dsh-continual-evolve 0.15.6 → 0.15.8
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/README.md +19 -8
- package/README.zh.md +19 -8
- package/client/client.js +6 -46
- package/lib/card-routes.js +3 -8
- package/lib/extraction-prompt.d.ts +17 -1
- package/lib/extraction-prompt.js +48 -0
- package/lib/extraction.js +37 -5
- package/lib/index.d.ts +34 -0
- package/lib/index.js +45 -0
- package/lib/memory-rules.d.ts +7 -0
- package/lib/memory-snapshot.d.ts +1 -3
- package/lib/memory-snapshot.js +1 -11
- package/lib/memory-tools.js +8 -1
- package/lib/review-prompt.d.ts +55 -0
- package/lib/review-prompt.js +105 -0
- package/lib/review.d.ts +99 -0
- package/lib/review.js +467 -0
- package/lib/skill-tools.js +3 -2
- package/lib/store-apply.d.ts +2 -0
- package/lib/store-apply.js +44 -8
- package/lib/store.d.ts +82 -22
- package/lib/store.js +188 -51
- package/lib/token-usage.d.ts +3 -2
- package/lib/token-usage.js +3 -2
- package/package.json +1 -1
package/README.md
CHANGED
|
@@ -7,7 +7,7 @@ English | [中文](README.zh.md)
|
|
|
7
7
|
[](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
|
|
8
8
|
[](LICENSE)
|
|
9
9
|
[](package.json)
|
|
10
|
-
[]()
|
|
11
11
|
[]()
|
|
12
12
|
[]()
|
|
13
13
|
[]()
|
|
@@ -21,10 +21,11 @@ Reusable experience gathered in one session (user preferences, pitfalls, project
|
|
|
21
21
|
## How it works
|
|
22
22
|
|
|
23
23
|
1. **Session-start injection** — the plugin registers a single system-prompt section: the workspace's memory index as a store query (hooks only, whole-line truncated over budget, ordered feedback > user > reference), the central-library path, and a three-line guide. The section is computed once per session and reused byte-for-byte, keeping the system prompt stable and the prompt cache warm; an empty store costs zero tokens.
|
|
24
|
-
2. **Four tools, one writer** — `memory_write` (create/update/delete) is the explicit path for "remember …" / "forget …": every proposal passes the code gates (id shape, type enum, the feedback Why/How contract, secret screening carried over from v1, 64KB body cap) inside one transaction. `memory_read` fetches bodies by id and searches by keyword — whitespace-separated terms are AND-combined, with literal substring matching for short terms and whenever the trigram index misses; the injected index carries hooks only. `skill_write` (create/update/delete in the project, plus an explicit move-to-global) sediments reusable procedures through the same discipline (kebab ids, secret screening, 64KB cap, no duplicate ids or bodies across scopes); every applied skill is materialized by the plugin as `<workspace>/.agents/skills/<id>/SKILL.md` — the database is the source of truth, the files are a read-only projection patrol restores on drift. `skill_read` fetches skill bodies by id and searches project plus global skills (the project shadows a same-named global); each body served by id increments that skill's
|
|
25
|
-
3. **Proposal-based extraction** — the
|
|
26
|
-
4. **
|
|
27
|
-
5. **
|
|
24
|
+
2. **Four tools, one writer** — `memory_write` (create/update/delete) is the explicit path for "remember …" / "forget …": every proposal passes the code gates (id shape, type enum, the feedback Why/How contract, secret screening carried over from v1, 64KB body cap, optional `corrects` links to the same-workspace active memory being superseded) inside one transaction. `memory_read` fetches bodies by id and searches by keyword — whitespace-separated terms are AND-combined, with literal substring matching for short terms and whenever the trigram index misses; the injected index carries hooks only. Each memory body served by id increments that memory's view counter (views + last viewed, the same presence heartbeat as skills). `skill_write` (create/update/delete in the project, plus an explicit move-to-global) sediments reusable procedures through the same discipline (kebab ids, secret screening, 64KB cap, no duplicate ids or bodies across scopes); every applied skill is materialized by the plugin as `<workspace>/.agents/skills/<id>/SKILL.md` — the database is the source of truth, the files are a read-only projection patrol restores on drift. `skill_read` fetches skill bodies by id and searches project plus global skills (the project shadows a same-named global); each body served by id increments that skill's view counter (views + last viewed), which the card shows as a presence heartbeat — viewed, not applied, so long-unviewed rows are removal candidates while pruning itself stays human. On hosts without the tools service the plugin degrades to "tell the user" phrasing and stays functional.
|
|
25
|
+
3. **Proposal-based extraction** — the trajectory-to-memory automation, audited in the `extraction_log`: every `agent/turn-stopping` schedules that session's boundary, with state kept **per session** (a run in flight keeps only its newest boundary — coalescing, not queueing; `compaction/start` and session close drain it) and **no idle timer**. A run reads the session increment since its cursor, feeds FTS-similar existing memories to one LLM call, and the model's structured proposal lands through the same gates; failures and rejections never advance the cursor. A cheap pre-gate (increment head + ownership triple-test, tiny verdict) runs first: refusals consume the increment as a model skip without the full call, and an unclear gate fails open to the full call — worst case degrades to the old single-call behavior, never to a stall. Full and gate usages ledger in separate `usage` / `cheap_usage` columns. Internal agents, empty increments, turns without real user prose, and turns that already carried an explicit `memory_write` are mechanically skipped — and every skip is ledgered, consecutive quiet turns of one session as a single row carrying how many wake-ups it stands for.
|
|
26
|
+
4. **Autonomous content-quality loop** — the second background automation, independent from extraction by construction (own prompts, own daily budget, own `review_log` ledger, no cursor; only the store's write gates are shared): a cheap gate model call decides whether a memory/skill entry deserves a close look, and only approvals run the evolve pass that judges content quality (memories on home-ownership plus accuracy/usability/reusability/duplication/freshness, skills on home-ownership plus trigger precision/executability/reusability/duplication) and proposes the rewrite. The same three home tests (user/environment vs repo-version subject, name-stripped sentence, repo facts live in ADR/docs) guard the extraction prompt, so repo-version specifics never enter as memories in the first place. Gate/leg failures ledger the error text instead of a bare code. New writes are reviewed as they land, the existing stock drains through a bounded backlog queue, and untouched entries requeue after 30 days. Two hard guarantees bound the autonomy: delete never lands automatically (rewrite or quarantine only — quarantine hides, never deletes) and oversized rewrites degrade to quarantine. A daily cap (default 100 items, new > corrects-linked > stale > spot-check priority, the tail drops instead of rolling over) bounds the token spend, and every terminal path lands one `item-review` verdict row plus one daily rollup row (budget vs reviewed vs backlog vs dropped, tokens split by cheap/evolve purpose) for later replay. Ships in trial mode (`review.dryRun`, default on): verdicts ledgered, nothing applied.
|
|
27
|
+
5. **Rollback is a ledger, not a mechanism** — every mutation lands an `extraction_log` row with full before/after snapshots; undo means rewriting the `before` values. Skill mutations land the same way in `skill_log`, review verdicts in `review_log`. A hygiene pass rides on every applied run: orphan FTS rows are dropped and secret-bearing rows are quarantined (hidden, never deleted; a quarantined skill's materialized file is removed so it stops loading). The read-only card surfaces quarantine anomalies.
|
|
28
|
+
6. **Read-only card** — mounted on the plugin's page in the official plugin manager (the `plugins.bundle.config` slot; hosts without it silently degrade to no card), shaped like the market's own settings card and aligned with ZCode's Settings → Memory viewer: a dropdown scope selector over the store's workspace partitions (opening on the host's current workspace), a search box, per-entry relative updated times, click-to-preview bodies (5 MiB cap), patrol warnings, and a skills section listing the workspace's project skills plus visible global skills (global rows badged, project shadowing global) with the same preview, each row showing its view count. Localized through the host's `locale/*.json` metadata channel; host theme tokens, the `Button` primitive, and zh/en copy that tracks the DSH language. The card is a request-time projection of the database and has no edit path.
|
|
28
29
|
|
|
29
30
|
Memory types follow the ZCode taxonomy: `user` (profile and environment facts), `feedback` (corrected or confirmed practices — bodies must carry **Why:** and **How to apply:** lines), `reference` (resource pointers). The extraction boundary is person- and environment-scoped knowledge only: decisions and trade-offs are repo-scoped by nature and belong to the repo's ADR route, never to memory.
|
|
30
31
|
|
|
@@ -55,6 +56,10 @@ No commands. On the first session after restart the index is injected automatica
|
|
|
55
56
|
| `memoryIndex.order` | `400` | Section order (upstream named slots start at `PLAN_POLICY=500`) |
|
|
56
57
|
| `memoryIndex.maxChars` | `6000` | Hard character budget for the injected index |
|
|
57
58
|
| `memoryIndex.extraction` | `true` | The proposal-based extraction run (turn-level, per-session slots, no idle timer) |
|
|
59
|
+
| `review.enabled` | `true` | The autonomous content-quality loop (own prompts/budget/ledger, trial dry-run) |
|
|
60
|
+
| `review.dryRun` | `true` | Ledger verdicts without landing them (flip off after the trial distribution reads clean) |
|
|
61
|
+
| `review.dailyBudget` | `100` | Reviewed items per UTC day (new > corrects-linked > stale > spot-check, tail drops) |
|
|
62
|
+
| `review.batchSize` | `10` | Max items per drain run |
|
|
58
63
|
| `memoryCard.enabled` | `true` | Read-only memory card in the official plugin manager (degrades to no card when the host lacks `webServer`/`plugins.bundle.config`) |
|
|
59
64
|
|
|
60
65
|
Profile patch example:
|
|
@@ -65,13 +70,15 @@ Profile patch example:
|
|
|
65
70
|
memoryIndex:
|
|
66
71
|
maxChars: 8000
|
|
67
72
|
extraction: true
|
|
73
|
+
review:
|
|
74
|
+
dryRun: false
|
|
68
75
|
```
|
|
69
76
|
|
|
70
77
|
## Development
|
|
71
78
|
|
|
72
79
|
```bash
|
|
73
80
|
pnpm install && pnpm build # deps + clean build -> lib/
|
|
74
|
-
pnpm test # vitest (
|
|
81
|
+
pnpm test # vitest (328 tests)
|
|
75
82
|
pnpm test:coverage # v8 coverage, CI-enforced thresholds
|
|
76
83
|
pnpm lint # oxlint src test client
|
|
77
84
|
pnpm check:pack # published-artifact consistency (also runs on prepack)
|
|
@@ -81,9 +88,13 @@ Layout:
|
|
|
81
88
|
|
|
82
89
|
```
|
|
83
90
|
├── src/
|
|
84
|
-
│ ├── index.ts # registration: section + tools + extraction + card wiring
|
|
91
|
+
│ ├── index.ts # registration: section + tools + extraction + review + card wiring
|
|
85
92
|
│ ├── store.ts # central SQLite store: DDL/WAL/FTS, reads, ledger, patrol, cursors
|
|
86
93
|
│ ├── store-apply.ts # the sole write gate: validate all, apply atomically, ledger
|
|
94
|
+
│ ├── token-usage.ts # single accounting entry: normalize provider usage, pure sums
|
|
95
|
+
│ ├── review.ts # autonomous quality loop: cheap gate → evolve, budget, scheduler
|
|
96
|
+
│ ├── review-prompt.ts # review prompts + verdict parsing (gate + memory/skill rubrics)
|
|
97
|
+
│ ├── store-apply.ts # the sole write gate: validate all, apply atomically, ledger
|
|
87
98
|
│ ├── memory-rules.ts # mechanical gates: enums, sizes, id shape, secret screening
|
|
88
99
|
│ ├── memory-section.ts # injection: store query / truncate / session freeze
|
|
89
100
|
│ ├── memory-guide.ts # the main-session guide (three lines)
|
|
@@ -100,7 +111,7 @@ Layout:
|
|
|
100
111
|
├── client/
|
|
101
112
|
│ └── client.js # hand-written client bundle: read-only card in the plugin manager
|
|
102
113
|
├── locale/ # host package metadata: localized display name + description (zh/en)
|
|
103
|
-
├── test/ # vitest suite (
|
|
114
|
+
├── test/ # vitest suite (25 files)
|
|
104
115
|
├── lib/ # build output (tsc)
|
|
105
116
|
├── docs/ # design.md (design) · FAQ.md (real-world pitfalls)
|
|
106
117
|
└── .agents/ # AI collaboration layer (AGENTS.md, skills, ADR notes)
|
package/README.zh.md
CHANGED
|
@@ -7,7 +7,7 @@
|
|
|
7
7
|
[](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
|
|
8
8
|
[](LICENSE)
|
|
9
9
|
[](package.json)
|
|
10
|
-
[]()
|
|
11
11
|
[]()
|
|
12
12
|
[]()
|
|
13
13
|
[]()
|
|
@@ -21,10 +21,11 @@ Agent 每个会话积累的可复用经验（用户偏好、踩坑教训、项
|
|
|
21
21
|
## 工作原理
|
|
22
22
|
|
|
23
23
|
1. **开局注入** —— 插件只注册一个 system-prompt section：注入本工作区的记忆索引（查库结果，只含钩子，超预算按整行截断，feedback > user > reference 排序）、中央库路径、三行指南。该 section 每会话只算一次并逐字节复用，system prompt 稳定、prompt cache 持续命中；空 store 零 token。
|
|
24
|
-
2. **四个工具，一个写者** —— `memory_write`（create/update/delete）承接显式的记住/忘掉：每条提案过代码门禁（id 规范、type 枚举、feedback 的 Why/How 契约、v1 移植的 secret 筛查、64KB
|
|
25
|
-
3. **提案制提取** ——
|
|
26
|
-
4.
|
|
27
|
-
5.
|
|
24
|
+
2. **四个工具，一个写者** —— `memory_write`（create/update/delete）承接显式的记住/忘掉：每条提案过代码门禁（id 规范、type 枚举、feedback 的 Why/How 契约、v1 移植的 secret 筛查、64KB 正文上限、可选 `corrects` 指向被替代的同工作区 active 记忆）后在一个事务内落盘。`memory_read` 按 id 取正文、按关键词检索——空格分隔的关键词取 AND，短词与 trigram 未命中时回退字面子串匹配；注入索引只有钩子。按 id 取到的每份记忆正文计一次查阅（与技能同纪律的存在心跳）。`skill_write`（项目内 create/update/delete + 显式搬到全局）沉淀可复用的操作规程，走同一套纪律（短横线 id、secret 筛查、64KB 上限、跨范围禁重名重文）；每条落地的技能由插件代码物化为 `<workspace>/.agents/skills/<id>/SKILL.md`——库是唯一真相，文件是只读投影，漂移由巡检按库还原。`skill_read` 按 id 取技能正文、检索项目与全局技能（同名时项目遮蔽全局）；按 id 取到的每份正文计一次查阅（查阅次数 + 上次查阅，卡片展示）。这是存在心跳——只证明被翻过，不证明有用：长期零查阅是删除候选，剪枝拍板仍需人工。宿主没有工具服务时降级为告诉用户措辞，注入不受影响。
|
|
25
|
+
3. **提案制提取** —— 轨迹到记忆的自动化，全程 `extraction_log` 可对账：每个 `agent/turn-stopping` 调度**该会话自己**的边界，状态按会话隔离（运行中只保留最新边界——合并而非排队；`compaction/start` 与会话收尾触发 drain），**没有空闲计时器**。一次运行读取该会话游标之后的轨迹增量，用 FTS 取相似既有记忆喂给一次 LLM 调用，模型的结构化提案过同一套门禁落盘；失败与被拒不推游标，下次触发重试。贵调用之前先过一道便宜预检门（增量前 4KB + 归属三测，小 verdict）：拒了直接按 model-skip 消费游标，不烧全量 prompt；门不清不楚就透传给贵调用——最差退化成老单调用，永不 stall。贵用量与门用量分 `usage` / `cheap_usage` 两列记账。内部 agent、空增量、无真实用户文本的轮次、当轮已有显式 `memory_write` 的轮次机械跳过——每次跳过都记账，同一会话连续的空转轮次合成一行并累计唤醒次数。
|
|
26
|
+
4. **内容质量自进化环** —— 第二条后台自动化，与提取在结构上独立（自有提示词、自有日预算、自有 `review_log` 账本、无游标；只共享库的写门）：便宜门模型先判某条记忆/技能值不值得细看，批了才跑贵改写，按内容质量打分（记忆：归属 + 准确/可用/可复用/不重复/不过时五维；技能：归属 + 触发精度/可执行完备/可复用/不重复四维）并给出改写提案。同一套归属三测（主语是用户/环境还是某仓库的某版机制、去名后还成立吗、仓库事实住 ADR/docs）也守在提取 prompt 门口，版本细节从源头就不进记忆；评审调用失败记错误原文，不记秃码。新写即审、存量走有界积压队列排空、长期未动 30 天回炉。两条硬保证框住自动化：删除永不自动落盘（只有改写与隔离——隔离隐藏不删），超幅改写自动转隔离。日上限默认 100 条（新写 > 被纠正牵连 > 陈旧 > 抽查，尾部丢弃不滚雪球）框住 token 开销；每条终态落一行 `item-review` verdict 行、每天合一行日 rollup（预算 vs 实审 vs 积压 vs 丢弃，token 按便宜/贵分账），方便以后复盘。默认试运行（`review.dryRun` 开）：只记 verdict，不落盘。
|
|
27
|
+
5. **回滚靠账本，不靠机制** —— 每次变更落一条带 before/after 全文快照的 `extraction_log` 行；undo 就是取 before 重写。技能变更同样落 `skill_log`，评审 verdict 落 `review_log`。每次应用后随跑一次巡检：孤儿 FTS 行清除、含密钥条目隔离（隐藏，不物理删除；被隔离技能的物化文件一并撤下，使其不再被加载）。只读卡片显形巡检异常。
|
|
28
|
+
6. **只读卡片** —— 挂在官方插件管理的本 bundle 页面（`plugins.bundle.config` slot，老宿主自动降级为无卡片）：形态对齐市场自家设置卡，内容对齐 ZCode 设置的记忆选项卡——下拉作用域选择器列出库里的工作区分区（默认选中宿主当前工作区）、搜索框、每条记忆的相对更新时间、点击行内展开正文预览（5 MiB 上限）、巡检异常警告，以及技能区（本工作区技能 + 可见的全局技能，全局行打标记，同名时项目遮蔽全局），预览同记忆，每行显示查阅次数。显示名与描述走宿主 `locale/*.json` 通道双语；宿主主题 token、`Button` 原语、中英文案跟随 DSH 语言。卡片是数据库的请求时投影，没有编辑路径。
|
|
28
29
|
|
|
29
30
|
记忆类型沿 ZCode 分类法：`user`（画像与环境事实）、`feedback`（被纠正/确认的做法——正文必带 **Why:** 与 **How to apply:**）、`reference`（资源指针）。提取边界只收"跟人与环境走的知识"：决策与取舍天然属于仓库，走仓库的 ADR 路线，不进记忆库。
|
|
30
31
|
|
|
@@ -55,6 +56,10 @@ dsh plugin add ZK-Andy/dsh-continual-evolve
|
|
|
55
56
|
| `memoryIndex.order` | `400` | section 顺序（上游命名槽位自 `PLAN_POLICY=500` 起） |
|
|
56
57
|
| `memoryIndex.maxChars` | `6000` | 注入索引的硬字符预算 |
|
|
57
58
|
| `memoryIndex.extraction` | `true` | 提案制提取运行（轮级、按会话分槽、无空闲计时器） |
|
|
59
|
+
| `review.enabled` | `true` | 内容质量自进化环（自有提示词/预算/账本，默认试运行） |
|
|
60
|
+
| `review.dryRun` | `true` | 只记 verdict 不落盘（试运行分布看顺后再关） |
|
|
61
|
+
| `review.dailyBudget` | `100` | 每天评审上限（新写 > 被纠正牵连 > 陈旧 > 抽查，尾部丢弃） |
|
|
62
|
+
| `review.batchSize` | `10` | 每次 drain 最多审几条 |
|
|
58
63
|
| `memoryCard.enabled` | `true` | 官方插件管理内的只读记忆卡片（宿主缺 `webServer`/`plugins.bundle.config` 时自动降级为无卡片） |
|
|
59
64
|
|
|
60
65
|
profile patch 示例：
|
|
@@ -65,13 +70,15 @@ profile patch 示例：
|
|
|
65
70
|
memoryIndex:
|
|
66
71
|
maxChars: 8000
|
|
67
72
|
extraction: true
|
|
73
|
+
review:
|
|
74
|
+
dryRun: false
|
|
68
75
|
```
|
|
69
76
|
|
|
70
77
|
## 开发
|
|
71
78
|
|
|
72
79
|
```bash
|
|
73
80
|
pnpm install && pnpm build # 依赖 + 干净构建 -> lib/
|
|
74
|
-
pnpm test # vitest（
|
|
81
|
+
pnpm test # vitest（328 例）
|
|
75
82
|
pnpm test:coverage # v8 覆盖率，CI 强制阈值
|
|
76
83
|
pnpm lint # oxlint src test client
|
|
77
84
|
pnpm check:pack # 发布产物一致性（prepack 也会跑）
|
|
@@ -81,9 +88,13 @@ pnpm check:pack # 发布产物一致性（prepack 也会跑）
|
|
|
81
88
|
|
|
82
89
|
```
|
|
83
90
|
├── src/
|
|
84
|
-
│ ├── index.ts # 注册：section + 工具 + 提取 + 卡片接线
|
|
91
|
+
│ ├── index.ts # 注册：section + 工具 + 提取 + 评审 + 卡片接线
|
|
85
92
|
│ ├── store.ts # 中央 SQLite 库：DDL/WAL/FTS、读面、账本、巡检、游标
|
|
86
93
|
│ ├── store-apply.ts # 唯一写门：全量校验、事务原子应用、账本
|
|
94
|
+
│ ├── token-usage.ts # 统一记账口：归一各家用量、纯累加
|
|
95
|
+
│ ├── review.ts # 内容质量自进化：便宜门 → 贵改写、预算、调度
|
|
96
|
+
│ ├── review-prompt.ts # 评审提示词 + verdict 解析（门 + 记忆/技能 rubric）
|
|
97
|
+
│ ├── store-apply.ts # 唯一写门：全量校验、事务原子应用、账本
|
|
87
98
|
│ ├── memory-rules.ts # 机械门禁：枚举、尺寸、id 规范、secret 筛查
|
|
88
99
|
│ ├── memory-section.ts # 注入：查库 / 截断 / 会话冻结
|
|
89
100
|
│ ├── memory-guide.ts # 主会话指南（三行）
|
|
@@ -100,7 +111,7 @@ pnpm check:pack # 发布产物一致性（prepack 也会跑）
|
|
|
100
111
|
├── client/
|
|
101
112
|
│ └── client.js # 手写 client bundle：官方插件管理内只读卡片
|
|
102
113
|
├── locale/ # 宿主包元数据：显示名 + 描述双语（zh/en）
|
|
103
|
-
├── test/ # vitest 测试（
|
|
114
|
+
├── test/ # vitest 测试（25 个文件）
|
|
104
115
|
├── lib/ # 构建产物（tsc）
|
|
105
116
|
├── docs/ # design.md（设计）· FAQ.md（踩坑）
|
|
106
117
|
└── .agents/ # AI 协作层（AGENTS.md、技能、ADR 笔记）
|
package/client/client.js
CHANGED
|
@@ -102,8 +102,7 @@ window.__ModuleLoader__.load({
|
|
|
102
102
|
skillsEmpty: "该工作区还没有技能——明确告诉模型沉淀为技能即可，重启后生效。",
|
|
103
103
|
skillScopeGlobal: "全局",
|
|
104
104
|
skillPreviewDeleted: "该技能已被删除或搬家，请刷新列表。",
|
|
105
|
-
|
|
106
|
-
reviewStats: "评审：应用 {applied} · 拒绝 {rejected} · 跳过 {skipped} · 失败 {failed} · token {tokens}",
|
|
105
|
+
skillViewed: "查看 {count} 次",
|
|
107
106
|
scopeLabel: "选择工作区",
|
|
108
107
|
searchPlaceholder: "搜索记忆…",
|
|
109
108
|
searchEmpty: "没有匹配的记忆文件。",
|
|
@@ -136,8 +135,7 @@ window.__ModuleLoader__.load({
|
|
|
136
135
|
skillsEmpty: "No skills in this workspace yet — ask the model to save one as a skill, then restart.",
|
|
137
136
|
skillScopeGlobal: "global",
|
|
138
137
|
skillPreviewDeleted: "This skill was deleted or moved — refresh the list.",
|
|
139
|
-
|
|
140
|
-
reviewStats: "Reviews: {applied} applied · {rejected} rejected · {skipped} skipped · {failed} failed · {tokens} tokens",
|
|
138
|
+
skillViewed: "viewed {count} times",
|
|
141
139
|
scopeLabel: "Choose workspace",
|
|
142
140
|
searchPlaceholder: "Search memory files…",
|
|
143
141
|
searchEmpty: "No matching memory files.",
|
|
@@ -196,22 +194,6 @@ window.__ModuleLoader__.load({
|
|
|
196
194
|
}).format(date);
|
|
197
195
|
}
|
|
198
196
|
|
|
199
|
-
/**
|
|
200
|
-
* Compact token totals for the review line: 0 / 999 / 12.4k / 3.1M.
|
|
201
|
-
*/
|
|
202
|
-
function formatTokens(total) {
|
|
203
|
-
if (typeof total !== "number" || !isFinite(total) || total <= 0) {
|
|
204
|
-
return "0";
|
|
205
|
-
}
|
|
206
|
-
if (total >= 1000000) {
|
|
207
|
-
return (total / 1000000).toFixed(1) + "M";
|
|
208
|
-
}
|
|
209
|
-
if (total >= 1000) {
|
|
210
|
-
return (total / 1000).toFixed(1) + "k";
|
|
211
|
-
}
|
|
212
|
-
return String(Math.round(total));
|
|
213
|
-
}
|
|
214
|
-
|
|
215
197
|
/**
|
|
216
198
|
* Assemble the card's view model: the workspace catalogue, then one
|
|
217
199
|
* snapshot per workspace. Network or API failure per workspace degrades
|
|
@@ -477,10 +459,11 @@ window.__ModuleLoader__.load({
|
|
|
477
459
|
if (time !== "") {
|
|
478
460
|
rowChildren.push(createElement("span", { key: "time", className: "dce-file-time" }, time));
|
|
479
461
|
}
|
|
480
|
-
// Skill rows carry V2
|
|
481
|
-
// field and skip this span. Zero means never
|
|
462
|
+
// Skill rows carry V2 view counters; memory rows have no such
|
|
463
|
+
// field and skip this span. Zero means never opened — the count
|
|
464
|
+
// is a presence heartbeat (viewed, not applied), not a value score.
|
|
482
465
|
if (typeof file.useCount === "number" && file.useCount > 0) {
|
|
483
|
-
rowChildren.push(createElement("span", { key: "usage", className: "dce-file-time" }, t("
|
|
466
|
+
rowChildren.push(createElement("span", { key: "usage", className: "dce-file-time" }, t("skillViewed", { count: file.useCount })));
|
|
484
467
|
}
|
|
485
468
|
var children = [
|
|
486
469
|
createElement(
|
|
@@ -763,29 +746,6 @@ window.__ModuleLoader__.load({
|
|
|
763
746
|
t("stats", { files: snapshot.fileCount }),
|
|
764
747
|
),
|
|
765
748
|
];
|
|
766
|
-
// Review-loop audit rides the memory snapshot: one compact line
|
|
767
|
-
// when the ledger has any judgments, nothing when it is quiet.
|
|
768
|
-
var review = snapshot.review;
|
|
769
|
-
if (
|
|
770
|
-
review !== null &&
|
|
771
|
-
review !== undefined &&
|
|
772
|
-
(review.applied + review.rejected + review.skipped + review.failed) > 0
|
|
773
|
-
) {
|
|
774
|
-
var reviewTokens = review.tokens === null || review.tokens === undefined ? 0 : review.tokens.total;
|
|
775
|
-
parts.push(
|
|
776
|
-
createElement(
|
|
777
|
-
"div",
|
|
778
|
-
{ key: "review", className: "dce-hint" },
|
|
779
|
-
t("reviewStats", {
|
|
780
|
-
applied: review.applied,
|
|
781
|
-
rejected: review.rejected,
|
|
782
|
-
skipped: review.skipped,
|
|
783
|
-
failed: review.failed,
|
|
784
|
-
tokens: formatTokens(reviewTokens),
|
|
785
|
-
}),
|
|
786
|
-
),
|
|
787
|
-
);
|
|
788
|
-
}
|
|
789
749
|
if (snapshot.quarantined.length > 0) {
|
|
790
750
|
parts.push(
|
|
791
751
|
createElement("div", { key: "quarantined", className: "dce-warn" }, t("quarantined") + snapshot.quarantined.map(function (entry) { return entry.id; }).join("、")),
|
package/lib/card-routes.js
CHANGED
|
@@ -12,7 +12,6 @@
|
|
|
12
12
|
* never a path. Handlers are synchronous and never throw past the response.
|
|
13
13
|
*/
|
|
14
14
|
import { memoryEntryContent, listCardWorkspaces, memorySnapshot, skillEntryContent, skillSnapshot } from "./memory-snapshot.js";
|
|
15
|
-
import { skillUsagePartition } from "./skill-rules.js";
|
|
16
15
|
import { canonicalPath } from "./workspace-hint.js";
|
|
17
16
|
/** URL prefix of the card API (kind-exact routes registered under it). */
|
|
18
17
|
export const CARD_API_WORKSPACES_PATH = "/dsh-continual-evolve/api/v1/workspaces";
|
|
@@ -174,13 +173,9 @@ export function mountCardRoutes(webServer, store, options = {}) {
|
|
|
174
173
|
}
|
|
175
174
|
return;
|
|
176
175
|
}
|
|
177
|
-
//
|
|
178
|
-
|
|
179
|
-
|
|
180
|
-
}
|
|
181
|
-
catch {
|
|
182
|
-
// Accounting never fails the preview it rides on.
|
|
183
|
-
}
|
|
176
|
+
// Human previews are display-only: people never audit skills by
|
|
177
|
+
// reading them, so previews leave no count. Only model-side
|
|
178
|
+
// consultation (skill_read by id) feeds the heartbeat.
|
|
184
179
|
sendJson(response, 200, {
|
|
185
180
|
id: content.id,
|
|
186
181
|
scope: content.scope,
|
|
@@ -10,7 +10,23 @@
|
|
|
10
10
|
* feedback contract) decide — the proposal is never trusted on its own.
|
|
11
11
|
*/
|
|
12
12
|
/** The extraction model's system prompt (Chinese — memory content is Chinese-first). */
|
|
13
|
-
export declare const EXTRACTION_SYSTEM_PROMPT = "\u4F60\u662F\u8BB0\u5FC6\u63D0\u53D6\u4E13\u5458\u3002\u4F60\u7684\u552F\u4E00\u4EFB\u52A1\uFF1A\u4ECE\u4F1A\u8BDD\u8F68\u8FF9\u589E\u91CF\u91CC\u5224\u65AD\u54EA\u4E9B\u4FE1\u606F\u503C\u5F97\u5B58\u5165\u7528\u6237\u7684\u8DE8\u4F1A\u8BDD\u6301\u4E45\u8BB0\u5FC6\uFF0C\u5E76\u63D0\u51FA\u7ED3\u6784\u5316\u63D0\u6848\u3002\u4F60\u4E0D\u6267\u884C\u4EFB\u52A1\u3001\u4E0D\u56DE\u7B54\u7528\u6237\u3001\u4E0D\u89E3\u91CA\u63A8\u7406\u3002\n\n## \u4F55\u65F6\u5199\u5165\u8BB0\u5FC6\n\n<type name=\"user\">\n <when_to_save>\u5F97\u77E5\u7528\u6237\u7684\u753B\u50CF\u4E0E\u73AF\u5883\u4E8B\u5B9E\uFF1A\u89D2\u8272\u3001\u6280\u672F\u6808\u3001\u7ECF\u9A8C\u6C34\u5E73\u3001\u504F\u597D\uFF0C\u4EE5\u53CA\u673A\u5668\u4E0E\u5DE5\u5177\u94FE\uFF08\u64CD\u4F5C\u7CFB\u7EDF\u3001\u88C5\u4E86\u4EC0\u4E48\u3001\u914D\u7F6E\u5728\u54EA\uFF09\u3002\u4F8B\uFF1A\"\u6211\u5728 Fedora \u4E0A\u5DE5\u4F5C\uFF0C\u65E5\u5E38\u8DD1 dotnet-desktop profile\"\u3002</when_to_save>\n</type>\n\n<type name=\"feedback\">\n <when_to_save>\u4E24\u7C7B\u4FE1\u53F7\uFF1A\n \uFF081\uFF09\u7EA0\u6B63\u2014\u2014\u7528\u6237\u8BF4\"\u4E0D\u662F\u8FD9\u6837\"\"\u522B\"\"\u505C\u4E0B\"\u7684\u90A3\u4E00\u8F6E\uFF0C\u5B58\u88AB\u7EA0\u6B63\u7684\u505A\u6CD5\u4E0E\u6B63\u786E\u505A\u6CD5\uFF1B\n \uFF082\uFF09\u786E\u8BA4\u2014\u2014\u66F4\u5B89\u9759\u4F46\u540C\u6837\u8981\u7D27\uFF1A\u7528\u6237\u63A5\u53D7\u4E86\u4F60\u4E0D\u5BFB\u5E38\u7684\u9009\u62E9\u800C\u65E0\u5F02\u8BAE\uFF0C\u6216\u660E\u786E\u8BF4\"\u5BF9\uFF0C\u5C31\u8FD9\u6837\"\u3002\u53EA\u5B58\u7EA0\u9519\u4F1A\u8BA9\u884C\u4E3A\u8D8A\u6765\u8D8A\u4FDD\u5B88\u3002\n \u4F8B\uFF1A\"\u6D4B\u8BD5\u522B mock \u6570\u636E\u5E93\uFF0C\u4E0A\u6B21 mock \u8FC7\u4E86\u7EBF\u4E0A\u8FC1\u79FB\u6302\u4E86\"\u2014\u2014\u5B58\u89C4\u5219\u5E76\u5E26\u4E0A\u4E8B\u6545\u539F\u56E0\u3002</when_to_save>\n <body_structure>\u89C4\u5219\u5148\u884C\uFF0C\u968F\u540E\u5FC5\u5E26\u4E24\u884C\uFF1A**Why:**\uFF08\u7528\u6237\u7ED9\u7684\u7406\u7531\u2014\u2014\u77E5\u9053\u4E3A\u4EC0\u4E48\u624D\u80FD\u5224\u65AD\u8FB9\u7F18\u60C5\u51B5\uFF09\u548C **How to apply:**\uFF08\u4F55\u65F6\u4F55\u5730\u751F\u6548\uFF09\u3002\u7F3A\u8FD9\u4E24\u884C\u7684\u63D0\u6848\u4F1A\u88AB\u673A\u68B0\u62D2\u7EDD\u3002</body_structure>\n</type>\n\n<type name=\"reference\">\n <when_to_save>\u7528\u6237\u63D0\u5230\u672A\u6765\u4F1A\u7528\u5230\u7684\u8D44\u6E90\u6307\u9488\uFF1AURL\u3001\u4EEA\u8868\u76D8\u3001\u5DE5\u5355\u3001\u672C\u5730\u6570\u636E\u5E93\u3001\u6587\u6863\u4F4D\u7F6E\u3002</when_to_save>\n</type>\n\n**\u8FB9\u754C\u5224\u636E\uFF1A\u6362\u4E00\u4E2A\u4ED3\u5E93\u8FD8\u6709\u7528\u7684\u4FE1\u606F\u624D\u8FDB\u8BB0\u5FC6\u3002**\u51B3\u7B56\u3001\u67B6\u6784\u53D6\u820D\u3001\u8FDB\u884C\u4E2D\u72B6\u6001\u53EA\u5BF9\u5F53\u524D\u4ED3\u5E93\u6709\u4EF7\u503C\u2014\u2014\u5B83\u4EEC\u8D70\u4ED3\u5E93\u7684 ADR/\u6587\u6863\u8DEF\u7EBF\uFF0C\u7EDD\u4E0D\u63D0\u6848\u3002\u80FD\u4ECE\u4EE3\u7801\u3001git \u5386\u53F2\u3001\u4ED3\u5E93\u6587\u4EF6\u91CC\u91CD\u65B0\u63A8\u5BFC\u51FA\u6765\u7684\u4E8B\u5B9E\u4E0D\u5B58\uFF1B\u4E34\u65F6\u4EFB\u52A1\u72B6\u6001\u3001\u4E00\u6B21\u6027\u8C03\u8BD5\u8FC7\u7A0B\u3001\u65E0\u590D\u73B0\u8BC1\u636E\u7684\u95EE\u9898\u4FEE\u590D\u4E0D\u5B58\u3002\u76F8\u5BF9\u65E5\u671F\u4E00\u5F8B\u8F6C\u6210\u7EDD\u5BF9\u65E5\u671F\uFF08\"\u5468\u56DB\"\u2192\"2026-10-08\"\uFF09\u3002\n\n## \u66F4\u65B0\u4F18\u5148\u4E8E\u65B0\u5EFA\n\n\u5DF2\u6709\u8BB0\u5FC6\u7684\u72B6\u6001\u53D8\u4E86\uFF0C\u63D0\u6848 