Update config.yaml

README.md

@@ -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.*
 
@@ -110,7 +121,7 @@ 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**: 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
@@ -455,9 +466,10 @@ 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.
+- **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.
-- **Auto-indexing** – scans the `knowledge_base/` directory for Markdown files and automatically indexes them with embeddings.
+- **Vector retrieval** – cosine similarity over stored embeddings with configurable threshold, aligned with Eino `retriever.Retriever` usage.
-- **Web management** – create, update, delete knowledge items through the web UI, with category-based organization.
+- **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):**
@@ -479,6 +491,17 @@ 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 +562,17 @@ 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)

README_CN.md

@@ -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。*
 
@@ -109,7 +120,7 @@ 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**：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
@@ -453,9 +464,10 @@ 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）。
+- **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。
-- **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。
+- **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）。
-- **Web 管理**：通过 Web 界面创建、更新、删除知识项，支持分类管理。
+- **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）：**
@@ -477,6 +489,17 @@ 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 +560,17 @@ 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）

config.yaml

@@ -10,7 +10,7 @@
 # ============================================
 
 # 前端显示的版本号（可选，不填则显示默认版本）
-version: "v1.6.47"
+version: "v1.6.49"
 # 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
@@ -102,9 +102,69 @@ agent:
 
   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:
+  # 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
@@ -115,7 +175,6 @@ multi_agent:
   # 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 描述中注入用户原文；0=不截断（默认），>0=总字符上限，负数=禁用
-  user_verbatim_anchor_max_runes: 0 # 主代理 system 中逐轮保留用户原文（压缩后刷新）；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
@@ -126,7 +185,8 @@ 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
@@ -150,6 +210,7 @@ multi_agent:
     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: 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
@@ -222,9 +283,17 @@ 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: ""

docs/MULTI_AGENT_EINO.md

@@ -26,7 +26,7 @@
 | 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。 |
+| 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`**：`runner.go` 将 `prependEinoMiddlewares(einoMWMain)` 产物作为 `ExecPreMiddlewares` 挂到 **Executor**（与 Deep/Supervisor 主代理同序：patch → reduction → toolsearch → plantask → filesystem → skill → summarization tail）；Planner/Replanner 仅 summarization tail + prompt 预算截断，不跑 MCP 工具链。 |
 
 ## 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 +60,5 @@
 | 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。 |
+| 2026-07-02 | **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。 |

internal/app/app.go

@@ -21,6 +21,7 @@ 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"
@@ -109,6 +110,10 @@ func New(cfg *config.Config, log *logger.Logger, configPath string) (*App, error
 	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)
@@ -202,14 +207,12 @@ 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
+		// 创建检索器（Eino MultiQuery + 重排流水线）
-		retrievalConfig := &knowledge.RetrievalConfig{
+		retrievalConfig := knowledge.RetrievalConfigFromYAML(cfg.Knowledge.Retrieval)
-			TopK:                cfg.Knowledge.Retrieval.TopK,
-			SimilarityThreshold: cfg.Knowledge.Retrieval.SimilarityThreshold,
-			SubIndexFilter:      cfg.Knowledge.Retrieval.SubIndexFilter,
-			PostRetrieve:        cfg.Knowledge.Retrieval.PostRetrieve,
-		}
 		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)
@@ -363,6 +366,7 @@ 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)
 	externalMCPHandler := handler.NewExternalMCPHandler(externalMCPMgr, cfg, configPath, log.Logger)
 	externalMCPHandler.SetAudit(auditSvc)
 	roleHandler := handler.NewRoleHandler(cfg, configPath, log.Logger)
@@ -812,11 +816,18 @@ 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/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)
@@ -1787,14 +1798,12 @@ func initializeKnowledge(
 		return nil, fmt.Errorf("初始化知识库嵌入器失败: %w", err)
 	}
 
-	// 创建检索器
+	// 创建检索器（Eino MultiQuery + 重排流水线）
-	retrievalConfig := &knowledge.RetrievalConfig{
+	retrievalConfig := knowledge.RetrievalConfigFromYAML(cfg.Knowledge.Retrieval)
-		TopK:                cfg.Knowledge.Retrieval.TopK,
-		SimilarityThreshold: cfg.Knowledge.Retrieval.SimilarityThreshold,
-		SubIndexFilter:      cfg.Knowledge.Retrieval.SubIndexFilter,
-		PostRetrieve:        cfg.Knowledge.Retrieval.PostRetrieve,
-	}
 	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)

internal/config/config.go

@@ -99,9 +99,6 @@ type MultiAgentConfig struct {
 	// 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"`
-	// UserVerbatimAnchorMaxRunes injects all user turns verbatim into system prompt (survives summarization refresh).
-	// 0 (default) = no cap; >0 = total rune cap; negative disables anchor injection.
-	UserVerbatimAnchorMaxRunes int `yaml:"user_verbatim_anchor_max_runes,omitempty" json:"user_verbatim_anchor_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"`
 	// EinoMiddleware wires optional ADK middleware (patchtoolcalls, toolsearch, plantask, reduction) and Deep extras.
@@ -110,11 +107,6 @@ type MultiAgentConfig struct {
 	EinoCallbacks MultiAgentEinoCallbacksConfig `yaml:"eino_callbacks,omitempty" json:"eino_callbacks,omitempty"`
 }
 
-// UserVerbatimAnchorMaxRunesEffective returns max runes for user verbatim anchor; 0 = unlimited; negative = disabled.
-func (c MultiAgentConfig) UserVerbatimAnchorMaxRunesEffective() int {
-	return c.UserVerbatimAnchorMaxRunes
-}
-
 // SubAgentUserContextMaxRunesEffective returns max runes for sub-agent task supplement; 0 = unlimited; negative = disabled.
 func (c MultiAgentConfig) SubAgentUserContextMaxRunesEffective() int {
 	return c.SubAgentUserContextMaxRunes
@@ -283,6 +275,8 @@ type MultiAgentEinoMiddlewareConfig struct {
 	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"`
 }
@@ -503,6 +497,17 @@ 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"`
@@ -627,10 +632,100 @@ type AgentConfig struct {
 }
 
 // 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"`
+}
+
+// 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 {
@@ -817,33 +912,13 @@ 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)
+		inlineTools := append([]ToolConfig(nil), cfg.Security.Tools...)
-		toolsDir := cfg.Security.ToolsDir
+		toolsDir := ResolveToolsDir(cfg.Security.ToolsDir, path)
-
+		merged, err := MergeToolsFromDir(toolsDir, inlineTools)
-		// 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)
 		if err != nil {
 			return nil, fmt.Errorf("从工具目录加载工具配置失败: %w", err)
 		}
-
+		cfg.Security.Tools = merged
-		// 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
 	}
 
 	// 外部 MCP：迁移 + 环境变量展开
@@ -887,6 +962,10 @@ func Load(path string) (*Config, error) {
 		}
 	}
 
+	if err := ValidateWecomConfig(cfg.Robots.Wecom); err != nil {
+		return nil, err
+	}
+
 	return &cfg, nil
 }
 
@@ -1111,6 +1190,75 @@ 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
@@ -1329,7 +1477,12 @@ 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",
@@ -1425,7 +1578,7 @@ 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"`
@@ -1433,13 +1586,62 @@ 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]。
+	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"`
 }
 

internal/config/robots_validate_test.go

@@ -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)
+			}
+		})
+	}
+}

internal/config/tools_reload_test.go

@@ -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)
+	}
+}

internal/database/conversation.go

@@ -3,6 +3,7 @@ package database
 import (
 	"database/sql"
 	"encoding/json"
+	"errors"
 	"fmt"
 	"os"
 	"path/filepath"
@@ -577,6 +578,19 @@ func (db *DB) ListUngroupedConversations(limit, offset int, sortBy, projectID st
 	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
@@ -1057,6 +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()

internal/database/hitl_logs.go

@@ -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
+}

internal/database/hitl_logs_test.go

@@ -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)
+	}
+}

internal/database/project.go

@@ -111,19 +111,43 @@ func (db *DB) GetProject(id string) (*Project, error) {
 	return &p, nil
 }
 
-// CountProjects 统计项目数量。
+func projectListSearchPattern(q string) string {
-func (db *DB) CountProjects(status, search string) (int, error) {
+	q = strings.TrimSpace(q)
-	query := `SELECT COUNT(*) FROM projects WHERE 1=1`
+	if q == "" {
-	args := []interface{}{}
+		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 != "" {
+	if pattern := projectListSearchPattern(search); pattern != "" {
-		pattern := "%" + q + "%"
+		query += ` AND (LOWER(name) LIKE LOWER(?) ESCAPE '\' OR LOWER(COALESCE(description,'')) LIKE LOWER(?) ESCAPE '\' OR LOWER(id) LIKE LOWER(?) ESCAPE '\')`
-		query += " AND (name LIKE ? OR COALESCE(description,'') LIKE ?)"
+		args = append(args, pattern, pattern, pattern)
-		args = append(args, 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, args = appendProjectListFilters(query, args, status, search)
-		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 += " ORDER BY pinned DESC, updated_at DESC LIMIT ? OFFSET ?"
 	args = append(args, limit, offset)
 

internal/database/project_search_test.go

@@ -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)
+	}
+}

internal/handler/agent.go

@@ -77,6 +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")
@@ -179,6 +186,8 @@ type AgentHandler struct {
 	batchCronParser   cron.Parser
 	// 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
+	hitlStrategySaver  HitlAuditStrategySaver
+	auditLLM           *openai.Client
 	audit              *audit.Service
 }
 
