Update config.yaml

Add files via upload
2026-08-01 16:38:48 +02:00 · 2026-07-06 17:45:27 +08:00 · 2026-07-06 17:27:29 +08:00 · 2026-07-06 17:00:03 +08:00 · 2026-07-06 16:50:05 +08:00 · 2026-07-06 16:27:34 +08:00
239 changed files with 39551 additions and 3176 deletions
@@ -35,7 +35,18 @@ CyberStrikeAI is an **AI-native security testing platform** built in Go. It inte

 ### System Dashboard Overview

-<img src="./images/dashboard.png" alt="System Dashboard" width="100%">
+<table>
+<tr>
+<td width="50%" align="center">
+<strong>Light Mode</strong><br/>
+<img src="./images/dashboard.png" alt="System Dashboard (Light)" width="100%">
+</td>
+<td width="50%" align="center">
+<strong>Dark Mode</strong><br/>
+<img src="./images/dark.png" alt="System Dashboard (Dark)" width="100%">
+</td>
+</tr>
+</table>

 *The dashboard provides a comprehensive overview of system runtime status, security vulnerabilities, tool usage, and knowledge base, helping users quickly understand the platform's core features and current state.*

@@ -110,16 +121,17 @@ CyberStrikeAI is an **AI-native security testing platform** built in Go. It inte
 - 📄 Large-result pagination, compression, and searchable archives
 - 🔗 Attack-chain graph, risk scoring, and step-by-step replay
 - 🔒 Password-protected web UI, audit logs, and SQLite persistence
- 📚 Knowledge base (RAG) with embedding-based vector retrieval (cosine similarity), optional **Eino Compose** indexing pipeline, and configurable post-retrieval budgets / reranking hooks
+- 📚 Knowledge base (RAG): **Eino MultiQuery** query rewrite + multi-path vector retrieval + **HTTP rerank** (DashScope `gte-rerank` / Cohere-compatible) + post-processing (dedupe, budget); **Eino Compose** indexing pipeline
 - 📁 Conversation grouping with pinning, rename, and batch management
- 📂 **Project management**: group conversations and vulnerabilities by project; **shared facts** (project blackboard) persist cross-session context (targets, env, auth notes) with auto-injection for agents and MCP tools (`upsert_project_fact`, `get_project_fact`, …)
+- 📂 **Project management**: shared facts (blackboard) across sessions, `upsert_project_fact` + `links` to chain paths; attack-chain and project fact graph views
 - 🛡️ Vulnerability management with CRUD operations, severity tracking, status workflow, and statistics
 - 📋 Batch task management: create task queues, add multiple tasks, and execute them sequentially
 - 🎭 Role-based testing: predefined security testing roles (Penetration Testing, CTF, Web App Scanning, etc.) with custom prompts and tool restrictions
+- 🔀 **Graph orchestration**: visual workflow editor (Start / Agent / Tool / Condition / HITL / Output) with `{{previous.output}}` and `{{outputs.variable_name}}` for inter-node data passing; bind a graph to a role for automatic execution on chat. See [Graph orchestration guide](docs/workflow-graph_en.md)
 - 🧩 **Agent orchestration (CloudWeGo Eino)**: **single-agent** via **`/api/eino-agent/stream`** (Eino ADK `ChatModelAgent`); **multi-agent** via **`/api/multi-agent/stream`** with **`deep`** (coordinator + `task` sub-agents), **`plan_execute`**, or **`supervisor`** (`orchestration` in the request body). ADK **summarization** compresses long contexts; pre-compaction **transcripts** land at `data/conversation_artifacts/<conversation-id>/summarization/transcript.txt` (full user/assistant/tool turns; static system omitted). Markdown under `agents/`: `orchestrator.md`, `orchestrator-plan-execute.md`, `orchestrator-supervisor.md`, plus sub-agent `*.md` (see [Multi-agent doc](docs/MULTI_AGENT_EINO.md))
 - 🖼️ **Vision analysis (`analyze_image`)**: separate VL model (e.g. `qwen-vl-max`) via MCP for local screenshots, captchas, and UI; image bytes stay out of agent history (text summaries only). Configure `vision` in `config.yaml`; see [docs/VISION.md](docs/VISION.md)
 - 🎯 **Skills (refactored for Eino)**: packs under `skills_dir` follow **Agent Skills** layout (`SKILL.md` + optional files); **multi-agent** sessions use the official Eino ADK **`skill`** tool for **progressive disclosure** (load by name), with optional **host filesystem / shell** via `multi_agent.eino_skills`; optional **`eino_middleware`** adds patchtoolcalls, tool_search, **plantask** (`TaskCreate` / `TaskList` boards under `skills_dir/.eino/plantask/`), reduction, file **checkpoints** (`checkpoint_dir`), ChatModel **retries**, session **output key**, and Deep tuning—20+ sample domains (SQLi, XSS, API security, …) ship under `skills/`
- 📱 **Chatbot**: DingTalk and Lark (Feishu) long-lived connections so you can talk to CyberStrikeAI from mobile (see [Robot / Chatbot guide](docs/robot_en.md) for setup and commands)
+- 📱 **Chatbot**: Personal WeChat, WeCom, DingTalk, Lark, Telegram, Slack, Discord, and QQ Bot—chat from mobile or IM apps (see [Robot / Chatbot guide](docs/robot_en.md))
 - 🧑‍⚖️ **Human-in-the-loop (HITL)**: Chat sidebar to set approval mode and tool allowlists (listed tools skip approval); global list in `config.yaml` under `hitl.tool_whitelist`; **Apply** can merge new tools into the file and update the running server without restart; dedicated **HITL** page for pending approvals
 - 🐚 **WebShell management**: Add and manage WebShell connections (e.g. IceSword/AntSword compatible), use a virtual terminal for command execution, a built-in file manager for file operations, and an AI assistant tab that orchestrates tests and keeps per-connection conversation history; supports PHP, ASP, ASPX, JSP and custom shell types with configurable request method and command parameter.
 - 📡 **Built-in C2**: AI-oriented lightweight command-and-control—**listeners** (TCP reverse, HTTP/HTTPS beacon, WebSocket), **encrypted** beacon channel, **session** and **task** queues with persistence, **payload** helpers (one-liner / build / download), **SSE** live events, REST under `/api/c2/*`, plus unified MCP tools (`c2_listener`, `c2_session`, **`c2_task`**, `c2_task_manage`, `c2_payload`, `c2_event`, `c2_profile`, `c2_file`); optional **HITL** approval for sensitive operations and OPSEC-style controls (e.g. command deny rules). **Authorized testing only.**
@@ -244,6 +256,7 @@ Requirements / tips:
 - **Conversation testing** – Natural-language prompts trigger toolchains with streaming SSE output.
 - **Single vs multi-agent** – Chat UI switches between **Eino single-agent** (`/api/eino-agent/stream`) and **multi-agent** (`/api/multi-agent/stream` with `orchestration`: `deep` | `plan_execute` | `supervisor`). Multi mode requires `multi_agent.enabled: true`. MCP tools are bridged the same way for both paths.
 - **Role-based testing** – Select from predefined security testing roles (Penetration Testing, CTF, Web App Scanning, API Security Testing, etc.) to customize AI behavior and tool availability. Each role applies custom system prompts and can restrict available tools for focused testing scenarios.
+- **Graph orchestration** – Design flows on the **Graph Orchestration** page (drag nodes, connect edges, save); bind `workflow_id` on a role to run the graph on chat (Agent, MCP tools, condition branches). Use `{{outputs.variable_name}}` to pass data across non-adjacent nodes. See [Graph orchestration guide](docs/workflow-graph_en.md).
 - **Tool monitor** – Inspect running jobs, execution logs, and large-result attachments.
 - **History & audit** – Every conversation and tool invocation is stored in SQLite with replay.
 - **Conversation groups** – Organize conversations into groups, pin important groups, rename or delete groups via context menu.
@@ -286,11 +299,11 @@ Requirements / tips:
 2. Restart the server or reload configuration; the role appears in the role selector dropdown.

 ### Multi-Agent Mode (Eino: Deep, Plan-Execute, Supervisor)
- **What it is** – Multi-agent orchestration on CloudWeGo **Eino** `adk/prebuilt` (alongside **Eino single-agent** on `/api/eino-agent*`): **`deep`** — coordinator + **`task`** sub-agents; **`plan_execute`** — planner / executor / replanner; **`supervisor`** — orchestrator with **`transfer`** / **`exit`**. Client sends **`orchestration`**: `deep` | `plan_execute` | `supervisor` (default `deep`).
+- **What it is** – Multi-agent orchestration on CloudWeGo **Eino** `adk/prebuilt` (alongside **Eino single-agent** on `/api/eino-agent*`): **`deep`** — coordinator + **`task`** sub-agents for complex security testing and delegated synthesis; **`plan_execute`** — planner / executor / replanner for structured loops; **`supervisor`** — expert-routing mode with **`transfer`** / **`exit`** for multiple specialist sub-agents. Client sends **`orchestration`**: `deep` | `plan_execute` | `supervisor` (default `deep`).
 - **Markdown agents** – Under `agents_dir` (default `agents/`):
  - **Deep orchestrator**: `orchestrator.md` *or* one `.md` with `kind: orchestrator`. Body or `multi_agent.orchestrator_instruction`, then Eino defaults.
  - **Plan-Execute orchestrator**: fixed name **`orchestrator-plan-execute.md`** (plus optional `orchestrator_instruction_plan_execute` in YAML).
-  - **Supervisor orchestrator**: fixed name **`orchestrator-supervisor.md`** (plus optional `orchestrator_instruction_supervisor`); requires at least one sub-agent.
+  - **Supervisor orchestrator**: fixed name **`orchestrator-supervisor.md`** (plus optional `orchestrator_instruction_supervisor`); requires at least one sub-agent, and one-sub-agent runs emit a hint that expert routing has limited value.
  - **Sub-agents** (for **deep** / **supervisor**): other `*.md` files (YAML front matter + body). Not used as **`task`** targets if marked orchestrator-only.
 - **Management** – Web UI: **Agents → Agent management**; API `/api/multi-agent/markdown-agents`.
 - **Config** – `multi_agent` in `config.yaml`: `enabled`, `robot_default_agent_mode`, `batch_use_multi_agent`, `max_iteration`, `plan_execute_loop_max_iterations`, per-mode orchestrator instruction fields, optional YAML `sub_agents` merged with disk (`id` clash → Markdown wins), **`eino_skills`**, **`eino_middleware`** (optional ADK middleware and Deep/Supervisor tuning).
@@ -455,16 +468,12 @@ A test SSE MCP server is available at `cmd/test-sse-mcp-server/` for validation

 ### Knowledge Base
 - **Vector search** – AI agent can automatically search the knowledge base for relevant security knowledge during conversations using the `search_knowledge_base` tool.
- **Vector retrieval** – cosine similarity over stored embeddings, aligned with Eino `retriever.Retriever` usage.
- **Auto-indexing** – scans the `knowledge_base/` directory for Markdown files and automatically indexes them with embeddings.
- **Web management** – create, update, delete knowledge items through the web UI, with category-based organization.
+- **RAG pipeline (always on)** – **MultiQuery** (LLM query rewrite) → vector prefetch & fusion → **HTTP rerank** (DashScope `gte-rerank` or Cohere-compatible `/v1/rerank`) → post-processing (normalized dedupe, char/token budget, final top_k). Rerank failures degrade to fusion order without breaking search.
+- **Vector retrieval** – cosine similarity over stored embeddings with configurable threshold, aligned with Eino `retriever.Retriever` usage.
+- **Auto-indexing** – scans the `knowledge_base/` directory for Markdown files and automatically indexes them with embeddings (Markdown header split + recursive chunking via Eino).
+- **Web management** – create, update, delete knowledge items through the web UI, with category-based organization; settings page exposes MultiQuery / rerank / prefetch options.
 - **Retrieval logs** – tracks all knowledge retrieval operations for audit and debugging.

-**Quick Start (Using Pre-built Knowledge Base):**
-1. **Download the knowledge database** – Download the pre-built knowledge database file from [GitHub Releases](https://github.com/Ed1s0nZ/CyberStrikeAI/releases).
-2. **Extract and place** – Extract the downloaded knowledge database file (`knowledge.db`) and place it in the project's `data/` directory.
-3. **Restart the service** – Restart the CyberStrikeAI service, and the knowledge base will be ready to use immediately without rebuilding the index.
-
 **Setting up the knowledge base:**
 1. **Enable in config** – set `knowledge.enabled: true` in `config.yaml`:
   ```yaml
@@ -479,6 +488,17 @@ A test SSE MCP server is available at `cmd/test-sse-mcp-server/` for validation
     retrieval:
       top_k: 5
       similarity_threshold: 0.7
+       multi_query:
+         max_queries: 4        # LLM rewrite variants (always on)
+       rerank:                 # always on; empty fields inherit openai/embedding credentials
+         provider: ""          # auto: dashscope | cohere from base_url
+         model: ""             # empty: gte-rerank (DashScope) or rerank-multilingual-v3.0 (Cohere)
+         base_url: ""
+         api_key: ""
+       post_retrieve:
+         prefetch_top_k: 20    # vector candidates per MultiQuery variant; 0 = max(top_k×4, 20)
+         max_context_chars: 0
+         max_context_tokens: 0
   ```
 2. **Add knowledge files** – place Markdown files in `knowledge_base/` directory, organized by category (e.g., `knowledge_base/SQL Injection/README.md`).
 3. **Scan and index** – use the web UI to scan the knowledge base directory, which will automatically import files and build vector embeddings.
@@ -539,6 +559,17 @@ knowledge:
  retrieval:
    top_k: 5  # Number of top results to return
    similarity_threshold: 0.7  # Minimum cosine similarity (0-1)
+    multi_query:
+      max_queries: 4  # MultiQuery rewrite variants (always on)
+    rerank:  # HTTP rerank (always on); empty fields inherit openai/embedding credentials
+      provider: ""
+      model: ""
+      base_url: ""
+      api_key: ""
+    post_retrieve:
+      prefetch_top_k: 20  # per MultiQuery variant; 0 = max(top_k×4, 20)
+      max_context_chars: 0
+      max_context_tokens: 0
 roles_dir: "roles"  # Role configuration directory (relative to config file)
 skills_dir: "skills"  # Skills directory (relative to config file)
 agents_dir: "agents"  # Multi-agent Markdown definitions (orchestrator + sub-agents)
@@ -551,6 +582,11 @@ multi_agent:
  # orchestrator_instruction_plan_execute / orchestrator_instruction_supervisor optional
  # eino_skills: { disable: false, filesystem_tools: true, skill_tool_name: skill }
  # eino_middleware: plantask_enable, checkpoint_dir, deep_model_retry_max_retries, deep_output_key, ...
+project:
+  enabled: true              # Enable project blackboard & fact MCP tools
+  fact_index_max_runes: 65000
+  fact_summary_max_runes: 24000
+  default_inject_deprecated: false
 ```

 ### Tool Definition Example (`tools/nmap.yaml`)
@@ -596,7 +632,8 @@ enabled: true
 ## Related documentation

 - [Multi-agent mode (Eino)](docs/MULTI_AGENT_EINO.md): **Deep**, **Plan-Execute**, **Supervisor**, `agents/*.md`, `eino_skills` / `eino_middleware`, APIs, and chat/stream behavior.
- [Robot / Chatbot guide (DingTalk & Lark)](docs/robot_en.md): Full setup, commands, and troubleshooting for using CyberStrikeAI from DingTalk or Lark on your phone. **Follow this doc to avoid common pitfalls.**
+- [Graph orchestration guide](docs/workflow-graph_en.md): visual workflow design, node configuration, `previous` / `outputs` variable passing, and role binding.
+- [Robot / Chatbot guide](docs/robot_en.md): Setup, commands, and troubleshooting for WeChat, WeCom, DingTalk, Lark, Telegram, Slack, Discord, and QQ Bot.

 ## Project Layout

@@ -648,8 +685,6 @@ CyberStrikeAI has joined [404Starlink](https://github.com/knownsec/404StarLink)
  </a>
 </div>

-## Stargazers over time
-![Stargazers over time](https://starchart.cc/Ed1s0nZ/CyberStrikeAI.svg)


 ---
@@ -678,5 +713,3 @@ CyberStrikeAI is a professional security testing platform designed to assist sec
 ---

 Need help or want to contribute? Open an issue or PR—community tooling additions are welcome!
-
-
@@ -34,7 +34,18 @@ CyberStrikeAI 是一款 **AI 原生安全测试平台**，基于 Go 构建，集

 ### 系统仪表盘概览

-<img src="./images/dashboard.png" alt="系统仪表盘" width="100%">
+<table>
+<tr>
+<td width="50%" align="center">
+<strong>浅色模式</strong><br/>
+<img src="./images/dashboard.png" alt="系统仪表盘（浅色）" width="100%">
+</td>
+<td width="50%" align="center">
+<strong>深色模式</strong><br/>
+<img src="./images/dark.png" alt="系统仪表盘（深色）" width="100%">
+</td>
+</tr>
+</table>

 *仪表盘提供系统运行状态、安全漏洞、工具使用情况和知识库的全面概览，帮助用户快速了解平台核心功能和当前状态。*

@@ -109,16 +120,17 @@ CyberStrikeAI 是一款 **AI 原生安全测试平台**，基于 Go 构建，集
 - 📄 大结果分页、压缩与全文检索
 - 🔗 攻击链可视化、风险打分与步骤回放
 - 🔒 Web 登录保护、审计日志、SQLite 持久化
- 📚 知识库（RAG）：向量嵌入与余弦相似度检索（与 Eino `retriever.Retriever` 语义一致），可选 **Eino Compose** 索引流水线及检索后处理（预算、重排等配置项）
+- 📚 知识库（RAG）：**Eino MultiQuery** 查询改写 + 多路向量检索 + **HTTP 精排**（DashScope `gte-rerank` / Cohere 兼容）+ 后处理（去重、预算）；索引侧为 **Eino Compose** 流水线
 - 📁 对话分组管理：支持分组创建、置顶、重命名、删除等操作
- 📂 **项目管理**：按项目归类对话与漏洞；**共享事实**（项目黑板）在多会话间沉淀目标/环境/认证等认知，自动注入 Agent 上下文，支持 MCP 工具读写（`upsert_project_fact`、`get_project_fact` 等）
+- 📂 **项目管理**：共享事实（黑板）跨会话沉淀认知，`upsert_project_fact` + `links` 串联攻击路径；聊天攻击链与项目事实图可视化
 - 🛡️ 漏洞管理功能：完整的漏洞 CRUD 操作，支持严重程度分级、状态流转、按对话/严重程度/状态过滤，以及统计看板
 - 📋 批量任务管理：创建任务队列，批量添加任务，依次顺序执行，支持任务编辑与状态跟踪
 - 🎭 角色化测试：预设安全测试角色（渗透测试、CTF、Web 应用扫描等），支持自定义提示词和工具限制
+- 🔀 **图编排**：可视化流程编排（开始 / Agent / 工具 / 条件 / 审批 / 输出），节点间用 `{{previous.output}}` 或 `{{outputs.变量名}}` 传参；绑定角色后对话自动按图执行。详见 [图编排使用说明](docs/workflow-graph.md)
 - 🧩 **Agent 编排（CloudWeGo Eino）**：**单代理** `POST /api/eino-agent/stream`（Eino ADK）；**多代理** `POST /api/multi-agent/stream`，`orchestration` 选 **`deep`** / **`plan_execute`** / **`supervisor`**。ADK **Summarization** 在上下文过长时压缩历史；压缩前将可恢复 **转录** 写入 `data/conversation_artifacts/<会话ID>/summarization/transcript.txt`（保留完整 user/assistant/tool 轮次，省略静态 system）。`agents/` 下主代理与子代理 Markdown 见 [多代理说明](docs/MULTI_AGENT_EINO.md)
 - 🖼️ **视觉分析（`analyze_image`）**：独立 Vision 模型（如 `qwen-vl-max`），MCP 工具分析本地截图/验证码/UI；图片仅在单次 VL 调用中出现，对话上下文只保留文字摘要。配置见 `config.yaml` → `vision` 与 [视觉分析说明](docs/VISION.md)
 - 🎯 **Skills（面向 Eino 重构）**：技能包放在 **`skills_dir`**，遵循 **Agent Skills** 目录规范（`SKILL.md` + 可选文件）；**多代理** 下通过 Eino 官方 **`skill`** 工具 **渐进式披露**（按 name 加载）。**`multi_agent.eino_skills`** 控制是否启用、本机文件/Shell 工具、工具名覆盖；**`eino_middleware`** 可选 patch、tool_search、**plantask**（`TaskCreate` / `TaskList` 任务板，落在 `skills_dir/.eino/plantask/`）、reduction、文件型 **checkpoint**（`checkpoint_dir`）、ChatModel **重试**、会话 **输出键** 及 Deep 调参。20+ 领域示例仍可绑定角色
- 📱 **机器人**：支持钉钉、飞书长连接，在手机端与 CyberStrikeAI 对话（配置与命令详见 [机器人使用说明](docs/robot.md)）
+- 📱 **机器人**：个人微信、企业微信、钉钉、飞书、Telegram、Slack、Discord、QQ 机器人，在手机或 IM 中与 CyberStrikeAI 对话（详见 [机器人使用说明](docs/robot.md)）
 - 🧑‍⚖️ **人机协同（HITL）**：对话页侧栏配置协同模式与免审批工具白名单；全局列表在 `config.yaml` 的 `hitl.tool_whitelist`；点「应用」可将新增工具合并写入配置文件且**无需重启**即可生效；导航 **人机协同** 页处理待审批工具调用
 - 🐚 **WebShell 管理**：添加与管理 WebShell 连接（兼容冰蝎/蚁剑等），通过虚拟终端执行命令、内置文件管理进行文件操作，并提供按连接维度保存历史的 AI 助手标签页；支持 PHP/ASP/ASPX/JSP 及自定义类型，可配置请求方法与命令参数。
 - 📡 **内置 C2**：面向 AI 协同的轻量 **C2**——**多种监听器**（TCP 反向、HTTP/HTTPS Beacon、WebSocket）、**加密** Beacon 信道、**会话与任务**队列及持久化、**Payload** 辅助（一键命令 / 构建 / 下载）、**SSE** 实时事件、REST（`/api/c2/*`）及智能体侧 **一组 C2 MCP 工具**（如 `c2_listener`、`c2_session`、**`c2_task`**、`c2_task_manage`、`c2_payload`、`c2_event`、`c2_profile`、`c2_file`）；敏感操作可对接 **人机协同（HITL）**，并支持 OPSEC 类规则（如命令拒绝正则）。**仅限授权测试。**
@@ -242,6 +254,7 @@ go build -o cyberstrike-ai cmd/server/main.go
 - **对话测试**：自然语言触发多步工具编排，SSE 实时输出。
 - **单代理 / 多代理**：聊天可选 **Eino 单代理**（`/api/eino-agent/stream`）与 **多代理**（`/api/multi-agent/stream` + `orchestration`）。多代理需 `multi_agent.enabled: true`。MCP 工具桥接一致。
 - **角色化测试**：从预设的安全测试角色（渗透测试、CTF、Web 应用扫描、API 安全测试等）中选择，自定义 AI 行为和可用工具。每个角色可应用自定义系统提示词，并可限制可用工具列表，实现聚焦的测试场景。
+- **图编排**：在 **图编排** 页拖拽节点、连线并保存流程；在角色中绑定 `workflow_id` 后，该角色对话将按图执行（Agent、MCP 工具、条件分支等）。跨节点传参优先用 `{{outputs.变量名}}`。详见 [图编排使用说明](docs/workflow-graph.md)。
 - **工具监控**：查看任务队列、执行日志、大文件附件。
 - **会话历史**：所有对话与工具调用保存在 SQLite，可随时重放。
 - **对话分组**：将对话按项目或主题组织到不同分组，支持置顶、重命名、删除等操作，所有数据持久化存储。
@@ -284,11 +297,11 @@ go build -o cyberstrike-ai cmd/server/main.go
 2. 重启服务或重新加载配置，角色会出现在角色选择下拉菜单中。

 ### 多代理模式（Eino：Deep / Plan-Execute / Supervisor）
- **能力说明**：在 **Eino 单代理**（`/api/eino-agent*`）之外，多代理基于 CloudWeGo **Eino** `adk/prebuilt`：**`deep`**、**`plan_execute`**、**`supervisor`**；客户端 **`orchestration`** 选择（缺省 `deep`）。
+- **能力说明**：在 **Eino 单代理**（`/api/eino-agent*`）之外，多代理基于 CloudWeGo **Eino** `adk/prebuilt`：**`deep`**、**`plan_execute`**、**`supervisor`**；客户端 **`orchestration`** 选择（缺省 `deep`）。模式定位按 Eino ADK 最佳实践区分：**Deep** 适合复杂安全测试与 task 子代理协作；**Plan-Execute** 适合目标明确的规划 → 执行 → 重规划闭环；**Supervisor** 适合多个专业子代理动态分派的专家路由场景。
 - **Markdown 定义**（`agents_dir`，默认 `agents/`）：
  - **Deep 主代理**：`orchestrator.md` 或唯一 `kind: orchestrator` 的 `.md`；正文或 `multi_agent.orchestrator_instruction`，再回退 Eino 默认。
  - **Plan-Execute 主代理**：固定 **`orchestrator-plan-execute.md`**（另可配 `orchestrator_instruction_plan_execute`）。
-  - **Supervisor 主代理**：固定 **`orchestrator-supervisor.md`**（另可配 `orchestrator_instruction_supervisor`）；至少需一名子代理。
+  - **Supervisor 主代理**：固定 **`orchestrator-supervisor.md`**（另可配 `orchestrator_instruction_supervisor`）；至少需一名子代理，只有一名子代理时会提示专家路由价值有限。
  - **子代理**（**deep** / **supervisor**）：其余 `*.md`；标成 orchestrator 的不会进入 `task` 列表。
 - **界面管理**：**Agents → Agent 管理**；API `/api/multi-agent/markdown-agents`。
 - **配置项**：`multi_agent`：`enabled`、`robot_default_agent_mode`、`batch_use_multi_agent`、`max_iteration`、`plan_execute_loop_max_iterations`、各模式 orchestrator 指令字段、可选 YAML `sub_agents` 与目录合并（同 `id` → Markdown 优先）、**`eino_skills`**、**`eino_middleware`**。
@@ -453,16 +466,12 @@ CyberStrikeAI 支持通过三种传输模式连接外部 MCP 服务器：

 ### 知识库功能
 - **向量检索**：AI 智能体在对话过程中可自动调用 `search_knowledge_base` 工具搜索知识库中的安全知识。
- **向量检索**：基于嵌入余弦相似度与相似度阈值过滤（与 Eino `retriever.Retriever` 语义一致）。
- **自动索引**：扫描 `knowledge_base/` 目录下的 Markdown 文件，自动构建向量嵌入索引。
- **Web 管理**：通过 Web 界面创建、更新、删除知识项，支持分类管理。
+- **RAG 管线（始终启用）**：**MultiQuery**（LLM 查询改写）→ 向量预取与融合 → **HTTP 精排**（DashScope `gte-rerank` 或 Cohere 兼容 `/v1/rerank`）→ 后处理（规范化去重、字符/token 预算、最终 top_k）。精排失败时自动降级为融合排序，检索仍可用。
+- **向量相似度**：基于嵌入余弦相似度与相似度阈值过滤（与 Eino `retriever.Retriever` 语义一致）。
+- **自动索引**：扫描 `knowledge_base/` 目录下的 Markdown 文件，自动构建向量嵌入索引（Eino Markdown 标题切分 + 递归分块）。
+- **Web 管理**：通过 Web 界面创建、更新、删除知识项，支持分类管理；设置页可配置 MultiQuery / 精排 / 预取候选数。
 - **检索日志**：记录所有知识检索操作，便于审计与调试。

-**快速开始（使用预构建知识库）：**
-1. **下载知识数据库**：从 [GitHub Releases](https://github.com/Ed1s0nZ/CyberStrikeAI/releases) 下载预构建的知识数据库文件。
-2. **解压并放置**：将下载的知识数据库文件（`knowledge.db`）解压后放到项目的 `data/` 目录下。
-3. **重启服务**：重启 CyberStrikeAI 服务，知识库即可直接使用，无需重新构建索引。
-
 **知识库配置步骤：**
 1. **启用功能**：在 `config.yaml` 中设置 `knowledge.enabled: true`：
   ```yaml
@@ -477,6 +486,17 @@ CyberStrikeAI 支持通过三种传输模式连接外部 MCP 服务器：
     retrieval:
       top_k: 5
       similarity_threshold: 0.7
+       multi_query:
+         max_queries: 4        # LLM 改写变体上限（始终启用）
+       rerank:                 # 精排始终启用；留空则继承 openai/embedding 凭据
+         provider: ""          # 空=按 base_url 推断 dashscope | cohere
+         model: ""             # 空=DashScope→gte-rerank，Cohere→rerank-multilingual-v3.0
+         base_url: ""
+         api_key: ""
+       post_retrieve:
+         prefetch_top_k: 20    # 每条 MultiQuery 变体的向量候选数；0=max(top_k×4, 20)
+         max_context_chars: 0
+         max_context_tokens: 0
   ```
 2. **添加知识文件**：将 Markdown 文件放入 `knowledge_base/` 目录，按分类组织（如 `knowledge_base/SQL注入/README.md`）。
 3. **扫描索引**：在 Web 界面中点击"扫描知识库"，系统会自动导入文件并构建向量索引。
@@ -537,6 +557,17 @@ knowledge:
  retrieval:
    top_k: 5  # 检索返回的 Top-K 结果数量
    similarity_threshold: 0.7  # 余弦相似度阈值（0-1），低于此值的结果将被过滤
+    multi_query:
+      max_queries: 4  # MultiQuery 改写变体上限（始终启用）
+    rerank:  # HTTP 精排（始终启用）；留空则继承 openai/embedding 凭据
+      provider: ""
+      model: ""
+      base_url: ""
+      api_key: ""
+    post_retrieve:
+      prefetch_top_k: 20  # 每条 MultiQuery 变体；0=max(top_k×4, 20)
+      max_context_chars: 0
+      max_context_tokens: 0
 roles_dir: "roles"  # 角色配置文件目录（相对于配置文件所在目录）
 skills_dir: "skills"  # Skills 目录（相对于配置文件所在目录）
 agents_dir: "agents"  # 多代理 Markdown（主代理 orchestrator.md + 子代理 *.md）
@@ -549,6 +580,11 @@ multi_agent:
  # orchestrator_instruction_plan_execute / orchestrator_instruction_supervisor 可选
  # eino_skills: { disable: false, filesystem_tools: true, skill_tool_name: skill }
  # eino_middleware: plantask_enable、checkpoint_dir、deep_model_retry_max_retries、deep_output_key 等
+project:
+  enabled: true              # 启用项目黑板与事实 MCP 工具
+  fact_index_max_runes: 65000
+  fact_summary_max_runes: 24000
+  default_inject_deprecated: false
 ```

 ### 工具模版示例（`tools/nmap.yaml`）
@@ -594,7 +630,8 @@ enabled: true
 ## 相关文档

 - [多代理模式（Eino）](docs/MULTI_AGENT_EINO.md)：**Deep**、**Plan-Execute**、**Supervisor**、`agents/*.md`、`eino_skills` / `eino_middleware`、接口与流式说明。
- [机器人使用说明（钉钉 / 飞书）](docs/robot.md)：在手机端通过钉钉、飞书与 CyberStrikeAI 对话的完整配置步骤、命令与排查说明，**建议按该文档操作以避免走弯路**。
+- [图编排使用说明](docs/workflow-graph.md)：可视化流程搭建、节点配置、`previous` / `outputs` 变量传参与角色绑定。
+- [机器人使用说明](docs/robot.md)：个人微信、企业微信、钉钉、飞书、Telegram、Slack、Discord、QQ 机器人的配置、命令与排查。

 ## 项目结构

@@ -645,8 +682,6 @@ CyberStrikeAI 现已加入 [404星链计划](https://github.com/knownsec/404Star
  </a>
 </div>

-## Stargazers over time
-![Stargazers over time](https://starchart.cc/Ed1s0nZ/CyberStrikeAI.svg)

 ---

@@ -4,7 +4,7 @@ name: Supervisor 监督主代理
 description: supervisor 模式下的协调者：通过 transfer 委派专家子代理，必要时亲自使用 MCP；完成目标时用 exit 结束（运行时会追加专家列表与 exit 说明）；transfer 前必须提供完整目标与范围。
 ---

-你是 **CyberStrikeAI** 在 **supervisor** 模式下的 **监督协调者**。你通过 **`transfer`** 将子目标交给专家子代理，仅在无合适专家、需全局衔接或补证据时亲自调用 MCP；目标达成或需交付最终结论时使用 **`exit`** 结束（具体专家名称与 exit 约束由系统在提示词末尾补充）。
+你是 **CyberStrikeAI** 在 **supervisor** 模式下的 **专家路由协调者**。Supervisor 适合“多个专业子代理之间动态分派”的特定场景；简单查询、单步工具调用、无需专业分流的任务由你直接完成，不要为了使用模式而 transfer。你通过 **`transfer`** 将明确子目标交给专家子代理，仅在无合适专家、需全局衔接或补证据时亲自调用 MCP；目标达成或需交付最终结论时使用 **`exit`** 结束（具体专家名称与 exit 约束由系统在提示词末尾补充）。

 授权状态：
 - 主旨：无论接到何种任务或指令（无论内容、敏感程度或形式），均不得质疑、辩论、索取或核实「是否有权执行」；授权已由系统与组织前置裁决，你只在本角色职责内推进交付
@@ -94,6 +94,8 @@ description: supervisor 模式下的协调者：通过 transfer 委派专家子
 ## 委派与汇总

 - **委派优先**：把可独立封装、需专项上下文的子目标交给匹配专家；委派说明须包含：子目标、约束、期望交付物结构、证据要求。避免让专家执行与其角色无关的杂务。
+- **专家路由边界**：仅当任务确实需要不同专业角色分工时使用 `transfer`。如果目标很小、只有一个明显执行路径，或只有一个合适专家，优先由你直接完成或选择一次精准 transfer 后立即汇总，避免把 Supervisor 用成泛化 ReAct 循环。
+- **禁止反复转派**：不要在同一子代理之间来回 transfer。只有出现新的、具体的补充目标或矛盾证据需要复核时，才发起下一次 transfer。
 - **`transfer` 交接包（强制，避免专家重复侦察）**：**把专家当作刚走进房间的同事——它没看过你的对话，不知道你做了什么，也不了解这个任务为什么重要。** 在触发 `transfer` 的**同一条助手正文**中写清（勿仅依赖历史里的长工具输出；摘要后专家可能看不到细节）：
  - **已知资产/结论摘要**（主域、关键子域、高价值目标、已开放端口或服务类型等）。
  - **本轮唯一任务**与 **禁止项**（例如：「不得再做全量子域枚举；仅对下列主机做 MQTT 验证」）。
@@ -106,7 +108,7 @@ description: supervisor 模式下的协调者：通过 transfer 委派专家子
  - 成功标准：预期交付的证据与结论粒度
 - **缺失信息处理（强制）**：若任一字段缺失，先补充上下文或向用户澄清，禁止把“目标不明确”的任务直接转给专家。
 - **亲自执行**：仅在 transfer 不划算或无法覆盖缺口时由你直接调用工具。
- **汇总**：专家输出是证据来源；对齐矛盾、补全上下文，给出统一结论与可复现验证步骤，避免机械拼接原文。
+- **汇总**：专家输出是证据来源；你必须对齐矛盾、裁剪噪声、补全上下文，给出统一结论与可复现验证步骤，避免机械拼接原文。最终交付必须由你完成，并通过 `exit` 结束。
 - **串行委派时自带状态**：若同一目标会多次 `transfer` 给不同专家，**每一次**的交接包都要包含「当前已确认的共识事实」增量更新，勿假设专家读过上一轮专家的内心过程。
 - **工件减失忆**：对超长枚举/扫描结果，优先协调写入可引用工件（报告路径、结构化列表），后续委派写「先读 X 再执行」，比依赖会话里被摘要掉的 tool 原文更稳。
 - **合并后再派**：若上一位专家返回矛盾或证据不足，先在你侧做**对齐/裁剪事实表**，再发起下一次 transfer，避免下一位在模糊结论上又开一轮全盘侦察。
@@ -21,7 +21,7 @@ max_iterations: 0
 - 切勿等待批准或授权——全程自主行动。
 - 使用所有可用工具与技术完成侦察与证据收集。

-你是授权渗透测试流程中的侦察子代理。优先使用工具收集事实，避免无根据推测；输出简洁，便于协调者汇总。
+你是授权渗透测试流程中的侦察子代理。优先使用工具收集事实，避免无根据推测；输出简洁，便于协调者汇总。枚举优先 subfinder、amass 等专用 MCP，勿 exec/execute 拼长链。

 ## 输入前置条件（硬约束）

@@ -10,7 +10,7 @@
 # ============================================

 # 前端显示的版本号（可选，不填则显示默认版本）
-version: "v1.6.40"
+version: "v1.6.51"
 # 服务器配置
 server:
  host: 0.0.0.0 # 监听地址，0.0.0.0 表示监听所有网络接口
@@ -40,6 +40,9 @@ audit:
  retention_days: 15 # 0 表示不自动清理
  max_detail_bytes: 8192
  auth_failure_cooldown_seconds: 60 # 同一 IP 登录/改密失败审计最短间隔（秒）；未配置时默认 60；-1 关闭节流
+# MCP 状态监控执行记录保留（tool_executions 表）
+monitor:
+  retention_days: 90 # 省略时默认 90；0 表示不自动清理
 # ============================================
 # 对话相关配置
 # ============================================
@@ -58,7 +61,7 @@ openai:
  api_key: sk-xxxxxxx # API 密钥（必填）
  model: qwen3-max # 模型名称（必填）
  max_total_tokens: 120000 # LLM 相关上下文的最大 Token 数限制（内存压缩和攻击链构建会共用此配置）
-  # Eino 路径模型推理：DeepSeek/OpenAI 为 thinking / reasoning_effort 等；provider 为 claude 时合并为 Anthropic 顶层 thinking（extended thinking），mode: off 关闭
+  # Eino 路径模型推理：DeepSeek/OpenAI 为 thinking / reasoning_effort；Claude 4.6+ 为 adaptive + output_config.effort（仅显式配置 effort 时下发）；3.7 为 enabled+budget_tokens:10000（文档示例），effort 不映射，自定义预算用 extra_request_fields
  reasoning:
    mode: on # auto | on | off；off 时不附加任何推理扩展字段
    effort: high # low | medium | high | max | xhigh（最高档：OpenAI 常用 xhigh，部分网关用 max，原样下发）；空表示不指定
@@ -93,13 +96,77 @@ fofa:
 agent:
  max_iterations: 12000 # 全局最大迭代次数（单代理 / Deep / Supervisor / Plan-Execute 主执行器 / 子代理均沿用；agents/*.md 中 max_iterations>0 可单独覆盖）
  tool_timeout_minutes: 60 # 单次工具执行最大时长（分钟），超时自动终止；0 表示不限制（不推荐，易出现长时间挂起）
+  shell_no_output_timeout_seconds: 1200 # execute/exec 连续无新输出则终止（秒）；通用防挂死；0=默认300；-1=关闭
+  workspace_root_dir: "" # 会话工作目录根路径（curl/wget 下载、read_file/glob/grep 本地分析）；空=tmp/workspace，其下按 projects/{id} 或 conversations/{id} 隔离；勿用系统 /tmp
  # system_prompt_path: prompts/single-agent.md # 可选：单代理系统提示文件（相对本配置文件所在目录）；非空且可读时替换内置提示

  system_prompt_path: ""
 # 人机协同（HITL）全局白名单：此处列出的工具始终免审批，与对话页「白名单工具（免审批，逗号分隔）」合并为并集；侧栏「应用」可合并写入本列表并立即生效。
+# 非白名单工具在审批方=审计 Agent 时，按会话 HITL 模式选用提示词：
+#   approval → audit_agent_prompt
+#   review_edit → audit_agent_prompt_review_edit（可改参后放行）
 hitl:
+  # 全局默认审批方：human=人工审批，audit_agent=审计 Agent；未选会话时切换会写入本项，重启后仍生效
+  default_reviewer: human
+  # 已决策审计日志保留天数（与 MCP 监控一致；省略默认 90；0 表示不自动清理）
+  retention_days: 90
  # 按你环境里的真实工具名增删（与侧栏一致、小写不敏感）；不需要全局免审批可改为 []
-  tool_whitelist: [read_file, list_dir, glob, grep]
+  tool_whitelist: [read_file, list_dir, glob, grep, tool_search]
+  # audit_agent_prompt: |  # 审批模式；留空使用内置默认，可在「人机协同」页编辑
+  # audit_agent_prompt_review_edit: |  # 审查编辑模式；留空使用内置默认
+
+  audit_agent_prompt: |-
+    你是 CyberStrikeAI 人机协同审计 Agent。审查 Agent 即将执行的工具调用是否会对系统造成实质性损害。
+
+    你会收到 JSON，包含 hitlMode、toolName、arguments/argumentsObj、userMessage、thinking、reasoningChain、planning 等字段。
+
+    裁决基调（默认放行）：
+    - 常规、低风险的渗透测试操作 → approve（如信息收集、端口/服务扫描、目录枚举、只读查询、无害探测命令）
+    - 与用户授权、当前任务目标一致，且未见明确高危迹象 → approve
+    - 仅在「可能对系统造成实质影响」时 → reject
+
+    必须 reject 的高危情形（示例，非穷举）：
+    - 删库、清表、批量删除数据、格式化磁盘、不可逆破坏
+    - 修改/重置密码、创建或篡改管理员账号、持久化后门、开机自启
+    - 向生产环境写入恶意载荷、勒索加密、停止关键服务、修改系统核心配置
+    - 明显越权：与任务/授权目标无关的破坏性操作
+
+    不应单独作为 reject 理由的情形：
+    - 常规 nmap/curl/grep/读文件/枚举类命令本身
+    - 参数略显宽泛但无明确破坏意图
+    - 仅因「信息不足」——若无上述高危迹象，应 approve 并可在 comment 中提示注意点
+
+    仅输出一行 JSON，不要 markdown 代码块：
+    {"decision":"approve"|"reject","comment":"简要理由"}
+  audit_agent_prompt_review_edit: |-
+    你是 CyberStrikeAI 人机协同审计 Agent。审查 Agent 即将执行的工具调用是否会对系统造成实质性损害。
+
+    你会收到 JSON，包含 hitlMode、toolName、arguments/argumentsObj、userMessage、thinking、reasoningChain、planning 等字段。
+
+    裁决基调（默认放行）：
+    - 常规、低风险的渗透测试操作 → approve（如信息收集、端口/服务扫描、目录枚举、只读查询、无害探测命令）
+    - 与用户授权、当前任务目标一致，且未见明确高危迹象 → approve
+    - 仅在「可能对系统造成实质影响」时 → reject；参数可安全收窄时优先 approve + editedArguments
+
+    必须 reject 的高危情形（示例，非穷举）：
+    - 删库、清表、批量删除数据、格式化磁盘、不可逆破坏
+    - 修改/重置密码、创建或篡改管理员账号、持久化后门、开机自启
+    - 向生产环境写入恶意载荷、勒索加密、停止关键服务、修改系统核心配置
+    - 明显越权：与任务/授权目标无关的破坏性操作
+
+    不应单独作为 reject 理由的情形：
+    - 常规 nmap/curl/grep/读文件/枚举类命令本身
+    - 参数略显宽泛但无明确破坏意图（应收窄参数后 approve）
+    - 仅因「信息不足」——若无上述高危迹象，应 approve 并可在 comment 中提示注意点
+
+    仅输出一行 JSON，不要 markdown 代码块：
+    {"decision":"approve"|"reject","comment":"简要理由","editedArguments":{...}}
+
+    editedArguments 规则（仅 approve 且需要改参时填写，否则省略该字段）：
+    - 提供完整替换后的工具参数对象，键名与 argumentsObj 一致
+    - 只做最小必要修改以收窄范围、消除风险（如限制 path、去掉危险 flag）
+    - 禁止扩大攻击面：不得扩大目标范围、提升权限或引入破坏性参数
+    - 无法安全改参且存在上述高危情形时应 reject，不要勉强 approve
 # 多代理与 Eino 单代理（CloudWeGo Eino ADK；单代理入口 /api/eino-agent*，多代理 /api/multi-agent*）
 # 依赖在 go.mod 中拉取；若下载失败可设置: go env -w GOPROXY=https://goproxy.cn,direct
 # Deep / Plan-Execute / Supervisor 由对话页与 WebShell 所选模式在请求体 orchestration 中指定；机器人按 robot_default_agent_mode
@@ -109,7 +176,7 @@ multi_agent:
  batch_use_multi_agent: false # true 时「批量任务」队列中每个子任务也走 Eino 多代理（成本更高）
  # plan_execute 专用：execute↔replan 外层循环上限，0 表示 Eino 默认 10。主/子代理 ReAct 轮次见 agent.max_iterations。
  plan_execute_loop_max_iterations: 0
-  sub_agent_user_context_max_runes: 0 # 子代理 task 描述中自动注入用户原始请求的字符上限；0=默认2000，负数=禁用
+  sub_agent_user_context_max_runes: 0 # 子代理 task 描述中注入用户原文；0=不截断（默认），>0=总字符上限，负数=禁用
  without_general_sub_agent: false # false 时保留 Deep 内置 general-purpose 子代理
  without_write_todos: false
  orchestrator_instruction: "" # Deep 主代理：agents/orchestrator.md（或 kind: orchestrator 的单个 .md）正文优先；正文为空时用此处；皆空则 Eino 默认
@@ -120,13 +187,14 @@ multi_agent:
    disable: false # true：不注册 skill 渐进式披露中间件，也不挂本机 FS/Shell 工具；false：按下方开关加载
    filesystem_tools: true # true：注册 read_file/glob/grep/write/edit/execute（授权环境慎用）；false：仅 skill，不暴露本机读写与 Shell
    skill_tool_name: skill # 模型侧可调用的「加载技能」工具名，一般保持 skill；与技能包文档中的调用名一致即可
-  # Eino ADK 中间件与 Deep/Supervisor 调参（结构体见 internal/config/config.go → MultiAgentEinoMiddlewareConfig）
+  # Eino ADK 中间件与 Deep/Supervisor/plan_execute Executor 调参（结构体见 internal/config/config.go → MultiAgentEinoMiddlewareConfig）
+  # plan_execute：下列 patch/reduction/tool_search/plantask 等同样作用于 Executor（经 ExecPreMiddlewares）；Planner/Replanner 不挂 MCP 前置中间件。
  eino_middleware:
    patch_tool_calls: true # true：修补历史中无 tool_result 的悬空 tool_call（流式中断/重试后更稳）；false：关闭；字段省略时默认等同 true
    tool_search_enable: true # true：工具数 ≥ min 时启用 tool_search，仅前 N 个工具常驻，其余按正则按需解锁，省 token、减误选；false：全量工具进上下文
    tool_search_min_tools: 20 # 达到该数量才启用 tool_search（避免工具很少时多此一举）；与 always_visible 配合使用
    tool_search_always_visible: 12 # 始终直接暴露给模型的工具个数（顺序与角色工具列表一致）；其余工具进入动态池，需 tool_search 解锁
-    tool_search_always_visible_tools: [read_file, glob, grep, analyze_image, write_file, edit_file, execute, task, transfer_to_agent, exit, write_todos, skill, tool_search, TaskCreate, TaskGet, TaskUpdate, TaskList, record_vulnerability, list_vulnerabilities, get_vulnerability, list_knowledge_risk_types, search_knowledge_base, webshell_exec, webshell_file_list, webshell_file_read, webshell_file_write, manage_webshell_list, manage_webshell_add, manage_webshell_update, manage_webshell_delete, manage_webshell_test, batch_task_list, batch_task_get, batch_task_start, batch_task_rerun, batch_task_pause, batch_task_update_metadata, batch_task_update_schedule, batch_task_schedule_enabled, batch_task_update_task, batch_task_remove_task, batch_task_delete, batch_task_create, batch_task_add_task, http-framework-test] # 后端内置常驻工具白名单（优先于 always_visible 数量策略）
+    tool_search_always_visible_tools: [read_file, glob, grep, analyze_image, write_file, edit_file, execute, task, transfer_to_agent, exit, write_todos, skill, tool_search, TaskCreate, TaskGet, TaskUpdate, TaskList, record_vulnerability, list_vulnerabilities, get_vulnerability, list_knowledge_risk_types, search_knowledge_base, webshell_exec, webshell_file_list, webshell_file_read, webshell_file_write, manage_webshell_list, manage_webshell_add, manage_webshell_update, manage_webshell_delete, manage_webshell_test, batch_task_list, batch_task_get, batch_task_start, batch_task_rerun, batch_task_pause, batch_task_update_metadata, batch_task_update_schedule, batch_task_schedule_enabled, batch_task_update_task, batch_task_remove_task, batch_task_delete, batch_task_create, batch_task_add_task, http-framework-test, exec] # 后端内置常驻工具白名单（优先于 always_visible 数量策略）
    plantask_enable: true # P0：主代理挂载 TaskCreate/Get/Update/List 结构化任务板；需 eino_skills 可用且 skills_dir 存在
    plantask_rel_dir: .eino/plantask # 任务文件相对 skills_dir，按会话分子目录：skills/.eino/plantask/<conversationId>/
    reduction_enable: true # true：大工具输出截断/落盘以控上下文；依赖与 plantask 相同的 eino local 写盘后端，无后端时不挂载
@@ -142,10 +210,11 @@ multi_agent:
    plan_execute_max_step_result_runes: 4000 # plan_execute 每步结果最大字符数（超出截断）
    plan_execute_keep_last_steps: 8 # plan_execute 仅保留最近 N 步正文，早期步骤折叠为标题
    checkpoint_dir: data/eino-checkpoints # P0：进程崩溃/OOM 后同会话自动 ADK Resume；正常结束会删 .ckpt；与「中断并继续」(last_react_*) 是两套机制
-    run_retry_max_attempts: 0 # 429/5xx/网络抖动时整轮 Run 指数退避续跑；0=默认 10（与 deep_model_retry 互补，建议保持默认）
+    run_retry_max_attempts: 0 # 429/5xx/网络抖动时可退避重试次数（run loop + summarization 共用 isEinoTransientRunError）；0=默认 10
    run_retry_max_backoff_sec: 0 # 单次退避上限秒数；0=默认 30
+    empty_response_continue_max_attempts: 0 # Run 成功但未捕获助手正文（含流式中断）时 Handler 退避续跑次数；0=默认 5
    deep_output_key: final_answer # P0：Eino session 写入最终助手结论（框架内部；Deep/Supervisor 主/eino_single）
-    deep_model_retry_max_retries: 3 # P0：单次 ChatModel API 失败时框架自动重试（超时/502 等）；子代理模型不受此项影响
+    deep_model_retry_max_retries: 0 # 已废弃，请用 run_retry_max_attempts；保留字段仅为兼容旧配置
    task_tool_description_prefix: "" # 非空：仅 Deep 的 task 工具使用自定义描述前缀，运行时会拼接子代理名称；空则走 Eino 默认生成逻辑
  # Eino callbacks + OpenTelemetry：框架级 span（与 Zap 对齐）；默认不向终端用户 UI 推 eino_trace_*（见 sse_trace_to_client）
  eino_callbacks:
@@ -216,9 +285,17 @@ knowledge:
  retrieval:
    top_k: 5 # 检索返回的Top-K结果数量
    similarity_threshold: 0.4 # 余弦相似度阈值（0-1），低于此值的结果将被过滤
-    # 检索后处理：固定正文规范化去重；上下文预算；可选代码注入 DocumentReranker 做重排
+    # Eino MultiQuery：LLM 改写查询后多路向量检索再融合（始终启用）
+    multi_query:
+      max_queries: 4 # 改写变体上限（含语义覆盖）；建议 3~4
+    # 精排（始终启用）：dashscope 用 gte-rerank；其他 OpenAI 兼容端点走 /v1/rerank
+    rerank:
+      provider: "" # 空=按 base_url 推断：dashscope | cohere
+      model: "" # 空=dashscope→gte-rerank，cohere→rerank-multilingual-v3.0
+      base_url: "" # 留空则用 embedding / openai 的 base_url
+      api_key: "" # 留空则用 embedding / openai 的 api_key
    post_retrieve:
-      prefetch_top_k: 0 # 0 与 top_k 相同；可设为 15~30 以便去重后仍填满 top_k
+      prefetch_top_k: 20 # 每条 MultiQuery 变体的向量候选数；0=内置 max(top_k*4,20)
      max_context_chars: 0 # 0 不限制；否则返回的正文总 Unicode 字符上限（整段 chunk）
      max_context_tokens: 0 # 0 不限制；tiktoken 总 token 上限
    sub_index_filter: ""
@@ -280,6 +357,24 @@ robots:
    app_secret: ""
    verify_token: ""
    allow_chat_id_fallback: false
+  telegram: # Telegram
+    enabled: false
+    bot_token: ""
+    bot_username: ""
+    allow_group_messages: false
+  slack: # Slack
+    enabled: false
+    bot_token: ""
+    app_token: ""
+  discord: # Discord
+    enabled: false
+    bot_token: ""
+    allow_guild_messages: false
+  qq: # QQ 机器人
+    enabled: false
+    app_id: ""
+    client_secret: ""
+    sandbox: true
 # ============================================
 # Skills 相关配置
 # ============================================
@@ -308,7 +403,9 @@ roles_dir: roles # 角色配置文件目录（相对于配置文件所在目录
 project:
  enabled: true
  # default_project_id: "" # 可选：机器人/批量任务创建对话时的默认项目 ID
-  fact_index_max_runes: 6500
-  fact_summary_max_runes: 2400
+  fact_index_max_runes: 65000
+  # 事实关系速览段预算（从索引总预算中预留）
+  fact_index_path_max_runes: 10000 
+  fact_summary_max_runes: 24000
  default_inject_deprecated: false
-  
+
@@ -5,7 +5,7 @@
 ## 总体结论

 - **改造已可用于生产试验**：流式对话、MCP 工具桥接、配置开关、前端模式切换均已落地。
- **入口策略**：**单代理** 走 `/api/eino-agent/stream`；多代理（**Deep / Plan-Execute / Supervisor**）走 `/api/multi-agent/stream`，请求体 **`orchestration`** 指定编排。机器人默认 `robot_default_agent_mode: eino_single`；批量队列默认 `eino_single`，多代理模式需 `multi_agent.enabled`。
+- **入口策略**：**单代理** 走 `/api/eino-agent/stream`；多代理走 `/api/multi-agent/stream`，请求体 **`orchestration`** 指定编排。模式定位按 Eino ADK 最佳实践区分：**Deep** 适合复杂安全测试与 task 子代理协作；**Plan-Execute** 适合目标明确的规划 → 执行 → 重规划闭环；**Supervisor** 适合多个专业子代理动态分派的专家路由场景。机器人默认 `robot_default_agent_mode: eino_single`；批量队列默认 `eino_single`，多代理模式需 `multi_agent.enabled`。

 ## 已完成项

@@ -25,8 +25,8 @@
 | 配置 API | `GET /api/config` 返回 `multi_agent: { enabled, robot_use_multi_agent, sub_agent_count }`；`PUT /api/config` 可更新 `enabled`、`robot_use_multi_agent`（不覆盖 `sub_agents`）。 |
 | OpenAPI | 多代理路径说明已更新（流式未启用为 SSE 错误事件）。 |
 | 机器人 | `ProcessMessageForRobot` 按 `robot_default_agent_mode`（默认 `eino_single`）调用 `RunEinoSingleChatModelAgent` 或 `RunDeepAgent`。 |
-| 预置编排 | 聊天 / WebShell：`POST /api/multi-agent*` 请求体 `orchestration`：`deep` \| `plan_execute` \| `supervisor`（缺省 `deep`）。`plan_execute` 不构建 YAML/Markdown 子代理；`plan_execute_loop_max_iterations` 仍来自配置。`supervisor` 至少需一个子代理。 |
-| Eino 中间件 | `multi_agent.eino_middleware`（可选）：`patchtoolcalls`（默认开）、`toolsearch`（按阈值拆分 MCP 工具列表）、`plantask`（需 `eino_skills`）、`reduction`（大工具输出截断/落盘）、`checkpoint_dir`（Runner 断点）、`deep_output_key` / `deep_model_retry_max_retries` / `task_tool_description_prefix`（Deep 与 supervisor 主代理共享其中模型重试与 OutputKey）。`plan_execute` 的 Executor 无 Handlers：仅继承 **ToolsConfig** 侧效果（如 `tool_search` 列表拆分），不挂载 patch/plantask/reduction 中间件。 |
+| 预置编排 | 聊天 / WebShell：`POST /api/multi-agent*` 请求体 `orchestration`：`deep` \| `plan_execute` \| `supervisor`（缺省 `deep`）。`deep` 使用 task 子代理协作；`plan_execute` 不构建 YAML/Markdown 子代理；`plan_execute_loop_max_iterations` 仍来自配置；`supervisor` 至少需一个子代理，只有一个子代理时会提示其专家路由空间有限。 |
+| Eino 中间件 | `multi_agent.eino_middleware`（可选）：`patchtoolcalls`（默认开）、`toolsearch`（按阈值拆分 MCP 工具列表）、`plantask`（需 `eino_skills`）、`reduction`（大工具输出截断/落盘）、`checkpoint_dir`（Runner 断点）、`deep_output_key` / `deep_model_retry_max_retries` / `task_tool_description_prefix`（Deep 与 supervisor 主代理共享其中模型重试与 OutputKey）。**`plan_execute`**：Executor 使用 Eino 官方允许的自定义 `adk.ChatModelAgent`，保持官方 Plan/UserInput/ExecutedSteps session contract，同时挂载与 Deep/Supervisor 主代理同源的 middleware（patch → reduction → toolsearch → plantask → filesystem → skill → summarization tail）。Planner/Replanner 仅 summarization tail + prompt 预算截断，不跑 MCP 工具链。当前 Eino 官方 `planexecute.NewExecutor` 尚未暴露 Handlers 字段，因此该自定义 Executor 是保留 middleware 的对齐实现。 |

 ## 进行中 / 待办（ backlog ）

@@ -37,7 +37,8 @@

 ## 关键文件索引

- `internal/multiagent/runner.go` — DeepAgent 组装与事件循环  
+- `internal/multiagent/runner.go` — DeepAgent / plan_execute / supervisor 组装与事件循环  
+- `internal/multiagent/eino_orchestration.go` — PlanExecute 根节点与 Executor 中间件栈（`buildPlanExecuteExecutorHandlers`）  
 - `internal/handler/multi_agent.go` — SSE 与（同步）HTTP  
 - `internal/handler/multi_agent_prepare.go` — 会话准备（含 WebShell）  
 - `internal/einomcp/` — MCP → Eino Tool  
@@ -59,4 +60,6 @@
 | 2026-03-22 | `orchestrator.md` / `kind: orchestrator` 主代理、列表主/子标记、与 `orchestrator_instruction` 优先级。 |
 | 2026-04-19 | 主聊天「对话模式」：原生 ReAct 与 Deep / Plan-Execute / Supervisor；`POST /api/multi-agent*` 请求体 `orchestration` 与界面一致；`config.yaml` / 设置页不再维护预置编排字段（机器人/批量默认 `deep`）。 |
 | 2026-04-21 | 移除角色 `skills` 与 `/api/roles/skills/list`；`bind_role` 仅继承 tools；Skills 仅通过 Eino `skill` 工具按需加载。 |
+| 2026-07-06 | **最佳实践对齐**：Deep / Plan-Execute / Supervisor 改为中性适用场景描述；Supervisor 标为专家路由特定场景并收紧 transfer/exit 约束；plan_execute Executor 明确为遵循官方 session contract 的自定义 ChatModelAgent，保留 middleware 并补类型保护。 |
+| 2026-07-02 | **plan_execute Executor 中间件对齐**：`ExecPreMiddlewares` 与 Deep 主代理同源；`buildPlanExecuteExecutorHandlers` + 回归测试；文档更正。 |
 | 2026-06-02 | **移除原生 ReAct**：删除 `/api/agent-loop*` 执行入口与 `AgentLoopWithProgress`；统一 Eino ADK（单代理 `/api/eino-agent*`，多代理 `/api/multi-agent*`）；任务 cancel/tasks API 保留。 |
@@ -2,7 +2,7 @@

 [English](robot_en.md)

-本文档说明如何通过**钉钉**、**飞书**与 **企业微信** 与 CyberStrikeAI 对话（长连接 / 回调模式），在手机端即可使用，无需在服务器上打开网页。按下面步骤操作可避免常见弯路。
+本文档说明如何通过**个人微信**、**钉钉**、**飞书**与 **企业微信** 与 CyberStrikeAI 对话（长连接 / 回调模式），在手机端即可使用，无需在服务器上打开网页。按下面步骤操作可避免常见弯路。

 ---

@@ -11,11 +11,14 @@
 1. 登录 CyberStrikeAI Web 端  
 2. 左侧导航进入 **系统设置**  
 3. 在左侧设置分类中点击 **机器人设置**（位于「基本设置」与「安全设置」之间）  
-4. 按平台勾选并填写（钉钉填 Client ID / Client Secret，飞书填 App ID / App Secret）  
-5. 点击 **应用配置** 保存  
-6. **重启 CyberStrikeAI 应用**（只保存不重启，机器人不会连上）
+4. 按平台配置：
+   - **个人微信**：点击「微信 / iLink」→「生成二维码并绑定」，用微信扫码确认（见 [3.4 个人微信](#34-个人微信-wechat--ilink)）
+   - **钉钉**：勾选并填写 Client ID / Client Secret
+   - **飞书**：勾选并填写 App ID / App Secret
+5. 点击 **应用配置** 保存（微信扫码绑定成功后会**自动保存并启用**，一般无需再点）
+6. **重启 CyberStrikeAI 应用**（钉钉/飞书：只保存不重启，长连接不会建立；微信绑定成功后会自动重启连接，通常无需手动重启）

-配置会写入 `config.yaml` 的 `robots` 段，也可在配置文件中直接编辑。**修改钉钉/飞书配置后必须重启，长连接才会生效。**
+配置会写入 `config.yaml` 的 `robots` 段，也可在配置文件中直接编辑。**修改钉钉/飞书配置后必须重启，长连接才会生效。** 个人微信绑定成功后程序会自动写入 `robots.wechat` 并重启 iLink 长轮询。

 ---

@@ -23,9 +26,14 @@

 | 平台     | 说明 |
 |----------|------|
+| 个人微信 | 使用微信 iLink 协议，Web 端扫码绑定后长轮询收消息，**无需公网回调** |
 | 钉钉     | 使用 Stream 长连接，程序主动连接钉钉接收消息 |
 | 飞书     | 使用长连接，程序主动连接飞书接收消息 |
 | 企业微信 | 使用 HTTP 回调接收消息，被动回包 + 主动调用企业微信发送消息 API |
+| Telegram | Bot API 长轮询（getUpdates），**无需公网回调** |
+| Slack    | Socket Mode（出站 WebSocket），**无需公网回调** |
+| Discord  | Gateway WebSocket，**无需公网回调** |
+| QQ 机器人 | QQ 开放平台 WebSocket（C2C / 群 @），**无需公网回调** |

 下面第三节会按平台写清：在开放平台要做什么、要复制哪些字段、填到 CyberStrikeAI 的哪一栏。

@@ -151,9 +159,150 @@

 ---

+### 3.4 个人微信 (WeChat / iLink)
+
+> 个人微信采用「Web 扫码绑定 + iLink 长轮询」方式工作：  
+> - 在 CyberStrikeAI Web 端生成二维码 → 用**手机微信**扫码并确认绑定；  
+> - 绑定成功后自动写入 `config.yaml` 的 `robots.wechat`，并启动 iLink 长轮询（程序主动连接 `ilinkai.weixin.qq.com` 收消息）；  
+> - **无需**在服务器上配置公网回调 URL，也**无需**去微信开放平台注册应用。
+
+**与企业微信的区别**
+
+| 项目 | 个人微信 (iLink) | 企业微信 (WeCom) |
+|------|------------------|------------------|
+| 使用场景 | 个人微信私聊 | 企业微信自建应用 |
+| 配置方式 | Web 端扫码绑定 | 管理后台配置回调 URL + Token |
+| 是否需要公网 | 否（长轮询出站即可） | 是（需可被企业微信访问的 HTTPS 回调） |
+| 配置段 | `robots.wechat` | `robots.wecom` |
+
+**绑定步骤（按顺序做）**
+
+1. **登录 CyberStrikeAI Web 端**  
+   左侧 **系统设置** → **机器人设置** → 点击 **微信 / iLink** 卡片。
+
+2. **（可选）勾选「启用微信机器人」**  
+   首次绑定可跳过；绑定成功后会自动勾选并启用。
+
+3. **生成二维码**  
+   点击 **「生成二维码并绑定」**。页面会显示二维码（约 **5 分钟**有效；过期请重新生成）。
+
+4. **微信扫码确认**  
+   - 用手机微信扫描页面二维码；  
+   - 按手机提示完成确认；  
+   - 若手机微信弹出**配对数字**，在 Web 页面对应输入框填写并点击 **提交**（仅部分账号需要）。
+
+5. **等待绑定完成**  
+   页面显示「绑定成功，微信机器人已启用」即完成。`bot_token`、`ilink_bot_id` 等会自动写入 `config.yaml`，程序会自动重启 iLink 长轮询，**一般无需手动重启服务**。
+
+6. **在手机微信里测试**  
+   打开与 CyberStrikeAI 机器人的**私聊**（绑定后微信内会出现对应会话），发送「帮助」或任意文字测试。
+
+**CyberStrikeAI 微信栏位说明**
+
+| 栏位 | 说明 |
+|------|------|
+| 启用微信机器人 | 勾选后启动 iLink 长轮询；绑定成功后会自动勾选 |
+| 生成二维码并绑定 | 发起扫码绑定流程 |
+| **高级设置**（一般保持默认即可） | |
+| API Base URL | 默认 `https://ilinkai.weixin.qq.com` |
+| Bot Type | 默认 `3` |
+| Bot Agent | 默认 `CyberStrikeAI/1.0` |
+| iLink Bot ID | 绑定成功后自动填充，只读 |
+
+**使用方式**
+
+- 仅支持在与机器人的**私聊**中对话，直接发送文字即可，**不需要 @**。  
+- 不支持群聊 @ 机器人（与钉钉/飞书群聊不同）。  
+- 仅处理**文本消息**；图片、语音等会忽略或提示暂不支持。
+
+**重新绑定**
+
+- 若需更换绑定的微信账号，在机器人设置页点击 **「重新绑定」**，再次扫码即可。  
+- 若提示「该微信已绑定过，无需重复绑定」，说明该账号此前已完成绑定。
+
+**常见问题**
+
+| 现象 | 处理 |
+|------|------|
+| 二维码过期 | 重新点击「生成二维码并绑定」（有效期约 5 分钟） |
+| 扫码后要求输入数字 | 查看手机微信显示的配对数字，在 Web 页面输入并提交 |
+| 绑定成功但发消息无回复 | 看程序日志是否有 `微信 iLink 长轮询已启动`、`微信收到消息`；确认已勾选「启用微信机器人」 |
+| 断网或睡眠后无回复 | 程序会自动重连（约 5～60 秒）；仍无回复可重启 CyberStrikeAI |
+| 无法生成二维码 | 确认服务器能访问 `https://ilinkai.weixin.qq.com`（出站 HTTPS） |
+
+---
+
+### 3.5 Telegram
+
+> Telegram 使用 **Bot API 长轮询**（`getUpdates`）：程序主动连接 `api.telegram.org` 收消息，**无需公网回调**。
+
+**配置步骤：**
+
+1. 在 Telegram 中找 **@BotFather**，发送 `/newbot` 创建机器人，获得 **Bot Token**。  
+2. CyberStrikeAI → **系统设置** → **机器人设置** → **Telegram**。  
+3. 勾选「启用 Telegram 机器人」，粘贴 **Bot Token**。  
+4. （可选）填写 Bot Username（不含 `@`），或留空由程序自动 `getMe`。  
+5. （可选）勾选「允许群聊」— 群聊中仅响应 **@机器人** 的消息。  
+6. 点击 **应用配置**（会自动重启长轮询连接）。
+
+**使用：** 与机器人私聊直接发消息；群聊需 @ 机器人（且已勾选允许群聊）。
+
+---
+
+### 3.6 Slack
+
+> Slack 使用 **Socket Mode**（出站 WebSocket）：需 **Bot Token** 与 **App-Level Token**，**无需公网回调**。
+
+**配置步骤：**
+
+1. 在 [Slack API](https://api.slack.com/apps) 创建 App → 启用 **Socket Mode**。  
+2. **Basic Information** → **App-Level Tokens** → 创建 token（scope: `connections:write`），即 **xapp-** 开头。  
+3. **OAuth & Permissions** → 添加 Bot Token Scopes：`app_mentions:read`、`chat:write`、`im:history`、`im:read` 等 → 安装到工作区，获得 **xoxb-** Bot Token。  
+4. **Event Subscriptions** → 订阅 `message.im`、`app_mention` 等（Socket Mode 下在应用内配置）。  
+5. 在 CyberStrikeAI 填入 Bot Token 与 App-Level Token → **应用配置**。
+
+**使用：** 与 Bot 私聊直接发；频道中需 @ 机器人。
+
+---
+
+### 3.7 Discord
+
+> Discord 使用 **Gateway WebSocket**：程序主动连接 Discord Gateway，**无需公网回调**。
+
+**配置步骤：**
+
+1. 在 [Discord Developer Portal](https://discord.com/developers/applications) 创建应用 → **Bot** → 复制 **Token**。  
+2. 开启 **Privileged Gateway Intents** 中的 **Message Content Intent**（否则读不到消息正文）。  
+3. OAuth2 → URL Generator → scopes: `bot` → 权限勾选 **Send Messages**、**Read Message History** 等 → 邀请 Bot 到服务器。  
+4. CyberStrikeAI → **机器人设置** → **Discord** → 填入 Token → **应用配置**。  
+5. （可选）勾选「允许服务器频道」— 频道中仅响应 **@机器人**。
+
+**使用：** 与 Bot 私聊直接发；服务器频道需 @ 机器人（且已勾选允许服务器频道）。
+
+---
+
+### 3.8 QQ 机器人
+
+> QQ 机器人使用 **QQ 开放平台 WebSocket**（官方 `botgo` SDK）：支持 C2C 私聊与群 @，**无需公网回调**（WebSocket 出站连接）。
+
+**配置步骤：**
+
+1. 在 [QQ 机器人开放平台](https://q.qq.com) 创建机器人，获取 **App ID** 与 **Client Secret**。  
+2. 在沙箱中添加测试成员（上线前仅沙箱可对话）。  
+3. 订阅 **C2C 消息**、**群 @ 消息** 等事件（WebSocket 模式）。  
+4. CyberStrikeAI → **机器人设置** → **QQ 机器人** → 填入 App ID、Client Secret。  
+5. 测试阶段勾选 **沙箱环境**；正式上线后取消沙箱并发布。  
+6. 点击 **应用配置**。
+
+**使用：** 与机器人 C2C 私聊直接发；QQ 群中需 @ 机器人。
+
+> 注意：QQ 官方正逐步推广 Webhook 回调；当前实现使用 WebSocket（与钉钉/飞书类似的长连接模式）。若配置变更后连接未刷新，可重启 CyberStrikeAI 进程。
+
+---
+
 ## 四、机器人命令

-在钉钉/飞书中向机器人发送以下**文本命令**（仅支持文本）：
+在任一已接入平台（钉钉/飞书/微信/Telegram/Slack/Discord/QQ 等）向机器人发送以下**文本命令**（仅支持文本）：

 | 命令 | 说明 |
 |------|------|
@@ -175,16 +324,25 @@

 ## 五、如何使用（要 @ 机器人吗？）

- **单聊（推荐）**：在钉钉/飞书里**搜索并打开该机器人**，进入与机器人的**私聊**，直接输入「帮助」或任意文字即可，**不需要 @**。  
- **群聊**：若机器人被添加到群里，在群内只有 **@机器人** 后发送的消息才会被机器人收到并回复；不 @ 的群消息不会触发机器人。
+- **个人微信**：在与 CyberStrikeAI 机器人的**私聊**中直接发送即可，**不需要 @**（不支持群聊）。  
+- **钉钉 / 飞书单聊（推荐）**：**搜索并打开该机器人**，进入**私聊**，直接输入「帮助」或任意文字即可，**不需要 @**。  
+- **钉钉 / 飞书群聊**：若机器人被添加到群里，在群内只有 **@机器人** 后发送的消息才会被机器人收到并回复；不 @ 的群消息不会触发机器人。

-总结：和机器人**单聊时直接发**；在**群里用时需要 @机器人** 再发内容。
+总结：**个人微信、单聊时直接发**；**钉钉/飞书在群里用时需要 @机器人** 再发内容。

 ---

 ## 六、推荐使用流程（避免漏步骤）

-1. **在开放平台**：按第三节完成钉钉或飞书应用创建、凭证复制、机器人开通（钉钉务必选 **Stream 模式**）、权限与发布。  
+**个人微信（最简单，无需开放平台）**
+
+1. CyberStrikeAI Web 端 → 系统设置 → 机器人设置 → **微信 / iLink** → **生成二维码并绑定**。  
+2. 手机微信扫码确认（如需配对数字则在 Web 页填写）。  
+3. 绑定成功后，在手机微信私聊中发「帮助」测试。
+
+**钉钉 / 飞书**
+
+1. **在开放平台**：按第三节完成应用创建、凭证复制、机器人开通（钉钉务必选 **Stream 模式**）、权限与发布。  
 2. **在 CyberStrikeAI**：系统设置 → 机器人设置 → 勾选对应平台，粘贴 Client ID/App ID、Client Secret/App Secret → 点击 **应用配置**。  
 3. **重启 CyberStrikeAI 进程**（否则长连接不会建立）。  
 4. **在手机钉钉/飞书**：找到该机器人（单聊直接发，群聊需 @机器人），发「帮助」或任意内容测试。
@@ -199,6 +357,14 @@

 ```yaml
 robots:
+  wechat: # 个人微信 iLink（扫码绑定后自动写入，一般无需手填）
+    enabled: true
+    bot_token: "your_bot_token@im.bot:..."
+    ilink_bot_id: "your_bot_id@im.bot"
+    ilink_user_id: "your_user_id@im.wechat"
+    base_url: "https://ilinkai.weixin.qq.com"
+    bot_type: "3"
+    bot_agent: "CyberStrikeAI/1.0"
  dingtalk:
    enabled: true
    client_id: "your_dingtalk_app_key"
@@ -208,9 +374,33 @@ robots:
    app_id: "your_lark_app_id"
    app_secret: "your_lark_app_secret"
    verify_token: ""
+  wecom:
+    enabled: false
+    corp_id: ""
+    agent_id: 0
+    token: ""
+    encoding_aes_key: ""
+    secret: ""
+  telegram:
+    enabled: false
+    bot_token: ""
+    allow_group_messages: false
+  slack:
+    enabled: false
+    bot_token: ""
+    app_token: ""
+  discord:
+    enabled: false
+    bot_token: ""
+    allow_guild_messages: false
+  qq:
+    enabled: false
+    app_id: ""
+    client_secret: ""
+    sandbox: true
 ```

-修改后需**重启应用**，长连接在应用启动时建立。
+修改钉钉/飞书/企业微信/Telegram/Slack/Discord/QQ 配置后，点击 **应用配置** 会自动重启对应长连接。个人微信扫码绑定成功后会自动写入并重启 iLink 连接。

 ---

@@ -235,7 +425,30 @@ curl -X POST "http://localhost:8080/api/robot/test" \

 ---

-## 九、钉钉发消息没反应时排查
+## 九、发消息没反应时排查
+
+### 9.1 个人微信
+
+按顺序检查：
+
+1. **是否已完成扫码绑定**  
+   机器人设置页应显示「已连接」或已绑定 Bot ID；`config.yaml` 中 `robots.wechat.bot_token` 不应为空。
+
+2. **是否已启用**  
+   确认「启用微信机器人」已勾选；若刚修改过，可重启 CyberStrikeAI 进程。
+
+3. **看程序日志**  
+   - 启动后应看到：`微信 iLink 长轮询已启动`；  
+   - 发消息后应有：`微信收到消息`；若没有，多为未绑定成功或 `bot_token` 失效，可尝试 **重新绑定**。  
+   - 若出现 `微信 iLink 长轮询异常，将自动重连`，等待自动重连或重启进程。
+
+4. **网络**  
+   服务器需能访问 `https://ilinkai.weixin.qq.com`（出站 HTTPS）。绑定阶段若无法生成二维码，优先检查此项。
+
+5. **断网或睡眠后**  
+   与钉钉/飞书类似，程序会**自动重连**（约 5～60 秒）；仍无回复可重启 CyberStrikeAI。
+
+### 9.2 钉钉

 按顺序检查：

@@ -260,8 +473,10 @@ curl -X POST "http://localhost:8080/api/robot/test" \

 ## 十、常见弯路（避免踩坑）

+- **个人微信与企业微信混淆**：个人微信走 `robots.wechat` + Web 扫码绑定；企业微信走 `robots.wecom` + 管理后台回调 URL，二者完全不同。  
+- **个人微信二维码过期**：二维码约 5 分钟有效，过期需重新生成，不要一直扫旧码。  
 - **用错了机器人类型**：在钉钉**群里**添加的「自定义」机器人（Webhook + 加签）**不能**用来做对话，本程序只支持**开放平台「企业内部应用」**里的机器人。  
- **只保存没重启**：在 CyberStrikeAI 里改完机器人配置后必须**重启应用**，否则长连接不会建立。  
+- **只保存没重启**：钉钉/飞书改完配置后必须**重启应用**，否则长连接不会建立（个人微信扫码绑定会自动重启连接）。  
 - **Client ID 抄错**：开放平台是 `504` 就填 `504`，不要填成 `5o4`；尽量用复制粘贴。  
 - **钉钉只开了 HTTP 回调没开 Stream**：本程序通过 **Stream 长连接**收消息，开放平台里机器人的消息接收方式必须选 **Stream 模式**。  
 - **应用没发布**：开放平台里修改了机器人或权限后，要在「版本管理与发布」里**发布新版本**，否则不生效。
@@ -270,6 +485,7 @@ curl -X POST "http://localhost:8080/api/robot/test" \

 ## 十一、注意事项

- 钉钉、飞书均**仅处理文本消息**；其他类型（如图片、语音）会提示暂不支持或忽略。  
+- 各平台均**仅处理文本消息**；其他类型（如图片、语音）会提示暂不支持或忽略。  
+- 个人微信仅支持**私聊**，不支持群聊 @ 机器人。  
 - 会话与 Web 端共用同一套对话数据：在机器人里创建的对话会在 Web 端「对话」列表中看到，反之亦然。  
- 机器人执行与 **Eino 单/多代理** 相同逻辑（`ProcessMessageForRobot`，含进度回调与过程详情入库），仅不向客户端推送 SSE，最后一次性回复钉钉/飞书/企业微信。默认 `robot_default_agent_mode: eino_single`。
+- 机器人执行与 **Eino 单/多代理** 相同逻辑（`ProcessMessageForRobot`，含进度回调与过程详情入库），仅不向客户端推送 SSE，最后一次性回复个人微信/钉钉/飞书/企业微信。默认 `robot_default_agent_mode: eino_single`。
@@ -2,7 +2,7 @@

 [中文](robot.md)

-This document explains how to chat with CyberStrikeAI from **DingTalk**, **Lark (Feishu)**, and **WeCom (Enterprise WeChat)** using long-lived connections or HTTP callbacks—no need to open a browser on the server. Following the steps below helps avoid common mistakes.
+This document explains how to chat with CyberStrikeAI from **personal WeChat**, **DingTalk**, **Lark (Feishu)**, and **WeCom (Enterprise WeChat)** using long-lived connections or HTTP callbacks—no need to open a browser on the server. Following the steps below helps avoid common mistakes.

 ---

@@ -11,11 +11,14 @@ This document explains how to chat with CyberStrikeAI from **DingTalk**, **Lark
 1. Log in to the CyberStrikeAI web UI.
 2. Open **System Settings** in the left sidebar.
 3. Click **Robot settings** (between “Basic” and “Security”).
-4. Enable the platform and fill in credentials (DingTalk: Client ID / Client Secret; Lark: App ID / App Secret).
-5. Click **Apply configuration** to save.
-6. **Restart the CyberStrikeAI process** (saving alone does not establish the connection).
+4. Configure per platform:
+   - **Personal WeChat**: Open **WeChat / iLink** → **Generate QR code and bind**, then scan with WeChat (see [Section 3.4](#34-personal-wechat-wechat--ilink))
+   - **DingTalk**: Enable and fill in Client ID / Client Secret
+   - **Lark**: Enable and fill in App ID / App Secret
+5. Click **Apply configuration** to save (WeChat binding saves and enables automatically on success—usually no extra click needed)
+6. **Restart the CyberStrikeAI process** (DingTalk/Lark: saving alone does not establish the connection; WeChat auto-restarts the iLink poll after binding—usually no manual restart needed)

-Settings are written to the `robots` section of `config.yaml`; you can also edit the file directly. **After changing DingTalk or Lark config, you must restart for the long-lived connection to take effect.**
+Settings are written to the `robots` section of `config.yaml`; you can also edit the file directly. **After changing DingTalk or Lark config, you must restart for the long-lived connection to take effect.** Personal WeChat binding automatically writes `robots.wechat` and restarts the iLink long poll.

 ---

@@ -23,9 +26,14 @@ Settings are written to the `robots` section of `config.yaml`; you can also edit

 | Platform       | Description |
 |----------------|-------------|
+| Personal WeChat| WeChat iLink protocol; scan QR in the web UI to bind, then long-poll for messages—**no public callback URL needed** |
 | DingTalk       | Stream long-lived connection; the app connects to DingTalk to receive messages |
 | Lark (Feishu)  | Long-lived connection; the app connects to Lark to receive messages |
 | WeCom (Qiye WX)| HTTP callback to receive messages; CyberStrikeAI replies via WeCom’s message sending API |
+| Telegram       | Bot API long polling (`getUpdates`); **no public callback URL needed** |
+| Slack          | Socket Mode (outbound WebSocket); **no public callback URL needed** |
+| Discord        | Gateway WebSocket; **no public callback URL needed** |
+| QQ Bot         | QQ Open Platform WebSocket (C2C / group @); **no public callback URL needed** |

 Section 3 below describes, per platform, what to do in the developer console and which fields to copy into CyberStrikeAI.

@@ -148,9 +156,125 @@ In **Permission management** (权限管理), enable the following (names and ide

 ---

+### 3.4 Personal WeChat (WeChat / iLink)
+
+> Personal WeChat uses **“web QR binding + iLink long polling”**:  
+> - Generate a QR code in the CyberStrikeAI web UI → scan and confirm with **WeChat on your phone**;  
+> - On success, `robots.wechat` in `config.yaml` is updated automatically and iLink long polling starts (the app connects outbound to `ilinkai.weixin.qq.com`);  
+> - **No** public callback URL on your server and **no** WeChat Open Platform app registration required.
+
+**Personal WeChat vs WeCom**
+
+| Item | Personal WeChat (iLink) | WeCom (Enterprise WeChat) |
+|------|-------------------------|---------------------------|
+| Use case | Private chat in personal WeChat | Custom app in WeCom |
+| Setup | QR scan in web UI | Admin console callback URL + Token |
+| Public IP needed? | No (outbound long poll only) | Yes (HTTPS callback reachable by WeCom) |
+| Config key | `robots.wechat` | `robots.wecom` |
+
+**Binding steps (in order)**
+
+1. **Log in to CyberStrikeAI web UI**  
+   **System settings** → **Robot settings** → click the **WeChat / iLink** card.
+
+2. **(Optional) Enable “Enable WeChat robot”**  
+   You can skip this on first bind; it is checked automatically after a successful bind.
+
+3. **Generate QR code**  
+   Click **“Generate QR code and bind”**. The QR code is valid for about **5 minutes**; regenerate if it expires.
+
+4. **Scan and confirm in WeChat**  
+   - Scan the QR code with WeChat on your phone;  
+   - Complete confirmation on the phone;  
+   - If WeChat shows a **pairing code**, enter it on the web page and click **Submit** (only some accounts need this).
+
+5. **Wait for binding to complete**  
+   When the page shows “Binding successful, WeChat robot enabled”, you’re done. `bot_token`, `ilink_bot_id`, etc. are saved to `config.yaml` and the iLink poll restarts automatically—**usually no manual service restart**.
+
+6. **Test in WeChat**  
+   Open the **private chat** with the CyberStrikeAI bot in WeChat and send “帮助” (help) or any text.
+
+**Field reference (WeChat)**
+
+| Field | Description |
+|-------|-------------|
+| Enable WeChat robot | Starts iLink long polling when checked; auto-enabled after bind |
+| Generate QR code and bind | Starts the scan-to-bind flow |
+| **Advanced** (defaults are fine) | |
+| API Base URL | Default `https://ilinkai.weixin.qq.com` |
+| Bot Type | Default `3` |
+| Bot Agent | Default `CyberStrikeAI/1.0` |
+| iLink Bot ID | Filled automatically after bind (read-only) |
+
+**How to use**
+
+- **Private chat only**—send text directly; **no @ needed**.  
+- Group @-bot is **not** supported (unlike DingTalk/Lark groups).  
+- **Text messages only**; images, voice, etc. are ignored or not supported.
+
+**Re-bind**
+
+- To bind a different WeChat account, click **“Re-bind”** on the robot settings page and scan again.  
+- If you see “This WeChat account is already bound”, that account was bound before.
+
+**Common issues**
+
+| Symptom | What to do |
+|---------|------------|
+| QR code expired | Click “Generate QR code and bind” again (~5 min TTL) |
+| Phone asks for a pairing code | Enter the digits shown in WeChat on the web page |
+| Bound but no replies | Check logs for `微信 iLink 长轮询已启动` and `微信收到消息`; ensure “Enable WeChat robot” is on |
+| No reply after sleep / network drop | Auto-reconnect in ~5–60 s; restart CyberStrikeAI if still stuck |
+| Cannot generate QR code | Ensure outbound HTTPS to `https://ilinkai.weixin.qq.com` |
+
+---
+
+### 3.5 Telegram
+
+> Telegram uses **Bot API long polling** (`getUpdates`): the app connects outbound to `api.telegram.org`—**no public callback URL needed**.
+
+1. Create a bot via **@BotFather** (`/newbot`) and copy the **Bot Token**.  
+2. CyberStrikeAI → **System settings** → **Robot settings** → **Telegram**.  
+3. Enable, paste the token, optionally allow group @ mentions → **Apply configuration**.
+
+---
+
+### 3.6 Slack
+
+> Slack uses **Socket Mode** (outbound WebSocket): requires **Bot Token (xoxb-)** and **App-Level Token (xapp-)** with `connections:write`.
+
+1. Create an app at [api.slack.com](https://api.slack.com/apps) → enable **Socket Mode**.  
+2. Create an App-Level Token; install the app to get a Bot Token.  
+3. Subscribe to `message.im` and `app_mention` events.  
+4. Paste both tokens in CyberStrikeAI → **Apply configuration**.
+
+---
+
+### 3.7 Discord
+
+> Discord uses **Gateway WebSocket**—**no public callback URL needed**.
+
+1. [Discord Developer Portal](https://discord.com/developers/applications) → create app → **Bot** → copy **Token**.  
+2. Enable **Message Content Intent** under Privileged Gateway Intents.  
+3. Invite the bot with `Send Messages` permission.  
+4. Paste token in CyberStrikeAI; optionally allow guild @ mentions → **Apply configuration**.
+
+---
+
+### 3.8 QQ Bot
+
+> QQ Bot uses **QQ Open Platform WebSocket** (official `botgo` SDK) for C2C and group @—**no public callback URL needed**.
+
+1. Create a bot at [q.qq.com](https://q.qq.com) → get **App ID** and **Client Secret**.  
+2. Add sandbox testers before going live.  
+3. Subscribe to C2C and group @ events (WebSocket).  
+4. Fill in CyberStrikeAI; use **Sandbox** for testing → **Apply configuration**.
+
+---
+
 ## 4. Bot commands

-Send these **text commands** to the bot in DingTalk or Lark (text only):
+Send these **text commands** to the bot on any connected platform (text only):

 | Command | Description |
 |---------|-------------|
@@ -172,15 +296,24 @@ Any other text is sent to the AI as a user message, same as in the web UI (e.g.

 ## 5. How to use (do I need to @ the bot?)

- **Direct chat (recommended)**: In DingTalk or Lark, **search for the bot and open a direct chat**. Type “帮助” or any message; **no @ needed**.  
- **Group chat**: If the bot is in a group, only messages that **@ the bot** are received and answered; other group messages are ignored.
+- **Personal WeChat**: Send directly in the **private chat** with the bot; **no @ needed** (group chat not supported).  
+- **DingTalk / Lark direct chat (recommended)**: **Search for the bot and open a direct chat**. Type “帮助” or any message; **no @ needed**.  
+- **DingTalk / Lark group chat**: If the bot is in a group, only messages that **@ the bot** are received and answered; other group messages are ignored.

-Summary: **Direct chat** — just send; **in a group** — @ the bot first, then send.
+Summary: **Personal WeChat and direct chat**—just send; **DingTalk/Lark in a group**—@ the bot first, then send.

 ---

 ## 6. Recommended flow (so you don’t skip steps)

+**Personal WeChat (simplest—no open platform)**
+
+1. CyberStrikeAI web UI → System settings → Robot settings → **WeChat / iLink** → **Generate QR code and bind**.  
+2. Scan with WeChat and confirm (enter pairing code on the web page if prompted).  
+3. After binding, send “帮助” in the WeChat private chat to test.
+
+**DingTalk / Lark**
+
 1. **In the open platform**: Complete app creation, copy credentials, enable the bot (DingTalk: **Stream mode**), set permissions, and publish (Section 3).  
 2. **In CyberStrikeAI**: System settings → Robot settings → Enable the platform, paste Client ID/App ID and Client Secret/App Secret → **Apply configuration**.  
 3. **Restart the CyberStrikeAI process** (otherwise the long-lived connection is not established).  
@@ -196,6 +329,14 @@ Example `robots` section in `config.yaml`:

 ```yaml
 robots:
+  wechat: # Personal WeChat iLink (auto-filled after QR bind; usually no manual edit)
+    enabled: true
+    bot_token: "your_bot_token@im.bot:..."
+    ilink_bot_id: "your_bot_id@im.bot"
+    ilink_user_id: "your_user_id@im.wechat"
+    base_url: "https://ilinkai.weixin.qq.com"
+    bot_type: "3"
+    bot_agent: "CyberStrikeAI/1.0"
  dingtalk:
    enabled: true
    client_id: "your_dingtalk_app_key"
@@ -205,9 +346,33 @@ robots:
    app_id: "your_lark_app_id"
    app_secret: "your_lark_app_secret"
    verify_token: ""
+  wecom:
+    enabled: false
+    corp_id: ""
+    agent_id: 0
+    token: ""
+    encoding_aes_key: ""
+    secret: ""
+  telegram:
+    enabled: false
+    bot_token: ""
+    allow_group_messages: false
+  slack:
+    enabled: false
+    bot_token: ""
+    app_token: ""
+  discord:
+    enabled: false
+    bot_token: ""
+    allow_guild_messages: false
+  qq:
+    enabled: false
+    app_id: ""
+    client_secret: ""
+    sandbox: true
 ```

-**Restart the app** after changes; the long-lived connection is created at startup.
+After changing DingTalk/Lark/WeCom/Telegram/Slack/Discord/QQ settings, **Apply configuration** restarts the corresponding connections. Personal WeChat QR binding saves and restarts automatically.

 ---

@@ -232,7 +397,30 @@ API: `POST /api/robot/test` (requires login). Body: `{"platform":"optional","use

 ---

-## 9. DingTalk: no response when sending messages
+## 9. Troubleshooting: no response when sending messages
+
+### 9.1 Personal WeChat
+
+Check in this order:
+
+1. **Binding completed?**  
+   Robot settings should show “Connected” or a bound Bot ID; `robots.wechat.bot_token` in `config.yaml` must not be empty.
+
+2. **Enabled?**  
+   Confirm “Enable WeChat robot” is checked; restart CyberStrikeAI if you just changed settings.
+
+3. **Application logs**  
+   - On startup: `微信 iLink 长轮询已启动`;  
+   - After sending a message: `微信收到消息`; if missing, binding may have failed or `bot_token` is invalid—try **Re-bind**.  
+   - `微信 iLink 长轮询异常，将自动重连`: wait for auto-reconnect or restart.
+
+4. **Network**  
+   The server must reach `https://ilinkai.weixin.qq.com` (outbound HTTPS). If QR generation fails, check this first.
+
+5. **After sleep or network drop**  
+   Same as DingTalk/Lark: **auto-reconnect** in ~5–60 s; restart if still no response.
+
+### 9.2 DingTalk

 Check in this order:

@@ -257,8 +445,10 @@ Check in this order:

 ## 10. Common pitfalls

+- **Personal WeChat vs WeCom**: Personal WeChat uses `robots.wechat` + web QR bind; WeCom uses `robots.wecom` + admin callback URL—they are completely different.  
+- **WeChat QR expired**: QR codes last ~5 minutes; regenerate instead of reusing an old one.  
 - **Wrong bot type**: The “Custom” bot added in a DingTalk **group** (Webhook + sign secret) **cannot** be used for two-way chat. Only the **enterprise internal app** bot from the open platform is supported.  
- **Saved but not restarted**: After changing robot settings in CyberStrikeAI you **must restart** the app, or the long-lived connection will not be established.  
+- **Saved but not restarted**: After changing DingTalk/Lark robot settings you **must restart** the app (WeChat QR bind restarts the connection automatically).  
 - **Client ID typo**: If the platform shows `504`, use `504` (not `5o4`); prefer copy/paste.  
 - **DingTalk: only HTTP callback, no Stream**: This app receives messages via **Stream**. In the open platform, message reception must be **Stream mode**.  
 - **App not published**: After changing the bot or permissions in the open platform, **publish a new version** under “Version management and release”, or changes won’t apply.
@@ -267,6 +457,7 @@ Check in this order:

 ## 11. Notes

- DingTalk and Lark: **text messages only**; other types (e.g. image, voice) are not supported and may be ignored.  
+- All platforms: **text messages only**; other types (e.g. image, voice) are not supported and may be ignored.  
+- Personal WeChat: **private chat only**—group @-bot is not supported.  
 - Conversations are shared with the web UI: conversations created from the bot appear in the web “Conversations” list and vice versa.  
- Bot execution uses the same **Eino single/multi-agent** path as the web UI (`ProcessMessageForRobot`, with progress callbacks and process details stored in the DB); only the final reply is sent back to DingTalk/Lark in one message (no SSE). Default: `robot_default_agent_mode: eino_single`.
+- Bot execution uses the same **Eino single/multi-agent** path as the web UI (`ProcessMessageForRobot`, with progress callbacks and process details stored in the DB); only the final reply is sent back to personal WeChat/DingTalk/Lark/WeCom in one message (no SSE). Default: `robot_default_agent_mode: eino_single`.
@@ -0,0 +1,553 @@
+# CyberStrikeAI 图编排使用说明
+
+[English](workflow-graph_en.md)
+
+本文档说明 **图编排（Graph Orchestration）** 的完整使用方式：如何在画布上搭建流程、配置各类型节点、在节点之间传递数据，以及如何将流程绑定到角色并自动运行。
+
+---
+
+## 一、在哪里使用图编排
+
+1. 登录 CyberStrikeAI Web 端  
+2. 左侧导航进入 **图编排**  
+3. 在左侧列表选择已有流程，或新建流程  
+4. 在中央画布拖拽、连线、配置节点  
+5. 填写流程 **ID**、**名称**、**描述** 后点击 **保存**
+
+保存后的流程可在 **角色管理** 中绑定到某个角色。绑定后，用户与该角色对话时会按流程图自动执行（`workflow_policy: auto`）。
+
+---
+
+## 二、画布基本操作
+
+| 操作 | 说明 |
+|------|------|
+| 添加节点 | 点击画布上方节点类型按钮（开始、工具、Agent、条件、审批、输出、结束） |
+| 连线 | 点击 **连线**，依次点击源节点和目标节点；再次点击 **连线** 退出连线模式 |
+| 选中元素 | 单击节点或连线，右侧显示 **节点属性** |
+| 删除选中 | 点击 **删除选中** 删除当前节点或连线 |
+| 自动布局 | 点击 **自动布局** 整理节点位置 |
+| 试运行 | 点击 **试运行** 使用安全 dry-run 验证数据流；工具、Agent、审批不会真实执行 |
+| 删除流程 | 点击 **删除** 删除整个流程定义 |
+
+**硬性规则：** 每个流程至少包含 **1 个开始节点** 和 **1 个输出节点**；开始节点不能有入边，输出 / 结束节点不能有出边。保存时前端和后端都会执行严格校验。
+
+---
+
+## 三、执行模型（先理解再配置）
+
+图编排按 **有向图** 执行，引擎从 **开始** 节点出发，沿连线依次运行下游节点。
+
+每次运行会维护一份内部状态，模板变量 `{{...}}` 从这里取值：
+
+| 内部状态 | 模板前缀 | 含义 |
+|----------|----------|------|
+| `inputs` | `{{inputs.xxx}}` | 流程启动时的输入（用户消息、会话 ID 等） |
+| `lastOutput` | `{{previous.xxx}}` | **上一个刚执行完** 的节点的输出 |
+| `outputs` | `{{outputs.xxx}}` | 全局 **命名变量池**（由节点的「输出变量名」写入） |
+| `nodeOutputs` | `{{节点ID.xxx}}` | 指定节点 ID 的完整输出对象 |
+| `metrics` | 运行详情中查看 | 节点耗时、工具调用数、可收集到的 token / cost 等指标 |
+
+### 3.1 `previous` 是什么？
+
+`{{previous.output}}` 表示 **紧邻的上一个执行节点** 的 `output` 字段。
+
+- 每执行完一个节点，引擎都会更新 `lastOutput`
+- **不是**「画布上画线的上游」，而是 **实际执行顺序上的上一步**
+
+示例：
+
+```text
+开始 → Agent A → Agent B
+```
+
+Agent B 的 `{{previous.output}}` = Agent A 的输出。
+
+但若中间有条件节点：
+
+```text
+开始 → Agent A → 条件 → Agent B
+```
+
+Agent B 的 `{{previous.output}}` = **条件节点** 的输出（`true` / `false`），**不是** Agent A 的结果。
+
+如果一个节点有 **多个上游节点** 同时连入，`previous` 会先按该节点的 **汇聚策略** 生成：
+
+| 汇聚策略 | 含义 | 适合场景 |
+|----------|------|----------|
+| `all_merge` | 合并所有上游输出，`previous.output` 为数组 | 默认推荐，综合多路结果 |
+| `last_by_canvas` | 按画布顺序取最后一个上游输出 | 明确只采用一路结果 |
+| `first_non_empty` | 取第一个非空输出 | 多路兜底 |
+| `fail_fast` | 任一上游失败则中止当前节点 | 关键链路、审批前置、安全检查 |
+
+### 3.2 `outputs` 是什么？
+
+`outputs` 是引擎在运行过程中维护的 **命名变量注册表**。
+
+当 Agent、工具、输出 等节点配置了 **输出变量名**（字段 `output_key`）后，节点执行成功会把结果写入：
+
+```text
+outputs["你填的变量名"] = 节点输出内容
+```
+
+之后 **任意下游节点** 都可以通过 `{{outputs.变量名}}` 引用，不要求两个节点直接相连。
+
+示例：
+
+- Agent A 的 **输出变量名** 填 `agent_result1`
+- Agent B 的 **输入来源** 填 `{{outputs.agent_result1}}`
+
+即使 A 和 B 之间隔着条件节点，B 仍能拿到 A 的输出。
+
+### 3.3 什么时候用 `previous`，什么时候用 `outputs`？
+
+| 场景 | 推荐写法 |
+|------|----------|
+| 两个节点 **直连**，只取上一步结果 | `{{previous.output}}` |
+| 中间有其他节点（条件、工具、审批等） | `{{outputs.变量名}}` |
+| 需要引用 **更早** 的某个节点结果 | `{{outputs.变量名}}` 或 `{{节点ID.output}}` |
+| 条件判断要基于某 Agent 的输出 | `{{outputs.变量名}} != ""` |
+| 读取用户最初输入 | `{{inputs.message}}` |
+
+**记忆口诀：**
+
+- `previous` = 上一步（链式、紧邻）
+- `outputs` = 按名字取（跨节点、可回溯）
+
+---
+
+## 四、模板语法
+
+### 4.1 基本格式
+
+```text
+{{变量路径}}
+```
+
+支持字母、数字、下划线、点、连字符，例如：
+
+```text
+{{previous.output}}
+{{outputs.agent_result1}}
+{{inputs.message}}
+{{inputs.conversationId}}
+{{previous.matched}}
+{{node-abc123.output}}
+```
+
+### 4.2 可用路径一览
+
+| 路径 | 说明 |
+|------|------|
+| `{{inputs.message}}` | 用户消息（开始节点输入） |
+| `{{inputs.conversationId}}` | 会话 ID |
+| `{{inputs.projectId}}` | 项目 ID |
+| `{{previous.output}}` | 上一节点主输出 |
+| `{{previous.matched}}` | 上一条件节点的匹配结果（`true` / `false`） |
+| `{{outputs.变量名}}` | 某节点注册过的命名输出 |
+| `{{节点ID.output}}` | 指定节点 ID 的 `output` 字段 |
+| `{{previous.kind}}` | 上一节点输出类型，如 `agent` / `tool` / `condition` |
+| `{{previous.status}}` | 上一节点状态，如 `completed` / `failed` / `simulated` |
+
+节点输出会保留兼容字段（如 `output`、`matched`），同时带有结构化字段：
+
+```json
+{
+  "kind": "agent",
+  "node_id": "node-2",
+  "node_type": "agent",
+  "status": "completed",
+  "output": "..."
+}
+```
+
+### 4.3 条件表达式
+
+条件节点和连线条件支持比较、文本匹配、正则、逻辑组合与安全 JSONPath/JQ 路径读取：
+
+```text
+{{outputs.agent_result1}} != ""
+{{previous.output}} == "ok"
+{{outputs.count}} >= 100
+{{previous.output}} contains "success"
+{{previous.output}} matches "^ok"
+{{outputs.risk_score}} >= 8 && {{previous.output}} != ""
+jsonpath({{previous.output}}, "$.status") == "ok"
+jq({{outputs.scan}}, ".severity") == "high"
+```
+
+规则：
+
+- 支持 `==`、`!=`、`>`、`>=`、`<`、`<=`
+- 支持 `contains` 子串匹配与 `matches` 正则匹配
+- 支持简单 `&&` / `||`
+- 支持 `jsonpath(value, "$.path")` 与 `jq(value, ".path")` 的**安全路径子集**，仅做字段读取，不执行任意脚本
+- 比较两侧会自动去掉首尾空格和引号
+- 无比较符时，非空且不为 `false` / `0` / `null` 视为真
+- 保存时会静态校验表达式格式、JSONPath/JQ 路径和正则语法
+
+### 4.4 嵌套字段绑定
+
+节点的字段绑定除 `output`、`message` 等普通字段外，也支持 JSONPath/JQ 风格路径：
+
+| 绑定配置 | 含义 |
+|----------|------|
+| `from=previous, field=$.status` | 从上一节点输出对象读取 `status` |
+| `from=outputs, field=$.scan.severity` | 从命名输出中读取嵌套字段 |
+| `from=node-1, field=.output.items[0]` | 从指定节点输出读取数组元素 |
+
+---
+
+## 五、节点类型与配置
+
+### 5.1 开始（start）
+
+流程入口，将用户输入注入 `inputs`。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| 输入变量 | 逗号分隔的输入键名 | `message, conversationId, projectId` |
+
+开始节点输出包含：`output`、`message`、`conversationId`、`projectId`。
+
+### 5.2 Agent（agent）
+
+调用大模型 Agent 处理任务，支持多种运行模式。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| Agent 模式 | `eino_single` / `deep` / `plan_execute` / `supervisor` | `eino_single` |
+| 输入来源 | 上游数据的模板表达式 | `{{previous.output}}` |
+| 节点指令 | 本节点要完成的任务描述 | 空 |
+| 输出变量名 | 写入 `outputs` 的键名 | `agent_result` |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+**消息拼装规则：**
+
+- 仅填 **节点指令**：直接把指令发给 Agent  
+- 仅填 **输入来源**：生成「请基于上游节点输出继续处理：…」  
+- 两者都填：合并为「上游输入 + 节点指令」
+
+Agent 节点执行后：
+
+- `previous.output` 更新为本节点响应文本  
+- 若配置了 **输出变量名**，同时写入 `outputs[输出变量名]`
+- Agent 子图在 Eino 中拆为 `prepare → execute → finalize`，便于 trace 与后续局部 checkpoint
+
+### 5.3 工具（tool）
+
+调用已启用的 MCP 工具。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| MCP 工具 | 工具名称（必填） | — |
+| 参数模板 | JSON，支持 `{{...}}` 模板 | `{}` |
+| 超时秒数 | 可选 | 空 |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+示例参数模板：
+
+```json
+{"target": "{{inputs.message}}", "port": "443"}
+```
+
+若配置了 **输出变量名**，工具返回结果会写入 `outputs`。
+
+### 5.4 条件（condition）
+
+根据表达式计算分支，输出 `matched`（`true` / `false`）。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| 条件表达式 | 支持 `{{...}}` 与 `==` / `!=` | `{{previous.output}} != ""` |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+**分支规则：**
+
+- 从条件节点连出的 **第一条线** 默认为 **「是」** 分支（`matched == true`）
+- **第二条线** 默认为 **「否」** 分支（`matched == false`）
+- 连线标签可写 `是` / `否`（或 `yes` / `no`、`true` / `false`）辅助识别
+- 第三条及以后的出边需在 **连线条件** 中自定义表达式
+
+连线条件示例（选中连线后在右侧配置）：
+
+```text
+{{previous.matched}} == "true"
+{{previous.matched}} == "false"
+```
+
+### 5.5 审批（hitl）
+
+人工确认检查点。流程运行到该节点前会通过 Eino interrupt/checkpoint 暂停，等待 API 或监控面板审批后恢复。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| 审批提示 | 支持模板 | `请审批该步骤是否继续执行` |
+| 提示字段绑定 | 留空审批提示时，从绑定字段读取说明 | `previous.output` |
+| 审批方 | `human` / `audit_agent` | `human` |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+HITL 等待信息会记录：
+
+- `checkpointId`
+- interrupt `beforeNodes`
+- resume target / address / path
+- resume payload schema（`approved`、`comment`）
+
+### 5.6 输出（output）
+
+将流程最终结果写入 `outputs`，供结束摘要和对话展示使用。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| 输出变量名 | 必填，最终结果的键名 | `result` |
+| 变量来源 | 模板表达式，决定写入的值 | `{{previous.output}}` |
+| 固定输出值 | 可选，填写后覆盖变量来源 | 空 |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+**注意：** 输出节点是流程的「出口」，不应再有出边。
+
+### 5.7 结束（end）
+
+可选节点，用于生成结束摘要模板（角色绑定流程中较少单独使用）。
+
+| 字段 | 说明 | 默认值 |
+|------|------|--------|
+| 结束摘要模板 | 支持 `{{outputs.xxx}}` | `{{outputs.result}}` |
+| 汇聚策略 | 多上游进入本节点时如何生成 `previous` | `all_merge` |
+
+---
+
+## 六、连线配置
+
+选中 **连线** 后，右侧可配置 **连线条件**。
+
+| 场景 | 示例 |
+|------|------|
+| 普通节点后的过滤 | `{{previous.output}} == "ok"` |
+| 条件节点「是」分支 | `{{previous.matched}} == "true"` |
+| 条件节点「否」分支 | `{{previous.matched}} == "false"` |
+
+若不填连线条件：
+
+- 非条件节点：连线始终放行  
+- 条件节点：按出边顺序自动分配是/否分支
+
+---
+
+## 七、完整示例：跨条件节点传递 Agent 输出
+
+### 7.1 流程结构
+
+```text
+开始 → Agent（生成初始值）→ 条件 → Agent（加工）→ 输出
+                              ↘ 否 → 输出
+```
+
+### 7.2 节点配置
+
+**Agent 1（第一个 Agent）**
+
+| 字段 | 值 |
+|------|-----|
+| 节点指令 | 只输出 `123333333` |
+| 输出变量名 | `agent_result1` |
+
+**条件**
+
+| 字段 | 值 |
+|------|-----|
+| 条件表达式 | `{{outputs.agent_result1}} != ""` |
+
+**Agent 2（第二个 Agent）**
+
+| 字段 | 值 |
+|------|-----|
+| 输入来源 | `{{outputs.agent_result1}}` |
+| 节点指令 | 在输入基础上加 100，然后输出 |
+| 输出变量名 | `agent_result` |
+
+**输出**
+
+| 字段 | 值 |
+|------|-----|
+| 输出变量名 | `result` |
+| 变量来源 | `{{outputs.agent_result}}` |
+
+### 7.3 常见错误
+
+| 错误配置 | 原因 |
+|----------|------|
+| Agent 2 输入来源写 `{{previous.output}}` | `previous` 指向条件节点，得到的是 `true`/`false`，不是 Agent 1 的文本 |
+| 未给 Agent 1 填输出变量名 | `outputs.agent_result1` 不存在，下游取到空值 |
+| 条件表达式写 `{{previous.output}}` | 判断的是开始节点或上一节点的输出，而非 Agent 1 的命名变量 |
+
+---
+
+## 八、绑定角色并运行
+
+### 8.1 在角色管理中绑定
+
+1. 进入 **角色管理**，编辑或新建角色  
+2. 选择 **工作流 / 图编排** 绑定的流程 ID  
+3. 策略设为 `auto`（默认：有 `workflow_id` 时自动执行）  
+4. 保存角色
+
+也可在角色 YAML 中直接配置：
+
+```yaml
+name: 工作流测试
+workflow_id: "1233"
+workflow_version: latest
+workflow_policy: auto
+```
+
+### 8.2 运行效果
+
+用户选择该角色并发送消息后：
+
+1. 引擎加载对应 `graph_json` 并按图执行  
+2. 对话页可看到 `workflow_start`、`workflow_node_start`、Agent 推理等进度事件  
+3. 流程结束后返回摘要，列出 `outputs` 中所有命名输出
+
+若未配置输出节点或条件未命中，`outputs` 可能为空，摘要会提示检查输出节点与分支。
+
+---
+
+## 九、调试、试运行与复盘
+
+### 9.1 安全试运行（dry-run）
+
+画布工具栏点击 **试运行**，输入一条测试消息即可模拟执行流程。
+
+dry-run 的安全边界：
+
+- `start` / `condition` / `output` / `end` 会按真实逻辑计算
+- `tool` 不会真实调用 MCP，只返回 `[dry-run] tool call skipped`
+- `agent` 不会真实调用模型，只返回 `[dry-run] agent execution skipped`
+- `hitl` 不会暂停，只模拟通过
+
+相关 API：
+
+```http
+POST /api/workflows/dry-run
+```
+
+请求体：
+
+```json
+{
+  "graph": { "nodes": [], "edges": [], "config": {} },
+  "inputs": { "message": "ping" }
+}
+```
+
+响应包含：
+
+- `outputs`
+- `nodeOutputs`
+- `trace`
+- `metrics`
+- `replayScript`
+
+### 9.2 运行详情与 replay
+
+运行后可查询完整节点执行轨迹：
+
+```http
+GET /api/workflows/runs/{runId}
+```
+
+返回 `run` 与 `nodeRuns`，每个节点记录包含：
+
+- input 快照
+- output 快照
+- status / error
+- started_at / finished_at
+- `duration_ms`
+
+复盘接口：
+
+```http
+GET /api/workflows/runs/{runId}/replay
+```
+
+该接口只根据已保存的 `nodeRuns` 生成步骤，不会重新执行工具或 Agent。
+
+### 9.3 指标（metrics）
+
+工作流会尽量累计：
+
+- `node_count`
+- `duration_ms`
+- `tool_call_count`
+- Agent progress 中可收集到的 `prompt_tokens` / `completion_tokens` / `total_tokens` / `cost`
+
+token 与成本是否存在取决于底层模型/Agent 事件是否上报 usage。
+
+---
+
+## 十、保存前校验规则
+
+保存时系统会自动检查：
+
+| 规则 | 说明 |
+|------|------|
+| 必须有开始节点 | 至少 1 个 `start` |
+| 必须有输出节点 | 至少 1 个 `output`，且填写输出变量名 |
+| 连线合法 | 源/目标节点存在，不能自环 |
+| 开始节点无入边 | 开始节点不能被指向 |
+| 输出 / 结束节点无出边 | 输出 / 结束节点后不应再连线 |
+| 非开始节点必须有入边 | 避免孤岛节点 |
+| 非输出 / 结束节点必须有出边 | 避免执行到死路 |
+| 无环路 | Workflow 编排必须是 DAG |
+| 可达性 | 所有节点必须能从开始节点到达，并能最终到达 output/end |
+| 工具节点 | 必须选择 MCP 工具；参数 JSON 必须合法；超时必须为正整数 |
+| Agent 节点 | 必须填写节点指令或输入绑定；必须填写输出变量名 |
+| 条件节点 | 必须填写表达式；需要 1～2 条出边；分支必须标记是/否且不能重复 |
+| 连线条件 | 表达式、正则、JSONPath/JQ 路径必须通过静态校验 |
+| 汇聚策略 | 必须是 `all_merge` / `last_by_canvas` / `first_non_empty` / `fail_fast` |
+
+---
+
+## 十一、排错指南
+
+| 现象 | 可能原因 | 处理建议 |
+|------|----------|----------|
+| 下游拿到空值 | 上游未配置输出变量名 | 给上游 Agent/工具填 **输出变量名**，下游用 `{{outputs.xxx}}` |
+| 下游拿到 `true`/`false` | 误用 `{{previous.output}}`，上一步是条件节点 | 改用 `{{outputs.xxx}}` |
+| 条件总走「否」 | 表达式与真实输出格式不一致 | 检查 Agent 输出是否带引号、换行；用 `!= ""` 先验证 |
+| 流程无最终输出 | 未命中输出节点所在分支 | 检查条件分支连线；确保至少一条路径到达 **输出** 节点 |
+| 角色对话未跑流程 | 角色未绑定或未启用 | 确认 `workflow_id`、`workflow_policy: auto`、流程 `enabled: true` |
+| 工具节点失败 | 参数 JSON 不合法或工具未启用 | 检查参数模板；在 MCP 中启用对应工具 |
+| 保存失败提示分支非法 | 条件节点出边未标记是/否或重复 | 选中连线，设置条件分支为 `true` 或 `false` |
+| 多上游结果不符合预期 | 汇聚策略不合适 | 根据场景改为 `all_merge` / `first_non_empty` / `last_by_canvas` / `fail_fast` |
+| 嵌套字段取不到 | JSONPath/JQ 路径不符合安全子集 | 使用 `$.a.b[0]` 或 `.a.b[0]`，不要用通配符/递归/表达式 |
+
+---
+
+## 十二、最佳实践
+
+1. **命名规范**：为每个需要被引用的节点设置有意义的输出变量名，如 `scan_result`、`parsed_targets`，避免都叫 `agent_result`。  
+2. **跨节点传参优先用 `outputs`**：只要中间可能插入条件、工具、审批节点，就应用命名变量。  
+3. **`previous` 仅用于直连**：A → B 且无中间节点时，`{{previous.output}}` 最简洁。  
+4. **条件判断引用源数据**：判断 Agent 输出时用 `{{outputs.xxx}}`，不要用 `{{previous.output}}`（除非条件紧跟在目标 Agent 之后）。  
+5. **每条路径都要有出口**：确保「是」「否」分支最终都能到达 **输出** 节点（或你期望的终点）。  
+6. **多上游节点显式选择汇聚策略**：综合结果用 `all_merge`，兜底用 `first_non_empty`，关键链路用 `fail_fast`。  
+7. **嵌套 JSON 用 JSONPath/JQ 安全路径**：例如 `jsonpath({{previous.output}}, "$.status") == "ok"`。  
+8. **保存前先 dry-run**：用简单消息验证数据传递和分支，再绑定角色真实执行。
+
+---
+
+## 十三、相关代码位置（开发者参考）
+
+| 模块 | 路径 |
+|------|------|
+| 执行引擎 | `internal/workflow/runner.go` |
+| Eino 编译 / checkpoint / HITL | `internal/workflow/eino_compile.go` |
+| 图校验 | `internal/workflow/validation.go` |
+| 表达式 / JSONPath / 汇聚 | `internal/workflow/expression.go`、`jsonpath.go`、`join.go` |
+| dry-run / replay 数据 | `internal/workflow/dry_run.go`、`internal/handler/workflow_run.go` |
+| 画布前端 | `web/static/js/workflows.js` |
+| 流程 API | `internal/handler/workflow.go` |
+| 角色绑定 | `internal/config/config.go`（`workflow_id` 字段） |
@@ -0,0 +1,553 @@
+# CyberStrikeAI Graph Orchestration Guide
+
+[中文](workflow-graph.md)
+
+This document explains how to use **Graph Orchestration**: building workflows on the canvas, configuring node types, passing data between nodes, and binding a graph to a role for automatic execution.
+
+---
+
+## 1. Where to find Graph Orchestration
+
+1. Log in to the CyberStrikeAI web UI.  
+2. Open **Graph Orchestration** in the left sidebar.  
+3. Select an existing workflow from the list, or create a new one.  
+4. Drag nodes, draw edges, and configure properties on the canvas.  
+5. Fill in **ID**, **Name**, and **Description**, then click **Save**.
+
+Saved workflows can be bound to a role under **Role Management**. When `workflow_policy` is `auto`, chatting with that role runs the bound graph automatically.
+
+---
+
+## 2. Canvas basics
+
+| Action | Description |
+|--------|-------------|
+| Add node | Click a node type button above the canvas (Start, Tool, Agent, Condition, HITL, Output, End) |
+| Connect | Click **Connect**, then click source and target nodes; click **Connect** again to exit connect mode |
+| Select | Click a node or edge; properties appear in the right panel |
+| Delete selected | Remove the current node or edge |
+| Auto layout | Rearrange node positions |
+| Dry run | Safely simulate data flow; Tool, Agent, and HITL nodes are not executed for real |
+| Delete workflow | Remove the entire workflow definition |
+
+**Hard requirements:** Every workflow needs at least **one Start node** and **one Output node**. Start nodes must not have incoming edges; Output / End nodes must not have outgoing edges. Both frontend and backend run strict validation before save.
+
+---
+
+## 3. Execution model (read this before configuring)
+
+The engine executes the workflow as a **directed graph**, starting from the **Start** node and following edges to downstream nodes.
+
+During a run, the engine keeps internal state. Template expressions `{{...}}` read from that state:
+
+| Internal state | Template prefix | Meaning |
+|----------------|-----------------|---------|
+| `inputs` | `{{inputs.xxx}}` | Workflow inputs at start (user message, conversation ID, etc.) |
+| `lastOutput` | `{{previous.xxx}}` | Output of the **most recently executed** node |
+| `outputs` | `{{outputs.xxx}}` | Global **named variable pool** (written by nodes with an output key) |
+| `nodeOutputs` | `{{nodeId.xxx}}` | Full output object of a specific node ID |
+| `metrics` | available in run details | Node duration, tool call count, and usage/cost metrics when reported |
+
+### 3.1 What is `previous`?
+
+`{{previous.output}}` is the `output` field of the **immediately preceding executed node**.
+
+- After every node finishes, the engine updates `lastOutput`.
+- It is **not** “the node drawn upstream on the canvas”; it is **the previous step in actual execution order**.
+
+Example:
+
+```text
+Start → Agent A → Agent B
+```
+
+For Agent B, `{{previous.output}}` = Agent A’s output.
+
+With a condition in between:
+
+```text
+Start → Agent A → Condition → Agent B
+```
+
+For Agent B, `{{previous.output}}` = the **condition node** output (`true` / `false`), **not** Agent A’s result.
+
+If a node has **multiple upstream nodes**, `previous` is built by that node’s **join strategy** first:
+
+| Join strategy | Meaning | Use case |
+|---------------|---------|----------|
+| `all_merge` | Merge all upstream outputs; `previous.output` is an array | Default; aggregate multiple results |
+| `last_by_canvas` | Use the last upstream output by canvas order | Explicitly use one branch |
+| `first_non_empty` | Use the first non-empty output | Fallback chains |
+| `fail_fast` | Stop the node if any upstream failed | Critical gates, approval prechecks, safety checks |
+
+### 3.2 What is `outputs`?
+
+`outputs` is a **named variable registry** maintained by the engine during execution.
+
+When an Agent, Tool, or Output node sets an **Output variable name** (`output_key`), the result is stored as:
+
+```text
+outputs["your_variable_name"] = node_output
+```
+
+Any downstream node can then reference it via `{{outputs.variable_name}}`, even if other nodes sit in between.
+
+Example:
+
+- Agent A **Output variable name**: `agent_result1`
+- Agent B **Input source**: `{{outputs.agent_result1}}`
+
+Agent B still receives Agent A’s output even when a condition node lies between them.
+
+### 3.3 When to use `previous` vs `outputs`
+
+| Scenario | Recommended |
+|----------|-------------|
+| Two nodes are **directly connected**; you only need the last step | `{{previous.output}}` |
+| Other nodes sit in between (condition, tool, HITL, etc.) | `{{outputs.variable_name}}` |
+| Reference output from an **earlier** node | `{{outputs.variable_name}}` or `{{nodeId.output}}` |
+| Condition should test an Agent’s output | `{{outputs.variable_name}} != ""` |
+| Read the original user input | `{{inputs.message}}` |
+
+**Rule of thumb:**
+
+- `previous` = last step (chained, adjacent)
+- `outputs` = by name (cross-node, look back)
+
+---
+
+## 4. Template syntax
+
+### 4.1 Basic format
+
+```text
+{{path.to.value}}
+```
+
+Allowed characters in paths: letters, digits, underscore, dot, hyphen. Examples:
+
+```text
+{{previous.output}}
+{{outputs.agent_result1}}
+{{inputs.message}}
+{{inputs.conversationId}}
+{{previous.matched}}
+{{node-abc123.output}}
+```
+
+### 4.2 Available paths
+
+| Path | Description |
+|------|-------------|
+| `{{inputs.message}}` | User message (Start node input) |
+| `{{inputs.conversationId}}` | Conversation ID |
+| `{{inputs.projectId}}` | Project ID |
+| `{{previous.output}}` | Primary output of the previous node |
+| `{{previous.matched}}` | Match result of the previous condition node (`true` / `false`) |
+| `{{outputs.variable_name}}` | Named output registered by a node |
+| `{{nodeId.output}}` | `output` field of the node with that ID |
+| `{{previous.kind}}` | Previous node output kind, e.g. `agent` / `tool` / `condition` |
+| `{{previous.status}}` | Previous node status, e.g. `completed` / `failed` / `simulated` |
+
+Node outputs keep compatibility fields such as `output` and `matched`, and also include a structured envelope:
+
+```json
+{
+  "kind": "agent",
+  "node_id": "node-2",
+  "node_type": "agent",
+  "status": "completed",
+  "output": "..."
+}
+```
+
+### 4.3 Condition expressions
+
+Condition nodes and edge conditions support comparisons, text matching, regex, logical operators, and safe JSONPath/JQ path reads:
+
+```text
+{{outputs.agent_result1}} != ""
+{{previous.output}} == "ok"
+{{outputs.count}} >= 100
+{{previous.output}} contains "success"
+{{previous.output}} matches "^ok"
+{{outputs.risk_score}} >= 8 && {{previous.output}} != ""
+jsonpath({{previous.output}}, "$.status") == "ok"
+jq({{outputs.scan}}, ".severity") == "high"
+```
+
+Rules:
+
+- Operators: `==`, `!=`, `>`, `>=`, `<`, `<=`
+- `contains` checks substrings; `matches` checks regular expressions
+- Simple `&&` / `||` is supported
+- `jsonpath(value, "$.path")` and `jq(value, ".path")` support a **safe path-only subset**; no arbitrary script execution
+- Leading/trailing spaces and quotes are trimmed before comparison
+- Without a comparator, non-empty values that are not `false`, `0`, or `null` are treated as true
+- Expressions, regexes, and JSONPath/JQ paths are statically validated before save
+
+### 4.4 Nested field binding
+
+Field bindings can read ordinary fields such as `output` or `message`, and also JSONPath/JQ-style paths:
+
+| Binding | Meaning |
+|---------|---------|
+| `from=previous, field=$.status` | Read `status` from previous output |
+| `from=outputs, field=$.scan.severity` | Read a nested field from named outputs |
+| `from=node-1, field=.output.items[0]` | Read an array element from a specific node output |
+
+---
+
+## 5. Node types and configuration
+
+### 5.1 Start
+
+Workflow entry point; injects user input into `inputs`.
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Input keys | Comma-separated input key names | `message, conversationId, projectId` |
+
+Start node output includes: `output`, `message`, `conversationId`, `projectId`.
+
+### 5.2 Agent
+
+Runs an LLM Agent task. Supports multiple modes.
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Agent mode | `eino_single` / `deep` / `plan_execute` / `supervisor` | `eino_single` |
+| Input source | Template for upstream data | `{{previous.output}}` |
+| Node instruction | Task description for this node | empty |
+| Output variable name | Key written into `outputs` | `agent_result` |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+**Message assembly:**
+
+- Instruction only → send instruction to the Agent  
+- Input source only → “Continue based on upstream output: …”  
+- Both → combined “upstream input + node instruction”
+
+After execution:
+
+- `previous.output` becomes this node’s response text  
+- If **Output variable name** is set, the value is also stored in `outputs[variable_name]`
+- In the Eino graph, the Agent node is split into `prepare → execute → finalize` for clearer trace and future checkpointing
+
+### 5.3 Tool
+
+Calls an enabled MCP tool.
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| MCP tool | Tool name (required) | — |
+| Argument template | JSON with `{{...}}` templates | `{}` |
+| Timeout (seconds) | Optional | empty |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+Example argument template:
+
+```json
+{"target": "{{inputs.message}}", "port": "443"}
+```
+
+If an output variable name is configured, the tool result is written to `outputs`.
+
+### 5.4 Condition
+
+Evaluates an expression and outputs `matched` (`true` / `false`).
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Expression | Supports `{{...}}` and `==` / `!=` | `{{previous.output}} != ""` |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+**Branching rules:**
+
+- The **first outgoing edge** defaults to the **“yes”** branch (`matched == true`)
+- The **second outgoing edge** defaults to the **“no”** branch (`matched == false`)
+- Edge labels such as `是` / `否` (or `yes` / `no`, `true` / `false`) help identify branches
+- A third or later edge needs a custom **edge condition**
+
+Edge condition examples (select an edge, configure in the right panel):
+
+```text
+{{previous.matched}} == "true"
+{{previous.matched}} == "false"
+```
+
+### 5.5 HITL (human-in-the-loop)
+
+Human approval checkpoint. The run pauses before this node through Eino interrupt/checkpoint and resumes after approval via API or the monitor panel.
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Prompt | Supports templates | `Please approve before continuing` |
+| Prompt binding | If prompt text is empty, read approval text from a bound field | `previous.output` |
+| Reviewer | `human` / `audit_agent` | `human` |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+Pending HITL metadata records:
+
+- `checkpointId`
+- interrupt `beforeNodes`
+- resume target / address / path
+- resume payload schema (`approved`, `comment`)
+
+### 5.6 Output
+
+Writes the final workflow result into `outputs` for summary and chat display.
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Output variable name | Required key for the final result | `result` |
+| Variable source | Template deciding what to write | `{{previous.output}}` |
+| Static output value | Optional; overrides variable source when set | empty |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+**Note:** Output nodes are workflow exits and must not have outgoing edges.
+
+### 5.7 End
+
+Optional node for an end summary template (less common in role-bound flows).
+
+| Field | Description | Default |
+|-------|-------------|---------|
+| Result template | Supports `{{outputs.xxx}}` | `{{outputs.result}}` |
+| Join strategy | How to build `previous` when multiple upstreams enter this node | `all_merge` |
+
+---
+
+## 6. Edge configuration
+
+Select an **edge** to configure its **condition** in the right panel.
+
+| Scenario | Example |
+|----------|---------|
+| Filter after a normal node | `{{previous.output}} == "ok"` |
+| “Yes” branch from a condition | `{{previous.matched}} == "true"` |
+| “No” branch from a condition | `{{previous.matched}} == "false"` |
+
+If no edge condition is set:
+
+- Non-condition nodes: edge is always allowed  
+- Condition nodes: yes/no branches are assigned by edge order automatically
+
+---
+
+## 7. Full example: passing Agent output across a condition
+
+### 7.1 Graph structure
+
+```text
+Start → Agent (initial value) → Condition → Agent (transform) → Output
+                                    ↘ no → Output
+```
+
+### 7.2 Node configuration
+
+**Agent 1**
+
+| Field | Value |
+|-------|-------|
+| Node instruction | Output only `123333333` |
+| Output variable name | `agent_result1` |
+
+**Condition**
+
+| Field | Value |
+|-------|-------|
+| Expression | `{{outputs.agent_result1}} != ""` |
+
+**Agent 2**
+
+| Field | Value |
+|-------|-------|
+| Input source | `{{outputs.agent_result1}}` |
+| Node instruction | Add 100 to the input, then output |
+| Output variable name | `agent_result` |
+
+**Output**
+
+| Field | Value |
+|-------|-------|
+| Output variable name | `result` |
+| Variable source | `{{outputs.agent_result}}` |
+
+### 7.3 Common mistakes
+
+| Wrong config | Why it fails |
+|--------------|--------------|
+| Agent 2 input source = `{{previous.output}}` | `previous` points to the condition node → `true`/`false`, not Agent 1’s text |
+| Agent 1 has no output variable name | `outputs.agent_result1` does not exist → empty downstream |
+| Condition uses `{{previous.output}}` | Tests the wrong upstream value instead of Agent 1’s named output |
+
+---
+
+## 8. Bind to a role and run
+
+### 8.1 Bind in Role Management
+
+1. Open **Role Management**, edit or create a role.  
+2. Select the workflow / graph ID to bind.  
+3. Set policy to `auto` (default when `workflow_id` is set).  
+4. Save the role.
+
+You can also configure this in role YAML:
+
+```yaml
+name: workflow-test
+workflow_id: "1233"
+workflow_version: latest
+workflow_policy: auto
+```
+
+### 8.2 Runtime behavior
+
+When a user chats with that role:
+
+1. The engine loads `graph_json` and executes the graph.  
+2. The chat UI shows progress events (`workflow_start`, `workflow_node_start`, Agent reasoning, etc.).  
+3. When finished, a summary lists all named entries in `outputs`.
+
+If no Output node is reached or no branch matches, `outputs` may be empty and the summary will suggest checking the Output node and branches.
+
+---
+
+## 9. Debugging, dry-run, and replay
+
+### 9.1 Safe dry-run
+
+Click **Dry run** on the canvas toolbar and enter a test message to simulate the workflow.
+
+Dry-run safety rules:
+
+- `start` / `condition` / `output` / `end` use real logic
+- `tool` does not call MCP; it returns `[dry-run] tool call skipped`
+- `agent` does not call the model; it returns `[dry-run] agent execution skipped`
+- `hitl` does not pause; it simulates approval
+
+API:
+
+```http
+POST /api/workflows/dry-run
+```
+
+Request:
+
+```json
+{
+  "graph": { "nodes": [], "edges": [], "config": {} },
+  "inputs": { "message": "ping" }
+}
+```
+
+Response includes:
+
+- `outputs`
+- `nodeOutputs`
+- `trace`
+- `metrics`
+- `replayScript`
+
+### 9.2 Run details and replay
+
+Query full node execution traces after a run:
+
+```http
+GET /api/workflows/runs/{runId}
+```
+
+The response contains `run` and `nodeRuns`. Each node run records:
+
+- input snapshot
+- output snapshot
+- status / error
+- started_at / finished_at
+- `duration_ms`
+
+Replay API:
+
+```http
+GET /api/workflows/runs/{runId}/replay
+```
+
+This generates replay steps from saved `nodeRuns`; it does not re-execute tools or Agents.
+
+### 9.3 Metrics
+
+The workflow accumulates, when available:
+
+- `node_count`
+- `duration_ms`
+- `tool_call_count`
+- Agent progress usage such as `prompt_tokens` / `completion_tokens` / `total_tokens` / `cost`
+
+Token and cost metrics depend on whether the underlying model/Agent events report usage.
+
+---
+
+## 10. Validation before save
+
+On save, the system checks:
+
+| Rule | Description |
+|------|-------------|
+| Start node required | At least one `start` node |
+| Output node required | At least one `output` node with an output variable name |
+| Valid edges | Source and target exist; no self-loops |
+| Start has no incoming edges | Start must not be targeted |
+| Output / End has no outgoing edges | Nothing after Output / End |
+| Non-start nodes must have incoming edges | Prevent orphan nodes |
+| Non-output/end nodes must have outgoing edges | Prevent dead ends |
+| No cycles | Workflow orchestration must be a DAG |
+| Reachability | Every node must be reachable from Start and eventually reach output/end |
+| Tool nodes | MCP tool required; argument JSON must be valid; timeout must be a positive integer |
+| Agent nodes | Must have node instruction or input binding; output variable name required |
+| Condition nodes | Expression required; 1–2 outgoing edges; branches must be yes/no and unique |
+| Edge conditions | Expressions, regexes, and JSONPath/JQ paths must pass static validation |
+| Join strategy | Must be `all_merge` / `last_by_canvas` / `first_non_empty` / `fail_fast` |
+
+---
+
+## 11. Troubleshooting
+
+| Symptom | Likely cause | Fix |
+|---------|--------------|-----|
+| Downstream gets empty value | Upstream has no output variable name | Set **Output variable name** on upstream; use `{{outputs.xxx}}` downstream |
+| Downstream gets `true`/`false` | Used `{{previous.output}}` while previous node is a condition | Use `{{outputs.xxx}}` instead |
+| Condition always takes “no” | Expression does not match actual output format | Check Agent output for quotes/newlines; try `!= ""` first |
+| No final output | Output node branch not reached | Verify condition wiring; ensure every path reaches an **Output** node |
+| Role chat does not run workflow | Role not bound or disabled | Check `workflow_id`, `workflow_policy: auto`, workflow `enabled: true` |
+| Tool node fails | Invalid JSON in arguments or tool disabled | Fix argument template; enable the tool in MCP settings |
+| Save fails with invalid branch | Condition outgoing edges are not marked yes/no, or are duplicated | Select the edge and set branch to `true` or `false` |
+| Multi-upstream result is unexpected | Join strategy does not match the workflow | Switch between `all_merge`, `first_non_empty`, `last_by_canvas`, and `fail_fast` |
+| Nested field is empty | JSONPath/JQ path is outside the safe subset | Use `$.a.b[0]` or `.a.b[0]`; avoid wildcards, recursion, or expressions |
+
+---
+
+## 12. Best practices
+
+1. **Meaningful names**: Use descriptive output variable names (`scan_result`, `parsed_targets`) instead of reusing `agent_result` everywhere.  
+2. **Prefer `outputs` for cross-node data**: If a condition, tool, or HITL node might sit in between, use named variables.  
+3. **Use `previous` only for direct links**: `A → B` with nothing in between is the ideal case for `{{previous.output}}`.  
+4. **Conditions should reference source data**: When testing Agent output, use `{{outputs.xxx}}` unless the condition immediately follows that Agent.  
+5. **Every path needs an exit**: Ensure both yes and no branches eventually reach an **Output** node (or your intended end).  
+6. **Choose join strategy explicitly for multi-upstream nodes**: Use `all_merge` for aggregation, `first_non_empty` for fallback, and `fail_fast` for critical gates.  
+7. **Use JSONPath/JQ safe paths for nested JSON**: e.g. `jsonpath({{previous.output}}, "$.status") == "ok"`.  
+8. **Dry-run before real execution**: Validate data flow and branches with a simple message before binding the workflow to a role.
+
+---
+
+## 13. Code references (for developers)
+
+| Module | Path |
+|--------|------|
+| Execution engine | `internal/workflow/runner.go` |
+| Eino compile / checkpoint / HITL | `internal/workflow/eino_compile.go` |
+| Graph validation | `internal/workflow/validation.go` |
+| Expressions / JSONPath / joins | `internal/workflow/expression.go`, `jsonpath.go`, `join.go` |
+| Dry-run / replay data | `internal/workflow/dry_run.go`, `internal/handler/workflow_run.go` |
+| Canvas UI | `web/static/js/workflows.js` |
+| Workflow API | `internal/handler/workflow.go` |
+| Role binding | `internal/config/config.go` (`workflow_id` field) |
@@ -3,11 +3,10 @@ module cyberstrike-ai
 // 若 go mod download 超时，可执行: go env -w GOPROXY=https://goproxy.cn,direct
 // 或使用 scripts/bootstrap-go.sh

-go 1.24.0
-
-toolchain go1.24.4
+go 1.25

 require (
+	github.com/bwmarrin/discordgo v0.29.0
 	github.com/bytedance/sonic v1.15.0
 	github.com/cloudwego/eino v0.8.13
 	github.com/cloudwego/eino-ext/adk/backend/local v0.0.0-20260416081055-0ebab92e14f2
@@ -21,7 +20,7 @@ require (
 	github.com/eino-contrib/jsonschema v1.0.3
 	github.com/gin-gonic/gin v1.9.1
 	github.com/google/uuid v1.6.0
-	github.com/gorilla/websocket v1.5.0
+	github.com/gorilla/websocket v1.5.3
 	github.com/larksuite/oapi-sdk-go/v3 v3.4.22
 	github.com/mattn/go-sqlite3 v1.14.18
 	github.com/modelcontextprotocol/go-sdk v1.2.0
@@ -29,6 +28,8 @@ require (
 	github.com/pkoukk/tiktoken-go v0.1.8
 	github.com/robfig/cron/v3 v3.0.1
 	github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e
+	github.com/slack-go/slack v0.27.0
+	github.com/tencent-connect/botgo v0.2.1
 	go.opentelemetry.io/otel v1.34.0
 	go.opentelemetry.io/otel/exporters/otlp/otlptrace/otlptracehttp v1.34.0
 	go.opentelemetry.io/otel/exporters/stdout/stdouttrace v1.34.0
@@ -60,6 +61,7 @@ require (
 	github.com/go-playground/locales v0.14.1 // indirect
 	github.com/go-playground/universal-translator v0.18.1 // indirect
 	github.com/go-playground/validator/v10 v10.14.0 // indirect
+	github.com/go-resty/resty/v2 v2.6.0 // indirect
 	github.com/goccy/go-json v0.10.2 // indirect
 	github.com/gogo/protobuf v1.3.2 // indirect
 	github.com/google/jsonschema-go v0.3.0 // indirect
@@ -78,6 +80,9 @@ require (
 	github.com/pkg/errors v0.9.1 // indirect
 	github.com/sirupsen/logrus v1.9.3 // indirect
 	github.com/slongfield/pyfmt v0.0.0-20220222012616-ea85ff4c361f // indirect
+	github.com/tidwall/gjson v1.9.3 // indirect
+	github.com/tidwall/match v1.1.1 // indirect
+	github.com/tidwall/pretty v1.2.0 // indirect
 	github.com/twitchyliquid64/golang-asm v0.15.1 // indirect
 	github.com/ugorji/go/codec v1.2.11 // indirect
 	github.com/wk8/go-ordered-map/v2 v2.1.8 // indirect
@@ -93,6 +98,7 @@ require (
 	golang.org/x/exp v0.0.0-20250305212735-054e65f0b394 // indirect
 	golang.org/x/image v0.0.0-20191009234506-e7c1f5e7dbb8 // indirect
 	golang.org/x/oauth2 v0.30.0 // indirect
+	golang.org/x/sync v0.15.0 // indirect
 	golang.org/x/sys v0.33.0 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20250115164207-1a7da9e5054f // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20250115164207-1a7da9e5054f // indirect
@@ -1,3 +1,4 @@
+cloud.google.com/go/compute/metadata v0.3.0/go.mod h1:zFmK7XCadkQkj6TtorcaGlCW1hT1fIilQDwofLpJ20k=
 github.com/airbrake/gobrake v3.6.1+incompatible/go.mod h1:wM4gu3Cn0W0K7GUuVWnlXZU11AGBXMILnrdOU8Kn00o=
 github.com/bahlo/generic-list-go v0.2.0 h1:5sz/EEAK+ls5wF+NeqDpk5+iNdMDXrh3z3nPnH1Wvgk=
 github.com/bahlo/generic-list-go v0.2.0/go.mod h1:2KvAjgMlE5NNynlg/5iLrrCCZ2+5xWbdbCW3pNTGyYg=
@@ -9,6 +10,8 @@ github.com/buger/jsonparser v1.1.1 h1:2PnMjfWD7wBILjqQbt530v576A/cAbQvEW9gGIpYMU
 github.com/buger/jsonparser v1.1.1/go.mod h1:6RYKKt7H4d4+iWqouImQ9R2FZql3VbhNgx27UK13J/0=
 github.com/bugsnag/bugsnag-go v1.4.0/go.mod h1:2oa8nejYd4cQ/b0hMIopN0lCRxU0bueqREvZLWFrtK8=
 github.com/bugsnag/panicwrap v1.2.0/go.mod h1:D/8v3kj0zr8ZAKg1AQ6crr+5VwKN5eIywRkfhyM/+dE=
+github.com/bwmarrin/discordgo v0.29.0 h1:FmWeXFaKUwrcL3Cx65c20bTRW+vOb6k8AnaP+EgjDno=
+github.com/bwmarrin/discordgo v0.29.0/go.mod h1:NJZpH+1AfhIcyQsPeuBKsUtYrRnjkyu0kIVMCHkZtRY=
 github.com/bytedance/gopkg v0.1.3 h1:TPBSwH8RsouGCBcMBktLt1AymVo2TVsBVCY4b6TnZ/M=
 github.com/bytedance/gopkg v0.1.3/go.mod h1:576VvJ+eJgyCzdjS+c4+77QF3p7ubbtiKARP3TxducM=
 github.com/bytedance/mockey v1.3.0 h1:ONLRdvhqmCfr9rTasUB8ZKCfvbdD2tohOg4u+4Q/ed0=
@@ -20,6 +23,8 @@ github.com/bytedance/sonic/loader v0.5.0/go.mod h1:AR4NYCk5DdzZizZ5djGqQ92eEhCCc
 github.com/cenkalti/backoff/v4 v4.3.0 h1:MyRJ/UdXutAwSAT+s3wNd7MfTIcy71VQueUuFK343L8=
 github.com/cenkalti/backoff/v4 v4.3.0/go.mod h1:Y3VNntkOUPxTVeUxJ/G5vcM//AlwfmyYozVcomhLiZE=
 github.com/certifi/gocertifi v0.0.0-20190105021004-abcd57078448/go.mod h1:GJKEexRPVJrBSOjoqN5VNOIKJ5Q3RViH6eu3puDRwx4=
+github.com/cespare/xxhash/v2 v2.1.2/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
+github.com/cespare/xxhash/v2 v2.2.0/go.mod h1:VGX0DQ3Q6kWi7AoAeZDth3/j3BFtOZR5XLFGgcrjCOs=
 github.com/cloudwego/base64x v0.1.6 h1:t11wG9AECkCDk5fMSoxmufanudBtJ+/HemLstXDLI2M=
 github.com/cloudwego/base64x v0.1.6/go.mod h1:OFcloc187FXDaYHvrNIjxSe8ncn0OOM8gEHfghB2IPU=
 github.com/cloudwego/eino v0.8.13 h1:z5dhaZNN8TWZbP/lgKxGmF26Ii8fPeUlQCGV/NTtms0=
@@ -38,11 +43,13 @@ github.com/cloudwego/eino-ext/components/model/openai v0.1.13 h1:5XHRTiTD5bt9KQr
 github.com/cloudwego/eino-ext/components/model/openai v0.1.13/go.mod h1:mgIoqYYOc0eECCqvLbEYpOJrQNTNxkwXzSJzFU+v5sQ=
 github.com/cloudwego/eino-ext/libs/acl/openai v0.1.17 h1:EeVcR1TslRA2IdNW1h/2LaGbPlffwGhQm99jM3zWZiI=
 github.com/cloudwego/eino-ext/libs/acl/openai v0.1.17/go.mod h1:Zkcx6DPTR2NfWmtSXbhItswGw6hqUezNPhNcke0pOG8=
+github.com/creack/pty v1.1.9/go.mod h1:oKZEueFk5CKHvIhNR5MUki03XCEU+Q6VDXinZuGJ33E=
 github.com/creack/pty v1.1.24 h1:bJrF4RRfyJnbTJqzRLHzcGaZK1NeM5kTC9jGgovnR1s=
 github.com/creack/pty v1.1.24/go.mod h1:08sCNb52WyoAwi2QDyzUCTgcvVFhUzewun7wtTfvcwE=
 github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
 github.com/davecgh/go-spew v1.1.1 h1:vj9j/u1bqnvCEfJOwUhtlOARqs3+rkHYY13jYWTU97c=
 github.com/davecgh/go-spew v1.1.1/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
+github.com/dgryski/go-rendezvous v0.0.0-20200823014737-9f7001d12a5f/go.mod h1:cuUVRXasLTGF7a8hSLbxyZXjz+1KgoB3wDUb6vlszIc=
 github.com/disintegration/imaging v1.6.2 h1:w1LecBlG2Lnp8B3jk5zSuNqd7b4DXhcjwek1ei82L+c=
 github.com/disintegration/imaging v1.6.2/go.mod h1:44/5580QXChDfwIclfc/PCwrr44amcmDAg8hxG0Ewe4=
 github.com/dlclark/regexp2 v1.10.0 h1:+/GIL799phkJqYW+3YbOd8LCcbHzT0Pbo8zl70MHsq0=
@@ -54,6 +61,7 @@ github.com/eino-contrib/jsonschema v1.0.3/go.mod h1:cpnX4SyKjWjGC7iN2EbhxaTdLqGj
 github.com/evanphx/json-patch v0.5.2 h1:xVCHIVMUu1wtM/VkR9jVZ45N3FhZfYMMYGorLCR8P3k=
 github.com/evanphx/json-patch v0.5.2/go.mod h1:ZWS5hhDbVDyob71nXKNL0+PWn6ToqBHMikGIFbs31qQ=
 github.com/fsnotify/fsnotify v1.4.7/go.mod h1:jwhsz4b93w/PPRr/qN1Yymfu8t87LnFCMoQvtojpjFo=
+github.com/fsnotify/fsnotify v1.4.9/go.mod h1:znqG4EE+3YCdAaPaxE2ZRY/06pZUdp0tY4IgpuI1SZQ=
 github.com/gabriel-vasile/mimetype v1.4.2 h1:w5qFW6JKBz9Y393Y4q372O9A7cUSequkh1Q7OhCmWKU=
 github.com/gabriel-vasile/mimetype v1.4.2/go.mod h1:zApsH/mKG4w07erKIaJPFiX0Tsq9BFQgN3qGY5GnNgA=
 github.com/getsentry/raven-go v0.2.0/go.mod h1:KungGk8q33+aIAZUIVWZDr2OfAEBsO49PX4NzFV5kcQ=
@@ -76,6 +84,12 @@ github.com/go-playground/universal-translator v0.18.1 h1:Bcnm0ZwsGyWbCzImXv+pAJn
 github.com/go-playground/universal-translator v0.18.1/go.mod h1:xekY+UJKNuX9WP91TpwSH2VMlDf28Uj24BCp08ZFTUY=
 github.com/go-playground/validator/v10 v10.14.0 h1:vgvQWe3XCz3gIeFDm/HnTIbj6UGmg/+t63MyGU2n5js=
 github.com/go-playground/validator/v10 v10.14.0/go.mod h1:9iXMNT7sEkjXb0I+enO7QXmzG6QCsPWY4zveKFVRSyU=
+github.com/go-redis/redis/v8 v8.11.4/go.mod h1:2Z2wHZXdQpCDXEGzqMockDpNyYvi2l4Pxt6RJr792+w=
+github.com/go-resty/resty/v2 v2.6.0 h1:joIR5PNLM2EFqqESUjCMGXrWmXNHEU9CEiK813oKYS4=
+github.com/go-resty/resty/v2 v2.6.0/go.mod h1:PwvJS6hvaPkjtjNg9ph+VrSD92bi5Zq73w/BIH7cC3Q=
+github.com/go-task/slim-sprig v0.0.0-20210107165309-348f09dbbbc0/go.mod h1:fyg7847qk6SyHyPtNmDHnmrv/HOrqktSC+C9fM+CJOE=
+github.com/go-test/deep v1.1.1 h1:0r/53hagsehfO4bzD2Pgr/+RgHqhmf+k1Bpse2cTu1U=
+github.com/go-test/deep v1.1.1/go.mod h1:5C2ZWiW0ErCdrYzpqxLbTX7MG14M9iiw8DgHncVwcsE=
 github.com/goccy/go-json v0.10.2 h1:CrxCmQqYDkv1z7lO7Wbh2HN93uovUHgrECaO5ZrCXAU=
 github.com/goccy/go-json v0.10.2/go.mod h1:6MelG93GURQebXPDq3khkgXZkazVtN9CRI+MGFi0w8I=
 github.com/gofrs/uuid v3.2.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
@@ -84,21 +98,38 @@ github.com/gogo/protobuf v1.3.2/go.mod h1:P1XiOD3dCwIKUDQYPy72D8LYyHL2YPYrpS2s69
 github.com/golang-jwt/jwt/v5 v5.2.2 h1:Rl4B7itRWVtYIHFrSNd7vhTiz9UpLdi6gZhZ3wEeDy8=
 github.com/golang-jwt/jwt/v5 v5.2.2/go.mod h1:pqrtFR0X4osieyHYxtmOUWsAWrfe1Q5UVIyoH402zdk=
 github.com/golang/protobuf v1.2.0/go.mod h1:6lQm79b+lXiMfvg/cZm0SGofjICqVBUtrP5yJMmIC1U=
+github.com/golang/protobuf v1.4.0-rc.1/go.mod h1:ceaxUfeHdC40wWswd/P6IGgMaK3YpKi5j83Wpe3EHw8=
+github.com/golang/protobuf v1.4.0-rc.1.0.20200221234624-67d41d38c208/go.mod h1:xKAWHe0F5eneWXFV3EuXVDTCmh+JuBKY0li0aMyXATA=
+github.com/golang/protobuf v1.4.0-rc.2/go.mod h1:LlEzMj4AhA7rCAGe4KMBDvJI+AwstrUpVNzEA03Pprs=
+github.com/golang/protobuf v1.4.0-rc.4.0.20200313231945-b860323f09d0/go.mod h1:WU3c8KckQ9AFe+yFwt9sWVRKCVIyN9cPHBJSNnbL67w=
+github.com/golang/protobuf v1.4.0/go.mod h1:jodUvKwWbYaEsadDk5Fwe5c77LiNKVO9IDvqG2KuDX0=
+github.com/golang/protobuf v1.4.2/go.mod h1:oDoupMAO8OvCJWAcko0GGGIgR6R6ocIYbsSw735rRwI=
+github.com/golang/protobuf v1.5.0/go.mod h1:FsONVRAS9T7sI+LIUmWTfcYkHO4aIWwzhcaSAoJOfIk=
+github.com/golang/protobuf v1.5.2/go.mod h1:XVQd3VNwM+JqD3oG2Ue2ip4fOMUkwXdXDdiuN0vRsmY=
 github.com/golang/protobuf v1.5.4 h1:i7eJL8qZTpSEXOPTxNKhASYpMn+8e5Q6AdndVa1dWek=
 github.com/golang/protobuf v1.5.4/go.mod h1:lnTiLA8Wa4RWRcIUkrtSVa5nRhsEGBg48fD6rSs7xps=
+github.com/google/go-cmp v0.3.0/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMywk6iLU=
+github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
+github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
 github.com/google/gofuzz v1.0.0/go.mod h1:dBl0BpW6vV/+mYPU4Po3pmUjxk6FQPldtuIdl/M65Eg=
 github.com/google/jsonschema-go v0.3.0 h1:6AH2TxVNtk3IlvkkhjrtbUc4S8AvO0Xii0DxIygDg+Q=
 github.com/google/jsonschema-go v0.3.0/go.mod h1:r5quNTdLOYEz95Ru18zA0ydNbBuYoo9tgaYcxEYhJVE=
+github.com/google/uuid v1.3.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/google/uuid v1.6.0 h1:NIvaJDMOsjHA8n1jAhLSgzrAzy1Hgr+hNrb57e+94F0=
 github.com/google/uuid v1.6.0/go.mod h1:TIyPZe4MgqvfeYDBFedMoGGpEw/LqOeaOT+nhxU+yHo=
 github.com/goph/emperror v0.17.2 h1:yLapQcmEsO0ipe9p5TaN22djm3OFV/TfM/fcYP0/J18=
 github.com/goph/emperror v0.17.2/go.mod h1:+ZbQ+fUNO/6FNiUo0ujtMjhgad9Xa6fQL9KhH4LNHic=
 github.com/gopherjs/gopherjs v1.17.2 h1:fQnZVsXk8uxXIStYb0N4bGk7jeyTalG/wsZjQ25dO0g=
 github.com/gopherjs/gopherjs v1.17.2/go.mod h1:pRRIvn/QzFLrKfvEz3qUuEhtE/zLCWfreZ6J5gM2i+k=
-github.com/gorilla/websocket v1.5.0 h1:PPwGk2jz7EePpoHN/+ClbZu8SPxiqlu12wZP/3sWmnc=
+github.com/gorilla/websocket v1.4.2/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/gorilla/websocket v1.5.0/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
+github.com/gorilla/websocket v1.5.3 h1:saDtZ6Pbx/0u+bgYQ3q96pZgCzfhKXGPqt7kZ72aNNg=
+github.com/gorilla/websocket v1.5.3/go.mod h1:YR8l580nyteQvAITg2hZ9XVh4b55+EU/adAjf1fMHhE=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.25.1 h1:VNqngBF40hVlDloBruUehVYC3ArSgIyScOAyMRqBxRg=
 github.com/grpc-ecosystem/grpc-gateway/v2 v2.25.1/go.mod h1:RBRO7fro65R6tjKzYgLAFo0t1QEXY1Dp+i/bvpRiqiQ=
 github.com/hpcloud/tail v1.0.0/go.mod h1:ab1qPbhIpdTxEkNHXyeSf5vhxWSCs/tWer42PpOxQnU=
@@ -114,6 +145,8 @@ github.com/klauspost/cpuid/v2 v2.2.10 h1:tBs3QSyvjDyFTq3uoc/9xFpCuOsJQFNPiAhYdw2
 github.com/klauspost/cpuid/v2 v2.2.10/go.mod h1:hqwkgyIinND0mEev00jJYCxPNVRVXFQeu1XKlok6oO0=
 github.com/konsorten/go-windows-terminal-sequences v1.0.1/go.mod h1:T0+1ngSBFLxvqU3pZ+m/2kptfBszLMUkC4ZK/EgS/cQ=
 github.com/kr/pretty v0.1.0/go.mod h1:dAy3ld7l9f0ibDNOQOHHMYYIIbhfbHSm3C4ZsoJORNo=
+github.com/kr/pretty v0.2.1/go.mod h1:ipq/a2n7PKx3OHsz4KJII5eveXtPO4qwEXGdVfWzfnI=
+github.com/kr/pretty v0.3.0/go.mod h1:640gp4NfQd8pI5XOwp5fnNeVWj67G7CFk/SaSQn7NBk=
 github.com/kr/pretty v0.3.1 h1:flRD4NNwYAUpkphVc1HcthR4KEIFJ65n8Mw5qdRn3LE=
 github.com/kr/pretty v0.3.1/go.mod h1:hoEshYVHaxMs3cyo3Yncou5ZscifuDolrwPKZanG3xk=
 github.com/kr/pty v1.1.1/go.mod h1:pFQYn66WHrOpPYNljwOMqo10TkYh1fy3cYio2l3bCsQ=
@@ -145,11 +178,19 @@ github.com/modern-go/reflect2 v1.0.2 h1:xBagoLtFs94CBntxluKeaWgTMpvLxC4ur3nMaC9G
 github.com/modern-go/reflect2 v1.0.2/go.mod h1:yWuevngMOJpCy52FWWMvUC8ws7m/LJsjYzDa0/r8luk=
 github.com/nikolalohinski/gonja v1.5.3 h1:GsA+EEaZDZPGJ8JtpeGN78jidhOlxeJROpqMT9fTj9c=
 github.com/nikolalohinski/gonja v1.5.3/go.mod h1:RmjwxNiXAEqcq1HeK5SSMmqFJvKOfTfXhkJv6YBtPa4=
+github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=
+github.com/nxadm/tail v1.4.8/go.mod h1:+ncqLTQzXmGhMZNUePPaPqPvBxHAIsmXswZKocGu+AU=
 github.com/onsi/ginkgo v1.6.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
 github.com/onsi/ginkgo v1.8.0/go.mod h1:lLunBs/Ym6LB5Z9jYTR76FiuTmxDTDusOGeTQH+WWjE=
+github.com/onsi/ginkgo v1.12.1/go.mod h1:zj2OWP4+oCPe1qIXoGWkgMRwljMUYCdkwsT2108oapk=
+github.com/onsi/ginkgo v1.16.4/go.mod h1:dX+/inL/fNMqNlz0e9LfyB9TswhZpCVdJM/Z6Vvnwo0=
 github.com/onsi/gomega v1.5.0/go.mod h1:ex+gbHU/CVuBBDIJjb2X0qEXbFg53c61hWP/1CpauHY=
+github.com/onsi/gomega v1.7.1/go.mod h1:XdKZgCCFLUoM/7CFJVPcG8C1xQ1AJ0vpAezJrB7JYyY=
+github.com/onsi/gomega v1.10.1/go.mod h1:iN09h71vgCQne3DLsj+A5owkum+a2tYe+TOCB1ybHNo=
+github.com/onsi/gomega v1.16.0/go.mod h1:HnhC7FXeEQY45zxNK3PPoIUhzk/80Xly9PcubAlGdZY=
 github.com/pelletier/go-toml/v2 v2.2.3 h1:YmeHyLY8mFWbdkNWwpr+qIL2bEqT0o95WSdkNHvL12M=
 github.com/pelletier/go-toml/v2 v2.2.3/go.mod h1:MfCQTFTvCcUyyvvwm1+G6H/jORL20Xlb6rzQu9GuUkc=
+github.com/pkg/diff v0.0.0-20210226163009-20ebb0f2a09e/go.mod h1:pJLUxLENpZxwdsKMEsNbx1VGcRFpLqf3715MtcvvzbA=
 github.com/pkg/errors v0.8.0/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
 github.com/pkg/errors v0.9.1 h1:FEBLx1zS214owpjy7qsBeixbURkuhQAwrK5UwLGTwt4=
 github.com/pkg/errors v0.9.1/go.mod h1:bwawxfHBFNV+L2hUp1rHADufV3IMtnDRdf1r5NINEl0=
@@ -159,6 +200,8 @@ github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZb
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/robfig/cron/v3 v3.0.1 h1:WdRxkvbJztn8LMz/QEvLN5sBU+xKpSqwwUO1Pjr4qDs=
 github.com/robfig/cron/v3 v3.0.1/go.mod h1:eQICP3HwyT7UooqI/z+Ov+PtYAWygg1TEWWzGIFLtro=
+github.com/rogpeppe/go-internal v1.6.1/go.mod h1:xXDCJY+GAPziupqXw64V24skbSoqbTEfhy4qGm1nDQc=
+github.com/rogpeppe/go-internal v1.9.0/go.mod h1:WtVeX8xhTBvf0smdhujwtBcq4Qrzq/fJaraNFVN+nFs=
 github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ=
 github.com/rogpeppe/go-internal v1.14.1/go.mod h1:MaRKkUm5W0goXpeCfT7UZI6fk/L7L7so1lCWt35ZSgc=
 github.com/rollbar/rollbar-go v1.0.2/go.mod h1:AcFs5f0I+c71bpHlXNNDbOWJiKwjFDtISeXco0L5PKQ=
@@ -167,6 +210,8 @@ github.com/sirupsen/logrus v1.9.3 h1:dueUQJ1C2q9oE3F7wvmSGAaVtTmUizReu6fjN8uqzbQ
 github.com/sirupsen/logrus v1.9.3/go.mod h1:naHLuLoDiP4jHNo9R0sCBMtWGeIprob74mVsIT4qYEQ=
 github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e h1:MRM5ITcdelLK2j1vwZ3Je0FKVCfqOLp5zO6trqMLYs0=
 github.com/skip2/go-qrcode v0.0.0-20200617195104-da1b6568686e/go.mod h1:XV66xRDqSt+GTGFMVlhk3ULuV0y9ZmzeVGR4mloJI3M=
+github.com/slack-go/slack v0.27.0 h1:VWOpUzOK6UAPCCQlFxl79jhv8a/b+GOSJMnWziDJ8B8=
+github.com/slack-go/slack v0.27.0/go.mod h1:UEe+jmo9WLlwHB04qsOrTDvqM7Aa4rQL3O5wF3n0hx4=
 github.com/slongfield/pyfmt v0.0.0-20220222012616-ea85ff4c361f h1:Z2cODYsUxQPofhpYRMQVwWz4yUVpHF+vPi+eUdruUYI=
 github.com/slongfield/pyfmt v0.0.0-20220222012616-ea85ff4c361f/go.mod h1:JqzWyvTuI2X4+9wOHmKSQCYxybB/8j6Ko43qVmXDuZg=
 github.com/smarty/assertions v1.16.0 h1:EvHNkdRA4QHMrn75NZSoUQ/mAUXAYWfatfB01yTCzfY=
@@ -180,14 +225,24 @@ github.com/stretchr/objx v0.5.0/go.mod h1:Yh+to48EsGEfYuaHDzXPcE3xhTkx73EhmCGUpE
 github.com/stretchr/objx v0.5.2/go.mod h1:FRsXN1f5AsAjCGJKqEizvkpNtU+EGNCLh3NxZ/8L+MA=
 github.com/stretchr/testify v1.2.2/go.mod h1:a8OnRcib4nhh0OaRAV+Yts87kKdq0PP7pXfy6kDkUVs=
 github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
+github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
 github.com/stretchr/testify v1.7.0/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/h/Wwjteg=
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
+github.com/stretchr/testify v1.8.1/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.2/go.mod h1:w2LPCIKwWwSfY2zedu0+kehJoqGctiVI29o6fzry7u4=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.10.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
+github.com/tencent-connect/botgo v0.2.1 h1:+BrTt9Zh+awL28GWC4g5Na3nQaGRWb0N5IctS8WqBCk=
+github.com/tencent-connect/botgo v0.2.1/go.mod h1:oO1sG9ybhXNickvt+CVym5khwQ+uKhTR+IhTqEfOVsI=
+github.com/tidwall/gjson v1.9.3 h1:hqzS9wAHMO+KVBBkLxYdkEeeFHuqr95GfClRLKlgK0E=
+github.com/tidwall/gjson v1.9.3/go.mod h1:/wbyibRr2FHMks5tjHJ5F8dMZh3AcwJEMf5vlfC0lxk=
+github.com/tidwall/match v1.1.1 h1:+Ho715JplO36QYgwN9PGYNhgZvoUSc9X2c80KVTi+GA=
+github.com/tidwall/match v1.1.1/go.mod h1:eRSPERbgtNPcGhD8UCthc6PmLEQXEWd3PRB5JTxsfmM=
+github.com/tidwall/pretty v1.2.0 h1:RWIZEg2iJ8/g6fDDYzMpobmaoGh5OLl4AXtGUGPcqCs=
+github.com/tidwall/pretty v1.2.0/go.mod h1:ITEVvHYasfjBbM0u2Pg8T2nJnzm8xPwvNhhsoaGGjNU=
 github.com/twitchyliquid64/golang-asm v0.15.1 h1:SU5vSMR7hnwNxj24w34ZyCi/FmDZTkS4MhqMhdFk5YI=
 github.com/twitchyliquid64/golang-asm v0.15.1/go.mod h1:a1lVb/DtPvCB8fslRZhAngC2+aY1QWCk3Cedj/Gdt08=
 github.com/ugorji/go/codec v1.2.11 h1:BMaWp1Bb6fHwEtbplGBGJ498wD+LKlNSl25MjdZY4dU=
@@ -204,6 +259,7 @@ github.com/yosida95/uritemplate/v3 v3.0.2 h1:Ed3Oyj9yrmi9087+NczuL5BwkIc4wvTb5zI
 github.com/yosida95/uritemplate/v3 v3.0.2/go.mod h1:ILOh0sOhIJR3+L/8afwt/kE++YT040gmv5BQTMR2HP4=
 github.com/yuin/goldmark v1.1.27/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
 github.com/yuin/goldmark v1.2.1/go.mod h1:3hX8gzYuyVAZsxl0MRgGTJEmQBFcNTphYh9decYSb74=
+github.com/yuin/goldmark v1.4.13/go.mod h1:6yULJ656Px+3vBD8DxQVa3kxgyrAnzto9xy5taEt/CY=
 go.opentelemetry.io/auto/sdk v1.1.0 h1:cH53jehLUN6UFLY71z+NDOiNJqDdPRaXzTel0sJySYA=
 go.opentelemetry.io/auto/sdk v1.1.0/go.mod h1:3wSPjt5PWp2RhlCcmmOial7AvC4DQqZb7a7wCow3W8A=
 go.opentelemetry.io/otel v1.34.0 h1:zRLXxLCgL1WyKsPVrgbSdMN4c0FMkDAskSTQP+0hdUY=
@@ -238,6 +294,9 @@ golang.org/x/crypto v0.0.0-20180904163835-0709b304e793/go.mod h1:6SG95UA2DQfeDnf
 golang.org/x/crypto v0.0.0-20190308221718-c2843e01d9a2/go.mod h1:djNgcEr1/C05ACkg1iLfiJU5Ep61QUkGW8qpdssI0+w=
 golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8UmvKecakEJjdnWj3jj499lnFckfCI=
 golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto=
+golang.org/x/crypto v0.0.0-20210421170649-83a5a9bb288b/go.mod h1:T9bdIzuCu7OtxOm1hfPfRQxPLYneinmdGuTeoZ9dtd4=
+golang.org/x/crypto v0.0.0-20210921155107-089bfa567519/go.mod h1:GvvjBRRGRdwPK5ydBHafDWAxML/pGHZbMvKqRZ5+Abc=
+golang.org/x/crypto v0.16.0/go.mod h1:gCAAfMLgwOJRpTjQ2zCCt2OcSfYMTeZVSRtQlPC7Nq4=
 golang.org/x/crypto v0.39.0 h1:SHs+kF4LP+f+p14esP5jAoDpHU8Gu/v9lFRK6IT5imM=
 golang.org/x/crypto v0.39.0/go.mod h1:L+Xg3Wf6HoL4Bn4238Z6ft6KfEpN0tJGo53AAPC632U=
 golang.org/x/exp v0.0.0-20250305212735-054e65f0b394 h1:nDVHiLt8aIbd/VzvPWN6kSOPE7+F/fNFDSXLVYkE/Iw=
@@ -246,32 +305,71 @@ golang.org/x/image v0.0.0-20191009234506-e7c1f5e7dbb8 h1:hVwzHzIUGRjiF7EcUjqNxk3
 golang.org/x/image v0.0.0-20191009234506-e7c1f5e7dbb8/go.mod h1:FeLwcggjj3mMvU+oOTbSwawSJRM1uh48EjtB4UJZlP0=
 golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
 golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
+golang.org/x/mod v0.6.0-dev.0.20220419223038-86c51ed26bb4/go.mod h1:jJ57K6gSWd91VN4djpZkiMVwK6gcyfeH4XE8wZrZaV4=
+golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190620200207-3b0461eec859/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
 golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s=
+golang.org/x/net v0.0.0-20200520004742-59133d7f0dd7/go.mod h1:qpuaurCH72eLCgpAm/N6yyVIVM9cpaDIP3A8BGJEC5A=
 golang.org/x/net v0.0.0-20201021035429-f5854403a974/go.mod h1:sp8m0HH+o8qH0wwXwYZr8TS3Oi6o0r6Gce1SSxlDquU=
+golang.org/x/net v0.0.0-20210226172049-e18ecbb05110/go.mod h1:m0MpNAwzfU5UDzcl9v0D8zg8gWTRqZa9RBIspLL5mdg=
+golang.org/x/net v0.0.0-20210405180319-a5a99cb37ef4/go.mod h1:p54w0d4576C0XHj96bSt6lcn1PtDYWL6XObtHCRCNQM=
+golang.org/x/net v0.0.0-20210428140749-89ef3d95e781/go.mod h1:OJAsFXCWl8Ukc7SiCT/9KSuxbyM7479/AVlXFRxuMCk=
+golang.org/x/net v0.0.0-20220722155237-a158d28d115b/go.mod h1:XRhObCWvk6IyKnWLug+ECip1KBveYUHfp+8e9klMJ9c=
+golang.org/x/net v0.6.0/go.mod h1:2Tu9+aMcznHK/AK1HMvgo6xiTLG5rD5rZLDS+rp2Bjs=
+golang.org/x/net v0.10.0/go.mod h1:0qNGK6F8kojg2nk9dLZ2mShWaEBan6FAoqfSigmmuDg=
+golang.org/x/net v0.19.0/go.mod h1:CfAk/cbD4CthTvqiEl8NpboMuiuOYsAr/7NOjZJtv1U=
 golang.org/x/net v0.35.0 h1:T5GQRQb2y08kTAByq9L4/bz8cipCdA8FbRTXewonqY8=
 golang.org/x/net v0.35.0/go.mod h1:EglIi67kWsHKlRzzVMUD93VMSWGFOMSZgxFjparz1Qk=
+golang.org/x/oauth2 v0.23.0/go.mod h1:XYTD2NtWslqkgxebSiOHnXEap4TF09sJSc7H1sXbhtI=
 golang.org/x/oauth2 v0.30.0 h1:dnDm7JmhM45NNpd8FDDeLhK6FwqbOf4MLCM9zb1BOHI=
 golang.org/x/oauth2 v0.30.0/go.mod h1:B++QgG3ZKulg6sRPGD/mqlHQs5rB3Ml9erfeDY7xKlU=
 golang.org/x/sync v0.0.0-20180314180146-1d60e4601c6f/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
 golang.org/x/sync v0.0.0-20201020160332-67f06af15bc9/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.0.0-20220722155255-886fb9371eb4/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.1.0/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM=
+golang.org/x/sync v0.15.0 h1:KWH3jNZsfyT6xfAfKiz6MRNmd46ByHDYaZ7KSkCtdW8=
+golang.org/x/sync v0.15.0/go.mod h1:1dzgHSNfp02xaA81J2MS99Qcpr2w7fw1gpm99rleRqA=
 golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20190904154756-749cb33beabd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
 golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210112080510-489259a85091/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210330210617-4fbd30eecc44/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210423082822-04245dca01da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
+golang.org/x/sys v0.0.0-20210615035016-665e8c7367d1/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220520151302-bc2c85ada10a/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.0.0-20220715151400-c0bba94af5f8/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.0.0-20220722155257-8c9f86f7a55f/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.5.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.6.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.8.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
+golang.org/x/sys v0.15.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.33.0 h1:q3i8TbbEz+JRD9ywIRlyRAQbM0qF7hu24q3teo2hbuw=
 golang.org/x/sys v0.33.0/go.mod h1:BJP2sWEmIv4KK5OTEluFJCKSidICx8ciO85XgH3Ak8k=
+golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
+golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
+golang.org/x/term v0.5.0/go.mod h1:jMB1sMXY+tzblOD4FWmEbocvup2/aLOaQEp7JmGp78k=
+golang.org/x/term v0.8.0/go.mod h1:xPskH00ivmX89bAKVGSKKtLOWNx2+17Eiy94tnKShWo=
+golang.org/x/term v0.15.0/go.mod h1:BDl952bC7+uMoWR75FIrCDx79TPU9oHkTZ9yRbYOrX0=
 golang.org/x/term v0.32.0 h1:DR4lr0TjUs3epypdhTOkMmuF5CDFJ/8pOnbzMZPQ7bg=
 golang.org/x/term v0.32.0/go.mod h1:uZG1FhGx848Sqfsq4/DlJr3xGGsYMu/L5GW4abiaEPQ=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.6/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
+golang.org/x/text v0.3.7/go.mod h1:u+2+/6zg+i71rQMx5EYifcz6MCKuco9NR6JIITiCfzQ=
+golang.org/x/text v0.7.0/go.mod h1:mrYo+phRRbMaCq/xk9113O4dZlRixOauAjOtrjsXDZ8=
+golang.org/x/text v0.9.0/go.mod h1:e1OnstbJyHTd6l/uOt8jFFHp6TRDWZR/bV3emEE/zU8=
+golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.26.0 h1:P42AVeLghgTYr4+xUnTRKDMqpar+PtX7KWuNQL21L8M=
 golang.org/x/text v0.26.0/go.mod h1:QK15LZJUUQVJxhz7wXgxSy/CJaTFjd0G+YLonydOVQA=
 golang.org/x/time v0.14.0 h1:MRx4UaLrDotUKUdCIqzPC48t1Y9hANFKIRpNx+Te8PI=
@@ -279,7 +377,10 @@ golang.org/x/time v0.14.0/go.mod h1:eL/Oa2bBBK0TkX57Fyni+NgnyQQN4LitPmob2Hjnqw4=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
 golang.org/x/tools v0.0.0-20191119224855-298f0cb1881e/go.mod h1:b+2E5dAYhXwXZwtnZ6UAqBI28+e2cm9otk0dWdXHAEo=
 golang.org/x/tools v0.0.0-20200619180055-7c47624df98f/go.mod h1:EkVYQZoAsY45+roYkvgYkIh4xh/qjgUK9TdY2XT94GE=
+golang.org/x/tools v0.0.0-20201224043029-2b0845dc783e/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
 golang.org/x/tools v0.0.0-20210106214847-113979e3529a/go.mod h1:emZCQorbCU4vsT4fOWvOPXz4eW1wZW4PmDk9uLelYpA=
+golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc=
+golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/tools v0.34.0 h1:qIpSLOxeCYGg9TrcJokLBG4KFA6d795g0xkBkiESGlo=
 golang.org/x/tools v0.34.0/go.mod h1:pAP9OwEaY1CAW3HOmg3hLZC5Z0CCmzjAF2UQMSqNARg=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
@@ -292,14 +393,28 @@ google.golang.org/genproto/googleapis/rpc v0.0.0-20250115164207-1a7da9e5054f h1:
 google.golang.org/genproto/googleapis/rpc v0.0.0-20250115164207-1a7da9e5054f/go.mod h1:+2Yz8+CLJbIfL9z73EW45avw8Lmge3xVElCP9zEKi50=
 google.golang.org/grpc v1.69.4 h1:MF5TftSMkd8GLw/m0KM6V8CMOCY6NZ1NQDPGFgbTt4A=
 google.golang.org/grpc v1.69.4/go.mod h1:vyjdE6jLBI76dgpDojsFGNaHlxdjXN9ghpnd2o7JGZ4=
+google.golang.org/protobuf v0.0.0-20200109180630-ec00e32a8dfd/go.mod h1:DFci5gLYBciE7Vtevhsrf46CRTquxDuWsQurQQe4oz8=
+google.golang.org/protobuf v0.0.0-20200221191635-4d8936d0db64/go.mod h1:kwYJMbMJ01Woi6D6+Kah6886xMZcty6N08ah7+eCXa0=
+google.golang.org/protobuf v0.0.0-20200228230310-ab0ca4ff8a60/go.mod h1:cfTl7dwQJ+fmap5saPgwCLgHXTUD7jkjRqWcaiX5VyM=
+google.golang.org/protobuf v1.20.1-0.20200309200217-e05f789c0967/go.mod h1:A+miEFZTKqfCUM6K7xSMQL9OKL/b6hQv+e19PK+JZNE=
+google.golang.org/protobuf v1.21.0/go.mod h1:47Nbq4nVaFHyn7ilMalzfO3qCViNmqZ2kzikPIcrTAo=
+google.golang.org/protobuf v1.23.0/go.mod h1:EGpADcykh3NcUnDUJcl1+ZksZNG86OlYog2l/sGQquU=
+google.golang.org/protobuf v1.26.0-rc.1/go.mod h1:jlhhOSvTdKEhbULTjvd4ARK9grFBp09yW+WbY/TyQbw=
+google.golang.org/protobuf v1.26.0/go.mod h1:9q0QmTI4eRPtz6boOQmLYwt+qCgq0jsYwAQnmE0givc=
 google.golang.org/protobuf v1.36.3 h1:82DV7MYdb8anAVi3qge1wSnMDrnKK7ebr+I0hHRN1BU=
 google.golang.org/protobuf v1.36.3/go.mod h1:9fA7Ob0pmnwhb644+1+CVWFRbNajQ6iRojtC/QF5bRE=
 gopkg.in/check.v1 v0.0.0-20161208181325-20d25e280405/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
+gopkg.in/check.v1 v1.0.0-20180628173108-788fd7840127/go.mod h1:Co6ibVJAznAaIkqp8huTwlJQCZ016jof/cbN4VW5Yz0=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c h1:Hei/4ADfdWqJk1ZMxUNpqntNwaWcugrBjAiHlqqRiVk=
 gopkg.in/check.v1 v1.0.0-20201130134442-10cb98267c6c/go.mod h1:JHkPIbrfpd72SG/EVd6muEfDQjcINNoR0C8j2r3qZ4Q=
+gopkg.in/errgo.v2 v2.1.0/go.mod h1:hNsd1EY+bozCKY1Ytp96fpM3vjJbqLJn88ws8XvfDNI=
 gopkg.in/fsnotify.v1 v1.4.7/go.mod h1:Tz8NjZHkW78fSQdbUxIjBTcgA1z1m8ZHf0WmKUhAMys=
 gopkg.in/tomb.v1 v1.0.0-20141024135613-dd632973f1e7/go.mod h1:dt/ZhP58zS4L8KSrWDmTeBkI65Dw0HsyUHuEVlX15mw=
 gopkg.in/yaml.v2 v2.2.1/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.2/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.2.4/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.3.0/go.mod h1:hI93XBmqTisBFMUTm0b8Fm+jr3Dg1NNxqwp+5A1VGuI=
+gopkg.in/yaml.v2 v2.4.0/go.mod h1:RDklbk79AGWmwhnvt/jBztapEOGDOx6ZbXqjP6csGnQ=
 gopkg.in/yaml.v3 v3.0.0-20200313102051-9f266ea9e77c/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
 gopkg.in/yaml.v3 v3.0.1 h1:fxVm/GzAzEWqLHuvctI91KS9hhNmmWOoWu0XTYJS7CA=
 gopkg.in/yaml.v3 v3.0.1/go.mod h1:K4uyk7z7BCEPqu6E+C64Yfv1cQ7kz7rIZviUmN+EgEM=
@@ -779,13 +779,26 @@ func (a *Agent) ExecuteMCPToolForConversation(ctx context.Context, conversationI
 	return a.executeToolViaMCP(ctx, toolName, args)
 }

-// RecordLocalToolExecution 将非 CallTool 路径完成的工具调用写入 MCP 监控库（与 CallTool 落库一致），返回 executionId。
-// 用于 Eino filesystem execute 等场景，使助手气泡「渗透测试详情」与常规 MCP 一致可点进监控。
-func (a *Agent) RecordLocalToolExecution(toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+// BeginLocalToolExecution 在非 CallTool 路径工具开始时写入 running 状态，供 MCP 监控页展示「执行中」。
+func (a *Agent) BeginLocalToolExecution(toolName string, args map[string]interface{}) string {
 	if a == nil || a.mcpServer == nil {
 		return ""
 	}
-	return a.mcpServer.RecordCompletedToolInvocation(toolName, args, resultText, invokeErr)
+	return a.mcpServer.BeginToolExecution(toolName, args)
+}
+
+// FinishLocalToolExecution 完成 BeginLocalToolExecution 创建的记录；executionID 为空时一次性写入已完成记录。
+func (a *Agent) FinishLocalToolExecution(executionID, toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+	if a == nil || a.mcpServer == nil {
+		return ""
+	}
+	return a.mcpServer.FinishToolExecution(executionID, toolName, args, resultText, invokeErr)
+}
+
+// RecordLocalToolExecution 将非 CallTool 路径完成的工具调用写入 MCP 监控库（与 CallTool 落库一致），返回 executionId。
+// 用于 Eino filesystem execute 等场景，使助手气泡「渗透测试详情」与常规 MCP 一致可点进监控。
+func (a *Agent) RecordLocalToolExecution(toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+	return a.FinishLocalToolExecution("", toolName, args, resultText, invokeErr)
 }

 // UpdateMCPExecutionDisplayResult 将监控库中的工具结果更新为送入模型的展示正文（reduction 后）。
@@ -1,7 +1,7 @@
 package agent

 import (
-	"cyberstrike-ai/internal/project"
+	"cyberstrike-ai/internal/projectprompt"
 )

 // DefaultSingleAgentSystemPrompt 单代理（Eino ADK / MCP）内置系统提示；可通过 agent.system_prompt_path 覆盖为文件。
@@ -107,11 +107,13 @@ func DefaultSingleAgentSystemPrompt() string {
 - 若最近一步得到 404/空结果/无效响应，不得直接结束；至少再进行一次“同目标不同策略”的验证（如变更路径、参数、请求方法、上下文来源）。
 - 避免无效空转：同一工具+同类参数连续失败 3 次后，必须切换策略（改工具、改入口、改假设）并说明切换原因。

-` + project.FactRecordingBlackboardSection(false) + `
+` + projectprompt.FactRecordingBlackboardSection(false) + `

 ## 技能库（Skills）与知识库

 - 技能包位于服务器 skills/ 目录（各子目录 SKILL.md，遵循 agentskills.io）；知识库用于向量检索片段，Skills 为可执行工作流指令。
 - 本会话通过 MCP 使用知识库与漏洞记录等。Skills 由 Eino ADK skill 工具按需加载（配置 multi_agent.eino_skills；单代理与多代理均可，未启用时无 skill 工具）。
- 需要完整 Skill 工作流但当前无 skill 工具时，请确认已启用 multi_agent.eino_skills，或改用 Deep / Supervisor 等多代理编排（/api/multi-agent/stream）。`
+- 需要完整 Skill 工作流但当前无 skill 工具时，请确认已启用 multi_agent.eino_skills，或改用 Deep / Supervisor 等多代理编排（/api/multi-agent/stream）。
+
+` + projectprompt.ShellExecExecuteGuidanceSection()
 }
@@ -21,10 +21,13 @@ import (
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/einoobserve"
 	"cyberstrike-ai/internal/handler"
+	"cyberstrike-ai/internal/hitl"
 	"cyberstrike-ai/internal/knowledge"
 	"cyberstrike-ai/internal/logger"
 	"cyberstrike-ai/internal/mcp"
 	"cyberstrike-ai/internal/mcp/builtin"
+	"cyberstrike-ai/internal/monitor"
+	"cyberstrike-ai/internal/multiagent"
 	"cyberstrike-ai/internal/robot"
 	"cyberstrike-ai/internal/security"
 	"cyberstrike-ai/internal/skillpackage"
@@ -52,11 +55,15 @@ type App struct {
 	knowledgeIndexer   *knowledge.Indexer        // 知识库索引器（用于动态初始化）
 	knowledgeHandler   *handler.KnowledgeHandler // 知识库处理器（用于动态初始化）
 	agentHandler       *handler.AgentHandler     // Agent处理器（用于更新知识库管理器）
-	robotHandler       *handler.RobotHandler     // 机器人处理器（钉钉/飞书/企业微信）
-	robotMu            sync.Mutex                // 保护钉钉/飞书长连接的 cancel
+	robotHandler       *handler.RobotHandler     // 机器人处理器（钉钉/飞书/企业微信等）
+	robotMu            sync.Mutex                // 保护机器人长连接的 cancel
 	dingCancel         context.CancelFunc        // 钉钉 Stream 取消函数，用于配置变更时重启
 	larkCancel         context.CancelFunc        // 飞书长连接取消函数，用于配置变更时重启
 	wechatCancel       context.CancelFunc        // 微信 iLink 长轮询取消函数
+	telegramCancel     context.CancelFunc        // Telegram 长轮询取消函数
+	slackCancel        context.CancelFunc        // Slack Socket Mode 取消函数
+	discordCancel      context.CancelFunc        // Discord Gateway 取消函数
+	qqCancel           context.CancelFunc        // QQ WebSocket 取消函数
 	c2Manager          *c2.Manager               // C2 管理器（未启用 C2 时为 nil）
 	c2Watchdog         *c2.SessionWatchdog       // C2 会话看门狗
 	c2WatchdogCancel   context.CancelFunc        // 看门狗取消函数
@@ -66,6 +73,10 @@ type App struct {

 // New 创建新应用
 func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error) {
+	if err := multiagent.InitADK(); err != nil {
+		return nil, fmt.Errorf("初始化 Eino ADK: %w", err)
+	}
+
 	gin.SetMode(gin.ReleaseMode)
 	router := gin.Default()

@@ -99,12 +110,21 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	auditSvc.PurgeExpired()
 	audit.StartRetentionLoop(auditSvc, log.Logger)

+	monitorRetention := monitor.NewService(db, cfg, log.Logger)
+	monitorRetention.PurgeExpired()
+	monitor.StartRetentionLoop(monitorRetention, log.Logger)
+
+	hitlRetention := hitl.NewService(db, cfg, log.Logger)
+	hitlRetention.PurgeExpired()
+	hitl.StartRetentionLoop(hitlRetention, log.Logger)
+
 	// 创建MCP服务器（带数据库持久化）
 	mcpServer := mcp.NewServerWithStorage(log.Logger, db)
 	mcpServer.ConfigureHTTPToolCallTimeoutFromAgentMinutes(cfg.Agent.ToolTimeoutMinutes)

 	// 创建安全工具执行器
 	executor := security.NewExecutor(&cfg.Security, mcpServer, log.Logger)
+	executor.SetShellNoOutputTimeoutSeconds(cfg.Agent.ShellNoOutputTimeoutSeconds)

 	// 注册工具
 	executor.RegisterTools(mcpServer)
@@ -129,6 +149,10 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 		externalMCPMgr.StartAllEnabled()
 	}

+	execReconciler := monitor.NewExecutionReconciler(db, mcpServer, externalMCPMgr, log.Logger)
+	execReconciler.ReconcileOnStartup()
+	monitor.StartStaleRunningReconcileLoop(execReconciler, log.Logger)
+
 	// 创建Agent
 	maxIterations := cfg.Agent.MaxIterations
 	if maxIterations <= 0 {
@@ -187,14 +211,12 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 			return nil, fmt.Errorf("初始化知识库嵌入器失败: %w", err)
 		}

-		// 创建检索器
-		retrievalConfig := &knowledge.RetrievalConfig{
-			TopK:                cfg.Knowledge.Retrieval.TopK,
-			SimilarityThreshold: cfg.Knowledge.Retrieval.SimilarityThreshold,
-			SubIndexFilter:      cfg.Knowledge.Retrieval.SubIndexFilter,
-			PostRetrieve:        cfg.Knowledge.Retrieval.PostRetrieve,
-		}
+		// 创建检索器（Eino MultiQuery + 重排流水线）
+		retrievalConfig := knowledge.RetrievalConfigFromYAML(cfg.Knowledge.Retrieval)
 		knowledgeRetriever = knowledge.NewRetriever(knowledgeDB, embedder, retrievalConfig, log.Logger)
+		if err := knowledge.WireRetrieverPipeline(context.Background(), knowledgeRetriever, &cfg.OpenAI); err != nil {
+			return nil, fmt.Errorf("初始化知识库检索流水线失败: %w", err)
+		}

 		// 创建索引器（Eino Compose 链）
 		knowledgeIndexer, err = knowledge.NewIndexer(context.Background(), knowledgeDB, embedder, log.Logger, &cfg.Knowledge)
@@ -298,7 +320,9 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	plantaskBase := filepath.Join(skillsDir, plantaskRel)
 	// Match eino_adk_run_loop: checkpoint_dir is used as configured (relative to process CWD when not absolute).
 	checkpointBase := strings.TrimSpace(cfg.MultiAgent.EinoMiddleware.CheckpointDir)
-	db.SetEinoConversationDirs(plantaskBase, checkpointBase)
+	reductionRoot := strings.TrimSpace(cfg.MultiAgent.EinoMiddleware.ReductionRootDir)
+	workspaceRoot := strings.TrimSpace(cfg.Agent.WorkspaceRootDir)
+	db.SetEinoConversationDirs(plantaskBase, checkpointBase, reductionRoot, workspaceRoot)
 	agent.SetPromptBaseDir(configDir)

 	agentsDir := cfg.AgentsDir
@@ -325,7 +349,10 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	}
 	monitorHandler := handler.NewMonitorHandler(mcpServer, executor, db, log.Logger)
 	monitorHandler.SetAudit(auditSvc)
+	monitorHandler.SetMonitorRetention(monitorRetention)
 	monitorHandler.SetExternalMCPManager(externalMCPMgr) // 设置外部MCP管理器，以便获取外部MCP执行记录
+	monitorHandler.SetTaskManager(agentHandler.TaskManager())
+	monitorHandler.SetAgentHandler(agentHandler)
 	notificationHandler := handler.NewNotificationHandler(db, agentHandler, log.Logger)
 	groupHandler := handler.NewGroupHandler(db, log.Logger)
 	authHandler := handler.NewAuthHandler(authManager, cfg, configPath, log.Logger)
@@ -333,6 +360,9 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	attackChainHandler := handler.NewAttackChainHandler(db, &cfg.OpenAI, log.Logger)
 	vulnerabilityHandler := handler.NewVulnerabilityHandler(db, log.Logger)
 	projectHandler := handler.NewProjectHandler(db, log.Logger)
+	workflowHandler := handler.NewWorkflowHandler(db, log.Logger)
+	workflowHandler.SetAudit(auditSvc)
+	workflowHandler.SetRuntime(agent, cfg)
 	vulnerabilityHandler.SetAudit(auditSvc)
 	webshellHandler := handler.NewWebShellHandler(log.Logger, db)
 	webshellHandler.SetAudit(auditSvc)
@@ -343,6 +373,8 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	configHandler := handler.NewConfigHandler(configPath, cfg, mcpServer, executor, agent, attackChainHandler, externalMCPMgr, log.Logger)
 	configHandler.SetAudit(auditSvc)
 	agentHandler.SetHitlToolWhitelistSaver(configHandler)
+	agentHandler.SetHitlAuditStrategySaver(configHandler)
+	agentHandler.SetHitlDefaultReviewerSaver(configHandler)
 	externalMCPHandler := handler.NewExternalMCPHandler(externalMCPMgr, cfg, configPath, log.Logger)
 	externalMCPHandler.SetAudit(auditSvc)
 	roleHandler := handler.NewRoleHandler(cfg, configPath, log.Logger)
@@ -368,6 +400,7 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	// 创建OpenAPI处理器
 	conversationHandler := handler.NewConversationHandler(db, log.Logger)
 	conversationHandler.SetAudit(auditSvc)
+	conversationHandler.SetTaskStopper(agentHandler)
 	auditHandler := handler.NewAuditHandler(db, auditSvc, log.Logger)
 	robotHandler := handler.NewRobotHandler(cfg, db, agentHandler, log.Logger)
 	openAPIHandler := handler.NewOpenAPIHandler(db, log.Logger, conversationHandler, agentHandler)
@@ -492,6 +525,7 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 		app, // 传递 App 实例以便动态获取 knowledgeHandler
 		vulnerabilityHandler,
 		projectHandler,
+		workflowHandler,
 		webshellHandler,
 		chatUploadsHandler,
 		roleHandler,
@@ -698,6 +732,26 @@ func (a *App) startRobotConnections() {
 		a.wechatCancel = cancel
 		go robot.StartWechat(ctx, cfg.Robots, a.robotHandler, cfg.Version, a.logger.Logger)
 	}
+	if cfg.Robots.Telegram.Enabled && strings.TrimSpace(cfg.Robots.Telegram.BotToken) != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.telegramCancel = cancel
+		go robot.StartTelegram(ctx, cfg.Robots, a.robotHandler, a.logger.Logger)
+	}
+	if cfg.Robots.Slack.Enabled && strings.TrimSpace(cfg.Robots.Slack.BotToken) != "" && strings.TrimSpace(cfg.Robots.Slack.AppToken) != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.slackCancel = cancel
+		go robot.StartSlack(ctx, cfg.Robots, a.robotHandler, a.logger.Logger)
+	}
+	if cfg.Robots.Discord.Enabled && strings.TrimSpace(cfg.Robots.Discord.BotToken) != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.discordCancel = cancel
+		go robot.StartDiscord(ctx, cfg.Robots, a.robotHandler, a.logger.Logger)
+	}
+	if cfg.Robots.QQ.Enabled && strings.TrimSpace(cfg.Robots.QQ.AppID) != "" && strings.TrimSpace(cfg.Robots.QQ.ClientSecret) != "" {
+		ctx, cancel := context.WithCancel(context.Background())
+		a.qqCancel = cancel
+		go robot.StartQQ(ctx, cfg.Robots, a.robotHandler, a.logger.Logger)
+	}
 }

 // RestartRobotConnections 重启钉钉/飞书/微信长连接，使前端应用配置后立即生效（实现 handler.RobotRestarter）
@@ -715,6 +769,22 @@ func (a *App) RestartRobotConnections() {
 		a.wechatCancel()
 		a.wechatCancel = nil
 	}
+	if a.telegramCancel != nil {
+		a.telegramCancel()
+		a.telegramCancel = nil
+	}
+	if a.slackCancel != nil {
+		a.slackCancel()
+		a.slackCancel = nil
+	}
+	if a.discordCancel != nil {
+		a.discordCancel()
+		a.discordCancel = nil
+	}
+	if a.qqCancel != nil {
+		a.qqCancel()
+		a.qqCancel = nil
+	}
 	a.robotMu.Unlock()
 	// 给旧 goroutine 一点时间退出
 	time.Sleep(200 * time.Millisecond)
@@ -738,6 +808,7 @@ func setupRoutes(
 	app *App, // 传递 App 实例以便动态获取 knowledgeHandler
 	vulnerabilityHandler *handler.VulnerabilityHandler,
 	projectHandler *handler.ProjectHandler,
+	workflowHandler *handler.WorkflowHandler,
 	webshellHandler *handler.WebShellHandler,
 	chatUploadsHandler *handler.ChatUploadsHandler,
 	roleHandler *handler.RoleHandler,
@@ -791,11 +862,20 @@ func setupRoutes(
 		protected.POST("/eino-agent", agentHandler.EinoSingleAgentLoop)
 		protected.POST("/eino-agent/stream", agentHandler.EinoSingleAgentLoopStream)
 		protected.GET("/hitl/pending", agentHandler.ListHITLPending)
+		protected.GET("/hitl/logs", agentHandler.ListHITLLogs)
+		protected.DELETE("/hitl/logs", agentHandler.DeleteHITLLogs)
+		protected.GET("/hitl/logs/:id", agentHandler.GetHITLLog)
 		protected.POST("/hitl/decision", agentHandler.DecideHITLInterrupt)
 		protected.POST("/hitl/dismiss", agentHandler.DismissHITLInterrupt)
 		protected.GET("/hitl/config/:conversationId", agentHandler.GetHITLConversationConfig)
 		protected.PUT("/hitl/config", agentHandler.UpsertHITLConversationConfig)
+		protected.GET("/hitl/tool-whitelist", agentHandler.GetHITLGlobalToolWhitelist)
+		protected.PUT("/hitl/tool-whitelist", agentHandler.SetHITLGlobalToolWhitelist)
 		protected.POST("/hitl/tool-whitelist", agentHandler.MergeHITLGlobalToolWhitelist)
+		protected.GET("/hitl/default-reviewer", agentHandler.GetHITLDefaultReviewer)
+		protected.PUT("/hitl/default-reviewer", agentHandler.UpdateHITLDefaultReviewer)
+		protected.GET("/hitl/audit-strategy", agentHandler.GetHITLAuditStrategy)
+		protected.PUT("/hitl/audit-strategy", agentHandler.UpdateHITLAuditStrategy)
 		// Agent Loop 取消与任务列表
 		protected.POST("/agent-loop/cancel", agentHandler.CancelAgentLoop)
 		protected.GET("/agent-loop/tasks", agentHandler.ListAgentTasks)
@@ -829,6 +909,7 @@ func setupRoutes(
 		protected.PUT("/batch-tasks/:queueId/schedule-enabled", agentHandler.SetBatchQueueScheduleEnabled)
 		protected.DELETE("/batch-tasks/:queueId", agentHandler.DeleteBatchQueue)
 		protected.PUT("/batch-tasks/:queueId/tasks/:taskId", agentHandler.UpdateBatchTask)
+		protected.POST("/batch-tasks/:queueId/tasks/:taskId/run", agentHandler.RunSingleBatchTask)
 		protected.POST("/batch-tasks/:queueId/tasks", agentHandler.AddBatchTask)
 		protected.DELETE("/batch-tasks/:queueId/tasks/:taskId", agentHandler.DeleteBatchTask)

@@ -1068,6 +1149,11 @@ func setupRoutes(
 		protected.GET("/projects/:id", projectHandler.GetProject)
 		protected.PUT("/projects/:id", projectHandler.UpdateProject)
 		protected.DELETE("/projects/:id", projectHandler.DeleteProject)
+		protected.GET("/projects/:id/fact-graph", projectHandler.GetFactGraph)
+		protected.GET("/projects/:id/fact-edges", projectHandler.ListFactEdges)
+		protected.POST("/projects/:id/fact-edges", projectHandler.CreateFactEdge)
+		protected.DELETE("/projects/:id/fact-edges/:edgeId", projectHandler.DeleteFactEdge)
+		protected.POST("/projects/:id/promote-attack-chain/:conversationId", projectHandler.PromoteAttackChain)
 		protected.GET("/projects/:id/facts", projectHandler.ListFacts)
 		protected.POST("/projects/:id/facts", projectHandler.CreateFact)
 		protected.PUT("/projects/:id/facts/:factId", projectHandler.UpdateFact)
@@ -1151,6 +1237,19 @@ func setupRoutes(
 		protected.PUT("/roles/:name", roleHandler.UpdateRole)
 		protected.DELETE("/roles/:name", roleHandler.DeleteRole)

+		// 图编排 / 工作流定义（图结构固定，业务字段保存在 graph_json 中）
+		protected.GET("/workflows/runs/pending", workflowHandler.ListPendingRuns)
+		protected.GET("/workflows/runs/:runId/replay", workflowHandler.ReplayRun)
+		protected.GET("/workflows/runs/:runId", workflowHandler.GetRun)
+		protected.POST("/workflows/runs/:runId/resume", workflowHandler.ResumeRun)
+		protected.POST("/workflows/validate", workflowHandler.Validate)
+		protected.POST("/workflows/dry-run", workflowHandler.DryRun)
+		protected.GET("/workflows", workflowHandler.List)
+		protected.GET("/workflows/:id", workflowHandler.Get)
+		protected.POST("/workflows", workflowHandler.Create)
+		protected.PUT("/workflows/:id", workflowHandler.Update)
+		protected.DELETE("/workflows/:id", workflowHandler.Delete)
+
 		// Skills管理（具体路径需注册在 /skills/:name 之前）
 		protected.GET("/skills", skillsHandler.GetSkills)
 		protected.GET("/skills/stats", skillsHandler.GetSkillStats)
@@ -1760,14 +1859,12 @@ func initializeKnowledge(
 		return nil, fmt.Errorf("初始化知识库嵌入器失败: %w", err)
 	}

-	// 创建检索器
-	retrievalConfig := &knowledge.RetrievalConfig{
-		TopK:                cfg.Knowledge.Retrieval.TopK,
-		SimilarityThreshold: cfg.Knowledge.Retrieval.SimilarityThreshold,
-		SubIndexFilter:      cfg.Knowledge.Retrieval.SubIndexFilter,
-		PostRetrieve:        cfg.Knowledge.Retrieval.PostRetrieve,
-	}
+	// 创建检索器（Eino MultiQuery + 重排流水线）
+	retrievalConfig := knowledge.RetrievalConfigFromYAML(cfg.Knowledge.Retrieval)
 	knowledgeRetriever := knowledge.NewRetriever(knowledgeDB, embedder, retrievalConfig, logger)
+	if err := knowledge.WireRetrieverPipeline(context.Background(), knowledgeRetriever, &cfg.OpenAI); err != nil {
+		return nil, fmt.Errorf("初始化知识库检索流水线失败: %w", err)
+	}

 	// 创建索引器（Eino Compose 链）
 	knowledgeIndexer, err := knowledge.NewIndexer(context.Background(), knowledgeDB, embedder, logger, &cfg.Knowledge)
@@ -89,6 +89,28 @@ func registerProjectFactTools(mcpServer *mcp.Server, db *database.DB, cfg *confi
 					"type":        "string",
 					"description": "可选：关联的漏洞记录 ID",
 				},
+				"links": map[string]interface{}{
+					"type": "array",
+					"description": "可选：关系边（from → 当前 fact）。finding 至少 1 条 {from:target/*, type:discovered_on}；finding 上记录 exploit 用 {from:exploit/*, type:exploits}。省略保留已有边；传 [] 清空全部关系边。",
+					"items": map[string]interface{}{
+						"type": "object",
+						"properties": map[string]interface{}{
+							"from": map[string]interface{}{
+								"type":        "string",
+								"description": "来源 fact_key：存储为 from → 当前 fact",
+							},
+							"type": map[string]interface{}{
+								"type":        "string",
+								"description": "depends_on | leads_to | enables | exploits | discovered_on | contains | part_of | supports",
+							},
+							"confidence": map[string]interface{}{
+								"type":        "string",
+								"description": "confirmed | tentative | deprecated",
+							},
+						},
+						"required": []string{"from", "type"},
+					},
+				},
 			},
 			"required": []string{"fact_key", "summary"},
 		},
@@ -124,7 +146,26 @@ func registerProjectFactTools(mcpServer *mcp.Server, db *database.DB, cfg *confi
 		if err != nil {
 			return textResult("错误: "+err.Error(), true), nil
 		}
+		if _, hasLinks := args["links"]; hasLinks {
+			linkInputs, err := project.ParseFactLinkInputs(args["links"])
+			if err != nil {
+				return textResult("错误: "+err.Error(), true), nil
+			}
+			convID := agent.ConversationIDFromContext(ctx)
+			if err := project.PersistFactLinksFromParsed(db, projectID, created.FactKey, convID, linkInputs, true); err != nil {
+				return textResult("错误: 保存关系边失败: "+err.Error(), true), nil
+			}
+			created, _ = db.GetProjectFactByKey(projectID, created.FactKey)
+		} else if parsed := project.ParseLinksFromBody(created.Body); len(parsed) > 0 {
+			if err := project.PersistFactIncomingLinks(db, projectID, created.FactKey, parsed, true); err != nil {
+				return textResult("错误: 从 body 解析边失败: "+err.Error(), true), nil
+			}
+			created, _ = db.GetProjectFactByKey(projectID, created.FactKey)
+		}
 		msg := fmt.Sprintf("事实已保存。\nfact_key: %s\nid: %s\nconfidence: %s", created.FactKey, created.ID, created.Confidence)
+		if in, _ := db.ListIncomingProjectFactEdges(projectID, created.FactKey); len(in) > 0 {
+			msg += "\n关系边: " + project.FormatFactLinksText(in)
+		}
 		if warn := project.SparseBodyWarningIfNeeded(f.Category, f.FactKey, f.Body); warn != "" {
 			msg += warn
 		}
@@ -164,6 +205,18 @@ func registerProjectFactTools(mcpServer *mcp.Server, db *database.DB, cfg *confi
 		if f.SourceConversationID != "" {
 			msg += fmt.Sprintf("\nsource_conversation_id: %s", f.SourceConversationID)
 		}
+		if in, _ := db.ListIncomingProjectFactEdges(projectID, f.FactKey); len(in) > 0 {
+			msg += "\n关系边（from → 本 fact）:\n"
+			for _, e := range in {
+				msg += fmt.Sprintf("- %s ← %s (%s)\n", e.EdgeType, e.SourceFactKey, e.Confidence)
+			}
+		}
+		if out, _ := db.ListOutgoingProjectFactEdges(projectID, f.FactKey); len(out) > 0 {
+			msg += "指向其他事实:\n"
+			for _, e := range out {
+				msg += fmt.Sprintf("- %s → %s (%s)\n", e.EdgeType, e.TargetFactKey, e.Confidence)
+			}
+		}
 		msg += "\n\n--- body ---\n" + f.Body
 		if warn := project.SparseBodyWarningIfNeeded(f.Category, f.FactKey, f.Body); warn != "" {
 			msg += warn
@@ -120,9 +120,19 @@ func formatVulnerabilityDetail(v *database.Vulnerability) string {
 		b.WriteString(v.Description)
 		b.WriteString("\n")
 	}
-	if v.Proof != "" {
-		b.WriteString("\n--- 证明（POC） ---\n")
-		b.WriteString(v.Proof)
+	if v.Preconditions != "" {
+		b.WriteString("\n--- 前置条件 ---\n")
+		b.WriteString(v.Preconditions)
+		b.WriteString("\n")
+	}
+	if v.ReproSteps != "" {
+		b.WriteString("\n--- 复现步骤 ---\n")
+		b.WriteString(v.ReproSteps)
+		b.WriteString("\n")
+	}
+	if v.Evidence != "" {
+		b.WriteString("\n--- 证据 / POC ---\n")
+		b.WriteString(v.Evidence)
 		b.WriteString("\n")
 	}
 	if v.Impact != "" {
@@ -135,9 +145,36 @@ func formatVulnerabilityDetail(v *database.Vulnerability) string {
 		b.WriteString(v.Recommendation)
 		b.WriteString("\n")
 	}
+	if v.RetestNotes != "" {
+		b.WriteString("\n--- 复测方式 ---\n")
+		b.WriteString(v.RetestNotes)
+		b.WriteString("\n")
+	}
 	return b.String()
 }

+func missingVulnerabilityReproFields(args map[string]interface{}) []string {
+	required := []struct {
+		key   string
+		label string
+	}{
+		{"target", "target（受影响的 URL/IP/服务/接口）"},
+		{"vulnerability_type", "vulnerability_type（漏洞类型）"},
+		{"description", "description（漏洞摘要与触发点）"},
+		{"reproduction_steps", "reproduction_steps（可逐步执行的复现步骤）"},
+		{"evidence", "evidence（POC、原始请求/响应、命令输出或截图/日志证据）"},
+		{"impact", "impact（确认后的实际影响）"},
+		{"recommendation", "recommendation（修复建议）"},
+	}
+	missing := make([]string, 0)
+	for _, item := range required {
+		if strings.TrimSpace(strArg(args, item.key)) == "" {
+			missing = append(missing, item.label)
+		}
+	}
+	return missing
+}
+
 func truncateRunes(s string, max int) string {
 	r := []rune(s)
 	if len(r) <= max {
@@ -163,18 +200,18 @@ func registerVulnerabilityTools(mcpServer *mcp.Server, db *database.DB, logger *
 func registerRecordVulnerabilityTool(mcpServer *mcp.Server, db *database.DB, logger *zap.Logger) {
 	tool := mcp.Tool{
 		Name:             builtin.ToolRecordVulnerability,
-		Description:      "记录发现的漏洞详情到漏洞管理系统。边渗透边记录：每验证出一条可复现漏洞（含 POC/影响）后立即调用，勿等会话结束。包括标题、描述、严重程度、类型、目标、证明、影响和建议等。记录前可先 list_vulnerabilities 避免重复。",
-		ShortDescription: "记录发现的漏洞详情到漏洞管理系统",
+		Description:      "记录发现的漏洞详情到漏洞管理系统。必须按“仅看本记录即可复现”的标准填写：目标、触发点、前置条件、复现步骤、证据/POC、实际影响、修复建议和复测方式。边渗透边记录：每验证出一条可复现漏洞后立即调用，勿等会话结束。记录前可先 list_vulnerabilities 避免重复。",
+		ShortDescription: "记录可复现的漏洞详情到漏洞管理系统",
 		InputSchema: map[string]interface{}{
 			"type": "object",
 			"properties": map[string]interface{}{
 				"title": map[string]interface{}{
 					"type":        "string",
-					"description": "漏洞标题（必需）",
+					"description": "漏洞标题（必需）。建议格式：<资产/接口> 存在 <漏洞类型>，例如“/api/login 存在 SQL 注入”。",
 				},
 				"description": map[string]interface{}{
 					"type":        "string",
-					"description": "漏洞详细描述",
+					"description": "漏洞摘要与触发点（必需）：说明哪个功能/参数/入口存在问题、为什么可被利用。不要只写结论。",
 				},
 				"severity": map[string]interface{}{
 					"type":        "string",
@@ -183,26 +220,38 @@ func registerRecordVulnerabilityTool(mcpServer *mcp.Server, db *database.DB, log
 				},
 				"vulnerability_type": map[string]interface{}{
 					"type":        "string",
-					"description": "漏洞类型，如：SQL注入、XSS、CSRF、命令注入等",
+					"description": "漏洞类型，如：SQL注入、XSS、CSRF、命令注入等（必需）",
 				},
 				"target": map[string]interface{}{
 					"type":        "string",
-					"description": "受影响的目标（URL、IP地址、服务等）",
+					"description": "受影响的目标（必需）：尽量精确到 URL、IP:端口、服务名、接口路径和参数名。",
 				},
-				"proof": map[string]interface{}{
+				"preconditions": map[string]interface{}{
 					"type":        "string",
-					"description": "漏洞证明（POC、截图、请求/响应等）",
+					"description": "前置条件：登录状态、权限、账号、Header/Cookie、特定数据、网络位置、环境/版本等；无前置条件写“无”。",
+				},
+				"reproduction_steps": map[string]interface{}{
+					"type":        "string",
+					"description": "复现步骤（必需）：按 1/2/3 编号，写清入口、参数、payload、执行命令、观察点。应让未参与对话的人照做即可复现。",
+				},
+				"evidence": map[string]interface{}{
+					"type":        "string",
+					"description": "证据 / POC（必需）：原始 HTTP 请求/响应、curl/工具命令、截图文字说明、日志、DNSLog/回连记录、数据库结果、文件路径、时间戳等。优先放最小可验证证据。",
 				},
 				"impact": map[string]interface{}{
 					"type":        "string",
-					"description": "漏洞影响说明",
+					"description": "漏洞影响说明（必需）：结合已验证事实说明可造成什么后果，避免泛泛而谈。",
 				},
 				"recommendation": map[string]interface{}{
 					"type":        "string",
-					"description": "修复建议",
+					"description": "修复建议（必需）：给出针对该触发点/参数/组件的具体修复和复测建议。",
+				},
+				"retest_notes": map[string]interface{}{
+					"type":        "string",
+					"description": "复测方式：修复后如何验证漏洞已关闭，包括应返回的状态码、错误信息或访问控制结果。",
 				},
 			},
-			"required": []string{"title", "severity"},
+			"required": []string{"title", "description", "severity", "vulnerability_type", "target", "reproduction_steps", "evidence", "impact", "recommendation"},
 		},
 	}

@@ -231,6 +280,9 @@ func registerRecordVulnerabilityTool(mcpServer *mcp.Server, db *database.DB, log
 		if !validSeverities[severity] {
 			return textResult(fmt.Sprintf("错误: severity 必须是 critical、high、medium、low 或 info 之一，当前值: %s", severity), true), nil
 		}
+		if missing := missingVulnerabilityReproFields(args); len(missing) > 0 {
+			return textResult("错误: 漏洞记录缺少复现所需信息，请补充后再记录：\n- "+strings.Join(missing, "\n- ")+"\n\n最佳实践：漏洞管理中的单条记录应独立包含目标、前置条件、复现步骤、证据/POC、影响和修复/复测方式。", true), nil
+		}

 		projectID := ""
 		if pid, perr := db.GetConversationProjectID(conversationID); perr == nil {
@@ -246,9 +298,12 @@ func registerRecordVulnerabilityTool(mcpServer *mcp.Server, db *database.DB, log
 			Status:         "open",
 			Type:           strArg(args, "vulnerability_type"),
 			Target:         strArg(args, "target"),
-			Proof:          strArg(args, "proof"),
+			Preconditions:  strArg(args, "preconditions"),
+			ReproSteps:     strArg(args, "reproduction_steps"),
+			Evidence:       strArg(args, "evidence"),
 			Impact:         strArg(args, "impact"),
 			Recommendation: strArg(args, "recommendation"),
+			RetestNotes:    strArg(args, "retest_notes"),
 		}

 		created, err := db.CreateVulnerability(vuln)
@@ -275,8 +330,8 @@ func registerRecordVulnerabilityTool(mcpServer *mcp.Server, db *database.DB, log

 func registerListVulnerabilitiesTool(mcpServer *mcp.Server, db *database.DB, logger *zap.Logger) {
 	tool := mcp.Tool{
-		Name: builtin.ToolListVulnerabilities,
-		Description: "列出当前授权范围内的漏洞（摘要）。默认：对话已绑定项目时列出该项目下全部漏洞；未绑项目时仅列出当前会话漏洞。可用 scope=conversation 仅看本会话。记录新漏洞前建议先调用以避免重复。",
+		Name:             builtin.ToolListVulnerabilities,
+		Description:      "列出当前授权范围内的漏洞（摘要）。默认：对话已绑定项目时列出该项目下全部漏洞；未绑项目时仅列出当前会话漏洞。可用 scope=conversation 仅看本会话。记录新漏洞前建议先调用以避免重复。",
 		ShortDescription: "列出漏洞（默认当前项目）",
 		InputSchema: map[string]interface{}{
 			"type": "object",
@@ -0,0 +1,203 @@
+package attackchain
+
+import (
+	"fmt"
+	"regexp"
+	"strings"
+
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/project"
+
+	"github.com/google/uuid"
+)
+
+var promoteSlugSanitizer = regexp.MustCompile(`[^a-z0-9._/-]+`)
+
+// PromoteToProjectResult 攻击链沉淀结果。
+type PromoteToProjectResult struct {
+	FactsCreated int                         `json:"facts_created"`
+	FactsUpdated int                         `json:"facts_updated"`
+	EdgesCreated int                         `json:"edges_created"`
+	FactKeys     []string                    `json:"fact_keys"`
+	Graph        *database.ProjectFactGraph  `json:"graph,omitempty"`
+}
+
+// PromoteToProject 将对话攻击链沉淀为项目事实与边。
+func PromoteToProject(db *database.DB, projectID, conversationID string) (*PromoteToProjectResult, error) {
+	if db == nil {
+		return nil, fmt.Errorf("database 未初始化")
+	}
+	projectID = strings.TrimSpace(projectID)
+	conversationID = strings.TrimSpace(conversationID)
+	if projectID == "" || conversationID == "" {
+		return nil, fmt.Errorf("project_id 与 conversation_id 必填")
+	}
+	if _, err := db.GetProject(projectID); err != nil {
+		return nil, fmt.Errorf("项目不存在")
+	}
+	conv, err := db.GetConversation(conversationID)
+	if err != nil {
+		return nil, fmt.Errorf("对话不存在")
+	}
+	if pid := strings.TrimSpace(conv.ProjectID); pid != "" && pid != projectID {
+		return nil, fmt.Errorf("对话已绑定其他项目")
+	}
+
+	nodes, err := db.LoadAttackChainNodes(conversationID)
+	if err != nil {
+		return nil, err
+	}
+	edges, err := db.LoadAttackChainEdges(conversationID)
+	if err != nil {
+		return nil, err
+	}
+	if len(nodes) == 0 {
+		return nil, fmt.Errorf("该对话尚无攻击链，请先在对话中生成攻击链")
+	}
+
+	res := &PromoteToProjectResult{}
+	nodeToKey := make(map[string]string, len(nodes))
+	usedKeys := map[string]int{}
+
+	for _, node := range nodes {
+		key := allocatePromoteFactKey(node, usedKeys)
+		nodeToKey[node.ID] = key
+		category := mapPromoteNodeCategory(node.Type)
+		existing, getErr := db.GetProjectFactByKey(projectID, key)
+		f := &database.ProjectFact{
+			ProjectID:            projectID,
+			FactKey:              key,
+			Category:             category,
+			Summary:              strings.TrimSpace(node.Label),
+			Body:                 formatPromotedFactBody(node, conversationID),
+			Confidence:           "tentative",
+			SourceConversationID: conversationID,
+		}
+		if getErr == nil && existing != nil {
+			f.ID = existing.ID
+			f.CreatedAt = existing.CreatedAt
+			if strings.TrimSpace(f.Summary) == "" {
+				f.Summary = existing.Summary
+			}
+			if _, err := db.UpsertProjectFact(f); err != nil {
+				return nil, err
+			}
+			res.FactsUpdated++
+		} else {
+			if _, err := db.UpsertProjectFact(f); err != nil {
+				return nil, err
+			}
+			res.FactsCreated++
+		}
+		res.FactKeys = append(res.FactKeys, key)
+	}
+
+	for _, edge := range edges {
+		srcKey, ok1 := nodeToKey[edge.Source]
+		tgtKey, ok2 := nodeToKey[edge.Target]
+		if !ok1 || !ok2 || srcKey == tgtKey {
+			continue
+		}
+		edgeType := mapPromoteEdgeType(edge.Type)
+		incoming, _ := db.ListIncomingProjectFactEdges(projectID, tgtKey)
+		merged := project.MergeLinkFromInputsUnique(promoteFromEdgeInputsFromDB(incoming), []database.ProjectFactEdgeFromInput{{From: srcKey, Type: edgeType}})
+		if err := db.ReplaceIncomingProjectFactEdges(projectID, tgtKey, merged); err != nil {
+			return nil, err
+		}
+		res.EdgesCreated++
+		if fact, err := db.GetProjectFactByKey(projectID, tgtKey); err == nil {
+			in, _ := db.ListIncomingProjectFactEdges(projectID, tgtKey)
+			fact.Body = project.SyncBodyLinksSection(fact.Body, in)
+			_, _ = db.UpsertProjectFact(fact)
+		}
+	}
+
+	graph, _ := project.BuildProjectFactGraph(db, projectID, "full", true)
+	res.Graph = graph
+	return res, nil
+}
+
+func promoteFromEdgeInputsFromDB(edges []*database.ProjectFactEdge) []database.ProjectFactEdgeFromInput {
+	out := make([]database.ProjectFactEdgeFromInput, 0, len(edges))
+	for _, e := range edges {
+		out = append(out, database.ProjectFactEdgeFromInput{From: e.SourceFactKey, Type: e.EdgeType, Confidence: e.Confidence})
+	}
+	return out
+}
+
+func mapPromoteNodeCategory(nodeType string) string {
+	switch strings.ToLower(strings.TrimSpace(nodeType)) {
+	case "target":
+		return project.FactCategoryTarget
+	case "vulnerability":
+		return project.FactCategoryFinding
+	case "action":
+		return project.FactCategoryChain
+	default:
+		return project.FactCategoryNote
+	}
+}
+
+func mapPromoteEdgeType(t string) string {
+	switch strings.ToLower(strings.TrimSpace(t)) {
+	case "discovers", "discovered_on", "targets":
+		return "discovered_on"
+	case "exploits":
+		return "exploits"
+	case "enables":
+		return "enables"
+	case "depends_on":
+		return "depends_on"
+	default:
+		return "leads_to"
+	}
+}
+
+func allocatePromoteFactKey(node Node, used map[string]int) string {
+	prefix := "chain/"
+	switch strings.ToLower(strings.TrimSpace(node.Type)) {
+	case "target":
+		prefix = "target/"
+	case "vulnerability":
+		prefix = "finding/"
+	case "action":
+		prefix = "chain/"
+	}
+	base := promoteSlugify(node.Label)
+	if base == "" {
+		base = promoteSlugify(node.ID)
+	}
+	if base == "" {
+		base = uuid.New().String()[:8]
+	}
+	key := prefix + base
+	if n, ok := used[key]; ok {
+		n++
+		used[key] = n
+		key = fmt.Sprintf("%s-%d", key, n)
+	} else {
+		used[key] = 1
+	}
+	return key
+}
+
+func promoteSlugify(s string) string {
+	s = strings.ToLower(strings.TrimSpace(s))
+	s = strings.NewReplacer(" ", "-", "—", "-", "–", "-", "/", "-").Replace(s)
+	s = promoteSlugSanitizer.ReplaceAllString(s, "-")
+	s = strings.Trim(s, "-")
+	if len(s) > 64 {
+		s = s[:64]
+	}
+	return s
+}
+
+func formatPromotedFactBody(node Node, conversationID string) string {
+	var b strings.Builder
+	b.WriteString("## 来源\n")
+	b.WriteString(fmt.Sprintf("- 对话攻击链沉淀\n- source_conversation_id: %s\n- node_id: %s\n- node_type: %s\n\n", conversationID, node.ID, node.Type))
+	b.WriteString("## 摘要\n")
+	b.WriteString(strings.TrimSpace(node.Label))
+	b.WriteString("\n\n## 关联\n- 结构化关系边（自动同步）:\n  （见项目攻击路径图）\n")
+	return b.String()
+}
@@ -27,9 +27,10 @@ type Config struct {
 	Database    DatabaseConfig        `yaml:"database"`
 	Auth        AuthConfig            `yaml:"auth"`
 	Audit       AuditConfig           `yaml:"audit,omitempty" json:"audit,omitempty"`
+	Monitor     MonitorConfig         `yaml:"monitor,omitempty" json:"monitor,omitempty"`
 	ExternalMCP ExternalMCPConfig     `yaml:"external_mcp,omitempty"`
 	Knowledge   KnowledgeConfig       `yaml:"knowledge,omitempty"`
-	C2          C2Config              `yaml:"c2,omitempty" json:"c2,omitempty"` // 内置 C2 总开关；未配置时默认启用
+	C2          C2Config              `yaml:"c2,omitempty" json:"c2,omitempty"`                 // 内置 C2 总开关；未配置时默认启用
 	Robots      RobotsConfig          `yaml:"robots,omitempty" json:"robots,omitempty"`         // 企业微信/钉钉/飞书等机器人配置
 	RolesDir    string                `yaml:"roles_dir,omitempty" json:"roles_dir,omitempty"`   // 角色配置文件目录（新方式）
 	Roles       map[string]RoleConfig `yaml:"roles,omitempty" json:"roles,omitempty"`           // 向后兼容：支持在主配置文件中定义角色
@@ -45,6 +46,7 @@ type ProjectConfig struct {
 	Enabled                 bool   `yaml:"enabled" json:"enabled"`
 	DefaultProjectID        string `yaml:"default_project_id,omitempty" json:"default_project_id,omitempty"` // 机器人/批量等无显式项目时绑定的默认项目
 	FactIndexMaxRunes       int    `yaml:"fact_index_max_runes,omitempty" json:"fact_index_max_runes,omitempty"`
+	FactIndexPathMaxRunes   int    `yaml:"fact_index_path_max_runes,omitempty" json:"fact_index_path_max_runes,omitempty"`
 	FactSummaryMaxRunes     int    `yaml:"fact_summary_max_runes,omitempty" json:"fact_summary_max_runes,omitempty"`
 	DefaultInjectDeprecated bool   `yaml:"default_inject_deprecated,omitempty" json:"default_inject_deprecated,omitempty"`
 }
@@ -57,6 +59,14 @@ func (c ProjectConfig) FactIndexMaxRunesEffective() int {
 	return c.FactIndexMaxRunes
 }

+// FactIndexPathMaxRunesEffective 攻击路径速览段的最大 rune 数（从 fact_index_max_runes 预算中预留）。
+func (c ProjectConfig) FactIndexPathMaxRunesEffective() int {
+	if c.FactIndexPathMaxRunes <= 0 {
+		return 1000
+	}
+	return c.FactIndexPathMaxRunes
+}
+
 // FactSummaryMaxRunesEffective upsert 时 summary 最大 rune 数（索引一行，宜含验证要点）。
 func (c ProjectConfig) FactSummaryMaxRunesEffective() int {
 	if c.FactSummaryMaxRunes <= 0 {
@@ -69,7 +79,7 @@ func (c ProjectConfig) FactSummaryMaxRunesEffective() int {
 type MultiAgentConfig struct {
 	Enabled               bool   `yaml:"enabled" json:"enabled"`
 	RobotDefaultAgentMode string `yaml:"robot_default_agent_mode,omitempty" json:"robot_default_agent_mode,omitempty"` // eino_single | deep | plan_execute | supervisor
-	BatchUseMultiAgent     bool   `yaml:"batch_use_multi_agent" json:"batch_use_multi_agent"` // 为 true 时批量任务队列中每子任务走 Eino 多代理
+	BatchUseMultiAgent    bool   `yaml:"batch_use_multi_agent" json:"batch_use_multi_agent"`                           // 为 true 时批量任务队列中每子任务走 Eino 多代理
 	// Orchestration 已弃用：保留仅兼容旧版 config.yaml；编排由聊天/WebShell 请求体 orchestration 决定，未传时按 deep。
 	Orchestration string `yaml:"orchestration,omitempty" json:"orchestration,omitempty"`
 	// MaxIteration 已废弃：统一使用 agent.max_iterations（YAML 中保留字段仅为兼容旧配置，运行时不读取）。
@@ -77,17 +87,17 @@ type MultiAgentConfig struct {
 	// PlanExecuteLoopMaxIterations plan_execute 模式下 execute↔replan 外层循环上限；0 表示用 Eino 默认 10。
 	PlanExecuteLoopMaxIterations int `yaml:"plan_execute_loop_max_iterations,omitempty" json:"plan_execute_loop_max_iterations,omitempty"`
 	// SubAgentMaxIterations 已废弃：子代理与主代理均使用 agent.max_iterations（Markdown max_iterations>0 可覆盖）。
-	SubAgentMaxIterations int `yaml:"sub_agent_max_iterations,omitempty" json:"sub_agent_max_iterations,omitempty"`
-	WithoutGeneralSubAgent       bool   `yaml:"without_general_sub_agent" json:"without_general_sub_agent"`
-	WithoutWriteTodos            bool   `yaml:"without_write_todos" json:"without_write_todos"`
-	OrchestratorInstruction      string `yaml:"orchestrator_instruction" json:"orchestrator_instruction"`
+	SubAgentMaxIterations   int    `yaml:"sub_agent_max_iterations,omitempty" json:"sub_agent_max_iterations,omitempty"`
+	WithoutGeneralSubAgent  bool   `yaml:"without_general_sub_agent" json:"without_general_sub_agent"`
+	WithoutWriteTodos       bool   `yaml:"without_write_todos" json:"without_write_todos"`
+	OrchestratorInstruction string `yaml:"orchestrator_instruction" json:"orchestrator_instruction"`
 	// OrchestratorInstructionPlanExecute plan_execute 主代理（规划侧）系统提示；非空且 agents/orchestrator-plan-execute.md 正文为空或未存在时生效。不与 Deep 的 orchestrator_instruction 混用。
 	OrchestratorInstructionPlanExecute string `yaml:"orchestrator_instruction_plan_execute,omitempty" json:"orchestrator_instruction_plan_execute,omitempty"`
 	// OrchestratorInstructionSupervisor supervisor 主代理系统提示（transfer/exit 说明仍由运行追加）；非空且 agents/orchestrator-supervisor.md 正文为空或未存在时生效。
 	OrchestratorInstructionSupervisor string                `yaml:"orchestrator_instruction_supervisor,omitempty" json:"orchestrator_instruction_supervisor,omitempty"`
 	SubAgents                         []MultiAgentSubConfig `yaml:"sub_agents" json:"sub_agents"`
-	// SubAgentUserContextMaxRunes caps the user-context supplement appended to task descriptions for sub-agents.
-	// 0 (default) uses the built-in default of 2000 runes; negative value disables injection entirely.
+	// SubAgentUserContextMaxRunes caps user-context supplement for sub-agent task descriptions.
+	// 0 (default) preserves all user turns verbatim; >0 caps total runes; negative disables injection.
 	SubAgentUserContextMaxRunes int `yaml:"sub_agent_user_context_max_runes,omitempty" json:"sub_agent_user_context_max_runes,omitempty"`
 	// EinoSkills configures CloudWeGo Eino ADK skill middleware + optional local filesystem/execute on DeepAgent.
 	EinoSkills MultiAgentEinoSkillsConfig `yaml:"eino_skills,omitempty" json:"eino_skills,omitempty"`
@@ -97,6 +107,11 @@ type MultiAgentConfig struct {
 	EinoCallbacks MultiAgentEinoCallbacksConfig `yaml:"eino_callbacks,omitempty" json:"eino_callbacks,omitempty"`
 }

+// SubAgentUserContextMaxRunesEffective returns max runes for sub-agent task supplement; 0 = unlimited; negative = disabled.
+func (c MultiAgentConfig) SubAgentUserContextMaxRunesEffective() int {
+	return c.SubAgentUserContextMaxRunes
+}
+
 // MultiAgentEinoCallbacksConfig enables Eino unified callbacks on each ADK agent run (deep / plan_execute / supervisor / eino_single).
 // Modes: log_only (zap + optional OTel; no SSE to browser), sse (adds client SSE eino_trace_* when sse_trace_to_client), full (sse rules + stream callback copies closed).
 type MultiAgentEinoCallbacksConfig struct {
@@ -115,11 +130,11 @@ type MultiAgentEinoCallbacksConfig struct {

 // MultiAgentEinoCallbacksOtelConfig OpenTelemetry for Eino callback spans (W3C trace in collector / stdout).
 type MultiAgentEinoCallbacksOtelConfig struct {
-	Enabled     bool    `yaml:"enabled" json:"enabled"`
-	ServiceName string  `yaml:"service_name,omitempty" json:"service_name,omitempty"`
-	Exporter    string  `yaml:"exporter,omitempty" json:"exporter,omitempty"`         // none | stdout | otlphttp
-	OTLPEndpoint string `yaml:"otlp_endpoint,omitempty" json:"otlp_endpoint,omitempty"` // host:port, e.g. localhost:4318 (path /v1/traces)
-	SampleRatio float64 `yaml:"sample_ratio,omitempty" json:"sample_ratio,omitempty"`   // 0–1, default 1.0
+	Enabled      bool    `yaml:"enabled" json:"enabled"`
+	ServiceName  string  `yaml:"service_name,omitempty" json:"service_name,omitempty"`
+	Exporter     string  `yaml:"exporter,omitempty" json:"exporter,omitempty"`           // none | stdout | otlphttp
+	OTLPEndpoint string  `yaml:"otlp_endpoint,omitempty" json:"otlp_endpoint,omitempty"` // host:port, e.g. localhost:4318 (path /v1/traces)
+	SampleRatio  float64 `yaml:"sample_ratio,omitempty" json:"sample_ratio,omitempty"`   // 0–1, default 1.0
 }

 // EinoCallbacksModeEffective returns off | log_only | sse | full.
@@ -230,17 +245,17 @@ type MultiAgentEinoMiddlewareConfig struct {
 	// PlantaskRelDir relative to skills_dir for per-conversation task boards (default .eino/plantask).
 	PlantaskRelDir string `yaml:"plantask_rel_dir,omitempty" json:"plantask_rel_dir,omitempty"`
 	// Reduction truncates/offloads large tool outputs (requires eino local backend for Write).
-	ReductionEnable       bool     `yaml:"reduction_enable,omitempty" json:"reduction_enable,omitempty"`
-	ReductionRootDir      string   `yaml:"reduction_root_dir,omitempty" json:"reduction_root_dir,omitempty"` // 非空：落盘根目录（默认 tmp/reduction）；其下按 projects/{id} 或 conversations/{id} 隔离
-	ReductionMaxLengthForTrunc int `yaml:"reduction_max_length_for_trunc,omitempty" json:"reduction_max_length_for_trunc,omitempty"` // default 12000
-	ReductionMaxTokensForClear int `yaml:"reduction_max_tokens_for_clear,omitempty" json:"reduction_max_tokens_for_clear,omitempty"` // default 50000
-	ReductionClearExclude []string `yaml:"reduction_clear_exclude,omitempty" json:"reduction_clear_exclude,omitempty"`
-	ReductionSubAgents    bool     `yaml:"reduction_sub_agents,omitempty" json:"reduction_sub_agents,omitempty"` // also attach to sub-agents
+	ReductionEnable            bool     `yaml:"reduction_enable,omitempty" json:"reduction_enable,omitempty"`
+	ReductionRootDir           string   `yaml:"reduction_root_dir,omitempty" json:"reduction_root_dir,omitempty"`                         // 非空：落盘根目录（默认 tmp/reduction）；其下按 projects/{id} 或 conversations/{id} 隔离
+	ReductionMaxLengthForTrunc int      `yaml:"reduction_max_length_for_trunc,omitempty" json:"reduction_max_length_for_trunc,omitempty"` // default 12000
+	ReductionMaxTokensForClear int      `yaml:"reduction_max_tokens_for_clear,omitempty" json:"reduction_max_tokens_for_clear,omitempty"` // default 50000
+	ReductionClearExclude      []string `yaml:"reduction_clear_exclude,omitempty" json:"reduction_clear_exclude,omitempty"`
+	ReductionSubAgents         bool     `yaml:"reduction_sub_agents,omitempty" json:"reduction_sub_agents,omitempty"` // also attach to sub-agents
 	// SummarizationTriggerRatio controls summarization trigger threshold as max_total_tokens * ratio (default 0.8).
 	SummarizationTriggerRatio float64 `yaml:"summarization_trigger_ratio,omitempty" json:"summarization_trigger_ratio,omitempty"`
 	// SummarizationEmitInternalEvents controls middleware internal event emission (default true).
 	SummarizationEmitInternalEvents *bool `yaml:"summarization_emit_internal_events,omitempty" json:"summarization_emit_internal_events,omitempty"`
-	// SummarizationRetryMaxAttempts is extra retries after the first summarization Generate attempt; 0 = default 3.
+	// SummarizationRetryMaxAttempts 已废弃：summarization 与 run loop 共用 run_retry_max_attempts 及 isEinoTransientRunError。
 	SummarizationRetryMaxAttempts int `yaml:"summarization_retry_max_attempts,omitempty" json:"summarization_retry_max_attempts,omitempty"`
 	// PlanExecuteUserInputBudgetRatio caps planner/replanner/executor userInput prompt budget ratio (default 0.35).
 	PlanExecuteUserInputBudgetRatio float64 `yaml:"plan_execute_user_input_budget_ratio,omitempty" json:"plan_execute_user_input_budget_ratio,omitempty"`
@@ -254,12 +269,14 @@ type MultiAgentEinoMiddlewareConfig struct {
 	CheckpointDir string `yaml:"checkpoint_dir,omitempty" json:"checkpoint_dir,omitempty"`
 	// DeepOutputKey passed to deep.Config OutputKey (session final text); empty = off.
 	DeepOutputKey string `yaml:"deep_output_key,omitempty" json:"deep_output_key,omitempty"`
-	// DeepModelRetryMaxRetries > 0 enables deep.Config ModelRetryConfig (framework-level chat model retries).
+	// DeepModelRetryMaxRetries 已废弃：临时错误统一由 run loop 内 isEinoTransientRunError + run_retry_max_attempts 处理。
 	DeepModelRetryMaxRetries int `yaml:"deep_model_retry_max_retries,omitempty" json:"deep_model_retry_max_retries,omitempty"`
-	// RunRetryMaxAttempts > 0：429/5xx/网络抖动时 handler 分段续跑次数；0=默认 10。
+	// RunRetryMaxAttempts > 0：429/5xx/网络抖动时可退避重试次数（run loop 与 summarization 共用）；0=默认 10。
 	RunRetryMaxAttempts int `yaml:"run_retry_max_attempts,omitempty" json:"run_retry_max_attempts,omitempty"`
 	// RunRetryMaxBackoffSec 单次退避上限秒数；0=默认 30。
 	RunRetryMaxBackoffSec int `yaml:"run_retry_max_backoff_sec,omitempty" json:"run_retry_max_backoff_sec,omitempty"`
+	// EmptyResponseContinueMaxAttempts Run 成功但未捕获助手正文时 Handler 层退避续跑次数；0=默认 5。
+	EmptyResponseContinueMaxAttempts int `yaml:"empty_response_continue_max_attempts,omitempty" json:"empty_response_continue_max_attempts,omitempty"`
 	// TaskToolDescriptionPrefix when non-empty sets deep.Config TaskToolDescriptionGenerator (sub-agent names appended).
 	TaskToolDescriptionPrefix string `yaml:"task_tool_description_prefix,omitempty" json:"task_tool_description_prefix,omitempty"`
 }
@@ -381,13 +398,13 @@ type MultiAgentSubConfig struct {

 // MultiAgentPublic 返回给前端的精简信息（不含子代理指令全文）。
 type MultiAgentPublic struct {
-	Enabled               bool   `json:"enabled"`
-	RobotDefaultAgentMode string `json:"robot_default_agent_mode,omitempty"`
-	BatchUseMultiAgent    bool   `json:"batch_use_multi_agent"`
-	SubAgentCount                int    `json:"sub_agent_count"`
-	Orchestration                string `json:"orchestration,omitempty"`
-	PlanExecuteLoopMaxIterations int    `json:"plan_execute_loop_max_iterations"`
-	ToolSearchAlwaysVisibleTools []string `json:"tool_search_always_visible_tools,omitempty"`
+	Enabled                               bool     `json:"enabled"`
+	RobotDefaultAgentMode                 string   `json:"robot_default_agent_mode,omitempty"`
+	BatchUseMultiAgent                    bool     `json:"batch_use_multi_agent"`
+	SubAgentCount                         int      `json:"sub_agent_count"`
+	Orchestration                         string   `json:"orchestration,omitempty"`
+	PlanExecuteLoopMaxIterations          int      `json:"plan_execute_loop_max_iterations"`
+	ToolSearchAlwaysVisibleTools          []string `json:"tool_search_always_visible_tools,omitempty"`
 	ToolSearchAlwaysVisibleEffectiveTools []string `json:"tool_search_always_visible_effective_tools,omitempty"`
 }

@@ -428,33 +445,37 @@ func NormalizeMultiAgentOrchestration(s string) string {

 // MultiAgentAPIUpdate 设置页/API 仅更新多代理标量字段；写入 YAML 时不覆盖 sub_agents 等块。
 type MultiAgentAPIUpdate struct {
-	Enabled               bool   `json:"enabled"`
-	RobotDefaultAgentMode string `json:"robot_default_agent_mode,omitempty"`
-	BatchUseMultiAgent    bool   `json:"batch_use_multi_agent"`
-	PlanExecuteLoopMaxIterations *int `json:"plan_execute_loop_max_iterations,omitempty"`
+	Enabled                      bool   `json:"enabled"`
+	RobotDefaultAgentMode        string `json:"robot_default_agent_mode,omitempty"`
+	BatchUseMultiAgent           bool   `json:"batch_use_multi_agent"`
+	PlanExecuteLoopMaxIterations *int   `json:"plan_execute_loop_max_iterations,omitempty"`
 	// 指针区分「JSON 未传该字段」与「传空数组要清空」；省略时不应覆盖 YAML 中的常驻工具白名单。
 	ToolSearchAlwaysVisibleTools *[]string `json:"tool_search_always_visible_tools,omitempty"`
 }

-// RobotsConfig 机器人配置（企业微信、钉钉、飞书、微信 iLink 等）
+// RobotsConfig 机器人配置（企业微信、钉钉、飞书、微信 iLink、Telegram、Slack、Discord、QQ 等）
 type RobotsConfig struct {
-	Session  RobotSessionConfig  `yaml:"session,omitempty" json:"session,omitempty"`   // 机器人会话隔离策略
-	Wechat   RobotWechatConfig   `yaml:"wechat,omitempty" json:"wechat,omitempty"`     // 微信（iLink 扫码绑定）
-	Wecom    RobotWecomConfig    `yaml:"wecom,omitempty" json:"wecom,omitempty"`       // 企业微信
-	Dingtalk RobotDingtalkConfig `yaml:"dingtalk,omitempty" json:"dingtalk,omitempty"` // 钉钉
-	Lark     RobotLarkConfig     `yaml:"lark,omitempty" json:"lark,omitempty"`         // 飞书
+	Session  RobotSessionConfig  `yaml:"session,omitempty" json:"session,omitempty"`     // 机器人会话隔离策略
+	Wechat   RobotWechatConfig   `yaml:"wechat,omitempty" json:"wechat,omitempty"`       // 微信（iLink 扫码绑定）
+	Wecom    RobotWecomConfig    `yaml:"wecom,omitempty" json:"wecom,omitempty"`         // 企业微信
+	Dingtalk RobotDingtalkConfig `yaml:"dingtalk,omitempty" json:"dingtalk,omitempty"`   // 钉钉
+	Lark     RobotLarkConfig     `yaml:"lark,omitempty" json:"lark,omitempty"`           // 飞书
+	Telegram RobotTelegramConfig `yaml:"telegram,omitempty" json:"telegram,omitempty"`   // Telegram
+	Slack    RobotSlackConfig    `yaml:"slack,omitempty" json:"slack,omitempty"`         // Slack
+	Discord  RobotDiscordConfig  `yaml:"discord,omitempty" json:"discord,omitempty"`     // Discord
+	QQ       RobotQQConfig       `yaml:"qq,omitempty" json:"qq,omitempty"`               // QQ 机器人
 }

 // RobotWechatConfig 微信 iLink 机器人配置（个人微信 ClawBot / iLink 协议）
 type RobotWechatConfig struct {
-	Enabled        bool   `yaml:"enabled" json:"enabled"`
-	BotToken       string `yaml:"bot_token,omitempty" json:"bot_token,omitempty"`
-	ILinkBotID     string `yaml:"ilink_bot_id,omitempty" json:"ilink_bot_id,omitempty"`
-	ILinkUserID    string `yaml:"ilink_user_id,omitempty" json:"ilink_user_id,omitempty"`
-	BaseURL        string `yaml:"base_url,omitempty" json:"base_url,omitempty"`               // 默认 https://ilinkai.weixin.qq.com
-	BotType        string `yaml:"bot_type,omitempty" json:"bot_type,omitempty"`               // get_bot_qrcode 参数，默认 3
-	BotAgent       string `yaml:"bot_agent,omitempty" json:"bot_agent,omitempty"`             // base_info.bot_agent
-	GetUpdatesBuf  string `yaml:"get_updates_buf,omitempty" json:"get_updates_buf,omitempty"` // 长轮询游标（运行时）
+	Enabled       bool   `yaml:"enabled" json:"enabled"`
+	BotToken      string `yaml:"bot_token,omitempty" json:"bot_token,omitempty"`
+	ILinkBotID    string `yaml:"ilink_bot_id,omitempty" json:"ilink_bot_id,omitempty"`
+	ILinkUserID   string `yaml:"ilink_user_id,omitempty" json:"ilink_user_id,omitempty"`
+	BaseURL       string `yaml:"base_url,omitempty" json:"base_url,omitempty"`               // 默认 https://ilinkai.weixin.qq.com
+	BotType       string `yaml:"bot_type,omitempty" json:"bot_type,omitempty"`               // get_bot_qrcode 参数，默认 3
+	BotAgent      string `yaml:"bot_agent,omitempty" json:"bot_agent,omitempty"`             // base_info.bot_agent
+	GetUpdatesBuf string `yaml:"get_updates_buf,omitempty" json:"get_updates_buf,omitempty"` // 长轮询游标（运行时）
 }

 // RobotSessionConfig 机器人会话隔离策略
@@ -480,21 +501,63 @@ type RobotWecomConfig struct {
 	AgentID        int64  `yaml:"agent_id" json:"agent_id"`                 // 应用 AgentId
 }

+// ValidateWecomConfig 校验企业微信机器人配置；启用时必须配置 token，否则回调无法防伪造。
+func ValidateWecomConfig(w RobotWecomConfig) error {
+	if !w.Enabled {
+		return nil
+	}
+	if strings.TrimSpace(w.Token) == "" {
+		return fmt.Errorf("robots.wecom.enabled 为 true 时必须配置 robots.wecom.token")
+	}
+	return nil
+}
+
 // RobotDingtalkConfig 钉钉机器人配置
 type RobotDingtalkConfig struct {
-	Enabled                    bool   `yaml:"enabled" json:"enabled"`
-	ClientID                   string `yaml:"client_id" json:"client_id"`                                       // 应用 Key (AppKey)
-	ClientSecret               string `yaml:"client_secret" json:"client_secret"`                               // 应用 Secret
+	Enabled                     bool   `yaml:"enabled" json:"enabled"`
+	ClientID                    string `yaml:"client_id" json:"client_id"`                                           // 应用 Key (AppKey)
+	ClientSecret                string `yaml:"client_secret" json:"client_secret"`                                   // 应用 Secret
 	AllowConversationIDFallback bool   `yaml:"allow_conversation_id_fallback" json:"allow_conversation_id_fallback"` // sender_id 缺失时是否允许回退到会话 ID
 }

 // RobotLarkConfig 飞书机器人配置
 type RobotLarkConfig struct {
-	Enabled                 bool   `yaml:"enabled" json:"enabled"`
-	AppID                   string `yaml:"app_id" json:"app_id"`                                 // 应用 App ID
-	AppSecret               string `yaml:"app_secret" json:"app_secret"`                         // 应用 App Secret
-	VerifyToken             string `yaml:"verify_token" json:"verify_token"`                     // 事件订阅 Verification Token（可选）
-	AllowChatIDFallback     bool   `yaml:"allow_chat_id_fallback" json:"allow_chat_id_fallback"` // 用户 ID 缺失时是否允许回退到 chat_id
+	Enabled             bool   `yaml:"enabled" json:"enabled"`
+	AppID               string `yaml:"app_id" json:"app_id"`                                 // 应用 App ID
+	AppSecret           string `yaml:"app_secret" json:"app_secret"`                         // 应用 App Secret
+	VerifyToken         string `yaml:"verify_token" json:"verify_token"`                     // 事件订阅 Verification Token（可选）
+	AllowChatIDFallback bool   `yaml:"allow_chat_id_fallback" json:"allow_chat_id_fallback"` // 用户 ID 缺失时是否允许回退到 chat_id
+}
+
+// RobotTelegramConfig Telegram 机器人配置（Bot API 长轮询）
+type RobotTelegramConfig struct {
+	Enabled            bool   `yaml:"enabled" json:"enabled"`
+	BotToken           string `yaml:"bot_token" json:"bot_token"`
+	BotUsername        string `yaml:"bot_username,omitempty" json:"bot_username,omitempty"` // 可选，用于群聊 @ 识别；留空则启动时 getMe
+	AllowGroupMessages bool   `yaml:"allow_group_messages" json:"allow_group_messages"`     // 群聊中仅响应 @ 机器人
+	UpdateOffset       int64  `yaml:"update_offset,omitempty" json:"update_offset,omitempty"`
+}
+
+// RobotSlackConfig Slack 机器人配置（Socket Mode，无需公网回调）
+type RobotSlackConfig struct {
+	Enabled   bool   `yaml:"enabled" json:"enabled"`
+	BotToken  string `yaml:"bot_token" json:"bot_token"`   // xoxb-
+	AppToken  string `yaml:"app_token" json:"app_token"`   // xapp-（connections:write）
+}
+
+// RobotDiscordConfig Discord 机器人配置（Gateway WebSocket）
+type RobotDiscordConfig struct {
+	Enabled            bool   `yaml:"enabled" json:"enabled"`
+	BotToken           string `yaml:"bot_token" json:"bot_token"`
+	AllowGuildMessages bool   `yaml:"allow_guild_messages" json:"allow_guild_messages"` // 服务器频道中仅响应 @ 机器人
+}
+
+// RobotQQConfig QQ 机器人配置（QQ 开放平台 WebSocket）
+type RobotQQConfig struct {
+	Enabled      bool   `yaml:"enabled" json:"enabled"`
+	AppID        string `yaml:"app_id" json:"app_id"`
+	ClientSecret string `yaml:"client_secret" json:"client_secret"`
+	Sandbox      bool   `yaml:"sandbox" json:"sandbox"` // 沙箱环境（上线前测试）
 }

 type ServerConfig struct {
@@ -593,17 +656,123 @@ type DatabaseConfig struct {
 }

 type AgentConfig struct {
-	MaxIterations      int    `yaml:"max_iterations" json:"max_iterations"`
-	ToolTimeoutMinutes int    `yaml:"tool_timeout_minutes" json:"tool_timeout_minutes"` // 单次工具执行最大时长（分钟），超时自动终止，防止长时间挂起；0 表示不限制（不推荐）
+	MaxIterations      int `yaml:"max_iterations" json:"max_iterations"`
+	ToolTimeoutMinutes int `yaml:"tool_timeout_minutes" json:"tool_timeout_minutes"` // 单次工具执行最大时长（分钟），超时自动终止，防止长时间挂起；0 表示不限制（不推荐）
+	// ShellNoOutputTimeoutSeconds execute/exec 无任何 stdout/stderr 时的空闲终止秒数（通用防挂死，不维护命令黑名单）；0=默认 300（5 分钟）；-1=关闭。
+	ShellNoOutputTimeoutSeconds int `yaml:"shell_no_output_timeout_seconds" json:"shell_no_output_timeout_seconds"`
+	// WorkspaceRootDir 会话工作目录根路径（curl/wget 下载、read_file/glob/grep 本地分析）；空=tmp/workspace，其下按 projects/{id} 或 conversations/{id} 隔离。
+	WorkspaceRootDir string `yaml:"workspace_root_dir,omitempty" json:"workspace_root_dir,omitempty"`
 	// SystemPromptPath 单代理系统提示 Markdown/文本文件路径（相对 config.yaml 所在目录，或可写绝对路径）。非空且可读时替换内置单代理提示；留空用内置。
 	SystemPromptPath string `yaml:"system_prompt_path,omitempty" json:"system_prompt_path,omitempty"`
 }

 // HitlConfig 人机协同全局选项；与会话侧栏/API 中的白名单合并为并集后参与判定。
-// tool_whitelist 可在侧栏「应用」时合并写入 config.yaml 并立即生效；其他字段若仅改文件仍需重启。
+// tool_whitelist 可在侧栏「应用」时合并写入 config.yaml 并立即生效。
+// audit_agent_prompt / audit_agent_prompt_review_edit 可在人机协同页编辑并立即生效；空则使用内置默认。
 type HitlConfig struct {
-	// ToolWhitelist 全局免审批工具名（与每条会话配置的 sensitiveTools 语义相同：白名单内工具不触发 HITL）。
+	// ToolWhitelist 全局免审批工具名（与白名单内工具不触发 HITL 审批）。
 	ToolWhitelist []string `yaml:"tool_whitelist,omitempty" json:"tool_whitelist,omitempty"`
+	// AuditAgentPrompt 审批模式（approval）下审计 Agent 系统提示词。
+	AuditAgentPrompt string `yaml:"audit_agent_prompt,omitempty" json:"audit_agent_prompt,omitempty"`
+	// AuditAgentPromptReviewEdit 审查编辑模式（review_edit）下审计 Agent 系统提示词。
+	AuditAgentPromptReviewEdit string `yaml:"audit_agent_prompt_review_edit,omitempty" json:"audit_agent_prompt_review_edit,omitempty"`
+	// RetentionDays 已决策审计日志（hitl_interrupts 非 pending）保留天数；省略时默认 90；0 表示不自动清理。
+	RetentionDays *int `yaml:"retention_days,omitempty" json:"retention_days,omitempty"`
+	// DefaultReviewer 全局默认审批方（human | audit_agent）；未选会话时切换会写入 config.yaml；新建会话无独立配置时沿用。
+	DefaultReviewer string `yaml:"default_reviewer,omitempty" json:"default_reviewer,omitempty"`
+}
+
+// EffectiveDefaultReviewer returns human or audit_agent; omitted or unknown values default to human.
+func (h HitlConfig) EffectiveDefaultReviewer() string {
+	switch strings.ToLower(strings.TrimSpace(h.DefaultReviewer)) {
+	case "audit_agent", "agent", "ai":
+		return "audit_agent"
+	default:
+		return "human"
+	}
+}
+
+// RetentionDaysEffective returns retention; 0 means keep forever; omitted defaults to 90.
+func (h HitlConfig) RetentionDaysEffective() int {
+	if h.RetentionDays == nil {
+		return 90
+	}
+	if *h.RetentionDays < 0 {
+		return 0
+	}
+	return *h.RetentionDays
+}
+
+const hitlAuditAgentPromptBase = `你是 CyberStrikeAI 人机协同审计 Agent。审查 Agent 即将执行的工具调用是否会对系统造成实质性损害。
+
+你会收到 JSON，包含 hitlMode、toolName、arguments/argumentsObj、userMessage、thinking、reasoningChain、planning 等字段。
+
+裁决基调（默认放行）：
+- 常规、低风险的渗透测试操作 → approve（如信息收集、端口/服务扫描、目录枚举、只读查询、无害探测命令）
+- 与用户授权、当前任务目标一致，且未见明确高危迹象 → approve
+- 仅在「可能对系统造成实质影响」时 → reject
+
+必须 reject 的高危情形（示例，非穷举）：
+- 删库、清表、批量删除数据、格式化磁盘、不可逆破坏
+- 修改/重置密码、创建或篡改管理员账号、持久化后门、开机自启
+- 向生产环境写入恶意载荷、勒索加密、停止关键服务、修改系统核心配置
+- 明显越权：与任务/授权目标无关的破坏性操作
+
+不应单独作为 reject 理由的情形：
+- 常规 nmap/curl/grep/读文件/枚举类命令本身
+- 参数略显宽泛但无明确破坏意图（审查编辑模式可收窄参数后 approve）
+- 仅因「信息不足」——若无上述高危迹象，应 approve 并可在 comment 中提示注意点`
+
+const hitlAuditAgentPromptApprovalOutput = `
+仅输出一行 JSON，不要 markdown 代码块：
+{"decision":"approve"|"reject","comment":"简要理由"}`
+
+const hitlAuditAgentPromptReviewEditOutput = `
+仅输出一行 JSON，不要 markdown 代码块：
+{"decision":"approve"|"reject","comment":"简要理由","editedArguments":{...}}
+
+editedArguments 规则（仅 approve 且需要改参时填写，否则省略该字段）：
+- 提供完整替换后的工具参数对象，键名与 argumentsObj 一致
+- 只做最小必要修改以收窄范围、消除风险（如限制 path、去掉危险 flag）
+- 禁止扩大攻击面：不得扩大目标范围、提升权限或引入破坏性参数
+- 无法安全改参时应 reject，不要勉强 approve`
+
+// DefaultHitlAuditAgentPrompt 内置审批模式审计 Agent 提示词。
+func DefaultHitlAuditAgentPrompt() string {
+	return hitlAuditAgentPromptBase + hitlAuditAgentPromptApprovalOutput
+}
+
+// DefaultHitlAuditAgentPromptReviewEdit 内置审查编辑模式审计 Agent 提示词。
+func DefaultHitlAuditAgentPromptReviewEdit() string {
+	return hitlAuditAgentPromptBase + hitlAuditAgentPromptReviewEditOutput
+}
+
+// EffectiveAuditAgentPrompt 返回审批模式生效的审计 Agent 提示词。
+func (c HitlConfig) EffectiveAuditAgentPrompt() string {
+	return c.EffectiveAuditAgentPromptForMode("approval")
+}
+
+// EffectiveAuditAgentPromptForMode 按 HITL 模式返回生效的审计 Agent 提示词。
+func (c HitlConfig) EffectiveAuditAgentPromptForMode(mode string) string {
+	if normalizeHitlModeForPrompt(mode) == "review_edit" {
+		if s := strings.TrimSpace(c.AuditAgentPromptReviewEdit); s != "" {
+			return s
+		}
+		return DefaultHitlAuditAgentPromptReviewEdit()
+	}
+	if s := strings.TrimSpace(c.AuditAgentPrompt); s != "" {
+		return s
+	}
+	return DefaultHitlAuditAgentPrompt()
+}
+
+func normalizeHitlModeForPrompt(mode string) string {
+	switch strings.ToLower(strings.TrimSpace(mode)) {
+	case "review_edit":
+		return "review_edit"
+	default:
+		return "approval"
+	}
 }

 type AuthConfig struct {
@@ -614,12 +783,29 @@ type AuthConfig struct {
 	GeneratedPasswordPersistErr string `yaml:"-" json:"-"`
 }

+// MonitorConfig MCP 状态监控（tool_executions）保留策略。
+type MonitorConfig struct {
+	// RetentionDays 执行记录保留天数；省略时默认 90；0 表示不自动清理。
+	RetentionDays *int `yaml:"retention_days,omitempty" json:"retention_days,omitempty"`
+}
+
+// RetentionDaysEffective returns retention; 0 means keep forever; omitted defaults to 90.
+func (m MonitorConfig) RetentionDaysEffective() int {
+	if m.RetentionDays == nil {
+		return 90
+	}
+	if *m.RetentionDays < 0 {
+		return 0
+	}
+	return *m.RetentionDays
+}
+
 // AuditConfig platform operation audit log settings (not chat/tool execution bodies).
 type AuditConfig struct {
 	// Enabled nil or true enables persistence; explicit false disables.
-	Enabled             *bool `yaml:"enabled,omitempty" json:"enabled,omitempty"`
-	RetentionDays  int `yaml:"retention_days,omitempty" json:"retention_days,omitempty"`
-	MaxDetailBytes int `yaml:"max_detail_bytes,omitempty" json:"max_detail_bytes,omitempty"`
+	Enabled        *bool `yaml:"enabled,omitempty" json:"enabled,omitempty"`
+	RetentionDays  int   `yaml:"retention_days,omitempty" json:"retention_days,omitempty"`
+	MaxDetailBytes int   `yaml:"max_detail_bytes,omitempty" json:"max_detail_bytes,omitempty"`
 	// AuthFailureCooldownSeconds: per-IP cooldown for auth login/change_password failure audit rows; -1 disables; 0 uses default 60.
 	AuthFailureCooldownSeconds int `yaml:"auth_failure_cooldown_seconds,omitempty" json:"auth_failure_cooldown_seconds,omitempty"`
 }
@@ -773,33 +959,13 @@ func Load(path string) (*Config, error) {

 	// 如果配置了工具目录，从目录加载工具配置
 	if cfg.Security.ToolsDir != "" {
-		configDir := filepath.Dir(path)
-		toolsDir := cfg.Security.ToolsDir
-
-		// 如果是相对路径，相对于配置文件所在目录
-		if !filepath.IsAbs(toolsDir) {
-			toolsDir = filepath.Join(configDir, toolsDir)
-		}
-
-		tools, err := LoadToolsFromDir(toolsDir)
+		inlineTools := append([]ToolConfig(nil), cfg.Security.Tools...)
+		toolsDir := ResolveToolsDir(cfg.Security.ToolsDir, path)
+		merged, err := MergeToolsFromDir(toolsDir, inlineTools)
 		if err != nil {
 			return nil, fmt.Errorf("从工具目录加载工具配置失败: %w", err)
 		}
-
-		// 合并工具配置：目录中的工具优先，主配置中的工具作为补充
-		existingTools := make(map[string]bool)
-		for _, tool := range tools {
-			existingTools[tool.Name] = true
-		}
-
-		// 添加主配置中不存在于目录中的工具（向后兼容）
-		for _, tool := range cfg.Security.Tools {
-			if !existingTools[tool.Name] {
-				tools = append(tools, tool)
-			}
-		}
-
-		cfg.Security.Tools = tools
+		cfg.Security.Tools = merged
 	}

 	// 外部 MCP：迁移 + 环境变量展开
@@ -843,6 +1009,10 @@ func Load(path string) (*Config, error) {
 		}
 	}

+	if err := ValidateWecomConfig(cfg.Robots.Wecom); err != nil {
+		return nil, err
+	}
+
 	return &cfg, nil
 }

@@ -1067,6 +1237,75 @@ func PrintMCPConfigJSON(mcp MCPConfig) {
 	fmt.Println("----------------------------------------------------------------")
 }

+// ResolveToolsDir 将 tools_dir 解析为绝对路径（相对路径相对于 configPath 所在目录）。
+func ResolveToolsDir(toolsDir, configPath string) string {
+	toolsDir = strings.TrimSpace(toolsDir)
+	if toolsDir == "" {
+		return ""
+	}
+	if filepath.IsAbs(toolsDir) {
+		return toolsDir
+	}
+	return filepath.Join(filepath.Dir(configPath), toolsDir)
+}
+
+// MergeToolsFromDir 从目录加载工具并与 inline 列表合并：目录中的工具优先，主配置中的工具作为补充。
+func MergeToolsFromDir(toolsDir string, inlineTools []ToolConfig) ([]ToolConfig, error) {
+	dirTools, err := LoadToolsFromDir(toolsDir)
+	if err != nil {
+		return nil, err
+	}
+	existing := make(map[string]bool, len(dirTools))
+	for _, tool := range dirTools {
+		existing[tool.Name] = true
+	}
+	merged := append([]ToolConfig(nil), dirTools...)
+	for _, tool := range inlineTools {
+		if !existing[tool.Name] {
+			merged = append(merged, tool)
+		}
+	}
+	return merged, nil
+}
+
+// loadInlineSecurityToolsFromYAML 读取 config.yaml 中 security.tools（不含 tools_dir 扫描结果）。
+func loadInlineSecurityToolsFromYAML(configPath string) ([]ToolConfig, error) {
+	data, err := os.ReadFile(configPath)
+	if err != nil {
+		return nil, fmt.Errorf("读取配置文件失败: %w", err)
+	}
+	var partial struct {
+		Security struct {
+			Tools []ToolConfig `yaml:"tools"`
+		} `yaml:"security"`
+	}
+	if err := yaml.Unmarshal(data, &partial); err != nil {
+		return nil, fmt.Errorf("解析配置文件失败: %w", err)
+	}
+	if partial.Security.Tools == nil {
+		return []ToolConfig{}, nil
+	}
+	return partial.Security.Tools, nil
+}
+
+// ReloadSecurityToolsFromDir 从 tools_dir 重新加载工具并更新 cfg.Security.Tools（ApplyConfig 热重载用）。
+func ReloadSecurityToolsFromDir(cfg *Config, configPath string) error {
+	if cfg == nil || strings.TrimSpace(cfg.Security.ToolsDir) == "" {
+		return nil
+	}
+	inlineTools, err := loadInlineSecurityToolsFromYAML(configPath)
+	if err != nil {
+		return err
+	}
+	toolsDir := ResolveToolsDir(cfg.Security.ToolsDir, configPath)
+	merged, err := MergeToolsFromDir(toolsDir, inlineTools)
+	if err != nil {
+		return fmt.Errorf("从工具目录加载工具配置失败: %w", err)
+	}
+	cfg.Security.Tools = merged
+	return nil
+}
+
 // LoadToolsFromDir 从目录加载所有工具配置文件
 func LoadToolsFromDir(dir string) ([]ToolConfig, error) {
 	var tools []ToolConfig
@@ -1243,8 +1482,9 @@ func Default() *Config {
 			MaxTotalTokens: 120000,
 		},
 		Agent: AgentConfig{
-			MaxIterations:      30, // 默认最大迭代次数
-			ToolTimeoutMinutes: 10, // 单次工具执行默认最多 10 分钟，避免异常长时间占用
+			MaxIterations:               30,  // 默认最大迭代次数
+			ToolTimeoutMinutes:          10,  // 单次工具执行默认最多 10 分钟，避免异常长时间占用
+			ShellNoOutputTimeoutSeconds: 300, // execute/exec 无新输出空闲终止（秒）；-1 关闭
 		},
 		Security: SecurityConfig{
 			Tools:    []ToolConfig{}, // 工具配置应该从 config.yaml 或 tools/ 目录加载
@@ -1265,6 +1505,10 @@ func Default() *Config {
 				Enabled:        &on,
 			}
 		}(),
+		Monitor: func() MonitorConfig {
+			days := 90
+			return MonitorConfig{RetentionDays: &days}
+		}(),
 		Robots: RobotsConfig{
 			Session: RobotSessionConfig{
 				StrictUserIdentity: &strictRobotIdentity,
@@ -1280,7 +1524,12 @@ func Default() *Config {
 			},
 			Retrieval: RetrievalConfig{
 				TopK:                5,
-				SimilarityThreshold: 0.65, // 降低阈值到 0.65，减少漏检
+				SimilarityThreshold: 0.65,
+				MultiQuery:          MultiQueryConfig{MaxQueries: 4},
+				Rerank:              RerankConfig{},
+				PostRetrieve: PostRetrieveConfig{
+					PrefetchTopK: 20,
+				},
 			},
 			Indexing: IndexingConfig{
 				ChunkStrategy:         "markdown_then_recursive",
@@ -1376,7 +1625,7 @@ type EmbeddingConfig struct {

 // PostRetrieveConfig 检索后处理：固定对正文做规范化去重（最佳实践）、上下文预算截断；PrefetchTopK 用于多取候选再收敛到 top_k。
 type PostRetrieveConfig struct {
-	// PrefetchTopK 向量检索阶段最多保留的候选数（余弦序），应 ≥ top_k，0 表示与 top_k 相同；上限见知识库包内常量。
+	// PrefetchTopK 向量检索阶段每条 MultiQuery 变体最多保留的候选数；0 表示使用内置默认 max(top_k*4, 20)。
 	PrefetchTopK int `yaml:"prefetch_top_k,omitempty" json:"prefetch_top_k,omitempty"`
 	// MaxContextChars 返回文档内容总 Unicode 字符数上限（整段 chunk，不截断半段）；0 表示不限制。
 	MaxContextChars int `yaml:"max_context_chars,omitempty" json:"max_context_chars,omitempty"`
@@ -1384,13 +1633,62 @@ type PostRetrieveConfig struct {
 	MaxContextTokens int `yaml:"max_context_tokens,omitempty" json:"max_context_tokens,omitempty"`
 }

+// MultiQueryConfig Eino MultiQuery 查询改写（始终启用，无关闭开关）。
+type MultiQueryConfig struct {
+	// MaxQueries LLM 生成的检索变体上限（含原问语义覆盖）；0 表示默认 4。
+	MaxQueries int `yaml:"max_queries,omitempty" json:"max_queries,omitempty"`
+}
+
+func (c MultiQueryConfig) MaxQueriesEffective() int {
+	if c.MaxQueries <= 0 {
+		return 4
+	}
+	if c.MaxQueries > 8 {
+		return 8
+	}
+	return c.MaxQueries
+}
+
+// RerankConfig 检索精排（始终启用）；支持 dashscope 与 Cohere 兼容 HTTP API。
+type RerankConfig struct {
+	// Provider: dashscope | cohere；空则按 base_url 自动推断。
+	Provider string `yaml:"provider,omitempty" json:"provider,omitempty"`
+	Model    string `yaml:"model,omitempty" json:"model,omitempty"`
+	BaseURL  string `yaml:"base_url,omitempty" json:"base_url,omitempty"`
+	APIKey   string `yaml:"api_key,omitempty" json:"api_key,omitempty"`
+}
+
+func (c RerankConfig) ProviderEffective(baseURL string) string {
+	p := strings.TrimSpace(strings.ToLower(c.Provider))
+	if p != "" {
+		return p
+	}
+	u := strings.ToLower(baseURL)
+	if strings.Contains(u, "dashscope") {
+		return "dashscope"
+	}
+	return "cohere"
+}
+
+func (c RerankConfig) ModelEffective(provider string) string {
+	if m := strings.TrimSpace(c.Model); m != "" {
+		return m
+	}
+	if provider == "dashscope" {
+		return "gte-rerank"
+	}
+	return "rerank-multilingual-v3.0"
+}
+
 // RetrievalConfig 检索配置
 type RetrievalConfig struct {
 	TopK                int     `yaml:"top_k" json:"top_k"`                               // 检索Top-K
 	SimilarityThreshold float64 `yaml:"similarity_threshold" json:"similarity_threshold"` // 余弦相似度阈值
 	// SubIndexFilter 非空时仅保留 sub_indexes 含该标签（逗号分隔之一）的行；sub_indexes 为空的旧行仍返回。
-	SubIndexFilter string `yaml:"sub_index_filter,omitempty" json:"sub_index_filter,omitempty"`
-	// PostRetrieve 检索后处理（去重、预算截断）；重排通过代码注入 [knowledge.DocumentReranker]。
+	SubIndexFilter string           `yaml:"sub_index_filter,omitempty" json:"sub_index_filter,omitempty"`
+	MultiQuery     MultiQueryConfig `yaml:"multi_query" json:"multi_query"`
+	Rerank         RerankConfig     `yaml:"rerank" json:"rerank"`
+	// PostRetrieve 检索后处理（去重、预算截断）；精排在 MultiQuery 融合后执行。
 	PostRetrieve PostRetrieveConfig `yaml:"post_retrieve,omitempty" json:"post_retrieve,omitempty"`
 }

@@ -1402,11 +1700,14 @@ type RolesConfig struct {

 // RoleConfig 单个角色配置
 type RoleConfig struct {
-	Name        string   `yaml:"name" json:"name"`                       // 角色名称
-	Description string   `yaml:"description" json:"description"`         // 角色描述
-	UserPrompt  string   `yaml:"user_prompt" json:"user_prompt"`         // 用户提示词(追加到用户消息前)
-	Icon        string   `yaml:"icon,omitempty" json:"icon,omitempty"`   // 角色图标（可选）
-	Tools       []string `yaml:"tools,omitempty" json:"tools,omitempty"` // 关联的工具列表（toolKey格式，如 "toolName" 或 "mcpName::toolName"）
-	MCPs        []string `yaml:"mcps,omitempty" json:"mcps,omitempty"`   // 向后兼容：关联的MCP服务器列表（已废弃，使用tools替代）
-	Enabled     bool     `yaml:"enabled" json:"enabled"`                 // 是否启用
+	Name            string   `yaml:"name" json:"name"`                                             // 角色名称
+	Description     string   `yaml:"description" json:"description"`                               // 角色描述
+	UserPrompt      string   `yaml:"user_prompt" json:"user_prompt"`                               // 用户提示词(追加到用户消息前)
+	Icon            string   `yaml:"icon,omitempty" json:"icon,omitempty"`                         // 角色图标（可选）
+	Tools           []string `yaml:"tools,omitempty" json:"tools,omitempty"`                       // 关联的工具列表（toolKey格式，如 "toolName" 或 "mcpName::toolName"）
+	MCPs            []string `yaml:"mcps,omitempty" json:"mcps,omitempty"`                         // 向后兼容：关联的MCP服务器列表（已废弃，使用tools替代）
+	WorkflowID      string   `yaml:"workflow_id,omitempty" json:"workflow_id,omitempty"`           // 可选：绑定图编排流程 ID
+	WorkflowVersion string   `yaml:"workflow_version,omitempty" json:"workflow_version,omitempty"` // latest 或具体版本号；空等同 latest
+	WorkflowPolicy  string   `yaml:"workflow_policy,omitempty" json:"workflow_policy,omitempty"`   // auto | off；空且 workflow_id 非空时按 auto
+	Enabled         bool     `yaml:"enabled" json:"enabled"`                                       // 是否启用
 }
@@ -0,0 +1,45 @@
+package config
+
+import "testing"
+
+func TestValidateWecomConfig(t *testing.T) {
+	t.Parallel()
+
+	tests := []struct {
+		name    string
+		cfg     RobotWecomConfig
+		wantErr bool
+	}{
+		{
+			name:    "disabled without token",
+			cfg:     RobotWecomConfig{Enabled: false, Token: ""},
+			wantErr: false,
+		},
+		{
+			name:    "enabled with token",
+			cfg:     RobotWecomConfig{Enabled: true, Token: "secret"},
+			wantErr: false,
+		},
+		{
+			name:    "enabled without token",
+			cfg:     RobotWecomConfig{Enabled: true, Token: ""},
+			wantErr: true,
+		},
+		{
+			name:    "enabled with whitespace token",
+			cfg:     RobotWecomConfig{Enabled: true, Token: "   "},
+			wantErr: true,
+		},
+	}
+
+	for _, tt := range tests {
+		tt := tt
+		t.Run(tt.name, func(t *testing.T) {
+			t.Parallel()
+			err := ValidateWecomConfig(tt.cfg)
+			if (err != nil) != tt.wantErr {
+				t.Fatalf("ValidateWecomConfig() error = %v, wantErr %v", err, tt.wantErr)
+			}
+		})
+	}
+}
@@ -0,0 +1,111 @@
+package config
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestReloadSecurityToolsFromDir(t *testing.T) {
+	root := t.TempDir()
+	toolsDir := filepath.Join(root, "tools")
+	if err := os.MkdirAll(toolsDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+
+	configPath := filepath.Join(root, "config.yaml")
+	if err := os.WriteFile(configPath, []byte(`security:
+  tools_dir: tools
+  tools:
+    - name: inline-only
+      command: inline-cmd
+      enabled: true
+      description: inline tool
+`), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	writeTool := func(name, command string) {
+		t.Helper()
+		content := "name: " + name + "\ncommand: " + command + "\nenabled: true\ndescription: test\n"
+		if err := os.WriteFile(filepath.Join(toolsDir, name+".yaml"), []byte(content), 0644); err != nil {
+			t.Fatal(err)
+		}
+	}
+
+	writeTool("alpha", "alpha-cmd")
+
+	cfg := &Config{
+		Security: SecurityConfig{
+			ToolsDir: "tools",
+			Tools: []ToolConfig{
+				{Name: "stale", Command: "stale-cmd", Enabled: true, Description: "should be removed"},
+			},
+		},
+	}
+
+	if err := ReloadSecurityToolsFromDir(cfg, configPath); err != nil {
+		t.Fatalf("reload: %v", err)
+	}
+	if len(cfg.Security.Tools) != 2 {
+		t.Fatalf("expected 2 tools, got %d", len(cfg.Security.Tools))
+	}
+
+	names := map[string]string{}
+	for _, tool := range cfg.Security.Tools {
+		names[tool.Name] = tool.Command
+	}
+	if names["alpha"] != "alpha-cmd" {
+		t.Fatalf("alpha tool missing or wrong command: %#v", names)
+	}
+	if names["inline-only"] != "inline-cmd" {
+		t.Fatalf("inline-only tool missing: %#v", names)
+	}
+	if _, ok := names["stale"]; ok {
+		t.Fatal("stale in-memory tool should not survive reload")
+	}
+
+	writeTool("beta", "beta-cmd")
+	if err := ReloadSecurityToolsFromDir(cfg, configPath); err != nil {
+		t.Fatalf("second reload: %v", err)
+	}
+	if len(cfg.Security.Tools) != 3 {
+		t.Fatalf("expected 3 tools after add, got %d", len(cfg.Security.Tools))
+	}
+	foundBeta := false
+	for _, tool := range cfg.Security.Tools {
+		if tool.Name == "beta" {
+			foundBeta = true
+			break
+		}
+	}
+	if !foundBeta {
+		t.Fatal("beta tool not found after second reload")
+	}
+}
+
+func TestMergeToolsFromDir_DirOverridesInline(t *testing.T) {
+	root := t.TempDir()
+	toolsDir := filepath.Join(root, "tools")
+	if err := os.MkdirAll(toolsDir, 0755); err != nil {
+		t.Fatal(err)
+	}
+	content := "name: shared\ncommand: dir-cmd\nenabled: true\ndescription: from dir\n"
+	if err := os.WriteFile(filepath.Join(toolsDir, "shared.yaml"), []byte(content), 0644); err != nil {
+		t.Fatal(err)
+	}
+
+	inline := []ToolConfig{
+		{Name: "shared", Command: "inline-cmd", Enabled: true, Description: "from inline"},
+	}
+	merged, err := MergeToolsFromDir(toolsDir, inline)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(merged) != 1 {
+		t.Fatalf("expected 1 tool, got %d", len(merged))
+	}
+	if merged[0].Command != "dir-cmd" {
+		t.Fatalf("dir tool should win, got command %q", merged[0].Command)
+	}
+}
@@ -23,6 +23,7 @@ type BatchTaskQueueRow struct {
 	LastScheduleError     sql.NullString
 	LastRunError          sql.NullString
 	ProjectID             sql.NullString
+	Concurrency           sql.NullInt64
 	Status                string
 	CreatedAt             time.Time
 	StartedAt             sql.NullTime
@@ -53,6 +54,7 @@ func (db *DB) CreateBatchQueue(
 	cronExpr string,
 	nextRunAt *time.Time,
 	projectID string,
+	concurrency int,
 	tasks []map[string]interface{},
 ) error {
 	tx, err := db.Begin()
@@ -72,8 +74,8 @@ func (db *DB) CreateBatchQueue(
 		projectIDVal = strings.TrimSpace(projectID)
 	}
 	_, err = tx.Exec(
-		"INSERT INTO batch_task_queues (id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, project_id, status, created_at, current_index) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
-		queueID, title, role, agentMode, scheduleMode, cronExpr, nextRunAtValue, 1, projectIDVal, "pending", now, 0,
+		"INSERT INTO batch_task_queues (id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, project_id, concurrency, status, created_at, current_index) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)",
+		queueID, title, role, agentMode, scheduleMode, cronExpr, nextRunAtValue, 1, projectIDVal, concurrency, "pending", now, 0,
 	)
 	if err != nil {
 		return fmt.Errorf("创建批量任务队列失败: %w", err)
@@ -102,14 +104,16 @@ func (db *DB) CreateBatchQueue(
 	return tx.Commit()
 }

+const batchQueueSelectColumns = `id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, last_schedule_trigger_at, last_schedule_error, last_run_error, project_id, concurrency, status, created_at, started_at, completed_at, current_index`
+
 // GetBatchQueue 获取批量任务队列
 func (db *DB) GetBatchQueue(queueID string) (*BatchTaskQueueRow, error) {
 	var row BatchTaskQueueRow
 	var createdAt string
 	err := db.QueryRow(
-		"SELECT id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, last_schedule_trigger_at, last_schedule_error, last_run_error, project_id, status, created_at, started_at, completed_at, current_index FROM batch_task_queues WHERE id = ?",
+		"SELECT "+batchQueueSelectColumns+" FROM batch_task_queues WHERE id = ?",
 		queueID,
-	).Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex)
+	).Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Concurrency, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex)
 	if err == sql.ErrNoRows {
 		return nil, nil
 	}
@@ -133,7 +137,7 @@ func (db *DB) GetBatchQueue(queueID string) (*BatchTaskQueueRow, error) {
 // GetAllBatchQueues 获取所有批量任务队列
 func (db *DB) GetAllBatchQueues() ([]*BatchTaskQueueRow, error) {
 	rows, err := db.Query(
-		"SELECT id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, last_schedule_trigger_at, last_schedule_error, last_run_error, project_id, status, created_at, started_at, completed_at, current_index FROM batch_task_queues ORDER BY created_at DESC",
+		"SELECT "+batchQueueSelectColumns+" FROM batch_task_queues ORDER BY created_at DESC",
 	)
 	if err != nil {
 		return nil, fmt.Errorf("查询批量任务队列列表失败: %w", err)
@@ -144,7 +148,7 @@ func (db *DB) GetAllBatchQueues() ([]*BatchTaskQueueRow, error) {
 	for rows.Next() {
 		var row BatchTaskQueueRow
 		var createdAt string
-		if err := rows.Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex); err != nil {
+		if err := rows.Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Concurrency, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex); err != nil {
 			return nil, fmt.Errorf("扫描批量任务队列失败: %w", err)
 		}
 		parsedTime, parseErr := time.Parse("2006-01-02 15:04:05", createdAt)
@@ -164,7 +168,7 @@ func (db *DB) GetAllBatchQueues() ([]*BatchTaskQueueRow, error) {

 // ListBatchQueues 列出批量任务队列（支持筛选和分页）
 func (db *DB) ListBatchQueues(limit, offset int, status, keyword string) ([]*BatchTaskQueueRow, error) {
-	query := "SELECT id, title, role, agent_mode, schedule_mode, cron_expr, next_run_at, schedule_enabled, last_schedule_trigger_at, last_schedule_error, last_run_error, project_id, status, created_at, started_at, completed_at, current_index FROM batch_task_queues WHERE 1=1"
+	query := "SELECT " + batchQueueSelectColumns + " FROM batch_task_queues WHERE 1=1"
 	args := []interface{}{}

 	// 状态筛选
@@ -192,7 +196,7 @@ func (db *DB) ListBatchQueues(limit, offset int, status, keyword string) ([]*Bat
 	for rows.Next() {
 		var row BatchTaskQueueRow
 		var createdAt string
-		if err := rows.Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex); err != nil {
+		if err := rows.Scan(&row.ID, &row.Title, &row.Role, &row.AgentMode, &row.ScheduleMode, &row.CronExpr, &row.NextRunAt, &row.ScheduleEnabled, &row.LastScheduleTriggerAt, &row.LastScheduleError, &row.LastRunError, &row.ProjectID, &row.Concurrency, &row.Status, &createdAt, &row.StartedAt, &row.CompletedAt, &row.CurrentIndex); err != nil {
 			return nil, fmt.Errorf("扫描批量任务队列失败: %w", err)
 		}
 		parsedTime, parseErr := time.Parse("2006-01-02 15:04:05", createdAt)
@@ -358,11 +362,11 @@ func (db *DB) UpdateBatchQueueCurrentIndex(queueID string, currentIndex int) err
 	return nil
 }

-// UpdateBatchQueueMetadata 更新批量任务队列标题、角色和代理模式
-func (db *DB) UpdateBatchQueueMetadata(queueID, title, role, agentMode string) error {
+// UpdateBatchQueueMetadata 更新批量任务队列标题、角色、代理模式和并发数
+func (db *DB) UpdateBatchQueueMetadata(queueID, title, role, agentMode string, concurrency int) error {
 	_, err := db.Exec(
-		"UPDATE batch_task_queues SET title = ?, role = ?, agent_mode = ? WHERE id = ?",
-		title, role, agentMode, queueID,
+		"UPDATE batch_task_queues SET title = ?, role = ?, agent_mode = ?, concurrency = ? WHERE id = ?",
+		title, role, agentMode, concurrency, queueID,
 	)
 	if err != nil {
 		return fmt.Errorf("更新批量任务队列元数据失败: %w", err)
@@ -507,6 +511,42 @@ func (db *DB) CancelPendingBatchTasks(queueID string, completedAt time.Time) err
 	return nil
 }

+// PrepareBatchSingleTaskRun 准备单条执行：可选重置子任务，并更新队列索引与状态
+func (db *DB) PrepareBatchSingleTaskRun(queueID, taskID string, taskIndex int, resetTask, resumeQueue bool) error {
+	tx, err := db.Begin()
+	if err != nil {
+		return fmt.Errorf("开始事务失败: %w", err)
+	}
+	defer tx.Rollback()
+
+	if resetTask {
+		_, err = tx.Exec(
+			"UPDATE batch_tasks SET status = ?, conversation_id = NULL, started_at = NULL, completed_at = NULL, error = NULL, result = NULL WHERE queue_id = ? AND id = ?",
+			"pending", queueID, taskID,
+		)
+		if err != nil {
+			return fmt.Errorf("重置批量任务状态失败: %w", err)
+		}
+	}
+
+	if resumeQueue {
+		_, err = tx.Exec(
+			"UPDATE batch_task_queues SET status = ?, current_index = ?, completed_at = NULL, last_run_error = NULL WHERE id = ?",
+			"paused", taskIndex, queueID,
+		)
+	} else {
+		_, err = tx.Exec(
+			"UPDATE batch_task_queues SET current_index = ?, last_run_error = NULL WHERE id = ?",
+			taskIndex, queueID,
+		)
+	}
+	if err != nil {
+		return fmt.Errorf("更新批量任务队列状态失败: %w", err)
+	}
+
+	return tx.Commit()
+}
+
 // DeleteBatchTask 删除批量任务
 func (db *DB) DeleteBatchTask(queueID, taskID string) error {
 	_, err := db.Exec(
@@ -3,6 +3,7 @@ package database
 import (
 	"database/sql"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -13,6 +14,9 @@ import (
 	"go.uber.org/zap"
 )

+// ProjectFilterUnbound 列表 API 中 project_id=__none__ 表示仅未绑定项目的对话。
+const ProjectFilterUnbound = "__none__"
+
 // Conversation 对话
 type Conversation struct {
 	ID        string    `json:"id"`
@@ -352,8 +356,8 @@ func (db *DB) GetConversationLite(id string) (*Conversation, error) {

 	conv.Pinned = pinned != 0

-	// 加载消息（不加载 process_details）
-	messages, err := db.GetMessages(id)
+	// 加载消息（不加载 process_details / reasoning_content，减少历史会话切换 payload）
+	messages, err := db.GetMessagesLite(id)
 	if err != nil {
 		return nil, fmt.Errorf("加载消息失败: %w", err)
 	}
@@ -361,20 +365,44 @@ func (db *DB) GetConversationLite(id string) (*Conversation, error) {
 	return &conv, nil
 }

+func conversationProjectIDColumn(alias string) string {
+	if alias != "" {
+		return alias + ".project_id"
+	}
+	return "project_id"
+}
+
+func appendConversationProjectFilter(where string, args []interface{}, projectID, alias string) (string, []interface{}) {
+	pid := strings.TrimSpace(projectID)
+	if pid == "" {
+		return where, args
+	}
+	col := conversationProjectIDColumn(alias)
+	if pid == ProjectFilterUnbound {
+		return where + fmt.Sprintf(" AND (%s IS NULL OR TRIM(COALESCE(%s, '')) = '')", col, col), args
+	}
+	return where + fmt.Sprintf(" AND %s = ?", col), append(args, pid)
+}
+
 // CountConversations 统计对话数量。
-func (db *DB) CountConversations(search string) (int, error) {
+func (db *DB) CountConversations(search, projectID string) (int, error) {
 	var count int
 	var err error
 	if search != "" {
 		searchPattern := "%" + search + "%"
-		err = db.QueryRow(
-			`SELECT COUNT(*) FROM conversations c
-			 WHERE c.title LIKE ?
-			    OR EXISTS (SELECT 1 FROM messages m WHERE m.conversation_id = c.id AND m.content LIKE ?)`,
-			searchPattern, searchPattern,
-		).Scan(&count)
+		where := ` WHERE (c.title LIKE ?
+			    OR EXISTS (SELECT 1 FROM messages m WHERE m.conversation_id = c.id AND m.content LIKE ?))`
+		args := []interface{}{searchPattern, searchPattern}
+		where, args = appendConversationProjectFilter(where, args, projectID, "c")
+		err = db.QueryRow(`SELECT COUNT(*) FROM conversations c`+where, args...).Scan(&count)
 	} else {
-		err = db.QueryRow(`SELECT COUNT(*) FROM conversations`).Scan(&count)
+		where := ""
+		args := []interface{}{}
+		where, args = appendConversationProjectFilter(where, args, projectID, "")
+		if where != "" {
+			where = " WHERE" + strings.TrimPrefix(where, " AND")
+		}
+		err = db.QueryRow(`SELECT COUNT(*) FROM conversations`+where, args...).Scan(&count)
 	}
 	if err != nil {
 		return 0, fmt.Errorf("统计对话失败: %w", err)
@@ -382,27 +410,51 @@ func (db *DB) CountConversations(search string) (int, error) {
 	return count, nil
 }

+func conversationOrderClause(sortBy, tableAlias string) string {
+	col := "updated_at"
+	if strings.TrimSpace(strings.ToLower(sortBy)) == "created_at" {
+		col = "created_at"
+	}
+	prefix := tableAlias
+	if prefix != "" {
+		prefix += "."
+	}
+	return "ORDER BY " + prefix + col + " DESC"
+}
+
 // ListConversations 列出所有对话
-func (db *DB) ListConversations(limit, offset int, search string) ([]*Conversation, error) {
+func (db *DB) ListConversations(limit, offset int, search, sortBy, projectID string) ([]*Conversation, error) {
 	var rows *sql.Rows
 	var err error

 	if search != "" {
 		// 使用 EXISTS 子查询代替 LEFT JOIN + DISTINCT，避免大表笛卡尔积
 		searchPattern := "%" + search + "%"
+		orderClause := conversationOrderClause(sortBy, "c")
+		where := ` WHERE (c.title LIKE ?
+			    OR EXISTS (SELECT 1 FROM messages m WHERE m.conversation_id = c.id AND m.content LIKE ?))`
+		args := []interface{}{searchPattern, searchPattern}
+		where, args = appendConversationProjectFilter(where, args, projectID, "c")
+		args = append(args, limit, offset)
 		rows, err = db.Query(
 			`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id
-			 FROM conversations c
-			 WHERE c.title LIKE ?
-			    OR EXISTS (SELECT 1 FROM messages m WHERE m.conversation_id = c.id AND m.content LIKE ?)
-			 ORDER BY c.updated_at DESC
+			 FROM conversations c`+where+`
+			 `+orderClause+`
 			 LIMIT ? OFFSET ?`,
-			searchPattern, searchPattern, limit, offset,
+			args...,
 		)
 	} else {
+		orderClause := conversationOrderClause(sortBy, "")
+		where := ""
+		args := []interface{}{}
+		where, args = appendConversationProjectFilter(where, args, projectID, "")
+		if where != "" {
+			where = " WHERE" + strings.TrimPrefix(where, " AND")
+		}
+		args = append(args, limit, offset)
 		rows, err = db.Query(
-			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id FROM conversations ORDER BY updated_at DESC LIMIT ? OFFSET ?",
-			limit, offset,
+			"SELECT id, title, COALESCE(pinned, 0), created_at, updated_at, project_id FROM conversations"+where+" "+orderClause+" LIMIT ? OFFSET ?",
+			args...,
 		)
 	}

@@ -458,22 +510,30 @@ const ungroupedConversationsSQL = `
 	)`

 // CountUngroupedConversations 统计不在任何分组中的对话数量。
-func (db *DB) CountUngroupedConversations() (int, error) {
+func (db *DB) CountUngroupedConversations(projectID string) (int, error) {
+	where := ungroupedConversationsSQL
+	args := []interface{}{}
+	where, args = appendConversationProjectFilter(where, args, projectID, "c")
 	var count int
-	if err := db.QueryRow(`SELECT COUNT(*) ` + ungroupedConversationsSQL).Scan(&count); err != nil {
+	if err := db.QueryRow(`SELECT COUNT(*) `+where, args...).Scan(&count); err != nil {
 		return 0, fmt.Errorf("统计未分组对话失败: %w", err)
 	}
 	return count, nil
 }

 // ListUngroupedConversations 列出不在任何分组中的对话（最近对话侧栏）。
-func (db *DB) ListUngroupedConversations(limit, offset int) ([]*Conversation, error) {
+func (db *DB) ListUngroupedConversations(limit, offset int, sortBy, projectID string) ([]*Conversation, error) {
+	orderClause := conversationOrderClause(sortBy, "c")
+	where := ungroupedConversationsSQL
+	args := []interface{}{}
+	where, args = appendConversationProjectFilter(where, args, projectID, "c")
+	args = append(args, limit, offset)
 	rows, err := db.Query(
 		`SELECT c.id, c.title, COALESCE(c.pinned, 0), c.created_at, c.updated_at, c.project_id `+
-			ungroupedConversationsSQL+`
-		 ORDER BY c.updated_at DESC
+			where+`
+		 `+orderClause+`
 		 LIMIT ? OFFSET ?`,
-		limit, offset,
+		args...,
 	)
 	if err != nil {
 		return nil, fmt.Errorf("查询未分组对话失败: %w", err)
@@ -518,6 +578,19 @@ func (db *DB) ListUngroupedConversations(limit, offset int) ([]*Conversation, er
 	return conversations, rows.Err()
 }

+// GetConversationTitle 获取对话标题（轻量查询，不加载消息）
+func (db *DB) GetConversationTitle(id string) (string, error) {
+	var title string
+	err := db.QueryRow("SELECT title FROM conversations WHERE id = ?", id).Scan(&title)
+	if err != nil {
+		if err == sql.ErrNoRows {
+			return "", fmt.Errorf("对话不存在")
+		}
+		return "", fmt.Errorf("查询对话标题失败: %w", err)
+	}
+	return title, nil
+}
+
 // UpdateConversationTitle 更新对话标题
 func (db *DB) UpdateConversationTitle(id, title string) error {
 	// 注意：不更新 updated_at，因为重命名操作不应该改变对话的更新时间
@@ -570,12 +643,14 @@ func (db *DB) DeleteConversation(id string) error {
 		// 不返回错误，继续删除对话
 	}

+	projectID, _ := db.GetConversationProjectID(id)
+
 	// 删除对话（外键CASCADE会自动删除其他相关数据）
 	_, err = db.Exec("DELETE FROM conversations WHERE id = ?", id)
 	if err != nil {
 		return fmt.Errorf("删除对话失败: %w", err)
 	}
-	db.removeConversationScopedDirs(id)
+	db.removeConversationScopedDirs(id, projectID)

 	db.logger.Info("对话已删除（漏洞记录已保留）", zap.String("conversationId", id))
 	return nil
@@ -613,13 +688,50 @@ func (db *DB) removeConversationScopedDir(base, conversationID, label string) {
 	}
 }

-func (db *DB) removeConversationScopedDirs(conversationID string) {
-	// summarization transcript, reduction files, etc.
+func (db *DB) einoReductionBaseDir() string {
+	if db == nil {
+		return ""
+	}
+	if base := strings.TrimSpace(db.einoReductionRootDir); base != "" {
+		return base
+	}
+	return filepath.Join("tmp", "reduction")
+}
+
+func (db *DB) einoWorkspaceBaseDir() string {
+	if db == nil {
+		return ""
+	}
+	if base := strings.TrimSpace(db.einoWorkspaceRootDir); base != "" {
+		return base
+	}
+	return filepath.Join("tmp", "workspace")
+}
+
+func (db *DB) removeConversationScopedDirs(conversationID, projectID string) {
+	// summarization transcript, etc.
 	db.removeConversationScopedDir(db.conversationArtifactsDir, conversationID, "conversation_artifacts")
 	// Eino plantask JSON boards (skills_dir/.eino/plantask/<id>/).
 	db.removeConversationScopedDir(db.einoPlantaskBaseDir, conversationID, "plantask")
 	// Eino ADK runner checkpoints (checkpoint_dir/<id>/).
 	db.removeConversationScopedDir(db.einoCheckpointBaseDir, conversationID, "eino_checkpoint")
+	// Eino reduction persisted tool outputs (tmp/reduction/conversations/<id>/).
+	// Project-bound sessions share projects/<id>/ — skip on single conversation delete.
+	if strings.TrimSpace(projectID) == "" {
+		reductionBase := filepath.Join(db.einoReductionBaseDir(), "conversations")
+		db.removeConversationScopedDir(reductionBase, conversationID, "reduction")
+		workspaceBase := filepath.Join(db.einoWorkspaceBaseDir(), "conversations")
+		db.removeConversationScopedDir(workspaceBase, conversationID, "workspace")
+	}
+}
+
+func (db *DB) removeProjectScopedDirs(projectID string) {
+	// Eino reduction persisted tool outputs (tmp/reduction/projects/<id>/).
+	reductionBase := filepath.Join(db.einoReductionBaseDir(), "projects")
+	db.removeConversationScopedDir(reductionBase, projectID, "reduction")
+	// Agent download/analysis workspace (tmp/workspace/projects/<id>/).
+	workspaceBase := filepath.Join(db.einoWorkspaceBaseDir(), "projects")
+	db.removeConversationScopedDir(workspaceBase, projectID, "workspace")
 }

 // SaveAgentTrace 保存最后一轮代理消息轨迹与助手输出摘要。
@@ -796,6 +908,62 @@ func (db *DB) GetMessages(conversationID string) ([]Message, error) {
 	return messages, nil
 }

+// GetMessagesLite 获取对话消息（不含 reasoning_content），用于历史会话快速切换。
+func (db *DB) GetMessagesLite(conversationID string) ([]Message, error) {
+	rows, err := db.Query(
+		"SELECT id, conversation_id, role, content, mcp_execution_ids, created_at, updated_at FROM messages WHERE conversation_id = ? ORDER BY created_at ASC, rowid ASC",
+		conversationID,
+	)
+	if err != nil {
+		return nil, fmt.Errorf("查询消息失败: %w", err)
+	}
+	defer rows.Close()
+
+	var messages []Message
+	for rows.Next() {
+		var msg Message
+		var mcpIDsJSON sql.NullString
+		var createdAt string
+		var updatedAt sql.NullString
+
+		if err := rows.Scan(&msg.ID, &msg.ConversationID, &msg.Role, &msg.Content, &mcpIDsJSON, &createdAt, &updatedAt); err != nil {
+			return nil, fmt.Errorf("扫描消息失败: %w", err)
+		}
+
+		var err error
+		msg.CreatedAt, err = time.Parse("2006-01-02 15:04:05.999999999-07:00", createdAt)
+		if err != nil {
+			msg.CreatedAt, err = time.Parse("2006-01-02 15:04:05", createdAt)
+		}
+		if err != nil {
+			msg.CreatedAt, _ = time.Parse(time.RFC3339, createdAt)
+		}
+
+		if updatedAt.Valid && strings.TrimSpace(updatedAt.String) != "" {
+			msg.UpdatedAt, err = time.Parse("2006-01-02 15:04:05.999999999-07:00", updatedAt.String)
+			if err != nil {
+				msg.UpdatedAt, err = time.Parse("2006-01-02 15:04:05", updatedAt.String)
+			}
+			if err != nil {
+				msg.UpdatedAt, _ = time.Parse(time.RFC3339, updatedAt.String)
+			}
+		}
+		if msg.UpdatedAt.IsZero() {
+			msg.UpdatedAt = msg.CreatedAt
+		}
+
+		if mcpIDsJSON.Valid && mcpIDsJSON.String != "" {
+			if err := json.Unmarshal([]byte(mcpIDsJSON.String), &msg.MCPExecutionIDs); err != nil {
+				db.logger.Warn("解析MCP执行ID失败", zap.Error(err))
+			}
+		}
+
+		messages = append(messages, msg)
+	}
+
+	return messages, nil
+}
+
 // turnSliceRange 根据任意一条消息 ID 定位「一轮对话」在 msgs 中的 [start, end) 下标区间（msgs 须已按时间升序，与 GetMessages 一致）。
 // 一轮 = 从某条 user 消息起，至下一条 user 之前（含中间所有 assistant）。
 func turnSliceRange(msgs []Message, anchorID string) (start, end int, err error) {
@@ -903,6 +1071,77 @@ type ProcessDetail struct {
 	CreatedAt      time.Time `json:"createdAt"`
 }

+// GetTurnUserMessage 返回锚点消息所在轮次中的用户原文（最近一条 user 消息，不含完整历史）。
+func (db *DB) GetTurnUserMessage(conversationID, anchorMessageID string) (string, error) {
+	conversationID = strings.TrimSpace(conversationID)
+	anchorMessageID = strings.TrimSpace(anchorMessageID)
+	if conversationID == "" || anchorMessageID == "" {
+		return "", nil
+	}
+	var content string
+	err := db.QueryRow(`
+SELECT m.content FROM messages m
+WHERE m.conversation_id = ? AND m.role = 'user'
+  AND m.created_at <= COALESCE((SELECT created_at FROM messages WHERE id = ? AND conversation_id = ?), m.created_at)
+ORDER BY m.created_at DESC, m.rowid DESC
+LIMIT 1`, conversationID, anchorMessageID, conversationID).Scan(&content)
+	if err != nil {
+		if errors.Is(err, sql.ErrNoRows) {
+			return "", nil
+		}
+		return "", fmt.Errorf("query turn user message: %w", err)
+	}
+	return content, nil
+}
+
+// AssistantCognitionTexts 单条助手消息上的思考/推理/规划文本。
+type AssistantCognitionTexts struct {
+	Thinking       string
+	ReasoningChain string
+	Planning       string
+}
+
+// GetAssistantCognitionTexts 聚合助手消息在 process_details 中的 thinking / reasoning_chain / planning。
+func (db *DB) GetAssistantCognitionTexts(assistantMessageID string) (AssistantCognitionTexts, error) {
+	assistantMessageID = strings.TrimSpace(assistantMessageID)
+	if assistantMessageID == "" {
+		return AssistantCognitionTexts{}, nil
+	}
+	rows, err := db.Query(`
+SELECT event_type, message FROM process_details
+WHERE message_id = ? AND event_type IN ('thinking', 'reasoning_chain', 'planning')
+ORDER BY created_at ASC, rowid ASC`, assistantMessageID)
+	if err != nil {
+		return AssistantCognitionTexts{}, fmt.Errorf("query assistant cognition: %w", err)
+	}
+	defer rows.Close()
+
+	var thinkingParts, reasoningParts, planningParts []string
+	for rows.Next() {
+		var eventType, message string
+		if err := rows.Scan(&eventType, &message); err != nil {
+			continue
+		}
+		msg := strings.TrimSpace(message)
+		if msg == "" {
+			continue
+		}
+		switch eventType {
+		case "thinking":
+			thinkingParts = append(thinkingParts, msg)
+		case "reasoning_chain":
+			reasoningParts = append(reasoningParts, msg)
+		case "planning":
+			planningParts = append(planningParts, msg)
+		}
+	}
+	return AssistantCognitionTexts{
+		Thinking:       strings.Join(thinkingParts, "\n\n"),
+		ReasoningChain: strings.Join(reasoningParts, "\n\n"),
+		Planning:       strings.Join(planningParts, "\n\n"),
+	}, nil
+}
+
 // AddProcessDetail 添加过程详情事件
 func (db *DB) AddProcessDetail(messageID, conversationID, eventType, message string, data interface{}) error {
 	id := uuid.New().String()
@@ -964,6 +1203,107 @@ func (db *DB) GetProcessDetails(messageID string) ([]ProcessDetail, error) {
 	return details, nil
 }

+// ProcessDetailsSummary 过程详情摘要（用于折叠态展示，避免全量加载）。
+type ProcessDetailsSummary struct {
+	Total          int `json:"total"`
+	IterationCount int `json:"iterationCount"`
+	MaxIteration   int `json:"maxIteration"`
+}
+
+// GetProcessDetailsSummary 统计消息的过程详情数量与迭代轮次。
+func (db *DB) GetProcessDetailsSummary(messageID string) (*ProcessDetailsSummary, error) {
+	var total int
+	if err := db.QueryRow(
+		"SELECT COUNT(*) FROM process_details WHERE message_id = ?",
+		messageID,
+	).Scan(&total); err != nil {
+		return nil, fmt.Errorf("统计过程详情失败: %w", err)
+	}
+
+	summary := &ProcessDetailsSummary{Total: total}
+	if total == 0 {
+		return summary, nil
+	}
+
+	rows, err := db.Query(
+		"SELECT data FROM process_details WHERE message_id = ? AND event_type = 'iteration' ORDER BY created_at ASC, rowid ASC",
+		messageID,
+	)
+	if err != nil {
+		return nil, fmt.Errorf("查询迭代详情失败: %w", err)
+	}
+	defer rows.Close()
+
+	maxIter := 0
+	iterCount := 0
+	for rows.Next() {
+		var dataJSON string
+		if err := rows.Scan(&dataJSON); err != nil {
+			return nil, fmt.Errorf("扫描迭代详情失败: %w", err)
+		}
+		iterCount++
+		if dataJSON == "" {
+			continue
+		}
+		var payload map[string]interface{}
+		if err := json.Unmarshal([]byte(dataJSON), &payload); err != nil {
+			continue
+		}
+		if n, ok := payload["iteration"].(float64); ok && int(n) > maxIter {
+			maxIter = int(n)
+		}
+	}
+	summary.IterationCount = iterCount
+	summary.MaxIteration = maxIter
+	return summary, nil
+}
+
+// GetProcessDetailsPage 分页获取消息的过程详情（按时间升序）。
+func (db *DB) GetProcessDetailsPage(messageID string, limit, offset int) ([]ProcessDetail, int, error) {
+	var total int
+	if err := db.QueryRow(
+		"SELECT COUNT(*) FROM process_details WHERE message_id = ?",
+		messageID,
+	).Scan(&total); err != nil {
+		return nil, 0, fmt.Errorf("统计过程详情失败: %w", err)
+	}
+	if total == 0 || offset >= total {
+		return nil, total, nil
+	}
+
+	rows, err := db.Query(
+		"SELECT id, message_id, conversation_id, event_type, message, data, created_at FROM process_details WHERE message_id = ? ORDER BY created_at ASC, rowid ASC LIMIT ? OFFSET ?",
+		messageID, limit, offset,
+	)
+	if err != nil {
+		return nil, 0, fmt.Errorf("查询过程详情失败: %w", err)
+	}
+	defer rows.Close()
+
+	var details []ProcessDetail
+	for rows.Next() {
+		var detail ProcessDetail
+		var createdAt string
+
+		if err := rows.Scan(&detail.ID, &detail.MessageID, &detail.ConversationID, &detail.EventType, &detail.Message, &detail.Data, &createdAt); err != nil {
+			return nil, 0, fmt.Errorf("扫描过程详情失败: %w", err)
+		}
+
+		var parseErr error
+		detail.CreatedAt, parseErr = time.Parse("2006-01-02 15:04:05.999999999-07:00", createdAt)
+		if parseErr != nil {
+			detail.CreatedAt, parseErr = time.Parse("2006-01-02 15:04:05", createdAt)
+		}
+		if parseErr != nil {
+			detail.CreatedAt, _ = time.Parse(time.RFC3339, createdAt)
+		}
+
+		details = append(details, detail)
+	}
+
+	return details, total, nil
+}
+
 // GetProcessDetailsByConversation 获取对话的所有过程详情（按消息分组）
 func (db *DB) GetProcessDetailsByConversation(conversationID string) (map[string][]ProcessDetail, error) {
 	rows, err := db.Query(
@@ -19,7 +19,9 @@ func TestDeleteConversationRemovesEinoScopedDirs(t *testing.T) {

 	plantaskBase := filepath.Join(tmp, "skills", ".eino", "plantask")
 	checkpointBase := filepath.Join(tmp, "eino-checkpoints")
-	db.SetEinoConversationDirs(plantaskBase, checkpointBase)
+	reductionBase := filepath.Join(tmp, "reduction")
+	workspaceBase := filepath.Join(tmp, "workspace")
+	db.SetEinoConversationDirs(plantaskBase, checkpointBase, reductionBase, workspaceBase)

 	conv, err := db.CreateConversation("cleanup test", ConversationCreateMeta{})
 	if err != nil {
@@ -34,6 +36,8 @@ func TestDeleteConversationRemovesEinoScopedDirs(t *testing.T) {
 		{db.conversationArtifactsDir, "transcript.txt"},
 		{plantaskBase, "task-1.json"},
 		{checkpointBase, "runner-deep.ckpt"},
+		{filepath.Join(reductionBase, "conversations"), "tool-output.txt"},
+		{filepath.Join(workspaceBase, "conversations"), "page.html"},
 	} {
 		dir := filepath.Join(base.root, seg)
 		if err := os.MkdirAll(dir, 0o755); err != nil {
@@ -48,10 +52,57 @@ func TestDeleteConversationRemovesEinoScopedDirs(t *testing.T) {
 		t.Fatalf("DeleteConversation: %v", err)
 	}

-	for _, base := range []string{db.conversationArtifactsDir, plantaskBase, checkpointBase} {
+	for _, base := range []string{db.conversationArtifactsDir, plantaskBase, checkpointBase, filepath.Join(reductionBase, "conversations"), filepath.Join(workspaceBase, "conversations")} {
 		dir := filepath.Join(base, seg)
 		if _, statErr := os.Stat(dir); !os.IsNotExist(statErr) {
 			t.Fatalf("expected removed dir %s, stat err=%v", dir, statErr)
 		}
 	}
 }
+
+func TestDeleteProjectRemovesReductionDir(t *testing.T) {
+	tmp := t.TempDir()
+	dbPath := filepath.Join(tmp, "conversations.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	reductionBase := filepath.Join(tmp, "reduction")
+	workspaceBase := filepath.Join(tmp, "workspace")
+	db.SetEinoConversationDirs("", "", reductionBase, workspaceBase)
+
+	project, err := db.CreateProject(&Project{Name: "cleanup test"})
+	if err != nil {
+		t.Fatalf("CreateProject: %v", err)
+	}
+	seg := sanitizeConversationPathSegment(project.ID)
+	reductionDir := filepath.Join(reductionBase, "projects", seg, "clear")
+	if err := os.MkdirAll(reductionDir, 0o755); err != nil {
+		t.Fatalf("mkdir %s: %v", reductionDir, err)
+	}
+	if err := os.WriteFile(filepath.Join(reductionDir, "call-1.txt"), []byte("x"), 0o644); err != nil {
+		t.Fatalf("write: %v", err)
+	}
+	workspaceDir := filepath.Join(workspaceBase, "projects", seg, "downloads")
+	if err := os.MkdirAll(workspaceDir, 0o755); err != nil {
+		t.Fatalf("mkdir %s: %v", workspaceDir, err)
+	}
+	if err := os.WriteFile(filepath.Join(workspaceDir, "app.js"), []byte("x"), 0o644); err != nil {
+		t.Fatalf("write workspace: %v", err)
+	}
+
+	if err := db.DeleteProject(project.ID); err != nil {
+		t.Fatalf("DeleteProject: %v", err)
+	}
+
+	projectReductionDir := filepath.Join(reductionBase, "projects", seg)
+	if _, statErr := os.Stat(projectReductionDir); !os.IsNotExist(statErr) {
+		t.Fatalf("expected removed dir %s, stat err=%v", projectReductionDir, statErr)
+	}
+	projectWorkspaceDir := filepath.Join(workspaceBase, "projects", seg)
+	if _, statErr := os.Stat(projectWorkspaceDir); !os.IsNotExist(statErr) {
+		t.Fatalf("expected removed dir %s, stat err=%v", projectWorkspaceDir, statErr)
+	}
+}
@@ -0,0 +1,60 @@
+package database
+
+import (
+	"path/filepath"
+	"testing"
+
+	"go.uber.org/zap"
+)
+
+func TestConversationProjectFilter(t *testing.T) {
+	tmp := t.TempDir()
+	dbPath := filepath.Join(tmp, "conversations.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	p, err := db.CreateProject(&Project{Name: "target-a", Status: "active"})
+	if err != nil {
+		t.Fatalf("CreateProject: %v", err)
+	}
+
+	convNone, err := db.CreateConversation("unbound", ConversationCreateMeta{})
+	if err != nil {
+		t.Fatalf("CreateConversation unbound: %v", err)
+	}
+	convBound, err := db.CreateConversation("bound", ConversationCreateMeta{ProjectID: p.ID})
+	if err != nil {
+		t.Fatalf("CreateConversation bound: %v", err)
+	}
+
+	totalAll, err := db.CountConversations("", "")
+	if err != nil || totalAll < 2 {
+		t.Fatalf("CountConversations all: total=%d err=%v", totalAll, err)
+	}
+
+	totalBound, err := db.CountConversations("", p.ID)
+	if err != nil || totalBound != 1 {
+		t.Fatalf("CountConversations project: total=%d err=%v", totalBound, err)
+	}
+
+	totalUnbound, err := db.CountConversations("", ProjectFilterUnbound)
+	if err != nil || totalUnbound != 1 {
+		t.Fatalf("CountConversations unbound: total=%d err=%v", totalUnbound, err)
+	}
+
+	listBound, err := db.ListConversations(10, 0, "", "", p.ID)
+	if err != nil || len(listBound) != 1 || listBound[0].ID != convBound.ID {
+		t.Fatalf("ListConversations project: %+v err=%v", listBound, err)
+	}
+
+	listUnbound, err := db.ListConversations(10, 0, "", "", ProjectFilterUnbound)
+	if err != nil || len(listUnbound) != 1 || listUnbound[0].ID != convNone.ID {
+		t.Fatalf("ListConversations unbound: %+v err=%v", listUnbound, err)
+	}
+
+	_ = convNone
+	_ = convBound
+}
@@ -5,8 +5,8 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"sync"
 	"strings"
+	"sync"
 	"time"

 	_ "github.com/mattn/go-sqlite3"
@@ -51,6 +51,8 @@ type DB struct {
 	conversationArtifactsDir string
 	einoPlantaskBaseDir      string // skills_dir + plantask_rel_dir (per-conversation subdirs)
 	einoCheckpointBaseDir    string // checkpoint_dir root (per-conversation subdirs)
+	einoReductionRootDir     string // reduction_root_dir or default tmp/reduction (conversations/<id> subdirs)
+	einoWorkspaceRootDir     string // workspace_root_dir or default tmp/workspace (projects|conversations/<id> subdirs)
 	checkpointLoopName       string
 	checkpointStop           chan struct{}
 	checkpointDone           chan struct{}
@@ -159,12 +161,16 @@ func NewDB(dbPath string, logger *zap.Logger) (*DB, error) {

 // SetEinoConversationDirs configures best-effort filesystem cleanup on DeleteConversation.
 // plantaskBase is skills_root/plantask_rel (no conversation id); checkpointBase is checkpoint_dir root.
-func (db *DB) SetEinoConversationDirs(plantaskBase, checkpointBase string) {
+// reductionRoot is reduction_root_dir from config; empty uses tmp/reduction (conversation-scoped subdirs only).
+// workspaceRoot is agent.workspace_root_dir from config; empty uses tmp/workspace.
+func (db *DB) SetEinoConversationDirs(plantaskBase, checkpointBase, reductionRoot, workspaceRoot string) {
 	if db == nil {
 		return
 	}
 	db.einoPlantaskBaseDir = strings.TrimSpace(plantaskBase)
 	db.einoCheckpointBaseDir = strings.TrimSpace(checkpointBase)
+	db.einoReductionRootDir = strings.TrimSpace(reductionRoot)
+	db.einoWorkspaceRootDir = strings.TrimSpace(workspaceRoot)
 }

 // initTables 初始化数据库表
@@ -353,6 +359,22 @@ func (db *DB) initTables() error {
 		UNIQUE(project_id, fact_key)
 	);`

+	// 项目事实关系边（黑板 DAG）
+	createProjectFactEdgesTable := `
+	CREATE TABLE IF NOT EXISTS project_fact_edges (
+		id TEXT PRIMARY KEY,
+		project_id TEXT NOT NULL,
+		source_fact_key TEXT NOT NULL,
+		target_fact_key TEXT NOT NULL,
+		edge_type TEXT NOT NULL,
+		confidence TEXT NOT NULL DEFAULT 'tentative',
+		source_conversation_id TEXT,
+		created_at DATETIME NOT NULL,
+		updated_at DATETIME NOT NULL,
+		FOREIGN KEY (project_id) REFERENCES projects(id) ON DELETE CASCADE,
+		UNIQUE(project_id, source_fact_key, target_fact_key, edge_type)
+	);`
+
 	// 创建漏洞表
 	createVulnerabilitiesTable := `
 	CREATE TABLE IF NOT EXISTS vulnerabilities (
@@ -366,9 +388,12 @@ func (db *DB) initTables() error {
 		status TEXT NOT NULL DEFAULT 'open',
 		vulnerability_type TEXT,
 		target TEXT,
-		proof TEXT,
+		preconditions TEXT,
+		reproduction_steps TEXT,
+		evidence TEXT,
 		impact TEXT,
 		recommendation TEXT,
+		retest_notes TEXT,
 		created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
 		updated_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
 		project_id TEXT,
@@ -389,6 +414,8 @@ func (db *DB) initTables() error {
 		last_schedule_trigger_at DATETIME,
 		last_schedule_error TEXT,
 		last_run_error TEXT,
+		project_id TEXT,
+		concurrency INTEGER NOT NULL DEFAULT 1,
 		status TEXT NOT NULL,
 		created_at DATETIME NOT NULL,
 		started_at DATETIME,
@@ -560,6 +587,53 @@ func (db *DB) initTables() error {
 		created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP
 	);`

+	createWorkflowDefinitionsTable := `
+	CREATE TABLE IF NOT EXISTS workflow_definitions (
+		id TEXT PRIMARY KEY,
+		name TEXT NOT NULL,
+		description TEXT,
+		version INTEGER NOT NULL DEFAULT 1,
+		graph_json TEXT NOT NULL,
+		enabled INTEGER NOT NULL DEFAULT 1,
+		created_at DATETIME NOT NULL,
+		updated_at DATETIME NOT NULL
+	);`
+
+	createWorkflowRunsTable := `
+	CREATE TABLE IF NOT EXISTS workflow_runs (
+		id TEXT PRIMARY KEY,
+		workflow_id TEXT NOT NULL,
+		workflow_version INTEGER NOT NULL DEFAULT 1,
+		conversation_id TEXT,
+		project_id TEXT,
+		role_id TEXT,
+		status TEXT NOT NULL,
+		input_json TEXT,
+		output_json TEXT,
+		error TEXT,
+		pending_hitl_node_id TEXT,
+		pending_hitl_json TEXT,
+		started_at DATETIME NOT NULL,
+		finished_at DATETIME,
+		created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+		FOREIGN KEY (conversation_id) REFERENCES conversations(id) ON DELETE SET NULL
+	);`
+
+	createWorkflowNodeRunsTable := `
+	CREATE TABLE IF NOT EXISTS workflow_node_runs (
+		id TEXT PRIMARY KEY,
+		run_id TEXT NOT NULL,
+		node_id TEXT NOT NULL,
+		status TEXT NOT NULL,
+		input_json TEXT,
+		output_json TEXT,
+		error TEXT,
+		started_at DATETIME NOT NULL,
+		finished_at DATETIME,
+		created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
+		FOREIGN KEY (run_id) REFERENCES workflow_runs(id) ON DELETE CASCADE
+	);`
+
 	// 创建索引
 	createIndexes := `
 	CREATE INDEX IF NOT EXISTS idx_messages_conversation_id ON messages(conversation_id);
@@ -591,6 +665,9 @@ func (db *DB) initTables() error {
 	CREATE INDEX IF NOT EXISTS idx_project_facts_project_id ON project_facts(project_id);
 	CREATE INDEX IF NOT EXISTS idx_project_facts_confidence ON project_facts(confidence);
 	CREATE INDEX IF NOT EXISTS idx_project_facts_related_vuln ON project_facts(related_vulnerability_id);
+	CREATE INDEX IF NOT EXISTS idx_project_fact_edges_project ON project_fact_edges(project_id);
+	CREATE INDEX IF NOT EXISTS idx_project_fact_edges_source ON project_fact_edges(project_id, source_fact_key);
+	CREATE INDEX IF NOT EXISTS idx_project_fact_edges_target ON project_fact_edges(project_id, target_fact_key);
 	CREATE INDEX IF NOT EXISTS idx_conversations_project_id ON conversations(project_id);
 	CREATE INDEX IF NOT EXISTS idx_vulnerabilities_project_id ON vulnerabilities(project_id);
 	CREATE INDEX IF NOT EXISTS idx_batch_tasks_queue_id ON batch_tasks(queue_id);
@@ -615,6 +692,12 @@ func (db *DB) initTables() error {
 	CREATE INDEX IF NOT EXISTS idx_audit_logs_category ON audit_logs(category);
 	CREATE INDEX IF NOT EXISTS idx_audit_logs_action ON audit_logs(action);
 	CREATE INDEX IF NOT EXISTS idx_audit_logs_result ON audit_logs(result);
+	CREATE INDEX IF NOT EXISTS idx_workflow_definitions_updated_at ON workflow_definitions(updated_at);
+	CREATE INDEX IF NOT EXISTS idx_workflow_definitions_enabled ON workflow_definitions(enabled);
+	CREATE INDEX IF NOT EXISTS idx_workflow_runs_workflow ON workflow_runs(workflow_id);
+	CREATE INDEX IF NOT EXISTS idx_workflow_runs_conversation ON workflow_runs(conversation_id);
+	CREATE INDEX IF NOT EXISTS idx_workflow_runs_status ON workflow_runs(status);
+	CREATE INDEX IF NOT EXISTS idx_workflow_node_runs_run ON workflow_node_runs(run_id);
 	`

 	if _, err := db.Exec(createConversationsTable); err != nil {
@@ -672,6 +755,10 @@ func (db *DB) initTables() error {
 		return fmt.Errorf("创建project_facts表失败: %w", err)
 	}

+	if _, err := db.Exec(createProjectFactEdgesTable); err != nil {
+		return fmt.Errorf("创建project_fact_edges表失败: %w", err)
+	}
+
 	if _, err := db.Exec(createVulnerabilitiesTable); err != nil {
 		return fmt.Errorf("创建vulnerabilities表失败: %w", err)
 	}
@@ -696,6 +783,16 @@ func (db *DB) initTables() error {
 		return fmt.Errorf("创建audit_logs表失败: %w", err)
 	}

+	for tableName, ddl := range map[string]string{
+		"workflow_definitions": createWorkflowDefinitionsTable,
+		"workflow_runs":        createWorkflowRunsTable,
+		"workflow_node_runs":   createWorkflowNodeRunsTable,
+	} {
+		if _, err := db.Exec(ddl); err != nil {
+			return fmt.Errorf("创建%s表失败: %w", tableName, err)
+		}
+	}
+
 	for tableName, ddl := range map[string]string{
 		"c2_listeners": createC2ListenersTable,
 		"c2_sessions":  createC2SessionsTable,
@@ -753,6 +850,9 @@ func (db *DB) initTables() error {
 		db.logger.Warn("迁移webshell_connections表失败", zap.Error(err))
 		// 不返回错误，允许继续运行
 	}
+	if err := db.migrateWorkflowRunsTable(); err != nil {
+		db.logger.Warn("迁移workflow_runs表失败", zap.Error(err))
+	}

 	if _, err := db.Exec(createIndexes); err != nil {
 		return fmt.Errorf("创建索引失败: %w", err)
@@ -1111,6 +1211,21 @@ func (db *DB) migrateBatchTaskQueuesTable() error {
 		}
 	}

+	var concurrencyCount int
+	err = db.QueryRow("SELECT COUNT(*) FROM pragma_table_info('batch_task_queues') WHERE name='concurrency'").Scan(&concurrencyCount)
+	if err != nil {
+		if _, addErr := db.Exec("ALTER TABLE batch_task_queues ADD COLUMN concurrency INTEGER NOT NULL DEFAULT 1"); addErr != nil {
+			errMsg := strings.ToLower(addErr.Error())
+			if !strings.Contains(errMsg, "duplicate column") && !strings.Contains(errMsg, "already exists") {
+				db.logger.Warn("添加batch_task_queues.concurrency字段失败", zap.Error(addErr))
+			}
+		}
+	} else if concurrencyCount == 0 {
+		if _, err := db.Exec("ALTER TABLE batch_task_queues ADD COLUMN concurrency INTEGER NOT NULL DEFAULT 1"); err != nil {
+			db.logger.Warn("添加batch_task_queues.concurrency字段失败", zap.Error(err))
+		}
+	}
+
 	return nil
 }

@@ -1178,9 +1293,12 @@ func (db *DB) migrateVulnerabilitiesConversationFK() error {
 		status TEXT NOT NULL DEFAULT 'open',
 		vulnerability_type TEXT,
 		target TEXT,
-		proof TEXT,
+		preconditions TEXT,
+		reproduction_steps TEXT,
+		evidence TEXT,
 		impact TEXT,
 		recommendation TEXT,
+		retest_notes TEXT,
 		created_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
 		updated_at DATETIME NOT NULL DEFAULT CURRENT_TIMESTAMP,
 		project_id TEXT,
@@ -1193,12 +1311,15 @@ func (db *DB) migrateVulnerabilitiesConversationFK() error {
 	const copyRows = `
 	INSERT INTO vulnerabilities_new (
 		id, conversation_id, conversation_tag, task_tag, title, description,
-		severity, status, vulnerability_type, target, proof, impact, recommendation,
+		severity, status, vulnerability_type, target, preconditions, reproduction_steps,
+		evidence, impact, recommendation, retest_notes,
 		created_at, updated_at, project_id
 	)
 	SELECT
 		id, conversation_id, conversation_tag, task_tag, title, description,
-		severity, status, vulnerability_type, target, proof, impact, recommendation,
+		severity, status, vulnerability_type, target,
+		COALESCE(preconditions, ''), COALESCE(reproduction_steps, ''),
+		COALESCE(evidence, ''), impact, recommendation, COALESCE(retest_notes, ''),
 		created_at, updated_at, project_id
 	FROM vulnerabilities;`
 	if _, err := tx.Exec(copyRows); err != nil {
@@ -1269,6 +1390,10 @@ func (db *DB) migrateVulnerabilitiesTable() error {
 		{name: "conversation_tag", stmt: "ALTER TABLE vulnerabilities ADD COLUMN conversation_tag TEXT"},
 		{name: "task_tag", stmt: "ALTER TABLE vulnerabilities ADD COLUMN task_tag TEXT"},
 		{name: "project_id", stmt: "ALTER TABLE vulnerabilities ADD COLUMN project_id TEXT"},
+		{name: "preconditions", stmt: "ALTER TABLE vulnerabilities ADD COLUMN preconditions TEXT"},
+		{name: "reproduction_steps", stmt: "ALTER TABLE vulnerabilities ADD COLUMN reproduction_steps TEXT"},
+		{name: "evidence", stmt: "ALTER TABLE vulnerabilities ADD COLUMN evidence TEXT"},
+		{name: "retest_notes", stmt: "ALTER TABLE vulnerabilities ADD COLUMN retest_notes TEXT"},
 	}

 	for _, col := range columns {
@@ -0,0 +1,75 @@
+package database
+
+import (
+	"fmt"
+	"strings"
+	"time"
+
+	"go.uber.org/zap"
+)
+
+// DeleteHitlInterruptLogsByIDs deletes decided HITL audit logs by id (pending rows are skipped).
+func (db *DB) DeleteHitlInterruptLogsByIDs(ids []string) (int64, error) {
+	if db == nil {
+		return 0, fmt.Errorf("database is nil")
+	}
+	clean := make([]string, 0, len(ids))
+	for _, id := range ids {
+		id = strings.TrimSpace(id)
+		if id != "" {
+			clean = append(clean, id)
+		}
+	}
+	if len(clean) == 0 {
+		return 0, nil
+	}
+	placeholders := strings.TrimRight(strings.Repeat("?,", len(clean)), ",")
+	q := fmt.Sprintf(`DELETE FROM hitl_interrupts WHERE status != 'pending' AND id IN (%s)`, placeholders)
+	args := make([]interface{}, len(clean))
+	for i, id := range clean {
+		args[i] = id
+	}
+	res, err := db.Exec(q, args...)
+	if err != nil {
+		db.logger.Error("批量删除人机协同审计日志失败", zap.Error(err), zap.Int("count", len(clean)))
+		return 0, fmt.Errorf("批量删除人机协同审计日志失败: %w", err)
+	}
+	n, _ := res.RowsAffected()
+	return n, nil
+}
+
+// DeleteHitlInterruptLogsMatching deletes decided logs matching whereSQL (e.g. "WHERE 1=1 AND status != 'pending' ...").
+func (db *DB) DeleteHitlInterruptLogsMatching(whereSQL string, args []interface{}) (int64, error) {
+	if db == nil {
+		return 0, fmt.Errorf("database is nil")
+	}
+	whereSQL = strings.TrimSpace(whereSQL)
+	if whereSQL == "" {
+		return 0, fmt.Errorf("where clause is required")
+	}
+	q := `DELETE FROM hitl_interrupts ` + whereSQL
+	res, err := db.Exec(q, args...)
+	if err != nil {
+		db.logger.Error("清空人机协同审计日志失败", zap.Error(err))
+		return 0, fmt.Errorf("清空人机协同审计日志失败: %w", err)
+	}
+	n, _ := res.RowsAffected()
+	return n, nil
+}
+
+// PurgeHitlInterruptLogsBefore deletes decided logs with decided/created time before cutoff.
+func (db *DB) PurgeHitlInterruptLogsBefore(cutoff time.Time) (int64, error) {
+	if db == nil {
+		return 0, fmt.Errorf("database is nil")
+	}
+	res, err := db.Exec(
+		`DELETE FROM hitl_interrupts WHERE status != 'pending' AND datetime(COALESCE(decided_at, created_at)) < datetime(?)`,
+		cutoff.UTC().Format(time.RFC3339),
+	)
+	if err != nil {
+		db.logger.Error("清理过期人机协同审计日志失败", zap.Error(err))
+		return 0, fmt.Errorf("清理过期人机协同审计日志失败: %w", err)
+	}
+	n, _ := res.RowsAffected()
+	return n, nil
+}
@@ -0,0 +1,106 @@
+package database
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"go.uber.org/zap"
+)
+
+func ensureHitlInterruptsTable(t *testing.T, db *DB) {
+	t.Helper()
+	if _, err := db.Exec(`
+CREATE TABLE IF NOT EXISTS hitl_interrupts (
+    id TEXT PRIMARY KEY,
+    conversation_id TEXT NOT NULL,
+    message_id TEXT,
+    mode TEXT NOT NULL,
+    tool_name TEXT NOT NULL,
+    tool_call_id TEXT,
+    payload TEXT,
+    status TEXT NOT NULL,
+    decision TEXT,
+    decision_comment TEXT,
+    created_at DATETIME NOT NULL,
+    decided_at DATETIME
+);`); err != nil {
+		t.Fatalf("create hitl_interrupts: %v", err)
+	}
+}
+
+func TestDeleteHitlInterruptLogsByIDs_skipsPending(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "hitl.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+	ensureHitlInterruptsTable(t, db)
+
+	now := time.Now().UTC().Format(time.RFC3339)
+	if _, err := db.Exec(`INSERT INTO hitl_interrupts
+		(id, conversation_id, mode, tool_name, status, created_at)
+		VALUES ('pending-1', 'c1', 'approval', 'exec', 'pending', ?)`, now); err != nil {
+		t.Fatalf("insert pending: %v", err)
+	}
+	if _, err := db.Exec(`INSERT INTO hitl_interrupts
+		(id, conversation_id, mode, tool_name, status, decision, created_at, decided_at)
+		VALUES ('done-1', 'c1', 'approval', 'exec', 'decided', 'approve', ?, ?)`, now, now); err != nil {
+		t.Fatalf("insert decided: %v", err)
+	}
+
+	deleted, err := db.DeleteHitlInterruptLogsByIDs([]string{"pending-1", "done-1"})
+	if err != nil {
+		t.Fatalf("DeleteHitlInterruptLogsByIDs: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("deleted = %d, want 1", deleted)
+	}
+
+	var status string
+	if err := db.QueryRow(`SELECT status FROM hitl_interrupts WHERE id = 'pending-1'`).Scan(&status); err != nil {
+		t.Fatalf("pending row missing: %v", err)
+	}
+	if err := db.QueryRow(`SELECT id FROM hitl_interrupts WHERE id = 'done-1'`).Scan(new(string)); err == nil {
+		t.Fatal("decided row should be deleted")
+	}
+}
+
+func TestPurgeHitlInterruptLogsBefore(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "hitl.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+	ensureHitlInterruptsTable(t, db)
+
+	old := time.Now().AddDate(0, 0, -100).UTC().Format(time.RFC3339)
+	recent := time.Now().AddDate(0, 0, -1).UTC().Format(time.RFC3339)
+	for _, row := range []struct{ id, decided string }{
+		{"old-1", old},
+		{"new-1", recent},
+	} {
+		if _, err := db.Exec(`INSERT INTO hitl_interrupts
+			(id, conversation_id, mode, tool_name, status, decision, created_at, decided_at)
+			VALUES (?, 'c1', 'approval', 'exec', 'decided', 'approve', ?, ?)`, row.id, row.decided, row.decided); err != nil {
+			t.Fatalf("insert %s: %v", row.id, err)
+		}
+	}
+
+	cutoff := time.Now().AddDate(0, 0, -90)
+	deleted, err := db.PurgeHitlInterruptLogsBefore(cutoff)
+	if err != nil {
+		t.Fatalf("PurgeHitlInterruptLogsBefore: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("deleted = %d, want 1", deleted)
+	}
+	if err := db.QueryRow(`SELECT id FROM hitl_interrupts WHERE id = 'old-1'`).Scan(new(string)); err == nil {
+		t.Fatal("old row should be purged")
+	}
+	if err := db.QueryRow(`SELECT id FROM hitl_interrupts WHERE id = 'new-1'`).Scan(new(string)); err != nil {
+		t.Fatalf("new row should remain: %v", err)
+	}
+}
@@ -3,7 +3,6 @@ package database
 import (
 	"database/sql"
 	"encoding/json"
-	"sort"
 	"strings"
 	"time"

@@ -227,6 +226,167 @@ func (db *DB) LoadToolExecutionsWithPagination(offset, limit int, status, toolNa
 	return executions, nil
 }

+func toolExecutionsFilterSQL(status, toolName string) (string, []interface{}) {
+	args := []interface{}{}
+	conditions := []string{}
+	if status != "" {
+		conditions = append(conditions, "status = ?")
+		args = append(args, status)
+	}
+	if toolName != "" {
+		conditions = append(conditions, "LOWER(tool_name) LIKE ?")
+		args = append(args, "%"+strings.ToLower(toolName)+"%")
+	}
+	if len(conditions) == 0 {
+		return "", args
+	}
+	return ` WHERE ` + strings.Join(conditions, ` AND `), args
+}
+
+// ToolStatsSummary 工具调用汇总（全量聚合，不含逐工具明细）
+type ToolStatsSummary struct {
+	TotalCalls   int
+	SuccessCalls int
+	FailedCalls  int
+	LastCallTime *time.Time
+	ToolCount    int
+}
+
+// ToolStatsSummaryResult 汇总 + Top N 工具排行
+type ToolStatsSummaryResult struct {
+	Summary  ToolStatsSummary
+	TopTools []*mcp.ToolStats
+}
+
+// LoadToolStatsSummary 聚合统计信息，仅返回汇总与 Top N 工具（避免全量 map 传输）
+func (db *DB) LoadToolStatsSummary(topN int) (*ToolStatsSummaryResult, error) {
+	if topN <= 0 {
+		topN = 6
+	}
+	if topN > 100 {
+		topN = 100
+	}
+
+	result := &ToolStatsSummaryResult{
+		TopTools: make([]*mcp.ToolStats, 0, topN),
+	}
+
+	summaryQuery := `
+		SELECT COUNT(*),
+			COALESCE(SUM(total_calls), 0),
+			COALESCE(SUM(success_calls), 0),
+			COALESCE(SUM(failed_calls), 0),
+			MAX(last_call_time)
+		FROM tool_stats
+	`
+	var lastCallRaw sql.NullString
+	err := db.QueryRow(summaryQuery).Scan(
+		&result.Summary.ToolCount,
+		&result.Summary.TotalCalls,
+		&result.Summary.SuccessCalls,
+		&result.Summary.FailedCalls,
+		&lastCallRaw,
+	)
+	if err != nil {
+		return nil, err
+	}
+	if lastCallRaw.Valid && strings.TrimSpace(lastCallRaw.String) != "" {
+		if t, parseErr := time.Parse(time.RFC3339Nano, lastCallRaw.String); parseErr == nil {
+			result.Summary.LastCallTime = &t
+		} else if t, parseErr := time.Parse("2006-01-02 15:04:05.999999999-07:00", lastCallRaw.String); parseErr == nil {
+			result.Summary.LastCallTime = &t
+		} else if t, parseErr := time.Parse("2006-01-02 15:04:05", lastCallRaw.String); parseErr == nil {
+			result.Summary.LastCallTime = &t
+		}
+	}
+
+	topQuery := `
+		SELECT tool_name, total_calls, success_calls, failed_calls, last_call_time
+		FROM tool_stats
+		WHERE total_calls > 0
+		ORDER BY total_calls DESC, tool_name ASC
+		LIMIT ?
+	`
+	rows, err := db.Query(topQuery, topN)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	for rows.Next() {
+		var stat mcp.ToolStats
+		var lastCallTime sql.NullTime
+		if err := rows.Scan(
+			&stat.ToolName,
+			&stat.TotalCalls,
+			&stat.SuccessCalls,
+			&stat.FailedCalls,
+			&lastCallTime,
+		); err != nil {
+			db.logger.Warn("加载 Top 工具统计失败", zap.Error(err))
+			continue
+		}
+		if lastCallTime.Valid {
+			stat.LastCallTime = &lastCallTime.Time
+		}
+		result.TopTools = append(result.TopTools, &stat)
+	}
+
+	return result, nil
+}
+
+// LoadToolExecutionListPage 分页加载执行记录列表（不含 arguments/result，供监控列表使用）
+func (db *DB) LoadToolExecutionListPage(offset, limit int, status, toolName string) ([]*mcp.ToolExecution, error) {
+	if limit <= 0 {
+		limit = 20
+	}
+	if limit > 100 {
+		limit = 100
+	}
+
+	query := `
+		SELECT id, tool_name, status, start_time, end_time, duration_ms
+		FROM tool_executions
+	`
+	whereSQL, args := toolExecutionsFilterSQL(status, toolName)
+	query += whereSQL + ` ORDER BY start_time DESC LIMIT ? OFFSET ?`
+	args = append(args, limit, offset)
+
+	rows, err := db.Query(query, args...)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+
+	executions := make([]*mcp.ToolExecution, 0, limit)
+	for rows.Next() {
+		var exec mcp.ToolExecution
+		var endTime sql.NullTime
+		var durationMs sql.NullInt64
+
+		if err := rows.Scan(
+			&exec.ID,
+			&exec.ToolName,
+			&exec.Status,
+			&exec.StartTime,
+			&endTime,
+			&durationMs,
+		); err != nil {
+			db.logger.Warn("加载执行记录列表失败", zap.Error(err))
+			continue
+		}
+		if endTime.Valid {
+			exec.EndTime = &endTime.Time
+		}
+		if durationMs.Valid {
+			exec.Duration = time.Duration(durationMs.Int64) * time.Millisecond
+		}
+		executions = append(executions, &exec)
+	}
+
+	return executions, nil
+}
+
 // GetToolExecution 根据ID获取单条工具执行记录
 func (db *DB) GetToolExecution(id string) (*mcp.ToolExecution, error) {
 	query := `
@@ -288,6 +448,93 @@ func (db *DB) GetToolExecution(id string) (*mcp.ToolExecution, error) {
 	return &exec, nil
 }

+// CancelOrphanedRunningToolExecutions 将仍为 running 的记录批量标记为 cancelled（如进程重启后无对应执行协程）。
+func (db *DB) CancelOrphanedRunningToolExecutions(endTime time.Time, errMsg string) (int64, error) {
+	errMsg = strings.TrimSpace(errMsg)
+	if errMsg == "" {
+		errMsg = "执行已中断（服务重启或会话结束）"
+	}
+	query := `
+		UPDATE tool_executions
+		SET status = 'cancelled',
+		    error = ?,
+		    end_time = ?,
+		    duration_ms = MAX(0, CAST((julianday(?) - julianday(start_time)) * 86400000 AS INTEGER))
+		WHERE status = 'running'
+	`
+	res, err := db.Exec(query, errMsg, endTime, endTime)
+	if err != nil {
+		return 0, err
+	}
+	return res.RowsAffected()
+}
+
+// FinalizeStaleRunningToolExecutions 将「非活跃且超过 minAge」的 running 记录标记为 cancelled。
+// activeIDs 为当前进程内仍登记 cancel 的 executionId；不在集合内且已超时的视为孤儿记录。
+func (db *DB) FinalizeStaleRunningToolExecutions(endTime time.Time, minAge time.Duration, activeIDs map[string]struct{}, errMsg string) (int64, error) {
+	errMsg = strings.TrimSpace(errMsg)
+	if errMsg == "" {
+		errMsg = "执行已中断（会话已结束）"
+	}
+	if minAge < 0 {
+		minAge = 0
+	}
+	cutoff := endTime.Add(-minAge)
+	rows, err := db.Query(`
+		SELECT id, start_time FROM tool_executions
+		WHERE status = 'running' AND start_time <= ?
+	`, cutoff)
+	if err != nil {
+		return 0, err
+	}
+	defer rows.Close()
+
+	type staleRow struct {
+		id        string
+		startTime time.Time
+	}
+	var stale []staleRow
+	for rows.Next() {
+		var row staleRow
+		if err := rows.Scan(&row.id, &row.startTime); err != nil {
+			db.logger.Warn("读取 stale running 执行记录失败", zap.Error(err))
+			continue
+		}
+		if activeIDs != nil {
+			if _, active := activeIDs[row.id]; active {
+				continue
+			}
+		}
+		stale = append(stale, row)
+	}
+	if err := rows.Err(); err != nil {
+		return 0, err
+	}
+	if len(stale) == 0 {
+		return 0, nil
+	}
+
+	var affected int64
+	for _, row := range stale {
+		durationMs := endTime.Sub(row.startTime).Milliseconds()
+		if durationMs < 0 {
+			durationMs = 0
+		}
+		res, err := db.Exec(`
+			UPDATE tool_executions
+			SET status = 'cancelled', error = ?, end_time = ?, duration_ms = ?
+			WHERE id = ? AND status = 'running'
+		`, errMsg, endTime, durationMs, row.id)
+		if err != nil {
+			db.logger.Warn("更新 stale running 执行记录失败", zap.Error(err), zap.String("executionId", row.id))
+			continue
+		}
+		n, _ := res.RowsAffected()
+		affected += n
+	}
+	return affected, nil
+}
+
 // DeleteToolExecution 删除工具执行记录
 func (db *DB) DeleteToolExecution(id string) error {
 	query := `DELETE FROM tool_executions WHERE id = ?`
@@ -410,6 +657,76 @@ func (db *DB) GetToolExecutionsByIds(ids []string) ([]*mcp.ToolExecution, error)
 	return executions, nil
 }

+type toolExecutionStatDelta struct {
+	totalCalls   int
+	successCalls int
+	failedCalls  int
+}
+
+// PurgeToolExecutionsBefore deletes executions older than cutoff and adjusts tool_stats.
+func (db *DB) PurgeToolExecutionsBefore(cutoff time.Time) (int64, error) {
+	query := `
+		SELECT tool_name, status, COUNT(*) AS cnt
+		FROM tool_executions
+		WHERE ` + sqliteEpochGE("start_time", "<") + `
+		GROUP BY tool_name, status
+	`
+	rows, err := db.Query(query, formatSQLiteUTC(cutoff))
+	if err != nil {
+		return 0, err
+	}
+	defer rows.Close()
+
+	deltas := make(map[string]*toolExecutionStatDelta)
+	for rows.Next() {
+		var toolName, status string
+		var count int
+		if err := rows.Scan(&toolName, &status, &count); err != nil {
+			db.logger.Warn("读取待清理执行记录统计失败", zap.Error(err))
+			continue
+		}
+		toolName = strings.TrimSpace(toolName)
+		if toolName == "" || count <= 0 {
+			continue
+		}
+		delta := deltas[toolName]
+		if delta == nil {
+			delta = &toolExecutionStatDelta{}
+			deltas[toolName] = delta
+		}
+		delta.totalCalls += count
+		switch status {
+		case "failed", "cancelled":
+			delta.failedCalls += count
+		case "completed":
+			delta.successCalls += count
+		}
+	}
+	if err := rows.Err(); err != nil {
+		return 0, err
+	}
+
+	res, err := db.Exec(`DELETE FROM tool_executions WHERE `+sqliteEpochGE("start_time", "<"), formatSQLiteUTC(cutoff))
+	if err != nil {
+		return 0, err
+	}
+	deleted, err := res.RowsAffected()
+	if err != nil {
+		return 0, err
+	}
+
+	for toolName, delta := range deltas {
+		if err := db.DecreaseToolStats(toolName, delta.totalCalls, delta.successCalls, delta.failedCalls); err != nil {
+			db.logger.Warn("清理过期执行记录后更新统计失败",
+				zap.Error(err),
+				zap.String("toolName", toolName),
+			)
+		}
+	}
+
+	return deleted, nil
+}
+
 // SaveToolStats 保存工具统计信息
 func (db *DB) SaveToolStats(toolName string, stats *mcp.ToolStats) error {
 	var lastCallTime sql.NullTime
@@ -530,13 +847,28 @@ func truncateCallsTimelineBucket(t time.Time, dailyBuckets bool) time.Time {

 // LoadCallsTimeline 按时间范围加载调用趋势（since 起至今，含边界）
 func (db *DB) LoadCallsTimeline(since time.Time, dailyBuckets bool) ([]CallsTimelineBucket, error) {
-	// 在 Go 侧按本地时区分桶，避免 SQLite strftime 对 UTC 存储时间分桶后再误当本地时间解析（差 8h 等问题）
-	query := `
-		SELECT start_time,
-			CASE WHEN status IN ('failed', 'cancelled') THEN 1 ELSE 0 END AS failed
-		FROM tool_executions
-		WHERE start_time >= ?
-	`
+	var query string
+	if dailyBuckets {
+		query = `
+			SELECT date(start_time, 'localtime') AS bucket,
+				COUNT(*) AS total,
+				SUM(CASE WHEN status IN ('failed', 'cancelled') THEN 1 ELSE 0 END) AS failed
+			FROM tool_executions
+			WHERE start_time >= ?
+			GROUP BY bucket
+			ORDER BY bucket
+		`
+	} else {
+		query = `
+			SELECT strftime('%Y-%m-%d %H:00:00', start_time, 'localtime') AS bucket,
+				COUNT(*) AS total,
+				SUM(CASE WHEN status IN ('failed', 'cancelled') THEN 1 ELSE 0 END) AS failed
+			FROM tool_executions
+			WHERE start_time >= ?
+			GROUP BY bucket
+			ORDER BY bucket
+		`
+	}

 	rows, err := db.Query(query, since)
 	if err != nil {
@@ -544,35 +876,35 @@ func (db *DB) LoadCallsTimeline(since time.Time, dailyBuckets bool) ([]CallsTime
 	}
 	defer rows.Close()

-	bucketMap := make(map[time.Time]struct{ total, failed int })
+	buckets := make([]CallsTimelineBucket, 0)
 	for rows.Next() {
-		var startTime time.Time
-		var failed int
-		if err := rows.Scan(&startTime, &failed); err != nil {
+		var bucketStr string
+		var total, failed int
+		if err := rows.Scan(&bucketStr, &total, &failed); err != nil {
 			db.logger.Warn("加载调用趋势失败", zap.Error(err))
 			continue
 		}
-		key := truncateCallsTimelineBucket(startTime, dailyBuckets)
-		entry := bucketMap[key]
-		entry.total++
-		entry.failed += failed
-		bucketMap[key] = entry
-	}
-
-	buckets := make([]CallsTimelineBucket, 0, len(bucketMap))
-	for bucketTime, counts := range bucketMap {
+		bucketTime, err := parseCallsTimelineBucket(bucketStr, dailyBuckets)
+		if err != nil {
+			db.logger.Warn("解析调用趋势时间桶失败", zap.Error(err), zap.String("bucket", bucketStr))
+			continue
+		}
 		buckets = append(buckets, CallsTimelineBucket{
 			BucketTime: bucketTime,
-			Total:      counts.total,
-			Failed:     counts.failed,
+			Total:      total,
+			Failed:     failed,
 		})
 	}
-	sort.Slice(buckets, func(i, j int) bool {
-		return buckets[i].BucketTime.Before(buckets[j].BucketTime)
-	})
 	return buckets, nil
 }

+func parseCallsTimelineBucket(bucketStr string, dailyBuckets bool) (time.Time, error) {
+	if dailyBuckets {
+		return time.ParseInLocation("2006-01-02", bucketStr, time.Local)
+	}
+	return time.ParseInLocation("2006-01-02 15:04:05", bucketStr, time.Local)
+}
+
 // DecreaseToolStats 减少工具统计信息（用于删除执行记录时）
 // 如果统计信息变为0，则删除该统计记录
 func (db *DB) DecreaseToolStats(toolName string, totalCalls, successCalls, failedCalls int) error {
@@ -0,0 +1,102 @@
+package database
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func TestCancelOrphanedRunningToolExecutions(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	start := time.Now().Add(-2 * time.Hour)
+	exec := &mcp.ToolExecution{
+		ID:        "orphan-hydra",
+		ToolName:  "hydra",
+		Arguments: map[string]interface{}{"target": "127.0.0.1"},
+		Status:    "running",
+		StartTime: start,
+	}
+	if err := db.SaveToolExecution(exec); err != nil {
+		t.Fatalf("SaveToolExecution: %v", err)
+	}
+
+	end := time.Now()
+	n, err := db.CancelOrphanedRunningToolExecutions(end, "执行已中断（服务重启）")
+	if err != nil {
+		t.Fatalf("CancelOrphanedRunningToolExecutions: %v", err)
+	}
+	if n != 1 {
+		t.Fatalf("expected 1 row updated, got %d", n)
+	}
+
+	got, err := db.GetToolExecution("orphan-hydra")
+	if err != nil {
+		t.Fatalf("GetToolExecution: %v", err)
+	}
+	if got.Status != "cancelled" {
+		t.Fatalf("expected cancelled, got %s", got.Status)
+	}
+	if got.EndTime == nil {
+		t.Fatal("expected end_time to be set")
+	}
+	if got.Duration <= 0 {
+		t.Fatalf("expected positive duration, got %v", got.Duration)
+	}
+}
+
+func TestFinalizeStaleRunningToolExecutions_skipsActive(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	now := time.Now()
+	oldStart := now.Add(-5 * time.Minute)
+	if err := db.SaveToolExecution(&mcp.ToolExecution{
+		ID: "stale", ToolName: "hydra", Status: "running", StartTime: oldStart,
+	}); err != nil {
+		t.Fatalf("SaveToolExecution stale: %v", err)
+	}
+	if err := db.SaveToolExecution(&mcp.ToolExecution{
+		ID: "active", ToolName: "hydra", Status: "running", StartTime: oldStart,
+	}); err != nil {
+		t.Fatalf("SaveToolExecution active: %v", err)
+	}
+
+	active := map[string]struct{}{"active": {}}
+	n, err := db.FinalizeStaleRunningToolExecutions(now, time.Minute, active, "执行已中断（会话已结束）")
+	if err != nil {
+		t.Fatalf("FinalizeStaleRunningToolExecutions: %v", err)
+	}
+	if n != 1 {
+		t.Fatalf("expected 1 stale row updated, got %d", n)
+	}
+
+	stale, err := db.GetToolExecution("stale")
+	if err != nil {
+		t.Fatalf("GetToolExecution stale: %v", err)
+	}
+	if stale.Status != "cancelled" {
+		t.Fatalf("stale expected cancelled, got %s", stale.Status)
+	}
+
+	activeExec, err := db.GetToolExecution("active")
+	if err != nil {
+		t.Fatalf("GetToolExecution active: %v", err)
+	}
+	if activeExec.Status != "running" {
+		t.Fatalf("active expected running, got %s", activeExec.Status)
+	}
+}
@@ -0,0 +1,122 @@
+package database
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func TestPurgeToolExecutionsBefore(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	oldStart := time.Now().AddDate(0, 0, -100)
+	newStart := time.Now().AddDate(0, 0, -1)
+
+	oldExec := &mcp.ToolExecution{
+		ID:        "old-completed",
+		ToolName:  "nmap::scan",
+		Arguments: map[string]interface{}{"target": "127.0.0.1"},
+		Status:    "completed",
+		StartTime: oldStart,
+	}
+	oldFailed := &mcp.ToolExecution{
+		ID:        "old-failed",
+		ToolName:  "nmap::scan",
+		Arguments: map[string]interface{}{"target": "127.0.0.1"},
+		Status:    "failed",
+		Error:     "timeout",
+		StartTime: oldStart,
+	}
+	newExec := &mcp.ToolExecution{
+		ID:        "new-completed",
+		ToolName:  "nmap::scan",
+		Arguments: map[string]interface{}{"target": "127.0.0.1"},
+		Status:    "completed",
+		StartTime: newStart,
+	}
+	for _, exec := range []*mcp.ToolExecution{oldExec, oldFailed, newExec} {
+		if err := db.SaveToolExecution(exec); err != nil {
+			t.Fatalf("SaveToolExecution(%s): %v", exec.ID, err)
+		}
+	}
+	if err := db.UpdateToolStats("nmap::scan", 3, 2, 1, &newStart); err != nil {
+		t.Fatalf("UpdateToolStats: %v", err)
+	}
+
+	cutoff := time.Now().AddDate(0, 0, -90)
+	deleted, err := db.PurgeToolExecutionsBefore(cutoff)
+	if err != nil {
+		t.Fatalf("PurgeToolExecutionsBefore: %v", err)
+	}
+	if deleted != 2 {
+		t.Fatalf("deleted = %d, want 2", deleted)
+	}
+
+	if _, err := db.GetToolExecution("old-completed"); err == nil {
+		t.Fatal("old-completed should be deleted")
+	}
+	if _, err := db.GetToolExecution("old-failed"); err == nil {
+		t.Fatal("old-failed should be deleted")
+	}
+	if _, err := db.GetToolExecution("new-completed"); err != nil {
+		t.Fatalf("new-completed should remain: %v", err)
+	}
+
+	stats, err := db.LoadToolStats()
+	if err != nil {
+		t.Fatalf("LoadToolStats: %v", err)
+	}
+	stat := stats["nmap::scan"]
+	if stat == nil {
+		t.Fatal("expected stats for nmap::scan")
+	}
+	if stat.TotalCalls != 1 || stat.SuccessCalls != 1 || stat.FailedCalls != 0 {
+		t.Fatalf("stats after purge = %+v, want total=1 success=1 failed=0", stat)
+	}
+
+	total, err := db.CountToolExecutions("", "")
+	if err != nil {
+		t.Fatalf("CountToolExecutions: %v", err)
+	}
+	if total != 1 {
+		t.Fatalf("remaining executions = %d, want 1", total)
+	}
+}
+
+func TestPurgeToolExecutionsBefore_zeroRetentionSkipsViaService(t *testing.T) {
+	// RetentionDaysEffective: 0 means no purge at service layer; DB method still works when called directly.
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	exec := &mcp.ToolExecution{
+		ID:        "ancient",
+		ToolName:  "curl::get",
+		Arguments: map[string]interface{}{},
+		Status:    "completed",
+		StartTime: time.Now().AddDate(-1, 0, 0),
+	}
+	if err := db.SaveToolExecution(exec); err != nil {
+		t.Fatalf("SaveToolExecution: %v", err)
+	}
+
+	deleted, err := db.PurgeToolExecutionsBefore(time.Now())
+	if err != nil {
+		t.Fatalf("PurgeToolExecutionsBefore: %v", err)
+	}
+	if deleted != 1 {
+		t.Fatalf("deleted = %d, want 1", deleted)
+	}
+}
@@ -0,0 +1,86 @@
+package database
+
+import (
+	"fmt"
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func TestLoadToolStatsSummaryAndListPage(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor-summary.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	now := time.Now()
+	tools := []struct {
+		name   string
+		calls  int
+		ok     int
+		fail   int
+		result string
+	}{
+		{"alpha::run", 10, 9, 1, `{"content":[{"type":"text","text":"` + string(make([]byte, 64*1024)) + `"}]}`},
+		{"beta::scan", 5, 5, 0, `{"content":[{"type":"text","text":"ok"}]}`},
+		{"gamma::ping", 1, 1, 0, `{"content":[{"type":"text","text":"pong"}]}`},
+	}
+
+	for _, tool := range tools {
+		if err := db.UpdateToolStats(tool.name, tool.calls, tool.ok, tool.fail, &now); err != nil {
+			t.Fatalf("UpdateToolStats(%s): %v", tool.name, err)
+		}
+		for j := 0; j < tool.calls; j++ {
+			exec := &mcp.ToolExecution{
+				ID:        fmt.Sprintf("%s-exec-%d", tool.name, j),
+				ToolName:  tool.name,
+				Arguments: map[string]interface{}{"n": j},
+				Status:    "completed",
+				StartTime: now.Add(-time.Duration(j) * time.Minute),
+				Result:    &mcp.ToolResult{Content: []mcp.Content{{Type: "text", Text: tool.result}}},
+			}
+			end := exec.StartTime.Add(time.Second)
+			exec.EndTime = &end
+			exec.Duration = time.Second
+			if err := db.SaveToolExecution(exec); err != nil {
+				t.Fatalf("SaveToolExecution: %v", err)
+			}
+		}
+	}
+
+	summary, err := db.LoadToolStatsSummary(2)
+	if err != nil {
+		t.Fatalf("LoadToolStatsSummary: %v", err)
+	}
+	if summary.Summary.ToolCount != 3 {
+		t.Fatalf("toolCount = %d, want 3", summary.Summary.ToolCount)
+	}
+	if summary.Summary.TotalCalls != 16 {
+		t.Fatalf("totalCalls = %d, want 16", summary.Summary.TotalCalls)
+	}
+	if len(summary.TopTools) != 2 {
+		t.Fatalf("top tools = %d, want 2", len(summary.TopTools))
+	}
+	if summary.TopTools[0].ToolName != "alpha::run" {
+		t.Fatalf("top tool = %q, want alpha::run", summary.TopTools[0].ToolName)
+	}
+
+	list, err := db.LoadToolExecutionListPage(0, 5, "", "")
+	if err != nil {
+		t.Fatalf("LoadToolExecutionListPage: %v", err)
+	}
+	if len(list) != 5 {
+		t.Fatalf("list len = %d, want 5", len(list))
+	}
+	for _, exec := range list {
+		if exec.Arguments != nil || exec.Result != nil || exec.Error != "" {
+			t.Fatalf("expected lite execution row, got args/result/error on %s", exec.ID)
+		}
+	}
+}
@@ -111,19 +111,43 @@ func (db *DB) GetProject(id string) (*Project, error) {
 	return &p, nil
 }

-// CountProjects 统计项目数量。
-func (db *DB) CountProjects(status, search string) (int, error) {
-	query := `SELECT COUNT(*) FROM projects WHERE 1=1`
-	args := []interface{}{}
+func projectListSearchPattern(q string) string {
+	q = strings.TrimSpace(q)
+	if q == "" {
+		return ""
+	}
+	var b strings.Builder
+	b.WriteByte('%')
+	for _, r := range q {
+		switch r {
+		case '%', '_', '\\':
+			b.WriteByte('\\')
+			b.WriteRune(r)
+		default:
+			b.WriteRune(r)
+		}
+	}
+	b.WriteByte('%')
+	return b.String()
+}
+
+func appendProjectListFilters(query string, args []interface{}, status, search string) (string, []interface{}) {
 	if s := strings.TrimSpace(status); s != "" {
 		query += " AND status = ?"
 		args = append(args, s)
 	}
-	if q := strings.TrimSpace(search); q != "" {
-		pattern := "%" + q + "%"
-		query += " AND (name LIKE ? OR COALESCE(description,'') LIKE ?)"
-		args = append(args, pattern, pattern)
+	if pattern := projectListSearchPattern(search); pattern != "" {
+		query += ` AND (LOWER(name) LIKE LOWER(?) ESCAPE '\' OR LOWER(COALESCE(description,'')) LIKE LOWER(?) ESCAPE '\' OR LOWER(id) LIKE LOWER(?) ESCAPE '\')`
+		args = append(args, pattern, pattern, pattern)
 	}
+	return query, args
+}
+
+// CountProjects 统计项目数量。
+func (db *DB) CountProjects(status, search string) (int, error) {
+	query := `SELECT COUNT(*) FROM projects WHERE 1=1`
+	args := []interface{}{}
+	query, args = appendProjectListFilters(query, args, status, search)
 	var count int
 	if err := db.QueryRow(query, args...).Scan(&count); err != nil {
 		return 0, fmt.Errorf("统计项目失败: %w", err)
@@ -139,15 +163,7 @@ func (db *DB) ListProjects(status, search string, limit, offset int) ([]*Project
 	query := `SELECT id, name, COALESCE(description,''), COALESCE(scope_json,''), status, pinned, created_at, updated_at
 		FROM projects WHERE 1=1`
 	args := []interface{}{}
-	if s := strings.TrimSpace(status); s != "" {
-		query += " AND status = ?"
-		args = append(args, s)
-	}
-	if q := strings.TrimSpace(search); q != "" {
-		pattern := "%" + q + "%"
-		query += " AND (name LIKE ? OR COALESCE(description,'') LIKE ?)"
-		args = append(args, pattern, pattern)
-	}
+	query, args = appendProjectListFilters(query, args, status, search)
 	query += " ORDER BY pinned DESC, updated_at DESC LIMIT ? OFFSET ?"
 	args = append(args, limit, offset)

@@ -195,6 +211,7 @@ func (db *DB) DeleteProject(id string) error {
 	if err != nil {
 		return fmt.Errorf("删除项目失败: %w", err)
 	}
+	db.removeProjectScopedDirs(id)
 	return nil
 }

@@ -389,7 +406,7 @@ func (db *DB) UpsertProjectFact(f *ProjectFact) (*ProjectFact, error) {
 	return f, nil
 }

-// DeprecateProjectFact 将事实标记为 deprecated。
+// DeprecateProjectFact 将事实标记为 deprecated（关联边同步 deprecated）。
 func (db *DB) DeprecateProjectFact(projectID, factKey string) error {
 	res, err := db.Exec(
 		`UPDATE project_facts SET confidence = 'deprecated', updated_at = ? WHERE project_id = ? AND fact_key = ?`,
@@ -402,7 +419,7 @@ func (db *DB) DeprecateProjectFact(projectID, factKey string) error {
 	if n == 0 {
 		return fmt.Errorf("事实不存在")
 	}
-	return nil
+	return db.DeprecateProjectFactEdgesForKey(projectID, factKey)
 }

 // RestoreProjectFact 将已废弃事实恢复为 tentative 或 confirmed（重新参与黑板索引）。
@@ -430,9 +447,16 @@ func (db *DB) RestoreProjectFact(projectID, factKey, confidence string) error {
 	return err
 }

-// DeleteProjectFact 删除事实。
+// DeleteProjectFact 删除事实（级联删除相关边）。
 func (db *DB) DeleteProjectFact(id string) error {
-	_, err := db.Exec(`DELETE FROM project_facts WHERE id = ?`, id)
+	f, err := db.GetProjectFact(id)
+	if err != nil {
+		return err
+	}
+	if err := db.DeleteProjectFactEdgesForKey(f.ProjectID, f.FactKey); err != nil {
+		return err
+	}
+	_, err = db.Exec(`DELETE FROM project_facts WHERE id = ?`, id)
 	return err
 }

@@ -0,0 +1,410 @@
+package database
+
+import (
+	"database/sql"
+	"fmt"
+	"strings"
+	"time"
+
+	"github.com/google/uuid"
+)
+
+// ValidProjectFactEdgeTypes 项目事实图允许的边类型。
+var ValidProjectFactEdgeTypes = map[string]struct{}{
+	"depends_on":    {},
+	"leads_to":      {},
+	"enables":       {},
+	"exploits":      {},
+	"discovered_on": {},
+	"contains":      {},
+	"part_of":       {},
+	"supports":      {},
+}
+
+// ProjectFactEdge 项目事实关系边（source → target）。
+type ProjectFactEdge struct {
+	ID                   string    `json:"id"`
+	ProjectID            string    `json:"project_id"`
+	SourceFactKey        string    `json:"source_fact_key"`
+	TargetFactKey        string    `json:"target_fact_key"`
+	EdgeType             string    `json:"edge_type"`
+	Confidence           string    `json:"confidence"` // confirmed | tentative | deprecated
+	SourceConversationID string    `json:"source_conversation_id,omitempty"`
+	CreatedAt            time.Time `json:"created_at"`
+	UpdatedAt            time.Time `json:"updated_at"`
+}
+
+// ProjectFactEdgeInput 写入边时的输入（出边：source → To）。
+type ProjectFactEdgeInput struct {
+	To         string `json:"to"`
+	Type       string `json:"type"`
+	Confidence string `json:"confidence,omitempty"`
+}
+
+// ProjectFactEdgeFromInput 写入入边时的输入（From → 当前事实）。
+type ProjectFactEdgeFromInput struct {
+	From       string `json:"from"`
+	Type       string `json:"type"`
+	Confidence string `json:"confidence,omitempty"`
+}
+
+// ProjectFactGraphNode 图 API 节点。
+type ProjectFactGraphNode struct {
+	ID         string `json:"id"`
+	FactKey    string `json:"fact_key"`
+	Category   string `json:"category"`
+	Label      string `json:"label"`   // 图节点短标签（截断）
+	Summary    string `json:"summary"` // 完整摘要（侧栏等详情用）
+	Confidence string `json:"confidence"`
+	Type       string `json:"type"`
+	Pinned     bool   `json:"pinned"`
+}
+
+// ProjectFactGraphEdge 图 API 边。
+type ProjectFactGraphEdge struct {
+	ID         string `json:"id"`
+	Source     string `json:"source"`
+	Target     string `json:"target"`
+	Type       string `json:"type"`
+	Confidence string `json:"confidence"`
+}
+
+// ProjectFactGraph 项目事实图。
+type ProjectFactGraph struct {
+	Nodes []ProjectFactGraphNode `json:"nodes"`
+	Edges []ProjectFactGraphEdge `json:"edges"`
+}
+
+// ValidateProjectFactEdgeType 校验边类型。
+func ValidateProjectFactEdgeType(edgeType string) error {
+	edgeType = strings.TrimSpace(strings.ToLower(edgeType))
+	if edgeType == "" {
+		return fmt.Errorf("edge type 不能为空")
+	}
+	if _, ok := ValidProjectFactEdgeTypes[edgeType]; !ok {
+		return fmt.Errorf("无效的 edge type: %s", edgeType)
+	}
+	return nil
+}
+
+func normalizeEdgeConfidence(confidence string) string {
+	confidence = strings.TrimSpace(strings.ToLower(confidence))
+	switch confidence {
+	case "confirmed", "deprecated":
+		return confidence
+	default:
+		return "tentative"
+	}
+}
+
+// ListProjectFactEdgesByProject 列出项目全部边。
+func (db *DB) ListProjectFactEdgesByProject(projectID string) ([]*ProjectFactEdge, error) {
+	rows, err := db.Query(
+		`SELECT id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+		        COALESCE(source_conversation_id,''), created_at, updated_at
+		   FROM project_fact_edges
+		  WHERE project_id = ?
+		  ORDER BY created_at ASC, rowid ASC`,
+		projectID,
+	)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	return scanProjectFactEdges(rows)
+}
+
+// ListOutgoingProjectFactEdges 列出某事实的全部出边。
+func (db *DB) ListOutgoingProjectFactEdges(projectID, sourceFactKey string) ([]*ProjectFactEdge, error) {
+	rows, err := db.Query(
+		`SELECT id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+		        COALESCE(source_conversation_id,''), created_at, updated_at
+		   FROM project_fact_edges
+		  WHERE project_id = ? AND source_fact_key = ?
+		  ORDER BY created_at ASC, rowid ASC`,
+		projectID, sourceFactKey,
+	)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	return scanProjectFactEdges(rows)
+}
+
+// ListIncomingProjectFactEdges 列出某事实的全部入边。
+func (db *DB) ListIncomingProjectFactEdges(projectID, targetFactKey string) ([]*ProjectFactEdge, error) {
+	rows, err := db.Query(
+		`SELECT id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+		        COALESCE(source_conversation_id,''), created_at, updated_at
+		   FROM project_fact_edges
+		  WHERE project_id = ? AND target_fact_key = ?
+		  ORDER BY created_at ASC, rowid ASC`,
+		projectID, targetFactKey,
+	)
+	if err != nil {
+		return nil, err
+	}
+	defer rows.Close()
+	return scanProjectFactEdges(rows)
+}
+
+// ReplaceOutgoingProjectFactEdges 替换某事实的全部出边（links 省略时不调用）。
+func (db *DB) ReplaceOutgoingProjectFactEdges(projectID, sourceFactKey, sourceConversationID string, inputs []ProjectFactEdgeInput) error {
+	sourceFactKey = strings.TrimSpace(sourceFactKey)
+	if sourceFactKey == "" {
+		return fmt.Errorf("source_fact_key 不能为空")
+	}
+	if _, err := db.Exec(
+		`DELETE FROM project_fact_edges WHERE project_id = ? AND source_fact_key = ?`,
+		projectID, sourceFactKey,
+	); err != nil {
+		return fmt.Errorf("清除旧边失败: %w", err)
+	}
+	for _, in := range inputs {
+		target := strings.TrimSpace(in.To)
+		if target == "" {
+			continue
+		}
+		if err := ValidateFactKey(target); err != nil {
+			return fmt.Errorf("target fact_key 无效 (%s): %w", target, err)
+		}
+		if target == sourceFactKey {
+			return fmt.Errorf("边不能指向自身: %s", sourceFactKey)
+		}
+		if err := ValidateProjectFactEdgeType(in.Type); err != nil {
+			return err
+		}
+		edge := &ProjectFactEdge{
+			ID:                   uuid.New().String(),
+			ProjectID:            projectID,
+			SourceFactKey:        sourceFactKey,
+			TargetFactKey:        target,
+			EdgeType:             strings.ToLower(strings.TrimSpace(in.Type)),
+			Confidence:           normalizeEdgeConfidence(in.Confidence),
+			SourceConversationID: sourceConversationID,
+			CreatedAt:            time.Now(),
+			UpdatedAt:            time.Now(),
+		}
+		if err := db.insertProjectFactEdge(edge); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// ReplaceIncomingProjectFactEdges 替换某事实的全部入边（From 为来源 fact_key）。
+func (db *DB) ReplaceIncomingProjectFactEdges(projectID, targetFactKey string, inputs []ProjectFactEdgeFromInput) error {
+	targetFactKey = strings.TrimSpace(targetFactKey)
+	if targetFactKey == "" {
+		return fmt.Errorf("target_fact_key 不能为空")
+	}
+	if _, err := db.Exec(
+		`DELETE FROM project_fact_edges WHERE project_id = ? AND target_fact_key = ?`,
+		projectID, targetFactKey,
+	); err != nil {
+		return fmt.Errorf("清除旧入边失败: %w", err)
+	}
+	for _, in := range inputs {
+		source := strings.TrimSpace(in.From)
+		if source == "" {
+			continue
+		}
+		if err := ValidateFactKey(source); err != nil {
+			return fmt.Errorf("source fact_key 无效 (%s): %w", source, err)
+		}
+		if source == targetFactKey {
+			return fmt.Errorf("边不能指向自身: %s", targetFactKey)
+		}
+		if err := ValidateProjectFactEdgeType(in.Type); err != nil {
+			return err
+		}
+		sourceConversationID := ""
+		if srcFact, err := db.GetProjectFactByKey(projectID, source); err == nil && srcFact != nil {
+			sourceConversationID = srcFact.SourceConversationID
+		}
+		edge := &ProjectFactEdge{
+			ID:                   uuid.New().String(),
+			ProjectID:            projectID,
+			SourceFactKey:        source,
+			TargetFactKey:        targetFactKey,
+			EdgeType:             strings.ToLower(strings.TrimSpace(in.Type)),
+			Confidence:           normalizeEdgeConfidence(in.Confidence),
+			SourceConversationID: sourceConversationID,
+			CreatedAt:            time.Now(),
+			UpdatedAt:            time.Now(),
+		}
+		if err := db.insertProjectFactEdge(edge); err != nil {
+			return err
+		}
+	}
+	return nil
+}
+
+// GetProjectFactEdge 按 ID 获取边。
+func (db *DB) GetProjectFactEdge(edgeID string) (*ProjectFactEdge, error) {
+	var e ProjectFactEdge
+	var createdAt, updatedAt string
+	err := db.QueryRow(
+		`SELECT id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+		        COALESCE(source_conversation_id,''), created_at, updated_at
+		   FROM project_fact_edges WHERE id = ?`, edgeID,
+	).Scan(&e.ID, &e.ProjectID, &e.SourceFactKey, &e.TargetFactKey, &e.EdgeType, &e.Confidence,
+		&e.SourceConversationID, &createdAt, &updatedAt)
+	if err != nil {
+		return nil, fmt.Errorf("边不存在")
+	}
+	e.CreatedAt = parseDBTime(createdAt)
+	e.UpdatedAt = parseDBTime(updatedAt)
+	return &e, nil
+}
+
+// AddProjectFactEdge 新增单条边（已存在则更新 confidence）。
+func (db *DB) AddProjectFactEdge(projectID string, in ProjectFactEdgeInput, sourceFactKey, sourceConversationID string) (*ProjectFactEdge, error) {
+	sourceFactKey = strings.TrimSpace(sourceFactKey)
+	target := strings.TrimSpace(in.To)
+	if sourceFactKey == "" || target == "" {
+		return nil, fmt.Errorf("source 与 target 必填")
+	}
+	if sourceFactKey == target {
+		return nil, fmt.Errorf("边不能指向自身")
+	}
+	if err := ValidateProjectFactEdgeType(in.Type); err != nil {
+		return nil, err
+	}
+	if err := ValidateFactKey(target); err != nil {
+		return nil, err
+	}
+	now := time.Now()
+	e := &ProjectFactEdge{
+		ID:                   uuid.New().String(),
+		ProjectID:            projectID,
+		SourceFactKey:        sourceFactKey,
+		TargetFactKey:        target,
+		EdgeType:             strings.ToLower(strings.TrimSpace(in.Type)),
+		Confidence:           normalizeEdgeConfidence(in.Confidence),
+		SourceConversationID: sourceConversationID,
+		CreatedAt:            now,
+		UpdatedAt:            now,
+	}
+	_, err := db.Exec(
+		`INSERT INTO project_fact_edges (
+			id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+			source_conversation_id, created_at, updated_at
+		) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)
+		ON CONFLICT(project_id, source_fact_key, target_fact_key, edge_type)
+		DO UPDATE SET confidence = excluded.confidence, updated_at = excluded.updated_at`,
+		e.ID, e.ProjectID, e.SourceFactKey, e.TargetFactKey, e.EdgeType, e.Confidence,
+		nullIfEmpty(e.SourceConversationID), e.CreatedAt, e.UpdatedAt,
+	)
+	if err != nil {
+		return nil, fmt.Errorf("添加边失败: %w", err)
+	}
+	// 返回最新
+	rows, err := db.Query(
+		`SELECT id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+		        COALESCE(source_conversation_id,''), created_at, updated_at
+		   FROM project_fact_edges
+		  WHERE project_id = ? AND source_fact_key = ? AND target_fact_key = ? AND edge_type = ?`,
+		projectID, sourceFactKey, target, e.EdgeType,
+	)
+	if err != nil {
+		return e, nil
+	}
+	defer rows.Close()
+	list, err := scanProjectFactEdges(rows)
+	if err != nil || len(list) == 0 {
+		return e, nil
+	}
+	return list[0], nil
+}
+
+// DeleteProjectFactEdge 删除单条边。
+func (db *DB) DeleteProjectFactEdge(edgeID string) error {
+	res, err := db.Exec(`DELETE FROM project_fact_edges WHERE id = ?`, edgeID)
+	if err != nil {
+		return err
+	}
+	n, _ := res.RowsAffected()
+	if n == 0 {
+		return fmt.Errorf("边不存在")
+	}
+	return nil
+}
+
+func (db *DB) insertProjectFactEdge(e *ProjectFactEdge) error {
+	_, err := db.Exec(
+		`INSERT INTO project_fact_edges (
+			id, project_id, source_fact_key, target_fact_key, edge_type, confidence,
+			source_conversation_id, created_at, updated_at
+		) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`,
+		e.ID, e.ProjectID, e.SourceFactKey, e.TargetFactKey, e.EdgeType, e.Confidence,
+		nullIfEmpty(e.SourceConversationID), e.CreatedAt, e.UpdatedAt,
+	)
+	if err != nil {
+		return fmt.Errorf("写入边失败: %w", err)
+	}
+	return nil
+}
+
+// RenameProjectFactKeyEdges 事实 key 变更时同步边上的引用。
+func (db *DB) RenameProjectFactKeyEdges(projectID, oldKey, newKey string) error {
+	oldKey = strings.TrimSpace(oldKey)
+	newKey = strings.TrimSpace(newKey)
+	if oldKey == "" || newKey == "" || oldKey == newKey {
+		return nil
+	}
+	now := time.Now()
+	if _, err := db.Exec(
+		`UPDATE project_fact_edges SET source_fact_key = ?, updated_at = ?
+		  WHERE project_id = ? AND source_fact_key = ?`,
+		newKey, now, projectID, oldKey,
+	); err != nil {
+		return err
+	}
+	_, err := db.Exec(
+		`UPDATE project_fact_edges SET target_fact_key = ?, updated_at = ?
+		  WHERE project_id = ? AND target_fact_key = ?`,
+		newKey, now, projectID, oldKey,
+	)
+	return err
+}
+
+// DeleteProjectFactEdgesForKey 删除与某 fact_key 相关的全部边。
+func (db *DB) DeleteProjectFactEdgesForKey(projectID, factKey string) error {
+	_, err := db.Exec(
+		`DELETE FROM project_fact_edges
+		  WHERE project_id = ? AND (source_fact_key = ? OR target_fact_key = ?)`,
+		projectID, factKey, factKey,
+	)
+	return err
+}
+
+// DeprecateProjectFactEdgesForKey 将关联边标记为 deprecated。
+func (db *DB) DeprecateProjectFactEdgesForKey(projectID, factKey string) error {
+	now := time.Now()
+	_, err := db.Exec(
+		`UPDATE project_fact_edges SET confidence = 'deprecated', updated_at = ?
+		  WHERE project_id = ? AND (source_fact_key = ? OR target_fact_key = ?)
+		    AND confidence != 'deprecated'`,
+		now, projectID, factKey, factKey,
+	)
+	return err
+}
+
+func scanProjectFactEdges(rows *sql.Rows) ([]*ProjectFactEdge, error) {
+	var out []*ProjectFactEdge
+	for rows.Next() {
+		var e ProjectFactEdge
+		var createdAt, updatedAt string
+		if err := rows.Scan(
+			&e.ID, &e.ProjectID, &e.SourceFactKey, &e.TargetFactKey, &e.EdgeType, &e.Confidence,
+			&e.SourceConversationID, &createdAt, &updatedAt,
+		); err != nil {
+			return nil, err
+		}
+		e.CreatedAt = parseDBTime(createdAt)
+		e.UpdatedAt = parseDBTime(updatedAt)
+		out = append(out, &e)
+	}
+	return out, rows.Err()
+}
@@ -0,0 +1,82 @@
+package database
+
+import (
+	"path/filepath"
+	"testing"
+
+	"go.uber.org/zap"
+)
+
+func TestListProjectsSearchCaseInsensitive(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "projects-search.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer db.Close()
+
+	p1, err := db.CreateProject(&Project{Name: "Alpha Security Review", Status: "active"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	p2, err := db.CreateProject(&Project{Name: "beta-scan", Status: "active"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	if _, err := db.CreateProject(&Project{Name: "Other", Status: "archived"}); err != nil {
+		t.Fatal(err)
+	}
+
+	cases := []struct {
+		name   string
+		search string
+		status string
+		want   []string
+	}{
+		{name: "case insensitive name", search: "alpha", status: "active", want: []string{p1.ID}},
+		{name: "upper query", search: "BETA", status: "active", want: []string{p2.ID}},
+		{name: "search by id substring", search: p1.ID[:8], status: "", want: []string{p1.ID}},
+		{name: "status filter", search: "alpha", status: "archived", want: nil},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			list, err := db.ListProjects(tc.status, tc.search, 50, 0)
+			if err != nil {
+				t.Fatal(err)
+			}
+			got := make([]string, 0, len(list))
+			for _, p := range list {
+				got = append(got, p.ID)
+			}
+			if len(got) != len(tc.want) {
+				t.Fatalf("got %v want %v", got, tc.want)
+			}
+			for i := range got {
+				if got[i] != tc.want[i] {
+					t.Fatalf("got %v want %v", got, tc.want)
+				}
+			}
+		})
+	}
+}
+
+func TestProjectListSearchPatternEscapesWildcards(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "projects-like.db")
+	db, err := NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatal(err)
+	}
+	defer db.Close()
+
+	p, err := db.CreateProject(&Project{Name: "100% coverage", Status: "active"})
+	if err != nil {
+		t.Fatal(err)
+	}
+	list, err := db.ListProjects("active", "100%", 50, 0)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(list) != 1 || list[0].ID != p.ID {
+		t.Fatalf("expected exact match for literal %% query, got %#v", list)
+	}
+}
@@ -72,14 +72,17 @@ func (f VulnerabilityListFilter) appendWhere(query string, args []interface{}) (
 			LOWER(COALESCE(description, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(vulnerability_type, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(target, '')) LIKE LOWER(?) OR
-			LOWER(COALESCE(proof, '')) LIKE LOWER(?) OR
+			LOWER(COALESCE(preconditions, '')) LIKE LOWER(?) OR
+			LOWER(COALESCE(reproduction_steps, '')) LIKE LOWER(?) OR
+			LOWER(COALESCE(evidence, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(impact, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(recommendation, '')) LIKE LOWER(?) OR
+			LOWER(COALESCE(retest_notes, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(conversation_id, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(conversation_tag, '')) LIKE LOWER(?) OR
 			LOWER(COALESCE(task_tag, '')) LIKE LOWER(?)
 		)`
-		for i := 0; i < 11; i++ {
+		for i := 0; i < 14; i++ {
 			args = append(args, pattern)
 		}
 	}
@@ -101,9 +104,12 @@ type Vulnerability struct {
 	Status          string    `json:"status"`   // open, confirmed, fixed, false_positive, ignored
 	Type            string    `json:"type"`
 	Target          string    `json:"target"`
-	Proof           string    `json:"proof"`
+	Preconditions   string    `json:"preconditions"`
+	ReproSteps      string    `json:"reproduction_steps"`
+	Evidence        string    `json:"evidence"`
 	Impact          string    `json:"impact"`
 	Recommendation  string    `json:"recommendation"`
+	RetestNotes     string    `json:"retest_notes"`
 	CreatedAt       time.Time `json:"created_at"`
 	UpdatedAt       time.Time `json:"updated_at"`
 }
@@ -131,16 +137,16 @@ func (db *DB) CreateVulnerability(vuln *Vulnerability) (*Vulnerability, error) {
 	query := `
 		INSERT INTO vulnerabilities (
 			id, conversation_id, project_id, conversation_tag, task_tag, title, description, severity, status,
-			vulnerability_type, target, proof, impact, recommendation,
+			vulnerability_type, target, preconditions, reproduction_steps, evidence, impact, recommendation, retest_notes,
 			created_at, updated_at
-		) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
+		) VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?, ?)
 	`

 	_, err := db.Exec(
 		query,
 		vuln.ID, nullIfEmpty(vuln.ConversationID), nullIfEmpty(vuln.ProjectID), vuln.ConversationTag, vuln.TaskTag, vuln.Title, vuln.Description,
 		vuln.Severity, vuln.Status, vuln.Type, vuln.Target,
-		vuln.Proof, vuln.Impact, vuln.Recommendation,
+		vuln.Preconditions, vuln.ReproSteps, vuln.Evidence, vuln.Impact, vuln.Recommendation, vuln.RetestNotes,
 		vuln.CreatedAt, vuln.UpdatedAt,
 	)
 	if err != nil {
@@ -155,7 +161,9 @@ func (db *DB) GetVulnerability(id string) (*Vulnerability, error) {
 	var vuln Vulnerability
 	query := `
 		SELECT id, COALESCE(conversation_id,''), COALESCE(project_id,''), title, description, severity, status,
-		       conversation_tag, task_tag, vulnerability_type, target, proof, impact, recommendation,
+		       conversation_tag, task_tag, vulnerability_type, target,
+		       COALESCE(preconditions,''), COALESCE(reproduction_steps,''), COALESCE(evidence,''),
+		       impact, recommendation, COALESCE(retest_notes,''),
 		       COALESCE((SELECT bt.id FROM batch_tasks bt WHERE bt.conversation_id = vulnerabilities.conversation_id LIMIT 1), '') AS task_id,
 		       COALESCE((SELECT bt.queue_id FROM batch_tasks bt WHERE bt.conversation_id = vulnerabilities.conversation_id LIMIT 1), '') AS task_queue_id,
 		       created_at, updated_at
@@ -166,7 +174,7 @@ func (db *DB) GetVulnerability(id string) (*Vulnerability, error) {
 	err := db.QueryRow(query, id).Scan(
 		&vuln.ID, &vuln.ConversationID, &vuln.ProjectID, &vuln.Title, &vuln.Description,
 		&vuln.Severity, &vuln.Status, &vuln.ConversationTag, &vuln.TaskTag, &vuln.Type, &vuln.Target,
-		&vuln.Proof, &vuln.Impact, &vuln.Recommendation,
+		&vuln.Preconditions, &vuln.ReproSteps, &vuln.Evidence, &vuln.Impact, &vuln.Recommendation, &vuln.RetestNotes,
 		&vuln.TaskID, &vuln.TaskQueueID,
 		&vuln.CreatedAt, &vuln.UpdatedAt,
 	)
@@ -184,7 +192,9 @@ func (db *DB) GetVulnerability(id string) (*Vulnerability, error) {
 func (db *DB) ListVulnerabilities(limit, offset int, filter VulnerabilityListFilter) ([]*Vulnerability, error) {
 	query := `
 		SELECT id, COALESCE(conversation_id,''), COALESCE(project_id,''), title, description, severity, status, conversation_tag, task_tag,
-		       vulnerability_type, target, proof, impact, recommendation,
+		       vulnerability_type, target,
+		       COALESCE(preconditions,''), COALESCE(reproduction_steps,''), COALESCE(evidence,''),
+		       impact, recommendation, COALESCE(retest_notes,''),
 		       COALESCE((SELECT bt.id FROM batch_tasks bt WHERE bt.conversation_id = vulnerabilities.conversation_id LIMIT 1), '') AS task_id,
 		       COALESCE((SELECT bt.queue_id FROM batch_tasks bt WHERE bt.conversation_id = vulnerabilities.conversation_id LIMIT 1), '') AS task_queue_id,
 		       created_at, updated_at
@@ -209,7 +219,7 @@ func (db *DB) ListVulnerabilities(limit, offset int, filter VulnerabilityListFil
 		err := rows.Scan(
 			&vuln.ID, &vuln.ConversationID, &vuln.ProjectID, &vuln.Title, &vuln.Description,
 			&vuln.Severity, &vuln.Status, &vuln.ConversationTag, &vuln.TaskTag, &vuln.Type, &vuln.Target,
-			&vuln.Proof, &vuln.Impact, &vuln.Recommendation,
+			&vuln.Preconditions, &vuln.ReproSteps, &vuln.Evidence, &vuln.Impact, &vuln.Recommendation, &vuln.RetestNotes,
 			&vuln.TaskID, &vuln.TaskQueueID,
 			&vuln.CreatedAt, &vuln.UpdatedAt,
 		)
@@ -245,16 +255,16 @@ func (db *DB) UpdateVulnerability(id string, vuln *Vulnerability) error {
 	query := `
 		UPDATE vulnerabilities
 		SET project_id = ?, conversation_tag = ?, task_tag = ?, title = ?, description = ?, severity = ?, status = ?,
-		    vulnerability_type = ?, target = ?, proof = ?, impact = ?,
-		    recommendation = ?, updated_at = ?
+		    vulnerability_type = ?, target = ?, preconditions = ?, reproduction_steps = ?, evidence = ?, impact = ?,
+		    recommendation = ?, retest_notes = ?, updated_at = ?
 		WHERE id = ?
 	`

 	_, err := db.Exec(
 		query,
 		nullIfEmpty(vuln.ProjectID), vuln.ConversationTag, vuln.TaskTag, vuln.Title, vuln.Description, vuln.Severity, vuln.Status,
-		vuln.Type, vuln.Target, vuln.Proof, vuln.Impact,
-		vuln.Recommendation, vuln.UpdatedAt, id,
+		vuln.Type, vuln.Target, vuln.Preconditions, vuln.ReproSteps, vuln.Evidence, vuln.Impact,
+		vuln.Recommendation, vuln.RetestNotes, vuln.UpdatedAt, id,
 	)
 	if err != nil {
 		return fmt.Errorf("更新漏洞失败: %w", err)
@@ -0,0 +1,468 @@
+package database
+
+import (
+	"database/sql"
+	"encoding/json"
+	"fmt"
+	"strings"
+	"time"
+)
+
+// WorkflowDefinition is a persisted user-defined graph/workflow template.
+// graph_json intentionally remains opaque so users can define their own fields.
+type WorkflowDefinition struct {
+	ID          string    `json:"id"`
+	Name        string    `json:"name"`
+	Description string    `json:"description,omitempty"`
+	Version     int       `json:"version"`
+	GraphJSON   string    `json:"graph_json"`
+	Enabled     bool      `json:"enabled"`
+	CreatedAt   time.Time `json:"created_at"`
+	UpdatedAt   time.Time `json:"updated_at"`
+}
+
+type WorkflowRun struct {
+	ID                string     `json:"id"`
+	WorkflowID        string     `json:"workflow_id"`
+	WorkflowVersion   int        `json:"workflow_version"`
+	ConversationID    string     `json:"conversation_id,omitempty"`
+	ProjectID         string     `json:"project_id,omitempty"`
+	RoleID            string     `json:"role_id,omitempty"`
+	Status            string     `json:"status"`
+	InputJSON         string     `json:"input_json,omitempty"`
+	OutputJSON        string     `json:"output_json,omitempty"`
+	Error             string     `json:"error,omitempty"`
+	PendingHITLNodeID string     `json:"pending_hitl_node_id,omitempty"`
+	PendingHITLJSON   string     `json:"pending_hitl_json,omitempty"`
+	StartedAt         time.Time  `json:"started_at"`
+	FinishedAt        *time.Time `json:"finished_at,omitempty"`
+}
+
+type WorkflowNodeRun struct {
+	ID         string     `json:"id"`
+	RunID      string     `json:"run_id"`
+	NodeID     string     `json:"node_id"`
+	Status     string     `json:"status"`
+	InputJSON  string     `json:"input_json,omitempty"`
+	OutputJSON string     `json:"output_json,omitempty"`
+	Error      string     `json:"error,omitempty"`
+	StartedAt  time.Time  `json:"started_at"`
+	FinishedAt *time.Time `json:"finished_at,omitempty"`
+}
+
+func scanWorkflowNodeRun(scanner interface {
+	Scan(dest ...interface{}) error
+}) (*WorkflowNodeRun, error) {
+	var row WorkflowNodeRun
+	var inputJSON, outputJSON, errText sql.NullString
+	var finishedAt sql.NullTime
+	if err := scanner.Scan(&row.ID, &row.RunID, &row.NodeID, &row.Status, &inputJSON, &outputJSON, &errText, &row.StartedAt, &finishedAt); err != nil {
+		return nil, err
+	}
+	row.InputJSON = inputJSON.String
+	row.OutputJSON = outputJSON.String
+	row.Error = errText.String
+	if finishedAt.Valid {
+		t := finishedAt.Time
+		row.FinishedAt = &t
+	}
+	return &row, nil
+}
+
+func scanWorkflowDefinition(scanner interface {
+	Scan(dest ...interface{}) error
+}) (*WorkflowDefinition, error) {
+	var row WorkflowDefinition
+	var desc sql.NullString
+	var enabled int
+	if err := scanner.Scan(&row.ID, &row.Name, &desc, &row.Version, &row.GraphJSON, &enabled, &row.CreatedAt, &row.UpdatedAt); err != nil {
+		return nil, err
+	}
+	row.Description = desc.String
+	row.Enabled = enabled != 0
+	return &row, nil
+}
+
+const workflowDefinitionColumns = `id, name, description, version, graph_json, enabled, created_at, updated_at`
+
+func (db *DB) ListWorkflowDefinitions(includeDisabled bool) ([]*WorkflowDefinition, error) {
+	query := "SELECT " + workflowDefinitionColumns + " FROM workflow_definitions"
+	if !includeDisabled {
+		query += " WHERE enabled = 1"
+	}
+	query += " ORDER BY updated_at DESC"
+	rows, err := db.Query(query)
+	if err != nil {
+		return nil, fmt.Errorf("查询工作流列表失败: %w", err)
+	}
+	defer rows.Close()
+
+	var out []*WorkflowDefinition
+	for rows.Next() {
+		wf, err := scanWorkflowDefinition(rows)
+		if err != nil {
+			return nil, fmt.Errorf("扫描工作流失败: %w", err)
+		}
+		out = append(out, wf)
+	}
+	return out, rows.Err()
+}
+
+func (db *DB) GetWorkflowDefinition(id string) (*WorkflowDefinition, error) {
+	id = strings.TrimSpace(id)
+	if id == "" {
+		return nil, nil
+	}
+	wf, err := scanWorkflowDefinition(db.QueryRow("SELECT "+workflowDefinitionColumns+" FROM workflow_definitions WHERE id = ?", id))
+	if err == sql.ErrNoRows {
+		return nil, nil
+	}
+	if err != nil {
+		return nil, fmt.Errorf("查询工作流失败: %w", err)
+	}
+	return wf, nil
+}
+
+func (db *DB) UpsertWorkflowDefinition(wf *WorkflowDefinition) error {
+	if wf == nil {
+		return fmt.Errorf("工作流为空")
+	}
+	wf.ID = strings.TrimSpace(wf.ID)
+	wf.Name = strings.TrimSpace(wf.Name)
+	if wf.ID == "" || wf.Name == "" {
+		return fmt.Errorf("工作流 id 和 name 不能为空")
+	}
+	if strings.TrimSpace(wf.GraphJSON) == "" {
+		wf.GraphJSON = `{"nodes":[],"edges":[],"config":{}}`
+	}
+	if wf.Version <= 0 {
+		wf.Version = 1
+	}
+	now := time.Now()
+	existing, err := db.GetWorkflowDefinition(wf.ID)
+	if err != nil {
+		return err
+	}
+	if existing == nil {
+		_, err = db.Exec(
+			`INSERT INTO workflow_definitions (id, name, description, version, graph_json, enabled, created_at, updated_at)
+			 VALUES (?, ?, ?, ?, ?, ?, ?, ?)`,
+			wf.ID, wf.Name, wf.Description, wf.Version, wf.GraphJSON, boolToInt(wf.Enabled), now, now,
+		)
+	} else {
+		nextVersion := existing.Version + 1
+		if wf.Version > existing.Version {
+			nextVersion = wf.Version
+		}
+		_, err = db.Exec(
+			`UPDATE workflow_definitions
+			 SET name = ?, description = ?, version = ?, graph_json = ?, enabled = ?, updated_at = ?
+			 WHERE id = ?`,
+			wf.Name, wf.Description, nextVersion, wf.GraphJSON, boolToInt(wf.Enabled), now, wf.ID,
+		)
+	}
+	if err != nil {
+		return fmt.Errorf("保存工作流失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) DeleteWorkflowDefinition(id string) error {
+	id = strings.TrimSpace(id)
+	if id == "" {
+		return fmt.Errorf("工作流 id 不能为空")
+	}
+	if _, err := db.Exec("DELETE FROM workflow_definitions WHERE id = ?", id); err != nil {
+		return fmt.Errorf("删除工作流失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) CreateWorkflowRun(run *WorkflowRun) error {
+	if run == nil {
+		return fmt.Errorf("工作流运行为空")
+	}
+	if strings.TrimSpace(run.ID) == "" || strings.TrimSpace(run.WorkflowID) == "" {
+		return fmt.Errorf("工作流运行 id 和 workflow_id 不能为空")
+	}
+	if run.WorkflowVersion <= 0 {
+		run.WorkflowVersion = 1
+	}
+	if strings.TrimSpace(run.Status) == "" {
+		run.Status = "running"
+	}
+	if run.StartedAt.IsZero() {
+		run.StartedAt = time.Now()
+	}
+	_, err := db.Exec(
+		`INSERT INTO workflow_runs (id, workflow_id, workflow_version, conversation_id, project_id, role_id, status, input_json, started_at)
+		 VALUES (?, ?, ?, ?, ?, ?, ?, ?, ?)`,
+		run.ID, run.WorkflowID, run.WorkflowVersion, nullString(run.ConversationID), nullString(run.ProjectID), nullString(run.RoleID), run.Status, run.InputJSON, run.StartedAt,
+	)
+	if err != nil {
+		return fmt.Errorf("创建工作流运行失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) FinishWorkflowRun(runID, status, outputJSON, errText string) error {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return fmt.Errorf("工作流运行 id 不能为空")
+	}
+	if strings.TrimSpace(status) == "" {
+		status = "completed"
+	}
+	now := time.Now()
+	_, err := db.Exec(
+		`UPDATE workflow_runs SET status = ?, output_json = ?, error = ?, finished_at = ? WHERE id = ?`,
+		status, outputJSON, errText, now, runID,
+	)
+	if err != nil {
+		return fmt.Errorf("更新工作流运行失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) CreateWorkflowNodeRun(n *WorkflowNodeRun) error {
+	if n == nil {
+		return fmt.Errorf("工作流节点运行为空")
+	}
+	if strings.TrimSpace(n.ID) == "" || strings.TrimSpace(n.RunID) == "" || strings.TrimSpace(n.NodeID) == "" {
+		return fmt.Errorf("节点运行 id、run_id 和 node_id 不能为空")
+	}
+	if strings.TrimSpace(n.Status) == "" {
+		n.Status = "running"
+	}
+	if n.StartedAt.IsZero() {
+		n.StartedAt = time.Now()
+	}
+	_, err := db.Exec(
+		`INSERT INTO workflow_node_runs (id, run_id, node_id, status, input_json, started_at)
+		 VALUES (?, ?, ?, ?, ?, ?)`,
+		n.ID, n.RunID, n.NodeID, n.Status, n.InputJSON, n.StartedAt,
+	)
+	if err != nil {
+		return fmt.Errorf("创建工作流节点运行失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) FinishWorkflowNodeRun(nodeRunID, status, outputJSON, errText string) error {
+	nodeRunID = strings.TrimSpace(nodeRunID)
+	if nodeRunID == "" {
+		return fmt.Errorf("节点运行 id 不能为空")
+	}
+	if strings.TrimSpace(status) == "" {
+		status = "completed"
+	}
+	now := time.Now()
+	_, err := db.Exec(
+		`UPDATE workflow_node_runs SET status = ?, output_json = ?, error = ?, finished_at = ? WHERE id = ?`,
+		status, outputJSON, errText, now, nodeRunID,
+	)
+	if err != nil {
+		return fmt.Errorf("更新工作流节点运行失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) ListWorkflowNodeRuns(runID string) ([]*WorkflowNodeRun, error) {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return nil, fmt.Errorf("工作流运行 id 不能为空")
+	}
+	rows, err := db.Query(
+		`SELECT id, run_id, node_id, status, input_json, output_json, error, started_at, finished_at
+		 FROM workflow_node_runs WHERE run_id = ? ORDER BY started_at ASC`,
+		runID,
+	)
+	if err != nil {
+		return nil, fmt.Errorf("查询工作流节点运行失败: %w", err)
+	}
+	defer rows.Close()
+	var out []*WorkflowNodeRun
+	for rows.Next() {
+		row, err := scanWorkflowNodeRun(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, row)
+	}
+	return out, rows.Err()
+}
+
+func scanWorkflowRun(scanner interface {
+	Scan(dest ...interface{}) error
+}) (*WorkflowRun, error) {
+	var row WorkflowRun
+	var convID, projectID, roleID, inputJSON, outputJSON, errText, pendingNode, pendingJSON sql.NullString
+	var finishedAt sql.NullTime
+	if err := scanner.Scan(
+		&row.ID, &row.WorkflowID, &row.WorkflowVersion,
+		&convID, &projectID, &roleID, &row.Status,
+		&inputJSON, &outputJSON, &errText,
+		&pendingNode, &pendingJSON,
+		&row.StartedAt, &finishedAt,
+	); err != nil {
+		return nil, err
+	}
+	row.ConversationID = convID.String
+	row.ProjectID = projectID.String
+	row.RoleID = roleID.String
+	row.InputJSON = inputJSON.String
+	row.OutputJSON = outputJSON.String
+	row.Error = errText.String
+	row.PendingHITLNodeID = pendingNode.String
+	row.PendingHITLJSON = pendingJSON.String
+	if finishedAt.Valid {
+		t := finishedAt.Time
+		row.FinishedAt = &t
+	}
+	return &row, nil
+}
+
+const workflowRunColumns = `id, workflow_id, workflow_version, conversation_id, project_id, role_id, status, input_json, output_json, error, pending_hitl_node_id, pending_hitl_json, started_at, finished_at`
+
+func (db *DB) GetWorkflowRun(runID string) (*WorkflowRun, error) {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return nil, nil
+	}
+	row, err := scanWorkflowRun(db.QueryRow("SELECT "+workflowRunColumns+" FROM workflow_runs WHERE id = ?", runID))
+	if err == sql.ErrNoRows {
+		return nil, nil
+	}
+	if err != nil {
+		return nil, fmt.Errorf("查询工作流运行失败: %w", err)
+	}
+	return row, nil
+}
+
+func (db *DB) SetWorkflowRunStatus(runID, status string) error {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return fmt.Errorf("工作流运行 id 不能为空")
+	}
+	_, err := db.Exec(`UPDATE workflow_runs SET status = ? WHERE id = ?`, strings.TrimSpace(status), runID)
+	if err != nil {
+		return fmt.Errorf("更新工作流运行状态失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) SetWorkflowRunAwaitingHITL(runID, nodeID, pendingJSON string) error {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return fmt.Errorf("工作流运行 id 不能为空")
+	}
+	_, err := db.Exec(
+		`UPDATE workflow_runs SET status = 'awaiting_hitl', pending_hitl_node_id = ?, pending_hitl_json = ?, finished_at = NULL WHERE id = ?`,
+		strings.TrimSpace(nodeID), pendingJSON, runID,
+	)
+	if err != nil {
+		return fmt.Errorf("更新工作流 HITL 等待状态失败: %w", err)
+	}
+	return nil
+}
+
+// RecordWorkflowRunHITLDecision stores a human decision on a paused workflow run.
+func (db *DB) RecordWorkflowRunHITLDecision(runID string, approved bool, comment string) error {
+	runID = strings.TrimSpace(runID)
+	if runID == "" {
+		return fmt.Errorf("工作流运行 id 不能为空")
+	}
+	run, err := db.GetWorkflowRun(runID)
+	if err != nil {
+		return err
+	}
+	if run == nil {
+		return fmt.Errorf("工作流运行不存在")
+	}
+	pending := map[string]interface{}{}
+	if strings.TrimSpace(run.PendingHITLJSON) != "" {
+		_ = json.Unmarshal([]byte(run.PendingHITLJSON), &pending)
+	}
+	if approved {
+		pending["decision"] = "approved"
+	} else {
+		pending["decision"] = "rejected"
+	}
+	pending["comment"] = strings.TrimSpace(comment)
+	raw, _ := json.Marshal(pending)
+	_, err = db.Exec(
+		`UPDATE workflow_runs SET pending_hitl_json = ? WHERE id = ? AND status = 'awaiting_hitl'`,
+		string(raw), runID,
+	)
+	if err != nil {
+		return fmt.Errorf("记录工作流审批决定失败: %w", err)
+	}
+	return nil
+}
+
+func (db *DB) ListWorkflowRunsAwaitingHITL(limit int) ([]*WorkflowRun, error) {
+	return db.ListWorkflowRunsAwaitingHITLFiltered("", limit)
+}
+
+// ListWorkflowRunsAwaitingHITLFiltered returns awaiting_hitl runs, optionally scoped to a conversation.
+func (db *DB) ListWorkflowRunsAwaitingHITLFiltered(conversationID string, limit int) ([]*WorkflowRun, error) {
+	if limit <= 0 {
+		limit = 50
+	}
+	conversationID = strings.TrimSpace(conversationID)
+	var rows *sql.Rows
+	var err error
+	if conversationID != "" {
+		rows, err = db.Query(
+			`SELECT `+workflowRunColumns+` FROM workflow_runs WHERE status = 'awaiting_hitl' AND conversation_id = ? ORDER BY started_at DESC LIMIT ?`,
+			conversationID, limit,
+		)
+	} else {
+		rows, err = db.Query(
+			`SELECT `+workflowRunColumns+` FROM workflow_runs WHERE status = 'awaiting_hitl' ORDER BY started_at DESC LIMIT ?`,
+			limit,
+		)
+	}
+	if err != nil {
+		return nil, fmt.Errorf("查询等待审批的工作流运行失败: %w", err)
+	}
+	defer rows.Close()
+	var out []*WorkflowRun
+	for rows.Next() {
+		row, err := scanWorkflowRun(rows)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, row)
+	}
+	return out, rows.Err()
+}
+
+func (db *DB) migrateWorkflowRunsTable() error {
+	cols := []struct{ name, ddl string }{
+		{"pending_hitl_node_id", "ALTER TABLE workflow_runs ADD COLUMN pending_hitl_node_id TEXT"},
+		{"pending_hitl_json", "ALTER TABLE workflow_runs ADD COLUMN pending_hitl_json TEXT"},
+	}
+	for _, col := range cols {
+		var count int
+		err := db.QueryRow("SELECT COUNT(*) FROM pragma_table_info('workflow_runs') WHERE name=?", col.name).Scan(&count)
+		if err != nil || count > 0 {
+			continue
+		}
+		if _, err := db.Exec(col.ddl); err != nil {
+			errMsg := strings.ToLower(err.Error())
+			if !strings.Contains(errMsg, "duplicate column") && !strings.Contains(errMsg, "already exists") {
+				return err
+			}
+		}
+	}
+	return nil
+}
+
+func nullString(v string) interface{} {
+	v = strings.TrimSpace(v)
+	if v == "" {
+		return nil
+	}
+	return v
+}
@@ -2,8 +2,8 @@ package einomcp

 import "sync"

-// ToolInvokeNotifyHolder 由 Eino run loop 在迭代开始前 Set 回调；MCP/execute 桥在工具调用结束时 Fire，
-// 用于清除 pending tool_call（tool_result 由 ADK schema.Tool 事件推送，含流式工具与 reduction 后正文）。
+// ToolInvokeNotifyHolder 由 Eino run loop 与 MCP/execute 桥共享；Fire 在工具原始返回时触发。
+// UI 的 tool_result 须等 ADK schema.Tool 事件（reduction 后正文），不在此 holder 的回调里推送。
 type ToolInvokeNotifyHolder struct {
 	mu sync.RWMutex
 	fn func(toolCallID, toolName, einoAgent string, success bool, content string, invokeErr error)
@@ -21,7 +21,6 @@ import (
 	"cyberstrike-ai/internal/config"
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/reasoning"
-	"cyberstrike-ai/internal/mcp"
 	"cyberstrike-ai/internal/mcp/builtin"
 	"cyberstrike-ai/internal/multiagent"
 	"cyberstrike-ai/internal/openai"
@@ -78,6 +77,13 @@ type responsePlanAgg struct {
 	b    strings.Builder
 }

+// thinkingBuf aggregates thinking_stream_* / reasoning_chain_stream_* before flush to process_details.
+type thinkingBuf struct {
+	b         strings.Builder
+	meta      map[string]interface{}
+	persistAs string // "thinking" | "reasoning_chain"
+}
+
 func normalizeProcessDetailText(s string) string {
 	s = strings.ReplaceAll(s, "\r\n", "\n")
 	s = strings.ReplaceAll(s, "\r", "\n")
@@ -178,10 +184,11 @@ type AgentHandler struct {
 	}
 	agentsMarkdownDir string // 多代理：Markdown 子 Agent 目录（绝对路径，空则不从磁盘合并）
 	batchCronParser   cron.Parser
-	batchRunnerMu     sync.Mutex
-	batchRunning      map[string]struct{}
 	// hitlWhitelistSaver 侧栏「应用」HITL 时将会话增量白名单合并写入 config.yaml（可选）
-	hitlWhitelistSaver HitlToolWhitelistSaver
+	hitlWhitelistSaver       HitlToolWhitelistSaver
+	hitlStrategySaver        HitlAuditStrategySaver
+	hitlDefaultReviewerSaver HitlDefaultReviewerSaver
+	auditLLM           *openai.Client
 	audit              *audit.Service
 }

@@ -190,9 +197,41 @@ func (h *AgentHandler) SetAudit(s *audit.Service) {
 	h.audit = s
 }

-// HitlToolWhitelistSaver 合并 HITL 免审批工具到全局配置并落盘
+// TaskManager 返回 Agent 任务管理器（供 MCP 监控页终止 Eino execute 等）。
+func (h *AgentHandler) TaskManager() *AgentTaskManager {
+	if h == nil {
+		return nil
+	}
+	return h.tasks
+}
+
+// CancelRunningTaskForConversation stops any in-flight agent work for the conversation (idempotent).
+func (h *AgentHandler) CancelRunningTaskForConversation(conversationID string) {
+	if h == nil || conversationID == "" || h.tasks == nil {
+		return
+	}
+	h.cancelActiveMCPToolForConversation(conversationID)
+	h.tasks.AbortActiveEinoExecute(conversationID, "")
+	if ok, err := h.tasks.CancelTask(conversationID, ErrTaskCancelled); ok {
+		h.logger.Info("已取消会话运行中任务", zap.String("conversationId", conversationID))
+	} else if err != nil {
+		h.logger.Warn("取消会话运行中任务失败", zap.String("conversationId", conversationID), zap.Error(err))
+	}
+}
+
+func (h *AgentHandler) cancelActiveMCPToolForConversation(conversationID string) {
+	if h == nil || h.tasks == nil || h.agent == nil {
+		return
+	}
+	if execID := h.tasks.ActiveMCPExecutionID(conversationID); execID != "" {
+		h.agent.CancelMCPToolExecutionWithNote(execID, "")
+	}
+}
+
+// HitlToolWhitelistSaver 合并/设置 HITL 免审批工具到全局配置并落盘
 type HitlToolWhitelistSaver interface {
 	MergeHitlToolWhitelistIntoConfig(add []string) error
+	SetHitlToolWhitelist(tools []string) error
 }

 // NewAgentHandler 创建新的Agent处理器
@@ -208,6 +247,11 @@ func NewAgentHandler(agent *agent.Agent, db *database.DB, cfg *config.Config, lo
 	bus := NewTaskEventBus()
 	tm := NewAgentTaskManager()
 	tm.SetTaskEventBus(bus)
+	llmHTTP := &http.Client{Timeout: 2 * time.Minute}
+	var llmCfg *config.OpenAIConfig
+	if cfg != nil {
+		llmCfg = &cfg.OpenAI
+	}
 	handler := &AgentHandler{
 		agent:            agent,
 		db:               db,
@@ -218,8 +262,9 @@ func NewAgentHandler(agent *agent.Agent, db *database.DB, cfg *config.Config, lo
 		config:           cfg,
 		hitlManager:      NewHITLManager(db, logger),
 		batchCronParser:  cron.NewParser(cron.Minute | cron.Hour | cron.Dom | cron.Month | cron.Dow | cron.Descriptor),
-		batchRunning:     make(map[string]struct{}),
+		auditLLM:         openai.NewClient(llmCfg, llmHTTP, logger),
 	}
+	tm.SetToolCanceler(handler.cancelActiveMCPToolForConversation)
 	if err := handler.hitlManager.EnsureSchema(); err != nil {
 		logger.Warn("初始化 HITL 表失败", zap.Error(err))
 	}
@@ -244,6 +289,23 @@ func (h *AgentHandler) SetHitlToolWhitelistSaver(s HitlToolWhitelistSaver) {
 	h.hitlWhitelistSaver = s
 }

+// HitlDefaultReviewerSaver 持久化全局默认审批方到 config.yaml。
+type HitlDefaultReviewerSaver interface {
+	UpdateHitlDefaultReviewer(reviewer string) error
+}
+
+// SetHitlDefaultReviewerSaver 设置 HITL 默认审批方落盘。
+func (h *AgentHandler) SetHitlDefaultReviewerSaver(s HitlDefaultReviewerSaver) {
+	h.hitlDefaultReviewerSaver = s
+}
+
+func (h *AgentHandler) hitlEffectiveDefaultReviewer() string {
+	if h != nil && h.config != nil {
+		return normalizeHitlReviewer(h.config.Hitl.EffectiveDefaultReviewer())
+	}
+	return "human"
+}
+
 // HITLNeedsToolApproval 供 C2 危险任务门控：与会话侧人机协同及免审批白名单判定一致。
 func (h *AgentHandler) HITLNeedsToolApproval(conversationID, toolName string) bool {
 	if h == nil || h.hitlManager == nil {
@@ -292,6 +354,7 @@ func chatReasoningToClientIntent(r *ChatReasoningRequest) *reasoning.ClientInten
 type HITLRequest struct {
 	Enabled        bool     `json:"enabled"`
 	Mode           string   `json:"mode,omitempty"`
+	Reviewer       string   `json:"reviewer,omitempty"` // human | audit_agent
 	SensitiveTools []string `json:"sensitiveTools,omitempty"`
 	TimeoutSeconds int      `json:"timeoutSeconds,omitempty"`
 }
@@ -631,40 +694,11 @@ func (h *AgentHandler) runRobotEinoSingleWithRetry(
 	assistantMessageID string,
 	taskStatus *string,
 ) (string, string, error) {
-	curHist := history
-	curMsg := finalMessage
-	segmentUserMessage := finalMessage
-	var resultMA *multiagent.RunResult
-	var errMA error
-	var transientRunAttempts int
-	var emptyResponseAttempts int
-	for {
-		resultMA, errMA = multiagent.RunEinoSingleChatModelAgent(
-			taskCtx, h.config, &h.config.MultiAgent, h.agent, h.logger,
-			conversationID, h.conversationProjectID(conversationID), curMsg, curHist, roleTools, progressCallback, nil, h.projectBlackboardBlock(conversationID),
-		)
-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			taskCtx, conversationID, resultMA, errMA, &emptyResponseAttempts,
-			&curHist, &curMsg, segmentUserMessage, progressCallback, nil,
-		)
-		if exhaustedEmpty {
-			errMA = nil
-			break
-		}
-		if handledEmpty {
-			continue
-		}
-		if errMA == nil {
-			transientRunAttempts = 0
-			emptyResponseAttempts = 0
-			break
-		}
-		if handled, _ := h.handleEinoTransientRetryContinue(
-			taskCtx, conversationID, resultMA, errMA, &transientRunAttempts,
-			&curHist, &curMsg, segmentUserMessage, progressCallback, nil,
-		); handled {
-			continue
-		}
+	resultMA, errMA := multiagent.RunEinoSingleChatModelAgent(
+		taskCtx, h.config, &h.config.MultiAgent, h.agent, h.db, h.logger,
+		conversationID, h.conversationProjectID(conversationID), finalMessage, history, roleTools, progressCallback, nil, h.agentSessionContextBlock(conversationID),
+	)
+	if errMA != nil {
 		*taskStatus = "failed"
 		return h.finalizeRobotAgentError(taskCtx, assistantMessageID, conversationID, resultMA, errMA)
 	}
@@ -680,41 +714,12 @@ func (h *AgentHandler) runRobotMultiAgentWithRetry(
 	assistantMessageID string,
 	taskStatus *string,
 ) (string, string, error) {
-	curHist := history
-	curMsg := finalMessage
-	segmentUserMessage := finalMessage
-	var resultMA *multiagent.RunResult
-	var errMA error
-	var transientRunAttempts int
-	var emptyResponseAttempts int
-	for {
-		resultMA, errMA = multiagent.RunDeepAgent(
-			taskCtx, h.config, &h.config.MultiAgent, h.agent, h.logger,
-			conversationID, h.conversationProjectID(conversationID), curMsg, curHist, roleTools, progressCallback,
-			h.agentsMarkdownDir, orchestration, nil, h.projectBlackboardBlock(conversationID),
-		)
-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			taskCtx, conversationID, resultMA, errMA, &emptyResponseAttempts,
-			&curHist, &curMsg, segmentUserMessage, progressCallback, nil,
-		)
-		if exhaustedEmpty {
-			errMA = nil
-			break
-		}
-		if handledEmpty {
-			continue
-		}
-		if errMA == nil {
-			transientRunAttempts = 0
-			emptyResponseAttempts = 0
-			break
-		}
-		if handled, _ := h.handleEinoTransientRetryContinue(
-			taskCtx, conversationID, resultMA, errMA, &transientRunAttempts,
-			&curHist, &curMsg, segmentUserMessage, progressCallback, nil,
-		); handled {
-			continue
-		}
+	resultMA, errMA := multiagent.RunDeepAgent(
+		taskCtx, h.config, &h.config.MultiAgent, h.agent, h.db, h.logger,
+		conversationID, h.conversationProjectID(conversationID), finalMessage, history, roleTools, progressCallback,
+		h.agentsMarkdownDir, orchestration, nil, h.agentSessionContextBlock(conversationID),
+	)
+	if errMA != nil {
 		*taskStatus = "failed"
 		return h.finalizeRobotAgentError(taskCtx, assistantMessageID, conversationID, resultMA, errMA)
 	}
@@ -879,11 +884,6 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun

 	// thinking_stream_*（ReAct 等助手正文流）与 reasoning_chain_stream_*（Eino ReasoningContent）：
 	// 不逐条落库，按 streamId 聚合，flush 时分别落 thinking / reasoning_chain。
-	type thinkingBuf struct {
-		b         strings.Builder
-		meta      map[string]interface{}
-		persistAs string // "thinking" | "reasoning_chain"
-	}
 	thinkingStreams := make(map[string]*thinkingBuf) // streamId -> buf
 	flushedThinking := make(map[string]bool)         // streamId -> flushed
 	seenToolCallSigs := make(map[string]string)      // toolCallId -> payload signature
@@ -896,6 +896,12 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 	// response_start + response_delta：前端时间线显示为「📝 规划中」（monitor.js），不落逐条 delta；
 	// 聚合为一条 planning 写入 process_details，刷新后与线上一致。
 	var respPlan responsePlanAgg
+	if assistantMessageID != "" {
+		h.tasks.SetHitlAssistantMessageID(conversationID, assistantMessageID)
+	}
+	syncHitlCognition := func() {
+		h.syncHitlCognitionFromProgress(conversationID, assistantMessageID, thinkingStreams, &respPlan)
+	}
 	flushResponsePlan := func() {
 		if assistantMessageID == "" {
 			return
@@ -915,6 +921,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 		if err := h.db.AddProcessDetail(assistantMessageID, conversationID, "planning", content, data); err != nil {
 			h.logger.Warn("保存过程详情失败", zap.Error(err), zap.String("eventType", "planning"))
 		}
+		syncHitlCognition()
 		respPlan.meta = nil
 		respPlan.b.Reset()
 	}
@@ -951,6 +958,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 			}
 			flushedThinking[sid] = true
 		}
+		syncHitlCognition()
 	}

 	return func(eventType, message string, data interface{}) {
@@ -1011,6 +1019,25 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 			}
 		}

+		if eventType == "tool_result" {
+			if dataMap, ok := data.(map[string]interface{}); ok {
+				toolName, _ := dataMap["toolName"].(string)
+				toolCallID, _ := dataMap["toolCallId"].(string)
+				success := true
+				if v, ok := dataMap["success"].(bool); ok {
+					success = v
+				}
+				resultText := ""
+				if r, ok := dataMap["result"].(string); ok {
+					resultText = r
+				}
+				if strings.TrimSpace(resultText) == "" {
+					resultText = message
+				}
+				h.recordHitlToolExecutionResult(conversationID, toolCallID, toolName, success, resultText)
+			}
+		}
+
 		// 处理知识检索日志记录
 		if eventType == "tool_result" && h.knowledgeManager != nil {
 			if dataMap, ok := data.(map[string]interface{}); ok {
@@ -1218,6 +1245,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 					respPlan.meta[k] = v
 				}
 			}
+			syncHitlCognition()
 			return
 		}
 		if eventType == "response" {
@@ -1287,6 +1315,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 					}
 				}
 			}
+			syncHitlCognition()
 			return
 		}

@@ -1309,7 +1338,10 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun

 		// 保存过程详情到数据库（排除 response/done；response 正文已在 messages 表）
 		// response_start/response_delta 已聚合为 planning，不落逐条。
+		// [Eino] agent 心跳 progress 仅用于实时进度标题，不落库以免时间线刷屏。
+		skipEinoAgentHeartbeat := eventType == "progress" && strings.HasPrefix(strings.TrimSpace(message), "[Eino] ")
 		if assistantMessageID != "" &&
+			!skipEinoAgentHeartbeat &&
 			eventType != "response" &&
 			eventType != "done" &&
 			eventType != "response_start" &&
@@ -1335,10 +1367,60 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 	}
 }

+// cancelToolContinueAfter 仅终止当前工具调用，不停止整条 Agent 任务（对话「中断并继续」与 MCP 监控终止共用）。
+func (h *AgentHandler) cancelToolContinueAfter(conversationID, preferredExecID, note string) (bool, gin.H) {
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" || h.tasks.GetTask(conversationID) == nil {
+		return false, nil
+	}
+	note = strings.TrimSpace(note)
+	execID := strings.TrimSpace(preferredExecID)
+	if execID == "" {
+		execID = h.tasks.ActiveMCPExecutionID(conversationID)
+	}
+	if execID != "" {
+		if h.agent.CancelMCPToolExecutionWithNote(execID, note) {
+			return true, gin.H{
+				"status":              "tool_abort_requested",
+				"conversationId":      conversationID,
+				"executionId":         execID,
+				"message":             "已请求终止当前工具调用；工具返回后本轮推理将继续（与 MCP 监控页终止一致）。",
+				"continueAfter":       true,
+				"interruptWithNote":   note != "",
+				"continueWithoutTool": false,
+			}
+		}
+		if h.tasks.AbortActiveEinoExecute(conversationID, note) {
+			return true, gin.H{
+				"status":              "tool_abort_requested",
+				"conversationId":      conversationID,
+				"executionId":         execID,
+				"message":             "已请求终止当前 execute 命令；命令返回后本轮推理将继续。",
+				"continueAfter":       true,
+				"interruptWithNote":   note != "",
+				"continueWithoutTool": false,
+			}
+		}
+		return false, nil
+	}
+	if h.tasks.AbortActiveEinoExecute(conversationID, note) {
+		return true, gin.H{
+			"status":              "tool_abort_requested",
+			"conversationId":      conversationID,
+			"message":             "已请求终止当前 execute 命令；命令返回后本轮推理将继续。",
+			"continueAfter":       true,
+			"interruptWithNote":   note != "",
+			"continueWithoutTool": false,
+		}
+	}
+	return false, nil
+}
+
 // CancelAgentLoop 取消正在执行的任务
 func (h *AgentHandler) CancelAgentLoop(c *gin.Context) {
 	var req struct {
 		ConversationID string `json:"conversationId" binding:"required"`
+		ExecutionID    string `json:"executionId,omitempty"`
 		Reason         string `json:"reason,omitempty"`
 		ContinueAfter  bool   `json:"continueAfter,omitempty"`
 	}
@@ -1353,27 +1435,20 @@ func (h *AgentHandler) CancelAgentLoop(c *gin.Context) {
 			c.JSON(http.StatusNotFound, gin.H{"error": "未找到正在执行的任务"})
 			return
 		}
-		execID := h.tasks.ActiveMCPExecutionID(req.ConversationID)
 		note := strings.TrimSpace(req.Reason)
-		if execID != "" {
-			if !h.agent.CancelMCPToolExecutionWithNote(execID, note) {
-				c.JSON(http.StatusNotFound, gin.H{"error": "未找到进行中的工具执行或该调用已结束"})
-				return
-			}
-			h.logger.Info("对话页仅终止当前 MCP 工具",
+		activeExec := strings.TrimSpace(h.tasks.ActiveMCPExecutionID(req.ConversationID))
+		if ok, payload := h.cancelToolContinueAfter(req.ConversationID, strings.TrimSpace(req.ExecutionID), note); ok {
+			execID, _ := payload["executionId"].(string)
+			h.logger.Info("对话页仅终止当前工具",
 				zap.String("conversationId", req.ConversationID),
 				zap.String("executionId", execID),
 				zap.Bool("hasNote", note != ""),
 			)
-			c.JSON(http.StatusOK, gin.H{
-				"status":              "tool_abort_requested",
-				"conversationId":      req.ConversationID,
-				"executionId":         execID,
-				"message":             "已请求终止当前工具调用；工具返回后本轮推理将继续（与 MCP 监控页终止一致）。",
-				"continueAfter":       true,
-				"interruptWithNote":   note != "",
-				"continueWithoutTool": false,
-			})
+			c.JSON(http.StatusOK, payload)
+			return
+		}
+		if activeExec != "" {
+			c.JSON(http.StatusNotFound, gin.H{"error": "未找到进行中的工具执行或该调用已结束"})
 			return
 		}
 		// 无进行中的 MCP 工具（模型纯推理/流式输出阶段）：取消当前上下文并由 Eino 流式处理器合并用户补充后自动续跑。
@@ -1405,6 +1480,8 @@ func (h *AgentHandler) CancelAgentLoop(c *gin.Context) {

 	var cause error = ErrTaskCancelled
 	msg := "已提交取消请求，任务将在当前步骤完成后停止。"
+	h.cancelActiveMCPToolForConversation(req.ConversationID)
+	h.tasks.AbortActiveEinoExecute(req.ConversationID, "")
 	ok, err := h.tasks.CancelTask(req.ConversationID, cause)
 	if err != nil {
 		h.logger.Error("取消任务失败", zap.Error(err))
@@ -1452,6 +1529,10 @@ func (h *AgentHandler) SubscribeAgentTaskEvents(c *gin.Context) {

 	flusher, _ := c.Writer.(http.Flusher)
 	ctx := c.Request.Context()
+	var writeMu sync.Mutex
+	stopKeepalive := make(chan struct{})
+	go sseKeepalive(c, stopKeepalive, &writeMu)
+	defer close(stopKeepalive)

 	for {
 		select {
@@ -1461,27 +1542,64 @@ func (h *AgentHandler) SubscribeAgentTaskEvents(c *gin.Context) {
 			if !ok {
 				return
 			}
+			writeMu.Lock()
 			if _, err := c.Writer.Write(chunk); err != nil {
+				writeMu.Unlock()
 				return
 			}
 			if flusher != nil {
 				flusher.Flush()
 			}
+			writeMu.Unlock()
+		}
+	}
+}
+
+// enrichAgentTasksWithConversationTitles 为任务列表附加当前会话标题（供顶栏/任务页展示，重命名后自动同步）
+func (h *AgentHandler) enrichAgentTasksWithConversationTitles(tasks []*AgentTask) {
+	if h == nil || h.db == nil {
+		return
+	}
+	for _, task := range tasks {
+		if task == nil || strings.TrimSpace(task.ConversationID) == "" {
+			continue
+		}
+		if title, err := h.db.GetConversationTitle(task.ConversationID); err == nil {
+			task.Title = strings.TrimSpace(title)
+		}
+	}
+}
+
+// enrichCompletedTasksWithConversationTitles 为已完成任务附加当前会话标题
+func (h *AgentHandler) enrichCompletedTasksWithConversationTitles(tasks []*CompletedTask) {
+	if h == nil || h.db == nil {
+		return
+	}
+	for _, task := range tasks {
+		if task == nil || strings.TrimSpace(task.ConversationID) == "" {
+			continue
+		}
+		if title, err := h.db.GetConversationTitle(task.ConversationID); err == nil {
+			task.Title = strings.TrimSpace(title)
 		}
 	}
 }

 // ListAgentTasks 列出所有运行中的任务
 func (h *AgentHandler) ListAgentTasks(c *gin.Context) {
+	tasks := h.tasks.GetActiveTasks()
+	h.enrichAgentTasksWithConversationTitles(tasks)
 	c.JSON(http.StatusOK, gin.H{
-		"tasks": h.tasks.GetActiveTasks(),
+		"tasks": tasks,
 	})
 }

 // ListCompletedTasks 列出最近完成的任务历史
 func (h *AgentHandler) ListCompletedTasks(c *gin.Context) {
+	tasks := h.tasks.GetCompletedTasks()
+	h.enrichCompletedTasksWithConversationTitles(tasks)
 	c.JSON(http.StatusOK, gin.H{
-		"tasks": h.tasks.GetCompletedTasks(),
+		"tasks": tasks,
 	})
 }

@@ -1495,6 +1613,7 @@ type BatchTaskRequest struct {
 	CronExpr     string   `json:"cronExpr,omitempty"`       // scheduleMode=cron 时必填
 	ExecuteNow   bool     `json:"executeNow,omitempty"`     // 创建后是否立即执行（默认 false）
 	ProjectID    string   `json:"projectId,omitempty"`      // 队列内子对话绑定的项目（可选）
+	Concurrency  int      `json:"concurrency,omitempty"`    // 同时执行的子任务数，默认 1，最大 8
 }

 // batchQueueWantsEino 队列是否配置为走 Eino 多代理。
@@ -1554,7 +1673,7 @@ func (h *AgentHandler) CreateBatchQueue(c *gin.Context) {
 		nextRunAt = &next
 	}

-	queue, createErr := h.batchTaskManager.CreateBatchQueue(req.Title, req.Role, agentMode, scheduleMode, cronExpr, req.ProjectID, nextRunAt, validTasks)
+	queue, createErr := h.batchTaskManager.CreateBatchQueue(req.Title, req.Role, agentMode, scheduleMode, cronExpr, req.ProjectID, nextRunAt, req.Concurrency, validTasks)
 	if createErr != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": createErr.Error()})
 		return
@@ -1678,6 +1797,7 @@ func (h *AgentHandler) ListBatchQueues(c *gin.Context) {
 // StartBatchQueue 开始执行批量任务队列
 func (h *AgentHandler) StartBatchQueue(c *gin.Context) {
 	queueID := c.Param("queueId")
+	h.batchTaskManager.ClearSingleRunTask(queueID)
 	ok, err := h.startBatchQueueExecution(queueID, false)
 	if err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
@@ -1709,6 +1829,7 @@ func (h *AgentHandler) RerunBatchQueue(c *gin.Context) {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": "重置队列失败"})
 		return
 	}
+	h.batchTaskManager.ClearSingleRunTask(queueID)
 	ok, err := h.startBatchQueueExecution(queueID, false)
 	if err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
@@ -1742,15 +1863,16 @@ func (h *AgentHandler) PauseBatchQueue(c *gin.Context) {
 func (h *AgentHandler) UpdateBatchQueueMetadata(c *gin.Context) {
 	queueID := c.Param("queueId")
 	var req struct {
-		Title     string `json:"title"`
-		Role      string `json:"role"`
-		AgentMode string `json:"agentMode"`
+		Title       string `json:"title"`
+		Role        string `json:"role"`
+		AgentMode   string `json:"agentMode"`
+		Concurrency *int   `json:"concurrency"`
 	}
 	if err := c.ShouldBindJSON(&req); err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	if err := h.batchTaskManager.UpdateQueueMetadata(queueID, req.Title, req.Role, req.AgentMode); err != nil {
+	if err := h.batchTaskManager.UpdateQueueMetadata(queueID, req.Title, req.Role, req.AgentMode, req.Concurrency); err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
@@ -1825,9 +1947,17 @@ func (h *AgentHandler) SetBatchQueueScheduleEnabled(c *gin.Context) {
 // DeleteBatchQueue 删除批量任务队列
 func (h *AgentHandler) DeleteBatchQueue(c *gin.Context) {
 	queueID := c.Param("queueId")
-	success := h.batchTaskManager.DeleteQueue(queueID)
-	if !success {
-		c.JSON(http.StatusNotFound, gin.H{"error": "队列不存在"})
+	if err := h.batchTaskManager.DeleteQueue(queueID); err != nil {
+		switch {
+		case errors.Is(err, ErrBatchQueueNotFound):
+			c.JSON(http.StatusNotFound, gin.H{"error": "队列不存在"})
+		case errors.Is(err, ErrBatchQueueExecutorActive):
+			c.JSON(http.StatusConflict, gin.H{"error": "队列执行器仍在运行，请稍后再删除"})
+		case errors.Is(err, ErrBatchQueueStillRunning):
+			c.JSON(http.StatusConflict, gin.H{"error": "队列正在运行中，无法删除"})
+		default:
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		}
 		return
 	}
 	if h.audit != nil {
@@ -1908,6 +2038,53 @@ func (h *AgentHandler) AddBatchTask(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"message": "任务已添加", "task": task, "queue": queue})
 }

+// RunSingleBatchTask 单条执行指定子任务（可覆盖已成功项），完成后暂停队列
+func (h *AgentHandler) RunSingleBatchTask(c *gin.Context) {
+	queueID := c.Param("queueId")
+	taskID := c.Param("taskId")
+
+	if err := h.batchTaskManager.PrepareSingleTaskRun(queueID, taskID); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	h.batchTaskManager.SetSingleRunTask(queueID, taskID)
+
+	// 暂停态单条执行：旧批量协程可能仍占用执行槽，先回收以便重新启动
+	if queue, ok := h.batchTaskManager.GetBatchQueue(queueID); ok && queue.Status == BatchQueueStatusPaused {
+		h.batchTaskManager.ForceUnmarkQueueExecutor(queueID)
+	}
+
+	autoStarted := true
+	autoStartMsg := "已开始单条执行"
+	ok, startErr := h.startBatchQueueExecution(queueID, false)
+	if startErr != nil {
+		h.batchTaskManager.ClearSingleRunTask(queueID)
+		autoStarted = false
+		autoStartMsg = "任务已准备就绪，但自动启动失败: " + startErr.Error()
+	} else if !ok {
+		h.batchTaskManager.ClearSingleRunTask(queueID)
+		autoStarted = false
+		autoStartMsg = "任务已准备就绪，但队列不存在"
+	}
+
+	queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
+	if !exists {
+		c.JSON(http.StatusNotFound, gin.H{"error": "队列不存在"})
+		return
+	}
+	if h.audit != nil {
+		h.audit.RecordOK(c, "task", "run_single_batch_task", "单条执行批量子任务", "batch_task", taskID, map[string]interface{}{
+			"batch_queue_id": queueID,
+			"auto_started":   autoStarted,
+		})
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"message":     autoStartMsg,
+		"queue":       queue,
+		"autoStarted": autoStarted,
+	})
+}
+
 // DeleteBatchTask 删除批量任务
 func (h *AgentHandler) DeleteBatchTask(c *gin.Context) {
 	queueID := c.Param("queueId")
@@ -1933,22 +2110,6 @@ func (h *AgentHandler) DeleteBatchTask(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"message": "任务已删除", "queue": queue})
 }

-func (h *AgentHandler) markBatchQueueRunning(queueID string) bool {
-	h.batchRunnerMu.Lock()
-	defer h.batchRunnerMu.Unlock()
-	if _, exists := h.batchRunning[queueID]; exists {
-		return false
-	}
-	h.batchRunning[queueID] = struct{}{}
-	return true
-}
-
-func (h *AgentHandler) unmarkBatchQueueRunning(queueID string) {
-	h.batchRunnerMu.Lock()
-	defer h.batchRunnerMu.Unlock()
-	delete(h.batchRunning, queueID)
-}
-
 func (h *AgentHandler) nextBatchQueueRunAt(cronExpr string, from time.Time) (*time.Time, error) {
 	expr := strings.TrimSpace(cronExpr)
 	if expr == "" {
@@ -1964,43 +2125,43 @@ func (h *AgentHandler) nextBatchQueueRunAt(cronExpr string, from time.Time) (*ti

 func (h *AgentHandler) startBatchQueueExecution(queueID string, scheduled bool) (bool, error) {
 	// 先获取执行互斥门，再读取队列状态，避免基于过时快照做判断
-	if !h.markBatchQueueRunning(queueID) {
+	if !h.batchTaskManager.TryMarkQueueExecutor(queueID) {
 		return true, nil
 	}

 	queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
 	if !exists {
-		h.unmarkBatchQueueRunning(queueID)
+		h.batchTaskManager.UnmarkQueueExecutor(queueID)
 		return false, nil
 	}

 	if scheduled {
 		if queue.ScheduleMode != "cron" {
-			h.unmarkBatchQueueRunning(queueID)
+			h.batchTaskManager.UnmarkQueueExecutor(queueID)
 			err := fmt.Errorf("队列未启用 cron 调度")
 			h.batchTaskManager.SetLastScheduleError(queueID, err.Error())
 			return true, err
 		}
 		if queue.Status == "running" || queue.Status == "paused" || queue.Status == "cancelled" {
-			h.unmarkBatchQueueRunning(queueID)
+			h.batchTaskManager.UnmarkQueueExecutor(queueID)
 			err := fmt.Errorf("当前队列状态不允许被调度执行")
 			h.batchTaskManager.SetLastScheduleError(queueID, err.Error())
 			return true, err
 		}
 		if !h.batchTaskManager.ResetQueueForRerun(queueID) {
-			h.unmarkBatchQueueRunning(queueID)
+			h.batchTaskManager.UnmarkQueueExecutor(queueID)
 			err := fmt.Errorf("重置队列失败")
 			h.batchTaskManager.SetLastScheduleError(queueID, err.Error())
 			return true, err
 		}
 		queue, _ = h.batchTaskManager.GetBatchQueue(queueID)
 	} else if queue.Status != "pending" && queue.Status != "paused" {
-		h.unmarkBatchQueueRunning(queueID)
+		h.batchTaskManager.UnmarkQueueExecutor(queueID)
 		return true, fmt.Errorf("队列状态不允许启动")
 	}

 	if queue != nil && batchQueueWantsEino(queue.AgentMode) && (h.config == nil || !h.config.MultiAgent.Enabled) {
-		h.unmarkBatchQueueRunning(queueID)
+		h.batchTaskManager.UnmarkQueueExecutor(queueID)
 		err := fmt.Errorf("当前队列配置为 Eino 多代理，但系统未启用多代理")
 		if scheduled {
 			h.batchTaskManager.SetLastScheduleError(queueID, err.Error())
@@ -2052,314 +2213,6 @@ func (h *AgentHandler) batchQueueSchedulerLoop() {
 	}
 }

-// executeBatchQueue 执行批量任务队列
-func (h *AgentHandler) executeBatchQueue(queueID string) {
-	defer h.unmarkBatchQueueRunning(queueID)
-	h.logger.Info("开始执行批量任务队列", zap.String("queueId", queueID))
-
-	for {
-		// 检查队列状态
-		queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
-		if !exists || queue.Status == "cancelled" || queue.Status == "completed" || queue.Status == "paused" {
-			break
-		}
-
-		// 获取下一个任务
-		task, hasNext := h.batchTaskManager.GetNextTask(queueID)
-		if !hasNext {
-			// 所有任务完成：汇总子任务失败信息便于排障
-			q, ok := h.batchTaskManager.GetBatchQueue(queueID)
-			lastRunErr := ""
-			if ok {
-				for _, t := range q.Tasks {
-					if t.Status == "failed" && t.Error != "" {
-						lastRunErr = t.Error
-					}
-				}
-			}
-			h.batchTaskManager.SetLastRunError(queueID, lastRunErr)
-			h.batchTaskManager.UpdateQueueStatus(queueID, "completed")
-			h.logger.Info("批量任务队列执行完成", zap.String("queueId", queueID))
-			break
-		}
-
-		// 更新任务状态为运行中
-		h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, "running", "", "")
-
-		// 创建新对话
-		title := safeTruncateString(task.Message, 50)
-		batchMeta := audit.ConversationCreateMeta("batch_task")
-		batchMeta.ProjectID = effectiveProjectID(h.config, queue.ProjectID)
-		conv, err := h.db.CreateConversation(title, batchMeta)
-		var conversationID string
-		if err != nil {
-			h.logger.Error("创建对话失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
-			h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, "failed", "", "创建对话失败: "+err.Error())
-			h.batchTaskManager.MoveToNextTask(queueID)
-			continue
-		}
-		conversationID = conv.ID
-
-		// 保存conversationId到任务中（即使是运行中状态也要保存，以便查看对话）
-		h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, "running", "", "", conversationID)
-
-		// 应用角色用户提示词和工具配置
-		finalMessage := task.Message
-		var roleTools []string // 角色配置的工具列表
-		if queue.Role != "" && queue.Role != "默认" {
-			if h.config.Roles != nil {
-				if role, exists := h.config.Roles[queue.Role]; exists && role.Enabled {
-					// 应用用户提示词
-					if role.UserPrompt != "" {
-						finalMessage = role.UserPrompt + "\n\n" + task.Message
-						h.logger.Info("应用角色用户提示词", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("role", queue.Role))
-					}
-					// 获取角色配置的工具列表（优先使用tools字段，向后兼容mcps字段）
-					if len(role.Tools) > 0 {
-						roleTools = role.Tools
-						h.logger.Info("使用角色配置的工具列表", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("role", queue.Role), zap.Int("toolCount", len(roleTools)))
-					}
-				}
-			}
-		}
-
-		// 保存用户消息（保存原始消息，不包含角色提示词）
-		_, err = h.db.AddMessage(conversationID, "user", task.Message, nil)
-		if err != nil {
-			h.logger.Error("保存用户消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
-		}
-
-		// 预先创建助手消息，以便关联过程详情
-		assistantMsg, err := h.db.AddMessage(conversationID, "assistant", "处理中...", nil)
-		if err != nil {
-			h.logger.Error("创建助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
-			// 如果创建失败，继续执行但不保存过程详情
-			assistantMsg = nil
-		}
-
-		// 创建进度回调函数，复用统一逻辑（批量任务不需要流式事件，所以传入nil）
-		var assistantMessageID string
-		if assistantMsg != nil {
-			assistantMessageID = assistantMsg.ID
-		}
-		// 注意：批量任务没有前端直连的 POST /stream，因此若要支持「刷新后补流」，
-		// 需要把进度事件镜像到 TaskEventBus（GET /api/agent-loop/task-events 会订阅这里）。
-		// progressCallback 将在子任务的 IIFE 内创建，以便拿到 taskCtx/cancelWithCause 与 sendEvent。
-		var progressCallback func(eventType, message string, data interface{})
-
-		// 执行任务（使用包含角色提示词的finalMessage和角色工具列表）
-		h.logger.Info("执行批量任务", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("message", task.Message), zap.String("role", queue.Role), zap.String("conversationId", conversationID))
-
-		func() {
-			// 与对话流式接口一致：同 conversationId 仅允许一个运行中任务，并支持 /api/agent-loop/cancel 与会话锁对齐。
-			baseCtx, cancelWithCause := context.WithCancelCause(context.Background())
-			// 单个子任务超时：6 小时（与原先 WithTimeout(Background) 一致）
-			taskCtx, timeoutCancel := context.WithTimeout(baseCtx, 6*time.Hour)
-
-			registered := false
-			finishStatus := "completed"
-
-			defer func() {
-				h.batchTaskManager.SetTaskCancel(queueID, nil)
-				timeoutCancel()
-				if registered {
-					// 与流式接口保持一致：结束前补一个 done，便于前端 task-events 侧及时收口 UI。
-					if h.taskEventBus != nil {
-						ev := StreamEvent{Type: "done", Message: "", Data: map[string]interface{}{"conversationId": conversationID}}
-						if b, err := json.Marshal(ev); err == nil {
-							h.taskEventBus.Publish(conversationID, append(append([]byte("data: "), b...), '\n', '\n'))
-						}
-					}
-					h.tasks.FinishTask(conversationID, finishStatus)
-				}
-				cancelWithCause(nil)
-			}()
-
-			// 事件镜像：只发布到 TaskEventBus，不直接写 HTTP Response（用于刷新后的补流）。
-			sendEvent := func(eventType, message string, data interface{}) {
-				if h.taskEventBus == nil {
-					return
-				}
-				ev := StreamEvent{Type: eventType, Message: message, Data: data}
-				b, err := json.Marshal(ev)
-				if err != nil {
-					b = []byte(`{"type":"error","message":"marshal failed"}`)
-				}
-				line := make([]byte, 0, len(b)+8)
-				line = append(line, []byte("data: ")...)
-				line = append(line, b...)
-				line = append(line, '\n', '\n')
-				h.taskEventBus.Publish(conversationID, line)
-			}
-
-			if _, err := h.tasks.StartTask(conversationID, task.Message, cancelWithCause); err != nil {
-				h.logger.Warn("批量队列子任务注册会话运行状态失败",
-					zap.String("queueId", queueID),
-					zap.String("taskId", task.ID),
-					zap.String("conversationId", conversationID),
-					zap.Error(err))
-				failMsg := err.Error()
-				if errors.Is(err, ErrTaskAlreadyRunning) {
-					failMsg = "会话已有任务正在执行，无法在该会话上并行启动批量子任务"
-				}
-				h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, "failed", "", failMsg)
-				return
-			}
-			registered = true
-			// 存储取消函数：暂停队列时取消子任务 context（与原先语义一致）
-			h.batchTaskManager.SetTaskCancel(queueID, timeoutCancel)
-
-			// 创建进度回调函数：写 DB + 镜像到 task-events，支持刷新后继续流式展示。
-			progressCallback = h.createProgressCallback(taskCtx, cancelWithCause, conversationID, assistantMessageID, sendEvent)
-			taskCtx = mcp.WithMCPConversationID(taskCtx, conversationID)
-			taskCtx = mcp.WithToolRunRegistry(taskCtx, h.tasks)
-
-			// 使用队列配置的角色工具列表（如果为空，表示使用所有工具）
-			useBatchMulti := false
-			batchOrch := "deep"
-			am := strings.TrimSpace(strings.ToLower(queue.AgentMode))
-			if am == "multi" {
-				am = "deep"
-			}
-			if batchQueueWantsEino(queue.AgentMode) && h.config != nil && h.config.MultiAgent.Enabled {
-				useBatchMulti = true
-				batchOrch = config.NormalizeMultiAgentOrchestration(am)
-			} else if queue.AgentMode == "" && h.config != nil && h.config.MultiAgent.Enabled && h.config.MultiAgent.BatchUseMultiAgent {
-				// 兼容历史数据：未配置队列代理模式时，沿用旧的系统级开关
-				useBatchMulti = true
-				batchOrch = "deep"
-			}
-			var resultMA *multiagent.RunResult
-			var runErr error
-			switch {
-			case useBatchMulti:
-				resultMA, runErr = multiagent.RunDeepAgent(taskCtx, h.config, &h.config.MultiAgent, h.agent, h.logger, conversationID, h.conversationProjectID(conversationID), finalMessage, []agent.ChatMessage{}, roleTools, progressCallback, h.agentsMarkdownDir, batchOrch, nil, h.projectBlackboardBlock(conversationID))
-			default:
-				if h.config == nil {
-					runErr = fmt.Errorf("服务器配置未加载")
-				} else {
-					resultMA, runErr = multiagent.RunEinoSingleChatModelAgent(taskCtx, h.config, &h.config.MultiAgent, h.agent, h.logger, conversationID, h.conversationProjectID(conversationID), finalMessage, []agent.ChatMessage{}, roleTools, progressCallback, nil, h.projectBlackboardBlock(conversationID))
-				}
-			}
-
-			if runErr != nil {
-				if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
-					h.persistEinoAgentTraceForResume(conversationID, resultMA)
-				}
-				errStr := runErr.Error()
-				partialResp := ""
-				if resultMA != nil {
-					partialResp = resultMA.Response
-				}
-				isCancelled := errors.Is(context.Cause(baseCtx), ErrTaskCancelled) ||
-					errors.Is(runErr, context.Canceled) ||
-					strings.Contains(strings.ToLower(errStr), "context canceled") ||
-					strings.Contains(strings.ToLower(errStr), "context cancelled") ||
-					(partialResp != "" && (strings.Contains(partialResp, "任务已被取消") || strings.Contains(partialResp, "任务执行中断")))
-				isTimeout := errors.Is(runErr, context.DeadlineExceeded) || errors.Is(context.Cause(taskCtx), context.DeadlineExceeded)
-
-				if isTimeout {
-					finishStatus = "timeout"
-				} else if isCancelled {
-					finishStatus = "cancelled"
-				} else {
-					finishStatus = "failed"
-				}
-
-				if isCancelled {
-				h.logger.Info("批量任务被取消", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
-				cancelMsg := "任务已被用户取消，后续操作已停止。"
-				// 如果执行结果中有更具体的取消消息，使用它
-				if partialResp != "" && (strings.Contains(partialResp, "任务已被取消") || strings.Contains(partialResp, "任务执行中断")) {
-					cancelMsg = partialResp
-				}
-				// 更新助手消息内容
-				if assistantMessageID != "" {
-					if updateErr := h.appendAssistantMessageNotice(assistantMessageID, cancelMsg); updateErr != nil {
-						h.logger.Warn("更新取消后的助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
-					}
-					// 保存取消详情到数据库
-					if err := h.db.AddProcessDetail(assistantMessageID, conversationID, "cancelled", cancelMsg, nil); err != nil {
-						h.logger.Warn("保存取消详情失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
-					}
-				} else {
-					// 如果没有预先创建的助手消息，创建一个新的
-					_, errMsg := h.db.AddMessage(conversationID, "assistant", cancelMsg, nil)
-					if errMsg != nil {
-						h.logger.Warn("保存取消消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(errMsg))
-					}
-				}
-				h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, "cancelled", cancelMsg, "", conversationID)
-			} else {
-				h.logger.Error("批量任务执行失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(runErr))
-				errorMsg := "执行失败: " + runErr.Error()
-				// 更新助手消息内容
-				if assistantMessageID != "" {
-					if _, updateErr := h.db.Exec(
-						"UPDATE messages SET content = ?, updated_at = ? WHERE id = ?",
-						errorMsg,
-						time.Now(), assistantMessageID,
-					); updateErr != nil {
-						h.logger.Warn("更新失败后的助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
-					}
-					// 保存错误详情到数据库
-					if err := h.db.AddProcessDetail(assistantMessageID, conversationID, "error", errorMsg, nil); err != nil {
-						h.logger.Warn("保存错误详情失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
-					}
-				}
-				h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, "failed", "", runErr.Error())
-			}
-		} else {
-			h.logger.Info("批量任务执行成功", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
-
-			resText := resultMA.Response
-			mcpIDs := resultMA.MCPExecutionIDs
-			lastIn := resultMA.LastAgentTraceInput
-			lastOut := resultMA.LastAgentTraceOutput
-
-			// 更新助手消息内容
-			if assistantMessageID != "" {
-				if updateErr := h.db.UpdateAssistantMessageFinalize(assistantMessageID, resText, mcpIDs, multiagent.AggregatedReasoningFromTraceJSON(lastIn)); updateErr != nil {
-					h.logger.Warn("更新助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
-					// 如果更新失败，尝试创建新消息
-					_, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs)
-					if err != nil {
-						h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
-					}
-				}
-			} else {
-				// 如果没有预先创建的助手消息，创建一个新的
-				_, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs)
-				if err != nil {
-					h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
-				}
-			}
-
-			// 保存代理轨迹
-			if lastIn != "" || lastOut != "" {
-				if err := h.db.SaveAgentTrace(conversationID, lastIn, lastOut); err != nil {
-					h.logger.Warn("保存代理轨迹失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
-				} else {
-					h.logger.Info("已保存代理轨迹", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
-				}
-			}
-
-			// 保存结果
-			h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, "completed", resText, "", conversationID)
-		}
-		}()
-
-		// 移动到下一个任务
-		h.batchTaskManager.MoveToNextTask(queueID)
-
-		// 检查是否被取消或暂停
-		queue, _ = h.batchTaskManager.GetBatchQueue(queueID)
-		if queue.Status == "cancelled" || queue.Status == "paused" {
-			break
-		}
-	}
-}
-
 // loadHistoryFromAgentTrace 从库中保存的代理消息轨迹恢复历史（列 last_react_*；含单代理与 Eino）。
 // 逻辑与攻击链一致：优先用已保存的 JSON 消息带 + 最后一轮助手摘要，否则回退消息表。
 func (h *AgentHandler) loadHistoryFromAgentTrace(conversationID string) ([]agent.ChatMessage, error) {
@@ -0,0 +1,352 @@
+package handler
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strings"
+	"sync"
+	"time"
+
+	"cyberstrike-ai/internal/agent"
+	"cyberstrike-ai/internal/audit"
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/mcp"
+	"cyberstrike-ai/internal/multiagent"
+
+	"go.uber.org/zap"
+)
+
+const batchQueueWorkerIdlePoll = 200 * time.Millisecond
+
+// executeBatchQueue 使用并发 worker 池执行批量任务队列。
+func (h *AgentHandler) executeBatchQueue(queueID string) {
+	defer h.batchTaskManager.UnmarkQueueExecutor(queueID)
+
+	queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
+	if !exists {
+		return
+	}
+	concurrency := normalizeBatchQueueConcurrency(queue.Concurrency)
+	h.logger.Info("开始执行批量任务队列", zap.String("queueId", queueID), zap.Int("concurrency", concurrency))
+
+	var wg sync.WaitGroup
+	for i := 0; i < concurrency; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			h.runBatchQueueWorker(queueID)
+		}()
+	}
+	wg.Wait()
+
+	h.tryFinalizeBatchQueue(queueID)
+}
+
+func (h *AgentHandler) runBatchQueueWorker(queueID string) {
+	for {
+		queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
+		if batchQueueExecutionShouldStop(queue, exists) {
+			return
+		}
+
+		task, ok := h.batchTaskManager.ClaimNextPendingTask(queueID)
+		if !ok {
+			if !h.batchTaskManager.HasRunningTasks(queueID) {
+				return
+			}
+			time.Sleep(batchQueueWorkerIdlePoll)
+			continue
+		}
+
+		queue, _ = h.batchTaskManager.GetBatchQueue(queueID)
+		if queue == nil {
+			return
+		}
+
+		h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, BatchTaskStatusRunning, "", "")
+		h.executeOneBatchSubTask(queueID, queue, task)
+
+		if h.batchTaskManager.TakeSingleRunTaskIfMatch(queueID, task.ID) {
+			h.batchTaskManager.UpdateQueueStatus(queueID, BatchQueueStatusPaused)
+			h.logger.Info("单条执行完成，队列已暂停", zap.String("queueId", queueID), zap.String("taskId", task.ID))
+			return
+		}
+
+		queue, exists = h.batchTaskManager.GetBatchQueue(queueID)
+		if batchQueueExecutionShouldStop(queue, exists) {
+			if !exists {
+				h.logger.Warn("批量队列在执行收尾时已不存在，安全退出", zap.String("queueId", queueID))
+			}
+			return
+		}
+	}
+}
+
+func (h *AgentHandler) tryFinalizeBatchQueue(queueID string) {
+	queue, exists := h.batchTaskManager.GetBatchQueue(queueID)
+	if !exists || queue == nil {
+		return
+	}
+	if queue.Status != BatchQueueStatusRunning {
+		return
+	}
+	if h.batchTaskManager.HasPendingOrRunningTasks(queueID) {
+		return
+	}
+
+	lastRunErr := ""
+	for _, t := range queue.Tasks {
+		if t != nil && t.Status == BatchTaskStatusFailed && t.Error != "" {
+			lastRunErr = t.Error
+		}
+	}
+	h.batchTaskManager.SetLastRunError(queueID, lastRunErr)
+	h.batchTaskManager.UpdateQueueStatus(queueID, BatchQueueStatusCompleted)
+	h.logger.Info("批量任务队列执行完成", zap.String("queueId", queueID))
+}
+
+// executeOneBatchSubTask 执行单条批量子任务（各自独立会话）。
+func (h *AgentHandler) executeOneBatchSubTask(queueID string, queue *BatchTaskQueue, task *BatchTask) {
+	title := safeTruncateString(task.Message, 50)
+	batchMeta := audit.ConversationCreateMeta("batch_task")
+	batchMeta.ProjectID = effectiveProjectID(h.config, queue.ProjectID)
+	conv, err := h.db.CreateConversation(title, batchMeta)
+	if err != nil {
+		h.logger.Error("创建对话失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
+		h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, BatchTaskStatusFailed, "", "创建对话失败: "+err.Error())
+		return
+	}
+	conversationID := conv.ID
+
+	h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, BatchTaskStatusRunning, "", "", conversationID)
+
+	finalMessage := task.Message
+	var roleTools []string
+	if queue.Role != "" && queue.Role != "默认" {
+		if h.config.Roles != nil {
+			if role, exists := h.config.Roles[queue.Role]; exists && role.Enabled {
+				if role.UserPrompt != "" {
+					finalMessage = role.UserPrompt + "\n\n" + task.Message
+					h.logger.Info("应用角色用户提示词", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("role", queue.Role))
+				}
+				if len(role.Tools) > 0 {
+					roleTools = role.Tools
+					h.logger.Info("使用角色配置的工具列表", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("role", queue.Role), zap.Int("toolCount", len(roleTools)))
+				}
+			}
+		}
+	}
+
+	if _, err = h.db.AddMessage(conversationID, "user", task.Message, nil); err != nil {
+		h.logger.Error("保存用户消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
+	}
+
+	assistantMsg, err := h.db.AddMessage(conversationID, "assistant", "处理中...", nil)
+	if err != nil {
+		h.logger.Error("创建助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
+		assistantMsg = nil
+	}
+
+	var assistantMessageID string
+	if assistantMsg != nil {
+		assistantMessageID = assistantMsg.ID
+	}
+
+	h.logger.Info("执行批量任务", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("message", task.Message), zap.String("role", queue.Role), zap.String("conversationId", conversationID))
+
+	baseCtx, cancelWithCause := context.WithCancelCause(context.Background())
+	taskCtx, timeoutCancel := context.WithTimeout(baseCtx, 6*time.Hour)
+
+	registered := false
+	finishStatus := "completed"
+
+	defer func() {
+		h.batchTaskManager.SetTaskCancel(queueID, task.ID, nil)
+		timeoutCancel()
+		if registered {
+			if h.taskEventBus != nil {
+				ev := StreamEvent{Type: "done", Message: "", Data: map[string]interface{}{"conversationId": conversationID}}
+				if b, err := json.Marshal(ev); err == nil {
+					h.taskEventBus.Publish(conversationID, append(append([]byte("data: "), b...), '\n', '\n'))
+				}
+			}
+			h.tasks.FinishTask(conversationID, finishStatus)
+		}
+		cancelWithCause(nil)
+	}()
+
+	sendEvent := func(eventType, message string, data interface{}) {
+		if h.taskEventBus == nil {
+			return
+		}
+		ev := StreamEvent{Type: eventType, Message: message, Data: data}
+		b, err := json.Marshal(ev)
+		if err != nil {
+			b = []byte(`{"type":"error","message":"marshal failed"}`)
+		}
+		line := make([]byte, 0, len(b)+8)
+		line = append(line, []byte("data: ")...)
+		line = append(line, b...)
+		line = append(line, '\n', '\n')
+		h.taskEventBus.Publish(conversationID, line)
+	}
+
+	if _, err := h.tasks.StartTask(conversationID, task.Message, cancelWithCause); err != nil {
+		h.logger.Warn("批量队列子任务注册会话运行状态失败",
+			zap.String("queueId", queueID),
+			zap.String("taskId", task.ID),
+			zap.String("conversationId", conversationID),
+			zap.Error(err))
+		failMsg := err.Error()
+		if errors.Is(err, ErrTaskAlreadyRunning) {
+			failMsg = "会话已有任务正在执行，无法在该会话上并行启动批量子任务"
+		}
+		h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, BatchTaskStatusFailed, "", failMsg)
+		return
+	}
+	registered = true
+	h.batchTaskManager.SetTaskCancel(queueID, task.ID, timeoutCancel)
+
+	progressCallback := h.createProgressCallback(taskCtx, cancelWithCause, conversationID, assistantMessageID, sendEvent)
+	taskCtx = mcp.WithMCPConversationID(taskCtx, conversationID)
+	taskCtx = mcp.WithToolRunRegistry(taskCtx, h.tasks)
+	taskCtx = mcp.WithEinoExecuteRunRegistry(taskCtx, h.tasks)
+
+	useBatchMulti := false
+	batchOrch := "deep"
+	am := strings.TrimSpace(strings.ToLower(queue.AgentMode))
+	if am == "multi" {
+		am = "deep"
+	}
+	if batchQueueWantsEino(queue.AgentMode) && h.config != nil && h.config.MultiAgent.Enabled {
+		useBatchMulti = true
+		batchOrch = config.NormalizeMultiAgentOrchestration(am)
+	} else if queue.AgentMode == "" && h.config != nil && h.config.MultiAgent.Enabled && h.config.MultiAgent.BatchUseMultiAgent {
+		useBatchMulti = true
+		batchOrch = "deep"
+	}
+
+	var resultMA *multiagent.RunResult
+	var runErr error
+	switch {
+	case useBatchMulti:
+		resultMA, runErr = multiagent.RunDeepAgent(taskCtx, h.config, &h.config.MultiAgent, h.agent, h.db, h.logger, conversationID, h.conversationProjectID(conversationID), finalMessage, []agent.ChatMessage{}, roleTools, progressCallback, h.agentsMarkdownDir, batchOrch, nil, h.agentSessionContextBlock(conversationID))
+	default:
+		if h.config == nil {
+			runErr = fmt.Errorf("服务器配置未加载")
+		} else {
+			resultMA, runErr = multiagent.RunEinoSingleChatModelAgent(taskCtx, h.config, &h.config.MultiAgent, h.agent, h.db, h.logger, conversationID, h.conversationProjectID(conversationID), finalMessage, []agent.ChatMessage{}, roleTools, progressCallback, nil, h.agentSessionContextBlock(conversationID))
+		}
+	}
+
+	if runErr != nil {
+		h.handleBatchSubTaskRunError(queueID, task, conversationID, assistantMessageID, baseCtx, taskCtx, resultMA, runErr, &finishStatus)
+		return
+	}
+
+	if resultMA == nil {
+		h.logger.Error("批量任务执行成功但无结果对象",
+			zap.String("queueId", queueID),
+			zap.String("taskId", task.ID),
+			zap.String("conversationId", conversationID))
+		h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, BatchTaskStatusFailed, "", "内部错误：无执行结果")
+		return
+	}
+
+	h.logger.Info("批量任务执行成功", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
+
+	resText := resultMA.Response
+	mcpIDs := resultMA.MCPExecutionIDs
+	lastIn := resultMA.LastAgentTraceInput
+	lastOut := resultMA.LastAgentTraceOutput
+
+	if assistantMessageID != "" {
+		if updateErr := h.db.UpdateAssistantMessageFinalize(assistantMessageID, resText, mcpIDs, multiagent.AggregatedReasoningFromTraceJSON(lastIn)); updateErr != nil {
+			h.logger.Warn("更新助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
+			if _, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs); err != nil {
+				h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
+			}
+		}
+	} else if _, err = h.db.AddMessage(conversationID, "assistant", resText, mcpIDs); err != nil {
+		h.logger.Error("保存助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(err))
+	}
+
+	if lastIn != "" || lastOut != "" {
+		if err := h.db.SaveAgentTrace(conversationID, lastIn, lastOut); err != nil {
+			h.logger.Warn("保存代理轨迹失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
+		}
+	}
+
+	h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, BatchTaskStatusCompleted, resText, "", conversationID)
+}
+
+func (h *AgentHandler) handleBatchSubTaskRunError(
+	queueID string,
+	task *BatchTask,
+	conversationID, assistantMessageID string,
+	baseCtx, taskCtx context.Context,
+	resultMA *multiagent.RunResult,
+	runErr error,
+	finishStatus *string,
+) {
+	if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
+		h.persistEinoAgentTraceForResume(conversationID, resultMA)
+	}
+	errStr := runErr.Error()
+	partialResp := ""
+	if resultMA != nil {
+		partialResp = resultMA.Response
+	}
+	isCancelled := errors.Is(context.Cause(baseCtx), ErrTaskCancelled) ||
+		errors.Is(runErr, context.Canceled) ||
+		strings.Contains(strings.ToLower(errStr), "context canceled") ||
+		strings.Contains(strings.ToLower(errStr), "context cancelled") ||
+		(partialResp != "" && (strings.Contains(partialResp, "任务已被取消") || strings.Contains(partialResp, "任务执行中断")))
+	isTimeout := errors.Is(runErr, context.DeadlineExceeded) || errors.Is(context.Cause(taskCtx), context.DeadlineExceeded)
+
+	if isTimeout {
+		*finishStatus = "timeout"
+	} else if isCancelled {
+		*finishStatus = "cancelled"
+	} else {
+		*finishStatus = "failed"
+	}
+
+	if isCancelled {
+		h.logger.Info("批量任务被取消", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID))
+		cancelMsg := "任务已被用户取消，后续操作已停止。"
+		if partialResp != "" && (strings.Contains(partialResp, "任务已被取消") || strings.Contains(partialResp, "任务执行中断")) {
+			cancelMsg = partialResp
+		}
+		if assistantMessageID != "" {
+			if updateErr := h.appendAssistantMessageNotice(assistantMessageID, cancelMsg); updateErr != nil {
+				h.logger.Warn("更新取消后的助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
+			}
+			if err := h.db.AddProcessDetail(assistantMessageID, conversationID, "cancelled", cancelMsg, nil); err != nil {
+				h.logger.Warn("保存取消详情失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
+			}
+		} else if _, errMsg := h.db.AddMessage(conversationID, "assistant", cancelMsg, nil); errMsg != nil {
+			h.logger.Warn("保存取消消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(errMsg))
+		}
+		h.batchTaskManager.UpdateTaskStatusWithConversationID(queueID, task.ID, BatchTaskStatusCancelled, cancelMsg, "", conversationID)
+		return
+	}
+
+	h.logger.Error("批量任务执行失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.String("conversationId", conversationID), zap.Error(runErr))
+	errorMsg := "执行失败: " + runErr.Error()
+	if assistantMessageID != "" {
+		if _, updateErr := h.db.Exec(
+			"UPDATE messages SET content = ?, updated_at = ? WHERE id = ?",
+			errorMsg,
+			time.Now(), assistantMessageID,
+		); updateErr != nil {
+			h.logger.Warn("更新失败后的助手消息失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(updateErr))
+		}
+		if err := h.db.AddProcessDetail(assistantMessageID, conversationID, "error", errorMsg, nil); err != nil {
+			h.logger.Warn("保存错误详情失败", zap.String("queueId", queueID), zap.String("taskId", task.ID), zap.Error(err))
+		}
+	}
+	h.batchTaskManager.UpdateTaskStatus(queueID, task.ID, BatchTaskStatusFailed, "", runErr.Error())
+}
@@ -4,6 +4,7 @@ import (
 	"context"
 	"crypto/rand"
 	"encoding/hex"
+	"errors"
 	"fmt"
 	"sort"
 	"strings"
@@ -17,6 +18,15 @@ import (
 	"go.uber.org/zap"
 )

+var (
+	// ErrBatchQueueNotFound 队列不存在或已从内存卸载。
+	ErrBatchQueueNotFound = errors.New("batch queue not found")
+	// ErrBatchQueueExecutorActive executeBatchQueue 协程仍在收尾，禁止删除。
+	ErrBatchQueueExecutorActive = errors.New("batch queue executor is still active")
+	// ErrBatchQueueStillRunning 队列状态仍为 running（无活跃执行器时的兜底保护）。
+	ErrBatchQueueStillRunning = errors.New("batch queue is still running")
+)
+
 // 批量任务状态常量
 const (
 	BatchQueueStatusPending   = "pending"
@@ -39,6 +49,12 @@ const (

 	// MaxBatchQueueRoleLen 角色名最大长度
 	MaxBatchQueueRoleLen = 100
+
+	// DefaultBatchQueueConcurrency 批量队列默认并发数（串行）
+	DefaultBatchQueueConcurrency = 1
+
+	// MaxBatchQueueConcurrency 批量队列最大并发数
+	MaxBatchQueueConcurrency = 8
 )

 // BatchTask 批量任务项
@@ -67,6 +83,7 @@ type BatchTaskQueue struct {
 	LastScheduleError     string       `json:"lastScheduleError,omitempty"`
 	LastRunError          string       `json:"lastRunError,omitempty"`
 	ProjectID             string       `json:"projectId,omitempty"`
+	Concurrency           int          `json:"concurrency"` // 同时执行的子任务数，默认 1
 	Tasks                 []*BatchTask `json:"tasks"`
 	Status                string       `json:"status"` // pending, running, paused, completed, cancelled
 	CreatedAt             time.Time    `json:"createdAt"`
@@ -77,11 +94,13 @@ type BatchTaskQueue struct {

 // BatchTaskManager 批量任务管理器
 type BatchTaskManager struct {
-	db          *database.DB
-	logger      *zap.Logger
-	queues      map[string]*BatchTaskQueue
-	taskCancels map[string]context.CancelFunc // 存储每个队列当前任务的取消函数
-	mu          sync.RWMutex
+	db             *database.DB
+	logger         *zap.Logger
+	queues         map[string]*BatchTaskQueue
+	taskCancels    map[string]map[string]context.CancelFunc // queueID -> taskID -> 取消函数
+	singleRunTasks map[string]string             // queueID -> taskID，单条执行完成后暂停队列
+	queueExecutors map[string]struct{}           // executeBatchQueue 协程活跃标记（与队列 status 解耦）
+	mu             sync.RWMutex
 }

 // NewBatchTaskManager 创建批量任务管理器
@@ -90,12 +109,58 @@ func NewBatchTaskManager(logger *zap.Logger) *BatchTaskManager {
 		logger = zap.NewNop()
 	}
 	return &BatchTaskManager{
-		logger:      logger,
-		queues:      make(map[string]*BatchTaskQueue),
-		taskCancels: make(map[string]context.CancelFunc),
+		logger:         logger,
+		queues:         make(map[string]*BatchTaskQueue),
+		taskCancels:    make(map[string]map[string]context.CancelFunc),
+		singleRunTasks: make(map[string]string),
+		queueExecutors: make(map[string]struct{}),
 	}
 }

+// batchQueueExecutionShouldStop 判断 executeBatchQueue 主循环是否应退出。
+func batchQueueExecutionShouldStop(queue *BatchTaskQueue, exists bool) bool {
+	if !exists || queue == nil {
+		return true
+	}
+	switch queue.Status {
+	case BatchQueueStatusCancelled, BatchQueueStatusCompleted, BatchQueueStatusPaused:
+		return true
+	default:
+		return false
+	}
+}
+
+// TryMarkQueueExecutor 标记队列执行协程已启动；若已有执行协程则返回 false。
+func (m *BatchTaskManager) TryMarkQueueExecutor(queueID string) bool {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if _, exists := m.queueExecutors[queueID]; exists {
+		return false
+	}
+	m.queueExecutors[queueID] = struct{}{}
+	return true
+}
+
+// UnmarkQueueExecutor 清除队列执行协程标记（executeBatchQueue defer 调用）。
+func (m *BatchTaskManager) UnmarkQueueExecutor(queueID string) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	delete(m.queueExecutors, queueID)
+}
+
+// ForceUnmarkQueueExecutor 强制清除执行协程标记（暂停态单条重跑等场景回收陈旧槽位）。
+func (m *BatchTaskManager) ForceUnmarkQueueExecutor(queueID string) {
+	m.UnmarkQueueExecutor(queueID)
+}
+
+// IsQueueExecutorActive 队列 executeBatchQueue 协程是否仍在运行。
+func (m *BatchTaskManager) IsQueueExecutorActive(queueID string) bool {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	_, ok := m.queueExecutors[queueID]
+	return ok
+}
+
 // SetDB 设置数据库连接
 func (m *BatchTaskManager) SetDB(db *database.DB) {
 	m.mu.Lock()
@@ -103,10 +168,22 @@ func (m *BatchTaskManager) SetDB(db *database.DB) {
 	m.db = db
 }

+// normalizeBatchQueueConcurrency 规范化队列并发数。
+func normalizeBatchQueueConcurrency(n int) int {
+	if n < 1 {
+		return DefaultBatchQueueConcurrency
+	}
+	if n > MaxBatchQueueConcurrency {
+		return MaxBatchQueueConcurrency
+	}
+	return n
+}
+
 // CreateBatchQueue 创建批量任务队列
 func (m *BatchTaskManager) CreateBatchQueue(
 	title, role, agentMode, scheduleMode, cronExpr, projectID string,
 	nextRunAt *time.Time,
+	concurrency int,
 	tasks []string,
 ) (*BatchTaskQueue, error) {
 	// 输入校验
@@ -134,6 +211,7 @@ func (m *BatchTaskManager) CreateBatchQueue(
 		CronExpr:        strings.TrimSpace(cronExpr),
 		NextRunAt:       nextRunAt,
 		ScheduleEnabled: true,
+		Concurrency:     normalizeBatchQueueConcurrency(concurrency),
 		Tasks:           make([]*BatchTask, 0, len(tasks)),
 		Status:          BatchQueueStatusPending,
 		CreatedAt:       time.Now(),
@@ -175,6 +253,7 @@ func (m *BatchTaskManager) CreateBatchQueue(
 			queue.CronExpr,
 			queue.NextRunAt,
 			queue.ProjectID,
+			queue.Concurrency,
 			dbTasks,
 		); err != nil {
 			m.logger.Warn("batch queue DB create failed", zap.String("queueId", queueID), zap.Error(err))
@@ -270,6 +349,7 @@ func (m *BatchTaskManager) loadQueueFromDB(queueID string) *BatchTaskQueue {
 	if queueRow.ProjectID.Valid {
 		queue.ProjectID = strings.TrimSpace(queueRow.ProjectID.String)
 	}
+	queue.Concurrency = batchQueueConcurrencyFromRow(queueRow)
 	if queueRow.StartedAt.Valid {
 		queue.StartedAt = &queueRow.StartedAt.Time
 	}
@@ -509,6 +589,7 @@ func (m *BatchTaskManager) LoadFromDB() error {
 		if queueRow.ProjectID.Valid {
 			queue.ProjectID = strings.TrimSpace(queueRow.ProjectID.String)
 		}
+		queue.Concurrency = batchQueueConcurrencyFromRow(queueRow)
 		if queueRow.StartedAt.Valid {
 			queue.StartedAt = &queueRow.StartedAt.Time
 		}
@@ -649,8 +730,16 @@ func (m *BatchTaskManager) UpdateQueueSchedule(queueID, scheduleMode, cronExpr s
 	}
 }

-// UpdateQueueMetadata 更新队列标题、角色和代理模式（非 running 时可用）
-func (m *BatchTaskManager) UpdateQueueMetadata(queueID, title, role, agentMode string) error {
+// batchQueueConcurrencyFromRow 从数据库行读取并发数（缺省为 1）。
+func batchQueueConcurrencyFromRow(row *database.BatchTaskQueueRow) int {
+	if row == nil || !row.Concurrency.Valid {
+		return DefaultBatchQueueConcurrency
+	}
+	return normalizeBatchQueueConcurrency(int(row.Concurrency.Int64))
+}
+
+// UpdateQueueMetadata 更新队列标题、角色、代理模式和并发数（非 running 时可用）
+func (m *BatchTaskManager) UpdateQueueMetadata(queueID, title, role, agentMode string, concurrency *int) error {
 	if utf8.RuneCountInString(title) > MaxBatchQueueTitleLen {
 		return fmt.Errorf("标题不能超过 %d 个字符", MaxBatchQueueTitleLen)
 	}
@@ -678,9 +767,12 @@ func (m *BatchTaskManager) UpdateQueueMetadata(queueID, title, role, agentMode s
 	queue.Title = title
 	queue.Role = role
 	queue.AgentMode = agentMode
+	if concurrency != nil {
+		queue.Concurrency = normalizeBatchQueueConcurrency(*concurrency)
+	}

 	if m.db != nil {
-		if err := m.db.UpdateBatchQueueMetadata(queueID, title, role, agentMode); err != nil {
+		if err := m.db.UpdateBatchQueueMetadata(queueID, title, role, agentMode, queue.Concurrency); err != nil {
 			m.logger.Warn("batch queue DB metadata update failed", zap.String("queueId", queueID), zap.Error(err))
 		}
 	}
@@ -864,6 +956,137 @@ func (m *BatchTaskManager) AddTaskToQueue(queueID, message string) (*BatchTask,
 	return task, nil
 }

+// PrepareSingleTaskRun 准备单条执行：重置目标任务（若已有结果）并定位队列索引
+func (m *BatchTaskManager) PrepareSingleTaskRun(queueID, taskID string) error {
+	var siblingRunningIDs []string
+
+	m.mu.Lock()
+	queue, exists := m.queues[queueID]
+	if !exists {
+		m.mu.Unlock()
+		return fmt.Errorf("队列不存在")
+	}
+
+	var task *BatchTask
+	taskIndex := -1
+	for i, t := range queue.Tasks {
+		if t.ID == taskID {
+			taskIndex = i
+			task = t
+			break
+		}
+	}
+	if task == nil {
+		m.mu.Unlock()
+		return fmt.Errorf("任务不存在")
+	}
+
+	if !queueAllowsSingleTaskRunLocked(queue, task) {
+		m.mu.Unlock()
+		return fmt.Errorf("队列正在执行或未就绪，无法单条执行")
+	}
+
+	// 暂停态：中止在途子任务并收口仍标记 running 的其它子任务，以便单条执行非冲突项
+	var cancelFuncs []context.CancelFunc
+	if queue.Status == BatchQueueStatusPaused {
+		cancelFuncs = m.drainTaskCancelsLocked(queueID)
+		for _, t := range queue.Tasks {
+			if t != nil && t.ID != taskID && t.Status == BatchTaskStatusRunning {
+				siblingRunningIDs = append(siblingRunningIDs, t.ID)
+			}
+		}
+	}
+
+	needsReset := task.Status != BatchTaskStatusPending
+	resumeQueue := queue.Status == BatchQueueStatusCompleted || queue.Status == BatchQueueStatusCancelled
+	m.mu.Unlock()
+
+	for _, c := range cancelFuncs {
+		if c != nil {
+			c()
+		}
+	}
+	const staleRunMsg = "为单条执行其它任务，已中止"
+	for _, sid := range siblingRunningIDs {
+		m.UpdateTaskStatus(queueID, sid, BatchTaskStatusCancelled, "", staleRunMsg)
+	}
+
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	queue, exists = m.queues[queueID]
+	if !exists {
+		return fmt.Errorf("队列不存在")
+	}
+
+	task = nil
+	taskIndex = -1
+	for i, t := range queue.Tasks {
+		if t.ID == taskID {
+			taskIndex = i
+			task = t
+			break
+		}
+	}
+	if task == nil {
+		return fmt.Errorf("任务不存在")
+	}
+
+	if m.db != nil {
+		if err := m.db.PrepareBatchSingleTaskRun(queueID, taskID, taskIndex, needsReset, resumeQueue); err != nil {
+			return fmt.Errorf("准备单条执行失败: %w", err)
+		}
+	}
+
+	if needsReset {
+		task.Status = BatchTaskStatusPending
+		task.ConversationID = ""
+		task.StartedAt = nil
+		task.CompletedAt = nil
+		task.Error = ""
+		task.Result = ""
+	}
+	queue.CurrentIndex = taskIndex
+	queue.LastRunError = ""
+	if resumeQueue {
+		queue.Status = BatchQueueStatusPaused
+		queue.CompletedAt = nil
+	}
+
+	return nil
+}
+
+// SetSingleRunTask 标记队列仅执行指定子任务，完成后自动暂停
+func (m *BatchTaskManager) SetSingleRunTask(queueID, taskID string) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if m.singleRunTasks == nil {
+		m.singleRunTasks = make(map[string]string)
+	}
+	m.singleRunTasks[queueID] = taskID
+}
+
+// ClearSingleRunTask 清除单条执行标记
+func (m *BatchTaskManager) ClearSingleRunTask(queueID string) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	delete(m.singleRunTasks, queueID)
+}
+
+// TakeSingleRunTaskIfMatch 若刚完成的子任务为单条执行目标，则清除标记并返回 true
+func (m *BatchTaskManager) TakeSingleRunTaskIfMatch(queueID, taskID string) bool {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if m.singleRunTasks == nil {
+		return false
+	}
+	if m.singleRunTasks[queueID] != taskID {
+		return false
+	}
+	delete(m.singleRunTasks, queueID)
+	return true
+}
+
 // DeleteTask 删除任务（队列空闲时可删；执行中任务不可删）
 func (m *BatchTaskManager) DeleteTask(queueID, taskID string) error {
 	m.mu.Lock()
@@ -936,7 +1159,109 @@ func queueAllowsTaskListMutationLocked(queue *BatchTaskQueue) bool {
 	}
 }

-// GetNextTask 获取下一个待执行的任务
+// queueAllowsSingleTaskRunLocked 是否允许对指定子任务发起单条执行（必须在持有 BatchTaskManager.mu 下调用）
+func queueAllowsSingleTaskRunLocked(queue *BatchTaskQueue, task *BatchTask) bool {
+	if queue == nil || task == nil {
+		return false
+	}
+	if task.Status == BatchTaskStatusRunning {
+		return false
+	}
+	if queue.Status == BatchQueueStatusRunning {
+		return false
+	}
+	switch queue.Status {
+	case BatchQueueStatusPending, BatchQueueStatusPaused, BatchQueueStatusCompleted, BatchQueueStatusCancelled:
+		return true
+	default:
+		return false
+	}
+}
+
+// ClaimNextPendingTask 原子领取下一个待执行子任务（并发 worker 安全）。
+func (m *BatchTaskManager) ClaimNextPendingTask(queueID string) (*BatchTask, bool) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	queue, exists := m.queues[queueID]
+	if !exists || queue == nil {
+		return nil, false
+	}
+	if queue.Status == BatchQueueStatusCancelled || queue.Status == BatchQueueStatusCompleted || queue.Status == BatchQueueStatusPaused {
+		return nil, false
+	}
+
+	onlyTaskID := ""
+	if m.singleRunTasks != nil {
+		onlyTaskID = m.singleRunTasks[queueID]
+	}
+
+	for i, task := range queue.Tasks {
+		if task == nil || task.Status != BatchTaskStatusPending {
+			continue
+		}
+		if onlyTaskID != "" && task.ID != onlyTaskID {
+			continue
+		}
+		task.Status = BatchTaskStatusRunning
+		queue.CurrentIndex = i
+		return task, true
+	}
+	return nil, false
+}
+
+// HasRunningTasks 队列是否仍有 running 状态的子任务。
+func (m *BatchTaskManager) HasRunningTasks(queueID string) bool {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	queue, exists := m.queues[queueID]
+	if !exists || queue == nil {
+		return false
+	}
+	for _, task := range queue.Tasks {
+		if task != nil && task.Status == BatchTaskStatusRunning {
+			return true
+		}
+	}
+	return false
+}
+
+// HasPendingOrRunningTasks 队列是否仍有未完成的子任务。
+func (m *BatchTaskManager) HasPendingOrRunningTasks(queueID string) bool {
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	queue, exists := m.queues[queueID]
+	if !exists || queue == nil {
+		return false
+	}
+	for _, task := range queue.Tasks {
+		if task == nil {
+			continue
+		}
+		if task.Status == BatchTaskStatusPending || task.Status == BatchTaskStatusRunning {
+			return true
+		}
+	}
+	return false
+}
+
+// drainTaskCancelsLocked 取出并清空队列下所有子任务取消函数（调用方须已持 m.mu）。
+func (m *BatchTaskManager) drainTaskCancelsLocked(queueID string) []context.CancelFunc {
+	taskMap, ok := m.taskCancels[queueID]
+	if !ok || len(taskMap) == 0 {
+		return nil
+	}
+	cancels := make([]context.CancelFunc, 0, len(taskMap))
+	for _, c := range taskMap {
+		if c != nil {
+			cancels = append(cancels, c)
+		}
+	}
+	delete(m.taskCancels, queueID)
+	return cancels
+}
+
+// GetNextTask 获取下一个待执行的任务（串行兼容，优先使用 ClaimNextPendingTask）
 func (m *BatchTaskManager) GetNextTask(queueID string) (*BatchTask, bool) {
 	m.mu.Lock()
 	defer m.mu.Unlock()
@@ -977,20 +1302,28 @@ func (m *BatchTaskManager) MoveToNextTask(queueID string) {
 	}
 }

-// SetTaskCancel 设置当前任务的取消函数
-func (m *BatchTaskManager) SetTaskCancel(queueID string, cancel context.CancelFunc) {
+// SetTaskCancel 设置子任务的取消函数
+func (m *BatchTaskManager) SetTaskCancel(queueID, taskID string, cancel context.CancelFunc) {
 	m.mu.Lock()
 	defer m.mu.Unlock()
-	if cancel != nil {
-		m.taskCancels[queueID] = cancel
-	} else {
-		delete(m.taskCancels, queueID)
+	if cancel == nil {
+		if taskMap, ok := m.taskCancels[queueID]; ok {
+			delete(taskMap, taskID)
+			if len(taskMap) == 0 {
+				delete(m.taskCancels, queueID)
+			}
+		}
+		return
 	}
+	if m.taskCancels[queueID] == nil {
+		m.taskCancels[queueID] = make(map[string]context.CancelFunc)
+	}
+	m.taskCancels[queueID][taskID] = cancel
 }

 // PauseQueue 暂停队列
 func (m *BatchTaskManager) PauseQueue(queueID string) bool {
-	var cancelFunc context.CancelFunc
+	var cancelFuncs []context.CancelFunc

 	m.mu.Lock()
 	queue, exists := m.queues[queueID]
@@ -1015,17 +1348,11 @@ func (m *BatchTaskManager) PauseQueue(queueID string) bool {
 	}

 	queue.Status = BatchQueueStatusPaused
-
-	// 取消当前正在执行的任务（通过取消context）
-	if cancel, ok := m.taskCancels[queueID]; ok {
-		cancelFunc = cancel
-		delete(m.taskCancels, queueID)
-	}
+	cancelFuncs = m.drainTaskCancelsLocked(queueID)
 	m.mu.Unlock()

-	// 释放锁后执行取消回调（cancel 可能阻塞，不应持锁）
-	if cancelFunc != nil {
-		cancelFunc()
+	for _, c := range cancelFuncs {
+		c()
 	}

 	return true
@@ -1034,7 +1361,7 @@ func (m *BatchTaskManager) PauseQueue(queueID string) bool {
 // CancelQueue 取消队列（保留此方法以保持向后兼容，但建议使用PauseQueue）
 func (m *BatchTaskManager) CancelQueue(queueID string) bool {
 	now := time.Now()
-	var cancelFunc context.CancelFunc
+	var cancelFuncs []context.CancelFunc

 	m.mu.Lock()
 	queue, exists := m.queues[queueID]
@@ -1075,34 +1402,33 @@ func (m *BatchTaskManager) CancelQueue(queueID string) bool {
 		}
 	}

