@jarkkojs/goosedump 0.12.11 → 0.12.12

package/README.md

@@ -1,8 +1,8 @@
 # goosedump
 
 `goosedump` browses, searches, converts, and compacts saved coding-agent
-conversations. It supports Claude Code, Codex, Crush, Gemini CLI, Goose,
-OpenCode, and Pi.
+conversations, and keeps project-scoped durable memory. It supports Claude Code,
+Codex, Crush, Gemini CLI, Goose, OpenCode, and Pi.
 
 It builds on ideas from [`lllyasviel/VCC`](https://github.com/lllyasviel/VCC).
 
@@ -63,72 +63,63 @@ model pull [all|embedding|text]
 `session copy`, `session remove`, and `memory forget` print their plan by default.
 Pass `--yes` to carry out the change.
 
-## Persistent memory
-
-`session compact` only creates a bounded summary; it never changes durable memory.
-Use `memory remember PROVIDER:ID` to retain unseen source events and extract atomic
-facts, decisions, preferences, procedures, and lessons with exact provenance.
-Remembering the same unchanged session is idempotent. When a new statement is close
-to an existing active memory of the same type, the older memory is marked superseded
-and linked to the successor. Human and JSON reports list each added statement
-(with `mem_` IDs) and any memories it superseded.
-
-`memory recall` searches the current project by default and fills an estimated token
-budget with ranked active memories. It first preserves exact lexical and entity-anchor
-matches (paths, crates, symbols, commands, concepts), expands through shared anchors,
-then fills remaining slots with BGE semantic matches. Existing databases are embedded
-in bounded batches; `memory status` reports indexed and pending counts. Pass `--history`
-to include superseded statements. Use `memory list` to browse, `memory show` to inspect
-provenance revision hashes, entities, and supersession links, and `memory forget` to preview
-deletion. Forgetting a memory ID removes the
-derived statement; forgetting `provider:session-id` removes that session's retained
-source events. Applied forgetting leaves content-free tombstones so deleted memory is
-not learned again accidentally.
-
-Summary output is bounded to an estimated 4096 tokens by default. Set
-`--summary-max-tokens NUMBER` to choose another budget, or use `0` for no limit.
-The bound is best-effort when preserved goals, blockers, decisions, and preferences
-alone exceed it.
-
-Session-index caches are versioned clean-break formats and are rebuilt when
-incompatible. Durable memory migrations preserve existing sources, statements, and
-evidence links; an unsupported schema version is rejected and must be reinitialized
-explicitly.
-
-## Inference performance
-
-The custom GPT-OSS-20B CPU engine uses every logical CPU available to the
-process by default. Override the compute thread count:
+## Compaction
+
+`session compact` creates a summary; it never changes durable memory. Summaries are
+bounded to an estimated 4,096 tokens by default. Use `--summary-max-tokens` to
+change the budget or `0` to disable it. The bound is best-effort when preserved
+goals, blockers, decisions, and preferences already exceed it.
+
+## Durable memory
+
+Memory is explicit and separate from compaction:
+
+1. **Remember:** [`gpt-oss-20b`](docs/models/gpt-oss-20b.md) extracts typed,
+   atomic statements with source provenance. [`bge-small-en-v1.5`](docs/models/bge-small-en-v1.5.md)
+   embeds each statement. SQLite stores the statements, vectors, and provenance.
+2. **Recall:** lexical and entity matches come first. Cosine-similar BGE vectors
+   fill the remaining slots. There is no separate vector database.
+
+Memories are classified as decisions, facts, preferences, procedures, or lessons.
+
+`memory remember` processes only new session entries, so remembering an unchanged
+session is idempotent. A new version of a memory can supersede an older active
+statement of the same type.
+
+Recall searches active memories from the current project by default. Use
+`--history` for superseded statements or `--all-projects` to search everywhere.
+`memory show` displays provenance, and `memory forget` leaves a tombstone so
+forgotten content is not learned again accidentally.
+
+Session-index caches are rebuilt when their format changes. Durable-memory schema
+migrations preserve stored sources, statements, and evidence links.
+
+## Local inference
+
+Both models run locally. Download them with `goosedump model pull`, or use
+`model pull text` or `model pull embedding`. Recall still uses lexical and entity
+matching when the embedding model is not cached.
+
+Text inference uses every logical CPU by default. Override it with
+`GOOSEDUMP_INFERENCE_THREADS`:
 
 ```sh
-GOOSEDUMP_INFERENCE_THREADS=6 \
-goosedump session compact pi:context-id
+GOOSEDUMP_INFERENCE_THREADS=6 goosedump session compact pi:context-id
 ```
 
-Compaction directive selection and durable-memory extraction use goosedump's custom
-GPT-OSS-20B CPU engine. Semantic recall uses the pinned 36.7 MB BGE-small-en-v1.5
-`Q8_0` encoder. Download both ahead of time with `goosedump model pull`, or select one
-with `goosedump model pull text` or `goosedump model pull embedding`. Recall falls back
-to lexical and entity matching when the embedding model is not cached.
-
-The `bench` feature builds a standalone harness that shells out to
-`goosedump session compact` with `GOOSEDUMP_PROFILE_COMPACT=1` and reports
-end-to-end and per-stage timings:
+The optional `bench` feature measures `session compact`. Keep the machine,
+session range, and model cache unchanged when comparing runs:
 
 ```sh
-# Edit benches/bench.txt to point at a real context, then:
+# Point benches/bench.txt at a real session first.
 cargo bench --features bench
 ```
 
-Each case emits JSON with per-run timing (including model loading), median and
-p95 latency, and per-stage medians and p95s. Keep the machine, context range,
-and model cache unchanged when comparing configurations.
-
 ## Pi extension
 
 The bundled [pi-goosedump extension](packages/pi-goosedump/README.md) adds
-session-history search, entry expansion, durable-memory recall, CWD-scoped session management,
-memory forget/status maintenance, and turn-driven goosedump compaction to Pi:
+session search, durable memory, session management, and goosedump compaction to
+Pi:
 
 ```sh
 pi install npm:pi-goosedump
@@ -152,5 +143,6 @@ The published Linux x64 and arm64 binaries are static glibc PIEs.
 ### Third Party Attribution
 
 1. GPT-OSS-20B: Apache 2.0
-   - Downloaded on first use at run-time. The model is not distributed together
-     with goosedump.
+2. bge-small-en-v1.5: MIT
+
+The models are downloaded at run time and are not distributed with goosedump.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@jarkkojs/goosedump",
-  "version": "0.12.11",
+  "version": "0.12.12",
   "description": "Coding agent context data browser",
   "license": "Apache-2.0 AND LGPL-2.1-or-later",
   "homepage": "https://github.com/jarkkojs/goosedump#readme",
@@ -21,10 +21,10 @@
     "LICENSE-LGPL-2.1"
   ],
   "optionalDependencies": {
-    "@jarkkojs/goosedump-darwin-arm64": "0.12.11",
-    "@jarkkojs/goosedump-linux-arm64": "0.12.11",
-    "@jarkkojs/goosedump-linux-x64": "0.12.11",
-    "@jarkkojs/goosedump-win32-x64": "0.12.11"
+    "@jarkkojs/goosedump-darwin-arm64": "0.12.12",
+    "@jarkkojs/goosedump-linux-arm64": "0.12.12",
+    "@jarkkojs/goosedump-linux-x64": "0.12.12",
+    "@jarkkojs/goosedump-win32-x64": "0.12.12"
   },
   "publishConfig": {
     "access": "public"