Bump actions/checkout from 4 to 6 - #1
Closed
dependabot[bot] wants to merge 1 commit into
Closed
Conversation
Bumps [actions/checkout](https://github.com/actions/checkout) from 4 to 6. - [Release notes](https://github.com/actions/checkout/releases) - [Changelog](https://github.com/actions/checkout/blob/main/CHANGELOG.md) - [Commits](actions/checkout@v4...v6) --- updated-dependencies: - dependency-name: actions/checkout dependency-version: '6' dependency-type: direct:production update-type: version-update:semver-major ... Signed-off-by: dependabot[bot] <support@github.com>
ContributorAuthor
Looks like actions/checkout is up-to-date now, so this is no longer needed. |
BigSimmo added a commit
that referenced
this pull request
Jul 2, 2026
The golden case "In the clinical flowchart, what is the next step after red-zone risk?" failed content-recall because the answer chunks (red zone -> escalate / urgent senior review) never reached the top 5. Three compounding causes, smallest fix applied at each level: 1. Candidate generation (root cause): the flowchart query variants "red zone risk flow" and "risk flow review urgent escalation" are fully conjunctive under websearch_to_tsquery and matched 0 and 2 live chunks - they contributed nothing. Replaced with a plain "red zone" variant (13 precise zone-action chunks live) gated on the query mentioning a zone. 2. Fast-path gating: both decideTextFastPath (document_lookup) and the visual_flowchart_risk_gate accepted action-free flowchart pages - the gate satisfied its two term groups across different results and image captions. Flowchart/zone action queries now require zone AND action language on a single top result before skipping structured retrieval (mirrors threshold_action_requires_structured_retrieval). 3. Ranking: riskFlowchartSource only recognised flowchart-worded text, so escalation protocols expressing the flowchart steps as prose took the -0.18 generic penalty while unrelated risk-assessment flowcharts kept the +0.16 boost. Zone+action text now counts as risk-flowchart source evidence. Validation: golden retrieval eval 10/10 (content_recall@5 1.0, up from 0.9667; doc_recall@5 1.0; hit_rate 1.0), latency eval 0 failures (median 1.2s, p90 12.1s), fixed case answers in ~1.0s via fast path with the correct evidence ranked #1. Full vitest 691 passed, typecheck and lint clean. Three new unit tests pin the gates and ranking rule. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
13 tasks
BigSimmo added a commit
that referenced
this pull request
Jul 3, 2026
* eval(retrieval): add content_mrr@10 passage-rank metric The golden retrieval eval measured document-level rank (mrr@10, over expectedDocumentSubstrings) and content-level *recall* (contentRecall@5, binary "is the answer passage in the top 5"), but nothing measured how HIGH the answer-bearing passage ranks. That left rerank/chunking changes that lift the right passage from #5 to #1 unprovable: content recall stays 1.0 across that move and doc-level mrr is blind to passage order within a document. Add contentReciprocalRankAt10 — the mean over a case's expected content terms of the reciprocal rank of the earliest top-10 result carrying that term (1.0 iff every term rides the rank-1 passage). Surface it in the summary as content_mrr_at_10, averaged only over cases that declare content terms (content_mrr_case_count) so structural zeros don't dilute the signal, plus a per-case contentRR@10 column and the human summary line. Purely additive: the summary type is inferred, so reindex-eval-gate and the other summary consumers are unaffected. Guarded by a focused test proving the metric drops to 0.5 when the answer passage is demoted below a distractor while content recall stays 1.0. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * Fix retrieval content MRR scoring * style: prettier-format eval-retrieval content_mrr scoring The retrievalLimitForGoldenCase fix landed without a prettier pass, failing the required verify check (format:check). Formatting-only; no logic change. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> * eval(retrieval): address Codex review on content_mrr@10 evidence text Two remaining P2 review findings on the passage-rank metric: - Quality-eval path truncation: runRetrievalQualityCases (eval-quality.ts) still fetched topK=testCase.topK, so content_mrr@10 silently degraded to content_mrr@topK for the many fixtures with topK<10. Now uses retrievalLimitForGoldenCase(=max(topK,10)), matching the standalone runner. hit@K semantics are unchanged (evaluateGoldenRetrievalCase still slices to the case's topK), so only positions 9-10 are exposed for the @10 metric. - Missing first-class table/visual evidence: resultContentEvidenceText matched table_facts and a few image fields but not typed index-unit content or the accessible table markdown / table rows, so a hit carrying the answer only in a medication-chart row / risk-matrix cell / flowchart step was invisible to contentReciprocalRankAt10. Now includes index_unit title+content and image accessibleTableMarkdown + flattened tableRows. The retrieval_synopsis stays in the evidence text: it is the stored first-class passage representation used in ranking/display, and the metadata-distractor test already guards the title/file/section vector that the earlier fix excluded. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> --------- Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
This was referenced Jul 8, 2026
BigSimmo pushed a commit
that referenced
this pull request
Jul 20, 2026
…idence (A-PR-2 part 3) lithium-therapy-monitoring was the only golden case with no document expectation, making its rr@10 a hardcoded 0.00 — measurement noise that masked real ordering headroom (live top-5: Lithium Clinical Guideline (EMHS) #1, Lithium Therapy Initiation (FSH) #2, Lithium (CAMHS) #3). expectedDocumentSubstrings gains ["Lithium"]: deliberately broad because the corpus carries multiple legitimate lithium guidelines (same pattern as the agitation pair) — the gate asserts subject precision in the top 5, not a single pinned title that would flake between equally-correct docs. Measured mrr@10 rises ~+0.028 from de-noising alone. Snapshot rebuilt from the same run-29763761133 artifact with the updated expectation so fixture and snapshot stay in lockstep (ranks 1-4 now grade as relevant; the psychotropic-generic rank 5 and the wrong-medication hard negative stay 0). Clinical sign-off note: this changes eval ground truth only — no runtime ranking behavior. Flagged in the PR for review. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01EXsJcLrbZUXwnBeG91cVo9
BigSimmo pushed a commit
that referenced
this pull request
Jul 22, 2026
…ce-metadata enums Address the CodeRabbit finding on the issue-#1 enum test: spy on logger.warn and assert it fires once per present-but-unrecognized document_status / clinical_validation_status / extraction_quality value (with field + value), while absent/blank inputs stay silent. Keeps the existing safe-fallback assertions — the return value is unchanged, so this pins the observability behaviour without altering any downstream ranking/rendering. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LRZ1EyBZW1ADXrZvMxEEsC
BigSimmo added a commit
that referenced
this pull request
Jul 22, 2026
6 tasks
5 tasks
BigSimmo pushed a commit
that referenced
this pull request
Jul 30, 2026
Three review rounds each found another row shape the detector silently dropped, because it asked "does this line look like a row?" and anything that did not was invisible to every check below. Patching the predicate a fourth time would only move the blind spot, so this inverts it: a table body is defined positionally, from its separator to the next heading or blank line, and every line in that span must be a well-formed row. Running that against the real file rather than its fixtures exposed the defect the previous logic was structurally unable to report. The archive section carries blank lines part way down its rows. GFM ends a table at the first blank line, so 56 of the 60 archived rows have been rendering as a paragraph of literal pipe characters, not as table rows. The prior checker passed that file with zero problems while counting all 114 rows. Rows outside every table are now their own reported failure, and the two stray blank lines are removed. Cell content is byte-identical; the row set sorts equal before and after, and the remaining churn is Prettier realigning what is now a single 60-row table. Also fixed while proving the new cases red: - ids are compared against a canonical zero-padded form, so `#1` and `#1` can no longer both exist as one allocation split across a merge - a deleted separator is reported rather than silently disabling the width check for its whole section - column counts are checked per block, against the width that block's own separator declares - body scanning uses an ATX heading test rather than startsWith("#"), because a row that loses its leading pipe begins `#1` — every id row does, so the old test ended the body early and hid the damaged row Six new self-test cases; five were green under the previous logic. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01FvU8z73P6TXUXoYBqN5K1P
18 tasks
7 tasks
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 freeto join this conversation on GitHub.
Already have an account?
Sign in to comment
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.
Bumps actions/checkout from 4 to 6.
Release notes
Sourced from actions/checkout's releases.
... (truncated)
Changelog
Sourced from actions/checkout's changelog.
... (truncated)
Commits
de0fac2Fix tag handling: preserve annotations and explicit fetch-tags (#2356)064fe7fAdd orchestration_id to git user-agent when ACTIONS_ORCHESTRATION_ID is set (...8e8c483Clarify v6 README (#2328)033fa0dAdd worktree support for persist-credentials includeIf (#2327)c2d88d3Update all references from v5 and v4 to v6 (#2314)1af3b93update readme/changelog for v6 (#2311)71cf226v6-beta (#2298)069c695Persist creds to a separate file (#2286)ff7abcdUpdate README to include Node.js 24 support details and requirements (#2248)08c6903Prepare v5.0.0 release (#2238)Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting
@dependabot rebase.Dependabot commands and options
You can trigger Dependabot actions by commenting on this PR:
@dependabot rebasewill rebase this PR@dependabot recreatewill recreate this PR, overwriting any edits that have been made to it@dependabot show <dependency name> ignore conditionswill show all of the ignore conditions of the specified dependency@dependabot ignore this major versionwill close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this minor versionwill close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself)@dependabot ignore this dependencywill close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself)