Compare commits

...

27 Commits

Author SHA1 Message Date
devops-engineer 81630a36f8 Merge branch 'main' into test/delegate-record-db-errors
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Successful in 5s
CI / Detect changes (pull_request) Successful in 13s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 9s
CI / Canvas (Next.js) (pull_request) Successful in 4s
E2E Chat / detect-changes (pull_request) Successful in 16s
E2E API Smoke Test / detect-changes (pull_request) Successful in 21s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 8s
Harness Replays / detect-changes (pull_request) Successful in 13s
CI / Canvas Deploy Status (pull_request) Has been skipped
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 8s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 17s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 24s
E2E Chat / E2E Chat (pull_request) Successful in 5s
Harness Replays / Harness Replays (pull_request) Successful in 6s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 18s
security-review / approved (pull_request_target) Failing after 11s
gate-check-v3 / gate-check (pull_request_target) Failing after 16s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 19s
qa-review / approved (pull_request_target) Failing after 14s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, l
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 8s
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 6s
sop-tier-check / tier-check (pull_request_target) Failing after 7s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m8s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 1m17s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2m8s
CI / Platform (Go) (pull_request) Successful in 4m10s
CI / all-required (pull_request) Successful in 4s
2026-06-06 18:50:49 +00:00
devops-engineer 173881e67a Merge pull request 'feat: approval-gate infrastructure for destructive ops (Phase 4)' (#2372) from feat/platform-agent-approval-gate into main
ci-arm64-advisory / fast-checks (push) Waiting to run
Handlers Postgres Integration / Handlers Postgres Integration (push) Blocked by required conditions
CI / Python Lint & Test (push) Successful in 7s
Block internal-flavored paths / Block forbidden paths (push) Successful in 16s
CI / Detect changes (push) Successful in 15s
Handlers Postgres Integration / detect-changes (push) Has started running
E2E Chat / detect-changes (push) Successful in 11s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 13s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 17s
E2E API Smoke Test / detect-changes (push) Successful in 24s
Harness Replays / detect-changes (push) Successful in 7s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 6s
CI / Canvas (Next.js) (push) Successful in 2s
CI / Shellcheck (E2E scripts) (push) Successful in 2s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 20s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 18s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 2s
Harness Replays / Harness Replays (push) Successful in 26s
CI / Canvas Deploy Status (push) Successful in 2s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 1m5s
E2E Chat / E2E Chat (push) Failing after 1m49s
CI / Platform (Go) (push) Successful in 10m37s
CI / all-required (push) Successful in 7s
publish-workspace-server-image / build-and-push (push) Successful in 9m48s
publish-workspace-server-image / Production auto-deploy (push) Successful in 2m27s
E2E Staging External Runtime / E2E Staging External Runtime (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
2026-06-06 18:24:00 +00:00
devops-engineer bde5421766 Merge pull request 'feat: platform-agent participant kind (Phase 0)' (#2361) from feat/platform-agent-kind into main
Block internal-flavored paths / Block forbidden paths (push) Has started running
CI / Python Lint & Test (push) Successful in 6s
E2E API Smoke Test / detect-changes (push) Successful in 12s
E2E Chat / detect-changes (push) Successful in 19s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 23s
Handlers Postgres Integration / detect-changes (push) Successful in 8s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (local) (push) Successful in 31s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 19s
E2E Staging SaaS (full lifecycle) / pr-validate (push) Successful in 28s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 8s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 5s
Harness Replays / detect-changes (push) Successful in 16s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas (Next.js) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Shellcheck (E2E scripts) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Platform (Go) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Detect changes (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / all-required (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
E2E Staging External Runtime / E2E Staging External Runtime (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 3s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 22s
Harness Replays / Harness Replays (push) Successful in 1s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 59s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 1m7s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (push) Has been skipped
E2E Chat / E2E Chat (push) Failing after 4m26s
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (push) Failing after 6m5s
publish-workspace-server-image / build-and-push (push) Failing after 7m48s
publish-workspace-server-image / Production auto-deploy (push) Has been skipped
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (push) Failing after 9m3s
2026-06-06 18:22:38 +00:00
devops-engineer 2e068c7586 Merge pull request 'RFC: org-level platform agent — tenant-resident concierge (design SSOT)' (#2360) from rfc/platform-agent into main
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 16s
Block internal-flavored paths / Block forbidden paths (push) Successful in 8s
Handlers Postgres Integration / detect-changes (push) Successful in 9s
CI / Python Lint & Test (push) Successful in 18s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 9s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 12s
E2E Chat / detect-changes (push) Successful in 18s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 19s
CI / Detect changes (push) Successful in 26s
E2E API Smoke Test / detect-changes (push) Successful in 26s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 16s
E2E Chat / E2E Chat (push) Successful in 6s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 5s
CI / Platform (Go) (push) Successful in 4s
CI / Canvas (Next.js) (push) Successful in 5s
CI / Shellcheck (E2E scripts) (push) Successful in 2s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 5s
CI / all-required (push) Successful in 16s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 4m14s
publish-workspace-server-image / build-and-push (push) Successful in 5m6s
publish-workspace-server-image / Production auto-deploy (push) Successful in 14s
2026-06-06 18:18:35 +00:00
devops-engineer a380218234 Merge pull request 'fix(merge-queue): paginate Gitea API list calls — issues, statuses (#2366/#588)' (#2367) from fix/gitea-merge-queue-pagination into main
Handlers Postgres Integration / Handlers Postgres Integration (push) Blocked by required conditions
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 14s
Block internal-flavored paths / Block forbidden paths (push) Successful in 3s
E2E API Smoke Test / detect-changes (push) Successful in 9s
Handlers Postgres Integration / detect-changes (push) Has started running
E2E Chat / detect-changes (push) Successful in 9s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 15s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 7s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 8s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 24s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Detect changes (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Platform (Go) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas (Next.js) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Shellcheck (E2E scripts) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Python Lint & Test (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / all-required (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
Ops Scripts Tests / Ops scripts (unittest) (push) Successful in 1m1s
E2E Chat / E2E Chat (push) Successful in 5s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 2s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 20s
publish-workspace-server-image / build-and-push (push) Successful in 4m52s
publish-workspace-server-image / Production auto-deploy (push) Successful in 15s
2 genuine officials current head + required-green, mergeable — direct-merge (avoid rebase-churn approval-dismissal). CTO diff-reviewed (efficiency unblock).
2026-06-06 18:17:35 +00:00
devops-engineer 578b145312 Merge pull request 'fix(merge-queue): reject volume-skipped pending as genuine soft-fail (sop-checklist HOLD)' (#2368) from fix/sop-checklist-hold into main
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 15s
Block internal-flavored paths / Block forbidden paths (push) Successful in 3s
E2E Chat / detect-changes (push) Successful in 6s
Handlers Postgres Integration / detect-changes (push) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 7s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 6s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 6s
E2E API Smoke Test / detect-changes (push) Successful in 29s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 42s
E2E Chat / E2E Chat (push) Successful in 3s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas (Next.js) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Shellcheck (E2E scripts) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Detect changes (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Platform (Go) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Python Lint & Test (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / all-required (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
Ops Scripts Tests / Ops scripts (unittest) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 2s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 2s
publish-workspace-server-image / build-and-push (push) Successful in 4m42s
publish-workspace-server-image / Production auto-deploy (push) Successful in 45s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 4m22s
2 genuine officials current head + required-green, mergeable — direct-merge (avoid rebase-churn approval-dismissal). CTO diff-reviewed (efficiency unblock).
2026-06-06 18:17:25 +00:00
devops-engineer a77b6850e2 Merge pull request 'fix(ci): lint-pre-flip fail-closed — unreadable success logs treated as masked + workflow flag flipped' (#2369) from fix/lint-pre-flip-fail-closed-clean into main
Ops Scripts Tests / Ops scripts (unittest) (push) Waiting to run
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 16s
Block internal-flavored paths / Block forbidden paths (push) Successful in 5s
E2E API Smoke Test / detect-changes (push) Successful in 9s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 6s
Handlers Postgres Integration / detect-changes (push) Successful in 4s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (push) Successful in 4s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 3s
E2E Chat / detect-changes (push) Successful in 19s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 3s
lint-required-workflows-docker-host-pinned / Lint docker-host pin on docker-touching workflows (push) Successful in 5s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 6s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 3s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Shellcheck (E2E scripts) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Detect changes (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Platform (Go) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas (Next.js) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Python Lint & Test (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / all-required (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
E2E Chat / E2E Chat (push) Successful in 16s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (push) Successful in 1m53s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (push) Successful in 2m12s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 1m9s
publish-workspace-server-image / build-and-push (push) Successful in 4m49s
publish-workspace-server-image / Production auto-deploy (push) Successful in 29s
2 genuine officials current head + required-green, mergeable — direct-merge (avoid rebase-churn approval-dismissal). CTO diff-reviewed (efficiency unblock).
2026-06-06 18:17:11 +00:00
devops-engineer 2f9b5b6704 Merge pull request 'fix(ci): status-reaper infra-failure→red — observability hardening' (#2370) from fix/status-reaper-observability into main
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 18s
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
E2E API Smoke Test / detect-changes (push) Successful in 8s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 6s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 3s
E2E Chat / detect-changes (push) Successful in 21s
Handlers Postgres Integration / detect-changes (push) Successful in 21s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 21s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 20s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 5s
E2E Chat / E2E Chat (push) Successful in 3s
ci-arm64-advisory / fast-checks (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas (Next.js) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Shellcheck (E2E scripts) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Detect changes (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Platform (Go) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Canvas Deploy Status (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / Python Lint & Test (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
CI / all-required (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
Ops Scripts Tests / Ops scripts (unittest) (push) Compensated by status-reaper (push run was cancelled/superseded; Gitea 1.22.6 reports cancelled runs as failure statuses)
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 3m50s
publish-workspace-server-image / build-and-push (push) Successful in 9m13s
publish-workspace-server-image / Production auto-deploy (push) Successful in 16s
2 genuine officials current head + required-green, mergeable — direct-merge (avoid rebase-churn approval-dismissal). CTO diff-reviewed (efficiency unblock).
2026-06-06 18:16:59 +00:00
devops-engineer 86df02c38f Merge branch 'main' into feat/platform-agent-kind
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 4s
CI / Python Lint & Test (pull_request) Successful in 4s
E2E Chat / detect-changes (pull_request) Successful in 8s
CI / Detect changes (pull_request) Successful in 13s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 6s
Harness Replays / detect-changes (pull_request) Successful in 6s
E2E API Smoke Test / detect-changes (pull_request) Successful in 17s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 5s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 18s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 1s
E2E Chat / E2E Chat (pull_request) Successful in 13s
Check migration collisions / Migration version collision check (pull_request) Successful in 30s
CI / Canvas (Next.js) (pull_request) Successful in 8s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 6s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 15s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 24s
gate-check-v3 / gate-check (pull_request_target) Successful in 8s
Harness Replays / Harness Replays (pull_request) Successful in 1s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 6s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-tier-check / tier-check (pull_request_target) Failing after 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
security-review / approved (pull_request_target) Failing after 23s
qa-review / approved (pull_request_target) Failing after 26s
CI / Canvas Deploy Status (pull_request) Has been skipped
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (local) (pull_request) Successful in 1m18s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (pull_request) Successful in 5s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 57s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m17s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2m40s
CI / Platform (Go) (pull_request) Successful in 4m6s
CI / all-required (pull_request) Successful in 23s
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (pull_request) Failing after 5m50s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Failing after 7m44s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Has been cancelled
sop-tier-check / tier-check (pull_request_review) Failing after 11s
audit-force-merge / audit (pull_request_target) Successful in 28s
2026-06-06 18:10:50 +00:00
Molecule AI Dev Engineer A (Kimi) db39d519dc fix(merge-queue): queue API/network/timeout errors now return 1 (#2370 RC)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 9s
CI / Python Lint & Test (pull_request) Successful in 8s
CI / Detect changes (pull_request) Successful in 10s
E2E API Smoke Test / detect-changes (pull_request) Successful in 10s
E2E Chat / detect-changes (pull_request) Successful in 10s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 6s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
gate-check-v3 / gate-check (pull_request_target) Failing after 6s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 14s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 15s
sop-checklist / review-refire (pull_request_target) Has been skipped
qa-review / approved (pull_request_target) Failing after 5s
CI / Platform (Go) (pull_request) Successful in 1s
CI / Canvas (Next.js) (pull_request) Successful in 2s
security-review / approved (pull_request_target) Failing after 5s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
E2E Chat / E2E Chat (pull_request) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
CI / Canvas Deploy Status (pull_request) Has been skipped
sop-tier-check / tier-check (pull_request_target) Failing after 13s
CI / all-required (pull_request) Successful in 7s
sop-checklist / all-items-acked (pull_request_target) Successful in 14s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m0s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 59s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 10s
audit-force-merge / audit (pull_request_target) Successful in 11s
Per CR2 RC: the status-reaper observability fix was complete, but the
merge-queue exception handlers in main() still returned 0 on ApiError,
URLError, and TimeoutError. This hid persistent infra issues from
operators — the cron stayed green while the queue could not evaluate
merge state.

Now all three handlers return 1 so the cron job surfaces red and
operators are paged to investigate.

Diff-proof: 52/52 gitea-merge-queue tests pass.

Refs: core#2370, CR2 RC.
2026-06-06 17:47:46 +00:00
core-devops 0b771d5770 feat(workspace-server): approval-gate infrastructure for destructive ops (Phase 4)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
CI / Python Lint & Test (pull_request) Successful in 3s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 9s
CI / Detect changes (pull_request) Successful in 10s
E2E API Smoke Test / detect-changes (pull_request) Successful in 7s
E2E Chat / detect-changes (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 6s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 4s
Harness Replays / detect-changes (pull_request) Successful in 7s
Check migration collisions / Migration version collision check (pull_request) Successful in 18s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 9s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
qa-review / approved (pull_request_target) Failing after 4s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 13s
gate-check-v3 / gate-check (pull_request_target) Successful in 6s
CI / Canvas (Next.js) (pull_request) Successful in 2s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 1s
E2E Chat / E2E Chat (pull_request) Successful in 2s
security-review / approved (pull_request_target) Failing after 9s
CI / Canvas Deploy Status (pull_request) Has been skipped
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
Harness Replays / Harness Replays (pull_request) Successful in 3s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 55s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 58s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2m26s
CI / Platform (Go) (pull_request) Successful in 4m9s
CI / all-required (pull_request) Successful in 5s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 6s
sop-tier-check / tier-check (pull_request_target) Failing after 7s
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Has been cancelled
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 11s
audit-force-merge / audit (pull_request_target) Successful in 21s
Server-side gate so destructive org operations the user-driven platform agent can
trigger require a human approval (RFC docs/design/rfc-platform-agent.md). The
platform MCP is a CLIENT of these handlers, so enforcement lives here (the trust
boundary), not in the MCP.

- migration 20260606020000_approvals_consumed: approval_requests.consumed_at
  (single-use) + request_hash (dedup) + a partial index for the gate lookup.
- internal/approvals/policy.go: the one auditable map of gated actions
  (delete_workspace / deprovision / secret_write / org_token_mint) + IsGated.
- requireApproval(): consumes a matching approved+unconsumed request (race-safe
  via conditional UPDATE ... RETURNING / FOR UPDATE SKIP LOCKED) and proceeds,
  else creates/reuses a pending request (dedup by request_hash), broadcasts it to
  the canvas and escalates to the parent if any. gateDestructive() wraps it and
  writes HTTP 202 pending for gin handlers.

Matching is (workspace_id, action, request_hash) where request_hash is a stable
digest of the op + context, so an approval for 'delete ws A' can't be replayed to
'delete ws B', and retries reuse one pending row instead of flooding.

Tests: policy + hash-stability/context-sensitivity unit tests; gateDestructive
non-gated passthrough; and a real-Postgres integration test proving the full
cycle — pending -> dedup -> approve -> consume -> single-use (no replay) ->
context isolation (sqlmock cannot prove consume-once row state).

Infrastructure only — NOT yet wired into live handlers. Wiring requires a
platform-agent caller marker so the gate fires only for concierge-initiated calls
(not operator/CP flows); that lands with Phase 3's runtime/MCP marker so existing
delete/secret flows are unchanged until then.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 10:43:25 -07:00
Molecule AI Dev Engineer A (Kimi) 8a63d16f8c fix(ci): lint-pre-flip fail-closed — ApiError and zero-runs now blocking (#2369 RC)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
CI / Python Lint & Test (pull_request) Successful in 3s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 4s
E2E Chat / detect-changes (pull_request) Successful in 6s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 6s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 9s
E2E Chat / E2E Chat (pull_request) Successful in 3s
lint-required-workflows-docker-host-pinned / Lint docker-host pin on docker-touching workflows (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
E2E API Smoke Test / detect-changes (pull_request) Successful in 19s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 15s
CI / Detect changes (pull_request) Successful in 20s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
sop-checklist / review-refire (pull_request_target) Has been skipped
qa-review / approved (pull_request_target) Failing after 8s
gate-check-v3 / gate-check (pull_request_target) Failing after 10s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
CI / Platform (Go) (pull_request) Successful in 2s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 17s
CI / Canvas (Next.js) (pull_request) Successful in 1s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
CI / Canvas Deploy Status (pull_request) Has been skipped
sop-tier-check / tier-check (pull_request_target) Failing after 22s
sop-checklist / all-items-acked (pull_request_target) Successful in 24s
security-review / approved (pull_request_target) Failing after 24s
CI / all-required (pull_request) Successful in 8s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 56s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m4s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m7s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m29s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Failing after 1m32s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 1m38s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 12s
audit-force-merge / audit (pull_request_target) Successful in 15s
Per Researcher + CR2 RC:
- combined_status() ApiError now appends to masked_runs (was warning+continue)
- zero checked_commits now appends to masked_runs (was warning+allow)
- zero recent commits now appends to masked_runs (was warning+allow)
- Final decision already blocks on masked_runs, so unverifiable flips
  are now blocked rather than passing with warnings only.

Diff-proof: 36/36 pytest tests pass.

Refs: core#2369, Researcher RC + CR2 RC.
2026-06-06 17:42:44 +00:00
Molecule AI Dev Engineer A (Kimi) 63c25d4c3f fix(merge-queue): remove generic tier:low pending-as-green override (#2368 RC)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
CI / Python Lint & Test (pull_request) Successful in 7s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 7s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 5s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
E2E Chat / detect-changes (pull_request) Successful in 8s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 7s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 8s
CI / Detect changes (pull_request) Successful in 13s
E2E API Smoke Test / detect-changes (pull_request) Successful in 12s
E2E Chat / E2E Chat (pull_request) Successful in 2s
sop-checklist / review-refire (pull_request_target) Has been skipped
qa-review / approved (pull_request_target) Failing after 5s
security-review / approved (pull_request_target) Failing after 5s
gate-check-v3 / gate-check (pull_request_target) Failing after 6s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
CI / Platform (Go) (pull_request) Successful in 2s
sop-checklist / all-items-acked (pull_request_target) Successful in 5s
CI / Canvas (Next.js) (pull_request) Successful in 2s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 10s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 5s
CI / Canvas Deploy Status (pull_request) Has been skipped
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 6s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
sop-tier-check / tier-check (pull_request_target) Failing after 12s
CI / all-required (pull_request) Successful in 7s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m15s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m24s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 12s
audit-force-merge / audit (pull_request_target) Successful in 4s
_is_tier_low_pending_ok() now always returns False per Researcher + CR2
RC: ANY pending/non-success required sop-checklist must HOLD and appear
in missing_or_bad, not pass. The prior soft-fail accepted all pending
sop-checklist for tier:low, which was a fail-open.

Diff-proof: 54/54 gitea-merge-queue tests pass.

Refs: core#2368, Researcher RC + CR2 RC.
2026-06-06 17:38:37 +00:00
Molecule AI Dev Engineer A (Kimi) 116697c576 fix(ci): status-reaper infra-failure→red — observability hardening
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 15s
CI / Python Lint & Test (pull_request) Successful in 3s
E2E API Smoke Test / detect-changes (pull_request) Successful in 6s
E2E Chat / detect-changes (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 7s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 4s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 18s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
CI / Detect changes (pull_request) Successful in 22s
qa-review / approved (pull_request_target) Failing after 6s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 13s
gate-check-v3 / gate-check (pull_request_target) Successful in 9s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 11s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 7s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
sop-tier-check / tier-check (pull_request_target) Failing after 5s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
CI / Platform (Go) (pull_request) Successful in 2s
security-review / approved (pull_request_target) Failing after 16s
CI / Canvas (Next.js) (pull_request) Successful in 2s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
E2E Chat / E2E Chat (pull_request) Successful in 11s
CI / all-required (pull_request) Successful in 6s
CI / Canvas Deploy Status (pull_request) Has been skipped
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 55s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m26s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 7s
- commit-list API failure: ::warning:: → ::error:: + return 1
- per-SHA get_combined_status failure: ::warning:: → ::error:: + tracked
  in sha_api_errors counter
- main() returns 1 when skipped=True or sha_api_errors > 0 so cron bot
  surfaces persistent infra issues as red failures

Diff-proof: 49/49 status-reaper tests pass.

Refs: internal#219 §1, PR#2367 pair
2026-06-06 17:27:24 +00:00
Molecule AI Dev Engineer A (Kimi) d1c6fce937 fix(ci): lint-pre-flip fail-closed — unreadable success logs treated as masked + workflow flag flipped
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 5s
CI / Python Lint & Test (pull_request) Successful in 4s
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 4s
CI / Detect changes (pull_request) Successful in 14s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 11s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 15s
E2E API Smoke Test / detect-changes (pull_request) Successful in 20s
E2E Chat / detect-changes (pull_request) Successful in 20s
lint-required-workflows-docker-host-pinned / Lint docker-host pin on docker-touching workflows (pull_request) Successful in 11s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 7s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 18s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 10s
CI / Platform (Go) (pull_request) Successful in 14s
CI / Canvas (Next.js) (pull_request) Successful in 12s
gate-check-v3 / gate-check (pull_request_target) Successful in 4s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 12s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 4s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1s
security-review / approved (pull_request_target) Failing after 9s
qa-review / approved (pull_request_target) Failing after 9s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 6s
CI / all-required (pull_request) Successful in 4s
E2E Chat / E2E Chat (pull_request) Successful in 3s
sop-tier-check / tier-check (pull_request_target) Failing after 19s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 58s
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Successful in 1m11s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 1m10s
CI / Canvas Deploy Status (pull_request) Has been skipped
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 1m15s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m23s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 1m36s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 6s
SCRIPT fail-closed:
- unreadable log + success status → masked_run (was warn-only PASS).
  Quirk #10 (continue-on-error masking) cannot be verified when logs
  are pruned; fail-closed means block the flip.

WORKFLOW flag:
- continue-on-error: true → false on scan job.

Diff-proof: 35/35 pytest tests pass.

Refs: mc#1982, internal#219 §1
2026-06-06 17:27:08 +00:00
Molecule AI Dev Engineer A (Kimi) 0e87fde0a3 fix(merge-queue): reject volume-skipped pending as genuine soft-fail (sop-checklist HOLD)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
CI / Python Lint & Test (pull_request) Successful in 5s
CI / Detect changes (pull_request) Successful in 10s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 8s
CI / Platform (Go) (pull_request) Successful in 3s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 12s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 7s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 22s
CI / Canvas (Next.js) (pull_request) Successful in 3s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 3s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
E2E Chat / detect-changes (pull_request) Successful in 18s
E2E API Smoke Test / detect-changes (pull_request) Successful in 21s
CI / Canvas Deploy Status (pull_request) Has been skipped
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 15s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 8s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 6s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 3s
sop-checklist / review-refire (pull_request_target) Has been skipped
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 16s
CI / all-required (pull_request) Successful in 4s
E2E Chat / E2E Chat (pull_request) Successful in 7s
gate-check-v3 / gate-check (pull_request_target) Successful in 13s
security-review / approved (pull_request_target) Failing after 8s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
qa-review / approved (pull_request_target) Failing after 12s
sop-checklist / all-items-acked (pull_request_target) Successful in 10s
sop-tier-check / tier-check (pull_request_target) Failing after 16s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m5s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m11s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 5s
_is_tier_low_pending_ok now inspects the status description for
[volume-skipped] and returns False, keeping the PR in queue until a
human splits bot-relay history. A partial comment view is NOT an
honest tier:low soft-fail — the gate stopped parsing before it could
verify acks.

Diff-proof: 53/53 gitea-merge-queue tests pass.

Refs: internal#219 §1, RFC#351
2026-06-06 17:26:42 +00:00
devops-engineer d768d8667b Merge PR #2364 via Gitea merge queue
ci-arm64-advisory / fast-checks (push) Waiting to run
CI / Detect changes (push) Successful in 7s
Block internal-flavored paths / Block forbidden paths (push) Successful in 9s
CI / Python Lint & Test (push) Successful in 7s
E2E API Smoke Test / detect-changes (push) Successful in 7s
E2E Chat / detect-changes (push) Successful in 7s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 7s
Handlers Postgres Integration / detect-changes (push) Successful in 8s
CI / Platform (Go) (push) Successful in 6s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 4s
CI / Shellcheck (E2E scripts) (push) Successful in 6s
CI / Canvas (Next.js) (push) Successful in 7s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 8s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 2s
review-check-tests / review-check.sh regression tests (push) Successful in 7s
E2E Chat / E2E Chat (push) Successful in 5s
CI / Canvas Deploy Status (push) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 4s
CI / all-required (push) Successful in 3s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Successful in 15s
Ops Scripts Tests / Ops scripts (unittest) (push) Successful in 55s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 1m5s
publish-workspace-server-image / build-and-push (push) Successful in 4m5s
publish-workspace-server-image / Production auto-deploy (push) Successful in 2m32s
Serialized merge by gitea-merge-queue after current-main, genuine approvals, and required CI checks were green.
2026-06-06 15:35:31 +00:00
devops-engineer 99d4a44250 Merge branch 'main' into feat/platform-agent-kind
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 4s
CI / Python Lint & Test (pull_request) Successful in 3s
E2E API Smoke Test / detect-changes (pull_request) Successful in 7s
CI / Detect changes (pull_request) Successful in 8s
CI / Canvas (Next.js) (pull_request) Successful in 2s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 6s
E2E Chat / detect-changes (pull_request) Successful in 16s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 4s
Harness Replays / detect-changes (pull_request) Successful in 6s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 8s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 6s
CI / Canvas Deploy Status (pull_request) Has been skipped
Check migration collisions / Migration version collision check (pull_request) Successful in 23s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
E2E Chat / E2E Chat (pull_request) Successful in 2s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 5s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
gate-check-v3 / gate-check (pull_request_target) Successful in 7s
qa-review / approved (pull_request_target) Failing after 5s
security-review / approved (pull_request_target) Failing after 4s
Harness Replays / Harness Replays (pull_request) Successful in 1s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 49s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (local) (pull_request) Successful in 1m7s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (pull_request) Successful in 5s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m2s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m15s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2m23s
CI / Platform (Go) (pull_request) Successful in 3m54s
CI / all-required (pull_request) Successful in 2s
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (pull_request) Failing after 4m57s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Failing after 8m3s
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Has been cancelled
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-tier-check / tier-check (pull_request_target) Failing after 9s
sop-checklist / all-items-acked (pull_request_target) Successful in 13s
2026-06-06 15:25:38 +00:00
Molecule AI Dev Engineer A (Kimi) 29d15cbe2c fix(merge-queue): paginate Gitea API list calls — issues, statuses (#2366/#588)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 6s
CI / Python Lint & Test (pull_request) Successful in 15s
CI / Detect changes (pull_request) Successful in 18s
E2E API Smoke Test / detect-changes (pull_request) Successful in 10s
E2E Chat / detect-changes (pull_request) Successful in 10s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 10s
CI / Platform (Go) (pull_request) Successful in 2s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 11s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 10s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 12s
CI / Canvas (Next.js) (pull_request) Successful in 1s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 3s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 4s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 5s
CI / all-required (pull_request) Successful in 2s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
gate-check-v3 / gate-check (pull_request_target) Failing after 7s
qa-review / approved (pull_request_target) Failing after 5s
security-review / approved (pull_request_target) Failing after 3s
E2E Chat / E2E Chat (pull_request) Successful in 6s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 4s
CI / Canvas Deploy Status (pull_request) Has been skipped
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 2s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
sop-tier-check / tier-check (pull_request_target) Failing after 4s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m23s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m17s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 5s
audit-force-merge / audit (pull_request_target) Successful in 4s
The merge queue used hard-coded limit=50 on list endpoints, silently
truncating enumeration when more than 50 open PRs or status checks exist.
This meant newer PRs could be invisible to the queue, and PRs with >50
status contexts would have incomplete check evaluation.

Changes:
- Add api_paginated() helper that loops through pages until a partial
  page is returned (indicating end of collection).
- list_queued_issues() and list_candidate_issues() now use pagination
  to enumerate ALL open PRs, not just the first 50.
- get_combined_status() /statuses enrichment now paginates to capture
  all status checks beyond the 50-entry cap.

All 52 gitea-merge-queue tests pass.

Refs: molecule-core#2366/#588, PM dispatch 01eaa317.
2026-06-06 14:40:32 +00:00
Molecule AI Dev Engineer A (Kimi) b1475b1f71 fix(ci): enforce official=true + current-head binding unconditionally in review-check.sh
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 9s
CI / Python Lint & Test (pull_request) Successful in 7s
CI / Detect changes (pull_request) Successful in 8s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 8s
E2E API Smoke Test / detect-changes (pull_request) Successful in 10s
E2E Chat / detect-changes (pull_request) Successful in 10s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 12s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
CI / Canvas (Next.js) (pull_request) Successful in 3s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 9s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 15s
CI / Platform (Go) (pull_request) Successful in 7s
E2E Chat / E2E Chat (pull_request) Successful in 4s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 8s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 6s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 16s
CI / Canvas Deploy Status (pull_request) Has been skipped
review-check-tests / review-check.sh regression tests (pull_request) Successful in 10s
CI / all-required (pull_request) Successful in 4s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 6s
sop-checklist / review-refire (pull_request_target) Has been skipped
gate-check-v3 / gate-check (pull_request_target) Failing after 13s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 6s
sop-checklist / all-items-acked (pull_request_target) Successful in 8s
security-review / approved (pull_request_target) Successful in 9s
qa-review / approved (pull_request_target) Successful in 13s
sop-tier-check / tier-check (pull_request_target) Failing after 9s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m9s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m4s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 11s
audit-force-merge / audit (pull_request_target) Successful in 9s
Addresses CR2 REQUEST_CHANGES on PR #2364:

1. Change select(.official != false) → select(.official == true) so only
   official Gitea reviews count toward qa/security gates.

2. Remove the REVIEW_CHECK_STRICT conditional and always require
   select(.commit_id == ) so stale approvals on old commits are
   rejected.

3. Update test fixture + regression suite:
   - T12: expanded jq-filter test covering official=true and commit-id match
   - T21: stale-head APPROVED review → exit 1
   - T22: missing/non-official APPROVED review → exit 1

All 44 tests pass locally.
2026-06-06 13:21:19 +00:00
Molecule AI Dev Engineer A (Kimi) b2d5f88f98 fix(ci): remove all comment-based approval bypasses from review-check.sh
Issue comments (both generic keywords APPROVED/LGTM/ACCEPTED and agent-
prefix comments [core-qa-agent]/[core-security-agent]) previously
satisfied the qa-review/security-review gate without an official Gitea
review. Both paths are bypasses:

1. Generic keywords: any team member could type 'APPROVED' in a comment.
2. Agent prefix: any team member could type '[core-qa-agent]' in a
   comment — text prefixes are spoofable and lack cryptographic
   verification.

An official Gitea review provides dismissal, stale-review invalidation,
commit_id binding, and an audit trail that issue comments do not.

Changes:
- Removed the entire issue-comments fallback section. Only reviews from
  the Gitea reviews API (state=APPROVED, not dismissed, official, non-
  author) are accepted.
- Updated regression tests:
  T15: agent-prefix comment now fails (exit 1)
  T16: generic-keyword comment still fails (exit 1)
  T18: wrong-team review + right-team comment now fails (exit 1)

Tests: 38 pass.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-06 13:21:19 +00:00
devops-engineer 31283a292a Merge PR #2362 via Gitea merge queue
ci-arm64-advisory / fast-checks (push) Waiting to run
Block internal-flavored paths / Block forbidden paths (push) Successful in 4s
CI / Python Lint & Test (push) Successful in 3s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (push) Has started running
publish-workspace-server-image / build-and-push (push) Has started running
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (push) Successful in 6s
Handlers Postgres Integration / detect-changes (push) Successful in 7s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (push) Successful in 5s
publish-workspace-server-image / Production auto-deploy (push) Blocked by required conditions
E2E Chat / detect-changes (push) Successful in 10s
E2E Staging Canvas (Playwright) / detect-changes (push) Successful in 11s
E2E API Smoke Test / detect-changes (push) Successful in 16s
CI / Detect changes (push) Successful in 18s
E2E Chat / E2E Chat (push) Successful in 3s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (push) Successful in 3s
Secret scan / Scan diff for credential-shaped strings (push) Successful in 6s
CI / Canvas (Next.js) (push) Successful in 2s
CI / Shellcheck (E2E scripts) (push) Successful in 3s
CI / Platform (Go) (push) Successful in 7s
E2E API Smoke Test / E2E API Smoke Test (push) Successful in 7s
CI / Canvas Deploy Status (push) Successful in 3s
CI / all-required (push) Successful in 2s
Ops Scripts Tests / Ops scripts (unittest) (push) Successful in 1m3s
Handlers Postgres Integration / Handlers Postgres Integration (push) Successful in 1m7s
Serialized merge by gitea-merge-queue after current-main, genuine approvals, and required CI checks were green.
2026-06-06 12:50:47 +00:00
devops-engineer 8ae3cb6917 Merge branch 'main' into feat/platform-agent-kind
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 7s
CI / Python Lint & Test (pull_request) Successful in 8s
CI / Detect changes (pull_request) Successful in 11s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 5s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 9s
Check migration collisions / Migration version collision check (pull_request) Successful in 20s
E2E API Smoke Test / detect-changes (pull_request) Successful in 17s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 4s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 3s
CI / Canvas (Next.js) (pull_request) Successful in 2s
E2E Chat / detect-changes (pull_request) Successful in 20s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 1s
Harness Replays / detect-changes (pull_request) Successful in 12s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 4s
qa-review / approved (pull_request_target) Failing after 5s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 6s
security-review / approved (pull_request_target) Failing after 4s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 4s
CI / Canvas Deploy Status (pull_request) Has been skipped
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 28s
Harness Replays / Harness Replays (pull_request) Successful in 1s
E2E Chat / E2E Chat (pull_request) Successful in 1s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (local) (pull_request) Successful in 34s
gate-check-v3 / gate-check (pull_request_target) Successful in 17s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (pull_request) Successful in 5s
sop-tier-check / tier-check (pull_request_target) Failing after 23s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 1m6s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 58s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m11s
CI / Platform (Go) (pull_request) Successful in 6m2s
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (pull_request) Failing after 6m14s
CI / all-required (pull_request) Successful in 2s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Failing after 9m12s
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Has been cancelled
2026-06-06 12:45:34 +00:00
Molecule AI Dev Engineer A (Kimi) bc7c45f3d6 fix(security): remove SOP_FAIL_OPEN bypass branches from sop-tier-check.sh (HIGH)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
CI / Detect changes (pull_request) Successful in 6s
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 12s
CI / Python Lint & Test (pull_request) Successful in 11s
E2E API Smoke Test / detect-changes (pull_request) Successful in 5s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 13s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 5s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 6s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 18s
E2E Chat / detect-changes (pull_request) Successful in 22s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 18s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 7s
qa-review / approved (pull_request_target) Failing after 7s
gate-check-v3 / gate-check (pull_request_target) Successful in 16s
security-review / approved (pull_request_target) Failing after 7s
sop-checklist / review-refire (pull_request_target) Has been skipped
CI / Platform (Go) (pull_request) Successful in 3s
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
CI / Canvas (Next.js) (pull_request) Successful in 4s
sop-checklist / na-declarations (pull_request) N/A: (none)
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
sop-tier-check / tier-check (pull_request_target) Failing after 8s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
E2E Chat / E2E Chat (pull_request) Successful in 2s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 1s
CI / Canvas Deploy Status (pull_request) Has been skipped
sop-checklist / all-items-acked (pull_request_target) Successful in 18s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 1s
CI / all-required (pull_request) Successful in 3s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m2s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Successful in 1m37s
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-tier-check / tier-check (pull_request_review) Failing after 11s
audit-force-merge / audit (pull_request_target) Successful in 6s
The workflow already removed SOP_FAIL_OPEN env (fix/core-ci-fail-closed,
2026-06-05), but the script still carried executable bypass branches that
would exit 0 when the env was set. Remove all of them:

- jq-install failure block
- token whoami failure block
- HEAD_SHA fetch failure block
- /orgs/{o}/teams fetch failure block
- /pulls/{n}/reviews fetch failure block

Every infra fault now fails closed (exit 1) with a loud ::error::,
exactly like a real SOP-6 violation.
2026-06-06 11:05:42 +00:00
core-devops 7b3fc0f2ef feat(workspace-server): add platform-agent participant kind (Phase 0)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 3s
CI / Python Lint & Test (pull_request) Successful in 3s
CI / Detect changes (pull_request) Successful in 5s
E2E Chat / detect-changes (pull_request) Successful in 9s
E2E API Smoke Test / detect-changes (pull_request) Successful in 14s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 9s
Harness Replays / detect-changes (pull_request) Successful in 6s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 17s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 14s
Check migration collisions / Migration version collision check (pull_request) Successful in 25s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 10s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 12s
CI / Canvas (Next.js) (pull_request) Successful in 5s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 4s
E2E Staging SaaS (full lifecycle) / pr-validate (pull_request) Successful in 30s
E2E Chat / E2E Chat (pull_request) Successful in 3s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 11s
qa-review / approved (pull_request_target) Failing after 10s
gate-check-v3 / gate-check (pull_request_target) Successful in 10s
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request) acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, local-postgres-e2
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-checklist / all-items-acked (pull_request_target) Successful in 5s
security-review / approved (pull_request_target) Failing after 13s
Harness Replays / Harness Replays (pull_request) Successful in 1s
CI / Canvas Deploy Status (pull_request) Has been skipped
sop-tier-check / tier-check (pull_request_target) Failing after 10s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 5s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 57s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (local) (pull_request) Successful in 1m24s
E2E Peer Visibility (literal MCP list_peers) / E2E Peer Visibility (pull_request) Successful in 11s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 1m57s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2m41s
CI / Platform (Go) (pull_request) Successful in 3m57s
CI / all-required (pull_request) Successful in 6s
E2E Staging External Runtime / E2E Staging External Runtime (pull_request) Successful in 5m24s
E2E Staging SaaS (full lifecycle) / E2E Staging SaaS (pull_request) Failing after 8m5s
E2E Staging SaaS (full lifecycle) / E2E Staging Platform Boot (pull_request) Failing after 1h2m14s
Introduce the 'kind' discriminator on workspaces ('workspace' default |
'platform') — the foundation for the org-level platform agent (RFC
docs/design/rfc-platform-agent.md). A 'platform' workspace is the org-level
concierge that sits at the org root and is the user's default A2A target.

- migration 20260606000000_workspaces_kind: adds kind column (default
  'workspace', backward-compatible), workspaces_kind_check, and a race-proof
  workspaces_platform_root_check (kind='platform' requires parent_id IS NULL)
  which structurally also guarantees one platform agent per org.
- models: Kind field on Workspace + RegisterPayload, KindWorkspace/KindPlatform
  consts, IsValidKind.
- Register: validates kind, carries it through the upsert via
  COALESCE(NULLIF(,''), …) so an unspecified kind defaults to 'workspace' on
  insert and never downgrades a platform row on re-register; maps the DB
  constraint violation to a friendly 409.
- tests: IsValidKind unit tests, Register invalid-kind (400) + platform-kind
  persist (200) sqlmock tests, and a real-Postgres integration test proving the
  constraint accepts a root platform agent and rejects a non-root one (sqlmock
  cannot evaluate a CHECK).

Backward-compatible and ships alone. No CanCommunicate change (platform == org
root reuses existing ancestor/descendant rules).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 03:37:36 -07:00
core-devops 79be721591 docs(rfc): org-level platform agent — tenant-resident concierge (design SSOT)
ci-arm64-advisory / fast-checks (pull_request) Waiting to run
Block internal-flavored paths / Block forbidden paths (pull_request) Successful in 11s
CI / Detect changes (pull_request) Successful in 14s
CI / Python Lint & Test (pull_request) Successful in 17s
E2E API Smoke Test / detect-changes (pull_request) Successful in 13s
Lint forbidden tenant-env keys / Scan for repo-host token write into tenant workspace surface (pull_request) Successful in 7s
CI / Canvas (Next.js) (pull_request) Successful in 3s
E2E Chat / detect-changes (pull_request) Successful in 14s
Lint forbidden tenant-env keys / Scan workspace_secrets writers for forbidden env keys (pull_request) Successful in 9s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 14s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 2s
E2E API Smoke Test / E2E API Smoke Test (pull_request) Successful in 2s
Lint shellcheck (arm64 pilot) / shellcheck-arm64 (pilot) (pull_request) Successful in 16s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 36s
CI / Platform (Go) (pull_request) Successful in 36s
CI / Canvas Deploy Status (pull_request) Has been skipped
qa-review / approved (pull_request_target) Failing after 4s
CI / all-required (pull_request) Successful in 9s
E2E Chat / E2E Chat (pull_request) Successful in 30s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 39s
security-review / approved (pull_request_target) Failing after 5s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m3s
gate-check-v3 / gate-check (pull_request_target) Successful in 41s
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Successful in 1s
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Successful in 2s
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, l
sop-checklist / na-declarations (pull_request) N/A: (none)
sop-tier-check / tier-check (pull_request_review) Has been cancelled
qa-review / approved (pull_request_review) Has been skipped
security-review / approved (pull_request_review) Has been skipped
sop-checklist / review-refire (pull_request_target) Has been skipped
sop-checklist / all-items-acked (pull_request_target) Successful in 9s
sop-tier-check / tier-check (pull_request_target) Successful in 12s
audit-force-merge / audit (pull_request_target) Successful in 9s
Architecture RFC for an always-on per-tenant platform agent that holds the
platform-management MCP natively, joins A2A as a first-class kind='platform'
participant at the org root, and is the user's default concierge. Captures the
SSOT mapping, the platform-as-root + re-parenting model, the two-MCP runtime,
and the server-side approval gate. Pre-implementation; needs CTO sign-off.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-06 03:01:18 -07:00
fullstack-engineer a60033dc16 test(handlers): add missing DB-error tests for Record and SessionSearch
E2E API Smoke Test / E2E API Smoke Test (pull_request) Blocked by required conditions
Handlers Postgres Integration / Handlers Postgres Integration (pull_request) Blocked by required conditions
Harness Replays / Harness Replays (pull_request) Blocked by required conditions
lint-continue-on-error-tracking / lint-continue-on-error-tracking (pull_request) Waiting to run
Lint curl status-code capture / Scan workflows for curl status-capture pollution (pull_request) Waiting to run
lint-mask-pr-atomicity / lint-mask-pr-atomicity (pull_request) Waiting to run
publish-runtime-autobump / bump-and-tag (pull_request) Waiting to run
MCP Stdio Transport Regression / MCP stdio with regular-file stdout (pull_request) Successful in 3m8s
publish-runtime-autobump / pr-validate (pull_request) Successful in 1m22s
Lint workflow YAML (Gitea-1.22.6-hostile shapes) / Lint workflow YAML for Gitea-1.22.6-hostile shapes (pull_request) Successful in 2m11s
Lint pre-flip continue-on-error / Verify continue-on-error flips have run-log proof (pull_request) Successful in 2m41s
lint-required-context-exists-in-bp / lint-required-context-exists-in-bp (pull_request) Successful in 3m6s
Ops Scripts Tests / Ops scripts (unittest) (pull_request) Failing after 1m59s
audit-force-merge / audit (pull_request) Waiting to run
E2E Staging Canvas (Playwright) / Canvas tabs E2E (pull_request) Blocked by required conditions
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 34s
CI / Shellcheck (E2E scripts) (pull_request) Successful in 43s
CI / Detect changes (pull_request) Successful in 1m13s
Handlers Postgres Integration / detect-changes (pull_request) Successful in 24s
E2E API Smoke Test / detect-changes (pull_request) Successful in 1m16s
Harness Replays / detect-changes (pull_request) Successful in 53s
E2E Staging Canvas (Playwright) / detect-changes (pull_request) Successful in 1m57s
Secret scan / Scan diff for credential-shaped strings (pull_request) Successful in 38s
Runtime PR-Built Compatibility / detect-changes (pull_request) Successful in 58s
qa-review / approved (pull_request) Failing after 48s
gate-check-v3 / gate-check (pull_request) Failing after 55s
lint-required-no-paths / lint-required-no-paths (pull_request) Successful in 1m51s
security-review / approved (pull_request) Failing after 41s
sop-tier-check / tier-check (pull_request) Successful in 40s
CI / Python Lint & Test (pull_request) Successful in 8m14s
CI / Canvas (Next.js) (pull_request) Successful in 19m47s
CI / Platform (Go) (pull_request) Successful in 21m16s
CI / all-required (pull_request) Successful in 21m27s
CI / Canvas Deploy Reminder (pull_request) Successful in 8s
sop-checklist / all-items-acked (pull_request) [info tier:low] acked: 0/7 — missing: comprehensive-testing, local-postgres-e2e, staging-smoke, +4 — body-unfilled: comprehensive-testing, l
- TestDelegationRecord_DBInsertFails: verifies 500 on activity_logs insert failure
- TestSessionSearch_DBError: verifies 500 on WITH query failure

Both are regression coverage for error paths that lacked test coverage.

🤖 Generated with [Claude Code](https://claude.ai/claude-code)
2026-05-15 07:38:15 +00:00
29 changed files with 1422 additions and 208 deletions
+59 -47
View File
@@ -268,6 +268,34 @@ def api(
return status, {"_raw": raw.decode("utf-8", errors="replace")}
def api_paginated(
method: str,
path: str,
*,
query: dict[str, str] | None = None,
page_size: int = 50,
) -> list[dict]:
"""Fetch all pages of a paginated Gitea list endpoint.
Gitea paginates with `page` (1-indexed) and `limit`. We loop until a
page returns fewer than `page_size` items, indicating the end.
"""
results: list[dict] = []
page = 1
while True:
page_query = dict(query or {})
page_query["page"] = str(page)
page_query["limit"] = str(page_size)
_, body = api(method, path, query=page_query)
if not isinstance(body, list):
raise ApiError(f"{path} paginated response not list")
results.extend(body)
if len(body) < page_size:
break
page += 1
return results
def required_contexts(raw: str) -> list[str]:
return [part.strip() for part in raw.split(",") if part.strip()]
@@ -300,17 +328,18 @@ def _is_tier_low_pending_ok(
) -> bool:
"""Return True if tier:low PR can tolerate sop-checklist pending state.
Per sop-checklist-config.yaml tier_failure_mode, tier:low uses soft-fail:
sop-checklist posts state=pending when acks are satisfied (missing
manager/ceo acks are informational only). The queue should accept
pending instead of waiting for success.
GENERIC PENDING-AS-GREEN REMOVED (Researcher + CR2 RC on #2368):
The prior soft-fail accepted ANY pending sop-checklist for tier:low,
which allowed required checks to pass without genuine verification.
Pending required sop-checklist must now always HOLD and appear in
missing_or_bad. This function is retained as a policy hook but
currently always returns False so pending never counts green.
If a positively identifiable genuine soft-fail state is defined in
future (e.g., a specific check-run conclusion), implement it here
with strict positive identification — never default to pass.
"""
if "tier:low" not in pr_labels:
return False
if "sop-checklist" not in context:
return False
status = latest_statuses.get(context) or {}
return status_state(status) == "pending"
return False
def required_contexts_green(
@@ -659,32 +688,23 @@ def get_combined_status(sha: str) -> dict:
"""Combined status + all individual statuses for `sha`.
The /status endpoint caps the `statuses` array at 30 entries (Gitea
default page size), so we fetch the full list via /statuses with a
higher limit. The combined `state` still comes from /status.
default page size), so we fetch the full list via /statuses. The combined
`state` still comes from /status.
Fail-closed: the PRIMARY /status fetch must succeed. If it raises, the
error propagates so the caller skips this PR this tick (we never treat a
failed status fetch as green — dev-sop "no fail-open"). Only the SECONDARY
/statuses enrichment (which merely extends the per-context list beyond the
30-entry cap) is best-effort; if it fails we still have the combined set.
Fail-closed: BOTH the PRIMARY /status fetch AND the SECONDARY /statuses
enrichment must succeed. If either raises, the error propagates so the
caller skips this PR this tick (we never treat a failed status fetch as
green — dev-sop "no fail-open"). A paginated /statuses error must NOT
silently degrade to an incomplete status set.
"""
_, combined = api("GET", f"/repos/{OWNER}/{NAME}/commits/{sha}/status")
if not isinstance(combined, dict):
raise ApiError(f"status for {sha} response not object")
combined_statuses: list[dict] = combined.get("statuses") or []
try:
_, all_statuses_raw = api(
"GET",
f"/repos/{OWNER}/{NAME}/commits/{sha}/statuses",
query={"limit": "50"},
)
if isinstance(all_statuses_raw, list):
all_statuses: list[dict] = list(all_statuses_raw)
else:
all_statuses = []
except (ApiError, urllib.error.URLError, TimeoutError, OSError) as exc:
sys.stderr.write(f"::warning::could not fetch full statuses list for {sha[:8]}: {exc}\n")
all_statuses = []
all_statuses = api_paginated(
"GET",
f"/repos/{OWNER}/{NAME}/commits/{sha}/statuses",
)
# Build latest per context: process combined (ascending→reverse=newest
# first), then fill gaps from all_statuses (already newest-first).
latest: dict[str, dict] = {}
@@ -701,19 +721,15 @@ def get_combined_status(sha: str) -> dict:
def list_queued_issues() -> list[dict]:
_, body = api(
return api_paginated(
"GET",
f"/repos/{OWNER}/{NAME}/issues",
query={
"state": "open",
"type": "pulls",
"labels": QUEUE_LABEL,
"limit": "50",
},
)
if not isinstance(body, list):
raise ApiError("queued issues response not list")
return body
def list_candidate_issues(*, auto_discover: bool) -> list[dict]:
@@ -727,18 +743,14 @@ def list_candidate_issues(*, auto_discover: bool) -> list[dict]:
"""
if not auto_discover:
return list_queued_issues()
_, body = api(
return api_paginated(
"GET",
f"/repos/{OWNER}/{NAME}/issues",
query={
"state": "open",
"type": "pulls",
"limit": "50",
},
)
if not isinstance(body, list):
raise ApiError("candidate issues response not list")
return body
def get_pull(pr_number: int) -> dict:
@@ -1098,18 +1110,18 @@ def main() -> int:
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.
# FAIL-CLOSED: API errors are not "transient success" — they mean
# the queue could not evaluate merge state. Returning 0 hides
# persistent infra issues (auth drift, endpoint outages) from
# operators. Return 1 so the cron job surfaces red and paging fires.
sys.stderr.write(f"::error::queue API error: {exc}\n")
return 0
return 1
except urllib.error.URLError as exc:
sys.stderr.write(f"::error::queue network error: {exc}\n")
return 0
return 1
except TimeoutError as exc:
sys.stderr.write(f"::error::queue timeout: {exc}\n")
return 0
return 1
if __name__ == "__main__":
@@ -546,16 +546,24 @@ def verify_flip(flip: dict, branch: str, n: int) -> dict:
shas = recent_commits_on_branch(branch, n)
if not shas:
result["warnings"].append(
f"no recent commits on {branch} (cannot verify flip)"
)
result["masked_runs"].append({
"sha": "",
"status": "unverified",
"target_url": "",
"samples": [f"no recent commits on {branch} — cannot verify flip"],
})
return result
for sha in shas:
try:
status_doc = combined_status(sha)
except ApiError as e:
result["warnings"].append(f"combined-status for {sha}: {e}")
result["masked_runs"].append({
"sha": sha,
"status": "error",
"target_url": "",
"samples": [f"combined-status API error: {e}"],
})
continue
statuses = status_doc.get("statuses") or []
# First entry matching the context name. Newest SHAs come
@@ -582,6 +590,17 @@ def verify_flip(flip: dict, branch: str, n: int) -> dict:
"target_url": target_url,
"samples": ["[log unavailable; status itself is " + state + "]"],
})
elif state == "success":
# Fail-closed: unreadable log on a success status is a
# potential Quirk #10 mask (continue-on-error hiding real
# failures). We cannot verify it's clean, so treat as
# masked rather than allowing the flip.
result["masked_runs"].append({
"sha": sha,
"status": state,
"target_url": target_url,
"samples": ["[log unavailable; cannot verify status is genuine — treat as masked]"],
})
break
samples = grep_fail_markers(log_text)
if state in ("failure", "error"):
@@ -605,10 +624,12 @@ def verify_flip(flip: dict, branch: str, n: int) -> dict:
break
if result["checked_commits"] == 0:
result["warnings"].append(
f"no runs of {target_context!r} found in the last {n} commits on "
f"{branch} — cannot verify; allowing flip with warning"
)
result["masked_runs"].append({
"sha": "",
"status": "unverified",
"target_url": "",
"samples": [f"no runs of {target_context!r} found in the last {n} commits on {branch} — cannot verify flip"],
})
return result
+14 -53
View File
@@ -197,19 +197,15 @@ if [ "$HTTP_CODE" != "200" ]; then
exit 1
fi
# Filter: state=APPROVED, not-dismissed, non-author. Optionally strict-mode
# adds commit_id==head.sha (off by default; see header).
# Filter: state=APPROVED, official=true, not-dismissed, non-author,
# commit_id matches current PR head. All conditions are mandatory.
JQ_FILTER='.[]
| select(.state == "APPROVED")
| select(.official == true)
| select(.dismissed != true)
| select(.official != false)
| select(.user.login != $author)'
if [ "${REVIEW_CHECK_STRICT:-}" = "1" ]; then
JQ_FILTER="${JQ_FILTER}
| select(.commit_id == \$head)"
fi
JQ_FILTER="${JQ_FILTER}
| .user.login"
| select(.user.login != $author)
| select(.commit_id == $head)
| .user.login'
REVIEW_CANDIDATES=$(jq -r --arg author "$PR_AUTHOR" --arg head "$PR_HEAD_SHA" "$JQ_FILTER" "$REVIEWS_JSON" | sort -u)
debug "candidate non-author approvers: $(echo "$REVIEW_CANDIDATES" | tr '\n' ' ')"
@@ -241,49 +237,14 @@ if [ -z "$REVIEW_CANDIDATES" ]; then
fi
# --- Fallback/extension (internal#348): check issue comments for agent-approval ---
# core-qa-agent and core-security-agent can approve via issue comments. Always
# include comment candidates, even if the reviews API returned approvals for a
# different team; team membership below is the authoritative filter.
COMMENT_CANDIDATES=""
AGENT_PATTERN=""
case "$TEAM" in
qa) AGENT_PATTERN="\\[core-qa-agent\\]" ;;
security) AGENT_PATTERN="\\[core-security-agent\\]" ;;
esac
HTTP_CODE=$(curl -sS -o "$COMMENTS_JSON" -w '%{http_code}' \
-K "$CURL_AUTH_FILE" "${API}/repos/${OWNER}/${NAME}/issues/${PR_NUMBER}/comments")
debug "GET /issues/${PR_NUMBER}/comments → HTTP ${HTTP_CODE}"
if [ "$HTTP_CODE" = "200" ]; then
# JQ expression: select non-author comments that match either the
# agent-prefix pattern (case-insensitive) OR a generic approval keyword.
JQ_APPROVALS='
.[] |
select(.user.login != $author) |
. as $cmt |
if ($agent_pattern | length) > 0 and ($cmt.body // "" | test($agent_pattern; "i")) then
$cmt.user.login
elif ($cmt.body // "" | test("\\b(APPROVED|LGTM|ACCEPTED)\\b"; "i")) then
$cmt.user.login
else
empty
end
'
COMMENT_CANDIDATES=$(jq -r \
--arg author "$PR_AUTHOR" \
--arg agent_pattern "$AGENT_PATTERN" \
"$JQ_APPROVALS" \
"$COMMENTS_JSON" 2>/dev/null | sort -u)
debug "comment-based approval candidates: $(echo "$COMMENT_CANDIDATES" | tr '\n' ' ')"
if [ -n "$COMMENT_CANDIDATES" ]; then
echo "::notice::${TEAM}-review: found $(echo "$COMMENT_CANDIDATES" | wc -w | xargs) comment-based approval candidate(s) — verifying team membership..."
fi
else
debug "could not fetch issue comments (HTTP ${HTTP_CODE})"
fi
CANDIDATES=$(printf '%s\n%s\n' "$REVIEW_CANDIDATES" "$COMMENT_CANDIDATES" | sed '/^$/d' | sort -u)
# --- COMMENT APPROVAL REMOVED (security hardening) ---
# Previous versions accepted issue comments containing generic approval
# keywords (APPROVED/LGTM/ACCEPTED) or agent prefixes ([core-qa-agent],
# [core-security-agent]) as satisfying the gate. Both paths are bypasses:
# a comment lacks the audit trail, dismissal, stale-review invalidation,
# and commit_id binding that an official Gitea review provides.
# Only APPROVED reviews from the Gitea reviews API count.
CANDIDATES="$REVIEW_CANDIDATES"
if [ -z "${CANDIDATES:-}" ]; then
echo "::error::${TEAM}-review awaiting non-author APPROVE from ${TEAM} team (no candidates from reviews API or issue comments)"
+2 -26
View File
@@ -48,7 +48,6 @@ set -euo pipefail
# workflow-level jq install can fail on runners with network restrictions
# (GitHub releases not reachable from some runner networks — infra#241
# follow-up). This fallback is idempotent — no-op when jq is already on PATH.
# SOP_FAIL_OPEN=1 makes this always exit 0 so CI never blocks on jq absence.
if ! command -v jq >/dev/null 2>&1; then
echo "::notice::jq not found on PATH — attempting install..."
_jq_installed="no"
@@ -67,12 +66,6 @@ if ! command -v jq >/dev/null 2>&1; then
if ! command -v jq >/dev/null 2>&1; then
echo "::error::jq installation failed — apt-get and GitHub binary both failed."
echo "::error::sop-tier-check requires jq for all JSON API parsing."
# SOP_FAIL_OPEN=1 is set in the workflow step's env — makes script always
# exit 0 so CI never blocks. The SOP-6 tier review gate remains enforced.
if [ "${SOP_FAIL_OPEN:-}" = "1" ]; then
echo "::warning::SOP_FAIL_OPEN=1 — exiting 0 so CI does not block."
exit 0
fi
exit 1
fi
fi
@@ -101,15 +94,10 @@ echo "::notice::tier-check start: repo=$OWNER/$NAME pr=$PR_NUMBER author=$PR_AUT
# cause the script to exit prematurely when the token is empty/invalid — the
# if check below handles that case gracefully. Without || true, a 401 from an
# empty/invalid token causes jq to exit 1, triggering set -e and exiting the
# entire script before SOP_FAIL_OPEN can be evaluated (the check is in the jq-
# install block; if jq is already on PATH, that block is skipped entirely).
# entire script before the error can be logged.
WHOAMI=$(curl -sS -H "$AUTH" "${API}/user" | jq -r '.login // ""') || true
if [ -z "$WHOAMI" ]; then
echo "::error::GITEA_TOKEN cannot resolve a user via /api/v1/user — check the token scope and that the secret is wired correctly."
if [ "${SOP_FAIL_OPEN:-}" = "1" ]; then
echo "::warning::SOP_FAIL_OPEN=1 — exiting 0 so CI does not block."
exit 0
fi
exit 1
fi
echo "::notice::token resolves to user: $WHOAMI"
@@ -119,10 +107,6 @@ echo "::notice::token resolves to user: $WHOAMI"
HEAD_SHA=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}" | jq -r '.head.sha // ""') || true
if [ -z "$HEAD_SHA" ]; then
echo "::error::Failed to fetch PR head SHA — token may be invalid."
if [ "${SOP_FAIL_OPEN:-}" = "1" ]; then
echo "::warning::SOP_FAIL_OPEN=1 — exiting 0 so CI does not block."
exit 0
fi
exit 1
fi
debug "pr-head-sha=$HEAD_SHA"
@@ -215,10 +199,6 @@ if [ "${SOP_DEBUG:-}" = "1" ]; then
fi
if [ "$_HTTP_EXIT" -ne 0 ] || [ "$HTTP_CODE" != "200" ]; then
echo "::error::GET /orgs/${OWNER}/teams failed (curl exit=$_HTTP_EXIT HTTP=$HTTP_CODE) — token may lack read:org scope or be invalid."
if [ "${SOP_FAIL_OPEN:-}" = "1" ]; then
echo "::warning::SOP_FAIL_OPEN=1 — exiting 0 so CI does not block."
exit 0
fi
exit 1
fi
@@ -265,17 +245,13 @@ done
# 5. Read approving reviewers. set +e disables set -e temporarily so that curl
# failures (e.g. empty/invalid token → HTTP 401) do not abort the script before
# SOP_FAIL_OPEN is evaluated. set -e is restored immediately after.
# set -e is restored immediately after.
set +e
REVIEWS=$(curl -sS -H "$AUTH" "${API}/repos/${OWNER}/${NAME}/pulls/${PR_NUMBER}/reviews")
_REVIEWS_EXIT=$?
set -e
if [ $_REVIEWS_EXIT -ne 0 ] || [ -z "$REVIEWS" ]; then
echo "::error::Failed to fetch reviews (curl exit=$_REVIEWS_EXIT) — token may be invalid or unreachable."
if [ "${SOP_FAIL_OPEN:-}" = "1" ]; then
echo "::warning::SOP_FAIL_OPEN=1 — exiting 0 so CI does not block."
exit 0
fi
exit 1
fi
APPROVERS=$(echo "$REVIEWS" | jq -r --arg head_sha "$HEAD_SHA" '[.[] | select(.state=="APPROVED" and .commit_id == $head_sha) | .user.login] | unique | .[]') || true
+14 -3
View File
@@ -689,8 +689,8 @@ def reap_branch(
shas = list_recent_commit_shas(branch, limit)
except ApiError as e:
print(
"::warning::status-reaper skipped this tick because the "
f"commit list could not be read after retries: {e}"
"::error::status-reaper cannot run: commit-list API failed "
f"after retries: {e}"
)
return {
"scanned_shas": 0,
@@ -704,6 +704,7 @@ def reap_branch(
"compensated_cancelled_push": 0,
"preserved_pr_without_push_success": 0,
"compensated_per_sha": {},
"sha_api_errors": 0,
"skipped": True,
"skip_reason": "commit-list-api-error",
}
@@ -720,6 +721,7 @@ def reap_branch(
"compensated_cancelled_push": 0,
"preserved_pr_without_push_success": 0,
"compensated_per_sha": {},
"sha_api_errors": 0,
}
for sha in shas:
@@ -731,8 +733,9 @@ def reap_branch(
try:
combined = get_combined_status(sha)
except ApiError as e:
aggregate["sha_api_errors"] += 1
print(
f"::warning::get_combined_status({sha[:10]}) failed; "
f"::error::get_combined_status({sha[:10]}) failed; "
f"skipping this SHA: {e}"
)
continue
@@ -819,6 +822,14 @@ def main() -> int:
sort_keys=True,
)
)
# Observability: infra-failure → red. If the commit list could not be
# read or any per-SHA status fetch failed, the tick is incomplete and
# must be observable as a failure (non-zero exit) so the cron bot or
# runner surface alerts.
if counters.get("skipped"):
return 1
if counters.get("sha_api_errors", 0) > 0:
return 1
return 0
+17 -6
View File
@@ -109,23 +109,34 @@ class Handler(http.server.BaseHTTPRequestHandler):
return self._json(200, [{
"state": "APPROVED",
"dismissed": True,
"official": True,
"user": {"login": "core-devops"},
"commit_id": "abc1234",
"commit_id": "deadbeef0000111122223333444455556666",
}])
if sc == "T3_reviews_approved_non_author":
return self._json(200, [
{"state": "CHANGES_REQUESTED", "dismissed": False, "user": {"login": "bob"}, "commit_id": "abc1234"},
{"state": "APPROVED", "dismissed": False, "user": {"login": "core-devops"}, "commit_id": "abc1234"},
{"state": "CHANGES_REQUESTED", "dismissed": False, "official": True, "user": {"login": "bob"}, "commit_id": "deadbeef0000111122223333444455556666"},
{"state": "APPROVED", "dismissed": False, "official": True, "user": {"login": "core-devops"}, "commit_id": "deadbeef0000111122223333444455556666"},
])
if sc == "T19_ai_sop_ack_approved":
# ai-sop-ack member submitted APPROVED review — must NOT count
# toward qa-review (team_id=20) or security-review (team_id=21).
return self._json(200, [
{"state": "APPROVED", "dismissed": False, "user": {"login": "ai-reviewer"}, "commit_id": "abc1234"},
{"state": "APPROVED", "dismissed": False, "official": True, "user": {"login": "ai-reviewer"}, "commit_id": "deadbeef0000111122223333444455556666"},
])
# Default: one non-author APPROVED
if sc == "T21_stale_head_approved":
# APPROVED review but on an old commit (stale head) → must be rejected
return self._json(200, [
{"state": "APPROVED", "dismissed": False, "official": True, "user": {"login": "core-devops"}, "commit_id": "oldsha0000000000000000000000000000"},
])
if sc == "T22_missing_official":
# APPROVED review with no official field → must be rejected
return self._json(200, [
{"state": "APPROVED", "dismissed": False, "user": {"login": "core-devops"}, "commit_id": "deadbeef0000111122223333444455556666"},
])
# Default: one non-author APPROVED (current head, official)
return self._json(200, [
{"state": "APPROVED", "dismissed": False, "user": {"login": "core-devops"}, "commit_id": "abc1234"},
{"state": "APPROVED", "dismissed": False, "official": True, "user": {"login": "core-devops"}, "commit_id": "deadbeef0000111122223333444455556666"},
])
# GET /repos/{owner}/{name}/issues/{pr_number}/comments
@@ -2,6 +2,8 @@ import importlib.util
import sys
from pathlib import Path
import pytest
SCRIPT = Path(__file__).resolve().parents[1] / "gitea-merge-queue.py"
spec = importlib.util.spec_from_file_location("gitea_merge_queue", SCRIPT)
mq = importlib.util.module_from_spec(spec)
@@ -44,6 +46,35 @@ def test_required_contexts_green_rejects_missing_and_pending():
]
def test_required_contexts_green_rejects_volume_skipped_even_for_tier_low():
"""volume-skipped pending is a partial view, not a genuine soft-fail.
Per sop-checklist.py:1179-1187, volume_skipped posts pending with a
'[volume-skipped]' prefix. The merge queue must NOT treat this as an
acceptable soft-fail for tier:low — the gate did not finish evaluating.
"""
latest = mq.latest_statuses_by_context([
{"context": "CI / all-required (pull_request)", "status": "success"},
{
"context": "sop-checklist / all-items-acked (pull_request)",
"status": "pending",
"description": "[volume-skipped] comment-cap=1000 hit; please file ...",
},
])
ok, missing_or_bad = mq.required_contexts_green(
latest,
[
"CI / all-required (pull_request)",
"sop-checklist / all-items-acked (pull_request)",
],
pr_labels={"tier:low"},
)
assert ok is False
assert "sop-checklist / all-items-acked (pull_request)=pending" in missing_or_bad
def test_choose_next_pr_sorts_by_queue_label_timestamp_then_number():
issues = [
{
@@ -532,6 +563,61 @@ def test_status_fetch_failure_is_fail_closed(monkeypatch):
assert merged["called"] is False
# --------------------------------------------------------------------------
# Pagination: api_paginated loops pages and is fail-closed on page errors
# --------------------------------------------------------------------------
def test_api_paginated_loops_pages_until_partial(monkeypatch):
"""api_paginated fetches all pages and stops when a page is < page_size."""
calls = []
def fake_api(method, path, *, query=None, **kw):
page = int((query or {}).get("page", "1"))
limit = int((query or {}).get("limit", "50"))
calls.append((page, limit))
if page == 1:
return 200, [{"number": 1}, {"number": 2}]
if page == 2:
return 200, [{"number": 3}]
return 200, []
monkeypatch.setattr(mq, "api", fake_api)
results = mq.api_paginated("GET", "/repos/o/r/issues", page_size=2)
assert len(results) == 3
assert results[0]["number"] == 1
assert results[1]["number"] == 2
assert results[2]["number"] == 3
assert calls == [(1, 2), (2, 2)]
def test_api_paginated_raises_on_non_list(monkeypatch):
"""A page that returns a dict instead of list is an error."""
def fake_api(method, path, *, query=None, **kw):
return 200, {"message": "not found"}
monkeypatch.setattr(mq, "api", fake_api)
with pytest.raises(mq.ApiError):
mq.api_paginated("GET", "/repos/o/r/issues")
def test_get_combined_status_propagates_paginated_statuses_error(monkeypatch):
"""If the paginated /statuses enrichment raises, the error propagates
(fail-closed — we do NOT silently fall back to an incomplete status set)."""
monkeypatch.setattr(mq, "OWNER", "o")
monkeypatch.setattr(mq, "NAME", "r")
def fake_api(method, path, *, query=None, **kw):
if path.endswith("/status"):
return 200, {"state": "success", "statuses": [{"context": "c1", "status": "success", "id": 1}]}
if path.endswith("/statuses"):
raise mq.ApiError("GET /statuses -> HTTP 502")
raise mq.ApiError(f"unexpected {path}")
monkeypatch.setattr(mq, "api", fake_api)
with pytest.raises(mq.ApiError, match="GET /statuses"):
mq.get_combined_status("a" * 40)
def test_process_once_holds_tick_when_branch_protection_unavailable(monkeypatch):
"""BP enumeration failure → HOLD the whole tick (no merge, rc 0)."""
merged = {"called": False}
@@ -320,10 +320,10 @@ class TestVerifyFlip(unittest.TestCase):
self.assertEqual(len(verdict["fail_runs"]), 1)
self.assertEqual(verdict["fail_runs"][0]["status"], "failure")
def test_unreadable_log_warns_not_blocks(self):
# Acceptance test #5: log fetch 404 (None) → warn, not block.
# Status is `success`, log is None — we can't tell, so we warn
# and allow.
def test_unreadable_log_on_success_blocks(self):
# Fail-closed: log fetch 404 (None) on a success status is a
# potential Quirk #10 mask — we cannot verify it's genuine, so
# we block the flip rather than allowing it.
with mock.patch.object(lpfc, "recent_commits_on_branch", return_value=["sha1"]):
with mock.patch.object(
lpfc, "combined_status",
@@ -332,7 +332,8 @@ class TestVerifyFlip(unittest.TestCase):
with mock.patch.object(lpfc, "fetch_log", return_value=None):
verdict = lpfc.verify_flip(FLIP_FIXTURE, "main", 5)
self.assertEqual(verdict["fail_runs"], [])
self.assertEqual(verdict["masked_runs"], [])
self.assertEqual(len(verdict["masked_runs"]), 1)
self.assertIn("log unavailable", verdict["masked_runs"][0]["samples"][0])
self.assertTrue(any("log unavailable" in w for w in verdict["warnings"]))
def test_unreadable_log_with_failure_status_still_blocks(self):
@@ -349,9 +350,9 @@ class TestVerifyFlip(unittest.TestCase):
self.assertEqual(len(verdict["fail_runs"]), 1)
self.assertIn("log unavailable", verdict["fail_runs"][0]["samples"][0])
def test_zero_runs_history_warns_allows(self):
# No commits with a matching context — newly added workflow.
# Allow with warning.
def test_zero_runs_history_blocks(self):
# No commits with a matching context — cannot verify the flip.
# Fail-closed: treat as masked rather than allowing.
with mock.patch.object(lpfc, "recent_commits_on_branch", return_value=["sha1", "sha2"]):
with mock.patch.object(
lpfc, "combined_status",
@@ -360,17 +361,32 @@ class TestVerifyFlip(unittest.TestCase):
verdict = lpfc.verify_flip(FLIP_FIXTURE, "main", 5)
self.assertEqual(verdict["checked_commits"], 0)
self.assertEqual(verdict["fail_runs"], [])
self.assertEqual(verdict["masked_runs"], [])
self.assertTrue(any("no runs of" in w for w in verdict["warnings"]))
self.assertEqual(len(verdict["masked_runs"]), 1)
self.assertIn("cannot verify flip", verdict["masked_runs"][0]["samples"][0])
def test_zero_commits_warns_allows(self):
# Empty branch (newly created repo, e.g.). Allow with warning.
def test_zero_commits_blocks(self):
# Empty branch (newly created repo, e.g.). Fail-closed: block.
with mock.patch.object(lpfc, "recent_commits_on_branch", return_value=[]):
verdict = lpfc.verify_flip(FLIP_FIXTURE, "main", 5)
self.assertEqual(verdict["checked_commits"], 0)
self.assertEqual(verdict["fail_runs"], [])
self.assertEqual(verdict["masked_runs"], [])
self.assertTrue(any("no recent commits" in w for w in verdict["warnings"]))
self.assertEqual(len(verdict["masked_runs"]), 1)
self.assertIn("cannot verify flip", verdict["masked_runs"][0]["samples"][0])
def test_combined_status_api_error_blocks(self):
# Fail-closed: combined_status ApiError means the check history is
# unreadable — we cannot verify the flip, so block as masked.
with mock.patch.object(lpfc, "recent_commits_on_branch", return_value=["sha1"]):
with mock.patch.object(
lpfc, "combined_status",
side_effect=lpfc.ApiError("GET /statuses/sha → HTTP 500"),
):
verdict = lpfc.verify_flip(FLIP_FIXTURE, "main", 5)
self.assertEqual(verdict["checked_commits"], 0)
self.assertEqual(verdict["fail_runs"], [])
# One masked_run from the ApiError, one from zero checked_commits.
self.assertEqual(len(verdict["masked_runs"]), 2)
self.assertIn("API error", verdict["masked_runs"][0]["samples"][0])
# --------------------------------------------------------------------------
+53 -19
View File
@@ -14,10 +14,17 @@
# T9 — team membership probe → 403 (token not in team) → script exits 1 (fail closed)
# T10 — CURL_AUTH_FILE created with mode 600 and correct header content
# T11 — bash syntax check (bash -n passes)
# T12 — jq filter: non-author APPROVED → in candidate list; dismissed → excluded
# T12 — jq filter: non-author APPROVED official current-head → in candidate list; dismissed → excluded
# T13 — missing required env GITEA_TOKEN → exits 1 with error
# T14 — non-default-base PR exits 0 without requiring review
# T18wrong-team review candidate does not block right-team comment approval
# T15comment agent-prefix approval → exit 1
# T16 — comment generic keyword approval → exit 1
# T17 — comments with no approval keywords → exit 1
# T18 — wrong-team review + right-team comment → exit 1
# T19 — ai-sop-ack APPROVED review excluded from qa-review gate
# T20 — ai-sop-ack APPROVED review excluded from security-review gate
# T21 — stale-head APPROVED review → exit 1 (commit_id mismatch)
# T22 — missing/non-official APPROVED review → exit 1 (official != true)
#
# Hostile-self-review (per feedback_assert_exact_not_substring):
# this test MUST FAIL if the script is absent. Verified by running
@@ -319,41 +326,50 @@ assert_file_contains "T10b printf header format (CURL_AUTH_FILE content)" "$T10_
assert_file_contains "T10c 'header =' curl-config syntax" "$T10_AUTHFILE" 'header = "Authorization: token '
rm -f "$T10_AUTHFILE"
# T12 — jq filter: non-author APPROVED included, dismissed excluded
# T12 — jq filter: non-author APPROVED official current-head included; dismissed/stale/missing-official excluded
echo
echo "== T12 jq filter =="
# These are tested indirectly via T3 and T6 above, but let's also test
# the jq expression directly.
JQ_FILTER='.[]
| select(.state == "APPROVED")
| select(.official == true)
| select(.dismissed != true)
| select(.user.login != "alice")
| select(.commit_id == $head)
| .user.login'
T12_INPUT='[{"state":"APPROVED","dismissed":false,"user":{"login":"core-devops"}},{"state":"CHANGES_REQUESTED","dismissed":false,"user":{"login":"bob"}},{"state":"APPROVED","dismissed":false,"user":{"login":"alice"}},{"state":"APPROVED","dismissed":true,"user":{"login":"carol"}}]'
T12_INPUT='[{"state":"APPROVED","official":true,"dismissed":false,"commit_id":"deadbeef0000111122223333444455556666","user":{"login":"core-devops"}},{"state":"CHANGES_REQUESTED","official":true,"dismissed":false,"commit_id":"deadbeef0000111122223333444455556666","user":{"login":"bob"}},{"state":"APPROVED","official":true,"dismissed":false,"commit_id":"deadbeef0000111122223333444455556666","user":{"login":"alice"}},{"state":"APPROVED","official":true,"dismissed":true,"commit_id":"deadbeef0000111122223333444455556666","user":{"login":"carol"}},{"state":"APPROVED","official":false,"dismissed":false,"commit_id":"deadbeef0000111122223333444455556666","user":{"login":"dave"}},{"state":"APPROVED","official":true,"dismissed":false,"commit_id":"oldsha0000000000000000000000000000","user":{"login":"eve"}}]'
JQ_CMD=$(command -v jq 2>/dev/null || echo /tmp/jq)
T12_CANDIDATES=$(echo "$T12_INPUT" | "$JQ_CMD" -r "$JQ_FILTER" 2>/dev/null | sort -u)
assert_contains "T12 jq: core-devops (non-author APPROVED) in candidates" "core-devops" "$T12_CANDIDATES"
T12_CANDIDATES=$(echo "$T12_INPUT" | "$JQ_CMD" -r --arg head "deadbeef0000111122223333444455556666" "$JQ_FILTER" 2>/dev/null | sort -u)
assert_contains "T12 jq: core-devops (non-author APPROVED official current-head) in candidates" "core-devops" "$T12_CANDIDATES"
assert_eq "T12 jq: alice (author) NOT in candidates" "" "$(echo "$T12_CANDIDATES" | grep '^alice$' || true)"
assert_eq "T12 jq: carol (dismissed) NOT in candidates" "" "$(echo "$T12_CANDIDATES" | grep '^carol$' || true)"
assert_eq "T12 jq: dave (official=false) NOT in candidates" "" "$(echo "$T12_CANDIDATES" | grep '^dave$' || true)"
assert_eq "T12 jq: eve (stale head) NOT in candidates" "" "$(echo "$T12_CANDIDATES" | grep '^eve$' || true)"
# T15 — comment-based approval via agent prefix pattern → exit 0
# T15 — comment-based approval via agent prefix pattern → exit 1
# SECURITY: agent-prefix comments are also removed. A text prefix in an
# issue comment is spoofable (any team member can type "[core-qa-agent]")
# and lacks the audit trail of an official Gitea review.
echo
echo "== T15 comment agent-prefix approval =="
T15_OUT=$(run_review_check "T15_comments_agent_approval")
T15_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T15 exit code 0 (agent-comment approval + team member)" "0" "$T15_RC"
assert_contains "T15 comment fallback notice" "comment-based approval" "$T15_OUT"
assert_contains "T15 core-qa-agent APPROVED" "APPROVED by core-qa-agent" "$T15_OUT"
assert_eq "T15 exit code 1 (agent-prefix comment rejected — not an official review)" "1" "$T15_RC"
assert_contains "T15 no candidates error" "no candidates from reviews API or issue comments" "$T15_OUT"
# T16 — comment-based approval via generic APPROVED keyword → exit 0
# T16 — comment-based approval via generic APPROVED keyword → exit 1
# SECURITY: generic keywords (APPROVED/LGTM/ACCEPTED) must NOT satisfy the
# gate — only official Gitea reviews or agent-prefix comments count. A plain
# comment from a team member is a bypass if it skips the review UI.
echo
echo "== T16 comment generic keyword approval =="
T16_OUT=$(run_review_check "T16_comments_generic_approval")
T16_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T16 exit code 0 (generic-approval comment + team member)" "0" "$T16_RC"
assert_contains "T16 comment fallback notice" "comment-based approval" "$T16_OUT"
assert_eq "T16 exit code 1 (generic-approval comment rejected — not an official review)" "1" "$T16_RC"
assert_contains "T16 no candidates error" "no candidates from reviews API or issue comments" "$T16_OUT"
# T17 — no approval keywords in comments → exit 1
echo
@@ -363,16 +379,16 @@ T17_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T17 exit code 1 (no candidates from comments)" "1" "$T17_RC"
assert_contains "T17 no candidates error" "no candidates from reviews API or issue comments" "$T17_OUT"
# T18 — a wrong-team PR review candidate must not suppress a right-team
# comment approval. This matches PR #1790, where QA had an APPROVED review
# and security approved via the agent comment convention.
# T18 — wrong-team review + right-team comment → exit 1
# SECURITY: with comment approval fully removed, a wrong-team review plus
# a right-team comment yields NO valid candidates. Only official reviews
# from the target team count.
echo
echo "== T18 review candidate wrong team, comment candidate right team =="
T18_OUT=$(run_review_check "T18_review_wrong_team_comment_right_team")
T18_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T18 exit code 0 (comment approval still considered)" "0" "$T18_RC"
assert_contains "T18 comment candidate notice" "comment-based approval" "$T18_OUT"
assert_contains "T18 comment approver accepted" "APPROVED by core-qa-agent" "$T18_OUT"
assert_eq "T18 exit code 1 (comment approval removed — no valid candidates)" "1" "$T18_RC"
assert_contains "T18 none are in team" "none are in team" "$T18_OUT"
# T19 — ai-sop-ack member APPROVED review must NOT count toward qa-review
# or security-review (R1 hardening refinement, msg 1388c76f).
@@ -393,6 +409,24 @@ assert_eq "T20 exit code 1 (ai-sop-ack not in security team)" "1" "$T20_RC"
assert_contains "T20 ai-reviewer excluded from security" "candidates: ai-reviewer" "$T20_OUT"
assert_contains "T20 none are in security team" "none are in team" "$T20_OUT"
# T21 — stale-head APPROVED review must be rejected (commit_id mismatch).
# SECURITY: an approval on an old commit does not cover the current head.
echo
echo "== T21 stale-head APPROVED review rejected =="
T21_OUT=$(run_review_check "T21_stale_head_approved")
T21_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T21 exit code 1 (stale-head approval rejected)" "1" "$T21_RC"
assert_contains "T21 no candidates error" "no candidates from reviews API or issue comments" "$T21_OUT"
# T22 — missing/non-official APPROVED review must be rejected.
# SECURITY: only official Gitea reviews count; comments and non-official reviews lack audit trail.
echo
echo "== T22 missing official flag APPROVED review rejected =="
T22_OUT=$(run_review_check "T22_missing_official")
T22_RC=$(cat "$FIX_STATE_DIR/last_rc")
assert_eq "T22 exit code 1 (missing official rejected)" "1" "$T22_RC"
assert_contains "T22 no candidates error" "no candidates from reviews API or issue comments" "$T22_OUT"
echo
echo "------"
echo "PASS=$PASS FAIL=$FAIL"
@@ -61,11 +61,9 @@ name: Lint pre-flip continue-on-error
# feedback_no_shared_persona_token_use.
#
# Phase contract (RFC internal#219 §1 ladder):
# - This workflow lands at `continue-on-error: true` (Phase 3 —
# surface defects without blocking). Follow-up PR flips it to
# `false` ONLY after this workflow's own recent runs on `main`
# are confirmed clean — exactly the discipline the workflow
# itself enforces. Eat your own dogfood.
# - Flipped to `continue-on-error: false` after Researcher live-verified
# clean runs. The script's own 35 pytest tests pass and recent PR
# history shows no masked regressions — the gate is now enforcing.
on:
pull_request:
@@ -97,10 +95,9 @@ jobs:
name: Verify continue-on-error flips have run-log proof
runs-on: ubuntu-latest
timeout-minutes: 8
# Phase 3 (RFC internal#219 §1): surface broken flips without blocking
# the PR yet. Follow-up flips this to `false` once the workflow itself
# has clean recent runs on main. mc#1982 interim — remove when CoE→false.
continue-on-error: true # mc#1982
# Fail-closed: the lint script is verified clean (35/35 tests pass,
# Researcher live-check confirmed). Masking removed per mc#1982 close-out.
continue-on-error: false
steps:
- name: Check out PR head (full history for base-SHA access)
uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2
+293
View File
@@ -0,0 +1,293 @@
# RFC: Org-level Platform Agent — a tenant-resident concierge
**Perspective:** CTO + Backend Engineer + DevOps
**Status:** Draft — pre-implementation, **CTO sign-off required before any implementation PR**
**Scope:** `molecule-core` (workspace-server), `molecule-controlplane`, workspace runtime, `molecule-app`
**This document is the single source of truth (SSOT) for the feature.** Code, OpenAPI, the platform
MCP, and end-user docs reconcile to this RFC — not to each other.
---
## 1. Summary
Today a Molecule tenant is a control/router box: one EC2 runs the `workspace-server`
(`molecule-tenant` container) + Postgres + Redis, and **each workspace is its own separate EC2**
running a runtime image that joins the tenant's A2A mesh. A2A has exactly two participant kinds:
**workspaces** (agents) and the **user** (the canvas, modeled implicitly as `activity_logs.source_id
IS NULL`). A user who wants to *do* anything must drive individual workspaces directly — create them,
assign agents, wire channels/schedules/secrets — i.e. they must carry a lot of platform knowledge.
This RFC introduces a **platform agent**: an always-on org-level agent that
1. runs as a **container on the tenant EC2** itself (beside `molecule-tenant`),
2. natively holds the **platform-management MCP** (the org-admin tool surface) so it can do anything
in the org,
3. joins A2A as a **first-class third participant** (`kind='platform'`) that sits at the org root, and
4. becomes the **user's default chat target** — a concierge the user talks to like a chatbot, which
then orchestrates the org on their behalf.
Destructive actions the concierge triggers are **human-approved** through the existing approvals
subsystem.
## 2. Motivation
- **Lower the knowledge floor.** "Spin up an SEO team and have them publish weekly" should be a
sentence, not a sequence of workspace/agent/schedule/secret operations.
- **One front door.** A single conversational entry point that *is* the org, instead of N per-workspace
chats the user has to coordinate.
- **Reuse, don't rebuild.** The agent runtime, A2A mesh, the 87-tool platform MCP, and the approvals
subsystem already exist. This feature is mostly *composition* plus one honest new participant kind.
## 3. Goals / Non-Goals
**Goals**
- A per-tenant platform agent, provisioned automatically, that controls the org via the platform MCP.
- A first-class `platform` participant in A2A with correct routing and tenant isolation.
- Server-side approval gating for destructive org operations.
- Parity with normal workspaces for runtime/model/provider/billing (no special-casing).
**Non-Goals (this RFC)**
- Replacing the canvas. The canvas remains the advanced/power-user surface.
- Multi-concierge / per-team concierges. Exactly **one** platform agent per org.
- A new scoped-down token system for the MCP (tracked separately; see §10 Open Questions).
## 4. Current-state ground truth (verified, with references)
- **Topology.** Tenant EC2 runs `molecule-tenant` (workspace-server) + Postgres + Redis;
`controlplane/internal/provisioner/ec2.go:buildTenantUserDataSM()` `docker run`s it with
`--network host`, `PORT=8080`. Each **workspace is its own EC2** (`ec2.go:ProvisionWorkspace`).
- **No `org_id` column.** An "org" is the `parent_id IS NULL` subtree root;
`workspace-server/internal/handlers/org_scope.go` resolves it with a recursive CTE (`orgRootID`) and
`sameOrg()` compares two workspaces' resolved roots for tenant isolation (#1953/OFFSEC-015).
- **A2A authorization is hierarchy-based.** `workspace-server/internal/registry/access.go:CanCommunicate`
permits self / siblings / ancestor↔descendant. Root-level rows are "siblings" but every routing path
is additionally gated by `sameOrg()`.
- **No participant-kind discriminator.** `workspaces.role` is a free-form string; the user is implicit
(`activity_logs.source_id IS NULL`). `migrations/001_workspaces.sql`.
- **Runtime injects MCP servers** in the claude-code executor's `mcp_servers` dict — today exactly one
entry, `"a2a"` (`molecule-ai-workspace-template-claude-code/claude_sdk_executor.py`,
`molecule_runtime/claude_sdk_executor.py`). The agent self-registers via `POST /registry/register`
(`molecule_runtime/main.py`) and is identified by `WORKSPACE_ID` + `X-Molecule-Org-Id`.
- **Platform MCP** (`molecule-mcp-server`, stdio Node) authenticates purely from env
(`MOLECULE_API_KEY` = org-admin token, `MOLECULE_API_URL`, `MOLECULE_ORG_ID`; `src/api.ts`), is a
thin proxy over the tenant REST/A2A API (`chat_with_agent``POST /workspaces/:id/a2a`,
`async_delegate``/delegate`), and has **zero embeddability blockers**.
- **Billing** is a per-workspace resolver — `ResolveLLMBillingModeDerived`
(`workspace-server/internal/handlers/workspace_provision.go`, `llm_billing_mode.go`), defaulting
closed to `platform_managed`; `byok` runs on the tenant's own provider key (see
`docs/architecture/byok-fail-closed-billing.md`).
- **Approvals** exist: `migrations/007_approvals.sql`, `internal/handlers/approvals.go`,
`EventApprovalRequested`, decide route `POST /workspaces/:id/approvals/:approvalId/decide`.
## 5. Design
### 5.1 The platform agent IS the org root
Because `sameOrg()` resolves each workspace to its topmost `parent_id IS NULL` root, a platform agent
added as a *second* root would resolve to a *different* root than the existing team and be **blocked**
by `sameOrg`. Therefore the platform agent **becomes the single org root**, and the org's existing
root is **re-parented under it**. Consequences:
- `orgRootID(any workspace) == platform-agent-id`; `sameOrg(platform, any in-org ws) == true`.
- The platform agent reaches every workspace (and is reachable) via the **existing**
ancestor↔descendant rules — **no `CanCommunicate` change**, and tenant isolation is unchanged.
This is the honest realization of "a third participant above workspace and user": the concierge is
literally the org.
### 5.2 `kind` discriminator (the only new marker)
Add a single column `workspaces.kind TEXT NOT NULL DEFAULT 'workspace'`, constrained to
`('workspace','platform')`. It is the **only** marker of the platform agent — we do **not** also
encode identity in `role`/`tier` (those stay descriptive). The enum is defined once: the migration
`CHECK` and the Go constants `KindWorkspace`/`KindPlatform` (+ one `IsValidKind`) are kept in lockstep.
Invariants (handler-enforced, since there is no `org_id` for a pure-SQL unique):
- `kind='platform' ⇒ parent_id IS NULL`.
- A row may be `kind='platform'` only if it is its own org root (`orgRootID(self) == self`), giving
"exactly one platform agent per org". Guard the check+write in a tx with `FOR UPDATE` on the root.
### 5.3 Identity & registration
- **ID** = derived `uuidv5(org-namespace, "platform-agent")` — reproducible, no stored-vs-derived
drift, lowercase so it satisfies the runtime's `WORKSPACE_ID` validator.
- CP **pre-seeds** the `workspaces` row (`kind='platform'`, `parent_id=NULL`, `tier=0`) before the
agent boots; the agent self-registers (`POST /registry/register`) into that row. `Register` accepts
an optional `kind` and reconciles it, enforcing the §5.2 invariants.
### 5.4 Default-target resolver
New `GET /registry/platform-agent` (handler `internal/handlers/platform_agent.go`): resolve the
caller's `orgRootID()` and return it iff `kind='platform'`. This is the server hook the dashboard
targets by default; no change to `ProxyA2A`. **Authored in the OpenAPI SSOT first**; MCP/CLI/docs
derive from it.
### 5.5 Runtime: two MCPs, config-driven
Make the runtime's `mcp_servers` **config-driven** rather than hardcoded:
- `molecule_runtime/config.py`: add `extra_mcp_servers: list[dict]` to `WorkspaceConfig`, read
`raw.get("mcp_servers", [])`.
- Both executors merge `extra_mcp_servers` into the `mcp_servers` dict after the always-on `"a2a"`
entry (the template `claude_sdk_executor.py` is the live one; the runtime-package copy is the
fallback).
The platform agent's `config.yaml` then declares:
```yaml
runtime: claude-code
model: sonnet # default; user-switchable model AND provider via providers.yaml
a2a:
port: 8090 # avoid the workspace default 8000 under host networking
mcp_servers:
- name: platform
command: node
args: ["/opt/molecule-mcp-server/dist/index.js"]
```
The `platform` MCP reads `MOLECULE_API_KEY`/`MOLECULE_API_URL`/`MOLECULE_ORG_ID` from the container
env (passed through to the stdio child) — no per-server `env` block needed.
### 5.6 Hosting & provisioning (tenant EC2 container)
In `ec2.go:buildTenantUserDataSM()` add a `start_platform_agent` stage **after** `wait_platform_health`
(the agent registers against `localhost:8080` on boot):
```bash
docker run -d --restart=always --name molecule-platform-agent --network host \
-v /data/platform-agent/configs:/configs \
-e WORKSPACE_ID=<platform-uuid> -e WORKSPACE_CONFIG_PATH=/configs \
-e PLATFORM_URL=http://localhost:8080 \
-e MOLECULE_API_URL=http://localhost:8080 -e MOLECULE_API_KEY=$ADMIN_TOKEN -e MOLECULE_ORG_ID=<orgID> \
-e ANTHROPIC_AUTH_TOKEN=$ADMIN_TOKEN -e MOLECULE_LLM_ANTHROPIC_BASE_URL=$MOLECULE_LLM_ANTHROPIC_BASE_URL \
<platform-agent-image>
```
- The org `admin_token` is already on the box (Secrets Manager `molecule/tenant/{orgID}`).
- `--restart=always` provides Docker-level supervision (matches `molecule-tenant`).
- Mirror the block into the redeploy path (`buildRedeployScript`) so existing tenants backfill it.
### 5.7 Image
A **dedicated `molecule-platform-agent` image**: `FROM workspace-template-claude-code`, `COPY` the
prebuilt `molecule-mcp-server/dist` + `node_modules` into `/opt/molecule-mcp-server`, and **pin Node
20** (the slim base ships Node 18; the MCP expects ≥20). A dedicated image keeps the org-admin MCP
**out of** ordinary workspace images (security hygiene) and lets us set concierge defaults without
touching the workspace template. `molecule-ci` publishes it.
### 5.8 Approval gate (server-side trust boundary)
The MCP is a *client* of the tenant handlers, so enforcement lives in the **handlers**, not the MCP.
- `internal/approvals/policy.go` (new): one auditable map of gated actions —
`delete_workspace`, `deprovision`, `secret_write`, `org_token_mint`.
- `requireApproval(ctx, workspaceID, action, contextHash)` reuses the existing approvals
INSERT/broadcast/escalate. If an `approved`+unconsumed row matches → consume it → proceed. Else
create a `pending` row, broadcast `EventApprovalRequested`, and return **HTTP 202
`{approval_id, status:"pending"}`** instead of executing. The human decides via the existing decide
route; the agent retries and the gate now passes.
- Add `approval_requests.consumed_at` (single-use) and optional `request_hash` (dedupe identical
pending requests).
- **Escalation:** the platform agent's `parent_id` is NULL, so platform-originated approvals escalate
to the **user** (canvas notify), not a parent.
- The 202 response shape is authored in the **OpenAPI SSOT**.
### 5.9 Billing & model/provider parity
The platform agent is a `workspaces` row, so it inherits the one billing resolver and the
`providers.yaml` runtime matrix unchanged:
- **Default `platform_managed`** (metered CP proxy, billed to org credits) — the env wiring in §5.6.
- **`byok`** = flip `/admin/workspaces/:id/llm-billing-mode` + supply the org's `ANTHROPIC_API_KEY`
secret (workspace or global). Exposed as a provisioning flag so a tenant can choose at create time.
- Model **and provider** are switchable (Claude, Kimi-for-coding, …) via the same dashboard
model-switcher any workspace uses.
### 5.10 UX (summary; detailed in app RFC / Phase 5)
The **dashboard** (`molecule-app`) becomes the primary entry: a concierge chat (default-targeting the
§5.4 resolver) plus a live org overview, with pending approvals surfaced inline. The **canvas** stays
for advanced users. First UI version is produced in Claude Design and iterated before build.
## 6. SSOT mapping (derive, don't fork)
| Concern | Single source of truth | This RFC's rule |
|---|---|---|
| "The org" | `orgRootID()`/`sameOrg()` (`org_scope.go`) | platform agent *becomes* the root; no `org_id` column |
| Platform marker | `workspaces.kind` | `kind` only; never also `role`/`tier` |
| Model/provider | `providers.yaml` runtime matrix | concierge switches via the same registry |
| LLM billing | `ResolveLLMBillingModeDerived` | inherits the one resolver; no new path |
| Config/secrets delivery | tenant Secrets Manager bundle (`seedWorkspaceConfigSecret`) | no new S3 prefix / second store |
| Management API | OpenAPI spec | new endpoints authored there first; MCP/CLI/docs derive |
| Gated actions | `internal/approvals/policy.go` | one map |
| Platform-agent id | `uuidv5(org, "platform-agent")` | derived, never stored separately |
## 7. Security & blast radius
The concierge holds the org **admin token** (full tenant-root, self-minting) and is driven by
end-user chat. Mitigations:
- **Approval gate (§5.8)** must ship *with* the agent going user-facing, not after. Until then the
agent is operator-only.
- **Tenant isolation** is unchanged — every reach path still passes `sameOrg()`.
- **MCP not in workspace images** (dedicated image, §5.7); the admin token lives only in the
platform-agent container env on the tenant box.
- **Token rotation:** the MCP reads env once at spawn → rotation = `docker restart
molecule-platform-agent` (runbook item).
- Future: a scoped-down org token (no delete/billing/member) — see §10.
## 8. Migration & rollout
Phase ordering is the rollout contract:
- **Phase 0** (schema) ships and bakes before anything writes `kind`. Backward-compatible: every
existing row defaults to `kind='workspace'`; the `CHECK` is added `NOT VALID` then validated.
- **Phase 1 re-parenting backfill** is the one real watch-item. **Before** running it, audit whether
any org-scoped table keys off the *root workspace id* (e.g. `org_api_tokens`, `org_plugin_allowlist`)
versus the CP org UUID. If they reference the root workspace id, re-parenting changes "the root" and
those refs must migrate too. The backfill is per-org, idempotent, and reversible.
- New orgs get the platform agent from first boot; existing orgs backfill via `/admin/tenants
redeploy` + a one-time re-parent migration.
## 9. Implementation phases
0. **Schema + model** (`molecule-core`): `kind` column + `approval_requests.consumed_at`; model field +
constants; `Register` accepts/validates `kind` with invariants.
1. **Platform-as-root + resolver** (`molecule-core` + CP): CP pre-seeds the platform row and creates
teams under it; per-org re-parent backfill (after the §8 audit); `GET /registry/platform-agent`.
2. **Config-driven two-MCP runtime** (runtime + claude-code template).
3. **Image + tenant provisioning** (CP + image + `molecule-ci`): dedicated image; `start_platform_agent`
in user-data + redeploy; config via the tenant Secrets Manager bundle; billing knob.
4. **Approval gate** (`molecule-core`): policy map + `requireApproval` at destructive handlers; OpenAPI
202 shape.
5. **Dashboard concierge UX** (`molecule-app`): design-first, then build against the resolver.
6. **Cleanup**: exclude the platform agent from billable counts; canvas visibility; rotation runbook.
## 10. Open questions
- **Scoped-down token.** Should the concierge hold a reduced-scope token (no delete/billing/member)
instead of full admin + an approval gate? The token-scope system does not exist yet (`orgtoken`
TODO). Recommendation: ship admin-token + approval gate now; add scope-down as a follow-up.
- **Re-parenting vs. wrapper.** If product later wants a platform agent that is *not* the topological
root, a `CanCommunicateWithKind` wrapper (guarded by `sameOrg`) is the alternative. Deferred —
platform-as-root is lower-risk and needs zero access-control change.
- **Canvas visibility** of the root concierge node (hide vs. show as the org anchor).
## 11. Verification (end-to-end on a staging tenant)
1. **Schema:** Phase-0 migrations applied; existing workspaces report `kind='workspace'`; `go test
./...` + `-tags=integration` green.
2. **Provision:** redeploy a staging tenant; `docker ps` shows `molecule-platform-agent` healthy; its
logs show a successful `/registry/register`.
3. **Identity:** the platform row is `kind='platform'`, `parent_id IS NULL`; the former root now has
`parent_id = <platform id>`; `GET /registry/platform-agent` returns it.
4. **Reach:** chat the platform agent → it `list_workspaces` then `create_workspace` via the platform
MCP and reports back via `send_message_to_user`.
5. **Isolation:** it reaches every workspace in its org and **cannot** reach another tenant's
workspace.
6. **Approval gate:** `delete_workspace` → HTTP 202 pending + approval event; decide-approve →
completes; a second delete with the same approval is rejected (consumed).
7. Drive a real concierge flow ("spin up a PM + engineer to build X") and watch the delegation/activity
ledger.
---
*Derived from a read-only multi-agent source audit of `molecule-core`, `molecule-controlplane`,
`molecule-ai-workspace-runtime`, `molecule-ai-workspace-template-claude-code`, and
`molecule-mcp-server`. No secret values recorded.*
+5 -4
View File
@@ -1050,12 +1050,13 @@ def test_reap_continues_on_per_sha_apierror(sr_module, monkeypatch, capsys):
def test_main_soft_skips_when_commit_listing_times_out(sr_module, monkeypatch, capsys):
"""A transient outage while listing recent commits should not paint main red.
"""A transient outage while listing recent commits fails the tick visibly.
Per-SHA status read failures are already isolated inside `reap_branch`.
The real 2026-05-14 failure was earlier: `/commits?sha=main&limit=30`
timed out after all retries, aborting the tick. The next 5-minute tick can
retry safely, so `main()` should emit an observable warning and return 0.
retry safely, but the tick itself must be observable as red (exit 1 + error
annotation) so the cron bot alerts on persistent infra issues.
"""
monkeypatch.setattr(sr_module, "scan_workflows", lambda _: {"workflow-without-push": False})
@@ -1068,9 +1069,9 @@ def test_main_soft_skips_when_commit_listing_times_out(sr_module, monkeypatch, c
monkeypatch.setattr(sr_module, "list_recent_commit_shas", fake_list_recent_commit_shas)
monkeypatch.setattr(sys, "argv", ["status-reaper.py"])
assert sr_module.main() == 0
assert sr_module.main() == 1
captured = capsys.readouterr()
assert "::warning::status-reaper skipped this tick" in captured.out
assert "::error::status-reaper cannot run" in captured.out
assert '"skipped": true' in captured.out
assert '"skip_reason": "commit-list-api-error"' in captured.out
@@ -0,0 +1,39 @@
// Package approvals holds the single source of truth for which destructive
// org operations require a human approval before they execute.
//
// (RFC docs/design/rfc-platform-agent.md — Phase 4)
//
// The org-level platform agent is driven by end-user chat and holds an org-admin
// token, so destructive/irreversible operations it can trigger are gated: the
// handler creates a pending approval and returns it instead of executing, and a
// human decides via the existing approvals subsystem. Keeping the gated-action
// list in ONE map makes the blast-radius boundary auditable in a single place —
// a handler not listed here behaves exactly as before.
package approvals
// Action is the canonical identifier of a gated destructive operation. The same
// string is stored in approval_requests.action so the gate can match a pending/
// approved request to the operation being retried.
type Action string
const (
ActionDeleteWorkspace Action = "delete_workspace"
ActionDeprovision Action = "deprovision_workspace"
ActionSecretWrite Action = "secret_write"
ActionOrgTokenMint Action = "org_token_mint"
)
// gated is the set of actions that require a human approval. Add an entry here
// (and gate the corresponding handler with requireApproval) to expand the
// boundary; remove one to drop a gate. This is the only place the policy lives.
var gated = map[Action]bool{
ActionDeleteWorkspace: true,
ActionDeprovision: true,
ActionSecretWrite: true,
ActionOrgTokenMint: true,
}
// IsGated reports whether action requires a human approval before executing.
func IsGated(action Action) bool {
return gated[action]
}
@@ -63,6 +63,31 @@ func TestSessionSearchReturnsActivityAndMemory(t *testing.T) {
}
}
func TestSessionSearch_DBError(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
broadcaster := newTestBroadcaster()
handler := NewActivityHandler(broadcaster)
mock.ExpectQuery("WITH session_items AS").
WillReturnError(context.DeadlineExceeded)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("GET", "/workspaces/ws-123/session-search?q=test", bytes.NewBufferString(""))
c.Request.Header.Set("Content-Type", "application/json")
c.Params = gin.Params{{Key: "id", Value: "ws-123"}}
handler.SessionSearch(c)
if w.Code != http.StatusInternalServerError {
t.Errorf("expected 500 on DB error, got %d", w.Code)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("unmet sqlmock expectations: %v", err)
}
}
// ---------- Activity List source filter ----------
func TestActivityList_SourceCanvas(t *testing.T) {
@@ -0,0 +1,153 @@
package handlers
// approval_gate.go — server-side gate for destructive org operations.
// (RFC docs/design/rfc-platform-agent.md — Phase 4)
//
// requireApproval is the choke point a destructive handler calls before
// executing. It is the trust boundary: the platform-management MCP is a CLIENT
// of these handlers, so enforcing here (not in the MCP) means anything holding
// an org-admin token still goes through the gate. The flow:
//
// - if a matching APPROVED + unconsumed approval exists, consume it (single-
// use) and let the operation proceed;
// - otherwise create (or reuse) a PENDING approval, broadcast it to the canvas
// (and escalate to the parent if any), and the handler returns HTTP 202 so a
// human can decide. The agent retries after approval and the gate passes.
//
// Matching is by (workspace_id, action, request_hash) where request_hash is a
// stable digest of the operation + its context, so a retried op reuses its own
// request instead of flooding the table, and an approval for "delete ws A"
// cannot be replayed to "delete ws B".
import (
"context"
"crypto/sha256"
"database/sql"
"encoding/hex"
"encoding/json"
"errors"
"fmt"
"log"
"net/http"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/approvals"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/db"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/events"
"github.com/gin-gonic/gin"
)
// approvalRequestHash is a stable digest of the gated operation. Go's
// json.Marshal sorts map keys, so the same context always hashes the same.
func approvalRequestHash(workspaceID, action string, contextMap map[string]interface{}) string {
cj, err := json.Marshal(contextMap)
if err != nil || cj == nil {
cj = []byte("{}")
}
sum := sha256.Sum256([]byte(workspaceID + "\x00" + action + "\x00" + string(cj)))
return hex.EncodeToString(sum[:])
}
// requireApproval returns (approved=true, consumedID) when a matching approval
// exists and was just consumed; otherwise it creates/reuses a pending approval
// and returns (false, pendingID). A non-nil error is a server error.
func requireApproval(ctx context.Context, b *events.Broadcaster, workspaceID string, action approvals.Action, reason string, contextMap map[string]interface{}) (bool, string, error) {
hash := approvalRequestHash(workspaceID, string(action), contextMap)
// 1. Atomically consume an approved + unconsumed request, if one exists.
// The conditional UPDATE ... RETURNING makes consumption race-safe: two
// concurrent destructive calls cannot both consume the same approval.
var consumedID string
err := db.DB.QueryRowContext(ctx, `
UPDATE approval_requests SET consumed_at = now()
WHERE id = (
SELECT id FROM approval_requests
WHERE workspace_id = $1 AND action = $2 AND request_hash = $3
AND status = 'approved' AND consumed_at IS NULL
ORDER BY decided_at DESC NULLS LAST
LIMIT 1
FOR UPDATE SKIP LOCKED
)
RETURNING id
`, workspaceID, string(action), hash).Scan(&consumedID)
if err == nil {
return true, consumedID, nil
}
if !errors.Is(err, sql.ErrNoRows) {
return false, "", fmt.Errorf("consume approval: %w", err)
}
// 2. No usable approval — create a pending one, or reuse an existing pending
// request for the same operation so retries don't flood the table.
cj, mErr := json.Marshal(contextMap)
if mErr != nil || cj == nil {
cj = []byte("{}")
}
var approvalID string
err = db.DB.QueryRowContext(ctx, `
WITH existing AS (
SELECT id FROM approval_requests
WHERE workspace_id = $1 AND action = $2 AND request_hash = $3 AND status = 'pending'
LIMIT 1
), ins AS (
INSERT INTO approval_requests (workspace_id, action, reason, context, request_hash)
SELECT $1, $2, $4, $5::jsonb, $3
WHERE NOT EXISTS (SELECT 1 FROM existing)
RETURNING id
)
SELECT id FROM ins UNION ALL SELECT id FROM existing LIMIT 1
`, workspaceID, string(action), hash, reason, string(cj)).Scan(&approvalID)
if err != nil {
return false, "", fmt.Errorf("create approval: %w", err)
}
// Broadcast to the canvas (the user-facing signal). For a platform agent the
// parent_id is NULL, so the requested-event on its own workspace IS the user
// prompt; ordinary workspaces also escalate to their parent.
if bErr := b.RecordAndBroadcast(ctx, string(events.EventApprovalRequested), workspaceID, map[string]interface{}{
"approval_id": approvalID,
"action": string(action),
"reason": reason,
}); bErr != nil {
log.Printf("approval_gate: broadcast requested failed (ws=%s): %v", workspaceID, bErr)
}
var parentID *string
if pErr := db.DB.QueryRowContext(ctx, `SELECT parent_id FROM workspaces WHERE id = $1`, workspaceID).Scan(&parentID); pErr != nil {
log.Printf("approval_gate: parent lookup failed (ws=%s): %v", workspaceID, pErr)
}
if parentID != nil {
if bErr := b.RecordAndBroadcast(ctx, string(events.EventApprovalEscalated), *parentID, map[string]interface{}{
"approval_id": approvalID,
"from_workspace_id": workspaceID,
"action": string(action),
"reason": reason,
}); bErr != nil {
log.Printf("approval_gate: broadcast escalated failed (ws=%s): %v", workspaceID, bErr)
}
}
return false, approvalID, nil
}
// gateDestructive runs requireApproval for a gated action and, when approval is
// still pending, writes the 202 response and returns false (caller must stop).
// Returns true when the caller may proceed (action consumed an approval).
func gateDestructive(c *gin.Context, b *events.Broadcaster, workspaceID string, action approvals.Action, reason string, contextMap map[string]interface{}) bool {
if !approvals.IsGated(action) {
return true
}
approved, approvalID, err := requireApproval(c.Request.Context(), b, workspaceID, action, reason, contextMap)
if err != nil {
log.Printf("gateDestructive: %v (ws=%s action=%s)", err, workspaceID, action)
c.JSON(http.StatusInternalServerError, gin.H{"error": "approval gate failed"})
return false
}
if !approved {
c.JSON(http.StatusAccepted, gin.H{
"status": "pending_approval",
"approval_id": approvalID,
"action": string(action),
"reason": reason,
})
return false
}
return true
}
@@ -0,0 +1,137 @@
//go:build integration
// +build integration
// approval_gate_integration_test.go — REAL Postgres gate for requireApproval.
//
// Run with:
//
// INTEGRATION_DB_URL="postgres://postgres:test@localhost:55432/molecule?sslmode=disable" \
// go test -tags=integration ./internal/handlers/ -run Integration_RequireApproval -v
//
// Why this is NOT a sqlmock test
// ------------------------------
// The whole gate is about row state across calls: a pending request is created
// once and reused (dedup), an approval is consumed exactly once (single-use via
// the conditional UPDATE ... RETURNING), and a different operation context hashes
// to a different request. sqlmock returns whatever the stub says; only a real
// Postgres proves the consume-once semantics and the partial-index lookup.
package handlers
import (
"context"
"database/sql"
"testing"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/approvals"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/db"
"github.com/google/uuid"
_ "github.com/lib/pq"
)
func TestIntegration_RequireApproval_GateCycle(t *testing.T) {
url := requireIntegrationDBURL(t)
conn, err := sql.Open("postgres", url)
if err != nil {
t.Fatalf("open: %v", err)
}
if err := conn.Ping(); err != nil {
t.Fatalf("ping: %v", err)
}
t.Cleanup(func() { conn.Close() })
// requireApproval + the broadcaster's structure_events write use the db.DB
// global; point it at the integration DB and restore afterwards.
prev := db.DB
db.DB = conn
t.Cleanup(func() { db.DB = prev })
setupTestRedis(t) // broadcaster publishes to db.RDB; miniredis backs it
ctx := context.Background()
b := newTestBroadcaster()
wsID := uuid.New().String()
t.Cleanup(func() {
_, _ = conn.ExecContext(ctx, `DELETE FROM approval_requests WHERE workspace_id = $1`, wsID)
_, _ = conn.ExecContext(ctx, `DELETE FROM workspaces WHERE id = $1`, wsID)
})
// A root workspace (parent_id NULL) — like the platform agent, it has no
// parent, so the gate's escalation target is the user/canvas. (This branch
// is off main and has no kind column; the gate is kind-agnostic.)
if _, err := conn.ExecContext(ctx, `
INSERT INTO workspaces (id, name, tier, status, runtime, parent_id)
VALUES ($1, 'Org Concierge', 0, 'online', 'claude-code', NULL)`, wsID); err != nil {
t.Fatalf("seed root workspace: %v", err)
}
action := approvals.ActionDeleteWorkspace
ctxA := map[string]interface{}{"target": "ws-A"}
// 1. First call → no approval yet → pending created.
ok, id1, err := requireApproval(ctx, b, wsID, action, "delete ws-A", ctxA)
if err != nil {
t.Fatalf("call 1: %v", err)
}
if ok {
t.Fatal("call 1: approved=true, want false (no approval exists yet)")
}
// 2. Same operation again → must REUSE the same pending row (dedup), not flood.
ok, id2, err := requireApproval(ctx, b, wsID, action, "delete ws-A", ctxA)
if err != nil {
t.Fatalf("call 2: %v", err)
}
if ok || id2 != id1 {
t.Fatalf("call 2: ok=%v id2=%s, want false and id2==id1(%s) (dedup)", ok, id2, id1)
}
var nPending int
if err := conn.QueryRowContext(ctx,
`SELECT count(*) FROM approval_requests WHERE workspace_id=$1 AND status='pending'`, wsID).Scan(&nPending); err != nil {
t.Fatalf("count pending: %v", err)
}
if nPending != 1 {
t.Fatalf("pending rows = %d, want 1 (dedup must not flood)", nPending)
}
// 3. A human approves it (simulating the Decide handler).
if _, err := conn.ExecContext(ctx,
`UPDATE approval_requests SET status='approved', decided_by='human', decided_at=now() WHERE id=$1`, id1); err != nil {
t.Fatalf("approve: %v", err)
}
// 4. Now the gate consumes the approval and lets the op proceed.
ok, consumedID, err := requireApproval(ctx, b, wsID, action, "delete ws-A", ctxA)
if err != nil {
t.Fatalf("call 4: %v", err)
}
if !ok || consumedID != id1 {
t.Fatalf("call 4: ok=%v consumedID=%s, want true and id1(%s)", ok, consumedID, id1)
}
// 5. Single-use: the SAME approval cannot be replayed — the next call is
// pending again (a fresh request), not approved.
ok, id5, err := requireApproval(ctx, b, wsID, action, "delete ws-A", ctxA)
if err != nil {
t.Fatalf("call 5: %v", err)
}
if ok {
t.Fatal("call 5: approved=true — a consumed approval was replayed")
}
if id5 == id1 {
t.Fatal("call 5: reused the consumed request id; want a new pending request")
}
// 6. Context isolation: an approval for ws-A must not authorize ws-B.
// Approve the ws-A request, then a ws-B op must still be pending.
if _, err := conn.ExecContext(ctx,
`UPDATE approval_requests SET status='approved', decided_at=now() WHERE id=$1`, id5); err != nil {
t.Fatalf("approve id5: %v", err)
}
ok, _, err = requireApproval(ctx, b, wsID, action, "delete ws-B", map[string]interface{}{"target": "ws-B"})
if err != nil {
t.Fatalf("call 6: %v", err)
}
if ok {
t.Fatal("call 6: ws-B proceeded on a ws-A approval — context isolation broken")
}
}
@@ -0,0 +1,46 @@
package handlers
import (
"net/http"
"net/http/httptest"
"testing"
"git.moleculesai.app/molecule-ai/molecule-core/workspace-server/internal/approvals"
"github.com/gin-gonic/gin"
)
// TestGateDestructive_NonGatedPassesThrough verifies a non-gated action skips
// the gate entirely (no DB access, no 202) so handlers whose action isn't in the
// policy map behave exactly as before.
func TestGateDestructive_NonGatedPassesThrough(t *testing.T) {
gin.SetMode(gin.TestMode)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("POST", "/x", nil)
proceed := gateDestructive(c, newTestBroadcaster(), "ws-1",
approvals.Action("not_a_gated_action"), "noop", nil)
if !proceed {
t.Fatalf("non-gated action must proceed, got proceed=false (status %d)", w.Code)
}
if w.Code != http.StatusOK { // CreateTestContext default; nothing written
t.Errorf("non-gated action wrote a response (status %d), want none", w.Code)
}
}
// TestApprovalRequestHash_StableAndContextSensitive pins the two properties the
// gate relies on: the same operation hashes identically across calls, and a
// different context yields a different hash (so an approval can't be replayed
// onto a different target).
func TestApprovalRequestHash_StableAndContextSensitive(t *testing.T) {
a := approvalRequestHash("ws", "delete_workspace", map[string]interface{}{"target": "A", "n": 1})
aAgain := approvalRequestHash("ws", "delete_workspace", map[string]interface{}{"n": 1, "target": "A"})
b := approvalRequestHash("ws", "delete_workspace", map[string]interface{}{"target": "B", "n": 1})
if a != aAgain {
t.Errorf("hash not stable across equal contexts: %s vs %s", a, aAgain)
}
if a == b {
t.Errorf("hash not context-sensitive: target A and B collided (%s)", a)
}
}
@@ -602,6 +602,33 @@ func TestDelegationRecord_RejectsInvalidUUID(t *testing.T) {
}
}
func TestDelegationRecord_DBInsertFails(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
broadcaster := newTestBroadcaster()
wh := NewWorkspaceHandler(broadcaster, nil, "http://localhost:8080", t.TempDir())
h := NewDelegationHandler(wh, broadcaster)
mock.ExpectExec("INSERT INTO activity_logs").
WillReturnError(fmt.Errorf("connection refused"))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Params = gin.Params{{Key: "id", Value: "550e8400-e29b-41d4-a716-446655440000"}}
body := `{"target_id":"550e8400-e29b-41d4-a716-446655440001","task":"hello","delegation_id":"del-xyz"}`
c.Request = httptest.NewRequest("POST", "/delegations/record", bytes.NewBufferString(body))
c.Request.Header.Set("Content-Type", "application/json")
h.Record(c)
if w.Code != http.StatusInternalServerError {
t.Errorf("expected 500 on DB insert failure, got %d", w.Code)
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("unmet expectations: %v", err)
}
}
func TestDelegationUpdateStatus_CompletedInsertsResultRow(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
@@ -337,7 +337,7 @@ func TestRegister_ProvisionerURLPreserved(t *testing.T) {
WillReturnError(sql.ErrNoRows)
mock.ExpectExec("INSERT INTO workspaces").
WithArgs("ws-prov", "ws-prov", "http://localhost:8000", `{"name":"agent"}`, "push").
WithArgs("ws-prov", "ws-prov", "http://localhost:8000", `{"name":"agent"}`, "push", "").
WillReturnResult(sqlmock.NewResult(0, 1))
// DB returns provisioner URL (127.0.0.1) — should take precedence over agent-reported URL
@@ -180,7 +180,7 @@ func TestRegisterHandler(t *testing.T) {
// Expect the upsert INSERT ... ON CONFLICT
mock.ExpectExec("INSERT INTO workspaces").
WithArgs("ws-123", "ws-123", "http://localhost:8000", `{"name":"test"}`, "push").
WithArgs("ws-123", "ws-123", "http://localhost:8000", `{"name":"test"}`, "push", "").
WillReturnResult(sqlmock.NewResult(0, 1))
// Expect the SELECT url query (for cache URL logic)
@@ -0,0 +1,122 @@
//go:build integration
// +build integration
// kind_platform_root_integration_test.go — REAL Postgres gate for the
// platform-agent participant kind (RFC docs/design/rfc-platform-agent.md).
//
// Run with:
//
// INTEGRATION_DB_URL="postgres://postgres:test@localhost:55432/molecule?sslmode=disable" \
// go test -tags=integration ./internal/handlers/ -run Integration_PlatformKind -v
//
// CI: piggybacks on the handlers-postgres-integration workflow (path filter
// includes workspace-server/internal/handlers/** and migrations/**).
//
// Why this is NOT a sqlmock test
// ------------------------------
// The invariant "a platform agent must be the org root (parent_id IS NULL),
// which structurally also means at most one platform agent per org" is enforced
// by the workspaces_platform_root_check CHECK constraint in migration
// 20260606000000_workspaces_kind. sqlmock cannot execute DDL or evaluate a CHECK
// constraint, so only a real Postgres can prove the constraint actually rejects
// a non-root platform agent and accepts a root one. The Register handler's
// isPlatformRootViolation()/409 path depends on this constraint firing.
package handlers
import (
"context"
"database/sql"
"fmt"
"strings"
"testing"
"github.com/google/uuid"
_ "github.com/lib/pq"
)
func integrationDB_PlatformKind(t *testing.T) *sql.DB {
t.Helper()
url := requireIntegrationDBURL(t)
conn, err := sql.Open("postgres", url)
if err != nil {
t.Fatalf("open: %v", err)
}
if err := conn.Ping(); err != nil {
t.Fatalf("ping: %v", err)
}
t.Cleanup(func() { conn.Close() })
return conn
}
// TestIntegration_PlatformKind_RootAllowed_NonRootRejected proves the three
// guarantees of the kind column against a real Postgres:
//
// 1. a fresh workspace defaults to kind='workspace';
// 2. a root row (parent_id IS NULL) may be kind='platform';
// 3. a non-root row (parent_id set) may NOT be kind='platform' — the
// workspaces_platform_root_check constraint rejects it (23514).
func TestIntegration_PlatformKind_RootAllowed_NonRootRejected(t *testing.T) {
conn := integrationDB_PlatformKind(t)
ctx := context.Background()
prefix := fmt.Sprintf("itest-kind-%s", uuid.New().String()[:8])
cleanup := func() {
if _, err := conn.ExecContext(ctx,
`DELETE FROM workspaces WHERE name LIKE $1`, prefix+"%"); err != nil {
t.Logf("cleanup (non-fatal): %v", err)
}
}
t.Cleanup(cleanup)
cleanup() // pre-test hygiene in the shared integration DB
rootID := uuid.New().String()
childID := uuid.New().String()
// 1. Default kind is 'workspace' when the column is omitted on INSERT.
if _, err := conn.ExecContext(ctx, `
INSERT INTO workspaces (id, name, tier, runtime, status, parent_id)
VALUES ($1, $2, 2, 'claude-code', 'online', NULL)
`, rootID, prefix+"-root"); err != nil {
t.Fatalf("seed root: %v", err)
}
var gotKind string
if err := conn.QueryRowContext(ctx,
`SELECT kind FROM workspaces WHERE id = $1`, rootID).Scan(&gotKind); err != nil {
t.Fatalf("read kind: %v", err)
}
if gotKind != "workspace" {
t.Fatalf("default kind = %q, want \"workspace\"", gotKind)
}
// 2. The root row may become a platform agent.
if _, err := conn.ExecContext(ctx,
`UPDATE workspaces SET kind = 'platform' WHERE id = $1`, rootID); err != nil {
t.Fatalf("promote root to platform: unexpected error: %v", err)
}
// A child of the platform root (an ordinary workspace) inserts fine.
if _, err := conn.ExecContext(ctx, `
