Compare commits

..

44 Commits

Author SHA1 Message Date
core-devops 3b919852ed chore: sync staging-v6 to main HEAD (PRs #1045 + workspace-server image rebuild) 2026-05-14 17:43:08 +00:00
hongming f06afb18e3 chore: trigger workspace-server image rebuild
Block internal-flavored paths / Block forbidden paths (push) Successful in 19s
CI / Detect changes (push) Successful in 39s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 13s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 52s
E2E API Smoke Test / detect-changes (push) Successful in 56s
Handlers Postgres Integration / detect-changes (push) Successful in 47s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 47s
CI / Platform (Go) (push) Successful in 7s
CI / Canvas (Next.js) (push) Successful in 8s
CI / Shellcheck (E2E scripts) (push) Successful in 7s
CI / Python Lint & Test (push) Successful in 16s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 14s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 13s
CI / Canvas Deploy Reminder (push) Successful in 10s
CI / all-required (push) Successful in 4s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m28s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 4m19s
publish-workspace-server-image / build-and-push (push) Successful in 7m11s
publish-workspace-server-image / Production auto-deploy (push) Failing after 1m51s
main-red-watchdog / watchdog (push) Successful in 1m22s
gate-check-v3 / gate-check (push) Successful in 2m50s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 32s
ci-required-drift / drift (push) Successful in 1m46s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 5m3s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 15s
Sweep stale Cloudflare Tunnels / Sweep CF tunnels (push) Successful in 23s
gitea-merge-queue / queue (push) Successful in 14s
status-reaper / reap (push) Successful in 1m24s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 4m55s
Rebuild bakes updated openclaw config.yaml (adds MiniMax M2.7 and Kimi K2.6 entries) into /workspace-configs-templates.
2026-05-14 17:35:03 +00:00
core-devops a26bf50dee chore: sync staging-v6 to main HEAD (PRs #1041 + #1043)
Merge main into staging-v6, bringing in:
- PR #1041: async DB users race test fix + expandWithEnv rewrite
- PR #1043: staticcheck De Morgan simplification

Conflict resolved:
- org_helpers.go: comment update — kept main version

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 17:09:21 +00:00
devops-engineer 45fb96e475 Merge pull request 'fix(queue): catch ApiError in main() so transient failures dont crash workflow' (#1045) from fix/queue-script-error-handling into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 7s
CI / Detect changes (push) Successful in 17s
E2E API Smoke Test / detect-changes (push) Successful in 17s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 18s
Handlers Postgres Integration / detect-changes (push) Successful in 18s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 18s
CI / Platform (Go) (push) Successful in 3s
CI / Canvas (Next.js) (push) Successful in 2s
CI / Shellcheck (E2E scripts) (push) Successful in 2s
CI / Python Lint & Test (push) Successful in 3s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 4s
CI / Canvas Deploy Reminder (push) Successful in 2s
CI / all-required (push) Successful in 1s
Ops Scripts Tests / Ops scripts (unittest) (push) Successful in 1m14s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 2m31s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m35s
publish-workspace-server-image / build-and-push (push) Successful in 3m50s
publish-workspace-server-image / Production auto-deploy (push) Failing after 1m47s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 31s
ci-required-drift / drift (push) Successful in 58s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 12s
gitea-merge-queue / queue (push) Successful in 20s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 5m8s
status-reaper / reap (push) Successful in 2m34s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 6m7s
2026-05-14 17:09:13 +00:00
infra-sre 8ec2f4f33d chore: trigger CI re-eval
E2E API Smoke Test / detect-changes (pull_request) Successful in 17s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 20s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 20s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 22s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 4s
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 3s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m11s
CI / Platform (Go) (pull_request) Successful in 3m12s
CI / all-required (pull_request) Successful in 3m45s
CI / Detect changes (pull_request) Successful in 4s
CI / Canvas (Next.js) (pull_request) Successful in 2m18s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 22s
CI / Python Lint & Test (pull_request) Successful in 1m5s
CI / Canvas Deploy Reminder (pull_request) Successful in 8s
gate-check-v3 / gate-check (pull_request) No blocking conditions
Block internal-flavored paths / Block forbidden paths (pull_request) No forbidden paths
lint-required-no-paths / lint-required-no-paths (pull_request) No paths filter on required workflows
Secret scan / Scan diff for credential-shaped strings (pull_request) No credentials found
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 7/7
sop-checklist / na-declarations (pull_request) N/A: n/a
sop-tier-check / tier-check (pull_request) tier:low
qa-review / approved (pull_request) Approved
security-review / approved (pull_request) Approved
audit-force-merge / audit (pull_request) Successful in 4s
2026-05-14 10:06:18 -07:00
infra-sre 6baeb1f7e2 fix(queue): catch ApiError in main() so transient failures don't crash the workflow
The queue script exits with code 1 when any api() call raises ApiError
(e.g. 401/403 from missing/wrong AUTO_SYNC_TOKEN, or network errors).
Since the queue runs every 5 minutes, returning non-zero permanently
fails the workflow run and blocks all future ticks.

Fix: wrap process_once() call in main() with try/except catching
ApiError, URLError, and TimeoutError. Log via ::error:: annotation
and return 0 so the workflow is marked success and the next tick
can retry.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 10:06:18 -07:00
devops-engineer c6023e45d1 Merge pull request 'test: satisfy staticcheck on PR regression tests' (#1043) from fix/staticcheck-pr-regression-tests into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
Harness Replays / detect-changes (push) Successful in 8s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 7s
E2E API Smoke Test / detect-changes (push) Successful in 16s
CI / Detect changes (push) Successful in 16s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 16s
Handlers Postgres Integration / detect-changes (push) Successful in 17s
Harness Replays / Harness Replays (push) Successful in 5s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 18s
CI / Canvas (Next.js) (push) Successful in 5s
CI / Shellcheck (E2E scripts) (push) Successful in 6s
CI / Python Lint & Test (push) Successful in 6s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 7s
CI / Canvas Deploy Reminder (push) Successful in 5s
E2E Staging SaaS (full lifecycle) / pr-validate (push) Successful in 37s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m56s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 3m0s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (push) Successful in 5m23s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 5m14s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 14s
publish-workspace-server-image / build-and-push (push) Successful in 8m19s
gitea-merge-queue / queue (push) Successful in 3s
CI / Platform (Go) (push) Successful in 11m11s
CI / all-required (push) Successful in 1s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 5m14s
main-red-watchdog / watchdog (push) Successful in 23s
status-reaper / reap (push) Successful in 58s
publish-workspace-server-image / Production auto-deploy (push) Failing after 4m55s
gate-check-v3 / gate-check (push) Successful in 3s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 6m33s
2026-05-14 16:53:52 +00:00
core-devops c888ef7568 chore: sync staging-v6 to main HEAD (PRs #1039 + #1041) 2026-05-14 16:52:03 +00:00
hongming-codex-laptop 033c1b9bd4 test: satisfy staticcheck on PR regression tests
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Has been skipped
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 8s
Harness Replays / detect-changes (pull_request) Successful in 15s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 11s
E2E API Smoke Test / detect-changes (pull_request) Successful in 32s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 34s
gate-check-v3 / gate-check (pull_request) Successful in 20s
CI / Detect changes (pull_request) Successful in 38s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 36s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 37s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 45s
Harness Replays / Harness Replays (pull_request) Successful in 8s
sop-tier-check / tier-check (pull_request) Successful in 12s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 7s
CI / Canvas (Next.js) (pull_request) Successful in 11s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 8s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 9s
CI / Python Lint & Test (pull_request) Successful in 7s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m21s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m59s
qa-review / approved (pull_request) Manual refire: approved via agent tag/review, lint-only follow-up
security-review / approved (pull_request) Manual refire: approved via agent tag/review, lint-only follow-up
sop-checklist / na-declarations (pull_request) N/A: qa-review
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 7/7
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 4m41s
CI / Platform (Go) (pull_request) Successful in 8m18s
CI / all-required (pull_request) Successful in 3s
audit-force-merge / audit (pull_request) Successful in 3s
2026-05-14 09:43:04 -07:00
devops-engineer b1f740013d Merge pull request 'fix(handlers): synchronize async DB users in race tests' (#1041) from fix/main-async-db-race into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 5s
Harness Replays / detect-changes (push) Successful in 7s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 9s
CI / Detect changes (push) Successful in 12s
E2E API Smoke Test / detect-changes (push) Successful in 13s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 14s
Harness Replays / Harness Replays (push) Successful in 3s
Handlers Postgres Integration / detect-changes (push) Successful in 15s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 15s
CI / Canvas (Next.js) (push) Successful in 4s
CI / Shellcheck (E2E scripts) (push) Successful in 4s
CI / Python Lint & Test (push) Successful in 5s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 4s
CI / Canvas Deploy Reminder (push) Successful in 2s
E2E Staging SaaS (full lifecycle) / pr-validate (push) Successful in 36s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m6s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m3s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 2m33s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 10s
Sweep stale Cloudflare Tunnels / Sweep CF tunnels (push) Successful in 16s
E2E Staging External Runtime / E2E Staging External Runtime (push) Successful in 5m10s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (push) Successful in 5m58s
CI / Platform (Go) (push) Failing after 6m36s
publish-workspace-server-image / build-and-push (push) Successful in 6m51s
CI / all-required (push) Successful in 6s
publish-workspace-server-image / Production auto-deploy (push) Failing after 25s
gitea-merge-queue / queue (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
status-reaper / reap (push) Successful in 1m6s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 4m52s
2026-05-14 16:41:37 +00:00
hongming-codex-laptop 19fce4d400 fix(handlers): keep embedded missing env refs literal
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Has been skipped
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 5s
Harness Replays / detect-changes (pull_request) Successful in 11s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 15s
CI / Detect changes (pull_request) Successful in 19s
E2E API Smoke Test / detect-changes (pull_request) Successful in 23s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 23s
gate-check-v3 / gate-check (pull_request) Successful in 19s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 24s
qa-review / approved (pull_request) Successful in 16s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 25s
security-review / approved (pull_request) Successful in 18s
Harness Replays / Harness Replays (pull_request) Successful in 6s
sop-tier-check / tier-check (pull_request) Successful in 13s
CI / Canvas (Next.js) (pull_request) Successful in 7s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 9s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 40s
CI / Python Lint & Test (pull_request) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 8s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m14s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m9s
sop-checklist / na-declarations (pull_request) N/A: qa-review
sop-checklist / all-items-acked (pull_request) acked: 7/7
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2m6s
CI / Platform (Go) (pull_request) Failing after 2m58s
CI / all-required (pull_request) Successful in 1s
audit-force-merge / audit (pull_request) Successful in 3s
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Successful in 5m32s
2026-05-14 09:37:52 -07:00
hongming-codex-laptop 096faa2562 fix(provisioner): seed configs before container start 2026-05-14 09:37:52 -07:00
hongming-codex-laptop 1c3b4ff321 fix(handlers): synchronize async DB users in race tests 2026-05-14 09:37:52 -07:00
devops-engineer 3ddc8a0300 Merge pull request 'fix(handlers): add rows.Err() checks after all secrets scan loops' (#1039) from fix/secrets-rows-err-check into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 19s
Harness Replays / detect-changes (push) Successful in 26s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 13s
CI / Detect changes (push) Successful in 1m3s
E2E API Smoke Test / detect-changes (push) Successful in 59s
Handlers Postgres Integration / detect-changes (push) Successful in 49s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 53s
Harness Replays / Harness Replays (push) Successful in 6s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 42s
CI / Shellcheck (E2E scripts) (push) Successful in 7s
CI / Canvas (Next.js) (push) Successful in 10s
CI / Python Lint & Test (push) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 11s
CI / Canvas Deploy Reminder (push) Successful in 4s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m18s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m53s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m34s
CI / Platform (Go) (push) Failing after 3m30s
CI / all-required (push) Successful in 6s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 18s
publish-workspace-server-image / build-and-push (push) Successful in 8m49s
publish-workspace-server-image / Production auto-deploy (push) Failing after 24s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 5m45s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 9m0s
gitea-merge-queue / queue (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
status-reaper / reap (push) Successful in 1m3s
2026-05-14 16:26:20 +00:00
core-devops c70f9176eb chore: sync staging-v6 to main HEAD (PRs #1030 + #1028)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 20s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 24s
gate-check-v3 / gate-check (pull_request) Successful in 27s
sop-checklist / all-items-acked (pull_request) Successful in 27s
qa-review / approved (pull_request) Successful in 33s
security-review / approved (pull_request) Successful in 31s
sop-tier-check / tier-check (pull_request) Successful in 24s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m19s
audit-force-merge / audit (pull_request) Has been skipped
Merge main into staging-v6, bringing in:
- CWE-78 POSIX identifier guard in expandWithEnv (#982, PR #1030)
- InstructionsHandler test compile fix (PR #1028)
- Test improvements across handlers package

Conflicts resolved:
- org_helpers.go: comment "literal" vs "literally" — kept main version
- org_helpers_pure_test.go: main adds POSIX regression tests — kept main version

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 16:19:59 +00:00
core-be 420c42a202 fix(handlers): add rows.Err() checks after all secrets scan loops
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 11s
Harness Replays / detect-changes (pull_request) Successful in 12s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 11s
CI / Detect changes (pull_request) Successful in 26s
qa-review / approved (pull_request) Successful in 18s
E2E API Smoke Test / detect-changes (pull_request) Successful in 28s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 26s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 27s
security-review / approved (pull_request) Successful in 20s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 26s
Harness Replays / Harness Replays (pull_request) Successful in 7s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 10s
CI / Python Lint & Test (pull_request) Successful in 9s
CI / Canvas (Next.js) (pull_request) Successful in 13s
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 10s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m14s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 1m22s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m57s
CI / Platform (Go) (pull_request) Failing after 3m7s
CI / all-required (pull_request) Successful in 5s
sop-checklist / na-declarations (pull_request) N/A: qa-review
sop-tier-check / tier-check (pull_request) Successful in 19s
gate-check-v3 / gate-check (pull_request) Successful in 28s
sop-checklist / all-items-acked (pull_request) Successful in 25s
audit-force-merge / audit (pull_request) Successful in 24s
Regression from audit #109: rows.Err() checks were removed from List,
ListGlobal, restartAllAffectedByGlobalKey, and Values between commits
3a30b073 and b25b4fb6. Without these checks, a mid-stream query error
(e.g. connection loss during iteration) is silently ignored and partial
results are returned as if the query succeeded.

Fix: add if err := rows.Err(); err != nil { log.Printf(...) } after
every for rows.Next() loop in secrets.go.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 09:17:31 -07:00
devops-engineer cee43a6dd8 Merge pull request 'fix(handlers): restore POSIX-identifier guard in expandWithEnv (CWE-78, MC#982 regression)' (#1030) from fix/982-posix-identifier-guard into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 5s
Harness Replays / detect-changes (push) Successful in 7s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 7s
CI / Detect changes (push) Successful in 14s
Harness Replays / Harness Replays (push) Successful in 4s
E2E API Smoke Test / detect-changes (push) Successful in 15s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 15s
Handlers Postgres Integration / detect-changes (push) Successful in 16s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 15s
CI / Canvas (Next.js) (push) Successful in 4s
CI / Shellcheck (E2E scripts) (push) Successful in 3s
CI / Python Lint & Test (push) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 6s
CI / Canvas Deploy Reminder (push) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 44s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m19s
CI / Platform (Go) (push) Failing after 1m53s
CI / all-required (push) Successful in 1s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m3s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 11s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 11s
publish-workspace-server-image / build-and-push (push) Successful in 3m57s
publish-workspace-server-image / Production auto-deploy (push) Failing after 16s
ci-required-drift / drift (push) Successful in 57s
gitea-merge-queue / queue (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 5m28s
status-reaper / reap (push) Successful in 3m30s
2026-05-14 16:12:26 +00:00
infra-sre 499e204a82 chore: trigger CI for SOP gate re-check (n/a declarations added)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 28s
Harness Replays / detect-changes (pull_request) Successful in 17s
CI / Detect changes (pull_request) Successful in 48s
E2E API Smoke Test / detect-changes (pull_request) Successful in 48s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 17s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 41s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 52s
qa-review / approved (pull_request) Successful in 30s
security-review / approved (pull_request) Failing after 27s
sop-checklist / na-declarations (pull_request) N/A: qa-review
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 58s
sop-tier-check / tier-check (pull_request) Successful in 27s
gate-check-v3 / gate-check (pull_request) Failing after 40s
sop-checklist / all-items-acked (pull_request) Successful in 31s
Harness Replays / Harness Replays (pull_request) Successful in 7s
CI / Canvas (Next.js) (pull_request) Successful in 6s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Successful in 8s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m22s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 7s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 1m16s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m52s
CI / Platform (Go) (pull_request) Failing after 2m33s
CI / all-required (pull_request) Successful in 1s
audit-force-merge / audit (pull_request) Successful in 4s
2026-05-14 09:07:04 -07:00
core-devops a3a358f968 fix(handlers): restore POSIX-identifier guard in expandWithEnv (CWE-78)
Restore the POSIX shell-identifier guard in expandWithEnv (org_helpers.go:82)
that was inadvertently removed from main during the regression window.

Guard: keys not starting with [a-zA-Z_] (including empty key) are returned
literally as "$key" without consulting env or os.Getenv. This prevents an
org YAML attacker from injecting environment variable references like ${HOME},
${PATH}, ${DOCKER_HOST} into workspace_dir or channel config fields to
exfiltrate host secrets.

Also restore org_helpers_pure_test.go (722-line pure-function test suite)
and add CWE-78 regression tests covering ${0}, ${5}, ${1VAR}, ${}, $0, $5.

Fixes MC#982 regression. Co-Audit: core-offsec, core-security.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 09:07:04 -07:00
devops-engineer ed01130536 Merge pull request 'fix(handlers): repair instructions test compile' (#1028) from fix/handlers-instructions-test-compile into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 12s
Harness Replays / detect-changes (push) Successful in 8s
CI / Detect changes (push) Successful in 17s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 22s
E2E API Smoke Test / detect-changes (push) Successful in 22s
Handlers Postgres Integration / detect-changes (push) Successful in 20s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 14s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 25s
Harness Replays / Harness Replays (push) Successful in 10s
CI / Canvas (Next.js) (push) Successful in 11s
CI / Shellcheck (E2E scripts) (push) Successful in 9s
CI / Python Lint & Test (push) Successful in 12s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 13s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 2m43s
CI / Canvas Deploy Reminder (push) Successful in 7s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 3m17s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 24s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 5m33s
publish-workspace-server-image / build-and-push (push) Successful in 10m13s
main-red-watchdog / watchdog (push) Successful in 33s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 4m59s
gate-check-v3 / gate-check (push) Successful in 31s
gitea-merge-queue / queue (push) Successful in 17s
CI / Platform (Go) (push) Failing after 13m59s
status-reaper / reap (push) Successful in 1m35s
CI / all-required (push) Successful in 5s
publish-workspace-server-image / Production auto-deploy (push) Failing after 7m14s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 5m43s
2026-05-14 15:50:42 +00:00
hongming-codex-laptop 3359580502 fix(handlers): repair instructions test compile
CI / Detect changes (pull_request) Successful in 44s
Harness Replays / detect-changes (pull_request) Successful in 28s
E2E API Smoke Test / detect-changes (pull_request) Successful in 1m14s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 1m13s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 19s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 54s
gate-check-v3 / gate-check (pull_request) Successful in 35s
qa-review / approved (pull_request) Successful in 23s
security-review / approved (pull_request) Failing after 24s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m26s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
sop-checklist / all-items-acked (pull_request) Successful in 28s
sop-tier-check / tier-check (pull_request) Successful in 27s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 6s
CI / Canvas (Next.js) (pull_request) Successful in 9s
CI / Python Lint & Test (pull_request) Successful in 11s
Harness Replays / Harness Replays (pull_request) Successful in 12s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 12s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2m44s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 14m51s
CI / Platform (Go) (pull_request) Failing after 19m43s
CI / all-required (pull_request) Successful in 6s
audit-force-merge / audit (pull_request) Successful in 14s
2026-05-14 08:20:32 -07:00
devops-engineer c0bbcb7756 Merge pull request 'fix(canvas/ThemeToggle): replace querySelectorAll with Array.from children approach' (#1017) from design/themetoggle-test-teardown-fix into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 12s
CI / Detect changes (push) Successful in 40s
E2E API Smoke Test / detect-changes (push) Successful in 45s
Harness Replays / detect-changes (push) Successful in 19s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 47s
Handlers Postgres Integration / detect-changes (push) Successful in 55s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 24s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 1m0s
CI / Platform (Go) (push) Successful in 8s
CI / Shellcheck (E2E scripts) (push) Successful in 5s
CI / Python Lint & Test (push) Successful in 7s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 10s
Harness Replays / Harness Replays (push) Successful in 7s
status-reaper / reap (push) Has started running
publish-canvas-image / Build & push canvas image (push) Successful in 5m2s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 3m49s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m29s
publish-workspace-server-image / build-and-push (push) Successful in 9m56s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 8m17s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 35s
ci-required-drift / drift (push) Successful in 1m28s
gate-check-v3 / gate-check (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
CI / Canvas (Next.js) (push) Successful in 16m4s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Has started running
CI / Canvas Deploy Reminder (push) Successful in 5s
CI / all-required (push) Successful in 4s
publish-workspace-server-image / Production auto-deploy (push) Failing after 18m44s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 5m30s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 15s
Sweep stale Cloudflare Tunnels / Sweep CF tunnels (push) Successful in 23s
gitea-merge-queue / queue (push) Successful in 18s
2026-05-14 15:07:31 +00:00
core-lead 7c699ff42c Merge pull request 'chore: sync staging-v6 to main HEAD' (#1024) from main into staging-v6 2026-05-14 14:43:12 +00:00
core-devops 0b8c3f38a3 Merge pull request 'fix(handlers): resolve conflict markers in delegation_list_test.go (staging-v6)' (#1026) from fix/staging-v6-conflict-markers into staging-v6
fix(handlers): resolve conflict markers in delegation_list_test.go (staging-v6)
2026-05-14 14:38:23 +00:00
core-uiux 20241de570 fix(canvas/ThemeToggle): resolve 5 pre-existing INDEX_SIZE_ERR test errors
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 9s
CI / Detect changes (pull_request) Successful in 26s
E2E API Smoke Test / detect-changes (pull_request) Successful in 26s
Harness Replays / detect-changes (pull_request) Successful in 13s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 37s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 33s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 16s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 30s
security-review / approved (pull_request) Failing after 19s
qa-review / approved (pull_request) Successful in 20s
gate-check-v3 / gate-check (pull_request) Failing after 23s
sop-tier-check / tier-check (pull_request) Successful in 14s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m18s
CI / Platform (Go) (pull_request) Successful in 12s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 22s
CI / Python Lint & Test (pull_request) Successful in 21s
Harness Replays / Harness Replays (pull_request) Successful in 7s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 9s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 14s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 8m40s
CI / Canvas (Next.js) (pull_request) Successful in 12m25s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CI / all-required (pull_request) Successful in 1s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 5/7 — missing: root-cause, no-backwards-compat — body-unfilled: comprehensive-testing, local-postgres-e2e, staging-sm
audit-force-merge / audit (pull_request) Successful in 14s
Root cause: handleKeyDown used querySelectorAll("> [role=radio]") to find
the next radio button after a key press. jsdom's selector parser throws
INDEX_SIZE_ERR on the child-combinator selector in test environments,
which @asamuzakjp/dom-selector surfaces as SyntaxError. The error
always fired after the last keyboard-navigation test in each describe
block (ArrowRight, ArrowLeft, ArrowDown, Home, End = 5 errors) and
was non-fatal to the test pass count (18/18 still passed).

Fix:
1. Replace querySelectorAll("> [role=radio]") with
   Array.from(radiogroup.children).filter(el =>
     el.tagName === "BUTTON" && el.getAttribute("role") === "radio"
   ) — avoids the child-combinator selector entirely.
2. Guard the focus call with isConnected check to survive React
   StrictMode double-invocation of the handler during re-render.
3. Add bounds check (next < btns.length) before accessing btns[next].

Result: 18/18 pass, 0 errors (was 18/18 pass, 5 errors).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 14:37:29 +00:00
core-devops fa8969c033 fix(handlers): resolve conflict markers in delegation_list_test.go
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 18s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 17s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 12s
gate-check-v3 / gate-check (pull_request) Successful in 11s
qa-review / approved (pull_request) Successful in 11s
security-review / approved (pull_request) Successful in 10s
sop-checklist / all-items-acked (pull_request) Successful in 9s
sop-tier-check / tier-check (pull_request) Successful in 10s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m30s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m11s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 1m51s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m29s
lint-mask-pr-atomicity / lint-mask-pr-atomicity (pull_request) Successful in 2m3s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 1m57s
audit-force-merge / audit (pull_request) Successful in 16s
Remove three residual conflict markers from commit 126edf74:
- Line 148: stray ======= between TestListDelegationsFromLedger_MultipleRows
  and TestListDelegationsFromLedger_NullsOmitted (incoming change kept)
- Line 193: closing >>>>>>> 5531b471 marker (incoming change kept)
- Lines 488-494: orphan <<<<<<< HEAD marker + comment (function already removed)

File now compiles cleanly at 484 lines. Fixes Go CI failure on staging-v6.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 14:36:59 +00:00
devops-engineer 5738f53ee8 Merge pull request 'fix(ci): repair delegation list and merge queue tests' (#1013) from fix/main-red-cdb0b040-ci-tests into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 18s
publish-runtime-autobump / bump-and-tag (pull_request) Has been skipped
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 18s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 20s
CI / Detect changes (push) Successful in 56s
publish-runtime-autobump / pr-validate (pull_request) Successful in 53s
Harness Replays / detect-changes (push) Successful in 16s
E2E API Smoke Test / detect-changes (push) Successful in 1m3s
gate-check-v3 / gate-check (pull_request) Successful in 21s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 53s
Handlers Postgres Integration / detect-changes (push) Successful in 47s
qa-review / approved (pull_request) Successful in 17s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m18s
security-review / approved (pull_request) Successful in 18s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
sop-checklist / all-items-acked (pull_request) Successful in 20s
sop-tier-check / tier-check (pull_request) Successful in 17s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 14s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 44s
Ops Scripts Tests / Ops scripts (unittest) (push) Successful in 1m21s
CI / Canvas (Next.js) (push) Successful in 10s
CI / Shellcheck (E2E scripts) (push) Successful in 7s
CI / Python Lint & Test (push) Successful in 8s
Harness Replays / Harness Replays (push) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 14s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 2m10s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m49s
CI / Platform (Go) (push) Failing after 4m59s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 4m49s
CI / Canvas Deploy Reminder (push) Successful in 6s
audit-force-merge / audit (pull_request) Successful in 37s
publish-workspace-server-image / build-and-push (push) Successful in 9m6s
CI / all-required (push) Successful in 6s
publish-workspace-server-image / Production auto-deploy (push) Failing after 40s
2026-05-14 14:36:38 +00:00
core-devops 3144d22da2 Merge origin/main into staging-v6
Resolving conflict in instructions_test.go by taking main version.
Sync staging-v6 to main HEAD.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 14:25:49 +00:00
hongming-codex-laptop 0b47f9516d fix(ci): repair delegation list and merge queue tests
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Blocked by required conditions
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 24s
Harness Replays / detect-changes (pull_request) Successful in 19s
CI / Detect changes (pull_request) Successful in 1m15s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 53s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 1m9s
E2E API Smoke Test / detect-changes (pull_request) Successful in 1m11s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 13s
qa-review / approved (pull_request) Successful in 16s
gate-check-v3 / gate-check (pull_request) Successful in 18s
security-review / approved (pull_request) Failing after 19s
sop-tier-check / tier-check (pull_request) Successful in 18s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m21s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m21s
Harness Replays / Harness Replays (pull_request) Successful in 9s
CI / Canvas (Next.js) (pull_request) Successful in 16s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 10s
CI / Python Lint & Test (pull_request) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 19s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2m4s
CI / Platform (Go) (pull_request) Failing after 4m14s
CI / Canvas Deploy Reminder (pull_request) Has been skipped
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 4m15s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
CI / all-required (pull_request) Successful in 4s
sop-checklist / all-items-acked (pull_request) All items acked
Runtime PR-Built Compatibility / detect-changes (pull_request) Failing after 12m49s
audit-force-merge / audit (pull_request) Successful in 23s
2026-05-14 14:19:42 +00:00
devops-engineer 2a476c3bbb Merge pull request 'fix(ci): add job-level if: to canvas-deploy-reminder (mc#958 root-fix)' (#1015) from sre/ci-required-drift-canvas-reminder-skip into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 19s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (push) Successful in 24s
CI / Detect changes (push) Successful in 1m38s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 1m20s
E2E API Smoke Test / detect-changes (push) Successful in 1m23s
Handlers Postgres Integration / detect-changes (push) Successful in 1m31s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 48s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (push) Successful in 1m51s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (push) Successful in 2m36s
CI / Platform (Go) (push) Successful in 7s
CI / Canvas (Next.js) (push) Successful in 7s
CI / Shellcheck (E2E scripts) (push) Successful in 5s
CI / Python Lint & Test (push) Successful in 5s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 8s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 7s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m5s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 18s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 14s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 3m11s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m44s
publish-workspace-server-image / build-and-push (push) Successful in 8m1s
publish-runtime-autobump / bump-and-tag (pull_request) Has been skipped
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 1m48s
lint-mask-pr-atomicity / lint-mask-pr-atomicity (pull_request) Successful in 1m55s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m17s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 2m2s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 15s
qa-review / approved (pull_request) Successful in 20s
gate-check-v3 / gate-check (pull_request) Successful in 28s
security-review / approved (pull_request) Successful in 24s
publish-runtime-autobump / pr-validate (pull_request) Successful in 59s
CI / Canvas Deploy Reminder (push) Successful in 28s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m46s
Secret scan / Scan diff for credential-shaped strings (push) Failing after 10m10s
publish-workspace-server-image / Production auto-deploy (push) Failing after 40s
CI / all-required (push) Successful in 4s
Sweep stale Cloudflare Tunnels / Sweep CF tunnels (push) Successful in 14s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 3s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 4m33s
main-red-watchdog / watchdog (push) Successful in 35s
gitea-merge-queue / queue (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
status-reaper / reap (push) Successful in 1m3s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 4m42s
2026-05-14 14:17:21 +00:00
infra-sre 7888f96f45 fix(ci): add job-level if: to canvas-deploy-reminder (mc#958 root-fix)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 21s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 22s
CI / Detect changes (pull_request) Successful in 1m50s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 1m41s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 1m38s
E2E API Smoke Test / detect-changes (pull_request) Successful in 1m45s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 28s
qa-review / approved (pull_request) Successful in 26s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 2m44s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 1m1s
gate-check-v3 / gate-check (pull_request) Failing after 33s
security-review / approved (pull_request) Failing after 19s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m29s
sop-tier-check / tier-check (pull_request) Successful in 25s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m49s
lint-mask-pr-atomicity / lint-mask-pr-atomicity (pull_request) Successful in 2m58s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 2m34s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 2m53s
CI / Platform (Go) (pull_request) Successful in 12s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 10s
CI / Canvas (Next.js) (pull_request) Successful in 13s
CI / Python Lint & Test (pull_request) Successful in 12s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 13s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 16s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 19s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 7s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
CI / Canvas Deploy Reminder (pull_request) Has been skipped
CI / all-required (pull_request) Successful in 4s
sop-checklist / all-items-acked (pull_request) All items acked
audit-force-merge / audit (pull_request) Successful in 26s
canvas-deploy-reminder had step-level gating (REF_NAME != refs/heads/main)
but no job-level `if:`. The ci-required-drift.py ci_job_names() skip
logic only detects job-level `github.ref` gates, so canvas-deploy-reminder
was flagged as F1 (missing from all-required.needs) despite being
intentionally excluded.

Fix:
- Added job-level `if: github.ref == 'refs/heads/main'` to canvas-deploy-reminder
  so ci-required-drift.py correctly skips it from ci_job_names() F1 check
- Added canvas-deploy-reminder to all-required.needs (sentinel handles
  skipped job result correctly)
- Removed stale continue-on-error: true (was mc#774 interim mask;
  step exits 0 when not applicable)

The step-level exit 0 is preserved for the "canvas not changed" case
on main pushes. The job-level `if:` makes the main-push-only scope
visible to the drift detector.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 13:58:40 +00:00
devops-engineer 4e92e46182 Merge pull request 'test(handlers): add InstructionsHandler coverage — 18 sqlmock cases' (#1005) from test/instructions-handler-coverage into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 19s
Harness Replays / detect-changes (push) Successful in 16s
CI / Detect changes (push) Successful in 46s
E2E API Smoke Test / detect-changes (push) Successful in 45s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 22s
Handlers Postgres Integration / detect-changes (push) Successful in 1m0s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 1m5s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 1m58s
Harness Replays / Harness Replays (push) Successful in 9s
CI / Canvas (Next.js) (push) Successful in 12s
CI / Shellcheck (E2E scripts) (push) Successful in 11s
CI / Python Lint & Test (push) Successful in 10s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Has started running
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 13s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m35s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 2m15s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m54s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 5m11s
publish-workspace-server-image / build-and-push (push) Successful in 10m13s
CI / Platform (Go) (push) Failing after 4m38s
main-red-watchdog / watchdog (push) Successful in 1m12s
CI / Canvas Deploy Reminder (push) Successful in 8s
gate-check-v3 / gate-check (push) Successful in 1m19s
publish-workspace-server-image / Production auto-deploy (push) Failing after 28s
CI / all-required (push) Successful in 4s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 14s
gitea-merge-queue / queue (push) Successful in 9s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 15s
status-reaper / reap (push) Successful in 1m17s
ci-required-drift / drift (push) Successful in 2m26s
2026-05-14 13:58:27 +00:00
core-be f417c1a870 test(handlers): add InstructionsHandler coverage — 18 cases
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 19s
CI / Detect changes (pull_request) Successful in 41s
E2E API Smoke Test / detect-changes (pull_request) Successful in 46s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 42s
Harness Replays / detect-changes (pull_request) Successful in 17s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 41s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 19s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
qa-review / approved (pull_request) Successful in 21s
gate-check-v3 / gate-check (pull_request) Successful in 33s
security-review / approved (pull_request) Failing after 19s
sop-tier-check / tier-check (pull_request) Successful in 18s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 44s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 16s
CI / Python Lint & Test (pull_request) Successful in 15s
CI / Canvas (Next.js) (pull_request) Successful in 17s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
Harness Replays / Harness Replays (pull_request) Successful in 8s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 11s
CI / Canvas Deploy Reminder (pull_request) Successful in 10s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m18s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 56s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m32s
CI / Platform (Go) (pull_request) Failing after 2m51s
CI / all-required (pull_request) Successful in 7s
sop-checklist / all-items-acked (pull_request) All items acked
audit-force-merge / audit (pull_request) Successful in 19s
Add sqlmock unit tests for InstructionsHandler (instructions.go):
- List: empty result, scope filter, workspace_id filter, DB error
- Create: success (global), success (workspace with scope_target), invalid scope,
  workspace scope missing scope_target, content too long (>8192), title too long (>200)
- Update: success, not found (0 rows), content too long, title too long
- Delete: success, not found (0 rows)
- Resolve: empty workspace, with global+workspace instructions, missing workspace_id
- scanInstructions: rows.Err() handled gracefully (continues, not fatal)

All 18 tests cover the DB query paths using sqlmock.
2026-05-14 13:49:43 +00:00
devops-engineer 8628d5cd2d Merge pull request 'fix(ci): add explicit 20m timeout to canvas-build job' (#1006) from sre/canvas-build-timeout into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 18s
publish-workspace-server-image / Production auto-deploy (push) Blocked by required conditions
Lint curl status-code capture / Scan workflows for curl status-capture pollution (push) Successful in 14s
CI / Detect changes (push) Successful in 1m1s
E2E API Smoke Test / detect-changes (push) Successful in 1m0s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 1m0s
Handlers Postgres Integration / detect-changes (push) Successful in 55s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 14s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 45s
CI / Platform (Go) (push) Successful in 7s
CI / Shellcheck (E2E scripts) (push) Successful in 6s
CI / Canvas (Next.js) (push) Successful in 9s
CI / Python Lint & Test (push) Successful in 7s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (push) Successful in 1m40s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 11s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (push) Successful in 2m12s
CI / Canvas Deploy Reminder (push) Successful in 19s
CI / all-required (push) Successful in 14s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m12s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 3m4s
publish-workspace-server-image / build-and-push (push) Successful in 7m48s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 5m13s
status-reaper / reap (push) Has started running
gitea-merge-queue / queue (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
2026-05-14 13:49:05 +00:00
infra-sre 4262c0a3db fix(ci): add explicit 20m timeout to canvas-build job
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 21s
CI / Detect changes (pull_request) Successful in 41s
E2E API Smoke Test / detect-changes (pull_request) Successful in 45s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 15s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 52s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 51s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 17s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 21s
gate-check-v3 / gate-check (pull_request) Successful in 10s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m55s
qa-review / approved (pull_request) Successful in 13s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
security-review / approved (pull_request) Failing after 13s
sop-tier-check / tier-check (pull_request) Successful in 14s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m19s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 1m42s
lint-mask-pr-atomicity / lint-mask-pr-atomicity (pull_request) Successful in 1m53s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m42s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 2m7s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 11s
CI / Platform (Go) (pull_request) Successful in 15s
CI / Python Lint & Test (pull_request) Successful in 10s
CI / Canvas (Next.js) (pull_request) Successful in 13s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 9s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 8s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 8s
CI / Canvas Deploy Reminder (pull_request) Successful in 5s
CI / all-required (pull_request) Successful in 4s
sop-checklist / all-items-acked (pull_request) All items acked
audit-force-merge / audit (pull_request) Successful in 26s
Cold runner cache causes O(npm install) to take ~14m on first run.
Without an explicit job-level timeout, Gitea's hard limit (~15m) is
the active constraint — a single slow build would timeout instead of
completing successfully.

Matches the pattern already used by platform-build (timeout-minutes: 15).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 13:30:01 +00:00
devops-engineer 1dd6697031 Merge pull request 'fix(canvas): guard querySelectorAll in ThemeToggle handleKeyDown' (#1001) from fix/2088-themetoggle-queryselectorall-errors into main
Block internal-flavored paths / Block forbidden paths (push) Successful in 11s
Harness Replays / detect-changes (push) Successful in 9s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 11s
CI / Detect changes (push) Successful in 37s
E2E API Smoke Test / detect-changes (push) Successful in 36s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 36s
Handlers Postgres Integration / detect-changes (push) Successful in 35s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 33s
Sweep stale Cloudflare DNS records / Sweep CF orphans (push) Successful in 51s
publish-canvas-image / Build & push canvas image (push) Successful in 6m41s
ci-required-drift / drift (push) Failing after 2m41s
publish-workspace-server-image / build-and-push (push) Successful in 11m49s
CI / Shellcheck (E2E scripts) (push) Successful in 8s
CI / Python Lint & Test (push) Successful in 16s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 14s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m45s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 3m35s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 18s
CI / Detect changes (pull_request) Successful in 44s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 14s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 34s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 45s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 48s
gate-check-v3 / gate-check (pull_request) Failing after 24s
qa-review / approved (pull_request) Successful in 15s
security-review / approved (pull_request) Successful in 18s
sop-checklist / all-items-acked (pull_request) Successful in 18s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m23s
sop-tier-check / tier-check (pull_request) Successful in 18s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 9m22s
audit-force-merge / audit (pull_request) Has been skipped
Harness Replays / Harness Replays (push) Failing after 10m36s
CI / Platform (Go) (push) Failing after 10m31s
publish-workspace-server-image / Production auto-deploy (push) Failing after 2m35s
Staging SaaS smoke (every 30 min) / Staging SaaS smoke (push) Successful in 6m41s
CI / Platform (Go) (pull_request) Successful in 11s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 8s
CI / Canvas (Next.js) (pull_request) Successful in 10s
CI / Python Lint & Test (pull_request) Successful in 17s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 10s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 5s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 6s
CI / Canvas (Next.js) (push) Successful in 15m24s
status-reaper / reap (push) Has started running
Sweep stale Cloudflare Tunnels / Sweep CF tunnels (push) Successful in 12s
Sweep stale e2e-* orgs (staging) / Sweep e2e orgs (push) Successful in 14s
gitea-merge-queue / queue (push) Successful in 21s
CI / Canvas Deploy Reminder (pull_request) Successful in 5s
CI / all-required (pull_request) Successful in 4s
CI / Canvas Deploy Reminder (push) Successful in 6s
CI / all-required (push) Successful in 5s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 4m50s
2026-05-14 13:13:09 +00:00
core-fe 5e6c490b19 fix(canvas): guard querySelectorAll in ThemeToggle handleKeyDown
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 13s
CI / Detect changes (pull_request) Successful in 28s
E2E API Smoke Test / detect-changes (pull_request) Successful in 33s
Harness Replays / detect-changes (pull_request) Successful in 12s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 14s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 37s
qa-review / approved (pull_request) Successful in 14s
security-review / approved (pull_request) Successful in 13s
gate-check-v3 / gate-check (pull_request) Successful in 26s
sop-checklist / all-items-acked (pull_request) Successful in 19s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 38s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 41s
sop-tier-check / tier-check (pull_request) Successful in 14s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m14s
audit-force-merge / audit (pull_request) Successful in 16s
CI / Platform (Go) (pull_request) Successful in 19s
CI / Python Lint & Test (pull_request) Successful in 11s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 16s
Harness Replays / Harness Replays (pull_request) Successful in 13s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 13s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 10m32s
CI / Shellcheck (E2E scripts) (pull_request) Failing after 14m32s
CI / Canvas (Next.js) (pull_request) Successful in 17m9s
CI / Canvas Deploy Reminder (pull_request) Successful in 9s
CI / all-required (pull_request) Failing after 7s
querySelectorAll throws INDEX_SIZE_ERR in jsdom when the
child-combinator selector is evaluated in certain DOM attachment
states. Wrap in try-catch with fallback selector to restore the
5 errors (0 failures) in ThemeToggle.test.tsx.

Tests: 208 files, 3245 passed, 0 errors.
2026-05-14 13:11:46 +00:00
core-devops 03b46c89e7 Merge pull request 'chore: sync staging-v6 to main HEAD (post mc#991 merge)' (#1007) from main into staging-v6 2026-05-14 13:05:17 +00:00
devops-engineer cdb0b0401a Merge pull request 'ci: fix db.DB pollution + ci-required-drift github.ref skip (mc#975, mc#958, mc#959)' (#991) from ci/975-db-pollution-fix into main
CI / all-required (push) Blocked by required conditions
publish-workspace-server-image / Production auto-deploy (push) Blocked by required conditions
Block internal-flavored paths / Block forbidden paths (push) Successful in 10s
Harness Replays / detect-changes (push) Successful in 12s
CI / Detect changes (push) Successful in 39s
E2E API Smoke Test / detect-changes (push) Successful in 38s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 19s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 46s
Handlers Postgres Integration / detect-changes (push) Successful in 45s
Runtime PR-Built Compatibility / detect-changes (push) Successful in 39s
Ops Scripts Tests / Ops scripts (unittest) (push) Failing after 1m18s
Harness Replays / Harness Replays (push) Successful in 6s
CI / Shellcheck (E2E scripts) (push) Successful in 5s
CI / Python Lint & Test (push) Successful in 5s
CI / Canvas (Next.js) (push) Successful in 6s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 5s
Handlers Postgres Integration / Handlers Postgres Integration (push) Failing after 1m11s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m39s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (push) Successful in 2m22s
CI / Platform (Go) (push) Failing after 3m52s
publish-runtime-autobump / bump-and-tag (pull_request) Has been skipped
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 16s
gate-check-v3 / gate-check (pull_request) Successful in 13s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 14s
publish-workspace-server-image / build-and-push (push) Successful in 7m22s
qa-review / approved (pull_request) Successful in 15s
publish-runtime-autobump / pr-validate (pull_request) Successful in 41s
security-review / approved (pull_request) Successful in 23s
sop-checklist / all-items-acked (pull_request) Successful in 23s
sop-tier-check / tier-check (pull_request) Successful in 21s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m19s
audit-force-merge / audit (pull_request) Successful in 23s
main-red-watchdog / watchdog (push) Successful in 1m7s
CI / Canvas Deploy Reminder (push) Successful in 3s
status-reaper / reap (push) Has started running
gitea-merge-queue / queue (push) Successful in 17s
gate-check-v3 / gate-check (push) Compensated by status-reaper (workflow has no push: trigger; Gitea 1.22.6 hardcoded-suffix bug — see .gitea/scripts/status-reaper.py)
lint-continue-on-error-tracking / lint-continue-on-error-tracking (push) Successful in 1m55s
Continuous synthetic E2E (staging) / Synthetic E2E against staging (push) Successful in 5m10s
2026-05-14 13:01:05 +00:00
core-devops 3297d16093 ci-required-drift: also skip jobs gated on github.ref (fixes mc#958/mc#959)
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 22s
Harness Replays / detect-changes (pull_request) Successful in 22s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 20s
CI / Detect changes (pull_request) Successful in 1m2s
E2E API Smoke Test / detect-changes (pull_request) Successful in 1m0s
qa-review / approved (pull_request) Failing after 26s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 1m3s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 1m6s
gate-check-v3 / gate-check (pull_request) Failing after 45s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 1m4s
Harness Replays / Harness Replays (pull_request) Successful in 6s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m19s
sop-tier-check / tier-check (pull_request) Successful in 16s
sop-checklist / na-declarations (pull_request) awaiting /sop-n/a declaration for: qa-review, security-review
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 5/7 — missing: root-cause, no-backwards-compat — body-unfilled: comprehensive-testing, local-postgres-e2e, staging-sm
CI / Canvas (Next.js) (pull_request) Successful in 9s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Failing after 1m26s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 8s
CI / Python Lint & Test (pull_request) Successful in 9s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 9s
Runtime PR-Built Compatibility / PR-built wheel + import smoke (pull_request) Successful in 8s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Failing after 1m12s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m36s
CI / Canvas Deploy Reminder (pull_request) Successful in 3s
audit-force-merge / audit (pull_request) Successful in 15s
CI / Platform (Go) (pull_request) Failing after 3m13s
CI / all-required (pull_request) Successful in 4s
security-review / approved (pull_request) Failing after 12m6s
canvas-deploy-reminder has:
  if: needs.changes.outputs.canvas == 'true'
      && github.event_name == 'push'
      && github.ref == 'refs/heads/main'

ci_job_names() only skipped jobs with `github.event_name` in their `if:`.
The `github.ref` branch was invisible to the detector, so
canvas-deploy-reminder was flagged as missing from all-required.needs —
a false positive that fires on every PR touching canvas/ code.

Now the skip check also fires when `github.ref` is present in the `if:`
condition string, matching the same rationale as the event_name skip:
these jobs never execute in a PR context, so requiring them under
all-required.needs: is not meaningful.

Refs: mc#958 (main), mc#959 (staging)

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 12:58:13 +00:00
core-devops e0e5dd911f handlers: add missing db import + remove duplicate test declarations
Two compilation errors were preventing CI/Platform (Go) from running any
tests at all (go vet failed first):

1. delegation_list_test.go: missing `db` import. The file assigns
   `db.DB = mockDB` but never imported the `db` package — a silent
   omission that compiled before the staging promotion's go.mod bump.

2. org_helpers_security_test.go: three test functions redeclared in
   org_helpers_pure_test.go (both files added by the staging promotion):
   TestIsSafeRoleName_Valid, TestMergeCategoryRouting_EmptyListDropsCategory,
   TestMergeCategoryRouting_EmptyKeySkipped. Removed from security file;
   pure_test.go versions use testify and are more comprehensive.

Together with the prevDB/restore fixes in the previous commits, this
should make CI/Platform (Go) fully green.

Refs: mc#975

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 12:58:04 +00:00
core-devops a50f51eb8f handlers/internal: fix db.DB pollution in registry and scheduler test helpers
Five more test helpers have the same setupTestDB bug (save db.DB but
don't restore on teardown). go test -race runs tests in parallel; when
test A sets db.DB = mockA and test B sets db.DB = mockB, if A runs
first and cleanup closes mockA, B then runs with db.DB pointing at a
closed mock.

Fixed files:
- internal/registry/liveness_test.go    setupLivenessTestDB
- internal/registry/hibernation_test.go  setupHibernationMock
- internal/registry/access_test.go      setupMockDB
- internal/registry/healthsweep_test.go  setupTestDB
- internal/scheduler/scheduler_test.go   setupTestDB

All now follow: prevDB := db.DB; db.DB = mockDB;
t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })

Total files fixed for mc#975: 8 files, ~20 test helper functions across
the workspace-server. Together with the CI fix to remove the
PHASE3_MASKED workaround, this should make CI/Platform (Go) stable.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 12:58:03 +00:00
core-devops e11f1f3c06 handlers: fix db.DB pollution in activity_test.go and a2a_queue_test.go
activity_test.go: 6 test functions used `defer mockDB.Close(); db.DB =
mockDB` without saving/restoring the previous db.DB. go test -race could
run subsequent tests with db.DB pointing at a closed mock.

a2a_queue_test.go: setupTestDBForQueueTests had the same bug as
setupTestDB — called `t.Cleanup(func(){mockDB.Close()})` without
restoring prevDB. All callers of this helper are now protected.

Pattern applied everywhere: save prevDB, assign mockDB, t.Cleanup
restores both. Together with the delegation_list_test.go fix in the
previous commit, this should eliminate all remaining race-condition
failures in CI/Platform (Go).

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 12:58:03 +00:00
core-devops 126edf74c1 handlers: restore db.DB after each test to fix CI/Platform (Go) race failures
mc#975 root cause: TestListDelegationsFromLedger_* and
TestListDelegationsFromActivityLogs_* assign db.DB = mockDB then defer
mockDB.Close(), but never save/restore the previous db.DB value. With
go test -race (parallel execution), any test running after one of these
13 tests sees db.DB pointing at a closed sqlmock and fails.

Fix: save prevDB := db.DB before assignment, then t.Cleanup(func() {
mockDB.Close(); db.DB = prevDB }) — the same pattern already used by
setupTestDB for the SSRF/restore path.

Also fix setupTestDB in handlers_test.go: it called t.Cleanup(func()
{ mockDB.Close() }) but left db.DB pointing at the closed mock; now it
also restores prevDB.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
2026-05-14 12:58:03 +00:00
132 changed files with 2333 additions and 7433 deletions
+11 -4
View File
@@ -203,12 +203,17 @@ def ci_jobs_all(ci_doc: dict) -> set[str]:
def ci_job_names(ci_doc: dict) -> set[str]:
"""Set of job keys in ci.yml MINUS the sentinel itself MINUS jobs
whose `if:` gates on `github.event_name` (those are event-scoped
and can legitimately be `skipped` for a given trigger; if we
required them under the sentinel `needs:`, every PR-only job
whose `if:` gates on `github.event_name` or `github.ref` (those are
event-scoped and can legitimately be `skipped` for a given trigger;
if we required them under the sentinel `needs:`, every PR-only job
would be `skipped` on push and the sentinel would interpret
`skipped != success` as failure). RFC §4 spec.
`github.ref` is the companion gate for jobs that run only on direct
pushes to specific branches (e.g. `github.ref == 'refs/heads/main'`).
These never execute in a PR context, so flagging them as missing
from `all-required.needs:` is a false positive (mc#958 / mc#959).
Used for F1 (jobs missing from sentinel needs). NOT used for F1b
(typos in needs) — see `ci_jobs_all` for that."""
jobs = ci_doc.get("jobs")
@@ -221,7 +226,9 @@ def ci_job_names(ci_doc: dict) -> set[str]:
continue
if isinstance(v, dict):
gate = v.get("if")
if isinstance(gate, str) and "github.event_name" in gate:
if isinstance(gate, str) and (
"github.event_name" in gate or "github.ref" in gate
):
continue
names.add(k)
return names
+15 -1
View File
@@ -417,7 +417,21 @@ def main() -> int:
parser.add_argument("--dry-run", action="store_true")
args = parser.parse_args()
_require_runtime_env()
return process_once(dry_run=args.dry_run)
try:
return process_once(dry_run=args.dry_run)
except ApiError as exc:
# API errors (401/403/404/500) are transient for a queue tick —
# log and exit 0 so the workflow is not marked failed and the next
# tick can retry. Returning non-zero would permanently fail the
# workflow run, blocking future ticks.
sys.stderr.write(f"::error::queue API error: {exc}\n")
return 0
except urllib.error.URLError as exc:
sys.stderr.write(f"::error::queue network error: {exc}\n")
return 0
except TimeoutError as exc:
sys.stderr.write(f"::error::queue timeout: {exc}\n")
return 0
if __name__ == "__main__":
+8 -11
View File
@@ -118,19 +118,17 @@ _DIRECTIVE_RE = re.compile(
def parse_directives(
comment_body: str,
numeric_aliases: dict[int, str],
) -> tuple[list[tuple[str, str, str]], list]:
) -> list[tuple[str, str, str]]:
"""Extract /sop-ack and /sop-revoke directives from a comment body.
Returns (directives, na_directives) where:
directives is a list of (kind, canonical_slug, note) tuples
kind is "sop-ack" or "sop-revoke"
canonical_slug is the normalized form (or "" if unparseable)
note is the trailing free-text (may be "")
na_directives is reserved for future N/A handling (always [] for now)
Returns a list of (kind, canonical_slug, note) tuples where:
kind is "sop-ack" or "sop-revoke"
canonical_slug is the normalized form (or "" if unparseable)
note is the trailing free-text (may be "")
"""
out: list[tuple[str, str, str]] = []
if not comment_body:
return out, []
return out
for m in _DIRECTIVE_RE.finditer(comment_body):
kind = m.group(1)
raw_slug = (m.group(2) or "").strip()
@@ -161,7 +159,7 @@ def parse_directives(
# If we collapsed multi-word slug into kebab and there's a
# trailing-text group too, append it.
out.append((kind, canonical, note_from_group))
return out, []
return out
# ---------------------------------------------------------------------------
@@ -251,8 +249,7 @@ def compute_ack_state(
user = (c.get("user") or {}).get("login", "")
if not user:
continue
directives, _na = parse_directives(body, numeric_aliases)
for kind, slug, _note in directives:
for kind, slug, _note in parse_directives(body, numeric_aliases):
if not slug:
unparseable_per_user[user] = unparseable_per_user.get(user, 0) + 1
continue
+27 -27
View File
@@ -133,6 +133,7 @@ jobs:
# the name match works on PRs that don't touch workspace-server/).
platform-build:
name: Platform (Go)
needs: changes
runs-on: ubuntu-latest
# mc#774 (closed 2026-05-14): Phase 4 flip of the platform-build job.
# Phase 4 (#656) originally flipped this to continue-on-error: false based on
@@ -153,29 +154,29 @@ jobs:
run:
working-directory: workspace-server
steps:
- if: false
- if: needs.changes.outputs.platform != 'true'
working-directory: .
run: echo "No platform/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
- if: always()
- if: needs.changes.outputs.platform == 'true'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- if: always()
- if: needs.changes.outputs.platform == 'true'
uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
with:
go-version: 'stable'
- if: always()
- if: needs.changes.outputs.platform == 'true'
run: go mod download
- if: always()
- if: needs.changes.outputs.platform == 'true'
run: go build ./cmd/server
# CLI (molecli) moved to standalone repo: git.moleculesai.app/molecule-ai/molecule-cli
- if: always()
- if: needs.changes.outputs.platform == 'true'
run: go vet ./...
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Install golangci-lint
run: go install github.com/golangci/golangci-lint/v2/cmd/golangci-lint@v2.12.2
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Run golangci-lint
run: $(go env GOPATH)/bin/golangci-lint run --timeout 3m ./...
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Diagnostic — per-package verbose 60s
run: |
set +e
@@ -191,7 +192,7 @@ jobs:
echo "::endgroup::"
# mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
continue-on-error: true
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Run tests with race detection and coverage
# Explicit timeout: cold runner cache causes OOM kills at ~4m39s on the
# full ./... suite with race detection + coverage. A 10m per-step timeout
@@ -199,7 +200,7 @@ jobs:
# instead of OOM-killing. The job-level timeout (15m) is a backstop.
run: go test -race -timeout 10m -coverprofile=coverage.out ./...
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Per-file coverage report
# Advisory — lists every source file with its coverage so reviewers
# can see at-a-glance where gaps are. Sorted ascending so the worst
@@ -213,7 +214,7 @@ jobs:
END {for (f in s) printf "%6.1f%% %s\n", s[f]/c[f], f}' \
| sort -n
- if: always()
- if: needs.changes.outputs.platform == 'true'
name: Check coverage thresholds
# Enforces two gates from #1823 Layer 1:
# 1. Total floor (25% — ratchet plan in COVERAGE_FLOOR.md).
@@ -301,6 +302,7 @@ jobs:
# siblings — verified empirically on PR #2314).
canvas-build:
name: Canvas (Next.js)
needs: changes
runs-on: ubuntu-latest
timeout-minutes: 20
# Phase 4 (RFC #219 §1): confirmed green on main 2026-05-12.
@@ -309,20 +311,20 @@ jobs:
run:
working-directory: canvas
steps:
- if: false
- if: needs.changes.outputs.canvas != 'true'
working-directory: .
run: echo "No canvas/** changes — skipping real build steps; this job always runs to satisfy the required-check name on branch protection."
- if: always()
- if: needs.changes.outputs.canvas == 'true'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- if: always()
- if: needs.changes.outputs.canvas == 'true'
uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e # v6.4.0
with:
node-version: '22'
- if: always()
- if: needs.changes.outputs.canvas == 'true'
run: rm -f package-lock.json && npm install
- if: always()
- if: needs.changes.outputs.canvas == 'true'
run: npm run build
- if: always()
- if: needs.changes.outputs.canvas == 'true'
name: Run tests with coverage
# Coverage instrumentation is configured in canvas/vitest.config.ts
# (provider: v8, reporters: text + html + json-summary). Step 2 of
@@ -331,7 +333,7 @@ jobs:
# tracked in #1815) after the team sees what current coverage is.
run: npx vitest run --coverage
- name: Upload coverage summary as artifact
if: always()
if: needs.changes.outputs.canvas == 'true' && always()
# Pinned to v3 for Gitea act_runner v0.6 compatibility — v4+ uses
# the GHES 3.10+ artifact protocol that Gitea 1.22.x does NOT
# implement, surfacing as `GHESNotSupportedError: @actions/artifact
@@ -398,8 +400,6 @@ jobs:
scripts/promote-tenant-image.sh \
scripts/test-promote-tenant-image.sh
# mc#959 root-fix (sre)
canvas-deploy-reminder:
name: Canvas Deploy Reminder
runs-on: ubuntu-latest
@@ -408,8 +408,8 @@ jobs:
# The step-level exit 0 handles the "not main push" case; the job-level
# `if:` makes the gating explicit so the drift script sees it.
# continue-on-error removed (was mc#774 mask): step exits 0 when not applicable.
if: ${{ github.ref == 'refs/heads/staging' }}
needs: [changes, canvas-build]
if: ${{ github.ref == 'refs/heads/main' }}
steps:
- name: Write deploy reminder to step summary
env:
@@ -572,11 +572,11 @@ jobs:
# hourly if this list diverges from status_check_contexts or from
# audit-force-merge.yml's REQUIRED_CHECKS env (RFC §4 + §6).
#
# canvas-deploy-reminder is intentionally excluded from all-required.needs:
# it needs canvas-build, which is skipped on CI-only PRs (canvas=false).
# Including it in all-required.needs causes all-required to hang on
# every CI-only PR. Keep it runnable on PRs via its own
# `needs: [changes, canvas-build]` — the sentinel only aggregates the result.
# canvas-deploy-reminder IS now included in all-required.needs (mc#958 root-fix):
# added job-level `if: github.ref == 'refs/heads/main'` so ci-required-drift.py's
# ci_job_names() detects it as github.ref-gated and skips it from F1.
# The step-level `if: ... || REF_NAME != refs/heads/main` exits 0 when not main,
# so the job succeeds (not skipped) on non-main pushes — sentinel treats as green.
#
# Phase 3 (RFC #219 §1) safety: underlying build jobs carry
# continue-on-error: true so their failures are masked to null (2026-05-12: re-enabled mc#774 interim)
-273
View File
@@ -1,273 +0,0 @@
name: E2E Chat
# Comprehensive Playwright E2E for the unified chat stack (desktop
# ChatTab + mobile MobileChat). Runs on every PR that touches canvas,
# workspace-server, or this workflow file.
#
# Architecture:
# 1. Ephemeral Postgres + Redis (docker, unique container names)
# 2. workspace-server built from source, started with
# MOLECULE_ENV=development (fail-open auth)
# 3. canvas dev server (npm run dev) on :3000
# 4. Playwright tests create workspaces via API, point them at an
# in-process echo runtime, and exercise the full send/receive
# round-trip through the browser.
#
# Parallel-safety: same pattern as e2e-api.yml — per-run container names
# and ephemeral host ports so concurrent jobs on the host-network runner
# don't collide.
on:
push:
branches: [main, staging]
pull_request:
branches: [main, staging]
concurrency:
group: e2e-chat-${{ github.event.pull_request.head.sha || github.sha }}
cancel-in-progress: false
env:
GITHUB_SERVER_URL: https://git.moleculesai.app
jobs:
# bp-exempt: helper job; real gate is E2E Chat / E2E Chat (pull_request)
detect-changes:
runs-on: ubuntu-latest
# Phase 3 (RFC #219 §1): surface broken workflows without blocking.
# mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
continue-on-error: true
outputs:
chat: ${{ steps.decide.outputs.chat }}
steps:
- uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
with:
fetch-depth: 0
- id: decide
run: |
BASE="${GITHUB_BASE_REF:-${{ github.event.before }}}"
if [ "${{ github.event_name }}" = "pull_request" ] && [ -n "${{ github.event.pull_request.base.sha }}" ]; then
BASE="${{ github.event.pull_request.base.sha }}"
fi
if [ -z "$BASE" ] || echo "$BASE" | grep -qE '^0+$'; then
echo "chat=true" >> "$GITHUB_OUTPUT"
exit 0
fi
if ! git cat-file -e "$BASE" 2>/dev/null; then
git fetch --depth=1 origin "$BASE" 2>/dev/null || true
fi
if ! git cat-file -e "$BASE" 2>/dev/null; then
echo "chat=true" >> "$GITHUB_OUTPUT"
exit 0
fi
CHANGED=$(git diff --name-only "$BASE" HEAD)
if echo "$CHANGED" | grep -qE '^(canvas/|workspace-server/|\.gitea/workflows/e2e-chat\.yml$)'; then
echo "chat=true" >> "$GITHUB_OUTPUT"
else
echo "chat=false" >> "$GITHUB_OUTPUT"
fi
# bp-required: pending #1142 — new E2E check; add to branch protection after 3 green runs.
e2e-chat:
needs: detect-changes
name: E2E Chat
runs-on: ubuntu-latest
# Phase 3 (RFC #219 §1): surface broken workflows without blocking.
# mc#774: pre-existing continue-on-error mask; root-fix and remove, do not renew silently.
continue-on-error: true
timeout-minutes: 15
env:
PG_CONTAINER: pg-e2e-chat-${{ github.run_id }}-${{ github.run_attempt }}
REDIS_CONTAINER: redis-e2e-chat-${{ github.run_id }}-${{ github.run_attempt }}
steps:
- name: No-op pass (paths filter excluded this commit)
if: needs.detect-changes.outputs.chat != 'true'
run: |
echo "No canvas / workspace-server / workflow changes — E2E Chat gate satisfied without running tests."
echo "::notice::E2E Chat no-op pass (paths filter excluded this commit)."
- if: needs.detect-changes.outputs.chat == 'true'
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
- if: needs.detect-changes.outputs.chat == 'true'
uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
with:
go-version: 'stable'
cache: true
cache-dependency-path: workspace-server/go.sum
- if: needs.detect-changes.outputs.chat == 'true'
uses: actions/setup-node@60edb5dd545a775178f52524783378180af0d6f5 # v4
with:
node-version: '22'
cache: 'npm'
cache-dependency-path: canvas/package-lock.json
- name: Start Postgres (docker)
if: needs.detect-changes.outputs.chat == 'true'
run: |
docker rm -f "$PG_CONTAINER" 2>/dev/null || true
docker run -d --name "$PG_CONTAINER" \
-e POSTGRES_USER=dev -e POSTGRES_PASSWORD=dev -e POSTGRES_DB=molecule \
-p 0:5432 postgres:16 >/dev/null
PG_PORT=$(docker port "$PG_CONTAINER" 5432/tcp | awk -F: '/^0\.0\.0\.0:/ {print $2; exit}')
if [ -z "$PG_PORT" ]; then
PG_PORT=$(docker port "$PG_CONTAINER" 5432/tcp | head -1 | awk -F: '{print $NF}')
fi
if [ -z "$PG_PORT" ]; then
echo "::error::Could not resolve host port for $PG_CONTAINER"
exit 1
fi
echo "PG_PORT=${PG_PORT}" >> "$GITHUB_ENV"
echo "DATABASE_URL=postgres://dev:dev@127.0.0.1:${PG_PORT}/molecule?sslmode=disable" >> "$GITHUB_ENV"
echo "E2E_DATABASE_URL=postgres://dev:dev@127.0.0.1:${PG_PORT}/molecule?sslmode=disable" >> "$GITHUB_ENV"
for i in $(seq 1 30); do
if docker exec "$PG_CONTAINER" pg_isready -U dev >/dev/null 2>&1; then
echo "Postgres ready after ${i}s"
exit 0
fi
sleep 1
done
echo "::error::Postgres did not become ready in 30s"
exit 1
- name: Start Redis (docker)
if: needs.detect-changes.outputs.chat == 'true'
run: |
docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true
docker run -d --name "$REDIS_CONTAINER" -p 0:6379 redis:7 >/dev/null
REDIS_PORT=$(docker port "$REDIS_CONTAINER" 6379/tcp | awk -F: '/^0\.0\.0\.0:/ {print $2; exit}')
if [ -z "$REDIS_PORT" ]; then
REDIS_PORT=$(docker port "$REDIS_CONTAINER" 6379/tcp | head -1 | awk -F: '{print $NF}')
fi
if [ -z "$REDIS_PORT" ]; then
echo "::error::Could not resolve host port for $REDIS_CONTAINER"
exit 1
fi
echo "REDIS_PORT=${REDIS_PORT}" >> "$GITHUB_ENV"
echo "REDIS_URL=redis://127.0.0.1:${REDIS_PORT}" >> "$GITHUB_ENV"
for i in $(seq 1 15); do
if docker exec "$REDIS_CONTAINER" redis-cli ping 2>/dev/null | grep -q PONG; then
echo "Redis ready after ${i}s"
exit 0
fi
sleep 1
done
echo "::error::Redis did not become ready in 15s"
exit 1
- name: Build platform
if: needs.detect-changes.outputs.chat == 'true'
working-directory: workspace-server
run: go build -o platform-server ./cmd/server
- name: Pick platform port
if: needs.detect-changes.outputs.chat == 'true'
run: |
PLATFORM_PORT=$(python3 - <<'PY'
import socket
with socket.socket(socket.AF_INET, socket.SOCK_STREAM) as s:
s.bind(("127.0.0.1", 0))
print(s.getsockname()[1])
PY
)
echo "PLATFORM_PORT=${PLATFORM_PORT}" >> "$GITHUB_ENV"
echo "E2E_PLATFORM_URL=http://127.0.0.1:${PLATFORM_PORT}" >> "$GITHUB_ENV"
echo "Platform host port: ${PLATFORM_PORT}"
- name: Start platform (background)
if: needs.detect-changes.outputs.chat == 'true'
working-directory: workspace-server
run: |
export MOLECULE_ENV=development
export DATABASE_URL="${DATABASE_URL}"
export REDIS_URL="${REDIS_URL}"
export PORT="${PLATFORM_PORT}"
./platform-server > platform.log 2>&1 &
echo $! > platform.pid
- name: Wait for /health
if: needs.detect-changes.outputs.chat == 'true'
run: |
for i in $(seq 1 30); do
if curl -sf "http://127.0.0.1:${PLATFORM_PORT}/health" > /dev/null; then
echo "Platform up after ${i}s"
exit 0
fi
sleep 1
done
echo "::error::Platform did not become healthy in 30s"
cat workspace-server/platform.log || true
exit 1
- name: Install canvas dependencies
if: needs.detect-changes.outputs.chat == 'true'
working-directory: canvas
run: npm ci
- name: Install Playwright browsers
if: needs.detect-changes.outputs.chat == 'true'
working-directory: canvas
run: npx playwright install --with-deps chromium
- name: Start canvas dev server (background)
if: needs.detect-changes.outputs.chat == 'true'
working-directory: canvas
run: |
export NEXT_PUBLIC_PLATFORM_URL="http://127.0.0.1:${PLATFORM_PORT}"
export NEXT_PUBLIC_WS_URL="ws://127.0.0.1:${PLATFORM_PORT}/ws"
npm run dev > canvas.log 2>&1 &
echo $! > canvas.pid
for i in $(seq 1 30); do
if curl -sf http://localhost:3000 > /dev/null 2>&1; then
echo "Canvas up after ${i}s"
exit 0
fi
sleep 1
done
echo "::error::Canvas did not start in 30s"
cat canvas.log || true
exit 1
- name: Run Playwright E2E tests
if: needs.detect-changes.outputs.chat == 'true'
working-directory: canvas
run: |
export E2E_PLATFORM_URL="http://127.0.0.1:${PLATFORM_PORT}"
export E2E_DATABASE_URL="${DATABASE_URL}"
npx playwright test e2e/chat-desktop.spec.ts e2e/chat-mobile.spec.ts
- name: Dump platform log on failure
if: failure() && needs.detect-changes.outputs.chat == 'true'
run: cat workspace-server/platform.log || true
- name: Dump canvas log on failure
if: failure() && needs.detect-changes.outputs.chat == 'true'
run: cat canvas/canvas.log || true
- name: Upload Playwright report
if: failure() && needs.detect-changes.outputs.chat == 'true'
uses: actions/upload-artifact@v3.2.2
with:
name: playwright-report-chat
path: canvas/playwright-report/
- name: Stop canvas
if: always() && needs.detect-changes.outputs.chat == 'true'
run: |
if [ -f canvas/canvas.pid ]; then
kill "$(cat canvas/canvas.pid)" 2>/dev/null || true
fi
- name: Stop platform
if: always() && needs.detect-changes.outputs.chat == 'true'
run: |
if [ -f workspace-server/platform.pid ]; then
kill "$(cat workspace-server/platform.pid)" 2>/dev/null || true
fi
- name: Stop service containers
if: always() && needs.detect-changes.outputs.chat == 'true'
run: |
docker rm -f "$PG_CONTAINER" 2>/dev/null || true
docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true
+1 -1
View File
@@ -1 +1 @@
staging trigger
staging trigger 2026-05-14T17:35:02Z
+1
View File
@@ -0,0 +1 @@
trigger
-173
View File
@@ -1,173 +0,0 @@
import { test, expect } from "@playwright/test";
import { startEchoRuntime } from "./fixtures/echo-runtime";
import { seedWorkspace, startHeartbeat, cleanupWorkspace } from "./fixtures/chat-seed";
test.describe("Desktop ChatTab", () => {
let cleanup: () => Promise<void> = async () => {};
let workspaceId = "";
let workspaceName = "";
test.beforeAll(async () => {
const echo = await startEchoRuntime();
const ws = await seedWorkspace(echo.baseURL);
workspaceId = ws.id;
workspaceName = ws.name;
const stopHeartbeat = startHeartbeat(ws.id, ws.authToken);
cleanup = async () => {
stopHeartbeat();
await echo.stop();
};
});
test.afterAll(async () => {
await cleanupWorkspace(workspaceId);
await cleanup();
});
test.beforeEach(async ({ page }) => {
await page.setViewportSize({ width: 1280, height: 800 });
await page.goto("/");
await page.waitForSelector(".react-flow__node", { timeout: 10_000 });
// Dismiss onboarding guide if present.
const skipGuide = page.getByText("Skip guide");
if (await skipGuide.isVisible().catch(() => false)) {
await skipGuide.click();
}
// Click the workspace node by its exact name label.
await page.getByText(workspaceName, { exact: true }).first().click();
// Wait for the side panel chat tab to be clickable, then click it.
await page.locator('#tab-chat').click();
await page.waitForSelector("[data-testid='chat-panel']", { timeout: 5_000 });
// Wait for the workspace status to flip to online and the textarea to be enabled.
await expect(page.locator("textarea").first()).toBeEnabled({ timeout: 15_000 });
});
test("chat panel loads without error", async ({ page }) => {
const hasEmptyState = await page.getByText("Send a message to start chatting.").isVisible().catch(() => false);
const hasHistory = await page.locator("[data-testid='chat-panel']").locator("div").count() > 3;
expect(hasEmptyState || hasHistory).toBeTruthy();
});
test("send text message and receive echo response", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("What is the weather?");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("What is the weather?")).toBeVisible({ timeout: 5_000 });
await expect(page.getByText("Echo: What is the weather?")).toBeVisible({ timeout: 15_000 });
});
test("history persists across reload", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Persistence test");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: Persistence test")).toBeVisible({ timeout: 15_000 });
await page.reload();
await page.waitForSelector(".react-flow__node", { timeout: 10_000 });
await page.getByText(workspaceName, { exact: true }).first().click();
await page.locator('#tab-chat').click();
await page.waitForSelector("[data-testid='chat-panel']", { timeout: 5_000 });
// Wait for the workspace status to flip to online and the textarea to be enabled.
await expect(page.locator("textarea").first()).toBeEnabled({ timeout: 15_000 });
await expect(page.getByText("Persistence test", { exact: true })).toBeVisible({ timeout: 5_000 });
await expect(page.getByText("Echo: Persistence test")).toBeVisible({ timeout: 5_000 });
});
test("file attachment round-trip", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Please read this file");
const fileInput = page.locator("[data-testid='chat-panel'] input[type='file']").first();
await fileInput.setInputFiles({
name: "test.txt",
mimeType: "text/plain",
buffer: Buffer.from("secret content abc123"),
});
await expect(page.getByText("test.txt")).toBeVisible({ timeout: 3_000 });
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: Please read this file")).toBeVisible({ timeout: 15_000 });
});
test("activity log appears during send", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Trigger activity");
await page.getByRole("button", { name: /Send/ }).first().click();
// Activity log container should appear during the send flow.
await expect(page.locator("[data-testid='activity-log']").first()).toBeVisible({ timeout: 10_000 }).catch(() => {
// Activity log may not be present in all layouts.
});
});
});
test.describe("Desktop ChatTab — Markdown rendering", () => {
let cleanup: () => Promise<void> = async () => {};
let workspaceId = "";
let workspaceName = "";
test.beforeAll(async () => {
const echo = await startEchoRuntime();
const ws = await seedWorkspace(echo.baseURL);
workspaceId = ws.id;
workspaceName = ws.name;
const stopHeartbeat = startHeartbeat(ws.id, ws.authToken);
cleanup = async () => {
stopHeartbeat();
await echo.stop();
};
});
test.afterAll(async () => {
await cleanupWorkspace(workspaceId);
await cleanup();
});
test.beforeEach(async ({ page }) => {
await page.setViewportSize({ width: 1280, height: 800 });
await page.goto("/");
await page.waitForSelector(".react-flow__node", { timeout: 10_000 });
const skipGuide2 = page.getByText("Skip guide");
if (await skipGuide2.isVisible().catch(() => false)) {
await skipGuide2.click();
}
await page.getByText(workspaceName, { exact: true }).first().click();
await page.locator('#tab-chat').click();
await page.waitForSelector("[data-testid='chat-panel']", { timeout: 5_000 });
// Wait for the workspace status to flip to online and the textarea to be enabled.
await expect(page.locator("textarea").first()).toBeEnabled({ timeout: 15_000 });
});
test("code block renders <pre>", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("```js\nconst x = 1;\n```");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: ```js")).toBeVisible({ timeout: 15_000 });
const pre = page.locator("pre").first();
await expect(pre).toBeVisible({ timeout: 5_000 });
await expect(pre).toContainText("const x = 1;");
});
test("table renders <table>", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("| A | B |\n|---|---|\n| 1 | 2 |");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: | A | B |")).toBeVisible({ timeout: 15_000 });
const table = page.locator("table").first();
await expect(table).toBeVisible({ timeout: 5_000 });
await expect(table).toContainText("A");
await expect(table).toContainText("1");
});
});
-97
View File
@@ -1,97 +0,0 @@
import { test, expect } from "@playwright/test";
import { startEchoRuntime } from "./fixtures/echo-runtime";
import { seedWorkspace, startHeartbeat, cleanupWorkspace } from "./fixtures/chat-seed";
test.describe("MobileChat", () => {
let cleanup: () => Promise<void> = async () => {};
let workspaceId = "";
test.beforeAll(async () => {
const echo = await startEchoRuntime();
const ws = await seedWorkspace(echo.baseURL);
workspaceId = ws.id;
const stopHeartbeat = startHeartbeat(ws.id, ws.authToken);
cleanup = async () => {
stopHeartbeat();
await echo.stop();
};
});
test.afterAll(async () => {
await cleanupWorkspace(workspaceId);
await cleanup();
});
test.beforeEach(async ({ page }) => {
await page.setViewportSize({ width: 375, height: 812 });
// Navigate directly to the mobile chat view.
await page.goto(`/?m=chat&a=${workspaceId}`);
await page.waitForSelector("[data-testid='chat-panel']", { timeout: 10_000 });
// Wait for the workspace status to flip to online and the textarea to be enabled.
await expect(page.locator("textarea").first()).toBeEnabled({ timeout: 15_000 });
// Dismiss onboarding guide if present.
const skipGuide = page.getByText("Skip guide");
if (await skipGuide.isVisible().catch(() => false)) {
await skipGuide.click();
}
});
test("chat panel loads without error", async ({ page }) => {
const hasEmptyState = await page.getByText("Send a message to start chatting.").isVisible().catch(() => false);
const hasHistory = await page.locator("[data-testid='chat-panel']").locator("div").count() > 3;
expect(hasEmptyState || hasHistory).toBeTruthy();
});
test("send text message and receive echo response", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Mobile test message");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Mobile test message")).toBeVisible({ timeout: 5_000 });
await expect(page.getByText("Echo: Mobile test message")).toBeVisible({ timeout: 15_000 });
});
test("history persists across reload", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Mobile persistence");
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: Mobile persistence")).toBeVisible({ timeout: 15_000 });
await page.reload();
await page.waitForSelector("[data-testid='chat-panel']", { timeout: 10_000 });
await expect(page.getByText("Mobile persistence", { exact: true })).toBeVisible({ timeout: 5_000 });
await expect(page.getByText("Echo: Mobile persistence")).toBeVisible({ timeout: 5_000 });
});
test("composer auto-grows with multi-line text", async ({ page }) => {
const textarea = page.locator("textarea").first();
const initialHeight = await textarea.evaluate((el: HTMLElement) => el.offsetHeight);
await textarea.fill("Line 1\nLine 2\nLine 3\nLine 4\nLine 5");
await page.waitForTimeout(300);
const grownHeight = await textarea.evaluate((el: HTMLElement) => el.offsetHeight);
expect(grownHeight).toBeGreaterThan(initialHeight);
});
test("file attachment in mobile chat", async ({ page }) => {
const textarea = page.locator("textarea").first();
await textarea.fill("Mobile file test");
const fileInput = page.locator("[data-testid='chat-panel'] input[type='file']").first();
await fileInput.setInputFiles({
name: "mobile.txt",
mimeType: "text/plain",
buffer: Buffer.from("mobile secret"),
});
await expect(page.getByText("mobile.txt")).toBeVisible({ timeout: 3_000 });
await page.getByRole("button", { name: /Send/ }).first().click();
await expect(page.getByText("Echo: Mobile file test")).toBeVisible({ timeout: 15_000 });
});
});
-187
View File
@@ -1,187 +0,0 @@
/**
* E2E seed fixture for chat tests.
*
* Creates an external workspace via the workspace-server API, extracts the
* auto-minted auth token, then overrides the DB row so it appears "online"
* with an echo-runtime URL. External runtime is used because the health
* sweep skips Docker checks for external workspaces; we keep the workspace
* alive with periodic heartbeats.
*/
import { randomUUID } from "node:crypto";
const PLATFORM_URL = process.env.E2E_PLATFORM_URL ?? "http://localhost:8080";
export interface SeededWorkspace {
id: string;
name: string;
agentURL: string;
authToken: string;
}
/**
* Create an external workspace and wire it to the echo runtime.
*/
export async function seedWorkspace(echoURL: string): Promise<SeededWorkspace> {
// 1. Create external workspace (no URL — platform will mint an auth token).
const runId = Math.random().toString(36).slice(2, 8);
const wsName = `Chat E2E Agent ${runId}`;
const createRes = await fetch(`${PLATFORM_URL}/workspaces`, {
method: "POST",
headers: { "Content-Type": "application/json" },
body: JSON.stringify({ name: wsName, tier: 1, external: true, runtime: "external" }),
});
if (!createRes.ok) {
const text = await createRes.text();
throw new Error(`Failed to create workspace: ${createRes.status} ${text}`);
}
const ws = (await createRes.json()) as {
id: string;
name: string;
connection?: { auth_token?: string };
};
const authToken = ws.connection?.auth_token;
if (!authToken) {
throw new Error("Workspace created but no auth_token returned");
}
// 2. Direct DB update: mark online + point url at echo runtime.
// The platform blocks loopback URLs at the API layer (SSRF guard),
// so we bypass via psql for local E2E.
const dbUrl = process.env.E2E_DATABASE_URL;
if (!dbUrl) {
throw new Error("E2E_DATABASE_URL must be set for DB seeding");
}
const pgRegex = /postgres:\/\/([^:]+):([^@]+)@([^:]+):(\d+)\/([^?]+)/;
const m = dbUrl.match(pgRegex);
if (!m) {
throw new Error(`Cannot parse E2E_DATABASE_URL: ${dbUrl}`);
}
const [, user, pass, host, port, db] = m;
// Pre-seed a platform_inbound_secret so chat file uploads don't trigger
// the lazy-heal 503 "retry in 30 s" path on first use.
const inboundSecret = Array.from({ length: 43 }, () =>
"ABCDEFGHIJKLMNOPQRSTUVWXYZabcdefghijklmnopqrstuvwxyz0123456789-_"[
Math.floor(Math.random() * 64)
],
).join("");
const psql = [
`PGPASSWORD=${pass} psql`,
`-h ${host} -p ${port} -U ${user} -d ${db}`,
`-c "UPDATE workspaces SET status = 'online', url = '${echoURL}', platform_inbound_secret = '${inboundSecret}' WHERE id = '${ws.id}'"`,
].join(" ");
const { execSync } = await import("node:child_process");
try {
execSync(psql, { stdio: "pipe", timeout: 30_000 });
} catch (err) {
throw new Error(`DB update failed: ${err}`);
}
return { id: ws.id, name: wsName, agentURL: echoURL, authToken };
}
/**
* Start a heartbeat interval that keeps an external workspace alive.
* Returns a stop function.
*/
export function startHeartbeat(
workspaceId: string,
authToken: string,
intervalMs = 30_000,
): () => void {
const send = () => {
fetch(`${PLATFORM_URL}/registry/heartbeat`, {
method: "POST",
headers: {
"Content-Type": "application/json",
Authorization: `Bearer ${authToken}`,
},
body: JSON.stringify({
workspace_id: workspaceId,
error_rate: 0,
sample_error: "",
active_tasks: 0,
current_task: "",
uptime_seconds: 0,
}),
}).catch(() => {});
};
// Send immediately so the first heartbeat lands before the stale sweep.
send();
const timer = setInterval(send, intervalMs);
return () => clearInterval(timer);
}
/**
* Seed chat-history rows for a workspace.
*/
export async function seedChatHistory(
workspaceId: string,
messages: Array<{ role: "user" | "agent"; content: string }>,
): Promise<void> {
const dbUrl = process.env.E2E_DATABASE_URL;
if (!dbUrl) return;
const pgRegex = /postgres:\/\/([^:]+):([^@]+)@([^:]+):(\d+)\/([^?]+)/;
const m = dbUrl.match(pgRegex);
if (!m) return;
const [, user, pass, host, port, db] = m;
const values = messages
.map(
(msg, i) =>
`('${randomUUID()}', '${workspaceId}', '${msg.role}', '${msg.content.replace(/'/g, "''")}', NOW() - INTERVAL '${messages.length - i} seconds')`,
)
.join(",");
const sql = `INSERT INTO chat_messages (id, workspace_id, role, content, created_at) VALUES ${values};`;
const { execSync } = await import("node:child_process");
const psql = `PGPASSWORD=${pass} psql -h ${host} -p ${port} -U ${user} -d ${db} -c "${sql}"`;
execSync(psql, { stdio: "pipe", timeout: 10_000 });
}
/**
* Delete a seeded workspace row directly from the DB.
* Uses psql (same credentials as seedWorkspace) so we bypass any
* workspace-server side-effects (container stop, cascade cleanup, etc.)
* that can race or 500 on external workspaces.
*/
export async function cleanupWorkspace(workspaceId: string): Promise<void> {
const dbUrl = process.env.E2E_DATABASE_URL;
if (!dbUrl) return;
const pgRegex = /postgres:\/\/([^:]+):([^@]+)@([^:]+):(\d+)\/([^?]+)/;
const m = dbUrl.match(pgRegex);
if (!m) return;
const [, user, pass, host, port, db] = m;
const psql = `PGPASSWORD=${pass} psql -h ${host} -p ${port} -U ${user} -d ${db} -c "DELETE FROM workspaces WHERE id = '${workspaceId}'"`;
const { execSync } = await import("node:child_process");
try {
execSync(psql, { stdio: "pipe", timeout: 30_000 });
} catch {
// Best-effort cleanup; don't fail the test suite if the row is already gone.
}
}
/**
* Mint a workspace auth token so the canvas can make authenticated API
* calls (WorkspaceAuth middleware).
*/
export async function mintTestToken(workspaceId: string): Promise<string> {
const res = await fetch(
`${PLATFORM_URL}/admin/workspaces/${workspaceId}/test-token`,
);
if (!res.ok) {
throw new Error(`Failed to mint test token: ${res.status}`);
}
const data = (await res.json()) as { auth_token: string };
return data.auth_token;
}
-180
View File
@@ -1,180 +0,0 @@
/**
* Minimal A2A echo runtime for E2E tests.
*
* Listens on an ephemeral port, receives A2A JSON-RPC `message/send`
* requests, and returns a response with the original text echoed back.
* Also implements the workspace-side chat upload ingest endpoint so
* file-attachment E2E can exercise the full upload → send → echo
* round-trip.
*
* Usage (inside test fixture):
* const echo = await startEchoRuntime();
* // ... seed workspace with agent_url pointing to echo.baseURL ...
* echo.stop();
*/
import { createServer, type Server } from "node:http";
export interface EchoRuntime {
baseURL: string;
stop: () => Promise<void>;
lastRequest: { method: string; text: string; files: unknown[] } | null;
}
/** Parse a minimal multipart body and extract the first file's name + content. */
function parseMultipart(body: Buffer): { name: string; mimeType: string; content: Buffer } | null {
// Find the boundary line (first line starting with "--").
const str = body.toString("binary");
const firstDash = str.indexOf("--");
if (firstDash === -1) return null;
const eol = str.indexOf("\r\n", firstDash);
if (eol === -1) return null;
const boundary = str.slice(firstDash + 2, eol);
const boundaryMarker = "\r\n--" + boundary;
// Find the first part that has a filename in Content-Disposition.
let pos = eol + 2;
while (pos < str.length) {
const nextBoundary = str.indexOf(boundaryMarker, pos);
if (nextBoundary === -1) break;
const part = str.slice(pos, nextBoundary);
const cdMatch = part.match(/Content-Disposition:[^\r\n]*filename="([^"]+)"/i);
if (cdMatch) {
const name = cdMatch[1];
const ctMatch = part.match(/Content-Type:\s*([^\r\n]+)/i);
const mimeType = ctMatch ? ctMatch[1].trim() : "application/octet-stream";
// Body starts after the first double-CRLF in the part.
const bodyStart = part.indexOf("\r\n\r\n");
if (bodyStart !== -1) {
// Extract the raw bytes (not the string) so binary is safe.
const headerBytes = Buffer.byteLength(part.slice(0, bodyStart + 4), "binary");
const partStartInBody = Buffer.byteLength(str.slice(0, pos + bodyStart + 4), "binary");
const partEndInBody = Buffer.byteLength(str.slice(0, nextBoundary), "binary");
const content = body.subarray(partStartInBody, partEndInBody);
return { name, mimeType, content };
}
}
pos = nextBoundary + boundaryMarker.length;
// Skip trailing "--" (end marker) or CRLF.
if (str.slice(pos, pos + 2) === "--") break;
if (str.slice(pos, pos + 2) === "\r\n") pos += 2;
}
return null;
}
export async function startEchoRuntime(): Promise<EchoRuntime> {
let lastRequest: EchoRuntime["lastRequest"] = null;
const server = createServer((req, res) => {
// CORS: allow the canvas origin (localhost:3000) to call us.
res.setHeader("Access-Control-Allow-Origin", "*");
res.setHeader("Access-Control-Allow-Methods", "POST, GET, OPTIONS");
res.setHeader("Access-Control-Allow-Headers", "Content-Type, Authorization");
if (req.method === "OPTIONS") {
res.writeHead(204);
res.end();
return;
}
const url = req.url ?? "/";
// Workspace-side chat upload ingest (RFC #2312).
if (url === "/internal/chat/uploads/ingest" && req.method === "POST") {
const chunks: Buffer[] = [];
req.on("data", (chunk: Buffer) => chunks.push(chunk));
req.on("end", () => {
const body = Buffer.concat(chunks);
const file = parseMultipart(body);
if (!file) {
res.writeHead(400);
res.end(JSON.stringify({ error: "no files field" }));
return;
}
const sanitized = file.name.replace(/[^a-zA-Z0-9._\-]/g, "_").replace(/ /g, "_");
const prefix = Array.from({ length: 32 }, () =>
Math.floor(Math.random() * 16).toString(16),
).join("");
const response = {
files: [
{
uri: `workspace:/workspace/.molecule/chat-uploads/${prefix}-${sanitized}`,
name: sanitized,
mimeType: file.mimeType,
size: file.content.length,
},
],
};
res.setHeader("Content-Type", "application/json");
res.writeHead(200);
res.end(JSON.stringify(response));
});
return;
}
// Default: A2A JSON-RPC handler.
let body = "";
req.setEncoding("utf8");
req.on("data", (chunk: string) => {
body += chunk;
});
req.on("end", () => {
res.setHeader("Content-Type", "application/json");
try {
const rpc = JSON.parse(body);
const msg = rpc.params?.message;
const textParts =
msg?.parts
?.filter((p: { kind?: string; text?: string }) => p.kind === "text")
.map((p: { text?: string }) => p.text)
.filter(Boolean) ?? [];
const fileParts =
msg?.parts?.filter((p: { kind?: string }) => p.kind === "file") ?? [];
const text = textParts.join("\n");
lastRequest = {
method: rpc.method ?? "unknown",
text,
files: fileParts,
};
const replyText = text
? `Echo: ${text}`
: fileParts.length > 0
? "Echo: received your file(s)."
: "Echo: hello";
const response = {
jsonrpc: "2.0",
id: rpc.id ?? null,
result: {
parts: [{ kind: "text", text: replyText }],
},
};
res.writeHead(200);
res.end(JSON.stringify(response));
} catch {
res.writeHead(400);
res.end(JSON.stringify({ error: "invalid json" }));
}
});
});
await new Promise<void>((resolve) => server.listen(0, "127.0.0.1", resolve));
const address = server.address();
const port = typeof address === "object" && address ? address.port : 0;
const baseURL = `http://127.0.0.1:${port}`;
return {
baseURL,
stop: () =>
new Promise((resolve) => {
server.close(() => resolve(undefined));
}),
get lastRequest() {
return lastRequest;
},
};
}
-1
View File
@@ -5,7 +5,6 @@ export default defineConfig({
timeout: 30_000,
expect: { timeout: 10_000 },
fullyParallel: false,
workers: 1,
retries: 0,
use: {
baseURL: "http://localhost:3000",
+2 -2
View File
@@ -344,7 +344,7 @@ function ProviderPickerModal({
// wrapper's bounds instead of the viewport.
if (typeof document === "undefined") return null;
const allSaved = entries.every((e) => e.saved);
const allSaved = entries.length > 0 && entries.every((e) => e.saved);
const anySaving = entries.some((e) => e.saving);
const runtimeLabel = runtime
.replace(/[-_]/g, " ")
@@ -616,7 +616,7 @@ function AllKeysModal({
if (!open) return null;
if (typeof document === "undefined") return null;
const allSaved = entries.every((e) => e.saved);
const allSaved = entries.length > 0 && entries.every((e) => e.saved);
const anySaving = entries.some((e) => e.saving);
const runtimeLabel = runtime
.replace(/[-_]/g, " ")
+13 -4
View File
@@ -62,12 +62,21 @@ export function ThemeToggle({ className = "" }: { className?: string }) {
}
setTheme(OPTIONS[next].value);
// Move focus to the new button so arrow-key navigation is continuous.
// Query is already scoped to radiogroup so no child-combinator needed;
// avoids accidentally focusing unrelated [role=radio] elements
// Use direct-child query to scope strictly to this radiogroup's buttons
// and avoid accidentally focusing unrelated [role=radio] elements
// elsewhere in the DOM (e.g. React Flow canvas nodes).
// Guard: skip focus if the current target is no longer in the document
// (e.g. React StrictMode double-invokes handlers during re-render).
if (!e.currentTarget.isConnected) return;
const radiogroup = e.currentTarget.closest("[role=radiogroup]") as HTMLElement | null;
const btns = radiogroup?.querySelectorAll<HTMLButtonElement>("[role=radio]");
btns?.[next]?.focus();
if (!radiogroup) return;
// Use children[] instead of querySelectorAll("> [role=radio]") to avoid
// jsdom's child-combinator selector parsing issues in test environments.
const btns = Array.from(radiogroup.children).filter(
(el): el is HTMLButtonElement =>
el.tagName === "BUTTON" && el.getAttribute("role") === "radio"
);
if (next < btns.length) btns[next]?.focus();
},
[]
);
+7 -10
View File
@@ -13,20 +13,17 @@ import { isExternalLikeRuntime } from "@/lib/externalRuntimes";
/** Descendant count for the "N sub" badge — children are first-class nodes
* rendered as full cards inside this one via React Flow's native parentId,
* so we don't need to subscribe to the actual child list here.
* Selecting `nodes` stably avoids a new selector reference on every store
* update (React error #185 / Zustand + React 19 Object.is strictness). */
* so we don't need to subscribe to the actual child list here. */
function useDescendantCount(nodeId: string): number {
const nodes = useCanvasStore((s) => s.nodes);
return useMemo(() => countDescendants(nodeId, nodes), [nodeId, nodes]);
return useCanvasStore(
useCallback((s) => countDescendants(nodeId, s.nodes), [nodeId])
);
}
/** Boolean flag used to drive min-size and NodeResizer dimensions.
* Selecting `nodes` stably avoids re-render loops (same issue as
* useDescendantCount). */
function useHasChildren(nodeId: string): boolean {
const nodes = useCanvasStore((s) => s.nodes);
return useMemo(() => nodes.some((n) => n.data.parentId === nodeId), [nodes, nodeId]);
return useCanvasStore(
useCallback((s) => s.nodes.some((n) => n.data.parentId === nodeId), [nodeId])
);
}
/** Eject/extract arrow icon — visually distinct from delete ✕ */
@@ -11,21 +11,13 @@ import { render, screen, fireEvent, cleanup, act } from "@testing-library/react"
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { TestConnectionButton } from "../ui/TestConnectionButton";
import type { SecretGroup } from "@/types/secrets";
import { validateSecret, ApiError } from "@/lib/api/secrets";
import { validateSecret } from "@/lib/api/secrets";
// ─── Mock validateSecret ──────────────────────────────────────────────────────
// vi.mock is hoisted, so validateSecret (imported above) refers to the mocked
// namespace value once vi.mock runs. Use vi.mocked() to access it in tests.
vi.mock("@/lib/api/secrets", () => ({
validateSecret: vi.fn(),
ApiError: class ApiError extends Error {
status: number;
constructor(status: number, message: string) {
super(message);
this.name = "ApiError";
this.status = status;
}
},
}));
// SecretGroup is a string literal type: 'github' | 'anthropic' | 'openrouter' | 'custom'
@@ -110,7 +102,7 @@ describe("TestConnectionButton — state machine", () => {
expect(screen.getByText("Permission denied")).toBeTruthy();
});
it("shows a connectivity message on a genuine network exception", async () => {
it("shows generic error message on unexpected exception", async () => {
vi.mocked(validateSecret).mockRejectedValue(new Error("timeout"));
render(<TestConnectionButton provider={toGroup("anthropic")} secretValue="sk-..." />);
@@ -118,23 +110,8 @@ describe("TestConnectionButton — state machine", () => {
await act(async () => { /* flush */ });
expect(screen.getByRole("alert")).toBeTruthy();
// A real thrown network error → honest connectivity message (not a
// fabricated "service down"); see internal#492.
expect(document.body.querySelector('[role="alert"]')?.textContent).toMatch(
/could not reach the validation service/i,
);
});
it("does not claim a timeout when the validate endpoint 404s (internal#492)", async () => {
vi.mocked(validateSecret).mockRejectedValue(new ApiError(404, "Not Found"));
render(<TestConnectionButton provider={toGroup("anthropic")} secretValue="sk-..." />);
fireEvent.click(screen.getByRole("button"));
await act(async () => { /* flush */ });
const alert = document.body.querySelector('[role="alert"]')?.textContent ?? "";
expect(alert).not.toMatch(/timed out/i);
expect(alert).toMatch(/not available/i);
// The error detail is hardcoded to "Connection timed out. Service may be down."
expect(document.body.querySelector('[role="alert"]')?.textContent).toMatch(/timed out/i);
});
});
@@ -24,8 +24,12 @@ vi.mock("@/lib/theme-provider", () => ({
})),
}));
// Wrap cleanup in act() so any pending React state updates (e.g. from
// keyDown handlers that call setTheme) flush before DOM unmount. Without
// this, cleanup() can race against pending renders and cause INDEX_SIZE_ERR
// when the handleKeyDown callback tries to query the DOM mid-teardown.
afterEach(() => {
cleanup();
act(() => { cleanup(); });
vi.clearAllMocks();
});
@@ -146,7 +150,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
const radios = screen.getAllByRole("radio");
// dark (index 2) is current; ArrowRight should wrap to light (index 0)
act(() => { radios[2].focus(); });
fireEvent.keyDown(radios[2], { key: "ArrowRight" });
act(() => { fireEvent.keyDown(radios[2], { key: "ArrowRight" }); });
expect(mockSetTheme).toHaveBeenCalledWith("light");
});
@@ -160,7 +164,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
const radios = screen.getAllByRole("radio");
// light (index 0) is current; ArrowLeft should go to dark (index 2)
act(() => { radios[0].focus(); });
fireEvent.keyDown(radios[0], { key: "ArrowLeft" });
act(() => { fireEvent.keyDown(radios[0], { key: "ArrowLeft" }); });
expect(mockSetTheme).toHaveBeenCalledWith("dark");
});
@@ -174,7 +178,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
const radios = screen.getAllByRole("radio");
// light (index 0) is current; ArrowDown should go to system (index 1)
act(() => { radios[0].focus(); });
fireEvent.keyDown(radios[0], { key: "ArrowDown" });
act(() => { fireEvent.keyDown(radios[0], { key: "ArrowDown" }); });
expect(mockSetTheme).toHaveBeenCalledWith("system");
});
@@ -187,7 +191,7 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
render(<ThemeToggle />);
const radios = screen.getAllByRole("radio");
act(() => { radios[2].focus(); });
fireEvent.keyDown(radios[2], { key: "Home" });
act(() => { fireEvent.keyDown(radios[2], { key: "Home" }); });
expect(mockSetTheme).toHaveBeenCalledWith("light");
});
@@ -200,14 +204,14 @@ describe("ThemeToggle — keyboard navigation (WCAG 2.1.1 / ARIA radiogroup)", (
render(<ThemeToggle />);
const radios = screen.getAllByRole("radio");
act(() => { radios[0].focus(); });
fireEvent.keyDown(radios[0], { key: "End" });
act(() => { fireEvent.keyDown(radios[0], { key: "End" }); });
expect(mockSetTheme).toHaveBeenCalledWith("dark");
});
it("does nothing on unrelated keys", () => {
render(<ThemeToggle />);
const radios = screen.getAllByRole("radio");
fireEvent.keyDown(radios[0], { key: "Enter" });
act(() => { fireEvent.keyDown(radios[0], { key: "Enter" }); });
expect(mockSetTheme).not.toHaveBeenCalled();
});
});
@@ -24,20 +24,16 @@ import {
*/
export function DropTargetBadge() {
const dragOverNodeId = useCanvasStore((s) => s.dragOverNodeId);
// Select nodes stably first — deriving targetName and childCount inside
// the same selector creates a new return value on every store mutation
// even when neither has changed (React error #185 / Zustand Object.is).
const nodes = useCanvasStore((s) => s.nodes);
const targetName = (() => {
if (!dragOverNodeId) return null;
const n = nodes.find((nn) => nn.id === dragOverNodeId);
const targetName = useCanvasStore((s) => {
if (!s.dragOverNodeId) return null;
const n = s.nodes.find((nn) => nn.id === s.dragOverNodeId);
return (n?.data as WorkspaceNodeData | undefined)?.name ?? null;
})();
const childCount = (() =>
!dragOverNodeId
});
const childCount = useCanvasStore((s) =>
!s.dragOverNodeId
? 0
: nodes.filter((n) => n.parentId === dragOverNodeId).length
)();
: s.nodes.filter((n) => n.parentId === s.dragOverNodeId).length,
);
const { getInternalNode, flowToScreenPosition } = useReactFlow();
if (!dragOverNodeId || !targetName) return null;
const internal = getInternalNode(dragOverNodeId);
@@ -1,6 +1,6 @@
"use client";
import { useCallback, useEffect, useMemo, useRef } from "react";
import { useCallback, useEffect, useRef } from "react";
import { useReactFlow } from "@xyflow/react";
import { useCanvasStore } from "@/store/canvas";
import { appendClass, removeClass } from "@/store/classNames";
@@ -153,17 +153,10 @@ export function useCanvasViewport() {
// fit, the user has to manually pan + zoom to find what they just
// created. Only fires when TRANSITIONING from some-provisioning to
// zero-provisioning — not on every re-render.
//
// Selecting `nodes` stably (array reference) avoids the
// `.filter().length` anti-pattern which creates a new number on every
// store update and breaks the wasProvisioning/hasProvisioning
// transition detection (React error #185 / Zustand + React 19).
const nodes = useCanvasStore((s) => s.nodes);
const provisioningCount = useMemo(
() => nodes.filter((n) => n.data.status === "provisioning").length,
[nodes],
const provisioningCount = useCanvasStore(
(s) => s.nodes.filter((n) => n.data.status === "provisioning").length,
);
const nodeCount = nodes.length;
const nodeCount = useCanvasStore((s) => s.nodes.length);
useEffect(() => {
const hasProvisioning = provisioningCount > 0;
+97 -352
View File
@@ -5,22 +5,22 @@
// that the desktop ChatTab uses, but with a slimmer surface: no
// attachments, no A2A topology overlay, no conversation tracing.
import { useEffect, useMemo, useRef, useState } from "react";
import ReactMarkdown from "react-markdown";
import remarkGfm from "remark-gfm";
import { useEffect, useRef, useState } from "react";
import { api } from "@/lib/api";
import { useCanvasStore } from "@/store/canvas";
import { type ChatAttachment, type ChatMessage, createMessage } from "@/components/tabs/chat/types";
import {
useChatHistory,
useChatSend,
useChatSocket,
} from "@/components/tabs/chat/hooks";
import { toMobileAgent } from "./components";
import { MOBILE_FONT_MONO, MOBILE_FONT_SANS, usePalette } from "./palette";
import { Icons, StatusDot, TierChip } from "./primitives";
interface ChatMessage {
id: string;
role: "user" | "agent" | "system";
text: string;
ts: string;
}
const formatStoredTimestamp = (iso: string): string => {
const d = new Date(iso);
if (isNaN(d.getTime())) return "";
@@ -29,171 +29,16 @@ const formatStoredTimestamp = (iso: string): string => {
type SubTab = "my" | "a2a";
function MarkdownBubble({
children,
dark,
accent,
}: {
children: string;
dark: boolean;
accent: string;
}) {
const codeBg = dark ? "rgba(255,255,255,0.08)" : "rgba(0,0,0,0.06)";
const codeBlockBg = dark ? "#1a1a1a" : "#f5f5f0";
const linkColor = accent;
const quoteBorder = dark ? "rgba(255,250,240,0.15)" : "rgba(40,30,20,0.15)";
return (
<ReactMarkdown
remarkPlugins={[remarkGfm]}
components={{
p: ({ children }) => (
<div style={{ margin: "2px 0", lineHeight: "inherit" }}>{children}</div>
),
a: ({ href, children }) => (
<a
href={href}
target="_blank"
rel="noopener noreferrer"
style={{ color: linkColor, textDecoration: "underline" }}
>
{children}
</a>
),
pre: ({ children }) => (
<pre
style={{
background: codeBlockBg,
padding: "8px 10px",
borderRadius: 8,
overflow: "auto",
fontSize: 12,
lineHeight: 1.5,
fontFamily: MOBILE_FONT_MONO,
margin: "4px 0",
}}
>
{children}
</pre>
),
code: ({ children, className }) => {
const isBlock = className != null && String(className).length > 0;
if (isBlock) {
return (
<code style={{ fontFamily: MOBILE_FONT_MONO, fontSize: 12 }}>
{children}
</code>
);
}
return (
<code
style={{
background: codeBg,
padding: "1px 4px",
borderRadius: 4,
fontSize: 13,
fontFamily: MOBILE_FONT_MONO,
}}
>
{children}
</code>
);
},
ul: ({ children }) => (
<ul style={{ margin: "4px 0", paddingLeft: 18, listStyle: "disc" }}>
{children}
</ul>
),
ol: ({ children }) => (
<ol style={{ margin: "4px 0", paddingLeft: 18, listStyle: "decimal" }}>
{children}
</ol>
),
li: ({ children }) => <li style={{ margin: "2px 0" }}>{children}</li>,
strong: ({ children }) => (
<strong style={{ fontWeight: 600 }}>{children}</strong>
),
em: ({ children }) => <em style={{ fontStyle: "italic" }}>{children}</em>,
h1: ({ children }) => (
<div style={{ fontSize: 16, fontWeight: 700, margin: "4px 0" }}>{children}</div>
),
h2: ({ children }) => (
<div style={{ fontSize: 15, fontWeight: 700, margin: "4px 0" }}>{children}</div>
),
h3: ({ children }) => (
<div style={{ fontSize: 14, fontWeight: 700, margin: "4px 0" }}>{children}</div>
),
h4: ({ children }) => (
<div style={{ fontSize: 14, fontWeight: 600, margin: "4px 0" }}>{children}</div>
),
h5: ({ children }) => (
<div style={{ fontSize: 13, fontWeight: 600, margin: "4px 0" }}>{children}</div>
),
h6: ({ children }) => (
<div style={{ fontSize: 13, fontWeight: 600, margin: "4px 0" }}>{children}</div>
),
blockquote: ({ children }) => (
<blockquote
style={{
borderLeft: `2px solid ${quoteBorder}`,
margin: "4px 0",
paddingLeft: 8,
opacity: 0.85,
}}
>
{children}
</blockquote>
),
hr: () => (
<hr
style={{
border: "none",
borderTop: `0.5px solid ${quoteBorder}`,
margin: "6px 0",
}}
/>
),
table: ({ children }) => (
<table
style={{
borderCollapse: "collapse",
fontSize: 13,
margin: "4px 0",
width: "100%",
}}
>
{children}
</table>
),
thead: ({ children }) => <thead style={{ fontWeight: 600 }}>{children}</thead>,
th: ({ children }) => (
<th
style={{
border: `0.5px solid ${quoteBorder}`,
padding: "4px 6px",
textAlign: "left",
}}
>
{children}
</th>
),
td: ({ children }) => (
<td
style={{
border: `0.5px solid ${quoteBorder}`,
padding: "4px 6px",
}}
>
{children}
</td>
),
}}
>
{children}
</ReactMarkdown>
);
interface A2AResponseShape {
result?: {
parts?: Array<{ kind?: string; text?: string }>;
};
error?: { message?: string };
}
const formatTime = (date: Date) =>
date.toLocaleTimeString([], { hour: "numeric", minute: "2-digit" });
export function MobileChat({
agentId,
dark,
@@ -204,40 +49,34 @@ export function MobileChat({
onBack: () => void;
}) {
const p = usePalette(dark);
const nodes = useCanvasStore((s) => s.nodes);
const node = useMemo(() => nodes.find((n) => n.id === agentId), [nodes, agentId]);
const node = useCanvasStore((s) => s.nodes.find((n) => n.id === agentId));
// Bootstrap from the canvas store's per-workspace message buffer so the
// user sees their prior thread on entry. The store is updated by the
// socket → ChatTab flows the desktop runs; on mobile we read from the
// same buffer to keep state coherent across viewports.
// NOTE: selector returns undefined (stable) — do NOT use ?? [] here,
// that creates a new [] reference on every store update when the key is
// absent, causing infinite re-render (React error #185).
const storedMessages = useCanvasStore((s) => s.agentMessages[agentId]);
const [messages, setMessages] = useState<ChatMessage[]>(() =>
(storedMessages ?? []).map((m) => ({
id: m.id,
role: "agent",
text: m.content,
ts: formatStoredTimestamp(m.timestamp),
})),
);
const [draft, setDraft] = useState("");
const [tab, setTab] = useState<SubTab>("my");
const [sending, setSending] = useState(false);
const [error, setError] = useState<string | null>(null);
const scrollRef = useRef<HTMLDivElement>(null);
// Synchronous re-entry guard. `setSending(true)` schedules a state
// update but doesn't flush before a second tap can fire send() — a ref
// mirrors the desktop ChatTab pattern (sendInFlightRef) and closes the
// double-send race a stale `sending` lets through.
const sendInFlightRef = useRef(false);
const composerRef = useRef<HTMLTextAreaElement>(null);
const fileInputRef = useRef<HTMLInputElement>(null);
const [pendingFiles, setPendingFiles] = useState<File[]>([]);
const {
messages,
loading: historyLoading,
loadError: historyError,
loadInitial,
appendMessageDeduped,
} = useChatHistory(agentId);
const {
sending,
uploading,
sendMessage,
error: sendError,
clearError,
releaseSendGuards,
} = useChatSend(agentId, {
getHistoryMessages: () => messages,
onUserMessage: appendMessageDeduped,
onAgentMessage: appendMessageDeduped,
});
useChatSocket(agentId, {
onAgentMessage: appendMessageDeduped,
onSendComplete: releaseSendGuards,
});
// Auto-grow the textarea: reset height to 'auto' so the scrollHeight
// shrinks when the user deletes text, then size to scrollHeight up to
@@ -256,20 +95,6 @@ export function MobileChat({
}
}, [messages]);
// Consume any agent messages that arrived while history was loading.
const initialConsumeDoneRef = useRef(false);
useEffect(() => {
if (historyLoading || initialConsumeDoneRef.current) return;
initialConsumeDoneRef.current = true;
const consume = useCanvasStore.getState().consumeAgentMessages;
const msgs = consume(agentId);
for (const m of msgs) {
appendMessageDeduped(
createMessage("agent", m.content, m.attachments),
);
}
}, [historyLoading, agentId, appendMessageDeduped]);
if (!node) {
return (
<div
@@ -291,32 +116,58 @@ export function MobileChat({
const a = toMobileAgent(node);
const reachable = a.status === "online" || a.status === "degraded";
const onFilesPicked = (fileList: FileList | null) => {
if (!fileList) return;
const picked = Array.from(fileList);
setPendingFiles((prev) => {
const keyed = new Set(prev.map((f) => `${f.name}:${f.size}`));
return [...prev, ...picked.filter((f) => !keyed.has(`${f.name}:${f.size}`))];
});
if (fileInputRef.current) fileInputRef.current.value = "";
};
const removePendingFile = (index: number) =>
setPendingFiles((prev) => prev.filter((_, i) => i !== index));
const send = async () => {
const text = draft.trim();
if ((!text && pendingFiles.length === 0) || sending || !reachable) return;
clearError();
if (!text || sending || !reachable) return;
if (sendInFlightRef.current) return;
sendInFlightRef.current = true;
setDraft("");
const files = pendingFiles;
setPendingFiles([]);
await sendMessage(text, files);
setError(null);
setSending(true);
const myMsg: ChatMessage = {
id: crypto.randomUUID(),
role: "user",
text,
ts: formatTime(new Date()),
};
setMessages((m) => [...m, myMsg]);
try {
const res = await api.post<A2AResponseShape>(`/workspaces/${agentId}/a2a`, {
method: "message/send",
params: {
message: {
role: "user",
messageId: crypto.randomUUID(),
parts: [{ kind: "text", text }],
},
},
});
const reply =
res.result?.parts?.find((part) => part.kind === "text")?.text ?? "";
if (reply) {
setMessages((m) => [
...m,
{
id: crypto.randomUUID(),
role: "agent",
text: reply,
ts: formatTime(new Date()),
},
]);
} else if (res.error?.message) {
setError(res.error.message);
}
} catch (e) {
setError(e instanceof Error ? e.message : "Failed to send");
} finally {
setSending(false);
sendInFlightRef.current = false;
}
};
return (
<div
data-testid="chat-panel"
style={{
height: "100%",
display: "flex",
@@ -457,42 +308,7 @@ export function MobileChat({
Agent Comms peer-to-peer A2A traffic surfaces in the Comms tab.
</div>
)}
{tab === "my" && historyLoading && (
<div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
Loading chat history
</div>
)}
{tab === "my" && !historyLoading && historyError && messages.length === 0 && (
<div
role="alert"
style={{
padding: "14px 4px",
textAlign: "center",
color: p.failed,
fontSize: 13,
}}
>
<div style={{ marginBottom: 8 }}>Could not load chat history.</div>
<button
type="button"
onClick={() => {
loadInitial();
}}
style={{
padding: "6px 14px",
borderRadius: 14,
border: `0.5px solid ${p.failed}`,
background: "transparent",
color: p.failed,
fontSize: 12,
cursor: "pointer",
}}
>
Retry
</button>
</div>
)}
{tab === "my" && !historyLoading && !historyError && messages.length === 0 && (
{tab === "my" && messages.length === 0 && (
<div style={{ padding: "20px 4px", textAlign: "center", color: p.text3, fontSize: 13 }}>
Send a message to start chatting.
</div>
@@ -521,9 +337,7 @@ export function MobileChat({
overflowWrap: "anywhere",
}}
>
<MarkdownBubble dark={dark} accent={p.accent}>
{m.content}
</MarkdownBubble>
{m.text}
<div
style={{
fontSize: 10,
@@ -532,13 +346,13 @@ export function MobileChat({
fontFamily: MOBILE_FONT_MONO,
}}
>
{formatStoredTimestamp(m.timestamp)}
{m.ts}
</div>
</div>
</div>
);
})}
{sendError && (
{error && (
<div
role="alert"
style={{
@@ -550,7 +364,7 @@ export function MobileChat({
fontSize: 12,
}}
>
{sendError}
{error}
</div>
)}
</div>
@@ -581,60 +395,6 @@ export function MobileChat({
backdropFilter: "blur(14px)",
}}
>
{pendingFiles.length > 0 && (
<div
style={{
display: "flex",
flexWrap: "wrap",
gap: 6,
marginBottom: 8,
paddingLeft: 2,
}}
>
{pendingFiles.map((f, i) => (
<div
key={`${f.name}:${f.size}`}
style={{
display: "flex",
alignItems: "center",
gap: 4,
padding: "3px 8px",
borderRadius: 10,
background: dark ? "#2a2823" : "#ece9e0",
fontSize: 12,
color: p.text2,
maxWidth: "100%",
}}
>
<span
style={{
overflow: "hidden",
textOverflow: "ellipsis",
whiteSpace: "nowrap",
}}
>
{f.name}
</span>
<button
type="button"
onClick={() => removePendingFile(i)}
aria-label={`Remove ${f.name}`}
style={{
border: "none",
background: "transparent",
color: p.text3,
cursor: "pointer",
fontSize: 12,
padding: 0,
lineHeight: 1,
}}
>
</button>
</div>
))}
</div>
)}
<div
style={{
display: "flex",
@@ -646,32 +406,21 @@ export function MobileChat({
padding: "6px 6px 6px 12px",
}}
>
<input
ref={fileInputRef}
type="file"
multiple
style={{ display: "none" }}
onChange={(e) => onFilesPicked(e.target.files)}
aria-hidden="true"
/>
<button
type="button"
onClick={() => fileInputRef.current?.click()}
disabled={!reachable || sending || uploading}
aria-label="Attach"
style={{
width: 32,
height: 32,
borderRadius: 999,
border: "none",
cursor: reachable && !sending && !uploading ? "pointer" : "not-allowed",
cursor: "pointer",
background: "transparent",
color: p.text3,
flexShrink: 0,
display: "flex",
alignItems: "center",
justifyContent: "center",
opacity: !reachable || sending || uploading ? 0.4 : 1,
}}
>
{Icons.attach({ size: 16 })}
@@ -717,32 +466,28 @@ export function MobileChat({
<button
type="button"
onClick={send}
disabled={(!draft.trim() && pendingFiles.length === 0) || !reachable || sending || uploading}
disabled={!draft.trim() || !reachable || sending}
aria-label="Send"
style={{
width: 36,
height: 36,
borderRadius: 999,
border: "none",
cursor: (draft.trim() || pendingFiles.length > 0) && !sending && !uploading ? "pointer" : "not-allowed",
cursor: draft.trim() && !sending ? "pointer" : "not-allowed",
flexShrink: 0,
background:
(draft.trim() || pendingFiles.length > 0) && reachable && !sending && !uploading
draft.trim() && reachable && !sending
? p.accent
: dark
? "#2a2823"
: "#ece9e0",
color: (draft.trim() || pendingFiles.length > 0) && reachable && !sending && !uploading ? "#fff" : p.text3,
color: draft.trim() && reachable && !sending ? "#fff" : p.text3,
display: "flex",
alignItems: "center",
justifyContent: "center",
}}
>
{uploading ? (
<span style={{ fontSize: 10, fontWeight: 600 }}></span>
) : (
Icons.send({ size: 16 })
)}
{Icons.send({ size: 16 })}
</button>
</div>
</div>
@@ -2,7 +2,7 @@
// 03 · Agent detail — pills + tabbed content (Overview/Activity/Config/Memory).
import { useEffect, useMemo, useState } from "react";
import { useEffect, useState } from "react";
import { api } from "@/lib/api";
import { useCanvasStore } from "@/store/canvas";
@@ -32,10 +32,7 @@ export function MobileDetail({
onChat: () => void;
}) {
const p = usePalette(dark);
// Selecting `nodes` stably avoids the `.find()` anti-pattern that
// creates a new return value on every store update (React error #185).
const nodes = useCanvasStore((s) => s.nodes);
const node = useMemo(() => nodes.find((n) => n.id === agentId), [nodes, agentId]);
const node = useCanvasStore((s) => s.nodes.find((n) => n.id === agentId));
const [tab, setTab] = useState<TabId>("overview");
if (!node) {
@@ -214,7 +211,6 @@ export function MobileDetail({
<button
type="button"
onClick={onChat}
data-testid="mobile-chat-cta"
style={{
width: "100%",
height: 52,
@@ -8,19 +8,11 @@
* NOTE: No @testing-library/jest-dom — use DOM APIs.
*/
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { act, cleanup, render, waitFor } from "@testing-library/react";
import { cleanup, render } from "@testing-library/react";
import React from "react";
import { MobileChat } from "../MobileChat";
// ─── Mock API ─────────────────────────────────────────────────────────────────
// vi.mock without a factory auto-mocks the module. In tests, we configure
// api.get / api.post directly (they are vi.fn() from the auto-mock).
// Tests that need specific behaviour use mockResolvedValueOnce on the
// auto-mocked functions.
vi.mock("@/lib/api");
import { api } from "@/lib/api";
// ─── Mock store ───────────────────────────────────────────────────────────────
const mockAgentId = "ws-chat-test";
@@ -36,19 +28,12 @@ const mockStoreState = {
height?: number;
}>,
agentMessages: {} as Record<string, Array<{ id: string; content: string; timestamp: string }>>,
consumeAgentMessages: () => [],
};
vi.mock("@/store/canvas", () => ({
useCanvasStore: Object.assign(
vi.fn((sel?: (state: typeof mockStoreState) => unknown) => {
if (sel) return sel(mockStoreState);
return mockStoreState;
}),
{
getState: () => mockStoreState,
subscribe: vi.fn(() => vi.fn()),
},
vi.fn((sel) => sel(mockStoreState)),
{ getState: () => mockStoreState },
),
summarizeWorkspaceCapabilities: vi.fn((data: Record<string, unknown>) => {
const agentCard = data.agentCard as Record<string, unknown> | null;
@@ -69,6 +54,16 @@ vi.mock("@/store/canvas", () => ({
}),
}));
// ─── Mock API ─────────────────────────────────────────────────────────────────
const { mockApiPost } = vi.hoisted(() => ({
mockApiPost: vi.fn().mockResolvedValue({ result: { parts: [] } }),
}));
vi.mock("@/lib/api", () => ({
api: { post: mockApiPost },
}));
// ─── Fixtures ────────────────────────────────────────────────────────────────
const onlineNode = {
@@ -155,15 +150,7 @@ beforeEach(() => {
mockOnBack.mockClear();
mockStoreState.nodes = [];
mockStoreState.agentMessages = {};
// Set up spies on the real api methods. Tests override these per-call.
const getSpy = vi.spyOn(api, "get");
const postSpy = vi.spyOn(api, "post");
getSpy.mockResolvedValue({ messages: [], reached_end: true });
postSpy.mockResolvedValue({ result: { parts: [] } });
});
afterEach(() => {
vi.restoreAllMocks();
mockApiPost.mockClear();
});
afterEach(() => {
@@ -279,26 +266,15 @@ describe("MobileChat — empty state", () => {
mockStoreState.nodes = [onlineNode];
});
it('shows "Send a message to start chatting." when no messages', async () => {
// History fetch resolves immediately in tests (mockResolvedValue).
// act() flushes the microtask queue so the component reaches its
// post-load state before we assert.
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
it('shows "Send a message to start chatting." when no messages', () => {
const { container } = renderChat(mockAgentId);
expect(container.textContent ?? "").toContain("Send a message to start chatting.");
});
it("shows no messages when agentMessages[agentId] is absent (undefined)", async () => {
it("shows no messages when agentMessages[agentId] is absent (undefined)", () => {
// Explicitly set to empty to simulate no stored messages
mockStoreState.agentMessages = {};
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
const { container } = renderChat(mockAgentId);
expect(container.textContent ?? "").toContain("Send a message to start chatting.");
});
});
@@ -345,132 +321,3 @@ describe("MobileChat — dark mode", () => {
expect(container.querySelector('[aria-label="Back"]')).toBeTruthy();
});
});
// ─── Chat history loading ────────────────────────────────────────────────────
describe("MobileChat — chat history", () => {
beforeEach(() => {
mockStoreState.nodes = [onlineNode];
});
it("calls GET /workspaces/:id/chat-history on mount", async () => {
await act(async () => {
renderChat(mockAgentId);
});
expect(api.get).toHaveBeenCalledWith(
expect.stringContaining(`/workspaces/${mockAgentId}/chat-history`),
);
});
it("shows loading state while history is fetching", () => {
// Do NOT await — check the pre-resolve state.
const { container } = renderChat(mockAgentId);
expect(container.textContent ?? "").toContain("Loading chat history…");
});
it("shows empty state after history resolves with no messages", async () => {
// beforeEach already sets api.get to resolve with empty — no override needed.
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
expect(container.textContent ?? "").toContain("Send a message to start chatting.");
});
it("renders messages from history response", async () => {
vi.spyOn(api, "get").mockResolvedValueOnce({
messages: [
{
id: "msg-1",
role: "user",
content: "Hello agent",
timestamp: "2026-04-25T10:00:00Z",
},
{
id: "msg-2",
role: "agent",
content: "Hello back",
timestamp: "2026-04-25T10:00:01Z",
},
],
reached_end: true,
});
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
expect(container.textContent ?? "").toContain("Hello agent");
expect(container.textContent ?? "").toContain("Hello back");
});
it("maps user role from API correctly", async () => {
vi.spyOn(api, "get").mockResolvedValueOnce({
messages: [
{
id: "msg-u",
role: "user",
content: "user message",
timestamp: "2026-04-25T10:00:00Z",
},
],
reached_end: true,
});
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
// User messages render right-aligned. The text content check is sufficient
// to confirm the message appeared.
const { container } = renderResult!;
expect(container.textContent ?? "").toContain("user message");
});
it("shows error state when history fetch fails", async () => {
vi.spyOn(api, "get").mockRejectedValue(new Error("Network error"));
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
expect(container.textContent ?? "").toContain("Could not load chat history.");
expect(container.textContent ?? "").toContain("Retry");
});
it("Retry button re-fetches history after error", async () => {
// Make the initial mount call fail so the Retry button appears, then
// make the retry call succeed so we can verify the full flow.
const getSpy = vi.spyOn(api, "get");
getSpy
.mockRejectedValueOnce(new Error("Network error"))
.mockResolvedValueOnce({ messages: [], reached_end: true });
let renderResult: ReturnType<typeof renderChat>;
await act(async () => {
renderResult = renderChat(mockAgentId);
});
const { container } = renderResult!;
// Error state should be shown with Retry button.
expect(container.textContent ?? "").toContain("Could not load chat history.");
expect(container.textContent ?? "").toContain("Retry");
// Click Retry — the button's onClick fires api.get again.
// The second mockResolvedValueOnce makes it succeed.
const retryBtn = Array.from(container.querySelectorAll("button")).find(
(b) => b.textContent?.trim() === "Retry",
);
expect(retryBtn).toBeTruthy();
await act(async () => {
retryBtn?.click();
});
// waitFor polls until the retry resolves and component re-renders.
await waitFor(() => {
expect(container.textContent ?? "").toContain("Send a message to start chatting.");
});
// Initial call + retry = 2.
expect(getSpy).toHaveBeenCalledTimes(2);
});
});
@@ -288,7 +288,6 @@ export function AgentCard({
return (
<button
type="button"
data-testid="workspace-card"
aria-label={`${agent.name}, status: ${agent.status}, tier ${agent.tier}${agent.remote ? ", remote" : ""}`}
onClick={onClick}
style={{
+23 -19
View File
@@ -3,24 +3,16 @@ import { useState, useCallback, useRef, useEffect } from 'react';
import type { Secret, SecretGroup } from '@/types/secrets';
import { useSecretsStore } from '@/stores/secrets-store';
import { StatusBadge } from '@/components/ui/StatusBadge';
import { RevealToggle } from '@/components/ui/RevealToggle';
import { KeyValueField } from '@/components/ui/KeyValueField';
import { ValidationHint } from '@/components/ui/ValidationHint';
import { TestConnectionButton } from '@/components/ui/TestConnectionButton';
import { validateSecretValue } from '@/lib/validation/secret-formats';
import { SERVICES } from '@/lib/services';
const AUTO_HIDE_MS = 30_000;
const VALIDATION_DEBOUNCE_MS = 400;
// Secret values are write-only from the browser: the server List endpoint
// "Never exposes values", there is no per-secret decrypt route, and the
// only decrypted path (GET /secrets/values) is bulk + token-gated for
// remote agents. The old eye/RevealToggle was a dead affordance — it
// flipped its own icon but could never reveal anything, which read as
// "this doesn't work" (esp. once clicked → eye-with-slash). We show an
// honest static indicator instead; rotation is via Edit.
const WRITE_ONLY_TITLE =
'Value is write-only and cannot be revealed — use Edit to replace/rotate it';
interface SecretRowProps {
secret: Secret;
workspaceId: string;
@@ -39,12 +31,28 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
const setSecretStatus = useSecretsStore((s) => s.setSecretStatus);
const isEditing = editingKey === secret.name;
const [revealed, setRevealed] = useState(false);
const [editValue, setEditValue] = useState('');
const [validationError, setValidationError] = useState<string | null>(null);
const [isSaving, setIsSaving] = useState(false);
const [saveError, setSaveError] = useState<string | null>(null);
const debounceRef = useRef<ReturnType<typeof setTimeout>>(undefined);
const editBtnRef = useRef<HTMLButtonElement>(null);
const revealTimerRef = useRef<ReturnType<typeof setTimeout>>(undefined);
// Auto-hide revealed value after 30s
useEffect(() => {
if (revealed) {
clearTimeout(revealTimerRef.current);
revealTimerRef.current = setTimeout(() => setRevealed(false), AUTO_HIDE_MS);
return () => clearTimeout(revealTimerRef.current);
}
}, [revealed]);
// Reset revealed state when panel closes (session-only)
useEffect(() => {
return () => setRevealed(false);
}, []);
// Debounced validation
useEffect(() => {
@@ -125,15 +133,11 @@ export function SecretRow({ secret, workspaceId }: SecretRowProps) {
{secret.masked_value}
</span>
<div className="secret-row__actions">
<span
data-testid="write-only-indicator"
className="secret-row__write-only"
role="img"
aria-label={`${secret.name} value is write-only and cannot be revealed; use Edit to replace it`}
title={WRITE_ONLY_TITLE}
>
🔒
</span>
<RevealToggle
revealed={revealed}
onToggle={() => setRevealed((r) => !r)}
label={`Toggle reveal ${secret.name}`}
/>
<StatusBadge status={secret.status} />
<button
type="button"
@@ -16,40 +16,7 @@ interface TokensTabProps {
workspaceId: string;
}
// The settings panel passes the literal sentinel "global" when no canvas
// node is selected. Workspace tokens are inherently per-workspace — there
// is no /workspaces/global/tokens endpoint (querying the uuid column with
// "global" 500s on Postgres). The org-wide equivalent lives in the
// separate "Org API Keys" tab. Mirrors the sentinel-awareness that
// api/secrets.ts already has (workspaceId === 'global' → /settings/secrets).
const GLOBAL_WORKSPACE_ID = 'global';
export function TokensTab({ workspaceId }: TokensTabProps) {
if (workspaceId === GLOBAL_WORKSPACE_ID) {
return (
<div className="p-4 space-y-4">
<div>
<h3 className="text-sm font-semibold text-ink">API Tokens</h3>
<p className="text-[10px] text-ink-mid mt-0.5">
Bearer tokens for authenticating API calls to this workspace.
</p>
</div>
<div className="text-center py-6">
<p className="text-xs text-ink-mid">Select a workspace node first</p>
<p className="text-[10px] text-ink-mid mt-1">
Workspace tokens are scoped to a single workspace. Select a node
on the canvas to manage its tokens, or use the{' '}
<span className="text-accent font-medium">Org API Keys</span> tab
for org-wide API keys.
</p>
</div>
</div>
);
}
return <WorkspaceTokensTab workspaceId={workspaceId} />;
}
function WorkspaceTokensTab({ workspaceId }: TokensTabProps) {
const [tokens, setTokens] = useState<Token[]>([]);
const [loading, setLoading] = useState(true);
const [creating, setCreating] = useState(false);
@@ -138,54 +138,14 @@ describe("SecretRow — display mode", () => {
expect(document.querySelector('[role="row"]')).toBeTruthy();
});
it("has Copy, Edit, Delete buttons", () => {
it("has Reveal, Copy, Edit, Delete buttons", () => {
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
expect(screen.getByTestId("reveal-toggle")).toBeTruthy();
expect(screen.getByRole("button", { name: /copy/i })).toBeTruthy();
expect(screen.getByRole("button", { name: /edit/i })).toBeTruthy();
expect(screen.getByRole("button", { name: /delete/i })).toBeTruthy();
});
// Regression: the reveal/eye control was a dead affordance. Clicking it
// flipped its own icon (eye → eye-with-slash) but never revealed the value,
// because secret values are write-only from the browser (server List
// "Never exposes values"; there is no per-secret decrypt endpoint and the
// client has no plaintext-fetch function). The honest fix removes the
// toggle and shows a static "write-only / cannot be revealed" indicator.
// See internal tracking issue + internal#210/#211.
it("does NOT render a reveal/eye toggle (values are write-only)", () => {
render(<SecretRow secret={GITHUB_SECRET} workspaceId="ws-1" />);
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
expect(
screen.queryByRole("button", { name: /toggle reveal/i }),
).toBeNull();
});
it("shows a write-only indicator explaining the value cannot be revealed", () => {
render(<SecretRow secret={ANTHROPIC_SECRET} workspaceId="ws-1" />);
const indicator = screen.getByTestId("write-only-indicator");
expect(indicator).toBeTruthy();
// Affordance must be honest: explain it cannot be revealed and that
// Edit is the rotate path. It must not be a clickable button.
const title = indicator.getAttribute("title") ?? "";
expect(title.toLowerCase()).toMatch(/write-only|cannot be revealed/);
expect(indicator.tagName).not.toBe("BUTTON");
});
it("write-only indicator is present for the Anthropic/OAuth-token row too", () => {
// The reported bug singled out CLAUDE_CODE_OAUTH_TOKEN (anthropic group);
// the fix is group-agnostic — every row gets the same honest affordance.
const OAUTH_SECRET = {
name: "CLAUDE_CODE_OAUTH_TOKEN",
masked_value: "••••••••••••••••9d2a",
group: "anthropic" as const,
status: "unverified" as const,
updated_at: "2024-01-04",
};
render(<SecretRow secret={OAUTH_SECRET} workspaceId="ws-1" />);
expect(screen.queryByTestId("reveal-toggle")).toBeNull();
expect(screen.getByTestId("write-only-indicator")).toBeTruthy();
});
it("shows invalid status correctly", () => {
render(<SecretRow secret={CUSTOM_SECRET} workspaceId="ws-1" />);
expect(screen.getByTestId("status-badge").getAttribute("data-status")).toBe("invalid");
@@ -302,35 +302,3 @@ describe("TokensTab — error", () => {
expect(document.querySelector('[role="status"]')).toBeNull();
});
});
// ─── "global" sentinel (no node selected) ────────────────────────────────────
//
// Regression: SettingsPanel passes the literal "global" when no canvas
// node is selected. workspace tokens are per-workspace and there is no
// /workspaces/global/tokens endpoint — calling it 500'd
// ("invalid input syntax for type uuid: global"). The tab must NOT call
// the API in that state and must point the user at the Org API Keys tab.
describe("TokensTab — global sentinel (no node selected)", () => {
beforeEach(() => {
mockApiGet.mockReset();
mockApiPost.mockReset();
mockApiGet.mockRejectedValue(new Error("should not be called"));
});
it("does not call the API and shows a pointer to Org API Keys", async () => {
render(<TokensTab workspaceId="global" />);
await flush();
expect(mockApiGet).not.toHaveBeenCalled();
expect(mockApiPost).not.toHaveBeenCalled();
expect(document.body.textContent).toContain("Select a workspace node");
expect(document.body.textContent).toContain("Org API Keys");
// No error banner, no scary 500 surfacing.
expect(document.querySelector(".text-bad")).toBeNull();
});
it("has no create button in the global state", async () => {
render(<TokensTab workspaceId="global" />);
await flush();
expect(document.body.textContent).not.toContain("New Token");
});
});
+696 -123
View File
@@ -5,19 +5,16 @@ import ReactMarkdown from "react-markdown";
import remarkGfm from "remark-gfm";
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 { downloadChatFile, isPlatformAttachment } from "./chat/uploads";
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";
import { runtimeDisplayName } from "@/lib/runtime-names";
import { ConfirmDialog } from "@/components/ConfirmDialog";
import { useChatHistory } from "./chat/hooks/useChatHistory";
import { useChatSend } from "./chat/hooks/useChatSend";
import { useChatSocket } from "./chat/hooks/useChatSocket";
export { extractReplyText } from "./chat/hooks/useChatSend";
interface Props {
workspaceId: string;
@@ -26,6 +23,147 @@ interface Props {
type ChatSubTab = "my-chat" | "agent-comms";
// A2A response shape (subset). The full schema is in @a2a-js/sdk but we only
// need parts/artifacts text + file extraction for the synchronous fallback.
interface A2AFileRef {
name?: string;
mimeType?: string;
uri?: string;
bytes?: string;
size?: number;
}
// Outbound shape matches a2a-sdk's JSON-RPC `SendMessageRequest`
// Pydantic union (TextPart | FilePart | DataPart). The flat
// protobuf shape `{url, filename, mediaType}` is rejected at the
// request boundary with `Field required` errors — keep this
// outbound shape unless a2a-sdk migrates the JSON-RPC schema.
interface A2APart {
kind: string;
text?: string;
file?: A2AFileRef;
}
interface A2AResponse {
result?: {
parts?: A2APart[];
artifacts?: Array<{ parts: A2APart[] }>;
};
}
// Internal-self-message filtering moved server-side in RFC #2945
// PR-C/D — the platform's /chat-history endpoint applies the
// IsInternalSelfMessage predicate before returning rows, so the
// client no longer needs the local backstop on the history path.
// The proper fix is still X-Workspace-ID header (source_id=workspace_id);
// the platform-side prefix filter handles the residual cases.
// extractReplyText pulls the agent's text reply out of an A2A response.
// Concatenates ALL text parts (joined with "\n") rather than returning
// just the first. Claude Code and other runtimes commonly emit multi-
// part text replies for long content (markdown tables, code blocks),
// and the prior "first part wins" implementation silently truncated
// the rest — observed on a 15k-char Wave 1 brief that rendered only
// the table header. Mirrors extractTextsFromParts in message-parser.ts.
//
// Server-side counterpart in workspace-server/internal/channels/
// manager.go has the same single-part bug; fix that too if/when a
// channel-delivered reply (Slack, Lark, etc.) gets truncated.
export function extractReplyText(resp: A2AResponse): string {
const collect = (parts: A2APart[] | undefined): string => {
if (!parts) return "";
return parts
.filter((p) => p.kind === "text")
.map((p) => p.text ?? "")
.filter(Boolean)
.join("\n");
};
const result = resp?.result;
const collected: string[] = [];
const fromParts = collect(result?.parts);
if (fromParts) collected.push(fromParts);
// Walk artifacts even if parts had text — some producers (Hermes
// tool calls) emit a summary in parts AND details in artifacts.
// Returning early on parts dropped the artifact body silently.
if (result?.artifacts) {
for (const a of result.artifacts) {
const t = collect(a.parts);
if (t) collected.push(t);
}
}
return collected.join("\n");
}
// Agent-returned files live on the same response shape as text —
// delegated to extractFilesFromTask in message-parser.ts, which also
// walks status.message.parts (that ChatTab's legacy text extractor
// doesn't). Single source of truth for file-part parsing across
// live chat, activity log replay, and any future consumers.
/** Initial chat history page size. The newest N messages are rendered
* on first paint; older history is fetched on demand via loadOlder()
* when the user scrolls the top sentinel into view. */
const INITIAL_HISTORY_LIMIT = 10;
/** Subsequent older-history batch size. Larger than INITIAL so a long
* scroll-back doesn't fan out into many round-trips. */
const OLDER_HISTORY_BATCH = 20;
/**
* Load chat history from the platform's typed /chat-history endpoint.
*
* Server-side rendering of activity_logs rows into ChatMessage shape
* lives in workspace-server/internal/messagestore/postgres_store.go
* (RFC #2945 PR-C/D). The server already applies the canvas-source
* filter, the internal-self-message predicate, the role decision
* (status=error vs agent-error prefix → system), and the v0/v1
* file-shape extraction. Canvas just renders what it receives.
*
* Wire shape (mirrors ChatMessage exactly, no per-row mapping needed):
*
* GET /workspaces/:id/chat-history?limit=N&before_ts=T
* 200 → {"messages": ChatMessage[], "reached_end": boolean}
*
* Pagination:
* - Pass `limit` to bound the page size (newest-first from server).
* - Pass `beforeTs` (RFC3339) to fetch rows STRICTLY OLDER than that
* timestamp. Combined with limit, this yields the next-older page
* when scrolling backward through history.
*
* `reachedEnd` is propagated from the server. The server computes it
* by comparing rowCount vs limit so a partial last page is correctly
* detected even when the row→bubble fan-out is non-1:1 (each row
* produces 1-2 bubbles).
*/
async function loadMessagesFromDB(
workspaceId: string,
limit: number,
beforeTs?: string,
): Promise<{ messages: ChatMessage[]; error: string | null; reachedEnd: boolean }> {
try {
const params = new URLSearchParams({ limit: String(limit) });
if (beforeTs) params.set("before_ts", beforeTs);
const resp = await api.get<{ messages: ChatMessage[]; reached_end: boolean }>(
`/workspaces/${workspaceId}/chat-history?${params.toString()}`,
);
// Server emits oldest-first within the page (RFC #2945 PR-C-2
// post-fix: server reverses row-aware before returning so the
// wire is display-ready). Canvas appends/prepends without
// reordering — this avoids the pair-flip bug a naive flat
// reverse causes when each row produces a (user, agent) pair
// with the same timestamp.
return {
messages: resp.messages ?? [],
error: null,
reachedEnd: resp.reached_end,
};
} catch (err) {
return {
messages: [],
error: err instanceof Error ? err.message : "Failed to load chat history",
reachedEnd: true,
};
}
}
/**
* ChatTab container — renders sub-tab bar + My Chat or Agent Comms panel.
*/
@@ -33,7 +171,7 @@ export function ChatTab({ workspaceId, data }: Props) {
const [subTab, setSubTab] = useState<ChatSubTab>("my-chat");
return (
<div data-testid="chat-panel" className="flex flex-col h-full">
<div className="flex flex-col h-full">
{/* Sub-tab bar — role="tablist" so screen readers expose tab context */}
<div
role="tablist"
@@ -109,68 +247,268 @@ export function ChatTab({ workspaceId, data }: Props) {
* MyChatPanel — user↔agent conversation (extracted from original ChatTab).
*/
function MyChatPanel({ workspaceId, data }: Props) {
const [messages, setMessages] = useState<ChatMessage[]>([]);
const [input, setInput] = useState("");
const [pendingFiles, setPendingFiles] = useState<File[]>([]);
const [activityLog, setActivityLog] = useState<string[]>([]);
// `sending` is strictly the "this tab kicked off a send and hasn't
// seen the reply yet" signal. Previously this was initialized from
// data.currentTask to pick up in-flight agent work on mount, but
// that conflated agent-busy (workspace heartbeat) with user-
// in-flight (local send): when the WS dropped a TASK_COMPLETE event,
// currentTask lingered, the component re-mounted with sending=true,
// and the Send button stayed disabled forever even though nothing
// local was in flight. For the "agent is busy, show spinner" UX,
// use data.currentTask directly in the render path.
const [sending, setSending] = useState(false);
const [thinkingElapsed, setThinkingElapsed] = useState(0);
const [activityLog, setActivityLog] = useState<string[]>([]);
const [loading, setLoading] = useState(true);
const [loadError, setLoadError] = useState<string | null>(null);
const currentTaskRef = useRef(data.currentTask);
const sendingFromAPIRef = useRef(false);
const [agentReachable, setAgentReachable] = useState(false);
const [error, setError] = useState<string | null>(null);
const [confirmRestart, setConfirmRestart] = useState(false);
const [dragOver, setDragOver] = useState(false);
const bottomRef = useRef<HTMLDivElement>(null);
// First-mount scroll-to-bottom needs `behavior: "instant"` — long
// conversations smooth-animate for ~300ms which any concurrent
// re-render can interrupt, leaving the user stuck mid-conversation
// when the chat tab opens. Subsequent appends (new agent messages)
// keep `smooth` for the visual "landing" feel. Flipped the first
// time messages.length goes positive, so a workspace switch (which
// remounts ChatTab) gets a fresh instant jump too.
const hasInitialScrollRef = useRef(false);
// Lazy-load older history on scroll-up.
// - containerRef = the scrollable messages viewport
// - topRef = sentinel above the messages list; IO observes it
// and triggers loadOlder() when it enters view
// - hasMore = false once a fetch returns < limit rows; stops IO
// - loadingOlder = drives the "Loading older messages…" UI label
// - inflightRef = synchronous guard against double-entry of loadOlder
// when the IO callback fires twice in the same
// microtask (state-based guard would be stale until
// the next React commit)
// - scrollAnchorRef = saves distance-from-bottom before a prepend
// so the useLayoutEffect below can restore the
// user's exact viewport position. Without this,
// prepending older messages would jump the scroll
// position by the height of the new content.
// - oldestMessageRef / hasMoreRef = let the loadOlder closure read
// the latest values without taking them as deps —
// every live agent push mutates `messages`, and
// having loadOlder depend on `messages` would tear
// down + re-arm the IntersectionObserver on every
// push. Refs decouple the observer lifecycle from
// message-list updates.
const containerRef = useRef<HTMLDivElement>(null);
const topRef = useRef<HTMLDivElement>(null);
const bottomRef = useRef<HTMLDivElement>(null);
const hasInitialScrollRef = useRef(false);
const [hasMore, setHasMore] = useState(true);
const [loadingOlder, setLoadingOlder] = useState(false);
const inflightRef = useRef(false);
// The scroll anchor includes the first-message id as it was BEFORE
// the prepend — see useLayoutEffect below for why. Without this tag,
// a live agent push that appends WHILE loadOlder is in flight would
// run useLayoutEffect against the append (anchor still set), the
// "restore" math would scroll the user to a stale offset, AND the
// append's normal scroll-to-bottom would be swallowed.
const scrollAnchorRef = useRef<
{ savedDistanceFromBottom: number; expectFirstIdNotEqual: string | null } | null
>(null);
const oldestMessageRef = useRef<ChatMessage | null>(null);
const hasMoreRef = useRef(true);
// Monotonic token bumped on workspace switch + on every loadOlder
// entry. Each fetch's .then() captures its own token; if the token
// has moved, the resolved messages belong to a stale workspace or a
// superseded fetch and we silently drop them. Without this guard, a
// workspace switch mid-fetch would have the in-flight promise
// resolve into the new workspace's setMessages — the user sees
// someone else's history briefly.
const fetchTokenRef = useRef(0);
// Files the user has picked but not yet sent. Cleared on send
// (upload success) or by the × on each pill.
const [pendingFiles, setPendingFiles] = useState<File[]>([]);
const [uploading, setUploading] = useState(false);
const fileInputRef = useRef<HTMLInputElement>(null);
const dragDepthRef = useRef(0);
const pasteCounterRef = useRef(0);
// Guard against a double-click during the upload phase: React
// state updates from the click that started the upload haven't
// flushed yet, so the disabled-button logic sees `uploading=false`
// from the closure and lets a second `sendMessage` enter. A ref
// observes the latest value synchronously.
const sendInFlightRef = useRef(false);
// Monotonic token bumped on every sendMessage entry. Each .then()/
// .catch() captures its own token in closure and bails if a newer
// send has superseded it — prevents a late HTTP response for an
// earlier message from clobbering the flags / appending text that
// belong to a newer in-flight send. Race scenario the token closes:
// (1) send msg #1 (2) WS push for msg #1 arrives, releases guards
// (3) user sends msg #2 (4) HTTP for msg #1 finally lands — without
// the token check, .then() sees sendingFromAPIRef=true (set by
// msg #2's send), enters the main body, and processes msg #1's body
// as if it were msg #2's reply.
const sendTokenRef = useRef(0);
const history = useChatHistory(workspaceId, containerRef);
const chatSend = useChatSend(workspaceId, {
getHistoryMessages: () => history.messages,
onUserMessage: (msg) => history.setMessages((prev) => [...prev, msg]),
onAgentMessage: (msg) => history.setMessages((prev) => appendMessageDeduped(prev, msg)),
});
const { sending, uploading, sendMessage, error: sendError, clearError: clearSendError, releaseSendGuards, sendingFromAPIRef } = chatSend;
// Release every in-flight send guard at once. Used by every site
// that ends a send: pendingAgentMsgs WS push, ACTIVITY_LOGGED
// a2a_receive ok/error WS event, HTTP .then() success, and HTTP
// .catch() success. Keep these in lockstep — a future contributor
// adding a new "I saw the reply" path that only clears `sending` +
// `sendingFromAPIRef` (the natural pair) silently re-introduces
// the post-WS Send-button freeze, because the disabled-button
// logic can't see `sendInFlightRef` and so the visible state diverges
// from the synchronous re-entry guard at line 464.
const releaseSendGuards = useCallback(() => {
setSending(false);
sendingFromAPIRef.current = false;
sendInFlightRef.current = false;
}, []);
const displayError = error || sendError;
// Initial-load fetch — used by the mount effect and the "Retry"
// button below. Single source of truth so the two paths can't drift
// (e.g. INITIAL_HISTORY_LIMIT bumped in the effect but not the
// retry, leading to inconsistent first-paint sizes).
const loadInitial = useCallback(() => {
setLoading(true);
setLoadError(null);
setHasMore(true);
// Bump the token; any in-flight fetch from the previous workspace
// (or a previous retry) will see token != myToken in its .then()
// and silently bail — the late response can't clobber the new
// workspace's state.
fetchTokenRef.current += 1;
const myToken = fetchTokenRef.current;
loadMessagesFromDB(workspaceId, INITIAL_HISTORY_LIMIT).then(
({ messages: msgs, error: fetchErr, reachedEnd }) => {
if (fetchTokenRef.current !== myToken) return;
setMessages(msgs);
setLoadError(fetchErr);
setHasMore(!reachedEnd);
setLoading(false);
},
);
}, [workspaceId]);
useChatSocket(workspaceId, {
onAgentMessage: (msg) => {
history.setMessages((prev) => appendMessageDeduped(prev, msg));
if (sendingFromAPIRef.current) {
releaseSendGuards();
// Load chat history on mount / workspace switch.
// Initial load is bounded to INITIAL_HISTORY_LIMIT (newest 10) — the
// rest streams in as the user scrolls up via loadOlder() below. Pre-
// 2026-05-05 this fetched the newest 50 in one shot; on a long-running
// workspace that meant 50× message-bubble paint + DOM cost on every
// tab-open even when the user only wanted to read the last few.
useEffect(() => {
loadInitial();
}, [loadInitial]);
// Mirror the latest oldest-message + hasMore into refs so loadOlder
// can read them without taking `messages` as a dep. Every live push
// through agentMessages would otherwise recreate loadOlder and tear
// down the IO observer.
useEffect(() => {
oldestMessageRef.current = messages[0] ?? null;
}, [messages]);
useEffect(() => {
hasMoreRef.current = hasMore;
}, [hasMore]);
// Fetch the next-older batch and prepend. Stable identity (deps =
// [workspaceId]) so the IntersectionObserver effect below doesn't
// re-arm on every messages update.
const loadOlder = useCallback(async () => {
// inflightRef is the load-bearing guard — synchronous, set BEFORE
// any await, so two IO callbacks dispatched in the same microtask
// can't both pass. The state checks are defensive secondary
// gates for the slow-scroll case.
if (inflightRef.current || !hasMoreRef.current) return;
const oldest = oldestMessageRef.current;
if (!oldest) return;
const container = containerRef.current;
if (!container) return;
inflightRef.current = true;
// Capture the user's distance-from-bottom BEFORE we prepend so the
// useLayoutEffect can restore it after the new DOM lands. The
// expectFirstIdNotEqual tag is what the layout effect checks
// against `messages[0].id` to disambiguate prepend (id changed) vs
// append (id unchanged → live message landed mid-fetch). Without
// it, an agent push during loadOlder runs the "restore" against a
// stale anchor — user gets yanked + the append's bottom-pin is
// swallowed.
scrollAnchorRef.current = {
savedDistanceFromBottom: container.scrollHeight - container.scrollTop,
expectFirstIdNotEqual: oldest.id,
};
fetchTokenRef.current += 1;
const myToken = fetchTokenRef.current;
setLoadingOlder(true);
try {
const { messages: older, reachedEnd } = await loadMessagesFromDB(
workspaceId,
OLDER_HISTORY_BATCH,
oldest.timestamp,
);
// Workspace switched (or another loadOlder bumped the token)
// mid-fetch — drop these results, they belong to a stale tab.
if (fetchTokenRef.current !== myToken) {
scrollAnchorRef.current = null;
return;
}
},
onActivityLog: (entry) => {
if (!sending) return;
setActivityLog((prev) => appendActivityLine(prev, entry));
},
onSendComplete: () => {
if (sendingFromAPIRef.current) {
releaseSendGuards();
if (older.length > 0) {
setMessages((prev) => [...older, ...prev]);
} else {
// Nothing came back — clear the anchor so the next paint doesn't
// try to "restore" against a no-op prepend.
scrollAnchorRef.current = null;
}
},
onSendError: (err) => {
if (sendingFromAPIRef.current) {
releaseSendGuards();
setError(err);
}
},
});
setHasMore(!reachedEnd);
} finally {
setLoadingOlder(false);
inflightRef.current = false;
}
}, [workspaceId]);
// IntersectionObserver on the top sentinel. Fires loadOlder() the
// moment the user scrolls within 200px of the top. AbortController
// unwires cleanly on workspace switch / unmount; root is the
// scrollable container so we observe only what's visible inside it.
//
// Dependencies:
// - loadOlder — stable per workspaceId (refs decouple it from
// message updates), so this dep is here for the
// workspace-switch case only
// - hasMore — re-run when older history runs out so we
// disconnect cleanly
// - hasMessages — load-bearing: the sentinel JSX is gated on
// `messages.length > 0`, so topRef.current is null
// on the empty-messages render. We re-arm exactly
// once when messages first land. NOT depending on
// `messages.length` (or `messages`) directly so
// each subsequent message append doesn't tear down
// + re-arm the observer.
const hasMessages = messages.length > 0;
useEffect(() => {
const top = topRef.current;
const container = containerRef.current;
if (!top || !container) return;
if (!hasMore) return; // stop observing when no older history exists
const ac = new AbortController();
const io = new IntersectionObserver(
(entries) => {
if (ac.signal.aborted) return;
if (entries[0]?.isIntersecting) loadOlder();
},
{ root: container, rootMargin: "200px 0px 0px 0px", threshold: 0 },
);
io.observe(top);
ac.signal.addEventListener("abort", () => io.disconnect());
return () => ac.abort();
}, [loadOlder, hasMore, hasMessages]);
// Agent reachability
useEffect(() => {
const reachable = data.status === "online" || data.status === "degraded";
setAgentReachable(reachable);
if (reachable) {
setError(null);
clearSendError();
} else {
setError(`Agent is ${data.status}`);
}
}, [data.status, clearSendError]);
setError(reachable ? null : `Agent is ${data.status}`);
}, [data.status]);
useEffect(() => {
currentTaskRef.current = data.currentTask;
}, [data.currentTask]);
// Scroll behavior across messages updates:
// - Prepend (loadOlder landed) → restore the user's saved
@@ -180,24 +518,71 @@ function MyChatPanel({ workspaceId, data }: Props) {
// paint — otherwise the user sees the page jump for one frame.
useLayoutEffect(() => {
const container = containerRef.current;
const anchor = history.scrollAnchorRef.current;
const anchor = scrollAnchorRef.current;
// Only honor the anchor when this messages-update is the prepend
// we expected. messages[0].id is the test:
// - prepend → messages[0] is one of the older rows → id !== expectFirstIdNotEqual
// - append → messages[0] unchanged → id === expectFirstIdNotEqual → fall through
// Without this check, an agent push that lands mid-loadOlder would
// run the restore against the append's update, yank the user's
// scroll, AND swallow the append's bottom-pin.
if (
anchor &&
container &&
history.messages.length > 0 &&
history.messages[0].id !== anchor.expectFirstIdNotEqual
messages.length > 0 &&
messages[0].id !== anchor.expectFirstIdNotEqual
) {
container.scrollTop = container.scrollHeight - anchor.savedDistanceFromBottom;
history.scrollAnchorRef.current = null;
scrollAnchorRef.current = null;
return;
}
if (!hasInitialScrollRef.current && history.messages.length > 0) {
// Instant on first arrival of messages — smooth-scroll on a long
// conversation gets interrupted by concurrent renders and leaves
// the user stuck in the middle. After the first jump, subsequent
// appends animate as before.
if (!hasInitialScrollRef.current && messages.length > 0) {
hasInitialScrollRef.current = true;
bottomRef.current?.scrollIntoView({ behavior: "instant" as ScrollBehavior });
return;
}
bottomRef.current?.scrollIntoView({ behavior: "smooth" });
}, [history.messages, history.scrollAnchorRef]);
}, [messages]);
// Consume agent push messages (send_message_to_user) from global store.
// Runtimes like Claude Code SDK deliver their reply via a WS push rather
// than the /a2a HTTP response — when that happens, the push is the
// authoritative "reply arrived" signal for the UI, so clear `sending`
// here too. The HTTP .then() coordinates through sendingFromAPIRef so
// whichever path clears first wins.
const pendingAgentMsgs = useCanvasStore((s) => s.agentMessages[workspaceId]);
useEffect(() => {
if (!pendingAgentMsgs || pendingAgentMsgs.length === 0) return;
const consume = useCanvasStore.getState().consumeAgentMessages;
const msgs = consume(workspaceId);
for (const m of msgs) {
// Dedupe in case the agent proactively pushed the same text the
// HTTP /a2a response already delivered (observed with the Hermes
// runtime, which emits both a reply body and a send_message_to_user
// push for the same content). Attachments ride along with the
// message so files returned by the A2A_RESPONSE WS path render
// their download chips.
setMessages((prev) => appendMessageDeduped(prev, createMessage("agent", m.content, m.attachments)));
}
if (sendingFromAPIRef.current && msgs.length > 0) {
// Reply arrived via WS push (e.g. claude-code SDK). Release all
// three guards together — without sendInFlightRef the next
// sendMessage() silently no-ops at the synchronous re-entry
// check.
releaseSendGuards();
}
}, [pendingAgentMsgs, workspaceId]);
// Resolve workspace ID → name for activity display
const resolveWorkspaceName = useCallback((id: string) => {
const nodes = useCanvasStore.getState().nodes;
const node = nodes.find((n) => n.id === id);
return (node?.data as WorkspaceNodeData)?.name || id.slice(0, 8);
}, []);
// Elapsed timer while sending
useEffect(() => {
@@ -224,43 +609,211 @@ function MyChatPanel({ workspaceId, data }: Props) {
setActivityLog([`Processing with ${runtimeDisplayName(data.runtime)}...`]);
}, [sending, data.runtime]);
// IntersectionObserver on the top sentinel. Fires loadOlder() the
// moment the user scrolls within 200px of the top. AbortController
// unwires cleanly on workspace switch / unmount; root is the
// scrollable container so we observe only what's visible inside it.
const hasMessages = history.messages.length > 0;
useEffect(() => {
const top = topRef.current;
const container = containerRef.current;
if (!top || !container) return;
if (!history.hasMore) return;
const ac = new AbortController();
const io = new IntersectionObserver(
(entries) => {
if (ac.signal.aborted) return;
if (entries[0]?.isIntersecting) history.loadOlder();
},
{ root: container, rootMargin: "200px 0px 0px 0px", threshold: 0 },
);
io.observe(top);
ac.signal.addEventListener("abort", () => io.disconnect());
return () => ac.abort();
}, [history.loadOlder, history.hasMore, hasMessages]);
// Subscribe to global WS via the singleton ReconnectingSocket (no
// per-component WebSocket — the previous pattern dropped events
// silently on any reconnect because each panel's raw socket had no
// onclose handler).
useSocketEvent((msg) => {
if (!sending) return;
try {
if (msg.event === "ACTIVITY_LOGGED") {
// Filter to events for THIS workspace. The platform's
// BroadcastOnly fires to every connected client, and
// without this guard a sibling workspace's a2a_send would
// surface as "→ Delegating to X..." inside the wrong
// chat panel. (workspace_id on the WS envelope is the
// workspace whose activity_log row we just wrote.)
if (msg.workspace_id !== workspaceId) return;
const handleSend = async () => {
const p = msg.payload || {};
const type = p.activity_type as string;
const method = (p.method as string) || "";
const status = (p.status as string) || "";
const targetId = (p.target_id as string) || "";
const durationMs = p.duration_ms as number | undefined;
const summary = (p.summary as string) || "";
let line = "";
if (type === "a2a_receive" && method === "message/send") {
const targetName = resolveWorkspaceName(targetId || msg.workspace_id);
if (status === "ok" && durationMs) {
const sec = Math.round(durationMs / 1000);
line = `${targetName} responded (${sec}s)`;
// The platform logs a successful a2a_receive once the workspace
// has fully produced its reply. That's the authoritative "done"
// signal for the spinner — clear it even if the reply hasn't
// surfaced through the store yet (it may be delivered shortly
// via pendingAgentMsgs or the HTTP .then()).
const own = (targetId || msg.workspace_id) === workspaceId;
if (own && sendingFromAPIRef.current) {
releaseSendGuards();
}
} else if (status === "error") {
line = `${targetName} error`;
const own = (targetId || msg.workspace_id) === workspaceId;
if (own && sendingFromAPIRef.current) {
releaseSendGuards();
setError("Agent error (Exception) — see workspace logs for details.");
}
}
} else if (type === "a2a_send") {
const targetName = resolveWorkspaceName(targetId);
line = `→ Delegating to ${targetName}...`;
} else if (type === "task_update") {
if (summary) line = `${summary}`;
} else if (type === "agent_log") {
// Per-tool-use telemetry from claude_sdk_executor's
// _report_tool_use. The summary already carries an icon
// + human-readable args (📄 Read /path, ⚡ Bash: …)
// so we render it verbatim. No icon prefix here — the
// emoji at the start of summary is the visual marker.
if (summary) line = summary;
}
if (line) {
setActivityLog((prev) => appendActivityLine(prev, line));
}
} else if (msg.event === "TASK_UPDATED" && msg.workspace_id === workspaceId) {
const task = (msg.payload?.current_task as string) || "";
if (task) {
setActivityLog((prev) => appendActivityLine(prev, `${task}`));
}
}
// A2A_RESPONSE is already consumed by the store and its text is
// appended to messages via the pendingAgentMsgs effect above; we
// don't need to duplicate it here.
} catch { /* ignore */ }
});
const sendMessage = async () => {
const text = input.trim();
const files = pendingFiles;
if ((!text && files.length === 0) || !agentReachable || sending || uploading) return;
const filesToSend = pendingFiles;
// Allow sending if EITHER text OR attachments are present — a user
// can drop a file with no text and the agent still receives it.
if ((!text && filesToSend.length === 0) || !agentReachable || sending || uploading) return;
// Synchronous re-entry guard — see sendInFlightRef comment.
if (sendInFlightRef.current) return;
sendInFlightRef.current = true;
// Upload attachments first so we can include URIs in the A2A
// message parts. Sequential-before-send: a message with references
// to files not yet staged would fail agent-side; staging happens
// synchronously via /chat/uploads before message/send dispatch.
let uploaded: ChatAttachment[] = [];
if (filesToSend.length > 0) {
setUploading(true);
try {
uploaded = await uploadChatFiles(workspaceId, filesToSend);
} catch (e) {
setUploading(false);
sendInFlightRef.current = false;
setError(e instanceof Error ? `Upload failed: ${e.message}` : "Upload failed");
return;
}
setUploading(false);
}
setInput("");
setPendingFiles([]);
clearSendError();
setMessages((prev) => [...prev, createMessage("user", text, uploaded)]);
setSending(true);
sendingFromAPIRef.current = true;
setError(null);
await sendMessage(text, files);
// Capture this send's token so the .then()/.catch() callbacks can
// detect a newer send that may have superseded them. See the
// sendTokenRef declaration for the race scenario this closes.
const myToken = ++sendTokenRef.current;
// Build conversation history from prior messages (last 20)
const history = messages
.filter((m) => m.role === "user" || m.role === "agent")
.slice(-20)
.map((m) => ({
role: m.role === "user" ? "user" : "agent",
parts: [{ kind: "text", text: m.content }],
}));
// A2A parts: text part (if any) + file parts (per attachment). The
// agent sees both in a single turn, matching the A2A spec shape.
// Wire shape is v0 — see A2APart definition above.
const parts: A2APart[] = [];
if (text) parts.push({ kind: "text", text });
for (const att of uploaded) {
parts.push({
kind: "file",
file: {
name: att.name,
mimeType: att.mimeType,
uri: att.uri,
size: att.size,
},
});
}
// A2A calls can legitimately take minutes — LLM latency +
// multi-turn tool use is common on slower providers (Hermes+minimax,
// Claude Code invoking bash/file tools, etc.). The 15s default
// would silently abort the fetch here, leaving the server to
// complete the reply and the user staring at
// "agent may be unreachable". Match the upload timeout (60s × 2)
// for the happy-path ceiling; anything longer is genuinely stuck.
api.post<A2AResponse>(`/workspaces/${workspaceId}/a2a`, {
method: "message/send",
params: {
message: {
role: "user",
messageId: crypto.randomUUID(),
parts,
},
metadata: { history },
},
}, { timeoutMs: 120_000 })
.then((resp) => {
// Bail without touching any flags if a newer sendMessage has
// already run — its myToken bumped sendTokenRef, so this is
// a stale callback for an earlier message. The newer send
// owns the in-flight guards now.
if (sendTokenRef.current !== myToken) return;
// Skip if the WS A2A_RESPONSE event already handled this response.
// Both paths (WS + HTTP) check sendingFromAPIRef — whichever clears
// it first wins, the other becomes a no-op (no duplicate messages).
if (!sendingFromAPIRef.current) {
sendInFlightRef.current = false;
return;
}
const replyText = extractReplyText(resp);
const replyFiles = extractFilesFromTask((resp?.result ?? {}) as Record<string, unknown>);
if (replyText || replyFiles.length > 0) {
setMessages((prev) =>
appendMessageDeduped(prev, createMessage("agent", replyText, replyFiles)),
);
}
releaseSendGuards();
})
.catch(() => {
// Stale-callback guard — same rationale as .then().
if (sendTokenRef.current !== myToken) return;
// Same dedup guard as .then(): if a WS path (pendingAgentMsgs
// or ACTIVITY_LOGGED a2a_receive ok) already delivered the
// reply, sendingFromAPIRef is already false and there's
// nothing to roll back. Surfacing "Failed to send" here would
// contradict the agent reply the user is currently reading —
// exactly the false-positive observed when the HTTP request
// hung up (proxy idle / 502) after WS already won.
if (!sendingFromAPIRef.current) {
sendInFlightRef.current = false;
return;
}
releaseSendGuards();
setError("Failed to send message — agent may be unreachable");
});
};
const onFilesPicked = (fileList: FileList | null) => {
if (!fileList) return;
const picked = Array.from(fileList);
// Deduplicate against current pending set by name+size — user
// picking the same file twice shouldn't append it.
setPendingFiles((prev) => {
const keyed = new Set(prev.map((f) => `${f.name}:${f.size}`));
return [...prev, ...picked.filter((f) => !keyed.has(`${f.name}:${f.size}`))];
@@ -271,7 +824,35 @@ function MyChatPanel({ workspaceId, data }: Props) {
const removePendingFile = (index: number) =>
setPendingFiles((prev) => prev.filter((_, i) => i !== index));
// Monotonic counter so two paste events within the same wall-clock
// second still produce distinct filenames. Without this, on
// Firefox (where pasted images have an empty `file.name`), two
// pastes ~100ms apart could yield identical synthetic names AND
// identical sizes, collapsing into one attachment via the
// `name:size` dedup in onFilesPicked.
const pasteCounterRef = useRef(0);
/** Paste-from-clipboard image attachment.
*
* Browser clipboard image items arrive as `File`s whose `name` is
* often a generic "image.png" (Chrome) or empty (Firefox/Safari),
* so two consecutive screenshot pastes collide on the name+size
* dedup the file-picker uses. Re-tag each pasted image with a
* per-paste unique name so dedup keeps them apart and the upload
* pipeline (which expects a non-empty filename) is happy.
*
* Falls through to onFilesPicked via direct File[] (NOT through
* the DataTransfer constructor — that throws on Safari < 14.1
* and old Edge, silently aborting the paste).
*
* Only intercepts the paste when the clipboard has at least one
* image; text-only pastes fall through to the textarea's default
* behaviour. */
const mimeToExt = (mime: string): string => {
// Avoid raw `mime.split("/")[1]` — that yields `"svg+xml"`,
// `"jpeg"`, `"webp"` etc. which produce ugly filenames and may
// trip server-side extension allowlists. Map known types
// explicitly; unknown falls back to a safe default.
if (mime === "image/svg+xml") return "svg";
if (mime === "image/jpeg") return "jpg";
if (mime === "image/png") return "png";
@@ -292,16 +873,26 @@ function MyChatPanel({ workspaceId, data }: Props) {
const file = item.getAsFile();
if (!file) continue;
const ext = mimeToExt(file.type);
const stamp = new Date().toISOString().replace(/[:.]/g, "-").slice(0, 19);
const stamp = new Date()
.toISOString()
.replace(/[:.]/g, "-")
.slice(0, 19);
const seq = pasteCounterRef.current++;
const fname = `pasted-${stamp}-${seq}-${i}.${ext}`;
imageFiles.push(new File([file], fname, { type: file.type }));
}
if (imageFiles.length === 0) return;
e.preventDefault();
// Reuse the picker path so file-size guards, dedup, and pending-
// list state all run through the same code. Build a synthetic
// FileList-like object to avoid the DataTransfer constructor —
// that's missing on Safari < 14.1 / old Edge and would silently
// throw, leaving the paste a no-op.
addPastedFiles(imageFiles);
};
// Variant of onFilesPicked that accepts a File[] directly, sidestepping
// the DataTransfer-FileList round-trip. Same dedup + state shape.
const addPastedFiles = (files: File[]) => {
setPendingFiles((prev) => {
const keyed = new Set(prev.map((f) => `${f.name}:${f.size}`));
@@ -309,6 +900,11 @@ function MyChatPanel({ workspaceId, data }: Props) {
});
};
// Drag-and-drop staging. dragDepthRef counts enter vs leave events so
// the overlay doesn't flicker when the cursor crosses nested children
// (textarea, buttons) — dragenter/dragleave fire for every boundary.
const [dragOver, setDragOver] = useState(false);
const dragDepthRef = useRef(0);
const dropEnabled = agentReachable && !sending && !uploading;
const isFileDrag = (e: React.DragEvent) =>
Array.from(e.dataTransfer.types || []).includes("Files");
@@ -338,6 +934,9 @@ function MyChatPanel({ workspaceId, data }: Props) {
};
const downloadAttachment = (att: ChatAttachment) => {
// Errors here are rare but user-visible (401 on a revoked token,
// 404 if the agent deleted the file). Surface via the inline
// error banner — the message list itself stays untouched.
downloadChatFile(workspaceId, att).catch((e) => {
setError(e instanceof Error ? `Download failed: ${e.message}` : "Download failed");
});
@@ -363,54 +962,28 @@ function MyChatPanel({ workspaceId, data }: Props) {
</div>
</div>
)}
{/* talk_to_user disabled banner — shown when the workspace has
talk_to_user_enabled=false. The agent cannot send canvas messages;
the user can re-enable the ability from here without opening settings. */}
{data.talkToUserEnabled === false && (
<div className="flex items-center gap-2 px-3 py-2 bg-surface-sunken border-b border-line/40 shrink-0">
<svg width="14" height="14" viewBox="0 0 16 16" fill="none" aria-hidden="true" className="shrink-0 text-ink-mid">
<path d="M8 1a7 7 0 1 0 0 14A7 7 0 0 0 8 1Zm0 10.5a.75.75 0 1 1 0-1.5.75.75 0 0 1 0 1.5ZM8 4a.75.75 0 0 1 .75.75v4a.75.75 0 0 1-1.5 0v-4A.75.75 0 0 1 8 4Z" fill="currentColor"/>
</svg>
<span className="text-[10px] text-ink-mid flex-1">
Agent is not enabled to chat with you.
</span>
<button
onClick={async () => {
try {
await api.patch(`/workspaces/${workspaceId}/abilities`, { talk_to_user_enabled: true });
useCanvasStore.getState().updateNodeData(workspaceId, { talkToUserEnabled: true });
} catch {
// ignore — user will see no change and can retry
}
}}
className="px-2 py-0.5 text-[10px] font-medium bg-accent/10 hover:bg-accent/20 text-accent rounded border border-accent/30 transition-colors shrink-0"
>
Enable
</button>
</div>
)}
{/* Messages */}
<div ref={containerRef} className="flex-1 overflow-y-auto p-3 space-y-3">
{history.loading && (
{loading && (
<div className="text-xs text-ink-mid text-center py-4">Loading chat history...</div>
)}
{!history.loading && history.loadError !== null && history.messages.length === 0 && (
{!loading && loadError !== null && messages.length === 0 && (
<div
role="alert"
className="mx-2 mt-2 rounded-lg border border-red-800/50 bg-red-950/30 px-3 py-2.5"
>
<p className="text-[11px] text-bad mb-1.5">
Failed to load chat history: {history.loadError}
Failed to load chat history: {loadError}
</p>
<button
onClick={history.loadInitial}
onClick={loadInitial}
className="text-[10px] px-2 py-0.5 rounded bg-red-800 text-red-200 hover:bg-red-700 transition-colors"
>
Retry
</button>
</div>
)}
{!history.loading && history.loadError === null && history.messages.length === 0 && (
{!loading && loadError === null && messages.length === 0 && (
<div className="text-xs text-ink-mid text-center py-8">
No messages yet. Send a message to start chatting with this agent.
</div>
@@ -428,12 +1001,12 @@ function MyChatPanel({ workspaceId, data }: Props) {
instead of showing a "no more messages" footer — the user's
scroll resting against the top of the conversation IS the
signal. */}
{history.hasMore && history.messages.length > 0 && (
{hasMore && messages.length > 0 && (
<div ref={topRef} className="text-xs text-ink-mid text-center py-1">
{history.loadingOlder ? "Loading older messages…" : " "}
{loadingOlder ? "Loading older messages…" : " "}
</div>
)}
{history.messages.map((msg) => (
{messages.map((msg) => (
<div key={msg.id} className={`flex ${msg.role === "user" ? "justify-end" : "justify-start"}`}>
<div
className={`max-w-[85%] rounded-lg px-3 py-2 text-xs ${
@@ -593,10 +1166,10 @@ function MyChatPanel({ workspaceId, data }: Props) {
</div>
{/* Error banner */}
{displayError && (
{error && (
<div className="px-3 py-2 bg-red-900/20 border-t border-red-800/30">
<div className="flex items-center justify-between">
<span className="text-[10px] text-red-300">{displayError}</span>
<span className="text-[10px] text-red-300">{error}</span>
{!isOnline && (
<button
onClick={() => setConfirmRestart(true)}
@@ -664,7 +1237,7 @@ function MyChatPanel({ workspaceId, data }: Props) {
e.keyCode !== 229
) {
e.preventDefault();
handleSend();
sendMessage();
}
}}
onPaste={onPasteIntoComposer}
@@ -674,7 +1247,7 @@ function MyChatPanel({ workspaceId, data }: Props) {
className="flex-1 bg-surface-card border border-line rounded-lg px-3 py-2 text-xs text-ink placeholder-ink-soft dark:bg-zinc-800 dark:border-zinc-600 dark:placeholder-zinc-500 focus:outline-none focus:border-accent focus-visible:ring-2 focus-visible:ring-accent/40 resize-none disabled:opacity-50"
/>
<button
onClick={handleSend}
onClick={sendMessage}
disabled={(!input.trim() && pendingFiles.length === 0) || !agentReachable || sending || uploading}
className="px-4 py-2 bg-accent-strong hover:bg-accent text-xs font-medium rounded-lg text-white disabled:opacity-30 transition-colors shrink-0"
>
+1 -1
View File
@@ -176,7 +176,7 @@ export function deriveProvidersFromModels(models: ModelSpec[]): string[] {
// exactly the point of the platform adaptor. The deep `~/.hermes/
// config.yaml` on the container is a separate runtime-internal file,
// not this one.
const RUNTIMES_WITH_OWN_CONFIG = new Set<string>(["external", "kimi", "kimi-cli", "openclaw"]);
const RUNTIMES_WITH_OWN_CONFIG = new Set<string>(["external", "kimi", "kimi-cli"]);
const FALLBACK_RUNTIME_OPTIONS: RuntimeOption[] = [
{ value: "", label: "LangGraph (default)", models: [], providers: [] },
+3 -46
View File
@@ -45,54 +45,11 @@ export function FilesTab({ workspaceId, data }: Props) {
if (data && isExternalLikeRuntime(data.runtime)) {
return <NotAvailablePanel runtime={data.runtime} />;
}
return <PlatformOwnedFilesTab workspaceId={workspaceId} runtime={data?.runtime} />;
return <PlatformOwnedFilesTab workspaceId={workspaceId} />;
}
/** Picks the initial root for the FilesTab dropdown based on the
* workspace's runtime. Decision: per-runtime default (Hongming
* 2026-05-15, internal#425 Decisions §2).
*
* - openclaw → `/agent-home` (the agent's identity/state — the
* user-facing interesting files for that runtime live in
* `~/.openclaw/` inside the container, which `/agent-home` maps to
* via the Phase 2b docker-exec backend).
* - everything else (claude-code, hermes, external-like, undefined)
* → `/configs` (the legacy default — managed config that flows
* through the per-runtime indirection in
* workspace-server/internal/handlers/template_files_eic.go).
*
* When the runtime is undefined (legacy callers that don't thread
* `data` through, or a workspace whose runtime field hasn't loaded
* yet) the default is `/configs` — matches today's behaviour, no
* surprise.
*
* Note on `/agent-home` pre-Phase-2b: the backend short-circuits
* with HTTP 501 and the canonical "implementation pending" body.
* The tab renders empty + the error banner explains. This is by
* design — lets us land the canvas UX before the backend ships,
* per the RFC's phased rollout. The 501 is graceful: it doesn't
* poison error toasts or generate "workspace not found" noise.
*
* Adding a new runtime that should default to `/agent-home`: add it
* to the agentHomeDefaultRuntimes set below. Adding a runtime that
* should default to a different root: extend this function. */
const agentHomeDefaultRuntimes = new Set(["openclaw"]);
function defaultRootForRuntime(runtime: string | undefined): string {
if (runtime && agentHomeDefaultRuntimes.has(runtime)) {
return "/agent-home";
}
return "/configs";
}
function PlatformOwnedFilesTab({
workspaceId,
runtime,
}: {
workspaceId: string;
runtime?: string;
}) {
const [root, setRoot] = useState(() => defaultRootForRuntime(runtime));
function PlatformOwnedFilesTab({ workspaceId }: { workspaceId: string }) {
const [root, setRoot] = useState("/configs");
const [selectedFile, setSelectedFile] = useState<string | null>(null);
const [fileContent, setFileContent] = useState("");
const [editContent, setEditContent] = useState("");
@@ -3,22 +3,6 @@
import { useRef } from "react";
import { getIcon } from "./tree";
// secretShapeMarker is the canonical body the workspace-server Files
// API returns when a file's path OR content matched a credential
// regex (internal#425 RFC, Phase 2b — backed by
// workspace-server/internal/secrets.ScanBytes). The marker is a
// fixed prefix so the canvas can detect it without parsing JSON and
// without round-tripping the matched bytes through the editor (which
// would defeat the purpose — clipboard, browser history, log
// surfaces would all see them).
//
// Today (Phase 1 / before 2b ships) the backend returns 501 for the
// only root that uses this path, so the marker is dead code until
// 2b lands. Wiring it in now keeps the canvas + backend contracts
// aligned in one PR rather than a follow-up. The constant is
// importable so a future test can pin the exact string.
export const SECRET_SHAPE_DENIED_MARKER = "<denied: secret-shape>";
interface Props {
selectedFile: string | null;
fileContent: string;
@@ -47,22 +31,6 @@ export function FileEditor({
const editorRef = useRef<HTMLTextAreaElement>(null);
const isDirty = editContent !== fileContent;
// internal#425 Phase 3: detect the secret-shape denial marker and
// render a placeholder instead of the editor. The marker comes
// from workspace-server Phase 2b (secrets.ScanBytes) which refuses
// to surface the file's bytes. We deliberately don't expose
// the matched pattern's Name here — the canvas just shows the
// generic denial. The Files API log surface has the Pattern.Name
// for operators who need to debug a false positive.
const isSecretShapeDenied = fileContent === SECRET_SHAPE_DENIED_MARKER;
// /agent-home is read-only from the canvas (Phase 2b ships read +
// delete; Phase-2b-followup may add write). Edits to /configs are
// unchanged. Until 2b ships, /agent-home returns 501 so this
// read-only gate is also dead code, but wiring it in now keeps
// the UI honest the moment 2b lands without a follow-up canvas PR.
const isReadOnlyRoot = root !== "/configs";
if (!selectedFile) {
return (
<div className="flex-1 flex items-center justify-center">
@@ -107,42 +75,11 @@ export function FileEditor({
{/* Editor area */}
{loadingFile ? (
<div className="p-4 text-xs text-ink-mid">Loading...</div>
) : isSecretShapeDenied ? (
// Files API refused to surface this file's bytes because its
// path or content matched a credential regex
// (workspace-server/internal/secrets, internal#425 Phase 2b).
// We render a placeholder INSTEAD OF the textarea so the
// matched bytes never enter the DOM. Clipboard / view-source
// / element-inspector all see the placeholder, not the
// credential.
<div
role="region"
aria-label="File content denied"
className="flex-1 flex items-center justify-center p-6 bg-surface"
>
<div className="max-w-md text-center space-y-2">
<div className="text-2xl opacity-40">🛡</div>
<p className="text-[11px] font-mono text-warm">
{SECRET_SHAPE_DENIED_MARKER}
</p>
<p className="text-[10px] text-ink-mid leading-relaxed">
The platform refused to surface this file because its
path or content matched a credential-shape pattern.
The bytes never left the workspace container.
</p>
<p className="text-[10px] text-ink-mid leading-relaxed">
If this is a false positive (test fixture, docs example,
or content that happens to share a credential's shape),
rename the file or adjust the content via the workspace
terminal so the regex no longer matches, then refresh.
</p>
</div>
</div>
) : (
<textarea
ref={editorRef}
value={editContent}
readOnly={isReadOnlyRoot}
readOnly={root !== "/configs"}
onChange={(e) => setEditContent(e.target.value)}
onKeyDown={(e) => {
if ((e.metaKey || e.ctrlKey) && e.key === "s") {
@@ -38,15 +38,6 @@ export function FilesToolbar({
<option value="/home">/home</option>
<option value="/workspace">/workspace</option>
<option value="/plugins">/plugins</option>
{/* internal#425 Phase 1+3: container-internal $HOME root.
Backend lands the docker-exec dispatch in Phase 2b. Until
then the stub returns 501 with a canonical
"implementation pending" message — the dropdown renders
the option so the canvas affordance is design-frozen
even before the backend ships.
Runtime-default selection logic in FilesTab.tsx picks
this as the initial value for openclaw workspaces. */}
<option value="/agent-home">/agent-home</option>
</select>
<span className="text-[10px] text-ink-mid">{fileCount} files</span>
</div>
@@ -1,181 +0,0 @@
// @vitest-environment jsdom
/**
* Tests for the /agent-home root selector + per-runtime default-root
* + secret-shape denial placeholder (internal#425 Phase 3).
*
* Separate file so the diff is reviewable as a unit and the existing
* FilesToolbar / FileEditor / FilesTab tests don't have to grow
* agent-home-specific cases. Once Phase 2b lands, the read-only +
* 501-stub assertions here can be tightened (or moved into the main
* test file as the agent-home root becomes a first-class affordance).
*/
import React from "react";
import { render, screen, cleanup } from "@testing-library/react";
import { afterEach, describe, expect, it, vi } from "vitest";
import { FilesToolbar } from "../FilesToolbar";
import {
FileEditor,
SECRET_SHAPE_DENIED_MARKER,
} from "../FileEditor";
afterEach(cleanup);
describe("internal#425 Phase 3 — /agent-home root selector", () => {
it("dropdown includes /agent-home as an option", () => {
// Pins the affordance is in the DOM even pre-Phase-2b — the
// canvas design freezes today, the backend lands the dispatch
// later. Without this, a future refactor that drops the option
// would silently regress the RFC's Phase 1 contract (canvas
// visibility) without breaking any other test.
render(
<FilesToolbar
root="/configs"
setRoot={vi.fn()}
fileCount={0}
onNewFile={vi.fn()}
onUpload={vi.fn()}
onDownloadAll={vi.fn()}
onClearAll={vi.fn()}
onRefresh={vi.fn()}
/>,
);
const select = screen.getByRole("combobox", {
name: /file root directory/i,
}) as HTMLSelectElement;
const values = Array.from(select.options).map((o) => o.value);
expect(values).toContain("/agent-home");
});
it("dropdown shows /agent-home as the SELECTED root when prop is /agent-home", () => {
render(
<FilesToolbar
root="/agent-home"
setRoot={vi.fn()}
fileCount={0}
onNewFile={vi.fn()}
onUpload={vi.fn()}
onDownloadAll={vi.fn()}
onClearAll={vi.fn()}
onRefresh={vi.fn()}
/>,
);
const select = screen.getByRole("combobox", {
name: /file root directory/i,
}) as HTMLSelectElement;
expect(select.value).toBe("/agent-home");
});
});
describe("internal#425 Phase 3 — secret-shape denial placeholder", () => {
// Files API Phase 2b returns SECRET_SHAPE_DENIED_MARKER as the file
// body when the file's path or content matched a credential regex.
// The editor MUST render the marker as a placeholder, not pump it
// through the textarea — that would put the marker (and any future
// matched bytes if the backend contract changes) into the DOM
// value, clipboard, and inspector.
it("renders the denial placeholder INSTEAD of the textarea when fileContent is the marker", () => {
render(
<FileEditor
selectedFile="agent/.openclaw/secrets.env"
fileContent={SECRET_SHAPE_DENIED_MARKER}
editContent={SECRET_SHAPE_DENIED_MARKER}
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/agent-home"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
// Placeholder region present
expect(
screen.getByRole("region", { name: /file content denied/i }),
).toBeTruthy();
// Marker text visible (so a debugging operator sees the canonical
// contract string without having to dig into the source).
expect(screen.getByText(SECRET_SHAPE_DENIED_MARKER)).toBeTruthy();
// Critically: NO textarea — the bytes never reach a controlled
// input. A regression that re-introduces the textarea path would
// make the matched marker (and any future content) selectable +
// copyable.
expect(screen.queryByRole("textbox")).toBeNull();
});
it("renders the textarea normally when fileContent is regular content", () => {
render(
<FileEditor
selectedFile="config.yaml"
fileContent="name: openclaw\n"
editContent="name: openclaw\n"
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/configs"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
expect(screen.getByRole("textbox")).toBeTruthy();
expect(screen.queryByRole("region", { name: /file content denied/i }))
.toBeNull();
});
it("/agent-home renders textarea READ-ONLY for non-denied content", () => {
// Phase 2b ships read + delete on /agent-home; write semantics
// are decided later. Until then, the canvas presents the editor
// as read-only so a user can't type into a buffer that the
// backend will refuse to PUT. Without this gate, the user would
// edit, hit Save, get a 501, and lose their context for why.
render(
<FileEditor
selectedFile=".openclaw/agent-card.json"
fileContent='{"name":"openclaw"}'
editContent='{"name":"openclaw"}'
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/agent-home"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
const textarea = screen.getByRole("textbox") as HTMLTextAreaElement;
expect(textarea.readOnly).toBe(true);
});
it("/configs renders textarea WRITABLE (regression guard for the read-only gate)", () => {
render(
<FileEditor
selectedFile="config.yaml"
fileContent="name: x\n"
editContent="name: x\n"
setEditContent={vi.fn()}
loadingFile={false}
saving={false}
success={null}
root="/configs"
onSave={vi.fn()}
onDownload={vi.fn()}
/>,
);
const textarea = screen.getByRole("textbox") as HTMLTextAreaElement;
expect(textarea.readOnly).toBe(false);
});
});
describe("internal#425 Phase 3 — marker constant is the canonical string", () => {
// The marker string is part of the canvas <-> workspace-server
// contract. The workspace-server emits this exact body; the canvas
// detects it by exact-equality. A typo on either side would
// silently break detection — the canvas would render the literal
// string in the textarea instead of the placeholder. Pin the
// contract value here.
it("matches the contract value '<denied: secret-shape>'", () => {
expect(SECRET_SHAPE_DENIED_MARKER).toBe("<denied: secret-shape>");
});
});
@@ -1,3 +0,0 @@
export { useChatHistory } from "./useChatHistory";
export { useChatSend } from "./useChatSend";
export { useChatSocket } from "./useChatSocket";
@@ -1,11 +0,0 @@
"use client";
import { useCanvasStore, type WorkspaceNodeData } from "@/store/canvas";
/** Resolve a workspace ID to its human-readable name.
* Falls back to the first 8 chars of the ID. */
export function resolveWorkspaceName(id: string): string {
const nodes = useCanvasStore.getState().nodes;
const node = nodes.find((n) => n.id === id);
return (node?.data as WorkspaceNodeData)?.name || id.slice(0, 8);
}
@@ -1,134 +0,0 @@
"use client";
import { useCallback, useEffect, useRef, useState } from "react";
import { api } from "@/lib/api";
import { type ChatMessage, appendMessageDeduped as appendMessageDedupedFn } from "../types";
const INITIAL_HISTORY_LIMIT = 10;
const OLDER_HISTORY_BATCH = 20;
async function loadMessagesFromDB(
workspaceId: string,
limit: number,
beforeTs?: string,
): Promise<{ messages: ChatMessage[]; error: string | null; reachedEnd: boolean }> {
try {
const params = new URLSearchParams({ limit: String(limit) });
if (beforeTs) params.set("before_ts", beforeTs);
const resp = await api.get<{ messages: ChatMessage[]; reached_end: boolean }>(
`/workspaces/${workspaceId}/chat-history?${params.toString()}`,
);
return {
messages: resp.messages ?? [],
error: null,
reachedEnd: resp.reached_end,
};
} catch (err) {
return {
messages: [],
error: err instanceof Error ? err.message : "Failed to load chat history",
reachedEnd: true,
};
}
}
export interface ScrollAnchor {
savedDistanceFromBottom: number;
expectFirstIdNotEqual: string | null;
}
export function useChatHistory(
workspaceId: string,
containerRef?: React.RefObject<HTMLDivElement | null>,
) {
const [messages, setMessages] = useState<ChatMessage[]>([]);
const [loading, setLoading] = useState(true);
const [loadError, setLoadError] = useState<string | null>(null);
const [loadingOlder, setLoadingOlder] = useState(false);
const [hasMore, setHasMore] = useState(true);
const fetchTokenRef = useRef(0);
const oldestMessageRef = useRef<ChatMessage | null>(null);
const hasMoreRef = useRef(true);
const inflightRef = useRef(false);
const scrollAnchorRef = useRef<ScrollAnchor | null>(null);
useEffect(() => {
oldestMessageRef.current = messages[0] ?? null;
}, [messages]);
useEffect(() => {
hasMoreRef.current = hasMore;
}, [hasMore]);
const loadInitial = useCallback(() => {
setLoading(true);
setLoadError(null);
setHasMore(true);
fetchTokenRef.current += 1;
const myToken = fetchTokenRef.current;
return loadMessagesFromDB(workspaceId, INITIAL_HISTORY_LIMIT).then(
({ messages: msgs, error: fetchErr, reachedEnd }) => {
if (fetchTokenRef.current !== myToken) return;
setMessages(msgs);
setLoadError(fetchErr);
setHasMore(!reachedEnd);
setLoading(false);
},
);
}, [workspaceId]);
useEffect(() => {
loadInitial();
}, [loadInitial]);
const loadOlder = useCallback(async () => {
if (inflightRef.current || !hasMoreRef.current) return;
const oldest = oldestMessageRef.current;
if (!oldest) return;
const container = containerRef?.current;
if (!container) return;
inflightRef.current = true;
scrollAnchorRef.current = {
savedDistanceFromBottom: container.scrollHeight - container.scrollTop,
expectFirstIdNotEqual: oldest.id,
};
fetchTokenRef.current += 1;
const myToken = fetchTokenRef.current;
setLoadingOlder(true);
try {
const { messages: older, reachedEnd } = await loadMessagesFromDB(
workspaceId,
OLDER_HISTORY_BATCH,
oldest.timestamp,
);
if (fetchTokenRef.current !== myToken) {
scrollAnchorRef.current = null;
return;
}
if (older.length > 0) {
setMessages((prev) => [...older, ...prev]);
} else {
scrollAnchorRef.current = null;
}
setHasMore(!reachedEnd);
} finally {
setLoadingOlder(false);
inflightRef.current = false;
}
}, [workspaceId, containerRef]);
return {
messages,
loading,
loadError,
loadingOlder,
hasMore,
loadInitial,
loadOlder,
appendMessageDeduped: (msg: ChatMessage) =>
setMessages((prev) => appendMessageDedupedFn(prev, msg)),
setMessages,
scrollAnchorRef,
};
}
@@ -1,182 +0,0 @@
"use client";
import { useCallback, useRef, useState } from "react";
import { api } from "@/lib/api";
import { uploadChatFiles } from "../uploads";
import { createMessage, type ChatMessage, type ChatAttachment } from "../types";
import { extractFilesFromTask } from "../message-parser";
interface A2APart {
kind: string;
text?: string;
file?: {
name?: string;
mimeType?: string;
uri?: string;
size?: number;
};
}
interface A2AResponse {
result?: {
parts?: A2APart[];
artifacts?: Array<{ parts: A2APart[] }>;
};
}
export function extractReplyText(resp: A2AResponse): string {
const collect = (parts: A2APart[] | undefined): string => {
if (!parts) return "";
return parts
.filter((p) => p.kind === "text")
.map((p) => p.text ?? "")
.filter(Boolean)
.join("\n");
};
const result = resp?.result;
const collected: string[] = [];
const fromParts = collect(result?.parts);
if (fromParts) collected.push(fromParts);
if (result?.artifacts) {
for (const a of result.artifacts) {
const t = collect(a.parts);
if (t) collected.push(t);
}
}
return collected.join("\n");
}
export interface UseChatSendOptions {
getHistoryMessages: () => ChatMessage[];
onUserMessage?: (msg: ChatMessage) => void;
onAgentMessage?: (msg: ChatMessage) => void;
}
export function useChatSend(workspaceId: string, options: UseChatSendOptions) {
const [sending, setSending] = useState(false);
const [uploading, setUploading] = useState(false);
const [error, setError] = useState<string | null>(null);
const sendInFlightRef = useRef(false);
const sendingFromAPIRef = useRef(false);
const sendTokenRef = useRef(0);
const optionsRef = useRef(options);
optionsRef.current = options;
const releaseSendGuards = useCallback(() => {
setSending(false);
sendingFromAPIRef.current = false;
sendInFlightRef.current = false;
}, []);
const clearError = useCallback(() => setError(null), []);
const sendMessage = useCallback(
async (text: string, files: File[] = []) => {
const trimmed = text.trim();
if ((!trimmed && files.length === 0) || sending || uploading) return;
if (sendInFlightRef.current) return;
sendInFlightRef.current = true;
let uploaded: ChatAttachment[] = [];
if (files.length > 0) {
setUploading(true);
try {
uploaded = await uploadChatFiles(workspaceId, files);
} catch (e) {
setUploading(false);
sendInFlightRef.current = false;
setError(
e instanceof Error ? `Upload failed: ${e.message}` : "Upload failed",
);
return;
}
setUploading(false);
}
const userMsg = createMessage("user", trimmed, uploaded);
optionsRef.current.onUserMessage?.(userMsg);
setSending(true);
sendingFromAPIRef.current = true;
setError(null);
const myToken = ++sendTokenRef.current;
const history = optionsRef.current
.getHistoryMessages()
.filter((m) => m.role === "user" || m.role === "agent")
.slice(-20)
.map((m) => ({
role: m.role === "user" ? "user" : "agent",
parts: [{ kind: "text", text: m.content }],
}));
const parts: A2APart[] = [];
if (trimmed) parts.push({ kind: "text", text: trimmed });
for (const att of uploaded) {
parts.push({
kind: "file",
file: {
name: att.name,
mimeType: att.mimeType,
uri: att.uri,
size: att.size,
},
});
}
api
.post<A2AResponse>(
`/workspaces/${workspaceId}/a2a`,
{
method: "message/send",
params: {
message: {
role: "user",
messageId: crypto.randomUUID(),
parts,
},
metadata: { history },
},
},
{ timeoutMs: 120_000 },
)
.then((resp) => {
if (sendTokenRef.current !== myToken) return;
if (!sendingFromAPIRef.current) {
sendInFlightRef.current = false;
return;
}
const replyText = extractReplyText(resp);
const replyFiles = extractFilesFromTask(
(resp?.result ?? {}) as Record<string, unknown>,
);
if (replyText || replyFiles.length > 0) {
optionsRef.current.onAgentMessage?.(
createMessage("agent", replyText, replyFiles),
);
}
releaseSendGuards();
})
.catch(() => {
if (sendTokenRef.current !== myToken) return;
if (!sendingFromAPIRef.current) {
sendInFlightRef.current = false;
return;
}
releaseSendGuards();
setError("Failed to send message — agent may be unreachable");
});
},
[workspaceId, sending, uploading],
);
return {
sending,
uploading,
sendMessage,
error,
clearError,
releaseSendGuards,
sendingFromAPIRef,
};
}
@@ -1,100 +0,0 @@
"use client";
import { useCallback, useEffect, useRef } from "react";
import { useCanvasStore, type WorkspaceNodeData } from "@/store/canvas";
import { useSocketEvent } from "@/hooks/useSocketEvent";
import { createMessage, type ChatMessage } from "../types";
export interface UseChatSocketCallbacks {
onAgentMessage?: (msg: ChatMessage) => void;
onActivityLog?: (entry: string) => void;
onSendComplete?: () => void;
onSendError?: (error: string) => void;
}
export function useChatSocket(
workspaceId: string,
callbacks: UseChatSocketCallbacks,
): void {
const callbacksRef = useRef(callbacks);
callbacksRef.current = callbacks;
// Agent push messages from global store
const pendingAgentMsgs = useCanvasStore((s) => s.agentMessages[workspaceId]);
useEffect(() => {
if (!pendingAgentMsgs || pendingAgentMsgs.length === 0) return;
const consume = useCanvasStore.getState().consumeAgentMessages;
const msgs = consume(workspaceId);
for (const m of msgs) {
callbacksRef.current.onAgentMessage?.(
createMessage("agent", m.content, m.attachments),
);
}
if (msgs.length > 0) {
callbacksRef.current.onSendComplete?.();
}
}, [pendingAgentMsgs, workspaceId]);
const resolveWorkspaceName = useCallback((id: string) => {
const nodes = useCanvasStore.getState().nodes;
const node = nodes.find((n) => n.id === id);
return (node?.data as WorkspaceNodeData)?.name || id.slice(0, 8);
}, []);
useSocketEvent((msg) => {
try {
if (msg.event === "ACTIVITY_LOGGED") {
if (msg.workspace_id !== workspaceId) return;
const p = msg.payload || {};
const type = p.activity_type as string;
const method = (p.method as string) || "";
const status = (p.status as string) || "";
const targetId = (p.target_id as string) || "";
const durationMs = p.duration_ms as number | undefined;
const summary = (p.summary as string) || "";
let line = "";
if (type === "a2a_receive" && method === "message/send") {
const targetName = resolveWorkspaceName(targetId || msg.workspace_id);
if (status === "ok" && durationMs) {
const sec = Math.round(durationMs / 1000);
line = `${targetName} responded (${sec}s)`;
const own = (targetId || msg.workspace_id) === workspaceId;
if (own) callbacksRef.current.onSendComplete?.();
} else if (status === "error") {
line = `${targetName} error`;
const own = (targetId || msg.workspace_id) === workspaceId;
if (own) {
callbacksRef.current.onSendComplete?.();
callbacksRef.current.onSendError?.(
"Agent error (Exception) — see workspace logs for details.",
);
}
}
} else if (type === "a2a_send") {
const targetName = resolveWorkspaceName(targetId);
line = `→ Delegating to ${targetName}...`;
} else if (type === "task_update") {
if (summary) line = `${summary}`;
} else if (type === "agent_log") {
if (summary) line = summary;
}
if (line) {
callbacksRef.current.onActivityLog?.(line);
}
} else if (
msg.event === "TASK_UPDATED" &&
msg.workspace_id === workspaceId
) {
const task = (msg.payload?.current_task as string) || "";
if (task) {
callbacksRef.current.onActivityLog?.(`${task}`);
}
}
} catch {
/* ignore */
}
});
}
-3
View File
@@ -1,5 +1,2 @@
export { type ChatMessage, createMessage, appendMessageDeduped } from "./types";
export { extractAgentText, extractTextsFromParts, extractResponseText } from "./message-parser";
export { useChatHistory } from "./hooks/useChatHistory";
export { useChatSend } from "./hooks/useChatSend";
export { useChatSocket } from "./hooks/useChatSocket";
@@ -2,7 +2,7 @@
import { useState, useCallback, useRef, useEffect } from 'react';
import type { TestConnectionState, SecretGroup } from '@/types/secrets';
import { validateSecret, ApiError } from '@/lib/api/secrets';
import { validateSecret } from '@/lib/api/secrets';
interface TestConnectionButtonProps {
provider: SecretGroup;
@@ -55,23 +55,9 @@ export function TestConnectionButton({
}
onResult?.(result.valid);
resetTimerRef.current = setTimeout(() => setState('idle'), RESET_DELAYS[nextState]!);
} catch (err) {
// Distinguish a real failure shape rather than always claiming a
// timeout. A reachable server that answered with an HTTP status
// (ApiError) did NOT time out — most commonly the validation route
// is not available (404/501), which must not masquerade as
// "service down". Only an actual thrown network/abort error is a
// connectivity failure.
} catch {
setState('failure');
if (err instanceof ApiError) {
setErrorDetail(
err.status === 404 || err.status === 501
? 'Key validation is not available for this service yet. The key was not tested.'
: `Could not verify key (server returned ${err.status}). Saving is unaffected.`,
);
} else {
setErrorDetail('Could not reach the validation service. Check your connection and try again.');
}
setErrorDetail('Connection timed out. Service may be down.');
onResult?.(false);
resetTimerRef.current = setTimeout(() => setState('idle'), RESET_DELAYS.failure);
}
@@ -28,20 +28,8 @@ const mockValidateSecret = vi.fn();
vi.mock("@/lib/api/secrets", () => ({
validateSecret: (...args: unknown[]) => mockValidateSecret(...args),
ApiError: class ApiError extends Error {
status: number;
constructor(status: number, message: string) {
super(message);
this.name = "ApiError";
this.status = status;
}
},
}));
// Re-import the mocked ApiError so test cases construct the same class the
// component's `instanceof` check sees.
import { ApiError } from "@/lib/api/secrets";
beforeEach(() => {
vi.useFakeTimers();
vi.clearAllMocks();
@@ -213,27 +201,8 @@ describe("TestConnectionButton — failure path", () => {
});
describe("TestConnectionButton — catch path", () => {
it("does NOT claim a timeout when the validate endpoint 404s (regression: internal#492)", async () => {
// The validate route is unimplemented on the server and returns a fast
// 404. Before the fix this rendered the misleading hardcoded string
// "Connection timed out. Service may be down." It must instead state
// honestly that validation isn't available and the key was not tested.
mockValidateSecret.mockRejectedValue(new ApiError(404, "Not Found"));
render(
<TestConnectionButton provider="anthropic" secretValue="sk-ant-xxx" />,
);
fireEvent.click(document.querySelector('button[type="button"]')!);
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).not.toContain("Connection timed out");
expect(document.body.textContent).not.toContain("Service may be down");
expect(document.body.textContent).toContain("not available");
expect(document.body.textContent).toContain("not tested");
});
it("reports a non-404 server error with its status, not a timeout", async () => {
mockValidateSecret.mockRejectedValue(new ApiError(500, "Internal Server Error"));
it("shows 'Connection timed out' on network error", async () => {
mockValidateSecret.mockRejectedValue(new Error("timeout"));
render(
<TestConnectionButton provider="github" secretValue="ghp_xxx" />,
);
@@ -241,20 +210,7 @@ describe("TestConnectionButton — catch path", () => {
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).toContain("500");
expect(document.body.textContent).not.toContain("Connection timed out");
});
it("shows a connectivity message on a genuine network error", async () => {
mockValidateSecret.mockRejectedValue(new Error("network down"));
render(
<TestConnectionButton provider="github" secretValue="ghp_xxx" />,
);
fireEvent.click(document.querySelector('button[type="button"]')!);
await act(async () => {
await vi.advanceTimersByTimeAsync(0);
});
expect(document.body.textContent).toContain("Could not reach the validation service");
expect(document.body.textContent).toContain("Connection timed out");
});
it("calls onResult(false) on network error", async () => {
+8 -12
View File
@@ -8,18 +8,14 @@ import { getTenantSlug } from "./tenant";
export const PLATFORM_URL =
process.env.NEXT_PUBLIC_PLATFORM_URL ?? "http://localhost:8080";
// 35s is long enough for the slowest server-side path (EIC SSH
// tunnel for tenant EC2 file operations, bounded server-side by
// `eicFileOpTimeout = 30 * time.Second` in
// workspace-server/internal/handlers/template_files_eic.go) so the
// canvas surfaces the server's real error instead of aborting first
// with a generic timeout. Shorter values caused "Save & Restart" to
// time out at the client before the backend returned its 5xx. The
// abort still propagates through AbortController so React components
// can render a retry affordance. Callers that know an endpoint is
// intentionally slow (org import walks a tree of workspaces with
// server-side pacing) can pass `timeoutMs` to override.
const DEFAULT_TIMEOUT_MS = 35_000;
// 15s is long enough for slow CP queries but short enough that a
// hung backend doesn't leave the UI spinning forever. The abort
// propagates through AbortController so React components can observe
// the error and render a retry affordance. Callers that know the
// endpoint is intentionally slow (org import walks a tree of
// workspaces with server-side pacing) can pass `timeoutMs` to
// override.
const DEFAULT_TIMEOUT_MS = 15_000;
export interface RequestOptions {
timeoutMs?: number;
-4
View File
@@ -519,10 +519,6 @@ export function buildNodesAndEdges(
// #2054 — server-declared per-workspace provisioning timeout.
// Falls through to the runtime profile when null/absent.
provisionTimeoutMs: ws.provision_timeout_ms ?? null,
// Workspace abilities — defaults preserved for old platform versions
// that don't yet include these columns in the GET response.
broadcastEnabled: ws.broadcast_enabled ?? false,
talkToUserEnabled: ws.talk_to_user_enabled ?? true,
},
};
if (hasParent) {
-7
View File
@@ -99,13 +99,6 @@ export interface WorkspaceNodeData extends Record<string, unknown> {
* @/lib/runtimeProfiles. Lets a slow runtime declare its cold-boot
* expectation without a canvas release. */
provisionTimeoutMs?: number | null;
/** When true the workspace may POST /broadcast to send org-wide messages.
* Default false. Toggled by user/admin via PATCH /workspaces/:id/abilities. */
broadcastEnabled?: boolean;
/** When false the workspace cannot deliver canvas chat messages.
* send_message_to_user / POST /notify return 403 and the canvas
* shows a "not enabled" state with a button to re-enable. Default true. */
talkToUserEnabled?: boolean;
}
export type PanelTab = "details" | "skills" | "chat" | "terminal" | "config" | "schedule" | "channels" | "files" | "memory" | "traces" | "events" | "activity" | "audit";
-3
View File
@@ -299,9 +299,6 @@ export interface WorkspaceData {
* `@/lib/runtimeProfiles` when absent (the default behavior for any
* template that hasn't yet declared the field). */
provision_timeout_ms?: number | null;
/** Workspace ability flags (migration 20260514). */
broadcast_enabled?: boolean;
talk_to_user_enabled?: boolean;
}
let socket: ReconnectingSocket | null = null;
-296
View File
@@ -1,296 +0,0 @@
#!/usr/bin/env bash
# E2E test: workspace broadcast and talk-to-user platform abilities.
#
# What this proves:
# 1. talk_to_user_enabled (default true) — POST /notify works out-of-the-box.
# 2. PATCH /workspaces/:id/abilities { talk_to_user_enabled: false } disables
# delivery: /notify → 403 with error="talk_to_user_disabled" + delegate hint.
# 3. Re-enabling talk_to_user_enabled restores delivery.
# 4. broadcast_enabled (default false) — POST /broadcast → 403 when disabled.
# 5. PATCH { broadcast_enabled: true } enables fan-out.
# 6. POST /broadcast delivers to all non-sender, non-removed workspaces:
# - Returns {"status":"sent","delivered":N}
# - Receiver's activity log has a broadcast_receive entry with the message.
# - Sender's activity log has a broadcast_sent entry.
# 7. The sender itself does NOT receive a broadcast_receive entry.
#
# Usage: tests/e2e/test_workspace_abilities_e2e.sh
# Prereqs: workspace-server on http://localhost:8080, MOLECULE_ENV != production
set -euo pipefail
source "$(dirname "$0")/_lib.sh"
PASS=0
FAIL=0
SENDER_ID=""
RECEIVER_ID=""
cleanup() {
for wid in "$SENDER_ID" "$RECEIVER_ID"; do
if [ -n "$wid" ]; then
curl -s -X DELETE "$BASE/workspaces/$wid?confirm=true" > /dev/null || true
fi
done
}
trap cleanup EXIT INT TERM
assert() {
local label="$1" actual="$2" expected="$3"
if [ "$actual" = "$expected" ]; then
echo " PASS — $label"
PASS=$((PASS+1))
else
echo " FAIL — $label"
echo " expected: $expected"
echo " actual: $actual"
FAIL=$((FAIL+1))
fi
}
assert_contains() {
local label="$1" haystack="$2" needle="$3"
if echo "$haystack" | grep -qF "$needle"; then
echo " PASS — $label"
PASS=$((PASS+1))
else
echo " FAIL — $label"
echo " needle: $needle"
echo " haystack: $haystack"
FAIL=$((FAIL+1))
fi
}
assert_not_contains() {
local label="$1" haystack="$2" needle="$3"
if ! echo "$haystack" | grep -qF "$needle"; then
echo " PASS — $label"
PASS=$((PASS+1))
else
echo " FAIL — $label (unexpected match)"
echo " needle: $needle"
echo " haystack: $haystack"
FAIL=$((FAIL+1))
fi
}
# ── Pre-sweep: remove any stale leftover workspaces from a prior aborted run ──
echo "=== Setup ==="
for NAME in "Abilities Sender" "Abilities Receiver"; do
PRIOR=$(curl -s "$BASE/workspaces" | python3 -c "
import json, sys
try:
print(' '.join(w['id'] for w in json.load(sys.stdin) if w.get('name') == '$NAME'))
except Exception:
pass
")
for _wid in $PRIOR; do
echo "Sweeping leftover '$NAME' workspace: $_wid"
curl -s -X DELETE "$BASE/workspaces/$_wid?confirm=true" > /dev/null || true
done
done
R=$(curl -s -X POST "$BASE/workspaces" -H "Content-Type: application/json" \
-d '{"name":"Abilities Sender","tier":1}')
SENDER_ID=$(echo "$R" | python3 -c 'import json,sys;print(json.load(sys.stdin)["id"])' 2>/dev/null || true)
[ -n "$SENDER_ID" ] || { echo "Failed to create sender workspace: $R"; exit 1; }
echo "Created sender workspace: $SENDER_ID"
R=$(curl -s -X POST "$BASE/workspaces" -H "Content-Type: application/json" \
-d '{"name":"Abilities Receiver","tier":1}')
RECEIVER_ID=$(echo "$R" | python3 -c 'import json,sys;print(json.load(sys.stdin)["id"])' 2>/dev/null || true)
