thincoder 0.12.37 → 0.12.39

package/CHANGELOG.md

@@ -0,0 +1,303 @@
+# Changelog
+
+本文件记录 ThinCoder CLI 的发布历史。格式基于 [Keep a Changelog](https://keepachangelog.com/zh-CN/1.0.0/)，版本遵循[语义化版本](https://semver.org/lang/zh-CN/)。
+
+## [0.12.39] — 2026-08-23
+
+### Added
+
+- **主 agent 委托策略**：`main.md` 把「广度探索 → explore 子代理（隔离上下文，逐步读/搜不进主历史）」「仅当即将立刻编辑时才自己 read」「coder 验证 = 读改动文件 + 跑测试」从建议升级为明确规则
+- **历史卫生**：轮末 `summarizeRunExplorations` 把一轮内连续探索结果（read/grep/glob/ls/code_search/doc_search/repo_outline）LLM 蒸馏为 `[Exploration summary]`（机器线收缩、人读线全量不变）；压缩 `SUMMARIZE_PROMPT` 加「已改动文件清单 + 未决点/待办」两清单
+- **编码纪律**：`discipline.md` 工作流程 + 调试策略要求用 `task` 跟踪；「改码前读文档」「中/小改后更新文档」嵌入 Workflow 各 tier 箭头序列
+
+### Fixed
+
+- 轮末探索摘要边界 `_runStartHistoryLen` 在压缩重建机器线后变 stale → 重置到 tail 起点
+
+## [0.12.38] — 2026-08-23
+
+### Added
+
+- **对齐 thinworker 编程工具集**：新增 `file_ops`（move/copy/rename）、`process`（列进程）、`get_current_time`、`sleep` 四个内置工具，及 `tree`（递归目录树 + `depth`，对齐 thinworker `repomap`）；各工具描述带「Route to X instead of bash」反向路由
+- **内部能力对齐 thinworker**：`grep` 加 `literal`/`ignoreCase`；`ls` 加 `filter`（通配符）；`bash` 加 `filter`（正则行过滤）；`git` 加 `show`/`rm`/`commit`/`push` 子命令 + `filter`；`verify` 加 `filter`/`workdir`
+- **`execute` 工具重做**：由同步 vm 沙箱改为 `node --input-type=module --eval` 子进程——支持顶层 `await`、动态 `import()`（直接加载项目 `.mjs`）、原生 `console`/`fetch`，新增 `workdir`/`filter` 参数，保留 killable 超时（无限循环可被终止）；`exec-prelude.mjs` 提供 readFile/writeFile/glob/grep/log/require（路径隔离 workspace）
+- **consult 指定子集模型**：`consult_start` 新增 `models` 选择器（`provider:model`/裸 provider/裸 model，大小写不敏感、去重保序）
+- **模型规格更新**：新增 glm-5.3、deepseek-v4-flash-vision-exp；gpt-5.6/claude-5 收敛 `thinking=false`
+
+### Fixed
+
+- **apply_patch 多 hunk 错位**：同一文件多个 hunks 因前一段改变行数而错位应用、静默损坏——改为重扫上下文 + splice
+- **git 写操作吞错**：`commit`/`push`/`rm` 改用 `runGitStrict` 返回 stderr + exit code，失败不再伪装成功；`show` 补 ref 校验（防 `-` 开头注入选项）
+- **tool 补齐项加固**：`get_current_time` 补 weekday；`sleep` 防 NaN；`tree` 深度/计数校验、省略号单次、根目录报错；`log` 非法 count 回退默认
+
+### Docs
+
+- `TOOLS.md` 注册表计数同步（含 ops/tree）
+- Changelog backfill 0.12.36 / 0.12.33
+
+## [0.12.37] — 2026-08-22
+
+### Fixed
+
+- **advisor 标签还原**：状态栏徽标与 /advisor 菜单项由 "GUARD" 显示名还原为 "ADVISOR"（内部配置字段 `advisor.guard` 不变，仅显示名）
+- **SSE 流式 tool_calls 防御性合并**（PROVIDER.md §10）：跳过 null/畸形元素并计数，按 index/id/name/tail 合并、补齐缺失 id、计数丢弃
+- **Windows 剪贴板 BOM 防御**：UTF-8 输出后剥离前导 `\uFEFF`（IK9UWM 后续）
+- **上下文压缩空安全**：`t.function?.name` 防 tool name 缺失
+
+### Refactor
+
+- **session.mjs 拆分**：`migrateHashLength` 抽到 `session-migrate.mjs`，文件回到 ≤500 行硬限内
+- **/config embedding 保存重构**：`embeddingPatch()` 抽取 + `DEFAULTS` 导出（供单测）
+
+### Prompt
+
+- **确认纪律 carve-out**：system.md 补 doc/code 一致性例外——"改动前确认"门禁不适用于已确认任务的既有义务（文档跟码一致、记录刚做的决策、关闭 advisor 标记的文档缺口）
+
+## [0.12.36] — 2026-08-22
+
+### Docs & advisor
+
+- **文档归属纪律 + advisor 设计评审增强**（规格 AGENT-LOOP.md §12）：新建 `docs/design/README.md` 文档地图（板块→文档映射表 + 存量碎片"待合并（TODO）"标注 + 归属规则）；system.md 补文档归属纪律条款（写文档前先查地图定位所属板块——找到就改、不得为既有板块新建文件；确无归属才新建并登记；同一机制只在一处详述权威源、其余引用不复制）；advisor-design.md 加第 7 维 **Document ownership**（与现有文档矛盾 🔴、该并入却新建/重复描述 🟡）与引用纪律（引用原文用精确 file:line、未核实标注 unverified）；design 提示词 fallback 删除转硬加载（`loadPrompt` 同 round1/2/3 待遇，缺失即抛错——静默降级会丢 Approval Signal 规则致评审无法批准）；messages.mjs design 分支 Instructions 补 Methodology compliance 维度、存在文档地图时注入 Document Map 段供归属检查对照。两端 prompts 保持 byte-identical、测试同步覆盖
+
+## [0.12.35] — 2026-08-21
+
+### Changed
+
+- **advisor 开关语义重构**：评审能力恒启用——`advisor` 工具任何模式都可调用（删除 `advisor.enabled` gate，不再返回 "not enabled"）；开关语义收敛为 guard——收尾推回仅当 `advisor.guard === true`（默认 OFF，评审自愿调用，打开才强制）。工程模式行为不变（评审恒可用、guard 豁免）
+- **`advisor.enabled` 废弃**：字段不再读写，存量配置不迁移——旧 `{ enabled: true }` 用户升级后不再强制评审（pre-release 约定，CHANGELOG 说明即可）；/advisor 菜单删除 "Advisor ON/OFF" toggle，Guard 成为唯一开关
+
+### Prompt system
+
+- **提示词借鉴增量（kimi-code 对照）**：explore.md 新增 Thoroughness levels 三档（quick 单点定向 / medium 默认适度并行 / thorough 全面分析且报告须列出搜索过什么与没找到什么）；main.md Delegate well 补委派 explore 时在 task 描述中指定彻底度（未指定走默认）；system.md 确认理解句补 "including the most important acceptance criteria"；subagent 工具 description 同步补彻底度说明。两端 15 个 prompt 文件保持 byte-identical（新增 CLI 侧比对测试防漂移）
+- **开工前计划确认纪律**：system.md 追加无豁免纪律——任何写文件动作（write/edit/apply_patch/insert_after/delete/hashline_edit 及一切写文件的 bash）前必须纯文字复述理解+计划要点并等待用户明确确认（未确认/沉默/用户回复新问题或新要求 → 一律不动手；"这太明显了不用问"不是跳过理由；用户的新问题不是确认；需求变化后重新复述重新确认）；engineering.md 澄清完成后、写需求/设计文档前同样须把理解+计划文字化并等待确认。两端 15 个 prompt 文件保持 byte-identical（两端测试断言关键句）
+
+## [0.12.34] — 2026-08-18
+
+### Added
+
+- **/rename 命令** — 改会话标题（renameSlot 双写，与 VS Code 共享）
+
+### Fixed
+
+- **/config 候选池 effort picker 显示真实枚举** — 从固定 min/low/medium/high/max 改为动态读 specForModel(model).reasoningEffortEnum；无枚举的模型跳过 effort 步
+- **question 工具 options 防御** — LLM 误传对象时取 label 字段，避免渲染 [object Object]
+
+## [0.12.33] — 2026-08-17
+
+### Changed
+
+- **撞轮数墙可无限继续**：subagent/飞刀/会诊统一经 continue 面板无限续（resume 保留 history，会诊继续重置墙钟；去掉 MAX_RESUMES）
+- **MiMo 预置 provider**：按量付费(api.xiaomimimo.com/v1) + Token Plan(token-plan-cn.xiaomimimo.com/v1)，模型规格 mimo-v2.5-pro/mimo-v2.5（1M 上下文 / 128K 输出 / 深度思考）
+- **环境变量配置源彻底移除**：THINCODER_* 回退全部删除，config.json 唯一配置源；空配置不再合成 deepseek 默认 provider
+- **effort 枚举钳制 + qwen3.8-max spec 修正**（consult/escalate）
+
+## [0.12.32] — 2026-08-16
+
+### Fixed
+
+- **会诊触发条款重构**（两轮会诊驱动的修复）：触发规则从飞刀段移入会诊段且自包含——功能请求语义（"会诊一下"触发、"consult the docs"不触发）+ 用户请求覆盖自主判断；consult_start 描述补对称触发句；飞刀段补 fly-in/口语变体
+- **飞刀三个真实断链**（会诊发现，此前"代码在但真实跑必翻车"）：
+  - 删墙钟看门狗——固定墙钟误杀正常但慢的手术（实测两个 max-effort 顾问读 5 个文件即撞 10min 墙）；完全依赖 turns + FETCH_TIMEOUT + 用户 Stop 直传
+  - effort 枚举钳制——池 effort 越界不再让候选"起飞即死"，回退预设并标注
+  - AUTO 传导对齐 subagent——headless 嵌入下父 autoApprove 正确放行子 agent 写操作
+- **config 加载校验**：consultModels 池 provider 名必须存在于 providers[]，条目形状校验——静默运行时失败改为启动即报错
+- **撞墙可继续（kimi-k3 飞刀）**：escalate 子 agent 撞 turn 上限后弹"继续?"（复用 onPermissionRequest，TUI 同款 y/n 面板），resume:true 续跑不重复注入任务、预算重置，上限 2 次；顺带修复 ContinueError e.turns → e.turn（原来打印 "undefined turns"）
+- consult 死代码补 precheck（无 key 时明确失败回复而非原始 401）
+
+### Docs
+
+- CLI CONSULTATION.md / ESCALATE.md 文档地图收录、FEATURES.md 功能全览补齐（7→11 个）、README 会诊别名、checklist T2-T6 验收
+
+## [0.12.31] — 2026-08-16
+
+### Fixed
+
+- **/config consult model picker**: adding a consult model now uses pickModelForSlot (provider AND model are both OPTION pickers, reusing /model's async-fetched model list) — was free-text for the model name
+- **Prompt adaptation**: CLI main.md was missing the consult (会诊) + escalate (飞刀) sections — the CLI main agent did not know "会诊" meant consult_start. Ported both + added the 会诊 alias to consult_start's tool description
+
+### Prompt system
+
+- Attention optimization + cross-end consistency: split over-long sentences, fixed an escalate-timing contradiction (up-front ability judgment), unified Review discipline + advisor rounds — all 15 prompt files byte-identical with the plugin
+
+### Docs
+
+- CONSULTATION.md + ESCALATE.md design docs (CLI implementation differences vs the plugin)
+
+## [0.12.30] — 2026-08-16
+
+### New: 会诊 (consult) + 飞刀 (escalate) — full VS Code plugin parity
+
+- `consult_start` / `consult_check` / `consult_stop`: several configured models run as parallel independent read-only consultants — each with its own TUI activity card, `main_history` access to the failure trail, arrival-order reply queue, stopped/terminated settle states, wall-clock watchdog
+- `escalate`: fly in a stronger model for one expert implementation run — coder role, full write path, permission gate, mutations merge into the parent's verify/advisor guards, turn-cap reads as partial work, timeout reads as timeout
+- Config: `agent.consultModels` ([{ provider, model, effort? }], up to 5, validated), `agent.consultTurns` (40), `agent.consultTimeoutMs` (600000)
+- **/config now manages the consult pool**: list / add / remove models; per-model reasoning-effort is an OPTION picker (none/min/low/medium/high/max); consultTurns + consultTimeoutMs (entered in minutes)
+
+### Discipline
+
+- UI rule added: fixed-choice values must be OPTIONS (picker/menu), never free-text — free-text only for genuinely open-ended input
+
+## [0.12.29] — 2026-08-16
+
+### Fixed
+
+- **Coder sub-agents (subagent role=coder) get verify + advisor** — CLI parity with the plugin's escalate diagnosis: the system prompt names both tools but the tool table only gave them to eng-coder; a coder sub-agent hit unknown-tool and self-verified via bash
+- **Cache-audit follow-ups**: OS/cwd reminder injected once per process (was every run); interrupt-resume now re-grounds the time (was stuck on the pre-interrupt time); skills scan sorted deterministically (filesystem-dependent readdir order could byte-change the system prompt with zero content change)
+
+## [0.12.28] — 2026-08-16
+
+### Cache-hit-rate fix (user-reported low hit rate on session start)
+
+- **Machine line (contextHistory) now keeps transient messages on persist** — every CLI invocation is a new process; the previous reals-only reload plus fresh re-injections (git/OS/outline/doc/memory/time) diverged at index ~1 → whole-prefix cache miss on the first request of every session. Resume now rebuilds a byte-identical machine line; new injections append at the tail
+- Time reminder moved to the END of the message sequence (after the user input) — aligned with the plugin fix, robust against any future machine-line disk reload
+
+### Fixed
+
+- normalizeToolPairing early-return hole: toolById empty must not skip placeholder filling when assistant tool_calls are declared (dangling tool_calls 400 otherwise)
+
+## [0.12.27] — 2026-08-15
+
+- Time injection moved OUT of the system prompt into a transient per-run user reminder — system prompts fully static again (prefix caches hit across hours, not minutes); local time + IANA timezone at second precision; now covers ALL agent depths (subagents previously had no time grounding at all)
+
+## [0.12.26] — 2026-08-15
+
+### ACP extensions for thincoder-desktop (proposals ①②③④, all implemented)
+
+- **① Session persistence**: every ACP turn end (success/cancel/failure — finally semantics) writes the session archive via saveSession; session/list / load / resume now have a real data source. Save is injectable and failures never break the queue
+- **② Checkpoints**: checkpoint/create / checkpoint/list / checkpoint/restore ACP handlers; NON-git cwds now snapshot by full-directory copy (v2 layout, nongit meta) instead of silently returning null
+- **③ Memory**: memory/list / memory/remove ACP handlers over the shared ~/.thincoder store
+- **④ Custom provider headers**: provider.headers object in config.json merges into every LLM request (chat + /models); Authorization cannot be overridden; non-string values sanitized out
+
+### Fixed
+
+- Time injection vs prefix-cache conflict: system-prompt "Current time" is now MINUTE precision — byte-identical within the same minute so DeepSeek prefix caches still hit (was: seconds precision broke the cache every run)
+
+## [0.12.25] — 2026-08-15
+
+- Local time + timezone injected into every system prompt (main agent, subagents, advisor) — prepareRun appends `Current time: <local> (<IANA zone>)`; sessionStart was ISO/UTC and session-scoped, subagents had nothing
+- bash.md Windows guidance corrected: the shell is cmd.exe (NOT Git Bash) — &&/|| work, cmd built-ins, NUL not /dev/null, prefer node -e for complex logic
+
+## [0.12.24] — 2026-08-14
+
+### Added
+
+- **glm-code provider preset** — the Zhipu GLM Coding Plan endpoint (`https://open.bigmodel.cn/api/coding/paas/v4`, glm-5.2, same key as GLM; server-side forced thinking).
+
+### Fixed
+
+- **Model specs synced with official vendor docs (verified 2026-08)** — DeepSeek v4 duals effort enum +low and cacheMode→auto; qwen3.x/max/plus maxOutput→131072 (qwen-plus was 32K).
+- **Retired models dropped** — deepseek-chat/reasoner, kimi-k2, moonshot v1 (vendor shutdowns; unknown IDs fall back to the 128K default spec).
+
+### Changed
+
+- Repository URL → github.com/xinbo-tech/thincoder.
+
+## [0.12.23] - 2026-08-13
+
+- **修复** svg 图片毒化会话——read_image 读 svg 后以 image_url 进历史，Kimi 等视觉 API（全部仅支持位图）此后每轮请求 400 "unsupported image format"，会话永久卡死；现在发送时按格式净化：非 png/jpeg/gif/webp 的 image part 替换为占位文本，净化上移至 format dispatch 之前覆盖 openai/anthropic/google 全部通路，历史本身不改写（切回支持的模型/格式可恢复）
+- **改进** read_image 对 svg 返回文本源码（svg 本是文本标记，任何模型可读，绕过 vision gate）；bmp 拒绝并提示转 PNG（无主流视觉 API 支持）
+
+## [0.12.22] - 2026-08-13
+
+- **修复** 缓存命中率对 Kimi 显示——usage 缓存字段归一化：Kimi/OpenAI 风格 `prompt_tokens_details.cached_tokens` 映射为 DeepSeek 风格 `prompt_cache_hit_tokens`，miss 由 prompt_tokens − hit 推导（此前 Kimi 的命中率永不显示）
+- **安全** fetch 重定向目标做 SSRF 检查——3xx 可把公网 URL 跳进内网（重定向绕过）；相对 URL 正确解析、仅 http/https、私网/元数据拦截
+- **新增** Tavily 结构化搜索（可选）——config 配 `websearch.apiKey` 后 `websearch` 走 Tavily API（稳定 JSON，不再依赖 Bing 页面结构）；无 key 回退 Bing 抓取，零门槛不破坏
+
+## [0.12.21] - 2026-08-13
+
+- **修复** 恢复会话大量重复 "❯ ThinCoder:" 标签——history 按每次 LLM 调用存一条 assistant 消息（一个 turn 多段），恢复时每段都渲染了标签；现在只在 turn 开始渲染一次，跨页懒加载边界状态正确保留
+- **改进** 恢复保真度：完整工具结果（不再一行摘要）+ reasoning 思考流以 dim 行恢复（超长自动折叠）——恢复后的会话与退出前基本一致；首帧渲染实测约 50ms
+
+## [0.12.20] - 2026-08-13
+
+- **修复** TUI 恢复旧 display 快照导致"看不到最新消息"——display 字段彻底废弃（saveSession 不再写、loadSession 不再读），恢复永远从 history 重建；配合 VS Code 端 0.1.5 的清空，跨端会话漂移根治
+- **新增** TUI 懒加载历史恢复：启动只物化最近 200 条消息（8000+ 条会话不再冻结启动），PgUp 到顶按 50 条/页加载更早历史，scroll 补偿保持视觉位置
+- **新增** question 选项列表末尾追加"✍ Custom answer…"——选中切自由输入，用户可补充/修正 AI 的预设选项
+- **重构** execute 工具移除假沙箱：require()/process 全可用（bash 本就能触达任意 Node API，拦 require 只会误导模型）；移除动态 import 拦截与 SSRF 私网拒绝；保留 timeout / cwd 约束 / 输出上限等工程保护
+- **改进** 工程模式 prompt：新增提问风格指引（默认开放式自由文本，选项仅用于有限枚举）；审查修复 5 处（需求优先步骤、designToken 仅走参数、用户审批呈现 advisor 发现、澄清完成判据、advisor 重试 3 轮上限）
+
+## [0.12.19] - 2026-08-11
+
+- **重构** bash 工具安全模型：移除全部破坏性命令文本拦截（rm -rf / DROP TABLE 等）——文本匹配是安全剧场（恶意模型可绕过、误伤正常操作），真实防线 = 审批层（autoApprove）+ 快照（gitGuardSnapshot / checkpoint），与 env 透传、git"快照后放行永不拦截"统一
+- **新增** 危险命令标注（detectDanger，参考 kimi-code）：recursive-delete / sudo / pipe-to-shell / dd / mkfs / 裸设备 / chmod 777 / fork bomb 在 TUI 与 ACP 审批面板红色标注——只提示不拦截，帮人做审批决策；引号感知（commit message 等纯文本不误标，反引号内容保留）
+- **文档** TOOLS.md 安全边界同步（零文本拦截 + 危险标注）
+
+## [0.12.18] - 2026-08-10
+
+- **修复** Qwen 路由等代理的模型 ID（如 `kimi/kimi-k3`）跳过 `reasoning_effort` 参数——路由可能误处理该参数导致空回复
+
+## [0.12.17] - 2026-08-10
+
+- **修复** `kimi/kimi-k3`（Qwen 路由前缀 ID）模型规格匹配 — 正确继承 kimi-k3 的 1M 上下文 / 131K 输出 / 多模态
+
+## [0.12.16] - 2026-08-10
+
+- **修复** 非 SSE JSON 响应被误判为错误（HTTP 200 + tool_calls 的合法 JSON 响应现在正确解析，而非报 "Response is not SSE"）
+- **改进** API 错误信息可读性：非 SSE 错误响应包含 HTTP 状态码 + 具体错误原因
+
+## [0.12.15] - 2026-08-10
+
+- **改进** API 错误信息可读性：非 SSE 响应预拦截，提取 HTTP 状态码 + 具体错误原因（替代原来模糊的 "Response is not SSE"）
+
+## [0.12.14] - 2026-08-10
+
+- **修复** 小终端 permission 面板挤出输入框（layout 溢出补偿新增 permission 压缩）
+- **修复** iTerm2 Ctrl+C 键盘协议序列泄漏（stdin 剥离未处理的 CSI u 序列）
+- **修复** eng 模式 advisor token 正则错配（改用完整 token 构建正则，与 prompt 格式一致）
+- **修复** 输入框 ↑ 键历史导航草稿丢失（进入/编辑历史模式时扩容草稿保护）
+- **重构** key-handler 拆分搜索模块（key-handler-search.mjs）
+- **文档** 架构文档计数/模块/状态同步更新
+
+## [0.12.13] - 2026-08-08
+
+评审机制全面重构（用户驱动的三轮决策）：
+
+- **prior 硬解析移除**：收敛轮注入上一轮评审的完整原文（模型直接理解），删除表头匹配与 all-clear 短语两类"字符串解析 LLM 输出"的脆弱机制
+- **评审触发范围收缩**：评审只跟代码修改绑定——bash/git 等副作用工具不再触发多余评审轮（评审后读日志/清理临时文件不再要求重复评审）
+- **AGENTS.md 文档地图**：需求基线声明（REQUIREMENTS.md + 设计文档 + 对话背景）+ docs/design/ 27 份文档分组清单，评审者按地图定位需求文档
+- **项目根发现**：多项目工作区从评审范围定位子项目 AGENTS.md（工作区元地图不遮蔽）；修复混合路径分隔符误判
+- **收敛体共享模块**：round 2+ 消息构建单一来源；空回复/纯工具输出不再冒充评审记录
+
+## [0.12.12] - 2026-08-07
+
+- advisor 记录按真实时序落盘（timeline）、markdown 表格 render-before-measure 对齐修复（含 heading 多行/双重粗体）、requirements 兜底、评审结论可用性提示
+- 双线消息历史（人读线 + 机读线）、压缩只作用于机读线、机读消息不进人读线
+- 临时文件（tmp-*）不触发 advisor guard；config.mjs 加固（spec 预排序、providers 守卫、saveConfig 写副本）
+- VS Code 扩展发布准备（marketplace 元数据、.vscodeignore、vscode-mock 依赖修复）
+
+## [0.12.11] - 2026-08-05
+
+- subagent 按类型配置模型（`/submodel` + `subagentModels`）
+- 可配置 bash shell（`/shell platform` 切换）
+- 其他稳定性与体验改进
+
+## [0.12.10] - 2026-08-05
+
+- 代码质量梳理：清理未使用的导出、advisor 计时器与静态导入修复、复评不再因旧会话数据误报
+
+## [0.12.9] - 2026-08-04
+
+- 提示词体系质量梳理：移除工程模式与 advisor 的冲突、交付评审语义修正
+
+## [0.12.8] - 2026-08-04
+
+- pending-task 推回最多触发一次（消除无界完成循环）
+
+## [0.12.7] - 2026-08-03
+
+- 折叠可读性修复（主输出/思考永不折叠）、窄终端宽表格裁剪
+
+## [0.12.6] - 2026-08-02
+
+- checkpoint v2、git 破坏性命令保护、鼠标支持、长消息折叠、bash 行为约束
+
+## [0.12.5] - 2026-08-01
+
+- 行内代码下划线样式
+
+## [0.12.4] - 2026-08-01
+
+- 压缩统一规范、Kimi For Coding、Ctrl+C 双重确认、空响应重试、markdown 渲染修复
+
+## [0.12.3] 及更早
+
+v0.12.x 早期版本、v0.11.x、v0.8.x、v0.7.x 与 v0.2–v0.6 系列——完整历史见 [git 提交记录](https://gitee.com/shanghai-xinbo/thincoder/commits/main)。

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "thincoder",
-  "version": "0.12.37",
+  "version": "0.12.39",
   "description": "Thin coding agent - zero dependencies, no build step, Node.js native. Sharp code, zero bloat.",
   "keywords": [
     "ai",
@@ -23,6 +23,7 @@
     "bin/",
     "src/",
     "README.md",
+    "CHANGELOG.md",
     "LICENSE"
   ],
   "repository": {

package/src/agent-tools/consult.mjs

@@ -19,6 +19,36 @@ function consultLabel(m) {
   return `${m.provider}:${m.model}`
 }
 
+/** Narrow the configured consultModels pool to a requested subset.
+ *  Each selector is "provider:model", a bare provider name, or a bare model name
+ *  (case-insensitive). Returns { models, error } — error set when a selector matches
+ *  nothing (surface the typo rather than silently dropping it). Absent/empty selectors
+ *  → the full pool. */
+function selectConsultModels(pool, selectors) {
+  if (selectors == null || (Array.isArray(selectors) && selectors.length === 0)) return { models: pool, error: null }
+  const list = Array.isArray(selectors) ? selectors : [selectors] // coerce a bare string → [string]
+  const selected = []
+  const seen = new Set()
+  const unknowns = []
+  for (const raw of list) {
+    const s = String(raw).trim().toLowerCase()
+    const matches = pool.filter((m) =>
+      consultLabel(m).toLowerCase() === s ||
+      String(m.provider ?? "").toLowerCase() === s ||
+      String(m.model ?? "").toLowerCase() === s,
+    )
+    if (matches.length === 0) unknowns.push(String(raw))
+    else for (const m of matches) {
+      const key = consultLabel(m)
+      if (!seen.has(key)) { seen.add(key); selected.push(m) }
+    }
+  }
+  if (unknowns.length > 0) {
+    return { models: null, error: `unknown consult model selector(s): ${unknowns.join(", ")} — choose from: ${pool.map(consultLabel).join(", ")}` }
+  }
+  return { models: selected, error: null }
+}
+
 /** Read-only tool injected into consultation children (via createAgent's tools).
  *  Lets the consultant pull the main agent's conversation history on demand —
  *  the failure trail is first-class evidence, not a retelling. */
@@ -225,31 +255,40 @@ export const consultStartTool = {
     "arrives, judge/verify it yourself with your own tools, and call consult_stop(id) once a reply is good enough.\n" +
     "Parameters:\n" +
     "- problem (required): a brief — the symptom, what you already tried (failure trail), and entry-point files. " +
-    "Do NOT paste raw error logs; consultants pull the main session history themselves via their main_history tool.",
+    "Do NOT paste raw error logs; consultants pull the main session history themselves via their main_history tool.\n" +
+    "- models (optional): subset of agent.consultModels to run — an array of \"provider:model\", bare provider, or bare model names (case-insensitive). Omit to run all.",
   parameters: {
     type: "object",
-    properties: { problem: { type: "string", description: "Problem brief (symptom + failure trail + entry files)" } },
+    properties: {
+      problem: { type: "string", description: "Problem brief (symptom + failure trail + entry files)" },
+      models: { type: "array", items: { type: "string" }, description: 'Optional subset of agent.consultModels to run (default: all). Each entry is "provider:model", a bare provider name, or a bare model name (case-insensitive).' },
+    },
     required: ["problem"],
   },
-  async execute({ problem }, ctx) {
+  async execute({ problem, models }, ctx) {
     if (typeof problem !== "string" || !problem.trim()) return "Error: problem is required and must be a non-empty string"
     const agent = ctx.agent
     if (!agent) return "Error: consult requires an agent context"
-    const models = agent.config?.agent?.consultModels ?? []
-    if (!Array.isArray(models) || models.length === 0)
+    const pool = agent.config?.agent?.consultModels ?? []
+    if (!Array.isArray(pool) || pool.length === 0)
       return "Consultation is not configured — add agent.consultModels ([{ provider, model }], up to 5) to ~/.thincoder/config.json"
-    if (models.length > 5) return `Error: consultModels supports at most 5 models (got ${models.length})`
+    if (pool.length > 5) return `Error: consultModels supports at most 5 models (got ${pool.length})`
+
+    // `models` (optional) narrows the pool to a subset; absent/empty → run the whole pool.
+    const picked = selectConsultModels(pool, models)
+    if (picked.error) return picked.error
+    const run = picked.models
 
     agent._consultSessions ??= new Map()
     const id = String((agent._consultIdCounter = (agent._consultIdCounter ?? 0) + 1))
     const session = {
       id, controllers: [], replies: [], pending: 0, waiters: [],
-      failed: 0, terminated: 0, stopped: false, received: 0, total: models.length,
-      models: models.map(consultLabel),
+      failed: 0, terminated: 0, stopped: false, received: 0, total: run.length,
+      models: run.map(consultLabel),
     }
     agent._consultSessions.set(id, session)
 
-    for (const m of models) {
+    for (const m of run) {
       session.pending++
       const ctrl = new AbortController()
       session.controllers.push(ctrl)

package/src/agent-tools/verify.mjs

@@ -2,7 +2,7 @@ import { repairHistory, listWorkDir } from "../agent.mjs"
 import { isDocFile } from "../advisor/repos.mjs"
 import { execSync, spawn, spawnSync } from "node:child_process"
 import { readFileSync, existsSync } from "node:fs"
-import { join } from "node:path"
+import { join, resolve } from "node:path"
 
 /**
  * Source module → test file mapping. Heuristic: the FIRST path component
@@ -58,12 +58,17 @@ export const verifyTool = {
     type: "object",
     properties: {
       full: { type: "boolean", description: "Run the full test suite (npm test) instead of just related tests. Default false — use sparingly, per the testing discipline rules." },
+      workdir: { type: "string", description: "Optional: run verify in this subdirectory (relative to cwd or absolute) — for monorepos" },
+      filter: { type: "string", description: "Optional: limit the test run to matching test names (node --test-name-pattern / npm test -- --test-name-pattern)" },
     },
   },
   readonly: true,
   outputPanel: true, // stream test output to a panel instead of inline
   async execute(args, ctx) {
     const cwd = ctx.agent.cwd
+    // workdir only relocates WHERE tests (and package.json) live — changed-file
+    // resolution (git diff) stays anchored to the project root.
+    const testCwd = args.workdir ? resolve(cwd, args.workdir) : cwd
     const lines = []
     lines.push("=== VERIFICATION REPORT ===")
     lines.push("")
@@ -130,7 +135,7 @@ export const verifyTool = {
     const relatedTests = [...new Set(modules.map((m) => MODULE_TO_TEST[m]).filter(Boolean))]
 
     // 4. Run tests
-    const pkgPath = join(cwd, "package.json")
+    const pkgPath = join(testCwd, "package.json")
     const hasTestScript = existsSync(pkgPath) && (() => { try { return !!JSON.parse(readFileSync(pkgPath, "utf8")).scripts?.test } catch { return false } })()
 
     if (args.full) {
@@ -138,7 +143,7 @@ export const verifyTool = {
       if (hasTestScript) {
         lines.push("")
         lines.push("Tests (full suite):")
-        const result = await runTestSuite(cwd, ctx)
+        const result = await runTestSuite(testCwd, ctx, args.filter)
         if (result.passed) {
           lines.push("✓ All tests passed.")
           ctx.agent._verifyPassed = !syntaxFailed
@@ -163,7 +168,7 @@ export const verifyTool = {
           continue
         }
         try {
-          const result = await runTestFile(cwd, testFile, ctx)
+          const result = await runTestFile(cwd, testFile, ctx, args.filter)
           if (result.passed) {
             lines.push(`  ✓ ${testFile}`)
           } else {
@@ -248,9 +253,9 @@ export const verifyTool = {
  * Run a single test file with node --test, no maxBuffer limit.
  * Returns { passed: boolean, tail: string } — the last few lines of output.
  */
-function runTestFile(cwd, testPath, ctx) {
+function runTestFile(cwd, testPath, ctx, filter) {
   return new Promise((resolve, reject) => {
-    const child = spawn("node", ["--test", testPath], {
+    const child = spawn("node", filter ? ["--test", "--test-name-pattern", filter, testPath] : ["--test", testPath], {
       cwd, stdio: ["ignore", "pipe", "pipe"],
       env: { ...process.env, FORCE_COLOR: "0" },
     })
@@ -288,9 +293,9 @@ function runTestFile(cwd, testPath, ctx) {
  * Test output is streamed through ctx.callbacks.onToolOutput (TUI can display progress in real time).
  * Returns { passed: boolean, tail: string }.
  */
-function runTestSuite(cwd, ctx) {
+function runTestSuite(cwd, ctx, filter) {
   return new Promise((resolve, reject) => {
-    const child = spawn("npm", ["test"], {
+    const child = spawn("npm", filter ? ["test", "--", `--test-name-pattern=${filter}`] : ["test"], {
       cwd, shell: true, stdio: ["ignore", "pipe", "pipe"],
       env: { ...process.env, FORCE_COLOR: "0" },
     })

package/src/agent.mjs

@@ -4,7 +4,7 @@
  */
 import { chat } from "./provider/index.mjs"
 import { estimateText } from "./provider/rate.mjs"
-import { compressIfNeeded, compressFallback, COMPRESS_FAILURE_LIMIT, pushReal } from "./context.mjs"
+import { compressIfNeeded, compressFallback, COMPRESS_FAILURE_LIMIT, pushReal, summarizeRunExplorations } from "./context.mjs"
 import { specForModel } from "./config.mjs"
 import { readFileSync } from "node:fs"
 import { join, dirname } from "node:path"
@@ -95,6 +95,7 @@ export function createAgent({
     _sessionStart: sessionStart,
     _lastPromptTokens: null, _usageAtLen: null,
     _compressFailures: 0,
+    _runStartHistoryLen: 0, // machine-line length at the start of the current run — end-of-run exploration distillation slices from here
     _currentTurn: 0, _maxTurns: 100, // turn counter for status bar display
   }
 }
@@ -106,6 +107,10 @@ export async function runAgent(agent, input, callbacks = {}, { depth = 0, signal
     { depth, signal, overrideTurns, resume, systemPrompt: SYSTEM_PROMPT, disciplineRules: DISCIPLINE_RULES, mainOverlay: MAIN_OVERLAY },
   )
 
+  // End-of-run exploration distillation boundary (CONTEXT-COMPACTION §5): prepareRun has already
+  // pushed the user input + injections, so everything appended from here is "this run's" work.
+  agent._runStartHistoryLen = agent.history.length
+
   // Per-run bookkeeping reset. On `resume` (ContinueError continuation) these are
   // PRESERVED: the resumed run must keep mutation tracking so the advisor/verify
   // guards stay active (a guard pushback on the last turn must not silently vanish),
@@ -301,6 +306,12 @@ export async function runAgent(agent, input, callbacks = {}, { depth = 0, signal
       honestReminderInjected = cr.honestReminderInjected
       advisorPushbacks = cr.advisorPushbacks
       if (cr.action === "continue") continue
+      if (depth === 0) {
+        // End-of-run exploration distillation (CONTEXT-COMPACTION §5): this run's inline
+        // exploration results become one semantic note before the final return. Silent (N3):
+        // distillation failure must never block the return or lose history.
+        try { await summarizeRunExplorations(agent, callbacks, signal) } catch { /* silent (N3) */ }
+      }
       return cr.content
     }
 

package/src/config.mjs

@@ -87,7 +87,7 @@ export const DEFAULTS = {
  * multimodal:        whether multimodal (image/vision input supported)
  * cacheMode:         context caching mode: "auto"=automatic / "prompt"=needs explicit / "none"=unsupported
  * thinkApi:          thinking API type: "type"=thinking.type field / "effort"=reasoning_effort field
- * thinkOnValue:      when thinkApi is "type", the value used to enable thinking (default "enabled"; MiniMax uses "adaptive")
+ * thinkEnabledValue: when thinkApi is "type", the value used to enable thinking (default "enabled"; MiniMax uses "adaptive")
  * reasoningEcho:     reasoning_content cross-turn echo strategy: "required"=must echo (error if missing) / "optional"=echo optional (default: don't echo)
  * reasoningEffortEnum: valid reasoning_effort enum values (if undeclared, no validation — passed through as-is)
  * tempRange:         valid temperature range [min, max] (if undeclared, no clamping)
@@ -96,6 +96,8 @@ const MODEL_SPECS = [
   // DeepSeek V4 series
   ["deepseek-v4-pro",   { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 2] }],
   ["deepseek-v4-flash", { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 2] }],
+  // DeepSeek V4 Flash Vision (experimental) — image input on top of the full V4-Flash stack
+  ["deepseek-v4-flash-vision-exp", { context: 1_000_000, maxOutput: 384_000, thinking: true,  prefixMode: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 2], multimodal: true }],
   // Kimi series
   ["kimi-k3",           { context: 1_000_000, maxOutput: 131_072, thinking: true,  partialMode: true, multimodal: true, cacheMode: "auto",  thinkApi: "effort", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"] }],
   // Qwen router prefixes model IDs with provider namespace: kimi/kimi-k3 → kimi-k3 (IK7K4V)
@@ -103,17 +105,22 @@ const MODEL_SPECS = [
   // Kimi For Coding endpoint uses the short model ID "k3" (same specs as kimi-k3) — IK5VGJ
   ["k3",                { context: 1_000_000, maxOutput: 131_072, thinking: true,  partialMode: true, multimodal: true, cacheMode: "auto",  thinkApi: "effort", reasoningEcho: "required", reasoningEffortEnum: ["low", "high", "max"] }],
   // GLM series
+  // GLM-5.3: thinking always-on (no "disabled"); effort converges to low/high/max — NOT the
+  //          7-level glm-5.2 enum (verified vs docs.bigmodel.cn GLM-5.3 page, 2026-08)
+  ["glm-5.3",           { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["low", "high", "max"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-5.2",           { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-5",             { context: 1_000_000, maxOutput: 128_000, thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", reasoningEffortEnum: ["max", "xhigh", "high", "medium", "low", "minimal", "none"], tempRange: [0, 1], noUsageStream: true }],
   ["glm-4",             { context: 128_000,   maxOutput: 32_000,  thinking: true,  cacheMode: "auto", thinkApi: "type", reasoningEcho: "optional", tempRange: [0, 1], noUsageStream: true }],
   // GPT series
+  ["gpt-5.6-sol",       { context: 1_050_000, maxOutput: 128_000, thinking: false, multimodal: true, cacheMode: "prompt" }],
+  ["gpt-5.6",           { context: 1_050_000, maxOutput: 128_000, thinking: false, multimodal: true, cacheMode: "prompt" }],
   ["gpt-4.1",           { context: 1_000_000, maxOutput: 128_000, thinking: false, cacheMode: "prompt" }],
   ["gpt-4o",            { context: 128_000,   maxOutput: 16_000,  thinking: false, multimodal: true, cacheMode: "prompt" }],
   // Qwen series
-  ["qwen3.8-max-preview", { context: 1_000_000, maxOutput: 128_000, thinking: true, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "high"], tempRange: [0, 2] }],
+  ["qwen3.8-max-preview", { context: 1_000_000, maxOutput: 131_072, thinking: true, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "medium", "low"], tempRange: [0, 2] }],
   // qwen3.7-max rejects image parts outright (DashScope 400 "Unexpected item type in content") — text-only
-  ["qwen3.7-max",       { context: 1_000_000, maxOutput: 128_000, thinking: true, partialMode: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "high"], tempRange: [0, 2] }],
-  ["qwen3.8-max",       { context: 1_000_000, maxOutput: 128_000, thinking: true, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "medium", "low"], tempRange: [0, 2] }],
+  ["qwen3.7-max",       { context: 1_000_000, maxOutput: 131_072, thinking: true, partialMode: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "high"], tempRange: [0, 2] }],
+  ["qwen3.8-max",       { context: 1_000_000, maxOutput: 131_072, thinking: true, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", reasoningEffortEnum: ["xhigh", "medium", "low"], tempRange: [0, 2] }],
   ["qwen-max",          { context: 1_000_000, maxOutput: 131_072, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
   ["qwen-plus",         { context: 1_000_000, maxOutput: 131_072,  thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
   ["qwen",              { context: 1_000_000, maxOutput: 131_072, thinking: false, partialMode: true, multimodal: true, cacheMode: "none", thinkApi: "effort", tempRange: [0, 2] }],
@@ -127,6 +134,8 @@ const MODEL_SPECS = [
   ["minimax-m3",        { context: 1_000_000, maxOutput: 128_000, thinking: true,  multimodal: true, cacheMode: "auto", thinkApi: "type", thinkEnabledValue: "adaptive", tempRange: [0, 2], noUsageStream: true }],
   ["minimax-m1",        { context: 256_000,   maxOutput: 128_000, thinking: false, cacheMode: "auto", noUsageStream: true }],
   // Grok series (xAI — OpenAI-compatible)
+  // grok-4.x: 500K context per xAI Grok 4.6 spec (corrected 2026-08; earlier entries said 1M)
+  ["grok-4.6",          { context: 500_000,   maxOutput: 64_000,  thinking: false, multimodal: true, tempRange: [0, 2] }],
   ["grok-4.5",          { context: 500_000,   maxOutput: 64_000,  thinking: false, multimodal: true, tempRange: [0, 2] }],
   ["grok-4",            { context: 500_000,   maxOutput: 64_000,  thinking: false, multimodal: true, tempRange: [0, 2] }],
   ["grok-4-mini",       { context: 128_000,   maxOutput: 16_000,  thinking: false, tempRange: [0, 2] }],
@@ -134,10 +143,13 @@ const MODEL_SPECS = [
   ["mistral-large",     { context: 128_000,   maxOutput: 32_000,  thinking: false, multimodal: true, tempRange: [0, 2] }],
   ["codestral",         { context: 256_000,   maxOutput: 32_000,  thinking: false, tempRange: [0, 2] }],
   // Claude series (Anthropic)
+  ["claude-opus-5",     { context: 1_000_000, maxOutput: 128_000, thinking: false, multimodal: true, cacheMode: "none", format: "anthropic" }],
+  ["claude-sonnet-5",   { context: 1_000_000, maxOutput: 128_000, thinking: false, multimodal: true, cacheMode: "none", format: "anthropic" }],
   ["claude-opus-4",     { context: 200_000,   maxOutput: 32_000,  thinking: false, multimodal: true, cacheMode: "none", format: "anthropic" }],
   ["claude-sonnet-4",   { context: 200_000,   maxOutput: 32_000,  thinking: false, multimodal: true, cacheMode: "none", format: "anthropic" }],
   ["claude-3.5-haiku",  { context: 200_000,   maxOutput: 8_192,   thinking: false, cacheMode: "none", format: "anthropic" }],
   // Gemini series (Google)
+  ["gemini-3-pro",      { context: 1_000_000, maxOutput: 64_000,  thinking: false, multimodal: true, cacheMode: "none", format: "google", noUsageStream: true }],
   ["gemini-2.5-pro",    { context: 2_000_000, maxOutput: 64_000,  thinking: false, multimodal: true, cacheMode: "none", format: "google", noUsageStream: true }],
   ["gemini-2.5-flash",  { context: 1_000_000, maxOutput: 64_000,  thinking: false, multimodal: true, cacheMode: "none", format: "google", noUsageStream: true }],
 ]