3 people d313f44a19 fix(ci): improve Claude Code review reliability (#955) ...

The Claude review step was failing ~40% of the time because:
- --allowedTools didn't include Read, Glob, Grep, Agent, causing 8-9
  permission denials per run and preventing Claude from reading files
  or spawning the subagents the prompt required
- Step 4 spawned N additional scoring agents per issue found, exhausting
  the 50-turn budget before the PR comment could be posted
- Subagents could independently post PR comments, causing fragmented output

Fix: add missing tools to --allowedTools, merge per-issue scoring into
the review agents themselves, and add guardrails ensuring exactly one
consolidated comment is always posted.

Co-authored-by: Claude Opus 4.6 <[email protected]>

2026-03-11 14:05:33 -07:00

..

scripts

ci: enforce regression tests for fix commits (#517)

2026-03-04 04:35:54 +00:00

workflows

fix(ci): improve Claude Code review reliability (#955)

2026-03-11 14:05:33 -07:00

labeler.yml

ci: add automated PR labeling system (#253)

2026-02-20 12:02:41 +04:00

pull_request_template.md

feat: add PR template with risk assessment (#837)

2026-03-10 11:06:47 -07:00