@agenr/openclaw-plugin 0.10.1 → 0.11.1
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 +38 -0
- package/dist/index.js +1848 -13255
- package/package.json +6 -1
package/CHANGELOG.md
CHANGED
|
@@ -1,5 +1,43 @@
|
|
|
1
1
|
# Changelog
|
|
2
2
|
|
|
3
|
+
## [0.11.1] - 2026-03-18
|
|
4
|
+
|
|
5
|
+
### Fixed
|
|
6
|
+
|
|
7
|
+
- Fixed `@agenr/openclaw-plugin` package missing `openclaw.extensions` field, which prevented OpenClaw from installing the plugin.
|
|
8
|
+
|
|
9
|
+
## [0.11.0] - 2026-03-18
|
|
10
|
+
|
|
11
|
+
### Changed
|
|
12
|
+
|
|
13
|
+
- **Recall pipeline rebuilt from scratch.** Removed ~42,000 lines of heuristic post-processing (decision policies, confidence gates, category rollup assembly, suppression chains, lexical rescue, expansion heuristics, name-bound token matching) and replaced them with a clean ~1,750-line retrieval pipeline: normalize → embed → scoped vector search → lexical search → combine scores → rerank top-N → top-k → return.
|
|
14
|
+
- Added a narrow second-stage reranker with query intent detection. The reranker operates only on a bounded candidate window and uses query-conditioned features (lexical specificity, scope match, metadata signals, temporal markers) instead of global corpus-wide score adjustments.
|
|
15
|
+
- Improved lexical candidate admission: FTS now evaluates all query variants before trimming, subject overlap is scored separately from content overlap, and recent/state-like entries get query-conditioned admission preference.
|
|
16
|
+
- Simplified the eval harness to measure ranked retrieval directly (hit@k, MRR, precision@k, scope bleed) instead of tracking deleted heuristic concepts.
|
|
17
|
+
|
|
18
|
+
### Added
|
|
19
|
+
|
|
20
|
+
- Added deterministic ingest-time classification: `entry_kind` (directive, state, identity, episode, reference) and `temporal_class` (ephemeral, durable) columns on entries, assigned at store time using type, subject, and content signals. No LLM calls — pure pattern matching.
|
|
21
|
+
- Added tag-based project inference at store time: entries with a single known-project tag and no explicit project assignment are automatically promoted.
|
|
22
|
+
- Added `agenr maintenance classify-entries` command to backfill classification metadata on existing databases.
|
|
23
|
+
- Added rerank intent detection (`policy_seeking`, `status_seeking`, `recentness_seeking`, `topic_seeking`, `general`) used exclusively by the reranker to condition feature weights.
|
|
24
|
+
|
|
25
|
+
### Fixed
|
|
26
|
+
|
|
27
|
+
- Fixed exact-policy queries consistently losing rank to generic same-topic entries.
|
|
28
|
+
- Fixed session handoff and status queries being polluted by handoff-infrastructure notes.
|
|
29
|
+
- Fixed temporal/recency queries returning older durable entries instead of recent events.
|
|
30
|
+
- Reduced project scope bleed in retrieval results.
|
|
31
|
+
|
|
32
|
+
### Removed
|
|
33
|
+
|
|
34
|
+
- Removed decision-policy state machine, confidence gates, and mode-dependent dispatch (~3,500 lines).
|
|
35
|
+
- Removed category rollup assembly subsystem (~3,700 lines).
|
|
36
|
+
- Removed suppression framework and reflection suppression (~800 lines).
|
|
37
|
+
- Removed rescue mechanisms (change-lookup-prior-state-rescue, structured-state-rescue).
|
|
38
|
+
- Removed query expansion heuristics, name-bound token matching, and topic-specific boosting.
|
|
39
|
+
- Removed surface-selection heuristics and compact-bundle diagnostics.
|
|
40
|
+
|
|
3
41
|
## [0.10.1] - 2026-03-17
|
|
4
42
|
|
|
5
43
|
### Fixed
|