[ -n "$RECEIVER_ID" ] || { echo "Failed to create receiver workspace: $R"; exit 1; }
echo "Created receiver workspace: $RECEIVER_ID"
# Mint workspace-scoped bearer tokens (test-only endpoint, disabled in prod).
SENDER_TOKEN=$(e2e_mint_test_token "$SENDER_ID")
[ -n "$SENDER_TOKEN" ] || { echo "Failed to mint sender token"; exit 1; }
SENDER_AUTH="Authorization: Bearer $SENDER_TOKEN"
# Admin token — any live workspace bearer satisfies AdminAuth in local dev.
# In production-like envs, set MOLECULE_ADMIN_TOKEN.
ADMIN_TOKEN="${MOLECULE_ADMIN_TOKEN:-$SENDER_TOKEN}"
ADMIN_AUTH="Authorization: Bearer $ADMIN_TOKEN"
# ─────────────────────────────────────────────────────────────────────────────
echo ""
echo "=== Part 1: talk_to_user ability ==="
echo ""
echo "--- 1a: /notify works with default talk_to_user_enabled=true ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST "$BASE/workspaces/$SENDER_ID/notify" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Hello from sender"}')
assert "POST /notify returns 200 when talk_to_user_enabled=true (default)" "$CODE" "200"
echo ""
echo "--- 1b: Disable talk_to_user ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X PATCH "$BASE/workspaces/$SENDER_ID/abilities" \
-H "Content-Type: application/json" -H "$ADMIN_AUTH" \
-d '{"talk_to_user_enabled": false}')
assert "PATCH /abilities talk_to_user_enabled=false returns 200" "$CODE" "200"
# Verify the flag is reflected in the workspace GET response.
WS=$(curl -s "$BASE/workspaces/$SENDER_ID" -H "$SENDER_AUTH")
FLAG=$(echo "$WS" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("talk_to_user_enabled","MISSING"))')
assert "GET /workspaces/:id reflects talk_to_user_enabled=false" "$FLAG" "False"
echo ""
echo "--- 1c: /notify blocked when talk_to_user disabled ---"
BODY=$(curl -s -w "" -X POST "$BASE/workspaces/$SENDER_ID/notify" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Should be blocked"}')
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST "$BASE/workspaces/$SENDER_ID/notify" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Should be blocked"}')
assert "POST /notify returns 403 when talk_to_user_enabled=false" "$CODE" "403"
ERR=$(echo "$BODY" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("error",""))' 2>/dev/null || echo "")
assert_contains "403 body contains talk_to_user_disabled error code" "$ERR" "talk_to_user_disabled"
HINT=$(echo "$BODY" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("hint",""))' 2>/dev/null || echo "")
assert_contains "403 body contains delegate_task hint" "$HINT" "delegate_task"
echo ""
echo "--- 1d: Re-enable talk_to_user and verify /notify works again ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X PATCH "$BASE/workspaces/$SENDER_ID/abilities" \
-H "Content-Type: application/json" -H "$ADMIN_AUTH" \
-d '{"talk_to_user_enabled": true}')
assert "PATCH /abilities talk_to_user_enabled=true returns 200" "$CODE" "200"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST "$BASE/workspaces/$SENDER_ID/notify" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Re-enabled, should work"}')
assert "POST /notify returns 200 after re-enabling talk_to_user" "$CODE" "200"
# ─────────────────────────────────────────────────────────────────────────────
echo ""
echo "=== Part 2: broadcast ability ==="
echo ""
echo "--- 2a: Broadcast blocked by default (broadcast_enabled=false) ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST "$BASE/workspaces/$SENDER_ID/broadcast" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Should be blocked"}')
assert "POST /broadcast returns 403 when broadcast_enabled=false (default)" "$CODE" "403"
echo ""
echo "--- 2b: Enable broadcast ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X PATCH "$BASE/workspaces/$SENDER_ID/abilities" \
-H "Content-Type: application/json" -H "$ADMIN_AUTH" \
-d '{"broadcast_enabled": true}')
assert "PATCH /abilities broadcast_enabled=true returns 200" "$CODE" "200"
WS=$(curl -s "$BASE/workspaces/$SENDER_ID" -H "$SENDER_AUTH")
FLAG=$(echo "$WS" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("broadcast_enabled","MISSING"))')
assert "GET /workspaces/:id reflects broadcast_enabled=true" "$FLAG" "True"
echo ""
echo "--- 2c: Successful broadcast fan-out ---"
BCAST=$(curl -s -X POST "$BASE/workspaces/$SENDER_ID/broadcast" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":"Org-wide notice: scheduled maintenance in 5 minutes."}')
BSTATUS=$(echo "$BCAST" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("status",""))' 2>/dev/null || echo "")
BDELIVERED=$(echo "$BCAST" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("delivered","-1"))' 2>/dev/null || echo "-1")
assert "POST /broadcast returns status=sent" "$BSTATUS" "sent"
# delivered count must be >= 1 (the receiver workspace).
echo " INFO — broadcast delivered=$BDELIVERED"
if python3 -c "import sys; sys.exit(0 if int('$BDELIVERED') >= 1 else 1)" 2>/dev/null; then
echo " PASS — delivered count >= 1"
PASS=$((PASS+1))
else
echo " FAIL — expected delivered >= 1, got $BDELIVERED"
FAIL=$((FAIL+1))
fi
echo ""
echo "--- 2d: Receiver activity log has broadcast_receive entry ---"
RECEIVER_TOKEN=$(e2e_mint_test_token "$RECEIVER_ID")
[ -n "$RECEIVER_TOKEN" ] || { echo "Failed to mint receiver token"; exit 1; }
RECEIVER_AUTH="Authorization: Bearer $RECEIVER_TOKEN"
ACT=$(curl -s -H "$RECEIVER_AUTH" "$BASE/workspaces/$RECEIVER_ID/activity?source=agent&limit=20")
ROW=$(echo "$ACT" | python3 -c '
import json, sys
rows = json.load(sys.stdin) or []
for r in rows:
if r.get("activity_type") == "broadcast_receive":
print(json.dumps(r))
break
')
[ -n "$ROW" ] || {
echo " FAIL — could not find broadcast_receive row in receiver activity"
FAIL=$((FAIL+1))
}
if [ -n "$ROW" ]; then
# Message is stored in summary field.
MSG=$(echo "$ROW" | python3 -c 'import json,sys;r=json.load(sys.stdin);print(r.get("summary",""))')
assert_contains "broadcast_receive row summary has original message" "$MSG" "scheduled maintenance"
# Sender ID is stored in source_id field.
SRC=$(echo "$ROW" | python3 -c 'import json,sys;r=json.load(sys.stdin);print(r.get("source_id",""))')
assert "broadcast_receive row source_id is sender workspace" "$SRC" "$SENDER_ID"
fi
echo ""
echo "--- 2e: Sender activity log has broadcast_sent entry ---"
ACT_SENDER=$(curl -s -H "$SENDER_AUTH" "$BASE/workspaces/$SENDER_ID/activity?limit=20")
SENT_ROW=$(echo "$ACT_SENDER" | python3 -c '
import json, sys
rows = json.load(sys.stdin) or []
for r in rows:
if r.get("activity_type") == "broadcast_sent":
print(json.dumps(r))
break
')
[ -n "$SENT_ROW" ] || {
echo " FAIL — could not find broadcast_sent row in sender activity"
FAIL=$((FAIL+1))
}
if [ -n "$SENT_ROW" ]; then
# Delivered count is baked into the summary field (no response_body for sender row).
SUMMARY=$(echo "$SENT_ROW" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("summary",""))')
assert_contains "broadcast_sent summary mentions workspace count" "$SUMMARY" "workspace"
fi
echo ""
echo "--- 2f: Sender does NOT receive a broadcast_receive entry ---"
SELF_RECV=$(echo "$ACT_SENDER" | python3 -c '
import json, sys
rows = json.load(sys.stdin) or []
for r in rows:
if r.get("activity_type") == "broadcast_receive":
print("found")
break
')
assert_not_contains "sender has no broadcast_receive in own activity log" "${SELF_RECV:-}" "found"
# ─────────────────────────────────────────────────────────────────────────────
echo ""
echo "--- 2g: Empty message is rejected ---"
CODE=$(curl -s -o /dev/null -w "%{http_code}" -X POST "$BASE/workspaces/$SENDER_ID/broadcast" \
-H "Content-Type: application/json" -H "$SENDER_AUTH" \
-d '{"message":""}')
assert "POST /broadcast with empty message returns 400" "$CODE" "400"
echo ""
echo "--- 2h: Partial PATCH does not clobber other flags ---"
# Set talk_to_user=false, then patch only broadcast — talk_to_user must stay false.
curl -s -o /dev/null -X PATCH "$BASE/workspaces/$SENDER_ID/abilities" \
-H "Content-Type: application/json" -H "$ADMIN_AUTH" \
-d '{"talk_to_user_enabled": false}'
curl -s -o /dev/null -X PATCH "$BASE/workspaces/$SENDER_ID/abilities" \
-H "Content-Type: application/json" -H "$ADMIN_AUTH" \
-d '{"broadcast_enabled": false}'
WS=$(curl -s "$BASE/workspaces/$SENDER_ID" -H "$SENDER_AUTH")
TUF=$(echo "$WS" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("talk_to_user_enabled","MISSING"))')
BEF=$(echo "$WS" | python3 -c 'import json,sys;print(json.load(sys.stdin).get("broadcast_enabled","MISSING"))')
assert "partial PATCH preserves talk_to_user_enabled=false" "$TUF" "False"
assert "partial PATCH sets broadcast_enabled=false" "$BEF" "False"
# ─────────────────────────────────────────────────────────────────────────────
echo ""
echo "=== Results: $PASS passed, $FAIL failed ==="
[ "$FAIL" -eq 0 ]
+21 -35
View File
@@ -97,28 +97,28 @@ const maxProxyResponseBody = 10 << 20
//
// Timeout model — three independent budgets, none of which gets in each other's way:
//
// 1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
// the entire request including streamed body reads, and would pre-empt
// legitimate slow cold-start flows (Claude Code first-token over OAuth
// can take 30-60s on boot; long-running agent synthesis can stream
// tokens for minutes). Total-request budget is enforced per-request
// via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
// 1. Client.Timeout — DELIBERATELY UNSET. Client.Timeout is a hard wall on
// the entire request including streamed body reads, and would pre-empt
// legitimate slow cold-start flows (Claude Code first-token over OAuth
// can take 30-60s on boot; long-running agent synthesis can stream
// tokens for minutes). Total-request budget is enforced per-request
// via context deadline (canvas = idle-only, agent-to-agent = 30 min ceiling).
//
// 2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
// black-holes TCP connects (instance terminated mid-flight, security group
// flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
// enough that Cloudflare's ~100s edge timeout can fire first and surface
// a generic 502 page to canvas. 10s is well above realistic intra-region
// latencies and well below CF's edge timeout.
// 2. Transport.DialContext — 10s connect timeout. When a workspace's EC2
// black-holes TCP connects (instance terminated mid-flight, security group
// flipped, NACL bug), the OS default is 75s on Linux / 21s on macOS — long
// enough that Cloudflare's ~100s edge timeout can fire first and surface
// a generic 502 page to canvas. 10s is well above realistic intra-region
// latencies and well below CF's edge timeout.
//
// 3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end
// to response-headers-start. Configurable via
// A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start
// first-byte (30-60s OAuth flow above) with enough room for Opus agent
// turns (big context + internal delegate_task round-trips routinely exceed
// the old 60s ceiling). Body streaming after headers is governed by the
// per-request context deadline, NOT this timeout — so multi-minute agent
// responses still work fine.
// 3. Transport.ResponseHeaderTimeout — 180s default. From request-body-end
// to response-headers-start. Configurable via
// A2A_PROXY_RESPONSE_HEADER_TIMEOUT (envx.Duration). Covers cold-start
// first-byte (30-60s OAuth flow above) with enough room for Opus agent
// turns (big context + internal delegate_task round-trips routinely exceed
// the old 60s ceiling). Body streaming after headers is governed by the
// per-request context deadline, NOT this timeout — so multi-minute agent
// responses still work fine.
//
// The point of (2) and (3) is to surface a *structured* 503 from
// handleA2ADispatchError when the workspace agent is unreachable, so canvas
@@ -399,21 +399,7 @@ func (h *WorkspaceHandler) proxyA2ARequest(ctx context.Context, workspaceID stri
// (no Do(), no maybeMarkContainerDead). The response is a synthetic
// {status:"queued"} envelope so the caller (canvas, another workspace)
// knows delivery is acknowledged but pending consumption.
deliveryMode, deliveryModeErr := lookupDeliveryMode(ctx, workspaceID)
if deliveryModeErr != nil {
// internal#497 fail-closed: a real DB/context error on the
// delivery-mode read MUST NOT silently fall through to the push
// dispatch path — that is exactly what silently misrouted every
// poll-mode peer for 5 days under the ce2db75f regression. Surface
// a structured error so the delegation is marked failed (loud +
// retryable) instead of dispatched to the wrong path.
log.Printf("ProxyA2A: delivery-mode lookup failed for %s: %v — failing closed", workspaceID, deliveryModeErr)
return 0, nil, &proxyA2AError{
Status: http.StatusServiceUnavailable,
Response: gin.H{"error": "delivery-mode lookup failed; refusing to dispatch to avoid silent misrouting"},
}
}
if deliveryMode == models.DeliveryModePoll {
if lookupDeliveryMode(ctx, workspaceID) == models.DeliveryModePoll {
if logActivity {
h.logA2AReceiveQueued(ctx, workspaceID, callerID, body, a2aMethod)
}
@@ -194,11 +194,6 @@ func (h *WorkspaceHandler) maybeMarkContainerDead(ctx context.Context, workspace
}
db.ClearWorkspaceKeys(ctx, workspaceID)
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
// Tracked via goAsync (not bare `go`) so the asyncWG can be drained
// before a test swaps the global db.DB. runRestartCycle reads db.DB
// before its provisioner gate, so an untracked detached goroutine
// races setupTestDB's t.Cleanup db.DB restore. Matches the already-
// correct site at a2a_proxy.go:648.
h.goAsync(func() { h.RestartByID(workspaceID) })
return true
}
@@ -246,9 +241,6 @@ func (h *WorkspaceHandler) preflightContainerHealth(ctx context.Context, workspa
}
db.ClearWorkspaceKeys(ctx, workspaceID)
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOffline), workspaceID, map[string]interface{}{})
// Tracked via goAsync (see maybeMarkContainerDead): preflight's
// detached restart must be drainable so it doesn't race the global
// db.DB swap in test cleanup.
h.goAsync(func() { h.RestartByID(workspaceID) })
return &proxyA2AError{
Status: http.StatusServiceUnavailable,
@@ -270,9 +262,8 @@ func (h *WorkspaceHandler) logA2AFailure(ctx context.Context, workspaceID, calle
errWsName = workspaceID
}
summary := "A2A request to " + errWsName + " failed: " + errMsg
parent := ctx
h.goAsync(func() {
logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
defer cancel()
LogActivity(logCtx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
@@ -318,9 +309,8 @@ func (h *WorkspaceHandler) logA2ASuccess(ctx context.Context, workspaceID, calle
}
summary := a2aMethod + " → " + wsNameForLog
toolTrace := extractToolTrace(respBody)
parent := ctx
h.goAsync(func() {
logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
defer cancel()
LogActivity(logCtx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
@@ -468,64 +458,40 @@ func parseUsageFromA2AResponse(body []byte) (inputTokens, outputTokens int64) {
return 0, 0
}
// lookupDeliveryMode returns the workspace's delivery_mode.
//
// internal#497 / RFC#497 fail-closed (SURGICAL scope): the *specific*
// failure mode that hid the ce2db75f regression for 5 days is now
// propagated instead of silently swallowed — a CONTEXT error
// (context.Canceled / context.DeadlineExceeded). Under ce2db75f the
// detached delegation goroutine ran on a cancelled request context, every
// `SELECT delivery_mode` failed `context canceled`, this function returned
// push, the poll-mode short-circuit in proxyA2ARequest was skipped, and
// poll-mode peers (e.g. an operator laptop on molecule-mcp-claude-channel)
// silently never got their a2a_receive inbox row. A transient,
// systematic-once-triggered context cancellation became permanent
// invisible misrouting. Returning that error lets the caller fail loud
// (mark the delegation failed) instead of mis-dispatching.
//
// Scope is deliberately narrow: only ctx errors propagate. Other DB
// errors retain the long-standing documented "fall back to push (today's
// synchronous behavior)" contract — that path is loud + recoverable
// (502 / SSRF reject / restart), unlike the silent poll-mode drop, and
// the surrounding proxy (incl. the sibling checkWorkspaceBudget) is
// intentionally built around that fail-open-to-push behavior. Widening
// further is an RFC#497 follow-up, not part of this P0 fix.
//
// A genuinely *absent* configuration is NOT an error and still resolves to
// push (the safe synchronous default): sql.ErrNoRows, a NULL/empty column,
// or an unrecognised value all return (push, nil).
// lookupDeliveryMode returns the workspace's delivery_mode. On any DB
// error or missing row it returns DeliveryModePush — the fail-closed
// default. "Closed" here means "fall back to today's behavior (synchronous
// dispatch)" rather than "fall back to drop the request silently into
// activity_logs where the agent might never see it." A poll-mode workspace
// that briefly reads as push will get its A2A request dispatched to the
// stored URL (or a 502 if no URL); a push-mode workspace that briefly
// reads as poll would get its request silently queued with no dispatch.
// The first failure is loud + recoverable; the second is silent.
//
// The function is intentionally lookup-only — it never mutates the row.
// The register handler (registry.go) is the only writer for delivery_mode.
//
// See #2339 PR 1 for the column + register-flow side; this is the
// proxy-side read used for the short-circuit in proxyA2ARequest.
func lookupDeliveryMode(ctx context.Context, workspaceID string) (string, error) {
func lookupDeliveryMode(ctx context.Context, workspaceID string) string {
var mode sql.NullString
err := db.DB.QueryRowContext(ctx,
`SELECT delivery_mode FROM workspaces WHERE id = $1`, workspaceID,
).Scan(&mode)
if err != nil {
// internal#497: a context cancellation/deadline MUST NOT be
// swallowed into a silent push default — that is the exact 5-day
// silent-misrouting vector. Propagate so the caller fails closed.
if errors.Is(err, context.Canceled) || errors.Is(err, context.DeadlineExceeded) {
log.Printf("ProxyA2A: lookupDeliveryMode(%s) context error (%v) — failing closed (NOT defaulting to push)", workspaceID, err)
return "", err
}
if !errors.Is(err, sql.ErrNoRows) {
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push (non-ctx DB error; legacy fail-open-to-push contract)", workspaceID, err)
log.Printf("ProxyA2A: lookupDeliveryMode(%s) failed (%v) — defaulting to push", workspaceID, err)
}
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
if !mode.Valid || mode.String == "" {
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
if !models.IsValidDeliveryMode(mode.String) {
log.Printf("ProxyA2A: workspace %s has invalid delivery_mode=%q — defaulting to push", workspaceID, mode.String)
return models.DeliveryModePush, nil
return models.DeliveryModePush
}
return mode.String, nil
return mode.String
}
// logA2AReceiveQueued records a poll-mode "queued" A2A receive into
@@ -544,9 +510,8 @@ func (h *WorkspaceHandler) logA2AReceiveQueued(ctx context.Context, workspaceID,
wsName = workspaceID
}
summary := a2aMethod + " → " + wsName + " (queued for poll)"
parent := ctx
h.goAsync(func() {
logCtx, cancel := context.WithTimeout(context.WithoutCancel(parent), 30*time.Second)
logCtx, cancel := context.WithTimeout(context.WithoutCancel(ctx), 30*time.Second)
defer cancel()
LogActivity(logCtx, h.broadcaster, ActivityParams{
WorkspaceID: workspaceID,
@@ -54,6 +54,7 @@ func TestPreflight_ContainerRunning_ReturnsNil(t *testing.T) {
_ = setupTestDB(t)
stub := &preflightLocalProv{running: true, err: nil}
h := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, h)
h.provisioner = stub
if err := h.preflightContainerHealth(context.Background(), "ws-running-123"); err != nil {
@@ -186,8 +187,8 @@ func TestProxyA2A_Preflight_RoutesThroughProvisionerSSOT(t *testing.T) {
}
var (
callsIsRunning bool
callsContainerInspectRaw bool
callsIsRunning bool
callsContainerInspectRaw bool
callsRunningContainerNameDirect bool
)
ast.Inspect(fn.Body, func(n ast.Node) bool {
@@ -262,6 +262,7 @@ func TestProxyA2A_Upstream502_TriggersContainerDeadCheck(t *testing.T) {
allowLoopbackForTest(t)
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
cp := &fakeCPProv{running: false}
handler.SetCPProvisioner(cp)
@@ -324,6 +325,7 @@ func TestProxyA2A_Upstream502_AliveAgent_PropagatesAsIs(t *testing.T) {
allowLoopbackForTest(t)
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
cp := &fakeCPProv{running: true}
handler.SetCPProvisioner(cp)
@@ -513,6 +515,7 @@ func TestProxyA2A_AllowedSelf_SkipsAccessCheck(t *testing.T) {
allowLoopbackForTest(t)
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
agentServer := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
w.Header().Set("Content-Type", "application/json")
@@ -661,18 +664,18 @@ func TestProxyA2A_CallerIDDerivedFromBearer(t *testing.T) {
// (column order: workspace_id, activity_type, source_id, target_id, ...)
mock.ExpectExec("INSERT INTO activity_logs").
WithArgs(
"ws-target", // $1 workspace_id
"a2a_receive", // $2 activity_type
sqlmock.AnyArg(), // $3 source_id — *string("ws-caller"), checked below
sqlmock.AnyArg(), // $4 target_id
sqlmock.AnyArg(), // $5 method
sqlmock.AnyArg(), // $6 summary
sqlmock.AnyArg(), // $7 request_body
sqlmock.AnyArg(), // $8 response_body
sqlmock.AnyArg(), // $9 tool_trace
sqlmock.AnyArg(), // $10 duration_ms
sqlmock.AnyArg(), // $11 status
sqlmock.AnyArg(), // $12 error_detail
"ws-target", // $1 workspace_id
"a2a_receive", // $2 activity_type
sqlmock.AnyArg(), // $3 source_id — *string("ws-caller"), checked below
sqlmock.AnyArg(), // $4 target_id
sqlmock.AnyArg(), // $5 method
sqlmock.AnyArg(), // $6 summary
sqlmock.AnyArg(), // $7 request_body
sqlmock.AnyArg(), // $8 response_body
sqlmock.AnyArg(), // $9 tool_trace
sqlmock.AnyArg(), // $10 duration_ms
sqlmock.AnyArg(), // $11 status
sqlmock.AnyArg(), // $12 error_detail
).
WillReturnResult(sqlmock.NewResult(0, 1))
@@ -1716,7 +1719,6 @@ func TestDispatchA2A_RejectsUnsafeURL(t *testing.T) {
}
}
// --- handleA2ADispatchError ---
func TestHandleA2ADispatchError_ContextDeadline(t *testing.T) {
@@ -1803,6 +1805,7 @@ func TestMaybeMarkContainerDead_CPOnly_NotRunning(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
cp := &fakeCPProv{running: false}
handler.SetCPProvisioner(cp)
@@ -1955,6 +1958,7 @@ func TestLogA2AFailure_Smoke(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
// Sync workspace-name lookup (called in the caller goroutine).
mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1973,6 +1977,7 @@ func TestLogA2AFailure_EmptyNameFallback(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
// Empty name from DB → summary uses the workspaceID as the name.
mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
@@ -1989,6 +1994,7 @@ func TestLogA2ASuccess_Smoke(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
WithArgs("ws-ok").
@@ -2005,6 +2011,7 @@ func TestLogA2ASuccess_ErrorStatus(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
handler := NewWorkspaceHandler(newTestBroadcaster(), nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, handler)
mock.ExpectQuery(`SELECT name FROM workspaces WHERE id =`).
WithArgs("ws-err").
@@ -2228,18 +2235,12 @@ func TestProxyA2A_PushMode_NoShortCircuit(t *testing.T) {
}
}
// TestProxyA2A_PollMode_FailsClosedToPush verifies the LEGACY safety
// contract is PRESERVED for non-context DB errors: a generic DB error
// reading delivery_mode still defaults to push (today's behavior), NOT
// poll. Failing to push means a poll-mode workspace briefly attempts a
// real dispatch — visible failure (502 / SSRF rejection / restart
// cascade), not a silent drop into activity_logs where the agent might
// never look. Loud > silent, recoverable > lost.
//
// internal#497 narrows the fail-closed change to *context* errors only
// (the actual ce2db75f regression vector); generic DB errors keep this
// long-standing fail-open-to-push contract. The ctx-error fail-closed is
// covered by TestLookupDeliveryMode_ContextCanceled_FailsClosed.
// TestProxyA2A_PollMode_FailsClosedToPush verifies the safety contract:
// a DB error reading delivery_mode must default to push (the existing
// behavior), NOT poll. Failing to push means a poll-mode workspace
// briefly attempts a real dispatch — visible failure (502 / SSRF
// rejection / restart cascade), not a silent drop into activity_logs
// where the agent might never look. Loud > silent, recoverable > lost.
func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t) // empty Redis — forces resolveAgentURL DB lookup
@@ -2250,8 +2251,7 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
expectBudgetCheck(mock, wsID)
// lookupDeliveryMode hits a generic (non-context) DB error → must
// still default push (legacy contract preserved by internal#497).
// lookupDeliveryMode hits a transient DB error → must default push.
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
WithArgs(wsID).
WillReturnError(sql.ErrConnDone)
@@ -2275,7 +2275,7 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
var resp map[string]interface{}
_ = json.Unmarshal(w.Body.Bytes(), &resp)
if resp["status"] == "queued" {
t.Errorf("generic DB error on delivery_mode lookup silently queued the request — must fail-open-to-push, got body: %s", w.Body.String())
t.Errorf("DB error on delivery_mode lookup silently queued the request — must fail-closed-to-push, got body: %s", w.Body.String())
}
}
@@ -2284,37 +2284,6 @@ func TestProxyA2A_PollMode_FailsClosedToPush(t *testing.T) {
}
}
// TestLookupDeliveryMode_ContextCanceled_FailsClosed is the internal#497
// regression test for the SECONDARY defect. It pins the exact invariant
// that hid the ce2db75f regression for 5 days: when the delivery_mode read
// fails because the context was cancelled (precisely what happened in the
// detached delegation goroutine running on a returned request context),
// lookupDeliveryMode MUST return an error and MUST NOT silently return
// "push". Returning push there is what skipped the poll-mode short-circuit
// and silently dropped 100% of poll-mode peer deliveries.
//
// A pre-cancelled context makes QueryRowContext fail with
// context.Canceled deterministically — no DB rows are mocked because the
// query never reaches a result.
func TestLookupDeliveryMode_ContextCanceled_FailsClosed(t *testing.T) {
mock := setupTestDB(t)
// The query fails on the cancelled ctx before matching; provide a
// permissive expectation so sqlmock doesn't complain about the attempt.
mock.ExpectQuery("SELECT delivery_mode FROM workspaces WHERE id").
WillReturnError(context.Canceled)
ctx, cancel := context.WithCancel(context.Background())
cancel() // simulate the HTTP handler having returned (request ctx dead)
mode, err := lookupDeliveryMode(ctx, "ws-poll-peer")
if err == nil {
t.Fatalf("internal#497 regression: lookupDeliveryMode swallowed a context error and returned mode=%q with nil err — this is the exact 5-day silent-misrouting vector", mode)
}
if mode == models.DeliveryModePush {
t.Errorf("internal#497 regression: context error must NOT default to push (got mode=%q)", mode)
}
}
// ==================== a2aClient ResponseHeaderTimeout config ====================
func TestA2AClientResponseHeaderTimeout(t *testing.T) {
@@ -26,6 +26,10 @@ import (
// setupTestDBForQueueTests creates a sqlmock DB using QueryMatcherEqual (exact
// string matching) so that ExpectQuery/ExpectExec patterns are compared verbatim.
// Uses the same global db.DB as setupTestDB so the handler can use it.
//
// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
// that tests running after this one are not polluted by a closed mock.
// Same fix as setupTestDB (handlers_test.go); same root cause as mc#975.
func setupTestDBForQueueTests(t *testing.T) sqlmock.Sqlmock {
t.Helper()
mockDB, mock, err := sqlmock.New(sqlmock.QueryMatcherOption(sqlmock.QueryMatcherEqual))
@@ -81,54 +85,6 @@ func TestExtractIdempotencyKey_emptyOnMissing(t *testing.T) {
}
}
// ──────────────────────────────────────────────────────────────────────────────
// extractExpiresInSeconds
// ──────────────────────────────────────────────────────────────────────────────
func TestExtractExpiresInSeconds_valid(t *testing.T) {
cases := []struct {
name string
body string
want int
}{
{"positive int", `{"params":{"expires_in_seconds":30}}`, 30},
{"zero", `{"params":{"expires_in_seconds":0}}`, 0},
{"large TTL", `{"params":{"expires_in_seconds":3600}}`, 3600},
{"nested message — not affected", `{"params":{"message":{"role":"user"},"expires_in_seconds":60}}`, 60},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := extractExpiresInSeconds([]byte(tc.body)); got != tc.want {
t.Errorf("extractExpiresInSeconds = %d, want %d", got, tc.want)
}
})
}
}
func TestExtractExpiresInSeconds_invalidOrMissing(t *testing.T) {
cases := []struct {
name string
body string
want int
}{
{"negative → 0", `{"params":{"expires_in_seconds":-5}}`, 0},
{"missing expires_in_seconds", `{"params":{"message":{"role":"user"}}}`, 0},
{"no params at all", `{"method":"message/send"}`, 0},
{"malformed JSON", `not json`, 0},
{"empty body", ``, 0},
{"null value", `{"params":{"expires_in_seconds":null}}`, 0},
{"string value", `{"params":{"expires_in_seconds":"30"}}`, 0},
{"float value", `{"params":{"expires_in_seconds":30.5}}`, 30},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
if got := extractExpiresInSeconds([]byte(tc.body)); got != tc.want {
t.Errorf("extractExpiresInSeconds(%q) = %d, want %d", tc.body, got, tc.want)
}
})
}
}
func TestExtractDelegationIDFromBody(t *testing.T) {
cases := []struct {
name string
@@ -482,13 +482,6 @@ func (h *ActivityHandler) Notify(c *gin.Context) {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
if errors.Is(err, ErrTalkToUserDisabled) {
c.JSON(http.StatusForbidden, gin.H{
"error": "talk_to_user_disabled",
"hint": "This workspace is not allowed to send messages directly to the user. Forward your update to a parent workspace using delegate_task — they may be able to reach the user.",
})
return
}
c.JSON(http.StatusInternalServerError, gin.H{"error": "internal error"})
return
}
@@ -464,9 +464,9 @@ func TestNotify_PersistsToActivityLogsForReloadRecovery(t *testing.T) {
t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
// Workspace existence check
mock.ExpectQuery(`SELECT name, talk_to_user_enabled FROM workspaces`).
mock.ExpectQuery(`SELECT name FROM workspaces`).
WithArgs("ws-notify").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("DD", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("DD"))
// Persistence INSERT — verify shape
mock.ExpectExec(`INSERT INTO activity_logs`).
@@ -511,9 +511,9 @@ func TestNotify_WithAttachments_PersistsFilePartsForReload(t *testing.T) {
db.DB = mockDB
t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
mock.ExpectQuery(`SELECT name, talk_to_user_enabled FROM workspaces`).
mock.ExpectQuery(`SELECT name FROM workspaces`).
WithArgs("ws-attach").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("DD", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("DD"))
// Capture the JSONB arg so we can assert on the persisted shape
// AFTER the call (must include parts[].kind=file so reload
@@ -640,9 +640,9 @@ func TestNotify_DBFailure_StillBroadcastsAnd200(t *testing.T) {
db.DB = mockDB
t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
mock.ExpectQuery(`SELECT name, talk_to_user_enabled FROM workspaces`).
mock.ExpectQuery(`SELECT name FROM workspaces`).
WithArgs("ws-x").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("DD", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("DD"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnError(fmt.Errorf("simulated db hiccup"))
@@ -2,212 +2,224 @@ package handlers
import (
"database/sql"
"encoding/json"
"net/http"
"net/http/httptest"
"os"
"strings"
"testing"
"github.com/DATA-DOG/go-sqlmock"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
)
// Valid UUID used throughout.
const wsToken = "00000000-0000-0000-0000-000000000030"
// ---------- TestTokensEnabled ----------
func TestTokensEnabled_EnvFlagTrue(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
if !TestTokensEnabled() {
t.Error("expected true when MOLECULE_ENABLE_TEST_TOKENS=1")
}
}
func TestTokensEnabled_ProductionEnv(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "")
t.Setenv("MOLECULE_ENV", "production")
if TestTokensEnabled() {
t.Error("expected false when MOLECULE_ENV=production")
}
}
func TestTokensEnabled_StagingEnv(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "")
t.Setenv("MOLECULE_ENV", "staging")
if !TestTokensEnabled() {
t.Error("expected true when MOLECULE_ENV=staging")
}
}
func TestTokensEnabled_EmptyEnv(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "")
t.Setenv("MOLECULE_ENV", "")
if !TestTokensEnabled() {
t.Error("expected true when MOLECULE_ENV is empty (local dev default)")
}
}
// ---------- GetTestToken ----------
func makeTokenHandler(t *testing.T) (*AdminTestTokenHandler, sqlmock.Sqlmock, func()) {
t.Helper()
mockDB, mock, err := sqlmock.New()
if err != nil {
t.Fatalf("failed to create sqlmock: %v", err)
}
prevDB := db.DB
db.DB = mockDB
return NewAdminTestTokenHandler(), mock, func() {
// Per agent-reviewer #7034: missing ExpectationsWereMet lets
// tests pass silently when the handler skips an expected
// SELECT/INSERT. Verify in cleanup so the failure is loud.
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("sqlmock expectations not met: %v", err)
}
db.DB = prevDB
mockDB.Close()
}
}
func getTestToken(t *testing.T, h *AdminTestTokenHandler, workspaceID string, adminToken string) *httptest.ResponseRecorder {
t.Helper()
func newTestTokenRequest(workspaceID string) (*httptest.ResponseRecorder, *gin.Context) {
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: workspaceID}}
req := httptest.NewRequest("GET", "/admin/workspaces/"+workspaceID+"/test-token", nil)
if adminToken != "" {
req.Header.Set("Authorization", "Bearer "+adminToken)
}
c.Request = req
h.GetTestToken(c)
return w
c.Request = httptest.NewRequest("GET", "/admin/workspaces/"+workspaceID+"/test-token", nil)
return w, c
}
func TestGetTestToken_DisabledByDefault(t *testing.T) {
// Set MOLECULE_ENV=production to simulate a locked-down environment.
func TestAdminTestToken_HiddenInProduction(t *testing.T) {
setupTestDB(t)
t.Setenv("MOLECULE_ENV", "production")
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "")
t.Setenv("MOLECULE_ENV", "production")
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "")
w, c := newTestTokenRequest("ws-1")
h.GetTestToken(c)
if w.Code != http.StatusNotFound {
t.Errorf("expected 404 when disabled, got %d: %s", w.Code, w.Body.String())
t.Fatalf("expected 404 in production, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_AdminTokenRequired_WrongToken(t *testing.T) {
// Set up: tokens enabled, ADMIN_TOKEN set, but request uses wrong token.
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
func TestAdminTestToken_EnabledViaFlagEvenInProd(t *testing.T) {
mock := setupTestDB(t)
t.Setenv("MOLECULE_ENV", "production")
os.Setenv("ADMIN_TOKEN", "correct-secret")
defer os.Unsetenv("ADMIN_TOKEN")
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "wrong-token")
if w.Code != http.StatusUnauthorized {
t.Errorf("expected 401, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_AdminTokenRequired_MissingBearer(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
os.Setenv("ADMIN_TOKEN", "correct-secret")
defer os.Unsetenv("ADMIN_TOKEN")
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "")
if w.Code != http.StatusUnauthorized {
t.Errorf("expected 401 when bearer missing, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_AdminTokenRequired_CorrectToken(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
os.Setenv("ADMIN_TOKEN", "correct-secret")
defer os.Unsetenv("ADMIN_TOKEN")
_, mock, cleanup := makeTokenHandler(t)
defer cleanup()
mock.ExpectQuery(`SELECT id FROM workspaces WHERE id = \$1`).
WithArgs(wsToken).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow(wsToken))
// IssueToken returns a token — we just need to verify the query ran.
mock.ExpectExec(`INSERT INTO workspace_auth_tokens`).
mock.ExpectQuery("SELECT id FROM workspaces WHERE id =").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-1"))
mock.ExpectExec("INSERT INTO workspace_auth_tokens").
WillReturnResult(sqlmock.NewResult(0, 1))
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "correct-secret")
w, c := newTestTokenRequest("ws-1")
h.GetTestToken(c)
if w.Code != http.StatusOK {
t.Errorf("expected 200, got %d: %s", w.Code, w.Body.String())
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_WorkspaceNotFound(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
// ADMIN_TOKEN not set — no auth header required.
func TestAdminTestToken_WorkspaceNotFound(t *testing.T) {
mock := setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
_, mock, cleanup := makeTokenHandler(t)
defer cleanup()
mock.ExpectQuery(`SELECT id FROM workspaces WHERE id = \$1`).
WithArgs(wsToken).
WillReturnError(sql.ErrNoRows)
mock.ExpectQuery("SELECT id FROM workspaces WHERE id =").
WithArgs("missing").
WillReturnError(sqlErrNoRows())
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "")
w, c := newTestTokenRequest("missing")
h.GetTestToken(c)
if w.Code != http.StatusNotFound {
t.Errorf("expected 404 for missing workspace, got %d: %s", w.Code, w.Body.String())
t.Fatalf("expected 404 for missing workspace, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_IssueTokenDBError(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
func TestAdminTestToken_HappyPath_TokenValidates(t *testing.T) {
mock := setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
_, mock, cleanup := makeTokenHandler(t)
defer cleanup()
mock.ExpectQuery("SELECT id FROM workspaces WHERE id =").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-1"))
mock.ExpectQuery(`SELECT id FROM workspaces WHERE id = \$1`).
WithArgs(wsToken).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow(wsToken))
// IssueToken fails.
mock.ExpectExec(`INSERT INTO workspace_auth_tokens`).
WillReturnError(sql.ErrConnDone)
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "")
if w.Code != http.StatusInternalServerError {
t.Errorf("expected 500 on token issue failure, got %d: %s", w.Code, w.Body.String())
}
}
func TestGetTestToken_ResponseContainsToken(t *testing.T) {
t.Setenv("MOLECULE_ENABLE_TEST_TOKENS", "1")
t.Setenv("MOLECULE_ENV", "production")
_, mock, cleanup := makeTokenHandler(t)
defer cleanup()
mock.ExpectQuery(`SELECT id FROM workspaces WHERE id = \$1`).
WithArgs(wsToken).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow(wsToken))
mock.ExpectExec(`INSERT INTO workspace_auth_tokens`).
// Capture the hash inserted by IssueToken so we can replay it on Validate.
var capturedHash []byte
mock.ExpectExec("INSERT INTO workspace_auth_tokens").
WithArgs("ws-1", sqlmock.AnyArg(), sqlmock.AnyArg()).
WillReturnResult(sqlmock.NewResult(0, 1))
h := NewAdminTestTokenHandler()
w := getTestToken(t, h, wsToken, "")
w, c := newTestTokenRequest("ws-1")
h.GetTestToken(c)
if w.Code != http.StatusOK {
t.Errorf("expected 200, got %d", w.Code)
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
}
body := w.Body.String()
if !(strings.Contains(body, "auth_token") && strings.Contains(body, wsToken)) {
t.Errorf("expected auth_token in response body, got: %s", body)
var resp struct {
AuthToken string `json:"auth_token"`
WorkspaceID string `json:"workspace_id"`
}
if err := json.Unmarshal(w.Body.Bytes(), &resp); err != nil {
t.Fatalf("bad json: %v", err)
}
if resp.AuthToken == "" {
t.Fatal("expected non-empty auth_token")
}
if resp.WorkspaceID != "ws-1" {
t.Errorf("expected workspace_id ws-1, got %q", resp.WorkspaceID)
}
if len(resp.AuthToken) < 32 {
t.Errorf("token looks too short: %d chars", len(resp.AuthToken))
}
// Now simulate ValidateToken lookup using the same DB — prove the token
// can be validated by feeding its sha256 back through ExpectedArgs.
// (We stub the SELECT rather than re-reading capturedHash since sqlmock
// doesn't capture live args; the important invariant is that the issued
// token passes ValidateToken given a matching hash row exists.)
_ = capturedHash
mock.ExpectQuery("SELECT t\\.id, t\\.workspace_id.*FROM workspace_auth_tokens t.*JOIN workspaces").
WithArgs(sqlmock.AnyArg()).
WillReturnRows(sqlmock.NewRows([]string{"id", "workspace_id"}).AddRow("tok-1", "ws-1"))
mock.ExpectExec("UPDATE workspace_auth_tokens SET last_used_at").
WillReturnResult(sqlmock.NewResult(0, 1))
if err := wsauth.ValidateToken(c.Request.Context(), db.DB, "ws-1", resp.AuthToken); err != nil {
t.Errorf("issued token failed to validate: %v", err)
}
}
func sqlErrNoRows() error { return sql.ErrNoRows }
// TestAdminTestToken_AdminTokenRequired_NoHeader pins the IDOR-fix (#112):
// when ADMIN_TOKEN is set, calls without an Authorization header MUST 401.
// Pre-fix, the route accepted any bearer that matched a live org token,
// allowing cross-org test-token minting. The current code uses
// subtle.ConstantTimeCompare against ADMIN_TOKEN explicitly. This test
// pins that no-header == 401 so a regression that re-enabled the AdminAuth
// fallback would fail loudly.
func TestAdminTestToken_AdminTokenRequired_NoHeader(t *testing.T) {
setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
t.Setenv("ADMIN_TOKEN", "the-admin-secret")
h := NewAdminTestTokenHandler()
w, c := newTestTokenRequest("ws-1")
h.GetTestToken(c)
if w.Code != http.StatusUnauthorized {
t.Fatalf("expected 401 with ADMIN_TOKEN set + no Authorization, got %d: %s", w.Code, w.Body.String())
}
}
// TestAdminTestToken_AdminTokenRequired_WrongHeader pins that a non-matching
// bearer is rejected. Critical for #112 — an attacker presenting any other
// org's token must NOT pass.
func TestAdminTestToken_AdminTokenRequired_WrongHeader(t *testing.T) {
setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
t.Setenv("ADMIN_TOKEN", "the-admin-secret")
h := NewAdminTestTokenHandler()
w, c := newTestTokenRequest("ws-1")
c.Request.Header.Set("Authorization", "Bearer wrong-token")
h.GetTestToken(c)
if w.Code != http.StatusUnauthorized {
t.Fatalf("expected 401 with wrong Authorization, got %d: %s", w.Code, w.Body.String())
}
}
// TestAdminTestToken_AdminTokenRequired_CorrectHeader pins the success
// path through the ADMIN_TOKEN gate. Together with the no-header + wrong-
// header pair, this proves the gate distinguishes correct from incorrect
// rather than (e.g.) erroring on every request.
func TestAdminTestToken_AdminTokenRequired_CorrectHeader(t *testing.T) {
mock := setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
t.Setenv("ADMIN_TOKEN", "the-admin-secret")
mock.ExpectQuery("SELECT id FROM workspaces WHERE id =").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-1"))
mock.ExpectExec("INSERT INTO workspace_auth_tokens").
WillReturnResult(sqlmock.NewResult(0, 1))
h := NewAdminTestTokenHandler()
w, c := newTestTokenRequest("ws-1")
c.Request.Header.Set("Authorization", "Bearer the-admin-secret")
h.GetTestToken(c)
if w.Code != http.StatusOK {
t.Fatalf("expected 200 with correct ADMIN_TOKEN, got %d: %s", w.Code, w.Body.String())
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("sqlmock expectations not met — INSERT into workspace_auth_tokens did not run, suggesting the gate short-circuited the success path: %v", err)
}
}
// TestAdminTestToken_AdminTokenEmpty_GateBypassedSafely pins that when
// ADMIN_TOKEN is unset (typical local-dev setup), the explicit gate is
// bypassed and the route works without an Authorization header. This is
// the same code path the existing TestAdminTestToken_EnabledViaFlagEvenInProd
// exercises, but pinned explicitly so a future refactor that conflates
// "ADMIN_TOKEN unset" with "always 401" gets caught immediately.
func TestAdminTestToken_AdminTokenEmpty_GateBypassedSafely(t *testing.T) {
mock := setupTestDB(t)
t.Setenv("MOLECULE_ENV", "development")
t.Setenv("ADMIN_TOKEN", "")
mock.ExpectQuery("SELECT id FROM workspaces WHERE id =").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("ws-1"))
mock.ExpectExec("INSERT INTO workspace_auth_tokens").
WillReturnResult(sqlmock.NewResult(0, 1))
h := NewAdminTestTokenHandler()
w, c := newTestTokenRequest("ws-1")
// Note: NO Authorization header — the gate is unset, so this MUST work.
h.GetTestToken(c)
if w.Code != http.StatusOK {
t.Fatalf("expected 200 with ADMIN_TOKEN empty + no Authorization, got %d: %s", w.Code, w.Body.String())
}
}
@@ -1,113 +0,0 @@
package handlers
import "encoding/json"
// agent_card_reconcile.go — server-side repair for the fleet-wide
// agent-card identity gap.
//
// Root cause: the runtime builds its AgentCard from config.name
// (workspace/main.py:198), and config.name is read from the
// CP-regenerated /configs/config.yaml whose `name:` field is the raw
// workspace UUID — NOT the friendly name the operator sees. The friendly
// name IS captured: POST /workspaces and PATCH /workspaces/:id (the
// canvas Details tab) write it to the trusted workspaces.name DB column.
// But /registry/register stores the runtime-supplied card verbatim
// (registry.go: `agent_card = EXCLUDED.agent_card`), so the stored card
// served at /.well-known/agent-card.json and returned to peers via
// agent_card_url ends up with name = UUID, description = "", role = null.
//
// Fix shape (deliberately minimal, no contract weakening): when the
// runtime-supplied card's `name` is empty or equals the workspace UUID
// (the placeholder the runtime had no better value for), the PLATFORM —
// not the agent — substitutes the friendly value from the trusted
// workspaces row. Identity stays platform-controlled: the agent never
// gains the ability to self-set its own name/role; the platform sources
// it from the operator-controlled DB column. We only ever FILL gaps
// (empty / UUID-placeholder); a card that already carries a real
// friendly name is never downgraded.
//
// list_peers / the /registry/:id/peers endpoint already resolve display
// names from workspaces.name directly (discovery.go / mcp_tools.go
// `SELECT w.id, w.name, ...`), so peer_name in delivered message tags
// was already correct — this fix closes the remaining surface: the
// agent_card blob itself (canvas Agent Card / Skills view, peer
// agent_card_url fetches, the well-known card).
//
// description / role degrade discovery the same way: an empty
// description and null role give peers nothing to reason about. We
// default description from the (now reconciled) name when blank and
// role from workspaces.role when the operator set one.
// reconcileAgentCardIdentity patches identity gaps in a runtime-supplied
// agent card from the trusted workspace DB row. It returns the
// (possibly rewritten) card bytes and whether anything changed. On any
// failure (malformed JSON, nothing to fill) it returns the input bytes
// unchanged with changed=false so the caller can store them verbatim —
// this is strictly no-worse-than-before, never a regression.
//
// Pure function: no DB / HTTP / globals, so it is exhaustively
// unit-testable (agent_card_reconcile_test.go) without booting the
// handler or a sqlmock.
func reconcileAgentCardIdentity(card json.RawMessage, workspaceID, dbName, dbRole string) (json.RawMessage, bool) {
var m map[string]any
if err := json.Unmarshal(card, &m); err != nil || m == nil {
// Malformed card — not this function's job to reject it (the
// upsert stores it as-is and downstream readers handle bad
// JSON). Return verbatim so byte-for-byte behaviour is
// preserved on the failure path.
return card, false
}
changed := false
// name: fill only when empty or the UUID placeholder. A dbName that
// is itself the UUID is a placeholder row (registry.go INSERT seeds
// name = id before the canvas sets a friendly one) — not a friendly
// name, so it is not an eligible source.
cardName, _ := m["name"].(string)
if (cardName == "" || cardName == workspaceID) &&
dbName != "" && dbName != workspaceID {
m["name"] = dbName
changed = true
}
// description: when blank, default to the (reconciled) name so peers
// and the canvas Agent Card view have a non-empty human label
// instead of "". Mirrors the runtime's own
// `config.description or config.name` fallback (main.py:199) but
// applied to the registry copy where the runtime's fallback was the
// UUID.
if desc, _ := m["description"].(string); desc == "" {
if n, _ := m["name"].(string); n != "" && n != workspaceID {
m["description"] = n
changed = true
}
}
// role: surface the operator-set workspaces.role when the card
// carries none. Discovery (peer_role) and the canvas Role row read
// workspaces.role directly; this just makes the standalone card
// self-describing too. Never overwrite a role the card already has.
if dbRole != "" {
if r, ok := m["role"].(string); !ok || r == "" {
m["role"] = dbRole
changed = true
}
}
if !changed {
// No-op: return the original bytes untouched so callers that
// compare/store get byte-identical input (re-marshalling would
// reorder keys for no reason).
return card, false
}
out, err := json.Marshal(m)
if err != nil {
// Re-marshal of a map we just unmarshalled should never fail;
// if it somehow does, fall back to the verbatim input rather
// than storing nothing.
return card, false
}
return out, true
}
@@ -1,166 +0,0 @@
package handlers
import (
"encoding/json"
"testing"
)
// TestReconcileAgentCardIdentity covers the server-side backfill that
// repairs the fleet-wide agent-card identity gap (internal#XXX): the
// runtime POSTs /registry/register with agent_card.name = the workspace
// UUID (because the CP-regenerated /configs/config.yaml sets name: <uuid>)
// while the trusted workspaces.name DB column — the value the canvas
// Details tab shows and lets the operator edit — holds the friendly
// name ("Claude Code Agent"). The platform reconciles them from the DB
// row (NOT from the agent — identity stays platform-controlled, not
// self-mutable).
func TestReconcileAgentCardIdentity(t *testing.T) {
const wsID = "3b81321b-1ec7-488c-96f7-72c42a968da6"
tests := []struct {
name string
card string
dbName string
dbRole string
wantName string
wantDesc string
wantRole string
wantChanged bool
}{
{
name: "name is the workspace UUID — backfill from DB",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6","description":"","capabilities":{"streaming":true}}`,
dbName: "Claude Code Agent",
dbRole: "",
wantName: "Claude Code Agent",
wantDesc: "Claude Code Agent",
wantRole: "",
wantChanged: true,
},
{
name: "empty name — backfill from DB",
card: `{"name":"","description":"x"}`,
dbName: "ops-agent",
dbRole: "sre",
wantName: "ops-agent",
wantDesc: "x",
wantRole: "sre",
wantChanged: true,
},
{
name: "role null in card, DB has role — backfill role only",
card: `{"name":"Reviewer","description":"Senior reviewer"}`,
dbName: "Reviewer",
dbRole: "code-reviewer",
wantName: "Reviewer",
wantDesc: "Senior reviewer",
wantRole: "code-reviewer",
wantChanged: true,
},
{
name: "card already has a real friendly name — do NOT clobber it",
// A richer card (e.g. an external channel agent) must win;
// the platform only fills gaps, never downgrades.
card: `{"name":"Claude Code (channel)","description":"Local Claude Code session bridged","role":"assistant"}`,
dbName: "hongming-pc",
dbRole: "operator",
wantName: "Claude Code (channel)",
wantDesc: "Local Claude Code session bridged",
wantRole: "assistant",
wantChanged: false,
},
{
name: "no DB name available — leave UUID name untouched (no worse than before)",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6","description":""}`,
dbName: "",
dbRole: "",
wantName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
wantDesc: "",
wantRole: "",
wantChanged: false,
},
{
name: "dbName equals UUID (placeholder row) — not a friendly name, leave untouched",
card: `{"name":"3b81321b-1ec7-488c-96f7-72c42a968da6"}`,
dbName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
dbRole: "",
wantName: "3b81321b-1ec7-488c-96f7-72c42a968da6",
wantDesc: "",
wantRole: "",
wantChanged: false,
},
{
name: "malformed card JSON — return unchanged, no panic",
card: `{not json`,
dbName: "Claude Code Agent",
dbRole: "",
wantChanged: false,
},
}
for _, tc := range tests {
t.Run(tc.name, func(t *testing.T) {
out, changed := reconcileAgentCardIdentity(
json.RawMessage(tc.card), wsID, tc.dbName, tc.dbRole,
)
if changed != tc.wantChanged {
t.Fatalf("changed = %v, want %v", changed, tc.wantChanged)
}
if !tc.wantChanged {
// Unchanged path must return the input bytes verbatim.
if string(out) != tc.card {
t.Fatalf("unchanged path mutated bytes:\n got %s\n want %s", out, tc.card)
}
return
}
var got map[string]any
if err := json.Unmarshal(out, &got); err != nil {
t.Fatalf("output not valid JSON: %v (%s)", err, out)
}
if g, _ := got["name"].(string); g != tc.wantName {
t.Errorf("name = %q, want %q", g, tc.wantName)
}
if g, _ := got["description"].(string); g != tc.wantDesc {
t.Errorf("description = %q, want %q", g, tc.wantDesc)
}
if tc.wantRole != "" {
if g, _ := got["role"].(string); g != tc.wantRole {
t.Errorf("role = %q, want %q", g, tc.wantRole)
}
}
})
}
}
// TestReconcileAgentCardIdentity_PreservesOtherFields ensures the
// reconcile is a minimal in-place patch — capabilities, version,
// skills and any unknown future fields survive untouched.
func TestReconcileAgentCardIdentity_PreservesOtherFields(t *testing.T) {
card := `{"name":"ws-uuid","description":"","version":"1.0.0",` +
`"capabilities":{"streaming":true,"pushNotifications":true},` +
`"skills":[{"id":"a","name":"a"}],"configuration_status":"ready"}`
out, changed := reconcileAgentCardIdentity(
json.RawMessage(card), "ws-uuid", "Friendly Name", "",
)
if !changed {
t.Fatal("expected changed = true")
}
var got map[string]any
if err := json.Unmarshal(out, &got); err != nil {
t.Fatalf("invalid JSON: %v", err)
}
if got["version"] != "1.0.0" {
t.Errorf("version not preserved: %v", got["version"])
}
if got["configuration_status"] != "ready" {
t.Errorf("configuration_status not preserved: %v", got["configuration_status"])
}
caps, ok := got["capabilities"].(map[string]any)
if !ok || caps["streaming"] != true {
t.Errorf("capabilities not preserved: %v", got["capabilities"])
}
skills, ok := got["skills"].([]any)
if !ok || len(skills) != 1 {
t.Errorf("skills not preserved: %v", got["skills"])
}
}
@@ -54,11 +54,6 @@ import (
// timeout) surface as wrapped errors and should be treated as 503.
var ErrWorkspaceNotFound = errors.New("agent_message: workspace not found")
// ErrTalkToUserDisabled is returned when the workspace has
// talk_to_user_enabled=false. Callers surface HTTP 403 so the Python tool
// can detect it and suggest forwarding to a parent workspace.
var ErrTalkToUserDisabled = errors.New("agent_message: talk_to_user disabled")
// 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
@@ -112,20 +107,16 @@ func (w *AgentMessageWriter) Send(
// notify call surfaced as "workspace not found" and masked real
// incidents in the alert path.
var wsName string
var talkToUserEnabled bool
err := w.db.QueryRowContext(ctx,
`SELECT name, talk_to_user_enabled FROM workspaces WHERE id = $1 AND status != 'removed'`,
`SELECT name FROM workspaces WHERE id = $1 AND status != 'removed'`,
workspaceID,
).Scan(&wsName, &talkToUserEnabled)
).Scan(&wsName)
if errors.Is(err, sql.ErrNoRows) {
return ErrWorkspaceNotFound
}
if err != nil {
return fmt.Errorf("agent_message: workspace lookup: %w", err)
}
if !talkToUserEnabled {
return ErrTalkToUserDisabled
}
// 2. Build broadcast payload + WS-emit. Same shape that ChatTab's
// AGENT_MESSAGE handler in canvas/src/store/canvas-events.ts has
@@ -88,9 +88,9 @@ func TestAgentMessageWriter_Send_Success_NoAttachments(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
@@ -116,9 +116,9 @@ func TestAgentMessageWriter_Send_Success_WithAttachments(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-att").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("Ryan", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Ryan"))
mock.ExpectExec(`INSERT INTO activity_logs.*'a2a_receive'.*'notify'`).
WithArgs(
@@ -173,9 +173,9 @@ func TestAgentMessageWriter_Send_WorkspaceNotFound(t *testing.T) {
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-missing").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}))
WillReturnRows(sqlmock.NewRows([]string{"name"}))
err := w.Send(context.Background(), "ws-missing", "lost in the void", nil)
if !errors.Is(err, ErrWorkspaceNotFound) {
@@ -202,9 +202,9 @@ func TestAgentMessageWriter_Send_DBInsertFailureStillReturnsNil(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-dbfail").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnError(errors.New("transient db error"))
@@ -223,9 +223,9 @@ func TestAgentMessageWriter_Send_PreviewTruncation(t *testing.T) {
mock := setupTestDB(t)
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-trunc").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("Ryan", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Ryan"))
longMsg := strings.Repeat("x", 200)
mock.ExpectExec(`INSERT INTO activity_logs`).
@@ -263,9 +263,9 @@ func TestAgentMessageWriter_Send_BroadcastsAgentMessageEvent(t *testing.T) {
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-bc").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("Workspace Name", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("Workspace Name"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
@@ -315,7 +315,7 @@ func TestAgentMessageWriter_Send_DBErrorOnLookupReturnsWrapped(t *testing.T) {
w := NewAgentMessageWriter(db.DB, newTestBroadcaster())
transientErr := errors.New("connection refused")
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-dbdown").
WillReturnError(transientErr)
@@ -350,9 +350,9 @@ func TestAgentMessageWriter_Send_NonASCIIMessagePersists(t *testing.T) {
// the byte-slice bug.
msg := strings.Repeat("你", 200)
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-cjk").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("CEO Ryan PC"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WithArgs(
@@ -395,9 +395,9 @@ func TestAgentMessageWriter_Send_OmitsAttachmentsKeyWhenEmpty(t *testing.T) {
emitter := &capturingEmitter{}
w := NewAgentMessageWriter(db.DB, emitter)
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-noatt").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("X", true))
WillReturnRows(sqlmock.NewRows([]string{"name"}).AddRow("X"))
mock.ExpectExec(`INSERT INTO activity_logs`).
WillReturnResult(sqlmock.NewResult(1, 1))
@@ -116,9 +116,6 @@ func (h *ApprovalsHandler) ListAll(c *gin.Context) {
"created_at": createdAt,
})
}
if err := rows.Err(); err != nil {
log.Printf("ListPendingApprovals rows.Err: %v", err)
}
c.JSON(http.StatusOK, approvals)
}
@@ -158,9 +155,6 @@ func (h *ApprovalsHandler) List(c *gin.Context) {
"created_at": createdAt,
})
}
if err := rows.Err(); err != nil {
log.Printf("ListApprovals rows.Err workspace=%s: %v", workspaceID, err)
}
c.JSON(http.StatusOK, approvals)
}
@@ -2,6 +2,7 @@ package handlers
import (
"context"
"database/sql"
"encoding/json"
"log"
"net/http"
@@ -162,32 +163,8 @@ func (h *DelegationHandler) Delegate(c *gin.Context) {
},
})
// Fire-and-forget: send A2A in a background goroutine.
//
// internal#497 — the goroutine MUST NOT inherit the HTTP request's
// cancellation. `ctx` here is c.Request.Context(); the handler returns
// 202 a few lines below, which cancels that context immediately. Before
// this fix (regression ce2db75f) executeDelegation ran on the
// request-scoped ctx, so every DB op + proxy call in the detached
// goroutine failed `context canceled` the instant the 202 was written.
// That silently broke 100% of A2A peer delegations fleet-wide since
// 2026-05-12 (poll-mode peers never got their a2a_receive inbox row;
// lookupDeliveryMode swallowed the ctx error and defaulted to push).
//
// context.WithoutCancel detaches cancellation/deadline while PRESERVING
// all context values (trace/correlation/tenant ids that proxyA2ARequest
// and the broadcaster read off ctx) — this is the established pattern in
// this package (a2a_proxy.go:850, a2a_proxy_helpers.go:525,
// registry.go:822). The 30-minute ceiling matches the prior internal
// budget executeDelegation used before ce2db75f and the proxy's own
// absolute agent-dispatch ceiling (a2a_proxy.go forwardCtx).
delegationCtx, cancelDelegation := context.WithTimeout(
context.WithoutCancel(ctx), 30*time.Minute,
)
go func() {
defer cancelDelegation()
h.executeDelegation(delegationCtx, sourceID, body.TargetID, delegationID, a2aBody)
}()
// Fire-and-forget: send A2A in background goroutine
go h.executeDelegation(ctx, sourceID, body.TargetID, delegationID, a2aBody)
// Broadcast event so canvas shows delegation in real-time
h.broadcaster.RecordAndBroadcast(ctx, string(events.EventDelegationSent), sourceID, map[string]interface{}{
@@ -722,7 +699,8 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
var result []map[string]interface{}
for rows.Next() {
var delegationID, callerID, calleeID, taskPreview, status, resultPreview, errorDetail string
var delegationID, callerID, calleeID, taskPreview, status string
var resultPreview, errorDetail sql.NullString
var lastHeartbeat, deadline, createdAt, updatedAt *time.Time
if err := rows.Scan(
&delegationID, &callerID, &calleeID, &taskPreview,
@@ -741,11 +719,11 @@ func (h *DelegationHandler) listDelegationsFromLedger(ctx context.Context, works
"updated_at": updatedAt,
"_ledger": true, // marker so callers know this row is from the ledger
}
if resultPreview != "" {
entry["response_preview"] = textutil.TruncateBytes(resultPreview, 300)
if resultPreview.Valid && resultPreview.String != "" {
entry["response_preview"] = textutil.TruncateBytes(resultPreview.String, 300)
}
if errorDetail != "" {
entry["error"] = errorDetail
if errorDetail.Valid && errorDetail.String != "" {
entry["error"] = errorDetail.String
}
if lastHeartbeat != nil {
entry["last_heartbeat"] = lastHeartbeat
@@ -145,6 +145,54 @@ func TestListDelegationsFromLedger_MultipleRows(t *testing.T) {
}
}
func TestListDelegationsFromLedger_NullsOmitted(t *testing.T) {
// last_heartbeat, deadline, result_preview, error_detail are all NULL.
// Handler must not panic and must omit those keys from the map.
mockDB, mock, err := sqlmock.New()
if err != nil {
t.Fatalf("failed to create sqlmock: %v", err)
}
prevDB := db.DB
db.DB = mockDB
t.Cleanup(func() { mockDB.Close(); db.DB = prevDB })
now := time.Now()
rows := sqlmock.NewRows([]string{
"delegation_id", "caller_id", "callee_id", "task_preview",
"status", "result_preview", "error_detail",
"last_heartbeat", "deadline", "created_at", "updated_at",
}).
AddRow("del-1", "ws-1", "ws-2", "task", "queued", nil, nil, nil, nil, now, now)
mock.ExpectQuery("SELECT .+ FROM delegations").
WithArgs("ws-1").
WillReturnRows(rows)
broadcaster := newTestBroadcaster()
wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
dh := NewDelegationHandler(wh, broadcaster)
got := dh.listDelegationsFromLedger(context.Background(), "ws-1")
if len(got) != 1 {
t.Fatalf("expected 1 entry, got %d", len(got))
}
e := got[0]
if _, ok := e["last_heartbeat"]; ok {
t.Error("last_heartbeat should be absent when NULL")
}
if _, ok := e["deadline"]; ok {
t.Error("deadline should be absent when NULL")
}
if _, ok := e["response_preview"]; ok {
t.Error("response_preview should be absent when NULL result_preview")
}
if _, ok := e["error"]; ok {
t.Error("error should be absent when NULL error_detail")
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("sqlmock expectations: %v", err)
}
}
func TestListDelegationsFromLedger_QueryError(t *testing.T) {
// Query failure returns nil — graceful fallback, no panic.
mockDB, mock, err := sqlmock.New()
@@ -438,10 +486,3 @@ func TestListDelegationsFromActivityLogs_RowsErr(t *testing.T) {
t.Errorf("sqlmock expectations: %v", err)
}
}
// TestListDelegationsFromActivityLogs_ScanErrorSkipped is removed.
//
// Same reason as TestListDelegationsFromLedger_ScanError: Go 1.25 causes
// sqlmock.NewRows([]string{}).AddRow(...) to panic in test SETUP. The handler
// has no recover(), so a scan panic would crash the process — the correct
// behaviour. Real-DB integration tests cover this path.
@@ -16,65 +16,6 @@ import (
"github.com/gin-gonic/gin"
)
// ---------- internal#497 regression: detached goroutine ctx must outlive the handler ----------
// TestDelegate_DetachedContext_SurvivesRequestCancellation pins the
// load-bearing invariant that regression ce2db75f violated: the context
// handed to executeDelegation in the fire-and-forget goroutine must NOT be
// cancelled when the HTTP handler returns 202 (which cancels
// c.Request.Context()). Before the fix, executeDelegation ran on the
// request-scoped ctx, so every DB op + proxy call failed `context
// canceled` the instant the 202 was written — silently breaking 100% of
// A2A peer delegations fleet-wide since 2026-05-12.
//
// This test asserts the exact ctx-derivation contract used by Delegate
// (context.WithoutCancel(parent) + a timeout budget): the derived context
// (a) stays alive after the parent is cancelled, and (b) still carries
// parent values (trace/correlation/tenant ids the downstream proxy +
// broadcaster read off ctx). It is intentionally DB-free and fast.
func TestDelegate_DetachedContext_SurvivesRequestCancellation(t *testing.T) {
type ctxKey string
const traceKey ctxKey = "trace-id"
// Simulate c.Request.Context() carrying a correlation value.
parent, cancelParent := context.WithCancel(
context.WithValue(context.Background(), traceKey, "trace-abc-123"),
)
// Exact derivation Delegate uses for the detached goroutine.
delegationCtx, cancelDelegation := context.WithTimeout(
context.WithoutCancel(parent), 30*time.Minute,
)
defer cancelDelegation()
// The HTTP handler "returns 202" → request context is cancelled.
cancelParent()
if err := parent.Err(); err == nil {
t.Fatal("precondition: parent context should be cancelled after the handler returns")
}
// (a) Cancellation MUST NOT propagate to the detached context.
select {
case <-delegationCtx.Done():
t.Fatalf("regression: detached delegation ctx was cancelled by the handler returning (err=%v) — executeDelegation would fail every DB op with `context canceled`", delegationCtx.Err())
default:
// alive — correct
}
// (b) Parent values MUST still be readable (WithoutCancel preserves
// values; trace/correlation/tenant ids the proxy + broadcaster use).
if got, _ := delegationCtx.Value(traceKey).(string); got != "trace-abc-123" {
t.Errorf("detached ctx lost the parent trace value: got %q, want %q", got, "trace-abc-123")
}
// And it still has a real deadline (the 30m budget), so it is not an
// unbounded background context.
if _, hasDeadline := delegationCtx.Deadline(); !hasDeadline {
t.Error("detached ctx must carry the 30-minute timeout budget, but has no deadline")
}
}
// ---------- Delegate: missing target_id → 400 ----------
func TestDelegate_MissingTargetID(t *testing.T) {
@@ -230,21 +230,20 @@ func TestWorkspaceList_WithData(t *testing.T) {
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
// 23 cols — broadcast_enabled + talk_to_user_enabled added after monthly_spend
// (migration 20260514). Column order must match scanWorkspaceRow exactly.
// 21 cols — see scanWorkspaceRow for order (max_concurrent_tasks
// lands between active_tasks and last_error_rate).
columns := []string{
"id", "name", "role", "tier", "status", "agent_card", "url",
"parent_id", "active_tasks", "max_concurrent_tasks",
"last_error_rate", "last_sample_error",
"uptime_seconds", "current_task", "runtime", "workspace_dir", "x", "y", "collapsed",
"budget_limit", "monthly_spend",
"broadcast_enabled", "talk_to_user_enabled",
}
rows := sqlmock.NewRows(columns).
AddRow("ws-1", "Agent One", "worker", 1, "online", []byte(`{"name":"agent1"}`), "http://localhost:8001",
nil, 3, 1, 0.02, "", 7200, "processing", "langgraph", "", 10.0, 20.0, false, nil, int64(0), false, true).
nil, 3, 1, 0.02, "", 7200, "processing", "langgraph", "", 10.0, 20.0, false, nil, int64(0)).
AddRow("ws-2", "Agent Two", "", 2, "degraded", []byte("null"), "",
nil, 0, 1, 0.6, "timeout", 100, "", "claude-code", "", 50.0, 60.0, true, nil, int64(0), false, true)
nil, 0, 1, 0.6, "timeout", 100, "", "claude-code", "", 50.0, 60.0, true, nil, int64(0))
mock.ExpectQuery("SELECT w.id, w.name").
WillReturnRows(rows)
@@ -8,7 +8,6 @@ import (
"fmt"
"net/http"
"net/http/httptest"
"sync"
"testing"
"time"
@@ -23,44 +22,18 @@ import (
"github.com/redis/go-redis/v9"
)
// liveTestHandlers tracks every WorkspaceHandler built during the test
// binary's lifetime so setupTestDB can drain their in-flight goAsync
// goroutines (notably the detached RestartByID restart cycle, which
// reads the global db.DB) BEFORE restoring db.DB. Without this drain a
// fire-and-forget restart goroutine spawned by one test outlives that
// test and races the db.DB swap in a later test's t.Cleanup — the
// 0x...d548 data race on platform/internal/db.DB.
var (
liveTestHandlersMu sync.Mutex
liveTestHandlers []*WorkspaceHandler
)
func init() {
gin.SetMode(gin.TestMode)
newHandlerHook = func(h *WorkspaceHandler) {
liveTestHandlersMu.Lock()
liveTestHandlers = append(liveTestHandlers, h)
liveTestHandlersMu.Unlock()
}
}
// drainTestAsync waits for every tracked handler's goAsync goroutines to
// finish. Called from setupTestDB's cleanup before db.DB is restored so
// no detached restart/provision goroutine is mid-read of db.DB when the
// pointer is swapped.
func drainTestAsync() {
liveTestHandlersMu.Lock()
handlers := make([]*WorkspaceHandler, len(liveTestHandlers))
copy(handlers, liveTestHandlers)
liveTestHandlersMu.Unlock()
for _, h := range handlers {
h.waitAsyncForTest()
}
}
// setupTestDB creates a sqlmock DB and assigns it to the global db.DB.
// It also disables the SSRF URL check so that httptest.NewServer loopback
// URLs and fake hostnames (*.example) used in tests don't trigger rejections.
//
// IMPORTANT: db.DB is saved before assignment and restored via t.Cleanup so
// that tests running after this one are not polluted by a closed mock.
// This is the single root cause of the systemic CI/Platform (Go) failures on
// main HEAD 8026f020 (mc#975).
func setupTestDB(t *testing.T) sqlmock.Sqlmock {
t.Helper()
mockDB, mock, err := sqlmock.New()
@@ -69,16 +42,7 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
}
prevDB := db.DB
db.DB = mockDB
t.Cleanup(func() {
// Drain detached async goroutines (e.g. goAsync(RestartByID),
// which reads db.DB in runRestartCycle before its provisioner
// gate) BEFORE swapping db.DB back. Doing the restore first
// would let an in-flight restart goroutine read db.DB while
// this line writes it — the data race this guards against.
drainTestAsync()
db.DB = prevDB
mockDB.Close()
})
t.Cleanup(func() { db.DB = prevDB; mockDB.Close() })
// Disable SSRF checks for the duration of this test only. Restore
// the previous state via t.Cleanup so that TestIsSafeURL_* tests
@@ -98,6 +62,11 @@ func setupTestDB(t *testing.T) sqlmock.Sqlmock {
return mock
}
func waitForHandlerAsyncBeforeDBCleanup(t *testing.T, h *WorkspaceHandler) {
t.Helper()
t.Cleanup(h.waitAsyncForTest)
}
// setupTestRedis creates a miniredis instance and assigns it to the global db.RDB.
func setupTestRedis(t *testing.T) *miniredis.Miniredis {
t.Helper()
@@ -397,6 +366,11 @@ func TestWorkspaceCreate(t *testing.T) {
}
func TestBuildProvisionerConfig_IncludesAwarenessSettings(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectQuery(`SELECT digest FROM runtime_image_pins`).
WithArgs("claude-code").
WillReturnError(sql.ErrNoRows)
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", "/tmp/configs")
@@ -433,21 +407,21 @@ func TestWorkspaceList(t *testing.T) {
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", "/tmp/configs")
// 23 cols: broadcast_enabled + talk_to_user_enabled added after monthly_spend
// (migration 20260514). Column order must match scanWorkspaceRow exactly.
// 21 cols: `max_concurrent_tasks` added between active_tasks and
// last_error_rate (see scanWorkspaceRow + COALESCE(w.max_concurrent_tasks, 1)
// in workspace.go). Column order must match that scan exactly.
columns := []string{
"id", "name", "role", "tier", "status", "agent_card", "url",
"parent_id", "active_tasks", "max_concurrent_tasks",
"last_error_rate", "last_sample_error",
"uptime_seconds", "current_task", "runtime", "workspace_dir", "x", "y", "collapsed",
"budget_limit", "monthly_spend",
"broadcast_enabled", "talk_to_user_enabled",
}
rows := sqlmock.NewRows(columns).
AddRow("ws-1", "Agent One", "worker", 1, "online", []byte("null"), "http://localhost:8001",
nil, 0, 1, 0.0, "", 100, "", "claude-code", "", 10.0, 20.0, false, nil, int64(0), false, true).
nil, 0, 1, 0.0, "", 100, "", "claude-code", "", 10.0, 20.0, false, nil, int64(0)).
AddRow("ws-2", "Agent Two", "manager", 2, "provisioning", []byte("null"), "",
nil, 0, 1, 0.0, "", 0, "", "langgraph", "", 50.0, 60.0, false, nil, int64(0), false, true)
nil, 0, 1, 0.0, "", 0, "", "langgraph", "", 50.0, 60.0, false, nil, int64(0))
mock.ExpectQuery("SELECT w.id, w.name").
WillReturnRows(rows)
@@ -1161,14 +1135,13 @@ func TestWorkspaceGet_CurrentTask(t *testing.T) {
"parent_id", "active_tasks", "max_concurrent_tasks", "last_error_rate", "last_sample_error",
"uptime_seconds", "current_task", "runtime", "workspace_dir", "x", "y", "collapsed",
"budget_limit", "monthly_spend",
"broadcast_enabled", "talk_to_user_enabled",
}
mock.ExpectQuery("SELECT w.id, w.name").
WithArgs("dddddddd-0004-0000-0000-000000000000").
WillReturnRows(sqlmock.NewRows(columns).AddRow(
"dddddddd-0004-0000-0000-000000000000", "Task Worker", "worker", 1, "online", []byte("null"), "http://localhost:9000",
nil, 2, 1, 0.0, "", 300, "Analyzing document", "langgraph", "", 10.0, 20.0, false,
nil, int64(0), false, true,
nil, int64(0),
))
w := httptest.NewRecorder()
@@ -248,9 +248,6 @@ func (h *InstructionsHandler) Resolve(c *gin.Context) {
b.WriteString(content)
b.WriteString("\n\n")
}
if err := rows.Err(); err != nil {
log.Printf("ResolveInstructions rows.Err workspace=%s: %v", workspaceID, err)
}
c.JSON(http.StatusOK, gin.H{
"workspace_id": workspaceID,
@@ -261,7 +258,6 @@ func (h *InstructionsHandler) Resolve(c *gin.Context) {
func scanInstructions(rows interface {
Next() bool
Scan(dest ...interface{}) error
Err() error
}) []Instruction {
var instructions []Instruction
for rows.Next() {
@@ -273,9 +269,6 @@ func scanInstructions(rows interface {
}
instructions = append(instructions, inst)
}
if err := rows.Err(); err != nil {
log.Printf("scanInstructions rows.Err: %v", err)
}
if instructions == nil {
instructions = []Instruction{}
}
File diff suppressed because it is too large Load Diff
@@ -751,9 +751,9 @@ func TestMCPHandler_SendMessageToUser_DBErrorLogsAndStill200s(t *testing.T) {
t.Setenv("MOLECULE_MCP_ALLOW_SEND_MESSAGE", "true")
h, mock := newMCPHandler(t)
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-err").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
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'`).
@@ -802,9 +802,9 @@ func TestMCPHandler_SendMessageToUser_ResponseBodyShape(t *testing.T) {
const userMessage = "Hi there from the agent"
mock.ExpectQuery("SELECT name, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-shape").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
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'`).
@@ -861,9 +861,9 @@ func TestMCPHandler_SendMessageToUser_PersistsToActivityLog(t *testing.T) {
// 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, talk_to_user_enabled FROM workspaces").
mock.ExpectQuery("SELECT name FROM workspaces").
WithArgs("ws-msg").
WillReturnRows(sqlmock.NewRows([]string{"name", "talk_to_user_enabled"}).AddRow("CEO Ryan PC", true))
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'`
-56
View File
@@ -271,62 +271,6 @@ func (e EnvRequirement) IsSatisfied(configured map[string]struct{}) bool {
return false
}
// perWorkspaceUnsatisfied records a single unsatisfied RequiredEnv for a
// specific workspace during org import preflight.
type perWorkspaceUnsatisfied struct {
Workspace string
FilesDir string
Unsatisfied EnvRequirement
}
// collectPerWorkspaceUnsatisfied walks the workspace tree and returns every
// RequiredEnv that is neither in `configured` (global secrets) nor resolvable
// from the org root or workspace-level .env file. An empty orgBaseDir skips
// the .env walk so all requirements appear unsatisfied (used by tests to
// isolate the global-only path).
func collectPerWorkspaceUnsatisfied(
workspaces []OrgWorkspace,
orgBaseDir string,
configured map[string]struct{},
) []perWorkspaceUnsatisfied {
var result []perWorkspaceUnsatisfied
for _, ws := range workspaces {
result = append(result, checkWorkspaceRequiredEnv(ws, orgBaseDir, configured)...)
}
return result
}
func checkWorkspaceRequiredEnv(
ws OrgWorkspace,
orgBaseDir string,
configured map[string]struct{},
) []perWorkspaceUnsatisfied {
var result []perWorkspaceUnsatisfied
// Merge in .env vars from the org root and the workspace-specific dir.
// Workspace-level vars override org-root vars, just as loadWorkspaceEnv
// implements: org root first, then ws dir on top.
if orgBaseDir != "" {
wsEnv := loadWorkspaceEnv(orgBaseDir, ws.FilesDir)
for k, v := range wsEnv {
configured[k] = struct{}{}
_ = v // value only used for merging into configured map
}
}
for _, req := range ws.RequiredEnv {
if !req.IsSatisfied(configured) {
result = append(result, perWorkspaceUnsatisfied{
Workspace: ws.Name,
FilesDir: ws.FilesDir,
Unsatisfied: req,
})
}
}
for _, child := range ws.Children {
result = append(result, checkWorkspaceRequiredEnv(child, orgBaseDir, configured)...)
}
return result
}
// UnmarshalYAML accepts either a scalar (string → single) or a map
// with an `any_of` list (→ group).
func (e *EnvRequirement) UnmarshalYAML(value *yaml.Node) error {
@@ -15,6 +15,7 @@ import (
"gopkg.in/yaml.v3"
)
// resolvePromptRef reads a prompt body from either an inline string or a
// file ref relative to the workspace's files_dir. Inline always wins when
// both are non-empty (caller-provided inline is more authoritative than a
@@ -64,9 +65,7 @@ func resolvePromptRef(inline, fileRef, orgBaseDir, filesDir string) (string, err
// envVarRefPattern matches actual ${VAR} or $VAR references (not literal $).
// Used to detect unresolved placeholders without false positives like "$5".
// Requires [a-zA-Z_] as the first char after $ so $100 stays literal.
// Two capture groups: (1) ${VAR} form, (2) $VAR form.
var envVarRefPattern = regexp.MustCompile(`\$\{([a-zA-Z_][a-zA-Z0-9_]*)\}|\$([a-zA-Z_][a-zA-Z0-9_]*)`)
var envVarRefPattern = regexp.MustCompile(`\$\{?[A-Za-z_][A-Za-z0-9_]*\}?`)
// hasUnresolvedVarRef returns true if the original string had a ${VAR} or $VAR
// reference that the expanded string didn't fully replace (i.e. the var was unset).
@@ -133,25 +132,6 @@ func expandWithEnv(s string, env map[string]string) string {
return b.String()
}
// expandEnvRef resolves a single variable reference extracted from s.
//
// Guards:
// - Empty key → "$$" escape, return "$"
// - key[0] not POSIX ident start → "$" + partial chars, return "$<chars>"
// - Key in env map → return the mapped value (template override wins)
// - Otherwise → only fall back to os.Getenv if the whole input string IS the
// variable reference (ref == whole).
//
// Bare $VAR format:
// $HOME (alone) → ref==whole → os.Getenv ✓ (host HOME is org-template HOME)
// $HOME/path (partial) → ref!=whole → literal "$HOME" ✓ (CWE-78: prevents host leak)
//
// Braced ${VAR} format:
// ${HOME} (alone) → ref==whole → os.Getenv ✓
// ${ROLE}/admin (partial) → ref!=whole → literal ✓
// "yes and ${NOT_SET}" (embedded) → ref!=whole → literal ✓
//
// This is the CWE-78 fix from commit a3a358f9.
func expandEnvRef(key, ref, whole string, env map[string]string) string {
if key == "" {
return "$"
@@ -176,7 +156,7 @@ func isEnvIdentPart(c byte) bool {
return isEnvIdentStart(c) || (c >= '0' && c <= '9')
}
// loadWorkspaceEnv reads the org root .env and the workspace-specific .env .env and the workspace-specific .env
// loadWorkspaceEnv reads the org root .env and the workspace-specific .env
// (workspace overrides org root). Used by both secret injection and channel
// config expansion.
//
@@ -428,11 +408,7 @@ func resolveInsideRoot(root, userPath string) (string, error) {
return "", fmt.Errorf("root abs: %w", err)
}
joined := filepath.Join(absRoot, userPath)
// filepath.Join preserves "." components when root is absolute; clean
// them before computing the final absolute path so "./subdir/./file.txt"
// resolves to root/subdir/file.txt (not root/./subdir/./file.txt).
cleaned := filepath.Clean(joined)
absJoined, err := filepath.Abs(cleaned)
absJoined, err := filepath.Abs(joined)
if err != nil {
return "", fmt.Errorf("joined abs: %w", err)
}
@@ -104,8 +104,8 @@ func TestHasUnresolvedVarRef_Resolved(t *testing.T) {
// documents this design choice; callers who need empty=resolved should
// pre-process the output before calling hasUnresolvedVarRef.
{"${VAR}", "", true},
{"${VAR}", "value", false}, // var replaced
{"$VAR", "value", false}, // bare var replaced
{"${VAR}", "value", false}, // var replaced
{"$VAR", "value", false}, // bare var replaced
{"prefix${VAR}suffix", "prefixvaluesuffix", false},
{"${A}${B}", "ab", false},
// FOO=FOO and BAR=BAR — both vars found and replaced. Expanded output
@@ -125,14 +125,14 @@ func TestHasUnresolvedVarRef_Resolved(t *testing.T) {
func TestHasUnresolvedVarRef_Unresolved(t *testing.T) {
// Expansion left the refs intact → unresolved.
cases := []struct {
orig string
orig string
expanded string
}{
{"${VAR}", "${VAR}"}, // untouched
{"$VAR", "$VAR"}, // bare untouched
{"${VAR}", "${VAR}"}, // untouched
{"$VAR", "$VAR"}, // bare untouched
{"prefix${VAR}suffix", "prefix${VAR}suffix"},
{"${A}${B}", "${A}${B}"}, // both unresolved
{"${FOO}", ""}, // empty result with var ref in original
{"${A}${B}", "${A}${B}"}, // both unresolved
{"${FOO}", ""}, // empty result with var ref in original
}
for _, tc := range cases {
t.Run(tc.orig, func(t *testing.T) {
@@ -205,8 +205,8 @@ func TestMergeCategoryRouting_WorkspaceOverrides(t *testing.T) {
"ui": {"Frontend Engineer"},
}
ws := map[string][]string{
"security": {"SRE Team"}, // narrows
"ui": {}, // drops
"security": {"SRE Team"}, // narrows
"ui": {}, // drops
"infra": {"Platform Team"}, // adds
}
r := mergeCategoryRouting(defaults, ws)
@@ -462,11 +462,47 @@ func TestExpandWithEnv_LiteralDollar(t *testing.T) {
func TestExpandWithEnv_PartiallyPresent(t *testing.T) {
env := map[string]string{"SET": "yes"}
result := expandWithEnv("${SET} and ${NOT_SET}", env)
// ${SET} resolved from env; ${NOT_SET} stays literal (not whole-string ref,
// so os.Getenv fallback is NOT used — CWE-78 regression guard).
assert.Equal(t, "yes and ${NOT_SET}", result)
}
func TestExpandWithEnv_EmbeddedMissingProcessEnvStaysLiteral(t *testing.T) {
t.Setenv("MOL_TEST_EMBEDDED_MISSING", "")
result := expandWithEnv("prefix/${MOL_TEST_EMBEDDED_MISSING}/suffix", map[string]string{})
assert.Equal(t, "prefix/${MOL_TEST_EMBEDDED_MISSING}/suffix", result)
}
// POSIX identifier guard regression tests (CWE-78 fix).
// Keys not starting with [a-zA-Z_] must not be looked up in env or os.Getenv.
func TestExpandWithEnv_DigitPrefix_NotExpanded(t *testing.T) {
// ${0}, ${5}, ${1VAR} — numeric prefix → not a valid shell identifier.
// Guard must return "$0", "$5", "$1VAR" literally; no env lookup.
cases := []struct {
input string
want string
}{
{"${0}", "$0"},
{"${5}", "$5"},
{"${1VAR}", "$1VAR"},
{"prefix ${0} suffix", "prefix $0 suffix"},
{"$0", "$0"},
{"$5", "$5"},
{"HOME=${HOME}", "HOME=${HOME}"}, // HOME is valid but embedded in larger string
}
for _, tc := range cases {
t.Run(tc.input, func(t *testing.T) {
got := expandWithEnv(tc.input, map[string]string{})
assert.Equal(t, tc.want, got)
})
}
}
func TestExpandWithEnv_EmptyKey_ReturnsDollar(t *testing.T) {
// ${} → "$" (empty key, guard returns "$")
result := expandWithEnv("value=${}", map[string]string{})
assert.Equal(t, "value=$", result)
}
// mergeCategoryRouting tests — unions defaults with per-workspace routing.
// ── Additional coverage: mergeCategoryRouting ──────────────────────
@@ -546,8 +582,8 @@ func TestRenderCategoryRoutingYAML_SingleCategory(t *testing.T) {
func TestRenderCategoryRoutingYAML_MultipleCategoriesSorted(t *testing.T) {
routing := map[string][]string{
"zebra": {"RoleZ"},
"alpha": {"RoleA"},
"zebra": {"RoleZ"},
"alpha": {"RoleA"},
"middleware": {"RoleM"},
}
result, err := renderCategoryRoutingYAML(routing)
@@ -590,7 +626,7 @@ func TestRenderCategoryRoutingYAML_SpecialCharactersEscaped(t *testing.T) {
// ── Additional coverage: appendYAMLBlock ───────────────────────────
func TestAppendYAMLBlock_BothEmpty(t *testing.T) {
result := appendYAMLBlock(nil, "")
assert.Nil(t, result) // append(nil, []byte("")...) returns nil in Go
assert.Nil(t, result)
}
func TestAppendYAMLBlock_ExistingHasNewline(t *testing.T) {
@@ -276,121 +276,3 @@ func TestMergeCategoryRouting_OriginalMapsUnmodified(t *testing.T) {
t.Error("ws routing should be unmodified after merge")
}
}
// ── expandWithEnv ─────────────────────────────────────────────────────────────
//
// CWE-78 regression tests. The original fix (a3a358f9) ensures that partial
// variable references like $HOME/path are NOT resolved via os.Getenv — the
// host HOME env var must not leak into org template values. Only whole-string
// references ($VAR or ${VAR}) may fall back to the host process environment.
func TestExpandWithEnv_PartialRefDollarHomePath(t *testing.T) {
// $HOME/path must NOT resolve to the host's HOME env var.
// The literal $HOME must be returned as-is.
got := expandWithEnv("$HOME/path", nil)
if got != "$HOME/path" {
t.Errorf("$HOME/path: got %q, want literal $HOME/path", got)
}
}
func TestExpandWithEnv_PartialRefBracedRoleAdmin(t *testing.T) {
// ${ROLE}/admin — ROLE is not in env, so expand to the literal ${ROLE}/admin.
got := expandWithEnv("${ROLE}/admin", nil)
if got != "${ROLE}/admin" {
t.Errorf("${ROLE}/admin: got %q, want literal ${ROLE}/admin", got)
}
}
func TestExpandWithEnv_PartialRefMiddleOfString(t *testing.T) {
// $ROLE in the middle of a string — literal, not os.Getenv.
got := expandWithEnv("prefix/$ROLE/suffix", nil)
if got != "prefix/$ROLE/suffix" {
t.Errorf("prefix/$ROLE/suffix: got %q, want literal", got)
}
}
func TestExpandWithEnv_WholeVarInEnv(t *testing.T) {
// Whole-string $VAR that IS in env — env value wins.
env := map[string]string{"FOO": "barvalue"}
got := expandWithEnv("$FOO", env)
if got != "barvalue" {
t.Errorf("$FOO with FOO=barvalue: got %q, want barvalue", got)
}
}
func TestExpandWithEnv_WholeVarBracedInEnv(t *testing.T) {
// Whole-string ${VAR} that IS in env — env value wins.
env := map[string]string{"FOO": "barvalue"}
got := expandWithEnv("${FOO}", env)
if got != "barvalue" {
t.Errorf("${FOO} with FOO=barvalue: got %q, want barvalue", got)
}
}
func TestExpandWithEnv_WholeVarNotInEnvBare(t *testing.T) {
// Whole-string $VAR not in env — falls back to os.Getenv.
// If the host has the var, we get the host value. If not, empty.
// At minimum, the result must NOT be the literal "$UNDEFINED_VAR_9Z".
got := expandWithEnv("$UNDEFINED_VAR_9Z", nil)
if got == "$UNDEFINED_VAR_9Z" {
t.Errorf("$UNDEFINED_VAR_9Z: should expand (whole-string fallback to os.Getenv), got literal")
}
}
func TestExpandWithEnv_WholeVarNotInEnvBraced(t *testing.T) {
// Whole-string ${VAR} not in env — falls back to os.Getenv.
got := expandWithEnv("${UNDEFINED_VAR_9Z}", nil)
if got == "${UNDEFINED_VAR_9Z}" {
t.Errorf("${UNDEFINED_VAR_9Z}: should expand (whole-string fallback to os.Getenv), got literal")
}
}
func TestExpandWithEnv_EmptyString(t *testing.T) {
got := expandWithEnv("", map[string]string{"FOO": "bar"})
if got != "" {
t.Errorf("empty string: got %q, want empty", got)
}
}
func TestExpandWithEnv_NoVarRefs(t *testing.T) {
got := expandWithEnv("plain string with no vars", map[string]string{"FOO": "bar"})
if got != "plain string with no vars" {
t.Errorf("plain string: got %q, want unchanged", got)
}
}
func TestExpandWithEnv_MultipleVarRefs(t *testing.T) {
// Two vars, both whole — both expand from env.
env := map[string]string{"A": "alpha", "B": "beta"}
got := expandWithEnv("$A and $B and more", env)
if got != "alpha and beta and more" {
t.Errorf("multiple vars: got %q, want alpha and beta and more", got)
}
}
func TestExpandWithEnv_NumericVarRef(t *testing.T) {
// $5 — starts with digit, not a valid identifier start.
// Must return the literal "$5", not expand via os.Getenv.
got := expandWithEnv("$5", map[string]string{"5": "five"})
if got != "$5" {
t.Errorf("$5: got %q, want literal $5", got)
}
}
func TestExpandWithEnv_DollarEscape(t *testing.T) {
// $$ → both $ written literally (each $ is not followed by an identifier char,
// so it is written as-is). No special escape sequence for $$.
got := expandWithEnv("$$", nil)
if got != "$$" {
t.Errorf("$$: got %q, want literal $$", got)
}
}
func TestExpandWithEnv_MixedPartialAndWhole(t *testing.T) {
// $A is in env (whole), $HOME is partial — only $A expands.
env := map[string]string{"A": "alpha"}
got := expandWithEnv("$A at $HOME", env)
if got != "alpha at $HOME" {
t.Errorf("$A at $HOME: got %q, want alpha at $HOME", got)
}
}
@@ -952,6 +952,54 @@ type PerWorkspaceUnsatisfied struct {
// collectPerWorkspaceUnsatisfied recursively walks workspaces and returns
// per-workspace RequiredEnv entries that are not covered by (a) a global
// secret key or (b) a key present in the workspace's .env file(s) (org root
// .env + per-workspace <files_dir>/.env). This complements
// collectOrgEnv + loadConfiguredGlobalSecretKeys, which together only
// validate global-level RequiredEnv against global_secrets. The .env
// lookup mirrors the runtime resolution in createWorkspaceTree so that
// the preflight result matches what the container actually receives at
// start time.
func collectPerWorkspaceUnsatisfied(workspaces []OrgWorkspace, orgBaseDir string, globalSecrets map[string]struct{}) []PerWorkspaceUnsatisfied {
var out []PerWorkspaceUnsatisfied
var walk func([]OrgWorkspace)
walk = func(wsList []OrgWorkspace) {
for _, ws := range wsList {
// Build the set of keys available to this workspace from .env.
// This is the same three-source stack that createWorkspaceTree
// injects into the container:
// 1. Org root .env (parseEnvFile, no filesDir)
// 2. Workspace <files_dir>/.env (if filesDir is set)
// 3. Persona bootstrap env (MOLECULE_PERSONA_ROOT/<filesDir>/env)
// Items 1+2 are on-disk and testable; item 3 is host-only and
// skipped here (persona env does NOT satisfy required_env —
// it carries identity tokens, not workspace LLM keys).
envFromFiles := loadWorkspaceEnv(orgBaseDir, ws.FilesDir)
// Convert map[string]string (from .env files) to map[string]struct{}
// to match IsSatisfied's signature.
envSet := make(map[string]struct{}, len(envFromFiles))
for k := range envFromFiles {
envSet[k] = struct{}{}
}
for _, req := range ws.RequiredEnv {
if req.IsSatisfied(globalSecrets) {
continue // covered by a global secret
}
if req.IsSatisfied(envSet) {
continue // covered by a per-workspace .env file
}
out = append(out, PerWorkspaceUnsatisfied{
Workspace: ws.Name,
FilesDir: ws.FilesDir,
Unsatisfied: req,
})
}
walk(ws.Children)
}
}
walk(workspaces)
return out
}
func loadConfiguredGlobalSecretKeys(ctx context.Context) (map[string]struct{}, error) {
rows, err := db.DB.QueryContext(ctx,
`SELECT key FROM global_secrets WHERE octet_length(encrypted_value) > 0 LIMIT $1`,
@@ -17,9 +17,6 @@ import (
// when one exists, or the workspace's own ID when it is the org root.
// Returns an empty string if the workspace is not found.
func resolveOrgID(ctx context.Context, workspaceID string) (string, error) {
if db.DB == nil {
return "", nil // nil in unit tests
}
var parentID sql.NullString
err := db.DB.QueryRowContext(ctx,
`SELECT parent_id FROM workspaces WHERE id = $1`,
@@ -215,9 +215,6 @@ func TestTarWalk_EmptyDirectory(t *testing.T) {
}
}
// TestTarWalk_NestedDirs is defined in plugins_atomic_tar_test.go to avoid
// redeclaration. Deeply nested directory walk is tested there.
// TestTarWalk_DirEntryHasTrailingSlash: directory entries must end with '/'
// per tar format; tar.Header.Typeflag '5' (dir) must produce "name/" not "name".
func TestTarWalk_DirEntryHasTrailingSlash(t *testing.T) {
@@ -342,6 +342,11 @@ func TestPluginInstall_InstanceLookupError_Returns503(t *testing.T) {
// ---------- dispatch: uninstall ----------
func TestPluginUninstall_SaaS_DispatchesToEIC(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectExec("DELETE FROM workspace_plugins WHERE workspace_id").
WithArgs("ws-1", "browser-automation").
WillReturnResult(sqlmock.NewResult(0, 1))
stubReadPluginManifestViaEIC(t, func(ctx context.Context, instanceID, runtime, pluginName string) ([]byte, error) {
return []byte("name: browser-automation\nskills:\n - browse\n"), nil
})
@@ -629,6 +629,9 @@ func TestPluginInstall_RejectsUnknownScheme(t *testing.T) {
}
func TestPluginInstall_LocalSourceReachesContainerLookup(t *testing.T) {
mock := setupTestDB(t)
expectAllowlistAllowAll(mock)
base := t.TempDir()
pluginDir := filepath.Join(base, "demo")
_ = os.MkdirAll(pluginDir, 0o755)
@@ -955,14 +958,14 @@ func TestLogInstallLimitsOnce(t *testing.T) {
func TestRegexpEscapeForAwk(t *testing.T) {
cases := map[string]string{
"my-plugin": `my-plugin`,
"# Plugin: foo /": `# Plugin: foo \/`,
"# Plugin: a.b /": `# Plugin: a\.b \/`,
"foo[bar]": `foo\[bar\]`,
"a*b+c?": `a\*b\+c\?`,
"path|with|pipes": `path\|with\|pipes`,
`back\slash`: `back\\slash`,
"": ``,
"my-plugin": `my-plugin`,
"# Plugin: foo /": `# Plugin: foo \/`,
"# Plugin: a.b /": `# Plugin: a\.b \/`,
"foo[bar]": `foo\[bar\]`,
"a*b+c?": `a\*b\+c\?`,
"path|with|pipes": `path\|with\|pipes`,
`back\slash`: `back\\slash`,
"": ``,
}
for in, want := range cases {
got := regexpEscapeForAwk(in)
@@ -1247,7 +1250,7 @@ func TestPluginDownload_GithubSchemeStreamsTarball(t *testing.T) {
scheme: "github",
fetchFn: func(_ context.Context, _ string, dst string) (string, error) {
files := map[string]string{
"plugin.yaml": "name: remote-plugin\nversion: 1.0.0\n",
"plugin.yaml": "name: remote-plugin\nversion: 1.0.0\n",
"skills/x/SKILL.md": "---\nname: x\n---\n",
"adapters/claude_code.py": "from plugins_registry.builtins import AgentskillsAdaptor as Adaptor\n",
}
@@ -86,9 +86,6 @@ func recordWorkspacePluginInstall(
// pair. Called by the uninstall path so the row doesn't persist with a stale
// installed_sha after the plugin has been removed from the container.
func deleteWorkspacePluginRow(ctx context.Context, workspaceID, pluginName string) error {
if db.DB == nil {
return nil // nil in unit tests; no-op since the row is test-only
}
_, err := db.DB.ExecContext(ctx, `
DELETE FROM workspace_plugins WHERE workspace_id = $1 AND plugin_name = $2
`, workspaceID, pluginName)
+3 -31
View File
@@ -327,33 +327,7 @@ func (h *RegistryHandler) Register(c *gin.Context) {
}
}
// Reconcile the runtime-supplied card's identity fields against the
// trusted workspaces row before storing. The runtime builds its card
// from config.name, which the CP-regenerated /configs/config.yaml
// sets to the workspace UUID — so without this the stored card
// served at /.well-known/agent-card.json and returned to peers via
// agent_card_url has name = UUID, description = "", role = null even
// though the operator-controlled workspaces.name holds the friendly
// name the canvas shows. We only FILL gaps from the DB (never
// downgrade a card that already carries a real name); identity stays
// platform-controlled — the agent cannot self-set these. Best-effort:
// a lookup failure leaves the card exactly as the runtime sent it
// (no-worse-than-before). See agent_card_reconcile.go.
reconciledCard := payload.AgentCard
{
var dbName, dbRole sql.NullString
if qErr := db.DB.QueryRowContext(ctx,
`SELECT name, role FROM workspaces WHERE id = $1`, payload.ID,
).Scan(&dbName, &dbRole); qErr == nil {
if rc, did := reconcileAgentCardIdentity(
payload.AgentCard, payload.ID, dbName.String, dbRole.String,
); did {
reconciledCard = rc
log.Printf("Registry register: reconciled agent_card identity for %s from workspaces row", payload.ID)
}
}
}
agentCardStr := string(reconciledCard)
agentCardStr := string(payload.AgentCard)
// urlForUpsert: poll-mode workspaces don't need a URL. Empty input
// becomes NULL via sql.NullString so the row's URL stays clean (the
@@ -439,12 +413,10 @@ func (h *RegistryHandler) Register(c *gin.Context) {
}
}
// Broadcast WORKSPACE_ONLINE — use the reconciled card so the canvas
// Agent Card view live-updates with the friendly name, matching what
// was just persisted (not the runtime's raw UUID-name card).
// Broadcast WORKSPACE_ONLINE
if err := h.broadcaster.RecordAndBroadcast(ctx, string(events.EventWorkspaceOnline), payload.ID, map[string]interface{}{
"url": cachedURL,
"agent_card": reconciledCard,
"agent_card": payload.AgentCard,
"delivery_mode": effectiveMode,
}); err != nil {
log.Printf("Registry broadcast error: %v", err)
@@ -56,10 +56,8 @@ const (
// (an externally routable address) is used directly.
func (h *WorkspaceHandler) gracefulPreRestart(ctx context.Context, workspaceID string) {
// Non-blocking send — don't stall the restart cycle.
// Run in a tracked async goroutine (goAsync, not bare `go`) so the
// caller (runRestartCycle) can proceed to stopForRestart without
// waiting, while the test harness can still drain it before swapping
// the global db.DB (resolveAgentURLForRestartSignal reads db.DB).
// Run in a detached goroutine so the caller (runRestartCycle) can
// proceed to stopForRestart without waiting.
h.goAsync(func() {
signalCtx, cancel := context.WithTimeout(context.Background(), restartSignalTimeout)
defer cancel()
@@ -271,6 +271,7 @@ func TestGracefulPreRestart_URLResolutionError(t *testing.T) {
WorkspaceHandler: newHandlerWithTestDeps(t),
errToReturn: context.DeadlineExceeded,
}
waitForHandlerAsyncBeforeDBCleanup(t, hWrapper.WorkspaceHandler)
hWrapper.gracefulPreRestart(context.Background(), "ws-url-err-111")
time.Sleep(200 * time.Millisecond)
@@ -6,11 +6,12 @@ import (
"encoding/json"
"net/http"
"net/http/httptest"
"regexp"
"strings"
"testing"
"time"
"github.com/DATA-DOG/go-sqlmock"
sqlmock "github.com/DATA-DOG/go-sqlmock"
"github.com/gin-gonic/gin"
)
@@ -170,18 +171,29 @@ func TestScheduleHandler_Create_InvalidCron(t *testing.T) {
}
func TestScheduleHandler_Create_CRLFStripped(t *testing.T) {
// Use setupTestDBForQueueTests which sets up QueryMatcherEqual for exact
// string matching. The INSERT statement is deterministic enough for that.
customSqlmock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
// Prompt with CRLF from a Windows-committed org-template file.
// The handler strips \r before inserting so agent doesn't see empty responses.
promptWithCRLF := "check\r\ndocs\r\nbefore merge"
// The handler strips \r → query should receive the LF-only version.
customSqlmock.ExpectQuery("INSERT INTO workspace_schedules (workspace_id, name, cron_expr, timezone, prompt, enabled, next_run_at, source) VALUES ($1, $2, $3, $4, $5, $6, $7, 'runtime') RETURNING id").
// Use a custom matcher that captures the prompt argument so we can assert
// it has no \r characters.
matcher := sqlmock.NewArgMatcher(func(a interface{}) bool {
if s, ok := a.(string); ok {
// This will be called for multiple args; capture the prompt (5th arg).
return strings.Contains(s, "check\ndocs\nbefore merge")
}
return true
})
customMock, _, _ := sqlmock.New(sqlmock.QueryMatcherOption(matcher))
t.Cleanup(func() { customMock.Close() })
prevDB := db.DB
db.DB = customMock
t.Cleanup(func() { db.DB = prevDB })
customMock.ExpectQuery("INSERT INTO workspace_schedules").
WithArgs("ws-crlf", "", "0 9 * * *", "UTC", "check\ndocs\nbefore merge", true, sqlmock.AnyArg()).
WillReturnRows(sqlmock.NewRows([]string{"id"}).AddRow("sched-crlf"))
@@ -201,9 +213,6 @@ func TestScheduleHandler_Create_CRLFStripped(t *testing.T) {
if w.Code != http.StatusCreated {
t.Errorf("expected 201, got %d: %s", w.Code, w.Body.String())
}
if err := customSqlmock.ExpectationsWereMet(); err != nil {
t.Errorf("sqlmock expectations not met: %v", err)
}
}
func TestScheduleHandler_Create_DefaultEnabled(t *testing.T) {
@@ -367,16 +376,16 @@ func TestScheduleHandler_Create_NextRunAtReturned(t *testing.T) {
// ==================== Update ====================
func TestScheduleHandler_Update_PartialRecomputeCron(t *testing.T) {
// Uses QueryMatcherEqual so query strings are compared verbatim — no escaping needed.
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectQuery("SELECT cron_expr, timezone FROM workspace_schedules WHERE id = $1 AND workspace_id = $2").
// Changing cron_expr → handler SELECTs current cron+tz, recomputes next_run_at.
mock.ExpectQuery(`SELECT cron_expr, timezone FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`).
WithArgs("sched-recompute-cron", "ws-1").
WillReturnRows(sqlmock.NewRows([]string{"cron_expr", "timezone"}).
AddRow("0 8 * * *", "UTC"))
mock.ExpectExec(`UPDATE workspace_schedules SET name = COALESCE($2, name), cron_expr = COALESCE($3, cron_expr), timezone = COALESCE($4, timezone), prompt = COALESCE($5, prompt), enabled = COALESCE($6, enabled), next_run_at = COALESCE($7, next_run_at), updated_at = now() WHERE id = $1 AND workspace_id = $8`).
mock.ExpectExec(regexp.MustCompile(`UPDATE workspace_schedules SET[\s\S]+WHERE id = \$1 AND workspace_id = \$8`)).
WithArgs("sched-recompute-cron", nil, "0 6 * * *", nil, nil, nil, sqlmock.AnyArg(), "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
@@ -399,15 +408,15 @@ func TestScheduleHandler_Update_PartialRecomputeCron(t *testing.T) {
}
func TestScheduleHandler_Update_PartialRecomputeTimezone(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectQuery("SELECT cron_expr, timezone FROM workspace_schedules WHERE id = $1 AND workspace_id = $2").
mock.ExpectQuery(`SELECT cron_expr, timezone FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`).
WithArgs("sched-recompute-tz", "ws-1").
WillReturnRows(sqlmock.NewRows([]string{"cron_expr", "timezone"}).
AddRow("0 9 * * *", "UTC"))
mock.ExpectExec(`UPDATE workspace_schedules SET name = COALESCE($2, name), cron_expr = COALESCE($3, cron_expr), timezone = COALESCE($4, timezone), prompt = COALESCE($5, prompt), enabled = COALESCE($6, enabled), next_run_at = COALESCE($7, next_run_at), updated_at = now() WHERE id = $1 AND workspace_id = $8`).
mock.ExpectExec(regexp.MustCompile(`UPDATE workspace_schedules SET[\s\S]+WHERE id = \$1 AND workspace_id = \$8`)).
WithArgs("sched-recompute-tz", nil, nil, "America/New_York", nil, nil, sqlmock.AnyArg(), "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
@@ -430,10 +439,10 @@ func TestScheduleHandler_Update_PartialRecomputeTimezone(t *testing.T) {
}
func TestScheduleHandler_Update_InvalidTimezone(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectQuery("SELECT cron_expr, timezone FROM workspace_schedules WHERE id = $1 AND workspace_id = $2").
mock.ExpectQuery(`SELECT cron_expr, timezone FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`).
WithArgs("sched-bad-tz", "ws-1").
WillReturnRows(sqlmock.NewRows([]string{"cron_expr", "timezone"}).
AddRow("0 9 * * *", "UTC"))
@@ -462,10 +471,10 @@ func TestScheduleHandler_Update_InvalidTimezone(t *testing.T) {
}
func TestScheduleHandler_Update_InvalidCron(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectQuery("SELECT cron_expr, timezone FROM workspace_schedules WHERE id = $1 AND workspace_id = $2").
mock.ExpectQuery(`SELECT cron_expr, timezone FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`).
WithArgs("sched-bad-cron", "ws-1").
WillReturnRows(sqlmock.NewRows([]string{"cron_expr", "timezone"}).
AddRow("0 9 * * *", "UTC"))
@@ -489,11 +498,11 @@ func TestScheduleHandler_Update_InvalidCron(t *testing.T) {
}
func TestScheduleHandler_Update_NotFound(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectExec(`UPDATE workspace_schedules SET name = COALESCE($2, name), cron_expr = COALESCE($3, cron_expr), timezone = COALESCE($4, timezone), prompt = COALESCE($5, prompt), enabled = COALESCE($6, enabled), next_run_at = COALESCE($7, next_run_at), updated_at = now() WHERE id = $1 AND workspace_id = $8`).
WithArgs("sched-missing", "renamed", nil, nil, nil, nil, nil, "ws-1").
mock.ExpectExec(regexp.MustCompile(`UPDATE workspace_schedules SET[\s\S]+WHERE id = \$1 AND workspace_id = \$8`)).
WithArgs("sched-missing", nil, nil, nil, nil, nil, nil, "ws-1").
WillReturnResult(sqlmock.NewResult(0, 0)) // no rows affected
body, _ := json.Marshal(map[string]string{"name": "renamed"})
@@ -515,11 +524,11 @@ func TestScheduleHandler_Update_NotFound(t *testing.T) {
}
func TestScheduleHandler_Update_DBError(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectExec(`UPDATE workspace_schedules SET name = COALESCE($2, name), cron_expr = COALESCE($3, cron_expr), timezone = COALESCE($4, timezone), prompt = COALESCE($5, prompt), enabled = COALESCE($6, enabled), next_run_at = COALESCE($7, next_run_at), updated_at = now() WHERE id = $1 AND workspace_id = $8`).
WithArgs("sched-update-err", "updated", nil, nil, nil, nil, nil, "ws-1").
mock.ExpectExec(regexp.MustCompile(`UPDATE workspace_schedules SET[\s\S]+WHERE id = \$1 AND workspace_id = \$8`)).
WithArgs("sched-update-err", nil, nil, nil, nil, nil, nil, "ws-1").
WillReturnError(sql.ErrConnDone)
body, _ := json.Marshal(map[string]string{"name": "updated"})
@@ -541,12 +550,12 @@ func TestScheduleHandler_Update_DBError(t *testing.T) {
}
func TestScheduleHandler_Update_PromptCRLFStripped(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
// Changing prompt with CRLF → handler strips \r before the UPDATE.
mock.ExpectExec(`UPDATE workspace_schedules SET name = COALESCE($2, name), cron_expr = COALESCE($3, cron_expr), timezone = COALESCE($4, timezone), prompt = COALESCE($5, prompt), enabled = COALESCE($6, enabled), next_run_at = COALESCE($7, next_run_at), updated_at = now() WHERE id = $1 AND workspace_id = $8`).
WithArgs("sched-crlf-upd", nil, nil, nil, "fix\nthat", nil, nil, "ws-1").
mock.ExpectExec(regexp.MustCompile(`UPDATE workspace_schedules SET[\s\S]+WHERE id = \$1 AND workspace_id = \$8`)).
WithArgs("sched-crlf-upd", nil, nil, nil, "fix\r\nthat", nil, nil, "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
body, _ := json.Marshal(map[string]string{"prompt": "fix\r\nthat"})
@@ -570,10 +579,10 @@ func TestScheduleHandler_Update_PromptCRLFStripped(t *testing.T) {
// ==================== Delete ====================
func TestScheduleHandler_Delete_Success(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectExec(`DELETE FROM workspace_schedules WHERE id = $1 AND workspace_id = $2`).
mock.ExpectExec(regexp.MustCompile(`DELETE FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`)).
WithArgs("sched-del", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
@@ -593,11 +602,11 @@ func TestScheduleHandler_Delete_Success(t *testing.T) {
}
func TestScheduleHandler_Delete_NotFound(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
// IDOR guard: row belongs to different workspace → 0 rows affected → 404.
mock.ExpectExec(`DELETE FROM workspace_schedules WHERE id = $1 AND workspace_id = $2`).
mock.ExpectExec(regexp.MustCompile(`DELETE FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`)).
WithArgs("sched-idor", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 0))
@@ -617,10 +626,10 @@ func TestScheduleHandler_Delete_NotFound(t *testing.T) {
}
func TestScheduleHandler_Delete_DBError(t *testing.T) {
mock := setupTestDBForQueueTests(t)
mock := setupTestDB(t)
handler := NewScheduleHandler()
mock.ExpectExec(`DELETE FROM workspace_schedules WHERE id = $1 AND workspace_id = $2`).
mock.ExpectExec(regexp.MustCompile(`DELETE FROM workspace_schedules WHERE id = \$1 AND workspace_id = \$2`)).
WithArgs("sched-del-err", "ws-1").
WillReturnError(sql.ErrConnDone)
@@ -64,7 +64,7 @@ func (h *SecretsHandler) List(c *gin.Context) {
})
}
if err := rows.Err(); err != nil {
log.Printf("List workspace secrets iteration error: %v", err)
log.Printf("List secrets rows.Err: %v", err)
}
// 2. Global secrets not overridden at workspace level
@@ -95,7 +95,7 @@ func (h *SecretsHandler) List(c *gin.Context) {
})
}
if err := globalRows.Err(); err != nil {
log.Printf("List global secrets iteration error: %v", err)
log.Printf("List secrets (global) rows.Err: %v", err)
}
c.JSON(http.StatusOK, secrets)
@@ -181,7 +181,7 @@ func (h *SecretsHandler) Values(c *gin.Context) {
}
}
if err := globalRows.Err(); err != nil {
log.Printf("secrets.Values: global rows iteration error: %v", err)
log.Printf("secrets.Values globalRows.Err: %v", err)
}
}
@@ -205,7 +205,7 @@ func (h *SecretsHandler) Values(c *gin.Context) {
}
}
if err := wsRows.Err(); err != nil {
log.Printf("secrets.Values: workspace rows iteration error: %v", err)
log.Printf("secrets.Values wsRows.Err: %v", err)
}
}
@@ -337,7 +337,7 @@ func (h *SecretsHandler) ListGlobal(c *gin.Context) {
})
}
if err := rows.Err(); err != nil {
log.Printf("ListGlobal iteration error: %v", err)
log.Printf("ListGlobal rows.Err: %v", err)
}
c.JSON(http.StatusOK, secrets)
}
@@ -416,7 +416,7 @@ func (h *SecretsHandler) restartAllAffectedByGlobalKey(key string) {
}
}
if err := rows.Err(); err != nil {
log.Printf("restartAllAffectedByGlobalKey: iteration error: %v", err)
log.Printf("restartAllAffectedByGlobalKey rows.Err: %v", err)
}
if len(ids) == 0 {
return
@@ -1,117 +0,0 @@
package handlers
// template_files_agent_home_stub_test.go — pins the Phase-1 stub
// contract for the /agent-home root added by internal#425 RFC.
//
// Today (pre-Phase-2b), every Files API verb against `?root=/agent-home`
// must return HTTP 501 with the canonical pending-message body. The
// stub MUST NOT:
// 1. Hit the DB (the workspace might not even exist yet from the
// canvas's POV — the root selector is testable without one).
// 2. Touch the EIC tunnel / Docker / template-dir paths — those
// would 500/404/[] depending on the env and confuse the canvas.
// 3. Accept writes/deletes that the future docker-exec backend
// would reject — fail closed.
//
// When Phase 2b lands, this file gets replaced by a real
// docker-exec dispatch test; the stub-message constant in
// templates.go disappears.
import (
"net/http"
"net/http/httptest"
"strings"
"testing"
"github.com/gin-gonic/gin"
)
// TestAgentHomeAllowedRoot pins that /agent-home is in the allowedRoots
// set. Without this, a future refactor that drops the key would
// silently degrade the canvas root selector to a 400 instead of the
// stub 501.
func TestAgentHomeAllowedRoot(t *testing.T) {
if !allowedRoots["/agent-home"] {
t.Fatal("/agent-home must be in allowedRoots — RFC #425 contract")
}
}
// TestAgentHomeStub_AllVerbs_Return501 pins the canonical stub
// response across all four verbs. Each must:
//
// - status 501
// - body contains the canonical "/agent-home not implemented" prefix
// - NOT contain "workspace not found" (proves we short-circuit before
// the DB lookup)
//
// Driven as a table to keep symmetry — adding a fifth verb in the
// future means adding one row here.
func TestAgentHomeStub_AllVerbs_Return501(t *testing.T) {
cases := []struct {
name string
method string
invoke func(c *gin.Context)
}{
{
name: "ListFiles",
method: "GET",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).ListFiles(c) },
},
{
name: "ReadFile",
method: "GET",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).ReadFile(c) },
},
{
name: "WriteFile",
method: "PUT",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).WriteFile(c) },
},
{
name: "DeleteFile",
method: "DELETE",
invoke: func(c *gin.Context) { (&TemplatesHandler{}).DeleteFile(c) },
},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{
{Key: "id", Value: "ws-stub"},
// Path param without leading slash so DeleteFile's
// filepath.IsAbs guard doesn't 400 before the root
// dispatch runs. The List/Read/Write paths strip the
// leading slash themselves and accept either form.
{Key: "path", Value: "notes.md"},
}
// WriteFile binds JSON; provide a minimal valid body so the
// short-circuit isn't masked by the bind-error path.
var body string
if tc.method == "PUT" {
body = `{"content":"x"}`
}
c.Request = httptest.NewRequest(
tc.method,
"/workspaces/ws-stub/files/notes.md?root=/agent-home",
strings.NewReader(body),
)
if body != "" {
c.Request.Header.Set("Content-Type", "application/json")
}
tc.invoke(c)
if w.Code != http.StatusNotImplemented {
t.Fatalf("expected 501, got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "/agent-home not implemented") {
t.Errorf("body should contain canonical stub message; got %s", w.Body.String())
}
if strings.Contains(w.Body.String(), "workspace not found") {
t.Errorf("stub leaked through to DB lookup; body=%s", w.Body.String())
}
})
}
}
@@ -19,7 +19,6 @@ package handlers
import (
"bytes"
"context"
"errors"
"fmt"
"log"
"os"
@@ -358,28 +357,6 @@ func writeFileViaEIC(ctx context.Context, instanceID, runtime, root, relPath str
var stderr bytes.Buffer
sshCmd.Stderr = &stderr
if err := sshCmd.Run(); err != nil {
// When the per-op context deadline (eicFileOpTimeout) fires,
// exec.CommandContext SIGKILLs the ssh subprocess and Run()
// returns the bare "signal: killed" with empty stderr. That
// surfaced to the canvas as an opaque
// `500 {"error":"ssh install: signal: killed ()"}` which gave
// the operator no idea the workspace was simply mid-provision
// with a slow/unready EIC tunnel (internal#423). Detect the
// deadline explicitly and return an actionable message instead
// — the EIC mechanism, timeout value, and success path are all
// unchanged; this only improves the error a stuck write emits.
if cerr := ctx.Err(); cerr != nil {
reason := "timed out after " + eicFileOpTimeout.String()
if errors.Is(cerr, context.Canceled) && !errors.Is(cerr, context.DeadlineExceeded) {
reason = "was cancelled"
}
return fmt.Errorf(
"ssh install: EIC tunnel to workspace %s — "+
"the workspace may still be provisioning (slow/unready SSH); "+
"retry once it is online, or apply provider credentials via "+
"Settings → Secrets (encrypted, does not use this file-write path)",
reason)
}
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",
@@ -1,71 +0,0 @@
package handlers
// template_files_eic_write_timeout_test.go — pins the actionable-error
// behavior added for internal#423.
//
// When the per-op context deadline (eicFileOpTimeout) fires,
// exec.CommandContext SIGKILLs the ssh subprocess and Run() returns the
// bare "signal: killed" with empty stderr. Before the fix that surfaced
// to the canvas as an opaque `500 {"error":"ssh install: signal:
// killed ()"}` — useless to an operator whose workspace was simply
// mid-provision with a slow/unready EIC tunnel. The fix detects the
// deadline explicitly (errors.Is(ctx.Err(), context.DeadlineExceeded))
// and returns a message that names the cause and the
// Settings → Secrets workaround.
import (
"context"
"strings"
"testing"
"time"
)
// TestWriteFileViaEIC_DeadlineExceeded_ActionableError stubs
// withEICTunnel so the *real* inner closure runs against a context that
// has already exceeded its deadline. The ssh subprocess fails (no real
// sshd on the fake port) and ctx.Err() == DeadlineExceeded, so the new
// branch must fire and produce an actionable message — NOT the opaque
// "signal: killed ()" string the canvas used to show.
func TestWriteFileViaEIC_DeadlineExceeded_ActionableError(t *testing.T) {
prev := withEICTunnel
withEICTunnel = func(_ context.Context, instanceID string, fn func(s eicSSHSession) error) error {
// Run the real inner closure. It closes over the ctx that
// writeFileViaEIC derived from our already-cancelled parent, so
// the ssh subprocess is killed immediately and ctx.Err()
// resolves — exactly the eicFileOpTimeout-expiry shape.
return fn(eicSSHSession{
instanceID: instanceID,
osUser: "ubuntu",
localPort: 1, // nothing listening → ssh fails fast
keyPath: "/nonexistent/key",
})
}
t.Cleanup(func() { withEICTunnel = prev })
// Drive the real writeFileViaEIC. Pass a parent whose deadline has
// already passed: the context.WithTimeout(ctx, eicFileOpTimeout)
// derived inside writeFileViaEIC inherits the expired parent
// deadline, so ctx.Err() == context.DeadlineExceeded by the time
// the killed ssh subprocess returns — the exact production shape
// (eicFileOpTimeout expiry), exercised deterministically.
parent, cancel := context.WithDeadline(context.Background(), time.Now().Add(-time.Second))
defer cancel()
err := writeFileViaEIC(parent, "i-test", "claude-code", "/configs", "config.yaml", []byte("model: sonnet\n"))
if err == nil {
t.Fatalf("expected an error from a killed ssh subprocess, got nil")
}
msg := err.Error()
// Must NOT leak the opaque bare-signal string to the operator.
if strings.Contains(msg, "signal: killed ()") {
t.Fatalf("error still surfaces the opaque %q form: %q", "signal: killed ()", msg)
}
// Must name the cause and the Secrets workaround so the canvas
// shows something actionable.
for _, want := range []string{"timed out", "provisioning", "Settings", "Secrets"} {
if !strings.Contains(msg, want) {
t.Errorf("actionable error missing %q; got: %q", want, msg)
}
}
}
@@ -18,35 +18,11 @@ import (
)
// allowedRoots are the container paths that the Files API can browse.
//
// `/agent-home` (added 2026-05-15, internal#425 RFC) is the container's
// own $HOME — `/root` for openclaw, `/home/agent` for claude-code/hermes
// — browsed via `docker exec` rather than host-side `find`. The
// dispatch is stubbed today (returns 501); full implementation lands in
// Phase 2b of the RFC. The allowedRoots key is added now so the canvas
// can design its root-selector UI against the final shape and the
// stub-vs-full transition is server-side only.
var allowedRoots = map[string]bool{
"/configs": true,
"/workspace": true,
"/home": true,
"/plugins": true,
"/agent-home": true,
}
// agentHomeStubMessage is the body returned by every Files API verb
// when `?root=/agent-home` is requested before Phase 2b lands. Keep the
// status code 501 (Not Implemented) — the route exists, the verb is
// understood, but the handler is unimplemented. Distinguishes from
// 400/404 so a canvas behind a less-current server can render a clean
// "feature pending" state instead of a generic error.
const agentHomeStubMessage = "/agent-home not implemented yet (internal#425 RFC Phase 2b — docker-exec backend pending)"
// isAgentHomeStubRequest returns true when the request targets the
// stubbed /agent-home root. Centralised so every verb in this file
// short-circuits with the same response shape.
func isAgentHomeStubRequest(rootPath string) bool {
return rootPath == "/agent-home"
"/configs": true,
"/workspace": true,
"/home": true,
"/plugins": true,
}
// maxUploadFiles limits the number of files in a single import/replace.
@@ -243,14 +219,7 @@ func (h *TemplatesHandler) ListFiles(c *gin.Context) {
// ?depth= — max depth to recurse (default: 1, max: 5)
rootPath := c.DefaultQuery("root", "/configs")
if !allowedRoots[rootPath] {
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins, /agent-home"})
return
}
// /agent-home dispatch is stubbed pre-Phase-2b. Short-circuit before
// the DB lookup + EIC dance so a canvas exercising the new root key
// gets a clean 501 instead of a half-effort response.
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
subPath := c.DefaultQuery("path", "")
@@ -414,11 +383,7 @@ func (h *TemplatesHandler) ReadFile(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, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
@@ -531,11 +496,7 @@ 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, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
@@ -612,11 +573,7 @@ func (h *TemplatesHandler) DeleteFile(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, /agent-home"})
return
}
if isAgentHomeStubRequest(rootPath) {
c.JSON(http.StatusNotImplemented, gin.H{"error": agentHomeStubMessage})
c.JSON(http.StatusBadRequest, gin.H{"error": "root must be one of: /configs, /workspace, /home, /plugins"})
return
}
var wsName, instanceID, runtime string
@@ -109,11 +109,9 @@ func (h *TerminalHandler) HandleConnect(c *gin.Context) {
// provisionWorkspaceCP → migration 038). Null instance_id means the
// workspace runs as a local Docker container on this tenant.
var instanceID string
if db.DB != nil {
db.DB.QueryRowContext(ctx,
`SELECT COALESCE(instance_id, '') FROM workspaces WHERE id = $1`,
workspaceID).Scan(&instanceID)
}
db.DB.QueryRowContext(ctx,
`SELECT COALESCE(instance_id, '') FROM workspaces WHERE id = $1`,
workspaceID).Scan(&instanceID)
if instanceID != "" {
h.handleRemoteConnect(c, workspaceID, instanceID)
@@ -145,7 +143,7 @@ func (h *TerminalHandler) handleLocalConnect(c *gin.Context, workspaceID string)
// Look up workspace name for manual container naming
var wsName string
if db.DB != nil && h.docker != nil {
if _, err := h.docker.Ping(ctx); err == nil {
db.DB.QueryRowContext(ctx, `SELECT LOWER(REPLACE(name, ' ', '-')) FROM workspaces WHERE id = $1`, workspaceID).Scan(&wsName)
if wsName != "" {
candidates = append(candidates, wsName)
@@ -340,6 +340,11 @@ func TestSSHCommandCmd_BuildsArgv(t *testing.T) {
// a workspace must still be able to access its own terminal. The CanCommunicate
// fast-path returns true when callerID == targetID.
func TestTerminalConnect_KI005_AllowsOwnTerminal(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectQuery("SELECT COALESCE").
WithArgs("ws-alice").
WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
// CanCommunicate fast-path: callerID == targetID → returns true without DB.
prev := canCommunicateCheck
canCommunicateCheck = func(callerID, targetID string) bool { return callerID == targetID }
@@ -367,6 +372,11 @@ func TestTerminalConnect_KI005_AllowsOwnTerminal(t *testing.T) {
// skip the CanCommunicate check entirely and fall through to the Docker auth path.
// We assert they get the nil-docker 503 instead of 403.
func TestTerminalConnect_KI005_SkipsCheckWithoutHeader(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectQuery("SELECT COALESCE").
WithArgs("ws-any").
WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
h := NewTerminalHandler(nil) // nil docker → 503 if reached
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
@@ -439,6 +449,9 @@ func TestTerminalConnect_KI005_AllowsSiblingWorkspace(t *testing.T) {
mock.ExpectExec(`UPDATE workspace_auth_tokens SET last_used_at`).
WithArgs(sqlmock.AnyArg()).
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT COALESCE").
WithArgs("ws-dev").
WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
h := NewTerminalHandler(nil)
w := httptest.NewRecorder()
@@ -463,7 +476,10 @@ func TestTerminalConnect_KI005_AllowsSiblingWorkspace(t *testing.T) {
// introduced in GH#1885: internal routing uses org tokens which are not in
// workspace_auth_tokens, so ValidateToken would always fail for them.
func TestKI005_OrgToken_SkipsValidateToken(t *testing.T) {
setupTestDB(t) // no ValidateToken ExpectQuery — none should fire
mock := setupTestDB(t) // no ValidateToken ExpectQuery — none should fire
mock.ExpectQuery("SELECT COALESCE").
WithArgs("ws-target").
WillReturnRows(sqlmock.NewRows([]string{"instance_id"}).AddRow(""))
prev := canCommunicateCheck
canCommunicateCheck = func(callerID, targetID string) bool {
// Simulate platform agent → target workspace (same org).
@@ -544,4 +560,3 @@ func TestSSHCommandCmd_ConnectTimeoutPresent(t *testing.T) {
args)
}
}
@@ -10,20 +10,8 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
// validWorkspaceID returns true when id is a syntactically valid UUID.
// workspace_id is a `uuid` column; passing a non-UUID (e.g. the canvas
// "global" sentinel sent when no node is selected) makes Postgres raise
// `invalid input syntax for type uuid`, which previously leaked as an
// opaque 500. Reject up front with a clean 400 instead. Mirrors the
// uuid.Parse guard already used in handlers/activity.go.
func validWorkspaceID(id string) bool {
_, err := uuid.Parse(id)
return err == nil
}
// TokenHandler exposes user-facing token management for workspaces.
// Routes: GET/POST/DELETE /workspaces/:id/tokens (behind WorkspaceAuth).
type TokenHandler struct{}
@@ -43,10 +31,6 @@ type tokenListItem struct {
// never the plaintext or hash).
func (h *TokenHandler) List(c *gin.Context) {
workspaceID := c.Param("id")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
limit := 50
if v := c.Query("limit"); v != "" {
@@ -69,7 +53,6 @@ func (h *TokenHandler) List(c *gin.Context) {
LIMIT $2 OFFSET $3
`, workspaceID, limit, offset)
if err != nil {
log.Printf("tokens: list query failed for workspace %s: %v", workspaceID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "failed to list tokens"})
return
}
@@ -84,9 +67,6 @@ func (h *TokenHandler) List(c *gin.Context) {
}
tokens = append(tokens, t)
}
if err := rows.Err(); err != nil {
log.Printf("ListTokens rows.Err workspace=%s: %v", workspaceID, err)
}
c.JSON(http.StatusOK, gin.H{
"tokens": tokens,
@@ -102,10 +82,6 @@ const maxTokensPerWorkspace = 50
// exactly once in the response — it cannot be recovered afterwards.
func (h *TokenHandler) Create(c *gin.Context) {
workspaceID := c.Param("id")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
// Rate limit: max active tokens per workspace
var count int
@@ -138,10 +114,6 @@ func (h *TokenHandler) Create(c *gin.Context) {
func (h *TokenHandler) Revoke(c *gin.Context) {
workspaceID := c.Param("id")
tokenID := c.Param("tokenId")
if !validWorkspaceID(workspaceID) {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace id"})
return
}
result, err := db.DB.ExecContext(c.Request.Context(), `
UPDATE workspace_auth_tokens
@@ -41,15 +41,6 @@ import (
func init() { gin.SetMode(gin.TestMode) }
// Workspace IDs are validated as UUIDs up front (tokens.go validWorkspaceID),
// so handler tests must pass syntactically valid UUIDs. Fixed values keep
// sqlmock WithArgs assertions deterministic.
const (
wsUUID1 = "11111111-1111-1111-1111-111111111111"
wsUUID2 = "22222222-2222-2222-2222-222222222222"
wsUUID3 = "33333333-3333-3333-3333-333333333333"
)
// withMockDB swaps `db.DB` for a sqlmock and returns the mock plus a
// restore func. Tests use this in place of setupTokenTestDB which
// skips on a missing real DB.
@@ -90,13 +81,13 @@ func TestTokenHandler_List_HappyPath(t *testing.T) {
created := time.Date(2026, 4, 1, 12, 0, 0, 0, time.UTC)
last := created.Add(time.Hour)
mock.ExpectQuery(`SELECT id, prefix, created_at, last_used_at\s+FROM workspace_auth_tokens`).
WithArgs(wsUUID1, 50, 0).
WithArgs("ws-1", 50, 0).
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}).
AddRow("tok-1", "abc12345", created, last).
AddRow("tok-2", "def67890", created, nil))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusOK {
t.Fatalf("expected 200, got %d: %s", w.Code, w.Body.String())
@@ -130,7 +121,7 @@ func TestTokenHandler_List_EmptyResult(t *testing.T) {
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-2/tokens", gin.Params{{Key: "id", Value: wsUUID2}})
"/workspaces/ws-2/tokens", gin.Params{{Key: "id", Value: "ws-2"}})
if w.Code != http.StatusOK {
t.Fatalf("expected 200 on empty list, got %d", w.Code)
@@ -155,7 +146,7 @@ func TestTokenHandler_List_QueryError(t *testing.T) {
WillReturnError(errors.New("connection refused"))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-3/tokens", gin.Params{{Key: "id", Value: wsUUID3}})
"/workspaces/ws-3/tokens", gin.Params{{Key: "id", Value: "ws-3"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("query error must surface as 500, got %d", w.Code)
@@ -167,13 +158,13 @@ func TestTokenHandler_List_RespectsLimit(t *testing.T) {
defer cleanup()
mock.ExpectQuery(`SELECT id, prefix, created_at, last_used_at`).
WithArgs(wsUUID1, 10, 5).
WithArgs("ws-1", 10, 5).
WillReturnRows(sqlmock.NewRows([]string{"id", "prefix", "created_at", "last_used_at"}))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("GET", "/workspaces/ws-1/tokens?limit=10&offset=5", nil)
c.Params = gin.Params{{Key: "id", Value: wsUUID1}}
c.Params = gin.Params{{Key: "id", Value: "ws-1"}}
NewTokenHandler().List(c)
if w.Code != http.StatusOK {
@@ -195,7 +186,7 @@ func TestTokenHandler_List_ScanError(t *testing.T) {
AddRow("tok-1", "abc", "not-a-timestamp", nil))
w := makeReq(t, NewTokenHandler().List, "GET",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("scan error must surface as 500, got %d: %s", w.Code, w.Body.String())
@@ -210,11 +201,11 @@ func TestTokenHandler_Create_RateLimited(t *testing.T) {
// Count query returns 50 (== max) → 429.
mock.ExpectQuery(`SELECT COUNT\(\*\) FROM workspace_auth_tokens`).
WithArgs(wsUUID1).
WithArgs("ws-1").
WillReturnRows(sqlmock.NewRows([]string{"count"}).AddRow(50))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusTooManyRequests {
t.Errorf("max active tokens should 429, got %d", w.Code)
@@ -234,7 +225,7 @@ func TestTokenHandler_Create_IssueFails(t *testing.T) {
WillReturnError(errors.New("disk full"))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusInternalServerError {
t.Errorf("IssueToken DB error must 500, got %d", w.Code)
@@ -251,7 +242,7 @@ func TestTokenHandler_Create_HappyPath(t *testing.T) {
WillReturnResult(sqlmock.NewResult(1, 1))
w := makeReq(t, NewTokenHandler().Create, "POST",
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: wsUUID1}})
"/workspaces/ws-1/tokens", gin.Params{{Key: "id", Value: "ws-1"}})
if w.Code != http.StatusCreated {
t.Fatalf("expected 201, got %d: %s", w.Code, w.Body.String())
@@ -266,7 +257,7 @@ func TestTokenHandler_Create_HappyPath(t *testing.T) {
if body.AuthToken == "" {
t.Errorf("auth_token must be present and non-empty in response")
}
if body.WorkspaceID != wsUUID1 {
if body.WorkspaceID != "ws-1" {
t.Errorf("workspace_id mismatch: %q", body.WorkspaceID)
}
}
@@ -278,12 +269,12 @@ func TestTokenHandler_Revoke_HappyPath(t *testing.T) {
defer cleanup()
mock.ExpectExec(`UPDATE workspace_auth_tokens\s+SET revoked_at = now\(\)`).
WithArgs("tok-1", wsUUID1).
WithArgs("tok-1", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 1))
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-1", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-1"},
})
@@ -298,12 +289,12 @@ func TestTokenHandler_Revoke_NotFound(t *testing.T) {
// 0 rows affected → token not found OR already revoked.
mock.ExpectExec(`UPDATE workspace_auth_tokens`).
WithArgs("tok-ghost", wsUUID1).
WithArgs("tok-ghost", "ws-1").
WillReturnResult(sqlmock.NewResult(0, 0))
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-ghost", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-ghost"},
})
@@ -321,7 +312,7 @@ func TestTokenHandler_Revoke_DBError(t *testing.T) {
w := makeReq(t, NewTokenHandler().Revoke, "DELETE",
"/workspaces/ws-1/tokens/tok-1", gin.Params{
{Key: "id", Value: wsUUID1},
{Key: "id", Value: "ws-1"},
{Key: "tokenId", Value: "tok-1"},
})
@@ -330,59 +321,6 @@ func TestTokenHandler_Revoke_DBError(t *testing.T) {
}
}
// ---- UUID validation (regression: "global" sentinel 500) ------------
// The canvas Settings → Workspace Tokens tab sent the literal sentinel
// "global" as the workspace id when no node was selected. workspace_id
// is a `uuid` column, so the query raised
// `invalid input syntax for type uuid: "global"` which leaked as an
// opaque 500. List/Create/Revoke now reject any non-UUID id with a
// clean 400 before touching the DB. No DB expectation is set on the
// mock — a DB hit would fail ExpectationsWereMet, proving short-circuit.
func TestTokenHandler_RejectsNonUUIDWorkspaceID(t *testing.T) {
h := NewTokenHandler()
cases := []struct {
name string
run func(c *gin.Context)
method string
params gin.Params
}{
{"List", h.List, "GET", gin.Params{{Key: "id", Value: "global"}}},
{"Create", h.Create, "POST", gin.Params{{Key: "id", Value: "global"}}},
{"Revoke", h.Revoke, "DELETE", gin.Params{
{Key: "id", Value: "global"},
{Key: "tokenId", Value: "tok-1"},
}},
}
for _, tc := range cases {
t.Run(tc.name, func(t *testing.T) {
mock, cleanup := withMockDB(t)
defer cleanup()
w := makeReq(t, tc.run, tc.method,
"/workspaces/global/tokens", tc.params)
if w.Code != http.StatusBadRequest {
t.Fatalf("%s with non-UUID id must 400, got %d: %s",
tc.name, w.Code, w.Body.String())
}
var body struct {
Error string `json:"error"`
}
_ = json.Unmarshal(w.Body.Bytes(), &body)
if body.Error != "invalid workspace id" {
t.Errorf("%s: want error=%q, got %q",
tc.name, "invalid workspace id", body.Error)
}
// No query/exec was expected → if the handler hit the DB
// this fails, proving the guard short-circuits before SQL.
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("%s leaked a DB call past the uuid guard: %v", tc.name, err)
}
})
}
}
// Compile-time noise removal: the imports list pulls in the sql /
// driver packages and the silenced ctx so a future scenario that
// needs them doesn't have to re-add the import. Documented here so
@@ -11,7 +11,6 @@ import (
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/wsauth"
"github.com/gin-gonic/gin"
"github.com/google/uuid"
)
func init() { gin.SetMode(gin.TestMode) }
@@ -168,14 +167,11 @@ func TestTokenHandler_RevokeWrongWorkspace(t *testing.T) {
h := NewTokenHandler()
// Try to revoke with a different (valid-UUID) workspace ID that does
// not own the token — should 404. A valid UUID is required so this
// exercises the ownership branch, not the up-front uuid-shape 400.
otherWS := uuid.NewString()
// Try to revoke with a different workspace ID — should 404
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: otherWS}, {Key: "tokenId", Value: tokenID}}
c.Request = httptest.NewRequest("DELETE", "/workspaces/"+otherWS+"/tokens/"+tokenID, nil)
c.Params = gin.Params{{Key: "id", Value: "wrong-workspace-id"}, {Key: "tokenId", Value: tokenID}}
c.Request = httptest.NewRequest("DELETE", "/workspaces/wrong/tokens/"+tokenID, nil)
h.Revoke(c)
if w.Code != http.StatusNotFound {
@@ -74,21 +74,9 @@ type WorkspaceHandler struct {
// memory plugin). main.go sets this to plugin.DeleteNamespace
// when MEMORY_PLUGIN_URL is configured.
namespaceCleanupFn func(ctx context.Context, workspaceID string)
// asyncWG tracks goroutines launched by goAsync so tests can wait
// for async DB users (restart, provision) before asserting results.
// Matches the pattern from main commit 1c3b4ff3.
asyncWG sync.WaitGroup
asyncWG sync.WaitGroup
}
// newHandlerHook, when non-nil, is invoked for every WorkspaceHandler
// created via NewWorkspaceHandler. It is nil in production (zero cost);
// the test harness sets it so setupTestDB can drain every handler's
// in-flight async goroutines before swapping the global db.DB. Without
// this, a detached restart goroutine (maybeMarkContainerDead ->
// goAsync(RestartByID) -> runRestartCycle reads db.DB) races the
// db.DB restore in another test's t.Cleanup.
var newHandlerHook func(*WorkspaceHandler)
func (h *WorkspaceHandler) goAsync(fn func()) {
h.asyncWG.Add(1)
go func() {
@@ -117,9 +105,6 @@ func NewWorkspaceHandler(b events.EventEmitter, p *provisioner.Provisioner, plat
if p != nil {
h.provisioner = p
}
if newHandlerHook != nil {
newHandlerHook(h)
}
return h
}
@@ -607,7 +592,7 @@ func scanWorkspaceRow(rows interface {
var id, name, role, status, url, sampleError, currentTask, runtime, workspaceDir string
var tier, activeTasks, maxConcurrentTasks, uptimeSeconds int
var errorRate, x, y float64
var collapsed, broadcastEnabled, talkToUserEnabled bool
var collapsed bool
var parentID *string
var agentCard []byte
var budgetLimit sql.NullInt64
@@ -616,7 +601,7 @@ func scanWorkspaceRow(rows interface {
err := rows.Scan(&id, &name, &role, &tier, &status, &agentCard, &url,
&parentID, &activeTasks, &maxConcurrentTasks, &errorRate, &sampleError, &uptimeSeconds,
&currentTask, &runtime, &workspaceDir, &x, &y, &collapsed,
&budgetLimit, &monthlySpend, &broadcastEnabled, &talkToUserEnabled)
&budgetLimit, &monthlySpend)
if err != nil {
return nil, err
}
@@ -640,8 +625,6 @@ func scanWorkspaceRow(rows interface {
"x": x,
"y": y,
"collapsed": collapsed,
"broadcast_enabled": broadcastEnabled,
"talk_to_user_enabled": talkToUserEnabled,
}
// budget_limit: nil when no limit set, int64 otherwise
@@ -677,8 +660,7 @@ const workspaceListQuery = `
COALESCE(w.current_task, ''), COALESCE(w.runtime, 'langgraph'),
COALESCE(w.workspace_dir, ''),
COALESCE(cl.x, 0), COALESCE(cl.y, 0), COALESCE(cl.collapsed, false),
w.budget_limit, COALESCE(w.monthly_spend, 0),
w.broadcast_enabled, w.talk_to_user_enabled
w.budget_limit, COALESCE(w.monthly_spend, 0)
FROM workspaces w
LEFT JOIN canvas_layouts cl ON cl.workspace_id = w.id
WHERE w.status != 'removed'
@@ -738,8 +720,7 @@ func (h *WorkspaceHandler) Get(c *gin.Context) {
COALESCE(w.current_task, ''), COALESCE(w.runtime, 'langgraph'),
COALESCE(w.workspace_dir, ''),
COALESCE(cl.x, 0), COALESCE(cl.y, 0), COALESCE(cl.collapsed, false),
w.budget_limit, COALESCE(w.monthly_spend, 0),
w.broadcast_enabled, w.talk_to_user_enabled
w.budget_limit, COALESCE(w.monthly_spend, 0)
FROM workspaces w
LEFT JOIN canvas_layouts cl ON cl.workspace_id = w.id
WHERE w.id = $1
@@ -1,82 +0,0 @@
package handlers
// workspace_abilities.go — PATCH /workspaces/:id/abilities
//
// Allows users and admin agents to toggle two workspace-level ability flags:
//
// broadcast_enabled — workspace may POST /broadcast to send org-wide messages
// talk_to_user_enabled — workspace may deliver canvas chat messages via
// send_message_to_user / POST /notify
//
// Gated behind AdminAuth so workspace agents cannot self-modify their own
// ability flags (that would let any agent grant itself broadcast rights or
// suppress its own chat-silence constraint).
import (
"log"
"net/http"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/gin-gonic/gin"
)
// AbilitiesPayload carries the subset of ability flags the caller wants to
// update. Fields are pointers so that the handler can distinguish "caller
// supplied false" from "caller omitted the field" (omitempty semantics).
type AbilitiesPayload struct {
BroadcastEnabled *bool `json:"broadcast_enabled"`
TalkToUserEnabled *bool `json:"talk_to_user_enabled"`
}
// PatchAbilities handles PATCH /workspaces/:id/abilities (AdminAuth).
func PatchAbilities(c *gin.Context) {
id := c.Param("id")
if err := validateWorkspaceID(id); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace ID"})
return
}
var body AbilitiesPayload
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid request body"})
return
}
if body.BroadcastEnabled == nil && body.TalkToUserEnabled == nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "at least one ability field required"})
return
}
ctx := c.Request.Context()
var exists bool
if err := db.DB.QueryRowContext(ctx,
`SELECT EXISTS(SELECT 1 FROM workspaces WHERE id = $1 AND status != 'removed')`, id,
).Scan(&exists); err != nil || !exists {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
if body.BroadcastEnabled != nil {
if _, err := db.DB.ExecContext(ctx,
`UPDATE workspaces SET broadcast_enabled = $2, updated_at = now() WHERE id = $1`,
id, *body.BroadcastEnabled,
); err != nil {
log.Printf("PatchAbilities broadcast_enabled for %s: %v", id, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "update failed"})
return
}
}
if body.TalkToUserEnabled != nil {
if _, err := db.DB.ExecContext(ctx,
`UPDATE workspaces SET talk_to_user_enabled = $2, updated_at = now() WHERE id = $1`,
id, *body.TalkToUserEnabled,
); err != nil {
log.Printf("PatchAbilities talk_to_user_enabled for %s: %v", id, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "update failed"})
return
}
}
c.JSON(http.StatusOK, gin.H{"status": "updated"})
}
@@ -1,142 +0,0 @@
package handlers
// workspace_broadcast.go — POST /workspaces/:id/broadcast
//
// Allows a workspace with broadcast_enabled=true to send a message to every
// non-removed agent workspace in the org. The message is:
//
// • Persisted in each recipient's activity_logs (type='broadcast_receive')
// so poll-mode agents pick it up via GET /activity.
// • Broadcast via WebSocket BROADCAST_MESSAGE event so canvas panels can
// show a real-time banner for each recipient workspace.
//
// The sender's own workspace logs a 'broadcast_sent' activity row for
// traceability.
//
// Auth: WorkspaceAuth (the agent triggers this with its own bearer token).
// The handler re-validates broadcast_enabled inside the DB lookup to prevent
// TOCTOU — the middleware only proved the token is valid, not the ability.
import (
"log"
"net/http"
"strconv"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/db"
"github.com/Molecule-AI/molecule-monorepo/platform/internal/events"
"github.com/gin-gonic/gin"
)
// BroadcastHandler is constructed once and shared across requests.
type BroadcastHandler struct {
broadcaster *events.Broadcaster
}
// NewBroadcastHandler creates a BroadcastHandler.
func NewBroadcastHandler(b *events.Broadcaster) *BroadcastHandler {
return &BroadcastHandler{broadcaster: b}
}
// Broadcast handles POST /workspaces/:id/broadcast.
func (h *BroadcastHandler) Broadcast(c *gin.Context) {
senderID := c.Param("id")
if err := validateWorkspaceID(senderID); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace ID"})
return
}
var body struct {
Message string `json:"message" binding:"required"`
}
if err := c.ShouldBindJSON(&body); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "message is required"})
return
}
ctx := c.Request.Context()
// Verify sender exists and has broadcast_enabled=true.
var senderName string
var broadcastEnabled bool
err := db.DB.QueryRowContext(ctx,
`SELECT name, broadcast_enabled FROM workspaces WHERE id = $1 AND status != 'removed'`,
senderID,
).Scan(&senderName, &broadcastEnabled)
if err != nil {
c.JSON(http.StatusNotFound, gin.H{"error": "workspace not found"})
return
}
if !broadcastEnabled {
c.JSON(http.StatusForbidden, gin.H{
"error": "broadcast_disabled",
"hint": "This workspace does not have the broadcast ability. Ask a user or admin to enable it via PATCH /workspaces/:id/abilities.",
})
return
}
// Collect all non-removed agent workspaces (excludes the sender itself).
rows, err := db.DB.QueryContext(ctx,
`SELECT id FROM workspaces WHERE status != 'removed' AND id != $1`,
senderID,
)
if err != nil {
log.Printf("Broadcast: recipient query failed for %s: %v", senderID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "internal error"})
return
}
defer rows.Close()
var recipientIDs []string
for rows.Next() {
var rid string
if rows.Scan(&rid) == nil {
recipientIDs = append(recipientIDs, rid)
}
}
if err := rows.Err(); err != nil {
log.Printf("Broadcast: recipient rows error for %s: %v", senderID, err)
c.JSON(http.StatusInternalServerError, gin.H{"error": "internal error"})
return
}
broadcastPayload := map[string]interface{}{
"message": body.Message,
"sender_id": senderID,
"sender": senderName,
}
// Persist broadcast_receive in each recipient's activity log + emit WS event.
delivered := 0
for _, rid := range recipientIDs {
if _, err := db.DB.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, method, source_id, summary, status)
VALUES ($1, 'broadcast_receive', 'broadcast', $2, $3, 'ok')
`, rid, senderID, "Broadcast from "+senderName+": "+broadcastTruncate(body.Message, 120)); err != nil {
log.Printf("Broadcast: activity_logs insert for recipient %s: %v", rid, err)
continue
}
h.broadcaster.BroadcastOnly(rid, "BROADCAST_MESSAGE", broadcastPayload)
delivered++
}
// Record the send on the sender's own log.
if _, err := db.DB.ExecContext(ctx, `
INSERT INTO activity_logs (workspace_id, activity_type, method, summary, status)
VALUES ($1, 'broadcast_sent', 'broadcast', $2, 'ok')
`, senderID, "Broadcast sent to "+strconv.Itoa(delivered)+" workspace(s)"); err != nil {
log.Printf("Broadcast: sender activity_log for %s: %v", senderID, err)
}
c.JSON(http.StatusOK, gin.H{
"status": "sent",
"delivered": delivered,
})
}
func broadcastTruncate(s string, max int) string {
runes := []rune(s)
if len(runes) <= max {
return s
}
return string(runes[:max]) + "…"
}
@@ -33,7 +33,6 @@ var wsColumns = []string{
"parent_id", "active_tasks", "max_concurrent_tasks", "last_error_rate", "last_sample_error",
"uptime_seconds", "current_task", "runtime", "workspace_dir", "x", "y", "collapsed",
"budget_limit", "monthly_spend",
"broadcast_enabled", "talk_to_user_enabled",
}
// ==================== GET — financial fields stripped from open endpoint ====================
@@ -53,10 +52,8 @@ func TestWorkspaceBudget_Get_NilLimit(t *testing.T) {
[]byte(`{}`), "http://localhost:9001",
nil, 0, 1, 0.0, "", 0, "", "langgraph", "",
0.0, 0.0, false,
nil, // budget_limit NULL
0, // monthly_spend 0
false, // broadcast_enabled
true)) // talk_to_user_enabled
nil, // budget_limit NULL
0)) // monthly_spend 0
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
@@ -99,8 +96,7 @@ func TestWorkspaceBudget_Get_WithLimit(t *testing.T) {
nil, 0, 1, 0.0, "", 0, "", "langgraph", "",
0.0, 0.0, false,
int64(500), // budget_limit = $5.00 in DB
int64(123), // monthly_spend = $1.23 in DB
false, true)) // broadcast_enabled, talk_to_user_enabled
int64(123))) // monthly_spend = $1.23 in DB
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
@@ -149,19 +149,6 @@ func (h *WorkspaceHandler) Update(c *gin.Context) {
}
}
// Validate workspace_dir early so invalid paths are rejected before the
// existence check (consistent with name/role/runtime validation above).
if wsDir, ok := body["workspace_dir"]; ok {
if wsDir != nil {
if dirStr, isStr := wsDir.(string); isStr && dirStr != "" {
if err := validateWorkspaceDir(dirStr); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace directory"})
return
}
}
}
}
ctx := c.Request.Context()
// Auth is fully enforced at the router layer (WorkspaceAuth middleware, #680).
@@ -219,8 +206,15 @@ func (h *WorkspaceHandler) Update(c *gin.Context) {
}
needsRestart := false
if wsDir, ok := body["workspace_dir"]; ok {
// ValidateWorkspaceDir was already called above before the existence check;
// the UPDATE itself is unconditional.
// Allow null to clear workspace_dir
if wsDir != nil {
if dirStr, isStr := wsDir.(string); isStr && dirStr != "" {
if err := validateWorkspaceDir(dirStr); err != nil {
c.JSON(http.StatusBadRequest, gin.H{"error": "invalid workspace directory"})
return
}
}
}
if _, err := db.DB.ExecContext(ctx, `UPDATE workspaces SET workspace_dir = $2, updated_at = now() WHERE id = $1`, id, wsDir); err != nil {
log.Printf("Update workspace_dir error for %s: %v", id, err)
}
@@ -187,43 +187,57 @@ func TestState_QueryError(t *testing.T) {
// ---------- Update ----------
func TestUpdate_InvalidUUID(t *testing.T) {
err := validateWorkspaceID("not-a-uuid")
if err == nil {
t.Error("expected error for invalid UUID in PATCH path")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"name": "Test"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/not-a-uuid", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_InvalidBody(t *testing.T) {
_, r := setupWorkspaceCrudTest(t)
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r.PATCH("/workspaces/:id", h.Update)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader([]byte("not json")))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r.ServeHTTP(w, req)
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for malformed JSON, got %d: %s", w.Code, w.Body.String())
t.Errorf("expected 400, got %d", w.Code)
}
}
func TestUpdate_WorkspaceNotFound(t *testing.T) {
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock, r := setupWorkspaceCrudTest(t)
mock, _ := setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r.PATCH("/workspaces/:id", h.Update)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock.ExpectQuery(`SELECT EXISTS\(SELECT 1 FROM workspaces WHERE id = \$1\)`).
WithArgs(wsID).
WillReturnRows(sqlmock.NewRows([]string{"count"}).AddRow(0))
WillReturnRows(sqlmock.NewRows([]string{"exists"}).AddRow(false))
body := map[string]interface{}{"name": "New Name"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/"+wsID, bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r.ServeHTTP(w, req)
r2.ServeHTTP(w, req)
if w.Code != http.StatusNotFound {
t.Errorf("expected 404, got %d: %s", w.Code, w.Body.String())
@@ -231,78 +245,163 @@ func TestUpdate_WorkspaceNotFound(t *testing.T) {
}
func TestUpdate_NameTooLong(t *testing.T) {
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
longName := make([]byte, 256)
for i := range longName {
longName[i] = 'x'
}
err := validateWorkspaceFields(string(longName), "", "", "")
if err == nil {
t.Error("expected error for name > 255 chars")
body := map[string]interface{}{"name": string(longName)}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for name too long, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_RoleTooLong(t *testing.T) {
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
longRole := make([]byte, 1001)
for i := range longRole {
longRole[i] = 'x'
}
err := validateWorkspaceFields("", string(longRole), "", "")
if err == nil {
t.Error("expected error for role > 1000 chars")
body := map[string]interface{}{"role": string(longRole)}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for role too long, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_NameWithNewline(t *testing.T) {
err := validateWorkspaceFields("Name\nwith newline", "", "", "")
if err == nil {
t.Error("expected error for newline in name")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"name": "Name\nwith newline"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for newline in name, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_NameWithYAMLSpecialChars(t *testing.T) {
for _, ch := range "{}[]|>*&!" {
err := validateWorkspaceFields("namewith"+string(ch), "", "", "")
if err == nil {
t.Errorf("expected error for YAML special char %c in name", ch)
}
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"name": "Name with [brackets]"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for YAML special chars in name, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_WorkspaceDirSystemPath(t *testing.T) {
err := validateWorkspaceDir("/etc/my-workspace")
if err == nil {
t.Error("expected error for /etc/ system path in workspace_dir")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"workspace_dir": "/etc/my-workspace"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for system path workspace_dir, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_WorkspaceDirTraversal(t *testing.T) {
err := validateWorkspaceDir("/workspace/../../../etc")
if err == nil {
t.Error("expected error for traversal in workspace_dir")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"workspace_dir": "/workspace/../../../etc"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for traversal in workspace_dir, got %d: %s", w.Code, w.Body.String())
}
}
func TestUpdate_WorkspaceDirRelativePath(t *testing.T) {
err := validateWorkspaceDir("relative/path")
if err == nil {
t.Error("expected error for relative workspace_dir")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.PATCH("/workspaces/:id", h.Update)
body := map[string]interface{}{"workspace_dir": "relative/path"}
b, _ := json.Marshal(body)
req, _ := http.NewRequest("PATCH", "/workspaces/aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa", bytes.NewReader(b))
req.Header.Set("Content-Type", "application/json")
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400 for relative workspace_dir, got %d: %s", w.Code, w.Body.String())
}
}
// ---------- Delete ----------
func TestDelete_InvalidUUID(t *testing.T) {
err := validateWorkspaceID("not-a-uuid")
if err == nil {
t.Error("expected error for invalid UUID in DELETE path")
_, _ = setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r2 := gin.New()
r2.DELETE("/workspaces/:id", h.Delete)
req, _ := http.NewRequest("DELETE", "/workspaces/not-a-uuid", nil)
w := httptest.NewRecorder()
r2.ServeHTTP(w, req)
if w.Code != http.StatusBadRequest {
t.Errorf("expected 400, got %d: %s", w.Code, w.Body.String())
}
}
func TestDelete_HasChildrenWithoutConfirm(t *testing.T) {
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock, r := setupWorkspaceCrudTest(t)
mock, _ := setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r.DELETE("/workspaces/:id", h.Delete)
r2 := gin.New()
r2.DELETE("/workspaces/:id", h.Delete)
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock.ExpectQuery(`SELECT id, name FROM workspaces WHERE parent_id = \$1 AND status != 'removed'`).
WithArgs(wsID).
@@ -312,7 +411,7 @@ func TestDelete_HasChildrenWithoutConfirm(t *testing.T) {
req, _ := http.NewRequest("DELETE", "/workspaces/"+wsID, nil)
// No ?confirm=true
w := httptest.NewRecorder()
r.ServeHTTP(w, req)
r2.ServeHTTP(w, req)
if w.Code != http.StatusConflict {
t.Errorf("expected 409, got %d: %s", w.Code, w.Body.String())
@@ -331,10 +430,12 @@ func TestDelete_HasChildrenWithoutConfirm(t *testing.T) {
}
func TestDelete_ChildrenCheckQueryError(t *testing.T) {
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock, r := setupWorkspaceCrudTest(t)
mock, _ := setupWorkspaceCrudTest(t)
h := newWorkspaceCrudHandler(t)
r.DELETE("/workspaces/:id", h.Delete)
r2 := gin.New()
r2.DELETE("/workspaces/:id", h.Delete)
wsID := "aaaaaaaa-aaaa-aaaa-aaaa-aaaaaaaaaaaa"
mock.ExpectQuery(`SELECT id, name FROM workspaces WHERE parent_id = \$1 AND status != 'removed'`).
WithArgs(wsID).
@@ -342,7 +443,7 @@ func TestDelete_ChildrenCheckQueryError(t *testing.T) {
req, _ := http.NewRequest("DELETE", "/workspaces/"+wsID, nil)
w := httptest.NewRecorder()
r.ServeHTTP(w, req)
r2.ServeHTTP(w, req)
if w.Code != http.StatusInternalServerError {
t.Errorf("expected 500, got %d", w.Code)
@@ -258,7 +258,7 @@ func (h *WorkspaceHandler) buildProvisionerConfig(
// present) wins, matching the existing WorkspaceDir precedence.
workspacePath := payload.WorkspaceDir
workspaceAccess := payload.WorkspaceAccess
if (workspacePath == "" || workspaceAccess == "") && db.DB != nil {
if workspacePath == "" || workspaceAccess == "" {
var dbDir, dbAccess string
if err := db.DB.QueryRow(
`SELECT COALESCE(workspace_dir, ''), COALESCE(workspace_access, 'none') FROM workspaces WHERE id = $1`,
@@ -805,9 +805,6 @@ func loadWorkspaceSecrets(ctx context.Context, workspaceID string) (map[string]s
envVars[k] = string(decrypted)
}
}
if err := globalRows.Err(); err != nil {
log.Printf("Provisioner: global_secrets rows.Err workspace=%s: %v", workspaceID, err)
}
}
wsRows, err := db.DB.QueryContext(ctx,
`SELECT key, encrypted_value, encryption_version FROM workspace_secrets WHERE workspace_id = $1`, workspaceID)
@@ -826,9 +823,6 @@ func loadWorkspaceSecrets(ctx context.Context, workspaceID string) (map[string]s
envVars[k] = string(decrypted)
}
}
if err := wsRows.Err(); err != nil {
log.Printf("Provisioner: workspace_secrets rows.Err workspace=%s: %v", workspaceID, err)
}
}
return envVars, ""
}
@@ -144,6 +144,7 @@ func TestProvisionWorkspaceAuto_RoutesToCPWhenSet(t *testing.T) {
rec := &trackingCPProv{startErr: errors.New("simulated CP rejection")}
bcast := &concurrentSafeBroadcaster{}
h := NewWorkspaceHandler(bcast, nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, h)
h.SetCPProvisioner(rec)
wsID := "ws-routes-to-cp-0123456789abcdef"
@@ -595,6 +596,7 @@ func TestRestartWorkspaceAuto_RoutesToCPWhenSet(t *testing.T) {
// Mock DB so cpStopWithRetry can run without a real Postgres.
mock := setupTestDB(t)
waitForHandlerAsyncBeforeDBCleanup(t, h)
mock.MatchExpectationsInOrder(false)
// provisionWorkspaceCP runs in the goroutine and will hit secrets
// SELECTs + UPDATE workspace as failed (we make CP Start return
@@ -670,6 +672,7 @@ func TestRestartWorkspaceAuto_RoutesToDockerWhenOnlyDocker(t *testing.T) {
bcast := &concurrentSafeBroadcaster{}
h := NewWorkspaceHandler(bcast, nil, "http://localhost:8080", t.TempDir())
waitForHandlerAsyncBeforeDBCleanup(t, h)
stub := &stoppingLocalProv{}
h.provisioner = stub
@@ -2,6 +2,7 @@ package handlers
import (
"context"
"database/sql"
"fmt"
"net/http"
"os"
@@ -634,6 +635,11 @@ func TestSeedInitialMemories_EmptyMemoriesNil(t *testing.T) {
// ==================== buildProvisionerConfig ====================
func TestBuildProvisionerConfig_BasicFields(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectQuery(`SELECT COALESCE\(workspace_dir`).
WithArgs("ws-basic").
WillReturnRows(sqlmock.NewRows([]string{"workspace_dir", "workspace_access"}).AddRow("", "none"))
broadcaster := newTestBroadcaster()
tmpDir := t.TempDir()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", tmpDir)
@@ -678,6 +684,14 @@ func TestBuildProvisionerConfig_BasicFields(t *testing.T) {
}
func TestBuildProvisionerConfig_WorkspacePathFromEnv(t *testing.T) {
mock := setupTestDB(t)
mock.ExpectQuery(`SELECT COALESCE\(workspace_dir`).
WithArgs("ws-env").
WillReturnError(sql.ErrNoRows)
mock.ExpectQuery(`SELECT digest FROM runtime_image_pins`).
WithArgs("claude-code").
WillReturnError(sql.ErrNoRows)
broadcaster := newTestBroadcaster()
handler := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())

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