Skip to content

chore: apply 51278a70d remediations onto origin/main#857

Closed
BigSimmo wants to merge 8 commits into
mainfrom
codex/main-apply-51278-merge-20260718-clean-final
Closed

chore: apply 51278a70d remediations onto origin/main#857
BigSimmo wants to merge 8 commits into
mainfrom
codex/main-apply-51278-merge-20260718-clean-final

Conversation

@BigSimmo

@BigSimmo BigSimmo commented Jul 18, 2026

Copy link
Copy Markdown
Owner

Summary

  • Apply the 51278a70d production-readiness remediation on the latest mainline by porting route/sitemap assertion alignment and schema drift-manifest synchronization.
  • Scope is test and migration-inventory safety only; runtime logic and provider behavior are unchanged.

Verification

  • Verification not run: local environment currently lacks required Node 24 runtime/dependency stack for full offline checks, and provider-backed checks are out-of-scope in this workspace.
  • UI verification not run: no local Playwright/runtime execution performed in this worktree.

Risk and rollout

  • Risk: medium; parity changes are only test/schema drift assertions, but stale expectations can mask regressions during future schema or routing updates if not kept synchronized.
  • Rollback: if checks fail post-merge, revert this PR to restore prior test expectations before further rollout.

@supabase

supabase Bot commented Jul 18, 2026

Copy link
Copy Markdown

This pull request has been ignored for the connected project sjrfecxgysukkwxsowpy because there are no changes detected in supabase directory. You can change this behaviour in Project Integrations Settings ↗︎.


Preview Branches by Supabase.
Learn more about Supabase Branching ↗︎.

@coderabbitai

coderabbitai Bot commented Jul 18, 2026

Copy link
Copy Markdown
Contributor

Warning

Review limit reached

@BigSimmo, you've reached your PR review limit, so we couldn't start this review.

Next review available in: 10 minutes

Enable usage-based reviews in Billing to review now. Otherwise, wait until the next included review is available.
You're only billed for reviews past your plan's rate limits ($0.25/file).

How can I continue?

After more reviews become available, a review can be triggered using the @coderabbitai review command as a PR comment. Alternatively, push new commits to this PR.

To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews.

How do review limits work?

CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability.

For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window.

Please refer docs for additional details.

Review details
⚙️ Run configuration

Configuration used: Path: .coderabbit.yaml

Review profile: CHILL

Plan: Pro Plus

Run ID: bef01672-46a2-40de-934c-e82f400eeea8

📥 Commits

Reviewing files that changed from the base of the PR and between 7094be4 and 07eeeca.

📒 Files selected for processing (7)
  • playwright.config.ts
  • tests/audit-content-services-regressions.test.ts
  • tests/audit-navigation-auth-regressions.test.ts
  • tests/supabase-schema.test.ts
  • tests/ui-accessibility.spec.ts
  • tests/ui-smoke.spec.ts
  • tests/ui-tools.spec.ts
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch codex/main-apply-51278-merge-20260718-clean-final

Comment @coderabbitai help to get the list of available commands.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: ac1773f050

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread playwright.config.ts
Comment on lines +59 to +60
contextOptions: {
reducedMotion: "no-preference",

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep reduced motion scoped to the transition check

Because the required Production UI lane runs npm run test:e2e:pr, which selects --project=chromium, setting the Chromium project to reducedMotion: "no-preference" makes every production Chromium spec run with animations enabled again. That contradicts the suite-level guard immediately above, which documents known click races in ui-stress/ui-smoke; a single dock-transition assertion should opt out locally with page.emulateMedia(...) instead of weakening the whole required UI gate.

Useful? React with 👍 / 👎.

Copy link
Copy Markdown
Owner Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

@codex fix

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Summary

  • Committed 1034f76 (fix: scope reduced-motion override to dock test) on branch work.
  • Restored the Chromium Playwright project to inherit the suite-wide reduced-motion configuration instead of overriding it with no-preference, keeping production UI specs protected from animation-related click races. playwright.config.tsL45-L60
  • Scoped the animation opt-out to the single bottom search dock transition assertion with page.emulateMedia({ reducedMotion: "no-preference" }), so that test can still verify the transform transition locally. tests/ui-tools.spec.tsL1016-L1022
  • Created PR metadata with the make_pr tool using title fix: scope reduced-motion override to dock test.

Testing

  • npm run workflow:flightplan -- --write-evidence --files playwright.config.ts
  • git diff --check
  • ⚠️ npm run test:focused -- --files tests/ui-tools.spec.ts,playwright.config.ts — focused runner refused test/config path selection and instructed running the full unit suite.
  • ⚠️ npm run test -- --run tests/ui-tools.spec.ts — could not run because node_modules/vitest/vitest.mjs is missing in this workspace; current runtime is Node v20.20.2.

Worktree

  • Current branch: work.
  • Worktree is clean after commit.

View task →

@BigSimmo

Copy link
Copy Markdown
Owner Author

@codex resolve actionable Codex review findings for this pull request and current head using the repository instructions. This is the pull request's single automatic repair pass: do not perform a fresh review, create new standalone findings, or request another review. Work only the existing unresolved Codex threads on the current head. Always fix P0 and P1 findings. For P2 and lower findings, fix only clear, scoped, low-risk issues; otherwise disposition them with a concise reason. After fixing or dispositioning a thread, reply in that thread with as the first line, followed by a concise summary; that marker authorizes the workflow to close that exact thread. If human input or new authorization is required, do not use the marker and leave the thread open with the blocker. Finish only after every actionable thread is fixed or dispositioned and closed, or explicitly left open for a human decision. Do not update the branch from main, address unrelated reviews, broaden scope, or create more than one scoped fix commit. Do not use external APIs, paid services, credentials, dependency changes, or broad refactors unless explicitly authorized. Add targeted tests where behavior changes and run the narrowest relevant validation.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: bd832bbc50

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment thread tests/audit-content-services-regressions.test.ts
Comment thread tests/audit-navigation-auth-regressions.test.ts
@github-actions

Copy link
Copy Markdown

CI triage

CI failed on this PR. Automated classification of the 3 failed job(s):

  • Unit coverageneeds investigation: inspect the failing step and uploaded diagnostics; rerun only after classifying the cause.
  • Production UIneeds investigation: inspect the failing step and uploaded diagnostics; rerun only after classifying the cause.
  • PR requiredneeds investigation: inspect the failing step and uploaded diagnostics; rerun only after classifying the cause.

Compared with main CI run #3291 (success).

Classification is evidence routing, not permission to ignore a failure. Exact quarantined Playwright identities remain governed by the flake ledger.

@BigSimmo
BigSimmo enabled auto-merge (squash) July 18, 2026 13:58
@BigSimmo

Copy link
Copy Markdown
Owner Author

Closing as superseded by merged PR #859 and merged PR #861. The remaining test/config-only patch still has unresolved source-contract blockers and is not safe to merge. Branch retained; no branch deletion performed.

@BigSimmo BigSimmo closed this Jul 18, 2026
auto-merge was automatically disabled July 18, 2026 14:11

Pull request was closed

@BigSimmo

Copy link
Copy Markdown
Owner Author

@copilot resolve the merge conflicts on this branch.

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 07eeeca259

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

expect(corrector).toContain("word % tok");
expect(corrector).toContain("limit 32");
expect(corrector).toContain("min_sim real default 0.45");
if (corrector.includes("set pg_trgm.similarity_threshold = 0.3")) {

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P2 Badge Keep the similarity threshold in the schema guard

In this clinical-query corrector guard, the change removes the assertions that the SQL still exposes min_sim real default 0.45 and actually applies best_sim >= min_sim; with only the remaining indexed-probe checks, a schema or migration can start rewriting low-similarity clinical search terms and this test will still pass. Because this function rewrites user clinical queries, the bounded-similarity gate is the safety behavior the test name promises to protect; keep an explicit assertion or executable check for the threshold.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants