agenr 0.9.91 → 0.9.93
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/CHANGELOG.md +28 -0
- package/dist/{chunk-3ACXGY5A.js → chunk-JTQXI332.js} +721 -64
- package/dist/{chunk-72P7SUVD.js → chunk-LQRZWCMN.js} +1 -1
- package/dist/{chunk-HRGV2SYO.js → chunk-V4TO364M.js} +18 -6
- package/dist/cli-main.js +1052 -309
- package/dist/{maintain-W23MDSKD.js → maintain-NBNOASPQ.js} +2 -2
- package/dist/openclaw-plugin/index.js +2 -2
- package/package.json +1 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,33 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [0.9.93] - 2026-03-13
|
|
4
|
+
|
|
5
|
+
### Added
|
|
6
|
+
|
|
7
|
+
- Added focused gold-eval coverage and regression protections for fallback surfaced-set suppression, blocker-shaped current-state routing, natural prerequisite pair assembly, residual holdout abstain/pair-selection cases, and currentness-update-posture bundle/commitment-state cases.
|
|
8
|
+
- Added memory-formation eval diagnostics that preserve extractor warnings in gold harness artifacts, making provider/auth failures visible instead of collapsing them into misleading empty extraction results.
|
|
9
|
+
|
|
10
|
+
### Fixed
|
|
11
|
+
|
|
12
|
+
- Hardened fallback surfaced-set selection so answer-bearing support can suppress adjacent same-topic distractors without reopening broad ranking changes.
|
|
13
|
+
- Fixed blocker-shaped `still blocked` status questions so they route into current-state/resolved-state handling instead of generic lexical fallback.
|
|
14
|
+
- Fixed natural prerequisite phrasing and bounded pair assembly so answerable prerequisite questions stop abstaining or dropping complementary support.
|
|
15
|
+
- Fixed residual holdout generic-intent abstain and prerequisite completeness cases, eliminating the last holdout distractor-intrusion failures.
|
|
16
|
+
- Fixed currentness-update-posture residuals by routing bounded policy-bundle questions into pair handling and tightening commitment-state recognition for settled `code slice` phrasing.
|
|
17
|
+
- Fixed sandbox eval credential resolution so inherited bad API-key env vars no longer override valid sandbox-config credentials during eval runs.
|
|
18
|
+
|
|
19
|
+
## [0.9.92] - 2026-03-13
|
|
20
|
+
|
|
21
|
+
### Added
|
|
22
|
+
|
|
23
|
+
- Added an `agenr eval harness --mode recall-regression` path for replaying live-brain snapshot recall cases as focused regression suites, with targeted fixtures and assertions for rank expectations and trace inspection.
|
|
24
|
+
- Added targeted full-recall regression coverage for lexical-candidate rescue and affinity-rerank edge cases, including generic-subject strong body matches and direct workspace repair answers with only soft meta wording.
|
|
25
|
+
|
|
26
|
+
### Fixed
|
|
27
|
+
|
|
28
|
+
- Tightened lexical candidate rescue so strong handoff-style body matches can survive vector-top-k misses and reach reranking in bounded recall flows.
|
|
29
|
+
- Refined affinity reranking so soft meta signals such as `workspace` or procedural wording no longer blanket-demote otherwise direct operational answers, while preserving demotion pressure for genuinely meta/config memories on non-meta queries.
|
|
30
|
+
|
|
3
31
|
## [0.9.91] - 2026-03-13
|
|
4
32
|
|
|
5
33
|
### Added
|