@@ -218,9 +227,10 @@ func (h *AgentHandler) cancelActiveMCPToolForConversation(conversationID string)
 	}
 }
 
-// HitlToolWhitelistSaver 合并 HITL 免审批工具到全局配置并落盘
+// 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
@@ -236,6 +246,11 @@ 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,
@@ -246,6 +261,7 @@ 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),
+		auditLLM:         openai.NewClient(llmCfg, llmHTTP, logger),
 	}
 	tm.SetToolCanceler(handler.cancelActiveMCPToolForConversation)
 	if err := handler.hitlManager.EnsureSchema(); err != nil {
@@ -320,6 +336,7 @@ 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"`
 }
@@ -849,11 +866,6 @@ 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
@@ -866,6 +878,12 @@ 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
@@ -885,6 +903,7 @@ 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()
 	}
@@ -921,6 +940,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 			}
 			flushedThinking[sid] = true
 		}
+		syncHitlCognition()
 	}
 
 	return func(eventType, message string, data interface{}) {
@@ -981,6 +1001,25 @@ 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 {
@@ -1188,6 +1227,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 					respPlan.meta[k] = v
 				}
 			}
+			syncHitlCognition()
 			return
 		}
 		if eventType == "response" {
@@ -1257,6 +1297,7 @@ func (h *AgentHandler) createProgressCallback(runCtx context.Context, cancelRun
 					}
 				}
 			}
+			syncHitlCognition()
 			return
 		}
 
@@ -1489,17 +1530,51 @@ func (h *AgentHandler) SubscribeAgentTaskEvents(c *gin.Context) {
 	}
 }
 
+// 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,
 	})
 }
 

internal/handler/config.go

@@ -798,6 +798,10 @@ 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),
@@ -1329,6 +1333,17 @@ 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 +1432,7 @@ 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{
+		retrievalConfig := knowledge.RetrievalConfigFromYAML(h.config.Knowledge.Retrieval)
-			TopK:                h.config.Knowledge.Retrieval.TopK,
-			SimilarityThreshold: h.config.Knowledge.Retrieval.SimilarityThreshold,
-			SubIndexFilter:      h.config.Knowledge.Retrieval.SubIndexFilter,
-			PostRetrieve:        h.config.Knowledge.Retrieval.PostRetrieve,
-		}
 		h.retrieverUpdater.UpdateConfig(retrievalConfig)
 		h.logger.Info("检索器配置已更新",
 			zap.Int("top_k", retrievalConfig.TopK),
@@ -1705,6 +1715,13 @@ 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 +1768,20 @@ 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 +1802,21 @@ 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, "audit_agent_prompt", cfg.AuditAgentPrompt)
+	setStringInMap(hitlNode, "audit_agent_prompt_review_edit", cfg.AuditAgentPromptReviewEdit)
+}
+
+// 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) {

internal/handler/eino_empty_response_continue.go

@@ -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
+}

internal/handler/eino_single_agent.go

@@ -178,6 +178,7 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 	var cumulativeMCPExecutionIDs []string
 	// 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
@@ -239,6 +240,13 @@ func (h *AgentHandler) EinoSingleAgentLoopStream(c *gin.Context) {
 		}
 
 		if runErr == nil {
+			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
 		}

internal/handler/hitl.go

@@ -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))
+	union := make([]string, 0, len(req.SensitiveTools)+16)
-	for _, t := range gw {
+	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))
+		add(t)
-		if n == "" {
-			continue
-		}
-		if _, ok := seen[n]; ok {
-			continue
-		}
-		seen[n] = struct{}{}
-		union = append(union, strings.TrimSpace(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)
+		(conversation_id, enabled, mode, reviewer, sensitive_tools, timeout_seconds, updated_at)
-		VALUES (?, ?, ?, ?, ?, ?)
+		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`,
+		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, string(tools), timeout, time.Now())
+		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).
+	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, &toolsJSON, &timeout)
+		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
@@ -390,6 +383,7 @@ func (m *HITLManager) LoadConversationConfig(conversationID string) (*HITLReques
 	return &HITLRequest{
 		Enabled:        enabledInt == 1,
 		Mode:           mode,
+		Reviewer:       normalizeHitlReviewer(reviewer),
 		SensitiveTools: tools,
 		TimeoutSeconds: timeout,
 	}, nil
@@ -413,15 +407,16 @@ 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=?`,
+		comment := "HITL timeout auto-reject for safety"
-			time.Now(), p.InterruptID)
+		_, _ = m.db.Exec(`UPDATE hitl_interrupts SET status='timeout', decision='reject', decision_comment=?, decided_at=?, decided_by='system' WHERE id=?`,
-		return hitlDecision{Decision: "approve", Comment: "timeout auto approve"}, nil
+			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()
 	}
@@ -445,12 +440,57 @@ func (h *AgentHandler) waitHITLApproval(runCtx context.Context, cancelRun contex
 	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 +519,12 @@ 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 +542,7 @@ 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 +572,6 @@ 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 +579,12 @@ 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`
+	q, args := h.buildHitlListQuery(false)
-	args := []interface{}{}
+	q, args = h.appendHitlListFilters(q, args, c)
-	if conversationID != "" {
+	total, err := h.countHitlQuery(q, args)
-		q += " AND conversation_id = ?"
+	if err != nil {
-		args = append(args, conversationID)
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
-	}
+		return
-	if status != "all" {
-		q += " AND status = ?"
-		args = append(args, status)
 	}
 	q += " ORDER BY created_at DESC LIMIT ? OFFSET ?"
 	args = append(args, pageSize, offset)
@@ -557,41 +594,12 @@ func (h *AgentHandler) ListHITLPending(c *gin.Context) {
 		return
 	}
 	defer rows.Close()
-	items := make([]map[string]interface{}, 0)
+	items, err := h.scanHitlInterruptRows(rows)
-	for rows.Next() {
+	if err != nil {
-		var id, cid, mode, toolName, toolCallID, payload, rowStatus string
+		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
-		var messageID sql.NullString
+		return
-		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
-			}(),
-		})
 	}
-	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 +644,7 @@ 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()})
@@ -732,6 +740,7 @@ func (h *AgentHandler) UpsertHITLConversationConfig(c *gin.Context) {
 		return
 	}
 	req.Mode = normalizeHitlMode(req.Mode)
+	req.Reviewer = normalizeHitlReviewer(req.Reviewer)
 	if err := h.hitlManager.SaveConversationConfig(req.ConversationID, &req.HITLRequest); err != nil {
 		c.JSON(http.StatusInternalServerError, gin.H{"error": err.Error()})
 		return
@@ -753,6 +762,44 @@ 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(),
+	})
+}
+
+// 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 {

internal/handler/hitl_audit_agent.go

@@ -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
+}

internal/handler/hitl_audit_agent_test.go

@@ -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)
+	}
+}

internal/handler/hitl_cognition.go

@@ -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
+	}
+}

internal/handler/hitl_context.go

@@ -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)
+}

internal/handler/hitl_context_test.go

@@ -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)
+	}
+}

internal/handler/hitl_execution.go

@@ -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)
+}

internal/handler/hitl_execution_test.go

@@ -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)
+	}
+}

internal/handler/hitl_logs.go

@@ -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))
+}

internal/handler/multi_agent.go

@@ -188,6 +188,7 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 	var cumulativeMCPExecutionIDs []string
 	// 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
@@ -251,6 +252,13 @@ func (h *AgentHandler) MultiAgentLoopStream(c *gin.Context) {
 		}
 
 		if runErr == nil {
+			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
 		}

internal/handler/project_context.go

@@ -7,7 +7,8 @@ import (
 	"go.uber.org/zap"
 )
 
-// agentSessionContextBlock 注入会话工作目录、项目黑板与用户原文锚点（用于 system prompt 追加块）。
+// 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 != "" {
@@ -16,9 +17,6 @@ func (h *AgentHandler) agentSessionContextBlock(conversationID string) string {
 	if bb := h.projectBlackboardBlock(conversationID); bb != "" {
 		parts = append(parts, bb)
 	}
-	if uv := h.userVerbatimAnchorBlock(conversationID); uv != "" {
-		parts = append(parts, uv)
-	}
 	return strings.Join(parts, "\n\n")
 }
 
