Remove Evidence-based and All sources chips from answer footer - #293
Closed
BigSimmo wants to merge 22 commits into
Closed
Remove Evidence-based and All sources chips from answer footer#293BigSimmo wants to merge 22 commits into
BigSimmo wants to merge 22 commits into
Conversation
The golden retrieval set was 100% lexical fast-path (embedding_skipped_rate=1.0), so it could not measure whether a re-index changes vector/embedding retrieval quality. - forceEmbedding option on searchChunksWithTelemetry (SearchChunksArgs): bypasses every lexical text-fast-path so retrieval always exercises the embedding/vector stage. Diagnostic/eval-only; folded into the search cache key; never set on production paths. - eval-retrieval.ts: per-case `forceEmbedding` field + a global `--force-embedding` flag. - 10 `vector-*` cases (psychiatric monographs: PTSD, OCD, panic, anorexia, GAD, Tourette, postnatal, bipolar, ADHD, opioid) with forceEmbedding=true. Each is a clinical query that must be answered by vector retrieval of the right monograph — verified live at document_recall@5=1.0, content_recall@5=1.0, all via strategy=hybrid (embedding used). Rationale: forcing embedding is the correct instrument for re-index measurement — you want to measure the vector index directly, not have a lexical shortcut mask a regression. Wording alone can't reliably force the vector path (the fast-path is driven by emergent lexical-match strength), so the flag makes these probes deterministic. Live golden eval: 34/34 pass (24 existing + 10 new), no regression. verify:cheap green (980). Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Wire forceEmbedding through eval runners and retrieval cache keys, bypass coverage/lexical shortcuts when forced, and add golden-case failure metrics so vector regressions cannot hide behind text-fast-path or cache hits.
…board Delete post-extraction dead code left in the monolith and trim unused imports. Also fix minor lint issues in favourites-hub, visual-evidence, and services-navigator.
…rdening fix(access): complete public retrieval scope and production access hardening
fix: restore anonymous production setup-status for psychiatry.tools
|
Updates to Preview Branch (cursor/remove-answer-bar-chips-8b1a) ↗︎
Tasks are run on every commit but only new migration files are pushed.
❌ Branch Error • Sun, 05 Jul 2026 18:59:39 UTC View logs for this Workflow Run ↗︎. |
BigSimmo
force-pushed
the
cursor/fix-all-db-issues-5f13
branch
from
July 5, 2026 17:53
bf46bb0 to
09b3567
Compare
BigSimmo
marked this pull request as ready for review
July 5, 2026 17:59
|
You have reached your Codex usage limits for code reviews. You can see your limits in the Codex usage dashboard. |
- Reduce answer composer inset to match chipless footer and restore scope focus target - Remove one-shot commit-access-rag-fix maintenance script - Include public corpus in owner-scoped retrieval_owner_matches SQL - Pin tools launcher selection while detail panel is open - Store anonymous public uploads with null owner_id and public storage paths - Register document_upload API rate limit bucket with defaults
BigSimmo
force-pushed
the
cursor/fix-all-db-issues-5f13
branch
2 times, most recently
from
July 5, 2026 18:42
6201117 to
09b3567
Compare
Co-authored-by: Cursor <cursoragent@cursor.com>
Owner
Author
|
Superseded by #303 — clean branch from main with full footer chip removal (all modes, not answer-only). |
Owner
Author
|
Closing in favor of #303 |
BigSimmo
pushed a commit
that referenced
this pull request
Aug 12, 2026
… rows Repairs. Two main-merges silently reverted edits from this branch, and the re-apply script missed them because it was hand-enumerated from round 1's second commit only: - #293 the entire min-h-tap refutation was gone (grep sm:min-h-0 returned 0); the row was back to asserting a defect that does not exist. Restored from a6bfc6f. This was the live hazard — as reverted it directed a reader to strip desktop step-downs and pin every control to 48px. - #266 restored the 2026-08-12 counts (54/31/23) over main's older 53/30/23. - #262 deliberately NOT restored: main's version is newer than mine and records --shadow-tight retired outright on 2026-08-10. - #289 archived; verified fixed in round 1 and never actually closed. Stamps. Sixteen rows were checked during the sweep, found correct, and left unchanged — which left no trace, so they were indistinguishable from rows nobody had opened. Each now carries VERIFIED CORRECT 2026-08-12 plus the measurement that settled it. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017paT42ZVMf8jaLtkjFxdy5
BigSimmo
added a commit
that referenced
this pull request
Aug 12, 2026
…310) and the ledger loss-detector (#311) (#1870) * docs(issues): capture the fuzzy-search drug-match finding and the loss-detector #310 — PR #1851's fuzzy catalogue search matches DIFFERENT drugs at edit distance 2. Measured by running the PR's own algorithm rather than reading it: fluoxetine -> duloxetine (Damerau counts the lu->ul transposition as one edit, both are 10 chars, so the >=8 tier's 2-edit budget allows it) and prednisone -> prednisolone. Intended recovery still works (sertraline, olanzapine) and the short-term guards hold (SSRI/SNRI, ADHD/ODD). Two real mitigations recorded so it is not over-read: fuzzy fires only when nothing matched literally, and sub-5-character terms are excluded. Tested fix is one line — cap the >=8 tier at 1 edit, which kills both cross-drug hits and keeps every legitimate typo case. Blast radius is eleven modules including medications.ts, because catalog-search.ts feeds the whole clinical catalogue. #311 — promote the derived ledger loss-detector into scripts/. Two main-merges silently reverted ledger edits this session, including the whole #293 refutation, and the hand-enumerated recovery list could not catch it. The derived version has now earned its place twice. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_017paT42ZVMf8jaLtkjFxdy5 * chore(ledger): record the finding-capture handoff Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> * chore(ci): run focused PR 1870 ledger correction * chore(ci): use repository Node version for PR 1870 fix * ci(pr-1870): merge current main and finalise ledger fixes * ci(pr-1870): scope final verification and publish normally --------- Co-authored-by: Claude <noreply@anthropic.com> Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
4 tasks
BigSimmo
pushed a commit
that referenced
this pull request
Aug 14, 2026
…merged #215, #210, and #293 were queued as `done` in this same PR, each citing a PR (#1949, #1953, #1962) that turned out still to be open, not merged — verified by checking whether each PR's actual file change is present on origin/main (none are). Reconciling the original `done` requests would have closed these rows while their fixes exist only on unmerged branches, one of which (#1949) currently has failing required CI. Converts all three to `update` requests documenting the correction and the real current state, so reconciling this PR now cannot close a row before its fix has actually landed. Leaves #98, #189, and #194 as `done` unchanged — those cite PR #1950 and PR #1947, both confirmed merged into main.
BigSimmo
added a commit
that referenced
this pull request
Aug 14, 2026
BigSimmo
pushed a commit
that referenced
this pull request
Aug 15, 2026
BigSimmo
added a commit
that referenced
this pull request
Aug 15, 2026
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Removes the Evidence-based and All sources footer chips from the answer-mode composer on all screen sizes. The answer bar now shows only the input pill and send button.
Scope and evidence remain reachable via the integrated + menu (
ScopeandEvidence mapactions).Changes
master-search-header.tsx: Hide footer chip row whensearchMode === "answer"only.ui-accessibility.spec.ts/ui-smoke.spec.ts: Open scope via + menu (Scope).capture-chrome-parity.ts: Drop removed chip selectors.scripts/capture-answer-bar-screenshot.ts: QA screenshot helper.Verification
Previously on this branch: accessibility e2e (2 passed) and demo answer smoke test passed.
Local screenshot: