agenr 2.0.0 → 2.1.0

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 CHANGED
@@ -2,6 +2,50 @@
2
2
 
3
3
  ## [Unreleased]
4
4
 
5
+ ## [2.1.0] - 2026-04-22
6
+
7
+ Recall ranking overhaul, before-turn memory patching, and eval/debug tooling minor release.
8
+
9
+ ### Added
10
+
11
+ - **Before-turn memory patching and eval coverage ship as a first-class recall surface.** Agenr now supports hybrid session-start patch selection, dedicated before-turn patch selection and reranking, internal before-turn eval routes, richer diagnostics, and corpus-backed fixture seeding for replay coverage.
12
+ - **Cross-encoder reranking and OpenClaw debug artifacts are now available.** The release adds an OpenAI-compatible cross-encoder stage, opt-in replay debug artifacts, and an agenr-only JSONL debug sink for OpenClaw runtime investigation.
13
+
14
+ ### Changed
15
+
16
+ - **Recall ranking is now built around reciprocal rank fusion plus diversification.** Unified recall now uses RRF as the primary relevance combiner, typed neighborhood expansion, MMR diversification, lineage-aware shaping, and tighter ordering and abstention rules.
17
+ - **Documentation and procedures were refreshed for the new recall model.** The recall guide was rewritten as a reference, procedural docs were updated, and the Obsidian LLM Wiki procedure was added to the repo-authored procedure set.
18
+
19
+ ### Fixed
20
+
21
+ - **Before-turn selector edge cases are more stable.** The release fixes fallback selection, short-name family matching, cross-encoder wiring, and small-pool top-1 ranking regressions that showed up while hardening the new ranking stack.
22
+
23
+ ### Validation
24
+
25
+ Changes since last push to `origin/master`:
26
+
27
+ - Add Obsidian LLM Wiki procedure and refresh procedures documentation
28
+ - Add before-turn memory patch selection, reranking, diagnostics, and internal eval seam
29
+ - Adopt reciprocal rank fusion, typed neighborhood expansion, and MMR diversification across recall pipelines
30
+ - Add cross-encoder reranking and wire it through recall and before-turn eval seams
31
+ - Tune ordering, abstention, thresholds, and lineage shaping for snapshot and before-turn ranking quality
32
+ - Add precision-first entity attribute recall
33
+ - Refresh recall and eval documentation and land corpus-backed replay and debug tooling
34
+
35
+ ## [2.0.1] - 2026-04-13
36
+
37
+ OpenClaw startup-failure handling patch release.
38
+
39
+ ### Fixed
40
+
41
+ - **OpenClaw plugin startup no longer crashes on agenr service initialization failures.** Startup-time database schema mismatches and similar initialization errors are now logged and surfaced as stable runtime/status failures instead of escaping as an unhandled promise rejection.
42
+
43
+ ### Validation
44
+
45
+ Changes since last push to `origin/master`:
46
+
47
+ - Handle OpenClaw startup schema mismatch failures gracefully
48
+
5
49
  ## [2.0.0] - 2026-04-13
6
50
 
7
51
  Procedural memory foundation, sync and recall pipelines, and unified routing major release.
@@ -1,5 +1,5 @@
1
1
  import * as openclaw_plugin_sdk_plugin_entry from 'openclaw/plugin-sdk/plugin-entry';
2
- import { T as TranscriptPort, P as ParsedTranscript } from '../../ports-D2NOK2gR.js';
2
+ import { T as TranscriptPort, P as ParsedTranscript } from '../../ports-Nj5nd2Ri.js';
3
3
 
4
4
  /**
5
5
  * Parses OpenClaw JSONL session exports into normalized agenr transcripts.