@@ -70,29 +68,6 @@ func (h *AgentHandler) projectBlackboardBlock(conversationID string) string {
 	return strings.TrimSpace(block)
 }
 
-// userVerbatimAnchorBlock 从 messages 表构建用户各轮原文锚点（压缩后仍由 summarization Finalize 刷新）。
-func (h *AgentHandler) userVerbatimAnchorBlock(conversationID string) string {
-	if h == nil || h.db == nil || h.config == nil {
-		return ""
-	}
-	conversationID = strings.TrimSpace(conversationID)
-	if conversationID == "" {
-		return ""
-	}
-	maxRunes := h.config.MultiAgent.UserVerbatimAnchorMaxRunesEffective()
-	if maxRunes < 0 {
-		return ""
-	}
-	msgs, err := h.db.GetMessages(conversationID)
-	if err != nil {
-		if h.logger != nil {
-			h.logger.Warn("构建用户原文锚点失败", zap.String("conversationId", conversationID), zap.Error(err))
-		}
-		return ""
-	}
-	return project.BuildUserVerbatimAnchorBlockFromMessages(msgs, maxRunes)
-}
-
 // conversationProjectID 返回对话绑定的项目 ID；未绑定或查询失败时返回空字符串。
 func (h *AgentHandler) conversationProjectID(conversationID string) string {
 	if h == nil || h.db == nil {

internal/handler/robot.go

@@ -711,12 +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")
@@ -724,7 +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")
@@ -865,27 +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
+	// 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）
+	// 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 := h.config.Robots.Wecom.Token
+	token, ok := h.wecomRequireToken(c)
-	if token != "" {
+	if !ok {
-		if msgSignature == "" {
+		return
-			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, "")
+	if msgSignature == "" {
-			return
+		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, "")
-		var tmp wecomXML
+		return
-		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))
+	var tmp wecomXML
-			c.String(http.StatusOK, "")
+	if err := xml.Unmarshal(bodyRaw, &tmp); err != nil {
-			return
+		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, "")
-		expected := h.signWecomRequest(token, timestamp, nonce, tmp.Encrypt)
+		return
-		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))
+	expected := h.signWecomRequest(token, timestamp, nonce, tmp.Encrypt)
-			c.String(http.StatusOK, "")
+	if expected != msgSignature {
-			return
+		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
@@ -899,6 +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")

internal/handler/robot_wecom_test.go

@@ -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)
+	}
+}

internal/handler/task_manager.go

@@ -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"`
@@ -42,6 +43,9 @@ type AgentTask struct {
 	// 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)
 }
 
@@ -233,6 +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"`
@@ -352,6 +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
 }
 

internal/hitl/retention.go

@@ -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")
+			}
+		}
+	}()
+}

internal/hitl/retention_test.go

@@ -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)
+	}
+}

internal/knowledge/eino_pipeline_retriever.go

@@ -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)

internal/knowledge/eino_retrieve_chain.go

@@ -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]）。
+// BuildKnowledgeRetrieveChain 编译「查询字符串 → 文档列表」的 Eino Chain（MultiQuery → 向量 → 重排 → 后处理）。
-// 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。
 func BuildKnowledgeRetrieveChain(ctx context.Context, r *Retriever) (compose.Runnable[string, []*schema.Document], error) {
 	if r == nil {
 		return nil, fmt.Errorf("retriever is nil")

internal/knowledge/eino_retriever_adapter.go

@@ -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.
-//
+// It returns prefetch-sized vector candidates only; rerank and post-process run in [knowledgePipelineRetriever].
-// 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].
 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
 }
 

internal/knowledge/rerank_http.go

@@ -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)

internal/knowledge/rerank_http_test.go

@@ -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")
+	}
+}

internal/knowledge/retrieval_postprocess.go

@@ -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
+	fetch := topK * 4
-	if po != nil && po.PrefetchTopK > fetch {
+	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

internal/knowledge/retrieval_postprocess_test.go

@@ -28,8 +28,8 @@ func TestDedupeByNormalizedContent(t *testing.T) {
 }
 
 func TestEffectivePrefetchTopK(t *testing.T) {
-	if g := EffectivePrefetchTopK(5, nil); g != 5 {
+	if g := EffectivePrefetchTopK(5, nil); g != 20 {
-		t.Fatalf("got %d", g)
+		t.Fatalf("default prefetch got %d want 20", g)
 	}
 	if g := EffectivePrefetchTopK(5, &config.PostRetrieveConfig{PrefetchTopK: 50}); g != 50 {
 		t.Fatalf("got %d", g)

internal/knowledge/retriever.go

@@ -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
-	SubIndexFilter string
+	MultiQuery          config.MultiQueryConfig
-	PostRetrieve   config.PostRetrieveConfig
+	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]。
+// RetrievalConfigFromYAML maps API/YAML retrieval settings into the knowledge package.
-func (r *Retriever) AsEinoRetriever() retriever.Retriever {
+func RetrievalConfigFromYAML(r config.RetrievalConfig) *RetrievalConfig {
-	return NewVectorEinoRetriever(r)
+	return &RetrievalConfig{
+		TopK:                r.TopK,
+		SimilarityThreshold: r.SimilarityThreshold,
+		SubIndexFilter:      r.SubIndexFilter,
+		MultiQuery:          r.MultiQuery,
+		Rerank:              r.Rerank,
+		PostRetrieve:        r.PostRetrieve,
+	}
 }

internal/knowledge/wire_retriever.go

@@ -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
+}

internal/multiagent/eino_empty_response.go

@@ -0,0 +1,59 @@
+package multiagent
+
+import (
+	"strings"
+	"time"
+
+	"cyberstrike-ai/internal/config"
+)
+
+const defaultEmptyResponseContinueMaxAttempts = 5
+
+// IsEinoEmptyResponseResult 判断 Run 是否以「未捕获助手正文」占位结束（非真实用户可见回复）。
+func IsEinoEmptyResponseResult(result *RunResult) bool {
+	if result == nil {
+		return false
+	}
+	return isEinoEmptyResponseText(result.Response)
+}
+
+func isEinoEmptyResponseText(s string) bool {
+	s = strings.TrimSpace(s)
+	if s == "" {
+		return false
+	}
+	return strings.Contains(s, "no assistant text was captured") ||
+		strings.Contains(s, "未捕获到助手文本输出")
+}
+
+// HasEinoResumeTrace 轨迹非空，续跑才有上下文可恢复。
+func HasEinoResumeTrace(result *RunResult) bool {
+	if result == nil {
+		return false
+	}
+	s := strings.TrimSpace(result.LastAgentTraceInput)
+	return s != "" && s != "[]" && s != "null"
+}
+
+// EmptyResponseContinueMaxAttemptsFromConfig 无助手正文时 Handler 层退避续跑上限；0=默认 5。
+func EmptyResponseContinueMaxAttemptsFromConfig(mw *config.MultiAgentEinoMiddlewareConfig) int {
+	if mw != nil && mw.EmptyResponseContinueMaxAttempts > 0 {
+		return mw.EmptyResponseContinueMaxAttempts
+	}
+	return defaultEmptyResponseContinueMaxAttempts
+}
+
+// EmptyResponseContinueBackoff 与 run_retry 相同指数退避（2s, 4s, 8s… capped）。
+func EmptyResponseContinueBackoff(attempt int, mw *config.MultiAgentEinoMiddlewareConfig) time.Duration {
+	maxBackoff := defaultEinoRunRetryMaxBackoff
+	if mw != nil && mw.RunRetryMaxBackoffSec > 0 {
+		maxBackoff = time.Duration(mw.RunRetryMaxBackoffSec) * time.Second
+	}
+	return einoTransientRetryBackoff(attempt, maxBackoff)
+}
+
+// FormatEmptyResponseContinueUserMessage 系统自动续跑时注入的 user 轮次（不写入 messages 表气泡）。
+func FormatEmptyResponseContinueUserMessage() string {
+	return strings.TrimSpace(`【系统自动续跑 / Auto resume】
+上一轮 Eino 会话未产出可见助手正文（可能流式中断或仅完成工具调用）。请基于已有轨迹与工具结果继续推进，并给出阶段性总结；勿重复已完成步骤。`)
+}

internal/multiagent/eino_empty_response_test.go

@@ -0,0 +1,38 @@
+package multiagent
+
+import "testing"
+
+func TestIsEinoEmptyResponseResult(t *testing.T) {
+	empty := &RunResult{
+		Response: "(Eino ADK single-agent session completed but no assistant text was captured. Check process details or logs.) " +
+			"（Eino ADK 单代理会话已完成，但未捕获到助手文本输出。请查看过程详情或日志。）",
+	}
+	if !IsEinoEmptyResponseResult(empty) {
+		t.Fatal("expected empty placeholder response")
+	}
+	ok := &RunResult{Response: "扫描完成，发现 2 个开放端口。"}
+	if IsEinoEmptyResponseResult(ok) {
+		t.Fatalf("expected real response, got placeholder match")
+	}
+	if IsEinoEmptyResponseResult(nil) {
+		t.Fatal("nil result should be false")
+	}
+}
+
+func TestHasEinoResumeTrace(t *testing.T) {
+	if HasEinoResumeTrace(nil) {
+		t.Fatal("nil")
+	}
+	if HasEinoResumeTrace(&RunResult{LastAgentTraceInput: "[]"}) {
+		t.Fatal("enable resume on empty trace")
+	}
+	if !HasEinoResumeTrace(&RunResult{LastAgentTraceInput: `[{"role":"user","content":"hi"}]`}) {
+		t.Fatal("expected resume trace")
+	}
+}
+
+func TestEmptyResponseContinueMaxAttemptsFromConfig(t *testing.T) {
+	if got := EmptyResponseContinueMaxAttemptsFromConfig(nil); got != defaultEmptyResponseContinueMaxAttempts {
+		t.Fatalf("default: got %d want %d", got, defaultEmptyResponseContinueMaxAttempts)
+	}
+}

internal/multiagent/eino_orchestration.go

@@ -80,34 +80,9 @@ func NewPlanExecuteRoot(ctx context.Context, a *PlanExecuteRootArgs) (adk.Resuma
 		return nil, fmt.Errorf("plan_execute replanner: %w", err)
 	}
 
-	// 组装 executor handler 栈，顺序与 Deep/Supervisor 主代理一致（outermost first）。
+	execHandlers, err := buildPlanExecuteExecutorHandlers(ctx, a)
-	var execHandlers []adk.ChatModelAgentMiddleware
+	if err != nil {
-	// 1. patchtoolcalls, reduction, toolsearch, plantask（来自 prependEinoMiddlewares）
+		return nil, err
-	if len(a.ExecPreMiddlewares) > 0 {
-		execHandlers = append(execHandlers, a.ExecPreMiddlewares...)
-	}
-	// 2. filesystem 中间件（可选）
-	if a.FilesystemMiddleware != nil {
-		execHandlers = append(execHandlers, a.FilesystemMiddleware)
-	}
-	// 3. skill 中间件（可选）
-	if a.SkillMiddleware != nil {
-		execHandlers = append(execHandlers, a.SkillMiddleware)
-	}
-	// 4. pre-summarization normalize + continuation dedup, then summarization (与 Deep/Supervisor 一致)
-	if a.AppCfg != nil {
-		sumMw, sumErr := newEinoSummarizationMiddleware(ctx, a.ExecModel, a.AppCfg, a.MwCfg, a.ConversationID, a.DB, a.ProjectID, a.Logger)
-		if sumErr != nil {
-			return nil, fmt.Errorf("plan_execute executor summarization: %w", sumErr)
-		}
-		execHandlers = appendEinoChatModelTailMiddlewares(execHandlers, einoChatModelTailConfig{
-			logger:         a.Logger,
-			phase:          "plan_execute_executor",
-			summarization:  sumMw,
-			modelName:      a.ModelName,
-			conversationID: a.ConversationID,
-			trace:          a.ModelFacingTrace,
-		})
 	}
 	executor, err := newPlanExecuteExecutor(ctx, &planexecute.ExecutorConfig{
 		Model:         a.ExecModel,
@@ -130,6 +105,39 @@ func NewPlanExecuteRoot(ctx context.Context, a *PlanExecuteRootArgs) (adk.Resuma
 	})
 }
 
+// buildPlanExecuteExecutorHandlers 组装 Executor 中间件栈（outermost first），与 Deep/Supervisor 主代理对齐：
+// ExecPreMiddlewares（patch / reduction / toolsearch / plantask）→ filesystem → skill → summarization tail。
+func buildPlanExecuteExecutorHandlers(ctx context.Context, a *PlanExecuteRootArgs) ([]adk.ChatModelAgentMiddleware, error) {
+	if a == nil {
+		return nil, fmt.Errorf("plan_execute: args 为空")
+	}
+	var execHandlers []adk.ChatModelAgentMiddleware
+	if len(a.ExecPreMiddlewares) > 0 {
+		execHandlers = append(execHandlers, a.ExecPreMiddlewares...)
+	}
+	if a.FilesystemMiddleware != nil {
+		execHandlers = append(execHandlers, a.FilesystemMiddleware)
+	}
+	if a.SkillMiddleware != nil {
+		execHandlers = append(execHandlers, a.SkillMiddleware)
+	}
+	if a.AppCfg != nil {
+		sumMw, sumErr := newEinoSummarizationMiddleware(ctx, a.ExecModel, a.AppCfg, a.MwCfg, a.ConversationID, a.DB, a.ProjectID, a.Logger)
+		if sumErr != nil {
+			return nil, fmt.Errorf("plan_execute executor summarization: %w", sumErr)
+		}
+		execHandlers = appendEinoChatModelTailMiddlewares(execHandlers, einoChatModelTailConfig{
+			logger:         a.Logger,
+			phase:          "plan_execute_executor",
+			summarization:  sumMw,
+			modelName:      a.ModelName,
+			conversationID: a.ConversationID,
+			trace:          a.ModelFacingTrace,
+		})
+	}
+	return execHandlers, nil
+}
+
 // planExecutePlannerGenInput 将 orchestrator instruction 作为 SystemMessage 注入 planner 输入。
 // 返回 nil 时 Eino 使用内置默认 planner prompt。
 func planExecutePlannerGenInput(

internal/multiagent/eino_summarize.go

@@ -22,15 +22,60 @@ import (
 	"go.uber.org/zap"
 )
 
-// einoSummarizeUserInstruction：压缩历史时保留渗透测试关键信息。
+// einoSummarizeUserInstruction：压缩历史时保留渗透测试与用户约束关键信息。
-const einoSummarizeUserInstruction = `在保持所有关键安全测试信息完整的前提下压缩对话历史。
+// 结构对齐 Eino 最佳实践（禁止工具、<analysis>+<summary>、<all_user_messages>），章节为安全测试领域化。
+const einoSummarizeUserInstruction = `关键：仅以纯文本响应。禁止调用任何工具（read_file、exec、grep、glob、write、edit 等）。
+上述对话中已包含全部待压缩上下文；不要要求用户粘贴历史，不要输出「请提供待压缩的对话历史」等占位/meta 回复。
+工具调用将被拒绝并浪费唯一一次摘要机会。
 
-必须保留：已确认漏洞与攻击路径、工具输出中的核心发现、凭证与认证细节、架构与薄弱点、当前进度、失败尝试与死路、策略决策。
+你的任务：在保持所有关键安全测试信息完整的前提下压缩对话历史，使后续代理能无缝继续同一授权测试任务。
-保留精确技术细节（URL、路径、参数、Payload、版本号、报错原文可摘要但要点不丢）。
-将冗长扫描输出概括为结论；重复发现合并表述。
-已枚举资产须保留**可继承的摘要**：主域、关键子域/主机短表（或数量+代表样例）、高价值目标与已识别服务/端口要点，避免后续子代理因「看不见清单」而重复全量枚举。
 
-输出须使后续代理能无缝继续同一授权测试任务。`
+压缩原则：
+- 必须保留：已确认漏洞与攻击路径、工具输出核心发现、凭证与认证细节、架构与薄弱点、当前进度、失败尝试与死路、策略决策
+- 保留精确技术细节（URL、路径、参数、Payload、版本号；报错原文可摘要但要点不丢）
+- 冗长扫描输出概括为结论；重复发现合并表述
+- 已枚举资产须保留可继承摘要：主域、关键子域/主机短表（或数量+代表样例）、高价值目标、已识别服务/端口要点
+
+输出格式（严格遵循，仅一轮回复）：
+1. 先输出 <analysis> 块：按时间顺序梳理对话，检查是否涵盖下方各章节要点；analysis 仅供自检，保持简洁（建议 ≤400 字）
+2. 再输出 <summary> 块：按以下章节写入可继承的压缩报告（无信息处写「无」，禁止留空模板占位符）
+
+<summary>
+## 1. 授权范围与约束
+- 目标/范围/禁止项（域名、路径、IP、环境）
+- 凭证/认证信息（账号、Token、Cookie；敏感值原文保留）
+- 用户指定的方法、工具、优先级与待办
+- 否定约束（不测什么、不用什么手法）
+
+## 2. 资产与服务枚举摘要
+- 主域/核心资产、关键子域或主机短表（或数量+代表样例）
+- 高价值目标、已识别服务/端口要点
+- 资产状态（存活/可攻/已排除/待验证）
+
+## 3. 架构与已知薄弱点
+- 技术栈/部署拓扑/信任边界
+- 已识别薄弱点列表
+
+## 4. 已确认漏洞与攻击路径
+- 漏洞名/CVE、URL/路径、参数/Payload、PoC 要点、影响等级
+- 攻击链/利用路径（步骤化）
+
+## 5. 工具核心发现与扫描结论
+- 各工具结论（概括核心输出，非冗长日志）
+- 重复发现合并表述
+
+## 6. 所有用户消息
+<all_user_messages>
+- [逐条列出非 tool 结果的用户消息要点；敏感约束与原文措辞尽量保留]
+</all_user_messages>
+
+## 7. 当前进度、策略决策与下一步
+- 当前位置（已完成/进行中/卡点）
+- 失败尝试与死路（方法、现象/报错摘要、结论）
+- 策略决策与下一步具体操作（须与最近用户请求及未完成任务一致）
+</summary>
+
+提醒：不要调用任何工具；必须基于上文已有对话直接输出 <analysis> 与 <summary>，勿输出 analysis 以外的正文。`
 
