
"PLATFORM_URL": "{{PLATFORM_URL}}",
@@ -38,3 +38,40 @@ func TestExternalTemplates_NoMoleculeOrgIDPlaceholder(t *testing.T) {
}
}
}
// TestExternalMcpTemplates_UseMoleculeMcpWrapper pins the invariant
// that operator-facing snippets configuring an MCP server entry point
// use the ``molecule-mcp`` console-script wrapper (mcp_cli.main),
// NOT the bare ``a2a_mcp_server`` module.
//
// Why: a2a_mcp_server exposes the MCP tools but does NOT call
// /registry/register or run the 20s heartbeat thread. mcp_cli wraps
// it with both, which is what flips the canvas presence indicator
// from awaiting_agent (OFFLINE) to online and keeps it that way.
// Originally tracked by molecule-core#2957 — operator hit the
// silent-OFFLINE failure mode when the Codex tab pointed at the bare
// module.
//
// The hermes-channel template intentionally uses the bare module: it
// owns the platform plugin path and runs its own
// register_platform/heartbeat code in-process, so wrapping with
// mcp_cli would double-heartbeat. universalMcp / codex / openclaw
// must all use the wrapper.
func TestExternalMcpTemplates_UseMoleculeMcpWrapper(t *testing.T) {
mustUseWrapper := map[string]string{
"externalUniversalMcpTemplate": externalUniversalMcpTemplate,
"externalCodexTemplate": externalCodexTemplate,
"externalOpenClawTemplate": externalOpenClawTemplate,
}
for name, body := range mustUseWrapper {
if !strings.Contains(body, "molecule-mcp") {
t.Errorf("%s does not reference 'molecule-mcp' — operator-facing MCP snippets must point at the heartbeat-wrapping console script, not the bare a2a_mcp_server module (#2957)", name)
}
if strings.Contains(body, `"-m", "molecule_runtime.a2a_mcp_server"`) {
t.Errorf("%s spawns 'python3 -m molecule_runtime.a2a_mcp_server' — that bypasses the standalone register/heartbeat wrapper, leaving the canvas showing the workspace OFFLINE (#2957). Use 'molecule-mcp' instead.", name)
}
if strings.Contains(body, `["-m", "molecule_runtime.a2a_mcp_server"]`) {
t.Errorf("%s spawns 'python3 -m molecule_runtime.a2a_mcp_server' — that bypasses the standalone register/heartbeat wrapper, leaving the canvas showing the workspace OFFLINE (#2957). Use 'molecule-mcp' instead.", name)
}
}
}
@@ -8,6 +8,7 @@ import (
"net/http"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
)
@@ -100,7 +101,7 @@ func (h *WorkspaceHandler) RotateExternalCredentials(c *gin.Context) {
// see when credentials were rotated. No PII; the token plaintext
// is NOT logged.
if h.broadcaster != nil {
h.broadcaster.RecordAndBroadcast(ctx, "EXTERNAL_CREDENTIALS_ROTATED", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventExternalCredentialsRotated), id, map[string]interface{}{
"workspace_id": id,
})
}
+170 -3
View File
@@ -11,18 +11,21 @@ import (
"os"
"testing"
"errors"
"github.com/DATA-DOG/go-sqlmock"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/gin-gonic/gin"
)
// newMCPHandler is a test helper that constructs an MCPHandler backed by the
// sqlmock DB set up by setupTestDB.
// sqlmock DB set up by setupTestDB. Uses newTestBroadcaster so handlers
// that BroadcastOnly (send_message_to_user, etc.) don't nil-panic on the
// hub — events.NewBroadcaster(nil) crashes inside hub.Broadcast.
func newMCPHandler(t *testing.T) (*MCPHandler, sqlmock.Sqlmock) {
t.Helper()
mock := setupTestDB(t)
h := NewMCPHandler(db.DB, events.NewBroadcaster(nil))
h := NewMCPHandler(db.DB, newTestBroadcaster())
return h, mock
}
@@ -628,6 +631,170 @@ func TestMCPHandler_SendMessageToUser_Blocked_WhenEnvNotSet(t *testing.T) {
}
}
// TestMCPHandler_SendMessageToUser_DBErrorLogsAndStill200s pins the
// "best-effort persistence" contract: when the activity_log INSERT
// fails (DB hiccup, constraint violation, transient connection drop),
// the tool MUST still return success to the agent because the WS
// broadcast already succeeded — the user has seen the message.
//
// This matches /notify (activity.go) behavior. Returning an error
// here would cause the agent to retry and re-broadcast, double-
// rendering the message in the user's live chat panel for every
// retry until the DB recovers.
func TestMCPHandler_SendMessageToUser_DBErrorLogsAndStill200s(t *testing.T) {
t.Setenv("MOLECULE_MCP_ALLOW_SEND_MESSAGE", "true")
h, mock := newMCPHandler(t)
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-err").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
// INSERT fails — must NOT abort the tool response.
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WillReturnError(errors.New("transient db error"))
w := mcpPost(t, h, "ws-err", map[string]interface{}{
"jsonrpc": "2.0",
"id": 100,
"method": "tools/call",
"params": map[string]interface{}{
"name": "send_message_to_user",
"arguments": map[string]interface{}{
"message": "should not be lost from the live chat",
},
},
})
var resp mcpResponse
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
t.Fatalf("response was not valid JSON-RPC: %v", err)
}
// Tool response is success — INSERT failure logged, broadcast
// already succeeded.
if resp.Error != nil {
t.Errorf("tool response should be success on DB error (broadcast won), got JSON-RPC error: %+v", resp.Error)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("expected DB calls in order: %v", err)
}
}
// TestMCPHandler_SendMessageToUser_ResponseBodyShape pins the
// response_body JSON shape stored in activity_logs. This shape MUST
// match what the canvas hydrater (extractResponseText in
// historyHydration.ts) reads — specifically `{"result": "<text>"}`.
// Any drift in the JSON shape silently breaks chat history without
// failing the INSERT.
//
// Caught the same drift class flagged in
// feedback_assert_exact_not_substring.md: a substring match on
// "result" would pass even if the field were renamed; we assert the
// exact JSON shape.
func TestMCPHandler_SendMessageToUser_ResponseBodyShape(t *testing.T) {
t.Setenv("MOLECULE_MCP_ALLOW_SEND_MESSAGE", "true")
h, mock := newMCPHandler(t)
const userMessage = "Hi there from the agent"
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-shape").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
// Capture the response_body argument and assert its exact shape.
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
"ws-shape",
sqlmock.AnyArg(), // summary
// The response_body MUST be JSON `{"result": "<message>"}`.
// Any other shape (e.g., wrapping in a Task object) breaks
// the canvas hydrater's `body.result` extractor.
`{"result":"`+userMessage+`"}`,
).
WillReturnResult(sqlmock.NewResult(1, 1))
w := mcpPost(t, h, "ws-shape", map[string]interface{}{
"jsonrpc": "2.0",
"id": 101,
"method": "tools/call",
"params": map[string]interface{}{
"name": "send_message_to_user",
"arguments": map[string]interface{}{
"message": userMessage,
},
},
})
if w.Code != 200 {
t.Fatalf("expected 200, got %d body=%s", w.Code, w.Body.String())
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("response_body shape drift — would silently break canvas chat history: %v", err)
}
}
// TestMCPHandler_SendMessageToUser_PersistsToActivityLog pins the fix
// for the reno-stars / CEO Ryan PC chat-history data-loss bug:
// external claude-code agents using molecule-mcp's send_message_to_user
// tool route through THIS handler (not the HTTP /notify endpoint),
// and the handler used to broadcast WS only — visible live, gone on
// reload because nothing wrote to activity_logs.
//
// Pins:
// - INSERT happens on the success path (broadcast + DB write).
// - INSERT shape mirrors the HTTP /notify handler exactly:
// activity_type='a2a_receive', method='notify', request_body NULL,
// response_body={"result": message}, status='ok'. The canvas
// hydration query (`type=a2a_receive&source=canvas`) treats
// both writers as the same shape — drift here means the bug
// re-surfaces silently.
func TestMCPHandler_SendMessageToUser_PersistsToActivityLog(t *testing.T) {
t.Setenv("MOLECULE_MCP_ALLOW_SEND_MESSAGE", "true")
h, mock := newMCPHandler(t)
// Workspace lookup — the handler verifies the workspace exists
// before it does anything else. Returning a name lets the
// broadcast payload populate; the test doesn't assert on the
// broadcast (no observable WS in this fake), only on the DB.
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-msg").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
// The persistence INSERT — pin the exact shape so a future
// refactor that switches columns or drops `method='notify'`
// breaks the test loud, not silently. Match by regex on the
// table + activity_type + method literals.
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
"ws-msg",
sqlmock.AnyArg(), // summary "Agent message: ..."
sqlmock.AnyArg(), // response_body JSON
).
WillReturnResult(sqlmock.NewResult(1, 1))
w := mcpPost(t, h, "ws-msg", map[string]interface{}{
"jsonrpc": "2.0",
"id": 99,
"method": "tools/call",
"params": map[string]interface{}{
"name": "send_message_to_user",
"arguments": map[string]interface{}{
"message": "Hello, this should persist!",
},
},
})
var resp mcpResponse
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
t.Fatalf("response was not valid JSON-RPC: %v\nbody=%s", err, w.Body.String())
}
if resp.Error != nil {
t.Errorf("unexpected JSON-RPC error: %+v", resp.Error)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("DB expectations not met (INSERT missing → reno-stars data-loss regression): %v", err)
}
}
// ─────────────────────────────────────────────────────────────────────────────
// Parse error
// ─────────────────────────────────────────────────────────────────────────────
+17 -13
View File
@@ -11,6 +11,7 @@ import (
"context"
"database/sql"
"encoding/json"
"errors"
"fmt"
"io"
"log"
@@ -330,20 +331,23 @@ func (h *MCPHandler) toolSendMessageToUser(ctx context.Context, workspaceID stri
return "", fmt.Errorf("send_message_to_user is not enabled on this MCP bridge (set MOLECULE_MCP_ALLOW_SEND_MESSAGE=true)")
}
var wsName string
err := h.database.QueryRowContext(ctx,
`SELECT name FROM workspaces WHERE id = $1 AND status != 'removed'`, workspaceID,
).Scan(&wsName)
if err != nil {
return "", fmt.Errorf("workspace not found")
// Single source of truth for chat-bearing agent → user messages —
// see agent_message_writer.go for the contract. The pre-RFC-#2945
// duplication of broadcast + INSERT logic between this handler and
// activity.go:Notify is what produced the reno-stars data-loss
// regression; both paths now route through the same writer.
//
// MCP send_message_to_user does not currently surface attachments
// (the tool args don't accept them); pass nil. If a future tool
// schema adds an attachments arg, build []AgentMessageAttachment
// and pass through.
writer := NewAgentMessageWriter(h.database, h.broadcaster)
if err := writer.Send(ctx, workspaceID, message, nil); err != nil {
if errors.Is(err, ErrWorkspaceNotFound) {
return "", fmt.Errorf("workspace not found")
}
return "", err
}
h.broadcaster.BroadcastOnly(workspaceID, "AGENT_MESSAGE", map[string]interface{}{
"message": message,
"workspace_id": workspaceID,
"name": wsName,
})
return "Message sent.", nil
}
@@ -0,0 +1,457 @@
package handlers
// memories_v2.go — HTTP endpoints that expose Memory v2 plugin state to
// the canvas Memory tab. Reads-only; writes still go through the MCP
// path (see mcp_tools_memory_v2.go) where SAFE-T1201 redaction +
// org-write audit happen at a single funnel.
//
// Why a separate v2 endpoint set rather than retrofitting memories.go:
//
// - memories.go reads `agent_memories` (legacy v1 table). After the
// 2026-05-05 cutover, agent commits go to the plugin's
// memory_records — agent_memories is frozen. The canvas Memory
// tab reading memories.go shows STALE data.
// - The plugin is loopback-only on each tenant (127.0.0.1:9100), so
// the canvas (browser) cannot call it directly. workspace-server
// proxies through these endpoints.
// - v2 has different shape (namespace tree, kind/source/pin/TTL,
// score) — overloading memories.go would break v1 consumers
// (admin export, the back-compat MCP shim).
//
// All endpoints sit under the same wsAuth group memories.go uses,
// so the existing per-tenant token gates them automatically.
import (
"errors"
"log"
"net/http"
"strconv"
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/client"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/contract"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/namespace"
"github.com/gin-gonic/gin"
)
// MemoriesV2Handler bundles the plugin client + namespace resolver
// behind a slim HTTP surface. Construction matches the rest of the
// handlers package: NewMemoriesV2Handler followed by WithMemoryV2 (or
// the test-only withMemoryV2APIs) at boot.
type MemoriesV2Handler struct {
plugin memoryPluginAPI
resolver namespaceResolverAPI
}
// NewMemoriesV2Handler constructs an unwired handler. Every method
// returns 503 until WithMemoryV2 is called — keeps a partial deploy
// (MEMORY_PLUGIN_URL absent) from crashing the canvas with 500s.
func NewMemoriesV2Handler() *MemoriesV2Handler {
return &MemoriesV2Handler{}
}
// WithMemoryV2 attaches the live plugin client + resolver. Returns
// the receiver for fluent boot-time wiring, mirroring MCPHandler.
func (h *MemoriesV2Handler) WithMemoryV2(plugin *client.Client, resolver *namespace.Resolver) *MemoriesV2Handler {
h.plugin = plugin
h.resolver = resolver
return h
}
// withMemoryV2APIs is the test-only injection path: takes the
// interfaces directly so unit tests don't have to construct a real
// *client.Client / namespace.Resolver. Keep symmetric with
// MCPHandler.withMemoryV2APIs so handler tests can re-use the same
// stubs.
func (h *MemoriesV2Handler) withMemoryV2APIs(plugin memoryPluginAPI, resolver namespaceResolverAPI) *MemoriesV2Handler {
h.plugin = plugin
h.resolver = resolver
return h
}
// available reports whether the v2 deps are wired. Each route checks
// this and returns 503 + a clear hint when the plugin isn't
// configured, matching the MCP-side error.
func (h *MemoriesV2Handler) available() error {
if h == nil || h.plugin == nil || h.resolver == nil {
return errors.New("memory plugin is not configured (set MEMORY_PLUGIN_URL)")
}
return nil
}
// ─────────────────────────────────────────────────────────────────────────────
// GET /workspaces/:id/v2/namespaces
//
// Returns the namespace tree the canvas uses to drive the Memory tab's
// namespace dropdown. Two arrays:
//
// - readable[]: every namespace this workspace can READ from. Drives
// the "show me memories from X" filter dropdown.
// - writable[]: subset of readable that this workspace can WRITE to.
// Used for future canvas-side commit (not in this PR but the
// contract is symmetric so the dropdown can disable read-only
// entries when wiring up commit).
//
// Each entry carries name + kind + a friendly label so the canvas
// doesn't have to parse `workspace:abc-123` itself. Kind ranks the
// dropdown grouping (workspace → team → org → custom).
// ─────────────────────────────────────────────────────────────────────────────
// NamespaceView is the UI-friendly DTO returned by GET v2/namespaces.
// Internal namespace.Namespace has fields the canvas doesn't need
// (resolver-internal flags, raw metadata blobs); this strips it down.
type NamespaceView struct {
Name string `json:"name"`
Kind contract.NamespaceKind `json:"kind"`
// Label is a stable display string the canvas can render directly.
// For workspace:<id> it's "Workspace (<short-id>)"; for team:<id>
// it's "Team (<short-id>)"; org/custom carry the raw suffix.
Label string `json:"label"`
}
// NamespacesResponse is the body of GET v2/namespaces.
type NamespacesResponse struct {
Readable []NamespaceView `json:"readable"`
Writable []NamespaceView `json:"writable"`
}
// Namespaces handles GET /workspaces/:id/v2/namespaces.
func (h *MemoriesV2Handler) Namespaces(c *gin.Context) {
if err := h.available(); err != nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": err.Error()})
return
}
workspaceID := c.Param("id")
ctx := c.Request.Context()
readable, err := h.resolver.ReadableNamespaces(ctx, workspaceID)
if err != nil {
log.Printf("v2/namespaces readable error workspace=%s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to resolve readable namespaces"})
return
}
writable, err := h.resolver.WritableNamespaces(ctx, workspaceID)
if err != nil {
log.Printf("v2/namespaces writable error workspace=%s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to resolve writable namespaces"})
return
}
c.JSON(http.StatusOK, NamespacesResponse{
Readable: namespacesToViews(readable),
Writable: namespacesToViews(writable),
})
}
// ─────────────────────────────────────────────────────────────────────────────
// GET /workspaces/:id/v2/memories
//
// Search the plugin for memories visible to this workspace.
//
// Query params (all optional):
// - namespace: a single readable namespace to scope to. Omitted ⇒ all
// readable namespaces (dropdown's "All" mode).
// - q: full-text query string. Empty ⇒ recency-ordered listing.
// - kind: one of fact|summary|checkpoint. Empty ⇒ all kinds.
// - limit: max rows. Defaults to 50, clamped to 100. Matches the
// v1 endpoint's clamp shape (memories.go:memoryRecallMaxLimit).
//
// Server-side ACL invariant: the request is ALWAYS intersected with
// the resolver's readable set on the server. A canvas-supplied
// `namespace=foo:bar` that this workspace can't read returns an empty
// list, NOT 403 — the canvas dropdown is built from /v2/namespaces
// so a forbidden value is a stale-cache bug, not malice. Existence
// non-inference: empty result is indistinguishable from "you can't
// read this namespace" — same as the wsAuth-protected v1 endpoints.
// ─────────────────────────────────────────────────────────────────────────────
const memoriesV2DefaultLimit = 50
const memoriesV2MaxLimit = 100
// Search handles GET /workspaces/:id/v2/memories.
func (h *MemoriesV2Handler) Search(c *gin.Context) {
if err := h.available(); err != nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": err.Error()})
return
}
workspaceID := c.Param("id")
ctx := c.Request.Context()
requestedNS := c.Query("namespace")
query := c.Query("q")
kindStr := c.Query("kind")
limit := parseLimit(c.Query("limit"))
// Resolve the readable set, then intersect the request.
// IntersectReadable handles both the empty-request case (return
// all readable) and the explicit-namespace case (return [ns] iff
// readable, else []).
var requested []string
if requestedNS != "" {
requested = []string{requestedNS}
}
scopedNamespaces, err := h.resolver.IntersectReadable(ctx, workspaceID, requested)
if err != nil {
log.Printf("v2/memories intersect error workspace=%s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to resolve namespaces"})
return
}
// Empty after intersection — caller asked for a namespace they
// can't read, OR they have no readable namespaces at all. Return
// [] (not 404) so the canvas can render its empty-state without
// special-casing.
if len(scopedNamespaces) == 0 {
c.JSON(http.StatusOK, MemoriesResponse{Memories: []MemoryView{}})
return
}
req := contract.SearchRequest{
Namespaces: scopedNamespaces,
Query: query,
Limit: limit,
}
if kindStr != "" {
req.Kinds = []contract.MemoryKind{contract.MemoryKind(kindStr)}
}
resp, err := h.plugin.Search(ctx, req)
if err != nil {
log.Printf("v2/memories plugin error workspace=%s: %v", workspaceID, err)
c.JSON(http.StatusBadGateway, gin.H{"error": "memory plugin search failed"})
return
}
out := MemoriesResponse{Memories: make([]MemoryView, 0, len(resp.Memories))}
for _, m := range resp.Memories {
out.Memories = append(out.Memories, memoryToView(m))
}
c.JSON(http.StatusOK, out)
}
// ─────────────────────────────────────────────────────────────────────────────
// DELETE /workspaces/:id/v2/memories/:memoryId
//
// Forget a memory. The plugin enforces its own ownership model — we
// pass `requested_by_namespace = workspace:<id>` so the audit trail
// records who initiated the forget; the plugin's ACL gate decides
// whether the deletion is allowed.
//
// 404 (not 403) on a missing or non-owned memory: existence-non-
// inferring response, matches the v1 DELETE in memories.go.
// ─────────────────────────────────────────────────────────────────────────────
// Forget handles DELETE /workspaces/:id/v2/memories/:memoryId.
func (h *MemoriesV2Handler) Forget(c *gin.Context) {
if err := h.available(); err != nil {
c.JSON(http.StatusServiceUnavailable, gin.H{"error": err.Error()})
return
}
workspaceID := c.Param("id")
memoryID := c.Param("memoryId")
ctx := c.Request.Context()
if memoryID == "" {
c.JSON(http.StatusBadRequest, gin.H{"error": "memoryId is required"})
return
}
body := contract.ForgetRequest{
RequestedByNamespace: "workspace:" + workspaceID,
}
if err := h.plugin.ForgetMemory(ctx, memoryID, body); err != nil {
// Map plugin not_found → 404. Anything else is upstream error.
var ce *contract.Error
if errors.As(err, &ce) && ce.Code == contract.ErrorCodeNotFound {
c.JSON(http.StatusNotFound, gin.H{"error": "memory not found"})
return
}
log.Printf("v2/memories forget error workspace=%s memory=%s: %v", workspaceID, memoryID, err)
c.JSON(http.StatusBadGateway, gin.H{"error": "memory plugin delete failed"})
return
}
c.JSON(http.StatusOK, gin.H{"status": "deleted"})
}
// ─────────────────────────────────────────────────────────────────────────────
// View shaping helpers
// ─────────────────────────────────────────────────────────────────────────────
// MemoryView is the canvas-facing shape of a v2 memory record. The raw
// contract.Memory carries internal fields we don't expose (raw
// `propagation` blob); MemoryView strips it to what the Memory tab
// renders.
type MemoryView struct {
ID string `json:"id"`
Namespace string `json:"namespace"`
Content string `json:"content"`
Kind contract.MemoryKind `json:"kind"`
Source contract.MemorySource `json:"source"`
Pin bool `json:"pin"`
ExpiresAt *time.Time `json:"expires_at,omitempty"`
CreatedAt time.Time `json:"created_at"`
// Score is the plugin's similarity score (1.0 = exact); only
// populated when ?q= is set and the plugin supports embedding.
Score *float64 `json:"score,omitempty"`
// SourceWorkspaceID is parsed out of `propagation.source_workspace_id`
// when present (cross-workspace propagation) — lets the canvas
// render a "from <peer>" badge so users can tell their own writes
// apart from team-shared memory.
SourceWorkspaceID string `json:"source_workspace_id,omitempty"`
}
// MemoriesResponse is the body of GET v2/memories.
type MemoriesResponse struct {
Memories []MemoryView `json:"memories"`
}
func memoryToView(m contract.Memory) MemoryView {
v := MemoryView{
ID: m.ID,
Namespace: m.Namespace,
Content: m.Content,
Kind: m.Kind,
Source: m.Source,
Pin: m.Pin,
ExpiresAt: m.ExpiresAt,
CreatedAt: m.CreatedAt,
Score: m.Score,
}
if m.Propagation != nil {
// `source_workspace_id` is a propagation contract field
// (RFC #2728 §5). Plugin emits it on writes that originated
// from a different workspace. Best-effort string extraction —
// don't fail rendering if shape drifts.
if raw, ok := m.Propagation["source_workspace_id"]; ok {
if s, ok := raw.(string); ok && s != "" {
v.SourceWorkspaceID = s
}
}
}
return v
}
// namespacesToViews converts resolver namespaces into UI-friendly
// views. Prefers `DisplayName` from the resolver (workspace.name from
// the DB) when present; falls back to a UUID-prefix label.
//
// Issue #2988: pre-fix, every namespace used a shortID-truncated UUID
// label. On a root workspace where workspace==team==org IDs collide
// (resolver derive() degenerate case), all three labels rendered
// identically. DisplayName disambiguates by surfacing real workspace
// names — the canvas dropdown now reads "Workspace (mac laptop)" /
// "Team (mac laptop)" / "Org (mac laptop)" for a root workspace
// rather than three identical UUID prefixes. The `kind` prefix
// "Workspace/Team/Org" still carries the semantic distinction.
func namespacesToViews(in []namespace.Namespace) []NamespaceView {
views := make([]NamespaceView, 0, len(in))
for _, n := range in {
views = append(views, NamespaceView{
Name: n.Name,
Kind: n.Kind,
Label: namespaceLabelWithName(n.Name, n.Kind, n.DisplayName),
})
}
return views
}
// namespaceLabel renders a human-friendly label for a namespace using
// the UUID-prefix fallback only. Kept for back-compat with callers
// that don't yet plumb a display name. New callers should use
// namespaceLabelWithName which prefers the workspace's display name
// when available.
//
// Format (UUID-prefix fallback):
// workspace:abc-123 → "Workspace (abc-123)"
// team:t-1 → "Team (t-1)"
// org:acme → "Org (acme)"
// custom:foo → "foo"
func namespaceLabel(name string, kind contract.NamespaceKind) string {
return namespaceLabelWithName(name, kind, "")
}
// namespaceLabelWithName renders the human-friendly label, preferring
// `displayName` when non-empty.
//
// When displayName is set:
// Workspace, "mac laptop" → "Workspace (mac laptop)"
// Team, "Engineering team" → "Team (Engineering team)"
// Org, "Hongming's Org" → "Org (Hongming's Org)"
//
// When displayName is empty (lookup miss, future-migration drop, etc.),
// falls back to the UUID-prefix shape for back-compat.
//
// Custom namespaces ignore displayName because they're operator-defined
// — the operator chose the raw suffix as the label, surfacing a
// different "name" would be a UX surprise.
func namespaceLabelWithName(name string, kind contract.NamespaceKind, displayName string) string {
suffix := ""
if i := indexOfColon(name); i >= 0 && i+1 < len(name) {
suffix = name[i+1:]
}
switch kind {
case contract.NamespaceKindWorkspace:
if displayName != "" {
return "Workspace (" + displayName + ")"
}
return "Workspace (" + shortID(suffix) + ")"
case contract.NamespaceKindTeam:
if displayName != "" {
return "Team (" + displayName + ")"
}
return "Team (" + shortID(suffix) + ")"
case contract.NamespaceKindOrg:
if displayName != "" {
return "Org (" + displayName + ")"
}
return "Org (" + suffix + ")"
case contract.NamespaceKindCustom:
// Operator-defined; the suffix IS the label they chose.
// displayName is ignored — surfacing a different name would
// be a UX surprise for an operator who deliberately named
// the namespace.
if suffix == "" {
return name
}
return suffix
default:
return name
}
}
// shortID truncates a UUID-like string to the first 8 chars so the
// dropdown stays readable. Keeps the full id available via the
// `name` field for click-to-copy / debugging.
func shortID(s string) string {
if len(s) <= 8 {
return s
}
return s[:8]
}
// indexOfColon is strings.IndexByte without the import, kept inline so
// the helper stays trivially auditable next to namespaceLabel.
func indexOfColon(s string) int {
for i := 0; i < len(s); i++ {
if s[i] == ':' {
return i
}
}
return -1
}
// parseLimit validates the ?limit= query value. Defaults +
// clamps mirror memoriesV2DefaultLimit / memoriesV2MaxLimit.
func parseLimit(raw string) int {
if raw == "" {
return memoriesV2DefaultLimit
}
n, err := strconv.Atoi(raw)
if err != nil || n <= 0 {
return memoriesV2DefaultLimit
}
if n > memoriesV2MaxLimit {
return memoriesV2MaxLimit
}
return n
}
@@ -0,0 +1,755 @@
package handlers
// memories_v2_test.go — comprehensive coverage for the Memory v2
// canvas-facing HTTP surface. Pinned shape:
//
// - 503 path when plugin unwired (every route)
// - GET /v2/namespaces success + readable/writable propagation
// - GET /v2/namespaces error path (resolver failure on either call)
// - GET /v2/memories: empty intersection, namespace passthrough,
// query+kind+limit propagation, plugin error mapping
// - DELETE /v2/memories/:id: success, plugin not_found→404, other
// plugin errors→502, missing memoryId→400
// - View shaping: namespaceLabel for all four kinds + truncation,
// memoryToView with/without propagation source, parseLimit edge
// cases (default, negative, zero, over-cap, non-numeric)
//
// Tests use the same `memoryPluginAPI` / `namespaceResolverAPI` fakes
// the MCP v2 tests use so we don't spin up a real plugin server.
import (
"context"
"encoding/json"
"errors"
"net/http"
"net/http/httptest"
"strings"
"testing"
"time"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/contract"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/memory/namespace"
"github.com/gin-gonic/gin"
)
// ─────────────────────────────────────────────────────────────────────────────
// Fakes
// ─────────────────────────────────────────────────────────────────────────────
type fakePlugin struct {
searchResp *contract.SearchResponse
searchErr error
searchReq contract.SearchRequest // captured for assertion
forgetErr error
forgetID string
forgetReq contract.ForgetRequest
}
func (f *fakePlugin) CommitMemory(ctx context.Context, ns string, body contract.MemoryWrite) (*contract.MemoryWriteResponse, error) {
return nil, errors.New("not implemented in fake")
}
func (f *fakePlugin) Search(ctx context.Context, body contract.SearchRequest) (*contract.SearchResponse, error) {
f.searchReq = body
if f.searchErr != nil {
return nil, f.searchErr
}
return f.searchResp, nil
}
func (f *fakePlugin) ForgetMemory(ctx context.Context, id string, body contract.ForgetRequest) error {
f.forgetID = id
f.forgetReq = body
return f.forgetErr
}
type fakeNSResolver struct {
readable []namespace.Namespace
readableErr error
writable []namespace.Namespace
writableErr error
intersect []string
intersectErr error
intersectIn []string // captured
}
func (f *fakeNSResolver) ReadableNamespaces(ctx context.Context, ws string) ([]namespace.Namespace, error) {
return f.readable, f.readableErr
}
func (f *fakeNSResolver) WritableNamespaces(ctx context.Context, ws string) ([]namespace.Namespace, error) {
return f.writable, f.writableErr
}
func (f *fakeNSResolver) CanWrite(ctx context.Context, ws, ns string) (bool, error) {
return true, nil
}
func (f *fakeNSResolver) IntersectReadable(ctx context.Context, ws string, requested []string) ([]string, error) {
f.intersectIn = requested
return f.intersect, f.intersectErr
}
// ─────────────────────────────────────────────────────────────────────────────
// Test helpers
// ─────────────────────────────────────────────────────────────────────────────
func init() {
gin.SetMode(gin.TestMode)
}
// newWiredHandler returns a handler with both the fake plugin + fake
// resolver attached. Tests that need the unwired (503) path use
// NewMemoriesV2Handler() directly.
func newWiredHandler(p *fakePlugin, r *fakeNSResolver) *MemoriesV2Handler {
return NewMemoriesV2Handler().withMemoryV2APIs(p, r)
}
func doRequest(t *testing.T, h *MemoriesV2Handler, method, path string, params gin.Params) *httptest.ResponseRecorder {
t.Helper()
rec := httptest.NewRecorder()
c, _ := gin.CreateTestContext(rec)
c.Params = params
req := httptest.NewRequest(method, path, nil)
c.Request = req
switch {
case method == http.MethodGet && strings.HasSuffix(path, "/v2/namespaces"):
h.Namespaces(c)
case method == http.MethodGet && strings.Contains(path, "/v2/memories"):
h.Search(c)
case method == http.MethodDelete:
h.Forget(c)
default:
t.Fatalf("doRequest: don't know how to dispatch %s %s", method, path)
}
return rec
}
func mustJSON(t *testing.T, body []byte, out interface{}) {
t.Helper()
if err := json.Unmarshal(body, out); err != nil {
t.Fatalf("json decode: %v\nbody=%s", err, string(body))
}
}
// ─────────────────────────────────────────────────────────────────────────────
// 503 — plugin unwired
// ─────────────────────────────────────────────────────────────────────────────
func TestMemoriesV2_PluginUnwired_All503(t *testing.T) {
h := NewMemoriesV2Handler() // no WithMemoryV2 / withMemoryV2APIs
cases := []struct {
name string
method string
path string
params gin.Params
}{
{"namespaces", http.MethodGet, "/workspaces/ws-a/v2/namespaces", gin.Params{{Key: "id", Value: "ws-a"}}},
{"search", http.MethodGet, "/workspaces/ws-a/v2/memories", gin.Params{{Key: "id", Value: "ws-a"}}},
{"forget", http.MethodDelete, "/workspaces/ws-a/v2/memories/m-1", gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: "m-1"}}},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
rec := doRequest(t, h, tc.method, tc.path, tc.params)
if rec.Code != http.StatusServiceUnavailable {
t.Errorf("expected 503, got %d", rec.Code)
}
var body map[string]string
mustJSON(t, rec.Body.Bytes(), &body)
if !strings.Contains(body["error"], "MEMORY_PLUGIN_URL") {
t.Errorf("503 body missing operator hint, got: %q", body["error"])
}
})
}
}
// ─────────────────────────────────────────────────────────────────────────────
// GET /v2/namespaces
// ─────────────────────────────────────────────────────────────────────────────
func TestMemoriesV2_Namespaces_Success(t *testing.T) {
resolver := &fakeNSResolver{
readable: []namespace.Namespace{
{Name: "workspace:abc-1234-5678", Kind: contract.NamespaceKindWorkspace},
{Name: "team:t-99", Kind: contract.NamespaceKindTeam},
{Name: "org:acme", Kind: contract.NamespaceKindOrg},
{Name: "custom:special", Kind: contract.NamespaceKindCustom},
},
writable: []namespace.Namespace{
{Name: "workspace:abc-1234-5678", Kind: contract.NamespaceKindWorkspace},
},
}
h := newWiredHandler(&fakePlugin{}, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/namespaces",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != 200 {
t.Fatalf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
}
var body NamespacesResponse
mustJSON(t, rec.Body.Bytes(), &body)
if len(body.Readable) != 4 {
t.Errorf("expected 4 readable, got %d", len(body.Readable))
}
if len(body.Writable) != 1 {
t.Errorf("expected 1 writable, got %d", len(body.Writable))
}
// Label shaping pinned exactly — drift would silently break the
// dropdown rendering.
wantLabels := map[string]string{
"workspace:abc-1234-5678": "Workspace (abc-1234)",
"team:t-99": "Team (t-99)",
"org:acme": "Org (acme)",
"custom:special": "special",
}
for _, v := range body.Readable {
want, ok := wantLabels[v.Name]
if !ok {
t.Errorf("unexpected namespace name %q", v.Name)
continue
}
if v.Label != want {
t.Errorf("namespace %q: want label %q, got %q", v.Name, want, v.Label)
}
}
}
func TestMemoriesV2_Namespaces_ReadableError(t *testing.T) {
resolver := &fakeNSResolver{readableErr: errors.New("boom")}
h := newWiredHandler(&fakePlugin{}, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/namespaces",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != http.StatusInternalServerError {
t.Errorf("expected 500, got %d", rec.Code)
}
}
func TestMemoriesV2_Namespaces_WritableError(t *testing.T) {
resolver := &fakeNSResolver{
readable: []namespace.Namespace{},
writableErr: errors.New("boom"),
}
h := newWiredHandler(&fakePlugin{}, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/namespaces",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != http.StatusInternalServerError {
t.Errorf("expected 500, got %d", rec.Code)
}
}
// ─────────────────────────────────────────────────────────────────────────────
// GET /v2/memories — search path
// ─────────────────────────────────────────────────────────────────────────────
func TestMemoriesV2_Search_NoReadableNamespaces_EmptyResult(t *testing.T) {
// Empty intersection (e.g. workspace just provisioned, plugin
// hasn't created namespaces yet, OR caller asked for ns they
// can't read). Expected: 200 with empty memories array, NOT 404.
resolver := &fakeNSResolver{intersect: []string{}}
plugin := &fakePlugin{searchResp: &contract.SearchResponse{Memories: []contract.Memory{}}}
h := newWiredHandler(plugin, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != 200 {
t.Errorf("expected 200, got %d", rec.Code)
}
var body MemoriesResponse
mustJSON(t, rec.Body.Bytes(), &body)
if body.Memories == nil {
t.Error("Memories should be empty array, not nil — JSON would render null")
}
if len(body.Memories) != 0 {
t.Errorf("expected empty memories, got %d", len(body.Memories))
}
// Plugin must NOT be called when intersection is empty.
if plugin.searchReq.Namespaces != nil {
t.Error("plugin Search should not be called when intersection is empty")
}
}
func TestMemoriesV2_Search_FullPath_NamespaceQueryKindLimit(t *testing.T) {
expiresAt := time.Now().Add(24 * time.Hour)
resolver := &fakeNSResolver{intersect: []string{"workspace:ws-a"}}
score := 0.87
plugin := &fakePlugin{
searchResp: &contract.SearchResponse{
Memories: []contract.Memory{
{
ID: "m-1",
Namespace: "workspace:ws-a",
Content: "fact one",
Kind: contract.MemoryKindFact,
Source: contract.MemorySourceAgent,
Pin: true,
ExpiresAt: &expiresAt,
CreatedAt: time.Now(),
Score: &score,
Propagation: map[string]interface{}{
"source_workspace_id": "ws-peer-42",
},
},
},
},
}
h := newWiredHandler(plugin, resolver)
rec := httptest.NewRecorder()
c, _ := gin.CreateTestContext(rec)
c.Params = gin.Params{{Key: "id", Value: "ws-a"}}
c.Request = httptest.NewRequest(http.MethodGet,
"/workspaces/ws-a/v2/memories?namespace=workspace:ws-a&q=hello&kind=fact&limit=10", nil)
h.Search(c)
if rec.Code != 200 {
t.Fatalf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
}
// Resolver received the requested namespace as a single-element list
if len(resolver.intersectIn) != 1 || resolver.intersectIn[0] != "workspace:ws-a" {
t.Errorf("resolver.IntersectReadable received %v, want [workspace:ws-a]", resolver.intersectIn)
}
// Plugin received query + kind + limit propagated through
if plugin.searchReq.Query != "hello" {
t.Errorf("plugin.Query=%q, want hello", plugin.searchReq.Query)
}
if len(plugin.searchReq.Kinds) != 1 || plugin.searchReq.Kinds[0] != contract.MemoryKindFact {
t.Errorf("plugin.Kinds=%v, want [fact]", plugin.searchReq.Kinds)
}
if plugin.searchReq.Limit != 10 {
t.Errorf("plugin.Limit=%d, want 10", plugin.searchReq.Limit)
}
// Response shape — pin/expires_at/score/source_workspace_id all
// surfaced into MemoryView so the canvas doesn't have to dig
// through propagation map.
var body MemoriesResponse
mustJSON(t, rec.Body.Bytes(), &body)
if len(body.Memories) != 1 {
t.Fatalf("expected 1 memory, got %d", len(body.Memories))
}
m := body.Memories[0]
if !m.Pin {
t.Error("Pin not propagated")
}
if m.ExpiresAt == nil {
t.Error("ExpiresAt not propagated")
}
if m.Score == nil || *m.Score != 0.87 {
t.Errorf("Score=%v, want 0.87", m.Score)
}
if m.SourceWorkspaceID != "ws-peer-42" {
t.Errorf("SourceWorkspaceID=%q, want ws-peer-42", m.SourceWorkspaceID)
}
}
func TestMemoriesV2_Search_NoNamespaceQuery_AllReadable(t *testing.T) {
// No ?namespace= → resolver.IntersectReadable receives nil (empty
// requested) and returns ALL readable. Plugin gets full set.
resolver := &fakeNSResolver{intersect: []string{"workspace:ws-a", "team:t-1"}}
plugin := &fakePlugin{searchResp: &contract.SearchResponse{}}
h := newWiredHandler(plugin, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != 200 {
t.Errorf("expected 200, got %d", rec.Code)
}
if resolver.intersectIn != nil {
t.Errorf("requested should be nil for unscoped query, got %v", resolver.intersectIn)
}
if len(plugin.searchReq.Namespaces) != 2 {
t.Errorf("plugin.Namespaces=%v, want both readable", plugin.searchReq.Namespaces)
}
}
func TestMemoriesV2_Search_IntersectError(t *testing.T) {
resolver := &fakeNSResolver{intersectErr: errors.New("db down")}
h := newWiredHandler(&fakePlugin{}, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != http.StatusInternalServerError {
t.Errorf("expected 500, got %d", rec.Code)
}
}
func TestMemoriesV2_Search_PluginError(t *testing.T) {
resolver := &fakeNSResolver{intersect: []string{"workspace:ws-a"}}
plugin := &fakePlugin{searchErr: errors.New("plugin down")}
h := newWiredHandler(plugin, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != http.StatusBadGateway {
t.Errorf("expected 502 (plugin error), got %d", rec.Code)
}
}
func TestMemoriesV2_Search_PropagationMissing_NoSourceWorkspaceID(t *testing.T) {
resolver := &fakeNSResolver{intersect: []string{"workspace:ws-a"}}
plugin := &fakePlugin{
searchResp: &contract.SearchResponse{
Memories: []contract.Memory{
{ID: "m-1", Namespace: "workspace:ws-a", Content: "no propagation"},
},
},
}
h := newWiredHandler(plugin, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
var body MemoriesResponse
mustJSON(t, rec.Body.Bytes(), &body)
if len(body.Memories) != 1 || body.Memories[0].SourceWorkspaceID != "" {
t.Errorf("SourceWorkspaceID should be empty when propagation is nil, got %q", body.Memories[0].SourceWorkspaceID)
}
}
func TestMemoriesV2_Search_PropagationWrongType_DoesNotPanic(t *testing.T) {
resolver := &fakeNSResolver{intersect: []string{"workspace:ws-a"}}
plugin := &fakePlugin{
searchResp: &contract.SearchResponse{
Memories: []contract.Memory{
{
ID: "m-1",
Content: "wrong-type propagation",
Propagation: map[string]interface{}{
"source_workspace_id": 12345, // int, not string
},
},
},
},
}
h := newWiredHandler(plugin, resolver)
rec := doRequest(t, h, http.MethodGet, "/workspaces/ws-a/v2/memories",
gin.Params{{Key: "id", Value: "ws-a"}})
if rec.Code != 200 {
t.Fatalf("expected 200 (graceful), got %d", rec.Code)
}
var body MemoriesResponse
mustJSON(t, rec.Body.Bytes(), &body)
// Wrong-typed prop entry → empty SourceWorkspaceID, no panic.
if body.Memories[0].SourceWorkspaceID != "" {
t.Errorf("expected empty SourceWorkspaceID for non-string propagation, got %q", body.Memories[0].SourceWorkspaceID)
}
}
// ─────────────────────────────────────────────────────────────────────────────
// DELETE /v2/memories/:memoryId
// ─────────────────────────────────────────────────────────────────────────────
func TestMemoriesV2_Forget_Success(t *testing.T) {
plugin := &fakePlugin{} // forgetErr nil
h := newWiredHandler(plugin, &fakeNSResolver{})
rec := doRequest(t, h, http.MethodDelete, "/workspaces/ws-a/v2/memories/mem-42",
gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: "mem-42"}})
if rec.Code != 200 {
t.Errorf("expected 200, got %d body=%s", rec.Code, rec.Body.String())
}
if plugin.forgetID != "mem-42" {
t.Errorf("plugin received memoryID=%q, want mem-42", plugin.forgetID)
}
if plugin.forgetReq.RequestedByNamespace != "workspace:ws-a" {
t.Errorf("requested_by_namespace=%q, want workspace:ws-a", plugin.forgetReq.RequestedByNamespace)
}
}
func TestMemoriesV2_Forget_PluginNotFound_Maps404(t *testing.T) {
plugin := &fakePlugin{
forgetErr: &contract.Error{Code: contract.ErrorCodeNotFound, Message: "no such memory"},
}
h := newWiredHandler(plugin, &fakeNSResolver{})
rec := doRequest(t, h, http.MethodDelete, "/workspaces/ws-a/v2/memories/m-1",
gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: "m-1"}})
if rec.Code != http.StatusNotFound {
t.Errorf("expected 404, got %d", rec.Code)
}
}
func TestMemoriesV2_Forget_PluginOtherError_Maps502(t *testing.T) {
plugin := &fakePlugin{
forgetErr: &contract.Error{Code: contract.ErrorCodeInternal, Message: "db dead"},
}
h := newWiredHandler(plugin, &fakeNSResolver{})
rec := doRequest(t, h, http.MethodDelete, "/workspaces/ws-a/v2/memories/m-1",
gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: "m-1"}})
if rec.Code != http.StatusBadGateway {
t.Errorf("expected 502, got %d", rec.Code)
}
}
func TestMemoriesV2_Forget_NonContractError_Maps502(t *testing.T) {
// A raw error (e.g. transport failure) — not a contract.Error —
// also bubbles up as 502.
plugin := &fakePlugin{forgetErr: errors.New("connection reset")}
h := newWiredHandler(plugin, &fakeNSResolver{})
rec := doRequest(t, h, http.MethodDelete, "/workspaces/ws-a/v2/memories/m-1",
gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: "m-1"}})
if rec.Code != http.StatusBadGateway {
t.Errorf("expected 502, got %d", rec.Code)
}
}
func TestMemoriesV2_Forget_MissingMemoryID_400(t *testing.T) {
h := newWiredHandler(&fakePlugin{}, &fakeNSResolver{})
rec := doRequest(t, h, http.MethodDelete, "/workspaces/ws-a/v2/memories/",
gin.Params{{Key: "id", Value: "ws-a"}, {Key: "memoryId", Value: ""}})
if rec.Code != http.StatusBadRequest {
t.Errorf("expected 400, got %d", rec.Code)
}
}
// ─────────────────────────────────────────────────────────────────────────────
// View-shaping unit tests — pin individual helpers
// ─────────────────────────────────────────────────────────────────────────────
// namespaceLabelWithName tests — the new code path that prefers
// DisplayName over UUID-prefix fallback (issue #2988).
func TestNamespaceLabelWithName_PrefersDisplayNameWhenSet(t *testing.T) {
cases := []struct {
name string
raw string
kind contract.NamespaceKind
display string
want string
}{
{"workspace with name", "workspace:abc-1234", contract.NamespaceKindWorkspace, "mac laptop", "Workspace (mac laptop)"},
{"team with name", "team:abc-1234", contract.NamespaceKindTeam, "Engineering", "Team (Engineering)"},
{"org with name", "org:acme", contract.NamespaceKindOrg, "Hongming's Org", "Org (Hongming's Org)"},
// Custom ignores displayName by design — operator chose the suffix.
{"custom ignores displayName", "custom:ops-shared", contract.NamespaceKindCustom, "FancyName", "ops-shared"},
{"unknown kind falls through", "weird:x", contract.NamespaceKind("future"), "WhoCares", "weird:x"},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
got := namespaceLabelWithName(tc.raw, tc.kind, tc.display)
if got != tc.want {
t.Errorf("namespaceLabelWithName(%q, %q, %q) = %q, want %q",
tc.raw, tc.kind, tc.display, got, tc.want)
}
})
}
}
func TestNamespaceLabelWithName_FallsBackToUUIDPrefixWhenEmpty(t *testing.T) {
// When displayName is empty (NULL in DB, lookup miss, etc.), the
// label shape MUST match the legacy UUID-prefix shape exactly so
// existing canvas behaviour is unchanged for callers that don't
// plumb a name.
cases := []struct {
raw string
kind contract.NamespaceKind
want string
}{
{"workspace:abcdefghij", contract.NamespaceKindWorkspace, "Workspace (abcdefgh)"},
{"team:t-99", contract.NamespaceKindTeam, "Team (t-99)"},
{"org:acme", contract.NamespaceKindOrg, "Org (acme)"},
}
for _, tc := range cases {
got := namespaceLabelWithName(tc.raw, tc.kind, "")
if got != tc.want {
t.Errorf("displayName=\"\" path: got %q, want %q", got, tc.want)
}
}
}
func TestNamespacesToViews_PassesDisplayNameThrough(t *testing.T) {
in := []namespace.Namespace{
{Name: "workspace:root-1", Kind: contract.NamespaceKindWorkspace, DisplayName: "mac laptop"},
{Name: "team:root-1", Kind: contract.NamespaceKindTeam, DisplayName: "mac laptop"}, // root → team aliases self
{Name: "org:root-1", Kind: contract.NamespaceKindOrg, DisplayName: "mac laptop"},
}
out := namespacesToViews(in)
if len(out) != 3 {
t.Fatalf("len = %d, want 3", len(out))
}
wantLabels := []string{
"Workspace (mac laptop)",
"Team (mac laptop)",
"Org (mac laptop)",
}
for i, v := range out {
if v.Label != wantLabels[i] {
t.Errorf("[%d] label = %q, want %q", i, v.Label, wantLabels[i])
}
}
}
func TestNamespacesToViews_FallsBackToUUIDLabelWhenDisplayNameEmpty(t *testing.T) {
// Exercises the back-compat path — DisplayName="" plumbs through
// to namespaceLabelWithName which returns the legacy UUID-prefix
// label. This is what callers see when the workspaces table
// has a NULL name (defensive — workspaces.name is NOT NULL today).
in := []namespace.Namespace{
{Name: "workspace:root-1", Kind: contract.NamespaceKindWorkspace}, // no DisplayName
}
out := namespacesToViews(in)
if out[0].Label != "Workspace (root-1)" {
t.Errorf("fallback label = %q, want %q", out[0].Label, "Workspace (root-1)")
}
}
func TestNamespaceLabel_AllKinds(t *testing.T) {
cases := []struct {
name string
kind contract.NamespaceKind
want string
}{
{"workspace:abcdefghij", contract.NamespaceKindWorkspace, "Workspace (abcdefgh)"}, // truncated to 8
{"workspace:abc", contract.NamespaceKindWorkspace, "Workspace (abc)"}, // shorter than 8, kept as-is
{"team:t-99", contract.NamespaceKindTeam, "Team (t-99)"},
{"org:acme", contract.NamespaceKindOrg, "Org (acme)"},
{"custom:my-ns", contract.NamespaceKindCustom, "my-ns"},
{"custom:", contract.NamespaceKindCustom, "custom:"}, // empty suffix → fallback to raw name
{"weird-no-colon", contract.NamespaceKindWorkspace, "Workspace ()"},
{"unknown:x", contract.NamespaceKind("future"), "unknown:x"}, // unknown kind → fallback to raw name
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
got := namespaceLabel(tc.name, tc.kind)
if got != tc.want {
t.Errorf("namespaceLabel(%q, %q) = %q, want %q", tc.name, tc.kind, got, tc.want)
}
})
}
}
func TestParseLimit(t *testing.T) {
cases := []struct {
raw string
want int
}{
{"", memoriesV2DefaultLimit},
{"10", 10},
{"0", memoriesV2DefaultLimit}, // ≤0 → default, not error
{"-5", memoriesV2DefaultLimit}, // negative → default
{"abc", memoriesV2DefaultLimit}, // non-numeric → default
{"99999", memoriesV2MaxLimit}, // over cap → clamped
{"100", memoriesV2MaxLimit}, // exactly cap → kept
{"99", 99}, // just under cap → kept
}
for _, tc := range cases {
t.Run("raw="+tc.raw, func(t *testing.T) {
if got := parseLimit(tc.raw); got != tc.want {
t.Errorf("parseLimit(%q) = %d, want %d", tc.raw, got, tc.want)
}
})
}
}
func TestMemoryToView_AllFieldsPropagated(t *testing.T) {
now := time.Now()
exp := now.Add(time.Hour)
score := 0.95
m := contract.Memory{
ID: "m-1",
Namespace: "team:t-1",
Content: "hello",
Kind: contract.MemoryKindSummary,
Source: contract.MemorySourceUser,
Pin: true,
ExpiresAt: &exp,
CreatedAt: now,
Score: &score,
Propagation: map[string]interface{}{
"source_workspace_id": "ws-other",
},
}
v := memoryToView(m)
if v.ID != m.ID || v.Namespace != m.Namespace || v.Content != m.Content {
t.Errorf("basic fields: %+v", v)
}
if v.Kind != contract.MemoryKindSummary || v.Source != contract.MemorySourceUser {
t.Errorf("kind/source: %+v", v)
}
if !v.Pin || v.ExpiresAt == nil || v.Score == nil || *v.Score != 0.95 {
t.Errorf("pin/expires/score: %+v", v)
}
if v.SourceWorkspaceID != "ws-other" {
t.Errorf("SourceWorkspaceID=%q, want ws-other", v.SourceWorkspaceID)
}
}
func TestNamespacesToViews_PreservesOrder(t *testing.T) {
in := []namespace.Namespace{
{Name: "team:t1", Kind: contract.NamespaceKindTeam},
{Name: "workspace:w1", Kind: contract.NamespaceKindWorkspace},
}
out := namespacesToViews(in)
if len(out) != 2 {
t.Fatalf("len=%d", len(out))
}
// Resolver determines order; we just preserve it. (Sorting can be
// added at the resolver layer if the canvas needs it.)
if out[0].Name != "team:t1" || out[1].Name != "workspace:w1" {
t.Errorf("order not preserved: %+v", out)
}
}
func TestNamespacesToViews_EmptyInput_EmptySlice(t *testing.T) {
out := namespacesToViews(nil)
if out == nil {
t.Error("expected empty slice, not nil — JSON-marshals as null otherwise")
}
if len(out) != 0 {
t.Errorf("expected len 0, got %d", len(out))
}
}
func TestIndexOfColon(t *testing.T) {
cases := []struct {
s string
want int
}{
{"abc:def", 3},
{":foo", 0},
{"nocolon", -1},
{"", -1},
{"a:b:c", 1}, // first colon only
}
for _, tc := range cases {
if got := indexOfColon(tc.s); got != tc.want {
t.Errorf("indexOfColon(%q) = %d, want %d", tc.s, got, tc.want)
}
}
}
func TestWithMemoryV2_FluentReturnsReceiver(t *testing.T) {
// WithMemoryV2 is the production wiring path (takes *client.Client +
// *namespace.Resolver). withMemoryV2APIs is the test path. The
// production call is structural — assigns the two fields and
// returns the receiver — but we still want a 100% coverage gate
// to catch a future refactor that accidentally drops the fluent
// return (breaking the boot-time chain in router.go).
//
// We can't pass nil for the typed pointers and call available()
// here because Go interface-with-nil-pointer is non-nil at the
// interface level — `available()` would not detect that as
// "unwired". The unwired-plugin behaviour is exhaustively
// covered by TestMemoriesV2_PluginUnwired_All503; this test just
// pins the fluent contract.
h := NewMemoriesV2Handler()
got := h.WithMemoryV2(nil, nil)
if got != h {
t.Error("WithMemoryV2 must return receiver for fluent chaining")
}
}
func TestShortID(t *testing.T) {
cases := map[string]string{
"": "",
"short": "short",
"exactly8": "exactly8",
"longer-than-eight": "longer-t",
"abc-1234-5678-90ab": "abc-1234",
}
for in, want := range cases {
if got := shortID(in); got != want {
t.Errorf("shortID(%q) = %q, want %q", in, got, want)
}
}
}
@@ -20,12 +20,14 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/channels"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/crypto"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/models"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/provisioner"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/provlog"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/scheduler"
"github.com/google/uuid"
)
// createWorkspaceTree recursively materialises an OrgWorkspace (and its
// descendants) into the workspaces + canvas_layouts tables and kicks off
// Docker provisioning. absX/absY are THIS workspace's absolute canvas
@@ -80,61 +82,6 @@ func (h *OrgHandler) createWorkspaceTree(ws OrgWorkspace, parentID *string, absX
}
}
// 5s timeout bounds the lookup independently of any HTTP request
// context. createWorkspaceTree runs in goroutines spawned from the
// /org/import handler, so plumbing the request context here would
// cascade-cancel into provisionWorkspaceAuto and abort in-flight
// EC2 provisioning if the client disconnected mid-import — that's
// the wrong behaviour. A short bounded timeout protects the
// per-row SELECT against a wedged DB without taking the
// drop-everything-on-disconnect tradeoff.
ctxLookup, cancelLookup := context.WithTimeout(context.Background(), 5*time.Second)
defer cancelLookup()
// Idempotency: if a workspace with the same (parent_id, name) already
// exists, skip the INSERT + canvas_layouts + broadcast + provisioning.
// This is what makes /org/import safe to call multiple times — the
// historical leak was every call recreating the entire tree (see
// tenant-hongming, 72 distinct child workspaces in 4 days, all from
// repeated org-template spawns of the same template).
//
// Recursion still runs on the existing id so partial-match templates
// (parent exists, some children missing) backfill the missing children
// instead of either no-op'ing the whole subtree or duplicating the
// existing children.
//
// /org/import is ADDITIVE-ONLY, never destructive. Children present
// in the existing tree but absent from the new template are
// preserved (no DELETE on diff). Skip-path also does NOT propagate
// updates to existing nodes — a re-import that adds an
// initial_memory or schedule to an existing workspace is silently
// dropped (the function bypasses seedInitialMemories, schedule SQL,
// channel config for skipped rows). To force-update an existing
// tree, delete and re-import or use a future /org/sync route.
existingID, existing, lookupErr := h.lookupExistingChild(ctxLookup, ws.Name, parentID)
if lookupErr != nil {
return fmt.Errorf("idempotency check for %s: %w", ws.Name, lookupErr)
}
if existing {
log.Printf("Org import: %q already exists (id=%s) — skipping create+provision, recursing into children for partial-match", ws.Name, existingID)
parentRef := ""
if parentID != nil {
parentRef = *parentID
}
provlog.Event("provision.skip_existing", map[string]any{
"name": ws.Name,
"existing_id": existingID,
"parent_id": parentRef,
"tier": tier,
})
*results = append(*results, map[string]interface{}{
"id": existingID,
"name": ws.Name,
"tier": tier,
"skipped": true,
})
return h.recurseChildrenForImport(ws, existingID, absX, absY, defaults, orgBaseDir, results, provisionSem)
}
id := uuid.New().String()
awarenessNS := workspaceAwarenessNamespace(id)
@@ -186,10 +133,67 @@ func (h *OrgHandler) createWorkspaceTree(ws OrgWorkspace, parentID *string, absX
if maxConcurrent <= 0 {
maxConcurrent = models.DefaultMaxConcurrentTasks
}
_, err := db.DB.ExecContext(ctx, `
// TOCTOU-safe insert (#2872 Critical 1).
//
// `ON CONFLICT DO NOTHING` paired with the partial unique index
// from migration 20260506000000_workspaces_unique_parent_name.up.sql
// atomically resolves a race window that the prior
// lookup-then-insert had: two concurrent /org/import POSTs both
// saw "not found" in lookupExistingChild and both INSERT'd the
// same (parent_id, name). After this swap the SECOND INSERT
// silently no-ops, RETURNING returns 0 rows → sql.ErrNoRows, and
// the skip-path runs.
//
// ON CONFLICT target uses (COALESCE(parent_id,...), name) WHERE
// status != 'removed' — must match the partial-index predicate
// EXACTLY for Postgres to consider the index applicable.
var insertedID string
err := db.DB.QueryRowContext(ctx, `
INSERT INTO workspaces (id, name, role, tier, runtime, awareness_namespace, status, parent_id, workspace_dir, workspace_access, max_concurrent_tasks)
VALUES ($1, $2, $3, $4, $5, $6, $7, $8, $9, $10, $11)
`, id, ws.Name, role, tier, runtime, awarenessNS, "provisioning", parentID, workspaceDir, workspaceAccess, maxConcurrent)
ON CONFLICT (COALESCE(parent_id, '00000000-0000-0000-0000-000000000000'::uuid), name)
WHERE status != 'removed'
DO NOTHING
RETURNING id
`, id, ws.Name, role, tier, runtime, awarenessNS, "provisioning", parentID, workspaceDir, workspaceAccess, maxConcurrent).Scan(&insertedID)
if errors.Is(err, sql.ErrNoRows) {
// Skip path — a non-removed row already exists for
// (parent_id, name). Re-select its id; idempotency-friendly
// semantics match the original lookupExistingChild path
// (parent_id IS NOT DISTINCT FROM matches NULL too,
// status='removed' rows are ignored).
ctxLookup, cancelLookup := context.WithTimeout(context.Background(), 5*time.Second)
defer cancelLookup()
existingID, found, selErr := h.lookupExistingChild(ctxLookup, ws.Name, parentID)
if selErr != nil {
return fmt.Errorf("post-conflict re-select for %s: %w", ws.Name, selErr)
}
if !found {
// Index conflicted but row vanished between INSERT and
// re-SELECT (status flipped to 'removed' concurrently).
// Surface as an error rather than silently retrying —
// the user can re-trigger /org/import safely.
return fmt.Errorf("workspace %q conflicted on insert but not visible on re-select (concurrent status flip?)", ws.Name)
}
log.Printf("Org import: %q already exists (id=%s) — skipping create+provision, recursing into children for partial-match", ws.Name, existingID)
parentRef := ""
if parentID != nil {
parentRef = *parentID
}
provlog.Event("provision.skip_existing", map[string]any{
"name": ws.Name,
"existing_id": existingID,
"parent_id": parentRef,
"tier": tier,
})
*results = append(*results, map[string]interface{}{
"id": existingID,
"name": ws.Name,
"tier": tier,
"skipped": true,
})
return h.recurseChildrenForImport(ws, existingID, absX, absY, defaults, orgBaseDir, results, provisionSem)
}
if err != nil {
log.Printf("Org import: failed to create %s: %v", ws.Name, err)
return fmt.Errorf("failed to create %s: %w", ws.Name, err)
@@ -227,7 +231,7 @@ func (h *OrgHandler) createWorkspaceTree(ws OrgWorkspace, parentID *string, absX
if parentID != nil {
payload["parent_id"] = *parentID
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_PROVISIONING", id, payload)
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceProvisioning), id, payload)
// Seed initial memories from workspace config or defaults (issue #1050).
// Per-workspace initial_memories override defaults; if workspace has none,
@@ -243,7 +247,7 @@ func (h *OrgHandler) createWorkspaceTree(ws OrgWorkspace, parentID *string, absX
if _, err := db.DB.ExecContext(ctx, `UPDATE workspaces SET status = $1, url = $2 WHERE id = $3`, models.StatusOnline, ws.URL, id); err != nil {
log.Printf("Org import: external workspace status update failed for %s: %v", ws.Name, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), id, map[string]interface{}{
"name": ws.Name, "external": true,
})
} else if h.workspace.HasProvisioner() {
@@ -31,11 +31,25 @@ import (
// tests pin the helper's three observable behaviors plus an AST gate
// that catches future re-introductions of the un-checked INSERT.
// lookupChildSQLRE anchors the sqlmock ExpectQuery on every load-bearing
// token of lookupExistingChild's SELECT (org_import.go:639-645). A loose
// substring match (the prior shape, just `SELECT id FROM workspaces`)
// would silent-pass a regression that drops `IS NOT DISTINCT FROM`
// (breaks NULL-parent matching), drops `parent_id` entirely (hijacks
// siblings of the same name across different parents), or drops the
// `status != 'removed'` filter (blocks re-import after Collapse).
// RFC #2872 Important-2.
//
// The four anchored tokens are exactly the predicates the bug shapes
// would tamper with. Whitespace is `\s+` so a future formatter pass
// doesn't churn this string.
const lookupChildSQLRE = `(?s)SELECT id FROM workspaces\s+WHERE name = \$1\s+AND parent_id IS NOT DISTINCT FROM \$2\s+AND status != 'removed'`
func TestLookupExistingChild_NotFound_ReturnsFalseNoError(t *testing.T) {
mock := setupTestDB(t)
// 0-row result → driver returns sql.ErrNoRows on Scan.
parent := "parent-1"
mock.ExpectQuery(`SELECT id FROM workspaces`).
mock.ExpectQuery(lookupChildSQLRE).
WithArgs("Alpha", &parent).
WillReturnRows(sqlmock.NewRows([]string{"id"}))
@@ -56,7 +70,7 @@ func TestLookupExistingChild_NotFound_ReturnsFalseNoError(t *testing.T) {
func TestLookupExistingChild_Found_ReturnsIDAndTrue(t *testing.T) {
mock := setupTestDB(t)
parent := "parent-1"
mock.ExpectQuery(`SELECT id FROM workspaces`).
mock.ExpectQuery(lookupChildSQLRE).
WithArgs("Alpha", &parent).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-existing-uuid"))
@@ -79,7 +93,7 @@ func TestLookupExistingChild_NilParent_MatchesRoot(t *testing.T) {
// a plain `=` would never match a NULL row. Pin that roots
// (parent_id=NULL) are still found by the lookup.
mock := setupTestDB(t)
mock.ExpectQuery(`SELECT id FROM workspaces`).
mock.ExpectQuery(lookupChildSQLRE).
WithArgs("RootAgent", (*string)(nil)).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-root-uuid"))
@@ -102,7 +116,7 @@ func TestLookupExistingChild_DBError_Propagates(t *testing.T) {
mock := setupTestDB(t)
parent := "parent-1"
connFail := errors.New("simulated postgres unavailable")
mock.ExpectQuery(`SELECT id FROM workspaces`).
mock.ExpectQuery(lookupChildSQLRE).
WithArgs("Alpha", &parent).
WillReturnError(connFail)
@@ -137,7 +151,7 @@ func TestLookupExistingChild_WrappedNoRows_TreatedAsNotFound(t *testing.T) {
mock := setupTestDB(t)
parent := "parent-1"
wrapped := fmt.Errorf("driver-wrapped: %w", sql.ErrNoRows)
mock.ExpectQuery(`SELECT id FROM workspaces`).
mock.ExpectQuery(lookupChildSQLRE).
WithArgs("Alpha", &parent).
WillReturnError(wrapped)
@@ -209,19 +223,42 @@ func findLookupAndWorkspacesInsertPos(t *testing.T, fname string, src []byte) (l
return
}
// Source-level guard — pins that org_import.go calls
// h.lookupExistingChild BEFORE its INSERT INTO workspaces.