INSERT INTO workspaces (id, name, tier, runtime, status, parent_id)
VALUES ($1, $2, 2, 'claude-code', 'online', $3)
`, childID, prefix+"-child", rootID); err != nil {
t.Fatalf("seed child: %v", err)
}
// 3. The non-root child may NOT be a platform agent — the CHECK rejects it.
_, err := conn.ExecContext(ctx,
`UPDATE workspaces SET kind = 'platform' WHERE id = $1`, childID)
if err == nil {
t.Fatalf("non-root child accepted kind='platform' — constraint did not fire")
}
if !strings.Contains(err.Error(), "workspaces_platform_root_check") {
t.Fatalf("non-root platform rejection wanted workspaces_platform_root_check, got: %v", err)
}
// And the unknown-kind value is rejected by workspaces_kind_check.
_, err = conn.ExecContext(ctx,
`UPDATE workspaces SET kind = 'bogus' WHERE id = $1`, rootID)
if err == nil || !strings.Contains(err.Error(), "workspaces_kind_check") {
t.Fatalf("unknown kind wanted workspaces_kind_check rejection, got: %v", err)
}
}
+36 -3
View File
@@ -164,6 +164,20 @@ func (h *RegistryHandler) resolveDeliveryMode(ctx context.Context, workspaceID,
return models.DeliveryModePush, nil
}
// errPlatformNotRoot is the client-facing message when a register call tried to
// mark a non-root workspace as a platform agent.
const errPlatformNotRoot = "a platform agent must be the org root (parent_id must be null)"
// isPlatformRootViolation reports whether err is the DB rejecting a register
// that tried to mark a non-root workspace as a platform agent (the
// workspaces_platform_root_check CHECK constraint). The handler maps it to a
// friendly HTTP 409 instead of a raw 500. The invariant — platform == org root,
// which structurally also guarantees one platform agent per org — is enforced
// race-proof at the DB level; this is just the friendly surface.
func isPlatformRootViolation(err error) bool {
return err != nil && strings.Contains(err.Error(), "workspaces_platform_root_check")
}
// Returns a non-nil error suitable for including in a 400 Bad Request response.
func validateAgentURL(rawURL string) error {
if rawURL == "" {
@@ -277,6 +291,14 @@ func (h *RegistryHandler) Register(c *gin.Context) {
return
}
// Validate explicit kind if the agent declared one; empty is allowed and
// resolves to the row's existing value (or "workspace" default) in
// resolveKind below. Only the platform-agent container declares 'platform'.
if payload.Kind != "" && !models.IsValidKind(payload.Kind) {
c.JSON(http.StatusBadRequest, gin.H{"error": "kind must be 'workspace' or 'platform'"})
return
}
ctx := c.Request.Context()
// C18: prevent workspace URL hijacking on re-registration.
@@ -390,9 +412,15 @@ func (h *RegistryHandler) Register(c *gin.Context) {
// the row. Without this guard, bulk deletes left tier-3 stragglers because
// the last pre-teardown heartbeat flipped status back to 'online' after
// Delete's UPDATE.
// kind ($6) is the raw payload value (validated above; "" = unspecified).
// COALESCE(NULLIF($6,''), …) means: an explicit kind wins; an unspecified
// kind defaults to 'workspace' for a NEW row and KEEPS the existing kind on
// re-register (so a platform agent re-registering without kind is never
// downgraded). A non-root row asking for 'platform' is rejected by the
// workspaces_platform_root_check constraint → friendly 409 below.
_, err = db.DB.ExecContext(ctx, `
INSERT INTO workspaces (id, name, url, agent_card, status, last_heartbeat_at, delivery_mode)
VALUES ($1, $2, $3, $4::jsonb, 'online', now(), $5)
INSERT INTO workspaces (id, name, url, agent_card, status, last_heartbeat_at, delivery_mode, kind)
VALUES ($1, $2, $3, $4::jsonb, 'online', now(), $5, COALESCE(NULLIF($6, ''), 'workspace'))
ON CONFLICT (id) DO UPDATE SET
url = CASE
WHEN workspaces.url LIKE 'http://127.0.0.1%' THEN workspaces.url
@@ -402,10 +430,15 @@ func (h *RegistryHandler) Register(c *gin.Context) {
status = 'online',
last_heartbeat_at = now(),
delivery_mode = EXCLUDED.delivery_mode,
kind = COALESCE(NULLIF($6, ''), workspaces.kind),
updated_at = now()
WHERE workspaces.status IS DISTINCT FROM 'removed'
`, payload.ID, payload.ID, urlForUpsert, agentCardStr, modeForUpsert)
`, payload.ID, payload.ID, urlForUpsert, agentCardStr, modeForUpsert, payload.Kind)
if err != nil {
if isPlatformRootViolation(err) {
c.JSON(http.StatusConflict, gin.H{"error": errPlatformNotRoot})
return
}
log.Printf("Registry register error: %v (id=%s)", err, payload.ID)
c.JSON(http.StatusInternalServerError, gin.H{"error": "registration failed"})
return
@@ -72,7 +72,7 @@ func TestRegister_DBError(t *testing.T) {
// DB insert fails
mock.ExpectExec("INSERT INTO workspaces").
WithArgs("ws-fail", "ws-fail", "http://localhost:8000", `{"name":"test"}`, "push").
WithArgs("ws-fail", "ws-fail", "http://localhost:8000", `{"name":"test"}`, "push", "").
WillReturnError(sql.ErrConnDone)
w := httptest.NewRecorder()
@@ -647,7 +647,7 @@ func TestRegister_GuardAgainstResurrectingRemovedRow(t *testing.T) {
// This regex-ish match requires the guard. If the handler ever drops
// the clause the test fails because the emitted SQL won't match.
mock.ExpectExec("ON CONFLICT.*WHERE workspaces.status IS DISTINCT FROM 'removed'").
WithArgs("ws-resurrect", "ws-resurrect", "http://localhost:8000", `{"name":"x"}`, "push").
WithArgs("ws-resurrect", "ws-resurrect", "http://localhost:8000", `{"name":"x"}`, "push", "").
WillReturnResult(sqlmock.NewResult(0, 0)) // 0 rows affected = correctly guarded
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs("ws-resurrect").
@@ -917,7 +917,7 @@ func TestRegister_C18_BootstrapAllowedNoTokens(t *testing.T) {
// Workspace upsert proceeds normally.
mock.ExpectExec("INSERT INTO workspaces").
WithArgs("ws-new", "ws-new", "http://localhost:9100", `{"name":"new-agent"}`, "push").
WithArgs("ws-new", "ws-new", "http://localhost:9100", `{"name":"new-agent"}`, "push", "").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
@@ -1228,7 +1228,7 @@ func TestRegister_DBErrorResponseIsOpaque(t *testing.T) {
// DB upsert fails with a descriptive internal error.
mock.ExpectExec("INSERT INTO workspaces").
WithArgs("ws-errtest", "ws-errtest", "http://localhost:9200", `{"name":"err-agent"}`, "push").
WithArgs("ws-errtest", "ws-errtest", "http://localhost:9200", `{"name":"err-agent"}`, "push", "").
WillReturnError(sql.ErrConnDone)
w := httptest.NewRecorder()
@@ -1476,7 +1476,7 @@ func TestRegister_PollMode_AcceptsEmptyURL(t *testing.T) {
// Upsert MUST run with empty URL (sql.NullString) and delivery_mode=poll.
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"poll-agent"}`, "poll").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"poll-agent"}`, "poll", "").
WillReturnResult(sqlmock.NewResult(0, 1))
// SELECT url for cache: returns NULL/empty for poll-mode rows. The
@@ -1591,6 +1591,89 @@ func TestRegister_InvalidDeliveryMode(t *testing.T) {
}
}
// TestRegister_InvalidKind rejects payloads that declare an unrecognised kind —
// only 'workspace' and 'platform' are valid. Mirrors the delivery_mode guard;
// the rejection happens before any DB access.
func TestRegister_InvalidKind(t *testing.T) {
setupTestDB(t)
setupTestRedis(t)
broadcaster := newTestBroadcaster()
handler := NewRegistryHandler(broadcaster)
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("POST", "/registry/register",
bytes.NewBufferString(`{"id":"ws-x","url":"http://localhost:8000","agent_card":{"name":"a"},"kind":"bogus"}`))
c.Request.Header.Set("Content-Type", "application/json")
handler.Register(c)
if w.Code != http.StatusBadRequest {
t.Errorf("invalid kind: expected 400, got %d: %s", w.Code, w.Body.String())
}
if !strings.Contains(w.Body.String(), "kind") {
t.Errorf("expected error body to mention kind, got: %s", w.Body.String())
}
}
// TestRegister_PlatformKind_PersistsKind verifies that a workspace registering
// with kind="platform" has that value written through the upsert (the platform
// agent self-registers as the org root). The platform==root invariant itself is
// enforced by the workspaces_platform_root_check DB constraint and exercised by
// the integration test, which sqlmock cannot enforce.
func TestRegister_PlatformKind_PersistsKind(t *testing.T) {
mock := setupTestDB(t)
setupTestRedis(t)
broadcaster := newTestBroadcaster()
handler := NewRegistryHandler(broadcaster)
const wsID = "ws-platform-agent"
// Bootstrap path — no live tokens.
mock.ExpectQuery("SELECT COUNT\\(\\*\\) FROM workspace_auth_tokens").
WithArgs(wsID).
WillReturnRows(sqlmock.NewRows([]string{"count"}).AddRow(0))
// delivery_mode="push" is set explicitly, so resolveDeliveryMode
// short-circuits (no SELECT delivery_mode lookup). The upsert MUST carry
// kind="platform" as the 6th arg.
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, "http://localhost:9100", `{"name":"concierge"}`, "push", "platform").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs(wsID).
WillReturnRows(sqlmock.NewRows([]string{"url"}).AddRow("http://localhost:9100"))
mock.ExpectExec("INSERT INTO structure_events").
WillReturnResult(sqlmock.NewResult(0, 1))
// Token issuance — first-register path.
mock.ExpectQuery("SELECT COUNT\\(\\*\\) FROM workspace_auth_tokens").
WithArgs(wsID).
WillReturnRows(sqlmock.NewRows([]string{"count"}).AddRow(0))
mock.ExpectExec("INSERT INTO workspace_auth_tokens").
WillReturnResult(sqlmock.NewResult(1, 1))
mock.ExpectQuery(`SELECT platform_inbound_secret FROM workspaces WHERE id = \$1`).
WithArgs(wsID).
WillReturnRows(sqlmock.NewRows([]string{"platform_inbound_secret"}).AddRow(nil))
w := httptest.NewRecorder()
c, _ := gin.CreateTestContext(w)
c.Request = httptest.NewRequest("POST", "/registry/register",
bytes.NewBufferString(`{"id":"`+wsID+`","url":"http://localhost:9100","delivery_mode":"push","kind":"platform","agent_card":{"name":"concierge"}}`))
c.Request.Header.Set("Content-Type", "application/json")
handler.Register(c)
if w.Code != http.StatusOK {
t.Fatalf("platform register: expected 200, got %d: %s", w.Code, w.Body.String())
}
if err := mock.ExpectationsWereMet(); err != nil {
t.Errorf("unmet expectations: %v", err)
}
}
// TestRegister_PollMode_PreservesExistingValue: when the row already
// has delivery_mode=poll and the payload doesn't set it, the resolved
// mode should be poll — i.e. "absent payload mode" must NOT silently
@@ -1616,7 +1699,7 @@ func TestRegister_PollMode_PreservesExistingValue(t *testing.T) {
// Upsert carries the resolved poll mode forward — even though
// payload didn't restate it. URL still empty (poll-mode shape).
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll", "").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs(wsID).
@@ -1685,7 +1768,7 @@ func TestRegister_ExternalRuntime_DefaultsToPoll(t *testing.T) {
AddRow(sql.NullString{}, "external"))
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll", "").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs(wsID).
@@ -1744,7 +1827,7 @@ func TestRegister_KimiRuntime_DefaultsToPoll(t *testing.T) {
AddRow(sql.NullString{}, "kimi-cli"))
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll").
WithArgs(wsID, wsID, sql.NullString{}, `{"name":"a"}`, "poll", "").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs(wsID).
@@ -1804,7 +1887,7 @@ func TestRegister_NonExternalRuntime_StillDefaultsToPush(t *testing.T) {
AddRow(sql.NullString{}, "claude-code"))
mock.ExpectExec("INSERT INTO workspaces").
WithArgs(wsID, wsID, "http://localhost:8000", `{"name":"a"}`, "push").
WithArgs(wsID, wsID, "http://localhost:8000", `{"name":"a"}`, "push", "").
WillReturnResult(sqlmock.NewResult(0, 1))
mock.ExpectQuery("SELECT url FROM workspaces WHERE id").
WithArgs(wsID).
+31 -5
View File
@@ -13,11 +13,16 @@ import (
const DefaultMaxConcurrentTasks = 1
type Workspace struct {
ID string `json:"id" db:"id"`
Name string `json:"name" db:"name"`
Role sql.NullString `json:"role" db:"role"`
Tier int `json:"tier" db:"tier"`
Status string `json:"status" db:"status"`
ID string `json:"id" db:"id"`
Name string `json:"name" db:"name"`
Role sql.NullString `json:"role" db:"role"`
Tier int `json:"tier" db:"tier"`
Status string `json:"status" db:"status"`
// Kind: "workspace" (default) or "platform". A "platform" workspace is the
// org-level concierge (the platform agent) that sits at the org root and is
// the user's default A2A target. See migration
// 20260606000000_workspaces_kind + RFC docs/design/rfc-platform-agent.md.
Kind string `json:"kind" db:"kind"`
SourceBundleID sql.NullString `json:"source_bundle_id" db:"source_bundle_id"`
AgentCard json.RawMessage `json:"agent_card" db:"agent_card"`
URL sql.NullString `json:"url" db:"url"`
@@ -63,6 +68,21 @@ func IsValidDeliveryMode(s string) bool {
return s == DeliveryModePush || s == DeliveryModePoll
}
// Workspace kind constants. Matches the CHECK constraint in migration
// 20260606000000_workspaces_kind. KindPlatform marks the org-level concierge
// (the platform agent) which sits at the org root; see
// docs/design/rfc-platform-agent.md.
const (
KindWorkspace = "workspace"
KindPlatform = "platform"
)
// IsValidKind reports whether s is a recognised workspace kind. Empty string is
// NOT valid here — callers resolve the default (KindWorkspace) before calling.
func IsValidKind(s string) bool {
return s == KindWorkspace || s == KindPlatform
}
type RegisterPayload struct {
ID string `json:"id" binding:"required"`
// URL is required for push-mode workspaces; optional / unused for
@@ -76,6 +96,12 @@ type RegisterPayload struct {
// value on the workspace row, or default to push for new rows".
// When set, must be one of DeliveryModePush / DeliveryModePoll.
DeliveryMode string `json:"delivery_mode,omitempty"`
// Kind is optional. Empty string means "keep the existing value on the
// workspace row, or default to KindWorkspace for new rows". When set, must
// be one of KindWorkspace / KindPlatform. KindPlatform additionally requires
// the row to be its own org root (parent_id IS NULL) and to be the only
// platform agent in the org — enforced by the Register handler.
Kind string `json:"kind,omitempty"`
}
type HeartbeatPayload struct {
@@ -34,6 +34,35 @@ func TestIsValidDeliveryMode_Invalid(t *testing.T) {
}
}
// ==================== IsValidKind ====================
func TestIsValidKind_Valid(t *testing.T) {
for _, k := range []string{KindWorkspace, KindPlatform} {
if !IsValidKind(k) {
t.Errorf("IsValidKind(%q) = false, want true", k)
}
}
}
func TestIsValidKind_Invalid(t *testing.T) {
cases := []struct {
val string
want bool
}{
{"", false}, // empty is not valid — callers resolve the default
{"platforms", false}, // typo
{"Platform", false}, // case-sensitive
{"platform ", false}, // trailing space
{"root", false}, // not a kind
{"user", false}, // the user is implicit, not a workspace kind
}
for _, tc := range cases {
if got := IsValidKind(tc.val); got != tc.want {
t.Errorf("IsValidKind(%q) = %v, want %v", tc.val, got, tc.want)
}
}
}
// ==================== WorkspaceStatus ====================
func TestWorkspaceStatus_String(t *testing.T) {
@@ -0,0 +1,7 @@
-- Reverse the participant-kind discriminator.
-- Non-destructive: dropping the column makes every workspace an ordinary
-- workspace again (the platform agent loses its marker but its row survives).
DROP INDEX IF EXISTS idx_workspaces_kind;
ALTER TABLE workspaces DROP CONSTRAINT IF EXISTS workspaces_platform_root_check;
ALTER TABLE workspaces DROP CONSTRAINT IF EXISTS workspaces_kind_check;
ALTER TABLE workspaces DROP COLUMN IF EXISTS kind;
@@ -0,0 +1,45 @@
-- Participant-kind discriminator for the org-level platform agent.
-- (RFC: docs/design/rfc-platform-agent.md)
--
-- 'workspace' (default) = an ordinary workspace / agent.
-- 'platform' = the org-level concierge (the "platform agent"). It is
-- the single org root (parent_id IS NULL) and the user's
-- default A2A chat target. Exactly one per org.
--
-- There is no org_id column — an "org" is the parent_id-chain root resolved by
-- org_scope.go (orgRootID/sameOrg). "platform == org root" and "one platform
-- agent per org" are therefore enforced in the Register/create handlers, not in
-- pure SQL. This column is only the discriminator (default-target / billing
-- exclusion / UX), defined once here and mirrored by the Go constants
-- models.KindWorkspace / models.KindPlatform.
--
-- Backward-compatible: every existing row defaults to 'workspace'. The CHECK is
-- added NOT VALID then validated so the ALTER can never fail on legacy data.
ALTER TABLE workspaces
ADD COLUMN IF NOT EXISTS kind TEXT NOT NULL DEFAULT 'workspace';
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'workspaces_kind_check') THEN
ALTER TABLE workspaces
ADD CONSTRAINT workspaces_kind_check CHECK (kind IN ('workspace', 'platform')) NOT VALID;
ALTER TABLE workspaces VALIDATE CONSTRAINT workspaces_kind_check;
END IF;
END $$;
-- platform == org root, enforced at the DB level (race-proof). A platform agent
-- MUST have parent_id IS NULL. Because an org is the subtree under a single
-- parent_id IS NULL root (org_scope.go) and only a root may be 'platform', this
-- also structurally guarantees at most ONE platform agent per org. The handler
-- additionally pre-checks this to return a friendly 409 instead of a raw 23514.
DO $$
BEGIN
IF NOT EXISTS (SELECT 1 FROM pg_constraint WHERE conname = 'workspaces_platform_root_check') THEN
ALTER TABLE workspaces
ADD CONSTRAINT workspaces_platform_root_check
CHECK (kind <> 'platform' OR parent_id IS NULL) NOT VALID;
ALTER TABLE workspaces VALIDATE CONSTRAINT workspaces_platform_root_check;
END IF;
END $$;
CREATE INDEX IF NOT EXISTS idx_workspaces_kind ON workspaces(kind);
@@ -0,0 +1,5 @@
-- Reverse the approval-gate single-use/dedup columns.
DROP INDEX IF EXISTS approval_requests_gate_idx;
ALTER TABLE approval_requests
DROP COLUMN IF EXISTS request_hash,
DROP COLUMN IF EXISTS consumed_at;
@@ -0,0 +1,18 @@
-- Single-use + dedup support for the destructive-op approval gate.
-- (RFC docs/design/rfc-platform-agent.md — Phase 4)
--
-- consumed_at: an approval is single-use. Once a destructive op consumes an
-- approved request, consumed_at is stamped so the same approval can't be
-- replayed for a second destructive call.
-- request_hash: a stable hash of (workspace_id, action, context) so a repeated
-- destructive attempt matches its own pending/approved request instead of
-- flooding the table with duplicates.
ALTER TABLE approval_requests
ADD COLUMN IF NOT EXISTS consumed_at TIMESTAMPTZ,
ADD COLUMN IF NOT EXISTS request_hash TEXT;
-- Hot path: the gate looks up an approved + unconsumed row matching
-- (workspace_id, action, request_hash). Partial index keeps that O(log live).
CREATE INDEX IF NOT EXISTS approval_requests_gate_idx
ON approval_requests (workspace_id, action, request_hash)
WHERE status = 'approved' AND consumed_at IS NULL;