dsh-engram 0.4.0 → 0.5.0

package/README.md

@@ -23,6 +23,21 @@ with one goal: **save tokens**.
   integration**: a completed or blocked goal (`goal/change` session event)
   auto-sediments as a `handoff`/`error` memory (`tag:goal`), so the outcome of
   a goal survives its session (see the `GET /api/dsh-engram/goals` read surface).
+- **User-correction / preference learning (`autoCapturePreferences`, default on,
+  zero LLM)** — the lesson that "when the AI makes a mistake and gets corrected,
+  that lesson should persist" ([correx](https://github.com/ozoz5/correx),
+  [PAHF](https://arxiv.org/abs/2602.16173), Mem0 preference extraction): a
+  `session/event` listener watches `user/message` and turns deterministic
+  correction/preference cues into a dedicated `preference` memory kind —
+  Chinese (`不要用X`, `改用X`, `以后统一用X`…) and English (`don't use X`,
+  `switch to X`, `prefer X`, `never use X`…) patterns, three directions
+  (`avoid` / `switch-to` / `prefer`), with interrogative/one-shot-instruction/
+  memory-tool-meta-talk filters to keep false positives out. `preference`
+  memories outrank every other kind in the `[ENGRAM]` block (`[R]` prefix) so a
+  standing user rule is the first line the model sees each session; per-session
+  cap + recent-window dedup mirror the auto-capture discipline. Zero LLM, zero
+  embeddings, deterministic and pure — extracted clauses are bounded, and every
+  write still goes through the secret redactor.
 - **Symbolic index + progressive disclosure** — a compact `[ENGRAM]` block (default
   budget 700 chars ≈ 175 tokens; one line per memory) is injected at prompt
   assembly and **frozen per session**, keeping the request prefix byte-stable for
@@ -51,6 +66,12 @@ with one goal: **save tokens**.
   Pure rule, zero LLM, pure read (never bumps `hits`); superseded stale truth does
   not occupy an injection slot (still fetchable via `engram_detail`); frozen per
   session together with `[ENGRAM]` for prefix stability.
+- **Read-path activation (D)** — a hit whose one-line preview is truncated
+  (>140 chars) carries a `…` marker and the block's trailing guidance names that
+  concrete id: `#<id> truncated — engram_detail <id> (full) · engram_recall <query>`.
+  So the model knows the full record is one deterministic `engram_detail` call
+  away instead of assuming the preview is the whole memory (proven gap in real
+  use: 66 sessions, zero `engram_detail` calls — the detail path was invisible).
 - **Memory-to-memory semantics** — `engram_store` accepts optional
   `supersedes` / `contradicts` memory ids (validated against the same
   workspace). A superseded ("stale truth") memory is demoted to the tail of
@@ -243,8 +264,8 @@ curl -s -X POST http://127.0.0.1:3080/api/dsh-engram/import \
 <!-- dsh-market compatibility block — keep labels bilingual and in sync with
      docs/RELEASE-NOTES.TEMPLATE.md (market README convention) -->
 
-- **DSH 版本 / DSH versions**: `>=0.1.2-alpha.2 <0.2.0-0` (dsh-engram `0.3.7`; releases `0.2.0`–`0.3.6` support the old generation only — see matrix below)
-- **最后验证日期 / Last verified**: 2026-09-10 — full regression on `dsh-v0.1.5-alpha.1`; real-machine settings GET/PUT/conflict/reset/restart-persistence on `dsh 0.1.5-rc.1` (isolated profile)
+- **DSH 版本 / DSH versions**: `>=0.1.2-alpha.2 <0.3.0-0` (本版 `0.5.0`; 已发布的 `0.3.7`、`0.4.0` 仍声明旧的 `0.1.x` 范围 `>=0.1.2-alpha.2 <0.2.0-0` — 见下方矩阵)
+- **最后验证日期 / Last verified**: 2026-10-15 — 设置模型迁移（entry-id volatile Config，兼容 DSH `0.2.x`）落地，npm test 329/329 通过；真实 `dsh 0.2.0-rc.2` 隔离 profile 运行烟测通过（见下方“当前发布”）
 - **安装方式已验证 / Verified install**: `dsh plugin --profile web add dsh-engram`
 
 > **Short version.** Every **published** release (`0.2.0` … `0.3.6`) supports
@@ -257,7 +278,8 @@ curl -s -X POST http://127.0.0.1:3080/api/dsh-engram/import \
 | dsh-engram release | Status | DSH support | Declared via |
 | --- | --- | --- | --- |
 | `0.2.0` … `0.3.6` (npm, GitHub v0.3.3–v0.3.6) | published | **old DSH only** — `0.1.0-rc.7` / `0.1.0-rc.8` / `0.1.1-rc.1` / `0.1.1-rc.2` | peers `@deepseek-ai/dsh-*@^0.1.0-rc.7` |
-| `0.3.7` (npm, GitHub v0.3.7) | published | **new DSH only** — `>=0.1.2-alpha.2 <0.2.0-0` | `engines.dsh` + peers `>=0.1.2-alpha.2 <0.2.0-0` |
+| `0.3.7` / `0.4.0` (npm) | published | **new DSH, settings `installSection`** — `>=0.1.2-alpha.2 <0.2.0-0` | `engines.dsh` + peers `>=0.1.2-alpha.2 <0.2.0-0` |
+| `0.5.0` (本期 / this release) | pre-release | **DSH `0.1.2-alpha.2` … `<0.3.0-0`** — 设置卡迁移到 entry-id volatile Config（`0.1.7+`/`0.2.x`），`≤0.1.5` 自动回退 `installSection` | `engines.dsh` + peers `>=0.1.2-alpha.2 <0.3.0-0` |
 
 ### Where the API family broke — `0.1.2-alpha.2`
 
@@ -282,36 +304,72 @@ HTTP route (`/api/dsh-engram/settings`, same-origin fetch like the memory
 viewer), so the card is generation-agnostic on both sides of the
 `0.1.2-alpha.2` boundary.
 
+**One more settings break, at `0.1.7` / `0.2.0`** — and the reason `0.4.0` was
+not actually loadable on the current DSH: `@deepseek-ai/dsh-settings` **removed
+`settings.installSection` again** in `0.1.7-alpha.2` (and keeps it removed in
+`0.2.x`). The new settings model is **entry-keyed**: editable fields are
+`.volatile()` fields of the plugin's own `Config` (validated + hot-committed by
+the loader), and the settings form is keyed by the profile entry id (`engram`),
+so nothing needs "mounting". `0.5.0` feature-detects the two generations in
+`installEngramSettings`:
+
+- DSH `≥0.1.7` / `0.2.x` — the 27 GUI knobs are the volatile `Config` fields
+  (`lib/settings.js` `makeEngineConfigSchema`, exported as `Config` from
+  `lib/index.js`); the card reads/writes entry `engram` through the same
+  `/api/dsh-engram/settings` HTTP route, and the `service.settings` seam
+  re-syncs `resolved` on `loader/volatile-update` so card edits land live on
+  new sessions.
+- DSH `≤0.1.5` — the legacy `settings.installSection` namespace (`dsh-engram`)
+  is registered as before; nothing changes.
+
+The declared range `>=0.1.2-alpha.2 <0.3.0-0` covers both, and the HTTP wire
+namespace stays `dsh-engram` on both generations (the seam's active namespace
+drives mutations).
+
 So: keep DSH on `0.1.1-rc.2` or older while running a release ≤ `0.3.6`, and
 upgrade the plugin to `>=0.3.7` before moving DSH to `0.1.2-alpha.2`.
 
-### Current release — `0.4.0`
+### Current release — `0.5.0`
 
-This release declares support for DSH `>=0.1.2-alpha.2 <0.2.0-0` and was fully
-validated against the `dsh-v0.1.5-alpha.1` source and web runtime from the local
-`deepseek-harness` checkout.
+The published `0.4.0` declared `>=0.1.2-alpha.2 <0.2.0-0` — which the semver
+gate **rejects on every DSH `0.2.0-0` prerelease** (`<0.2.0-0` excludes
+`0.2.0-rc.x`), and its host settings half still called the `installSection`
+API that `dsh-settings 0.1.7+` removed. `0.5.0` fixes **both**: the range
+opens to `<0.3.0-0` (verified against DSH's own `includePrerelease` check, so
+`0.2.0-rc.2` and the whole `0.2.x` line pass), and the settings card is
+migrated onto the entry-id **volatile Config** model described above (with a
+feature-detected legacy fallback).
 
 | Component | Supported range |
 | --- | --- |
-| DSH runtime / host / client package family | `>=0.1.2-alpha.2 <0.2.0-0` |
+| DSH runtime / host / client package family | `>=0.1.2-alpha.2 <0.3.0-0` |
 | `@deepseek-ai/cordis` | `^4.0.2` |
 | `@deepseek-ai/schemastery` | `^3.18.2` |
 | Node.js | `>=22.19.0` |
 
-`0.1.2-alpha.2` is the minimum version for this API family: host settings use
-`settings.installSection`, and the browser settings card reads and writes
-through the plugin's own HTTP route (`/api/dsh-engram/settings`, see Route B
-above). Host import and settings-registration smoke checks pass on
-`0.1.2-alpha.2` and `0.1.3-alpha.2`; the full regression suite is validated
-on `0.1.5-alpha.1` (real-machine GET/PUT/conflict/reset/persist-across-restart
-all verified on `dsh 0.1.5-rc.1` with an isolated profile). The older
+`0.1.2-alpha.2` is the minimum version for this API family: host settings are
+**feature-detected** — on DSH `≤0.1.5` they register the `dsh-engram`
+namespace via `settings.installSection`; on `≥0.1.7` / `0.2.x` the form is the
+plugin's `Config` with the 27 GUI knobs marked `.volatile()` (entry id
+`engram`). The browser settings card reads and writes through the plugin's own
+HTTP route (`/api/dsh-engram/settings`, see Route B above) on both. The full
+regression suite (npm test 329/329, incl. the new settings-v2 coverage for the
+volatile-Config model) passes against the DSH `0.2.0-rc.2` dependency set
+(cordis 4.0.4 + schemastery 3.18.4 + cosmokit, matching the global DSH CLI).
+The `.volatile()`/loader hot-commit path and the describe-side projection were
+verified against the real `dsh-settings 0.2.0-rc.2` utilities, and a full
+real-machine boot smoke on an isolated `dsh 0.2.0-rc.2` profile **passed**:
+the plugin boots with no version-range denial, the settings card form is
+served for entry `engram` (all 27 GUI knobs, incl. `trustedHosts`), and a
+GET → PUT (`mutate` ops, revision 0→1) → unset round trip on
+`/api/dsh-engram/settings` lands in the profile row and reads back. The older
 `0.1.0-rc.7` and `0.1.1` API graphs are outside this release's compatibility
 range.
 
 To install the DSH version used for validation:
 
 ```sh
-npm install --global @deepseek-ai/dsh@0.1.5-alpha.1
+npm install --global @deepseek-ai/dsh@0.2.0-rc.2
 dsh --version
 ```
 
@@ -705,9 +763,59 @@ later request. The two switches are independent.
   simply never trigger (no boundary → no prune, zero side effects); the
   corpus-wide dry run activates on 38% of sessions. If the pruner service is
   absent the mechanism disables itself with one log line.
+- **Boundary sources**: todo-progress completion and goal terminal events
+  (default), plus an optional **request-count cadence**
+  (`boundaryPruneIdleCadence`, default 0/off) — the "step idle" source that
+  covers the ~62% of sessions which never touch todo/goal (recon:
+  `eval/recon-idle-boundary.mjs`; +85% saved chars at cadence 50 in the
+  counterfactual `eval/simulate-idle-cadence.mjs`), still repayment-gated.
+- **Threshold override**: `boundaryPruneThresholdChars` (default 0 → host's
+  8192). Set e.g. 2048 with smaller retained edges
+  (`boundaryPruneHeadChars`/`boundaryPruneTailChars`) to prune earlier —
+  T2048+small-edges lands 2.4× the first-prune savings of the host default on
+  the real corpus (10.14M vs 4.23M chars). Lowering the threshold is safe with
+  `resultPack` on, which archives the removed middles.
 - Default **off**: `boundaryPrune: false`. When on, the log shows
   `engram boundary-prune (todo @N reqs): pruned …`.
 
+### ResultPack L2 (archive + `result_recall`, default OFF)
+
+BoundaryPrune makes pruning lossless: the removed middle of every pruned
+tool result is redacted (same rules as the memory write path) and archived to
+`~/.dsh/engram/resultpack/<callId>.json`, and the pruned surface node gets a
+tail handle — `[middle archived: result_recall(<callId>) 可取]` — so the model
+knows the full result is one step away. `result_recall(callId, offset?)`
+returns the archived middle in paged text blocks (progressive disclosure, the
+same philosophy as `[ENGRAM]` → `engram_detail`, and the complete
+ObservationPack pattern from SoL-Pi mechanism ③).
+
+- **Lossless by construction**: L1 pruning shrinks the replay; L2 keeps the
+  original recoverable on demand — the "model rereads a pruned result" failure
+  mode goes to zero.
+- **Scoped cost**: archives live outside the memory domain (big blobs never
+  bloat the domain JSON or the [ENGRAM] index); retention is a mtime sweep
+  (`resultPackRetentionDays`, default 7) riding the same GC cadence.
+- **Self-disabling**: L2 without `boundaryPrune` has nothing to archive, so it
+  registers no tool and emits one warning.
+- Default **off**: `resultPack: false` (must be on together with
+  `boundaryPrune: true`). When active the log shows
+  `engram result-pack enabled: result_recall(callId, offset) registered`.
+
+### Activation telemetry (SoL-Pi M15/C13)
+
+Mechanisms must be provably activating, and dormant ones are off by default.
+`/api/dsh-engram/stats` (and the GUI overview) now answer
+`activation: { boundaryPrune, recall }`:
+
+- `boundaryPrune` — cumulative, durable record of real BoundaryPrune fires
+  (fires / prunedResults / charsRemoved / byKind todo|goal|step / lastFire),
+  written to `~/.dsh/engram/boundary-prune.status.json` on every landed prune,
+  independent of `resultPack`.
+- `recall` — the injection leg of the recall funnel: how many `[RECALL]`
+  blocks actually made it into sessions (`recall-injections.json`), closing
+  the loop already measured from session logs (engram_recall queries → hits →
+  engram_detail follows) so you can see injection→query→detail activation.
+
 ## Auto-capture policy
 
 Capture is deterministic and offline — it only sees tool *results*, never the
@@ -790,6 +898,15 @@ Defaults are token-conscious; override any key via the profile patch
 - id: engram
   config:
     autoCapture: true        # zero-LLM tool-result capture
+    autoCapturePreferences: true  # zero-LLM user-correction/preference capture (prefer/avoid/switch-to cues)
+    preferenceCapturePerSession: 8  # per-session preference memory cap
+    boundaryPrune: false       # ResultPack L1: prune stale over-threshold tool results at todo/goal boundaries (default OFF)
+    boundaryPruneThresholdChars: 0   # threshold override (0 = host 8192; e.g. 2048 prunes earlier)
+    boundaryPruneHeadChars: 0  # retained head under an override (0 = host 4096)
+    boundaryPruneTailChars: 0  # retained tail under an override (0 = host 1024)
+    boundaryPruneIdleCadence: 0   # request-count boundary for todo/goal-less sessions (0 = event-only)
+    resultPack: false          # ResultPack L2: archive pruned middles + result_recall paged recall (default OFF; needs L1 on)
+    resultPackRetentionDays: 7 # archive retention days (mtime sweep on the GC cadence)
     sessionSearch: true      # engram_recall may also FTS past sessions
     recallScope: workspace   # recall scope: "workspace" (strict isolation, default) | "global" (opt-in cross-workspace recall with [W:<ws>] origin markers)
     autoRecallOnStart: true  # session-start auto recall (false = back to pure pull)
@@ -816,7 +933,7 @@ Defaults are token-conscious; override any key via the profile patch
 ## Development
 
 ```sh
-npm test            # 279 tests: core + web API + GC + usage-observability + Context GC + ESR triggers + BoundaryPrune (node:test)
+npm test            # 291 tests: core + web API + GC + usage-observability + Context GC + ESR triggers + BoundaryPrune + preference learning (node:test)
 npm run eval        # offline recall + structure benchmark (deterministic)
 npm run build:client
 ```

package/README.zh.md

@@ -17,6 +17,15 @@
   + 失败行）自动捕获为 `tags:["error","test"]`、信号上调。DSH **goal 域打通**：completed/blocked 的
   goal（`goal/change` 会话事件）自动沉淀为 `handoff`/`error` 记忆（`tag:goal`），目标结局不随会话消散
   （读取面见 `GET /api/dsh-engram/goals`）。
+- **用户纠正/偏好学习（`autoCapturePreferences`，默认开，零 LLM）** — 「AI 犯错被纠正后，教训要留存」
+  （[correx](https://github.com/ozoz5/correx)、[PAHF](https://arxiv.org/abs/2602.16173)、Mem0 偏好提取）：
+  一个 `session/event` 监听器盯 `user/message`，用确定性纠正/偏好句式把用户话语沉淀为独立的
+  `preference` 记忆 kind——中文（`不要用X`、`改用X`、`以后统一用X`…）与英文（`don't use X`、
+  `switch to X`、`prefer X`、`never use X`…）模式，三种方向（`avoid` / `switch-to` / `prefer`），
+  并带疑问句 / 一次性操作指令 / 记忆工具元话语过滤器抑制误报。`preference` 记忆在 `[ENGRAM]`
+  块里**压过其它所有 kind**（`[R]` 前缀），让用户的长期规则成为每会话模型看到的第一行；
+  每会话上限 + 近期窗口去重与自动捕获同纪律。零 LLM、零向量、确定性纯函数——提取片段有界，
+  每条写入依旧先过密钥脱敏器。
 - **符号索引 + 渐进披露** — 一个紧凑的 `[ENGRAM]` 块（默认预算 700 字符 ≈ 175 token；每条记忆一行）在
   组装提示词时注入，并**按会话冻结**，让请求前缀字节稳定以复用 KV 缓存。模型需要细节时用
   `engram_recall` / `engram_detail` 下钻，而不是把命中的原文灌进上下文。召回对内存池做
@@ -35,6 +44,10 @@
   agentmemory 候选①）——相关记忆不依赖模型想起来就已在上下文里。纯规则、零 LLM、
   纯读不 bump 命中；superseded 过期真相不占注入槽（仍可 `engram_detail` 重取）；
   与 `[ENGRAM]` 一起按会话冻结保持前缀稳定。
+- **读路径激活（D）** — 命中条目的单行预览被截断（>140 字符）时带 `…` 标记，且块尾
+  引导行点名该具体 id：`#<id> truncated — engram_detail <id> (full) · engram_recall <query>`。
+  模型由此知道完整记录就在一次确定性 `engram_detail` 之后，而不是以为预览就是全文
+  （实证盲区：66 个会话 0 次 `engram_detail`——下钻路径此前对模型不可见）。
 - **记忆间语义（supersede/contradict）** — `engram_store` 可选收 `supersedes` / `contradicts`
   记忆 id（同工作区校验）。被 supersede 的「过期真相」在召回里**降级到尾部**、并从 `[ENGRAM]`
   块中**剔除**（新陈述占行）；被 contradicts 的记忆保留排序但标注 `· contradicted by <id>`。
@@ -153,8 +166,8 @@ curl -s -X POST http://127.0.0.1:3080/api/dsh-engram/import \
 
 <!-- dsh-market 兼容信息块 —— 与 docs/RELEASE-NOTES.TEMPLATE.md 的市场 README 公约保持一致 -->
 
-- **DSH 版本**：`>=0.1.2-alpha.2 <0.2.0-0`（dsh-engram `0.3.7`；`0.2.0`–`0.3.6` 仅旧代际 —— 见下文矩阵）
-- **最后验证日期**：2026-09-10 —— `dsh-v0.1.5-alpha.1` 完整回归；`dsh 0.1.5-rc.1` 隔离 profile 真机验证设置 GET/PUT/冲突/复位/跨重启持久化
+- **DSH 版本**：`>=0.1.2-alpha.2 <0.3.0-0`（本版 `0.5.0`；已发布的 `0.3.7`、`0.4.0` 仍声明旧的 `0.1.x` 范围 `>=0.1.2-alpha.2 <0.2.0-0` —— 见下文矩阵）
+- **最后验证日期**：2026-10-15 —— 设置模型迁移（entry-id volatile Config，兼容 DSH `0.2.x`）落地，npm test 329/329 通过；真实 `dsh 0.2.0-rc.2` 隔离 profile 运行烟测通过（见下文“当前发布”）
 - **安装方式已验证**：`dsh plugin --profile web add dsh-engram`
 
 > **一句话结论**：所有**已真正发布**的版本（`0.2.0` … `0.3.6`）**只支持旧版
@@ -165,7 +178,8 @@ curl -s -X POST http://127.0.0.1:3080/api/dsh-engram/import \
 | dsh-engram 发布版本 | 状态 | 支持的 DSH | 声明方式 |
 | --- | --- | --- | --- |
 | `0.2.0` … `0.3.6`（npm 全量 + GitHub v0.3.3–v0.3.6） | 已发布 | **仅旧版** —— `0.1.0-rc.7` / `0.1.0-rc.8` / `0.1.1-rc.1` / `0.1.1-rc.2` | peers `@deepseek-ai/dsh-*@^0.1.0-rc.7` |
-| `0.3.7`（npm + GitHub v0.3.7） | 已发布 | **仅新版** —— `>=0.1.2-alpha.2 <0.2.0-0` | `engines.dsh` + peers 同范围 |
+| `0.3.7` / `0.4.0`（npm） | 已发布 | **新版 DSH，settings `installSection`** —— `>=0.1.2-alpha.2 <0.2.0-0` | `engines.dsh` + peers 同范围 |
+| `0.5.0`（本期 / this release） | 预发布 | **DSH `0.1.2-alpha.2` … `<0.3.0-0`** —— 设置卡迁移到 entry-id volatile Config（`0.1.7+`/`0.2.x`），`≤0.1.5` 自动回退 `installSection` | `engines.dsh` + peers `>=0.1.2-alpha.2 <0.3.0-0` |
 
 ### API 族断裂点:`0.1.2-alpha.2`
 
@@ -185,33 +199,59 @@ curl -s -X POST http://127.0.0.1:3080/api/dsh-engram/import \
 HTTP 路由（`/api/dsh-engram/settings`，与记忆 viewer 同样的同源 fetch）读写
 `dsh-engram` settings namespace，因此在 `0.1.2-alpha.2` 分界线两侧都是代际无关的。
 
+**`0.1.7` / `0.2.0` 还有一次 settings 断裂**——`0.4.0` 在最新 DSH 上启动被拒的
+真正原因：`@deepseek-ai/dsh-settings` 在 `0.1.7-alpha.2` **再次移除了
+`settings.installSection`**（`0.2.x` 一路保留）。新设置模型是**条目式**的：可编辑字段
+是插件自身 `Config` 的 `.volatile()` 字段（由 loader 校验并热提交），设置表单以
+profile 条目 id（`engram`）为命名空间，不再需要任何“挂载”调用。`0.5.0`
+在 `installEngramSettings` 里对两代际做特性检测：
+
+- DSH `≥0.1.7` / `0.2.x` —— 27 个 GUI 旋钮即 `Config` 的 volatile 字段
+  （`lib/settings.js` `makeEngineConfigSchema`，由 `lib/index.js` 导出为
+  `Config`）；卡片仍走同一 `/api/dsh-engram/settings` HTTP 路由读写条目 `engram`，
+  `service.settings` 接缝在 `loader/volatile-update` 事件上把 `resolved`
+  重新同步，卡片编辑对新会话即时生效。
+- DSH `≤0.1.5` —— 照旧注册旧 `settings.installSection` 命名空间（`dsh-engram`）。
+
+声明范围 `>=0.1.2-alpha.2 <0.3.0-0` 同时覆盖两代际；HTTP wire 命名空间在两代际都保持
+`dsh-engram`（由接缝的活动命名空间驱动写入）。
+
 所以：跑 ≤ `0.3.6` 的已发布版本时请把 DSH 保持在 `0.1.1-rc.2` 或更旧；升级
 DSH 到 `0.1.2-alpha.2` 之前，先升级插件到 `>=0.3.7`。
 
-### 当前发布版本 —— `0.4.0`
+### 当前发布版本 —— `0.5.0`
 
-当前发布版本声明适配 DSH `>=0.1.2-alpha.2 <0.2.0-0`，并以本地
-`deepseek-harness` 的 `dsh-v0.1.5-alpha.1` 代码和 Web 运行时完成完整验证。
+已发布的 `0.4.0` 声明 `>=0.1.2-alpha.2 <0.2.0-0`——这个范围被 semver 门槛在
+**所有 DSH `0.2.0-0` 预发布**上拒绝（`<0.2.0-0` 排除 `0.2.0-rc.x`），且其宿主设置端
+仍在调用 `dsh-settings 0.1.7+` 已移除的 `installSection` API。`0.5.0`
+**两处都修复**：范围放宽到 `<0.3.0-0`（用 DSH 自身的 `includePrerelease` 检查验证过，
+`0.2.0-rc.2` 及整个 `0.2.x` 线都放行）；设置卡迁移到上面描述的 entry-id **volatile
+Config** 模型（并带特性检测的旧代际回退）。
 
 | 组件 | 适配版本 |
 | --- | --- |
-| DSH runtime / host / client 包族 | `>=0.1.2-alpha.2 <0.2.0-0` |
+| DSH runtime / host / client 包族 | `>=0.1.2-alpha.2 <0.3.0-0` |
 | `@deepseek-ai/cordis` | `^4.0.2` |
 | `@deepseek-ai/schemastery` | `^3.18.2` |
 | Node.js | `>=22.19.0` |
 
-`0.1.2-alpha.2` 是这组 API 的最低版本：宿主设置注册使用
-`settings.installSection`，浏览器端设置卡通过插件自有 HTTP 路由
-（`/api/dsh-engram/settings`，见上文 Route B）读写。
-`0.1.2-alpha.2` 和 `0.1.3-alpha.2` 已完成宿主导入与设置注册 smoke 验证；
-`0.1.5-alpha.1` 已完成完整回归（并在 `dsh 0.1.5-rc.1` 隔离 profile 上真机验证
-设置 GET/PUT/冲突/复位/跨重启持久化全通）。旧的 `0.1.0-rc.7` 与 `0.1.1` API 图不在
+`0.1.2-alpha.2` 是这组 API 的最低版本：宿主设置注册按代际**特性检测**——DSH `≤0.1.5`
+走 `settings.installSection` 注册 `dsh-engram` 命名空间；`≥0.1.7` / `0.2.x` 走插件
+`Config`（27 个 GUI 旋钮标记为 `.volatile()`，条目 id `engram`）。浏览器设置卡在两代际
+都经插件自有 HTTP 路由（`/api/dsh-engram/settings`，见上文 Route B）读写。完整回归
+（npm test 329/329，含新增的 volatile-Config 模型 settings-v2 覆盖）在 DSH
+`0.2.0-rc.2` 依赖集（cordis 4.0.4 + schemastery 3.18.4 + cosmokit，与全局 DSH CLI 同版本）
+上通过；`.volatile()`/loader 热提交路径与 describe 侧投影已针对真实 `dsh-settings
+0.2.0-rc.2` 工具函数验证；并在隔离的 `dsh 0.2.0-rc.2` profile 上完成了**真机启动烟测并
+通过**：插件启动无版本范围拒绝、设置卡表单以条目 `engram` 对外提供（全部 27 个 GUI
+旋钮，含 `trustedHosts`）、`/api/dsh-engram/settings` 的 GET → PUT（mutate ops，
+revision 0→1）→ unset 往返落盘并读回。旧的 `0.1.0-rc.7` 与 `0.1.1` API 图不在
 本发布版本的兼容范围内。
 
 如需按验证版本安装 DSH：
 
 ```sh
-npm install --global @deepseek-ai/dsh@0.1.5-alpha.1
+npm install --global @deepseek-ai/dsh@0.2.0-rc.2
 dsh --version
 ```
 
@@ -333,7 +373,7 @@ npm run build:client
 ## 测试与评测
 
 ```sh
-npm test    # 279 项单元测试（含 usage 滚动 / /stats 路由 / Context GC / ESR 触发 / BoundaryPrune）
+npm test    # 311 项单元测试（含 usage 滚动 / /stats 路由 / Context GC / ESR 触发 / BoundaryPrune）
 npm run eval  # 离线召回 + 结构基准（确定性语料，跑真实 store/recall 路径）
 ```
 
@@ -518,9 +558,48 @@ Context GC 管「压缩的摘要内容」，BoundaryPrune 管「确定性剪枝
   workspace 历史先验 + 超过后 ×2 外推（有界乐观），长会话不会被挡死。
 - **诚实激活面**：goal=0 且无 todo 推进的会话天然不触发（无边界不剪，零副作用）；
   全量干跑 77 会话激活 38%。pruner 服务缺席即自动禁用并打一条日志。
+- **边界源**：默认 todo 完成推进 / goal 终态事件；可选**空闲步数边界**
+  （`boundaryPruneIdleCadence`，默认 0=关）——覆盖约 62% 从不动 todo/goal 的
+  会话（侦察：`eval/recon-idle-boundary.mjs`；反事实：`eval/simulate-idle-cadence.mjs`
+  显示 cadence 50 时节省 +85%），仍受偿还门约束。
+- **阈值覆盖**：`boundaryPruneThresholdChars`（默认 0=宿主 8192）。设为 2048
+  并配更小保留边缘（`boundaryPruneHeadChars`/`boundaryPruneTailChars`）可更早
+  开剪——T2048+小边缘在真实语料上首剪节省是宿主默认的 2.4 倍（10.14M vs 4.23M
+  字符）。降阈值在 `resultPack` 开启时安全（被剪中段有归档兜底）。
 - 默认**关**：`boundaryPrune: false`。开启后启动日志出现
   `engram boundary-prune (todo @N reqs): pruned …`。
 
+### ResultPack L2（结果归档 + `result_recall`，默认关）
+
+让 BoundaryPrune 剪枝**无损**：每个被剪工具结果的被移除中段，按与记忆写入
+相同的规则脱敏后归档到 `~/.dsh/engram/resultpack/<callId>.json`，并在剪枝
+节点尾部追加 handle——`[middle archived: result_recall(<callId>) 可取]`——
+模型知道完整结果就在一步之遥。`result_recall(callId, offset?)` 按页返回
+归档中段（渐进披露，与 `[ENGRAM]` → `engram_detail` 同一哲学，也是 SoL-Pi
+机制③ ObservationPack 的完整形态）。
+
+- **构造性无损**：L1 剪掉的是重放、L2 保留的是可随时取回的原文——「模型回头
+  找被剪结果」的失败模式归零。
+- **成本受控**：归档在记忆域之外（大块内容永远不会撑大 domain JSON 或
+  [ENGRAM] 索引）；保留期 `resultPackRetentionDays`（默认 7 天）按 mtime 清理，
+  搭 GC 同一节奏。
+- **自我禁用**：只开 L2 不开 L1 将无内容可归档，故不注册工具并打一条警告。
+- 默认**关**：`resultPack: false`（须与 `boundaryPrune: true` 同开）。开启后
+  启动日志出现 `engram result-pack enabled: result_recall(callId, offset) registered`。
+
+### 激活遥测（SoL-Pi M15/C13）
+
+机制必须可证明在激活，休眠机制默认关。`/api/dsh-engram/stats`（以及 GUI
+overview）现在返回 `activation: { boundaryPrune, recall }`：
+
+- `boundaryPrune`——BoundaryPrune 真实 fire 的累计持久记录（fires /
+  prunedResults / charsRemoved / byKind todo|goal|step / lastFire），每次剪枝
+  落盘到 `~/.dsh/engram/boundary-prune.status.json`，与 `resultPack` 无关。
+- `recall`——召回漏斗的**注入腿**：实际进过会话的 `[RECALL]` 块数量
+  （`recall-injections.json`），与从 session log 已统计的另一端
+  （engram_recall 查询 → 命中 → engram_detail 下钻）闭合，可看到
+  注入→查询→下钻的完整激活。
+
 ## 自动捕获策略
 
 捕获是确定性、离线的——只看到工具*结果*，从不看对话本身。什么会被记录成一条记忆：
@@ -591,6 +670,15 @@ promote: 2 pending todo(s) vs 1 ESR task(s) — esr_task(name="…") #suggest-pr
 - id: engram
   config:
     autoCapture: true        # 零 LLM 工具结果捕获
+    autoCapturePreferences: true  # 零 LLM 用户纠正/偏好捕获（prefer/avoid/switch-to 句式）
+    preferenceCapturePerSession: 8  # 每会话偏好记忆条数上限
+    boundaryPrune: false       # ResultPack L1：todo/goal 边界剪掉超阈值旧工具结果（默认关）
+    boundaryPruneThresholdChars: 0   # 阈值覆盖（0=宿主 8192；如 2048 可更早开剪）
+    boundaryPruneHeadChars: 0  # 覆盖时的保留头部（0=宿主 4096）
+    boundaryPruneTailChars: 0  # 覆盖时的保留尾部（0=宿主 1024）
+    boundaryPruneIdleCadence: 0   # 空闲步数边界（0=仅事件边界；覆盖无 todo/goal 会话）
+    resultPack: false          # ResultPack L2：剪掉的中段脱敏归档 + result_recall 按页召回（默认关，须与 L1 同开）
+    resultPackRetentionDays: 7 # 归档保留天数（mtime 清理，走 GC 节奏）
     sessionSearch: true      # engram_recall 也可对历史会话 FTS
     recallScope: workspace   # 召回范围：workspace（严格工作区隔离，默认）| global（可选跨工作区召回，带 [W:<ws>] 来源标记）
     autoRecallOnStart: true  # 会话启动自动召回：按首条消息注入 [RECALL] 块（false=回到纯拉取）

package/docs/PROPOSAL-resultpack.zh.md

@@ -3,7 +3,7 @@
 > 依据:[SoL-Pi](https://nvlabs.github.io/SoL-Pi/) 四幸存机制之二(ObservationPack:归档载荷、上下文留 handle+摘录、按页召回)
 > 与提案池 C11「Reduce tool output before its first prompt insertion」/ C23「Build observation packs before paying for full bodies」。
 > 数据:[Oracle Analysis](./ORACLE-ANALYSIS.zh.md)(97 真实会话、13.9K 请求、15.0K 工具调用)。
-> **状态:L1 已实现(`lib/boundary-prune.js`,默认关;L0 见 §6,全量干跑见 §6.1)。L2 归档召回未实施。**
+> **状态:L1 已实现(`lib/boundary-prune.js`,默认关;L0 见 §6,全量干跑见 §6.1)。L2 已实现(`lib/result-pack.js`,默认关)。**
 
 ---
 
@@ -56,6 +56,8 @@ L1 剪掉的中段今天直接丢弃(仅 session 日志保留原文,模型取不
 - 注册 `result_recall(callId, offset?)` 工具,按页返回归档中段 —— 与 [ENGRAM] 渐进披露同一哲学:索引行→详情下钻;
 - 剪枝结果尾部追加一行 handle:`[middle pruned: result_recall(callId) 可取]`,模型可自主决定是否下钻(M3 遥测将能看到激活率)。
 
+> **已实现(2026-09-23,§8)**:实现细节与设计中两处修正——①归档落 `~/.dsh/engram/resultpack/<callId>.json`(独立文件而非域表,大块内容不撑 domain JSON);②handle 走宿主 surface-replace 协议(`session.append("tool/result", …, surfaceOp replace)`),replay-safe 零 LLM;脱敏先于持久化。17 项单测 + L1→L2 钩子 3 项 + 进程内端到端(归档→分页→缺档)验证通过。
+
 ### L3 · 上游提案(严格 C11)
 
 向 DSH 提 PR:ToolRuntime 开放 per-tool 可扩展 finalizeContent 链(或"结果归档 transport")。附上 oracle 数据(96% 集中在三个工具、top-10 占 46%)作为动机。
@@ -128,8 +130,10 @@ L1 剪掉的中段今天直接丢弃(仅 session 日志保留原文,模型取不
 
 ## 8. 后续
 
-- **L2(未实施)**:pruned 中段归档 + `result_recall` 按页召回 + handle 行;T2048 阈值与 L2 绑定。
-- **激活遥测**:fire 事件已可从 session log 的 `compaction/prune` 序列读出;建议 /stats 加一个「boundary-prune vs overflow-prune 来源区分」计数(用 fire 前后日志行归属判定)。
+- ~~**L2**~~ **已实现**(2026-09-23, `lib/result-pack.js`):pruned 中段归档 + `result_recall` 按页召回 + handle 行;默认关(`resultPack`,须与 `boundaryPrune` 同开),保留 7 天走 GC;T2048 阈值与 L2 绑定,**现已满足开低阈值的归档前提**。
+- ~~**激活遥测**~~ **已实现**(2026-09-23):`/stats` 与 GUI overview 返回 `activation: { boundaryPrune, recall }` —— BoundaryPrune fire 每次落盘 `~/.dsh/engram/boundary-prune.status.json`(fires/prunedResults/charsRemoved/byKind,与 resultPack 无关),[RECALL] 注入计数落盘 `recall-injections.json`,与 session-log 已统计的 recall 漏斗(查询→命中→detail 下钻)闭合(SoL-Pi M15/C13)。
+- ~~**step 空转边界**~~ **已实现**(2026-09-23):`boundaryPruneIdleCadence`(默认 0=关)——请求计数边界,覆盖无 todo/goal 会话。侦察 105 会话:65 个无边界、含 5.23M over-threshold 暴露(38%);反事实仿真(cadence 50):激活面 36→64 会话、首剪节省 4.23M→7.84M(+85%),仍受偿还门约束。
+- **T2048 落地**(2026-09-23):`boundaryPruneThresholdChars`/`HeadChars`/`TailChars`(默认 0=宿主)——插件以 `Object.create(pruner)` 原型克隆宿主 pruner 实例、仅覆盖 config,宿主不变。真实语料干跑:T2048 H1024/T256 首剪 10.14M vs 宿主默认 4.23M(+2.4x)。
 - **上游提案(L3)**:ToolRuntime 开放 finalizeContent 链,附 oracle 数据。
 
 

package/docs/RELEASE-NOTES-v0.5.0.md

@@ -0,0 +1,58 @@
+## dsh-engram v0.5.0
+
+DSH 0.2.x 兼容修复版：`0.1.7` 起 `@deepseek-ai/dsh-settings` 移除了
+`settings.installSection`，设置卡改为**条目式 volatile Config** 模型；本版本把设置
+绑定迁移到新模型（entry-id `engram`），并把声明范围修到能覆盖 DSH `0.2.x` 全系，
+使插件在最新 DSH 上恢复加载与设置卡读写。
+
+### 功能
+
+- **DSH ≥0.1.7 / 0.2.x 设置模型支持** — 插件 `Config`（`lib/index.js` 导出的
+  `Config`）声明全部 48 个 DEFAULTS 键；27 个 GUI 旋钮为 `.volatile()` 字段，
+  设置表单由 DSH 以 profile 条目 id `engram` 对外提供，卡片编辑经
+  `loader/volatile-update` **热提交**到运行配置（新会话即时生效，已冻结块保持
+  冻结——插件既有契约）。其余键普通声明，profile patch 里的内部旋钮不再被校验丢弃。
+- **双代际特性检测** — `installEngramSettings` 自动识别宿主：DSH `≤0.1.5`
+  回退旧的 `settings.installSection` 命名空间（`dsh-engram`），行为与 0.4.0 完全
+  一致；`≥0.1.7` / `0.2.x` 走新模型（无挂载调用）。HTTP wire 命名空间两代际都保持
+  `dsh-engram`，**客户端 bundle 零改动**。
+
+### 修复
+
+- **版本范围**：`engines.dsh` + 5 个 `@deepseek-ai/dsh-*` peer 从
+  `>=0.1.2-alpha.2 <0.2.0-0` 修正为 `>=0.1.2-alpha.2 <0.3.0-0`——原范围把
+  DSH `0.2.0-rc.x` 全部排除（semver 预发布窗口），插件在最新 DSH 上被兼容门槛拒绝。
+  新范围已用 DSH 自身的 `includePrerelease` 检查实测：`0.2.0-rc.2` 与整个 `0.2.x`
+  线放行，`0.3.0-0` 拒绝。
+- **宿主设置崩溃**：移除对已不存在的 `settings.installSection` 的无条件调用
+  （其在 `dsh-settings 0.1.7-alpha.2` 起被删除），改为特性检测。
+- **`boundaryPruneThresholdChars` 默认 `null` → `0`**：与设置卡长期使用的
+  “0=用宿主 8192” 语义一致（`0` 与 `null` 在剪枝判定中等价），并让 describe 的
+  表单值完整包含该键。
+
+### 其他
+
+- 测试 329/329 通过（新增 `test/settings-v2.test.mjs` 6 个用例，覆盖 volatile
+  Config 校验/解包/热同步与两代际安装路径；`test/api.test.mjs` 随 ns 语义更新）。
+- settings 投影与写路径针对真实 `dsh-settings 0.2.0-rc.2` 工具函数
+  （`volatileForm`/`projectForm`/`isVolatilePath`/`plainConfig`）验证；
+  真实 cordis 4.0.4 集成验证 Config 校验与热提交。
+- **真机烟测通过**（隔离 profile，`dsh 0.2.0-rc.2`，`--port 3099`）：插件启动无
+  版本拒绝、`/api/dsh-engram/settings` 提供 27 键表单、
+  GET → PUT（mutate，revision 0→1）→ unset 往返落盘并读回。
+- `scripts/prepublish-check.mjs` 随新导出面与 peer 范围更新，`prepublishOnly`
+  在 0.2.x peer 集上通过。
+
+## DSH 版本支持
+
+- **支持的 DSH 范围**：>=0.1.2-alpha.2 <0.3.0-0
+- **peer 声明**：
+  - `@deepseek-ai/dsh-compaction`: `>=0.1.2-alpha.2 <0.3.0-0`
+  - `@deepseek-ai/dsh-compaction-basic`: `>=0.1.2-alpha.2 <0.3.0-0`
+  - `@deepseek-ai/dsh-llm`: `>=0.1.2-alpha.2 <0.3.0-0`
+  - `@deepseek-ai/dsh-settings`: `>=0.1.2-alpha.2 <0.3.0-0`
+  - `@deepseek-ai/dsh-storage-domain`: `>=0.1.2-alpha.2 <0.3.0-0`
+- **验证版本**：`dsh-v0.2.0-rc.2`（全局 DSH CLI，并针对真实
+  `dsh-settings` / `cordis` / `schemastery` 依赖集）
+- **最后验证日期**：2026-10-15
+- **安装方式已验证**：`dsh plugin --profile web add dsh-engram`

package/lib/api.js

@@ -12,7 +12,7 @@
 
 import { uuid, shortId } from "./util.js";
 import { collectToolCounts, collectUsageStats } from "./usage.js";
-import { SETTINGS_NS } from "./settings.js";
+import { SETTINGS_NS, WIRE_SETTINGS_NS, LEGACY_SETTINGS_NS } from "./settings.js";
 
 /** Route family prefix (kept in sync with the client half). */
 export const API_PREFIX = "/api/dsh-engram";
@@ -160,8 +160,9 @@ export function makeEngramRoutes(service) {
     writeJson(res, 200, {
       ...summary,
       indexes,
-      captures: service.captureStats ?? { total: 0, git: 0, file: 0, error: 0 },
+      captures: service.captureStats ?? { total: 0, git: 0, file: 0, error: 0, preference: 0 },
       gc: service.gcStats ?? { lastRun: 0, archivedMemories: 0, archivedTasks: 0, removedLinks: 0 },
+      activation: service.packTelemetry ? service.packTelemetry() : { boundaryPrune: null, recall: null },
       compaction: service.compactionStatus ?? { host: "unknown", web: { action: "unknown", presets: [] } },
       config: service.config ?? {},
       anonymous: {
@@ -512,6 +513,10 @@ export function makeEngramRoutes(service) {
         recallHitsPerQuery: queries > 0 ? +(hitsTotal / queries).toFixed(3) : null,
         detailFollowRate: queries > 0 ? +(detailFollows / queries).toFixed(4) : null,
       },
+      // SoL-Pi activation telemetry: the durable BoundaryPrune / ResultPack
+      // activation record (fires actually landed on this profile) + the
+      // [RECALL] injection-funnel leg (blocks actually injected into sessions).
+      activation: service.packTelemetry ? service.packTelemetry() : { boundaryPrune: null, recall: null },
     });
   };
 
@@ -561,8 +566,13 @@ export function makeEngramRoutes(service) {
       // Normalize both onto the HTTP contract {namespaces:[...]} the client uses.
       const payload = settings.describe();
       const namespaces = Array.isArray(payload) ? payload : (payload?.namespaces ?? []);
-      const view = namespaces.find((n) => n && n.ns === SETTINGS_NS);
-      writeJson(res, 200, view ? { namespaces: [view] } : { namespaces: [] });
+      // The seam carries the ACTIVE namespace — entry id `engram` on DSH
+      // ≥0.1.7 / 0.2.x, legacy `dsh-engram` on ≤0.1.5. The view is re-labelled
+      // onto the stable WIRE_SETTINGS_NS the client card filters on, so the
+      // shipped client works unchanged across generations.
+      const activeNs = settings.ns ?? SETTINGS_NS;
+      const view = namespaces.find((n) => n && (n.ns === activeNs || n.ns === LEGACY_SETTINGS_NS));
+      writeJson(res, 200, view ? { namespaces: [{ ...view, ns: WIRE_SETTINGS_NS }] } : { namespaces: [] });
     } catch (error) {
       writeError(res, 500, String(error?.message ?? error));
     }
@@ -586,10 +596,13 @@ export function makeEngramRoutes(service) {
       return writeError(res, 400, "body must provide ops (array of {op,path[,value]}) or patch (object)");
     }
     try {
+      // Drive the seam's ACTIVE namespace (entry id `engram` on DSH ≥0.1.7 /
+      // 0.2.x, legacy `dsh-engram` on ≤0.1.5), never the wire label.
+      const activeNs = settings.ns ?? SETTINGS_NS;
       if (Array.isArray(ops)) {
-        await settings.mutate(SETTINGS_NS, ops, expectedRevision);
+        await settings.mutate(activeNs, ops, expectedRevision);
       } else {
-        await settings.update(SETTINGS_NS, patch, expectedRevision);
+        await settings.update(activeNs, patch, expectedRevision);
       }
       writeJson(res, 200, { ok: true });
     } catch (error) {