dsh-paoding 0.4.4 → 0.4.5

package/docs/architecture.md

@@ -58,6 +58,7 @@ dsh-paoding（中文品牌「庖丁」，取庖丁解牛之意）是 DSH（DeepS
         │               │               │               │
         ▼               ▼               ▼               ▼
    web_search       read/read_image  read/read_image  glob/grep/read/
+   web_fetch
    mcp__tavily__*   glob/grep/bash/  write/edit/      read_image/bash/
    (5 个)           skill/           glob/grep/bash/  ask_user_question/
    glob/grep/read   web_search       skill/web_search todo_write/
@@ -78,7 +79,7 @@ dsh-paoding（中文品牌「庖丁」，取庖丁解牛之意）是 DSH（DeepS
 |---|---|---|---|
 | 单体（现状，未裁剪） | 60 工具全量 | **~16.2k** | 每请求固定注入 |
 | 编排主 agent | 21 项白名单（∩ 注册面） | **~5.5k** | ↓66%；内部搜索零委派延迟 |
-| search_external 子 agent | 10 项 allow | ~3.0k | 仅实际联网调研时才产生 |
+| search_external 子 agent | 11 项 allow | ~3.0k | 仅实际联网调研时才产生 |
 | design 子 agent | 12 项 allow | ~3.3k | 仅实际委派设计时才产生 |
 | implement 子 agent | 17 项 allow | ~3.8k | 仅实际委派实现时才产生 |
 | search_internal_deep 子 agent | 10 项 allow | 未单独估算 | 仅实际委派全仓深搜时才产生 |
@@ -123,7 +124,7 @@ dsh-paoding（中文品牌「庖丁」，取庖丁解牛之意）是 DSH（DeepS
 **host 工具不在白名单常量内硬编码**：`mcp__*` 与插件工具（codegraph / memory_search / mnemon_* 等）
 是"检测期事实"——主 agent 需要时经配置文件 `$DSH_HOME/dsh-paoding.config.yml` 的 `main_agent_extra`
 勾选，生成层按运行时检测把仍启用的注入 restrict 的 `config.allow`，停用即自动清除（详见
-[docs/configuration.md](configuration.md)）。因此主 agent 的默认面**不包含** `web_search`、全部
+[docs/configuration.md](configuration.md)）。因此主 agent 的默认面**不包含** `web_search` / `web_fetch`、全部
 `mcp__tavily__*`、`write` / `edit` / `str_replace_editor`、`skill`、`workflow`、`ralph` 及未过滤的
 `subagent` / `subagent_fork`——这些要么属于角色子 agent，要么成本被刻意清零。
 
@@ -142,7 +143,7 @@ dsh-paoding（中文品牌「庖丁」，取庖丁解牛之意）是 DSH（DeepS
 
 | 委派工具 | 实例 ID | persona 一句话职责 | 加载成本 |
 |---|---|---|---|
-| `search_external` | `delegation-search-external` | 只做联网调研（web_search + tavily），绝不改文件；返回结构化研究摘要（发现、来源、待答问题） | ~3.0k，仅委派时 |
+| `search_external` | `delegation-search-external` | 只做联网调研（web_search + web_fetch + tavily），绝不改文件；返回结构化研究摘要（发现、来源、待答问题） | ~3.0k，仅委派时 |
 | `design` | `delegation-design` | 产出 UI/UX 设计、线框与前端 spec，可用 skill 工具加载设计技能（frontend-design、html-ppt）；先读参考再交付 spec，不写最终代码 | ~3.3k，仅委派时 |
 | `implement` | `delegation-implement` | 写与改代码：先读上下文 → 精准修改 → 验证（build/test/grep）；不改架构 | ~3.8k，仅委派时 |
 | `search_internal_deep` | `delegation-search-internal-deep` | 只做仓库探索：不改文件、不联网；处理主 agent 上下文装不下的任务（全仓 grep dump、超页大文件通读、跨目录符号/定义追踪），只回浓缩摘要 | 未单独估算，仅委派时 |
@@ -157,12 +158,12 @@ dsh-paoding（中文品牌「庖丁」，取庖丁解牛之意）是 DSH（DeepS
 **不做**库存对账：手写进去、两头都不占的名字不会被剔除，会静默落盘、运行时以 unknown tools 拒创建
 （与下方该角色的 codegraph 注同一口径），见 [docs/configuration.md](configuration.md)）。
 