 // newEinoSummarizationMiddleware 使用 Eino ADK Summarization 中间件（见 https://www.cloudwego.io/zh/docs/eino/core_modules/eino_adk/eino_adk_chatmodelagentmiddleware/middleware_summarization/）。
 // 触发阈值：估算 token 超过 openai.max_total_tokens * summarization_trigger_ratio（默认 0.8）时摘要。
@@ -144,13 +189,13 @@ func newEinoSummarizationMiddleware(
 			},
 		},
 		Finalize: func(ctx context.Context, originalMessages []adk.Message, summary adk.Message) ([]adk.Message, error) {
+			summary = stripAnalysisFromSummarizationMessage(summary)
 			out, ferr := summarizeFinalizeWithRecentAssistantToolTrail(ctx, originalMessages, summary, tokenCounter, recentTrailMax)
 			if ferr != nil {
 				return nil, ferr
 			}
 			if appCfg != nil {
 				out = refreshFactIndexInMessages(out, db, projectID, appCfg.Project, logger)
-				out = refreshUserVerbatimAnchorInMessages(out, db, conversationID, appCfg.MultiAgent.UserVerbatimAnchorMaxRunesEffective(), logger)
 			}
 			return out, nil
 		},
@@ -414,36 +459,6 @@ func writeSummarizationTranscript(path string, msgs []adk.Message) error {
 	return nil
 }
 
-// refreshUserVerbatimAnchorInMessages 压缩后从 messages 表刷新 system 中的用户原文锚点。
-func refreshUserVerbatimAnchorInMessages(msgs []adk.Message, db *database.DB, conversationID string, maxRunes int, logger *zap.Logger) []adk.Message {
-	if maxRunes < 0 || db == nil {
-		return msgs
-	}
-	conversationID = strings.TrimSpace(conversationID)
-	if conversationID == "" {
-		return msgs
-	}
-	rows, err := db.GetMessages(conversationID)
-	if err != nil {
-		if logger != nil {
-			logger.Warn("summarization: 刷新用户原文锚点失败",
-				zap.String("conversationId", conversationID),
-				zap.Error(err),
-			)
-		}
-		return msgs
-	}
-	block := project.BuildUserVerbatimAnchorBlockFromMessages(rows, maxRunes)
-	if block == "" {
-		return msgs
-	}
-	out := project.RefreshUserVerbatimAnchorInMessages(msgs, block)
-	if logger != nil {
-		logger.Info("summarization: 已刷新用户原文锚点", zap.String("conversationId", conversationID))
-	}
-	return out
-}
-
 func einoSummarizationTokenCounter(openAIModel string) summarization.TokenCounterFunc {
 	tc := agent.NewTikTokenCounter()
 	return func(ctx context.Context, input *summarization.TokenCounterInput) (int, error) {

internal/multiagent/eino_summarize_output.go

@@ -0,0 +1,73 @@
+package multiagent
+
+import (
+	"regexp"
+	"strings"
+
+	"github.com/cloudwego/eino/adk"
+	"github.com/cloudwego/eino/schema"
+)
+
+var (
+	summarizationAnalysisBlockRegex = regexp.MustCompile(`(?is)<analysis>\s*.*?\s*</analysis>`)
+	summarizationSummaryBlockRegex  = regexp.MustCompile(`(?is)<summary>\s*(.*?)\s*</summary>`)
+)
+
+// stripAnalysisFromSummarizationMessage removes the <analysis> block from a post-processed
+// Eino summary user message. Analysis helps one-shot generation quality but should not
+// occupy continuation context after compaction.
+func stripAnalysisFromSummarizationMessage(msg adk.Message) adk.Message {
+	if msg == nil {
+		return msg
+	}
+	cloned := *msg
+	if cloned.Content != "" {
+		cloned.Content = stripAnalysisFromSummarizationText(cloned.Content)
+	}
+	if len(cloned.UserInputMultiContent) > 0 {
+		parts := make([]schema.MessageInputPart, len(cloned.UserInputMultiContent))
+		copy(parts, cloned.UserInputMultiContent)
+		// Only the first text part carries model output plus Eino preamble/transcript path.
+		for i := range parts {
+			if parts[i].Type != schema.ChatMessagePartTypeText || parts[i].Text == "" {
+				continue
+			}
+			if i == 0 {
+				parts[i].Text = stripAnalysisFromSummarizationText(parts[i].Text)
+			}
+			break
+		}
+		cloned.UserInputMultiContent = parts
+	}
+	return &cloned
+}
+
+func stripAnalysisFromSummarizationText(text string) string {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return text
+	}
+	stripped := strings.TrimSpace(summarizationAnalysisBlockRegex.ReplaceAllString(text, ""))
+	if stripped == "" {
+		return text
+	}
+	return stripped
+}
+
+// extractSummarizationSummaryBody returns the inner text of the last <summary> block when present.
+// Used by tests and optional strict compaction paths.
+func extractSummarizationSummaryBody(text string) (string, bool) {
+	text = strings.TrimSpace(text)
+	if text == "" {
+		return "", false
+	}
+	all := summarizationSummaryBlockRegex.FindAllStringSubmatch(text, -1)
+	if len(all) == 0 || len(all[len(all)-1]) < 2 {
+		return "", false
+	}
+	body := strings.TrimSpace(all[len(all)-1][1])
+	if body == "" {
+		return "", false
+	}
+	return body, true
+}

internal/multiagent/eino_summarize_output_test.go

@@ -0,0 +1,67 @@
+package multiagent
+
+import (
+	"strings"
+	"testing"
+
+	"github.com/cloudwego/eino/schema"
+)
+
+func TestStripAnalysisFromSummarizationText(t *testing.T) {
+	in := "<analysis>internal notes</analysis>\n\n<summary>\n## 1. 授权\n- example.com\n</summary>"
+	got := stripAnalysisFromSummarizationText(in)
+	if strings.Contains(got, "<analysis>") {
+		t.Fatalf("analysis block should be removed: %q", got)
+	}
+	if !strings.Contains(got, "## 1. 授权") {
+		t.Fatalf("summary body should remain: %q", got)
+	}
+}
+
+func TestStripAnalysisFromSummarizationMessage_UserInputMultiContent(t *testing.T) {
+	msg := &schema.Message{
+		Role: schema.User,
+		UserInputMultiContent: []schema.MessageInputPart{
+			{
+				Type: schema.ChatMessagePartTypeText,
+				Text: "此会话延续自此前一段因上下文耗尽而终止的对话。\n\n<analysis>draft</analysis>\n<summary>body</summary>\n\n完整记录位于：/tmp/transcript.txt",
+			},
+			{
+				Type: schema.ChatMessagePartTypeText,
+				Text: "请从我们中断的地方继续对话，无需向用户提出任何进一步的问题。",
+			},
+		},
+	}
+	out := stripAnalysisFromSummarizationMessage(msg)
+	if len(out.UserInputMultiContent) != 2 {
+		t.Fatalf("expected 2 parts, got %d", len(out.UserInputMultiContent))
+	}
+	if strings.Contains(out.UserInputMultiContent[0].Text, "<analysis>") {
+		t.Fatalf("part 0 should drop analysis: %q", out.UserInputMultiContent[0].Text)
+	}
+	if !strings.Contains(out.UserInputMultiContent[0].Text, "<summary>body</summary>") {
+		t.Fatalf("part 0 should keep summary: %q", out.UserInputMultiContent[0].Text)
+	}
+	if out.UserInputMultiContent[1].Text != "请从我们中断的地方继续对话，无需向用户提出任何进一步的问题。" {
+		t.Fatalf("continue instruction part should be unchanged: %q", out.UserInputMultiContent[1].Text)
+	}
+}
+
+func TestExtractSummarizationSummaryBody(t *testing.T) {
+	body, ok := extractSummarizationSummaryBody("<analysis>x</analysis><summary>  kept  </summary>")
+	if !ok || body != "kept" {
+		t.Fatalf("extract summary body: ok=%v body=%q", ok, body)
+	}
+	_, ok = extractSummarizationSummaryBody("plain text only")
+	if ok {
+		t.Fatal("expected false for plain text")
+	}
+}
+
+func TestStripAnalysisFromSummarizationText_NoAnalysisUnchanged(t *testing.T) {
+	in := "<summary>only summary</summary>"
+	got := stripAnalysisFromSummarizationText(in)
+	if got != in {
+		t.Fatalf("expected unchanged text, got %q", got)
+	}
+}

internal/multiagent/eino_summarize_payload.go

@@ -1,35 +1,12 @@
 package multiagent
 
 import (
-	"github.com/bytedance/sonic"
+	copenai "cyberstrike-ai/internal/openai"
 )
 
 // stripReasoningFromSummarizationPayload removes thinking / reasoning fields from a
 // chat-completions JSON body. Applied only to summarization Generate calls via
 // model.ModelOptions on the shared ChatModel — main-agent requests are unchanged.
 func stripReasoningFromSummarizationPayload(rawBody []byte) ([]byte, error) {
-	var payload map[string]any
+	return copenai.StripReasoningFromChatCompletionBody(rawBody)
-	if err := sonic.Unmarshal(rawBody, &payload); err != nil {
-		return rawBody, nil
-	}
-	changed := false
-	for _, key := range []string{
-		"thinking",
-		"reasoning_effort",
-		"output_config",
-		"reasoning",
-	} {
-		if _, ok := payload[key]; ok {
-			delete(payload, key)
-			changed = true
-		}
-	}
-	if !changed {
-		return rawBody, nil
-	}
-	out, err := sonic.Marshal(payload)
-	if err != nil {
-		return rawBody, err
-	}
-	return out, nil
 }

internal/multiagent/hitl_middleware.go

@@ -3,7 +3,6 @@ package multiagent
 import (
 	"context"
 	"errors"
-	"fmt"
 	"strings"
 
 	"github.com/cloudwego/eino/adk"
@@ -75,8 +74,8 @@ func hitlInvokableToolCallMiddleware() compose.InvokableToolMiddleware {
 					if err != nil {
 						if IsHumanRejectError(err) {
 							// Human rejection should be a soft tool result so the model can continue iterating.
-							msg := fmt.Sprintf("[HITL Reject] Tool '%s' was rejected by human reviewer. Reason: %s\nPlease adjust parameters/plan and continue without this call.",
+							// tool_search 须保持 JSON，否则 Eino toolsearch 中间件解析历史时会硬崩 ChatModel。
-								input.Name, strings.TrimSpace(err.Error()))
+							msg := HitlRejectToolResult(input.Name, err.Error())
 							// transfer_to_agent 在 Eino 中标记为 returnDirectly：工具成功后 ReAct 子图会直接 END，
 							// 并依赖真实工具内的 SendToolGenAction 触发移交。HITL 拒绝时不会执行真实工具，
 							// 若仍走 returnDirectly 分支，监督者会在无 Transfer 动作的情况下结束，模型不再迭代。
@@ -103,8 +102,7 @@ func hitlStreamableToolCallMiddleware() compose.StreamableToolMiddleware {
 					edited, err := fn(ctx, input.Name, input.Arguments)
 					if err != nil {
 						if IsHumanRejectError(err) {
-							msg := fmt.Sprintf("[HITL Reject] Tool '%s' was rejected by human reviewer. Reason: %s\nPlease adjust parameters/plan and continue without this call.",
+							msg := HitlRejectToolResult(input.Name, err.Error())
-								input.Name, strings.TrimSpace(err.Error()))
 							hitlClearReturnDirectlyIfTransfer(ctx, input.Name)
 							return &compose.StreamToolOutput{
 								Result: schema.StreamReaderFromArray([]string{msg}),

internal/multiagent/hitl_toolsearch_compat.go

@@ -0,0 +1,85 @@
+package multiagent
+
+import (
+	"encoding/json"
+	"fmt"
+	"strings"
+)
+
+const toolSearchToolName = "tool_search"
+
+// HitlExemptMetaTools 为编排/元工具：不直接执行攻击动作，但会阻塞 agent 控制流。
+// tool_search 必须免审批，否则其 HITL 拒绝结果与 Eino toolsearch 中间件不兼容（会硬崩 ChatModel）。
+var HitlExemptMetaTools = []string{
+	toolSearchToolName,
+	"skill",
+	"task",
+	"write_todos",
+	"transfer_to_agent",
+	"exit",
+	"TaskCreate",
+	"TaskGet",
+	"TaskUpdate",
+	"TaskList",
+}
+
+// IsToolSearchTool reports whether name is the Eino dynamictool tool_search meta-tool.
+func IsToolSearchTool(name string) bool {
+	return strings.EqualFold(strings.TrimSpace(name), toolSearchToolName)
+}
+
+// MergeHitlExemptMetaTools unions configured whitelist with built-in meta-tool exemptions.
+func MergeHitlExemptMetaTools(configured []string) []string {
+	merged := make([]string, 0, len(configured)+len(HitlExemptMetaTools))
+	seen := make(map[string]struct{}, len(configured)+len(HitlExemptMetaTools))
+	add := func(name string) {
+		n := strings.ToLower(strings.TrimSpace(name))
+		if n == "" {
+			return
+		}
+		if _, ok := seen[n]; ok {
+			return
+		}
+		seen[n] = struct{}{}
+		merged = append(merged, strings.TrimSpace(name))
+	}
+	for _, t := range configured {
+		add(t)
+	}
+	for _, t := range HitlExemptMetaTools {
+		add(t)
+	}
+	return merged
+}
+
+type toolSearchHitlRejectPayload struct {
+	SelectedTools []string `json:"selectedTools"`
+	HitlRejected  bool     `json:"_hitlRejected"`
+	Reason        string   `json:"reason"`
+}
+
+// HitlRejectToolResult returns a tool result body safe for downstream consumers.
+// tool_search must stay JSON-shaped so toolsearch.extractSelectedTools does not terminate the graph.
+func HitlRejectToolResult(toolName, reason string) string {
+	reason = strings.TrimSpace(reason)
+	if !IsToolSearchTool(toolName) {
+		if reason == "" {
+			reason = "rejected by reviewer"
+		}
+		return fmt.Sprintf("[HITL Reject] Tool '%s' was rejected by reviewer. Reason: %s\nPlease adjust parameters/plan and continue without this call.",
+			strings.TrimSpace(toolName), reason)
+	}
+	payload := toolSearchHitlRejectPayload{
+		SelectedTools: []string{},
+		HitlRejected:  true,
+		Reason:        reason,
+	}
+	if payload.Reason == "" {
+		payload.Reason = "tool_search rejected by reviewer; no dynamic tools unlocked"
+	}
+	out, err := json.Marshal(payload)
+	if err != nil {
+		return `{"selectedTools":[],"_hitlRejected":true,"reason":"tool_search rejected by reviewer"}`
+	}
+	return string(out)
+}

internal/multiagent/hitl_toolsearch_compat_test.go

@@ -0,0 +1,48 @@
+package multiagent
+
+import (
+	"encoding/json"
+	"strings"
+	"testing"
+)
+
+func TestHitlRejectToolResult_toolSearchIsJSON(t *testing.T) {
+	raw := HitlRejectToolResult("tool_search", "rejected by user: timeout")
+	var payload toolSearchHitlRejectPayload
+	if err := json.Unmarshal([]byte(raw), &payload); err != nil {
+		t.Fatalf("unmarshal: %v", err)
+	}
+	if len(payload.SelectedTools) != 0 {
+		t.Fatalf("expected empty selectedTools, got %v", payload.SelectedTools)
+	}
+	if !payload.HitlRejected {
+		t.Fatal("expected _hitlRejected true")
+	}
+	if !strings.Contains(payload.Reason, "timeout") {
+		t.Fatalf("reason=%q", payload.Reason)
+	}
+}
+
+func TestHitlRejectToolResult_otherToolKeepsLegacyText(t *testing.T) {
+	raw := HitlRejectToolResult("nmap", "too risky")
+	if strings.HasPrefix(raw, "{") {
+		t.Fatalf("expected legacy text, got %q", raw)
+	}
+	if !strings.HasPrefix(raw, "[HITL Reject]") {
+		t.Fatalf("expected [HITL Reject] prefix, got %q", raw)
+	}
+}
+
+func TestMergeHitlExemptMetaTools_includesToolSearch(t *testing.T) {
+	merged := MergeHitlExemptMetaTools([]string{"read_file"})
+	found := false
+	for _, name := range merged {
+		if IsToolSearchTool(name) {
+			found = true
+			break
+		}
+	}
+	if !found {
+		t.Fatalf("tool_search missing from %v", merged)
+	}
+}

internal/multiagent/plan_execute_executor_handlers_test.go

@@ -0,0 +1,85 @@
+package multiagent
+
+import (
+	"context"
+	"fmt"
+	"testing"
+
+	"cyberstrike-ai/internal/config"
+
+	"github.com/cloudwego/eino/adk"
+	"github.com/cloudwego/eino/components/tool"
+)
+
+type stubChatModelAgentMiddleware struct {
+	adk.BaseChatModelAgentMiddleware
+	tag string
+}
+
+func stubMW(tag string) adk.ChatModelAgentMiddleware {
+	return &stubChatModelAgentMiddleware{tag: tag}
+}
+
+func TestBuildPlanExecuteExecutorHandlers_IncludesExecPreMiddlewares(t *testing.T) {
+	t.Parallel()
+	pre := []adk.ChatModelAgentMiddleware{
+		stubMW("patch"),
+		stubMW("reduction"),
+	}
+
+	got, err := buildPlanExecuteExecutorHandlers(context.Background(), &PlanExecuteRootArgs{
+		ExecPreMiddlewares:   pre,
+		FilesystemMiddleware: stubMW("filesystem"),
+		SkillMiddleware:      stubMW("skill"),
+	})
+	if err != nil {
+		t.Fatalf("buildPlanExecuteExecutorHandlers: %v", err)
+	}
+	if len(got) != 4 {
+		t.Fatalf("expected 4 pre-tail handlers (2 pre + fs + skill), got %d", len(got))
+	}
+	for i, want := range []string{"patch", "reduction", "filesystem", "skill"} {
+		st, ok := got[i].(*stubChatModelAgentMiddleware)
+		if !ok || st.tag != want {
+			t.Fatalf("handler[%d]: got %#v want tag %q", i, got[i], want)
+		}
+	}
+}
+
+func stubTools(n int) []tool.BaseTool {
+	out := make([]tool.BaseTool, n)
+	for i := 0; i < n; i++ {
+		out[i] = stubTool{name: fmt.Sprintf("t%d", i)}
+	}
+	return out
+}
+
+func TestBuildPlanExecuteExecutorHandlers_NilArgs(t *testing.T) {
+	t.Parallel()
+	if _, err := buildPlanExecuteExecutorHandlers(context.Background(), nil); err == nil {
+		t.Fatal("expected error for nil args")
+	}
+}
+
+func TestPrependEinoMiddlewares_Main_IncludesPatch(t *testing.T) {
+	t.Parallel()
+	ctx := context.Background()
+	mw := configMultiAgentEinoMiddlewareForTest()
+	mw.ReductionEnable = false
+	mw.ToolSearchEnable = false
+	mw.PlantaskEnable = false
+	_, extra, _, err := prependEinoMiddlewares(ctx, mw, einoMWMain, stubTools(25), nil, "", "conv-test", "", nil)
+	if err != nil {
+		t.Fatalf("prependEinoMiddlewares: %v", err)
+	}
+	if len(extra) == 0 {
+		t.Fatal("expected patch middleware on einoMWMain when patch_tool_calls enabled")
+	}
+}
+
+func configMultiAgentEinoMiddlewareForTest() *config.MultiAgentEinoMiddlewareConfig {
+	patch := true
+	return &config.MultiAgentEinoMiddlewareConfig{
+		PatchToolCalls: &patch,
+	}
+}

internal/multiagent/runner.go

@@ -432,6 +432,22 @@ func RunDeepAgent(
 	var da adk.Agent
 	switch orchMode {
 	case "plan_execute":
+		plannerModelCfg := &einoopenai.ChatModelConfig{
+			APIKey:     appCfg.OpenAI.APIKey,
+			BaseURL:    strings.TrimSuffix(appCfg.OpenAI.BaseURL, "/"),
+			Model:      appCfg.OpenAI.Model,
+			HTTPClient: httpClient,
+		}
+		reasoning.ApplyPlanExecutePlannerModelConfig(plannerModelCfg, &appCfg.OpenAI)
+		peMainModel, perr := einoopenai.NewChatModel(ctx, plannerModelCfg)
+		if perr != nil {
+			return nil, fmt.Errorf("plan_execute 规划模型: %w", perr)
+		}
+		if logger != nil {
+			logger.Info("plan_execute: planner/replanner 使用无 reasoning 的独立 ChatModel（ToolChoiceForced 兼容）",
+				zap.String("model", appCfg.OpenAI.Model),
+			)
+		}
 		execModel, perr := einoopenai.NewChatModel(ctx, baseModelCfg)
 		if perr != nil {
 			return nil, fmt.Errorf("plan_execute 执行器模型: %w", perr)
@@ -445,7 +461,7 @@ func RunDeepAgent(
 			}
 		}
 		peRoot, perr := NewPlanExecuteRoot(ctx, &PlanExecuteRootArgs{
-			MainToolCallingModel: mainModel,
+			MainToolCallingModel: peMainModel,
 			ExecModel:            execModel,
 			OrchInstruction:      orchInstruction,
 			ToolsCfg:             mainToolsCfg,
@@ -458,6 +474,7 @@ func RunDeepAgent(
 			ProjectID:            projectID,
 			Logger:               logger,
 			ModelName:            appCfg.OpenAI.Model,
+			// 与 Deep/Supervisor 主代理同源：patch / reduction / toolsearch / plantask（见 buildPlanExecuteExecutorHandlers）。
 			ExecPreMiddlewares:   mainOrchestratorPre,
 			SkillMiddleware:      einoSkillMW,
 			FilesystemMiddleware: peFsMw,

internal/openai/claude_bridge.go

@@ -806,10 +806,12 @@ func isClaudeProvider(cfg *config.OpenAIConfig) bool {
 // Eino HTTP Client Bridge
 // ============================================================
 
-// NewEinoHTTPClient 为 einoopenai.ChatModelConfig 返回一个 http.Client，包含两层 transport 包装：
+// NewEinoHTTPClient 为 einoopenai.ChatModelConfig 返回一个 http.Client，包含多层 transport 包装：
-//  1. 当 cfg.Provider 为 claude 时，最内层套 claudeRoundTripper，把 OpenAI /chat/completions 透明
+//  1. 当 cfg.Provider 为 claude 时，套 claudeRoundTripper，把 OpenAI /chat/completions 透明
 //     桥接为 Anthropic /v1/messages（并把 Claude SSE 翻译回 OpenAI SSE 格式）。
-//  2. 最外层无条件套 einoSSESanitizingRoundTripper，吞掉中转站发的 SSE 心跳/注释/控制行
+//  2. reasoningToolChoiceCompatRoundTripper：tool_choice=required/object 时剥离 thinking 字段，避免
+//     plan_execute replanner 等强制工具调用与推理模式冲突（部分网关返回 400）。
+//  3. 最外层无条件套 einoSSESanitizingRoundTripper，吞掉中转站发的 SSE 心跳/注释/控制行
 //     (": keepalive" / "event: ping" / "retry: 3000" 等)，避免 Eino 用的 meguminnnnnnnnn/go-openai
 //     SDK 在累计超过 300 个非 "data:" 行后抛 "stream has sent too many empty messages"。
 //
@@ -825,6 +827,7 @@ func NewEinoHTTPClient(cfg *config.OpenAIConfig, base *http.Client) *http.Client
 	if transport == nil {
 		transport = http.DefaultTransport
 	}
+	transport = &reasoningToolChoiceCompatRoundTripper{base: transport}
 	if isClaudeProvider(cfg) {
 		transport = &claudeRoundTripper{
 			base:   transport,

internal/openai/reasoning_payload.go

@@ -0,0 +1,79 @@
+package openai
+
+import (
+	"github.com/bytedance/sonic"
+)
+
+// reasoningPayloadKeys are OpenAI-compatible root fields that enable "thinking" /
+// extended-reasoning modes on gateways such as DashScope/Qwen and MiniMax.
+var reasoningPayloadKeys = []string{
+	"thinking",
+	"reasoning_effort",
+	"output_config",
+	"reasoning",
+}
+
+// StripReasoningFromChatCompletionBody removes thinking / reasoning fields from a
+// chat-completions JSON body.
+func StripReasoningFromChatCompletionBody(rawBody []byte) ([]byte, error) {
+	var payload map[string]any
+	if err := sonic.Unmarshal(rawBody, &payload); err != nil {
+		return rawBody, nil
+	}
+	if !stripReasoningFields(payload) {
+		return rawBody, nil
+	}
+	out, err := sonic.Marshal(payload)
+	if err != nil {
+		return rawBody, err
+	}
+	return out, nil
+}
+
+// StripReasoningIfForcedToolChoice removes thinking / reasoning fields when the
+// request sets tool_choice to "required" or an object. Several providers reject
+// that combination (e.g. DashScope: "tool_choice does not support being set to
+// required or object in thinking mode").
+func StripReasoningIfForcedToolChoice(rawBody []byte) ([]byte, error) {
+	var payload map[string]any
+	if err := sonic.Unmarshal(rawBody, &payload); err != nil {
+		return rawBody, nil
+	}
+	if !forcedToolChoiceIncompatibleWithThinking(payload) {
+		return rawBody, nil
+	}
+	if !stripReasoningFields(payload) {
+		return rawBody, nil
+	}
+	out, err := sonic.Marshal(payload)
+	if err != nil {
+		return rawBody, err
+	}
+	return out, nil
+}
+
+func stripReasoningFields(payload map[string]any) bool {
+	changed := false
+	for _, key := range reasoningPayloadKeys {
+		if _, ok := payload[key]; ok {
+			delete(payload, key)
+			changed = true
+		}
+	}
+	return changed
+}
+
+func forcedToolChoiceIncompatibleWithThinking(payload map[string]any) bool {
+	tc, ok := payload["tool_choice"]
+	if !ok || tc == nil {
+		return false
+	}
+	switch v := tc.(type) {
+	case string:
+		return v == "required"
+	case map[string]any:
+		return true
+	default:
+		return false
+	}
+}

