dsh-subagent-profile 0.4.0 → 0.5.1

package/README.md

@@ -19,13 +19,15 @@ For [DeepSeek Harness](https://github.com/deepseek-ai/dsh) (DSH).
 
 | | Built-in `subagent` | `dsh-subagent-profile` |
 |---|---|---|
-| Per-subtask model / preset | ❌ same brain for every subtask | ✅ pick per subtask |
+| Per-subtask model / preset | ✅ optional `provider` / `model` / `reasoning_effort` (after enabling model selection) | ✅ one profile bundles preset + model + effort + tool scope + budget; overridable per call |
 | Reusable named setups | ❌ | ✅ profiles |
 | Tool-scope narrowing | ❌ | ✅ whitelist ∩ parent, `run_code` always removed |
 | Safety checks | ❌ | ✅ whitelist / cost / intersection / approval / budget, all recorded |
 | Cost visibility | ❌ | ✅ per-dispatch estimate + savings comparison |
-| Decision ledger | ❌ | ✅ full trace: request vs. effective, gates, execution, settlement |
+| Decision ledger | ❌ | ✅ full trace: request vs. effective, checks, execution, settlement |
 | GUI management | ❌ | ✅ settings page + per-session ledger tab |
+| Performance-based suggestions | ❌ | ✅ confirm to apply, undo anytime |
+| Official model-selection interplay | ✅ enforced natively once enabled | ✅ dispatch follows the same whitelist (out-of-range routes are rejected) |
 
 ## Installation
 
@@ -34,7 +36,7 @@ dsh plugin --profile web add dsh-subagent-profile        # published package
 dsh plugin --profile web add ./dsh-subagent-profile      # from a local checkout
 ```
 
-Restart `dsh web`. This is a standard **bundle plugin**: it provides the `dispatch` tool, the profile provider, the `subagent-profiles` service, the `/subagent-profiles/*` loopback management routes, the settings page (「子 Agent 方案」), the per-session ledger tab, and the `dispatch` tool-call card in the web GUI. On startup it also **self-installs an agent preset** — **`orchestrator`** (「编排者模式」) — pick it in the new-session preset picker. The sync is idempotent and re-runs on every startup, so upgrading the plugin updates the preset.
+Restart `dsh web`. This is a standard **bundle plugin**: it provides the `dispatch` tool, the profile provider, the `subagent-profiles` service, the `/subagent-profiles/*` loopback management routes, the settings page (「子 Agent 方案」), the per-session ledger tab, and the `dispatch` tool-call card in the web GUI. On startup it also **self-installs an agent preset** — **`orchestrator-v2`** (「编排者模式 V2」) — pick it in the new-session preset picker. The sync is idempotent and re-runs on every startup, so upgrading the plugin updates the preset.
 
 ## Usage
 
@@ -95,14 +97,16 @@ Delegation never lets a subagent gain more power than you already have — this
   - `summaries.json` — aggregated per-profile statistics (versioned, rebuilt on corruption).
   - `adopted-state.json` — adoption verdict state for child results (cross-restart).
   - `reminders.json` — reminder store (one reminder = one audit record).
-- `~/.dsh/.agent-presets/orchestrator/` — the self-installed `orchestrator` agent preset (synced from the bundled `presets/orchestrator/` on every startup).
+- `~/.dsh/.agent-presets/orchestrator-v2/` — the self-installed `orchestrator-v2` agent preset (synced from the bundled `presets/orchestrator-v2/` on every startup).
 
-`DSH_HOME` is respected and defaults to `~/.dsh`. Uninstalling the plugin removes the data files above and the self-installed `orchestrator` preset directory (other plugins' presets are left untouched); re-installing or re-launching re-syncs the preset and regenerates the data files.
+`DSH_HOME` is respected and defaults to `~/.dsh`. Uninstalling the plugin removes the data files above and the self-installed `orchestrator-v2` preset directory (other plugins' presets are left untouched); re-installing or re-launching re-syncs the preset and regenerates the data files.
 
 ## Known limitations
 
 - **Background dispatch** requires `@deepseek-ai/dsh-jobs` and `@deepseek-ai/dsh-tool-jobs` to be loaded; otherwise it fails with "dispatch: 后台派发不可用：缺少 jobs 服务".
 - **Continuable mode** goes through the DSH standard composition path, so the `preset` swap and `reasoningEffort` are ignored (the child inherits the parent preset at the default reasoning effort).
+- **Continuable follow-ups** are delivered through the official `send_message` channel (the plugin drives the child via the official child handle).
+- **Official model selection is a web-line feature**: the session policy for the built-in subagent tools ships with the web app and is not available in headless deployments. In production it is off by default and must be enabled before it takes effect.
 - **Who decides the child's final tool set depends on the mode**:
   - Continuable: narrowed by this plugin up front — the child's `allow` = (parent tool set − `run_code` − `deny`) ∩ `allow`. Assumption: continuable inherits the parent preset, so the child's tool set ≈ the parent's; if dsh's behavior changes so the two differ (e.g. a future preset swap composing a different tool set), tool narrowing fails with a hard error (conservatively safe — never silently granting more), to be replaced with a true parent ∩ child intersection once dsh provides an official seam.
   - One-shot: decided by dsh; the plugin cannot read the final restricted result and the card reports "tools are finally granted by the system".
@@ -112,58 +116,13 @@ Delegation never lets a subagent gain more power than you already have — this
 
 ```
 dsh-subagent-profile/
-├── index.mjs                     # host side: the plugin itself (dispatch tool, profile provider, service, HTTP routes)
+├── index.mjs          # plugin entry: dispatch tool, profile provider, services, HTTP routes
 ├── lib/
-│   ├── client.js                 # browser side: settings page + ledger + dispatch tool-call card
-│   └── core/                     # host-side modules (lightweight layering)
-│       ├── pure.mjs              # dependency-free pure functions (sanitize / prune / guard math — unit-tested)
-│       ├── shims.mjs             # the single @deepseek-ai import facade (guards fail loud, helpers degrade softly)
-│       ├── catalog.mjs           # tool-name → zh / category tables (zero-dep)
-│       ├── catalog-cache.mjs     # process-shared catalog snapshot (models / presets / tools, TTL cache)
-│       ├── cost-guard.mjs        # runtime capability checks (provider / model / reasoning effort)
-│       ├── cost-evidence.mjs     # counterfactual savings evidence (token-saving proof)
-│       ├── prices.mjs            # per-dispatch price table (average-based placeholder)
-│       ├── decision-trace.mjs    # decision trace (checks / effective / settled) + failure ledger
-│       ├── delegation.mjs        # background one-shot settling + child usage collection
-│       ├── dispatch-gates.mjs    # pre-dispatch safety checks (whitelist / cost / intersection / budget)
-│       ├── dispatch-guard.mjs    # concurrency + per-parent token budget guard
-│       ├── dispatch-schema.mjs   # dispatch tool input/output schema declarations
-│       ├── dispatch-tool.mjs     # dispatch tool factory (defineTool + execute + syncTool)
-│       ├── draft-gates.mjs       # draft profile gates (three checks)
-│       ├── drafts-store.mjs      # draft profile persistence
-│       ├── escape.mjs            # escape-hatch allow store
-│       ├── evolution-ledger.mjs  # decision ledger (jsonl) + governance audit
-│       ├── evolution-summary.mjs # aggregate statistics (per-profile, capability/budget axes)
-│       ├── evolution-advice.mjs  # read-only dispatch suggestion generation
-│       ├── adoption-tracker.mjs  # child-result adoption verdict tracking (cross-restart)
-│       ├── adoption-reminder.mjs # adoption-verdict reminder generation
-│       ├── reminder-store.mjs    # reminder store + audit-coupled records
-│       ├── background-ledger.mjs # background job ledger (in-memory, resets on restart)
-│       ├── http-routes.mjs       # settings loopback HTTP routes
-│       ├── intersection.mjs      # tool-intersection pure core
-│       ├── presets-sync.mjs      # bundled preset self-install (hash-gated sync)
-│       ├── profile-provider.mjs  # the `profile` subagent provider
-│       ├── profile-directory.mjs # read-only profile directory (for the model)
-│       ├── profiles-store.mjs    # profile registry store + switch persistence
-│       └── whitelist.mjs         # system-trust preset whitelist
-├── presets/orchestrator/         # bundled "orchestrator" agent preset (self-installed, synced on every startup)
-├── cordis.patch.yml              # bundle patch: inserts the plugin row into the host composition
-├── .gitea/workflows/ci.yml       # bare-CI (Gitea Actions; needs an Act runner on the server)
-├── package.json                  # metadata, files whitelist, exports (test / test:bare / preflight scripts)
-├── scripts/
-│   ├── preflight.mjs             # preflight: preset-tree reconciliation + no hardcoded version badge (zero-dep)
-│   └── leak-scan.mjs             # public-release gate: scans all history + worktree for sensitive patterns
-├── docs/
-│   └── screenshots/              # README screenshots
-├── test/                         # host-side tests (node:test, zero extra deps; 438 cases)
-│   ├── README.md / README.zh.md  # test directory guide (EN/ZH) — two-tier split explained
-│   ├── harness/ctx.mjs           # fake Cordis ctx + ~/.dsh isolation
-│   ├── pure / input-schema / catalog-integrity.test.mjs   # bare tier (import-free, runs in bare CI)
-│   └── *.test.mjs                # junction tier (local only): characterization / facade / gating / persist / recycle /
-│                                 #   cost-guard / continuable-guard / decision-trace / dispatch-guard / escape-hatch /
-│                                 #   evolution-* / csrf / label-preset-sync / percall-spec / trust-label / audit-meta / …
-├── README.md / README.zh.md      # this document (EN/ZH)
-└── LICENSE
+│   ├── client.js      # browser side: settings page, per-session ledger, dispatch tool-call card
+│   └── core/          # host-side modules by domain: gates, ledger, evolution, profiles, query, sync
+├── presets/           # bundled agent presets (e.g. orchestrator-v2)
+├── test/              # node:test suite (pure and junction tiers)
+└── docs/              # screenshots
 ```
 
 ## Contributing
@@ -174,7 +133,7 @@ If this plugin has been useful to you, please give it a ⭐ on GitHub — it hel
 
 ## Credits
 
-The bundled `orchestrator` agent preset was inspired by [dsh-liangshen](https://github.com/zhu1090093659/dsh-web-ui/tree/main/packages/dsh-liangshen) (梁神模式) from [dsh-web-ui](https://github.com/zhu1090093659/dsh-web-ui), licensed under Apache-2.0. Thanks to its author for the great work.
+The bundled `orchestrator-v2` agent preset was inspired by [dsh-liangshen](https://github.com/zhu1090093659/dsh-web-ui/tree/main/packages/dsh-liangshen) (梁神模式) from [dsh-web-ui](https://github.com/zhu1090093659/dsh-web-ui), licensed under Apache-2.0. Thanks to its author for the great work.
 
 ## License
 

package/README.zh.md

@@ -19,13 +19,15 @@
 
 | | 内置 `subagent` | `dsh-subagent-profile` |
 |---|---|---|
-| 按子任务选模型/预设 | ❌ 每个子任务同一个「大脑」 | ✅ 按任务逐个指定 |
+| 按子任务选模型/预设 | ✅ 可选 `provider` / `model` / `reasoning_effort`（需先启用模型选择） | ✅ 方案级 profile：预设+模型+推理强度+工具范围+预算一捆，per-call 可覆盖 |
 | 可复用的命名方案 | ❌ | ✅ 方案（profile） |
 | 工具范围收敛 | ❌ | ✅ 白名单 ∩ 父会话，`run_code` 恒移除 |
 | 派发前安全检查 | ❌ | ✅ 白名单/成本/交集/审批/预算，全程记录 |
 | 成本可见 | ❌ | ✅ 每次派发的成本估算 + 节省对照 |
-| 派发决策台账 | ❌ | ✅ 请求vs生效、检查结果、执行、结算全留痕 |
+| 派发决策台账 | ❌ | ✅ 请求 vs 生效、检查结果、执行、结算全留痕 |
 | 界面管理 | ❌ | ✅ 设置页 + 会话内台账标签页 |
+| 基于表现的改进建议 | ❌ | ✅ 确认后应用 · 随时撤销 |
+| 官方模型选择联动 | ✅ 启用后由官方工具自身校验 | ✅ 官方启用后派发遵循同一白名单（越界路由直接拒绝） |
 
 ## 安装
 
@@ -34,7 +36,7 @@ dsh plugin --profile web add dsh-subagent-profile        # 发布包
 dsh plugin --profile web add ./dsh-subagent-profile      # 本地源码
 ```
 
-重启 `dsh web`。这是一个标准的 **bundle 插件**：提供 `dispatch` 工具、方案提供者、`subagent-profiles` 服务、`/subagent-profiles/*` 回环管理路由、设置页（「子 Agent 方案」）、会话内派发决策台账标签页，以及 web 界面中的 `dispatch` 工具卡片。启动时还会**自动安装一个 agent 预设**——**`orchestrator`**（「编排者模式」）——在新会话的预设选择器里选用。同步是幂等的且每次启动重跑，升级插件即更新预设。
+重启 `dsh web`。这是一个标准的 **bundle 插件**：提供 `dispatch` 工具、方案提供者、`subagent-profiles` 服务、`/subagent-profiles/*` 回环管理路由、设置页（「子 Agent 方案」）、会话内派发决策台账标签页，以及 web 界面中的 `dispatch` 工具卡片。启动时还会**自动安装一个 agent 预设**——**`orchestrator-v2`**（「编排者模式 V2」）——在新会话的预设选择器里选用。同步是幂等的且每次启动重跑，升级插件即更新预设。
 
 ## 使用
 
@@ -95,14 +97,16 @@ dispatch(
   - `summaries.json` —— 按方案聚合的统计（带版本号，损坏自动重建）。
   - `adopted-state.json` —— 子结果采纳判定状态（跨重启）。
   - `reminders.json` —— 提醒存储（一条提醒 = 一条审计记录）。
-- `~/.dsh/.agent-presets/orchestrator/` —— 自动安装的 `orchestrator` 预设（每次启动从内置 `presets/orchestrator/` 同步）。
+- `~/.dsh/.agent-presets/orchestrator-v2/` —— 自动安装的 `orchestrator-v2` 预设（每次启动从内置 `presets/orchestrator-v2/` 同步）。
 
-尊重 `DSH_HOME` 环境变量（默认 `~/.dsh`）。卸载插件会移除上述数据文件与自动安装的 `orchestrator` 预设目录（其他插件的预设不动）；重装或重启会重新同步预设并重建数据文件。
+尊重 `DSH_HOME` 环境变量（默认 `~/.dsh`）。卸载插件会移除上述数据文件与自动安装的 `orchestrator-v2` 预设目录（其他插件的预设不动）；重装或重启会重新同步预设并重建数据文件。
 
 ## 已知限制
 
 - **后台派发**需要 `@deepseek-ai/dsh-jobs` 与 `@deepseek-ai/dsh-tool-jobs` 已加载；否则报「dispatch: 后台派发不可用：缺少 jobs 服务」。
 - **持久（continuable）模式**走 DSH 标准组合路径，`preset` 换用与 `reasoningEffort` 会被忽略（子代理继承父预设与默认推理强度）。
+- **持久模式的后续轮次走官方 `send_message`**（插件通过官方子代理句柄驱动后续对话）。
+- **官方模型选择是 web 线功能**：内置 subagent 工具的会话策略随 web 应用提供，headless 部署没有；生产默认未启用，需手动开启后才会生效。
 - **子代理的最终工具集由谁决定，取决于模式**：
   - 持久（continuable）模式：由本插件预先收敛——子代理 `allow` =（父工具集 − `run_code` − `deny`）∩ `allow`。前提假设：持久模式沿用父会话预设，故子工具集与父会话基本一致；一旦 dsh 的行为变化导致两者不同（如未来支持预设换用后组合出不同工具集），工具收敛会**直接报错拒绝**（保守安全，绝不静默放行），待 dsh 官方提供相应接口后替换为真正的父 ∩ 子交集。
   - 一次性模式：由 dsh 决定，插件读不到最终受限结果；卡片显示「工具由系统最终授予」。
@@ -112,58 +116,13 @@ dispatch(
 
 ```
 dsh-subagent-profile/
-├── index.mjs                     # 宿主侧：插件本体（dispatch 工具、方案提供者、服务、HTTP 路由）
+├── index.mjs          # 插件入口：dispatch 工具、方案提供方、服务与 HTTP 路由
 ├── lib/
-│   ├── client.js                 # 浏览器侧：设置页 + 台账 + dispatch 工具卡片
-│   └── core/                     # 宿主侧模块（轻量分层）
-│       ├── pure.mjs              # 零依赖纯函数（清洗/剪枝/护栏数学——单测覆盖）
-│       ├── shims.mjs             # 唯一的 @deepseek-ai 导入门面（护栏大声失败，辅助软降级）
-│       ├── catalog.mjs           # 工具名 → 中文/分类表（零依赖）
-│       ├── catalog-cache.mjs     # 进程共享目录快照（模型/预设/工具，TTL 缓存）
-│       ├── cost-guard.mjs        # 运行时能力检查（提供方/模型/推理强度）
-│       ├── cost-evidence.mjs     # 省 token 反事实对照证据
-│       ├── prices.mjs            # 每次派发单价表（当前为均价占位）
-│       ├── decision-trace.mjs    # 决策轨迹（检查/生效/结算）+ 失败台账
-│       ├── delegation.mjs        # 后台一次性结算 + 子用量采集
-│       ├── dispatch-gates.mjs    # 派发前安全检查（白名单/成本/交集/预算）
-│       ├── dispatch-guard.mjs    # 并发 + 每父会话 token 预算护栏
-│       ├── dispatch-schema.mjs   # dispatch 工具输入/输出 schema 声明
-│       ├── dispatch-tool.mjs     # dispatch 工具工厂（defineTool + execute + syncTool）
-│       ├── draft-gates.mjs       # 草稿方案三道闸
-│       ├── drafts-store.mjs      # 草稿方案持久化
-│       ├── escape.mjs            # 逃生舱放行存储
-│       ├── evolution-ledger.mjs  # 派发决策台账（jsonl）+ 治理审计
-│       ├── evolution-summary.mjs # 聚合统计（按方案，能力/预算双轴）
-│       ├── evolution-advice.mjs  # 只读派发建议生成
-│       ├── adoption-tracker.mjs  # 子结果采纳判定跟踪（跨重启）
-│       ├── adoption-reminder.mjs # 采纳判定提醒生成
-│       ├── reminder-store.mjs    # 提醒存储 + 审计耦合记录
-│       ├── background-ledger.mjs # 后台任务台账（内存态，重启即失）
-│       ├── http-routes.mjs       # 设置回环 HTTP 路由
-│       ├── intersection.mjs      # 工具交集纯核心
-│       ├── presets-sync.mjs      # 内置预设自动安装（哈希门控同步）
-│       ├── profile-provider.mjs  # `profile` 子代理提供者
-│       ├── profile-directory.mjs # 只读方案目录（供模型参考）
-│       ├── profiles-store.mjs    # 方案注册表存储 + 开关持久化
-│       └── whitelist.mjs         # system-trust 预设白名单
-├── presets/orchestrator/         # 内置「orchestrator」预设（自动安装，每次启动同步）
-├── cordis.patch.yml              # bundle patch：把插件行插入宿主组合
-├── .gitea/workflows/ci.yml       # bare-CI（Gitea Actions；需服务器上的 Act runner）
-├── package.json                  # 元数据、files 白名单、exports（test / test:bare / preflight 脚本）
-├── scripts/
-│   ├── preflight.mjs             # 预检：预设树一致 + 无硬编码版本徽章（零依赖）
-│   └── leak-scan.mjs             # 公开发布门：扫描全历史与工作区的敏感模式
-├── docs/
-│   └── screenshots/              # README 截图
-├── test/                         # 宿主侧测试（node:test，零额外依赖；438 用例）
-│   ├── README.md / README.zh.md  # 测试目录指南（中英）——两层拆分说明
-│   ├── harness/ctx.mjs           # 假 Cordis ctx + ~/.dsh 隔离
-│   ├── pure / input-schema / catalog-integrity.test.mjs   # bare 层（免导入，bare CI 可跑）
-│   └── *.test.mjs                # junction 层（仅本地）：characterization / facade / gating / persist / recycle /
-│                                 #   cost-guard / continuable-guard / decision-trace / dispatch-guard / escape-hatch /
-│                                 #   evolution-* / csrf / label-preset-sync / percall-spec / trust-label / audit-meta / …
-├── README.md / README.zh.md      # 本文档（英/中）
-└── LICENSE
+│   ├── client.js      # 浏览器端：设置页、每会话台账、派发工具调用卡片
+│   └── core/          # 宿主端核心模块（按域：闸门、台账、自进化、方案、查询、同步）
+├── presets/           # 内置 Agent 预设（如 orchestrator-v2）
+├── test/              # node:test 测试套件（纯函数层 + 接线层）
+└── docs/              # 截图
 ```
 
 ## 贡献
@@ -174,7 +133,7 @@ dsh-subagent-profile/
 
 ## 致谢
 
-内置的 `orchestrator` 预设灵感来自 [dsh-web-ui](https://github.com/zhu1090093659/dsh-web-ui) 的 [dsh-liangshen](https://github.com/zhu1090093659/dsh-web-ui/tree/main/packages/dsh-liangshen)（梁神模式），Apache-2.0 许可。感谢作者。
+内置的 `orchestrator-v2` 预设灵感来自 [dsh-web-ui](https://github.com/zhu1090093659/dsh-web-ui) 的 [dsh-liangshen](https://github.com/zhu1090093659/dsh-web-ui/tree/main/packages/dsh-liangshen)（梁神模式），Apache-2.0 许可。感谢作者。
 
 ## 许可