agenr 0.9.65 → 0.9.68

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
@@ -1,5 +1,68 @@
1
1
  # Changelog
2
2
 
3
+ ## [0.9.68] - 2026-03-05
4
+
5
+ ### Added
6
+
7
+ - Added standalone `agenr synthetic` command to generate synthetic recall signals against existing database entries without re-running ingest.
8
+ - Added `agenr synthetic` options for source-file scoping, similarity/session/event thresholds, dry-run mode, JSON output, and optional post-pass quality seeding.
9
+ - Added command coverage for standalone synthetic execution, dry-run no-write behavior, source-file scoping, and quality seeding flow.
10
+
11
+ ### Changed
12
+
13
+ - `agenr backfill-claims` now runs claim extraction in parallel with a configurable `--concurrency` limit (default `5`), significantly reducing wall-clock time for large databases. The default `--batch-size` also increased from `10` to `50`.
14
+
15
+ ### Fixed
16
+
17
+ - `agenr ingest` now runs synthetic recall generation by default after successful ingest; use `--no-synthetic` to disable the post-ingest synthetic pass.
18
+ - Updated synthetic ingest documentation and tests for the default-on behavior, including explicit `--no-synthetic` disable coverage.
19
+ - Claim extraction during ingest is now disabled by default for better ingest throughput; use `--claims` to opt in, or run `agenr backfill-claims` for bulk claim extraction.
20
+ - Added `agenr ingest --contradiction` to explicitly enable contradiction checks during ingest regardless of config.
21
+ - Clarified and tested ingest contradiction defaults: contradiction checks remain disabled by default unless `config.contradiction.enableDuringIngest === true` or `--contradiction` is passed.
22
+ - OpenClaw plugin `agenr_store` now defaults `platform` to `openclaw` when the tool call omits `platform`, while preserving explicitly passed platform values.
23
+ - Added OpenClaw tool registration tests covering `agenr_store` default platform injection and explicit platform pass-through.
24
+ - Fixed OpenClaw session-start dedupe persistence: `hasSeenSession`/`markSessionSeen` now use a durable `seen_sessions` SQLite table with in-memory map fast-path caching.
25
+ - Added OpenClaw session dedupe diagnostics (`hasSeenSession key=... found=... mapSize=...`) to detect map resets and repeated `isFirst=true` triggers.
26
+ - Added seen-session cleanup and limits for OpenClaw dedupe state (evict rows older than 24 hours and cap persisted rows to `AGENR_OPENCLAW_MAX_SEEN_SESSIONS`).
27
+ - Added OpenClaw regression tests for first/second-hit dedupe behavior, persistence across simulated module reload, stale-row cleanup, and max-row capping.
28
+
29
+ ## [0.9.67] - 2026-03-05
30
+
31
+ ### Added
32
+
33
+ - Added hybrid mid-session recall presentation in OpenClaw plugin: inject top matches and surface remaining matches as a `[MEMORY CHECK]` subject summary nudge.
34
+ - Added `midSessionRecall.mode` config with `hybrid` (default), `inject` (legacy), and `nudge` modes.
35
+ - Added `midSessionRecall.injectMax` config (default `2`) to control how many entries are directly injected in hybrid mode.
36
+
37
+ ### Changed
38
+
39
+ - Mid-session recall now defaults to `hybrid` mode instead of injecting all fresh matches.
40
+ - Added nudge suppression when the most recent assistant turn already includes an `agenr_recall` tool call.
41
+
42
+ ## [0.9.66] - 2026-03-04
43
+
44
+ ### Added
45
+
46
+ - Added `agenr recall --index --json` for project-grouped memory index output (`projects`, `totalEntries`).
47
+ - Added `--null-project` as an explicit `agenr recall` filter for NULL-project-only queries.
48
+ - Added OpenClaw plugin memory-index module at `src/openclaw-plugin/memory-index.ts` with dedicated formatter and unit tests.
49
+ - Added pre-store embedding dedup layer for ingest (#474) with 0.90 threshold, sameType gate, event exclusion.
50
+ - Added `survivorEmbeddings` return from pre-store dedup, threaded `EmbeddingCache` through write queue into `storeEntries`.
51
+ - Added `embeddingCache?: EmbeddingCache` to `StoreEntriesOptions`.
52
+
53
+ ### Changed
54
+
55
+ - OpenClaw session-start browse recall now uses stricter universal filters (`--null-project`, `--min-importance 7`) with a 30-day window and a 20-entry cap.
56
+ - OpenClaw session-start memory index is now loaded through `agenr recall --index --json`.
57
+
58
+ ### Fixed
59
+
60
+ - Capped consolidation reflection importance at max source importance (hard cap 8 unless source was 9+) to prevent importance inflation during merges (#472).
61
+ - Added merge prompt guidance: "Merging entries does not make them more important - it makes them more concise."
62
+ - Added retroactive fix to downgrade inflated importance-9 reflections to 7.
63
+ - Fixed consolidate leaving superseded source entries as active; they are now properly retired with reason 'superseded' (#465).
64
+ - Added maintain task to retroactively retire existing superseded-but-active ghost entries.
65
+
3
66
  ## [0.9.65] - 2026-03-04
4
67
 
5
68
  ### Added
package/README.md CHANGED
@@ -244,6 +244,7 @@ This exposes four tools: `agenr_recall`, `agenr_store`, `agenr_extract`, `agenr_
244
244
  | `agenr config` | Show and update agenr configuration |
245
245
  | `agenr auth` | Authentication status and diagnostics |
246
246
  | `agenr ingest <paths...>` | Bulk-ingest files and directories |
247
+ | `agenr synthetic` | Generate synthetic recall signals from existing DB entries (no re-ingest required) |
247
248
  | `agenr extract <files...>` | Extract knowledge entries from text files |
248
249
  | `agenr store [files...]` | Store entries with semantic dedup |
249
250
  | `agenr recall [query]` | Semantic + memory-aware recall. Use `--since`/`--until` for date ranges, `--around` for target-date ranking, `--browse` for temporal mode. |