update \u6539\u539F\u6761\u76EE\uFF1B\u65B0\u65E7\u5E76\u5B58\u6BD4\u6CA1\u6709\u8BB0\u5FC6\u66F4\u7CDF\u3002\u8981\u66F4\u65B0\u6216\u5220\u9664\u7684\u6761\u76EE\u4F1A\u8FDE\u540C\u5168\u6587\u7ED9\u4F60\uFF0C\u63D0\u6848\u91CC\u5199\u5B83\u7684 id\u3002\u6CA1\u6709\u503C\u5F97\u6C89\u6DC0\u7684\u4E1C\u897F\u5C31\u660E\u786E\u8BF4 skip\u2014\u2014\u5B81\u7F3A\u52FF\u6EE5\u3002\n\n## \u8F93\u51FA\u683C\u5F0F\n\n\u53EA\u8F93\u51FA\u4E00\u4E2A JSON \u5BF9\u8C61\uFF0C\u4E0D\u8981\u4EE3\u7801\u56F4\u680F\u3001\u4E0D\u8981\u89E3\u91CA\uFF1A\n\n{\"decision\":\"apply\"|\"skip\",\"reason\":\"<\u4E00\u53E5\u8BDD\u4F9D\u636E>\",\"proposals\":[{\"action\":\"create\"|\"update\"|\"delete\",\"id\":\"<kebab-slug\uFF0Cupdate/delete \u5FC5\u586B>\",\"type\":\"user\"|\"feedback\"|\"reference\",\"title\":\"<\u77ED\u6807\u9898>\",\"description\":\"<\u4E00\u53E5\u8BDD\u76F8\u5173\u6027\u94A9\u5B50>\",\"body\":\"<\u6B63\u6587>\",\"sourceSeqs\":\"<\u7528\u6237\u539F\u8BDD\u6240\u5728 seq\uFF0C\u5982 820-831\uFF0C\u53EF\u7701\u7565>\"}]}";
|
|
13
|
+
export declare const EXTRACTION_SYSTEM_PROMPT = "\u4F60\u662F\u8BB0\u5FC6\u63D0\u53D6\u4E13\u5458\u3002\u4F60\u7684\u552F\u4E00\u4EFB\u52A1\uFF1A\u4ECE\u4F1A\u8BDD\u8F68\u8FF9\u589E\u91CF\u91CC\u5224\u65AD\u54EA\u4E9B\u4FE1\u606F\u503C\u5F97\u5B58\u5165\u7528\u6237\u7684\u8DE8\u4F1A\u8BDD\u6301\u4E45\u8BB0\u5FC6\uFF0C\u5E76\u63D0\u51FA\u7ED3\u6784\u5316\u63D0\u6848\u3002\u4F60\u4E0D\u6267\u884C\u4EFB\u52A1\u3001\u4E0D\u56DE\u7B54\u7528\u6237\u3001\u4E0D\u89E3\u91CA\u63A8\u7406\u3002\n\n## \u4F55\u65F6\u5199\u5165\u8BB0\u5FC6\n\n<type name=\"user\">\n <when_to_save>\u5F97\u77E5\u7528\u6237\u7684\u753B\u50CF\u4E0E\u73AF\u5883\u4E8B\u5B9E\uFF1A\u89D2\u8272\u3001\u6280\u672F\u6808\u3001\u7ECF\u9A8C\u6C34\u5E73\u3001\u504F\u597D\uFF0C\u4EE5\u53CA\u673A\u5668\u4E0E\u5DE5\u5177\u94FE\uFF08\u64CD\u4F5C\u7CFB\u7EDF\u3001\u88C5\u4E86\u4EC0\u4E48\u3001\u914D\u7F6E\u5728\u54EA\uFF09\u3002\u4F8B\uFF1A\"\u6211\u5728 Fedora \u4E0A\u5DE5\u4F5C\uFF0C\u65E5\u5E38\u8DD1 dotnet-desktop profile\"\u3002</when_to_save>\n</type>\n\n<type name=\"feedback\">\n <when_to_save>\u4E24\u7C7B\u4FE1\u53F7\uFF1A\n \uFF081\uFF09\u7EA0\u6B63\u2014\u2014\u7528\u6237\u8BF4\"\u4E0D\u662F\u8FD9\u6837\"\"\u522B\"\"\u505C\u4E0B\"\u7684\u90A3\u4E00\u8F6E\uFF0C\u5B58\u88AB\u7EA0\u6B63\u7684\u505A\u6CD5\u4E0E\u6B63\u786E\u505A\u6CD5\uFF1B\n \uFF082\uFF09\u786E\u8BA4\u2014\u2014\u66F4\u5B89\u9759\u4F46\u540C\u6837\u8981\u7D27\uFF1A\u7528\u6237\u63A5\u53D7\u4E86\u4F60\u4E0D\u5BFB\u5E38\u7684\u9009\u62E9\u800C\u65E0\u5F02\u8BAE\uFF0C\u6216\u660E\u786E\u8BF4\"\u5BF9\uFF0C\u5C31\u8FD9\u6837\"\u3002\u53EA\u5B58\u7EA0\u9519\u4F1A\u8BA9\u884C\u4E3A\u8D8A\u6765\u8D8A\u4FDD\u5B88\u3002\n \u4F8B\uFF1A\"\u6D4B\u8BD5\u522B mock \u6570\u636E\u5E93\uFF0C\u4E0A\u6B21 mock \u8FC7\u4E86\u7EBF\u4E0A\u8FC1\u79FB\u6302\u4E86\"\u2014\u2014\u5B58\u89C4\u5219\u5E76\u5E26\u4E0A\u4E8B\u6545\u539F\u56E0\u3002</when_to_save>\n <body_structure>\u89C4\u5219\u5148\u884C\uFF0C\u968F\u540E\u5FC5\u5E26\u4E24\u884C\uFF1A**Why:**\uFF08\u7528\u6237\u7ED9\u7684\u7406\u7531\u2014\u2014\u77E5\u9053\u4E3A\u4EC0\u4E48\u624D\u80FD\u5224\u65AD\u8FB9\u7F18\u60C5\u51B5\uFF09\u548C **How to apply:**\uFF08\u4F55\u65F6\u4F55\u5730\u751F\u6548\uFF09\u3002\u7F3A\u8FD9\u4E24\u884C\u7684\u63D0\u6848\u4F1A\u88AB\u673A\u68B0\u62D2\u7EDD\u3002</body_structure>\n</type>\n\n<type name=\"reference\">\n <when_to_save>\u7528\u6237\u63D0\u5230\u672A\u6765\u4F1A\u7528\u5230\u7684\u8D44\u6E90\u6307\u9488\uFF1AURL\u3001\u4EEA\u8868\u76D8\u3001\u5DE5\u5355\u3001\u672C\u5730\u6570\u636E\u5E93\u3001\u6587\u6863\u4F4D\u7F6E\u3002</when_to_save>\n</type>\n\n**\u8FB9\u754C\u5224\u636E\uFF1A\u6362\u4E00\u4E2A\u4ED3\u5E93\u8FD8\u6709\u7528\u7684\u4FE1\u606F\u624D\u8FDB\u8BB0\u5FC6\u3002**\u51B3\u7B56\u3001\u67B6\u6784\u53D6\u820D\u3001\u8FDB\u884C\u4E2D\u72B6\u6001\u53EA\u5BF9\u5F53\u524D\u4ED3\u5E93\u6709\u4EF7\u503C\u2014\u2014\u5B83\u4EEC\u8D70\u4ED3\u5E93\u7684 ADR/\u6587\u6863\u8DEF\u7EBF\uFF0C\u7EDD\u4E0D\u63D0\u6848\u3002\u80FD\u4ECE\u4EE3\u7801\u3001git \u5386\u53F2\u3001\u4ED3\u5E93\u6587\u4EF6\u91CC\u91CD\u65B0\u63A8\u5BFC\u51FA\u6765\u7684\u4E8B\u5B9E\u4E0D\u5B58\uFF1B\u4E34\u65F6\u4EFB\u52A1\u72B6\u6001\u3001\u4E00\u6B21\u6027\u8C03\u8BD5\u8FC7\u7A0B\u3001\u65E0\u590D\u73B0\u8BC1\u636E\u7684\u95EE\u9898\u4FEE\u590D\u4E0D\u5B58\u3002\u76F8\u5BF9\u65E5\u671F\u4E00\u5F8B\u8F6C\u6210\u7EDD\u5BF9\u65E5\u671F\uFF08\"\u5468\u56DB\"\u2192\"2026-10-08\"\uFF09\u3002\n\n**\u5F52\u5C5E\u4E09\u6D4B\uFF08\u4EFB\u4E00\u4E0D\u901A\u8FC7\u5373\u4E0D\u63D0\u6848\uFF0C\u4E0E\u4E0A\u9762\u7684\u8FB9\u754C\u5224\u636E\u662F\u540C\u4E00\u628A\u5C3A\u5B50\uFF09\uFF1A**\n1. \u4E3B\u8BED\u6D4B\u8BD5\u2014\u2014\u8FD9\u6761\u7684\u4E3B\u8BED\u662F\"\u6211/\u73AF\u5883\"\uFF0C\u8FD8\u662F\"\u8FD9\u4E2A\u4ED3\u5E93\u7684\u67D0\u7248\u673A\u5236\"\uFF1F\u7248\u672C\u53F7\u3001\u9608\u503C\u3001\u5F00\u5173\u540D\u4E00\u51FA\u73B0\uFF0C\u4E3B\u8BED\u5C31\u662F\u4ED3\u5E93\uFF0C\u4E0D\u63D0\u6848\u3002\n2. \u53BB\u540D\u6D4B\u8BD5\u2014\u2014\u628A\u4ED3\u5E93\u540D\u3001\u7248\u672C\u53F7\u3001\u673A\u5236\u540D\u5168\u62B9\u6389\uFF0C\u53E5\u5B50\u8FD8\u6210\u7ACB\u5417\uFF1F\u4E0D\u6210\u7ACB\uFF0C\u4E0D\u63D0\u6848\u3002\n3. \u5F52\u5C5E\u6D4B\u8BD5\u2014\u2014\u4ED3\u5E93\u4E8B\u5B9E\uFF08\u8BBE\u8BA1\u62CD\u677F\u3001\u7248\u672C\u7EC6\u8282\u3001\u4EFB\u52A1\u72B6\u6001\uFF09\u4F4F ADR/docs/\u4EA4\u63A5\uFF1B\u8BB0\u5FC6\u53EA\u6536\u8DDF\u4EBA\u8D70\u7684\uFF08\u534F\u4F5C\u504F\u597D\u3001\u73AF\u5883\u4E8B\u5B9E\u3001\u8DE8\u9879\u76EE\u505A\u6CD5\uFF09\u3002\n\n## \u66F4\u65B0\u4F18\u5148\u4E8E\u65B0\u5EFA\n\n\u5DF2\u6709\u8BB0\u5FC6\u7684\u72B6\u6001\u53D8\u4E86\uFF0C\u63D0\u6848 update \u6539\u539F\u6761\u76EE\uFF1B\u65B0\u65E7\u5E76\u5B58\u6BD4\u6CA1\u6709\u8BB0\u5FC6\u66F4\u7CDF\u3002\u8981\u66F4\u65B0\u6216\u5220\u9664\u7684\u6761\u76EE\u4F1A\u8FDE\u540C\u5168\u6587\u7ED9\u4F60\uFF0C\u63D0\u6848\u91CC\u5199\u5B83\u7684 id\u3002\u6CA1\u6709\u503C\u5F97\u6C89\u6DC0\u7684\u4E1C\u897F\u5C31\u660E\u786E\u8BF4 skip\u2014\u2014\u5B81\u7F3A\u52FF\u6EE5\u3002\n\n## \u8F93\u51FA\u683C\u5F0F\n\n\u53EA\u8F93\u51FA\u4E00\u4E2A JSON \u5BF9\u8C61\uFF0C\u4E0D\u8981\u4EE3\u7801\u56F4\u680F\u3001\u4E0D\u8981\u89E3\u91CA\uFF1A\n\n{\"decision\":\"apply\"|\"skip\",\"reason\":\"<\u4E00\u53E5\u8BDD\u4F9D\u636E>\",\"proposals\":[{\"action\":\"create\"|\"update\"|\"delete\",\"id\":\"<kebab-slug\uFF0Cupdate/delete \u5FC5\u586B>\",\"type\":\"user\"|\"feedback\"|\"reference\",\"title\":\"<\u77ED\u6807\u9898>\",\"description\":\"<\u4E00\u53E5\u8BDD\u76F8\u5173\u6027\u94A9\u5B50>\",\"body\":\"<\u6B63\u6587>\",\"sourceSeqs\":\"<\u7528\u6237\u539F\u8BDD\u6240\u5728 seq\uFF0C\u5982 820-831\uFF0C\u53EF\u7701\u7565>\"}]}";
|
|
14
|
+
/** The pre-gate system prompt: a small verdict before the expensive full call. */
|
|
15
|
+
export declare const EXTRACTION_CHEAP_SYSTEM_PROMPT = "\u4F60\u662F\u8BB0\u5FC6\u63D0\u53D6\u7684\u9884\u68C0\u95E8\u3002\u53EA\u5224\u8FD9\u8F6E\u8F68\u8FF9\u589E\u91CF\u91CC\u6709\u6CA1\u6709\u503C\u5F97\u6C89\u6DC0\u7684\u8DE8\u4F1A\u8BDD\u8BB0\u5FC6\uFF08\u7528\u6237\u753B\u50CF\u4E0E\u73AF\u5883\u4E8B\u5B9E\u3001\u53EF\u590D\u7528\u7684\u505A\u6CD5\u7EA0\u6B63\u4E0E\u786E\u8BA4\u3001\u672A\u6765\u4F1A\u7528\u7684\u8D44\u6E90\u6307\u9488\uFF09\uFF0C\u5148\u8FC7\u5F52\u5C5E\u4E09\u6D4B\uFF1A\u4E3B\u8BED\u662F\u7528\u6237/\u73AF\u5883\u8FD8\u662F\u672C\u4ED3\u5E93\u7684\u67D0\u7248\u673A\u5236\uFF1B\u62B9\u6389\u4ED3\u5E93\u540D\u7248\u672C\u53F7\u673A\u5236\u540D\u540E\u8FD8\u6210\u7ACB\u5417\uFF1B\u4ED3\u5E93\u4E8B\u5B9E\u4F4F ADR/docs\u3002\u5F52\u5C5E\u4E0D\u8FC7\u76F4\u63A5\u5224 false\u3002\u53EA\u8F93\u51FA JSON\uFF0C\u4E0D\u8981\u4EE3\u7801\u56F4\u680F\u3001\u4E0D\u8981\u89E3\u91CA\uFF1A\n\n{\"worthExtracting\":true|false,\"reason\":\"<\u4E00\u53E5\u8BDD\u4F9D\u636E>\"}";
|
|
16
|
+
/** Head length of the serialized increment the pre-gate reads (small by design). */
|
|
17
|
+
export declare const CHEAP_INCREMENT_MAX = 4000;
|
|
18
|
+
/** The pre-gate prompt: increment head only — no manifest, no candidates. */
|
|
19
|
+
export declare function cheapPrompt(input: {
|
|
20
|
+
incrementHead: string;
|
|
21
|
+
userSeqs: readonly number[];
|
|
22
|
+
}): string;
|
|
23
|
+
/** The pre-gate verdict; `null` when the model did not return verdict JSON. */
|
|
24
|
+
export interface CheapVerdict {
|
|
25
|
+
worth: boolean;
|
|
26
|
+
reason: string;
|
|
27
|
+
}
|
|
28
|
+
/** Parse the pre-gate answer. `null` means fail-open: run the full call. */
|
|
29
|
+
export declare function parseCheapAnswer(text: string): CheapVerdict | null;
|
|
14
30
|
/** The existing-memory manifest line shown to the model. */
|
|
15
31
|
export declare function manifestLineOf(record: {
|
|
16
32
|
id: string;
|
package/lib/extraction-prompt.js
CHANGED
|
@@ -32,6 +32,11 @@ export const EXTRACTION_SYSTEM_PROMPT = `你是记忆提取专员。你的唯一
|
|
|
32
32
|
|
|
33
33
|
**边界判据：换一个仓库还有用的信息才进记忆。**决策、架构取舍、进行中状态只对当前仓库有价值——它们走仓库的 ADR/文档路线，绝不提案。能从代码、git 历史、仓库文件里重新推导出来的事实不存；临时任务状态、一次性调试过程、无复现证据的问题修复不存。相对日期一律转成绝对日期（"周四"→"2026-10-08"）。
|
|
34
34
|
|
|
35
|
+
**归属三测（任一不通过即不提案，与上面的边界判据是同一把尺子）：**
|
|
36
|
+
1. 主语测试——这条的主语是"我/环境"，还是"这个仓库的某版机制"？版本号、阈值、开关名一出现，主语就是仓库，不提案。
|
|
37
|
+
2. 去名测试——把仓库名、版本号、机制名全抹掉，句子还成立吗？不成立，不提案。
|
|
38
|
+
3. 归属测试——仓库事实（设计拍板、版本细节、任务状态）住 ADR/docs/交接；记忆只收跟人走的（协作偏好、环境事实、跨项目做法）。
|
|
39
|
+
|
|
35
40
|
## 更新优先于新建
|
|
36
41
|
|
|
37
42
|
已有记忆的状态变了，提案 update 改原条目；新旧并存比没有记忆更糟。要更新或删除的条目会连同全文给你，提案里写它的 id。没有值得沉淀的东西就明确说 skip——宁缺勿滥。
|
|
@@ -41,6 +46,49 @@ export const EXTRACTION_SYSTEM_PROMPT = `你是记忆提取专员。你的唯一
|
|
|
41
46
|
只输出一个 JSON 对象，不要代码围栏、不要解释：
|
|
42
47
|
|
|
43
48
|
{"decision":"apply"|"skip","reason":"<一句话依据>","proposals":[{"action":"create"|"update"|"delete","id":"<kebab-slug，update/delete 必填>","type":"user"|"feedback"|"reference","title":"<短标题>","description":"<一句话相关性钩子>","body":"<正文>","sourceSeqs":"<用户原话所在 seq，如 820-831，可省略>"}]}`;
|
|
49
|
+
/** The pre-gate system prompt: a small verdict before the expensive full call. */
|
|
50
|
+
export const EXTRACTION_CHEAP_SYSTEM_PROMPT = `你是记忆提取的预检门。只判这轮轨迹增量里有没有值得沉淀的跨会话记忆（用户画像与环境事实、可复用的做法纠正与确认、未来会用的资源指针），先过归属三测：主语是用户/环境还是本仓库的某版机制；抹掉仓库名版本号机制名后还成立吗；仓库事实住 ADR/docs。归属不过直接判 false。只输出 JSON，不要代码围栏、不要解释：
|
|
51
|
+
|
|
52
|
+
{"worthExtracting":true|false,"reason":"<一句话依据>"}`;
|
|
53
|
+
/** Head length of the serialized increment the pre-gate reads (small by design). */
|
|
54
|
+
export const CHEAP_INCREMENT_MAX = 4000;
|
|
55
|
+
/** The pre-gate prompt: increment head only — no manifest, no candidates. */
|
|
56
|
+
export function cheapPrompt(input) {
|
|
57
|
+
return [
|
|
58
|
+
"（用户直接发言所在 seq：",
|
|
59
|
+
`${input.userSeqs.length > 0 ? input.userSeqs.join(",") : "无"}）`,
|
|
60
|
+
input.incrementHead,
|
|
61
|
+
"按系统指令输出 JSON 判定。",
|
|
62
|
+
].join("\n");
|
|
63
|
+
}
|
|
64
|
+
/** Parse the pre-gate answer. `null` means fail-open: run the full call. */
|
|
65
|
+
export function parseCheapAnswer(text) {
|
|
66
|
+
const stripped = text.trim().replace(/^```(?:json)?\s*/i, "").replace(/\s*```$/i, "").trim();
|
|
67
|
+
const start = stripped.indexOf("{");
|
|
68
|
+
const end = stripped.lastIndexOf("}");
|
|
69
|
+
if (start < 0 || end <= start) {
|
|
70
|
+
return null;
|
|
71
|
+
}
|
|
72
|
+
let parsed;
|
|
73
|
+
try {
|
|
74
|
+
parsed = JSON.parse(stripped.slice(start, end + 1));
|
|
75
|
+
}
|
|
76
|
+
catch {
|
|
77
|
+
return null;
|
|
78
|
+
}
|
|
79
|
+
// Defensive: the sliced text always starts with "{", so a successful
|
|
80
|
+
// JSON.parse here is always an object — same guard as parseExtractionAnswer.
|
|
81
|
+
/* v8 ignore next 3 */
|
|
82
|
+
if (typeof parsed !== "object" || parsed === null) {
|
|
83
|
+
return null;
|
|
84
|
+
}
|
|
85
|
+
const answer = parsed;
|
|
86
|
+
if (typeof answer.worthExtracting !== "boolean") {
|
|
87
|
+
return null;
|
|
88
|
+
}
|
|
89
|
+
const reason = typeof answer.reason === "string" && answer.reason.length > 0 ? answer.reason : "无理由";
|
|
90
|
+
return { worth: answer.worthExtracting, reason: reason.slice(0, 300) };
|
|
91
|
+
}
|
|
44
92
|
/** The existing-memory manifest line shown to the model. */
|
|
45
93
|
export function manifestLineOf(record) {
|
|
46
94
|
return `- id=${record.id}｜type=${record.type}｜title=${record.title}｜钩子=${record.description}`;
|
package/lib/extraction.js
CHANGED
|
@@ -1,5 +1,5 @@
|
|
|
1
1
|
import { boundaryCursorOf, evaluateSlice, eventsAfterCursor, isInternalAgent, seqOfCursor, serializeIncrement } from "./extraction-surface.js";
|
|
2
|
-
import { EXTRACTION_SYSTEM_PROMPT, extractionPrompt, manifestLineOf, parseExtractionAnswer } from "./extraction-prompt.js";
|
|
2
|
+
import { CHEAP_INCREMENT_MAX, EXTRACTION_CHEAP_SYSTEM_PROMPT, EXTRACTION_SYSTEM_PROMPT, cheapPrompt, extractionPrompt, manifestLineOf, parseCheapAnswer, parseExtractionAnswer } from "./extraction-prompt.js";
|
|
3
3
|
import { cwdOf } from "./memory-section.js";
|
|
4
4
|
/** Head length of a failed run's raw answer kept in the ledger `files` column. */
|
|
5
5
|
const FAILURE_RAW_MAX = 2048;
|
|
@@ -107,6 +107,35 @@ async function runExtractionInner(deps, target, opts) {
|
|
|
107
107
|
}
|
|
108
108
|
};
|
|
109
109
|
const increment = serializeIncrement(slice.events, opts.incrementMaxChars);
|
|
110
|
+
// ── Cheap pre-gate: a small verdict before the expensive full call
|
|
111
|
+
// (manifest + full-body candidates + full increment). A "not worth it"
|
|
112
|
+
// consumes the increment exactly like a model skip; an unclear gate
|
|
113
|
+
// (unparseable/failed) fails OPEN to the full call — worst case degrades
|
|
114
|
+
// to the old single-call behavior, never to a stall.
|
|
115
|
+
let cheapUsage;
|
|
116
|
+
{
|
|
117
|
+
const gateStarted = Date.now();
|
|
118
|
+
try {
|
|
119
|
+
const gate = await streamOnce(deps.llm, target, cheapPrompt({ incrementHead: increment.slice(0, CHEAP_INCREMENT_MAX), userSeqs: slice.userSeqs }), EXTRACTION_CHEAP_SYSTEM_PROMPT, 512);
|
|
120
|
+
cheapUsage = gate.usage;
|
|
121
|
+
const verdict = parseCheapAnswer(gate.text);
|
|
122
|
+
if (verdict !== null && !verdict.worth) {
|
|
123
|
+
advanceCursor();
|
|
124
|
+
store.logSkipped({
|
|
125
|
+
...ledgerBase,
|
|
126
|
+
skipReason: `model-skip (cheap-gate): ${verdict.reason}`,
|
|
127
|
+
status: "skipped",
|
|
128
|
+
model: target.model,
|
|
129
|
+
cheapUsage,
|
|
130
|
+
durationMs: Date.now() - gateStarted,
|
|
131
|
+
});
|
|
132
|
+
return { status: "skipped", skipReason: verdict.reason, cursor: boundarySeq };
|
|
133
|
+
}
|
|
134
|
+
}
|
|
135
|
+
catch {
|
|
136
|
+
// Fail open: the full call below is the old behavior.
|
|
137
|
+
}
|
|
138
|
+
}
|
|
110
139
|
const manifest = store.list(target.workspaceId).slice(0, 50).map(manifestLineOf);
|
|
111
140
|
const candidates = candidateRecords(store, target.workspaceId, slice.userText);
|
|
112
141
|
const prompt = extractionPrompt({
|
|
@@ -126,7 +155,7 @@ async function runExtractionInner(deps, target, opts) {
|
|
|
126
155
|
catch (error) {
|
|
127
156
|
const { message, detail } = errorText(error);
|
|
128
157
|
try {
|
|
129
|
-
store.logSkipped({ ...ledgerBase, skipReason: "llm-failed", status: "failed", durationMs: Date.now() - started, files: detail });
|
|
158
|
+
store.logSkipped({ ...ledgerBase, skipReason: "llm-failed", status: "failed", durationMs: Date.now() - started, cheapUsage, files: detail });
|
|
130
159
|
}
|
|
131
160
|
catch (ledgerError) {
|
|
132
161
|
throw new Error(`llm call failed (${message}); failure ledger write also failed (${errorText(ledgerError).message})`);
|
|
@@ -145,6 +174,7 @@ async function runExtractionInner(deps, target, opts) {
|
|
|
145
174
|
status: "failed",
|
|
146
175
|
model: target.model,
|
|
147
176
|
usage,
|
|
177
|
+
cheapUsage,
|
|
148
178
|
durationMs: Date.now() - started,
|
|
149
179
|
files: text.slice(0, FAILURE_RAW_MAX),
|
|
150
180
|
});
|
|
@@ -160,6 +190,7 @@ async function runExtractionInner(deps, target, opts) {
|
|
|
160
190
|
status: "skipped",
|
|
161
191
|
model: target.model,
|
|
162
192
|
usage,
|
|
193
|
+
cheapUsage,
|
|
163
194
|
durationMs: Date.now() - started,
|
|
164
195
|
});
|
|
165
196
|
return { status: "skipped", skipReason: parsed.reason, cursor: boundarySeq };
|
|
@@ -171,6 +202,7 @@ async function runExtractionInner(deps, target, opts) {
|
|
|
171
202
|
runId: `extract:${target.sessionId}:${boundarySeq ?? "tail"}`,
|
|
172
203
|
model: target.model,
|
|
173
204
|
usage,
|
|
205
|
+
cheapUsage,
|
|
174
206
|
decision: parsed.reason,
|
|
175
207
|
}, parsed.proposals);
|
|
176
208
|
if (!outcomes.every((outcome) => outcome.ok)) {
|
|
@@ -193,7 +225,7 @@ function formatCandidate(record) {
|
|
|
193
225
|
return [`# 候选 id=${record.id}（type=${record.type}）`, `title=${record.title}`, `钩子=${record.description}`, "全文：", record.body].join("\n");
|
|
194
226
|
}
|
|
195
227
|
/** One streaming text call with the host session identity forwarded. */
|
|
196
|
-
async function streamOnce(llm, target, prompt) {
|
|
228
|
+
async function streamOnce(llm, target, prompt, system = EXTRACTION_SYSTEM_PROMPT, maxTokens = 4096) {
|
|
197
229
|
let text = "";
|
|
198
230
|
let usage;
|
|
199
231
|
let finish;
|
|
@@ -201,8 +233,8 @@ async function streamOnce(llm, target, prompt) {
|
|
|
201
233
|
provider: target.provider,
|
|
202
234
|
model: target.model,
|
|
203
235
|
messages: [{ role: "user", content: [{ type: "text", text: prompt }] }],
|
|
204
|
-
system
|
|
205
|
-
maxTokens
|
|
236
|
+
system,
|
|
237
|
+
maxTokens,
|
|
206
238
|
// MissingSessionID pitfall: direct calls must carry the host session.
|
|
207
239
|
sessionId: target.sessionId,
|
|
208
240
|
};
|
package/lib/index.d.ts
CHANGED
|
@@ -79,6 +79,23 @@ export declare const Config: z<Schemastery.ObjectS<NoInfer<{
|
|
|
79
79
|
*/
|
|
80
80
|
extraction: z<boolean, boolean, "plain">;
|
|
81
81
|
}>>, "plain">;
|
|
82
|
+
/**
|
|
83
|
+
* The autonomous content-quality loop (own prompts, own daily budget,
|
|
84
|
+
* own ledger — shares only the store's write gates with extraction).
|
|
85
|
+
* `dryRun` ledgers verdicts without landing them (trial mode, default
|
|
86
|
+
* on); `dailyBudget` caps reviewed items per UTC day (default 100).
|
|
87
|
+
*/
|
|
88
|
+
review: z<Schemastery.ObjectS<NoInfer<{
|
|
89
|
+
enabled: z<boolean, boolean, "plain">;
|
|
90
|
+
dryRun: z<boolean, boolean, "plain">;
|
|
91
|
+
dailyBudget: z<number, number, "plain">;
|
|
92
|
+
batchSize: z<number, number, "plain">;
|
|
93
|
+
}>>, Schemastery.ObjectT<NoInfer<{
|
|
94
|
+
enabled: z<boolean, boolean, "plain">;
|
|
95
|
+
dryRun: z<boolean, boolean, "plain">;
|
|
96
|
+
dailyBudget: z<number, number, "plain">;
|
|
97
|
+
batchSize: z<number, number, "plain">;
|
|
98
|
+
}>>, "plain">;
|
|
82
99
|
/**
|
|
83
100
|
* The read-only memory card in the official plugin manager
|
|
84
101
|
* (`plugins.bundle.config`). Defaults to on; hosts without the
|
|
@@ -121,6 +138,23 @@ export declare const Config: z<Schemastery.ObjectS<NoInfer<{
|
|
|
121
138
|
*/
|
|
122
139
|
extraction: z<boolean, boolean, "plain">;
|
|
123
140
|
}>>, "plain">;
|
|
141
|
+
/**
|
|
142
|
+
* The autonomous content-quality loop (own prompts, own daily budget,
|
|
143
|
+
* own ledger — shares only the store's write gates with extraction).
|
|
144
|
+
* `dryRun` ledgers verdicts without landing them (trial mode, default
|
|
145
|
+
* on); `dailyBudget` caps reviewed items per UTC day (default 100).
|
|
146
|
+
*/
|
|
147
|
+
review: z<Schemastery.ObjectS<NoInfer<{
|
|
148
|
+
enabled: z<boolean, boolean, "plain">;
|
|
149
|
+
dryRun: z<boolean, boolean, "plain">;
|
|
150
|
+
dailyBudget: z<number, number, "plain">;
|
|
151
|
+
batchSize: z<number, number, "plain">;
|
|
152
|
+
}>>, Schemastery.ObjectT<NoInfer<{
|
|
153
|
+
enabled: z<boolean, boolean, "plain">;
|
|
154
|
+
dryRun: z<boolean, boolean, "plain">;
|
|
155
|
+
dailyBudget: z<number, number, "plain">;
|
|
156
|
+
batchSize: z<number, number, "plain">;
|
|
157
|
+
}>>, "plain">;
|
|
124
158
|
/**
|
|
125
159
|
* The read-only memory card in the official plugin manager
|
|
126
160
|
* (`plugins.bundle.config`). Defaults to on; hosts without the
|
package/lib/index.js
CHANGED
|
@@ -31,6 +31,7 @@
|
|
|
31
31
|
import z from "@deepseek-ai/schemastery";
|
|
32
32
|
import { mountCardRoutes } from "./card-routes.js";
|
|
33
33
|
import { createExtractionScheduler } from "./extraction.js";
|
|
34
|
+
import { createReviewScheduler } from "./review.js";
|
|
34
35
|
import { createFrozenMemorySection, cwdOf, DEFAULT_MAX_CHARS, DEFAULT_MEMORY_SECTION_ORDER, MEMORY_SECTION_NAME, memorySectionText, } from "./memory-section.js";
|
|
35
36
|
import { registerMemoryTools } from "./memory-tools.js";
|
|
36
37
|
import { registerSkillTools } from "./skill-tools.js";
|
|
@@ -59,6 +60,18 @@ export const Config = z.object({
|
|
|
59
60
|
*/
|
|
60
61
|
extraction: z.boolean(),
|
|
61
62
|
}),
|
|
63
|
+
/**
|
|
64
|
+
* The autonomous content-quality loop (own prompts, own daily budget,
|
|
65
|
+
* own ledger — shares only the store's write gates with extraction).
|
|
66
|
+
* `dryRun` ledgers verdicts without landing them (trial mode, default
|
|
67
|
+
* on); `dailyBudget` caps reviewed items per UTC day (default 100).
|
|
68
|
+
*/
|
|
69
|
+
review: z.object({
|
|
70
|
+
enabled: z.boolean(),
|
|
71
|
+
dryRun: z.boolean(),
|
|
72
|
+
dailyBudget: z.natural(),
|
|
73
|
+
batchSize: z.natural(),
|
|
74
|
+
}),
|
|
62
75
|
/**
|
|
63
76
|
* The read-only memory card in the official plugin manager
|
|
64
77
|
* (`plugins.bundle.config`). Defaults to on; hosts without the
|
|
@@ -119,6 +132,37 @@ function mountExtractionWhenAvailable(host, store, config) {
|
|
|
119
132
|
createExtractionScheduler(events, { store, surface, llm });
|
|
120
133
|
});
|
|
121
134
|
}
|
|
135
|
+
/**
|
|
136
|
+
* Arm the review scheduler through a nested inject: the loop needs only the
|
|
137
|
+
* LLM sibling (no trajectory reader — it judges stored items, not session
|
|
138
|
+
* increments), so it mounts independently from extraction. Own prompts, own
|
|
139
|
+
* budget, own ledger; the store's write gates are the only shared surface.
|
|
140
|
+
*/
|
|
141
|
+
function mountReviewWhenAvailable(host, store, config) {
|
|
142
|
+
const log = host.logger("continual-evolve");
|
|
143
|
+
if (config.review?.enabled === false) {
|
|
144
|
+
log.info("review disabled by config — extraction and tools unaffected");
|
|
145
|
+
return;
|
|
146
|
+
}
|
|
147
|
+
const nested = host;
|
|
148
|
+
const events = host;
|
|
149
|
+
if (typeof nested.inject !== "function" || typeof events.on !== "function") {
|
|
150
|
+
log.warn("host context exposes no inject/on — review not armed (injection and tools unaffected)");
|
|
151
|
+
return;
|
|
152
|
+
}
|
|
153
|
+
nested.inject(["llm"], (scoped) => {
|
|
154
|
+
const context = scoped;
|
|
155
|
+
const llm = (context.llm ?? context.get?.("llm"));
|
|
156
|
+
createReviewScheduler(events, { store, llm }, {
|
|
157
|
+
enabled: true,
|
|
158
|
+
dryRun: config.review?.dryRun ?? true,
|
|
159
|
+
dailyBudget: config.review?.dailyBudget ?? 100,
|
|
160
|
+
batchSize: config.review?.batchSize ?? 10,
|
|
161
|
+
staleDays: 30,
|
|
162
|
+
minIntervalMs: 5 * 60 * 1000,
|
|
163
|
+
});
|
|
164
|
+
});
|
|
165
|
+
}
|
|
122
166
|
/**
|
|
123
167
|
* Mount the card routes on the host web server through a nested inject, so
|
|
124
168
|
* the plugin stays mountable on hosts without that service. Called once the
|
|
@@ -156,6 +200,7 @@ export function apply(host, config) {
|
|
|
156
200
|
state.store = store;
|
|
157
201
|
mountToolsWhenAvailable(host, store, state);
|
|
158
202
|
mountExtractionWhenAvailable(host, store, config);
|
|
203
|
+
mountReviewWhenAvailable(host, store, config);
|
|
159
204
|
if (config.memoryCard?.enabled !== false) {
|
|
160
205
|
mountCardWhenAvailable(host, store);
|
|
161
206
|
}
|