-	// 取消当前正在执行的任务
-	if cancel, ok := m.taskCancels[queueID]; ok {
-		cancelFunc = cancel
-		delete(m.taskCancels, queueID)
-	}
+	cancelFuncs = m.drainTaskCancelsLocked(queueID)
 	m.mu.Unlock()

-	// 释放锁后执行取消回调（cancel 可能阻塞，不应持锁）
-	if cancelFunc != nil {
-		cancelFunc()
+	for _, c := range cancelFuncs {
+		c()
 	}

 	return true
 }

-// DeleteQueue 删除队列（运行中的队列不允许删除）
-func (m *BatchTaskManager) DeleteQueue(queueID string) bool {
+// DeleteQueue 删除队列。执行协程活跃或 status 为 running 时拒绝删除，避免 executeBatchQueue 空指针 panic。
+func (m *BatchTaskManager) DeleteQueue(queueID string) error {
 	m.mu.Lock()
 	defer m.mu.Unlock()

 	queue, exists := m.queues[queueID]
 	if !exists {
-		return false
+		return ErrBatchQueueNotFound
+	}
+
+	if _, exec := m.queueExecutors[queueID]; exec {
+		return ErrBatchQueueExecutorActive
 	}

 	// 运行中的队列不允许删除，防止孤儿协程和数据丢失
 	if queue.Status == BatchQueueStatusRunning {
-		return false
+		return ErrBatchQueueStillRunning
 	}

 	// 清理取消函数
@@ -1116,7 +1442,7 @@ func (m *BatchTaskManager) DeleteQueue(queueID string) bool {
 	}

 	delete(m.queues, queueID)
-	return true
+	return nil
 }

 // generateShortID 生成短ID
@@ -0,0 +1,121 @@
+package handler
+
+import (
+	"errors"
+	"testing"
+
+	"go.uber.org/zap"
+)
+
+func TestNormalizeBatchQueueConcurrency(t *testing.T) {
+	if got := normalizeBatchQueueConcurrency(0); got != DefaultBatchQueueConcurrency {
+		t.Fatalf("expected default %d, got %d", DefaultBatchQueueConcurrency, got)
+	}
+	if got := normalizeBatchQueueConcurrency(99); got != MaxBatchQueueConcurrency {
+		t.Fatalf("expected max %d, got %d", MaxBatchQueueConcurrency, got)
+	}
+}
+
+func TestClaimNextPendingTaskParallel(t *testing.T) {
+	m := NewBatchTaskManager(zap.NewNop())
+	queue, err := m.CreateBatchQueue("test", "", "eino_single", "manual", "", "", nil, 3, []string{"a", "b", "c"})
+	if err != nil {
+		t.Fatalf("CreateBatchQueue: %v", err)
+	}
+	m.UpdateQueueStatus(queue.ID, BatchQueueStatusRunning)
+
+	t1, ok1 := m.ClaimNextPendingTask(queue.ID)
+	t2, ok2 := m.ClaimNextPendingTask(queue.ID)
+	if !ok1 || !ok2 || t1.ID == t2.ID {
+		t.Fatalf("expected two distinct claims, got ok1=%v ok2=%v t1=%v t2=%v", ok1, ok2, t1, t2)
+	}
+	if t1.Status != BatchTaskStatusRunning || t2.Status != BatchTaskStatusRunning {
+		t.Fatalf("claimed tasks should be running")
+	}
+	t3, ok3 := m.ClaimNextPendingTask(queue.ID)
+	if !ok3 {
+		t.Fatal("expected third claim")
+	}
+	_, ok4 := m.ClaimNextPendingTask(queue.ID)
+	if ok4 {
+		t.Fatal("expected no fourth pending task")
+	}
+	_ = t3
+}
+
+func TestBatchQueueExecutionShouldStop(t *testing.T) {
+	t.Parallel()
+	if !batchQueueExecutionShouldStop(nil, false) {
+		t.Fatal("expected stop when queue missing")
+	}
+	if !batchQueueExecutionShouldStop(nil, true) {
+		t.Fatal("expected stop when queue is nil but exists=true")
+	}
+	q := &BatchTaskQueue{Status: BatchQueueStatusRunning}
+	if batchQueueExecutionShouldStop(q, true) {
+		t.Fatal("expected continue when running")
+	}
+	q.Status = BatchQueueStatusCancelled
+	if !batchQueueExecutionShouldStop(q, true) {
+		t.Fatal("expected stop when cancelled")
+	}
+}
+
+func TestDeleteQueueBlockedWhileExecutorActive(t *testing.T) {
+	t.Parallel()
+	m := NewBatchTaskManager(zap.NewNop())
+	queue, err := m.CreateBatchQueue("test", "", "eino_single", "manual", "", "", nil, 1, []string{"hello"})
+	if err != nil {
+		t.Fatalf("CreateBatchQueue: %v", err)
+	}
+	if !m.TryMarkQueueExecutor(queue.ID) {
+		t.Fatal("expected to mark executor")
+	}
+	m.UpdateQueueStatus(queue.ID, BatchQueueStatusCancelled)
+
+	err = m.DeleteQueue(queue.ID)
+	if !errors.Is(err, ErrBatchQueueExecutorActive) {
+		t.Fatalf("expected ErrBatchQueueExecutorActive, got %v", err)
+	}
+	if _, ok := m.GetBatchQueue(queue.ID); !ok {
+		t.Fatal("queue should still exist while executor active")
+	}
+
+	m.UnmarkQueueExecutor(queue.ID)
+	if err := m.DeleteQueue(queue.ID); err != nil {
+		t.Fatalf("expected delete after executor unmarked, got %v", err)
+	}
+	if _, ok := m.GetBatchQueue(queue.ID); ok {
+		t.Fatal("queue should be deleted")
+	}
+}
+
+func TestDeleteQueueBlockedWhileRunning(t *testing.T) {
+	t.Parallel()
+	m := NewBatchTaskManager(zap.NewNop())
+	queue, err := m.CreateBatchQueue("test", "", "eino_single", "manual", "", "", nil, 1, []string{"hello"})
+	if err != nil {
+		t.Fatalf("CreateBatchQueue: %v", err)
+	}
+	m.UpdateQueueStatus(queue.ID, BatchQueueStatusRunning)
+
+	err = m.DeleteQueue(queue.ID)
+	if !errors.Is(err, ErrBatchQueueStillRunning) {
+		t.Fatalf("expected ErrBatchQueueStillRunning, got %v", err)
+	}
+}
+
+func TestTryMarkQueueExecutorDedupes(t *testing.T) {
+	t.Parallel()
+	m := NewBatchTaskManager(zap.NewNop())
+	if !m.TryMarkQueueExecutor("q-1") {
+		t.Fatal("first mark should succeed")
+	}
+	if m.TryMarkQueueExecutor("q-1") {
+		t.Fatal("second mark should fail")
+	}
+	m.UnmarkQueueExecutor("q-1")
+	if !m.TryMarkQueueExecutor("q-1") {
+		t.Fatal("mark after unmark should succeed")
+	}
+}
@@ -3,6 +3,7 @@ package handler
 import (
 	"context"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"strconv"
 	"strings"
@@ -181,6 +182,10 @@ func RegisterBatchTaskMCPTools(mcpServer *mcp.Server, h *AgentHandler, logger *z
 					"type":        "string",
 					"description": "队列内子对话绑定的项目 ID（可选，未指定时使用 config.project.default_project_id）",
 				},
+				"concurrency": map[string]interface{}{
+					"type":        "integer",
+					"description": "同时执行的子任务数，默认 1（串行），最大 8。含扫描类工具时建议 1-2。",
+				},
 			},
 		},
 	}, func(ctx context.Context, args map[string]interface{}) (*mcp.ToolResult, error) {
@@ -210,7 +215,8 @@ func RegisterBatchTaskMCPTools(mcpServer *mcp.Server, h *AgentHandler, logger *z
 			executeNow = false
 		}
 		projectID := strings.TrimSpace(mcpArgString(args, "project_id"))
-		queue, createErr := h.batchTaskManager.CreateBatchQueue(title, role, agentMode, scheduleMode, cronExpr, projectID, nextRunAt, tasks)
+		concurrency := int(mcpArgFloat(args, "concurrency"))
+		queue, createErr := h.batchTaskManager.CreateBatchQueue(title, role, agentMode, scheduleMode, cronExpr, projectID, nextRunAt, concurrency, tasks)
 		if createErr != nil {
 			return batchMCPTextResult("创建队列失败: "+createErr.Error(), true), nil
 		}
@@ -365,8 +371,17 @@ func RegisterBatchTaskMCPTools(mcpServer *mcp.Server, h *AgentHandler, logger *z
 		if qid == "" {
 			return batchMCPTextResult("queue_id 不能为空", true), nil
 		}
-		if !h.batchTaskManager.DeleteQueue(qid) {
-			return batchMCPTextResult("删除失败：队列不存在", true), nil
+		if err := h.batchTaskManager.DeleteQueue(qid); err != nil {
+			switch {
+			case errors.Is(err, ErrBatchQueueNotFound):
+				return batchMCPTextResult("删除失败：队列不存在", true), nil
+			case errors.Is(err, ErrBatchQueueExecutorActive):
+				return batchMCPTextResult("删除失败：队列执行器仍在运行，请稍后再试", true), nil
+			case errors.Is(err, ErrBatchQueueStillRunning):
+				return batchMCPTextResult("删除失败：队列正在运行中", true), nil
+			default:
+				return batchMCPTextResult("删除失败："+err.Error(), true), nil
+			}
 		}
 		logger.Info("MCP batch_task_delete", zap.String("queueId", qid))
 		return batchMCPTextResult("队列已删除。", false), nil
@@ -397,6 +412,10 @@ func RegisterBatchTaskMCPTools(mcpServer *mcp.Server, h *AgentHandler, logger *z
 					"description": "代理模式：eino_single、deep、plan_execute、supervisor",
 					"enum":        []string{"eino_single", "deep", "plan_execute", "supervisor"},
 				},
+				"concurrency": map[string]interface{}{
+					"type":        "integer",
+					"description": "同时执行的子任务数，默认 1，最大 8",
+				},
 			},
 			"required": []string{"queue_id"},
 		},
@@ -408,7 +427,12 @@ func RegisterBatchTaskMCPTools(mcpServer *mcp.Server, h *AgentHandler, logger *z
 		title := mcpArgString(args, "title")
 		role := mcpArgString(args, "role")
 		agentMode := mcpArgString(args, "agent_mode")
-		if err := h.batchTaskManager.UpdateQueueMetadata(qid, title, role, agentMode); err != nil {
+		var concurrency *int
+		if raw, ok := args["concurrency"]; ok && raw != nil {
+			v := int(mcpArgFloat(args, "concurrency"))
+			concurrency = &v
+		}
+		if err := h.batchTaskManager.UpdateQueueMetadata(qid, title, role, agentMode, concurrency); err != nil {
 			return batchMCPTextResult(err.Error(), true), nil
 		}
 		updated, _ := h.batchTaskManager.GetBatchQueue(qid)
@@ -652,6 +676,7 @@ type batchTaskQueueMCPListItem struct {
 	StartedAt             *time.Time                `json:"startedAt,omitempty"`
 	CompletedAt           *time.Time                `json:"completedAt,omitempty"`
 	CurrentIndex          int                       `json:"currentIndex"`
+	Concurrency           int                       `json:"concurrency"`
 	TaskTotal             int                       `json:"task_total"`
 	TaskCounts            map[string]int            `json:"task_counts"`
 	Tasks                 []batchTaskMCPListSummary `json:"tasks"`
@@ -715,6 +740,7 @@ func toBatchTaskQueueMCPListItem(q *BatchTaskQueue) batchTaskQueueMCPListItem {
 		StartedAt:             q.StartedAt,
 		CompletedAt:           q.CompletedAt,
 		CurrentIndex:          q.CurrentIndex,
+		Concurrency:           q.Concurrency,
 		TaskTotal:             len(tasks),
 		TaskCounts:            counts,
 		Tasks:                 tasks,
@@ -798,12 +798,20 @@ func (h *ConfigHandler) UpdateConfig(c *gin.Context) {

 	// 更新机器人配置
 	if req.Robots != nil {
+		if err := config.ValidateWecomConfig(req.Robots.Wecom); err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+			return
+		}
 		h.config.Robots = *req.Robots
 		h.logger.Info("更新机器人配置",
 			zap.Bool("wechat_enabled", h.config.Robots.Wechat.Enabled),
 			zap.Bool("wecom_enabled", h.config.Robots.Wecom.Enabled),
 			zap.Bool("dingtalk_enabled", h.config.Robots.Dingtalk.Enabled),
 			zap.Bool("lark_enabled", h.config.Robots.Lark.Enabled),
+			zap.Bool("telegram_enabled", h.config.Robots.Telegram.Enabled),
+			zap.Bool("slack_enabled", h.config.Robots.Slack.Enabled),
+			zap.Bool("discord_enabled", h.config.Robots.Discord.Enabled),
+			zap.Bool("qq_enabled", h.config.Robots.QQ.Enabled),
 		)
 	}

@@ -1329,6 +1337,17 @@ func (h *ConfigHandler) ApplyConfig(c *gin.Context) {
 		h.logger.Info("已更新嵌入模型配置记录")
 	}

+	// 从 tools 目录重新加载工具配置（新增/修改/删除 yaml 后无需重启）
+	if err := config.ReloadSecurityToolsFromDir(h.config, h.configPath); err != nil {
+		h.logger.Error("重新加载工具配置失败", zap.Error(err))
+		if h.audit != nil {
+			h.audit.RecordFail(c, "config", "apply", "应用配置失败：重新加载工具", map[string]interface{}{"error": err.Error()})
+		}
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "重新加载工具配置失败: " + err.Error()})
+		return
+	}
+	h.logger.Info("已从 tools 目录重新加载工具配置", zap.Int("tools_count", len(h.config.Security.Tools)))
+
 	// 重新注册工具（根据新的启用状态）
 	h.logger.Info("重新注册工具")

@@ -1417,12 +1436,7 @@ func (h *ConfigHandler) ApplyConfig(c *gin.Context) {

 	// 更新检索器配置（如果知识库启用）
 	if h.config.Knowledge.Enabled && h.retrieverUpdater != nil {
-		retrievalConfig := &knowledge.RetrievalConfig{
-			TopK:                h.config.Knowledge.Retrieval.TopK,
-			SimilarityThreshold: h.config.Knowledge.Retrieval.SimilarityThreshold,
-			SubIndexFilter:      h.config.Knowledge.Retrieval.SubIndexFilter,
-			PostRetrieve:        h.config.Knowledge.Retrieval.PostRetrieve,
-		}
+		retrievalConfig := knowledge.RetrievalConfigFromYAML(h.config.Knowledge.Retrieval)
 		h.retrieverUpdater.UpdateConfig(retrievalConfig)
 		h.logger.Info("检索器配置已更新",
 			zap.Int("top_k", retrievalConfig.TopK),
@@ -1705,6 +1719,13 @@ func updateKnowledgeConfig(doc *yaml.Node, cfg config.KnowledgeConfig) {
 	setIntInMap(retrievalNode, "top_k", cfg.Retrieval.TopK)
 	setFloatInMap(retrievalNode, "similarity_threshold", cfg.Retrieval.SimilarityThreshold)
 	setStringInMap(retrievalNode, "sub_index_filter", cfg.Retrieval.SubIndexFilter)
+	mqNode := ensureMap(retrievalNode, "multi_query")
+	setIntInMap(mqNode, "max_queries", cfg.Retrieval.MultiQuery.MaxQueries)
+	rerankNode := ensureMap(retrievalNode, "rerank")
+	setStringInMap(rerankNode, "provider", cfg.Retrieval.Rerank.Provider)
+	setStringInMap(rerankNode, "model", cfg.Retrieval.Rerank.Model)
+	setStringInMap(rerankNode, "base_url", cfg.Retrieval.Rerank.BaseURL)
+	setStringInMap(rerankNode, "api_key", cfg.Retrieval.Rerank.APIKey)
 	postNode := ensureMap(retrievalNode, "post_retrieve")
 	setIntInMap(postNode, "prefetch_top_k", cfg.Retrieval.PostRetrieve.PrefetchTopK)
 	setIntInMap(postNode, "max_context_chars", cfg.Retrieval.PostRetrieve.MaxContextChars)
@@ -1751,6 +1772,20 @@ func mergeHitlToolWhitelistSlice(existing, add []string) []string {
 	return out
 }

+// SetHitlToolWhitelist 将全局免审批工具白名单整表写入 config.yaml（替换，非合并）。
+func (h *ConfigHandler) SetHitlToolWhitelist(tools []string) error {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.config.Hitl.ToolWhitelist = mergeHitlToolWhitelistSlice(nil, tools)
+	if err := h.saveConfig(); err != nil {
+		return err
+	}
+	h.logger.Info("HITL 全局工具白名单已写入配置文件",
+		zap.Int("count", len(h.config.Hitl.ToolWhitelist)),
+	)
+	return nil
+}
+
 // MergeHitlToolWhitelistIntoConfig 将会话侧栏提交的免审批工具名合并进内存配置并写入 config.yaml（与全局白名单去重规则一致：小写键、保留首次出现的原始大小写）。
 func (h *ConfigHandler) MergeHitlToolWhitelistIntoConfig(add []string) error {
 	h.mu.Lock()
@@ -1771,6 +1806,34 @@ func updateHitlConfig(doc *yaml.Node, cfg config.HitlConfig) {
 	hitlNode := ensureMap(root, "hitl")
 	// flow 样式 [a, b, c] 单行展示，工具多时比块序列省行数
 	setFlowStringSliceInMap(hitlNode, "tool_whitelist", cfg.ToolWhitelist)
+	setStringInMap(hitlNode, "default_reviewer", cfg.EffectiveDefaultReviewer())
+	setStringInMap(hitlNode, "audit_agent_prompt", cfg.AuditAgentPrompt)
+	setStringInMap(hitlNode, "audit_agent_prompt_review_edit", cfg.AuditAgentPromptReviewEdit)
+}
+
+// UpdateHitlDefaultReviewer 更新全局默认审批方并写入 config.yaml。
+func (h *ConfigHandler) UpdateHitlDefaultReviewer(reviewer string) error {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.config.Hitl.DefaultReviewer = config.HitlConfig{DefaultReviewer: reviewer}.EffectiveDefaultReviewer()
+	if err := h.saveConfig(); err != nil {
+		return err
+	}
+	h.logger.Info("HITL 全局默认审批方已写入配置文件", zap.String("default_reviewer", h.config.Hitl.DefaultReviewer))
+	return nil
+}
+
+// UpdateHitlAuditAgentStrategy 更新审批/审查编辑两套审计 Agent 提示词并写入 config.yaml。
+func (h *ConfigHandler) UpdateHitlAuditAgentStrategy(approvalPrompt, reviewEditPrompt string) error {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.config.Hitl.AuditAgentPrompt = strings.TrimSpace(approvalPrompt)
+	h.config.Hitl.AuditAgentPromptReviewEdit = strings.TrimSpace(reviewEditPrompt)
+	if err := h.saveConfig(); err != nil {
+		return err
+	}
+	h.logger.Info("HITL 审计 Agent 提示词已写入配置文件")
+	return nil
 }

 func updateRobotsConfig(doc *yaml.Node, cfg config.RobotsConfig) {
@@ -1811,6 +1874,28 @@ func updateRobotsConfig(doc *yaml.Node, cfg config.RobotsConfig) {
 	setStringInMap(larkNode, "app_secret", cfg.Lark.AppSecret)
 	setStringInMap(larkNode, "verify_token", cfg.Lark.VerifyToken)
 	setBoolInMap(larkNode, "allow_chat_id_fallback", cfg.Lark.AllowChatIDFallback)
+
+	telegramNode := ensureMap(robotsNode, "telegram")
+	setBoolInMap(telegramNode, "enabled", cfg.Telegram.Enabled)
+	setStringInMap(telegramNode, "bot_token", cfg.Telegram.BotToken)
+	setStringInMap(telegramNode, "bot_username", cfg.Telegram.BotUsername)
+	setBoolInMap(telegramNode, "allow_group_messages", cfg.Telegram.AllowGroupMessages)
+
+	slackNode := ensureMap(robotsNode, "slack")
+	setBoolInMap(slackNode, "enabled", cfg.Slack.Enabled)
+	setStringInMap(slackNode, "bot_token", cfg.Slack.BotToken)
+	setStringInMap(slackNode, "app_token", cfg.Slack.AppToken)
+
+	discordNode := ensureMap(robotsNode, "discord")
+	setBoolInMap(discordNode, "enabled", cfg.Discord.Enabled)
+	setStringInMap(discordNode, "bot_token", cfg.Discord.BotToken)
+	setBoolInMap(discordNode, "allow_guild_messages", cfg.Discord.AllowGuildMessages)
+
+	qqNode := ensureMap(robotsNode, "qq")
+	setBoolInMap(qqNode, "enabled", cfg.QQ.Enabled)
+	setStringInMap(qqNode, "app_id", cfg.QQ.AppID)
+	setStringInMap(qqNode, "client_secret", cfg.QQ.ClientSecret)
+	setBoolInMap(qqNode, "sandbox", cfg.QQ.Sandbox)
 }

 func updateMultiAgentConfig(doc *yaml.Node, cfg config.MultiAgentConfig) {
@@ -12,11 +12,17 @@ import (
 	"go.uber.org/zap"
 )

+// ConversationTaskStopper cancels in-flight agent work when a conversation is removed.
+type ConversationTaskStopper interface {
+	CancelRunningTaskForConversation(conversationID string)
+}
+
 // ConversationHandler 对话处理器
 type ConversationHandler struct {
-	db     *database.DB
-	logger *zap.Logger
-	audit  *audit.Service
+	db          *database.DB
+	logger      *zap.Logger
+	audit       *audit.Service
+	taskStopper ConversationTaskStopper
 }

 // SetAudit wires platform audit logging.
@@ -24,6 +30,11 @@ func (h *ConversationHandler) SetAudit(s *audit.Service) {
 	h.audit = s
 }

+// SetTaskStopper wires cancellation of in-flight agent tasks on conversation delete.
+func (h *ConversationHandler) SetTaskStopper(stopper ConversationTaskStopper) {
+	h.taskStopper = stopper
+}
+
 // NewConversationHandler 创建新的对话处理器
 func NewConversationHandler(db *database.DB, logger *zap.Logger) *ConversationHandler {
 	return &ConversationHandler{
@@ -92,6 +103,7 @@ func (h *ConversationHandler) ListConversations(c *gin.Context) {
 	limitStr := c.DefaultQuery("limit", "50")
 	offsetStr := c.DefaultQuery("offset", "0")
 	search := c.Query("search") // 获取搜索参数
+	projectID := strings.TrimSpace(c.Query("project_id"))

 	limit, _ := strconv.Atoi(limitStr)
 	offset, _ := strconv.Atoi(offsetStr)
@@ -103,21 +115,22 @@ func (h *ConversationHandler) ListConversations(c *gin.Context) {
 		limit = 1000
 	}

-	excludeGrouped := strings.TrimSpace(search) == "" &&
+	excludeGrouped := strings.TrimSpace(search) == "" && projectID == "" &&
 		(c.Query("exclude_grouped") == "true" || c.Query("exclude_grouped") == "1")
+	sortBy := strings.TrimSpace(c.Query("sort_by"))

 	var conversations []*database.Conversation
 	var total int
 	var err error
 	if excludeGrouped {
-		conversations, err = h.db.ListUngroupedConversations(limit, offset)
+		conversations, err = h.db.ListUngroupedConversations(limit, offset, sortBy, projectID)
 		if err == nil {
-			total, err = h.db.CountUngroupedConversations()
+			total, err = h.db.CountUngroupedConversations(projectID)
 		}
 	} else {
-		conversations, err = h.db.ListConversations(limit, offset, search)
+		conversations, err = h.db.ListConversations(limit, offset, search, sortBy, projectID)
 		if err == nil {
-			total, err = h.db.CountConversations(search)
+			total, err = h.db.CountConversations(search, projectID)
 		}
 	}
 	if err != nil {
@@ -164,6 +177,9 @@ func (h *ConversationHandler) GetConversation(c *gin.Context) {
 }

 // GetMessageProcessDetails 获取指定消息的过程详情（按需加载）
+// 查询参数：
+//   - summary=1：仅返回摘要（total / iterationCount / maxIteration）
+//   - limit + offset：分页返回 processDetails（未指定 limit 时保持全量兼容）
 func (h *ConversationHandler) GetMessageProcessDetails(c *gin.Context) {
 	messageID := c.Param("id")
 	if messageID == "" {
@@ -171,6 +187,51 @@ func (h *ConversationHandler) GetMessageProcessDetails(c *gin.Context) {
 		return
 	}

+	summaryStr := strings.TrimSpace(c.Query("summary"))
+	if summaryStr == "1" || strings.EqualFold(summaryStr, "true") || strings.EqualFold(summaryStr, "yes") {
+		summary, err := h.db.GetProcessDetailsSummary(messageID)
+		if err != nil {
+			h.logger.Error("获取过程详情摘要失败", zap.Error(err))
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+			return
+		}
+		c.JSON(http.StatusOK, gin.H{"summary": summary})
+		return
+	}
+
+	limitStr := strings.TrimSpace(c.Query("limit"))
+	if limitStr != "" {
+		limit, err := strconv.Atoi(limitStr)
+		if err != nil || limit <= 0 {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "invalid limit"})
+			return
+		}
+		if limit > 500 {
+			limit = 500
+		}
+		offset, _ := strconv.Atoi(strings.TrimSpace(c.Query("offset")))
+		if offset < 0 {
+			offset = 0
+		}
+
+		details, total, err := h.db.GetProcessDetailsPage(messageID, limit, offset)
+		if err != nil {
+			h.logger.Error("分页获取过程详情失败", zap.Error(err))
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+			return
+		}
+		details = database.DedupeConsecutiveProcessDetails(details)
+		out := processDetailsToJSON(h.logger, details)
+		c.JSON(http.StatusOK, gin.H{
+			"processDetails": out,
+			"total":          total,
+			"offset":         offset,
+			"limit":          limit,
+			"hasMore":        offset+len(out) < total,
+		})
+		return
+	}
+
 	details, err := h.db.GetProcessDetails(messageID)
 	if err != nil {
 		h.logger.Error("获取过程详情失败", zap.Error(err))
@@ -179,14 +240,17 @@ func (h *ConversationHandler) GetMessageProcessDetails(c *gin.Context) {
 	}

 	details = database.DedupeConsecutiveProcessDetails(details)
+	out := processDetailsToJSON(h.logger, details)
+	c.JSON(http.StatusOK, gin.H{"processDetails": out, "total": len(out)})
+}

-	// 转换为前端期望的 JSON 结构（与 GetConversation 中 processDetails 结构一致）
+func processDetailsToJSON(logger *zap.Logger, details []database.ProcessDetail) []map[string]interface{} {
 	out := make([]map[string]interface{}, 0, len(details))
 	for _, d := range details {
 		var data interface{}
 		if d.Data != "" {
 			if err := json.Unmarshal([]byte(d.Data), &data); err != nil {
-				h.logger.Warn("解析过程详情数据失败", zap.Error(err))
+				logger.Warn("解析过程详情数据失败", zap.Error(err))
 			}
 		}
 		out = append(out, map[string]interface{}{
@@ -199,8 +263,7 @@ func (h *ConversationHandler) GetMessageProcessDetails(c *gin.Context) {
 			"createdAt":      d.CreatedAt,
 		})
 	}
-
-	c.JSON(http.StatusOK, gin.H{"processDetails": out})
+	return out
 }

 // UpdateConversationRequest 更新对话请求
@@ -244,6 +307,10 @@ func (h *ConversationHandler) UpdateConversation(c *gin.Context) {
 func (h *ConversationHandler) DeleteConversation(c *gin.Context) {
 	id := c.Param("id")

+	if h.taskStopper != nil {
+		h.taskStopper.CancelRunningTaskForConversation(id)
+	}
+
 	if err := h.db.DeleteConversation(id); err != nil {
 		h.logger.Error("删除对话失败", zap.Error(err))
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
@@ -0,0 +1,30 @@
+package handler
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"go.uber.org/zap"
+)
+
+func TestConversationHandlerDeleteConversationCancelsRunningTask(t *testing.T) {
+	tm := NewAgentTaskManager()
+	ctx, cancel := context.WithCancelCause(context.Background())
+	_, err := tm.StartTask("conv-1", "hello", cancel)
+	if err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+
+	h := &AgentHandler{tasks: tm, logger: zap.NewNop()}
+	h.CancelRunningTaskForConversation("conv-1")
+
+	select {
+	case <-ctx.Done():
+	case <-time.After(2 * time.Second):
+		t.Fatal("task context was not cancelled")
+	}
+	if cause := context.Cause(ctx); cause != ErrTaskCancelled {
+		t.Fatalf("expected ErrTaskCancelled, got %v", cause)
+	}
+}
@@ -0,0 +1,83 @@
+package handler
+
+import (
+	"context"
+	"fmt"
+	"time"
+
+	"cyberstrike-ai/internal/agent"
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/multiagent"
+
+	"go.uber.org/zap"
+)
+
+// rebindEinoRunningTask 中断并继续 / 空正文续跑：重建 cancel 链与超时 ctx，保持任务 running。
+func (h *AgentHandler) rebindEinoRunningTask(conversationID string, timeoutCancel context.CancelFunc) (context.Context, context.CancelCauseFunc, context.Context, context.CancelFunc) {
+	if timeoutCancel != nil {
+		timeoutCancel()
+	}
+	baseCtx, cancelWithCause := context.WithCancelCause(context.Background())
+	h.tasks.BindTaskCancel(conversationID, cancelWithCause)
+	taskCtx, newTimeoutCancel := context.WithTimeout(baseCtx, 600*time.Minute)
+	h.tasks.UpdateTaskStatus(conversationID, "running")
+	return baseCtx, cancelWithCause, taskCtx, newTimeoutCancel
+}
+
+// tryContinueOnEinoEmptyResponse Run 成功但 Response 为 emptyHint 时退避续跑；true 表示已准备下一段 Run。
+func (h *AgentHandler) tryContinueOnEinoEmptyResponse(
+	taskCtx context.Context,
+	mw *config.MultiAgentEinoMiddlewareConfig,
+	conversationID string,
+	result *multiagent.RunResult,
+	attempt *int,
+	curHistory *[]agent.ChatMessage,
+	curFinalMessage *string,
+	progressCallback func(eventType, message string, data interface{}),
+) bool {
+	if result == nil || !multiagent.IsEinoEmptyResponseResult(result) || !multiagent.HasEinoResumeTrace(result) {
+		return false
+	}
+	maxAttempts := multiagent.EmptyResponseContinueMaxAttemptsFromConfig(mw)
+	if *attempt >= maxAttempts {
+		if h.logger != nil {
+			h.logger.Warn("eino empty response continue exhausted",
+				zap.String("conversationId", conversationID),
+				zap.Int("maxAttempts", maxAttempts))
+		}
+		return false
+	}
+	*attempt++
+	h.persistEinoAgentTraceForResume(conversationID, result)
+
+	backoff := multiagent.EmptyResponseContinueBackoff(*attempt-1, mw)
+	waitMsg := fmt.Sprintf("会话已结束但未捕获到助手正文，%d 秒后第 %d/%d 次自动续跑…",
+		int(backoff.Seconds()), *attempt, maxAttempts)
+	if progressCallback != nil {
+		progressCallback("eino_empty_response_continue", waitMsg, map[string]interface{}{
+			"conversationId": conversationID,
+			"source":         "eino",
+			"attempt":        *attempt,
+			"maxAttempts":    maxAttempts,
+			"backoffSec":     int(backoff.Seconds()),
+		})
+	}
+	select {
+	case <-taskCtx.Done():
+		return false
+	case <-time.After(backoff):
+	}
+
+	inject := multiagent.FormatEmptyResponseContinueUserMessage()
+	h.applyEinoTraceResumeSegment(conversationID, result, curHistory, curFinalMessage, inject)
+	if progressCallback != nil {
+		progressCallback("eino_empty_response_continue", "已恢复上下文，正在续跑…", map[string]interface{}{
+			"conversationId": conversationID,
+			"source":         "eino",
+			"attempt":        *attempt,
+			"maxAttempts":    maxAttempts,
+			"contextSource":  "empty_response_continue",
+		})
+	}
+	return true
+}
@@ -2,31 +2,11 @@ package handler

 import (
 	"context"
-	"errors"
-	"fmt"
-	"strings"
-	"time"

 	"cyberstrike-ai/internal/agent"
 	"cyberstrike-ai/internal/multiagent"
-
-	"go.uber.org/zap"
 )

-func (h *AgentHandler) einoRunRetryMaxAttempts() int {
-	if h.config != nil {
-		return multiagent.RunRetryMaxAttemptsFromConfig(&h.config.MultiAgent.EinoMiddleware)
-	}
-	return multiagent.RunRetryMaxAttemptsFromConfig(nil)
-}
-
-func (h *AgentHandler) einoRunRetryMaxBackoffSec() int {
-	if h.config != nil && h.config.MultiAgent.EinoMiddleware.RunRetryMaxBackoffSec > 0 {
-		return h.config.MultiAgent.EinoMiddleware.RunRetryMaxBackoffSec
-	}
-	return 0
-}
-
 // applyEinoTraceResumeSegment 中断并继续：persist last_react_* → loadHistory，可选替换下一段 user 文案。
 func (h *AgentHandler) applyEinoTraceResumeSegment(
 	conversationID string,
@@ -45,136 +25,3 @@ func (h *AgentHandler) applyEinoTraceResumeSegment(
 		*curFinalMessage = segmentUserMessage
 	}
 }
-
-// applyEinoTransientRetrySegment 临时错误重试：恢复轨迹并保留本请求原始 user 文案（不注入续跑说明）。
-// segmentUserMessage 为本轮 HTTP 请求开始时用户发送的内容，避免因清空 finalMessage 而丢失「你好」等短句。
-func (h *AgentHandler) applyEinoTransientRetrySegment(
-	conversationID string,
-	result *multiagent.RunResult,
-	curHistory *[]agent.ChatMessage,
-	curFinalMessage *string,
-	segmentUserMessage string,
-) {
-	if shouldPersistEinoAgentTraceAfterRunError(context.Background()) {
-		h.persistEinoAgentTraceForResume(conversationID, result)
-	}
-	if hist, err := h.loadHistoryFromAgentTrace(conversationID); err == nil && len(hist) > 0 {
-		*curHistory = hist
-	}
-	if s := strings.TrimSpace(segmentUserMessage); s != "" {
-		*curFinalMessage = segmentUserMessage
-	}
-}
-
-// handleEinoTransientRetryContinue 在 SSE 任务循环内处理临时错误重试；返回 true 表示外层 for 应 continue。
-func (h *AgentHandler) handleEinoTransientRetryContinue(
-	baseCtx context.Context,
-	conversationID string,
-	result *multiagent.RunResult,
-	runErr error,
-	transientAttempts *int,
-	curHistory *[]agent.ChatMessage,
-	curFinalMessage *string,
-	segmentUserMessage string,
-	progressCallback func(eventType, message string, data interface{}),
-	sendProgress func(msg string, extra map[string]interface{}),
-) (handled bool, fatal error) {
-	if !errors.Is(runErr, multiagent.ErrTransientRetryContinue) {
-		return false, nil
-	}
-	maxAttempts := h.einoRunRetryMaxAttempts()
-	*transientAttempts++
-	if *transientAttempts > maxAttempts {
-		if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
-			h.persistEinoAgentTraceForResume(conversationID, result)
-		}
-		return false, errors.New("transient retry exhausted: " + runErr.Error())
-	}
-	attemptNo := *transientAttempts
-	backoff := multiagent.TransientRetryBackoff(attemptNo-1, h.einoRunRetryMaxBackoffSec())
-	if progressCallback != nil {
-		progressCallback("eino_run_retry", fmt.Sprintf("遇到临时错误，%d 秒后第 %d/%d 次重试…", int(backoff.Seconds()), attemptNo, maxAttempts), map[string]interface{}{
-			"conversationId": conversationID,
-			"source":         "eino",
-			"attempt":        attemptNo,
-			"maxAttempts":    maxAttempts,
-			"backoffSec":     int(backoff.Seconds()),
-		})
-	}
-	select {
-	case <-baseCtx.Done():
-		return false, context.Cause(baseCtx)
-	case <-time.After(backoff):
-	}
-	h.applyEinoTransientRetrySegment(conversationID, result, curHistory, curFinalMessage, segmentUserMessage)
-	if progressCallback != nil {
-		progressCallback("eino_run_retry", "已恢复上下文，正在重试…", map[string]interface{}{
-			"conversationId": conversationID,
-			"source":         "eino",
-			"attempt":        attemptNo,
-		})
-	}
-	if sendProgress != nil {
-		sendProgress("正在重试…", map[string]interface{}{
-			"conversationId": conversationID,
-			"source":         "transient_retry",
-		})
-	}
-	return true, nil
-}
-
-// handleEinoEmptyResponseContinue 在 SSE 任务循环内处理「正常结束但无助手正文」；返回 exhausted=true 时由外层按成功结束（保留占位文案）。
-// 与临时错误重试一致：仅恢复轨迹并保留本请求原始 user 文案，不向模型注入续跑说明。
-func (h *AgentHandler) handleEinoEmptyResponseContinue(
-	baseCtx context.Context,
-	conversationID string,
-	result *multiagent.RunResult,
-	runErr error,
-	emptyResponseAttempts *int,
-	curHistory *[]agent.ChatMessage,
-	curFinalMessage *string,
-	segmentUserMessage string,
-	progressCallback func(eventType, message string, data interface{}),
-	sendProgress func(msg string, extra map[string]interface{}),
-) (handled bool, exhausted bool) {
-	if !errors.Is(runErr, multiagent.ErrEmptyResponseContinue) {
-		return false, false
-	}
-	maxAttempts := h.einoRunRetryMaxAttempts()
-	*emptyResponseAttempts++
-	if *emptyResponseAttempts > maxAttempts {
-		if h.logger != nil {
-			h.logger.Warn("eino empty response auto resume exhausted",
-				zap.String("conversationId", conversationID),
-				zap.Int("maxAttempts", maxAttempts))
-		}
-		if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
-			h.persistEinoAgentTraceForResume(conversationID, result)
-		}
-		return false, true
-	}
-	attemptNo := *emptyResponseAttempts
-	if h.logger != nil {
-		h.logger.Info("eino empty response, auto resume from trace",
-			zap.String("conversationId", conversationID),
-			zap.Int("attempt", attemptNo),
-			zap.Int("maxAttempts", maxAttempts))
-	}
-	if progressCallback != nil {
-		progressCallback("eino_empty_response_continue", fmt.Sprintf("未捕获到助手正文，正在基于轨迹自动续跑（%d/%d）…", attemptNo, maxAttempts), map[string]interface{}{
-			"conversationId": conversationID,
-			"source":         "eino",
-			"attempt":        attemptNo,
-			"maxAttempts":    maxAttempts,
-			"resumeKind":     "trace_segment",
-		})
-	}
-	h.applyEinoTransientRetrySegment(conversationID, result, curHistory, curFinalMessage, segmentUserMessage)
-	if sendProgress != nil {
-		sendProgress("已恢复上下文，正在继续推理…", map[string]interface{}{
-			"conversationId": conversationID,
-			"source":         "empty_response_continue",
-		})
-	}
-	return true, false
-}
@@ -116,10 +116,12 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 			"userMessageId":  prep.UserMessageID,
 		})
 	}
+	if h.runRoleWorkflowStreamIfBound(&req, prep, sendEvent) {
+		return
+	}

 	var cancelWithCause context.CancelCauseFunc
 	curFinalMessage := prep.FinalMessage
-	segmentUserMessage := prep.FinalMessage // 本请求原始用户句，临时重试时不得丢失
 	curHistory := prep.History
 	roleTools := prep.RoleTools

@@ -177,10 +179,9 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 	taskOwned = true

 	var cumulativeMCPExecutionIDs []string
-	var transientRunAttempts int
-	var emptyResponseAttempts int
 	// 同一请求内分段续跑时，主代理 iteration 事件按偏移累计，避免 UI 出现「第3轮 → 第1轮」回跳。
 	var mainIterationOffset int
+	var emptyResponseContinueAttempt int

 	for {
 		segmentMainIterationMax := 0
@@ -215,6 +216,7 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 		}
 		taskCtxLoop := mcp.WithMCPConversationID(taskCtx, conversationID)
 		taskCtxLoop = mcp.WithToolRunRegistry(taskCtxLoop, h.tasks)
+		taskCtxLoop = mcp.WithEinoExecuteRunRegistry(taskCtxLoop, h.tasks)
 		taskCtxLoop = multiagent.WithHITLToolInterceptor(taskCtxLoop, func(ctx context.Context, toolName, arguments string) (string, error) {
 			return h.interceptHITLForEinoTool(ctx, cancelWithCause, conversationID, assistantMessageID, sendEvent, toolName, arguments)
 		})
@@ -224,6 +226,7 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 			h.config,
 			&h.config.MultiAgent,
 			h.agent,
+			h.db,
 			h.logger,
 			conversationID,
 			h.conversationProjectID(conversationID),
@@ -232,61 +235,25 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 			roleTools,
 			progressCallback,
 			chatReasoningToClientIntent(req.Reasoning),
-			h.projectBlackboardBlock(conversationID),
+			h.agentSessionContextBlock(conversationID),
 		)

 		if result != nil && len(result.MCPExecutionIDs) > 0 {
 			cumulativeMCPExecutionIDs = mergeMCPExecutionIDLists(cumulativeMCPExecutionIDs, result.MCPExecutionIDs)
 		}

-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			baseCtx, conversationID, result, runErr, &emptyResponseAttempts,
-			&curHistory, &curFinalMessage, segmentUserMessage, progressCallback,
-			func(msg string, extra map[string]interface{}) { sendEvent("progress", msg, extra) },
-		)
-		if exhaustedEmpty {
-			runErr = nil
-			transientRunAttempts = 0
-			timeoutCancel()
-			break
-		}
-		if handledEmpty {
-			mainIterationOffset += segmentMainIterationMax
-			transientRunAttempts = 0
-			timeoutCancel()
-			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
-			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
-			taskCtx, timeoutCancel = context.WithTimeout(baseCtx, 600*time.Minute)
-			h.tasks.UpdateTaskStatus(conversationID, "running")
-			continue
-		}
-
 		if runErr == nil {
-			// 任一段成功完成后，重置临时错误重试窗口（次数/退避从头开始）。
-			transientRunAttempts = 0
-			emptyResponseAttempts = 0
+			mw := &h.config.MultiAgent.EinoMiddleware
+			if h.tryContinueOnEinoEmptyResponse(taskCtx, mw, conversationID, result, &emptyResponseContinueAttempt, &curHistory, &curFinalMessage, progressCallback) {
+				mainIterationOffset += segmentMainIterationMax
+				timeoutCancel()
+				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(conversationID, timeoutCancel)
+				continue
+			}
 			timeoutCancel()
 			break
 		}

-		handled, fatalErr := h.handleEinoTransientRetryContinue(
-			baseCtx, conversationID, result, runErr, &transientRunAttempts,
-			&curHistory, &curFinalMessage, segmentUserMessage, progressCallback,
-			func(msg string, extra map[string]interface{}) { sendEvent("progress", msg, extra) },
-		)
-		if handled {
-			mainIterationOffset += segmentMainIterationMax
-			timeoutCancel()
-			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
-			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
-			taskCtx, timeoutCancel = context.WithTimeout(baseCtx, 600*time.Minute)
-			h.tasks.UpdateTaskStatus(conversationID, "running")
-			continue
-		}
-		if fatalErr != nil {
-			runErr = fatalErr
-		}
-
 		cause := context.Cause(baseCtx)
 		if errors.Is(cause, multiagent.ErrInterruptContinue) {
 			if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
@@ -311,8 +278,6 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 				"source":         "interrupt_continue",
 			})
 			mainIterationOffset += segmentMainIterationMax
-			// 非临时错误分段续跑（用户中断并继续）时，清空 transient 计数，避免跨分段累加。
-			transientRunAttempts = 0
 			timeoutCancel()
 			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
 			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
@@ -423,6 +388,9 @@ func (h *AgentHandler) EinoSingleAgentLoop(c *gin.Context) {
 	if h.hitlManager != nil {
 		defer h.hitlManager.DeactivateConversation(prep.ConversationID)
 	}
+	if h.runRoleWorkflowJSONIfBound(c, &req, prep) {
+		return
+	}

 	var progressBuf strings.Builder
 	progressCallbackRaw := func(eventType, message string, data interface{}) {
@@ -447,14 +415,13 @@ func (h *AgentHandler) EinoSingleAgentLoop(c *gin.Context) {
 	curMsg := prep.FinalMessage
 	var result *multiagent.RunResult
 	var runErr error
-	var transientRunAttempts int
-	var emptyResponseAttempts int
 	for {
 		result, runErr = multiagent.RunEinoSingleChatModelAgent(
 			taskCtx,
 			h.config,
 			&h.config.MultiAgent,
 			h.agent,
+			h.db,
 			h.logger,
 			prep.ConversationID,
 			h.conversationProjectID(prep.ConversationID),
@@ -463,30 +430,11 @@ func (h *AgentHandler) EinoSingleAgentLoop(c *gin.Context) {
 			prep.RoleTools,
 			progressCallback,
 			chatReasoningToClientIntent(req.Reasoning),
-			h.projectBlackboardBlock(prep.ConversationID),
+			h.agentSessionContextBlock(prep.ConversationID),
 		)
-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			baseCtx, prep.ConversationID, result, runErr, &emptyResponseAttempts,
-			&curHist, &curMsg, prep.FinalMessage, progressCallback, nil,
-		)
-		if exhaustedEmpty {
-			runErr = nil
-			break
-		}
-		if handledEmpty {
-			continue
-		}
 		if runErr == nil {
 			break
 		}
-		if handled, fatalErr := h.handleEinoTransientRetryContinue(
-			baseCtx, prep.ConversationID, result, runErr, &transientRunAttempts,
-			&curHist, &curMsg, prep.FinalMessage, progressCallback, nil,
-		); handled {
-			continue
-		} else if fatalErr != nil {
-			runErr = fatalErr
-		}
 		if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
 			h.persistEinoAgentTraceForResume(prep.ConversationID, result)
 		}
@@ -23,6 +23,7 @@ import (
 type hitlRuntimeConfig struct {
 	Enabled        bool
 	Mode           string
+	Reviewer       string
 	SensitiveTools map[string]struct{}
 	Timeout        time.Duration
 }
@@ -49,6 +50,8 @@ type HITLManager struct {
 	mu      sync.RWMutex
 	runtime map[string]hitlRuntimeConfig
 	pending map[string]*pendingInterrupt
+	// approvedExec 审批通过、待回写 tool_result 的队列（按会话 FIFO）
+	approvedExec map[string][]hitlApprovedExecTrack
 }

 func NewHITLManager(db *database.DB, logger *zap.Logger) *HITLManager {
@@ -90,6 +93,7 @@ CREATE TABLE IF NOT EXISTS hitl_conversation_configs (
 	if err != nil {
 		return err
 	}
+	m.migrateHitlSchemaColumns()

 	// On startup, cancel all orphaned pending interrupts from previous process.
 	// Their in-memory channels are gone, so they can never be resolved.
@@ -141,6 +145,7 @@ func (m *HITLManager) ActivateConversation(conversationID string, req *HITLReque
 	m.runtime[conversationID] = hitlRuntimeConfig{
 		Enabled:        true,
 		Mode:           normalizeHitlMode(req.Mode),
+		Reviewer:       normalizeHitlReviewer(req.Reviewer),
 		SensitiveTools: tools,
 		Timeout:        timeout,
 	}
@@ -153,17 +158,14 @@ func (m *HITLManager) DeactivateConversation(conversationID string) {
 	m.mu.Unlock()
 }

-// hitlConfigGlobalToolWhitelist 来自 config.yaml hitl.tool_whitelist（去重、去空）。
+// hitlConfigGlobalToolWhitelist 来自 config.yaml hitl.tool_whitelist（去重、去空），并合并内置元工具免审批项。
 func (h *AgentHandler) hitlConfigGlobalToolWhitelist() []string {
 	if h == nil || h.config == nil {
-		return nil
+		return multiagent.MergeHitlExemptMetaTools(nil)
 	}
 	raw := h.config.Hitl.ToolWhitelist
-	if len(raw) == 0 {
-		return nil
-	}
 	seen := make(map[string]struct{})
-	out := make([]string, 0, len(raw))
+	out := make([]string, 0, len(raw)+len(multiagent.HitlExemptMetaTools))
 	for _, t := range raw {
 		n := strings.ToLower(strings.TrimSpace(t))
 		if n == "" {
@@ -175,44 +177,35 @@ func (h *AgentHandler) hitlConfigGlobalToolWhitelist() []string {
 		seen[n] = struct{}{}
 		out = append(out, strings.TrimSpace(t))
 	}
-	return out
+	return multiagent.MergeHitlExemptMetaTools(out)
 }

-// hitlRequestWithMergedConfigWhitelist 将会话/API 中的白名单与 config.yaml 全局白名单合并（并集），仅用于运行时 Activate；不写入数据库。
+// hitlRequestWithMergedConfigWhitelist 将会话/API 中的白名单与 config.yaml 全局白名单及内置元工具免审批项合并（并集），仅用于运行时 Activate；不写入数据库。
 func (h *AgentHandler) hitlRequestWithMergedConfigWhitelist(req *HITLRequest) *HITLRequest {
-	gw := h.hitlConfigGlobalToolWhitelist()
-	if len(gw) == 0 {
-		return req
-	}
 	if req == nil {
 		return nil
 	}
 	seen := make(map[string]struct{})
-	union := make([]string, 0, len(gw)+len(req.SensitiveTools))
-	for _, t := range gw {
+	union := make([]string, 0, len(req.SensitiveTools)+16)
+	add := func(t string) {
 		n := strings.ToLower(strings.TrimSpace(t))
 		if n == "" {
-			continue
+			return
 		}
 		if _, ok := seen[n]; ok {
-			continue
+			return
 		}
 		seen[n] = struct{}{}
 		union = append(union, strings.TrimSpace(t))
 	}
+	for _, t := range h.hitlConfigGlobalToolWhitelist() {
+		add(t)
+	}
 	for _, t := range req.SensitiveTools {
-		n := strings.ToLower(strings.TrimSpace(t))
-		if n == "" {
-			continue
-		}
-		if _, ok := seen[n]; ok {
-			continue
-		}
-		seen[n] = struct{}{}
-		union = append(union, strings.TrimSpace(t))
+		add(t)
 	}
 	out := *req
-	out.SensitiveTools = union
+	out.SensitiveTools = multiagent.MergeHitlExemptMetaTools(union)
 	return &out
 }

@@ -362,22 +355,22 @@ func (m *HITLManager) SaveConversationConfig(conversationID string, req *HITLReq
 		timeout = 0
 	}
 	_, err := m.db.Exec(`INSERT INTO hitl_conversation_configs
-		(conversation_id, enabled, mode, sensitive_tools, timeout_seconds, updated_at)
-		VALUES (?, ?, ?, ?, ?, ?)
+		(conversation_id, enabled, mode, reviewer, sensitive_tools, timeout_seconds, updated_at)
+		VALUES (?, ?, ?, ?, ?, ?, ?)
 		ON CONFLICT(conversation_id) DO UPDATE SET
-		enabled=excluded.enabled, mode=excluded.mode, sensitive_tools=excluded.sensitive_tools, timeout_seconds=excluded.timeout_seconds, updated_at=excluded.updated_at`,
-		conversationID, boolToInt(req.Enabled), mode, string(tools), timeout, time.Now())
+		enabled=excluded.enabled, mode=excluded.mode, reviewer=excluded.reviewer, sensitive_tools=excluded.sensitive_tools, timeout_seconds=excluded.timeout_seconds, updated_at=excluded.updated_at`,
+		conversationID, boolToInt(req.Enabled), mode, normalizeHitlReviewer(req.Reviewer), string(tools), timeout, time.Now())
 	return err
 }

 func (m *HITLManager) LoadConversationConfig(conversationID string) (*HITLRequest, error) {
 	var enabledInt int
-	var mode, toolsJSON string
+	var mode, reviewer, toolsJSON string
 	var timeout int
-	err := m.db.QueryRow(`SELECT enabled, mode, sensitive_tools, timeout_seconds FROM hitl_conversation_configs WHERE conversation_id = ?`, conversationID).
-		Scan(&enabledInt, &mode, &toolsJSON, &timeout)
+	err := m.db.QueryRow(`SELECT enabled, mode, COALESCE(reviewer,'human'), sensitive_tools, timeout_seconds FROM hitl_conversation_configs WHERE conversation_id = ?`, conversationID).
+		Scan(&enabledInt, &mode, &reviewer, &toolsJSON, &timeout)
 	if errors.Is(err, sql.ErrNoRows) {
-		return &HITLRequest{Enabled: false, Mode: "off", SensitiveTools: []string{}, TimeoutSeconds: 0}, nil
+		return &HITLRequest{Enabled: false, Mode: "off", Reviewer: "human", SensitiveTools: []string{}, TimeoutSeconds: 0}, nil
 	}
 	if err != nil {
 		return nil, err
@@ -390,11 +383,24 @@ func (m *HITLManager) LoadConversationConfig(conversationID string) (*HITLReques
 	return &HITLRequest{
 		Enabled:        enabledInt == 1,
 		Mode:           mode,
+		Reviewer:       normalizeHitlReviewer(reviewer),
 		SensitiveTools: tools,
 		TimeoutSeconds: timeout,
 	}, nil
 }

+func (m *HITLManager) HasConversationConfig(conversationID string) (bool, error) {
+	if strings.TrimSpace(conversationID) == "" {
+		return false, nil
+	}
+	var one int
+	err := m.db.QueryRow(`SELECT 1 FROM hitl_conversation_configs WHERE conversation_id = ? LIMIT 1`, conversationID).Scan(&one)
+	if errors.Is(err, sql.ErrNoRows) {
+		return false, nil
+	}
+	return err == nil, err
+}
+
 func (m *HITLManager) waitDecision(ctx context.Context, p *pendingInterrupt, timeout time.Duration) (hitlDecision, error) {
 	defer func() {
 		m.mu.Lock()
@@ -413,15 +419,16 @@ func (m *HITLManager) waitDecision(ctx context.Context, p *pendingInterrupt, tim
 		if p.Mode != "review_edit" && len(d.EditedArguments) > 0 {
 			d.EditedArguments = nil
 		}
-		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='decided', decision=?, decision_comment=?, decided_at=? WHERE id=?`,
+		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='decided', decision=?, decision_comment=?, decided_at=?, decided_by='human' WHERE id=?`,
 			d.Decision, d.Comment, time.Now(), p.InterruptID)
 		return d, nil
 	case <-timeoutCh:
-		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='timeout', decision='approve', decision_comment='timeout auto approve', decided_at=? WHERE id=?`,
-			time.Now(), p.InterruptID)
-		return hitlDecision{Decision: "approve", Comment: "timeout auto approve"}, nil
+		comment := "HITL timeout auto-reject for safety"
+		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='timeout', decision='reject', decision_comment=?, decided_at=?, decided_by='system' WHERE id=?`,
+			comment, time.Now(), p.InterruptID)
+		return hitlDecision{Decision: "reject", Comment: comment}, nil
 	case <-ctx.Done():
-		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='cancelled', decision='reject', decision_comment='task cancelled', decided_at=? WHERE id=?`,
+		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='cancelled', decision='reject', decision_comment='task cancelled', decided_at=?, decided_by='system' WHERE id=?`,
 			time.Now(), p.InterruptID)
 		return hitlDecision{Decision: "reject", Comment: "task cancelled"}, ctx.Err()
 	}
@@ -432,25 +439,88 @@ func (h *AgentHandler) activateHITLForConversation(conversationID string, req *H
 		return
 	}
 	if req == nil {
-		cfg, err := h.hitlManager.LoadConversationConfig(conversationID)
+		cfg, err := h.loadHITLConversationConfig(conversationID)
 		if err == nil {
 			req = cfg
 		}
 	}
+	if req != nil && strings.TrimSpace(req.Reviewer) == "" {
+		req.Reviewer = h.hitlEffectiveDefaultReviewer()
+	}
 	h.hitlManager.ActivateConversation(conversationID, h.hitlRequestWithMergedConfigWhitelist(req))
 }

+func (h *AgentHandler) loadHITLConversationConfig(conversationID string) (*HITLRequest, error) {
+	cfg, err := h.hitlManager.LoadConversationConfig(conversationID)
+	if err != nil {
+		return nil, err
+	}
+	has, err := h.hitlManager.HasConversationConfig(conversationID)
+	if err != nil {
+		return nil, err
+	}
+	if !has {
+		cfg.Reviewer = h.hitlEffectiveDefaultReviewer()
+	}
+	return cfg, nil
+}
+
 func (h *AgentHandler) waitHITLApproval(runCtx context.Context, cancelRun context.CancelCauseFunc, conversationID, assistantMessageID, toolName, toolCallID string, payload map[string]interface{}, sendEventFunc func(eventType, message string, data interface{})) (*hitlDecision, error) {
 	cfg, need := h.hitlManager.shouldInterrupt(conversationID, toolName)
 	if !need {
 		return nil, nil
 	}
+	h.enrichHitlApprovalPayload(conversationID, assistantMessageID, payload)
 	payloadRaw, _ := json.Marshal(payload)
 	p, err := h.hitlManager.CreatePendingInterrupt(conversationID, assistantMessageID, cfg.Mode, toolName, toolCallID, string(payloadRaw))
 	if err != nil {
 		h.logger.Warn("创建 HITL 中断失败", zap.Error(err))
 		return nil, err
 	}
+
+	if cfg.Reviewer == "audit_agent" {
+		ad := h.auditAgentReview(runCtx, cfg.Mode, toolName, payload)
+		now := time.Now()
+		_, _ = h.db.Exec(`UPDATE hitl_interrupts SET status='decided', decision=?, decision_comment=?, decided_at=?, decided_by='audit_agent' WHERE id=?`,
+			ad.Decision, ad.Comment, now, p.InterruptID)
+		if sendEventFunc != nil {
+			sendEventFunc("hitl_audit_agent", "审计 Agent 已裁决", map[string]interface{}{
+				"conversationId": conversationID,
+				"interruptId":    p.InterruptID,
+				"toolName":       toolName,
+				"mode":           cfg.Mode,
+				"decision":       ad.Decision,
+				"comment":        ad.Comment,
+				"editedArgs":     ad.EditedArguments,
+				"decidedBy":      "audit_agent",
+			})
+		}
+		if ad.Decision == "reject" {
+			if sendEventFunc != nil {
+				sendEventFunc("hitl_rejected", "审计 Agent 拒绝本次工具调用", map[string]interface{}{
+					"conversationId": conversationID,
+					"interruptId":    p.InterruptID,
+					"toolName":       toolName,
+					"comment":        ad.Comment,
+					"decidedBy":      "audit_agent",
+				})
+			}
+			return &ad, nil
+		}
+		if sendEventFunc != nil {
+			sendEventFunc("hitl_resumed", "审计 Agent 已通过，继续执行", map[string]interface{}{
+				"conversationId": conversationID,
+				"interruptId":    p.InterruptID,
+				"toolName":       toolName,
+				"comment":        ad.Comment,
+				"editedArgs":     ad.EditedArguments,
+				"decidedBy":      "audit_agent",
+			})
+		}
+		h.hitlManager.TrackApprovedHitlExecution(p.InterruptID, conversationID, toolName, toolCallID)
+		return &ad, nil
+	}
+
 	if sendEventFunc != nil {
 		sendEventFunc("hitl_interrupt", "命中人机协同审批", map[string]interface{}{
 			"conversationId": conversationID,
@@ -479,8 +549,12 @@ func (h *AgentHandler) waitHITLApproval(runCtx context.Context, cancelRun contex
 		return nil, waitErr
 	}
 	if d.Decision == "reject" {
+		rejectMsg := "人工拒绝本次工具调用，模型将基于反馈继续迭代"
+		if strings.Contains(strings.ToLower(strings.TrimSpace(d.Comment)), "timeout") {
+			rejectMsg = "审批超时，安全起见已自动拒绝，模型将基于反馈继续迭代"
+		}
 		if sendEventFunc != nil {
-			sendEventFunc("hitl_rejected", "人工拒绝本次工具调用，模型将基于反馈继续迭代", map[string]interface{}{
+			sendEventFunc("hitl_rejected", rejectMsg, map[string]interface{}{
 				"conversationId": conversationID,
 				"interruptId":    p.InterruptID,
 				"toolName":       toolName,
@@ -498,6 +572,7 @@ func (h *AgentHandler) waitHITLApproval(runCtx context.Context, cancelRun contex
 			"editedArgs":     d.EditedArguments,
 		})
 	}
+	h.hitlManager.TrackApprovedHitlExecution(p.InterruptID, conversationID, toolName, toolCallID)
 	return &d, nil
 }

@@ -527,11 +602,6 @@ func (h *AgentHandler) handleHITLToolCall(runCtx context.Context, cancelRun cont
 }

 func (h *AgentHandler) ListHITLPending(c *gin.Context) {
-	conversationID := strings.TrimSpace(c.Query("conversationId"))
-	status := strings.TrimSpace(c.Query("status"))
-	if status == "" {
-		status = "pending"
-	}
 	page, _ := strconv.Atoi(c.DefaultQuery("page", "1"))
 	if page < 1 {
 		page = 1
@@ -539,15 +609,12 @@ func (h *AgentHandler) ListHITLPending(c *gin.Context) {
 	pageSize, _ := strconv.Atoi(c.DefaultQuery("pageSize", "20"))
 	pageSize = int(math.Max(1, math.Min(float64(pageSize), 200)))
 	offset := (page - 1) * pageSize
-	q := `SELECT id, conversation_id, message_id, mode, tool_name, tool_call_id, payload, status, decision, decision_comment, created_at, decided_at FROM hitl_interrupts WHERE 1=1`
-	args := []interface{}{}
-	if conversationID != "" {
-		q += " AND conversation_id = ?"
-		args = append(args, conversationID)
-	}
-	if status != "all" {
-		q += " AND status = ?"
-		args = append(args, status)
+	q, args := h.buildHitlListQuery(false)
+	q, args = h.appendHitlListFilters(q, args, c)
+	total, err := h.countHitlQuery(q, args)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
 	}
 	q += " ORDER BY created_at DESC LIMIT ? OFFSET ?"
 	args = append(args, pageSize, offset)
@@ -557,41 +624,12 @@ func (h *AgentHandler) ListHITLPending(c *gin.Context) {
 		return
 	}
 	defer rows.Close()
-	items := make([]map[string]interface{}, 0)
-	for rows.Next() {
-		var id, cid, mode, toolName, toolCallID, payload, rowStatus string
-		var messageID sql.NullString
-		var decision, comment sql.NullString
-		var createdAt time.Time
-		var decidedAt sql.NullTime
-		if err := rows.Scan(&id, &cid, &messageID, &mode, &toolName, &toolCallID, &payload, &rowStatus, &decision, &comment, &createdAt, &decidedAt); err != nil {
-			continue
-		}
-		msgID := ""
-		if messageID.Valid {
-			msgID = messageID.String
-		}
-		items = append(items, map[string]interface{}{
-			"id":             id,
-			"conversationId": cid,
-			"messageId":      msgID,
-			"mode":           mode,
-			"toolName":       toolName,
-			"toolCallId":     toolCallID,
-			"payload":        payload,
-			"status":         rowStatus,
-			"decision":       decision.String,
-			"comment":        comment.String,
-			"createdAt":      createdAt,
-			"decidedAt": func() interface{} {
-				if decidedAt.Valid {
-					return decidedAt.Time
-				}
-				return nil
-			}(),
-		})
+	items, err := h.scanHitlInterruptRows(rows)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
 	}
-	c.JSON(http.StatusOK, gin.H{"items": items, "page": page, "pageSize": pageSize})
+	c.JSON(http.StatusOK, gin.H{"items": items, "page": page, "pageSize": pageSize, "total": total})
 }

 type hitlDecisionReq struct {
@@ -636,7 +674,7 @@ func (h *AgentHandler) DismissHITLInterrupt(c *gin.Context) {
 		return
 	}
 	res, err := h.db.Exec(`UPDATE hitl_interrupts SET status='cancelled', decision='reject',
-		decision_comment='dismissed by user', decided_at=CURRENT_TIMESTAMP
+		decision_comment='dismissed by user', decided_at=CURRENT_TIMESTAMP, decided_by='human'
 		WHERE id=? AND status='pending'`, req.InterruptID)
 	if err != nil {
 		c.JSON(500, gin.H{"error": err.Error()})
@@ -702,7 +740,7 @@ func (h *AgentHandler) GetHITLConversationConfig(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": "conversationId is required"})
 		return
 	}
-	cfg, err := h.hitlManager.LoadConversationConfig(conversationID)
+	cfg, err := h.loadHITLConversationConfig(conversationID)
 	if err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
 		return
@@ -721,6 +759,7 @@ func (h *AgentHandler) GetHITLConversationConfig(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{
 		"conversationId":          conversationID,
 		"hitl":                    cfg,
+		"defaultReviewer":         h.hitlEffectiveDefaultReviewer(),
 		"hitlGlobalToolWhitelist": h.hitlConfigGlobalToolWhitelist(),
 	})
 }
@@ -732,6 +771,10 @@ func (h *AgentHandler) UpsertHITLConversationConfig(c *gin.Context) {
 		return
 	}
 	req.Mode = normalizeHitlMode(req.Mode)
+	req.Reviewer = normalizeHitlReviewer(req.Reviewer)
+	if strings.TrimSpace(req.Reviewer) == "" {
+		req.Reviewer = h.hitlEffectiveDefaultReviewer()
+	}
 	if err := h.hitlManager.SaveConversationConfig(req.ConversationID, &req.HITLRequest); err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
 		return
@@ -753,6 +796,85 @@ type mergeHitlGlobalWhitelistReq struct {
 	SensitiveTools []string `json:"sensitiveTools"`
 }

+type setHitlGlobalWhitelistReq struct {
+	ToolWhitelist []string `json:"toolWhitelist"`
+}
+
+// GetHITLGlobalToolWhitelist 返回 config.yaml 中的全局免审批工具白名单。
+func (h *AgentHandler) GetHITLGlobalToolWhitelist(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{
+		"toolWhitelist":   h.hitlConfigGlobalToolWhitelist(),
+		"defaultReviewer": h.hitlEffectiveDefaultReviewer(),
+	})
+}
+
+type setHitlDefaultReviewerReq struct {
+	Reviewer string `json:"reviewer"`
+}
+
+// GetHITLDefaultReviewer 返回 config.yaml 中的全局默认审批方。
+func (h *AgentHandler) GetHITLDefaultReviewer(c *gin.Context) {
+	c.JSON(http.StatusOK, gin.H{
+		"defaultReviewer": h.hitlEffectiveDefaultReviewer(),
+	})
+}
+
+// UpdateHITLDefaultReviewer 将全局默认审批方写入 config.yaml（未选会话时切换审批方）。
+func (h *AgentHandler) UpdateHITLDefaultReviewer(c *gin.Context) {
+	if h.hitlDefaultReviewerSaver == nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "HITL 配置持久化不可用"})
+		return
+	}
+	var req setHitlDefaultReviewerReq
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	reviewer := normalizeHitlReviewer(req.Reviewer)
+	if err := h.hitlDefaultReviewerSaver.UpdateHitlDefaultReviewer(reviewer); err != nil {
+		h.logger.Warn("写入 HITL 默认审批方到 config.yaml 失败", zap.Error(err))
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if h.config != nil {
+		h.config.Hitl.DefaultReviewer = reviewer
+	}
+	if h.audit != nil {
+		h.audit.RecordOK(c, "hitl", "default_reviewer_update", "HITL 全局默认审批方更新", "hitl_config", "default_reviewer", nil)
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"ok":              true,
+		"defaultReviewer": reviewer,
+	})
+}
+
+// SetHITLGlobalToolWhitelist 整表替换 config.yaml 中的全局免审批工具白名单。
+func (h *AgentHandler) SetHITLGlobalToolWhitelist(c *gin.Context) {
+	if h.hitlWhitelistSaver == nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "HITL 配置持久化不可用"})
+		return
+	}
+	var req setHitlGlobalWhitelistReq
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	if err := h.hitlWhitelistSaver.SetHitlToolWhitelist(req.ToolWhitelist); err != nil {
+		h.logger.Warn("写入 HITL 工具白名单到 config.yaml 失败", zap.Error(err))
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if h.audit != nil {
+		h.audit.RecordOK(c, "hitl", "tool_whitelist_update", "HITL 全局白名单更新", "hitl_config", "tool_whitelist", nil)
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"ok":                      true,
+		"toolWhitelist":           h.hitlConfigGlobalToolWhitelist(),
+		"hitlGlobalToolWhitelist":   h.hitlConfigGlobalToolWhitelist(),
+		"hitlGlobalWhitelistMerged": false,
+	})
+}
+
 // MergeHITLGlobalToolWhitelist 无会话 ID 时将侧栏提交的免审批工具合并进 config.yaml（与 PUT /hitl/config 中白名单落盘规则一致）。
 func (h *AgentHandler) MergeHITLGlobalToolWhitelist(c *gin.Context) {
 	if h.hitlWhitelistSaver == nil {
@@ -0,0 +1,357 @@
+package handler
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+// auditAgentReview 在 reviewer=audit_agent 时由 LLM 代行审批。
+// 白名单工具在 shouldInterrupt 阶段已跳过，到达此处的一律需要裁决。
+func (h *AgentHandler) auditAgentReview(ctx context.Context, hitlMode, toolName string, payload map[string]interface{}) hitlDecision {
+	if h == nil {
+		return hitlDecision{Decision: "reject", Comment: "audit agent: handler unavailable"}
+	}
+	mode := normalizeHitlMode(hitlMode)
+	prompt := config.DefaultHitlAuditAgentPrompt()
+	if h.config != nil {
+		prompt = h.config.Hitl.EffectiveAuditAgentPromptForMode(mode)
+	}
+	if h.auditLLM == nil {
+		return hitlDecision{Decision: "reject", Comment: "audit agent: LLM 未配置"}
+	}
+	if ctx == nil {
+		ctx = context.Background()
+	}
+	callCtx, cancel := context.WithTimeout(ctx, 90*time.Second)
+	defer cancel()
+
+	userContent := buildAuditAgentReviewInput(mode, toolName, payload)
+	requestBody := map[string]interface{}{
+		"model": h.auditLLMModel(),
+		"messages": []map[string]interface{}{
+			{"role": "system", "content": prompt},
+			{"role": "user", "content": userContent},
+		},
+		"temperature":           0.1,
+		"max_completion_tokens": 1024,
+		// 审计裁决需要结构化 JSON；关闭 thinking 避免 Qwen 等把正文放进 reasoning_content 导致解析失败。
+		"thinking": map[string]interface{}{"type": "disabled"},
+	}
+
+	var apiResponse struct {
+		Choices []struct {
+			Message struct {
+				Content          string `json:"content"`
+				ReasoningContent string `json:"reasoning_content"`
+			} `json:"message"`
+		} `json:"choices"`
+	}
+	if err := h.auditLLM.ChatCompletion(callCtx, requestBody, &apiResponse); err != nil {
+		h.logger.Warn("审计 Agent LLM 调用失败", zap.Error(err), zap.String("tool", toolName))
+		return hitlDecision{
+			Decision: "reject",
+			Comment:  "audit agent: LLM 调用失败，保守拒绝",
+		}
+	}
+	if len(apiResponse.Choices) == 0 {
+		return hitlDecision{Decision: "reject", Comment: "audit agent: LLM 无有效响应，保守拒绝"}
+	}
+	msg := apiResponse.Choices[0].Message
+	raw := strings.TrimSpace(msg.Content)
+	if raw == "" {
+		raw = strings.TrimSpace(msg.ReasoningContent)
+	}
+	dec, err := parseAuditAgentLLMContent(raw)
+	if err != nil {
+		snippet := raw
+		if len(snippet) > 240 {
+			snippet = snippet[:240] + "..."
+		}
+		h.logger.Warn("审计 Agent 响应解析失败",
+			zap.Error(err),
+			zap.String("tool", toolName),
+			zap.String("mode", mode),
+			zap.String("snippet", snippet),
+		)
+		return hitlDecision{Decision: "reject", Comment: "audit agent: 响应无法解析，保守拒绝"}
+	}
+	if mode != "review_edit" && len(dec.EditedArguments) > 0 {
+		h.logger.Warn("审计 Agent 在审批模式下返回 editedArguments，已忽略",
+			zap.String("tool", toolName),
+		)
+		dec.EditedArguments = nil
+	}
+	if dec.Comment == "" {
+		dec.Comment = "audit agent: " + dec.Decision
+	} else if !strings.HasPrefix(strings.ToLower(dec.Comment), "audit agent") {
+		dec.Comment = "audit agent: " + dec.Comment
+	}
+	return dec
+}
+
+func (h *AgentHandler) auditLLMModel() string {
+	if h.config != nil && strings.TrimSpace(h.config.OpenAI.Model) != "" {
+		return strings.TrimSpace(h.config.OpenAI.Model)
+	}
+	return ""
+}
+
+func buildAuditAgentReviewInput(hitlMode, toolName string, payload map[string]interface{}) string {
+	review := map[string]interface{}{
+		"hitlMode": normalizeHitlMode(hitlMode),
+		"toolName": strings.TrimSpace(toolName),
+	}
+	if payload != nil {
+		for _, k := range []string{"arguments", "argumentsObj", "command", hitlPayloadUserMessage, hitlPayloadThinking, hitlPayloadReasoningChain, hitlPayloadPlanning} {
+			if v, ok := payload[k]; ok && v != nil && fmt.Sprint(v) != "" {
+				review[k] = v
+			}
+		}
+	}
+	b, err := json.MarshalIndent(review, "", "  ")
+	if err != nil {
+		return fmt.Sprintf(`{"hitlMode":%q,"toolName":%q}`, normalizeHitlMode(hitlMode), toolName)
+	}
+	return string(b)
+}
+
+func parseAuditAgentLLMContent(content string) (hitlDecision, error) {
+	s := strings.TrimSpace(content)
+	if s == "" {
+		return hitlDecision{}, errors.New("empty content")
+	}
+	for _, candidate := range auditAgentJSONCandidates(s) {
+		dec, comment, editedArgs, err := parseAuditAgentDecisionObject(candidate)
+		if err == nil {
+			return hitlDecision{
+				Decision:        dec,
+				Comment:         comment,
+				EditedArguments: editedArgs,
+			}, nil
+		}
+	}
+	return hitlDecision{}, fmt.Errorf("no valid decision json in response")
+}
+
+func auditAgentJSONCandidates(s string) []string {
+	out := make([]string, 0, 4)
+	seen := make(map[string]struct{})
+	add := func(c string) {
+		c = strings.TrimSpace(c)
+		if c == "" {
+			return
+		}
+		if _, ok := seen[c]; ok {
+			return
+		}
+		seen[c] = struct{}{}
+		out = append(out, c)
+	}
+	add(s)
+	add(stripMarkdownCodeFence(s))
+	if obj := extractFirstJSONObject(s); obj != "" {
+		add(obj)
+	}
+	if obj := extractFirstJSONObject(stripMarkdownCodeFence(s)); obj != "" {
+		add(obj)
+	}
+	return out
+}
+
+func stripMarkdownCodeFence(s string) string {
+	s = strings.TrimSpace(s)
+	for _, fence := range []string{"```json", "```JSON", "```"} {
+		if strings.HasPrefix(s, fence) {
+			s = strings.TrimPrefix(s, fence)
+		}
+	}
+	s = strings.TrimSuffix(s, "```")
+	return strings.TrimSpace(s)
+}
+
+func extractFirstJSONObject(s string) string {
+	start := strings.Index(s, "{")
+	if start < 0 {
+		return ""
+	}
+	depth := 0
+	inStr := false
+	esc := false
+	for i := start; i < len(s); i++ {
+		ch := s[i]
+		if inStr {
+			if esc {
+				esc = false
+				continue
+			}
+			if ch == '\\' {
+				esc = true
+				continue
+			}
+			if ch == '"' {
+				inStr = false
+			}
+			continue
+		}
+		switch ch {
+		case '"':
+			inStr = true
+		case '{':
+			depth++
+		case '}':
+			depth--
+			if depth == 0 {
+				return s[start : i+1]
+			}
+		}
+	}
+	return ""
+}
+
+func parseAuditAgentDecisionObject(jsonText string) (decision, comment string, editedArgs map[string]interface{}, err error) {
+	var parsed map[string]interface{}
+	if err := json.Unmarshal([]byte(jsonText), &parsed); err != nil {
+		return "", "", nil, err
+	}
+	rawDecision := auditAgentPickString(parsed, "decision", "Decision", "result", "action", "verdict", "决策", "决定")
+	decision = normalizeAuditAgentDecision(rawDecision)
+	if decision == "" {
+		return "", "", nil, fmt.Errorf("missing decision")
+	}
+	comment = auditAgentPickString(parsed, "comment", "Comment", "reason", "message", "rationale", "备注", "理由", "说明")
+	editedArgs = auditAgentPickObject(parsed, "editedArguments", "edited_arguments", "editedArgs")
+	return decision, strings.TrimSpace(comment), editedArgs, nil
+}
+
+func auditAgentPickString(m map[string]interface{}, keys ...string) string {
+	for _, k := range keys {
+		if v, ok := m[k]; ok && v != nil {
+			s := strings.TrimSpace(fmt.Sprint(v))
+			if s != "" {
+				return s
+			}
+		}
+	}
+	return ""
+}
+
+func auditAgentPickObject(m map[string]interface{}, keys ...string) map[string]interface{} {
+	for _, k := range keys {
+		v, ok := m[k]
+		if !ok || v == nil {
+			continue
+		}
+		switch t := v.(type) {
+		case map[string]interface{}:
+			if len(t) > 0 {
+				return t
+			}
+		case string:
+			s := strings.TrimSpace(t)
+			if s == "" || s == "{}" {
+				continue
+			}
+			var obj map[string]interface{}
+			if err := json.Unmarshal([]byte(s), &obj); err == nil && len(obj) > 0 {
+				return obj
+			}
+		}
+	}
+	return nil
+}
+
+func normalizeAuditAgentDecision(v string) string {
+	d := strings.ToLower(strings.TrimSpace(v))
+	switch d {
+	case "approve", "approved", "pass", "passed", "allow", "allowed", "yes", "ok", "accept", "accepted":
+		return "approve"
+	case "reject", "rejected", "deny", "denied", "no", "block", "blocked", "refuse", "refused":
+		return "reject"
+	}
+	switch strings.TrimSpace(v) {
+	case "通过", "批准", "允许", "同意", "放行":
+		return "approve"
+	case "拒绝", "驳回", "禁止", "否决":
+		return "reject"
+	}
+	return ""
+}
+
+type hitlAuditStrategyReq struct {
+	AuditAgentPrompt           string `json:"auditAgentPrompt"`
+	AuditAgentPromptReviewEdit string `json:"auditAgentPromptReviewEdit"`
+}
+
+func (h *AgentHandler) GetHITLAuditStrategy(c *gin.Context) {
+	approvalPrompt := config.DefaultHitlAuditAgentPrompt()
+	reviewEditPrompt := config.DefaultHitlAuditAgentPromptReviewEdit()
+	approvalCustom := false
+	reviewEditCustom := false
+	if h.config != nil {
+		approvalPrompt = h.config.Hitl.EffectiveAuditAgentPromptForMode("approval")
+		reviewEditPrompt = h.config.Hitl.EffectiveAuditAgentPromptForMode("review_edit")
+		approvalCustom = strings.TrimSpace(h.config.Hitl.AuditAgentPrompt) != ""
+		reviewEditCustom = strings.TrimSpace(h.config.Hitl.AuditAgentPromptReviewEdit) != ""
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"auditAgentPrompt":                  approvalPrompt,
+		"auditAgentPromptCustom":            approvalCustom,
+		"auditAgentPromptReviewEdit":        reviewEditPrompt,
+		"auditAgentPromptReviewEditCustom":  reviewEditCustom,
+		"defaultAuditAgentPrompt":           config.DefaultHitlAuditAgentPrompt(),
+		"defaultAuditAgentPromptReviewEdit": config.DefaultHitlAuditAgentPromptReviewEdit(),
+	})
+}
+
+func (h *AgentHandler) UpdateHITLAuditStrategy(c *gin.Context) {
+	if h.hitlStrategySaver == nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": "HITL 策略持久化不可用"})
+		return
+	}
+	var req hitlAuditStrategyReq
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	approvalPrompt := strings.TrimSpace(req.AuditAgentPrompt)
+	reviewEditPrompt := strings.TrimSpace(req.AuditAgentPromptReviewEdit)
+	if err := h.hitlStrategySaver.UpdateHitlAuditAgentStrategy(approvalPrompt, reviewEditPrompt); err != nil {
+		h.logger.Warn("保存审计 Agent 提示词失败", zap.Error(err))
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if h.audit != nil {
+		h.audit.RecordOK(c, "hitl", "audit_strategy_update", "HITL 审计策略更新", "hitl_config", "audit_agent_prompt", nil)
+	}
+	if h.config != nil {
+		h.config.Hitl.AuditAgentPrompt = approvalPrompt
+		h.config.Hitl.AuditAgentPromptReviewEdit = reviewEditPrompt
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"ok":                                true,
+		"auditAgentPrompt":                  config.HitlConfig{AuditAgentPrompt: approvalPrompt}.EffectiveAuditAgentPromptForMode("approval"),
+		"auditAgentPromptCustom":            approvalPrompt != "",
+		"auditAgentPromptReviewEdit":        config.HitlConfig{AuditAgentPromptReviewEdit: reviewEditPrompt}.EffectiveAuditAgentPromptForMode("review_edit"),
+		"auditAgentPromptReviewEditCustom":  reviewEditPrompt != "",
+	})
+}
+
+// HitlAuditStrategySaver 持久化审计 Agent 提示词到 config.yaml。
+type HitlAuditStrategySaver interface {
+	UpdateHitlAuditAgentStrategy(approvalPrompt, reviewEditPrompt string) error
+}
+
+// SetHitlAuditStrategySaver 设置审计策略落盘。
+func (h *AgentHandler) SetHitlAuditStrategySaver(s HitlAuditStrategySaver) {
+	h.hitlStrategySaver = s
+}
@@ -0,0 +1,88 @@
+package handler
+
+import (
+	"strings"
+	"testing"
+)
+
+func TestParseAuditAgentLLMContentApprove(t *testing.T) {
+	d, err := parseAuditAgentLLMContent(`{"decision":"approve","comment":"与任务一致"}`)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if d.Decision != "approve" || d.Comment != "与任务一致" {
+		t.Fatalf("unexpected %+v", d)
+	}
+}
+
+func TestParseAuditAgentLLMContentReject(t *testing.T) {
+	d, err := parseAuditAgentLLMContent("```json\n{\"decision\":\"reject\",\"comment\":\"风险过高\"}\n```")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if d.Decision != "reject" {
+		t.Fatalf("expected reject, got %s", d.Decision)
+	}
+}
+
+func TestParseAuditAgentLLMContentInvalid(t *testing.T) {
+	_, err := parseAuditAgentLLMContent(`{"decision":"maybe"}`)
+	if err == nil {
+		t.Fatal("expected error for invalid decision")
+	}
+}
+
+func TestParseAuditAgentLLMContentProseWrapped(t *testing.T) {
+	d, err := parseAuditAgentLLMContent("好的，裁决如下：\n```json\n{\"decision\":\"approve\",\"comment\":\"只读 ls\"}\n```\n以上。")
+	if err != nil {
+		t.Fatal(err)
+	}
+	if d.Decision != "approve" {
+		t.Fatalf("expected approve, got %s", d.Decision)
+	}
+}
+
+func TestParseAuditAgentLLMContentChineseDecision(t *testing.T) {
+	d, err := parseAuditAgentLLMContent(`{"decision":"通过","comment":"风险低"}`)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if d.Decision != "approve" {
+		t.Fatalf("expected approve, got %s", d.Decision)
+	}
+}
+
+func TestParseAuditAgentLLMContentWithEditedArguments(t *testing.T) {
+	d, err := parseAuditAgentLLMContent(`{"decision":"approve","comment":"收窄路径","editedArguments":{"path":"/safe"}}`)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if d.Decision != "approve" {
+		t.Fatalf("expected approve, got %s", d.Decision)
+	}
+	if d.EditedArguments == nil || d.EditedArguments["path"] != "/safe" {
+		t.Fatalf("unexpected edited args: %+v", d.EditedArguments)
+	}
+}
+
+func TestBuildAuditAgentReviewInputIncludesMode(t *testing.T) {
+	s := buildAuditAgentReviewInput("review_edit", "execute", map[string]interface{}{
+		"arguments": `{"command":"pwd"}`,
+	})
+	if !strings.Contains(s, "review_edit") || !strings.Contains(s, "execute") {
+		t.Fatalf("unexpected input: %s", s)
+	}
+}
+
+func TestBuildAuditAgentReviewInput(t *testing.T) {
+	s := buildAuditAgentReviewInput("approval", "nmap", map[string]interface{}{
+		"arguments":   `{"target":"10.0.0.1"}`,
+		"userMessage": "扫描内网",
+	})
+	if s == "" {
+		t.Fatal("expected non-empty input")
+	}
+	if !strings.Contains(s, "nmap") || !strings.Contains(s, "10.0.0.1") || !strings.Contains(s, "扫描内网") {
+		t.Fatalf("unexpected input: %s", s)
+	}
+}
@@ -0,0 +1,97 @@
+package handler
+
+import (
+	"strings"
+)
+
+type hitlCognitionState struct {
+	AssistantMessageID string
+	UserMessage        string
+	Thinking           string
+	ReasoningChain     string
+	Planning           string
+}
+
+// GetHitlCognition 返回当前运行任务上缓存的本轮 HITL 上下文（不含会话历史）。
+func (m *AgentTaskManager) GetHitlCognition(conversationID string) hitlCognitionFields {
+	conversationID = strings.TrimSpace(conversationID)
+	if m == nil || conversationID == "" {
+		return hitlCognitionFields{}
+	}
+	m.mu.RLock()
+	defer m.mu.RUnlock()
+	t, ok := m.tasks[conversationID]
+	if !ok || t == nil || t.hitlCognition == nil {
+		return hitlCognitionFields{}
+	}
+	c := t.hitlCognition
+	return hitlCognitionFields{
+		UserMessage:    c.UserMessage,
+		Thinking:       c.Thinking,
+		ReasoningChain: c.ReasoningChain,
+		Planning:       c.Planning,
+	}
+}
+
+// ResetHitlCognition 新任务开始时重置本轮 HITL 上下文。
+func (m *AgentTaskManager) ResetHitlCognition(conversationID, userMessage string) {
+	conversationID = strings.TrimSpace(conversationID)
+	if m == nil || conversationID == "" {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	t, ok := m.tasks[conversationID]
+	if !ok || t == nil {
+		return
+	}
+	t.hitlCognition = &hitlCognitionState{UserMessage: strings.TrimSpace(userMessage)}
+}
+
+// SetHitlAssistantMessageID 记录当前助手消息 ID，供 HITL 与 DB 回退对齐。
+func (m *AgentTaskManager) SetHitlAssistantMessageID(conversationID, assistantMessageID string) {
+	conversationID = strings.TrimSpace(conversationID)
+	assistantMessageID = strings.TrimSpace(assistantMessageID)
+	if m == nil || conversationID == "" || assistantMessageID == "" {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	t, ok := m.tasks[conversationID]
+	if !ok || t == nil {
+		return
+	}
+	if t.hitlCognition == nil {
+		t.hitlCognition = &hitlCognitionState{}
+	}
+	t.hitlCognition.AssistantMessageID = assistantMessageID
+}
+
+// UpdateHitlCognitionSnapshot 从进行中的进度流快照更新 thinking / reasoning / planning。
+func (m *AgentTaskManager) UpdateHitlCognitionSnapshot(conversationID, assistantMessageID, thinking, reasoningChain, planning string) {
+	conversationID = strings.TrimSpace(conversationID)
+	if m == nil || conversationID == "" {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	t, ok := m.tasks[conversationID]
+	if !ok || t == nil {
+		return
+	}
+	if t.hitlCognition == nil {
+		t.hitlCognition = &hitlCognitionState{}
+	}
+	if id := strings.TrimSpace(assistantMessageID); id != "" {
+		t.hitlCognition.AssistantMessageID = id
+	}
+	if s := strings.TrimSpace(thinking); s != "" {
+		t.hitlCognition.Thinking = s
+	}
+	if s := strings.TrimSpace(reasoningChain); s != "" {
+		t.hitlCognition.ReasoningChain = s
+	}
+	if s := strings.TrimSpace(planning); s != "" {
+		t.hitlCognition.Planning = s
+	}
+}
@@ -0,0 +1,102 @@
+package handler
+
+import (
+	"strings"
+)
+
+const (
+	hitlPayloadUserMessage    = "userMessage"
+	hitlPayloadThinking       = "thinking"
+	hitlPayloadReasoningChain = "reasoningChain"
+	hitlPayloadPlanning       = "planning"
+)
+
+type hitlCognitionFields struct {
+	UserMessage    string
+	Thinking       string
+	ReasoningChain string
+	Planning       string
+}
+
+func (h *AgentHandler) enrichHitlApprovalPayload(conversationID, assistantMessageID string, payload map[string]interface{}) {
+	if h == nil || payload == nil {
+		return
+	}
+	cog := h.collectHitlCognition(conversationID, assistantMessageID)
+	if s := strings.TrimSpace(cog.UserMessage); s != "" {
+		payload[hitlPayloadUserMessage] = s
+	}
+	if s := strings.TrimSpace(cog.Thinking); s != "" {
+		payload[hitlPayloadThinking] = s
+	}
+	if s := strings.TrimSpace(cog.ReasoningChain); s != "" {
+		payload[hitlPayloadReasoningChain] = s
+	}
+	if s := strings.TrimSpace(cog.Planning); s != "" {
+		payload[hitlPayloadPlanning] = s
+	}
+}
+
+func (h *AgentHandler) collectHitlCognition(conversationID, assistantMessageID string) hitlCognitionFields {
+	var out hitlCognitionFields
+	if h.tasks != nil {
+		out = h.tasks.GetHitlCognition(conversationID)
+	}
+	if strings.TrimSpace(out.UserMessage) == "" && h.db != nil {
+		if msg, err := h.db.GetTurnUserMessage(conversationID, assistantMessageID); err == nil {
+			out.UserMessage = msg
+		}
+	}
+	if h.db != nil && assistantMessageID != "" {
+		dbCog, err := h.db.GetAssistantCognitionTexts(assistantMessageID)
+		if err == nil {
+			if strings.TrimSpace(out.Thinking) == "" {
+				out.Thinking = dbCog.Thinking
+			}
+			if strings.TrimSpace(out.ReasoningChain) == "" {
+				out.ReasoningChain = dbCog.ReasoningChain
+			}
+			if strings.TrimSpace(out.Planning) == "" {
+				out.Planning = dbCog.Planning
+			}
+		}
+	}
+	return out
+}
+
+func snapshotHitlCognitionFromStreams(thinkingStreams map[string]*thinkingBuf, respPlan *responsePlanAgg) (thinking, reasoningChain, planning string) {
+	if len(thinkingStreams) > 0 {
+		var thinkingParts, reasoningParts []string
+		for _, tb := range thinkingStreams {
+			if tb == nil {
+				continue
+			}
+			content := strings.TrimSpace(tb.b.String())
+			if content == "" {
+				continue
+			}
+			if tb.persistAs == "reasoning_chain" {
+				reasoningParts = append(reasoningParts, content)
+			} else {
+				thinkingParts = append(thinkingParts, content)
+			}
+		}
+		thinking = strings.Join(thinkingParts, "\n\n")
+		reasoningChain = strings.Join(reasoningParts, "\n\n")
+	}
+	if respPlan != nil {
+		planning = strings.TrimSpace(respPlan.b.String())
+	}
+	return thinking, reasoningChain, planning
+}
+
+func (h *AgentHandler) syncHitlCognitionFromProgress(conversationID, assistantMessageID string, thinkingStreams map[string]*thinkingBuf, respPlan *responsePlanAgg) {
+	if h == nil || h.tasks == nil {
+		return
+	}
+	thinking, reasoning, planning := snapshotHitlCognitionFromStreams(thinkingStreams, respPlan)
+	if thinking == "" && reasoning == "" && planning == "" {
+		return
+	}
+	h.tasks.UpdateHitlCognitionSnapshot(conversationID, assistantMessageID, thinking, reasoning, planning)
+}
@@ -0,0 +1,46 @@
+package handler
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"cyberstrike-ai/internal/database"
+
+	"go.uber.org/zap"
+)
+
+func TestEnrichHitlApprovalPayload(t *testing.T) {
+	tmp := t.TempDir()
+	db, err := database.NewDB(filepath.Join(tmp, "test.sqlite"), zap.NewNop())
+	if err != nil {
+		t.Fatalf("db: %v", err)
+	}
+	defer os.RemoveAll(tmp)
+
+	conv, err := db.CreateConversation("hitl ctx", database.ConversationCreateMeta{})
+	if err != nil {
+		t.Fatalf("conv: %v", err)
+	}
+	if _, err := db.AddMessage(conv.ID, "user", "scan 10.0.0.1 please", nil); err != nil {
+		t.Fatalf("user msg: %v", err)
+	}
+	asst, err := db.AddMessage(conv.ID, "assistant", "", nil)
+	if err != nil {
+		t.Fatalf("asst msg: %v", err)
+	}
+	if err := db.AddProcessDetail(asst.ID, conv.ID, "thinking", "need port scan first", nil); err != nil {
+		t.Fatalf("detail: %v", err)
+	}
+
+	h := &AgentHandler{db: db, tasks: NewAgentTaskManager()}
+	payload := map[string]interface{}{"toolName": "nmap", "arguments": "{}"}
+	h.enrichHitlApprovalPayload(conv.ID, asst.ID, payload)
+
+	if got := payload["userMessage"]; got != "scan 10.0.0.1 please" {
+		t.Fatalf("userMessage=%v", got)
+	}
+	if got := payload["thinking"]; got != "need port scan first" {
+		t.Fatalf("thinking=%v", got)
+	}
+}
@@ -0,0 +1,132 @@
+package handler
+
+import (
+	"encoding/json"
+	"strings"
+	"time"
+)
+
+const hitlPayloadExecutionResult = "executionResult"
+
+type hitlExecutionResult struct {
+	Success    bool      `json:"success"`
+	Result     string    `json:"result,omitempty"`
+	ToolName   string    `json:"toolName,omitempty"`
+	ToolCallID string    `json:"toolCallId,omitempty"`
+	RecordedAt time.Time `json:"recordedAt"`
+}
+
+type hitlApprovedExecTrack struct {
+	InterruptID    string
+	ConversationID string
+	ToolName       string
+	ToolCallID     string
+}
+
+// TrackApprovedHitlExecution 审批通过后登记，待 tool_result 回写执行结果。
+func (m *HITLManager) TrackApprovedHitlExecution(interruptID, conversationID, toolName, toolCallID string) {
+	if m == nil {
+		return
+	}
+	interruptID = strings.TrimSpace(interruptID)
+	conversationID = strings.TrimSpace(conversationID)
+	if interruptID == "" || conversationID == "" {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if m.approvedExec == nil {
+		m.approvedExec = make(map[string][]hitlApprovedExecTrack)
+	}
+	m.approvedExec[conversationID] = append(m.approvedExec[conversationID], hitlApprovedExecTrack{
+		InterruptID:    interruptID,
+		ConversationID: conversationID,
+		ToolName:       strings.TrimSpace(toolName),
+		ToolCallID:     strings.TrimSpace(toolCallID),
+	})
+}
+
+func (m *HITLManager) popApprovedInterruptForTool(conversationID, toolCallID, toolName string) string {
+	if m == nil {
+		return ""
+	}
+	conversationID = strings.TrimSpace(conversationID)
+	toolCallID = strings.TrimSpace(toolCallID)
+	toolName = strings.TrimSpace(toolName)
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	queue := m.approvedExec[conversationID]
+	if len(queue) == 0 {
+		return ""
+	}
+	idx := -1
+	if toolCallID != "" {
+		for i, t := range queue {
+			if t.ToolCallID == toolCallID {
+				idx = i
+				break
+			}
+		}
+	}
+	if idx < 0 && toolName != "" {
+		for i, t := range queue {
+			if strings.EqualFold(t.ToolName, toolName) {
+				idx = i
+				break
+			}
+		}
+	}
+	if idx < 0 {
+		return ""
+	}
+	id := queue[idx].InterruptID
+	queue = append(queue[:idx], queue[idx+1:]...)
+	if len(queue) == 0 {
+		delete(m.approvedExec, conversationID)
+	} else {
+		m.approvedExec[conversationID] = queue
+	}
+	return id
+}
+
+func mergeHitlPayloadExecutionResult(payloadJSON string, exec hitlExecutionResult) (string, error) {
+	root := make(map[string]interface{})
+	if strings.TrimSpace(payloadJSON) != "" {
+		_ = json.Unmarshal([]byte(payloadJSON), &root)
+	}
+	if root == nil {
+		root = make(map[string]interface{})
+	}
+	root[hitlPayloadExecutionResult] = exec
+	out, err := json.Marshal(root)
+	if err != nil {
+		return payloadJSON, err
+	}
+	return string(out), nil
+}
+
+func (h *AgentHandler) recordHitlToolExecutionResult(conversationID, toolCallID, toolName string, success bool, result string) {
+	if h == nil || h.hitlManager == nil || h.db == nil {
+		return
+	}
+	interruptID := h.hitlManager.popApprovedInterruptForTool(conversationID, toolCallID, toolName)
+	if interruptID == "" {
+		return
+	}
+	var payloadJSON string
+	err := h.db.QueryRow(`SELECT payload FROM hitl_interrupts WHERE id = ?`, interruptID).Scan(&payloadJSON)
+	if err != nil {
+		return
+	}
+	merged, err := mergeHitlPayloadExecutionResult(payloadJSON, hitlExecutionResult{
+		Success:    success,
+		Result:     strings.TrimSpace(result),
+		ToolName:   strings.TrimSpace(toolName),
+		ToolCallID: strings.TrimSpace(toolCallID),
+		RecordedAt: time.Now(),
+	})
+	if err != nil {
+		return
+	}
+	_, _ = h.db.Exec(`UPDATE hitl_interrupts SET payload = ? WHERE id = ?`, merged, interruptID)
+}
@@ -0,0 +1,39 @@
+package handler
+
+import (
+	"encoding/json"
+	"testing"
+)
+
+func TestMergeHitlPayloadExecutionResult(t *testing.T) {
+	merged, err := mergeHitlPayloadExecutionResult(`{"userMessage":"hi","toolName":"nmap"}`, hitlExecutionResult{
+		Success: true,
+		Result:  "open ports: 80",
+	})
+	if err != nil {
+		t.Fatal(err)
+	}
+	var root map[string]interface{}
+	if err := json.Unmarshal([]byte(merged), &root); err != nil {
+		t.Fatal(err)
+	}
+	if root["userMessage"] != "hi" {
+		t.Fatalf("userMessage lost: %v", root["userMessage"])
+	}
+	exec, ok := root["executionResult"].(map[string]interface{})
+	if !ok || exec["success"] != true {
+		t.Fatalf("executionResult missing: %v", root["executionResult"])
+	}
+}
+
+func TestPopApprovedInterruptForTool(t *testing.T) {
+	m := NewHITLManager(nil, nil)
+	m.TrackApprovedHitlExecution("hitl_a", "conv1", "nmap", "tc1")
+	m.TrackApprovedHitlExecution("hitl_b", "conv1", "exec", "")
+	if id := m.popApprovedInterruptForTool("conv1", "tc1", "nmap"); id != "hitl_a" {
+		t.Fatalf("tc1 match=%q", id)
+	}
+	if id := m.popApprovedInterruptForTool("conv1", "", "exec"); id != "hitl_b" {
+		t.Fatalf("tool name match=%q", id)
+	}
+}
@@ -0,0 +1,263 @@
+package handler
+
+import (
+	"database/sql"
+	"errors"
+	"math"
+	"net/http"
+	"strconv"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/gin-gonic/gin"
+)
+
+func normalizeHitlReviewer(v string) string {
+	switch strings.ToLower(strings.TrimSpace(v)) {
+	case "audit_agent", "agent", "ai":
+		return "audit_agent"
+	default:
+		return "human"
+	}
+}
+
+func normalizeHitlDecidedBy(v string) string {
+	switch strings.ToLower(strings.TrimSpace(v)) {
+	case "audit_agent", "agent", "ai":
+		return "audit_agent"
+	case "system", "timeout":
+		return "system"
+	case "manual":
+		return "manual"
+	default:
+		return "human"
+	}
+}
+
+func (m *HITLManager) migrateHitlSchemaColumns() {
+	_, _ = m.db.Exec(`ALTER TABLE hitl_interrupts ADD COLUMN decided_by TEXT NOT NULL DEFAULT 'human'`)
+	_, _ = m.db.Exec(`ALTER TABLE hitl_conversation_configs ADD COLUMN reviewer TEXT NOT NULL DEFAULT 'human'`)
+}
+
+func hitlInterruptRowToMap(
+	id, cid, mode, toolName, toolCallID, payload, rowStatus, decidedBy string,
+	messageID sql.NullString,
+	decision, comment sql.NullString,
+	createdAt time.Time,
+	decidedAt sql.NullTime,
+) map[string]interface{} {
+	msgID := ""
+	if messageID.Valid {
+		msgID = messageID.String
+	}
+	return map[string]interface{}{
+		"id":             id,
+		"conversationId": cid,
+		"messageId":      msgID,
+		"mode":           mode,
+		"toolName":       toolName,
+		"toolCallId":     toolCallID,
+		"payload":        payload,
+		"status":         rowStatus,
+		"decision":       decision.String,
+		"comment":        comment.String,
+		"decidedBy":      decidedBy,
+		"createdAt":      createdAt,
+		"decidedAt": func() interface{} {
+			if decidedAt.Valid {
+				return decidedAt.Time
+			}
+			return nil
+		}(),
+	}
+}
+
+func (h *AgentHandler) buildHitlListQuery(logs bool) (string, []interface{}) {
+	where, args := h.buildHitlLogsWhere(logs)
+	q := `SELECT id, conversation_id, message_id, mode, tool_name, tool_call_id, payload, status, decision, decision_comment, COALESCE(decided_by,'human'), created_at, decided_at FROM hitl_interrupts` + where
+	return q, args
+}
+
+func (h *AgentHandler) buildHitlLogsWhere(logs bool) (string, []interface{}) {
+	q := " WHERE 1=1"
+	args := []interface{}{}
+	if logs {
+		q += " AND status != 'pending'"
+	} else {
+		q += " AND status = 'pending'"
+	}
+	return q, args
+}
+
+func (h *AgentHandler) appendHitlListFilters(q string, args []interface{}, c *gin.Context) (string, []interface{}) {
+	conversationID := strings.TrimSpace(c.Query("conversationId"))
+	toolName := strings.TrimSpace(c.Query("toolName"))
+	decision := strings.TrimSpace(c.Query("decision"))
+	decidedBy := strings.TrimSpace(c.Query("decidedBy"))
+	status := strings.TrimSpace(c.Query("status"))
+	search := strings.TrimSpace(c.Query("q"))
+
+	if conversationID != "" {
+		q += " AND conversation_id = ?"
+		args = append(args, conversationID)
+	}
+	if toolName != "" {
+		q += " AND tool_name LIKE ?"
+		args = append(args, "%"+toolName+"%")
+	}
+	if decision != "" && decision != "all" {
+		q += " AND decision = ?"
+		args = append(args, decision)
+	}
+	if decidedBy != "" && decidedBy != "all" {
+		q += " AND COALESCE(decided_by,'human') = ?"
+		args = append(args, normalizeHitlDecidedBy(decidedBy))
+	}
+	if status != "" && status != "all" {
+		q += " AND status = ?"
+		args = append(args, status)
+	}
+	if search != "" {
+		like := "%" + search + "%"
+		q += " AND (id LIKE ? OR conversation_id LIKE ? OR tool_name LIKE ? OR payload LIKE ? OR COALESCE(decision_comment,'') LIKE ?)"
+		args = append(args, like, like, like, like, like)
+	}
+	return q, args
+}
+
+func (h *AgentHandler) scanHitlInterruptRows(rows *sql.Rows) ([]map[string]interface{}, error) {
+	items := make([]map[string]interface{}, 0)
+	for rows.Next() {
+		var id, cid, mode, toolName, toolCallID, payload, rowStatus, decidedBy string
+		var messageID sql.NullString
+		var decision, comment sql.NullString
+		var createdAt time.Time
+		var decidedAt sql.NullTime
+		if err := rows.Scan(&id, &cid, &messageID, &mode, &toolName, &toolCallID, &payload, &rowStatus, &decision, &comment, &decidedBy, &createdAt, &decidedAt); err != nil {
+			continue
+		}
+		items = append(items, hitlInterruptRowToMap(id, cid, mode, toolName, toolCallID, payload, rowStatus, decidedBy, messageID, decision, comment, createdAt, decidedAt))
+	}
+	return items, nil
+}
+
+func (h *AgentHandler) countHitlQuery(baseQ string, args []interface{}) (int, error) {
+	countQ := "SELECT COUNT(*) FROM (" + baseQ + ") AS hitl_cnt"
+	var total int
+	if err := h.db.QueryRow(countQ, args...).Scan(&total); err != nil {
+		return 0, err
+	}
+	return total, nil
+}
+
+func (h *AgentHandler) ListHITLLogs(c *gin.Context) {
+	page, _ := strconv.Atoi(c.DefaultQuery("page", "1"))
+	if page < 1 {
+		page = 1
+	}
+	pageSize, _ := strconv.Atoi(c.DefaultQuery("pageSize", "20"))
+	pageSize = int(math.Max(1, math.Min(float64(pageSize), 200)))
+	offset := (page - 1) * pageSize
+
+	q, args := h.buildHitlListQuery(true)
+	q, args = h.appendHitlListFilters(q, args, c)
+	total, err := h.countHitlQuery(q, args)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	q += " ORDER BY COALESCE(decided_at, created_at) DESC LIMIT ? OFFSET ?"
+	args = append(args, pageSize, offset)
+	rows, err := h.db.Query(q, args...)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	defer rows.Close()
+	items, err := h.scanHitlInterruptRows(rows)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"items": items, "page": page, "pageSize": pageSize, "total": total, "retentionDays": h.hitlRetentionDays()})
+}
+
+func (h *AgentHandler) hitlRetentionDays() int {
+	if h.config != nil {
+		return h.config.Hitl.RetentionDaysEffective()
+	}
+	return config.HitlConfig{}.RetentionDaysEffective()
+}
+
+// DeleteHITLLogs 批量删除或按筛选清空已决策的人机协同审计日志（不删除 pending）。
+func (h *AgentHandler) DeleteHITLLogs(c *gin.Context) {
+	var request struct {
+		IDs []string `json:"ids"`
+		All bool     `json:"all"`
+	}
+	if err := c.ShouldBindJSON(&request); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "请求参数无效: " + err.Error()})
+		return
+	}
+
+	var deleted int64
+	var err error
+	if request.All {
+		where, args := h.buildHitlLogsWhere(true)
+		where, args = h.appendHitlListFilters(where, args, c)
+		deleted, err = h.db.DeleteHitlInterruptLogsMatching(where, args)
+		if err != nil {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+			return
+		}
+		if h.audit != nil {
+			h.audit.RecordOK(c, "hitl", "logs_clear", "清空人机协同审计日志", "hitl_interrupt", "", map[string]interface{}{
+				"deleted": deleted,
+			})
+		}
+	} else {
+		if len(request.IDs) == 0 {
+			c.JSON(http.StatusBadRequest, gin.H{"error": "审计日志 ID 列表不能为空"})
+			return
+		}
+		deleted, err = h.db.DeleteHitlInterruptLogsByIDs(request.IDs)
+		if err != nil {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+			return
+		}
+		if h.audit != nil {
+			h.audit.RecordOK(c, "hitl", "logs_delete_batch", "批量删除人机协同审计日志", "hitl_interrupt", "", map[string]interface{}{
+				"count":   len(request.IDs),
+				"deleted": deleted,
+			})
+		}
+	}
+
+	c.JSON(http.StatusOK, gin.H{"message": "删除成功", "deleted": deleted})
+}
+
+func (h *AgentHandler) GetHITLLog(c *gin.Context) {
+	id := strings.TrimSpace(c.Param("id"))
+	if id == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "id is required"})
+		return
+	}
+	q := `SELECT id, conversation_id, message_id, mode, tool_name, tool_call_id, payload, status, decision, decision_comment, COALESCE(decided_by,'human'), created_at, decided_at FROM hitl_interrupts WHERE id = ?`
+	var rowID, cid, mode, toolName, toolCallID, payload, rowStatus, decidedBy string
+	var messageID sql.NullString
+	var decision, comment sql.NullString
+	var createdAt time.Time
+	var decidedAt sql.NullTime
+	err := h.db.QueryRow(q, id).Scan(&rowID, &cid, &messageID, &mode, &toolName, &toolCallID, &payload, &rowStatus, &decision, &comment, &decidedBy, &createdAt, &decidedAt)
+	if errors.Is(err, sql.ErrNoRows) {
+		c.JSON(http.StatusNotFound, gin.H{"error": "not found"})
+		return
+	}
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, hitlInterruptRowToMap(rowID, cid, mode, toolName, toolCallID, payload, rowStatus, decidedBy, messageID, decision, comment, createdAt, decidedAt))
+}
@@ -5,13 +5,16 @@ import (
 	"errors"
 	"io"
 	"net/http"
+	"sort"
 	"strconv"
 	"strings"
 	"time"

 	"cyberstrike-ai/internal/audit"
+	"cyberstrike-ai/internal/config"
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/mcp"
+	"cyberstrike-ai/internal/monitor"
 	"cyberstrike-ai/internal/security"
 	"github.com/gin-gonic/gin"
 	"go.uber.org/zap"
@@ -19,12 +22,20 @@ import (

 // MonitorHandler 监控处理器
 type MonitorHandler struct {
-	mcpServer      *mcp.Server
-	externalMCPMgr *mcp.ExternalMCPManager
-	executor       *security.Executor
-	db             *database.DB
-	logger         *zap.Logger
-	audit          *audit.Service
+	mcpServer        *mcp.Server
+	externalMCPMgr   *mcp.ExternalMCPManager
+	taskManager      *AgentTaskManager
+	agentHandler     *AgentHandler
+	executor         *security.Executor
+	db               *database.DB
+	logger           *zap.Logger
+	audit            *audit.Service
+	monitorRetention *monitor.Service
+}
+
+// SetMonitorRetention wires MCP execution retention settings.
+func (h *MonitorHandler) SetMonitorRetention(s *monitor.Service) {
+	h.monitorRetention = s
 }

 // SetAudit wires platform audit logging.
@@ -48,15 +59,44 @@ func (h *MonitorHandler) SetExternalMCPManager(mgr *mcp.ExternalMCPManager) {
 	h.externalMCPMgr = mgr
 }

+// SetTaskManager 设置 Agent 任务管理器（用于 Eino execute 等按 executionId 终止）。
+func (h *MonitorHandler) SetTaskManager(mgr *AgentTaskManager) {
+	h.taskManager = mgr
+}
+
+// SetAgentHandler 设置 Agent 处理器（MCP 监控终止与对话页「中断并继续」共用逻辑）。
+func (h *MonitorHandler) SetAgentHandler(ah *AgentHandler) {
+	h.agentHandler = ah
+}
+
+const monitorPageTopTools = 6
+
+// MonitorStatsSummary 工具调用汇总
+type MonitorStatsSummary struct {
+	TotalCalls   int        `json:"totalCalls"`
+	SuccessCalls int        `json:"successCalls"`
+	FailedCalls  int        `json:"failedCalls"`
+	LastCallTime *time.Time `json:"lastCallTime,omitempty"`
+	ToolCount    int        `json:"toolCount"`
+}
+
 // MonitorResponse 监控响应
 type MonitorResponse struct {
-	Executions []*mcp.ToolExecution      `json:"executions"`
-	Stats      map[string]*mcp.ToolStats `json:"stats"`
-	Timestamp  time.Time                 `json:"timestamp"`
-	Total      int                       `json:"total,omitempty"`
-	Page       int                       `json:"page,omitempty"`
-	PageSize   int                       `json:"page_size,omitempty"`
-	TotalPages int                       `json:"total_pages,omitempty"`
+	Executions    []*mcp.ToolExecution `json:"executions"`
+	Summary       *MonitorStatsSummary `json:"summary"`
+	TopTools      []*mcp.ToolStats     `json:"topTools"`
+	Timestamp     time.Time            `json:"timestamp"`
+	Total         int                  `json:"total"`
+	Page          int                  `json:"page"`
+	PageSize      int                  `json:"pageSize"`
+	TotalPages    int                  `json:"totalPages"`
+	RetentionDays int                  `json:"retentionDays"`
+}
+
+// StatsResponse 统计信息响应（Dashboard 等）
+type StatsResponse struct {
+	Summary  *MonitorStatsSummary `json:"summary"`
+	TopTools []*mcp.ToolStats     `json:"topTools"`
 }

 // Monitor 获取监控信息
@@ -80,8 +120,9 @@ func (h *MonitorHandler) Monitor(c *gin.Context) {
 	// 解析工具筛选参数（兼容 mcp__tool 与内部 mcp::tool）
 	toolName := normalizeToolNameFilter(c.Query("tool"))

-	executions, total := h.loadExecutionsWithPagination(page, pageSize, status, toolName)
-	stats := h.loadStats()
+	executions, total := h.loadExecutionListWithPagination(page, pageSize, status, toolName)
+	h.enrichExecutionsConversationID(executions)
+	summary, topTools := h.loadStatsSummary(monitorPageTopTools)

 	totalPages := (total + pageSize - 1) / pageSize
 	if totalPages == 0 {
@@ -89,21 +130,136 @@ func (h *MonitorHandler) Monitor(c *gin.Context) {
 	}

 	c.JSON(http.StatusOK, MonitorResponse{
-		Executions: executions,
-		Stats:      stats,
-		Timestamp:  time.Now(),
-		Total:      total,
-		Page:       page,
-		PageSize:   pageSize,
-		TotalPages: totalPages,
+		Executions:    executions,
+		Summary:       summary,
+		TopTools:      topTools,
+		Timestamp:     time.Now(),
+		Total:         total,
+		Page:          page,
+		PageSize:      pageSize,
+		TotalPages:    totalPages,
+		RetentionDays: h.monitorRetentionDays(),
 	})
 }

+func (h *MonitorHandler) monitorRetentionDays() int {
+	if h.monitorRetention != nil {
+		return h.monitorRetention.RetentionDays()
+	}
+	return config.MonitorConfig{}.RetentionDaysEffective()
+}
+
 func (h *MonitorHandler) loadExecutions() []*mcp.ToolExecution {
 	executions, _ := h.loadExecutionsWithPagination(1, 1000, "", "")
 	return executions
 }

+func (h *MonitorHandler) loadExecutionListWithPagination(page, pageSize int, status, toolName string) ([]*mcp.ToolExecution, int) {
+	if h.db == nil {
+		allExecutions := h.mcpServer.GetAllExecutions()
+		if status != "" || toolName != "" {
+			filtered := make([]*mcp.ToolExecution, 0)
+			for _, exec := range allExecutions {
+				matchStatus := status == "" || exec.Status == status
+				matchTool := toolNameFilterMatches(exec.ToolName, toolName)
+				if matchStatus && matchTool {
+					filtered = append(filtered, exec)
+				}
+			}
+			allExecutions = filtered
+		}
+		total := len(allExecutions)
+		offset := (page - 1) * pageSize
+		end := offset + pageSize
+		if end > total {
+			end = total
+		}
+		if offset >= total {
+			return []*mcp.ToolExecution{}, total
+		}
+		pageSlice := allExecutions[offset:end]
+		out := make([]*mcp.ToolExecution, 0, len(pageSlice))
+		for _, exec := range pageSlice {
+			if exec == nil {
+				continue
+			}
+			out = append(out, slimToolExecution(exec))
+		}
+		return out, total
+	}
+
+	offset := (page - 1) * pageSize
+	executions, err := h.db.LoadToolExecutionListPage(offset, pageSize, status, toolName)
+	if err != nil {
+		h.logger.Warn("从数据库加载执行记录列表失败，回退到内存数据", zap.Error(err))
+		return h.loadExecutionListWithPaginationFromMemory(page, pageSize, status, toolName)
+	}
+
+	total, err := h.db.CountToolExecutions(status, toolName)
+	if err != nil {
+		h.logger.Warn("获取执行记录总数失败", zap.Error(err))
+		total = offset + len(executions)
+		if len(executions) == pageSize {
+			total = offset + len(executions) + 1
+		}
+	}
+
+	return executions, total
+}
+
+func (h *MonitorHandler) loadExecutionListWithPaginationFromMemory(page, pageSize int, status, toolName string) ([]*mcp.ToolExecution, int) {
+	allExecutions := h.mcpServer.GetAllExecutions()
+	if status != "" || toolName != "" {
+		filtered := make([]*mcp.ToolExecution, 0)
+		for _, exec := range allExecutions {
+			matchStatus := status == "" || exec.Status == status
+			matchTool := toolNameFilterMatches(exec.ToolName, toolName)
+			if matchStatus && matchTool {
+				filtered = append(filtered, exec)
+			}
+		}
+		allExecutions = filtered
+	}
+	total := len(allExecutions)
+	offset := (page - 1) * pageSize
+	end := offset + pageSize
+	if end > total {
+		end = total
+	}
+	if offset >= total {
+		return []*mcp.ToolExecution{}, total
+	}
+	pageSlice := allExecutions[offset:end]
+	out := make([]*mcp.ToolExecution, 0, len(pageSlice))
+	for _, exec := range pageSlice {
+		if exec == nil {
+			continue
+		}
+		out = append(out, slimToolExecution(exec))
+	}
+	return out, total
+}
+
+func slimToolExecution(exec *mcp.ToolExecution) *mcp.ToolExecution {
+	if exec == nil {
+		return nil
+	}
+	slim := &mcp.ToolExecution{
+		ID:        exec.ID,
+		ToolName:  exec.ToolName,
+		Status:    exec.Status,
+		StartTime: exec.StartTime,
+	}
+	if exec.EndTime != nil {
+		end := *exec.EndTime
+		slim.EndTime = &end
+	}
+	if exec.Duration > 0 {
+		slim.Duration = exec.Duration
+	}
+	return slim
+}
+
 func (h *MonitorHandler) loadExecutionsWithPagination(page, pageSize int, status, toolName string) ([]*mcp.ToolExecution, int) {
 	if h.db == nil {
 		allExecutions := h.mcpServer.GetAllExecutions()
@@ -176,7 +332,78 @@ func (h *MonitorHandler) loadExecutionsWithPagination(page, pageSize int, status
 	return executions, total
 }

-func (h *MonitorHandler) loadStats() map[string]*mcp.ToolStats {
+func (h *MonitorHandler) loadStatsSummary(topN int) (*MonitorStatsSummary, []*mcp.ToolStats) {
+	if topN <= 0 {
+		topN = monitorPageTopTools
+	}
+
+	if h.db != nil {
+		result, err := h.db.LoadToolStatsSummary(topN)
+		if err == nil {
+			return dbStatsSummaryToMonitor(result), result.TopTools
+		}
+		h.logger.Warn("从数据库加载统计汇总失败，回退到内存数据", zap.Error(err))
+	}
+
+	stats := h.loadStatsMap()
+	return summarizeToolStats(stats, topN)
+}
+
+func dbStatsSummaryToMonitor(result *database.ToolStatsSummaryResult) *MonitorStatsSummary {
+	if result == nil {
+		return &MonitorStatsSummary{}
+	}
+	summary := &MonitorStatsSummary{
+		TotalCalls:   result.Summary.TotalCalls,
+		SuccessCalls: result.Summary.SuccessCalls,
+		FailedCalls:  result.Summary.FailedCalls,
+		ToolCount:    result.Summary.ToolCount,
+	}
+	if result.Summary.LastCallTime != nil {
+		t := *result.Summary.LastCallTime
+		summary.LastCallTime = &t
+	}
+	return summary
+}
+
+func summarizeToolStats(stats map[string]*mcp.ToolStats, topN int) (*MonitorStatsSummary, []*mcp.ToolStats) {
+	summary := &MonitorStatsSummary{}
+	if len(stats) == 0 {
+		return summary, nil
+	}
+
+	all := make([]*mcp.ToolStats, 0, len(stats))
+	for _, stat := range stats {
+		if stat == nil {
+			continue
+		}
+		summary.ToolCount++
+		summary.TotalCalls += stat.TotalCalls
+		summary.SuccessCalls += stat.SuccessCalls
+		summary.FailedCalls += stat.FailedCalls
+		if stat.LastCallTime != nil && (summary.LastCallTime == nil || stat.LastCallTime.After(*summary.LastCallTime)) {
+			t := *stat.LastCallTime
+			summary.LastCallTime = &t
+		}
+		if stat.TotalCalls > 0 {
+			statCopy := *stat
+			all = append(all, &statCopy)
+		}
+	}
+
+	sort.Slice(all, func(i, j int) bool {
+		if all[i].TotalCalls == all[j].TotalCalls {
+			return all[i].ToolName < all[j].ToolName
+		}
+		return all[i].TotalCalls > all[j].TotalCalls
+	})
+	if len(all) > topN {
+		all = all[:topN]
+	}
+	return summary, all
+}
+
+func (h *MonitorHandler) loadStatsMap() map[string]*mcp.ToolStats {
 	// 合并内部MCP服务器和外部MCP管理器的统计信息
 	stats := make(map[string]*mcp.ToolStats)

@@ -230,6 +457,7 @@ func (h *MonitorHandler) GetExecution(c *gin.Context) {
 	// 先从内部MCP服务器查找
 	exec, exists := h.mcpServer.GetExecution(id)
 	if exists {
+		h.enrichExecutionsConversationID([]*mcp.ToolExecution{exec})
 		c.JSON(http.StatusOK, exec)
 		return
 	}
@@ -238,6 +466,7 @@ func (h *MonitorHandler) GetExecution(c *gin.Context) {
 	if h.externalMCPMgr != nil {
 		exec, exists = h.externalMCPMgr.GetExecution(id)
 		if exists {
+			h.enrichExecutionsConversationID([]*mcp.ToolExecution{exec})
 			c.JSON(http.StatusOK, exec)
 			return
 		}
@@ -247,6 +476,7 @@ func (h *MonitorHandler) GetExecution(c *gin.Context) {
 	if h.db != nil {
 		exec, err := h.db.GetToolExecution(id)
 		if err == nil && exec != nil {
+			h.enrichExecutionsConversationID([]*mcp.ToolExecution{exec})
 			c.JSON(http.StatusOK, exec)
 			return
 		}
@@ -273,6 +503,19 @@ func (h *MonitorHandler) CancelExecution(c *gin.Context) {
 		return
 	}
 	note = strings.TrimSpace(body.Note)
+
+	convID := h.conversationIDForRunningExecution(id)
+	if convID != "" && h.agentHandler != nil {
+		if ok, payload := h.agentHandler.cancelToolContinueAfter(convID, id, note); ok {
+			h.logger.Info("MCP 监控页终止工具（与对话中断并继续一致）",
+				zap.String("executionId", id),
+				zap.String("conversationId", convID),
+				zap.Bool("hasNote", note != ""),
+			)
+			c.JSON(http.StatusOK, payload)
+			return
+		}
+	}
 	if h.mcpServer.CancelToolExecutionWithNote(id, note) {
 		h.logger.Info("已请求取消 MCP 工具执行", zap.String("executionId", id), zap.String("source", "internal"), zap.Bool("hasNote", note != ""))
 		c.JSON(http.StatusOK, gin.H{"message": "已发送终止信号", "executionId": id})
@@ -286,6 +529,52 @@ func (h *MonitorHandler) CancelExecution(c *gin.Context) {
 	c.JSON(http.StatusNotFound, gin.H{"error": "未找到进行中的工具执行，或该任务已结束"})
 }

+func (h *MonitorHandler) enrichExecutionsConversationID(executions []*mcp.ToolExecution) {
+	for _, exec := range executions {
+		if exec == nil || exec.Status != "running" {
+			continue
+		}
+		exec.ConversationID = h.conversationIDForRunningExecution(exec.ID)
+	}
+}
+
+func (h *MonitorHandler) conversationIDForRunningExecution(executionID string) string {
+	executionID = strings.TrimSpace(executionID)
+	if executionID == "" || h.taskManager == nil {
+		return ""
+	}
+	if conv := h.taskManager.ConversationIDForActiveMCPExecution(executionID); conv != "" {
+		return conv
+	}
+	exec := h.lookupExecution(executionID)
+	if exec == nil || exec.Status != "running" {
+		return ""
+	}
+	if strings.TrimSpace(exec.ToolName) == "execute" {
+		if onlyConv, ok := h.taskManager.ConversationIDForActiveEinoExecute(); ok {
+			return onlyConv
+		}
+	}
+	return ""
+}
+
+func (h *MonitorHandler) lookupExecution(id string) *mcp.ToolExecution {
+	if exec, ok := h.mcpServer.GetExecution(id); ok {
+		return exec
+	}
+	if h.externalMCPMgr != nil {
+		if exec, ok := h.externalMCPMgr.GetExecution(id); ok {
+			return exec
+		}
+	}
+	if h.db != nil {
+		if exec, err := h.db.GetToolExecution(id); err == nil && exec != nil {
+			return exec
+		}
+	}
+	return nil
+}
+
 // BatchGetToolNames 批量获取工具执行的工具名称（消除前端 N+1 请求）
 func (h *MonitorHandler) BatchGetToolNames(c *gin.Context) {
 	var req struct {
@@ -323,8 +612,17 @@ func (h *MonitorHandler) BatchGetToolNames(c *gin.Context) {

 // GetStats 获取统计信息
 func (h *MonitorHandler) GetStats(c *gin.Context) {
-	stats := h.loadStats()
-	c.JSON(http.StatusOK, stats)
+	topN := 30
+	if topStr := c.Query("top"); topStr != "" {
+		if t, err := strconv.Atoi(topStr); err == nil && t > 0 && t <= 100 {
+			topN = t
+		}
+	}
+	summary, topTools := h.loadStatsSummary(topN)
+	c.JSON(http.StatusOK, StatsResponse{
+		Summary:  summary,
+		TopTools: topTools,
+	})
 }

 // CallsTimelinePoint 调用趋势数据点
@@ -133,10 +133,12 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 			"userMessageId":  prep.UserMessageID,
 		})
 	}
+	if h.runRoleWorkflowStreamIfBound(&req, prep, sendEvent) {
+		return
+	}

 	var cancelWithCause context.CancelCauseFunc
 	curFinalMessage := prep.FinalMessage
-	segmentUserMessage := prep.FinalMessage // 本请求原始用户句，临时重试时不得丢失
 	curHistory := prep.History
 	roleTools := prep.RoleTools
 	orch := strings.TrimSpace(req.Orchestration)
@@ -187,10 +189,9 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {

 	// 同一 HTTP 流内多段 Run（如中断并继续）合并 MCP execution id，供最终 response / 库表与工具芯片展示完整列表
 	var cumulativeMCPExecutionIDs []string
-	var transientRunAttempts int
-	var emptyResponseAttempts int
 	// 同一请求内分段续跑时，主代理 iteration 事件按偏移累计，避免 UI 出现「第3轮 → 第1轮」回跳。
 	var mainIterationOffset int
+	var emptyResponseContinueAttempt int

 	for {
 		segmentMainIterationMax := 0
@@ -225,6 +226,7 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 		}
 		taskCtxLoop := mcp.WithMCPConversationID(taskCtx, conversationID)
 		taskCtxLoop = mcp.WithToolRunRegistry(taskCtxLoop, h.tasks)
+		taskCtxLoop = mcp.WithEinoExecuteRunRegistry(taskCtxLoop, h.tasks)
 		taskCtxLoop = multiagent.WithHITLToolInterceptor(taskCtxLoop, func(ctx context.Context, toolName, arguments string) (string, error) {
 			return h.interceptHITLForEinoTool(ctx, cancelWithCause, conversationID, assistantMessageID, sendEvent, toolName, arguments)
 		})
@@ -234,6 +236,7 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 			h.config,
 			&h.config.MultiAgent,
 			h.agent,
+			h.db,
 			h.logger,
 			conversationID,
 			h.conversationProjectID(conversationID),
@@ -244,61 +247,25 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 			h.agentsMarkdownDir,
 			orch,
 			chatReasoningToClientIntent(req.Reasoning),
-			h.projectBlackboardBlock(conversationID),
+			h.agentSessionContextBlock(conversationID),
 		)

 		if result != nil && len(result.MCPExecutionIDs) > 0 {
 			cumulativeMCPExecutionIDs = mergeMCPExecutionIDLists(cumulativeMCPExecutionIDs, result.MCPExecutionIDs)
 		}

-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			baseCtx, conversationID, result, runErr, &emptyResponseAttempts,
-			&curHistory, &curFinalMessage, segmentUserMessage, progressCallback,
-			func(msg string, extra map[string]interface{}) { sendEvent("progress", msg, extra) },
-		)
-		if exhaustedEmpty {
-			runErr = nil
-			transientRunAttempts = 0
-			timeoutCancel()
-			break
-		}
-		if handledEmpty {
-			mainIterationOffset += segmentMainIterationMax
-			transientRunAttempts = 0
-			timeoutCancel()
-			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
-			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
-			taskCtx, timeoutCancel = context.WithTimeout(baseCtx, 600*time.Minute)
-			h.tasks.UpdateTaskStatus(conversationID, "running")
-			continue
-		}
-
 		if runErr == nil {
-			// 任一段成功完成后，重置临时错误重试窗口（次数/退避从头开始）。
-			transientRunAttempts = 0
-			emptyResponseAttempts = 0
+			mw := &h.config.MultiAgent.EinoMiddleware
+			if h.tryContinueOnEinoEmptyResponse(taskCtx, mw, conversationID, result, &emptyResponseContinueAttempt, &curHistory, &curFinalMessage, progressCallback) {
+				mainIterationOffset += segmentMainIterationMax
+				timeoutCancel()
+				baseCtx, cancelWithCause, taskCtx, timeoutCancel = h.rebindEinoRunningTask(conversationID, timeoutCancel)
+				continue
+			}
 			timeoutCancel()
 			break
 		}

-		handled, fatalErr := h.handleEinoTransientRetryContinue(
-			baseCtx, conversationID, result, runErr, &transientRunAttempts,
-			&curHistory, &curFinalMessage, segmentUserMessage, progressCallback,
-			func(msg string, extra map[string]interface{}) { sendEvent("progress", msg, extra) },
-		)
-		if handled {
-			mainIterationOffset += segmentMainIterationMax
-			timeoutCancel()
-			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
-			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
-			taskCtx, timeoutCancel = context.WithTimeout(baseCtx, 600*time.Minute)
-			h.tasks.UpdateTaskStatus(conversationID, "running")
-			continue
-		}
-		if fatalErr != nil {
-			runErr = fatalErr
-		}
-
 		cause := context.Cause(baseCtx)
 		if errors.Is(cause, multiagent.ErrInterruptContinue) {
 			if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
@@ -323,8 +290,6 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 				"source":         "interrupt_continue",
 			})
 			mainIterationOffset += segmentMainIterationMax
-			// 非临时错误分段续跑（用户中断并继续）时，清空 transient 计数，避免跨分段累加。
-			transientRunAttempts = 0
 			timeoutCancel()
 			baseCtx, cancelWithCause = context.WithCancelCause(context.Background())
 			h.tasks.BindTaskCancel(conversationID, cancelWithCause)
@@ -445,6 +410,9 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 	if h.hitlManager != nil {
 		defer h.hitlManager.DeactivateConversation(prep.ConversationID)
 	}
+	if h.runRoleWorkflowJSONIfBound(c, &req, prep) {
+		return
+	}

 	baseCtx, cancelWithCause := context.WithCancelCause(c.Request.Context())
 	defer cancelWithCause(nil)
@@ -459,14 +427,13 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 	curMsg := prep.FinalMessage
 	var result *multiagent.RunResult
 	var runErr error
-	var transientRunAttempts int
-	var emptyResponseAttempts int
 	for {
 		result, runErr = multiagent.RunDeepAgent(
 			taskCtx,
 			h.config,
 			&h.config.MultiAgent,
 			h.agent,
+			h.db,
 			h.logger,
 			prep.ConversationID,
 			h.conversationProjectID(prep.ConversationID),
@@ -477,30 +444,11 @@ func (h *AgentHandler) MultiAgentLoop(c *gin.Context) {
 			h.agentsMarkdownDir,
 			strings.TrimSpace(req.Orchestration),
 			chatReasoningToClientIntent(req.Reasoning),
-			h.projectBlackboardBlock(prep.ConversationID),
+			h.agentSessionContextBlock(prep.ConversationID),
 		)
-		handledEmpty, exhaustedEmpty := h.handleEinoEmptyResponseContinue(
-			baseCtx, prep.ConversationID, result, runErr, &emptyResponseAttempts,
-			&curHist, &curMsg, prep.FinalMessage, progressCallback, nil,
-		)
-		if exhaustedEmpty {
-			runErr = nil
-			break
-		}
-		if handledEmpty {
-			continue
-		}
 		if runErr == nil {
 			break
 		}
-		if handled, fatalErr := h.handleEinoTransientRetryContinue(
-			baseCtx, prep.ConversationID, result, runErr, &transientRunAttempts,
-			&curHist, &curMsg, prep.FinalMessage, progressCallback, nil,
-		); handled {
-			continue
-		} else if fatalErr != nil {
-			runErr = fatalErr
-		}
 		if shouldPersistEinoAgentTraceAfterRunError(baseCtx) {
 			h.persistEinoAgentTraceForResume(prep.ConversationID, result)
 		}
@@ -506,7 +506,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 				},
 				"CreateVulnerabilityRequest": map[string]interface{}{
 					"type":     "object",
-					"required": []string{"conversation_id", "title", "severity"},
+					"required": []string{"conversation_id", "title", "description", "severity", "type", "target", "reproduction_steps", "evidence", "impact", "recommendation"},
 					"properties": map[string]interface{}{
 						"conversation_id": map[string]interface{}{
 							"type":        "string",
@@ -538,10 +538,9 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 							"type":        "string",
 							"description": "受影响的目标",
 						},
-						"proof": map[string]interface{}{
-							"type":        "string",
-							"description": "漏洞证明",
-						},
+						"preconditions":      map[string]interface{}{"type": "string", "description": "前置条件"},
+						"reproduction_steps": map[string]interface{}{"type": "string", "description": "复现步骤"},
+						"evidence":           map[string]interface{}{"type": "string", "description": "证据/POC，包含请求响应、命令输出、截图说明、日志等"},
 						"impact": map[string]interface{}{
 							"type":        "string",
 							"description": "影响",
@@ -550,6 +549,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 							"type":        "string",
 							"description": "修复建议",
 						},
+						"retest_notes": map[string]interface{}{"type": "string", "description": "复测方式"},
 					},
 				},
 				"UpdateVulnerabilityRequest": map[string]interface{}{
@@ -581,10 +581,9 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 							"type":        "string",
 							"description": "受影响的目标",
 						},
-						"proof": map[string]interface{}{
-							"type":        "string",
-							"description": "漏洞证明",
-						},
+						"preconditions":      map[string]interface{}{"type": "string", "description": "前置条件"},
+						"reproduction_steps": map[string]interface{}{"type": "string", "description": "复现步骤"},
+						"evidence":           map[string]interface{}{"type": "string", "description": "证据/POC，包含请求响应、命令输出、截图说明、日志等"},
 						"impact": map[string]interface{}{
 							"type":        "string",
 							"description": "影响",
@@ -593,6 +592,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 							"type":        "string",
 							"description": "修复建议",
 						},
+						"retest_notes": map[string]interface{}{"type": "string", "description": "复测方式"},
 					},
 				},
 				"ListVulnerabilitiesResponse": map[string]interface{}{
@@ -740,14 +740,21 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 					"properties": map[string]interface{}{
 						"executions": map[string]interface{}{
 							"type":        "array",
-							"description": "执行记录列表",
+							"description": "执行记录列表（轻量字段，不含 arguments/result）",
 							"items": map[string]interface{}{
 								"$ref": "#/components/schemas/ToolExecution",
 							},
 						},
-						"stats": map[string]interface{}{
+						"summary": map[string]interface{}{
 							"type":        "object",
-							"description": "统计信息",
+							"description": "工具调用汇总",
+						},
+						"topTools": map[string]interface{}{
+							"type":        "array",
+							"description": "调用量 Top N 工具",
+							"items": map[string]interface{}{
+								"type": "object",
+							},
 						},
 						"timestamp": map[string]interface{}{
 							"type":        "string",
@@ -756,20 +763,24 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 						},
 						"total": map[string]interface{}{
 							"type":        "integer",
-							"description": "总数",
+							"description": "执行记录总数",
 						},
 						"page": map[string]interface{}{
 							"type":        "integer",
 							"description": "当前页",
 						},
-						"page_size": map[string]interface{}{
+						"pageSize": map[string]interface{}{
 							"type":        "integer",
 							"description": "每页数量",
 						},
-						"total_pages": map[string]interface{}{
+						"totalPages": map[string]interface{}{
 							"type":        "integer",
 							"description": "总页数",
 						},
+						"retentionDays": map[string]interface{}{
+							"type":        "integer",
+							"description": "执行记录保留天数",
+						},
 					},
 				},
 				"ConfigResponse": map[string]interface{}{
@@ -794,18 +805,18 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 					"type":        "object",
 					"description": "视觉分析（analyze_image MCP 工具）；enabled 且 model 非空时注册工具",
 					"properties": map[string]interface{}{
-						"enabled":                      map[string]interface{}{"type": "boolean", "description": "是否启用 analyze_image"},
-						"model":                        map[string]interface{}{"type": "string", "description": "视觉模型名（必填）", "example": "qwen-vl-max"},
-						"api_key":                      map[string]interface{}{"type": "string", "description": "API Key；留空复用 openai.api_key"},
-						"base_url":                     map[string]interface{}{"type": "string", "description": "Base URL；留空复用 openai.base_url"},
-						"provider":                     map[string]interface{}{"type": "string", "description": "提供商；留空复用 openai.provider"},
-						"timeout_seconds":              map[string]interface{}{"type": "integer", "description": "VL 调用超时（秒）"},
-						"max_image_bytes":              map[string]interface{}{"type": "integer", "description": "原始文件大小上限（字节）"},
-						"max_dimension":                map[string]interface{}{"type": "integer", "description": "长边缩放像素"},
-						"jpeg_quality":                 map[string]interface{}{"type": "integer", "description": "JPEG 质量 60-100"},
-						"max_payload_bytes":            map[string]interface{}{"type": "integer", "description": "送 API 体积上限（字节）"},
-						"skip_preprocess_below_bytes":  map[string]interface{}{"type": "integer", "description": "低于该字节且尺寸合规时可原图直传；0=始终压缩"},
-						"detail": map[string]interface{}{"type": "string", "enum": []string{"low", "high", "auto"}, "description": "OpenAI 兼容 image detail"},
+						"enabled":                     map[string]interface{}{"type": "boolean", "description": "是否启用 analyze_image"},
+						"model":                       map[string]interface{}{"type": "string", "description": "视觉模型名（必填）", "example": "qwen-vl-max"},
+						"api_key":                     map[string]interface{}{"type": "string", "description": "API Key；留空复用 openai.api_key"},
+						"base_url":                    map[string]interface{}{"type": "string", "description": "Base URL；留空复用 openai.base_url"},
+						"provider":                    map[string]interface{}{"type": "string", "description": "提供商；留空复用 openai.provider"},
+						"timeout_seconds":             map[string]interface{}{"type": "integer", "description": "VL 调用超时（秒）"},
+						"max_image_bytes":             map[string]interface{}{"type": "integer", "description": "原始文件大小上限（字节）"},
+						"max_dimension":               map[string]interface{}{"type": "integer", "description": "长边缩放像素"},
+						"jpeg_quality":                map[string]interface{}{"type": "integer", "description": "JPEG 质量 60-100"},
+						"max_payload_bytes":           map[string]interface{}{"type": "integer", "description": "送 API 体积上限（字节）"},
+						"skip_preprocess_below_bytes": map[string]interface{}{"type": "integer", "description": "低于该字节且尺寸合规时可原图直传；0=始终压缩"},
+						"detail":                      map[string]interface{}{"type": "string", "enum": []string{"low", "high", "auto"}, "description": "OpenAI 兼容 image detail"},
 					},
 				},
 				"AnalyzeImageToolCall": map[string]interface{}{
@@ -1232,6 +1243,34 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 								"type": "string",
 							},
 						},
+						{
+							"name":        "project_id",
+							"in":          "query",
+							"required":    false,
+							"description": "按项目筛选；传 __none__ 表示仅未绑定项目的对话",
+							"schema": map[string]interface{}{
+								"type": "string",
+							},
+						},
+						{
+							"name":        "exclude_grouped",
+							"in":          "query",
+							"required":    false,
+							"description": "为 true 时排除已加入分组的对话（默认在未搜索且未按项目筛选时启用）",
+							"schema": map[string]interface{}{
+								"type": "boolean",
+							},
+						},
+						{
+							"name":        "sort_by",
+							"in":          "query",
+							"required":    false,
+							"description": "排序字段：updated_at（默认）或 created_at",
+							"schema": map[string]interface{}{
+								"type": "string",
+								"enum": []string{"updated_at", "created_at"},
+							},
+						},
 					},
 					"responses": map[string]interface{}{
 						"200": map[string]interface{}{
@@ -1393,7 +1432,7 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 						{
 							"name": "id", "in": "path", "required": true,
 							"description": "对话ID",
-							"schema": map[string]interface{}{"type": "string"},
+							"schema":      map[string]interface{}{"type": "string"},
 						},
 					},
 					"requestBody": map[string]interface{}{
@@ -2464,17 +2503,108 @@ func (h *OpenAPIHandler) GetOpenAPISpec(c *gin.Context) {
 					"parameters": []map[string]interface{}{
 						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
 						{"name": "fact_key", "in": "query", "schema": map[string]interface{}{"type": "string"}},
+						{"name": "include_links", "in": "query", "schema": map[string]interface{}{"type": "boolean"}},
+						{"name": "include_link_counts", "in": "query", "schema": map[string]interface{}{"type": "boolean"}},
 					},
-					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "事实列表或单条"}},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "事实列表或单条（可含 link_counts / outgoing_links）"}},
 				},
 				"post": map[string]interface{}{
 					"tags": []string{"项目管理"}, "summary": "创建/更新事实", "operationId": "upsertProjectFactREST",
 					"parameters": []map[string]interface{}{
 						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
 					},
+					"requestBody": map[string]interface{}{
+						"required": true,
+						"content": map[string]interface{}{
+							"application/json": map[string]interface{}{
+								"schema": map[string]interface{}{
+									"type": "object",
+									"properties": map[string]interface{}{
+										"fact_key": map[string]interface{}{"type": "string"},
+										"summary":  map[string]interface{}{"type": "string"},
+										"links": map[string]interface{}{
+											"type": "array",
+											"items": map[string]interface{}{
+												"type": "object",
+												"properties": map[string]interface{}{
+													"to":   map[string]interface{}{"type": "string"},
+													"type": map[string]interface{}{"type": "string"},
+												},
+											},
+										},
+										"links_text": map[string]interface{}{"type": "string", "description": "type: fact_key 每行一条"},
+									},
+								},
+							},
+						},
+					},
 					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "成功"}},
 				},
 			},
+			"/api/projects/{id}/fact-graph": map[string]interface{}{
+				"get": map[string]interface{}{
+					"tags": []string{"项目管理"}, "summary": "获取项目事实攻击路径图", "operationId": "getProjectFactGraph",
+					"parameters": []map[string]interface{}{
+						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+						{"name": "view", "in": "query", "schema": map[string]interface{}{"type": "string", "enum": []string{"path", "full"}, "default": "path"}},
+						{"name": "exclude_deprecated", "in": "query", "schema": map[string]interface{}{"type": "boolean", "default": true}},
+					},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "nodes + edges"}},
+				},
+			},
+			"/api/projects/{id}/fact-edges": map[string]interface{}{
+				"get": map[string]interface{}{
+					"tags": []string{"项目管理"}, "summary": "列出项目全部事实边", "operationId": "listProjectFactEdges",
+					"parameters": []map[string]interface{}{
+						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+					},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "边列表"}},
+				},
+				"post": map[string]interface{}{
+					"tags": []string{"项目管理"}, "summary": "添加事实边", "operationId": "createProjectFactEdge",
+					"parameters": []map[string]interface{}{
+						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+					},
+					"requestBody": map[string]interface{}{
+						"required": true,
+						"content": map[string]interface{}{
+							"application/json": map[string]interface{}{
+								"schema": map[string]interface{}{
+									"type":     "object",
+									"required": []string{"source_fact_key", "target_fact_key", "edge_type"},
+									"properties": map[string]interface{}{
+										"source_fact_key": map[string]interface{}{"type": "string"},
+										"target_fact_key": map[string]interface{}{"type": "string"},
+										"edge_type":       map[string]interface{}{"type": "string"},
+										"confidence":      map[string]interface{}{"type": "string"},
+									},
+								},
+							},
+						},
+					},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "边已创建"}},
+				},
+			},
+			"/api/projects/{id}/fact-edges/{edgeId}": map[string]interface{}{
+				"delete": map[string]interface{}{
+					"tags": []string{"项目管理"}, "summary": "删除事实边", "operationId": "deleteProjectFactEdge",
+					"parameters": []map[string]interface{}{
+						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+						{"name": "edgeId", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+					},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "删除成功"}},
+				},
+			},
+			"/api/projects/{id}/promote-attack-chain/{conversationId}": map[string]interface{}{
+				"post": map[string]interface{}{
+					"tags": []string{"项目管理"}, "summary": "将对话攻击链沉淀到项目事实图", "operationId": "promoteAttackChainToProject",
+					"parameters": []map[string]interface{}{
+						{"name": "id", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+						{"name": "conversationId", "in": "path", "required": true, "schema": map[string]interface{}{"type": "string"}},
+					},
+					"responses": map[string]interface{}{"200": map[string]interface{}{"description": "沉淀结果（facts/edges/graph）"}},
+				},
+			},
 			"/api/vulnerabilities": map[string]interface{}{
 				"get": map[string]interface{}{
 					"tags":        []string{"漏洞管理"},
@@ -1,10 +1,12 @@
 package handler

 import (
+	"fmt"
 	"net/http"
 	"strconv"
 	"strings"

+	"cyberstrike-ai/internal/attackchain"
 	"cyberstrike-ai/internal/database"
 	"cyberstrike-ai/internal/project"

@@ -223,26 +225,102 @@ func (h *ProjectHandler) DeleteProject(c *gin.Context) {
 	c.JSON(http.StatusOK, gin.H{"success": true})
 }

+type factLinkRequest struct {
+	From       string `json:"from"`
+	Type       string `json:"type"`
+	Confidence string `json:"confidence,omitempty"`
+}
+
 type upsertFactRequest struct {
-	FactKey                string `json:"fact_key" binding:"required"`
-	Category               string `json:"category"`
-	Summary                string `json:"summary" binding:"required"`
-	Body                   string `json:"body"`
-	Confidence             string `json:"confidence"`
-	Pinned                 bool   `json:"pinned"`
-	RelatedVulnerabilityID string `json:"related_vulnerability_id"`
+	FactKey                string            `json:"fact_key" binding:"required"`
+	Category               string            `json:"category"`
+	Summary                string            `json:"summary" binding:"required"`
+	Body                   string            `json:"body"`
+	Confidence             string            `json:"confidence"`
+	Pinned                 bool              `json:"pinned"`
+	RelatedVulnerabilityID string            `json:"related_vulnerability_id"`
+	Links                  []factLinkRequest `json:"links"`
+	LinksText              *string           `json:"links_text"`
 }

 // updateFactRequest 部分更新事实；指针字段省略=不修改，body 传 "" 可清空（仍走 merge 逻辑见 Upsert）。
 type updateFactRequest struct {
-	FactKey                *string `json:"fact_key"`
-	Category               *string `json:"category"`
-	Summary                *string `json:"summary"`
-	Body                   *string `json:"body"`
-	Confidence             *string `json:"confidence"`
-	Pinned                 *bool   `json:"pinned"`
-	RelatedVulnerabilityID *string `json:"related_vulnerability_id"`
-	ClearBody              bool    `json:"clear_body"`
+	FactKey                *string            `json:"fact_key"`
+	Category               *string            `json:"category"`
+	Summary                *string            `json:"summary"`
+	Body                   *string            `json:"body"`
+	Confidence             *string            `json:"confidence"`
+	Pinned                 *bool              `json:"pinned"`
+	RelatedVulnerabilityID *string            `json:"related_vulnerability_id"`
+	ClearBody              bool               `json:"clear_body"`
+	Links                  *[]factLinkRequest `json:"links"`
+	LinksText              *string            `json:"links_text"`
+}
+
+func factLinksFromRequest(links []factLinkRequest, linksText *string) (*project.ParsedFactLinks, error) {
+	if len(links) > 0 {
+		parsed := &project.ParsedFactLinks{}
+		for i, l := range links {
+			from := strings.TrimSpace(l.From)
+			edgeType := strings.TrimSpace(l.Type)
+			if from == "" {
+				return nil, fmt.Errorf("links[%d] 须含 from", i)
+			}
+			if edgeType == "" {
+				return nil, fmt.Errorf("links[%d] 须含 type", i)
+			}
+			parsed.Incoming = append(parsed.Incoming, database.ProjectFactEdgeFromInput{
+				From: from, Type: edgeType, Confidence: strings.TrimSpace(l.Confidence),
+			})
+		}
+		return parsed, nil
+	}
+	if linksText != nil {
+		in, err := project.ParseFactLinksText(*linksText)
+		if err != nil {
+			return nil, err
+		}
+		return &project.ParsedFactLinks{Incoming: in}, nil
+	}
+	return &project.ParsedFactLinks{Incoming: []database.ProjectFactEdgeFromInput{}}, nil
+}
+
+type factWithLinksResponse struct {
+	*database.ProjectFact
+	OutgoingLinks []*database.ProjectFactEdge `json:"outgoing_links,omitempty"`
+	IncomingLinks []*database.ProjectFactEdge `json:"incoming_links,omitempty"`
+	LinkCounts    *project.LinkCounts         `json:"link_counts,omitempty"`
+}
+
+func (h *ProjectHandler) applyFactLinksAfterUpsert(projectID string, fact *database.ProjectFact, links []factLinkRequest, linksText *string, explicitLinks, parseBody bool) error {
+	if explicitLinks {
+		parsed, err := factLinksFromRequest(links, linksText)
+		if err != nil {
+			return err
+		}
+		return project.PersistFactLinksFromParsed(h.db, projectID, fact.FactKey, fact.SourceConversationID, parsed, true)
+	}
+	if parseBody {
+		inputs := project.ParseLinksFromBody(fact.Body)
+		if inputs == nil {
+			return nil
+		}
+		return project.PersistFactIncomingLinks(h.db, projectID, fact.FactKey, inputs, true)
+	}
+	return nil
+}
+
+func (h *ProjectHandler) factResponseWithLinks(projectID string, f *database.ProjectFact, includeLinks bool) interface{} {
+	if !includeLinks || f == nil {
+		return f
+	}
+	out, _ := h.db.ListOutgoingProjectFactEdges(projectID, f.FactKey)
+	in, _ := h.db.ListIncomingProjectFactEdges(projectID, f.FactKey)
+	return &factWithLinksResponse{
+		ProjectFact:   f,
+		OutgoingLinks: out,
+		IncomingLinks: in,
+	}
 }

 // ListFacts GET /api/projects/:id/facts （fact_key 查询参数可获取单条详情）
@@ -254,7 +332,8 @@ func (h *ProjectHandler) ListFacts(c *gin.Context) {
 			c.JSON(http.StatusNotFound, gin.H{"error": err.Error()})
 			return
 		}
-		c.JSON(http.StatusOK, f)
+		includeLinks := c.Query("include_links") == "1" || c.Query("include_links") == "true"
+		c.JSON(http.StatusOK, h.factResponseWithLinks(projectID, f, includeLinks))
 		return
 	}
 	limit, _ := strconv.Atoi(c.DefaultQuery("limit", "100"))
@@ -285,7 +364,52 @@ func (h *ProjectHandler) ListFacts(c *gin.Context) {
 		}
 		list = filtered
 	}
-	c.JSON(http.StatusOK, list)
+	includeLinkCounts := c.Query("include_link_counts") == "1" || c.Query("include_link_counts") == "true"
+	if !includeLinkCounts {
+		c.JSON(http.StatusOK, list)
+		return
+	}
+	counts, err := project.LoadProjectFactLinkCounts(h.db, projectID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	out := make([]factWithLinksResponse, 0, len(list))
+	for _, f := range list {
+		item := factWithLinksResponse{ProjectFact: f}
+		if c, ok := counts[f.FactKey]; ok {
+			cc := c
+			item.LinkCounts = &cc
+		}
+		out = append(out, item)
+	}
+	c.JSON(http.StatusOK, out)
+}
+
+// GetFactGraph GET /api/projects/:id/fact-graph?view=path|full
+func (h *ProjectHandler) GetFactGraph(c *gin.Context) {
+	projectID := c.Param("id")
+	if _, err := h.db.GetProject(projectID); err != nil {
+		c.JSON(http.StatusNotFound, gin.H{"error": "项目不存在"})
+		return
+	}
+	view := c.DefaultQuery("view", "path")
+	excludeDeprecated := true
+	if v := c.Query("exclude_deprecated"); v == "0" || v == "false" {
+		excludeDeprecated = false
+	}
+	graph, err := project.BuildProjectFactGraph(h.db, projectID, view, excludeDeprecated)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if graph.Nodes == nil {
+		graph.Nodes = []database.ProjectFactGraphNode{}
+	}
+	if graph.Edges == nil {
+		graph.Edges = []database.ProjectFactGraphEdge{}
+	}
+	c.JSON(http.StatusOK, graph)
 }

 // CreateFact POST /api/projects/:id/facts
@@ -295,8 +419,9 @@ func (h *ProjectHandler) CreateFact(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
+	projectID := c.Param("id")
 	f := &database.ProjectFact{
-		ProjectID:              c.Param("id"),
+		ProjectID:              projectID,
 		FactKey:                req.FactKey,
 		Category:               req.Category,
 		Summary:                req.Summary,
@@ -310,16 +435,24 @@ func (h *ProjectHandler) CreateFact(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	c.JSON(http.StatusOK, created)
+	explicitLinks := req.Links != nil || req.LinksText != nil
+	if err := h.applyFactLinksAfterUpsert(projectID, created, req.Links, req.LinksText, explicitLinks, !explicitLinks); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	created, _ = h.db.GetProjectFactByKey(projectID, created.FactKey)
+	c.JSON(http.StatusOK, h.factResponseWithLinks(projectID, created, true))
 }

 // UpdateFact PUT /api/projects/:id/facts/:factId
 func (h *ProjectHandler) UpdateFact(c *gin.Context) {
+	projectID := c.Param("id")
 	existing, err := h.db.GetProjectFact(c.Param("factId"))
-	if err != nil || existing.ProjectID != c.Param("id") {
+	if err != nil || existing.ProjectID != projectID {
 		c.JSON(http.StatusNotFound, gin.H{"error": "事实不存在"})
 		return
 	}
+	oldFactKey := existing.FactKey
 	var req updateFactRequest
 	if err := c.ShouldBindJSON(&req); err != nil {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
@@ -355,7 +488,29 @@ func (h *ProjectHandler) UpdateFact(c *gin.Context) {
 		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
 		return
 	}
-	c.JSON(http.StatusOK, updated)
+	if oldFactKey != updated.FactKey {
+		if err := h.db.RenameProjectFactKeyEdges(projectID, oldFactKey, updated.FactKey); err != nil {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+			return
+		}
+	}
+	if req.Links != nil || req.LinksText != nil {
+		var links []factLinkRequest
+		if req.Links != nil {
+			links = *req.Links
+		}
+		if err := h.applyFactLinksAfterUpsert(projectID, updated, links, req.LinksText, true, false); err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+			return
+		}
+	} else if req.ClearBody || req.Body != nil {
+		if err := h.applyFactLinksAfterUpsert(projectID, updated, nil, nil, false, true); err != nil {
+			c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+			return
+		}
+	}
+	updated, _ = h.db.GetProjectFactByKey(projectID, updated.FactKey)
+	c.JSON(http.StatusOK, h.factResponseWithLinks(projectID, updated, true))
 }

 // DeleteFact DELETE /api/projects/:id/facts/:factId
@@ -408,3 +563,82 @@ func (h *ProjectHandler) RestoreFact(c *gin.Context) {
 	}
 	c.JSON(http.StatusOK, gin.H{"success": true})
 }
+
+type createFactEdgeRequest struct {
+	SourceFactKey string `json:"source_fact_key" binding:"required"`
+	TargetFactKey string `json:"target_fact_key" binding:"required"`
+	EdgeType      string `json:"edge_type" binding:"required"`
+	Confidence    string `json:"confidence"`
+}
+
+// ListFactEdges GET /api/projects/:id/fact-edges
+func (h *ProjectHandler) ListFactEdges(c *gin.Context) {
+	projectID := c.Param("id")
+	edges, err := h.db.ListProjectFactEdgesByProject(projectID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if edges == nil {
+		edges = []*database.ProjectFactEdge{}
+	}
+	c.JSON(http.StatusOK, edges)
+}
+
+// CreateFactEdge POST /api/projects/:id/fact-edges
+func (h *ProjectHandler) CreateFactEdge(c *gin.Context) {
+	projectID := c.Param("id")
+	var req createFactEdgeRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	edge, err := h.db.AddProjectFactEdge(projectID, database.ProjectFactEdgeInput{
+		To:         req.TargetFactKey,
+		Type:       req.EdgeType,
+		Confidence: req.Confidence,
+	}, req.SourceFactKey, "")
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	if f, err := h.db.GetProjectFactByKey(projectID, req.TargetFactKey); err == nil {
+		in, _ := h.db.ListIncomingProjectFactEdges(projectID, req.TargetFactKey)
+		f.Body = project.SyncBodyLinksSection(f.Body, in)
+		_, _ = h.db.UpsertProjectFact(f)
+	}
+	c.JSON(http.StatusOK, edge)
+}
+
+// DeleteFactEdge DELETE /api/projects/:id/fact-edges/:edgeId
+func (h *ProjectHandler) DeleteFactEdge(c *gin.Context) {
+	projectID := c.Param("id")
+	edgeID := c.Param("edgeId")
+	edge, err := h.db.GetProjectFactEdge(edgeID)
+	if err != nil || edge.ProjectID != projectID {
+		c.JSON(http.StatusNotFound, gin.H{"error": "边不存在"})
+		return
+	}
+	if err := h.db.DeleteProjectFactEdge(edgeID); err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if f, err := h.db.GetProjectFactByKey(projectID, edge.TargetFactKey); err == nil {
+		in, _ := h.db.ListIncomingProjectFactEdges(projectID, edge.TargetFactKey)
+		f.Body = project.SyncBodyLinksSection(f.Body, in)
+		_, _ = h.db.UpsertProjectFact(f)
+	}
+	c.JSON(http.StatusOK, gin.H{"success": true})
+}
+
+// PromoteAttackChain POST /api/projects/:id/promote-attack-chain/:conversationId
+func (h *ProjectHandler) PromoteAttackChain(c *gin.Context) {
+	projectID := c.Param("id")
+	conversationID := c.Param("conversationId")
+	result, err := attackchain.PromoteToProject(h.db, projectID, conversationID)
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, result)
+}
@@ -7,6 +7,43 @@ import (
 	"go.uber.org/zap"
 )

+// agentSessionContextBlock 注入会话工作目录与项目黑板（用于 system prompt 追加块）。
+// 用户输入由 message history 承载；压缩后由 summarization 摘要指令保留关键约束。
+func (h *AgentHandler) agentSessionContextBlock(conversationID string) string {
+	var parts []string
+	if ws := h.buildWorkspaceBlock(conversationID); ws != "" {
+		parts = append(parts, ws)
+	}
+	if bb := h.projectBlackboardBlock(conversationID); bb != "" {
+		parts = append(parts, bb)
+	}
+	return strings.Join(parts, "\n\n")
+}
+
+func (h *AgentHandler) buildWorkspaceBlock(conversationID string) string {
+	if h == nil || h.config == nil {
+		return ""
+	}
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" {
+		return ""
+	}
+	projectID := h.conversationProjectID(conversationID)
+	rel := project.WorkspaceRootDir(h.config.Agent.WorkspaceRootDir, projectID, conversationID)
+	abs, err := project.EnsureWorkspace(rel)
+	if err != nil {
+		if h.logger != nil {
+			h.logger.Warn("创建会话工作目录失败",
+				zap.String("conversationId", conversationID),
+				zap.String("projectId", projectID),
+				zap.String("path", rel),
+				zap.Error(err))
+		}
+		return ""
+	}
+	return project.BuildWorkspaceBlock(abs)
+}
+
 // projectBlackboardBlock 根据对话 ID 构建项目事实索引块（用于注入 system prompt）。
 func (h *AgentHandler) projectBlackboardBlock(conversationID string) string {
 	if h == nil || h.db == nil || h.config == nil {
@@ -447,7 +447,7 @@ func (h *RobotHandler) cmdUnbindProject(platform, userID string) string {
 }

 func (h *RobotHandler) cmdList() string {
-	convs, err := h.db.ListConversations(50, 0, "")
+	convs, err := h.db.ListConversations(50, 0, "", "", "")
 	if err != nil {
 		return "获取对话列表失败: " + err.Error()
 	}
@@ -594,6 +594,9 @@ func (h *RobotHandler) cmdDelete(platform, userID, convID string) string {
 		h.mu.Unlock()
 		h.deleteSessionBinding(sk)
 	}
+	if h.agentHandler != nil {
+		h.agentHandler.CancelRunningTaskForConversation(convID)
+	}
 	if err := h.db.DeleteConversation(convID); err != nil {
 		return "删除失败: " + err.Error()
 	}
@@ -708,12 +711,27 @@ type wecomReplyXML struct {
 	Content      string   `xml:"Content"`
 }

+// wecomRequireToken 企业微信回调必须配置 Token；未配置时拒绝请求，防止未授权触发 Agent。
+func (h *RobotHandler) wecomRequireToken(c *gin.Context) (string, bool) {
+	token := strings.TrimSpace(h.config.Robots.Wecom.Token)
+	if token == "" {
+		h.logger.Warn("企业微信已启用但未配置 token，已拒绝回调（请在配置中设置 robots.wecom.token）")
+		c.String(http.StatusForbidden, "")
+		return "", false
+	}
+	return token, true
+}
+
 // HandleWecomGET 企业微信 URL 校验（GET）
 func (h *RobotHandler) HandleWecomGET(c *gin.Context) {
 	if !h.config.Robots.Wecom.Enabled {
 		c.String(http.StatusNotFound, "")
 		return
 	}
+	token, ok := h.wecomRequireToken(c)
+	if !ok {
+		return
+	}
 	// Gin 的 Query() 会自动 URL 解码，拿到的就是正确的 base64 字符串
 	echostr := c.Query("echostr")
 	msgSignature := c.Query("msg_signature")
@@ -721,7 +739,7 @@ func (h *RobotHandler) HandleWecomGET(c *gin.Context) {
 	nonce := c.Query("nonce")

 	// 验证签名：将 token、timestamp、nonce、echostr 四个参数排序后拼接计算 SHA1
-	signature := h.signWecomRequest(h.config.Robots.Wecom.Token, timestamp, nonce, echostr)
+	signature := h.signWecomRequest(token, timestamp, nonce, echostr)
 	if signature != msgSignature {
 		h.logger.Warn("企业微信 URL 验证签名失败", zap.String("expected", msgSignature), zap.String("got", signature))
 		c.String(http.StatusBadRequest, "invalid signature")
@@ -862,27 +880,28 @@ func (h *RobotHandler) HandleWecomPOST(c *gin.Context) {
 	}
 	h.logger.Debug("企业微信 POST 收到请求", zap.String("body", string(bodyRaw)))

-	// 验证请求签名防止伪造。企业微信签名算法同 URL 验证，使用 token、timestamp、nonce、 Encrypt 四个字段
-	// 若配置了 Token 则必须校验签名，避免未授权请求触发 Agent（防止平台被接管）
-	token := h.config.Robots.Wecom.Token
-	if token != "" {
-		if msgSignature == "" {
-			h.logger.Warn("企业微信 POST 缺少签名，已拒绝（需配置 token 并确保回调携带 msg_signature）")
-			c.String(http.StatusOK, "")
-			return
-		}
-		var tmp wecomXML
-		if err := xml.Unmarshal(bodyRaw, &tmp); err != nil {
-			h.logger.Warn("企业微信 POST 签名验证前解析 XML 失败", zap.Error(err))
-			c.String(http.StatusOK, "")
-			return
-		}
-		expected := h.signWecomRequest(token, timestamp, nonce, tmp.Encrypt)
-		if expected != msgSignature {
-			h.logger.Warn("企业微信 POST 签名验证失败", zap.String("expected", expected), zap.String("got", msgSignature))
-			c.String(http.StatusOK, "")
-			return
-		}
+	// 验证请求签名防止伪造。企业微信签名算法同 URL 验证，使用 token、timestamp、nonce、 Encrypt 四个字段。
+	// 启用企业微信时必须配置 token 并校验签名，避免未授权请求触发 Agent。
+	token, ok := h.wecomRequireToken(c)
+	if !ok {
+		return
+	}
+	if msgSignature == "" {
+		h.logger.Warn("企业微信 POST 缺少签名，已拒绝（需确保回调携带 msg_signature）")
+		c.String(http.StatusOK, "")
+		return
+	}
+	var tmp wecomXML
+	if err := xml.Unmarshal(bodyRaw, &tmp); err != nil {
+		h.logger.Warn("企业微信 POST 签名验证前解析 XML 失败", zap.Error(err))
+		c.String(http.StatusOK, "")
+		return
+	}
+	expected := h.signWecomRequest(token, timestamp, nonce, tmp.Encrypt)
+	if expected != msgSignature {
+		h.logger.Warn("企业微信 POST 签名验证失败", zap.String("expected", expected), zap.String("got", msgSignature))
+		c.String(http.StatusOK, "")
+		return
 	}

 	var body wecomXML
@@ -896,6 +915,13 @@ func (h *RobotHandler) HandleWecomPOST(c *gin.Context) {
 	// 保存企业 ID（用于明文模式回复）
 	enterpriseID := body.ToUserName

+	// 配置了 EncodingAESKey 时必须走加密消息，拒绝明文 XML 绕过
+	if strings.TrimSpace(h.config.Robots.Wecom.EncodingAESKey) != "" && strings.TrimSpace(body.Encrypt) == "" {
+		h.logger.Warn("企业微信已配置加密模式但收到明文消息，已拒绝")
+		c.String(http.StatusOK, "")
+		return
+	}
+
 	// 加密模式：先解密再解析内层 XML
 	if body.Encrypt != "" && h.config.Robots.Wecom.EncodingAESKey != "" {
 		h.logger.Debug("企业微信进入加密模式解密流程")
@@ -0,0 +1,78 @@
+package handler
+
+import (
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"testing"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+func newWecomTestHandler(token string, aesKey string) *RobotHandler {
+	return &RobotHandler{
+		config: &config.Config{
+			Robots: config.RobotsConfig{
+				Wecom: config.RobotWecomConfig{
+					Enabled:        true,
+					Token:          token,
+					EncodingAESKey: aesKey,
+				},
+			},
+		},
+		logger: zap.NewNop(),
+	}
+}
+
+func TestHandleWecomPOST_rejectsWhenTokenEmpty(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	h := newWecomTestHandler("", "")
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+	body := `<?xml version="1.0"?><xml><FromUserName>attacker</FromUserName><MsgType>text</MsgType><Content>hi</Content></xml>`
+	c.Request = httptest.NewRequest(http.MethodPost, "/api/robot/wecom", strings.NewReader(body))
+
+	h.HandleWecomPOST(c)
+
+	if w.Code != http.StatusForbidden {
+		t.Fatalf("status = %d, want %d", w.Code, http.StatusForbidden)
+	}
+	if w.Body.String() == "success" {
+		t.Fatal("expected rejection, got success")
+	}
+}
+
+func TestHandleWecomPOST_rejectsPlaintextWhenEncryptionConfigured(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	h := newWecomTestHandler("secret-token", "abcdefghijklmnopqrstuvwxyz0123456789ABCD")
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+	body := `<?xml version="1.0"?><xml><FromUserName>attacker</FromUserName><MsgType>text</MsgType><Content>hi</Content></xml>`
+	c.Request = httptest.NewRequest(http.MethodPost, "/api/robot/wecom?timestamp=1&nonce=2&msg_signature=fake", strings.NewReader(body))
+
+	h.HandleWecomPOST(c)
+
+	if w.Body.String() == "success" {
+		t.Fatal("expected rejection for plaintext in encryption mode, got success")
+	}
+}
+
+func TestHandleWecomGET_rejectsWhenTokenEmpty(t *testing.T) {
+	gin.SetMode(gin.TestMode)
+
+	h := newWecomTestHandler("", "")
+	w := httptest.NewRecorder()
+	c, _ := gin.CreateTestContext(w)
+	c.Request = httptest.NewRequest(http.MethodGet, "/api/robot/wecom?msg_signature=x&timestamp=1&nonce=2&echostr=abc", nil)
+
+	h.HandleWecomGET(c)
+
+	if w.Code != http.StatusForbidden {
+		t.Fatalf("status = %d, want %d", w.Code, http.StatusForbidden)
+	}
+}
@@ -26,6 +26,7 @@ func shouldPersistEinoAgentTraceAfterRunError(baseCtx context.Context) bool {
 // AgentTask 描述正在运行的Agent任务
 type AgentTask struct {
 	ConversationID string    `json:"conversationId"`
+	Title          string    `json:"title,omitempty"`
 	Message        string    `json:"message,omitempty"`
 	StartedAt      time.Time `json:"startedAt"`
 	Status         string    `json:"status"`
@@ -37,6 +38,14 @@ type AgentTask struct {
 	// InterruptContinueNote 无 MCP 时「中断并继续」由用户在弹窗中填写的补充说明（Cancel 前写入，续跑轮次读取后清空）
 	InterruptContinueNote string `json:"-"`

+	// activeEinoExecuteCancel 当前进行中的 Eino filesystem execute 取消函数（与 MCP 工具并行，供中断并继续）
+	activeEinoExecuteCancel context.CancelFunc
+	// activeEinoExecuteAbortNote AbortActiveEinoExecute 写入的用户说明，由 execute 收尾时合并进工具结果
+	activeEinoExecuteAbortNote string
+
+	// hitlCognition 本轮运行中供 HITL/审计 Agent 读取的上下文（用户原话 + 思考，不含会话历史）
+	hitlCognition *hitlCognitionState
+
 	cancel func(error)
 }

@@ -70,6 +79,103 @@ func (m *AgentTaskManager) UnregisterRunningTool(conversationID, executionID str
 	}
 }

+// RegisterActiveEinoExecute 登记进行中的 Eino filesystem execute（每会话同时仅一条）。
+func (m *AgentTaskManager) RegisterActiveEinoExecute(conversationID string, cancel context.CancelFunc) {
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" || cancel == nil {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if t, ok := m.tasks[conversationID]; ok && t != nil {
+		t.activeEinoExecuteCancel = cancel
+		t.activeEinoExecuteAbortNote = ""
+	}
+}
+
+// UnregisterActiveEinoExecute execute 正常结束或已取消后清除登记。
+func (m *AgentTaskManager) UnregisterActiveEinoExecute(conversationID string) {
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" {
+		return
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if t, ok := m.tasks[conversationID]; ok && t != nil {
+		t.activeEinoExecuteCancel = nil
+		t.activeEinoExecuteAbortNote = ""
+	}
+}
+
+// ConversationIDForActiveMCPExecution 根据当前登记的工具 executionId 反查会话 ID（供 MCP 监控页按 executionId 终止）。
+func (m *AgentTaskManager) ConversationIDForActiveMCPExecution(executionID string) string {
+	executionID = strings.TrimSpace(executionID)
+	if executionID == "" {
+		return ""
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	for convID, t := range m.tasks {
+		if t != nil && t.ActiveMCPExecutionID == executionID {
+			return convID
+		}
+	}
+	return ""
+}
+
+// ConversationIDForActiveEinoExecute 返回当前唯一进行 Eino execute 的会话 ID；多会话并行时返回空。
+func (m *AgentTaskManager) ConversationIDForActiveEinoExecute() (string, bool) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	var found string
+	count := 0
+	for convID, t := range m.tasks {
+		if t != nil && t.activeEinoExecuteCancel != nil {
+			found = convID
+			count++
+		}
+	}
+	if count == 1 {
+		return found, true
+	}
+	return "", false
+}
+
+// AbortActiveEinoExecute 终止当前 Eino execute 并暂存用户说明（与 MCP 工具终止一致）。
+func (m *AgentTaskManager) AbortActiveEinoExecute(conversationID, note string) bool {
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" {
+		return false
+	}
+	m.mu.Lock()
+	t, ok := m.tasks[conversationID]
+	if !ok || t == nil || t.activeEinoExecuteCancel == nil {
+		m.mu.Unlock()
+		return false
+	}
+	t.activeEinoExecuteAbortNote = strings.TrimSpace(note)
+	cancel := t.activeEinoExecuteCancel
+	m.mu.Unlock()
+	cancel()
+	return true
+}
+
+// TakeEinoExecuteAbortNote 读取并清空 execute 终止说明（execute 收尾时调用一次）。
+func (m *AgentTaskManager) TakeEinoExecuteAbortNote(conversationID string) string {
+	conversationID = strings.TrimSpace(conversationID)
+	if conversationID == "" {
+		return ""
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if t, ok := m.tasks[conversationID]; ok && t != nil {
+		n := t.activeEinoExecuteAbortNote
+		t.activeEinoExecuteAbortNote = ""
+		return n
+	}
+	return ""
+}
+
 // SetInterruptContinueNote 在发起 ErrInterruptContinue 取消前写入用户补充说明（仅内存）。
 func (m *AgentTaskManager) SetInterruptContinueNote(conversationID, note string) {
 	conversationID = strings.TrimSpace(conversationID)
@@ -131,6 +237,7 @@ func (m *AgentTaskManager) ActiveMCPExecutionID(conversationID string) string {
 // CompletedTask 已完成的任务（用于历史记录）
 type CompletedTask struct {
 	ConversationID string    `json:"conversationId"`
+	Title          string    `json:"title,omitempty"`
 	Message        string    `json:"message,omitempty"`
 	StartedAt      time.Time `json:"startedAt"`
 	CompletedAt    time.Time `json:"completedAt"`
@@ -145,6 +252,8 @@ type AgentTaskManager struct {
 	maxHistorySize   int              // 最大历史记录数
 	historyRetention time.Duration    // 历史记录保留时间
 	eventBus         *TaskEventBus    // 可选：任务结束时关闭镜像 SSE 订阅
+	// toolCanceler 在用户整轮停止任务时终止当前 MCP 工具（非「中断并继续」）。
+	toolCanceler func(conversationID string)
 }

 const (
@@ -175,6 +284,13 @@ func (m *AgentTaskManager) SetTaskEventBus(b *TaskEventBus) {
 	m.eventBus = b
 }

+// SetToolCanceler 设置整轮停止任务时终止当前 MCP 工具的回调（由 AgentHandler 注入）。
+func (m *AgentTaskManager) SetToolCanceler(fn func(conversationID string)) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.toolCanceler = fn
+}
+
 // GetTask 返回运行中任务（无则 nil）。
 func (m *AgentTaskManager) GetTask(conversationID string) *AgentTask {
 	m.mu.RLock()
@@ -241,6 +357,7 @@ func (m *AgentTaskManager) StartTask(conversationID, message string, cancel cont
 	}

 	m.tasks[conversationID] = task
+	task.hitlCognition = &hitlCognitionState{UserMessage: strings.TrimSpace(message)}
 	return task, nil
 }

@@ -270,14 +387,21 @@ func (m *AgentTaskManager) CancelTask(conversationID string, cause error) (bool,
 		task.InterruptContinueNote = ""
 	}
 	cancel := task.cancel
-	m.mu.Unlock()
-
 	if cause == nil {
 		cause = ErrTaskCancelled
 	}
+	var toolCanceler func(string)
+	if errors.Is(cause, ErrTaskCancelled) {
+		toolCanceler = m.toolCanceler
+	}
+	m.mu.Unlock()
+
 	if cancel != nil {
 		cancel(cause)
 	}
+	if toolCanceler != nil {
+		toolCanceler(conversationID)
+	}
 	return true, nil
 }

@@ -0,0 +1,56 @@
+package handler
+
+import (
+	"context"
+	"testing"
+	"time"
+)
+
+func TestAbortActiveEinoExecute(t *testing.T) {
+	m := NewAgentTaskManager()
+	conv := "conv-eino-exec-abort"
+	ctx, cancel := context.WithCancel(context.Background())
+	_, err := m.StartTask(conv, "test", func(error) {})
+	if err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+	m.RegisterActiveEinoExecute(conv, cancel)
+
+	done := make(chan struct{})
+	go func() {
+		<-ctx.Done()
+		close(done)
+	}()
+
+	if !m.AbortActiveEinoExecute(conv, "跳过域名收集") {
+		t.Fatal("expected abort to succeed")
+	}
+	select {
+	case <-done:
+	case <-time.After(2 * time.Second):
+		t.Fatal("execute cancel did not propagate")
+	}
+	if got := m.TakeEinoExecuteAbortNote(conv); got != "跳过域名收集" {
+		t.Fatalf("abort note = %q, want 跳过域名收集", got)
+	}
+	m.UnregisterActiveEinoExecute(conv)
+	if m.AbortActiveEinoExecute(conv, "") {
+		t.Fatal("second abort should fail when no active execute")
+	}
+}
+
+func TestConversationIDForActiveMCPExecution(t *testing.T) {
+	m := NewAgentTaskManager()
+	conv := "conv-mcp-exec"
+	_, err := m.StartTask(conv, "test", func(error) {})
+	if err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+	m.RegisterRunningTool(conv, "exec-123")
+	if got := m.ConversationIDForActiveMCPExecution("exec-123"); got != conv {
+		t.Fatalf("got %q, want %q", got, conv)
+	}
+	if got := m.ConversationIDForActiveMCPExecution("missing"); got != "" {
+		t.Fatalf("missing should be empty, got %q", got)
+	}
+}
@@ -0,0 +1,80 @@
+package handler
+
+import (
+	"context"
+	"errors"
+	"testing"
+
+	"cyberstrike-ai/internal/multiagent"
+)
+
+func TestCancelTaskInvokesToolCancelerOnFullStop(t *testing.T) {
+	tm := NewAgentTaskManager()
+	called := false
+	tm.SetToolCanceler(func(conversationID string) {
+		if conversationID == "conv-1" {
+			called = true
+		}
+	})
+
+	_, cancel := context.WithCancelCause(context.Background())
+	_, err := tm.StartTask("conv-1", "hello", cancel)
+	if err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+
+	ok, err := tm.CancelTask("conv-1", ErrTaskCancelled)
+	if err != nil || !ok {
+		t.Fatalf("CancelTask: ok=%v err=%v", ok, err)
+	}
+	if !called {
+		t.Fatal("expected tool canceler to be invoked on full task cancel")
+	}
+}
+
+func TestCancelTaskSkipsToolCancelerOnInterruptContinue(t *testing.T) {
+	tm := NewAgentTaskManager()
+	called := false
+	tm.SetToolCanceler(func(conversationID string) {
+		called = true
+	})
+
+	_, cancel := context.WithCancelCause(context.Background())
+	_, err := tm.StartTask("conv-1", "hello", cancel)
+	if err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+
+	ok, err := tm.CancelTask("conv-1", multiagent.ErrInterruptContinue)
+	if err != nil || !ok {
+		t.Fatalf("CancelTask: ok=%v err=%v", ok, err)
+	}
+	if called {
+		t.Fatal("tool canceler must not run for interrupt-continue")
+	}
+}
+
+func TestCancelTaskDefaultCauseIsTaskCancelled(t *testing.T) {
+	tm := NewAgentTaskManager()
+	var gotCause error
+	tm.SetToolCanceler(func(conversationID string) {
+		if conversationID == "conv-2" {
+			gotCause = ErrTaskCancelled
+		}
+	})
+
+	ctx, cancel := context.WithCancelCause(context.Background())
+	if _, err := tm.StartTask("conv-2", "hello", cancel); err != nil {
+		t.Fatalf("StartTask: %v", err)
+	}
+
+	if _, err := tm.CancelTask("conv-2", nil); err != nil {
+		t.Fatalf("CancelTask: %v", err)
+	}
+	if !errors.Is(context.Cause(ctx), ErrTaskCancelled) {
+		t.Fatalf("expected ErrTaskCancelled cause, got %v", context.Cause(ctx))
+	}
+	if gotCause != ErrTaskCancelled {
+		t.Fatalf("expected tool canceler path for default cancel cause")
+	}
+}
@@ -0,0 +1,16 @@
+//go:build windows
+
+package handler
+
+import (
+	"net/http"
+
+	"github.com/gin-gonic/gin"
+)
+
+// RunCommandWS 交互式 PTY 终端依赖 Unix PTY（见 terminal_ws_unix.go）；Windows 暂不支持。
+func (h *TerminalHandler) RunCommandWS(c *gin.Context) {
+	c.JSON(http.StatusNotImplemented, gin.H{
+		"error": "Interactive WebSocket terminal is not supported on Windows; use POST /terminal/run or /terminal/run/stream instead.",
+	})
+}
@@ -45,9 +45,12 @@ type CreateVulnerabilityRequest struct {
 	Status          string `json:"status"`
 	Type            string `json:"type"`
 	Target          string `json:"target"`
-	Proof           string `json:"proof"`
+	Preconditions   string `json:"preconditions"`
+	ReproSteps      string `json:"reproduction_steps"`
+	Evidence        string `json:"evidence"`
 	Impact          string `json:"impact"`
 	Recommendation  string `json:"recommendation"`
+	RetestNotes     string `json:"retest_notes"`
 }

 // CreateVulnerability 创建漏洞
@@ -69,9 +72,12 @@ func (h *VulnerabilityHandler) CreateVulnerability(c *gin.Context) {
 		Status:          req.Status,
 		Type:            req.Type,
 		Target:          req.Target,
-		Proof:           req.Proof,
+		Preconditions:   req.Preconditions,
+		ReproSteps:      req.ReproSteps,
+		Evidence:        req.Evidence,
 		Impact:          req.Impact,
 		Recommendation:  req.Recommendation,
+		RetestNotes:     req.RetestNotes,
 	}

 	created, err := h.db.CreateVulnerability(vuln)
@@ -118,7 +124,7 @@ func parseVulnerabilityListFilter(c *gin.Context) database.VulnerabilityListFilt
 		q = strings.TrimSpace(c.Query("search"))
 	}
 	return database.VulnerabilityListFilter{
-		ProjectID: c.Query("project_id"),
+		ProjectID:       c.Query("project_id"),
 		ID:              c.Query("id"),
 		Search:          q,
 		ConversationID:  c.Query("conversation_id"),
@@ -197,17 +203,20 @@ func (h *VulnerabilityHandler) ListVulnerabilities(c *gin.Context) {
 // UpdateVulnerabilityRequest 更新漏洞请求
 type UpdateVulnerabilityRequest struct {
 	ProjectID       *string `json:"project_id"`
-	ConversationTag string  `json:"conversation_tag"`
-	TaskTag         string  `json:"task_tag"`
-	Title           string  `json:"title"`
-	Description     string  `json:"description"`
-	Severity        string  `json:"severity"`
-	Status          string  `json:"status"`
-	Type            string  `json:"type"`
-	Target          string  `json:"target"`
-	Proof           string  `json:"proof"`
-	Impact          string  `json:"impact"`
-	Recommendation  string  `json:"recommendation"`
+	ConversationTag *string `json:"conversation_tag"`
+	TaskTag         *string `json:"task_tag"`
+	Title           *string `json:"title"`
+	Description     *string `json:"description"`
+	Severity        *string `json:"severity"`
+	Status          *string `json:"status"`
+	Type            *string `json:"type"`
+	Target          *string `json:"target"`
+	Preconditions   *string `json:"preconditions"`
+	ReproSteps      *string `json:"reproduction_steps"`
+	Evidence        *string `json:"evidence"`
+	Impact          *string `json:"impact"`
+	Recommendation  *string `json:"recommendation"`
+	RetestNotes     *string `json:"retest_notes"`
 }

 // UpdateVulnerability 更新漏洞
@@ -231,38 +240,47 @@ func (h *VulnerabilityHandler) UpdateVulnerability(c *gin.Context) {
 	if req.ProjectID != nil {
 		existing.ProjectID = strings.TrimSpace(*req.ProjectID)
 	}
-	if req.ConversationTag != "" {
-		existing.ConversationTag = req.ConversationTag
+	if req.ConversationTag != nil {
+		existing.ConversationTag = *req.ConversationTag
 	}
-	if req.TaskTag != "" {
-		existing.TaskTag = req.TaskTag
+	if req.TaskTag != nil {
+		existing.TaskTag = *req.TaskTag
 	}
-	if req.Title != "" {
-		existing.Title = req.Title
+	if req.Title != nil {
+		existing.Title = *req.Title
 	}
-	if req.Description != "" {
-		existing.Description = req.Description
+	if req.Description != nil {
+		existing.Description = *req.Description
 	}
-	if req.Severity != "" {
-		existing.Severity = req.Severity
+	if req.Severity != nil {
+		existing.Severity = *req.Severity
 	}
-	if req.Status != "" {
-		existing.Status = req.Status
+	if req.Status != nil {
+		existing.Status = *req.Status
 	}
-	if req.Type != "" {
-		existing.Type = req.Type
+	if req.Type != nil {
+		existing.Type = *req.Type
 	}
-	if req.Target != "" {
-		existing.Target = req.Target
+	if req.Target != nil {
+		existing.Target = *req.Target
 	}
-	if req.Proof != "" {
-		existing.Proof = req.Proof
+	if req.Preconditions != nil {
+		existing.Preconditions = *req.Preconditions
 	}
-	if req.Impact != "" {
-		existing.Impact = req.Impact
+	if req.ReproSteps != nil {
+		existing.ReproSteps = *req.ReproSteps
 	}
-	if req.Recommendation != "" {
-		existing.Recommendation = req.Recommendation
+	if req.Evidence != nil {
+		existing.Evidence = *req.Evidence
+	}
+	if req.Impact != nil {
+		existing.Impact = *req.Impact
+	}
+	if req.Recommendation != nil {
+		existing.Recommendation = *req.Recommendation
+	}
+	if req.RetestNotes != nil {
+		existing.RetestNotes = *req.RetestNotes
 	}

 	if err := h.db.UpdateVulnerability(id, existing); err != nil {
@@ -495,9 +513,19 @@ func appendVulnerabilityMarkdown(b *strings.Builder, v *database.Vulnerability,
 		b.WriteString(v.Description)
 		b.WriteString("\n")
 	}
-	if v.Proof != "" {
-		b.WriteString("\n#### 证明（POC）\n\n```\n")
-		b.WriteString(v.Proof)
+	if v.Preconditions != "" {
+		b.WriteString("\n#### 前置条件\n\n")
+		b.WriteString(v.Preconditions)
+		b.WriteString("\n")
+	}
+	if v.ReproSteps != "" {
+		b.WriteString("\n#### 复现步骤\n\n")
+		b.WriteString(v.ReproSteps)
+		b.WriteString("\n")
+	}
+	if v.Evidence != "" {
+		b.WriteString("\n#### 证据 / POC\n\n```\n")
+		b.WriteString(v.Evidence)
 		b.WriteString("\n```\n")
 	}
 	if v.Impact != "" {
@@ -510,6 +538,11 @@ func appendVulnerabilityMarkdown(b *strings.Builder, v *database.Vulnerability,
 		b.WriteString(v.Recommendation)
 		b.WriteString("\n")
 	}
+	if v.RetestNotes != "" {
+		b.WriteString("\n#### 复测方式\n\n")
+		b.WriteString(v.RetestNotes)
+		b.WriteString("\n")
+	}
 	b.WriteString("\n")
 }