-**`search_external`（外部调研，10 项）**
+**`search_external`（外部调研，11 项）**
 
 | 字段 | 值 |
 |---|---|
 | persona 职责 | 只做联网调研并返回结构化研究摘要（发现、来源、待答问题）；绝不修改文件 |
-| toolFilter.allow | `web_search`、`mcp__tavily__tavily_search`、`mcp__tavily__tavily_crawl`、`mcp__tavily__tavily_extract`、`mcp__tavily__tavily_map`、`mcp__tavily__tavily_research`、`glob`、`grep`、`read`、`ask_user_question` |
+| toolFilter.allow | `web_search`、`web_fetch`、`mcp__tavily__tavily_search`、`mcp__tavily__tavily_crawl`、`mcp__tavily__tavily_extract`、`mcp__tavily__tavily_map`、`mcp__tavily__tavily_research`、`glob`、`grep`、`read`、`ask_user_question` |
 | 加载成本 | ~3.0k tokens，仅实际联网调研时发生 |
 
 **`design`（设计，12 项）**

package/docs/architecture_en.md

@@ -70,6 +70,7 @@ allow lists are in the "Roles & tool surfaces" section below):
             │                   │                   │                   │               
             ▼                   ▼                   ▼                   ▼               
     web_search           read/read_image      read/read_image      glob/grep/read
+    web_fetch
     mcp__tavily__*       glob/grep/bash       write/edit           read_image/bash
     (5 tools)            skill/web_search     glob/grep/bash       ask_user_question
     glob/grep/read       ask_user_question    skill/web_search     todo_write
@@ -90,8 +91,8 @@ In the diagram:
   ask_user_question / get_goal / create_goal / update_goal / exit_plan_mode / job_output / job_list /
   job_kill);
 - Four arrows fan out to the **role sub-agents**, each created on demand (cold path). search_external
-  carries web_search, the five `mcp__tavily__*` tools, plus glob/grep/read and ask_user_question, with no
-  write/edit; design carries read/read_image/glob/grep/bash/skill/web_search plus coordination tools;
+  carries web_search, web_fetch, the five `mcp__tavily__*` tools, plus glob/grep/read and ask_user_question,
+  with no write/edit; design carries read/read_image/glob/grep/bash/skill/web_search plus coordination tools;
   implement carries read/read_image/write/edit/glob/grep/bash/skill/web_search plus coordination and
   goal tools;
   search_internal_deep carries the full read-only internal-search surface (glob/grep/read/read_image/bash
@@ -107,7 +108,7 @@ measured calibration; figures are order-of-magnitude estimates):
 |---|---|---|---|
 | Monolithic (status quo, untrimmed) | All 60 tools | **~16.2k** | Paid in full on every request |
 | Orchestrator main agent | 21-entry whitelist (∩ registry) | **~5.5k** | ↓66%; zero delegation latency for internal search |
-| search_external sub-agent | 10 allowed entries | ~3.0k | Paid only when web research actually runs |
+| search_external sub-agent | 11 allowed entries | ~3.0k | Paid only when web research actually runs |
 | design sub-agent | 12 allowed entries | ~3.3k | Paid only when a design task is delegated |
 | implement sub-agent | 17 allowed entries | ~3.8k | Paid only when an implementation task is delegated |
 | search_internal_deep sub-agent | 10 allowed entries | not separately estimated | Paid only when a deep repo search is delegated |
@@ -160,7 +161,7 @@ memory_search / mnemon_* etc.) are "install-time facts" — when the main agent
 `main_agent_extra` in the configuration file `$DSH_HOME/dsh-paoding.config.yml`, the generator injects the
 still-enabled ones into the restrict `config.allow` based on runtime detection, and disabled ones are
 dropped automatically (see [docs/configuration_en.md](configuration_en.md)). The main agent's default surface
-therefore excludes `web_search`, every `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`,
+therefore excludes `web_search` / `web_fetch`, every `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`,
 `workflow`, `ralph`, and the unfiltered `subagent` / `subagent_fork` — either because they belong to role
 sub-agents or because their cost is deliberately zeroed out.
 
@@ -184,7 +185,7 @@ For example, a `ppt` agent carrying the `html-ppt` skill gives slide-making its
 
 | Delegation tool | Instance ID | Persona in one sentence | Load cost |
 |---|---|---|---|
-| `search_external` | `delegation-search-external` | Web research only (web_search + tavily), never modifies files; returns a structured research summary (findings, sources, open questions) | ~3.0k, only when delegated |
+| `search_external` | `delegation-search-external` | Web research only (web_search + web_fetch + tavily), never modifies files; returns a structured research summary (findings, sources, open questions) | ~3.0k, only when delegated |
 | `design` | `delegation-design` | Produces UI/UX designs, wireframes and frontend specs; may load design skills (frontend-design, html-ppt) via the skill tool; reads reference material first, delivers a spec, does not implement final code | ~3.3k, only when delegated |
 | `implement` | `delegation-implement` | Writes and edits code: read surrounding context → surgical change → verify (build/test/grep); does not redesign architecture | ~3.8k, only when delegated |
 | `search_internal_deep` | `delegation-search-internal-deep` | Repository exploration only: never modifies files, never uses the network; handles tasks too heavy for the main agent's context (whole-repo grep dumps, full-file reads beyond a page, cross-directory symbol/definition tracking); returns condensed summaries only | not separately estimated, only when delegated |
@@ -213,12 +214,12 @@ on disk silently, and fail at runtime with unknown tools at child creation — s
 note for that role below; see
 [docs/configuration_en.md](configuration_en.md)).
 
-**`search_external` (external research, 10 entries)**
+**`search_external` (external research, 11 entries)**
 
 | Field | Value |
 |---|---|
 | Persona job | Web research only, returning a structured research summary (findings, sources, open questions); never modifies files |
-| toolFilter.allow | `web_search`, `mcp__tavily__tavily_search`, `mcp__tavily__tavily_crawl`, `mcp__tavily__tavily_extract`, `mcp__tavily__tavily_map`, `mcp__tavily__tavily_research`, `glob`, `grep`, `read`, `ask_user_question` |
+| toolFilter.allow | `web_search`, `web_fetch`, `mcp__tavily__tavily_search`, `mcp__tavily__tavily_crawl`, `mcp__tavily__tavily_extract`, `mcp__tavily__tavily_map`, `mcp__tavily__tavily_research`, `glob`, `grep`, `read`, `ask_user_question` |
 | Load cost | ~3.0k tokens, incurred only when web research actually runs |
 
 **`design` (design, 12 entries)**

package/docs/configuration.md

@@ -73,6 +73,7 @@ roles:                  # toolName -> { persona?, tools[] }
       You are the external-research agent. Web research only — never modify files.
     tools:
       - web_search
+      - web_fetch
       - mcp__tavily__tavily_search
       - mcp__tavily__tavily_crawl
       - mcp__tavily__tavily_extract
@@ -138,11 +139,14 @@ skills:                 # skill -> 分配给的角色（写进角色 persona 的
     search_external:
       tools:
         - web_search
+        - web_fetch
         - mcp__tavily__tavily_*   # 生成时展开为 search/crawl/extract/map/research（以实际检测为准）
   ```
 
   `main_agent_extra` 与自定义角色的 `tools` 同样支持。配置文件里模式条目原样存取（配置面板回显不受影响），只有生成的 preset 里落的是展开后的具体名。
 
+  > 宿主 0.2.1-rc.2 起可在 **设置 → 网页搜索** 开启 DeepSeek Search / Fetch API：`web_search` / `web_fetch` 的名字不变，后方 provider 自动切换到官方新后端——无需改动庖丁配置，角色 allow 里的这两个名字照常生效。
+
 示例（替换 `implement` 的 persona 与 tools）：下方 tools 与静态默认一致——注意它不含 `str_replace_editor`（原因见 8.2）。显式写出 tools 等于固定意图：将来静态源怎么改都不再影响本角色：
 
 ```yaml
@@ -350,7 +354,7 @@ fork 的语义（如实说明）：
 | 内部搜索（热路径） | `glob` `grep` `read` `read_image` `bash` |
 | 协调 | `todo_write` `ask_user_question` `get_goal` `create_goal` `update_goal` `exit_plan_mode` `job_output` `job_list` `job_kill` |
 
-对照说明：`web_search`、全部 `mcp__tavily__*`、`write` / `edit` / `str_replace_editor`、`skill`、`workflow`、`ralph`、未过滤的 `subagent` 委派等**刻意不在**主 agent 面上（host 工具如 codegraph / `memory_search` / mnemon 同理不硬编码进源码，需要时用 `main_agent_extra` 勾选，见 3.2）。另外 `restrict.mjs` 在注册层对主 agent deny 了 `skill`（目录注入守卫查的是注册面而非模型可见面），主 agent 的技能目录注入随之归零。
+对照说明：`web_search` / `web_fetch`、全部 `mcp__tavily__*`、`write` / `edit` / `str_replace_editor`、`skill`、`workflow`、`ralph`、未过滤的 `subagent` 委派等**刻意不在**主 agent 面上（host 工具如 codegraph / `memory_search` / mnemon 同理不硬编码进源码，需要时用 `main_agent_extra` 勾选，见 3.2）。另外 `restrict.mjs` 在注册层对主 agent deny 了 `skill`（目录注入守卫查的是注册面而非模型可见面），主 agent 的技能目录注入随之归零。
 
 ### 3.2 追加工具：main_agent_extra
 

package/docs/configuration_en.md

@@ -73,6 +73,7 @@ roles:                  # toolName -> { persona?, tools[] }
       You are the external-research agent. Web research only — never modify files.
     tools:
       - web_search
+      - web_fetch
       - mcp__tavily__tavily_search
       - mcp__tavily__tavily_crawl
       - mcp__tavily__tavily_extract
@@ -138,11 +139,14 @@ Of the four built-in delegation roles, the installer (the `ROLES` constant) mana
     search_external:
       tools:
         - web_search
+        - web_fetch
         - mcp__tavily__tavily_*   # expanded at generation to search/crawl/extract/map/research (per actual detection)
   ```
 
   `main_agent_extra` and custom-role `tools` support them too. Pattern entries are stored and read back verbatim in the config file (the config panel renders them fine); only the generated preset contains the expanded concrete names.
 
+  > Host 0.2.1-rc.2 and later can enable the DeepSeek Search / Fetch API under **Settings → Web Search**: `web_search` / `web_fetch` keep their names while the provider behind them switches to the official new backend — no 庖丁 (Paoding) config change needed, and both names in a role's allow list keep working as-is.
+
 Example — replacing `implement`'s persona and tools. The `tools` below match the static default — note that it does **not** contain `str_replace_editor` (why: see 8.2). Writing `tools` out explicitly freezes the intent: later changes to the static source no longer affect this role:
 
 ```yaml
@@ -350,7 +354,7 @@ The `MAIN_AGENT_ALLOW` constant in `restrict.mjs` is the **base** (21 names) tha
 | Internal search (hot path) | `glob` `grep` `read` `read_image` `bash` |
 | Coordination | `todo_write` `ask_user_question` `get_goal` `create_goal` `update_goal` `exit_plan_mode` `job_output` `job_list` `job_kill` |
 
-For orientation: `web_search`, every `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`, `workflow`, `ralph`, and the unfiltered `subagent` delegation are **deliberately absent** from the main-agent surface (host tools such as codegraph / `memory_search` / mnemon are likewise not hard-coded into the source — opt them in via `main_agent_extra`, see 3.2). `restrict.mjs` also denies `skill` at the registry level for the main agent (the catalog-injection guard checks registry visibility, not the model-facing list), which brings the main agent's skill-catalog token tax to zero.
+For orientation: `web_search` / `web_fetch`, every `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`, `workflow`, `ralph`, and the unfiltered `subagent` delegation are **deliberately absent** from the main-agent surface (host tools such as codegraph / `memory_search` / mnemon are likewise not hard-coded into the source — opt them in via `main_agent_extra`, see 3.2). `restrict.mjs` also denies `skill` at the registry level for the main agent (the catalog-injection guard checks registry visibility, not the model-facing list), which brings the main agent's skill-catalog token tax to zero.
 
 ### 3.2 Appending tools: main_agent_extra
 

package/docs/orchestration.md

@@ -10,7 +10,7 @@
 dsh-paoding 把 DSH 从「单体 agent 全量加载工具」改造成「主 agent 编排 + 角色子 agent 分工」。分工遵循任务纹理：
 
 - **热路径——内部文件问题不委派。** 找代码、查引用、读文件这类问题由主 agent 自己用只读工具解决：`glob` / `grep` / `read` / `read_image` / `bash` 全部在主 agent 白名单内，零委派往返延迟。persona 文案里的 `codegraph` 是 host MCP 工具，仅在安装期检测到 codegraph 服务器并经 `main_agent_extra` 注入后才真正可用（详见[配置](configuration.md)与[安装](installation.md)）。
-- **冷路径——只干自己那活的角色子 agent。** 外部调研委派 `search_external`（只带 `web_search` + tavily 五工具 + 本地只读）、UI/前端设计委派 `design`（读参考 + 设计技能 + 出 spec，不写最终代码）、代码实现委派 `implement`（读上下文 → 精准修改 → 验证）、超大仓库全量探索委派 `search_internal_deep`（第四角色，2026-09 加入，见下节与[架构](architecture.md)）。每个子 agent 只在真正被委派的那一次才加载工具面（按需加载）。
+- **冷路径——只干自己那活的角色子 agent。** 外部调研委派 `search_external`（只带 `web_search` / `web_fetch` + tavily 五工具 + 本地只读）、UI/前端设计委派 `design`（读参考 + 设计技能 + 出 spec，不写最终代码）、代码实现委派 `implement`（读上下文 → 精准修改 → 验证）、超大仓库全量探索委派 `search_internal_deep`（第四角色，2026-09 加入，见下节与[架构](architecture.md)）。每个子 agent 只在真正被委派的那一次才加载工具面（按需加载）。
 - **运行中指挥。** 子 agent 运行期间，主 agent 可用 `send_message` 追加指示、`list_agents` 查看状态、`interrupt_agent` 叫停（三者由 `dsh-tool-subagent-control` 注册，属「子 agent 管理」工具面）。
 - **完成后只集成摘要。** 主 agent 从不把子 agent 的完整上下文倒进自己的上下文——它只收一份摘要（见第 5 节「上下文隔离」）。
 
@@ -22,7 +22,7 @@ dsh-paoding 把 DSH 从「单体 agent 全量加载工具」改造成「主 agen
 | 子 agent 管理 | `send_message` / `list_agents` / `interrupt_agent` |
 | 内部搜索（热路径） | `glob` / `grep` / `read` / `read_image` / `bash` |
 | 协调 | `todo_write` / `ask_user_question` / `get_goal` / `create_goal` / `update_goal` / `exit_plan_mode` / `job_output` / `job_list` / `job_kill` |
-| 主 agent 刻意看不到（节选，全文见 `restrict.mjs` 头注释） | `web_search`、`mcp__tavily__*`、`write` / `edit` / `str_replace_editor`、`skill`、`workflow`、`ralph`、`ssh_*`、`mcp__tablepro__*`、`describe_image`、裸 `subagent` / `subagent_fork` |
+| 主 agent 刻意看不到（节选，全文见 `restrict.mjs` 头注释） | `web_search` / `web_fetch`、`mcp__tavily__*`、`write` / `edit` / `str_replace_editor`、`skill`、`workflow`、`ralph`、`ssh_*`、`mcp__tablepro__*`、`describe_image`、裸 `subagent` / `subagent_fork` |
 
 每请求工具开销（估算，随注册面浮动）：主 agent 全量 ~16.2k tokens → 白名单后 ~5.5k；`search_external` ~3.0k / `design` ~3.3k / `implement` ~3.8k，仅在真正委派时发生（数值来源：`agent.cordis.yml` 头部注释）。
 

package/docs/orchestration_en.md

@@ -10,7 +10,7 @@ Orchestration is the core of dsh-paoding: the main agent (the orchestrator) deco
 dsh-paoding turns DSH from "a single agent that loads every tool" into "a main agent that orchestrates plus role agents that specialize". The split follows the texture of the task:
 
 - **Hot path — internal file questions are never delegated.** Finding code, chasing references, and reading files are solved by the main agent itself with its read-only tools: `glob` / `grep` / `read` / `read_image` / `bash` are all on the main-agent allow list, so there is zero delegation round-trip latency. `codegraph` in the persona copy is a host MCP tool: it is only actually available when the install-time detection finds the codegraph server and it is injected through `main_agent_extra` (see [Configuration](configuration_en.md) and [Installation](installation_en.md)).
-- **Cold path — role agents that carry only their own tools.** External research goes to `search_external` (only `web_search` + the five tavily tools + local reads); UI/frontend design goes to `design` (reads references, loads design skills, produces specs, never writes final code); code implementation goes to `implement` (read context → surgical change → verify); whole-repo deep exploration goes to `search_internal_deep` (a fourth role added 2026-09, see next section and [Architecture](architecture_en.md)). Each subagent is paid for only the run in which it is actually used (pay-per-use).
+- **Cold path — role agents that carry only their own tools.** External research goes to `search_external` (only `web_search` / `web_fetch` + the five tavily tools + local reads); UI/frontend design goes to `design` (reads references, loads design skills, produces specs, never writes final code); code implementation goes to `implement` (read context → surgical change → verify); whole-repo deep exploration goes to `search_internal_deep` (a fourth role added 2026-09, see next section and [Architecture](architecture_en.md)). Each subagent is paid for only the run in which it is actually used (pay-per-use).
 - **Directing a running child.** While a subagent runs, the main agent can append instructions with `send_message`, inspect status with `list_agents`, and stop it with `interrupt_agent` (all three are registered by `dsh-tool-subagent-control` and belong to the "child management" surface).
 - **Integrate summaries only.** The main agent never dumps a child's full context into its own — it receives one summary (see section 5, Context isolation).
 
@@ -22,7 +22,7 @@ The main agent's model-facing surface is narrowed by `restrict.mjs` on the `syst
 | Child management | `send_message` / `list_agents` / `interrupt_agent` |
 | Internal search (hot path) | `glob` / `grep` / `read` / `read_image` / `bash` |
 | Coordination | `todo_write` / `ask_user_question` / `get_goal` / `create_goal` / `update_goal` / `exit_plan_mode` / `job_output` / `job_list` / `job_kill` |
-| Deliberately hidden from the main agent (excerpt; full list in the `restrict.mjs` header comment) | `web_search`, `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`, `workflow`, `ralph`, `ssh_*`, `mcp__tablepro__*`, `describe_image`, bare `subagent` / `subagent_fork` |
+| Deliberately hidden from the main agent (excerpt; full list in the `restrict.mjs` header comment) | `web_search` / `web_fetch`, `mcp__tavily__*`, `write` / `edit` / `str_replace_editor`, `skill`, `workflow`, `ralph`, `ssh_*`, `mcp__tablepro__*`, `describe_image`, bare `subagent` / `subagent_fork` |
 
 Per-request tool tax (estimates; they float with the registered surface): full monolithic main agent ~16.2k tokens → ~5.5k after the allow list; `search_external` ~3.0k / `design` ~3.3k / `implement` ~3.8k, incurred only when actually delegated (figures from the header comment of `agent.cordis.yml`).
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "dsh-paoding",
-  "version": "0.4.4",
+  "version": "0.4.5",
   "description": "庖丁 — DSH (DeepSeek Harness) 编排模式安装器：host 感知的角色工具过滤 + Web 设置页可视化配置器",
   "type": "module",
   "license": "MIT",
@@ -20,7 +20,8 @@
     "cordis.patch.yml"
   ],
   "engines": {
-    "node": ">=18"
+    "node": ">=18",
+    "dsh": ">=0.1.5 <0.3"
   },
   "peerDependencies": {
     "@deepseek-ai/dsh": ">=0.1.5"

package/plugins/paoding-config-ui/icon.svg

@@ -0,0 +1,8 @@
+<svg xmlns="http://www.w3.org/2000/svg" viewBox="0 0 64 64">
+  <rect width="64" height="64" rx="14" fill="#4D6BFE"/>
+  <g transform="rotate(-45 32 32)">
+    <rect x="14" y="11" width="32" height="22" rx="3" fill="#FFFFFF"/>
+    <circle cx="41" cy="16.5" r="2" fill="#4D6BFE"/>
+    <rect x="44" y="17" width="13" height="10" rx="4" fill="#FFFFFF" opacity="0.85"/>
+  </g>
+</svg>

package/plugins/paoding-config-ui/index.mjs

@@ -42,7 +42,7 @@ import { fileURLToPath } from 'node:url'
 import { getState, refreshState, isStateCacheStale, serializeState, installAssignments, resolveDshHome, discoverWorkspaceCandidates, ensurePresetInstalled, pluginVersion, exportConfigPayload, importConfigContent, listPresets, resolveWorkspacePathByPresetId, deleteWorkspacePreset } from './api-core.mjs'
 import { collectModelRefs } from '../../tools/lib/health.mjs'
 import { detectSkills } from '../../tools/lib/skills.mjs'
-import { collectRuntimeFacts } from './runtime-inventory.mjs'
+import { collectRuntimeFacts, detectHmrOf } from './runtime-inventory.mjs'
 import { getVersionInfo } from '../../tools/lib/version.mjs'
 import { runUpgrade } from '../../tools/lib/upgrade.mjs'
 
@@ -694,7 +694,15 @@ export async function apply(ctx) {
           // 200 + error 字段，面板据此静默降级（不打扰使用）。timeoutMs 3000：
           // 检测只是锦上添花，不值得让面板等更久。layout 告知客户端挂载形态
           //（升级确认框按此分流警示文案），见 MOUNT_LAYOUT 注释。
-          json(res, 200, { ...(await getVersionInfo({ timeoutMs: 3000 })), layout: MOUNT_LAYOUT })
+          // hotReloadable：宿主插件清单里有启用的 dsh-hmr 插件行（0.2.1+ web/
+          // desktop 默认）→ 升级后刷新页面即生效，确认框 / 成功 note 换
+          // 「刷新即生效」文案；探测失败 / 非 web 部署拿不到运行时 → false，
+          // 回落「需重启 DSH」文案。永不抛出（detectHmrOf 自捕）。
+          json(res, 200, {
+            ...(await getVersionInfo({ timeoutMs: 3000 })),
+            layout: MOUNT_LAYOUT,
+            hotReloadable: detectHmrOf(ctx),
+          })
           return
         }
 

package/plugins/paoding-config-ui/lib/client.js

@@ -449,8 +449,10 @@ window.__ModuleLoader__.load({
       "menu.upgradeConfirm": { zh: "升级", en: "Upgrade" },
       "menu.upgradeDevBody": { zh: "当前为开发 link 直连形态：无法就地升级，请手动执行 dsh plugin add dsh-paoding@latest 切换到 registry 版本。仍要继续尝试吗？", en: "This is a dev link checkout: it cannot be upgraded in place. Run dsh plugin add dsh-paoding@latest manually to switch to the registry version. Continue anyway?" },
       "menu.upgradeBody": { zh: "确定升级到 {v}？升级将通过插件通道原地换版本，完成后需重启 DSH 生效。", en: "Upgrade to {v}? The upgrade swaps the version in place through the plugin channel; restart DSH afterwards to apply it." },
+      "menu.upgradeBodyHot": { zh: "确定升级到 {v}？升级将通过插件通道原地换版本，完成后刷新页面即生效（编排预设自动按新版重生成）。", en: "Upgrade to {v}? The upgrade swaps the version in place through the plugin channel; refresh the page afterwards — orchestration presets regenerate automatically." },
       "menu.upToDate": { zh: "已是最新版本", en: "Already up to date" },
       "menu.upgraded": { zh: "✅ 已升级到 {v}，重启 DSH 后新版本生效（preset 会自动按新版重生成）", en: "✅ Upgraded to {v} — restart DSH to apply the new version (the preset regenerates itself against it)" },
+      "menu.upgradedHot": { zh: "✅ 已升级到 {v}，刷新页面即生效（preset 会自动按新版重生成）", en: "✅ Upgraded to {v} — refresh the page to apply (the preset regenerates itself against it)" },
       "menu.errTail": { zh: "：{tail}", en: ": {tail}" },
       "menu.langTip": { zh: "切换界面语言", en: "Switch UI language" },
     };
@@ -3679,15 +3681,22 @@ window.__ModuleLoader__.load({
     // 改通用确认弹窗，confirmCtrl 单例见 70 片段）文案按挂载形态分流：
     // dev link 直连形态（layout 由服务端 version 路由按包根 .git 判定）无法
     // 就地升级，把手动切换命令说在前头；installed（registry 版）原地换版本，
-    // 从简。反馈（成功 note / 失败 err，含子进程输出尾部）都收在卡内，不与
+    // 按宿主热重载能力（version 路由 hotReloadable：插件清单里有启用的
+    // dsh-hmr 行）再分两级——有则「刷新页面即生效」，无则「重启 DSH 生效」。
+    // 反馈（成功 note / 失败 err，含子进程输出尾部）都收在卡内，不与
     // 面板的 toast 反馈混流。升级非破坏性操作，danger 不置位；弹窗本体由
     // PageShell 末尾的 ConfirmLayer 渲染（页头与面板发起的确认共用一层）。
     function runUpgradeFlow(verInfo, setVerInfo, setUpgBusy, setUpgNote, setUpgErr) {
       if (!verInfo || !verInfo.latest) return;
       var isDev = verInfo.layout === "dev";
+      // 二级分流：宿主插件清单里有启用的 dsh-hmr 插件行（0.2.1+ web/desktop
+      // 发布 profile 默认带上，version 路由的 hotReloadable 字段）时，插件
+      // 通道原地换版本后刷新页面即生效，无需重启 DSH——确认框与成功 note
+      // 都换「刷新即生效」文案；字段缺失 / 探测失败回落「需重启」文案。
+      var hot = verInfo.hotReloadable === true;
       var msg = isDev
         ? t("menu.upgradeDevBody")
-        : t("menu.upgradeBody", { v: versionTagOf(verInfo.latest) });
+        : t(hot ? "menu.upgradeBodyHot" : "menu.upgradeBody", { v: versionTagOf(verInfo.latest) });
       confirmCtrl.ask({
         title: t("menu.upgradeTitle"),
         body: msg,
@@ -3702,7 +3711,7 @@ window.__ModuleLoader__.load({
             var done = versionTagOf((r && r.version) || verInfo.latest);
             // 服务端返回了 message 就原文透传（服务端消息不做客户端翻译），
             // 没有才落本地化兜底文案。
-            setUpgNote((r && r.message) || t("menu.upgraded", { v: done }));
+            setUpgNote((r && r.message) || t(hot ? "menu.upgradedHot" : "menu.upgraded", { v: done }));
             // 重拉版本信息：服务端有 1 小时缓存且本进程挂的还是旧代码，重启前
             // 更新卡可能仍在（重启后自然消失），以此处的生效提示为准。
             paodingApi("version").then(function (d) {

