fix: close architecture review guard gaps#463
Conversation
|
This pull request has been ignored for the connected project Preview Branches by Supabase. |
|
Important Review skippedNo new commits to review since the last review. ⚙️ Run configurationConfiguration used: Organization UI Review profile: CHILL Plan: Pro Plus Run ID: You can disable this status message by setting the Use the checkbox below for a quick retry:
📝 WalkthroughWalkthroughPlatform-aware project identity utilities now distinguish Windows and POSIX path semantics. Architecture regression tests now parse broader dynamic-import forms and detect runtime self-import cycles, with the review ledger recording the follow-up. ChangesIdentity and architecture guard
Estimated code review effort: 3 (Moderate) | ~20 minutes Caution Pre-merge checks failedPlease resolve all errors before merging. Addressing warnings is optional.
❌ Failed checks (1 error, 1 warning)
✅ Passed checks (9 passed)
✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 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 `@tests/local-server-utils.test.ts`:
- Around line 22-23: Replace the collision-based assertions for localProjectId
and stableProjectPort with checks that upperCaseRoot and lowerCaseRoot normalize
differently, while verifying each function’s deterministic behavior and valid
output range; alternatively, assert pinned expected fixture values without
requiring distinct outputs.
🪄 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: Organization UI
Review profile: CHILL
Plan: Pro Plus
Run ID: 06b4b2bb-ca47-4ddd-87a3-543c37941acc
📒 Files selected for processing (4)
docs/branch-review-ledger.mdsrc/lib/local-server-utils.mjstests/architecture-boundaries.test.tstests/local-server-utils.test.ts
|
@coderabbitai review The prior finding was addressed in |
🧩 Analysis chain🏁 Script executed: #!/bin/bash
set -euo pipefail
fd -t f "local-server-utils.test.ts" | xargs -I{} sh -c 'echo "== {} =="; cat -n {}'
git log --oneline -5
git log --oneline --all | grep -i f08b7f0 || trueLength of output: 2649
It no longer assumes distinct hash/modulo outputs across all four inputs, which addresses the flakiness concern from the prior review. Kicking off a fresh review of the PR now. ✅ Action performedReview finished.
|
Resolved in f08b7f0: replaced probabilistic collision assertions with deterministic normalization, repeatability, ID-shape, and port-range checks. Focused test passes 2/2; hosted format, lint, typecheck, unit coverage, safety, and build checks are green.
1 participant
Summary
Why
These are the three valid CodeRabbit findings raised on PR #457. That PR was merged before the corrective push completed, so this focused follow-up applies only those fixes to the merged
maintree.Verification
tests/architecture-boundaries.test.ts— 6 passedtests/local-server-utils.test.ts— 2 passedgit diff --check— passednpm ci --offline, the worktree install became incomplete and a rerun failed on missingnext/lucide-reactdeclarations. Hosted CI's clean install is the authoritative typecheck for this head.Not run
No browser, provider-backed Supabase/OpenAI, deployment, or production checks were run.
Risk
Low and isolated to local project identity generation and test-only architecture graph parsing. Existing one-argument callers retain their behavior on Windows.