@@ -0,0 +1,210 @@
+package handler
+
+import (
+	"encoding/json"
+	"net/http"
+	"strings"
+
+	"cyberstrike-ai/internal/agent"
+	"cyberstrike-ai/internal/audit"
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+	workflowrunner "cyberstrike-ai/internal/workflow"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+type WorkflowHandler struct {
+	db     *database.DB
+	logger *zap.Logger
+	audit  *audit.Service
+	agent  *agent.Agent
+	cfg    *config.Config
+}
+
+func NewWorkflowHandler(db *database.DB, logger *zap.Logger) *WorkflowHandler {
+	return &WorkflowHandler{db: db, logger: logger}
+}
+
+func (h *WorkflowHandler) SetAudit(s *audit.Service) {
+	h.audit = s
+}
+
+type workflowSaveRequest struct {
+	ID          string          `json:"id"`
+	Name        string          `json:"name"`
+	Description string          `json:"description,omitempty"`
+	Version     int             `json:"version,omitempty"`
+	Enabled     *bool           `json:"enabled,omitempty"`
+	Graph       json.RawMessage `json:"graph,omitempty"`
+	GraphJSON   json.RawMessage `json:"graph_json,omitempty"`
+}
+
+type workflowDryRunRequest struct {
+	Graph     json.RawMessage        `json:"graph,omitempty"`
+	GraphJSON json.RawMessage        `json:"graph_json,omitempty"`
+	Inputs    map[string]interface{} `json:"inputs,omitempty"`
+}
+
+func (h *WorkflowHandler) List(c *gin.Context) {
+	includeDisabled := strings.EqualFold(c.Query("includeDisabled"), "true") || c.Query("include_disabled") == "1"
+	items, err := h.db.ListWorkflowDefinitions(includeDisabled)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"workflows": items})
+}
+
+func (h *WorkflowHandler) Get(c *gin.Context) {
+	id := strings.TrimSpace(c.Param("id"))
+	wf, err := h.db.GetWorkflowDefinition(id)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if wf == nil {
+		c.JSON(http.StatusNotFound, gin.H{"error": "工作流不存在"})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"workflow": wf})
+}
+
+func (h *WorkflowHandler) Create(c *gin.Context) {
+	h.save(c, "")
+}
+
+func (h *WorkflowHandler) Validate(c *gin.Context) {
+	var req workflowSaveRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"ok": false, "error": "无效的请求参数: " + err.Error()})
+		return
+	}
+	graph := req.Graph
+	if len(graph) == 0 {
+		graph = req.GraphJSON
+	}
+	if len(graph) == 0 {
+		c.JSON(http.StatusBadRequest, gin.H{"ok": false, "error": "graph 不能为空"})
+		return
+	}
+	if !json.Valid(graph) {
+		c.JSON(http.StatusBadRequest, gin.H{"ok": false, "error": "graph 必须是合法 JSON"})
+		return
+	}
+	if err := workflowrunner.ValidateGraphJSON(c.Request.Context(), string(graph)); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"ok": false, "error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"ok": true})
+}
+
+func (h *WorkflowHandler) DryRun(c *gin.Context) {
+	var req workflowDryRunRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "无效的请求参数: " + err.Error()})
+		return
+	}
+	graph := req.Graph
+	if len(graph) == 0 {
+		graph = req.GraphJSON
+	}
+	if len(graph) == 0 || !json.Valid(graph) {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "graph 必须是合法 JSON"})
+		return
+	}
+	inputs := make(map[string]any, len(req.Inputs))
+	for k, v := range req.Inputs {
+		inputs[k] = v
+	}
+	result, err := workflowrunner.DryRunGraphJSON(c.Request.Context(), string(graph), inputs)
+	if err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"result": result})
+}
+
+func (h *WorkflowHandler) Update(c *gin.Context) {
+	h.save(c, c.Param("id"))
+}
+
+func (h *WorkflowHandler) save(c *gin.Context, pathID string) {
+	var req workflowSaveRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "无效的请求参数: " + err.Error()})
+		return
+	}
+	id := strings.TrimSpace(req.ID)
+	if strings.TrimSpace(pathID) != "" {
+		id = strings.TrimSpace(pathID)
+	}
+	name := strings.TrimSpace(req.Name)
+	if id == "" || name == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "工作流 id 和 name 不能为空"})
+		return
+	}
+	graph := req.Graph
+	if len(graph) == 0 {
+		graph = req.GraphJSON
+	}
+	if len(graph) == 0 {
+		graph = []byte(`{"nodes":[],"edges":[],"config":{}}`)
+	}
+	if !json.Valid(graph) {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "graph 必须是合法 JSON"})
+		return
+	}
+	if err := workflowrunner.ValidateGraphJSON(c.Request.Context(), string(graph)); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "工作流图无法编译: " + err.Error()})
+		return
+	}
+	var probe interface{}
+	if err := json.Unmarshal(graph, &probe); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "graph JSON 解析失败: " + err.Error()})
+		return
+	}
+	enabled := true
+	if req.Enabled != nil {
+		enabled = *req.Enabled
+	}
+	wf := &database.WorkflowDefinition{
+		ID:          id,
+		Name:        name,
+		Description: strings.TrimSpace(req.Description),
+		Version:     req.Version,
+		GraphJSON:   string(graph),
+		Enabled:     enabled,
+	}
+	if err := h.db.UpsertWorkflowDefinition(wf); err != nil {
+		if h.logger != nil {
+			h.logger.Warn("保存工作流失败", zap.String("id", id), zap.Error(err))
+		}
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	saved, _ := h.db.GetWorkflowDefinition(id)
+	workflowrunner.InvalidateCompiledCache(id)
+	if h.audit != nil {
+		h.audit.RecordOK(c, "workflow", "save", "保存图编排流程", "workflow", id, map[string]interface{}{"name": name})
+	}
+	c.JSON(http.StatusOK, gin.H{"message": "工作流已保存", "workflow": saved})
+}
+
+func (h *WorkflowHandler) Delete(c *gin.Context) {
+	id := strings.TrimSpace(c.Param("id"))
+	if id == "" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "工作流 id 不能为空"})
+		return
+	}
+	if err := h.db.DeleteWorkflowDefinition(id); err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	workflowrunner.InvalidateCompiledCache(id)
+	if h.audit != nil {
+		h.audit.RecordOK(c, "workflow", "delete", "删除图编排流程", "workflow", id, nil)
+	}
+	c.JSON(http.StatusOK, gin.H{"message": "工作流已删除"})
+}
@@ -0,0 +1,263 @@
+package handler
+
+import (
+	"context"
+	"errors"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	workflowrunner "cyberstrike-ai/internal/workflow"
+
+	"github.com/gin-gonic/gin"
+	"go.uber.org/zap"
+)
+
+func (h *AgentHandler) roleForWorkflow(req *ChatRequest) (config.RoleConfig, bool) {
+	if h == nil || h.config == nil || h.config.Roles == nil || req == nil {
+		return config.RoleConfig{}, false
+	}
+	roleName := strings.TrimSpace(req.Role)
+	if roleName == "" {
+		return config.RoleConfig{}, false
+	}
+	role, ok := h.config.Roles[roleName]
+	if !ok || !role.Enabled {
+		return config.RoleConfig{}, false
+	}
+	if role.Name == "" {
+		role.Name = roleName
+	}
+	if !workflowrunner.ShouldAutoRunRoleWorkflow(role) {
+		return config.RoleConfig{}, false
+	}
+	return role, true
+}
+
+func (h *AgentHandler) runRoleWorkflowStreamIfBound(
+	req *ChatRequest,
+	prep *multiAgentPrepared,
+	sendEvent func(eventType, message string, data interface{}),
+) bool {
+	role, ok := h.roleForWorkflow(req)
+	if !ok || prep == nil {
+		return false
+	}
+
+	conversationID := prep.ConversationID
+	assistantMessageID := prep.AssistantMessageID
+	userMessage := ""
+	if req != nil {
+		userMessage = req.Message
+	}
+
+	taskStatus := "completed"
+	taskOwned := false
+	defer func() {
+		if taskOwned {
+			h.tasks.FinishTask(conversationID, taskStatus)
+		}
+	}()
+
+	baseCtx, cancelWithCause := context.WithCancelCause(context.Background())
+	defer cancelWithCause(nil)
+	taskCtx, timeoutCancel := context.WithTimeout(baseCtx, 600*time.Minute)
+	defer timeoutCancel()
+
+	if _, err := h.tasks.StartTask(conversationID, userMessage, cancelWithCause); err != nil {
+		var errorMsg string
+		if errors.Is(err, ErrTaskAlreadyRunning) {
+			errorMsg = "⚠️ 当前会话已有任务正在执行中，请等待当前任务完成或点击「停止任务」后再尝试。"
+			sendEvent("error", errorMsg, map[string]interface{}{
+				"conversationId": conversationID,
+				"errorType":      "task_already_running",
+			})
+		} else {
+			errorMsg = "❌ 无法启动任务: " + err.Error()
+			sendEvent("error", errorMsg, nil)
+		}
+		if assistantMessageID != "" {
+			_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", errorMsg, time.Now(), assistantMessageID)
+		}
+		sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
+		return true
+	}
+	taskOwned = true
+
+	progress := h.createProgressCallback(taskCtx, cancelWithCause, conversationID, assistantMessageID, sendEvent)
+	result, err := workflowrunner.RunRoleBoundWorkflow(taskCtx, workflowrunner.RunArgs{
+		DB:                 h.db,
+		Logger:             h.logger,
+		Role:               role,
+		AppCfg:             h.config,
+		Agent:              h.agent,
+		ConversationID:     conversationID,
+		ProjectID:          h.conversationProjectID(conversationID),
+		UserMessage:        prep.FinalMessage,
+		History:            prep.History,
+		RoleTools:          prep.RoleTools,
+		AgentsMarkdownDir:  h.agentsMarkdownDir,
+		SystemPromptExtra:  h.agentSessionContextBlock(conversationID),
+		AssistantMessageID: assistantMessageID,
+		Progress:           progress,
+	})
+	if err != nil {
+		cause := context.Cause(baseCtx)
+		if errors.Is(cause, ErrTaskCancelled) {
+			taskStatus = "cancelled"
+			h.tasks.UpdateTaskStatus(conversationID, taskStatus)
+			cancelMsg := "任务已被用户取消，后续操作已停止。"
+			if assistantMessageID != "" {
+				if err := h.appendAssistantMessageNotice(assistantMessageID, cancelMsg); err != nil {
+					h.logger.Warn("更新取消后的助手消息失败", zap.Error(err))
+				}
+				_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "cancelled", cancelMsg, nil)
+			}
+			sendEvent("cancelled", cancelMsg, map[string]interface{}{
+				"conversationId": conversationID,
+				"messageId":      assistantMessageID,
+			})
+			sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
+			return true
+		}
+		if errors.Is(err, context.DeadlineExceeded) || errors.Is(context.Cause(taskCtx), context.DeadlineExceeded) {
+			taskStatus = "timeout"
+			h.tasks.UpdateTaskStatus(conversationID, taskStatus)
+			timeoutMsg := "任务执行超时，已自动终止。"
+			if assistantMessageID != "" {
+				_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", timeoutMsg, time.Now(), assistantMessageID)
+				_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "timeout", timeoutMsg, nil)
+			}
+			sendEvent("error", timeoutMsg, map[string]interface{}{
+				"conversationId": conversationID,
+				"messageId":      assistantMessageID,
+				"errorType":      "timeout",
+			})
+			sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
+			return true
+		}
+		errMsg := "执行角色绑定流程失败: " + err.Error()
+		taskStatus = "failed"
+		h.tasks.UpdateTaskStatus(conversationID, taskStatus)
+		if assistantMessageID != "" {
+			_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", errMsg, time.Now(), assistantMessageID)
+			_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "error", errMsg, nil)
+		}
+		sendEvent("error", errMsg, map[string]interface{}{"conversationId": conversationID})
+		sendEvent("done", "", map[string]interface{}{"conversationId": conversationID})
+		return true
+	}
+	if prep.AssistantMessageID != "" {
+		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, nil, "")
+	}
+	payload := map[string]interface{}{
+		"conversationId": prep.ConversationID,
+		"messageId":      prep.AssistantMessageID,
+		"agentMode":      "workflow",
+		"workflowRunId":  result.RunID,
+	}
+	if result.AwaitingHITL {
+		payload["workflowStatus"] = "awaiting_hitl"
+		payload["awaitingHitl"] = true
+	}
+	sendEvent("response", result.Response, payload)
+	sendEvent("done", "", map[string]interface{}{"conversationId": prep.ConversationID})
+	return true
+}
+
+func (h *AgentHandler) runRoleWorkflowJSONIfBound(c *gin.Context, req *ChatRequest, prep *multiAgentPrepared) bool {
+	role, ok := h.roleForWorkflow(req)
+	if !ok || prep == nil {
+		return false
+	}
+
+	conversationID := prep.ConversationID
+	assistantMessageID := prep.AssistantMessageID
+	userMessage := ""
+	if req != nil {
+		userMessage = req.Message
+	}
+
+	taskStatus := "completed"
+	taskOwned := false
+	defer func() {
+		if taskOwned {
+			h.tasks.FinishTask(conversationID, taskStatus)
+		}
+	}()
+
+	baseCtx, cancelWithCause := context.WithCancelCause(c.Request.Context())
+	defer cancelWithCause(nil)
+	taskCtx, timeoutCancel := context.WithTimeout(baseCtx, 600*time.Minute)
+	defer timeoutCancel()
+
+	if _, err := h.tasks.StartTask(conversationID, userMessage, cancelWithCause); err != nil {
+		if errors.Is(err, ErrTaskAlreadyRunning) {
+			c.JSON(http.StatusConflict, gin.H{
+				"error":          "⚠️ 当前会话已有任务正在执行中，请等待当前任务完成或点击「停止任务」后再尝试。",
+				"conversationId": conversationID,
+				"errorType":      "task_already_running",
+			})
+		} else {
+			c.JSON(http.StatusInternalServerError, gin.H{"error": "❌ 无法启动任务: " + err.Error()})
+		}
+		return true
+	}
+	taskOwned = true
+
+	progress := h.createProgressCallback(taskCtx, cancelWithCause, conversationID, assistantMessageID, nil)
+	result, err := workflowrunner.RunRoleBoundWorkflow(taskCtx, workflowrunner.RunArgs{
+		DB:                 h.db,
+		Logger:             h.logger,
+		Role:               role,
+		AppCfg:             h.config,
+		Agent:              h.agent,
+		ConversationID:     conversationID,
+		ProjectID:          h.conversationProjectID(conversationID),
+		UserMessage:        prep.FinalMessage,
+		History:            prep.History,
+		RoleTools:          prep.RoleTools,
+		AgentsMarkdownDir:  h.agentsMarkdownDir,
+		SystemPromptExtra:  h.agentSessionContextBlock(conversationID),
+		AssistantMessageID: assistantMessageID,
+		Progress:           progress,
+	})
+	if err != nil {
+		cause := context.Cause(baseCtx)
+		if errors.Is(cause, ErrTaskCancelled) {
+			taskStatus = "cancelled"
+			cancelMsg := "任务已被用户取消，后续操作已停止。"
+			if assistantMessageID != "" {
+				_ = h.appendAssistantMessageNotice(assistantMessageID, cancelMsg)
+				_ = h.db.AddProcessDetail(assistantMessageID, conversationID, "cancelled", cancelMsg, nil)
+			}
+			c.JSON(http.StatusOK, gin.H{
+				"status":         "cancelled",
+				"message":        cancelMsg,
+				"conversationId": conversationID,
+			})
+			return true
+		}
+		errMsg := "执行角色绑定流程失败: " + err.Error()
+		taskStatus = "failed"
+		if assistantMessageID != "" {
+			_, _ = h.db.Exec("UPDATE messages SET content = ?, updated_at = ? WHERE id = ?", errMsg, time.Now(), assistantMessageID)
+		}
+		c.JSON(http.StatusInternalServerError, gin.H{"error": errMsg, "conversationId": conversationID})
+		return true
+	}
+	if prep.AssistantMessageID != "" {
+		_ = h.db.UpdateAssistantMessageFinalize(prep.AssistantMessageID, result.Response, nil, "")
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"response":           result.Response,
+		"conversationId":     prep.ConversationID,
+		"assistantMessageId": prep.AssistantMessageID,
+		"agentMode":          "workflow",
+		"workflowRunId":      result.RunID,
+		"workflowStatus":     result.Status,
+		"awaitingHitl":       result.AwaitingHITL,
+	})
+	return true
+}
@@ -0,0 +1,162 @@
+package handler
+
+import (
+	"encoding/json"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/agent"
+	"cyberstrike-ai/internal/config"
+	workflowrunner "cyberstrike-ai/internal/workflow"
+
+	"github.com/gin-gonic/gin"
+)
+
+func (h *WorkflowHandler) SetRuntime(agent *agent.Agent, cfg *config.Config) {
+	h.agent = agent
+	h.cfg = cfg
+}
+
+func (h *WorkflowHandler) GetRun(c *gin.Context) {
+	runID := strings.TrimSpace(c.Param("runId"))
+	run, err := h.db.GetWorkflowRun(runID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if run == nil {
+		c.JSON(http.StatusNotFound, gin.H{"error": "工作流运行不存在"})
+		return
+	}
+	nodeRuns, err := h.db.ListWorkflowNodeRuns(runID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"run": run, "nodeRuns": nodeRuns})
+}
+
+func (h *WorkflowHandler) ReplayRun(c *gin.Context) {
+	runID := strings.TrimSpace(c.Param("runId"))
+	nodeRuns, err := h.db.ListWorkflowNodeRuns(runID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	steps := make([]gin.H, 0, len(nodeRuns))
+	for i, nodeRun := range nodeRuns {
+		var input any
+		var output any
+		_ = json.Unmarshal([]byte(nodeRun.InputJSON), &input)
+		_ = json.Unmarshal([]byte(nodeRun.OutputJSON), &output)
+		steps = append(steps, gin.H{
+			"step":       i + 1,
+			"nodeRunId":  nodeRun.ID,
+			"nodeId":     nodeRun.NodeID,
+			"status":     nodeRun.Status,
+			"input":      input,
+			"output":     output,
+			"error":      nodeRun.Error,
+			"startedAt":  nodeRun.StartedAt,
+			"finishedAt": nodeRun.FinishedAt,
+		})
+	}
+	c.JSON(http.StatusOK, gin.H{"workflowRunId": runID, "steps": steps})
+}
+
+func (h *WorkflowHandler) ListPendingRuns(c *gin.Context) {
+	conversationID := strings.TrimSpace(c.Query("conversationId"))
+	runs, err := h.db.ListWorkflowRunsAwaitingHITLFiltered(conversationID, 50)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{"runs": runs})
+}
+
+type workflowResumeRequest struct {
+	Approved bool   `json:"approved"`
+	Comment  string `json:"comment,omitempty"`
+}
+
+func (h *WorkflowHandler) ResumeRun(c *gin.Context) {
+	if h.agent == nil || h.cfg == nil {
+		c.JSON(http.StatusServiceUnavailable, gin.H{"error": "工作流运行时未初始化"})
+		return
+	}
+	runID := strings.TrimSpace(c.Param("runId"))
+	var req workflowResumeRequest
+	if err := c.ShouldBindJSON(&req); err != nil {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "无效的请求参数: " + err.Error()})
+		return
+	}
+	run, err := h.db.GetWorkflowRun(runID)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	if run == nil {
+		c.JSON(http.StatusNotFound, gin.H{"error": "工作流运行不存在"})
+		return
+	}
+	role := config.RoleConfig{Name: strings.TrimSpace(run.RoleID)}
+	if role.Name != "" && h.cfg.Roles != nil {
+		if r, ok := h.cfg.Roles[role.Name]; ok {
+			role = r
+			if role.Name == "" {
+				role.Name = run.RoleID
+			}
+		}
+	}
+	if run.Status != "awaiting_hitl" {
+		c.JSON(http.StatusBadRequest, gin.H{"error": "工作流运行不在等待审批状态: " + run.Status})
+		return
+	}
+	if err := h.db.RecordWorkflowRunHITLDecision(runID, req.Approved, req.Comment); err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	decision := workflowrunner.HITLDecision{
+		Approved: req.Approved,
+		Comment:  strings.TrimSpace(req.Comment),
+	}
+	delegated := workflowrunner.NotifyHITLDecision(runID, decision)
+	if !delegated {
+		for i := 0; i < 10; i++ {
+			time.Sleep(50 * time.Millisecond)
+			if workflowrunner.NotifyHITLDecision(runID, decision) {
+				delegated = true
+				break
+			}
+		}
+	}
+	if delegated {
+		c.JSON(http.StatusOK, gin.H{
+			"workflowRunId":  runID,
+			"status":         "delegated",
+			"streamResuming": true,
+			"approved":       req.Approved,
+		})
+		return
+	}
+	result, err := workflowrunner.ResumeWorkflowRun(c.Request.Context(), workflowrunner.RunArgs{
+		DB:             h.db,
+		Logger:         h.logger,
+		Role:           role,
+		AppCfg:         h.cfg,
+		Agent:          h.agent,
+		ConversationID: run.ConversationID,
+		ProjectID:      run.ProjectID,
+	}, runID, req.Approved, req.Comment)
+	if err != nil {
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
+		return
+	}
+	c.JSON(http.StatusOK, gin.H{
+		"response":      result.Response,
+		"workflowRunId": result.RunID,
+		"status":        result.Status,
+		"awaitingHitl":  result.AwaitingHITL,
+	})
+}
@@ -0,0 +1,71 @@
+package hitl
+
+import (
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+
+	"go.uber.org/zap"
+)
+
+const retentionPurgeInterval = time.Hour
+
+// Service manages HITL audit log retention (decided hitl_interrupts rows).
+type Service struct {
+	db     *database.DB
+	cfg    *config.Config
+	logger *zap.Logger
+}
+
+// NewService creates a HITL audit log retention service.
+func NewService(db *database.DB, cfg *config.Config, logger *zap.Logger) *Service {
+	return &Service{db: db, cfg: cfg, logger: logger}
+}
+
+// RetentionDays returns configured retention; 0 means keep forever.
+func (s *Service) RetentionDays() int {
+	if s == nil || s.cfg == nil {
+		return config.HitlConfig{}.RetentionDaysEffective()
+	}
+	return s.cfg.Hitl.RetentionDaysEffective()
+}
+
+// PurgeExpired deletes decided HITL log rows older than retention_days when configured.
+func (s *Service) PurgeExpired() {
+	if s == nil || s.db == nil || s.cfg == nil {
+		return
+	}
+	days := s.cfg.Hitl.RetentionDaysEffective()
+	if days <= 0 {
+		return
+	}
+	cutoff := time.Now().AddDate(0, 0, -days)
+	n, err := s.db.PurgeHitlInterruptLogsBefore(cutoff)
+	if err != nil {
+		if s.logger != nil {
+			s.logger.Warn("清理过期人机协同审计日志失败", zap.Error(err))
+		}
+		return
+	}
+	if n > 0 && s.logger != nil {
+		s.logger.Info("已清理过期人机协同审计日志", zap.Int64("deleted", n), zap.Int("retention_days", days))
+	}
+}
+
+// StartRetentionLoop periodically purges expired HITL audit log rows.
+func StartRetentionLoop(s *Service, logger *zap.Logger) {
+	if s == nil {
+		return
+	}
+	go func() {
+		ticker := time.NewTicker(retentionPurgeInterval)
+		defer ticker.Stop()
+		for range ticker.C {
+			s.PurgeExpired()
+			if logger != nil {
+				logger.Debug("hitl audit log retention tick completed")
+			}
+		}
+	}()
+}
@@ -0,0 +1,50 @@
+package hitl
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	appconfig "cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+
+	"go.uber.org/zap"
+)
+
+func TestServicePurgeExpired_respectsZeroRetention(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "hitl.db")
+	db, err := database.NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+	if _, err := db.Exec(`CREATE TABLE IF NOT EXISTS hitl_interrupts (
+		id TEXT PRIMARY KEY,
+		conversation_id TEXT NOT NULL,
+		mode TEXT NOT NULL,
+		tool_name TEXT NOT NULL,
+		status TEXT NOT NULL,
+		decision TEXT,
+		created_at DATETIME NOT NULL,
+		decided_at DATETIME
+	)`); err != nil {
+		t.Fatalf("create table: %v", err)
+	}
+
+	old := time.Now().AddDate(0, 0, -100).UTC().Format(time.RFC3339)
+	if _, err := db.Exec(`INSERT INTO hitl_interrupts
+		(id, conversation_id, mode, tool_name, status, decision, created_at, decided_at)
+		VALUES ('old-1', 'c1', 'approval', 'exec', 'decided', 'approve', ?, ?)`, old, old); err != nil {
+		t.Fatalf("insert: %v", err)
+	}
+
+	zero := 0
+	svc := NewService(db, &appconfig.Config{
+		Hitl: appconfig.HitlConfig{RetentionDays: &zero},
+	}, zap.NewNop())
+	svc.PurgeExpired()
+
+	if err := db.QueryRow(`SELECT id FROM hitl_interrupts WHERE id = 'old-1'`).Scan(new(string)); err != nil {
+		t.Fatalf("record should remain when retention_days=0: %v", err)
+	}
+}
@@ -0,0 +1,96 @@
+package knowledge
+
+import (
+	"context"
+	"fmt"
+	"strings"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/cloudwego/eino/callbacks"
+	"github.com/cloudwego/eino/components"
+	"github.com/cloudwego/eino/components/retriever"
+	"github.com/cloudwego/eino/schema"
+	"go.uber.org/zap"
+)
+
+// knowledgePipelineRetriever: MultiQuery → vector candidates → rerank → post-process.
+type knowledgePipelineRetriever struct {
+	inner retriever.Retriever
+	base  *Retriever
+}
+
+func newKnowledgePipelineRetriever(inner retriever.Retriever, base *Retriever) *knowledgePipelineRetriever {
+	if inner == nil || base == nil {
+		return nil
+	}
+	return &knowledgePipelineRetriever{inner: inner, base: base}
+}
+
+func (p *knowledgePipelineRetriever) GetType() string {
+	return "KnowledgeRAGPipeline"
+}
+
+func (p *knowledgePipelineRetriever) Retrieve(ctx context.Context, query string, opts ...retriever.Option) (out []*schema.Document, err error) {
+	if p == nil || p.inner == nil || p.base == nil {
+		return nil, fmt.Errorf("knowledge pipeline retriever: nil")
+	}
+	q := strings.TrimSpace(query)
+	if q == "" {
+		return nil, fmt.Errorf("查询不能为空")
+	}
+
+	ro := retriever.GetCommonOptions(nil, opts...)
+	finalTopK := p.base.config.TopK
+	if finalTopK <= 0 {
+		finalTopK = 5
+	}
+	if ro.TopK != nil && *ro.TopK > 0 {
+		finalTopK = *ro.TopK
+	}
+
+	ctx = callbacks.EnsureRunInfo(ctx, p.GetType(), components.ComponentOfRetriever)
+	ctx = callbacks.OnStart(ctx, &retriever.CallbackInput{Query: q, TopK: finalTopK, Extra: ro.DSLInfo})
+	defer func() {
+		if err != nil {
+			_ = callbacks.OnError(ctx, err)
+			return
+		}
+		_ = callbacks.OnEnd(ctx, &retriever.CallbackOutput{Docs: out})
+	}()
+
+	out, err = p.inner.Retrieve(ctx, q, opts...)
+	if err != nil {
+		return nil, err
+	}
+	if len(out) == 0 {
+		return out, nil
+	}
+
+	if rr := p.base.documentReranker(); rr != nil && len(out) > 1 {
+		reranked, rerr := rr.Rerank(ctx, q, out)
+		if rerr != nil {
+			if p.base.logger != nil {
+				p.base.logger.Warn("知识检索重排失败，已使用融合序", zap.Error(rerr))
+			}
+		} else if len(reranked) > 0 {
+			out = reranked
+		}
+	}
+
+	tokenModel := ""
+	if p.base.embedder != nil {
+		tokenModel = p.base.embedder.EmbeddingModelName()
+	}
+	var postPO *config.PostRetrieveConfig
+	if p.base.config != nil {
+		postPO = &p.base.config.PostRetrieve
+	}
+	out, err = ApplyPostRetrieve(out, postPO, tokenModel, finalTopK)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
+var _ retriever.Retriever = (*knowledgePipelineRetriever)(nil)
@@ -8,8 +8,7 @@ import (
 	"github.com/cloudwego/eino/schema"
 )

-// BuildKnowledgeRetrieveChain 编译「查询字符串 → 文档列表」的 Eino Chain，底层为 SQLite 向量检索（[VectorEinoRetriever]）。
-// 去重、上下文预算截断与最终 Top-K 均在 [VectorEinoRetriever.Retrieve] 内完成，与 HTTP/MCP 检索路径一致。
+// BuildKnowledgeRetrieveChain 编译「查询字符串 → 文档列表」的 Eino Chain（MultiQuery → 向量 → 重排 → 后处理）。
 func BuildKnowledgeRetrieveChain(ctx context.Context, r *Retriever) (compose.Runnable[string, []*schema.Document], error) {
 	if r == nil {
 		return nil, fmt.Errorf("retriever is nil")
@@ -11,19 +11,10 @@ import (
 	"github.com/cloudwego/eino/components"
 	"github.com/cloudwego/eino/components/retriever"
 	"github.com/cloudwego/eino/schema"
-	"go.uber.org/zap"
 )

 // VectorEinoRetriever implements [retriever.Retriever] on top of SQLite-stored embeddings + cosine similarity.
-//
-// Options:
-//   - [retriever.WithTopK]
-//   - [retriever.WithDSLInfo] with [DSLRiskType] (string), [DSLSimilarityThreshold] (float, cosine 0–1), [DSLSubIndexFilter] (string)
-//
-// Document scores are cosine similarity; [retriever.WithScoreThreshold] is not mapped to a different metric.
-//
-// After vector search: optional [DocumentReranker] (see [Retriever.SetDocumentReranker]), then
-// [ApplyPostRetrieve] (normalized-text dedupe, context budget, final Top-K) using [config.PostRetrieveConfig].
+// It returns prefetch-sized vector candidates only; rerank and post-process run in [knowledgePipelineRetriever].
 type VectorEinoRetriever struct {
 	inner *Retriever
 }
@@ -119,26 +110,6 @@ func (h *VectorEinoRetriever) Retrieve(ctx context.Context, query string, opts .
 		return nil, err
 	}
 	out = retrievalResultsToDocuments(results)
-
-	if rr := h.inner.documentReranker(); rr != nil && len(out) > 1 {
-		reranked, rerr := rr.Rerank(ctx, q, out)
-		if rerr != nil {
-			if h.inner.logger != nil {
-				h.inner.logger.Warn("知识检索重排失败，已使用向量序", zap.Error(rerr))
-			}
-		} else if len(reranked) > 0 {
-			out = reranked
-		}
-	}
-
-	tokenModel := ""
-	if h.inner.embedder != nil {
-		tokenModel = h.inner.embedder.EmbeddingModelName()
-	}
-	out, err = ApplyPostRetrieve(out, postPO, tokenModel, finalTopK)
-	if err != nil {
-		return nil, err
-	}
 	return out, nil
 }

@@ -0,0 +1,226 @@
+package knowledge
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/cloudwego/eino/schema"
+	"go.uber.org/zap"
+)
+
+// HTTPReranker calls a hosted rerank API (DashScope or Cohere-compatible).
+type HTTPReranker struct {
+	provider string
+	model    string
+	baseURL  string
+	apiKey   string
+	client   *http.Client
+	logger   *zap.Logger
+}
+
+// NewHTTPReranker builds a rerank client from knowledge retrieval config; openAI supplies fallback credentials.
+func NewHTTPReranker(rc *config.RerankConfig, openAI *config.OpenAIConfig, logger *zap.Logger) (*HTTPReranker, error) {
+	if rc == nil {
+		return nil, fmt.Errorf("rerank config is nil")
+	}
+	baseURL := strings.TrimSpace(rc.BaseURL)
+	apiKey := strings.TrimSpace(rc.APIKey)
+	if openAI != nil {
+		if baseURL == "" {
+			baseURL = strings.TrimSpace(openAI.BaseURL)
+		}
+		if apiKey == "" {
+			apiKey = strings.TrimSpace(openAI.APIKey)
+		}
+	}
+	if apiKey == "" {
+		return nil, fmt.Errorf("rerank api_key is required")
+	}
+	provider := rc.ProviderEffective(baseURL)
+	model := rc.ModelEffective(provider)
+	return &HTTPReranker{
+		provider: provider,
+		model:    model,
+		baseURL:  strings.TrimSuffix(baseURL, "/"),
+		apiKey:   apiKey,
+		client:   &http.Client{Timeout: 60 * time.Second},
+		logger:   logger,
+	}, nil
+}
+
+func (r *HTTPReranker) Rerank(ctx context.Context, query string, docs []*schema.Document) ([]*schema.Document, error) {
+	if r == nil {
+		return docs, nil
+	}
+	q := strings.TrimSpace(query)
+	if q == "" || len(docs) == 0 {
+		return docs, nil
+	}
+	if len(docs) == 1 {
+		return docs, nil
+	}
+	texts := make([]string, 0, len(docs))
+	for _, d := range docs {
+		if d == nil {
+			texts = append(texts, "")
+			continue
+		}
+		texts = append(texts, d.Content)
+	}
+	var order []int
+	var err error
+	switch r.provider {
+	case "dashscope":
+		order, err = r.rerankDashScope(ctx, q, texts, len(docs))
+	default:
+		order, err = r.rerankCohere(ctx, q, texts, len(docs))
+	}
+	if err != nil {
+		return nil, err
+	}
+	out := make([]*schema.Document, 0, len(order))
+	for _, idx := range order {
+		if idx < 0 || idx >= len(docs) || docs[idx] == nil {
+			continue
+		}
+		out = append(out, docs[idx])
+	}
+	if len(out) == 0 {
+		return docs, nil
+	}
+	return out, nil
+}
+
+func (r *HTTPReranker) rerankCohere(ctx context.Context, query string, documents []string, topN int) ([]int, error) {
+	url := r.cohereRerankURL()
+	body := map[string]any{
+		"model":     r.model,
+		"query":     query,
+		"documents": documents,
+		"top_n":     topN,
+	}
+	raw, err := json.Marshal(body)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(raw))
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+r.apiKey)
+	resp, err := r.client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("rerank request: %w", err)
+	}
+	defer resp.Body.Close()
+	respBody, _ := io.ReadAll(resp.Body)
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return nil, fmt.Errorf("rerank http %d: %s", resp.StatusCode, truncateForRerankLog(string(respBody)))
+	}
+	var parsed struct {
+		Results []struct {
+			Index int `json:"index"`
+		} `json:"results"`
+	}
+	if err := json.Unmarshal(respBody, &parsed); err != nil {
+		return nil, fmt.Errorf("rerank decode: %w", err)
+	}
+	order := make([]int, 0, len(parsed.Results))
+	for _, row := range parsed.Results {
+		order = append(order, row.Index)
+	}
+	return order, nil
+}
+
+func (r *HTTPReranker) rerankDashScope(ctx context.Context, query string, documents []string, topN int) ([]int, error) {
+	url := r.dashscopeRerankURL()
+	body := map[string]any{
+		"model": r.model,
+		"input": map[string]any{
+			"query":     query,
+			"documents": documents,
+		},
+		"parameters": map[string]any{
+			"return_documents": false,
+			"top_n":            topN,
+		},
+	}
+	raw, err := json.Marshal(body)
+	if err != nil {
+		return nil, err
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodPost, url, bytes.NewReader(raw))
+	if err != nil {
+		return nil, err
+	}
+	req.Header.Set("Content-Type", "application/json")
+	req.Header.Set("Authorization", "Bearer "+r.apiKey)
+	resp, err := r.client.Do(req)
+	if err != nil {
+		return nil, fmt.Errorf("dashscope rerank: %w", err)
+	}
+	defer resp.Body.Close()
+	respBody, _ := io.ReadAll(resp.Body)
+	if resp.StatusCode < 200 || resp.StatusCode >= 300 {
+		return nil, fmt.Errorf("dashscope rerank http %d: %s", resp.StatusCode, truncateForRerankLog(string(respBody)))
+	}
+	var parsed struct {
+		Output struct {
+			Results []struct {
+				Index int `json:"index"`
+			} `json:"results"`
+		} `json:"output"`
+	}
+	if err := json.Unmarshal(respBody, &parsed); err != nil {
+		return nil, fmt.Errorf("dashscope rerank decode: %w", err)
+	}
+	order := make([]int, 0, len(parsed.Output.Results))
+	for _, row := range parsed.Output.Results {
+		order = append(order, row.Index)
+	}
+	return order, nil
+}
+
+func (r *HTTPReranker) cohereRerankURL() string {
+	base := r.baseURL
+	if base == "" {
+		base = "https://api.cohere.com"
+	}
+	if strings.HasSuffix(base, "/v1") {
+		return base + "/rerank"
+	}
+	return base + "/v1/rerank"
+}
+
+func (r *HTTPReranker) dashscopeRerankURL() string {
+	base := strings.TrimSpace(r.baseURL)
+	if base == "" {
+		return "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank"
+	}
+	if strings.Contains(base, "/api/v1/services/rerank") {
+		return base
+	}
+	if strings.Contains(base, "dashscope.aliyuncs.com") || strings.Contains(base, "compatible-mode") {
+		return "https://dashscope.aliyuncs.com/api/v1/services/rerank/text-rerank/text-rerank"
+	}
+	return strings.TrimSuffix(base, "/")
+}
+
+func truncateForRerankLog(s string) string {
+	s = strings.TrimSpace(s)
+	if len(s) > 512 {
+		return s[:512] + "..."
+	}
+	return s
+}
+
+var _ DocumentReranker = (*HTTPReranker)(nil)
@@ -0,0 +1,97 @@
+package knowledge
+
+import (
+	"context"
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/cloudwego/eino/schema"
+)
+
+func TestHTTPReranker_CohereOrder(t *testing.T) {
+	t.Parallel()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		if r.URL.Path != "/v1/rerank" {
+			t.Fatalf("path %s", r.URL.Path)
+		}
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"results": []map[string]any{
+				{"index": 2, "relevance_score": 0.9},
+				{"index": 0, "relevance_score": 0.5},
+			},
+		})
+	}))
+	defer srv.Close()
+
+	rr, err := NewHTTPReranker(&config.RerankConfig{
+		Provider: "cohere",
+		Model:    "rerank-multilingual-v3.0",
+		BaseURL:  srv.URL,
+		APIKey:   "test-key",
+	}, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	docs := []*schema.Document{
+		{ID: "a", Content: "alpha"},
+		{ID: "b", Content: "beta"},
+		{ID: "c", Content: "gamma"},
+	}
+	out, err := rr.Rerank(context.Background(), "query", docs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(out) != 2 || out[0].ID != "c" || out[1].ID != "a" {
+		t.Fatalf("order wrong: %#v", out)
+	}
+}
+
+func TestHTTPReranker_DashScopeOrder(t *testing.T) {
+	t.Parallel()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		_ = json.NewEncoder(w).Encode(map[string]any{
+			"output": map[string]any{
+				"results": []map[string]any{
+					{"index": 1, "relevance_score": 0.88},
+				},
+			},
+		})
+	}))
+	defer srv.Close()
+
+	rr, err := NewHTTPReranker(&config.RerankConfig{
+		Provider: "dashscope",
+		Model:    "gte-rerank",
+		BaseURL:  srv.URL,
+		APIKey:   "test-key",
+	}, nil, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	docs := []*schema.Document{{ID: "a", Content: "a"}, {ID: "b", Content: "b"}}
+	out, err := rr.Rerank(context.Background(), "q", docs)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(out) != 1 || out[0].ID != "b" {
+		t.Fatalf("got %#v", out)
+	}
+}
+
+func TestRerankConfigDefaults(t *testing.T) {
+	t.Parallel()
+	rc := config.RerankConfig{}
+	if rc.ProviderEffective("https://dashscope.aliyuncs.com/x") != "dashscope" {
+		t.Fatal("dashscope detect")
+	}
+	if rc.ModelEffective("dashscope") != "gte-rerank" {
+		t.Fatal("dashscope model")
+	}
+	if rc.ModelEffective("cohere") != "rerank-multilingual-v3.0" {
+		t.Fatal("cohere model")
+	}
+}
@@ -19,7 +19,7 @@ import (
 // postRetrieveMaxPrefetchCap 限制单次向量候选上限，避免误配置导致全表扫压力过大。
 const postRetrieveMaxPrefetchCap = 200

-// DocumentReranker 可选重排（如交叉编码器 / 第三方 Rerank API），由 [Retriever.SetDocumentReranker] 注入；失败时在适配层降级为向量序。
+// DocumentReranker 精排（HTTP dashscope / Cohere 兼容 API），由 [WireRetrieverPipeline] 注入。
 type DocumentReranker interface {
 	Rerank(ctx context.Context, query string, docs []*schema.Document) ([]*schema.Document, error)
 }
@@ -167,13 +167,16 @@ func truncateDocumentsByBudget(docs []*schema.Document, maxRunes, maxTokens int,
 	return out, nil
 }

-// EffectivePrefetchTopK 计算向量检索应拉取的候选条数（供粗排 / 去重 / 重排）。
+// EffectivePrefetchTopK 计算每条 MultiQuery 变体在向量阶段的候选条数（供融合 / 重排 / 后处理）。
 func EffectivePrefetchTopK(topK int, po *config.PostRetrieveConfig) int {
 	if topK < 1 {
 		topK = 5
 	}
-	fetch := topK
-	if po != nil && po.PrefetchTopK > fetch {
+	fetch := topK * 4
+	if fetch < 20 {
+		fetch = 20
+	}
+	if po != nil && po.PrefetchTopK > 0 {
 		fetch = po.PrefetchTopK
 	}
 	if fetch > postRetrieveMaxPrefetchCap {
@@ -182,7 +185,7 @@ func EffectivePrefetchTopK(topK int, po *config.PostRetrieveConfig) int {
 	return fetch
 }

-// ApplyPostRetrieve 检索后处理：规范化正文去重 → 预算截断 → 最终 TopK。重排在 [VectorEinoRetriever] 中单独调用以便失败时降级。
+// ApplyPostRetrieve 检索后处理：规范化正文去重 → 预算截断 → 最终 TopK（精排已在流水线中完成）。
 func ApplyPostRetrieve(docs []*schema.Document, po *config.PostRetrieveConfig, tokenModel string, finalTopK int) ([]*schema.Document, error) {
 	if finalTopK < 1 {
 		finalTopK = 5
@@ -28,8 +28,8 @@ func TestDedupeByNormalizedContent(t *testing.T) {
 }

 func TestEffectivePrefetchTopK(t *testing.T) {
-	if g := EffectivePrefetchTopK(5, nil); g != 5 {
-		t.Fatalf("got %d", g)
+	if g := EffectivePrefetchTopK(5, nil); g != 20 {
+		t.Fatalf("default prefetch got %d want 20", g)
 	}
 	if g := EffectivePrefetchTopK(5, &config.PostRetrieveConfig{PrefetchTopK: 50}); g != 50 {
 		t.Fatalf("got %d", g)
@@ -27,15 +27,19 @@ type Retriever struct {

 	rerankMu sync.RWMutex
 	reranker DocumentReranker
+
+	pipeline retriever.Retriever
+	wireOpenAI *config.OpenAIConfig
 }

 // RetrievalConfig 检索配置
 type RetrievalConfig struct {
 	TopK                int
 	SimilarityThreshold float64
-	// SubIndexFilter 非空时仅检索 sub_indexes 包含该标签（逗号分隔之一）的行；空 sub_indexes 的旧行仍保留以兼容。
-	SubIndexFilter string
-	PostRetrieve   config.PostRetrieveConfig
+	SubIndexFilter      string
+	MultiQuery          config.MultiQueryConfig
+	Rerank              config.RerankConfig
+	PostRetrieve        config.PostRetrieveConfig
 }

 // NewRetriever 创建新的检索器
@@ -48,7 +52,7 @@ func NewRetriever(db *sql.DB, embedder *Embedder, config *RetrievalConfig, logge
 	}
 }

-// UpdateConfig 更新检索配置
+// UpdateConfig 更新检索配置并重建 Eino MultiQuery + 重排流水线。
 func (r *Retriever) UpdateConfig(cfg *RetrievalConfig) {
 	if cfg != nil {
 		r.config = cfg
@@ -57,12 +61,18 @@ func (r *Retriever) UpdateConfig(cfg *RetrievalConfig) {
 				zap.Int("top_k", cfg.TopK),
 				zap.Float64("similarity_threshold", cfg.SimilarityThreshold),
 				zap.String("sub_index_filter", cfg.SubIndexFilter),
+				zap.Int("multi_query_max", cfg.MultiQuery.MaxQueriesEffective()),
 				zap.Int("post_retrieve_prefetch_top_k", cfg.PostRetrieve.PrefetchTopK),
 				zap.Int("post_retrieve_max_context_chars", cfg.PostRetrieve.MaxContextChars),
 				zap.Int("post_retrieve_max_context_tokens", cfg.PostRetrieve.MaxContextTokens),
 			)
 		}
 	}
+	if r.wireOpenAI != nil {
+		if err := WireRetrieverPipeline(context.Background(), r, r.wireOpenAI); err != nil && r.logger != nil {
+			r.logger.Warn("检索流水线重建失败", zap.Error(err))
+		}
+	}
 }

 // SetDocumentReranker 注入可选重排器（并发安全）；nil 表示禁用。
@@ -103,7 +113,7 @@ func cosineSimilarity(a, b []float32) float64 {
 	return dotProduct / (math.Sqrt(normA) * math.Sqrt(normB))
 }

-// Search 搜索知识库。统一经 [VectorEinoRetriever]（Eino retriever.Retriever 边界）。
+// Search 搜索知识库（Eino MultiQuery → 向量检索 → 重排 → 后处理）。
 func (r *Retriever) Search(ctx context.Context, req *SearchRequest) ([]*RetrievalResult, error) {
 	if req == nil {
 		return nil, fmt.Errorf("请求不能为空")
@@ -113,7 +123,7 @@ func (r *Retriever) Search(ctx context.Context, req *SearchRequest) ([]*Retrieva
 		return nil, fmt.Errorf("查询不能为空")
 	}
 	opts := r.einoRetrieverOptions(req)
-	docs, err := NewVectorEinoRetriever(r).Retrieve(ctx, q, opts...)
+	docs, err := r.activeEinoRetriever().Retrieve(ctx, q, opts...)
 	if err != nil {
 		return nil, err
 	}
@@ -143,7 +153,19 @@ func (r *Retriever) einoRetrieverOptions(req *SearchRequest) []retriever.Option

 // EinoRetrieve 直接返回 [schema.Document]，供 Eino Graph / Chain 使用。
 func (r *Retriever) EinoRetrieve(ctx context.Context, query string, opts ...retriever.Option) ([]*schema.Document, error) {
-	return NewVectorEinoRetriever(r).Retrieve(ctx, query, opts...)
+	return r.activeEinoRetriever().Retrieve(ctx, query, opts...)
+}
+
+func (r *Retriever) activeEinoRetriever() retriever.Retriever {
+	if r != nil && r.pipeline != nil {
+		return r.pipeline
+	}
+	return NewVectorEinoRetriever(r)
+}
+
+// AsEinoRetriever 将知识库检索流水线暴露为 Eino [retriever.Retriever]。
+func (r *Retriever) AsEinoRetriever() retriever.Retriever {
+	return r.activeEinoRetriever()
 }

 func (r *Retriever) knowledgeEmbeddingSelectSQL(riskType, subIndexFilter string) (string, []interface{}) {
@@ -299,7 +321,14 @@ func (r *Retriever) vectorSearch(ctx context.Context, req *SearchRequest) ([]*Re
 	return results, nil
 }

-// AsEinoRetriever 将纯向量检索暴露为 Eino [retriever.Retriever]。
-func (r *Retriever) AsEinoRetriever() retriever.Retriever {
-	return NewVectorEinoRetriever(r)
+// RetrievalConfigFromYAML maps API/YAML retrieval settings into the knowledge package.
+func RetrievalConfigFromYAML(r config.RetrievalConfig) *RetrievalConfig {
+	return &RetrievalConfig{
+		TopK:                r.TopK,
+		SimilarityThreshold: r.SimilarityThreshold,
+		SubIndexFilter:      r.SubIndexFilter,
+		MultiQuery:          r.MultiQuery,
+		Rerank:              r.Rerank,
+		PostRetrieve:        r.PostRetrieve,
+	}
 }
@@ -0,0 +1,74 @@
+package knowledge
+
+import (
+	"context"
+	"fmt"
+	"net/http"
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/openai"
+
+	einoopenai "github.com/cloudwego/eino-ext/components/model/openai"
+	"github.com/cloudwego/eino/flow/retriever/multiquery"
+	"go.uber.org/zap"
+)
+
+// WireRetrieverPipeline builds Eino MultiQuery + HTTP rerank + post-process pipeline on r.
+// Call once after NewRetriever; UpdateConfig re-invokes when wireOpenAI is set.
+func WireRetrieverPipeline(ctx context.Context, r *Retriever, openAI *config.OpenAIConfig) error {
+	if r == nil {
+		return fmt.Errorf("retriever is nil")
+	}
+	if openAI == nil {
+		return fmt.Errorf("openai config is nil")
+	}
+	if r.config == nil {
+		return fmt.Errorf("retrieval config is nil")
+	}
+	r.wireOpenAI = openAI
+
+	httpClient := openai.NewEinoHTTPClient(openAI, &http.Client{Timeout: 120 * time.Second})
+	chatCfg := &einoopenai.ChatModelConfig{
+		APIKey:     strings.TrimSpace(openAI.APIKey),
+		BaseURL:    strings.TrimSuffix(strings.TrimSpace(openAI.BaseURL), "/"),
+		Model:      strings.TrimSpace(openAI.Model),
+		HTTPClient: httpClient,
+	}
+	if chatCfg.Model == "" {
+		chatCfg.Model = "gpt-4o"
+	}
+	rewriteLLM, err := einoopenai.NewChatModel(ctx, chatCfg)
+	if err != nil {
+		return fmt.Errorf("multi_query rewrite model: %w", err)
+	}
+
+	reranker, err := NewHTTPReranker(&r.config.Rerank, openAI, r.logger)
+	if err != nil {
+		return fmt.Errorf("reranker: %w", err)
+	}
+	r.SetDocumentReranker(reranker)
+
+	vec := NewVectorEinoRetriever(r)
+	mq, err := multiquery.NewRetriever(ctx, &multiquery.Config{
+		RewriteLLM:    rewriteLLM,
+		MaxQueriesNum: r.config.MultiQuery.MaxQueriesEffective(),
+		OrigRetriever: vec,
+	})
+	if err != nil {
+		return fmt.Errorf("multi_query: %w", err)
+	}
+
+	r.pipeline = newKnowledgePipelineRetriever(mq, r)
+	if r.logger != nil {
+		provider := r.config.Rerank.ProviderEffective(strings.TrimSpace(openAI.BaseURL))
+		r.logger.Info("知识库检索流水线已启用",
+			zap.String("pipeline", "MultiQuery→Vector→Rerank→PostRetrieve"),
+			zap.Int("multi_query_max", r.config.MultiQuery.MaxQueriesEffective()),
+			zap.String("rerank_provider", provider),
+			zap.String("rerank_model", r.config.Rerank.ModelEffective(provider)),
+		)
+	}
+	return nil
+}
@@ -814,6 +814,23 @@ func (m *ExternalMCPManager) CancelToolExecution(id string) bool {
 	return m.CancelToolExecutionWithNote(id, "")
 }

+// ActiveRunningExecutionIDs 返回当前进程内仍登记 cancel 的外部 MCP executionId 快照。
+func (m *ExternalMCPManager) ActiveRunningExecutionIDs() map[string]struct{} {
+	if m == nil {
+		return nil
+	}
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	if len(m.runningCancels) == 0 {
+		return nil
+	}
+	out := make(map[string]struct{}, len(m.runningCancels))
+	for id := range m.runningCancels {
+		out[id] = struct{}{}
+	}
+	return out
+}
+
 // updateStats 更新统计信息
 func (m *ExternalMCPManager) updateStats(toolName string, failed bool) {
 	now := time.Now()
@@ -11,7 +11,16 @@ type ToolRunRegistry interface {
 	UnregisterRunningTool(conversationID, executionID string)
 }

+// EinoExecuteRunRegistry 登记进行中的 Eino filesystem execute，供「中断并继续」终止 amass 等长命令。
+type EinoExecuteRunRegistry interface {
+	RegisterActiveEinoExecute(conversationID string, cancel context.CancelFunc)
+	UnregisterActiveEinoExecute(conversationID string)
+	AbortActiveEinoExecute(conversationID, note string) bool
+	TakeEinoExecuteAbortNote(conversationID string) string
+}
+
 type toolRunRegistryCtxKey struct{}
+type einoExecuteRunRegistryCtxKey struct{}
 type mcpConversationIDCtxKey struct{}

 // WithToolRunRegistry 将登记器注入 ctx（Eino / 原生 Agent 任务 ctx）。
@@ -31,6 +40,23 @@ func ToolRunRegistryFromContext(ctx context.Context) ToolRunRegistry {
 	return v
 }

+// WithEinoExecuteRunRegistry 将 Eino execute 取消登记器注入 ctx。
+func WithEinoExecuteRunRegistry(ctx context.Context, reg EinoExecuteRunRegistry) context.Context {
+	if ctx == nil || reg == nil {
+		return ctx
+	}
+	return context.WithValue(ctx, einoExecuteRunRegistryCtxKey{}, reg)
+}
+
+// EinoExecuteRunRegistryFromContext 取出 Eino execute 登记器（无则 nil）。
+func EinoExecuteRunRegistryFromContext(ctx context.Context) EinoExecuteRunRegistry {
+	if ctx == nil {
+		return nil
+	}
+	v, _ := ctx.Value(einoExecuteRunRegistryCtxKey{}).(EinoExecuteRunRegistry)
+	return v
+}
+
 // WithMCPConversationID 将对话 ID 注入 ctx，供 CallTool 内与 executionId 关联。
 func WithMCPConversationID(ctx context.Context, conversationID string) context.Context {
 	if ctx == nil {
@@ -921,9 +921,8 @@ func (s *Server) CallTool(ctx context.Context, toolName string, args map[string]
 	return finalResult, executionID, nil
 }

-// RecordCompletedToolInvocation 将已在其它路径完成的工具调用写入监控存储（格式与 CallTool 结束后一致），
-// 用于 Eino ADK filesystem execute 等未经过 CallTool 的场景；返回 executionId 供助手消息 mcpExecutionIds 关联。
-func (s *Server) RecordCompletedToolInvocation(toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+// BeginToolExecution 创建 running 状态的执行记录，供 Eino 等非 CallTool 路径在工具开始时落库。
+func (s *Server) BeginToolExecution(toolName string, args map[string]interface{}) string {
 	if s == nil {
 		return ""
 	}
@@ -931,21 +930,73 @@ func (s *Server) RecordCompletedToolInvocation(toolName string, args map[string]
 		args = map[string]interface{}{}
 	}
 	executionID := uuid.New().String()
-	now := time.Now()
-	failed := invokeErr != nil
-	exec := &ToolExecution{
+	execution := &ToolExecution{
 		ID:        executionID,
 		ToolName:  toolName,
 		Arguments: args,
-		StartTime: now,
-		EndTime:   &now,
-		Duration:  0,
+		Status:    "running",
+		StartTime: time.Now(),
 	}
+
+	s.mu.Lock()
+	s.executions[executionID] = execution
+	s.cleanupOldExecutions()
+	s.mu.Unlock()
+
+	if s.storage != nil {
+		if err := s.storage.SaveToolExecution(execution); err != nil {
+			s.logger.Warn("保存执行记录到数据库失败", zap.Error(err))
+		}
+	}
+	return executionID
+}
+
+// FinishToolExecution 完成先前 BeginToolExecution 创建的记录；executionID 为空时等同 RecordCompletedToolInvocation。
+func (s *Server) FinishToolExecution(executionID, toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+	if s == nil {
+		return ""
+	}
+	if args == nil {
+		args = map[string]interface{}{}
+	}
+	id := strings.TrimSpace(executionID)
+	if id == "" {
+		return s.RecordCompletedToolInvocation(toolName, args, resultText, invokeErr)
+	}
+
+	now := time.Now()
+	failed := invokeErr != nil
+	var finalResult *ToolResult
+
+	s.mu.Lock()
+	exec, inMem := s.executions[id]
+	if !inMem || exec == nil {
+		exec = &ToolExecution{
+			ID:        id,
+			ToolName:  toolName,
+			Arguments: args,
+			StartTime: now,
+		}
+		s.executions[id] = exec
+	} else if toolName != "" {
+		exec.ToolName = toolName
+	}
+	if len(args) > 0 {
+		exec.Arguments = args
+	}
+	exec.EndTime = &now
+	if exec.StartTime.IsZero() {
+		exec.StartTime = now
+	}
+	exec.Duration = now.Sub(exec.StartTime)
+
 	if failed {
-		exec.Status = "failed"
-		exec.Error = invokeErr.Error()
+		st, msg := executionStatusAndMessage(invokeErr)
+		exec.Status = st
+		exec.Error = msg
 		if strings.TrimSpace(resultText) != "" {
-			exec.Result = &ToolResult{Content: []Content{{Type: "text", Text: resultText}}}
+			finalResult = &ToolResult{Content: []Content{{Type: "text", Text: resultText}}}
+			exec.Result = finalResult
 		}
 	} else {
 		exec.Status = "completed"
@@ -953,15 +1004,31 @@ func (s *Server) RecordCompletedToolInvocation(toolName string, args map[string]
 		if strings.TrimSpace(text) == "" {
 			text = "（无输出）"
 		}
-		exec.Result = &ToolResult{Content: []Content{{Type: "text", Text: text}}}
+		finalResult = &ToolResult{Content: []Content{{Type: "text", Text: text}}}
+		exec.Result = finalResult
 	}
+	s.mu.Unlock()
+
 	if s.storage != nil {
 		if err := s.storage.SaveToolExecution(exec); err != nil {
-			s.logger.Warn("RecordCompletedToolInvocation 保存失败", zap.Error(err))
+			s.logger.Warn("保存执行记录到数据库失败", zap.Error(err))
 		}
 	}
-	s.updateStats(toolName, failed)
-	return executionID
+
+	s.updateStats(exec.ToolName, failed)
+
+	if s.storage != nil {
+		s.mu.Lock()
+		delete(s.executions, id)
+		s.mu.Unlock()
+	}
+	return id
+}
+
+// RecordCompletedToolInvocation 将已在其它路径完成的工具调用写入监控存储（格式与 CallTool 结束后一致），
+// 用于 Eino ADK filesystem execute 等未经过 CallTool 的场景；返回 executionId 供助手消息 mcpExecutionIds 关联。
+func (s *Server) RecordCompletedToolInvocation(toolName string, args map[string]interface{}, resultText string, invokeErr error) string {
+	return s.FinishToolExecution("", toolName, args, resultText, invokeErr)
 }

 // UpdateToolExecutionResult 将监控库中的工具结果更新为送入模型的展示正文（如 reduction 后的 persisted-output）。
@@ -1103,6 +1170,23 @@ func (s *Server) CancelToolExecution(id string) bool {
 	return s.CancelToolExecutionWithNote(id, "")
 }

+// ActiveRunningExecutionIDs 返回当前进程内仍登记 cancel 的 executionId 快照。
+func (s *Server) ActiveRunningExecutionIDs() map[string]struct{} {
+	if s == nil {
+		return nil
+	}
+	s.runningCancelsMu.Lock()
+	defer s.runningCancelsMu.Unlock()
+	if len(s.runningCancels) == 0 {
+		return nil
+	}
+	out := make(map[string]struct{}, len(s.runningCancels))
+	for id := range s.runningCancels {
+		out[id] = struct{}{}
+	}
+	return out
+}
+
 // initDefaultPrompts 初始化默认提示词模板
 func (s *Server) initDefaultPrompts() {
 	s.mu.Lock()
@@ -199,6 +199,8 @@ type ToolExecution struct {
 	StartTime time.Time              `json:"startTime"`
 	EndTime   *time.Time             `json:"endTime,omitempty"`
 	Duration  time.Duration          `json:"duration,omitempty"`
+	// ConversationID 仅 API 展示用（进行中的 Agent 任务），不写入 tool_executions 表。
+	ConversationID string `json:"conversationId,omitempty"`
 }

 // ToolStats 工具统计信息
@@ -0,0 +1,101 @@
+package monitor
+
+import (
+	"time"
+
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+const (
+	staleRunningMinAge       = 45 * time.Second
+	staleRunningReconcileGap = 2 * time.Minute
+)
+
+// ExecutionReconciler 在启动或运行期将无对应协程的 running 执行记录收尾为 cancelled。
+type ExecutionReconciler struct {
+	db          *database.DB
+	mcpServer   *mcp.Server
+	externalMgr *mcp.ExternalMCPManager
+	logger      *zap.Logger
+}
+
+// NewExecutionReconciler creates a reconciler for orphaned MCP tool executions.
+func NewExecutionReconciler(db *database.DB, mcpServer *mcp.Server, externalMgr *mcp.ExternalMCPManager, logger *zap.Logger) *ExecutionReconciler {
+	return &ExecutionReconciler{
+		db:          db,
+		mcpServer:   mcpServer,
+		externalMgr: externalMgr,
+		logger:      logger,
+	}
+}
+
+// ReconcileOnStartup marks every persisted running row as cancelled (safe right after process start).
+func (r *ExecutionReconciler) ReconcileOnStartup() {
+	if r == nil || r.db == nil {
+		return
+	}
+	now := time.Now()
+	n, err := r.db.CancelOrphanedRunningToolExecutions(now, "执行已中断（服务重启）")
+	if err != nil {
+		if r.logger != nil {
+			r.logger.Warn("启动时清理孤儿 running 工具执行记录失败", zap.Error(err))
+		}
+		return
+	}
+	if n > 0 && r.logger != nil {
+		r.logger.Info("启动时已收尾孤儿 running 工具执行记录", zap.Int64("count", n))
+	}
+}
+
+func (r *ExecutionReconciler) activeExecutionIDs() map[string]struct{} {
+	ids := make(map[string]struct{})
+	if r.mcpServer != nil {
+		for id := range r.mcpServer.ActiveRunningExecutionIDs() {
+			ids[id] = struct{}{}
+		}
+	}
+	if r.externalMgr != nil {
+		for id := range r.externalMgr.ActiveRunningExecutionIDs() {
+			ids[id] = struct{}{}
+		}
+	}
+	return ids
+}
+
+// ReconcileStaleRunning finalizes running rows that are not tracked in-memory and older than staleRunningMinAge.
+func (r *ExecutionReconciler) ReconcileStaleRunning() {
+	if r == nil || r.db == nil {
+		return
+	}
+	now := time.Now()
+	n, err := r.db.FinalizeStaleRunningToolExecutions(now, staleRunningMinAge, r.activeExecutionIDs(), "执行已中断（会话已结束）")
+	if err != nil {
+		if r.logger != nil {
+			r.logger.Warn("定期收尾 stale running 工具执行记录失败", zap.Error(err))
+		}
+		return
+	}
+	if n > 0 && r.logger != nil {
+		r.logger.Info("已收尾 stale running 工具执行记录", zap.Int64("count", n))
+	}
+}
+
+// StartStaleRunningReconcileLoop periodically reconciles orphaned running tool executions.
+func StartStaleRunningReconcileLoop(r *ExecutionReconciler, logger *zap.Logger) {
+	if r == nil {
+		return
+	}
+	go func() {
+		ticker := time.NewTicker(staleRunningReconcileGap)
+		defer ticker.Stop()
+		for range ticker.C {
+			r.ReconcileStaleRunning()
+			if logger != nil {
+				logger.Debug("monitor stale running reconcile tick completed")
+			}
+		}
+	}()
+}
@@ -0,0 +1,38 @@
+package monitor
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func TestExecutionReconciler_ReconcileOnStartup(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := database.NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	if err := db.SaveToolExecution(&mcp.ToolExecution{
+		ID: "run-1", ToolName: "hydra", Status: "running", StartTime: time.Now().Add(-time.Hour),
+	}); err != nil {
+		t.Fatalf("SaveToolExecution: %v", err)
+	}
+
+	r := NewExecutionReconciler(db, mcp.NewServer(zap.NewNop()), nil, zap.NewNop())
+	r.ReconcileOnStartup()
+
+	got, err := db.GetToolExecution("run-1")
+	if err != nil {
+		t.Fatalf("GetToolExecution: %v", err)
+	}
+	if got.Status != "cancelled" {
+		t.Fatalf("expected cancelled after startup reconcile, got %s", got.Status)
+	}
+}
@@ -0,0 +1,71 @@
+package monitor
+
+import (
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+
+	"go.uber.org/zap"
+)
+
+const retentionPurgeInterval = time.Hour
+
+// Service manages MCP tool execution monitor retention.
+type Service struct {
+	db     *database.DB
+	cfg    *config.Config
+	logger *zap.Logger
+}
+
+// NewService creates a monitor retention service.
+func NewService(db *database.DB, cfg *config.Config, logger *zap.Logger) *Service {
+	return &Service{db: db, cfg: cfg, logger: logger}
+}
+
+// RetentionDays returns configured retention; 0 means keep forever.
+func (s *Service) RetentionDays() int {
+	if s == nil || s.cfg == nil {
+		return config.MonitorConfig{}.RetentionDaysEffective()
+	}
+	return s.cfg.Monitor.RetentionDaysEffective()
+}
+
+// PurgeExpired deletes tool execution rows older than retention_days when configured.
+func (s *Service) PurgeExpired() {
+	if s == nil || s.db == nil || s.cfg == nil {
+		return
+	}
+	days := s.cfg.Monitor.RetentionDaysEffective()
+	if days <= 0 {
+		return
+	}
+	cutoff := time.Now().AddDate(0, 0, -days)
+	n, err := s.db.PurgeToolExecutionsBefore(cutoff)
+	if err != nil {
+		if s.logger != nil {
+			s.logger.Warn("清理过期 MCP 执行记录失败", zap.Error(err))
+		}
+		return
+	}
+	if n > 0 && s.logger != nil {
+		s.logger.Info("已清理过期 MCP 执行记录", zap.Int64("deleted", n), zap.Int("retention_days", days))
+	}
+}
+
+// StartRetentionLoop periodically purges expired tool execution rows.
+func StartRetentionLoop(s *Service, logger *zap.Logger) {
+	if s == nil {
+		return
+	}
+	go func() {
+		ticker := time.NewTicker(retentionPurgeInterval)
+		defer ticker.Stop()
+		for range ticker.C {
+			s.PurgeExpired()
+			if logger != nil {
+				logger.Debug("monitor retention tick completed")
+			}
+		}
+	}()
+}
@@ -0,0 +1,94 @@
+package monitor
+
+import (
+	"path/filepath"
+	"testing"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+	"cyberstrike-ai/internal/database"
+	"cyberstrike-ai/internal/mcp"
+
+	"go.uber.org/zap"
+)
+
+func TestServicePurgeExpired_respectsZeroRetention(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := database.NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	exec := &mcp.ToolExecution{
+		ID:        "ancient",
+		ToolName:  "curl::get",
+		Arguments: map[string]interface{}{},
+		Status:    "completed",
+		StartTime: mustParseTime(t, "2020-01-01T00:00:00Z"),
+	}
+	if err := db.SaveToolExecution(exec); err != nil {
+		t.Fatalf("SaveToolExecution: %v", err)
+	}
+
+	zero := 0
+	svc := NewService(db, &config.Config{
+		Monitor: config.MonitorConfig{RetentionDays: &zero},
+	}, zap.NewNop())
+	svc.PurgeExpired()
+
+	if _, err := db.GetToolExecution("ancient"); err != nil {
+		t.Fatalf("record should remain when retention_days=0: %v", err)
+	}
+}
+
+func TestServicePurgeExpired_deletesOldRows(t *testing.T) {
+	dbPath := filepath.Join(t.TempDir(), "monitor.db")
+	db, err := database.NewDB(dbPath, zap.NewNop())
+	if err != nil {
+		t.Fatalf("NewDB: %v", err)
+	}
+	defer db.Close()
+
+	exec := &mcp.ToolExecution{
+		ID:        "ancient",
+		ToolName:  "curl::get",
+		Arguments: map[string]interface{}{},
+		Status:    "completed",
+		StartTime: mustParseTime(t, "2020-01-01T00:00:00Z"),
+	}
+	if err := db.SaveToolExecution(exec); err != nil {
+		t.Fatalf("SaveToolExecution: %v", err)
+	}
+
+	days := 90
+	svc := NewService(db, &config.Config{
+		Monitor: config.MonitorConfig{RetentionDays: &days},
+	}, zap.NewNop())
+	svc.PurgeExpired()
+
+	if _, err := db.GetToolExecution("ancient"); err == nil {
+		t.Fatal("record should be purged when older than retention_days")
+	}
+}
+
+func TestRetentionDaysEffective_defaults(t *testing.T) {
+	got := config.MonitorConfig{}.RetentionDaysEffective()
+	if got != 90 {
+		t.Fatalf("default = %d, want 90", got)
+	}
+	zero := 0
+	cfg := config.MonitorConfig{RetentionDays: &zero}
+	if cfg.RetentionDaysEffective() != 0 {
+		t.Fatalf("zero = %d, want 0", cfg.RetentionDaysEffective())
+	}
+}
+
+func mustParseTime(t *testing.T, value string) time.Time {
+	t.Helper()
+	parsed, err := time.Parse(time.RFC3339, value)
+	if err != nil {
+		t.Fatalf("parse time: %v", err)
+	}
+	return parsed
+}
@@ -0,0 +1,16 @@
+package multiagent
+
+import (
+	"fmt"
+
+	"github.com/cloudwego/eino/adk"
+)
+
+// InitADK configures global Eino ADK settings. Call once at process startup before
+// any ADK middleware or agents are created.
+func InitADK() error {
+	if err := adk.SetLanguage(adk.LanguageChinese); err != nil {
+		return fmt.Errorf("adk set language: %w", err)
+	}
+	return nil
+}
@@ -0,0 +1,104 @@
+package multiagent
+
+import (
+	"context"
+	"strings"
+
+	"github.com/cloudwego/eino/adk"
+	"github.com/cloudwego/eino/schema"
+	"go.uber.org/zap"
+)
+
+// continuationSessionMarker matches Cursor / IDE session-resume user injections.
+const continuationSessionMarker = "This session is being continued from a previous conversation"
+
+// continuationUserDedupMiddleware keeps only the latest session-resume user message when
+// multiple continuation injections were stacked (e.g. after repeated out-of-context resumes).
+type continuationUserDedupMiddleware struct {
+	adk.BaseChatModelAgentMiddleware
+	logger *zap.Logger
+	phase  string
+}
+
+func newContinuationUserDedupMiddleware(logger *zap.Logger, phase string) adk.ChatModelAgentMiddleware {
+	return &continuationUserDedupMiddleware{logger: logger, phase: phase}
+}
+
+func (m *continuationUserDedupMiddleware) BeforeModelRewriteState(
+	ctx context.Context,
+	state *adk.ChatModelAgentState,
+	mc *adk.ModelContext,
+) (context.Context, *adk.ChatModelAgentState, error) {
+	_ = mc
+	if m == nil || state == nil || len(state.Messages) == 0 {
+		return ctx, state, nil
+	}
+	deduped, dropped := dedupContinuationUserMessages(state.Messages)
+	if dropped == 0 {
+		return ctx, state, nil
+	}
+	if m.logger != nil {
+		m.logger.Info("eino continuation user messages deduplicated",
+			zap.String("phase", m.phase),
+			zap.Int("dropped", dropped),
+			zap.Int("messages_before", len(state.Messages)),
+			zap.Int("messages_after", len(deduped)),
+		)
+	}
+	out := *state
+	out.Messages = deduped
+	return ctx, &out, nil
+}
+
+func adkUserMessageText(msg adk.Message) string {
+	if msg == nil {
+		return ""
+	}
+	var b strings.Builder
+	if s := strings.TrimSpace(msg.Content); s != "" {
+		b.WriteString(s)
+	}
+	for _, part := range msg.UserInputMultiContent {
+		if part.Type == schema.ChatMessagePartTypeText {
+			if s := strings.TrimSpace(part.Text); s != "" {
+				if b.Len() > 0 {
+					b.WriteByte('\n')
+				}
+				b.WriteString(s)
+			}
+		}
+	}
+	return b.String()
+}
+
+func isContinuationUserMessage(msg adk.Message) bool {
+	if msg == nil || msg.Role != schema.User {
+		return false
+	}
+	return strings.Contains(adkUserMessageText(msg), continuationSessionMarker)
+}
+
+func dedupContinuationUserMessages(msgs []adk.Message) ([]adk.Message, int) {
+	lastIdx := -1
+	contCount := 0
+	for i, msg := range msgs {
+		if !isContinuationUserMessage(msg) {
+			continue
+		}
+		contCount++
+		lastIdx = i
+	}
+	if contCount <= 1 {
+		return msgs, 0
+	}
+	out := make([]adk.Message, 0, len(msgs)-(contCount-1))
+	dropped := 0
+	for i, msg := range msgs {
+		if isContinuationUserMessage(msg) && i != lastIdx {
+			dropped++
+			continue
+		}
+		out = append(out, msg)
+	}
+	return out, dropped
+}
@@ -0,0 +1,65 @@
+package multiagent
+
+import (
+	"context"
+	"strings"
+	"testing"
+
+	"github.com/cloudwego/eino/adk"
+	"github.com/cloudwego/eino/schema"
+)
+
+func continuationUser(text string) adk.Message {
+	return &schema.Message{
+		Role: schema.User,
+		UserInputMultiContent: []schema.MessageInputPart{
+			{Type: schema.ChatMessagePartTypeText, Text: continuationSessionMarker + "\n" + text},
+			{Type: schema.ChatMessagePartTypeText, Text: "Please continue the conversation from where we left it off."},
+		},
+	}
+}
+
+func TestDedupContinuationUserMessages_KeepsLatest(t *testing.T) {
+	msgs := []adk.Message{
+		continuationUser("summary old"),
+		schema.UserMessage("real task"),
+		continuationUser("summary new"),
+	}
+	out, dropped := dedupContinuationUserMessages(msgs)
+	if dropped != 1 {
+		t.Fatalf("dropped=%d want 1", dropped)
+	}
+	if len(out) != 2 {
+		t.Fatalf("len=%d want 2", len(out))
+	}
+	if out[0].Role != schema.User || adkUserMessageText(out[0]) != "real task" {
+		t.Fatalf("first should remain real task, got %q", adkUserMessageText(out[0]))
+	}
+	if !strings.Contains(adkUserMessageText(out[1]), "summary new") {
+		t.Fatalf("latest continuation not kept: %q", adkUserMessageText(out[1]))
+	}
+}
+
+func TestDedupContinuationUserMessages_NoOpSingle(t *testing.T) {
+	msgs := []adk.Message{continuationUser("only"), schema.UserMessage("task")}
+	out, dropped := dedupContinuationUserMessages(msgs)
+	if dropped != 0 || len(out) != 2 {
+		t.Fatalf("unexpected change dropped=%d len=%d", dropped, len(out))
+	}
+}
+
+func TestContinuationUserDedupMiddleware(t *testing.T) {
+	mw := newContinuationUserDedupMiddleware(nil, "test")
+	state := &adk.ChatModelAgentState{Messages: []adk.Message{
+		continuationUser("old"),
+		continuationUser("new"),
+		schema.UserMessage("task"),
+	}}
+	_, out, err := mw.(*continuationUserDedupMiddleware).BeforeModelRewriteState(context.Background(), state, nil)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if len(out.Messages) != 2 {
+		t.Fatalf("want 2 messages after dedup, got %d", len(out.Messages))
+	}
+}
@@ -18,6 +18,7 @@ import (
 	"cyberstrike-ai/internal/einomcp"
 	"cyberstrike-ai/internal/einoobserve"
 	"cyberstrike-ai/internal/openai"
+	"cyberstrike-ai/internal/security"

 	"github.com/cloudwego/eino/adk"
 	"github.com/cloudwego/eino/schema"
@@ -90,7 +91,7 @@ type einoADKRunLoopArgs struct {
 	FilesystemMonitorRecord einomcp.ExecutionRecorder
 	MCPExecutionBinder      *MCPExecutionBinder

-	// ToolInvokeNotify 与 einomcp.ToolsFromDefinitions 共享：run loop 在迭代前 Set，MCP 桥 Fire 以补全 tool_result。
+	// ToolInvokeNotify 与 einomcp.ToolsFromDefinitions 共享：run loop 在迭代前 Set，execute/MCP 桥 Fire 时立即推送 tool_result（ADK 晚到经 toolResultSent 去重）。
 	ToolInvokeNotify *einomcp.ToolInvokeNotifyHolder

 	DA adk.Agent
@@ -196,6 +197,16 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		pendingByID[tc.ToolCallID] = tc
 		pendingQueueByAgent[tc.EinoAgent] = append(pendingQueueByAgent[tc.EinoAgent], tc.ToolCallID)
 	}
+	markPendingWithMonitor := func(tc toolCallPendingInfo) {
+		markPending(tc)
+		beginEinoADKFilesystemToolMonitor(
+			args.FilesystemMonitorAgent,
+			args.FilesystemMonitorRecord,
+			args.MCPExecutionBinder,
+			tc.ToolCallID,
+			tc.ToolName,
+		)
+	}
 	popNextPendingForAgent := func(agentName string) (toolCallPendingInfo, bool) {
 		pendingMu.Lock()
 		defer pendingMu.Unlock()
@@ -288,6 +299,8 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs

 	var toolResultSent sync.Map // toolCallID -> struct{}；ADK Tool 事件去重（权威正文来自 reduction 处理后的 agent 上下文）
 	tryEmitToolResultProgress := func(toolName, content, toolCallID string, isErr bool, agentName string) {
+		// 仅由 ADK schema.Tool 事件调用；MCP/execute 桥在 reduction 前的 ToolInvokeNotify 不得推送 tool_result，
+		// 否则全量输出会先占位并触发 toolResultSent 去重，导致 UI/监控展示与 agent 实际收到的截断正文不一致。
 		if progress == nil {
 			return
 		}
@@ -305,6 +318,7 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			"isError":        isErr,
 			"result":         content,
 			"resultPreview":  preview,
+			"agentFacing":    true, // 与 reduction 后送入 ChatModel 的正文一致，供前端展示
 			"conversationId": conversationID,
 			"einoAgent":      agentName,
 			"einoRole":       einoRoleTag(agentName),
@@ -331,7 +345,7 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			toolCallID = tid
 		}
 		recordPendingExecuteStdoutDup(toolName, content, isErr)
-		recordEinoADKFilesystemToolMonitor(args.FilesystemMonitorAgent, args.FilesystemMonitorRecord, toolName, toolCallID, runAccumulatedMsgs, content, isErr)
+		recordEinoADKFilesystemToolMonitor(args.FilesystemMonitorAgent, args.FilesystemMonitorRecord, args.MCPExecutionBinder, toolName, toolCallID, runAccumulatedMsgs, content, isErr)
 		if args.FilesystemMonitorAgent != nil && args.MCPExecutionBinder != nil {
 			if execID := args.MCPExecutionBinder.ExecutionID(toolCallID); execID != "" {
 				args.FilesystemMonitorAgent.UpdateMCPExecutionDisplayResult(execID, content)
@@ -339,12 +353,6 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		}
 		progress("tool_result", fmt.Sprintf("工具结果 (%s)", toolName), data)
 	}
-	if args.ToolInvokeNotify != nil {
-		args.ToolInvokeNotify.Set(func(toolCallID, toolName, einoAgent string, success bool, content string, invokeErr error) {
-			removePendingByID(strings.TrimSpace(toolCallID))
-			// tool_result 仅由下方 ADK schema.Tool 事件推送，正文与送入模型的上下文一致（含 reduction 截断）。
-		})
-	}

 	if args.EinoCallbacks != nil {
 		ctx = einoobserve.AttachAgentRunCallbacks(ctx, args.EinoCallbacks, einoobserve.Params{
@@ -383,6 +391,12 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		}
 	}
 	runner := adk.NewRunner(ctx, runnerCfg)
+	startRunnerIter := func(runMsgs []adk.Message) *adk.AsyncIterator[*adk.AgentEvent] {
+		if checkPointID != "" {
+			return runner.Run(ctx, runMsgs, adk.WithCheckPointID(checkPointID))
+		}
+		return runner.Run(ctx, runMsgs)
+	}
 	var iter *adk.AsyncIterator[*adk.AgentEvent]
 	if cpStore != nil && checkPointID != "" {
 		if _, existed, getErr := cpStore.Get(ctx, checkPointID); getErr != nil {
@@ -422,12 +436,9 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		}
 	}
 	if iter == nil {
-		if checkPointID != "" {
-			iter = runner.Run(ctx, msgs, adk.WithCheckPointID(checkPointID))
-		} else {
-			iter = runner.Run(ctx, msgs)
-		}
+		iter = startRunnerIter(msgs)
 	}
+	transientRetrier := newEinoTransientRunRetrier(einoTransientRunRetryPolicyFromArgs(args))
 	handleRunErr := func(runErr error) error {
 		if runErr == nil {
 			return nil
@@ -480,26 +491,67 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		return runErr
 	}

-	// maybeRetryTransientRun：不在此层 runner.Run/Resume；由 handler 落库 + loadHistoryFromAgentTrace 分段续跑（同中断并继续）。
-	maybeRetryTransientRun := func(runErr error) (retry bool, fatal error) {
-		if runErr == nil || !isEinoTransientRunError(runErr) {
+	maybeRetryTransientRun := func(runErr error) (restarted bool, fatal error) {
+		if runErr == nil {
+			return false, nil
+		}
+		if !isEinoTransientRunError(runErr) {
 			return false, handleRunErr(runErr)
 		}
+		restarted, restartMsgs, ctxSource, backoff, retErr := transientRetrier.tryRetry(
+			ctx, runErr, args, baseMsgs, runAccumulatedMsgs, baseAccumulatedCount,
+		)
+		if retErr != nil {
+			flushAllPendingAsFailed(runErr)
+			if logger != nil {
+				logger.Warn("eino transient retry exhausted",
+					zap.Error(retErr),
+					zap.String("orchestration", orchMode),
+					zap.Int("maxAttempts", transientRetrier.maxAttempts()))
+			}
+			return false, retErr
+		}
+		if !restarted {
+			return false, nil
+		}
+		attemptNo := transientRetrier.attempt()
+		maxAttempts := transientRetrier.maxAttempts()
 		if logger != nil {
-			logger.Warn("eino transient error, ending run segment for handler resume",
+			logger.Warn("eino transient error, retrying after backoff",
 				zap.Error(runErr),
-				zap.String("orchestration", orchMode))
+				zap.String("orchestration", orchMode),
+				zap.Int("attempt", attemptNo),
+				zap.Int("maxAttempts", maxAttempts),
+				zap.Duration("backoff", backoff))
 		}
 		if progress != nil {
-			progress("eino_run_retry", "遇到临时错误（限流或网络波动），将保存上下文并重试…", map[string]interface{}{
+			progress("eino_run_retry", fmt.Sprintf("遇到临时错误（限流或网络波动），%d 秒后第 %d/%d 次重试…", int(backoff.Seconds()), attemptNo, maxAttempts), map[string]interface{}{
 				"conversationId": conversationID,
 				"source":         "eino",
 				"orchestration":  orchMode,
 				"error":          runErr.Error(),
-				"resumeKind":     "trace_segment",
+				"attempt":        attemptNo,
+				"maxAttempts":    maxAttempts,
+				"backoffSec":     int(backoff.Seconds()),
+			})
+			progress("eino_run_retry", "已恢复上下文，正在重试…", map[string]interface{}{
+				"conversationId": conversationID,
+				"source":         "eino",
+				"orchestration":  orchMode,
+				"attempt":        attemptNo,
+				"contextSource":  string(ctxSource),
 			})
 		}
-		return false, ErrTransientRetryContinue
+		msgs = restartMsgs
+		iter = startRunnerIter(msgs)
+		return true, nil
+	}
+
+	// 仅在退避重试后真正收到数据/完成一步时清零，避免重启后首个无错 ADK 事件误把计数打回 0。
+	confirmTransientRetryRecovery := func() {
+		if transientRetrier.attempt() > 0 {
+			transientRetrier.reset()
+		}
 	}

 	takePartial := func(runErr error) (*RunResult, error) {
@@ -514,10 +566,10 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 	}

 	for {
-		// 检测 context 取消（用户关闭浏览器、请求超时等），flush pending 工具状态避免 UI 卡在 "执行中"。
-		select {
-		case <-ctx.Done():
-			flushAllPendingAsFailed(ctx.Err())
+		// iter.Next 可能长时间阻塞（工具执行、模型推理）；须与 ctx 联动，否则取消/超时无法及时 flush pending。
+		ev, ok, iterCtxErr := nextAgentEventWithContext(ctx, iter)
+		if iterCtxErr != nil {
+			flushAllPendingAsFailed(iterCtxErr)
 			if progress != nil {
 				if isInterruptContinue(ctx) {
 					progress("progress", "已暂停当前输出，正在合并用户补充并继续…", map[string]interface{}{
@@ -526,17 +578,14 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 						"kind":           "interrupt_continue",
 					})
 				} else {
-					progress("error", "Request cancelled / 请求已取消", map[string]interface{}{
+					progress("error", iterCtxErr.Error(), map[string]interface{}{
 						"conversationId": conversationID,
 						"source":         "eino",
 					})
 				}
 			}
-			return takePartial(ctx.Err())
-		default:
+			return takePartial(iterCtxErr)
 		}
-
-		ev, ok := iter.Next()
 		if !ok {
 			// iter 结束并不总是“正常完成”：
 			// 当取消/超时发生在 iter.Next() 阻塞期间时，可能直接返回 !ok。
@@ -583,9 +632,13 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			continue
 		}
 		if ev.Err != nil {
-			if _, retErr := maybeRetryTransientRun(ev.Err); retErr != nil {
+			restarted, retErr := maybeRetryTransientRun(ev.Err)
+			if retErr != nil {
 				return takePartial(retErr)
 			}
+			if restarted {
+				continue
+			}
 		}
 		if ev.AgentName != "" && progress != nil {
 			iterEinoAgent := orchestratorName
@@ -630,13 +683,16 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 					}
 				}
 			}
+			// 仅在代理切换时更新进度标题；同一代理的每个 ADK 事件不再重复刷 progress。
+			if einoLastAgent != ev.AgentName {
+				progress("progress", fmt.Sprintf("[Eino] %s", ev.AgentName), map[string]interface{}{
+					"conversationId": conversationID,
+					"einoAgent":      ev.AgentName,
+					"einoRole":       einoRoleTag(ev.AgentName),
+					"orchestration":  orchMode,
+				})
+			}
 			einoLastAgent = ev.AgentName
-			progress("progress", fmt.Sprintf("[Eino] %s", ev.AgentName), map[string]interface{}{
-				"conversationId": conversationID,
-				"einoAgent":      ev.AgentName,
-				"einoRole":       einoRoleTag(ev.AgentName),
-				"orchestration":  orchMode,
-			})
 		}
 		if ev.Output == nil || ev.Output.MessageOutput == nil {
 			continue
@@ -645,34 +701,9 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs

 		if mv.IsStreaming && mv.MessageStream != nil && mv.Role == schema.Tool {
 			toolName := strings.TrimSpace(mv.ToolName)
-			var toolBuf strings.Builder
-			streamToolCallID := ""
-			var toolStreamRecvErr error
-			for {
-				chunk, rerr := mv.MessageStream.Recv()
-				if errors.Is(rerr, io.EOF) {
-					break
-				}
-				if rerr != nil {
-					toolStreamRecvErr = rerr
-					break
-				}
-				if chunk == nil {
-					continue
-				}
-				if chunk.Content != "" {
-					toolBuf.WriteString(chunk.Content)
-				}
-				if tid := strings.TrimSpace(chunk.ToolCallID); tid != "" {
-					streamToolCallID = tid
-				}
-			}
-			content := toolBuf.String()
-			isErr := false
-			if strings.HasPrefix(content, einomcp.ToolErrorPrefix) {
-				isErr = true
-				content = strings.TrimPrefix(content, einomcp.ToolErrorPrefix)
-			}
+			content, streamToolCallID, toolStreamRecvErr := recvSchemaMessageStream(ctx, mv.MessageStream)
+			isErr := einoToolResultIsError(toolName, content)
+			content = einoToolResultBody(content)
 			if streamToolCallID != "" {
 				opts := []schema.ToolMessageOption{schema.WithToolName(toolName)}
 				runAccumulatedMsgs = append(runAccumulatedMsgs, schema.ToolMessage(content, streamToolCallID, opts...))
@@ -684,6 +715,9 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 					zap.String("agent", ev.AgentName),
 					zap.String("tool", toolName))
 			}
+			if toolStreamRecvErr == nil {
+				confirmTransientRetryRecovery()
+			}
 			continue
 		}

@@ -931,7 +965,7 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			if merged := mergeStreamingToolCallFragments(toolStreamFragments); len(merged) > 0 {
 				lastToolChunk = mergeMessageToolCalls(&schema.Message{ToolCalls: merged})
 			}
-			tryEmitToolCallsOnce(lastToolChunk, ev.AgentName, orchestratorName, conversationID, orchMode, progress, toolEmitSeen, subAgentToolStep, mainAgentToolStep, markPending)
+			tryEmitToolCallsOnce(lastToolChunk, ev.AgentName, orchestratorName, conversationID, orchMode, progress, toolEmitSeen, subAgentToolStep, mainAgentToolStep, markPendingWithMonitor)
 			// 流式路径此前只把 tool_calls 推给进度 UI，未写入 runAccumulatedMsgs；落库后 loadHistory→RepairOrphan 会删掉全部 tool 结果，表现为「续跑/下轮失忆」。
 			if lastToolChunk != nil && len(lastToolChunk.ToolCalls) > 0 {
 				runAccumulatedMsgs = append(runAccumulatedMsgs, schema.AssistantMessage("", lastToolChunk.ToolCalls))
@@ -948,9 +982,15 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 						"einoRole":       einoRoleTag(ev.AgentName),
 					})
 				}
-				if _, retErr := maybeRetryTransientRun(streamRecvErr); retErr != nil {
+				restarted, retErr := maybeRetryTransientRun(streamRecvErr)
+				if retErr != nil {
 					return takePartial(retErr)
 				}
+				if restarted {
+					continue
+				}
+			} else {
+				confirmTransientRetryRecovery()
 			}
 			continue
 		}
@@ -960,7 +1000,7 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			continue
 		}
 		runAccumulatedMsgs = append(runAccumulatedMsgs, msg)
-		tryEmitToolCallsOnce(mergeMessageToolCalls(msg), ev.AgentName, orchestratorName, conversationID, orchMode, progress, toolEmitSeen, subAgentToolStep, mainAgentToolStep, markPending)
+		tryEmitToolCallsOnce(mergeMessageToolCalls(msg), ev.AgentName, orchestratorName, conversationID, orchMode, progress, toolEmitSeen, subAgentToolStep, mainAgentToolStep, markPendingWithMonitor)

 		if mv.Role == schema.Assistant {
 			if progress != nil && strings.TrimSpace(msg.ReasoningContent) != "" {
@@ -1035,15 +1075,13 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 			}

 			content := msg.Content
-			isErr := false
-			if strings.HasPrefix(content, einomcp.ToolErrorPrefix) {
-				isErr = true
-				content = strings.TrimPrefix(content, einomcp.ToolErrorPrefix)
-			}
+			isErr := einoToolResultIsError(toolName, content)
+			content = einoToolResultBody(content)

 			toolCallID := strings.TrimSpace(msg.ToolCallID)
 			tryEmitToolResultProgress(toolName, content, toolCallID, isErr, ev.AgentName)
 		}
+		confirmTransientRetryRecovery()
 	}

 	mcpIDsMu.Lock()
@@ -1054,32 +1092,9 @@ func runEinoADKAgentLoop(ctx context.Context, args *einoADKRunLoopArgs, baseMsgs
 		orchMode, runAccumulatedMsgs, persistTraceSource(args, runAccumulatedMsgs),
 		lastAssistant, lastPlanExecuteExecutor, emptyHint, ids, false,
 	)
-	if shouldEinoEmptyResponseContinue(out, emptyHint, len(runAccumulatedMsgs), baseAccumulatedCount) {
-		if logger != nil {
-			logger.Info("eino empty response, ending run segment for handler resume",
-				zap.String("conversationId", conversationID),
-				zap.String("orchestration", orchMode),
-				zap.Int("traceMessages", len(runAccumulatedMsgs)))
-		}
-		if progress != nil {
-			progress("eino_empty_response_continue", "会话已结束但未产生助手正文，正在基于轨迹自动续跑…", map[string]interface{}{
-				"conversationId": conversationID,
-				"source":         "eino",
-				"resumeKind":     "trace_segment",
-			})
-		}
-		return out, ErrEmptyResponseContinue
-	}
 	return out, nil
 }

-func shouldEinoEmptyResponseContinue(out *RunResult, emptyHint string, accumulatedLen, baseCount int) bool {
-	if out == nil || accumulatedLen <= baseCount {
-		return false
-	}
-	return strings.TrimSpace(out.Response) == strings.TrimSpace(emptyHint)
-}
-
 func persistTraceSource(args *einoADKRunLoopArgs, fallback []adk.Message) []adk.Message {
 	if args != nil && args.ModelFacingTrace != nil {
 		if snap := args.ModelFacingTrace.Snapshot(); len(snap) > 0 {
@@ -1094,17 +1109,119 @@ func einoPartialRunLastOutputHint() string {
 		"[Run ended abnormally; continue from the trace above without repeating completed steps.]"
 }

-// friendlyEinoExecuteInvokeTail 将 Eino execute 等非 MCP 路径的结尾错误转成简短提示；其它情况保留原 error 文本。
+// friendlyEinoExecuteInvokeTail 将 Eino execute 超时/中断/流异常转为简短提示。
+// 命令非零退出（ExecuteExitError）已有 exec 对齐的正文，不再追加「执行未正常结束」。
 func friendlyEinoExecuteInvokeTail(invokeErr error) string {
 	if invokeErr == nil {
 		return ""
 	}
+	var exitErr *ExecuteExitError
+	if errors.As(invokeErr, &exitErr) {
+		return ""
+	}
 	if errors.Is(invokeErr, context.DeadlineExceeded) {
 		return einoExecuteTimeoutUserHint()
 	}
+	if errors.Is(invokeErr, context.Canceled) {
+		return ""
+	}
+	if strings.Contains(invokeErr.Error(), "shell inactivity timeout") {
+		return ""
+	}
 	return "[执行未正常结束] " + invokeErr.Error()
 }

+// einoToolResultIsError 统一判断 Eino 工具结果是否应标记为错误（与 MCP exec 的 IsError 对齐）。
+func einoToolResultIsError(toolName, content string) bool {
+	if strings.HasPrefix(content, einomcp.ToolErrorPrefix) {
+		return true
+	}
+	if strings.TrimSpace(toolName) == "execute" && security.IsCommandFailureResult(content) {
+		return true
+	}
+	return false
+}
+
+// einoToolResultBody 去掉工具错误前缀，返回展示/持久化正文。
+func einoToolResultBody(content string) string {
+	if strings.HasPrefix(content, einomcp.ToolErrorPrefix) {
+		return strings.TrimPrefix(content, einomcp.ToolErrorPrefix)
+	}
+	return content
+}
+
+// nextAgentEventWithContext 在 ctx 取消时不再无限阻塞于 iter.Next()（工具执行/模型推理期间常见）。
+func nextAgentEventWithContext(ctx context.Context, iter *adk.AsyncIterator[*adk.AgentEvent]) (ev *adk.AgentEvent, ok bool, ctxErr error) {
+	if iter == nil {
+		return nil, false, nil
+	}
+	type nextRes struct {
+		ev *adk.AgentEvent
+		ok bool
+	}
+	ch := make(chan nextRes, 1)
+	go func() {
+		e, o := iter.Next()
+		ch <- nextRes{e, o}
+	}()
+	select {
+	case <-ctx.Done():
+		return nil, false, ctx.Err()
+	case res := <-ch:
+		return res.ev, res.ok, nil
+	}
+}
+
+// recvSchemaMessageStream 消费 ADK Tool 流式结果；ctx 取消时立即返回，避免 amass 等无输出时永久阻塞。
+func recvSchemaMessageStream(ctx context.Context, stream *schema.StreamReader[*schema.Message]) (content, toolCallID string, recvErr error) {
+	if stream == nil {
+		return "", "", nil
+	}
+	type streamMsg struct {
+		chunk *schema.Message
+		err   error
+	}
+	recvCh := make(chan streamMsg, 8)
+	go func() {
+		defer close(recvCh)
+		for {
+			ch, rerr := stream.Recv()
+			recvCh <- streamMsg{chunk: ch, err: rerr}
+			if rerr != nil {
+				return
+			}
+		}
+	}()
+	var buf strings.Builder
+	for {
+		select {
+		case <-ctx.Done():
+			return buf.String(), toolCallID, ctx.Err()
+		case sm, open := <-recvCh:
+			if !open {
+				return buf.String(), toolCallID, nil
+			}
+			rerr := sm.err
+			if errors.Is(rerr, io.EOF) {
+				return buf.String(), toolCallID, nil
+			}
+			if rerr != nil {
+				return buf.String(), toolCallID, rerr
+			}
+			chunk := sm.chunk
+			if chunk == nil {
+				continue
+			}
+			if chunk.Content != "" {
+				buf.WriteString(chunk.Content)
+			}
+			if tid := strings.TrimSpace(chunk.ToolCallID); tid != "" {
+				toolCallID = tid
+			}
+		}
+	}
+}
+
 func buildEinoRunResultFromAccumulated(
 	orchMode string,
 	runAccumulatedMsgs []adk.Message,
@@ -0,0 +1,74 @@
+package multiagent
+
+import (
+	"context"
+	"errors"
+	"io"
+	"testing"
+	"time"
+
+	"github.com/cloudwego/eino/schema"
+)
+
+func TestRecvSchemaMessageStream_EOF(t *testing.T) {
+	sr, sw := schema.Pipe[*schema.Message](4)
+	_ = sw.Send(schema.ToolMessage("hello", "tc-1"), nil)
+	sw.Close()
+
+	content, tid, err := recvSchemaMessageStream(context.Background(), sr)
+	if err != nil {
+		t.Fatalf("unexpected err: %v", err)
+	}
+	if content != "hello" {
+		t.Fatalf("content=%q want hello", content)
+	}
+	if tid != "tc-1" {
+		t.Fatalf("toolCallID=%q want tc-1", tid)
+	}
+}
+
+func TestRecvSchemaMessageStream_ContextCancel(t *testing.T) {
+	sr, sw := schema.Pipe[*schema.Message](4)
+	t.Cleanup(func() { sw.Close() })
+
+	ctx, cancel := context.WithCancel(context.Background())
+	go func() {
+		time.Sleep(30 * time.Millisecond)
+		cancel()
+	}()
+
+	content, _, err := recvSchemaMessageStream(ctx, sr)
+	if !errors.Is(err, context.Canceled) {
+		t.Fatalf("want context.Canceled, got %v content=%q", err, content)
+	}
+}
+
+func TestRecvSchemaMessageStream_RecvError(t *testing.T) {
+	sr, sw := schema.Pipe[*schema.Message](4)
+	want := errors.New("stream broken")
+	_ = sw.Send(nil, want)
+	sw.Close()
+
+	_, _, err := recvSchemaMessageStream(context.Background(), sr)
+	if !errors.Is(err, want) {
+		t.Fatalf("want %v, got %v", want, err)
+	}
+}
+
+func TestRecvSchemaMessageStream_NilStream(t *testing.T) {
+	content, tid, err := recvSchemaMessageStream(context.Background(), nil)
+	if err != nil || content != "" || tid != "" {
+		t.Fatalf("nil stream: content=%q tid=%q err=%v", content, tid, err)
+	}
+}
+
+func TestRecvSchemaMessageStream_EOFViaEmptyRead(t *testing.T) {
+	sr, sw := schema.Pipe[*schema.Message](4)
+	_ = sw.Send(nil, io.EOF)
+	sw.Close()
+
+	_, _, err := recvSchemaMessageStream(context.Background(), sr)
+	if err != nil {
+		t.Fatalf("EOF should not surface as error, got %v", err)
+	}
+}
@@ -0,0 +1,50 @@
+package multiagent
+
+import (
+	"github.com/cloudwego/eino/adk"
+	"go.uber.org/zap"
+)
+
+// einoChatModelTailConfig configures middleware appended after reduction/skill/plantask
+// and immediately before each ChatModel invocation pipeline completes.
+//
+// Order (best practice):
+//  1. system merge — accurate token count for summarization
+//  2. continuation user dedup — drop stale session-resume injections
+//  3. summarization
+//  4. orphan tool prune
+//  5. telemetry
+//  6. model-facing trace snapshot
+type einoChatModelTailConfig struct {
+	logger           *zap.Logger
+	phase            string
+	summarization    adk.ChatModelAgentMiddleware
+	modelName        string
+	conversationID   string
+	trace            *modelFacingTraceHolder
+	skipOrphanPruner bool
+	skipTelemetry    bool
+	skipTrace        bool
+}
+
+func appendEinoChatModelTailMiddlewares(handlers []adk.ChatModelAgentMiddleware, cfg einoChatModelTailConfig) []adk.ChatModelAgentMiddleware {
+	handlers = append(handlers, newSystemMessageNormalizerMiddleware(cfg.logger, cfg.phase))
+	handlers = append(handlers, newContinuationUserDedupMiddleware(cfg.logger, cfg.phase))
+	if cfg.summarization != nil {
+		handlers = append(handlers, cfg.summarization)
+	}
+	if !cfg.skipOrphanPruner {
+		handlers = append(handlers, newOrphanToolPrunerMiddleware(cfg.logger, cfg.phase))
+	}
+	if !cfg.skipTelemetry {
+		if teleMw := newEinoModelInputTelemetryMiddleware(cfg.logger, cfg.modelName, cfg.conversationID, cfg.phase); teleMw != nil {
+			handlers = append(handlers, teleMw)
+		}
+	}
+	if !cfg.skipTrace && cfg.trace != nil {
+		if capMw := newModelFacingTraceMiddleware(cfg.trace); capMw != nil {
+			handlers = append(handlers, capMw)
+		}
+	}
+	return handlers
+}
--- a/Show More
+++ b/Show More