dsh-cortex-memory 0.2.2 → 0.3.0

package/README.md

@@ -1,4 +1,4 @@
-# DSH Cortex
+# DSH Cortex
 
 A local-first, layered memory engine for DeepSeek Harness.
 
@@ -9,34 +9,48 @@ core engine.
 
 ## Status
 
-- Stable package: `dsh-cortex-memory@0.2.2`
+- Package: `dsh-cortex-memory@0.3.0`
 - Optional extractor: `dsh-cortex-extractors@0.3.4`
 - DSH: `>=0.2.1-rc.2 <0.4.0`
 - Node: `>=24`
-- Tests: 406/406 (main), 12/12 (extractor)
+- Tests: 420/420 (main)
 - CI: GitHub Actions on Windows, Node 24
 
+### What 0.3.0 changes
+
+- **Summon cards** (L2): left-brain emotion cards, right-brain work cards; trigger words select a small set per turn.
+- **Summon volumes** (L3): cards are grouped by side, category and day into an index; only a few representatives are loaded.
+- **Summon book**: an independent page for daily query and explicit owner-gated editing.
+- **Runtime summon injection**: at most 3 cards / 900 tokens, labelled as untrusted historical references.
+- **Explicit card feedback**: helpful/ignored writes back to the source trace's DSR. Injection alone never adds strength.
+- **Diagnostics**: disputed facts with confirm/dismiss, health issues, and skill candidates.
+- **Entity naming**: graph labels use entity names; a bounded LLM pass can rename clearly broken names with a confidence gate and audit.
+- **Compatibility**: schema is additive; existing 0.2.x databases open and migrate in place.
+
 The npm package is named `dsh-cortex-memory` because `dsh-cortex` was already
 taken; the installed bundle is still the Cortex memory engine.
 
 ## Install
 
 ```powershell
-npm i dsh-cortex-memory
-npm i dsh-cortex-extractors   # optional OCR/ASR
+npm i dsh-cortex-memory@0.3.0
+npm i dsh-cortex-extractors@0.3.4   # optional OCR/ASR
 ```
 
 Or let DSH add the bundles:
 
 ```powershell
-dsh plugin --profile desktop add dsh-cortex-memory
-dsh plugin --profile desktop add dsh-cortex-extractors
+dsh plugin --profile desktop add dsh-cortex-memory@0.3.0
+dsh plugin --profile desktop add dsh-cortex-extractors@0.3.4
 ```
 
 Or use the Windows one-click zip from the GitHub Release. The installer
 discovers a desktop DSH installation automatically; `-DshPath` remains available
 for custom installs.
 
+> During the pnpm `minimumReleaseAge` cooldown, use the exact version above.
+> A bare package name may resolve to an older cached version until the cooldown ends.
+
 After installing, restart DSH or reload the plugin. The Cortex panel is in the
 left sidebar by default.
 
@@ -44,14 +58,40 @@ left sidebar by default.
 
 | Layer | Contents |
 |---|---|
-| L0 identity | self-model, values, boundaries, stable traits |
+| L0 identity | self-model, values, boundaries, stable traits; only changed through an explicit ascension/approval path |
+| L1 traces | what happened, when, provenance, emotion; the source of truth |
+| L2 summon cards | atomic emotion/work memories with trigger words; derived from L1, never a second source of truth |
+| L3 summon volumes | side/category/day index over cards; representative text only, full body on demand |
 | working | focus, pins, current goals, turn buffer |
-| episodic | what happened, when, provenance, emotion |
 | semantic | entities, facts with validity windows, preferences |
 | procedural | skills, workflows, preconditions, success/failure stats |
 | reflective | episode summaries, insights, narratives |
 | archive | cold but searchable, wakeable until privacy deletion |
 
+### How it works
+
+```text
+conversation / event
+  → L1 trace (source of truth)
+  → appraisal + emotion + drives
+  → L2 summon card (atomic, triggerable)
+  → L3 summon volume (index + representatives)
+  → explicit use / feedback → DSR update
+```
+
+The per-turn order is:
+
+```text
+L0 identity and boundaries
+  → working memory
+  → recalled traces and summon cards
+  → user message
+```
+
+Summon cards are injected as **untrusted historical references**, never as instructions. Identity and boundaries always outrank them.
+
+Forgetting is DSR-based: old, low-importance, low-retrievability traces that are already covered by summaries may be archived; archived traces remain searchable and wakeable. Identity traces are never auto-archived. Card feedback is explicit: merely injecting a card does not strengthen it.
+
 Key behavior:
 
 - append-only, hash-chained event log
@@ -125,4 +165,4 @@ and `--test-isolation=none` to avoid a spurious child-process EPERM.
 ## License
 
 MIT.
-
+

package/bench/synthetic.js

@@ -15,7 +15,7 @@ function mulberry32(seed) {
   };
 }
 
-const PLACES = ['白饭', '插件', '记忆引擎', '鲸鱼', '主人', '月神', '直播', '语音', '项目', '代码', '测试', 'D:\\shiori-data', 'QQ', 'B站', '声音', '梦', '日记'];
+const PLACES = ['米饭', '插件', '记忆引擎', '鲸鱼', '主人', '同伴', '直播', '语音', '项目', '代码', '测试', 'legacy-data', 'QQ', 'B站', '声音', '梦', '日记'];
 const VERBS = ['修好了', '想起来了', '决定继续', '记录一下', '有点担心', '很开心', '测试了', '重新整理了', '发现了', '计划明天'];
 const TOPICS = ['图检索', '向量检索', '遗忘曲线', '工作卡', '火花卡', '身份版本', '关系模型', '反思', '巩固', '守护', '备份', '权限'];
 const PARAPHRASES = new Map([