fix: restore phase 0 qa trust#154
Conversation
|
No actionable comments were generated in the recent review. 🎉 ℹ️ Recent review info⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (2)
🚧 Files skipped from review as they are similar to previous changes (1)
📝 WalkthroughWalkthroughAdds a premium QA architecture plan and implements storage updates for evidence/deploy linking, refactors assertion consensus to support response/evidence and arbiter votes with improved failure/selector detection, and updates tester entry points and execution-engine selection to support visual exploratory runs. ChangesPremium QA Architecture & Implementation
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches📝 Generate docstrings
🧪 Generate unit tests (beta)
Comment |
There was a problem hiding this comment.
Actionable comments posted: 2
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@docs/premium-qa-architecture-plan.md`:
- Line 219: The prose uses the lowercase platform name `.github/workflows`;
update that occurrence to use the consistent, capitalized platform name `GitHub`
(e.g., change `.github/workflows` in the sentence to `GitHub` while keeping the
repository path literal if intended, or write `GitHub` before the
`.github/workflows` path for clarity) so references to GitHub are capitalized
consistently across the document.
In `@src/retrace/storage/repositories/incidents.py`:
- Around line 1290-1301: The UPDATE in update_failure_deploy currently executes
without verifying that a row was changed; capture the result of conn.execute
(e.g., cursor = conn.execute(...)) and check cursor.rowcount after the
statement, and if it is 0 raise a clear exception (e.g., ValueError or a
domain-specific NotFoundError) that includes the provided failure_id so callers
know the deploy correlation failed because the failure wasn't found; keep the
existing deploy_sha.strip() and timestamp logic but ensure you raise the error
before exiting the with-block.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: 0b996a1d-e6cc-441a-b819-c06807157780
📒 Files selected for processing (6)
docs/premium-qa-architecture-plan.mdsrc/retrace/storage/core.pysrc/retrace/storage/repositories/incidents.pysrc/retrace/tester/__init__.pysrc/retrace/tester/assertions.pysrc/retrace/tester/specs.py
Summary
Restores default-branch trust after the tester/storage modularization and adds the premium QA architecture plan.
Changes
IncidentRepository_run_playwright_specand_run_shellretrace.tester.run_specdocs/premium-qa-architecture-plan.mdValidation
uv run ruff check src testsuv run pytest -q(969 passed, 4 skipped)uv run pytest tests/test_tester_playwright.py -q(3 passed)cd packages/browser && npm ci && npm test && npm run build(24 passed, TypeScript build passed)Notes
This PR intentionally does not start Phase 1. It only restores a green base and documents the architecture direction.
Summary by CodeRabbit
Documentation
New Features
Refactor