package/plugins/paoding-config-ui/package.json

@@ -1,10 +1,15 @@
 {
   "name": "paoding-config-ui",
-  "version": "0.4.4",
+  "version": "0.4.5",
   "private": true,
   "type": "module",
   "main": "index.mjs",
-  "description": "庖丁 (dsh-paoding) 可视化配置器 — DSH Web 左侧栏全页配置插件（侧栏入口 + /api/paoding 路由）",
+  "icon": "./icon.svg",
+  "description": "庖丁 (dsh-paoding) 可视化配置器 — DSH Web 左侧栏全页配置插件（侧栏入口 + /api/paoding 路由）· Visual config panel for dsh-paoding in the DSH Web sidebar",
+  "engines": {
+    "node": ">=18",
+    "dsh": ">=0.1.5 <0.3"
+  },
   "dsh": {
     "client": {
       "platform": "web",

package/plugins/paoding-config-ui/runtime-inventory.mjs

@@ -206,6 +206,28 @@ function detectPresetSystemOf(ctx) {
   }
 }
 
+/**
+ * 宿主热重载能力探测：插件清单里存在 @deepseek-ai/dsh-hmr 插件行（dsh
+ * 0.2.1+ 的 web / desktop 发布 profile 默认带上）且已启用，即认为宿主支持
+ * 插件热重载——面板升级（插件通道原地换版本）完成后刷新页面即生效，无需
+ * 重启 DSH。取数复用 collectPluginEntries 的路径（getService
+ * ('pluginInventory') → list() → entries）；服务缺席 / 形状异常 / 任何异常
+ * 一律 false（安全侧：回落「需重启」文案），永不抛出。
+ */
+export function detectHmrOf(ctx) {
+  try {
+    const { entries, ok } = collectPluginEntries(ctx, [])
+    if (!ok) return false
+    // collectPluginEntries 已剔除 enabled===false 的条目，此处再判一次仅为
+    // 兑现判定语义（enabled!==false）；moduleName / entryId 任一含 'dsh-hmr'
+    // 即命中（不同宿主版本两字段的命名习惯有差异，取并集）。
+    return entries.some((e) => e.enabled !== false
+      && (e.moduleName?.includes('dsh-hmr') || e.entryId?.includes('dsh-hmr')))
+  } catch {
+    return false
+  }
+}
+
 /**
  * 采集运行时事实（供 collectState 合并 / UI 展示）。
  * 永不抛出：任何异常都会落到 error 里，返回部分结果。

package/presets/orchestrator/agent.cordis.yml

@@ -243,11 +243,12 @@
         toolName: search_external
         backgroundMode: one-shot
         persona: |-
-          You are the external-research agent. Your job is web research only — use web_search and the tavily tools; you never modify files. Search the web, extract key facts, and return a concise structured research summary (findings, sources, open questions).
+          You are the external-research agent. Your job is web research only — use web_search, web_fetch and the tavily tools; you never modify files. Search the web, extract key facts, and return a concise structured research summary (findings, sources, open questions).
           On tool failure, do not retry a denied operation: report the failure compactly — what you completed, the exact error, which tool/permission you lack, and your suggested next step — so the orchestrator can re-delegate or adjust.
         toolFilter:
           allow:
             - web_search
+            - web_fetch
             - mcp__tavily__tavily_search
             - mcp__tavily__tavily_crawl
             - mcp__tavily__tavily_extract

package/presets/orchestrator/restrict.mjs

@@ -24,7 +24,7 @@
  * 停用即自动清除。本文件只保留 dsh 核心工具。
  *
  * What the main agent deliberately does NOT see (all costs drop to zero for
- * its requests): web_search, every mcp__tavily__*, write / edit /
+ * its requests): web_search, web_fetch, every mcp__tavily__*, write / edit /
  * str_replace_editor, skill (+ its ~1.3k-token catalog), workflow, ralph,
  * ssh_*, mcp__tablepro__*, describe_image, and the unfiltered subagent /
  * subagent_fork delegations.