Skip to content

Commit 34633f2

Browse files
docs: README 双表补 v0.7.25/v0.7.26(含 v0.7.25 遗漏)+ CHANGELOG v0.7.26 + 工具数 7→8 (#97)
- 最近版本亮点 + 进化路线图(中英)补 v0.7.25(工具兼容性加固 + memory_get/render 内容预览 + 巩固模型引导,上次发布漏更)与 v0.7.26(defaultEffort 陷阱根治 + LLM 连通性测试) - 根 README 概要路线图同步(英文补 v0.7.23 对齐中文) - CHANGELOG 新增 [0.7.26]:resolveDreamEffort 能力探测 / 设置面板 6 字段提示 / llm-providers + test-model 端点 / 测试清理 - 架构图与源码结构工具数 7→8(memory_get 加入后遗留) Co-authored-by: Anans-Ivresse <[email protected]>
1 parent e6f0d7f commit 34633f2

4 files changed

Lines changed: 40 additions & 4 deletions

File tree

‎README.md‎

Lines changed: 5 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -106,6 +106,8 @@ dsh web
106106
| **v0.7.21** | 修复 autoDream/sleep 的 effort 回退在流式路径失效(catch 式回退死代码→流级捕获失败原因 + 去 effort 重试 + audit 记真实原因) | ✅ |
107107
| **v0.7.22** | 恢复 skipInvalid 宽容校验(issue #89:弱模型整单拒绝→单条跳过 + 合法子集应用 + run 记 degraded)+ autoDream 最小触发间隔 | ✅ |
108108
| **v0.7.23** | 记忆沉淀「反复失败」根治(consolidation 合法空数组 [] → no-op)+ 空体修复第二段(dreamMaxTokens 默认 8192→32768)+ skipInvalid splice 残留 bug | ✅ |
109+
| **v0.7.25** | 工具兼容性加固(memory_get 工具 + 内容预览 + 巩固模型引导,718 测试全绿) | ✅ |
110+
| **v0.7.26** | 记忆巩固 UNSUPPORTED_REASONING_EFFORT 根治(defaultEffort 陷阱 → resolveDreamEffort 能力探测)+ LLM 模型连通性测试(llm-providers / test-model,732 测试全绿) | ✅ |
109111
| **v0.8.0** | 图谱增强:兴趣漂移可视化 + scope 隔离(issue #17)+ 跨 workspace 共享 | 🚧 计划中(9 月末) |
110112

111113
> 完整逐小版本路线图见 [dsh-mneme/README.md](dsh-mneme/README.md#-进化路线图)(中)/ [dsh-mneme/README.en.md](dsh-mneme/README.en.md#-evolution-roadmap)(英)。
@@ -211,6 +213,9 @@ Works out of the box. Enable these as needed:
211213
| **v0.7.0** | Self-evolving memory: heat decay + sleep dual-protection + entity heat projection | ✅ |
212214
| **v0.7.21** | Fix autoDream/sleep effort fallback dead on the stream path (catch-based retry → stream-level failure capture + effortless retry + real cause in audit) | ✅ |
213215
| **v0.7.22** | Restore skipInvalid tolerant validation (issue #89: weak-model whole-batch rejection → per-item skip + valid-subset apply + run marked degraded) + autoDream min trigger interval | ✅ |
216+
| **v0.7.23** | "Consolidation keeps failing" root cause (legal empty array [] → no-op) + empty-body part 2 (dreamMaxTokens default 8192→32768) + skipInvalid splice residue bug | ✅ |
217+
| **v0.7.25** | Tool-compat hardening (memory_get tool + render content preview + consolidation-model guide, 718 tests green) | ✅ |
218+
| **v0.7.26** | Consolidation UNSUPPORTED_REASONING_EFFORT root fix (defaultEffort trap → resolveDreamEffort capability probing) + LLM connectivity test (llm-providers / test-model, 732 tests green) | ✅ |
214219
| **v0.8.0** | Graph enhancement: interest-drift visualization + scope isolation (issue #17) + cross-workspace sharing | 🚧 Planned (late Sep) |
215220

216221
> Full per-minor-version roadmap: [dsh-mneme/README.md](dsh-mneme/README.md#-进化路线图) (zh) / [dsh-mneme/README.en.md](dsh-mneme/README.en.md#-evolution-roadmap) (en).

‎dsh-mneme/CHANGELOG.md‎

Lines changed: 23 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -1,5 +1,28 @@
11
# Changelog
22

3+
## [0.7.26] - 2026-09-09
4+
5+
## 🐛 修复
6+
7+
- **记忆巩固 `UNSUPPORTED_REASONING_EFFORT` 根治(defaultEffort 陷阱)**:harness 在调用方省略 effort 参数时注入 `reasoning.defaultEffort`(模型声明的最低档),若该默认档位本身不被模型支持(如火山 coding 适配器声明 `defaultEffort="low"` 而模型只收某固定档位),则任何重试策略都无效——换 effort 或去掉 effort 都会被同一个理由拒绝。修复:新增 `resolveDreamEffort`,在发流**前**经 `ctx.llm.resolveModelInfo()` 探测路由模型支持的 effort 档位,再发送受支持的档位——
8+
- 配置档位(`dreamReasoningEffort` / `sleepReasoningEffort`)被支持 → 原样发送;
9+
- 配置档位不被支持 → 自动换用模型声明的 `defaultEffort`(若也支持)或首个支持档位,并 `logger.warn` 留痕;
10+
- 模型声明无 reasoning 能力 → 省略 effort 字段(发送普通补全请求);
11+
- `resolveModelInfo` 查询失败 → 按配置原样发送(fail-open,不因探测失败卡死巩固)。
12+
- 影响面:autoDream(`dream.js`)与 sleep(`dream/sleep.js`)两条路径共用该 helper。
13+
- **设置面板巩固/睡眠模型字段选型提示**:`dreamProvider`/`dreamModel`/`dreamReasoningEffort`/`sleepProvider`/`sleepModel`/`sleepReasoningEffort` 6 字段补 `.description()`——引导选非思考模型(思考模型可能烧光 token 预算返回空体导致巩固失败),并说明 effort 不支持时会自动换档。
14+
15+
## ✨ 新增
16+
17+
- **巩固/睡眠模型连通性测试(Web 设置面板配套后端)**:
18+
- `GET /api/dsh-mneme/llm-providers`:宿主侧 LLM provider/model 发现(`ctx.llm.listProviders()`/`listModels()`,逐 provider best-effort),返回 `{ providers: [{ provider, models: [{ id, name }] }] }`,无 `ctx.llm` 时 501;**密钥仅存宿主侧,不经插件侧、不入本端点**。
19+
- `POST /api/dsh-mneme/test-model`:`{ provider?, model?, reasoningEffort? }` 连通性探测——最小流式调用(maxTokens 16)实测模型真实可通。**空 body = 按巩固路由解析**(`dreamProvider/dreamModel > agent 默认模型`,解析不出返回 400 `no-route`);部分输入(有 provider 缺 model)400 `missing-provider-or-model`;成功 200 `{ ok:true, durationMs, modelId }`(+`reply` 预览),失败 502 `{ ok:false, error, durationMs, modelId }`;requireAuth 鉴权。
20+
21+
## 🏗️ 工程
22+
23+
- **测试清理**:`client.test.js` 移除 identity `.replace()`(CodeQL `js/identity-replacement` 告警 #1,测试死代码)。
24+
- 732 测试全绿。
25+
326
## [0.7.25] - 2026-09-09
427

528
## 🆕 新增

‎dsh-mneme/README.en.md‎

Lines changed: 6 additions & 2 deletions
Original file line numberDiff line numberDiff line change
@@ -173,6 +173,8 @@ Every **background LLM call** (autoDream consolidation + summary, autoSummarize
173173
174174
| Version | Highlights |
175175
|------|------|
176+
| **v0.7.26** | Consolidation `UNSUPPORTED_REASONING_EFFORT` root-cause fix + dream/sleep model connectivity test: root-caused the **defaultEffort trap** — the harness injects `reasoning.defaultEffort` when effort is omitted, so if that default tier itself is unsupported, retrying without effort never helps (whatever effort is sent gets rejected); fix: new `resolveDreamEffort` proactively queries `ctx.llm.resolveModelInfo()` for the model's supported effort tiers and sends a supported one — an unsupported configured tier auto-falls back to the model's default/first supported tier, and the field is omitted when the model declares no reasoning capability. Settings panel adds selection hints on 6 dream/sleep model fields (guiding toward non-thinking models so they don't burn the token budget on reasoning). New `GET /api/dsh-mneme/llm-providers` (host-side provider/model discovery; keys never touch the plugin side) + `POST /api/dsh-mneme/test-model` (connectivity test; empty body resolves via the consolidation route and returns `modelId`); 732 tests green |
177+
| **v0.7.25** | Tool-compat hardening + `memory_get`/render content preview + consolidation-model guide: new `memory_get` tool (8th model tool, read a single memory's full body by id) + `memory_search`/`memory_list` render now embeds title/metadata/body preview (the model reads actual memory content even when the host only forwards render text) + consolidation-model selection guide (config comments/README classification, non-thinking vs thinking). Fixed `memory_get` execute nested inside output crashing with `userExecute is not a function` (previous tests only counted tool names, never executed it) + tool de-dup on live patch reload + Standalone API port-collision retry (EADDRINUSE) + client inject declaration alignment + better-sidebar hardening; 718 tests green |
176178
| **v0.7.24** | Fixed DSH Desktop plugin-tree load crash (v0.7.23 regression): cordis 4's ctx is a Proxy — accessing a property not declared in `inject` throws `cannot get property "webServer" without inject` (not `undefined`), and removing webServer from inject meant cordis no longer waited for the host service, so Desktop crashed on restart; fix: restored webServer to inject (cordis applies the plugin only after the host service is ready) + apply/register guard switched to `ctx.reflect.get` (inject-free read, returns `undefined` when absent, never throws); verified with a real cordis + dsh-host-webserver plugin (API routes 200, unknown path 404, headless silently inactive); 714 tests green |
177179
| **v0.7.23** | Root-caused "memory consolidation keeps failing": a legal empty decision array `[]` from consolidation is no longer treated as a failure (CONSOLIDATION_PROMPT explicitly allows "no output when nothing needs changing", so a model with a healthy, non-redundant memory legitimately returns `[]` — yet `validateDecisions` hard-rejected it as `decision list must be a non-empty array`, failing the whole run and flooding the audit with failures; **model-agnostic** — ChatGPT/Claude hit the same trap; fix: empty array short-circuits to `ok:true` no-op instead of tripping the implicit-keep coverage check). Plus: empty-body fix part 2 (`dreamMaxTokens` default 8192→32768 so thinking models don't burn the whole budget on reasoning) + skipInvalid splice residue bug (length equality ≠ content equality, skipped decisions leaked into apply/audit); 712 tests green |
178180
| **v0.7.22** | Restored the v0.6.9 skipInvalid tolerant-validation path (issue #89 regression, lost in the v0.7.11 rewrite): `dreamSkipInvalid` (default true) skips individual invalid decisions, applies the valid subset, and marks the run degraded; `allowCrossTypeMerge` (default false) explicitly relaxes cross-type merging — weak models (e.g. qwen3.8-flash) with jittery schema compliance no longer fail the whole batch and burn LLM calls. Strict mode and the sleep path behave unchanged; global caps/coverage floors still reject the whole run (running over cap = broken model, not minor schema drift). New `dreamMinIntervalMinutes` (0–10080, default 0 = unlimited) minimum autoDream trigger interval — failed/degraded runs also consume the interval (throttling exists to stop back-to-back failing calls); feature_flags whitelist now 34 keys; 696 tests green |
@@ -230,6 +232,8 @@ Every **background LLM call** (autoDream consolidation + summary, autoSummarize
230232
| v0.7.20 | ✅ Done | Heat restore + phase-two frontend + better-sidebar fix | Heat model fully restored (issue #87, backported from v0.7.10: power-law decay + TYPE_DECAY + sleep heat-combined dual protection + entity heat projection) + acceptance checklist landed (heatEnabled default OFF / feature_flags 31 keys / lightMode linkage / sleep demotion audit / updated_at⊥last_accessed_at contract) + phase-two frontend (/list heat projection, HeatBadge three-tier, order=heat page-local sort) + better-sidebar fix (issue #88: inner dynamic sub-plugin); 685 tests green |
231233
| v0.7.21 | ✅ Done | effort-fallback stream fix | Catch-based effort fallback was dead code on the stream path (dsh-llm rc.1 turns adapter failures into a terminal error finish chunk instead of a throw) → `streamText` captures the finish-chunk cause (`describeStreamFailure`) + `withEffortFallback` gains a `getStreamError` accessor (retries without effort when rejected) + `runAuditedLlm` supports `spec.streamError` (real cause in audit); 688 tests green |
232234
| v0.7.22 | ✅ Done | skipInvalid tolerant-validation restore (issue #89) + autoDream throttle | Restored v0.6.9 skipInvalid dual-track structure (lost in the v0.7.11 rewrite): `dreamSkipInvalid` skips individual invalid decisions + applies the valid subset + marks the run degraded; `allowCrossTypeMerge` explicitly relaxes cross-type merging; weak models (qwen3.8-flash) with jittery schema compliance no longer fail the whole batch. New `dreamMinIntervalMinutes` (0–10080, default 0) minimum trigger interval — failed/degraded runs also consume it. Strict mode / sleep path unchanged; feature_flags whitelist 34 keys; 696 tests green |
235+
| v0.7.25 | ✅ Done | Tool-compat hardening + content preview + consolidation-model guide | New `memory_get` tool (8th model tool, full-body read by id) + `memory_search`/`memory_list` render embeds title/metadata/body preview + consolidation-model selection guide; fixed `memory_get` execute nested inside output (`userExecute is not a function`) + tool de-dup on live patch reload + Standalone API port-collision retry + client inject alignment + better-sidebar hardening; 718 tests green |
236+
| **v0.7.26** | ✅ Done | Consolidation effort-trap root fix + LLM connectivity test | `UNSUPPORTED_REASONING_EFFORT` root cause (defaultEffort trap: harness injects `reasoning.defaultEffort` when effort is omitted, so an unsupported default can never be retried) → `resolveDreamEffort` proactively queries `ctx.llm.resolveModelInfo()` for the model's supported effort tiers (unsupported configured tier falls back to the model's default/first supported tier; field omitted when the model declares no reasoning capability); settings panel adds selection hints on 6 dream/sleep model fields; new `GET /api/dsh-mneme/llm-providers` + `POST /api/dsh-mneme/test-model` (connectivity test; empty body resolves via the consolidation route; keys never touch the plugin side); 732 tests green |
233237
| **v0.8.0** | 🚧 Planned (late Sep) | Graph enhancement | Interest-drift visualization + scope isolation (issue #17) + cross-workspace sharing |
234238

235239
> All new capabilities ship as **toggleable features** (enabled/disabled via configuration), conservatively on by default and never breaking existing behavior. The `failure_memories` table and the autoDream decision engine have already paved the way for future reflective growth.
@@ -420,7 +424,7 @@ dsh-mneme config show # Show current config (toke
420424
│ 服务层:saveWithDedupe / injectCandidates │
421425
│ / mergeHumanEdits / onWrite 钩子 │
422426
├─────────────────────────────────────────────────┤
423-
│ 模型接口:7 个工具 + 自动注入 + 会话摘要 │
427+
│ 模型接口:8 个工具 + 自动注入 + 会话摘要 │
424428
├─────────────────────────────────────────────────┤
425429
│ autoDream:阈值调度 → LLM 决策清单 │
426430
│ → 校验(fail-safe)→ 应用 → 摘要 │
@@ -437,7 +441,7 @@ src/
437441
├── mirror.js # Markdown 镜像(渲染/解析,人工优先)
438442
├── service.js # 领域逻辑(去重合并、注入筛选、写入钩子)
439443
├── config.js # schemastery 配置 schema
440-
├── tools.js # 7 个模型工具(defineTool)
444+
├── tools.js # 8 个模型工具(defineTool)
441445
├── inject.js # systemPrompt.context 动态注入
442446
├── summarize.js # 会话结束 LLM 摘要
443447
├── dream.js # autoDream 调度 + runDream(LLM 决策 + 摘要)

0 commit comments

Comments
 (0)