- align dev-release workflow with protected-branch bypass used by release.yml
- add a workflow regression test so checkout and release auth do not drift back to github.token
- cache only Bun's package cache so CI stops restoring partial hard-linked node_modules trees
- bump the cache key to avoid reusing corrupt node_modules archives on self-hosted runners
- Add concurrency group keyed on github.ref with cancel-in-progress to stop superseded runs on rapid pushes
- Split validate matrix into: validate (typecheck/lint/format), build, test
- Build uploads dist/ artifact; test downloads instead of rebuilding (removes inline build:all duplication)
- Net: faster feedback, less runner time, DRY build step
- ci.yml: 5-job matrix (typecheck/lint/format/build/test), fail-fast off,
actions/cache on ~/.bun/install/cache + node_modules + ui/node_modules.
Target wall time ~60-90s vs prior ~3-4min.
- .husky/pre-push: add bun run build:all to feature-branch fast gate so
UI tsc -b errors are caught pre-push (~18s warm).
- CLAUDE.md (symlinked as AGENTS.md): fix validate drift (maintainability
is NOT part of validate), add CI-First Protocol mandating gh pr checks
--watch after every push, replace pre-commit checklist with two-tier
model (iterative push vs pre-merge).
Branch protection on main/dev must be updated post-merge to require the
new matrix status checks instead of the single legacy "validate" check.
- replace hardcoded GLM endpoint with vars.AI_REVIEW_BASE_URL
- replace hardcoded model with vars.AI_REVIEW_MODEL
- use secrets.AI_REVIEW_API_KEY for auth token
- add configuration reference in header comment
- switch the reviewer workflow from glm-5-turbo to glm-5.1
- increase workflow timeout to 20 minutes and max turns to 45
- lock the workflow test to the full reviewer model configuration
Closes#922
- replace raw assistant-text fallback with structured output normalization
- simplify the review prompt toward a tighter findings-only contract
- add tests for malformed output, safe fallback, and markdown escaping
- Increase per-reviewer max-turns 25→40 (security review hit limit on
large PRs like codex runtime with ~5000 line diff)
- Increase orchestrator max-turns 15→20
- Improve fallback extraction: concatenate ALL assistant messages (not
just last) when reviewer hits turn limit without writing output file
- Add descriptive prefix to fallback output explaining why extraction
was needed (e.g., "hit turn limit", "no execution log")
- Ensures something meaningful is posted even when CI jobs fail
Replace echo with printf '%s\n' for subagent prompt GITHUB_OUTPUT writes
to match the existing main prompt pattern (line 216). Prevents edge case
where echo misinterprets leading -n/-e as flags.
--allowedTools is an approval list (skip permission prompts), redundant
with bypassPermissions. --tools is the actual availability whitelist.
Also simplified tool list: Bash sub-patterns (gh pr diff *, etc.) aren't
supported by --tools. The workflow token has contents:read only, so the
agent physically cannot push/delete/modify the repo even with full Bash.
- Remove --allowedTools from claude_args (redundant with bypassPermissions,
was never actually restricting tools)
- Strengthen orchestrator prompt: MANDATORY/FORBIDDEN language for subagent
dispatch, explicit "you MUST use Agent tool" enforcement
- Increase --max-turns from 20 to 30 (large PRs with 31 files need ~25 turns)
- Explicitly instruct Claude to use Write tool (not Edit/python3 fallback)
- Add READ-ONLY constraint to prevent source code modifications
- Previous run hit error_max_turns at turn 21 despite successfully writing review
Part of #818
- Upgrade review model from glm-5 to glm-5.1
- Add fallback step: if Claude doesn't write pr_review.md, extract
last assistant message from execution output as review content
- Upload claude-execution-output.json as artifact (7-day retention)
so review sessions can be inspected after the job completes
- Publish review comment runs on always() instead of only on success,
so fallback-extracted reviews still get posted
Allows seeing Claude's full output in CI logs instead of the
opaque "full output hidden for security" message. Helps debug
slow reviews and identify bottlenecks.
claude-code-action@v1 auto-updates its bundled Claude Code and Agent SDK.
The custom path_to_claude_code_executable forced the runner's stale CLI
(v2.1.39) to be used instead, causing validateHeaders auth failures when
the SDK updated to 0.2.85. Let the action manage its own installation.
Closes#810
Root cause: Bun's test runner fails to resolve exports from directory
index.ts files during parallel test execution. The api-command/index.ts
imports 8 subcommand modules — if any fail to load during concurrent
test runs, the entire module fails with "Export not found."
Fix: extract createApiCommandHandler into handler.ts (lightweight, only
imports named-command-router). Test imports from handler.ts directly,
bypassing the heavy index.ts that loads all subcommand modules.
Also:
- Remove stale api-command.ts barrel file
- Use explicit /index import paths in source
- Migrate CI validate to self-hosted runner with clean artifact step
- Disable Bun cache (no-cache: true) on self-hosted runner
Tam Nhu Tran