Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions CHANGELOG.md
Original file line number Diff line number Diff line change
Expand Up @@ -8,6 +8,12 @@ Please choose versions by [Semantic Versioning](http://semver.org/).
* MINOR version when you add functionality in a backwards-compatible manner, and
* PATCH version when you make backwards-compatible bug fixes.

## Unreleased

- feat: golden set covers `curated-1` — 155 entries over 20 PRs, up from 42 over 5. All 115 unmatched findings from the curated-1 Opus pass were adjudicated individually: 113 new entries, plus 2 findings that turned out to be an issue the set already held, re-reported in different words, where the existing key was relaxed rather than duplicated. One issue, one entry — a duplicate is what inflated recall to a spurious `1.000` in `v0.37.0`
- feat: **`rejected` entries 1 → 20, so precision can now actually be lost.** The set was 42 accepted / 1 rejected, and the report page said outright that no configuration could lose precision. A finding is rejected when it is a correct observation naming no defect: polish, taste, or a consequence the finding itself concludes is intended. The clearest cluster is `github-releaser-agent#8`, where four findings disqualify themselves in their own text — *"worth a follow-up rather than in isolation"*, *"not a correctness fix"*, *"so not a deviation"*, *"raise as a dark-factory issue rather than here"*
- fix: `path` may be null on a golden entry. A commit-message finding (*"commit `c6f136a` — subject is 62 chars"*) has no file, and since identity stopped reading `path` it no longer needs one. The live-set check required it to be truthy, which rejected exactly those legitimate entries

## v0.41.0

- fix: golden-set identity is the signature alone. `rule_id` is now an additional constraint when both sides carry one, never a short-circuit, and neither `path` nor `line` is read. Both defects were demonstrated on real rows before the change: the `github-pr-review-agent#11` CHANGELOG entry (a bullet bundling three concerns) matched an unrelated `fix:`-vs-`chore:` prefix finding purely because both carried `changelog/conventional-prefix-required`, so any configuration finding *some* instance of a rule was credited with the specific one; and the "write-scoped token still minted under `--skip-post`" issue, keyed to `pkg/factory/runner.go`, scored a miss when a later run anchored it at `cmd/run-task/main.go` while naming `runner.go` in its own body
Expand Down
Loading
Loading