fixing-ci

Fixing CI

Overview

Diagnose failing CI from GitHub logs, fix each issue with an atomic commit, and iterate locally until the full suite is green — then push once.

Principle: One fix, one commit. Never push until all checks pass locally.

Workflow

1. DIAGNOSE      → Pull failure logs from GitHub, list all failures
2. For each failure:
   a. REPRODUCE  → Run the failing check locally to confirm you see it
   b. FIX        → Fix root cause (not downstream symptoms)
   c. VERIFY FIX → Re-run the check to confirm it passes
   d. COMMIT     → Atomic commit for this fix
3. VERIFY ALL    → Run the full suite locally
   ↳ If anything fails → go back to step 2
   ↳ All green → proceed
4. PUSH          → Push all commits

Step 1: Diagnose

# See recent CI runs on current branch
gh run list --branch $(git branch --show-current) --limit 5

# View failing run (find run-id from above)
gh run view <run-id>

# Stream logs from only the failed steps
gh run view <run-id> --log-failed

Read top-to-bottom and list all distinct failures before fixing any of them. Find the first error in each job — not symptoms that cascade from it.

Step 2: Fix Loop (repeat per failure)

a. Reproduce

Check the project's AGENTS.md for exact commands. Common mappings:

CI Job	Typical Local Command
Lint	pnpm lint
Typecheck	pnpm typecheck
Tests	pnpm test
Build	pnpm build

Run the failing check and confirm you see the same error locally before touching code.

b. Fix

• Fix the root cause — lint errors often cascade from a single type error upstream
• Don't fix just to silence the error; understand why it's wrong
• If the fix is unclear, read the relevant library docs or AGENTS.md before guessing

c. Verify the Fix

Re-run the specific check to confirm it passes before committing.

d. Commit