// onConflictDoNothingRE pins the TOCTOU-safe shape introduced by
// migration 20260506000000_workspaces_unique_parent_name.up.sql +
// the org_import.go INSERT swap (#2872 Critical 1). The workspaces
// INSERT MUST funnel concurrent collisions through the partial unique
// index — `ON CONFLICT (...) WHERE status != 'removed' DO NOTHING`
// is the literal pg statement form that achieves it.
//
// The pattern intentionally requires both the COALESCE expression
// (so root-workspace NULL parents collide) AND the partial-index WHERE
// clause (so 'removed' rows don't block re-imports). A regression that
// drops either piece would make the index target a different shape
// than the migration created, and Postgres would emit
// "no unique or exclusion constraint matching the ON CONFLICT
// specification" at runtime — but only on the FIRST collision attempt
// in production, not in CI without a live race. This regex catches
// the shape in source so the bug never ships.
var onConflictDoNothingRE = regexp.MustCompile(
`(?s)ON\s+CONFLICT\s*\(\s*COALESCE\s*\(\s*parent_id\s*,\s*'00000000-0000-0000-0000-000000000000'::uuid\s*\)\s*,\s*name\s*\).*?WHERE\s+status\s*!=\s*'removed'.*?DO\s+NOTHING`,
)
// Source-level guard — pins that org_import.go's INSERT INTO workspaces
// uses the TOCTOU-safe ON CONFLICT DO NOTHING pattern.
//
// Per memory feedback_behavior_based_ast_gates.md: pin the behavior
// (idempotency check before INSERT), not just function names. If a
// future refactor reintroduces the un-checked INSERT (the original
// bug shape that leaked 72 workspaces in 4 days), this test fails.
// (atomic conflict resolution at the DB), not just function names.
// If a future refactor reintroduces the un-checked INSERT (the original
// bug shape that leaked 72 workspaces in 4 days at tenant-hongming),
// this test fails BEFORE the broken code reaches production where the
// race window opens.
//
// AST-walk implementation closes the silent-false-pass mode that the
// previous bytes.Index gate had — see workspacesInsertRE comment for
// the failure mode (workspaces_audit / workspace_secrets / etc.
// shadowing the real target via prefix match).
func TestCreateWorkspaceTree_CallsLookupBeforeInsert(t *testing.T) {
// Replaces an earlier "lookup-before-insert" gate that became obsolete
// when this swap moved idempotency into the database. The earlier
// gate would silent-false-pass against ON CONFLICT — even though that
// shape is correct — because lookupExistingChild now runs AFTER the
// INSERT (only on the skip path, to retrieve the existing id).
func TestCreateWorkspaceTree_InsertUsesOnConflictDoNothing(t *testing.T) {
wd, err := os.Getwd()
if err != nil {
t.Fatalf("getwd: %v", err)
@@ -230,30 +267,24 @@ func TestCreateWorkspaceTree_CallsLookupBeforeInsert(t *testing.T) {
if err != nil {
t.Fatalf("read org_import.go: %v", err)
}
lookupPos, insertPos, fset := findLookupAndWorkspacesInsertPos(t, "org_import.go", src)
if lookupPos == token.NoPos {
t.Fatalf("AST: no call to lookupExistingChild in org_import.go — idempotency check removed?")
}
if insertPos == token.NoPos {
insertSQL := findWorkspacesInsertSQL(t, "org_import.go", src)
if insertSQL == "" {
t.Fatalf("AST: no SQL literal matching `^\\s*INSERT INTO workspaces\\s*\\(` in any CallExpr in org_import.go — schema change or rename?")
}
if lookupPos > insertPos {
t.Errorf("lookupExistingChild call at %s must come BEFORE INSERT INTO workspaces at %s — non-idempotent ordering would re-leak under repeat /org/import calls",
fset.Position(lookupPos), fset.Position(insertPos))
if !onConflictDoNothingRE.MatchString(insertSQL) {
t.Errorf("workspaces INSERT SQL does NOT use the TOCTOU-safe ON CONFLICT shape — concurrent /org/import POSTs will silently double-insert. Required pattern:\n ON CONFLICT (COALESCE(parent_id, '00000000-...'::uuid), name) WHERE status != 'removed' DO NOTHING\n\nActual SQL:\n%s", insertSQL)
}
}
// TestGate_FailsWhenLookupAfterInsert proves the gate actually catches
// the bug it's named after — running it against synthetic Go source
// where the lookup call is positioned AFTER the workspaces INSERT must
// produce lookupPos > insertPos, which the production gate flags as
// an ERROR. Without this test the gate could regress to "always pass"
// and we wouldn't notice until the bug shipped again.
// TestGate_FailsWhenInsertOmitsOnConflict proves the gate actually
// catches the bug it's named after — running it against synthetic Go
// source where the workspaces INSERT lacks the ON CONFLICT clause must
// fail the regex match. Without this test the gate could regress to
// "always pass" and the TOCTOU window would silently reopen.
//
// Per memory feedback_assert_exact_not_substring.md: verify a
// tightened test FAILS on old code before merging.
func TestGate_FailsWhenLookupAfterInsert(t *testing.T) {
// Per memory feedback_assert_exact_not_substring.md: verify the
// tightened test FAILS on the bug shape before merging.
func TestGate_FailsWhenInsertOmitsOnConflict(t *testing.T) {
const buggySrc = `package handlers
import "context"
@@ -264,26 +295,57 @@ func (fakeDB) ExecContext(ctx context.Context, sql string, args ...interface{})
type fakeOrgHandler struct{}
func (h *fakeOrgHandler) lookupExistingChild(ctx context.Context, name string, parentID *string) (string, bool, error) {
return "", false, nil
}
func buggyCreate(h *fakeOrgHandler, db fakeDB, ctx context.Context, name string, parentID *string) {
// Bug shape: INSERT runs FIRST, lookup runs AFTER. This is the
// non-idempotent ordering the gate exists to forbid.
// Bug shape: bare INSERT, no ON CONFLICT. Two concurrent calls
// race past the unique-index check before either completes the
// transaction; constraint failure surfaces as a 500 to the
// caller (not graceful skip). Pre-#2872 this would silently
// duplicate-insert.
db.ExecContext(ctx, ` + "`INSERT INTO workspaces (id, name) VALUES ($1, $2)`" + `, "x", name)
h.lookupExistingChild(ctx, name, parentID)
}
`
lookupPos, insertPos, _ := findLookupAndWorkspacesInsertPos(t, "buggy.go", []byte(buggySrc))
if lookupPos == token.NoPos || insertPos == token.NoPos {
t.Fatalf("synthetic buggy source missing expected nodes (lookupPos=%v insertPos=%v) — helper logic regression", lookupPos, insertPos)
insertSQL := findWorkspacesInsertSQL(t, "buggy.go", []byte(buggySrc))
if insertSQL == "" {
t.Fatalf("synthetic buggy source missing workspaces INSERT — helper logic regression")
}
if lookupPos < insertPos {
t.Fatalf("synthetic bug shape (lookup AFTER insert) returned lookupPos=%d < insertPos=%d — gate would NOT fire on actual bug, regression!", lookupPos, insertPos)
if onConflictDoNothingRE.MatchString(insertSQL) {
t.Fatalf("synthetic bug shape (bare INSERT, no ON CONFLICT) was MATCHED by the gate — regression: gate would not flag the actual bug. SQL:\n%s", insertSQL)
}
// Implicit: lookupPos > insertPos here, which the production gate
// flags via t.Errorf. This proves the gate is live, not vestigial.
}
// findWorkspacesInsertSQL walks `src` and returns the unquoted SQL of
// the first string literal matching workspacesInsertRE inside any
// CallExpr's argument list. Returns "" if none found. Helper for the
// ON CONFLICT gate above.
func findWorkspacesInsertSQL(t *testing.T, fname string, src []byte) string {
t.Helper()
fset := token.NewFileSet()
file, err := parser.ParseFile(fset, fname, src, parser.ParseComments)
if err != nil {
t.Fatalf("parse %s: %v", fname, err)
}
var sql string
ast.Inspect(file, func(n ast.Node) bool {
call, ok := n.(*ast.CallExpr)
if !ok {
return true
}
for _, arg := range call.Args {
lit, ok := arg.(*ast.BasicLit)
if !ok || lit.Kind != token.STRING {
continue
}
raw := lit.Value
if unq, err := strconv.Unquote(raw); err == nil {
raw = unq
}
if workspacesInsertRE.MatchString(raw) && sql == "" {
sql = raw
}
}
return true
})
return sql
}
// TestGate_IgnoresAuditTableShadow proves the regex tightening
@@ -451,6 +451,201 @@ func TestIntegration_PendingUploads_AckedIndexExists(t *testing.T) {
}
}
// TestIntegration_PollUpload_AtomicRollback_AcrossBothTables proves the
// #149 cross-table contract at the database layer: when PutBatchTx and
// LogActivityTx run in the same caller-owned Tx and an activity INSERT
// fails after some rows have already been INSERTed, Rollback unwinds
// BOTH tables, leaving zero rows.
//
// Coverage map (#149):
// - chat_files_poll_test.go's TestPollUpload_AtomicRollbackOnActivityInsertFailure
// uses sqlmock to prove the Go handler issues Begin / N inserts /
// Rollback in the right order (no Commit on failure path).
// - This integration test proves the helpers + real Postgres compose
// correctly: rollback after a mid-Tx activity insert failure
// actually reverts BOTH the prior activity row AND the
// pending_uploads rows from PutBatchTx.
// - The pre-existing TestIntegration_PendingUploads_PutBatch_AtomicRollback
// covers the pending_uploads-only case.
//
// Failure injection: a NUL byte in `summary` (TEXT column) — lib/pq
// rejects it at the protocol layer. Same trick the existing PutBatch
// AtomicRollback test uses for the pending_uploads INSERT.
func TestIntegration_PollUpload_AtomicRollback_AcrossBothTables(t *testing.T) {
conn := integrationDB_PendingUploads(t)
ctx := context.Background()
// activity_logs has a FK to workspaces(id) — seed a real row so
// non-failing inserts succeed. Wipe activity_logs + this workspaces
// row at end so the next test sees a clean slate (the integrationDB
// helper only wipes pending_uploads).
wsID := uuid.New()
if _, err := conn.ExecContext(ctx,
`INSERT INTO workspaces (id, name) VALUES ($1, 'test-149-rollback')`, wsID,
); err != nil {
t.Fatalf("seed workspace: %v", err)
}
t.Cleanup(func() {
// CASCADE on workspaces FK deletes the activity_logs rows; explicit
// DELETE on activity_logs catches any rows that somehow leaked.
_, _ = conn.ExecContext(context.Background(), `DELETE FROM activity_logs WHERE workspace_id = $1`, wsID)
_, _ = conn.ExecContext(context.Background(), `DELETE FROM workspaces WHERE id = $1`, wsID)
})
store := pendinguploads.NewPostgres(conn)
// Mirror uploadPollMode's Tx shape: BeginTx → PutBatchTx → N ×
// LogActivityTx → Commit (or Rollback on failure).
tx, err := conn.BeginTx(ctx, nil)
if err != nil {
t.Fatalf("BeginTx: %v", err)
}
items := []pendinguploads.PutItem{
{Content: []byte("first"), Filename: "a.txt", Mimetype: "text/plain"},
{Content: []byte("second"), Filename: "b.txt", Mimetype: "text/plain"},
}
fileIDs, err := store.PutBatchTx(ctx, tx, wsID, items)
if err != nil {
t.Fatalf("PutBatchTx: %v", err)
}
if len(fileIDs) != 2 {
t.Fatalf("len(fileIDs) = %d, want 2", len(fileIDs))
}
// First activity insert succeeds — would commit if not for the
// rollback that the second insert's failure forces.
wsIDStr := wsID.String()
method := "chat_upload_receive"
okSummary := "chat_upload_receive: a.txt"
if _, err := LogActivityTx(ctx, tx, nil, ActivityParams{
WorkspaceID: wsIDStr,
ActivityType: "a2a_receive",
TargetID: &wsIDStr,
Method: &method,
Summary: &okSummary,
Status: "ok",
}); err != nil {
t.Fatalf("first LogActivityTx (should succeed): %v", err)
}
// Second activity insert: NUL byte in summary triggers lib/pq
// "invalid byte sequence for encoding UTF8: 0x00" — the canonical
// "DB-side error after some Tx work has already happened" we want.
badSummary := "chat_upload_receive: b\x00.txt"
_, err = LogActivityTx(ctx, tx, nil, ActivityParams{
WorkspaceID: wsIDStr,
ActivityType: "a2a_receive",
TargetID: &wsIDStr,
Method: &method,
Summary: &badSummary,
Status: "ok",
})
if err == nil {
t.Fatal("expected error from NUL-byte summary, got nil")
}
// Caller (uploadPollMode in production) rolls back on the error.
if rbErr := tx.Rollback(); rbErr != nil {
t.Fatalf("Rollback: %v", rbErr)
}
// THE assertion this test exists for: BOTH tables must have zero
// rows for this workspace. Pre-#149 the activity_logs row from the
// first insert would persist (separate fire-and-forget INSERT) and
// pending_uploads would also persist (committed by PutBatch's own
// Tx). Post-#149 the shared Tx + Rollback unwinds both.
var puCount, alCount int
if err := conn.QueryRowContext(ctx,
`SELECT COUNT(*) FROM pending_uploads WHERE workspace_id = $1`, wsID,
).Scan(&puCount); err != nil {
t.Fatalf("count pending_uploads: %v", err)
}
if err := conn.QueryRowContext(ctx,
`SELECT COUNT(*) FROM activity_logs WHERE workspace_id = $1`, wsID,
).Scan(&alCount); err != nil {
t.Fatalf("count activity_logs: %v", err)
}
if puCount != 0 {
t.Errorf("pending_uploads leaked %d row(s) after Rollback — #149 regression", puCount)
}
if alCount != 0 {
t.Errorf("activity_logs leaked %d row(s) after Rollback — #149 regression "+
"(THIS is the scenario the ticket called out: pre-fix, the first activity row "+
"committed in its own implicit Tx, leaving an orphan)", alCount)
}
}
// TestIntegration_PollUpload_HappyPath_AcrossBothTables is the positive
// counterpart to the rollback test: when nothing fails, both tables
// commit together and the row counts match.
func TestIntegration_PollUpload_HappyPath_AcrossBothTables(t *testing.T) {
conn := integrationDB_PendingUploads(t)
ctx := context.Background()
wsID := uuid.New()
if _, err := conn.ExecContext(ctx,
`INSERT INTO workspaces (id, name) VALUES ($1, 'test-149-happy')`, wsID,
); err != nil {
t.Fatalf("seed workspace: %v", err)
}
t.Cleanup(func() {
_, _ = conn.ExecContext(context.Background(), `DELETE FROM activity_logs WHERE workspace_id = $1`, wsID)
_, _ = conn.ExecContext(context.Background(), `DELETE FROM workspaces WHERE id = $1`, wsID)
})
store := pendinguploads.NewPostgres(conn)
tx, err := conn.BeginTx(ctx, nil)
if err != nil {
t.Fatalf("BeginTx: %v", err)
}
items := []pendinguploads.PutItem{
{Content: []byte("a"), Filename: "a.txt", Mimetype: "text/plain"},
{Content: []byte("b"), Filename: "b.txt", Mimetype: "text/plain"},
{Content: []byte("c"), Filename: "c.txt", Mimetype: "text/plain"},
}
if _, err := store.PutBatchTx(ctx, tx, wsID, items); err != nil {
t.Fatalf("PutBatchTx: %v", err)
}
wsIDStr := wsID.String()
method := "chat_upload_receive"
for _, it := range items {
summary := "chat_upload_receive: " + it.Filename
if _, err := LogActivityTx(ctx, tx, nil, ActivityParams{
WorkspaceID: wsIDStr,
ActivityType: "a2a_receive",
TargetID: &wsIDStr,
Method: &method,
Summary: &summary,
Status: "ok",
}); err != nil {
t.Fatalf("LogActivityTx %q: %v", it.Filename, err)
}
}
if err := tx.Commit(); err != nil {
t.Fatalf("Commit: %v", err)
}
var puCount, alCount int
if err := conn.QueryRowContext(ctx,
`SELECT COUNT(*) FROM pending_uploads WHERE workspace_id = $1`, wsID,
).Scan(&puCount); err != nil {
t.Fatalf("count pending_uploads: %v", err)
}
if err := conn.QueryRowContext(ctx,
`SELECT COUNT(*) FROM activity_logs WHERE workspace_id = $1`, wsID,
).Scan(&alCount); err != nil {
t.Fatalf("count activity_logs: %v", err)
}
if puCount != 3 {
t.Errorf("pending_uploads count = %d, want 3", puCount)
}
if alCount != 3 {
t.Errorf("activity_logs count = %d, want 3", alCount)
}
}
func TestIntegration_PendingUploads_GetIgnoresExpiredAndAcked(t *testing.T) {
conn := integrationDB_PendingUploads(t)
store := pendinguploads.NewPostgres(conn)
@@ -2,6 +2,7 @@ package handlers_test
import (
"context"
"database/sql"
"encoding/json"
"errors"
"net/http"
@@ -84,6 +85,9 @@ func (f *fakeStorage) Sweep(_ context.Context, _ time.Duration) (pendinguploads.
func (f *fakeStorage) PutBatch(_ context.Context, _ uuid.UUID, _ []pendinguploads.PutItem) ([]uuid.UUID, error) {
return nil, nil
}
func (f *fakeStorage) PutBatchTx(_ context.Context, _ *sql.Tx, _ uuid.UUID, _ []pendinguploads.PutItem) ([]uuid.UUID, error) {
return nil, nil
}
func newRouter(handler *handlers.PendingUploadsHandler) *gin.Engine {
gin.SetMode(gin.TestMode)
+33 -6
View File
@@ -4,6 +4,7 @@ import (
"bytes"
"context"
"io"
"log"
"os"
"path/filepath"
"strings"
@@ -177,16 +178,42 @@ func strDefault(m map[string]interface{}, key, fallback string) string {
return fallback
}
// findRunningContainer returns the live container name for workspaceID, or ""
// when the container is genuinely not running OR the daemon errored
// transiently. Routed through provisioner.RunningContainerName as the SSOT
// (molecule-core#10) so this handler agrees with healthsweep on the same
// inputs. Transient daemon errors are logged distinctly so triage doesn't
// confuse a flaky daemon with a stopped container.
func (h *PluginsHandler) findRunningContainer(ctx context.Context, workspaceID string) string {
if h.docker == nil {
name, err := provisioner.RunningContainerName(ctx, h.docker, workspaceID)
if err != nil {
log.Printf("plugins: docker inspect transient error for %s: %v (treating as not-running for this request)", workspaceID, err)
return ""
}
name := provisioner.ContainerName(workspaceID)
info, err := h.docker.ContainerInspect(ctx, name)
if err == nil && info.State.Running {
return name
return name
}
// isExternalRuntime reports whether the workspace's runtime is the
// `external` (remote-pull) shape introduced in Phase 30. External
// workspaces have no local container — `POST /plugins` (push-install via
// docker exec) doesn't apply to them; they pull via the download endpoint
// instead. Returns false (allow-install) if the lookup is unwired or
// errors — failing open here is safe because the downstream
// findRunningContainer step still gates on a real container being there.
//
// Background — molecule-core#10: without this check, external workspaces
// fall through to findRunningContainer's NotFound path and return a
// misleading 503 "container not running" instead of a clear "use the
// pull endpoint" message.
func (h *PluginsHandler) isExternalRuntime(workspaceID string) bool {
if h.runtimeLookup == nil {
return false
}
return ""
runtime, err := h.runtimeLookup(workspaceID)
if err != nil {
return false
}
return runtime == "external"
}
func (h *PluginsHandler) execAsRoot(ctx context.Context, containerName string, cmd []string) (string, error) {
@@ -0,0 +1,176 @@
package handlers
import (
"go/ast"
"go/parser"
"go/token"
"strings"
"testing"
)
// TestFindRunningContainer_RoutesThroughProvisionerSSOT is a behavior-based
// AST gate: it pins the invariant that PluginsHandler.findRunningContainer
// MUST go through provisioner.RunningContainerName for its is-running check,
// instead of carrying its own copy of cli.ContainerInspect logic.
//
// Background — molecule-core#10: a parallel impl of "is the workspace's
// container running" used to live in plugins.go. It drifted from the
// canonical impl in healthsweep (which goes through Provisioner.IsRunning
// → RunningContainerName) on edge cases like "transient daemon error" —
// the duplicate would 503 with a misleading message while healthsweep
// correctly stayed defensive. Consolidating onto RunningContainerName as
// the SSOT prevents any future copy from re-introducing that drift.
//
// Mutation invariant: if a future PR replaces the provisioner call with
// `h.docker.ContainerInspect(...)` directly, this test fails. That's the
// signal to either (a) extend RunningContainerName's contract OR (b)
// document why this call site needs to differ. Either way: the drift
// gets a reviewer's attention instead of shipping silently.
func TestFindRunningContainer_RoutesThroughProvisionerSSOT(t *testing.T) {
fset := token.NewFileSet()
file, err := parser.ParseFile(fset, "plugins.go", nil, parser.ParseComments)
if err != nil {
t.Fatalf("parse plugins.go: %v", err)
}
var fn *ast.FuncDecl
ast.Inspect(file, func(n ast.Node) bool {
f, ok := n.(*ast.FuncDecl)
if !ok || f.Name.Name != "findRunningContainer" {
return true
}
// Confirm receiver is *PluginsHandler so we don't pick up an unrelated
// helper of the same name. ast.Recv is a FieldList — receivers carry
// at most one field.
if f.Recv == nil || len(f.Recv.List) == 0 {
return true
}
fn = f
return false
})
if fn == nil {
t.Fatal("findRunningContainer not found in plugins.go — was it renamed? update this test or the SSOT routing assumption")
}
var (
callsRunningContainerName bool
callsContainerInspectRaw bool
)
ast.Inspect(fn.Body, func(n ast.Node) bool {
call, ok := n.(*ast.CallExpr)
if !ok {
return true
}
sel, ok := call.Fun.(*ast.SelectorExpr)
if !ok {
return true
}
// Pkg.Func form: provisioner.RunningContainerName(...)
if pkgIdent, ok := sel.X.(*ast.Ident); ok {
if pkgIdent.Name == "provisioner" && sel.Sel.Name == "RunningContainerName" {
callsRunningContainerName = true
}
}
// Receiver-then-method form: h.docker.ContainerInspect(...) /
// p.cli.ContainerInspect(...) — anything ending in
// .ContainerInspect that's NOT routed through provisioner.
if sel.Sel.Name == "ContainerInspect" {
callsContainerInspectRaw = true
}
return true
})
if !callsRunningContainerName {
t.Errorf(
"findRunningContainer must call provisioner.RunningContainerName for the SSOT inspect — see molecule-core#10. Found no such call.",
)
}
if callsContainerInspectRaw {
t.Errorf(
"findRunningContainer carries a direct ContainerInspect call. This is the parallel-impl drift molecule-core#10 fixed. " +
"Either route through provisioner.RunningContainerName OR — if a new use case truly needs a different inspect — extend RunningContainerName's contract first and update this gate to allow the specific delta.",
)
}
}
// TestProvisionerIsRunning_RoutesThroughRunningContainerName mirrors the
// gate above but for the OTHER consumer of the SSOT — Provisioner.IsRunning
// (called by healthsweep). If a future refactor makes IsRunning carry its
// own ContainerInspect again, the two consumers' edge-case behaviors will
// silently drift. Keep them yoked.
func TestProvisionerIsRunning_RoutesThroughRunningContainerName(t *testing.T) {
fset := token.NewFileSet()
file, err := parser.ParseFile(fset, "../provisioner/provisioner.go", nil, parser.ParseComments)
if err != nil {
t.Fatalf("parse provisioner.go: %v", err)
}
var fn *ast.FuncDecl
ast.Inspect(file, func(n ast.Node) bool {
f, ok := n.(*ast.FuncDecl)
if !ok || f.Name.Name != "IsRunning" || f.Recv == nil {
return true
}
// The receiver type must be *Provisioner specifically. CPProvisioner
// has its own IsRunning that talks HTTP to the controlplane and is
// out of scope for this gate.
if !receiverIs(f, "Provisioner") {
return true
}
fn = f
return false
})
if fn == nil {
t.Fatal("Provisioner.IsRunning not found — was it renamed? update this test")
}
var (
callsRunningContainerName bool
callsContainerInspectRaw bool
)
ast.Inspect(fn.Body, func(n ast.Node) bool {
call, ok := n.(*ast.CallExpr)
if !ok {
return true
}
// Same-package call: bare identifier (e.g. RunningContainerName(...)).
if id, ok := call.Fun.(*ast.Ident); ok && id.Name == "RunningContainerName" {
callsRunningContainerName = true
return true
}
// Selector call: pkg.Func (e.g. provisioner.RunningContainerName)
// OR recv.Method (e.g. p.cli.ContainerInspect).
sel, ok := call.Fun.(*ast.SelectorExpr)
if !ok {
return true
}
switch sel.Sel.Name {
case "RunningContainerName":
callsRunningContainerName = true
case "ContainerInspect":
callsContainerInspectRaw = true
}
return true
})
if !callsRunningContainerName {
t.Errorf("Provisioner.IsRunning must call RunningContainerName for the SSOT inspect — see molecule-core#10")
}
if callsContainerInspectRaw {
t.Errorf("Provisioner.IsRunning carries a direct ContainerInspect call; route through RunningContainerName instead")
}
}
// receiverIs reports whether fn's receiver is `*<typeName>` or `<typeName>`.
func receiverIs(fn *ast.FuncDecl, typeName string) bool {
if fn.Recv == nil || len(fn.Recv.List) == 0 {
return false
}
expr := fn.Recv.List[0].Type
if star, ok := expr.(*ast.StarExpr); ok {
expr = star.X
}
id, ok := expr.(*ast.Ident)
return ok && strings.EqualFold(id.Name, typeName)
}
@@ -32,6 +32,18 @@ import (
// inside the workspace at startup.
func (h *PluginsHandler) Install(c *gin.Context) {
workspaceID := c.Param("id")
// External-runtime guard (molecule-core#10): push-install via docker
// exec is meaningless for `runtime='external'` workspaces — they have
// no local container. Reject early with a hint pointing at the
// pull-mode endpoint, instead of falling through to a misleading
// "container not running" 503 from findRunningContainer.
if h.isExternalRuntime(workspaceID) {
c.JSON(http.StatusUnprocessableEntity, gin.H{
"error": "plugin install via push is not supported for external runtimes",
"hint": "external workspaces pull plugins via GET /workspaces/:id/plugins/:name/download",
})
return
}
// Cap the JSON body so a pathological POST can't exhaust parser memory.
bodyMax := envx.Int64("PLUGIN_INSTALL_BODY_MAX_BYTES", defaultInstallBodyMaxBytes)
c.Request.Body = http.MaxBytesReader(c.Writer, c.Request.Body, bodyMax)
@@ -93,6 +105,16 @@ func (h *PluginsHandler) Uninstall(c *gin.Context) {
pluginName := c.Param("name")
ctx := c.Request.Context()
// Mirror Install's external-runtime guard (molecule-core#10) so the
// two endpoints reject the same shape with the same message.
if h.isExternalRuntime(workspaceID) {
c.JSON(http.StatusUnprocessableEntity, gin.H{
"error": "plugin uninstall via docker exec is not supported for external runtimes",
"hint": "external workspaces manage their own plugin directory; remove it locally",
})
return
}
if err := validatePluginName(pluginName); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid plugin name"})
return
@@ -0,0 +1,176 @@
package handlers
import (
"bytes"
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/gin-gonic/gin"
)
// TestPluginInstall_ExternalRuntime_Returns422 — molecule-core#10.
// Install on a `runtime='external'` workspace must NOT fall through to
// findRunningContainer (which would 503 with a misleading "container not
// running"). It must return 422 with a hint pointing at the pull-mode
// download endpoint.
func TestPluginInstall_ExternalRuntime_Returns422(t *testing.T) {
h := NewPluginsHandler(t.TempDir(), nil, nil).
WithRuntimeLookup(func(workspaceID string) (string, error) {
return "external", nil
})
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ba1789b0-4d21-4f4f-a878-fa226bf77cf5"}}
c.Request = httptest.NewRequest(
"POST",
"/workspaces/ba1789b0-4d21-4f4f-a878-fa226bf77cf5/plugins",
bytes.NewBufferString(`{"source":"local://my-plugin"}`),
)
c.Request.Header.Set("Content-Type", "application/json")
h.Install(c)
if w.Code != http.StatusUnprocessableEntity {
t.Errorf("expected 422 (Unprocessable Entity) for runtime='external', got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "external runtimes") {
t.Errorf("expected error body to mention 'external runtimes', got: %s", w.Body.String())
}
if !strings.Contains(w.Body.String(), "download") {
t.Errorf("expected error body to point at the download endpoint, got: %s", w.Body.String())
}
}
// TestPluginUninstall_ExternalRuntime_Returns422 — symmetric guard on the
// uninstall path (DELETE /workspaces/:id/plugins/:name). External
// workspaces manage their own plugin directory locally; the platform
// can't docker-exec into them.
func TestPluginUninstall_ExternalRuntime_Returns422(t *testing.T) {
h := NewPluginsHandler(t.TempDir(), nil, nil).
WithRuntimeLookup(func(workspaceID string) (string, error) {
return "external", nil
})
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ba1789b0-4d21-4f4f-a878-fa226bf77cf5"},
{Key: "name", Value: "my-plugin"},
}
c.Request = httptest.NewRequest(
"DELETE",
"/workspaces/ba1789b0-4d21-4f4f-a878-fa226bf77cf5/plugins/my-plugin",
nil,
)
h.Uninstall(c)
if w.Code != http.StatusUnprocessableEntity {
t.Errorf("expected 422 for runtime='external', got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "external runtimes") {
t.Errorf("expected error body to mention 'external runtimes', got: %s", w.Body.String())
}
}
// TestPluginInstall_ContainerBackedRuntime_FallsThroughGuard — the runtime
// guard MUST NOT short-circuit container-backed runtimes. With
// `runtime='claude-code'` the install proceeds past the guard; without a
// real plugin source it'll fail downstream (here: 404 from local resolver
// because no plugin staged), which is the correct error to surface.
//
// This is the mutation-test partner: deleting the `runtime == "external"`
// check would still pass TestPluginInstall_ExternalRuntime (because Install
// would 404 instead of 422 — but the test asserts 422), and would still
// pass this test (because both pre-fix and post-fix produce 404 here).
// What this case pins is "non-external still falls through," catching
// any over-eager guard that rejects all runtimes.
func TestPluginInstall_ContainerBackedRuntime_FallsThroughGuard(t *testing.T) {
h := NewPluginsHandler(t.TempDir(), nil, nil).
WithRuntimeLookup(func(workspaceID string) (string, error) {
return "claude-code", nil
})
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "c7c28c0b-4ea5-4e75-9728-3ba860081708"}}
c.Request = httptest.NewRequest(
"POST",
"/workspaces/c7c28c0b-4ea5-4e75-9728-3ba860081708/plugins",
bytes.NewBufferString(`{"source":"local://nonexistent-plugin"}`),
)
c.Request.Header.Set("Content-Type", "application/json")
h.Install(c)
if w.Code == http.StatusUnprocessableEntity {
t.Errorf("runtime='claude-code' must fall through the external guard; got 422: %s", w.Body.String())
}
// The local resolver will fail to find the plugin → 404. Anything
// other than 422 (which would mean we mis-classified) is fine.
if w.Code != http.StatusNotFound {
t.Errorf("expected 404 (plugin not found in registry), got %d: %s", w.Code, w.Body.String())
}
}
// TestPluginInstall_NoRuntimeLookup_FailsOpen — when the runtime lookup
// is unwired (test fixtures, niche deploy shapes) the guard MUST default
// to allowing the install attempt. The downstream findRunningContainer
// step still gates on a real container, so failing open here doesn't
// expose a bypass — it just preserves backwards-compat with deployments
// that haven't wired the lookup.
func TestPluginInstall_NoRuntimeLookup_FailsOpen(t *testing.T) {
h := NewPluginsHandler(t.TempDir(), nil, nil) // NO WithRuntimeLookup
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-no-lookup"}}
c.Request = httptest.NewRequest(
"POST",
"/workspaces/ws-no-lookup/plugins",
bytes.NewBufferString(`{"source":"local://nonexistent"}`),
)
c.Request.Header.Set("Content-Type", "application/json")
h.Install(c)
if w.Code == http.StatusUnprocessableEntity {
t.Errorf("nil runtimeLookup must fall through (fail-open); got 422: %s", w.Body.String())
}
}
// TestPluginInstall_RuntimeLookupErrors_FailsOpen — same fail-open story
// for transient DB errors in the lookup. We don't want a momentary
// Postgres hiccup to flip every plugin install into a 422.
func TestPluginInstall_RuntimeLookupErrors_FailsOpen(t *testing.T) {
h := NewPluginsHandler(t.TempDir(), nil, nil).
WithRuntimeLookup(func(workspaceID string) (string, error) {
return "", errFakeDB
})
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-db-flake"}}
c.Request = httptest.NewRequest(
"POST",
"/workspaces/ws-db-flake/plugins",
bytes.NewBufferString(`{"source":"local://nonexistent"}`),
)
c.Request.Header.Set("Content-Type", "application/json")
h.Install(c)
if w.Code == http.StatusUnprocessableEntity {
t.Errorf("runtimeLookup error must fall through (fail-open); got 422: %s", w.Body.String())
}
}
// errFakeDB is a sentinel for the fail-open lookup-error case.
var errFakeDB = &fakeError{msg: "synthetic db error"}
type fakeError struct{ msg string }
func (e *fakeError) Error() string { return e.msg }
+10 -10
View File
@@ -414,7 +414,7 @@ func (h *RegistryHandler) Register(c *gin.Context) {
}
// Broadcast WORKSPACE_ONLINE
if err := h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", payload.ID, map[string]interface{}{
if err := h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.ID, map[string]interface{}{
"url": cachedURL,
"agent_card": payload.AgentCard,
"delivery_mode": effectiveMode,
@@ -572,7 +572,7 @@ func (h *RegistryHandler) Heartbeat(c *gin.Context) {
// Broadcast current task update only when it changed (avoid spamming on every heartbeat)
if payload.CurrentTask != prevTask {
h.broadcaster.BroadcastOnly(payload.WorkspaceID, "TASK_UPDATED", map[string]interface{}{
h.broadcaster.BroadcastOnly(payload.WorkspaceID, string(events.EventTaskUpdated), map[string]interface{}{
"current_task": payload.CurrentTask,
"active_tasks": payload.ActiveTasks,
})
@@ -593,7 +593,7 @@ func (h *RegistryHandler) Heartbeat(c *gin.Context) {
// so per-heartbeat cost is one in-memory channel send per active
// SSE subscriber and one WS hub fan-out. At 30s heartbeat cadence
// this is far below any noise floor on either path.
h.broadcaster.BroadcastOnly(payload.WorkspaceID, "WORKSPACE_HEARTBEAT", map[string]interface{}{
h.broadcaster.BroadcastOnly(payload.WorkspaceID, string(events.EventWorkspaceHeartbeat), map[string]interface{}{
"active_tasks": payload.ActiveTasks,
"uptime_seconds": payload.UptimeSeconds,
})
@@ -678,7 +678,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
if err != nil {
log.Printf("Heartbeat: failed to mark %s degraded (wedged): %v", payload.WorkspaceID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_DEGRADED", payload.WorkspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceDegraded), payload.WorkspaceID, map[string]interface{}{
"runtime_state": "wedged",
"sample_error": payload.SampleError,
})
@@ -699,7 +699,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
if _, err := db.DB.ExecContext(ctx, `UPDATE workspaces SET status = $1, updated_at = now() WHERE id = $2`, models.StatusDegraded, payload.WorkspaceID); err != nil {
log.Printf("Heartbeat: failed to mark %s degraded: %v", payload.WorkspaceID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_DEGRADED", payload.WorkspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceDegraded), payload.WorkspaceID, map[string]interface{}{
"error_rate": payload.ErrorRate,
"sample_error": payload.SampleError,
})
@@ -718,7 +718,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
if _, err := db.DB.ExecContext(ctx, `UPDATE workspaces SET status = $1, updated_at = now() WHERE id = $2`, models.StatusOnline, payload.WorkspaceID); err != nil {
log.Printf("Heartbeat: failed to recover %s to online: %v", payload.WorkspaceID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", payload.WorkspaceID, map[string]interface{}{})
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.WorkspaceID, map[string]interface{}{})
}
// Recovery: if workspace was offline but is now sending heartbeats, bring it back online.
@@ -728,7 +728,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
if _, err := db.DB.ExecContext(ctx, `UPDATE workspaces SET status = $1, updated_at = now() WHERE id = $2 AND status = 'offline'`, models.StatusOnline, payload.WorkspaceID); err != nil {
log.Printf("Heartbeat: failed to recover %s from offline: %v", payload.WorkspaceID, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", payload.WorkspaceID, map[string]interface{}{})
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.WorkspaceID, map[string]interface{}{})
}
// Auto-recovery: if a workspace is marked "provisioning" but is actively sending
@@ -743,7 +743,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
} else {
log.Printf("Heartbeat: transitioned %s from provisioning to online (heartbeat received)", payload.WorkspaceID)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", payload.WorkspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.WorkspaceID, map[string]interface{}{
"recovered_from": currentStatus,
})
}
@@ -771,7 +771,7 @@ func (h *RegistryHandler) evaluateStatus(c *gin.Context, payload models.Heartbea
} else {
log.Printf("Heartbeat: transitioned %s from awaiting_agent to online (heartbeat received)", payload.WorkspaceID)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", payload.WorkspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.WorkspaceID, map[string]interface{}{
"recovered_from": currentStatus,
})
}
@@ -820,7 +820,7 @@ func (h *RegistryHandler) UpdateCard(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(c.Request.Context(), "AGENT_CARD_UPDATED", payload.WorkspaceID, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(c.Request.Context(), string(events.EventAgentCardUpdated), payload.WorkspaceID, map[string]interface{}{
"agent_card": payload.AgentCard,
})
@@ -1,23 +1,20 @@
package handlers
// template_files_eic.go — SSH-backed file write for SaaS workspaces
// (EC2-per-workspace). Pairs with the existing Docker-path in templates.go
// (WriteFile) and template_import.go (ReplaceFiles).
// template_files_eic.go — SSH-backed file operations for SaaS workspaces
// (EC2-per-workspace). Pairs with the local-Docker path in templates.go
// (List/Read/Write/Delete) and template_import.go (ReplaceFiles).
//
// Flow for a single file write:
// 1. Generate ephemeral ed25519 keypair (on-disk for ≤ write duration).
// 2. Push the public key via `aws ec2-instance-connect send-ssh-public-key`
// so the target sshd accepts it for the next 60s.
// 3. Open a TLS-tunnelled TCP port via `aws ec2-instance-connect open-tunnel`
// from a local free port → workspace's sshd on 22.
// 4. Pipe content to `ssh ... "install -D -m 0644 /dev/stdin <abs path>"`.
// `install -D` creates any missing parent dirs atomically. File is owned
// by whichever $OSUser we authenticated as (ubuntu by default).
// 5. Close tunnel + wipe keydir.
// Architecture note: every operation goes through `withEICTunnel`, which
// owns the ephemeral-keypair → key-push → tunnel → port-wait dance. Per-
// op helpers (list/read/write/delete) only carry the remote command +
// stdin/stdout shape. This keeps the EIC connection logic in one place
// so a fix to the dance — e.g. PR #2822's `LogLevel=ERROR` shim — only
// touches one helper.
//
// All the AWS calls + ssh tunnel exec go through the same package-level
// func vars defined in terminal.go (openTunnelCmd, sendSSHPublicKey) so
// tests can stub them the same way the terminal tests do.
// Path translation rules: see resolveWorkspaceFilePath. `/configs`
// is the per-runtime managed-config indirection (claude-code → /configs,
// hermes → /home/ubuntu/.hermes); other allow-listed roots (`/home`,
// `/workspace`, `/plugins`) pass through literally.
import (
"bytes"
@@ -32,8 +29,7 @@ import (
)
// workspaceFilePathPrefix maps a runtime name to the absolute base path on
// the workspace EC2 where the Files API's relative paths land. New runtimes
// can be added here without touching handler code.
// the workspace EC2 where the runtime's managed-config dir lives.
//
// Keep these stable — changing the base path for an existing runtime
// without a migration shim will make previously-saved files disappear from
@@ -60,41 +56,104 @@ var workspaceFilePathPrefix = map[string]string{
// those runtimes actually have on disk.
}
func resolveWorkspaceFilePath(runtime, relPath string) (string, error) {
// resolveWorkspaceFilePath translates (runtime, root, relPath) into an
// absolute path on the workspace EC2.
//
// `root="/configs"` (or empty / unrecognized) is treated as the
// runtime's MANAGED-config dir via workspaceFilePathPrefix —
// /home/ubuntu/.hermes for hermes, /configs for claude-code, etc.
// This preserves the v1 ReadFile/WriteFile behavior where the canvas's
// Config tab GETs/PUTs "config.yaml" without specifying a root and
// lands in the runtime's own config dir, even though that dir's
// absolute path differs per runtime.
//
// Any other allow-listed root (`/home`, `/workspace`, `/plugins`) is
// treated as a LITERAL absolute path on the EC2 host. Those roots are
// universal Linux paths that don't need per-runtime indirection.
//
// Restricting the literal pass-through to allowedRoots is the
// security boundary — the handler also gates this same set, so the
// resolver is defence-in-depth: even if a future caller forgets the
// handler-side check, the resolver won't translate `?root=/etc` into
// a real absolute path.
//
// relPath is sanitised by validateRelPath (no absolute, no `..`).
func resolveWorkspaceFilePath(runtime, root, relPath string) (string, error) {
if err := validateRelPath(relPath); err != nil {
return "", err
}
base, ok := workspaceFilePathPrefix[strings.ToLower(strings.TrimSpace(runtime))]
if !ok {
base = "/configs"
}
base := resolveWorkspaceRootPath(runtime, root)
return filepath.Join(base, filepath.Clean(relPath)), nil
}
// eicFileWriteTimeout bounds the whole dance. Key push is <500ms, tunnel
// is 1-2s, ssh + write is <2s. 30s gives headroom for slow pulls without
// hanging the Files API forever under EIC misconfiguration.
const eicFileWriteTimeout = 30 * time.Second
// writeFileViaEIC writes a single file to the workspace EC2 at the
// absolute path that resolveWorkspaceFilePath computed. On success,
// optionally invokes the runtime's reload hook (not implemented yet —
// tracked as follow-up; for today the canvas issues a separate Restart
// after Save).
// resolveWorkspaceRootPath returns the absolute base directory on the
// workspace EC2 for a given (runtime, root) pair, without touching a
// relative file path. Used by listFilesViaEIC to compute the directory
// to walk; resolveWorkspaceFilePath joins this with relPath.
//
// instanceID: AWS EC2 instance id from workspaces.instance_id.
// runtime: used only for path-prefix resolution.
// relPath: the relative path the caller validated (no /, no ..).
// content: file body bytes.
func writeFileViaEIC(ctx context.Context, instanceID, runtime, relPath string, content []byte) error {
// Centralising the runtime-vs-literal indirection here means
// list/read/write/delete agree on what `?root=/configs` means for
// hermes vs claude-code vs an unknown runtime — otherwise list could
// show one directory while read/write target another.
func resolveWorkspaceRootPath(runtime, root string) string {
root = strings.TrimSpace(root)
// "/configs" + empty + unrecognized → runtime's managed-config dir.
// The runtime prefix map is the SSOT for that translation.
if root == "" || root == "/configs" || !allowedRoots[root] {
base, ok := workspaceFilePathPrefix[strings.ToLower(strings.TrimSpace(runtime))]
if !ok {
base = "/configs"
}
return base
}
// Literal universal path (`/home`, `/workspace`, `/plugins`).
return root
}
// eicFileOpTimeout bounds the whole tunnel + ssh dance. Key push is
// <500ms, tunnel is 1-2s, ssh + remote command is <2s for read/write.
// 30s gives headroom for slow EIC pulls + the larger `find` walk that
// listFilesViaEIC issues, without hanging the Files API forever under
// EIC misconfiguration.
const eicFileOpTimeout = 30 * time.Second
// eicFileOpTimeout was historically named eicFileWriteTimeout when the
// only EIC op was writeFile. Keep an alias so any external test that
// pinned the old name still compiles; rename can land as a follow-up
// once we've gone a release without the alias being touched.
//
//nolint:revive // intentional alias for back-compat with prior tests.
const eicFileWriteTimeout = eicFileOpTimeout
// eicSSHSession describes an open EIC tunnel ready for an ssh subprocess.
// Only valid inside the closure passed to withEICTunnel — the underlying
// keypair + tunnel are torn down when the closure returns.
type eicSSHSession struct {
keyPath string
localPort int
osUser string
instanceID string
}
// withEICTunnel sets up an EIC SSH session (ephemeral keypair → push
// → AWS open-tunnel → wait-for-port), invokes fn with a session handle,
// and tears everything down on return. The caller is responsible for
// applying the per-op context.WithTimeout before calling — this helper
// only owns the EIC dance, not the operation budget, so a caller that
// needs a different timeout (e.g. a large bulk import) doesn't have to
// fight a hard-coded one.
//
// All AWS calls go through the package-level func vars in terminal.go
// (sendSSHPublicKey, openTunnelCmd) so tests can stub them the same way
// terminal_test.go does. The whole helper is also assigned to a
// `var` (`withEICTunnel`) so handler-dispatch tests can stub the entire
// dance instead of having to wire up a fake tunnel + fake ssh server.
var withEICTunnel = realWithEICTunnel
func realWithEICTunnel(ctx context.Context, instanceID string, fn func(s eicSSHSession) error) error {
if instanceID == "" {
return fmt.Errorf("workspace has no instance_id — not a SaaS EC2 workspace")
}
absPath, err := resolveWorkspaceFilePath(runtime, relPath)
if err != nil {
return fmt.Errorf("invalid path: %w", err)
}
osUser := os.Getenv("WORKSPACE_EC2_OS_USER")
if osUser == "" {
osUser = "ubuntu"
@@ -104,11 +163,7 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, relPath string, c
region = "us-east-2"
}
ctx, cancel := context.WithTimeout(ctx, eicFileWriteTimeout)
defer cancel()
// Ephemeral keypair.
keyDir, err := os.MkdirTemp("", "molecule-filewrite-*")
keyDir, err := os.MkdirTemp("", "molecule-eic-*")
if err != nil {
return fmt.Errorf("keydir mkdir: %w", err)
}
@@ -116,7 +171,7 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, relPath string, c
keyPath := keyDir + "/id"
if out, kerr := exec.CommandContext(ctx, "ssh-keygen",
"-t", "ed25519", "-f", keyPath, "-N", "", "-q",
"-C", "molecule-filewrite",
"-C", "molecule-eic",
).CombinedOutput(); kerr != nil {
return fmt.Errorf("ssh-keygen: %w (%s)", kerr, strings.TrimSpace(string(out)))
}
@@ -125,24 +180,21 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, relPath string, c
return fmt.Errorf("read pubkey: %w", err)
}
// 1. Push key.
if err := sendSSHPublicKey(ctx, region, instanceID, osUser, strings.TrimSpace(string(pubKey))); err != nil {
return fmt.Errorf("send-ssh-public-key: %w", err)
}
// 2. Open tunnel on an OS-picked free port.
localPort, err := pickFreePort()
if err != nil {
return fmt.Errorf("pick free port: %w", err)
}
opts := eicSSHOptions{
tunnel := openTunnelCmd(eicSSHOptions{
InstanceID: instanceID,
OSUser: osUser,
Region: region,
LocalPort: localPort,
PrivateKeyPath: keyPath,
}
tunnel := openTunnelCmd(opts)
})
tunnel.Env = os.Environ()
if err := tunnel.Start(); err != nil {
return fmt.Errorf("open-tunnel start: %w", err)
@@ -157,183 +209,330 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, relPath string, c
return fmt.Errorf("tunnel never listened: %w", err)
}
// 3. SSH + install -D. `install` creates any missing parent dirs and
// writes the file atomically via temp-file-rename. Permissions 0644
// match the existing tar-unpack defaults on the Docker path.
//
// `sudo -n` (non-interactive) prefix: the canonical containerized
// workspace layout puts /configs at the root, owned by root because
// cloud-init runs as root (see
// molecule-controlplane/internal/provisioner/userdata_containerized.go).
// SSH-as-ubuntu can't write into /configs without escalation.
// Ubuntu has passwordless sudo on EC2 by default; sudo -n fails fast
// (no prompt) if that ever changes, surfacing a clean error instead
// of a hang. The hermes path /home/ubuntu/.hermes is ubuntu-owned
// and doesn't strictly need sudo, but using it uniformly avoids
// per-runtime branching here.
//
// The remote command is fully deterministic — no user-controlled
// input reaches a shell eval (absPath is built from a map + Clean()).
sshArgs := []string{
"-i", keyPath,
return fn(eicSSHSession{
keyPath: keyPath,
localPort: localPort,
osUser: osUser,
instanceID: instanceID,
})
}
// sshArgs returns the standard ssh CLI args for an EIC session pointed
// at the local tunnel port + a single remote command string.
//
// `LogLevel=ERROR` silences the benign "Warning: Permanently added
// '[127.0.0.1]:NNNNN' to known hosts" notice that ssh emits on every
// fresh tunnel connection. Without this, the notice lands on stderr
// and fools the read/list "empty stdout + empty stderr → not found"
// classifiers into thinking the warning is a real ssh-layer error → 500
// instead of 404 (Hermes config.yaml load, hongming tenant, 2026-05-05
// 02:38; PR #2822). Real auth/tunnel errors stay visible because they're
// emitted at ERROR level.
//
// Originally each helper assembled its own ssh args inline, so PR #2822's
// LogLevel=ERROR fix had to be applied to every copy. Centralising here
// means future ssh-option tweaks only land in one place.
func (s eicSSHSession) sshArgs(remoteCommand string) []string {
return []string{
"-i", s.keyPath,
"-o", "StrictHostKeyChecking=no",
"-o", "UserKnownHostsFile=/dev/null",
// LogLevel=ERROR silences the benign "Warning: Permanently
// added '[127.0.0.1]:NNNNN' to known hosts" notice that ssh
// emits on every fresh tunnel connection. Without this, the
// notice lands on stderr and fools readFileViaEIC's "empty
// stdout + empty stderr → file not found" classifier into
// thinking the warning is a real ssh-layer error → 500
// instead of 404 (Hermes config.yaml load, hongming tenant,
// 2026-05-05 02:38). Real auth/tunnel errors stay visible
// because they're emitted at ERROR level.
"-o", "LogLevel=ERROR",
"-o", "ServerAliveInterval=15",
"-p", fmt.Sprintf("%d", localPort),
fmt.Sprintf("%s@127.0.0.1", osUser),
fmt.Sprintf("sudo -n install -D -m 0644 /dev/stdin %s", shellQuote(absPath)),
"-p", fmt.Sprintf("%d", s.localPort),
fmt.Sprintf("%s@127.0.0.1", s.osUser),
remoteCommand,
}
sshCmd := exec.CommandContext(ctx, "ssh", sshArgs...)
sshCmd.Env = os.Environ()
sshCmd.Stdin = bytes.NewReader(content)
var stderr bytes.Buffer
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
return fmt.Errorf("ssh install: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
// buildInstallShell returns the remote command for atomically writing
// `/dev/stdin` to absPath with mode 0644 via `sudo -n install -D`.
// `install -D` creates any missing parent dirs and writes via
// temp-file-rename (atomic). Pure function for direct testability —
// the only variable input (absPath) is shellQuote-wrapped to defeat
// any shell metachar in a future caller's path.
func buildInstallShell(absPath string) string {
return fmt.Sprintf("sudo -n install -D -m 0644 /dev/stdin %s", shellQuote(absPath))
}
// buildCatShell returns the remote command for reading absPath and
// swallowing missing-file stderr (so the empty-stdout + non-zero-exit
// case is unambiguous → os.ErrNotExist at the caller).
func buildCatShell(absPath string) string {
return fmt.Sprintf("sudo -n cat %s 2>/dev/null", shellQuote(absPath))
}
// buildRmShell returns the remote command for `sudo -n rm -f` against
// absPath. `-f` (not `-rf`) is intentional — directory removal needs
// its own explicit endpoint if/when the canvas grows that affordance,
// and `-rf` would let a misclassified directory entry trigger a
// recursive delete.
func buildRmShell(absPath string) string {
return fmt.Sprintf("sudo -n rm -f %s", shellQuote(absPath))
}
// buildFindShell returns the remote command for enumerating files
// under listPath up to maxDepth, emitting `TYPE|SIZE|REL_PATH` lines
// (matches the local-Docker container path's parser exactly).
//
// `2>/dev/null` swallows find's "No such file" error so a missing
// listing root surfaces as empty stdout (handler returns []) rather
// than 500.
//
// `stat -c %s` is GNU coreutils; `stat -f %z` is BSD. Try GNU first,
// fall back to BSD, then 0 — same shape the local-Docker `sh -c`
// version uses so a future cross-runtime fleet (Alpine vs Ubuntu)
// doesn't regress.
//
// Hidden / cache dir pruning matches the container path: .git,
// __pycache__, node_modules, .DS_Store. Without these the tree drowns
// in transient artefacts on a /workspace listing.
func buildFindShell(listPath string, maxDepth int) string {
return fmt.Sprintf(
`sudo -n find %s -maxdepth %d -not -path '*/.git/*' -not -path '*/__pycache__/*' -not -path '*/node_modules/*' -not -name .DS_Store 2>/dev/null | while IFS= read -r f; do `+
`rel="${f#%s/}"; [ "$rel" = %s ] && continue; [ -z "$rel" ] && continue; `+
`if [ -d "$f" ]; then echo "d|0|$rel"; else `+
`s=$(stat -c %%s "$f" 2>/dev/null || stat -f %%z "$f" 2>/dev/null || echo 0); echo "f|$s|$rel"; `+
`fi; done`,
shellQuote(listPath), maxDepth, shellQuote(listPath), shellQuote(listPath),
)
}
// parseFindOutput parses TYPE|SIZE|REL_PATH lines emitted by
// buildFindShell into eicFileEntry rows. Whitespace-only lines and
// malformed rows are silently skipped — the same behaviour as the
// local-Docker container parser for symmetric output.
func parseFindOutput(raw []byte) []eicFileEntry {
files := make([]eicFileEntry, 0)
for _, line := range strings.Split(string(raw), "\n") {
parts := strings.SplitN(line, "|", 3)
if len(parts) != 3 || parts[2] == "" {
continue
}
var size int64
fmt.Sscanf(parts[1], "%d", &size)
files = append(files, eicFileEntry{
Path: parts[2],
Size: size,
Dir: parts[0] == "d",
})
}
log.Printf("writeFileViaEIC: ws instance=%s runtime=%s wrote %d bytes → %s",
instanceID, runtime, len(content), absPath)
return nil
return files
}
// shellQuote wraps a value in single quotes + escapes embedded single
// quotes for POSIX sh. Used for the sole piece of variable data in the
// remote ssh command. (absPath is already built from a map + Clean() so
// traversal is blocked regardless; this is defence-in-depth against
// future refactor that might accept user paths here.)
// quotes for POSIX sh. Used for the variable parts of remote ssh
// commands (absolute paths). The paths are already built from a
// validated allowlist + Clean(), so traversal is blocked regardless;
// this is defence-in-depth against a future refactor that might accept
// user paths directly here.
func shellQuote(s string) string {
return "'" + strings.ReplaceAll(s, "'", `'\''`) + "'"
}
// writeFileViaEIC writes a single file to the workspace EC2 at the
// absolute path that resolveWorkspaceFilePath computed. On success,
// optionally invokes the runtime's reload hook (not implemented yet —
// tracked as follow-up; for today the canvas issues a separate Restart
// after Save).
//
// `install -D` creates any missing parent dirs and writes atomically
// via temp-file-rename. Permissions 0644 match the existing tar-unpack
// defaults on the Docker path.
//
// `sudo -n` (non-interactive) prefix: the canonical containerized
// workspace layout puts /configs at the root, owned by root because
// cloud-init runs as root (see
// molecule-controlplane/internal/provisioner/userdata_containerized.go).
// SSH-as-ubuntu can't write into /configs without escalation. Ubuntu
// has passwordless sudo on EC2 by default; sudo -n fails fast (no
// prompt) if that ever changes, surfacing a clean error instead of a
// hang. The hermes path /home/ubuntu/.hermes is ubuntu-owned and
// doesn't strictly need sudo, but using it uniformly avoids per-runtime
// branching here.
func writeFileViaEIC(ctx context.Context, instanceID, runtime, root, relPath string, content []byte) error {
absPath, err := resolveWorkspaceFilePath(runtime, root, relPath)
if err != nil {
return fmt.Errorf("invalid path: %w", err)
}
ctx, cancel := context.WithTimeout(ctx, eicFileOpTimeout)
defer cancel()
return withEICTunnel(ctx, instanceID, func(s eicSSHSession) error {
sshCmd := exec.CommandContext(ctx, "ssh", s.sshArgs(buildInstallShell(absPath))...)
sshCmd.Env = os.Environ()
sshCmd.Stdin = bytes.NewReader(content)
var stderr bytes.Buffer
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
return fmt.Errorf("ssh install: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
log.Printf("writeFileViaEIC: ws instance=%s runtime=%s root=%s wrote %d bytes → %s",
instanceID, runtime, root, len(content), absPath)
return nil
})
}
// readFileViaEIC reads a single file from the workspace EC2 at the
// absolute path that resolveWorkspaceFilePath computes. Mirrors
// writeFileViaEIC end-to-end (ephemeral keypair, EIC tunnel, ssh) so
// canvas's Config tab can GET back what it just PUT. Pre-fix the GET
// path (templates.go ReadFile) only handled local Docker containers
// + a host-side template fallback; SaaS workspaces (EC2-per-workspace)
// always 404'd because neither handles their on-EC2 layout.
// writeFileViaEIC (ephemeral keypair, EIC tunnel, ssh) so the canvas's
// Config tab can GET back what it just PUT.
//
// Returns ("", os.ErrNotExist) when the remote path doesn't exist so
// the handler can map it to HTTP 404 cleanly. Other errors propagate.
func readFileViaEIC(ctx context.Context, instanceID, runtime, relPath string) ([]byte, error) {
if instanceID == "" {
return nil, fmt.Errorf("workspace has no instance_id — not a SaaS EC2 workspace")
}
absPath, err := resolveWorkspaceFilePath(runtime, relPath)
//
// `sudo -n cat`: /configs is root-owned (same reason writeFileViaEIC
// needs sudo). The path is built from a validated map + Clean(), so no
// user-controlled string reaches the shell here. `2>/dev/null` swallows
// `cat: ...: No such file` so the missing-file case returns empty
// stdout + non-zero exit, which we translate to os.ErrNotExist.
func readFileViaEIC(ctx context.Context, instanceID, runtime, root, relPath string) ([]byte, error) {
absPath, err := resolveWorkspaceFilePath(runtime, root, relPath)
if err != nil {
return nil, fmt.Errorf("invalid path: %w", err)
}
osUser := os.Getenv("WORKSPACE_EC2_OS_USER")
if osUser == "" {
osUser = "ubuntu"
}
region := os.Getenv("AWS_REGION")
if region == "" {
region = "us-east-2"
}
ctx, cancel := context.WithTimeout(ctx, eicFileWriteTimeout)
ctx, cancel := context.WithTimeout(ctx, eicFileOpTimeout)
defer cancel()
keyDir, err := os.MkdirTemp("", "molecule-fileread-*")
if err != nil {
return nil, fmt.Errorf("keydir mkdir: %w", err)
}
defer func() { _ = os.RemoveAll(keyDir) }()
keyPath := keyDir + "/id"
if out, kerr := exec.CommandContext(ctx, "ssh-keygen",
"-t", "ed25519", "-f", keyPath, "-N", "", "-q",
"-C", "molecule-fileread",
).CombinedOutput(); kerr != nil {
return nil, fmt.Errorf("ssh-keygen: %w (%s)", kerr, strings.TrimSpace(string(out)))
}
pubKey, err := os.ReadFile(keyPath + ".pub")
if err != nil {
return nil, fmt.Errorf("read pubkey: %w", err)
}
if err := sendSSHPublicKey(ctx, region, instanceID, osUser, strings.TrimSpace(string(pubKey))); err != nil {
return nil, fmt.Errorf("send-ssh-public-key: %w", err)
}
localPort, err := pickFreePort()
if err != nil {
return nil, fmt.Errorf("pick free port: %w", err)
}
tunnel := openTunnelCmd(eicSSHOptions{
InstanceID: instanceID,
OSUser: osUser,
Region: region,
LocalPort: localPort,
PrivateKeyPath: keyPath,
var out []byte
runErr := withEICTunnel(ctx, instanceID, func(s eicSSHSession) error {
sshCmd := exec.CommandContext(ctx, "ssh", s.sshArgs(buildCatShell(absPath))...)
sshCmd.Env = os.Environ()
var stdout, stderr bytes.Buffer
sshCmd.Stdout = &stdout
sshCmd.Stderr = &stderr
err := sshCmd.Run()
out = stdout.Bytes()
if err != nil {
// `cat` returns 1 on missing file; with 2>/dev/null we have no
// stderr distinguisher. Treat empty-stdout + empty-stderr +
// non-zero exit as not-found rather than a tunnel/auth error
// (those usually produce stderr from ssh itself, not from the
// remote command).
if len(out) == 0 && stderr.Len() == 0 {
return os.ErrNotExist
}
return fmt.Errorf("ssh cat: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
log.Printf("readFileViaEIC: ws instance=%s runtime=%s root=%s read %d bytes ← %s",
instanceID, runtime, root, len(out), absPath)
return nil
})
tunnel.Env = os.Environ()
if err := tunnel.Start(); err != nil {
return nil, fmt.Errorf("open-tunnel start: %w", err)
}
defer func() {
if tunnel.Process != nil {
_ = tunnel.Process.Kill()
}
_ = tunnel.Wait()
}()
if err := waitForPort(ctx, "127.0.0.1", localPort, 10*time.Second); err != nil {
return nil, fmt.Errorf("tunnel never listened: %w", err)
}
// `sudo -n cat`: /configs is root-owned by cloud-init (same reason
// writeFileViaEIC needs sudo to install). The path is built from a
// validated map + Clean(), so no user-controlled string reaches the
// shell here. `2>/dev/null` swallows `cat: ...: No such file` so
// the missing-file case returns empty stdout + non-zero exit, which
// we translate to os.ErrNotExist below.
sshCmd := exec.CommandContext(ctx, "ssh",
"-i", keyPath,
"-o", "StrictHostKeyChecking=no",
"-o", "UserKnownHostsFile=/dev/null",
// LogLevel=ERROR silences the benign "Warning: Permanently
// added '[127.0.0.1]:NNNNN' to known hosts" notice that ssh
// emits on every fresh tunnel connection. Without this, the
// notice lands on stderr and fools readFileViaEIC's "empty
// stdout + empty stderr → file not found" classifier into
// thinking the warning is a real ssh-layer error → 500
// instead of 404 (Hermes config.yaml load, hongming tenant,
// 2026-05-05 02:38). Real auth/tunnel errors stay visible
// because they're emitted at ERROR level.
"-o", "LogLevel=ERROR",
"-o", "ServerAliveInterval=15",
"-p", fmt.Sprintf("%d", localPort),
fmt.Sprintf("%s@127.0.0.1", osUser),
fmt.Sprintf("sudo -n cat %s 2>/dev/null", shellQuote(absPath)),
)
sshCmd.Env = os.Environ()
var stdout, stderr bytes.Buffer
sshCmd.Stdout = &stdout
sshCmd.Stderr = &stderr
runErr := sshCmd.Run()
out := stdout.Bytes()
if runErr != nil {
// `cat` returns 1 on missing file; with 2>/dev/null we have no
// stderr distinguisher. Treat empty-stdout + non-zero exit as
// not-found rather than a tunnel/auth error (those usually
// produce stderr from ssh itself, not from the remote command).
if len(out) == 0 && stderr.Len() == 0 {
return nil, os.ErrNotExist
}
return nil, fmt.Errorf("ssh cat: %w (%s)", runErr, strings.TrimSpace(stderr.String()))
return nil, runErr
}
log.Printf("readFileViaEIC: ws instance=%s runtime=%s read %d bytes ← %s",
instanceID, runtime, len(out), absPath)
return out, nil
}
// eicFileEntry is the wire shape returned by listFilesViaEIC. It
// matches the inline `fileEntry` in templates.go::ListFiles so the
// handler can emit either path's output without a translation layer.
type eicFileEntry struct {
Path string `json:"path"`
Size int64 `json:"size"`
Dir bool `json:"dir"`
}
// listFilesViaEIC enumerates files under <root>/<sub> on the workspace
// EC2 host, up to the given depth, returning entries with paths
// relative to the listing root (matching the local-Docker path's
// output). Closes the symmetry gap that left ListFiles silently
// returning [] for SaaS workspaces — see issue #2999.
//
// Output line format: TYPE|SIZE|REL_PATH (matches the container's find
// shell so the parser is identical). `find -maxdepth N` traverses up
// to N levels; the canvas requests depth=1 by default and re-fetches
// when the user expands a directory.
//
// Pruning: same hidden / cache dirs as the container path (.git,
// __pycache__, node_modules, .DS_Store) so the canvas's tree doesn't
// drown in transient artefacts.
//
// `sudo -n` matches the read/write paths — even though the universal
// roots (/home, /workspace, /plugins) are typically ubuntu-owned and
// don't need it, /configs and runtime-prefix dirs do (root-owned by
// cloud-init), and using sudo uniformly avoids per-root branching.
func listFilesViaEIC(ctx context.Context, instanceID, runtime, root, sub string, depth int) ([]eicFileEntry, error) {
if sub != "" {
if err := validateRelPath(sub); err != nil {
return nil, fmt.Errorf("invalid sub: %w", err)
}
}
if depth < 1 {
depth = 1
}
if depth > 5 {
depth = 5
}
listPath := resolveWorkspaceRootPath(runtime, root)
if sub != "" {
listPath = filepath.Join(listPath, filepath.Clean(sub))
}
ctx, cancel := context.WithTimeout(ctx, eicFileOpTimeout)
defer cancel()
var rawOutput []byte
runErr := withEICTunnel(ctx, instanceID, func(s eicSSHSession) error {
sshCmd := exec.CommandContext(ctx, "ssh", s.sshArgs(buildFindShell(listPath, depth))...)
sshCmd.Env = os.Environ()
var stdout, stderr bytes.Buffer
sshCmd.Stdout = &stdout
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
// Empty stdout + empty stderr after we swallowed find's
// own error stream means the listing root genuinely
// doesn't exist on this workspace — return an empty
// slice rather than a 500. Real ssh/tunnel errors emit
// to stderr at LogLevel=ERROR.
if stdout.Len() == 0 && stderr.Len() == 0 {
rawOutput = nil
return nil
}
return fmt.Errorf("ssh find: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
rawOutput = stdout.Bytes()
return nil
})
if runErr != nil {
return nil, runErr
}
files := parseFindOutput(rawOutput)
log.Printf("listFilesViaEIC: ws instance=%s runtime=%s root=%s sub=%s depth=%d → %d entries from %s",
instanceID, runtime, root, sub, depth, len(files), listPath)
return files, nil
}
// deleteFileViaEIC removes a single file from the workspace EC2.
// Returns nil for both "deleted" and "didn't exist" — `rm -f` doesn't
// distinguish, and the canvas's delete-then-refresh flow doesn't need
// it to.
//
// Symmetry note: pre-fix DeleteFile (templates.go:514) had no EIC
// branch, so right-click delete on a SaaS workspace would fall through
// to the local-Docker path, find no container (dockerCli is nil on
// SaaS), and try the ephemeral-volume path which itself only handles
// local Docker volumes. Net effect: silent no-op. Closing this gap is
// part of issue #2999.
func deleteFileViaEIC(ctx context.Context, instanceID, runtime, root, relPath string) error {
absPath, err := resolveWorkspaceFilePath(runtime, root, relPath)
if err != nil {
return fmt.Errorf("invalid path: %w", err)
}
ctx, cancel := context.WithTimeout(ctx, eicFileOpTimeout)
defer cancel()
return withEICTunnel(ctx, instanceID, func(s eicSSHSession) error {
sshCmd := exec.CommandContext(ctx, "ssh", s.sshArgs(buildRmShell(absPath))...)
sshCmd.Env = os.Environ()
var stderr bytes.Buffer
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
return fmt.Errorf("ssh rm: %w (%s)", err, strings.TrimSpace(stderr.String()))
}
log.Printf("deleteFileViaEIC: ws instance=%s runtime=%s root=%s removed %s",
instanceID, runtime, root, absPath)
return nil
})
}
@@ -0,0 +1,303 @@
package handlers
// template_files_eic_dispatch_test.go — handler-level tests for the
// EIC dispatch added in PR-A of issue #2999. Pre-PR-A, ListFiles and
// DeleteFile silently fell through to the local-Docker path on SaaS
// workspaces (where dockerCli is nil) and returned [] / silent no-op.
// These tests pin the new behavior:
//
// 1. instance_id != "" → handler invokes the EIC helper
// 2. EIC success → 200 with the helper's payload
// 3. EIC error → 500 (does NOT fall through to local-Docker /
// template-dir, which would mask the real failure)
// 4. instance_id == "" → existing local-Docker / template-dir
// fallback (back-compat with self-hosted operators)
//
// Stubs `withEICTunnel` so the entire EIC dance (keypair, AWS calls,
// tunnel, ssh) is replaced with a fake closure that yields a captured
// session — lets the test capture what the inner closure would have
// done without spinning up a real sshd. The test for the actual
// remote shell shapes lives in template_files_eic_shells_test.go
// (pure-function tests on buildFindShell / buildInstallShell etc).
import (
"context"
"encoding/json"
"errors"
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/DATA-DOG/go-sqlmock"
"github.com/gin-gonic/gin"
)
// stubWithEICTunnel replaces the package-level withEICTunnel with a
// closure that records its inputs and runs fn against a fake session,
// returning fnErr from the inner fn if non-nil. Restores the original
// on test cleanup.
func stubWithEICTunnel(t *testing.T, fnErr error) (calls *[]string) {
t.Helper()
captured := []string{}
calls = &captured
prev := withEICTunnel
withEICTunnel = func(ctx context.Context, instanceID string, fn func(s eicSSHSession) error) error {
captured = append(captured, instanceID)
// Hand the closure a sentinel session so any code that pulls
// session fields gets deterministic non-empty values. The
// closure's exec.Command call will fail at runtime because no
// real ssh exists for instanceID="i-test"; but most
// dispatch-tests inject fnErr directly to skip that.
return fnErr
}
t.Cleanup(func() { withEICTunnel = prev })
return calls
}
// stubWithEICTunnelReturning is like stubWithEICTunnel but lets the
// test substitute the inner fn entirely so it can populate `out` /
// return shaped errors without invoking the real ssh closure.
func stubWithEICTunnelReturning(t *testing.T, replacement func(s eicSSHSession) error) (calls *[]string) {
t.Helper()
captured := []string{}
calls = &captured
prev := withEICTunnel
withEICTunnel = func(ctx context.Context, instanceID string, _ func(s eicSSHSession) error) error {
captured = append(captured, instanceID)
return replacement(eicSSHSession{instanceID: instanceID, osUser: "ubuntu", localPort: 12345, keyPath: "/tmp/k"})
}
t.Cleanup(func() { withEICTunnel = prev })
return calls
}
// ---- ListFiles EIC dispatch ----
// TestListFiles_EICDispatch_Success: a workspace with instance_id set
// must route to listFilesViaEIC, NOT to local-Docker / template-dir.
// Verifies the handler hands the EIC helper's output back as JSON.
//
// Until PR-A this test would fail no matter what mocks were in place —
// the dispatch branch did not exist.
func TestListFiles_EICDispatch_Success(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-eic").
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).
AddRow("My Agent", "i-test", "claude-code"))
// The package-level withEICTunnel stub doesn't get to set the
// listFilesViaEIC outparam, so we have to override the helper at
// a higher level. Instead, we stub withEICTunnel to *return* the
// inner closure's err — but we can't reach the byte-output path.
// Use the dedicated stubWithEICTunnelReturning + intercept ssh:
// since the tunnel stub doesn't run the closure's ssh exec at all
// when we replace the inner fn, the helper's `rawOutput` stays
// nil and parseFindOutput returns []. Sufficient for "200 + empty"
// dispatch verification.
stubWithEICTunnelReturning(t, func(s eicSSHSession) error {
return nil // skip the real ssh; outer rawOutput stays nil → []
})
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-eic"}}
c.Request = httptest.NewRequest("GET", "/workspaces/ws-eic/files?root=/configs", nil)
(&TemplatesHandler{}).ListFiles(c)
if w.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
}
var got []map[string]interface{}
if err := json.Unmarshal(w.Body.Bytes(), &got); err != nil {
t.Fatalf("response not JSON array: %v (body=%s)", err, w.Body.String())
}
// EIC stub returned no output → empty list. The point of this
// assertion is "200 with [] from EIC", not "fell through to host
// template fallback which would 200 with []" — to discriminate,
// we ALSO assert mock expectations were met (proving the new SQL
// shape was queried) AND the local-Docker fallback path can't
// have run (handler.docker is nil here, so findContainer returns
// "" and the only paths that reach 200 are EIC or template-dir;
// template-dir requires a non-empty configsDir which we left at
// "" via the zero-value handler).
if got == nil {
t.Errorf("expected JSON array (even if empty); got null")
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("unmet sqlmock expectations: %v", err)
}
}
// TestListFiles_EICDispatch_Error: a real EIC failure (network blip,
// AWS API throttle, sshd down) must surface as 500, NOT silently fall
// through to the local-Docker path which would mask the failure as
// "0 files" — which is the exact UX symptom the PR-A bug report cites.
func TestListFiles_EICDispatch_Error(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-eic-err").
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).
AddRow("My Agent", "i-test", "claude-code"))
stubWithEICTunnel(t, errors.New("eic open-tunnel: timeout"))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-eic-err"}}
c.Request = httptest.NewRequest("GET", "/workspaces/ws-eic-err/files?root=/home", nil)
(&TemplatesHandler{}).ListFiles(c)
if w.Code != http.StatusInternalServerError {
t.Fatalf("expected 500, got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "failed to list files") {
t.Errorf("error body should describe ListFiles failure; got %s", w.Body.String())
}
}
// TestListFiles_EICBranch_NotTakenForSelfHosted: workspaces with no
// instance_id (self-hosted, local-Docker path) MUST NOT enter the EIC
// branch. Stubs withEICTunnel to fail loudly if it's called — the
// stub being invoked is itself the assertion failure.
func TestListFiles_EICBranch_NotTakenForSelfHosted(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-local").
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).
AddRow("Local Agent", "", ""))
prev := withEICTunnel
withEICTunnel = func(ctx context.Context, instanceID string, fn func(s eicSSHSession) error) error {
t.Errorf("withEICTunnel called for self-hosted workspace (instance_id=''); EIC branch must be gated on non-empty instance_id")
return errors.New("should not be called")
}
defer func() { withEICTunnel = prev }()
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-local"}}
c.Request = httptest.NewRequest("GET", "/workspaces/ws-local/files", nil)
(&TemplatesHandler{configsDir: t.TempDir()}).ListFiles(c)
// Don't pin the response code here — the local path's behavior is
// covered by TestListFiles_FallbackToHost_NoTemplate. Just confirm
// EIC wasn't called.
}
// ---- DeleteFile EIC dispatch ----
// TestDeleteFile_EICDispatch_Success: same shape as ListFiles —
// instance_id != "" routes to deleteFileViaEIC and returns 200 on
// success. Pre-PR-A right-click delete on a SaaS workspace silently
// no-op'd because findContainer returned "" and the ephemeral-volume
// fallback only handles local Docker volumes.
func TestDeleteFile_EICDispatch_Success(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-eic-del").
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).
AddRow("My Agent", "i-test", "claude-code"))
stubWithEICTunnel(t, nil)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ws-eic-del"},
{Key: "path", Value: "old.txt"},
}
c.Request = httptest.NewRequest("DELETE", "/workspaces/ws-eic-del/files/old.txt", nil)
(&TemplatesHandler{}).DeleteFile(c)
if w.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), `"deleted"`) {
t.Errorf("expected status:deleted; got %s", w.Body.String())
}
}
func TestDeleteFile_EICDispatch_Error(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-eic-del-err").
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).
AddRow("My Agent", "i-test", "hermes"))
stubWithEICTunnel(t, errors.New("ssh rm: connection refused"))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ws-eic-del-err"},
{Key: "path", Value: "old.txt"},
}
c.Request = httptest.NewRequest("DELETE", "/workspaces/ws-eic-del-err/files/old.txt", nil)
(&TemplatesHandler{}).DeleteFile(c)
if w.Code != http.StatusInternalServerError {
t.Fatalf("expected 500, got %d: %s", w.Code, w.Body.String())
}
}
// TestListFiles_RootValidation: the handler must reject roots outside
// the allowlist BEFORE any DB query (otherwise a bad root would burn
// a tunnel + EIC call to discover what a 400 already knows). Critical
// security guard — without it `?root=/etc` would translate via the
// resolver's literal-pass-through. Let me prove the gate exists by
// driving an out-of-allowlist root and asserting 400 + no DB query.
func TestListFiles_RootValidation(t *testing.T) {
setupTestDB(t)
setupTestRedis(t)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "ws-x"}}
c.Request = httptest.NewRequest("GET", "/workspaces/ws-x/files?root=/etc", nil)
(&TemplatesHandler{}).ListFiles(c)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for /etc root, got %d: %s", w.Code, w.Body.String())
}
}
// TestDeleteFile_RootValidation mirrors the ListFiles guard. PR-A
// added ?root= handling to DeleteFile so the canvas's right-click
// delete works on any root (not just /configs) — that means the
// allowlist guard has to be present here too, otherwise an unsafe
// root flows straight into the resolver.
func TestDeleteFile_RootValidation(t *testing.T) {
setupTestDB(t)
setupTestRedis(t)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ws-x"},
{Key: "path", Value: "f.txt"},
}
c.Request = httptest.NewRequest("DELETE", "/workspaces/ws-x/files/f.txt?root=/etc", nil)
(&TemplatesHandler{}).DeleteFile(c)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for /etc root, got %d: %s", w.Code, w.Body.String())
}
}
@@ -0,0 +1,200 @@
package handlers
// template_files_eic_shells_test.go — pure-function tests for the
// remote shell builders + parser. Factored out of the EIC helpers so
// the wire shape can be pinned without standing up a real EIC tunnel
// or sshd. If a future edit changes the find/install/cat/rm shell in
// a way that drifts from the local-Docker container path, these tests
// catch it before staging.
import (
"strings"
"testing"
)
// TestBuildInstallShell pins the write-side remote command. `install`
// (not `cp`/`tee`) is load-bearing — it creates parent dirs (-D) and
// writes atomically via temp-file-rename. Permissions 0644 match the
// local-Docker tar-unpack defaults so a save → restart → save → restart
// cycle doesn't flip-flop file modes per backend.
func TestBuildInstallShell(t *testing.T) {
got := buildInstallShell("/configs/config.yaml")
wants := []string{
"sudo -n", // privilege escalation for root-owned /configs
"install -D", // creates parent dirs
"-m 0644", // permission contract
"/dev/stdin", // pipe-from-ssh source
"'/configs/config.yaml'", // shell-quoted destination
}
for _, w := range wants {
if !strings.Contains(got, w) {
t.Errorf("buildInstallShell missing %q in: %s", w, got)
}
}
}
// TestBuildCatShell pins the read-side remote command. `2>/dev/null`
// is load-bearing: without it the missing-file case emits "cat: ...:
// No such file" to stderr, and the helper's "empty stdout + empty
// stderr → os.ErrNotExist" classifier fires the wrong branch (500
// instead of 404). The tunnel-warning silencer (LogLevel=ERROR in
// sshArgs) handles the ssh side; this one handles the remote-cmd side.
func TestBuildCatShell(t *testing.T) {
got := buildCatShell("/home/ubuntu/.hermes/config.yaml")
wants := []string{
"sudo -n",
"cat",
"'/home/ubuntu/.hermes/config.yaml'",
"2>/dev/null", // missing-file → empty stdout + non-zero exit
}
for _, w := range wants {
if !strings.Contains(got, w) {
t.Errorf("buildCatShell missing %q in: %s", w, got)
}
}
}
// TestBuildRmShell pins `rm -f`, NOT `rm -rf`. A misclassified
// directory entry passing through the validator must NOT trigger a
// recursive delete. Directory removal needs its own explicit endpoint
// when/if the canvas grows that affordance.
func TestBuildRmShell(t *testing.T) {
got := buildRmShell("/configs/dead.yaml")
wants := []string{"sudo -n", "rm -f", "'/configs/dead.yaml'"}
for _, w := range wants {
if !strings.Contains(got, w) {
t.Errorf("buildRmShell missing %q in: %s", w, got)
}
}
// Negative assertion: NEVER emit -rf.
if strings.Contains(got, "rm -rf") {
t.Errorf("buildRmShell uses -rf, must use -f only: %s", got)
}
}
// TestBuildFindShell pins the listing-side remote command — it must
// match the local-Docker path's parser shape (TYPE|SIZE|REL_PATH per
// line) AND prune the same hidden / cache directories. If either
// side drifts, a /workspace listing on EC2 either drowns in node_modules
// noise (pruning regression) or drops files entirely (parser shape
// regression).
func TestBuildFindShell(t *testing.T) {
got := buildFindShell("/workspace", 2)
wants := []string{
"sudo -n find",
"'/workspace'",
"-maxdepth 2",
// Matches local-Docker container path; without these the EC2
// listing fills with VCS/build artefacts.
"-not -path '*/.git/*'",
"-not -path '*/__pycache__/*'",
"-not -path '*/node_modules/*'",
"-not -name .DS_Store",
"2>/dev/null", // missing-root → empty stdout + non-zero exit
// Wire shape — emit "TYPE|SIZE|REL_PATH" so parseFindOutput
// (and the canvas tree builder) can decode each line.
"d|0|",
"f|",
// Portable stat: GNU first, BSD fallback, then 0.
"stat -c %s",
"stat -f %z",
}
for _, w := range wants {
if !strings.Contains(got, w) {
t.Errorf("buildFindShell missing %q in: %s", w, got)
}
}
}
// TestBuildFindShell_DepthForwarding catches a regression where the
// helper hard-codes a depth instead of using the caller's value.
// `?depth=` on the canvas side controls how many levels expand on
// load — losing it means the file tree is either empty (depth=0) or
// the network blows up on a top-level /home with everyone's $HOME
// (uncapped).
func TestBuildFindShell_DepthForwarding(t *testing.T) {
for _, d := range []int{1, 3, 5} {
got := buildFindShell("/configs", d)
want := "-maxdepth " + intToStr(d)
if !strings.Contains(got, want) {
t.Errorf("buildFindShell depth=%d output missing %q: %s", d, want, got)
}
}
}
// intToStr avoids pulling strconv into a one-liner; matches the shell
// builder's fmt.Sprintf %d output exactly.
func intToStr(n int) string {
if n == 0 {
return "0"
}
neg := n < 0
if neg {
n = -n
}
var buf [20]byte
i := len(buf)
for n > 0 {
i--
buf[i] = byte('0' + n%10)
n /= 10
}
s := string(buf[i:])
if neg {
return "-" + s
}
return s
}
// TestParseFindOutput pins the parser. Each line is TYPE|SIZE|REL,
// blank/short lines silently skipped. Pre-PR-A this logic was inlined
// in the handler with the same shape; extracting + testing separately
// removes the "regex passes against the inline parser but a future
// refactor of the handler subtly changes the parse" failure mode.
func TestParseFindOutput(t *testing.T) {
in := []byte(`d|0|nested
f|123|nested/a.yaml
f|45|README.md
invalid-line
f||no-size
d|0|
`)
got := parseFindOutput(in)
// Want 4 entries: nested(d), nested/a.yaml(f,123), README.md(f,45),
// no-size(f,0). Blank lines, "invalid-line" (no pipes), and
// `d|0|` (empty rel) are skipped.
wantPaths := []string{"nested", "nested/a.yaml", "README.md", "no-size"}
if len(got) != len(wantPaths) {
t.Fatalf("got %d entries, want %d: %+v", len(got), len(wantPaths), got)
}
for i, w := range wantPaths {
if got[i].Path != w {
t.Errorf("entry[%d].Path = %q, want %q", i, got[i].Path, w)
}
}
if !got[0].Dir {
t.Errorf("entry[0] should be Dir")
}
if got[1].Size != 123 {
t.Errorf("entry[1].Size = %d, want 123", got[1].Size)
}
if got[3].Size != 0 {
t.Errorf("entry[3].Size on missing-size line = %d, want 0", got[3].Size)
}
}
// TestParseFindOutput_EmptyInput — a missing listing root yields
// empty stdout (find swallows the "No such file" via 2>/dev/null),
// which must round-trip to a JSON `[]`, not null. The handler does
// `make([]eicFileEntry, 0)` to enforce this; the test pins the
// helper-level guarantee independently.
func TestParseFindOutput_EmptyInput(t *testing.T) {
got := parseFindOutput([]byte(""))
if got == nil {
t.Errorf("parseFindOutput(\"\") returned nil; want empty slice for JSON []")
}
if len(got) != 0 {
t.Errorf("parseFindOutput(\"\") = %+v; want []", got)
}
}
@@ -7,39 +7,112 @@ import (
"testing"
)
// TestResolveWorkspaceFilePath_KnownRuntimes — the runtime → base-path
// map is the source of truth for where saved files land on the workspace
// EC2. Changing a base path without a migration shim silently orphans
// previously-saved files; this test pins the current contract.
func TestResolveWorkspaceFilePath_KnownRuntimes(t *testing.T) {
// TestResolveWorkspaceFilePath_RuntimeIndirection pins the
// `?root="/configs"` (or empty / unrecognized) → runtime managed-config
// dir behavior. Hermes uses /home/ubuntu/.hermes; claude-code uses
// /configs; unknowns fall back to /configs. This indirection is the
// reason hermes Config-tab edits land in the right place even though
// the canvas only ever sends `?root=/configs`. Changing it without a
// migration shim silently orphans previously-saved files.
func TestResolveWorkspaceFilePath_RuntimeIndirection(t *testing.T) {
cases := []struct {
runtime string
root string
relPath string
want string
}{
{"hermes", "config.yaml", "/home/ubuntu/.hermes/config.yaml"},
{"HERMES", "config.yaml", "/home/ubuntu/.hermes/config.yaml"}, // case-insensitive
{"hermes", "nested/a.yaml", "/home/ubuntu/.hermes/nested/a.yaml"},
{"hermes", "/configs", "config.yaml", "/home/ubuntu/.hermes/config.yaml"},
{"HERMES", "/configs", "config.yaml", "/home/ubuntu/.hermes/config.yaml"}, // case-insensitive
{"hermes", "/configs", "nested/a.yaml", "/home/ubuntu/.hermes/nested/a.yaml"},
{"hermes", "", "config.yaml", "/home/ubuntu/.hermes/config.yaml"}, // empty root → runtime indirection
{"hermes", "/etc", "config.yaml", "/home/ubuntu/.hermes/config.yaml"}, // out-of-allowlist → runtime indirection
// claude-code (and any future containerized runtime) lands at /configs —
// the path user-data creates and bind-mounts into the container. Pre-fix
// this fell through to /opt/configs which doesn't exist on workspace EC2s
// and would 500 with EACCES on save (the bug that motivated this gate).
{"claude-code", "config.yaml", "/configs/config.yaml"},
{"CLAUDE-CODE", "config.yaml", "/configs/config.yaml"}, // case-insensitive
{"langgraph", "config.yaml", "/opt/configs/config.yaml"},
{"external", "skills.json", "/opt/configs/skills.json"},
{"", "config.yaml", "/configs/config.yaml"}, // empty → default
{"unknown", "config.yaml", "/configs/config.yaml"}, // unknown → default
{"claude-code", "/configs", "config.yaml", "/configs/config.yaml"},
{"CLAUDE-CODE", "/configs", "config.yaml", "/configs/config.yaml"}, // case-insensitive
{"langgraph", "/configs", "config.yaml", "/opt/configs/config.yaml"},
{"external", "/configs", "skills.json", "/opt/configs/skills.json"},
{"", "/configs", "config.yaml", "/configs/config.yaml"}, // empty runtime → default
{"unknown", "/configs", "config.yaml", "/configs/config.yaml"}, // unknown → default
}
for _, tc := range cases {
t.Run(tc.runtime+"/"+tc.relPath, func(t *testing.T) {
got, err := resolveWorkspaceFilePath(tc.runtime, tc.relPath)
t.Run(tc.runtime+"+"+tc.root+"/"+tc.relPath, func(t *testing.T) {
got, err := resolveWorkspaceFilePath(tc.runtime, tc.root, tc.relPath)
if err != nil {
t.Fatalf("unexpected err: %v", err)
}
if got != tc.want {
t.Errorf("resolveWorkspaceFilePath(%q,%q) = %q, want %q",
tc.runtime, tc.relPath, got, tc.want)
t.Errorf("resolveWorkspaceFilePath(%q,%q,%q) = %q, want %q",
tc.runtime, tc.root, tc.relPath, got, tc.want)
}
})
}
}
// TestResolveWorkspaceFilePath_LiteralRoots pins that the universal
// allow-listed roots (`/home`, `/workspace`, `/plugins`) pass through
// LITERALLY rather than getting rewritten to the runtime prefix. This
// is the half of the resolver that the FilesTab "/home" selector
// depends on — without it, picking /home on a hermes workspace would
// route to /home/ubuntu/.hermes (the runtime indirection) and the
// canvas's tree row would never line up with what the user sees on
// the EC2 host.
func TestResolveWorkspaceFilePath_LiteralRoots(t *testing.T) {
cases := []struct {
runtime string
root string
relPath string
want string
}{
// /home is always literal regardless of runtime — it's a
// universal Linux path, not a managed-config indirection.
{"hermes", "/home", "ubuntu/.bashrc", "/home/ubuntu/.bashrc"},
{"claude-code", "/home", "ubuntu/notes.md", "/home/ubuntu/notes.md"},
{"langgraph", "/home", "ubuntu/x", "/home/ubuntu/x"},
// /workspace and /plugins are also literal — runtime is ignored.
{"hermes", "/workspace", "src/main.go", "/workspace/src/main.go"},
{"claude-code", "/plugins", "p/manifest.yaml", "/plugins/p/manifest.yaml"},
}
for _, tc := range cases {
t.Run(tc.runtime+"+"+tc.root+"/"+tc.relPath, func(t *testing.T) {
got, err := resolveWorkspaceFilePath(tc.runtime, tc.root, tc.relPath)
if err != nil {
t.Fatalf("unexpected err: %v", err)
}
if got != tc.want {
t.Errorf("resolveWorkspaceFilePath(%q,%q,%q) = %q, want %q",
tc.runtime, tc.root, tc.relPath, got, tc.want)
}
})
}
}
// TestResolveWorkspaceRootPath pins the directory-only translation
// used by listFilesViaEIC. Same indirection rules as
// resolveWorkspaceFilePath but without joining a relative path.
func TestResolveWorkspaceRootPath(t *testing.T) {
cases := []struct {
runtime string
root string
want string
}{
{"hermes", "/configs", "/home/ubuntu/.hermes"},
{"claude-code", "/configs", "/configs"},
{"hermes", "", "/home/ubuntu/.hermes"},
{"hermes", "/home", "/home"},
{"claude-code", "/workspace", "/workspace"},
{"hermes", "/plugins", "/plugins"},
{"unknown", "/configs", "/configs"},
{"hermes", "/etc", "/home/ubuntu/.hermes"}, // not allowlisted → runtime indirection
}
for _, tc := range cases {
t.Run(tc.runtime+"+"+tc.root, func(t *testing.T) {
got := resolveWorkspaceRootPath(tc.runtime, tc.root)
if got != tc.want {
t.Errorf("resolveWorkspaceRootPath(%q,%q) = %q, want %q",
tc.runtime, tc.root, got, tc.want)
}
})
}
@@ -53,48 +126,80 @@ func TestResolveWorkspaceFilePath_KnownRuntimes(t *testing.T) {
// We only assert the cases that Clean() can't rescue.
func TestResolveWorkspaceFilePath_RejectsTraversal(t *testing.T) {
bad := []string{
"../etc/shadow", // escapes base via ..
"/etc/shadow", // absolute path
"./../../etc", // multiple ..
"a/../../etc", // escapes via deeper ..
"../etc/shadow", // escapes base via ..
"/etc/shadow", // absolute path
"./../../etc", // multiple ..
"a/../../etc", // escapes via deeper ..
}
for _, rel := range bad {
t.Run(rel, func(t *testing.T) {
_, err := resolveWorkspaceFilePath("hermes", rel)
_, err := resolveWorkspaceFilePath("hermes", "/configs", rel)
if err == nil {
t.Errorf("resolveWorkspaceFilePath(hermes, %q) should have errored, got nil", rel)
t.Errorf("resolveWorkspaceFilePath(hermes,/configs,%q) should have errored, got nil", rel)
}
})
}
}
// TestSSHArgs_LogLevelErrorBothSites pins that BOTH ssh invocations
// (writeFileViaEIC + readFileViaEIC) include `-o LogLevel=ERROR`.
// TestSSHArgs_HardenedFlags pins the ssh option set returned by
// eicSSHSession.sshArgs(). Centralising the args was deliberate so a
// fix like PR #2822's `LogLevel=ERROR` (silences the benign
// known-hosts warning that fooled the read/list "empty stderr → not
// found" classifier) only needs to land in one place.
//
// Without that flag, ssh emits a "Warning: Permanently added
// '[127.0.0.1]:NNNNN' (ED25519) to the list of known hosts." line on
// every fresh tunnel connection (even with UserKnownHostsFile=/dev/null
// — that prevents persistence, not the warning). The warning lands on
// stderr, which fools readFileViaEIC's "empty stdout + empty stderr →
// file not found" classifier into thinking the warning is a real
// ssh-layer error and returning 500 instead of 404.
//
// Caught 2026-05-05 02:38 on hongming.moleculesai.app: opening Hermes
// workspace's Config tab returned 500 with body
// Caught 2026-05-05 02:38 on hongming.moleculesai.app: opening
// Hermes workspace's Config tab returned 500 with body
// `ssh cat: exit status 1 (Warning: Permanently added '[127.0.0.1]:37951'…)`.
//
// LogLevel=ERROR silences info+warning while keeping real auth/tunnel
// errors visible. This test reads the source and asserts the flag
// appears at least twice (one per ssh block) — fires if a future edit
// removes it from either site.
func TestSSHArgs_LogLevelErrorBothSites(t *testing.T) {
// Asserts each load-bearing flag appears in the args slice — fires if
// a future edit removes any of them.
func TestSSHArgs_HardenedFlags(t *testing.T) {
s := eicSSHSession{keyPath: "/tmp/k", localPort: 12345, osUser: "ubuntu", instanceID: "i-x"}
got := s.sshArgs("echo hi")
wantFragments := [][]string{
{"-i", "/tmp/k"},
{"-o", "StrictHostKeyChecking=no"},
{"-o", "UserKnownHostsFile=/dev/null"},
{"-o", "LogLevel=ERROR"},
{"-o", "ServerAliveInterval=15"},
{"-p", "12345"},
}
joined := strings.Join(got, " ")
for _, frag := range wantFragments {
if !strings.Contains(joined, strings.Join(frag, " ")) {
t.Errorf("sshArgs() missing fragment %v; got: %v", frag, got)
}
}
// Last two args must be `<user>@127.0.0.1` then the remote command.
if got[len(got)-2] != "ubuntu@127.0.0.1" {
t.Errorf("sshArgs() second-last must be user@127.0.0.1; got: %q", got[len(got)-2])
}
if got[len(got)-1] != "echo hi" {
t.Errorf("sshArgs() last must be the remote command; got: %q", got[len(got)-1])
}
}
// TestEicSSHSessionSingleSourceForSSHFlags is a structural guard: the
// production EIC source must invoke s.sshArgs() exclusively for ssh
// invocations — direct ssh args inlined in any helper would re-open
// the regression that PR #2822 closed (LogLevel=ERROR drift between
// helpers). Counts `s.sshArgs(` occurrences (one per file op) and
// fails if anyone copy-pastes a raw ssh args slice.
func TestEicSSHSessionSingleSourceForSSHFlags(t *testing.T) {
src, err := os.ReadFile("template_files_eic.go")
if err != nil {
t.Fatalf("read source: %v", err)
}
matches := regexp.MustCompile(`"-o", "LogLevel=ERROR"`).FindAllIndex(src, -1)
if len(matches) < 2 {
t.Errorf("expected LogLevel=ERROR in BOTH ssh blocks (write + read); found %d occurrences", len(matches))
// Each of write/read/list/delete should call s.sshArgs once.
matches := regexp.MustCompile(`s\.sshArgs\(`).FindAllIndex(src, -1)
if len(matches) < 4 {
t.Errorf("expected ≥4 s.sshArgs() callers (write/read/list/delete); found %d", len(matches))
}
// Belt and braces: no helper should be assembling its own
// `LogLevel=ERROR` literal outside of sshArgs.
literal := regexp.MustCompile(`"-o", "LogLevel=ERROR"`).FindAllIndex(src, -1)
if len(literal) != 1 {
t.Errorf("LogLevel=ERROR must appear exactly once (in sshArgs); found %d occurrences — drift risk", len(literal))
}
}
@@ -216,7 +216,12 @@ func (h *TemplatesHandler) ReplaceFiles(c *gin.Context) {
// as a follow-up.
if instanceID != "" {
for relPath, content := range body.Files {
if err := writeFileViaEIC(ctx, instanceID, runtime, relPath, []byte(content)); err != nil {
// ReplaceFiles is a bulk template-import endpoint — files
// always land in the runtime's managed-config dir. Pass
// "/configs" so resolveWorkspaceFilePath routes through the
// runtime prefix map (matches the local-Docker arm below
// which always copies to /configs).
if err := writeFileViaEIC(ctx, instanceID, runtime, "/configs", relPath, []byte(content)); err != nil {
log.Printf("ReplaceFiles EIC for %s path=%s: %v", workspaceID, relPath, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to write file %s: %v", relPath, err)})
return
+71 -10
View File
@@ -243,8 +243,11 @@ func (h *TemplatesHandler) ListFiles(c *gin.Context) {
listPath = rootPath + "/" + subPath
}
var wsName string
if err := db.DB.QueryRowContext(ctx, `SELECT name FROM workspaces WHERE id = $1`, workspaceID).Scan(&wsName); err != nil {
var wsName, instanceID, runtime string
if err := db.DB.QueryRowContext(ctx,
`SELECT name, COALESCE(instance_id, ''), COALESCE(runtime, '') FROM workspaces WHERE id = $1`,
workspaceID,
).Scan(&wsName, &instanceID, &runtime); err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
@@ -255,6 +258,32 @@ func (h *TemplatesHandler) ListFiles(c *gin.Context) {
Dir bool `json:"dir"`
}
// SaaS workspace (EC2-per-workspace) — no Docker on this tenant. List
// via SSH through the EIC endpoint, mirroring ReadFile/WriteFile's
// dispatch. Pre-fix this branch was missing and SaaS workspaces
// always fell through to local-Docker check (finds nothing on a SaaS
// tenant) + template-dir fallback (returns the seed template, not
// the persisted state, and almost never matches on user-named
// workspaces). Net effect: the canvas Files tab always rendered "0
// files / No config files yet" for SaaS workspaces, regardless of
// what was actually on disk. See issue #2999.
if instanceID != "" {
entries, err := listFilesViaEIC(ctx, instanceID, runtime, rootPath, subPath, depth)
if err != nil {
log.Printf("ListFiles EIC for %s root=%s sub=%s: %v", workspaceID, rootPath, subPath, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to list files: %v", err)})
return
}
// Translate to the handler's wire shape (the field names match
// 1:1, but Go can't implicit-convert named struct types).
out := make([]fileEntry, 0, len(entries))
for _, e := range entries {
out = append(out, fileEntry{Path: e.Path, Size: e.Size, Dir: e.Dir})
}
c.JSON(http.StatusOK, out)
return
}
// Try container filesystem first
if containerName := h.findContainer(ctx, workspaceID); containerName != "" {
// Portable file listing: works on both GNU and BusyBox/Alpine.
@@ -378,12 +407,13 @@ func (h *TemplatesHandler) ReadFile(c *gin.Context) {
// canvas Config tab always 404'd for SaaS workspaces — visible to
// users after #2781 added the "no config.yaml" error UX.
//
// The ?root= query param is intentionally ignored on the SaaS path —
// it's a local-Docker concept (arbitrary container roots). The
// runtime → base-path map (workspaceFilePathPrefix in
// template_files_eic.go) is the SaaS source of truth.
// `?root=` flows through resolveWorkspaceFilePath: "/configs" stays
// the per-runtime managed-config indirection (claude-code → /configs,
// hermes/home/ubuntu/.hermes); other allow-listed roots
// (`/home`, `/workspace`, `/plugins`) pass through literally so
// list/read/write/delete agree on what file a tree row points to.
if instanceID != "" {
content, err := readFileViaEIC(ctx, instanceID, runtime, filePath)
content, err := readFileViaEIC(ctx, instanceID, runtime, rootPath, filePath)
if err == nil {
c.JSON(http.StatusOK, gin.H{
"path": filePath,
@@ -468,6 +498,11 @@ func (h *TemplatesHandler) WriteFile(c *gin.Context) {
}
ctx := c.Request.Context()
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
if err := db.DB.QueryRowContext(ctx,
`SELECT name, COALESCE(instance_id, ''), COALESCE(runtime, '') FROM workspaces WHERE id = $1`,
@@ -479,8 +514,11 @@ func (h *TemplatesHandler) WriteFile(c *gin.Context) {
// SaaS workspace (EC2-per-workspace) — no Docker on this tenant. Write
// via SSH through the EIC endpoint to the runtime-specific path.
// `?root=` flows through the same per-runtime / literal indirection
// as ReadFile so list/read/write/delete agree on what file a tree
// row points to.
if instanceID != "" {
if err := writeFileViaEIC(ctx, instanceID, runtime, filePath, []byte(body.Content)); err != nil {
if err := writeFileViaEIC(ctx, instanceID, runtime, rootPath, filePath, []byte(body.Content)); err != nil {
log.Printf("WriteFile EIC for %s path=%s: %v", workspaceID, filePath, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to write file: %v", err)})
return
@@ -528,12 +566,35 @@ func (h *TemplatesHandler) DeleteFile(c *gin.Context) {
}
ctx := c.Request.Context()
var wsName string
if err := db.DB.QueryRowContext(ctx, `SELECT name FROM workspaces WHERE id = $1`, workspaceID).Scan(&wsName); err != nil {
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
if err := db.DB.QueryRowContext(ctx,
`SELECT name, COALESCE(instance_id, ''), COALESCE(runtime, '') FROM workspaces WHERE id = $1`,
workspaceID,
).Scan(&wsName, &instanceID, &runtime); err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
// SaaS workspace (EC2-per-workspace) — no Docker on this tenant. Delete
// via SSH through the EIC endpoint, mirroring ReadFile/WriteFile's
// dispatch. Pre-fix this branch was missing — DeleteFile fell through
// to local-Docker (no container) + ephemeral-volume (no Docker) and
// silently 500'd. See issue #2999.
if instanceID != "" {
if err := deleteFileViaEIC(ctx, instanceID, runtime, rootPath, filePath); err != nil {
log.Printf("DeleteFile EIC for %s root=%s path=%s: %v", workspaceID, rootPath, filePath, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": fmt.Sprintf("failed to delete file: %v", err)})
return
}
c.JSON(http.StatusOK, gin.H{"status": "deleted", "path": filePath})
return
}
// Delete via docker exec when container is running
if containerName := h.findContainer(ctx, workspaceID); containerName != "" {
// CWE-78: use filepath.Join instead of string concat to prevent path
@@ -750,7 +750,11 @@ func TestListFiles_WorkspaceNotFound(t *testing.T) {
handler := NewTemplatesHandler(t.TempDir(), nil, nil)
mock.ExpectQuery("SELECT name FROM workspaces WHERE id =").
// SQL shape: SELECT name, COALESCE(instance_id, ''), COALESCE(runtime, '') FROM workspaces WHERE id = $1
// (matches the L/R/W/D unified shape so dispatchers can branch on
// instance_id; sqlmock matches via QueryMatcherRegexp so the parens
// need escaping.)
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-nonexist").
WillReturnError(sql.ErrNoRows)
@@ -777,9 +781,9 @@ func TestListFiles_FallbackToHost_NoTemplate(t *testing.T) {
tmpDir := t.TempDir()
handler := NewTemplatesHandler(tmpDir, nil, nil) // nil docker = no container
mock.ExpectQuery("SELECT name FROM workspaces WHERE id =").
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-fallback").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Unknown Agent"))
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).AddRow("Unknown Agent", "", ""))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
@@ -817,9 +821,9 @@ func TestListFiles_FallbackToHost_WithTemplate(t *testing.T) {
handler := NewTemplatesHandler(tmpDir, nil, nil)
mock.ExpectQuery("SELECT name FROM workspaces WHERE id =").
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-tmpl").
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Test Agent"))
WillReturnRows(sqlmock.NewRows([]string{"name", "instance_id", "runtime"}).AddRow("Test Agent", "", ""))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
@@ -1103,7 +1107,7 @@ func TestDeleteFile_WorkspaceNotFound(t *testing.T) {
handler := NewTemplatesHandler(t.TempDir(), nil, nil)
mock.ExpectQuery("SELECT name FROM workspaces WHERE id =").
mock.ExpectQuery(`SELECT name, COALESCE\(instance_id, ''\), COALESCE\(runtime, ''\) FROM workspaces WHERE id =`).
WithArgs("ws-del-nf").
WillReturnError(sql.ErrNoRows)
+21 -22
View File
@@ -112,7 +112,6 @@ func (h *WorkspaceHandler) SetCPProvisioner(cp provisioner.CPProvisionerAPI) {
h.cpProv = cp
}
// SetEnvMutators wires a provisionhook.Registry into the handler. Plugins
// living in separate repos register on the same Registry instance during
// boot (see cmd/server/main.go) and main.go calls this setter once before
@@ -361,7 +360,7 @@ func (h *WorkspaceHandler) Create(c *gin.Context) {
// populate the Runtime pill on the side panel immediately — without it
// the node lives as "runtime: unknown" until something refetches the
// workspace row (which nothing does during provisioning).
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_PROVISIONING", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceProvisioning), id, map[string]interface{}{
"name": payload.Name,
"tier": payload.Tier,
"runtime": payload.Runtime,
@@ -388,7 +387,7 @@ func (h *WorkspaceHandler) Create(c *gin.Context) {
if err := db.CacheURL(ctx, id, payload.URL); err != nil {
log.Printf("External workspace: failed to cache URL for %s: %v", id, err)
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_ONLINE", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), id, map[string]interface{}{
"name": payload.Name, "external": true,
})
} else {
@@ -407,7 +406,7 @@ func (h *WorkspaceHandler) Create(c *gin.Context) {
} else {
connectionToken = tok
}
h.broadcaster.RecordAndBroadcast(ctx, "WORKSPACE_AWAITING_AGENT", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceAwaitingAgent), id, map[string]interface{}{
"name": payload.Name, "external": true,
})
}
@@ -539,24 +538,24 @@ func scanWorkspaceRow(rows interface {
}
ws := map[string]interface{}{
"id": id,
"name": name,
"tier": tier,
"status": status,
"url": url,
"parent_id": parentID,
"active_tasks": activeTasks,
"max_concurrent_tasks": maxConcurrentTasks,
"last_error_rate": errorRate,
"last_sample_error": sampleError,
"uptime_seconds": uptimeSeconds,
"current_task": currentTask,
"runtime": runtime,
"workspace_dir": nilIfEmpty(workspaceDir),
"monthly_spend": monthlySpend,
"x": x,
"y": y,
"collapsed": collapsed,
"id": id,
"name": name,
"tier": tier,
"status": status,
"url": url,
"parent_id": parentID,
"active_tasks": activeTasks,
"max_concurrent_tasks": maxConcurrentTasks,
"last_error_rate": errorRate,
"last_sample_error": sampleError,
"uptime_seconds": uptimeSeconds,
"current_task": currentTask,
"runtime": runtime,
"workspace_dir": nilIfEmpty(workspaceDir),
"monthly_spend": monthlySpend,
"x": x,
"y": y,
"collapsed": collapsed,
}
// budget_limit: nil when no limit set, int64 otherwise
@@ -6,6 +6,7 @@ import (
"strings"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/models"
"github.com/gin-gonic/gin"
)
@@ -85,7 +86,7 @@ func (h *WorkspaceHandler) BootstrapFailed(c *gin.Context) {
return
}
h.broadcaster.RecordAndBroadcast(c.Request.Context(), "WORKSPACE_PROVISION_FAILED", id, map[string]interface{}{
h.broadcaster.RecordAndBroadcast(c.Request.Context(), string(events.EventWorkspaceProvisionFailed), id, map[string]interface{}{
"error": errMsg,
"log_tail": tail,
"source": "bootstrap_watcher",

Some files were not shown because too many files have changed in this diff Show More