dsh-continual-evolve 0.10.4 → 0.10.6

package/README.md

@@ -7,7 +7,7 @@
 [![CI](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml/badge.svg)](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Node](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933)](package.json)
-[![Tests](https://img.shields.io/badge/tests-1075%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-1097%20passing-brightgreen)]()
 [![Coverage · statements](https://img.shields.io/badge/coverage_statements-98%25-brightgreen)]()
 [![Coverage · branches](https://img.shields.io/badge/coverage_branches-92%25-green)]()
 [![Coverage · functions](https://img.shields.io/badge/coverage_functions-99%25-brightgreen)]()
@@ -34,7 +34,7 @@ Agents accumulate reusable experience (repeated failures, durable facts, reusabl
 2. **Capability-aware auxiliary calls** — the memory loop, review, planner, wrapup, and fate resolve exact provider/model metadata through [`src/llm-text.ts`](src/llm-text.ts), use the lowest advertised enabled reasoning effort (falling back to a closing effort only when no enabled level exists), and forward the host session id for provider routing; models without reasoning metadata use their provider default.
 3. **Guard** — code-enforced validation: edit schema, blast-radius/scope coherence, and the promotion policy (project-scoped markers, thin content, near-duplicate detection, credential screening keep the global store clean — secrets are rejected at every write sink, including mount materialization). Global creates that near-duplicate an existing entry are rejected at write time (≥0.8 similarity); moderate overlaps carry a `conflictHint` for later consolidation.
 4. **Approve** — global and project writes require explicit human approval; the dialog shows the bounded structured edit diff and conflict warnings, while malformed/lost responses remain retryable rather than counting as rejection.
-5. **Apply & inject** — memory batches preflight every persistent approval, recheck abort before writes, and compensate earlier scope writes if a later batch fails; every successful scope still passes through snapshot + audit. Prompt notes and delegation specs inject into the system prompt (capped, relevance-ranked, contradicted entries demoted, zero tokens when empty); memories/skills appear as a relevance-ordered capped directory index (`- [memory:type:id] title` hooks, full text one `evolve_list` away).
+5. **Apply & inject** — memory batches preflight every persistent approval, recheck abort before writes, and compensate earlier scope writes if a later batch fails; every successful scope still passes through snapshot + audit. Prompt notes and delegation specs inject into the system prompt (capped, relevance-ranked, contradicted entries demoted, zero tokens when empty); memory CONTENT injects at session start under a hard character budget, frozen per session, with the when_to_save guide riding along; skills still appear as a relevance-ordered capped directory index.
 6. **Validate & roll back** — benchmarks score candidates against frozen cases; rejected candidates roll back deterministically and are captured as draft regression cases (`auto_regression` benchmark).
 
 ## Install
@@ -55,14 +55,11 @@ Commands (in-session):
 
 | Command | Effect |
 |---|---|
-| `/evolve` | help + current local store |
+| `/evolve` | short help + current local store (`/evolve help all` lists every subcommand) |
 | `/evolve list · history · rollback <id>` | inspect and revert (add `project` for this project's store, `global` for the cross-project store) |
 | `/evolve plan [msg]` | run the LLM planner against the store |
 | `/evolve wrapup` | assess this session's local entries: promote / archive / keep |
-| `/evolve archive · unarchive · demote <id>` | hide from injection (data kept, restorable) — `demote` targets global noise |
-| `/evolve recall [scope] <query…>` | targeted memory recall: full content with version, source, and staleness |
-| `/evolve remember <type> [scope] <text…>` | immediately persist one typed memory (`user|feedback|project|reference`) |
-| `/evolve forget [scope] <query…>` | locate one memory and archive it (restorable); ambiguous queries only list |
+| `/evolve archive · unarchive <id>` | hide from injection (data kept, restorable) |
 | `/evolve consolidate [apply] [merge]` | report (or apply) one batch archive of conflict-hinted + stale zero-use global entries; `merge` folds near-duplicate content into the survivors |
 | `/evolve failures` | aggregated failure classes (gate + benchmark) |
 | `/evolve log [tail N] [session <id>]` | plugin log |
@@ -73,13 +70,13 @@ Commands (in-session):
 | `/evolve pause · resume · status` | pause/resume the auto-review gate (manual tools keep working), gate state |
 | `/evolve usage` | per-entry injection counts + exact provider-reported tokens for direct memory/review/planner/wrapup/fate calls (benchmark host subagents excluded) |
 
-Model tools: `evolve_list / add / update / delete / rollback / recall` (`evolve_delete` takes `id` or a batch `ids` array — one refinement, one approval; `evolve_recall` filters by query, kinds, scopes, memory types, and limit, and returns full content with version, source, and staleness).
+Model tools: `evolve_list / add / update / delete / rollback / recall` (`evolve_delete` takes `id` or a batch `ids` array — one refinement, one approval; `evolve_recall` filters by query, kinds, scopes, memory types, and limit, and returns full content with version, source, and staleness). Memory reads and writes live in the conversation — the model carries the injected memory index plus `evolve_recall`/`evolve_add` — so there are no `/evolve remember · forget · recall` counterparts: ask in chat.
 
 For third-party consumers: every applied evolution (gate or manual) appends a structured `evolve_complete` event to `reviews.jsonl` (`src/evolve-event.ts` defines the shape) alongside the human-readable audit records.
 
 `/evolve usage` also reads `evolve/token-usage.jsonl`: exact provider-reported input/cache/output/total tokens for the plugin's direct memory-agent, review, planner, manual-wrapup, and automatic-fate calls. The report covers a retained tail rather than lifetime usage, distinguishes missing provider samples, and explicitly excludes host benchmark subagents, their agent-loop calls, and per-entry injection attribution.
 
-Injection shape: prompt notes and delegation specs inject with content (≤6/kind × 180 chars, relevance-ranked). Memories and skills appear as a relevance-ordered directory index (`[memory:type:id] title` hooks, capped at 15 lines with a fold counter) — full text via `evolve_recall` (targeted) or `evolve_list`. Every memory apply also refreshes a readable `MEMORY.md` index plus one fact file per entry in the store directory. Empty store = zero injected tokens.
+Injection shape: prompt notes and delegation specs inject with content (≤6/kind × 180 chars, relevance-ranked). Memories inject as CONTENT at session start: the `evolve:memory-index` section (order 400) carries the when_to_save guide plus every memory body the budget allows, ranked `project > feedback > user > reference`, with overflow degraded to `[memory:type:id] title` hooks and the remainder counted (hard cap `memoryIndex.maxChars`, default 6000 chars; `evolve_recall` reads anything not shown). The section is computed once per session and reused byte-for-byte, so the system prompt stays stable and prompt-cache reads keep hitting — a memory written mid-session appears in the next session. Skills still appear as a relevance-ordered directory index (capped at 15 lines with a fold counter); memories no longer do. Every memory apply also refreshes a readable `MEMORY.md` index plus one fact file per entry in the store directory. With `memoryIndex.guide` off and an empty store, injection is zero tokens.
 
 ## Configuration
 
@@ -94,13 +91,18 @@ Injection shape: prompt notes and delegation specs inject with content (≤6/kin
 | `reviewBudgetTokens` | `4096` | output budget for the gate call |
 | `notifyOnAutoReview` | `true` | visible follow-up notice after an applied gate run |
 | `requireGlobalApproval` | `true` | global and project edits ask for explicit approval |
+| `recordLanguage` | `auto` | authoring **and dialog** language: `auto` follows the DSH client preference, then the session's own user text, then `en`; `zh`/`en` pin it |
 | `localFate` | `false` | optional local-entry promote/archive fate assessment; unreachable while the listener runs memory-only, so it only affects direct/full callers |
 | `fateIntervalTurns` | follows `reviewIntervalTurns` | minimum turns between fate assessments |
 | `goalBlockedWrapupTurns` | `3` | consecutive blocked-goal gate runs trigger one fate assessment (`0` disables) |
 | `promotionBlockPatterns` | POSIX paths, session ids, `~/.dsh` | content matching these is project-scoped and never promoted to global |
 | `promotionMinChars` | `100` | whole promotions below this length stay local |
 | `injectionDirectoryLines` | `15` | entry-directory lines per build before folding into a counter |
-| `sectionOrder` | `118` | system-prompt section order |
+| `sectionOrder` | `118` | system-prompt section order for the guidance + entries sections |
+| `memoryIndex.enabled` | `true` | register the `evolve:memory-index` content section |
+| `memoryIndex.guide` | `true` | include the when_to_save guide (with the store empty and this off, the section renders nothing) |
+| `memoryIndex.order` | `400` | section order (upstream named slots start at `PLAN_POLICY=500`; the plugin's other sections sit at 118/119) |
+| `memoryIndex.maxChars` | `6000` | hard character budget for the injected memories block |
 | `skillsDir` | `<dshHome>/skills` | where skill entries materialize as SKILL.md bundles |
 | `rubricKey` | auto-generated key file | AES-256-GCM passphrase for benchmark rubrics (`DSH_EVOLVE_RUBRIC_KEY` overrides) |
 | `logToFile` / `logLevel` / `logMaxBytes` | `true` / `1` / 5 MiB | plugin-owned JSONL file log with rotation |
@@ -142,7 +144,7 @@ before aborting.
 
 ```bash
 pnpm install && pnpm build   # deps + tsc -> lib/
-pnpm test                    # vitest (1075 tests)
+pnpm test                    # vitest (1097 tests)
 pnpm test:coverage           # v8 coverage, thresholds enforced in CI
 pnpm coverage:gaps           # locate uncovered lines per file (read-only)
 pnpm lint                    # oxlint src test
@@ -152,7 +154,7 @@ Project layout:
 
 ```
 ├── src/                   # engine, tools, commands, memory agent, recall, projection, gate, fate, benchmark, injection + token usage…
-├── test/                  # vitest suites (58 files)
+├── test/                  # vitest suites (59 files)
 ├── lib/                   # build output (tsc)
 ├── docs/
 │   ├── design.md          # full design doc (hardening matrix)

package/README.zh.md

@@ -7,7 +7,7 @@
 [![CI](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml/badge.svg)](https://github.com/ZK-Andy/dsh-continual-evolve/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/license-MIT-blue.svg)](LICENSE)
 [![Node](https://img.shields.io/badge/node-%5E22.19%20%7C%7C%20%3E%3D24-339933)](package.json)
-[![Tests](https://img.shields.io/badge/tests-1075%20passing-brightgreen)]()
+[![Tests](https://img.shields.io/badge/tests-1097%20passing-brightgreen)]()
 [![Coverage · statements](https://img.shields.io/badge/coverage_statements-98%25-brightgreen)]()
 [![Coverage · branches](https://img.shields.io/badge/coverage_branches-92%25-green)]()
 [![Coverage · functions](https://img.shields.io/badge/coverage_functions-99%25-brightgreen)]()
@@ -34,7 +34,7 @@ Agent 在每个会话里积累可复用经验（重复失败、持久事实、
 2. **能力感知的辅助调用**——memory loop、review、planner、wrapup、fate 通过 [`src/llm-text.ts`](src/llm-text.ts) 解析精确 provider/model 能力并使用模型公布的最低开启 reasoning effort，同时转发 host session id 供 provider 路由；只有没有开启档时才回退关闭档，没有 reasoning 元数据时使用 provider 默认行为。
 3. **守卫**——代码强制校验：编辑 schema、blast-radius 与作用域一致性、晋升政策（项目专属标记 / 过薄内容 / 近似重复检测 / 凭据筛查保持全局库干净——密钥类内容在所有写入出口被拒，含 mount 物化）。全局 create 与既有条目高度相似（≥0.8）时写入即拒；中等重叠带 `conflictHint` 供后续合并。
 4. **审批**——全局与项目写入需明确人工批准；弹窗展示有界结构化编辑 diff 与冲突提示，弹窗丢失/响应畸形会重试，不会被误记为拒绝。
-5. **应用与注入**——memory 批次先完成所有持久化审批，写前重查 abort；后续 scope 失败时补偿回滚先前写入，成功 scope 仍保留快照与审计。prompt 补充与委派规格注入系统提示词（封顶、按相关性排序、被证伪条目降权、空 store 零 token）；memory/skill 以按相关性排序的目录索引出现（`[memory:type:id] 标题`钩子）。
+5. **应用与注入**——memory 批次先完成所有持久化审批，写前重查 abort；后续 scope 失败时补偿回滚先前写入，成功 scope 仍保留快照与审计。prompt 补充与委派规格注入系统提示词（封顶、按相关性排序、被证伪条目降权、空 store 零 token）；**memory 正文**在会话开场按硬预算注入（会话内冻结，when_to_save 指南随行）；skill 仍以按相关性排序的目录索引出现。
 6. **验证与回滚**——benchmark 用冻结用例为候选打分；被拒候选确定性回滚，并自动沉淀为 draft 回归用例（`auto_regression` 基准）。
 
 ## 安装
@@ -55,14 +55,11 @@ dsh plugin add ZK-Andy/dsh-continual-evolve
 
 | 命令 | 效果 |
 |---|---|
-| `/evolve` | 帮助 + 当前 local store |
+| `/evolve` | 简短帮助 + 当前 local store（`/evolve help all` 列全部子命令） |
 | `/evolve list · history · rollback <id>` | 查看与回滚（加 `project` 操作本项目库，`global` 操作跨项目库） |
 | `/evolve plan [msg]` | 对 store 运行 LLM 规划器 |
 | `/evolve wrapup` | 收尾本会话 local 条目：晋升 / 归档 / 保留 |
-| `/evolve archive · unarchive · demote <id>` | 从注入中隐藏（数据保留可恢复）——`demote` 针对全局噪声 |
-| `/evolve recall [scope] <query…>` | 定向记忆召回：全文 + 版本 + 来源 + 过时信号 |
-| `/evolve remember <type> [scope] <text…>` | 立即持久化一条类型化记忆（`user|feedback|project|reference`） |
-| `/evolve forget [scope] <query…>` | 按 query 定位一条记忆并归档（可恢复）；多义只列候选不写 |
+| `/evolve archive · unarchive <id>` | 从注入中隐藏（数据保留可恢复） |
 | `/evolve consolidate [apply] [merge]` | 报告（或应用）冲突提示 + 零使用陈旧全局条目的批量归档；`merge` 将近重复内容并入幸存原条目 |
 | `/evolve failures` | 失败类聚合（门禁 + benchmark） |
 | `/evolve log [tail N] [session <id>]` | 插件日志 |
@@ -73,13 +70,13 @@ dsh plugin add ZK-Andy/dsh-continual-evolve
 | `/evolve pause · resume · status` | 暂停/恢复自动门禁（手动工具不受影响）、门禁状态 |
 | `/evolve usage` | 每条目注入次数 + memory/review/planner/wrapup/fate 直属调用的 provider 精确 token（不含 benchmark 宿主子代理） |
 
-模型工具：`evolve_list / add / update / delete / rollback / recall`（`evolve_delete` 支持 `id` 或批量 `ids` 数组——一次 refinement、一次审批；`evolve_recall` 按 query/kind/scope/memoryType/limit 过滤，返回全文 + 版本 + 来源 + 过时信号）。
+模型工具：`evolve_list / add / update / delete / rollback / recall`（`evolve_delete` 支持 `id` 或批量 `ids` 数组——一次 refinement、一次审批；`evolve_recall` 按 query/kind/scope/memoryType/limit 过滤，返回全文 + 版本 + 来源 + 过时信号）。记忆的读写都在对话里完成——模型手里有注入的记忆索引 + `evolve_recall`/`evolve_add`——因此不再有 `/evolve remember · forget · recall` 对应命令：直接在对话里说。
 
 第三方消费：每次进化落地（门禁或手动）都会向 `reviews.jsonl` 追加结构化 `evolve_complete` 事件（shape 见 `src/evolve-event.ts`），与人类可读的审计记录并存。
 
 `/evolve usage` 还会读取 `evolve/token-usage.jsonl`：插件直属 memory Agent、review、planner、手动 wrapup 与自动 fate 调用的 provider 精确 input/cache/output/total token。报告只覆盖保留尾部而非终身累计，单独显示 provider 未返回 usage 的调用，并明确排除宿主 benchmark 子代理、其 agent-loop 调用与逐条 memory 注入归因。
 
-注入形态：prompt 补充与委派规格带内容注入（每 kind ≤6 条 × 180 字符，按相关性排序）。memory/skill 以按相关性排序的目录索引出现（`[memory:type:id] 标题`钩子，15 行封顶 + 折叠计数行）——全文经 `evolve_recall`（精确）或 `evolve_list` 获取。每次 memory 落盘同时刷新 store 目录下的可读 `MEMORY.md` 索引 + 单事实文件。空 store = 零注入 token。
+注入形态：prompt 补充与委派规格带内容注入（每 kind ≤6 条 × 180 字符，按相关性排序）。memory 以**正文**在会话开场注入：`evolve:memory-index` section（order 400）承载 when_to_save 指南 + 预算内的全部记忆正文，排序 `project > feedback > user > reference`，放不下的降级为 `[memory:type:id] 标题`钩子、其余折叠计数（硬上限 `memoryIndex.maxChars`，默认 6000 字符；未展示的用 `evolve_recall` 读）。该 section 每会话只算一次并逐字节复用，system prompt 因此稳定、prompt cache 持续命中——会话中途写入的记忆下个会话生效。skill 仍以按相关性排序的目录索引出现（15 行封顶 + 折叠计数行），memory 不再列入。每次 memory 落盘同时刷新 store 目录下的可读 `MEMORY.md` 索引 + 单事实文件。`memoryIndex.guide` 关闭且 store 为空时 = 零注入 token。
 
 ## 配置
 
@@ -94,13 +91,18 @@ dsh plugin add ZK-Andy/dsh-continual-evolve
 | `reviewBudgetTokens` | `4096` | 门禁调用输出预算 |
 | `notifyOnAutoReview` | `true` | 门禁应用后发可见跟进通知 |
 | `requireGlobalApproval` | `true` | 全局与项目写入需明确批准 |
+| `recordLanguage` | `auto` | 记录**与弹窗**语言：`auto` 依次跟随 DSH 客户端偏好 → 会话自身用户文本 → `en`；`zh`/`en` 固定 |
 | `localFate` | `false` | 可选的本地条目晋升/归档 fate 评估；listener 以 memory-only 运行时不可达，只对直接/完整调用者生效 |
 | `fateIntervalTurns` | 跟随 `reviewIntervalTurns` | 归宿评估的最小回合间隔 |
 | `goalBlockedWrapupTurns` | `3` | 连续阻塞目标的门禁轮数触发一次归宿评估（`0` 关闭） |
 | `promotionBlockPatterns` | POSIX 路径、session id、`~/.dsh` | 内容命中即判定项目专属，永不晋升全局 |
 | `promotionMinChars` | `100` | 低于此长度的整体晋升留在本地 |
 | `injectionDirectoryLines` | `15` | 每次构建的目录行数上限，超出折叠为计数行 |
-| `sectionOrder` | `118` | 系统提示词 section 顺序 |
+| `sectionOrder` | `118` | 指南与条目两个 section 的系统提示词顺序 |
+| `memoryIndex.enabled` | `true` | 是否注册 `evolve:memory-index` 内容 section |
+| `memoryIndex.guide` | `true` | 是否注入 when_to_save 指南（关闭且 store 为空时该 section 不渲染） |
+| `memoryIndex.order` | `400` | section 顺序（上游命名槽位自 `PLAN_POLICY=500` 起；本插件另两段在 118/119） |
+| `memoryIndex.maxChars` | `6000` | 注入记忆块的硬字符预算 |
 | `skillsDir` | `<dshHome>/skills` | 技能条目物化为 SKILL.md 的根目录 |
 | `rubricKey` | 自动生成本地密钥文件 | benchmark rubric 的 AES-256-GCM 口令（`DSH_EVOLVE_RUBRIC_KEY` 可覆盖） |
 | `logToFile` / `logLevel` / `logMaxBytes` | `true` / `1` / 5 MiB | 插件自带 JSONL 文件日志带轮转 |
@@ -126,7 +128,7 @@ profile patch 示例：
 
 ```bash
 pnpm install && pnpm build   # 依赖 + tsc -> lib/
-pnpm test                    # vitest（1075 例）
+pnpm test                    # vitest（1097 例）
 pnpm test:coverage           # v8 覆盖率，CI 强制阈值
 pnpm coverage:gaps           # 定位各文件未覆盖行（只读）
 pnpm lint                    # oxlint src test
@@ -136,7 +138,7 @@ pnpm lint                    # oxlint src test
 
 ```
 ├── src/                   # 引擎、工具、命令、memory Agent、召回、投影、门禁、fate、benchmark、注入 + token 用量…
-├── test/                  # vitest 测试套件（58 个文件）
+├── test/                  # vitest 测试套件（59 个文件）
 ├── lib/                   # 构建产物（tsc）
 ├── docs/
 │   ├── design.md          # 完整设计文档（硬化矩阵）

package/lib/approval.d.ts

@@ -6,8 +6,11 @@
  */
 import type { Context } from "@deepseek-ai/cordis";
 import type { Agent } from "@deepseek-ai/dsh-agent";
-import type { RecordLanguage } from "./record-language.js";
+import { type RecordLanguagePreference } from "./record-language.js";
 export type ScopeApprovalDecision = "approved" | "declined";
+/** Labels the approval dialog offers for each decision (parser contract). */
+export declare const APPROVE_LABELS: readonly ["批准", "Approve"];
+export declare const DECLINE_LABELS: readonly ["拒绝", "Decline"];
 export interface QuestionService {
     ask(request: {
         questions: {
@@ -24,6 +27,7 @@ export interface QuestionService {
         answers?: {
             id: string;
             selected?: string[];
+            custom?: string;
         }[];
     }>;
 }
@@ -41,20 +45,28 @@ export declare function questionServiceOf(ctx: Context): QuestionService | undef
  * Copy follows the headline → details → impact shape in the resolved dialog
  * language; labels stay literal per language for parser compatibility.
  *
+ * Language resolution runs the full record-language chain — explicit config,
+ * then the durable client preference, then the session's own recent user text
+ * — because an approval dialog raised from a tool call DOES have a session
+ * behind it. Stopping at the durable tier gave a Chinese-speaking user English
+ * dialogs whenever the stored preference was unset (2026-10-01).
+ *
  * @param ctx Cordis context carrying the userQuestions service.
  * @param agent Agent prompting the question, if any.
  * @param signal Abort signal for the question, if any.
  * @param scope Target persistent scope.
  * @param what Edit summary; truncated to 300 chars with "…" when longer.
- * @param lang Dialog language; absent → resolved per call (durable client
- *             preference, else `en`).
+ * @param configured Plugin `recordLanguage` preference; `auto`/absent defers
+ *                   to the durable preference and the session's user text.
  * @returns "approved" when the user picks the approval label, otherwise "declined".
  * @throws When the service is missing or the answer is not unique/explicit.
  */
-export declare function requestScopeApproval(ctx: Context, agent: Agent | undefined, signal: AbortSignal | undefined, scope: "project" | "global", what: string, lang?: RecordLanguage): Promise<ScopeApprovalDecision>;
+export declare function requestScopeApproval(ctx: Context, agent: Agent | undefined, signal: AbortSignal | undefined, scope: "project" | "global", what: string, configured?: RecordLanguagePreference): Promise<ScopeApprovalDecision>;
 /**
  * Ask the user to approve a global edit. Throws when the service is missing,
  * the user declines, or the question cannot be answered.
+ *
+ * @param configured Plugin `recordLanguage` preference (see {@link requestScopeApproval}).
  */
-export declare function requireGlobalApproval(ctx: Context, agent: Agent | undefined, signal: AbortSignal | undefined, what: string): Promise<void>;
+export declare function requireGlobalApproval(ctx: Context, agent: Agent | undefined, signal: AbortSignal | undefined, what: string, configured?: RecordLanguagePreference): Promise<void>;
 //# sourceMappingURL=approval.d.ts.map

package/lib/approval.js

@@ -1,4 +1,39 @@
-import { approvalCopy, resolveDialogLanguage } from "./copy.js";
+import { approvalCopy } from "./copy.js";
+import { normalizeRecordLanguage, resolveRecordLanguage } from "./record-language.js";
+import { recentUserText } from "./inject.js";
+/** Labels the approval dialog offers for each decision (parser contract). */
+export const APPROVE_LABELS = ["批准", "Approve"];
+export const DECLINE_LABELS = ["拒绝", "Decline"];
+/**
+ * Typed ("Other") answers accepted as an explicit decision once normalized.
+ * Deliberately exact: a substring rule would read "不批准" as approval, and a
+ * misread decision is far worse than asking the human to click the button.
+ */
+const TYPED_APPROVALS = new Set(["批准", "approve"]);
+const TYPED_DECLINES = new Set(["拒绝", "decline"]);
+/** Trim case/quotes/trailing punctuation and a trailing 吧/了 from a typed answer. */
+function normalizeTypedAnswer(text) {
+    return text
+        .trim()
+        .toLowerCase()
+        .replace(/^[\s"'“”「」]+/, "")
+        .replace(/[\s"'“”「」。！!，,、]+$/, "")
+        .replace(/[吧了]$/, "");
+}
+/**
+ * Read a free-text answer as a decision, or `undefined` when it matches no
+ * label exactly. Never guesses.
+ */
+function typedDecision(custom) {
+    if (typeof custom !== "string")
+        return undefined;
+    const normalized = normalizeTypedAnswer(custom);
+    if (TYPED_APPROVALS.has(normalized))
+        return "approved";
+    if (TYPED_DECLINES.has(normalized))
+        return "declined";
+    return undefined;
+}
 /**
  * Lazily resolve the userQuestions service from the context.
  * Returns undefined when the service is not loaded — callers decide
@@ -15,22 +50,30 @@ export function questionServiceOf(ctx) {
  * Copy follows the headline → details → impact shape in the resolved dialog
  * language; labels stay literal per language for parser compatibility.
  *
+ * Language resolution runs the full record-language chain — explicit config,
+ * then the durable client preference, then the session's own recent user text
+ * — because an approval dialog raised from a tool call DOES have a session
+ * behind it. Stopping at the durable tier gave a Chinese-speaking user English
+ * dialogs whenever the stored preference was unset (2026-10-01).
+ *
  * @param ctx Cordis context carrying the userQuestions service.
  * @param agent Agent prompting the question, if any.
  * @param signal Abort signal for the question, if any.
  * @param scope Target persistent scope.
  * @param what Edit summary; truncated to 300 chars with "…" when longer.
- * @param lang Dialog language; absent → resolved per call (durable client
- *             preference, else `en`).
+ * @param configured Plugin `recordLanguage` preference; `auto`/absent defers
+ *                   to the durable preference and the session's user text.
  * @returns "approved" when the user picks the approval label, otherwise "declined".
  * @throws When the service is missing or the answer is not unique/explicit.
  */
-export async function requestScopeApproval(ctx, agent, signal, scope, what, lang) {
+export async function requestScopeApproval(ctx, agent, signal, scope, what, configured) {
     const userQuestions = questionServiceOf(ctx);
     if (!userQuestions) {
         throw new Error("global evolution edits require the userQuestions service (load @deepseek-ai/dsh-user-questions)");
     }
-    const copy = approvalCopy(scope, what, lang ?? resolveDialogLanguage(ctx));
+    const lang = normalizeRecordLanguage(configured) ??
+        resolveRecordLanguage({ ctx, trajectoryText: recentUserText(agent) });
+    const copy = approvalCopy(scope, what, lang);
     const answer = await userQuestions.ask({
         questions: [
             {
@@ -46,20 +89,38 @@ export async function requestScopeApproval(ctx, agent, signal, scope, what, lang
     if (matching.length !== 1 || !Array.isArray(matching[0]?.selected)) {
         throw new Error("evolution approval returned no unique explicit decision");
     }
-    const selected = [...new Set(matching[0]?.selected ?? [])];
-    const approvals = selected.filter((label) => label === "批准" || label === "Approve");
-    const declines = selected.filter((label) => label === "拒绝" || label === "Decline");
-    if (approvals.length + declines.length !== 1 || selected.length !== 1) {
+    const entry = matching[0];
+    const selected = [...new Set(entry.selected)];
+    if (selected.length === 0) {
+        // A typed "Other" answer counts only when it matches a dialog label
+        // exactly; anything fuzzier stays an error, so a lost or ambiguous
+        // reply is never recorded as a durable rejection.
+        const typed = typedDecision(entry.custom);
+        if (typed !== undefined) {
+            return typed;
+        }
+        throw new Error(`evolution approval needs one clicked option (${APPROVE_LABELS.join("/")} or ${DECLINE_LABELS.join("/")}) — a typed reply cannot serve as a decision`);
+    }
+    if (selected.length !== 1) {
         throw new Error(`evolution approval returned an invalid decision: ${JSON.stringify(selected)}`);
     }
-    return approvals.length === 1 ? "approved" : "declined";
+    const label = selected[0];
+    if (APPROVE_LABELS.includes(label)) {
+        return "approved";
+    }
+    if (DECLINE_LABELS.includes(label)) {
+        return "declined";
+    }
+    throw new Error(`evolution approval returned an unknown decision label: ${JSON.stringify(label)}`);
 }
 /**
  * Ask the user to approve a global edit. Throws when the service is missing,
  * the user declines, or the question cannot be answered.
+ *
+ * @param configured Plugin `recordLanguage` preference (see {@link requestScopeApproval}).
  */
-export async function requireGlobalApproval(ctx, agent, signal, what) {
-    if ((await requestScopeApproval(ctx, agent, signal, "global", what)) !== "approved") {
+export async function requireGlobalApproval(ctx, agent, signal, what, configured) {
+    if ((await requestScopeApproval(ctx, agent, signal, "global", what, configured)) !== "approved") {
         throw new Error("global evolution edit rejected by the user");
     }
 }

package/lib/auto.js

@@ -504,6 +504,7 @@ export async function runMemoryExtractionPhase(ctx, engine, agent, config, state
         decisionCursor: memorySnapshot.cursor,
         scopeDecisions: state.memoryDecisions,
         onScopeDecision: (key, decision) => rememberMemoryDecision(state, key, decision),
+        ...(config.recordLanguage !== undefined ? { recordLanguage: config.recordLanguage } : {}),
         ...(signal ? { signal } : {}),
     });
     for (const result of application.results) {

package/lib/command.d.ts

@@ -6,6 +6,7 @@ import type { Context } from "@deepseek-ai/cordis";
 import type { HarnessEntry, HarnessState, RefinementKind } from "./types.js";
 import type { EvolutionEngine } from "./service.js";
 import type { PromotionPolicy } from "./promotion.js";
+import type { RecordLanguagePreference } from "./record-language.js";
 export interface CommandGateOptions {
     requireGlobalApproval: boolean;
 }
@@ -22,6 +23,8 @@ export interface CommandRuntimeOptions {
      * registered; this is not a registration gate.
      */
     autoReview?: boolean;
+    /** Plugin `recordLanguage` preference for dialog copy (see `approval.ts`). */
+    recordLanguage?: RecordLanguagePreference;
 }
 export declare function registerEvolveCommand(ctx: Context, engine: EvolutionEngine, opts: CommandGateOptions, runtime: CommandRuntimeOptions): void;
 /**