You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
@claude — the repo's @claude handler (.github/workflows/claude.yml, using anthropics/claude-code-action) is BROKEN: it replies to every mention with "Claude finished … in 0s" and does no real work. This blocks cross-repo infra requests (e.g. #166 — provision the mendys DB role). Please investigate, fix, and add guardrails.
Evidence (from the failing run logs)
Handler fetches the issue comment OK, then its change-detection phase runs GET /compare/main...claude/issue-166-<ts> → 404 "Branch does not exist remotely" → Error checking for changes in branch: HttpError: Not Found (compare two commits). The working branch was never created (Claude produced no commits) and the diff step assumes it exists, so it bails.
The run also executes stray, irrelevant setup inside the Claude step: cd e2e && npm install && npx playwright install chromium --with-deps && npx playwright test — leftover e2e content in the handler's prompt / base command / loaded CLAUDE.md.
NOT an Anthropic credit/key problem (step reports success in ~0s).
git log -p -- .github/workflows/claude.yml: find when the anthropics/claude-code-action version/ref changed, when the prompt/direct_prompt/override_prompt/claude_args/settings changed, when an e2e/playwright command was introduced, or when trigger/base-branch/use_commit_signing/branch handling changed.
Also check root CLAUDE.md / .github prompt files — the e2e commands may come from a loaded instruction file, not the YAML.
Report the exact breaking commit + why.
Phase 2 — Fix
Restore a known-good config: correct/pinned action SHA that doesn't 404 on a no-op run, remove e2e/playwright leftovers from the prompt, fix branch handling so a no-change run doesn't crash on compare. Keep secrets as secrets. Minimal, reviewable diff.
Phase 3 — Guardrails (so an edit can't silently break the handler again)
actionlint (+ a claude-handler sanity check) as a REQUIRED status check on any PR touching .github/workflows/**.
CODEOWNERS requiring review for .github/workflows/** (esp. claude*.yml).
Pin third-party actions to full commit SHAs (comment the human-readable version) for the claude handlers.
A lightweight smoke check (scheduled/manual) that mentions @claude on a sandbox/labeled test issue and asserts a real, non-"0s" response — catches regressions fast.
Short "editing the @claude handlers" runbook (prompt do/don'ts, SHA-pin policy, how to test), consistent with the FuzeSDLC governance baseline.
Then action Provision dedicated mendys Postgres role + Mongo user (MendysRobotics prod blocked) #166: provision the dedicated mendys PostgreSQL role + mendys MongoDB user (mirroring fuzekeys/fuzesocial) and deliver creds to MendysRobotics as GH Actions secrets MENDYS_PG_USERNAME/MENDYS_PG_PASSWORD/MENDYS_MONGO_USERNAME/MENDYS_MONGO_PASSWORD via secure hand-off — never paste raw values.
Ship the handler fix and the guardrails as separate small PRs. Report the breaking commit.
@claude — the repo's
@claudehandler (.github/workflows/claude.yml, usinganthropics/claude-code-action) is BROKEN: it replies to every mention with "Claude finished … in 0s" and does no real work. This blocks cross-repo infra requests (e.g. #166 — provision themendysDB role). Please investigate, fix, and add guardrails.Evidence (from the failing run logs)
GET /compare/main...claude/issue-166-<ts>→ 404 "Branch does not exist remotely" →Error checking for changes in branch: HttpError: Not Found (compare two commits). The working branch was never created (Claude produced no commits) and the diff step assumes it exists, so it bails.cd e2e && npm install && npx playwright install chromium --with-deps && npx playwright test— leftover e2e content in the handler's prompt / base command / loaded CLAUDE.md.Phase 1 — Investigate which push broke it
git log --oneline -30 -- .github/workflows/claude.yml(+ claude-auto-pr.yml, claude-ci-autofix.yml, ci-failure-triage.yml).git log -p -- .github/workflows/claude.yml: find when theanthropics/claude-code-actionversion/ref changed, when the prompt/direct_prompt/override_prompt/claude_args/settingschanged, when an e2e/playwright command was introduced, or when trigger/base-branch/use_commit_signing/branch handling changed.git blamethe lines producing the e2e commands and the branch/diff behavior; correlate commit dates with when the 0s behavior began (issue Provision dedicatedmendysPostgres role + Mongo user (MendysRobotics prod blocked) #166 created 2026-07-07, first bad reply minutes later).Phase 2 — Fix
Restore a known-good config: correct/pinned action SHA that doesn't 404 on a no-op run, remove e2e/playwright leftovers from the prompt, fix branch handling so a no-change run doesn't crash on compare. Keep secrets as secrets. Minimal, reviewable diff.
Phase 3 — Guardrails (so an edit can't silently break the handler again)
.github/workflows/**..github/workflows/**(esp. claude*.yml).Phase 4 — Verify & close the loop
mendysPostgres role + Mongo user (MendysRobotics prod blocked) #166 and confirm the handler does real work (branch + response, not 0s).mendysPostgres role + Mongo user (MendysRobotics prod blocked) #166: provision the dedicatedmendysPostgreSQL role +mendysMongoDB user (mirroring fuzekeys/fuzesocial) and deliver creds to MendysRobotics as GH Actions secretsMENDYS_PG_USERNAME/MENDYS_PG_PASSWORD/MENDYS_MONGO_USERNAME/MENDYS_MONGO_PASSWORDvia secure hand-off — never paste raw values.Ship the handler fix and the guardrails as separate small PRs. Report the breaking commit.
Refs: izzywdev/MendysRobotics#134, FuzeInfra #166.