internal/openai/reasoning_payload_test.go

@@ -0,0 +1,120 @@
+package openai
+
+import (
+	"io"
+	"net/http"
+	"strings"
+	"testing"
+)
+
+func TestStripReasoningFromChatCompletionBody(t *testing.T) {
+	in := []byte(`{"model":"deepseek-chat","messages":[],"thinking":{"type":"enabled"},"reasoning_effort":"high"}`)
+	out, err := StripReasoningFromChatCompletionBody(in)
+	if err != nil {
+		t.Fatal(err)
+	}
+	s := string(out)
+	if strings.Contains(s, "thinking") || strings.Contains(s, "reasoning_effort") {
+		t.Fatalf("expected reasoning fields stripped, got %s", s)
+	}
+	if !strings.Contains(s, `"model":"deepseek-chat"`) {
+		t.Fatalf("expected model preserved, got %s", s)
+	}
+
+	plain := []byte(`{"model":"gpt-4o","messages":[]}`)
+	out2, err := StripReasoningFromChatCompletionBody(plain)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if string(out2) != string(plain) {
+		t.Fatalf("expected unchanged payload, got %s", out2)
+	}
+}
+
+func TestStripReasoningIfForcedToolChoice(t *testing.T) {
+	cases := []struct {
+		name    string
+		in      string
+		strip   bool
+		contain string
+	}{
+		{
+			name:  "required strips thinking",
+			in:    `{"model":"minimax","messages":[],"thinking":{"type":"enabled"},"tool_choice":"required","tools":[]}`,
+			strip: true,
+		},
+		{
+			name:  "object tool_choice strips thinking",
+			in:    `{"model":"qwen","messages":[],"thinking":{"type":"enabled"},"tool_choice":{"type":"function","function":{"name":"respond"}}}`,
+			strip: true,
+		},
+		{
+			name:    "auto keeps thinking",
+			in:      `{"model":"qwen","messages":[],"thinking":{"type":"enabled"},"tool_choice":"auto"}`,
+			strip:   false,
+			contain: "thinking",
+		},
+		{
+			name:    "no tool_choice keeps thinking",
+			in:      `{"model":"qwen","messages":[],"thinking":{"type":"enabled"}}`,
+			strip:   false,
+			contain: "thinking",
+		},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			out, err := StripReasoningIfForcedToolChoice([]byte(tc.in))
+			if err != nil {
+				t.Fatal(err)
+			}
+			s := string(out)
+			hasThinking := strings.Contains(s, "thinking")
+			if tc.strip && hasThinking {
+				t.Fatalf("expected thinking stripped, got %s", s)
+			}
+			if !tc.strip && tc.contain != "" && !strings.Contains(s, tc.contain) {
+				t.Fatalf("expected %q in %s", tc.contain, s)
+			}
+			if !tc.strip && string(out) != tc.in {
+				t.Fatalf("expected unchanged payload, got %s", s)
+			}
+		})
+	}
+}
+
+func TestReasoningToolChoiceCompatRoundTripper(t *testing.T) {
+	var gotBody string
+	rt := &reasoningToolChoiceCompatRoundTripper{
+		base: roundTripperFunc(func(req *http.Request) (*http.Response, error) {
+			b, _ := io.ReadAll(req.Body)
+			gotBody = string(b)
+			return &http.Response{
+				StatusCode: 200,
+				Body:       io.NopCloser(strings.NewReader(`{"choices":[{"message":{"content":"ok"}}]}`)),
+				Header:     http.Header{"Content-Type": []string{"application/json"}},
+			}, nil
+		}),
+	}
+	req, err := http.NewRequest(http.MethodPost, "https://example.com/v1/chat/completions", strings.NewReader(
+		`{"model":"m","thinking":{"type":"enabled"},"tool_choice":"required","messages":[]}`,
+	))
+	if err != nil {
+		t.Fatal(err)
+	}
+	_, err = rt.RoundTrip(req)
+	if err != nil {
+		t.Fatal(err)
+	}
+	if strings.Contains(gotBody, "thinking") {
+		t.Fatalf("expected thinking stripped in transit, got %s", gotBody)
+	}
+	if !strings.Contains(gotBody, `"tool_choice":"required"`) {
+		t.Fatalf("expected tool_choice preserved, got %s", gotBody)
+	}
+}
+
+type roundTripperFunc func(*http.Request) (*http.Response, error)
+
+func (f roundTripperFunc) RoundTrip(req *http.Request) (*http.Response, error) {
+	return f(req)
+}

internal/openai/reasoning_tool_choice_compat.go

@@ -0,0 +1,43 @@
+package openai
+
+import (
+	"bytes"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+)
+
+// reasoningToolChoiceCompatRoundTripper strips thinking/reasoning fields from
+// chat/completions requests that force tool_choice, which some gateways reject
+// when thinking mode is enabled on the same request.
+type reasoningToolChoiceCompatRoundTripper struct {
+	base http.RoundTripper
+}
+
+func (rt *reasoningToolChoiceCompatRoundTripper) RoundTrip(req *http.Request) (*http.Response, error) {
+	if rt == nil || rt.base == nil || req == nil || req.Body == nil {
+		if rt != nil && rt.base != nil {
+			return rt.base.RoundTrip(req)
+		}
+		return http.DefaultTransport.RoundTrip(req)
+	}
+	if req.Method != http.MethodPost || !strings.HasSuffix(req.URL.Path, "/chat/completions") {
+		return rt.base.RoundTrip(req)
+	}
+
+	body, err := io.ReadAll(req.Body)
+	_ = req.Body.Close()
+	if err != nil {
+		return nil, err
+	}
+
+	patched, perr := StripReasoningIfForcedToolChoice(body)
+	if perr != nil {
+		patched = body
+	}
+	req.Body = io.NopCloser(bytes.NewReader(patched))
+	req.ContentLength = int64(len(patched))
+	req.Header.Set("Content-Length", strconv.Itoa(len(patched)))
+	return rt.base.RoundTrip(req)
+}

internal/project/user_verbatim_anchor.go

@@ -1,170 +0,0 @@
-package project
-
-import (
-	"fmt"
-	"strings"
-
-	"cyberstrike-ai/internal/database"
-
-	"github.com/cloudwego/eino/adk"
-	"github.com/cloudwego/eino/schema"
-)
-
-const (
-	// UserVerbatimSectionHeading 用户原文锚点可读标题（块内保留，供 Agent 阅读）。
-	UserVerbatimSectionHeading = "## 用户历史输入（原文保留，勿省略或改写）"
-
-	// UserVerbatimSectionStartMarker / EndMarker：HTML 注释边界，供程序化替换；对模型无指令语义。
-	UserVerbatimSectionStartMarker = "<!-- user-verbatim-start -->"
-	UserVerbatimSectionEndMarker   = "<!-- user-verbatim-end -->"
-)
-
-// ExtractUserContentsFromMessages 按时间顺序提取 user 角色消息的原文（跳过空白）。
-func ExtractUserContentsFromMessages(msgs []database.Message) []string {
-	out := make([]string, 0, len(msgs))
-	for i := range msgs {
-		if !strings.EqualFold(strings.TrimSpace(msgs[i].Role), "user") {
-			continue
-		}
-		content := strings.TrimSpace(msgs[i].Content)
-		if content == "" {
-			continue
-		}
-		out = append(out, content)
-	}
-	return out
-}
-
-// BuildUserVerbatimAnchorBlockFromMessages 从 messages 表行构建用户原文锚点块。
-// maxRunes: 0 = 不截断；>0 = 总 rune 上限（仍保留每一轮，仅对超长单条做尾部截断提示）。
-func BuildUserVerbatimAnchorBlockFromMessages(msgs []database.Message, maxRunes int) string {
-	return BuildUserVerbatimAnchorBlock(ExtractUserContentsFromMessages(msgs), maxRunes)
-}
-
-// BuildUserVerbatimAnchorBlock 将各轮用户原文格式化为 system prompt 锚点块。
-func BuildUserVerbatimAnchorBlock(userContents []string, maxRunes int) string {
-	if len(userContents) == 0 {
-		return ""
-	}
-	lines := make([]string, 0, len(userContents))
-	for _, content := range userContents {
-		content = strings.TrimSpace(content)
-		if content == "" {
-			continue
-		}
-		lines = append(lines, fmt.Sprintf("[第%d轮] %s", len(lines)+1, content))
-	}
-	if len(lines) == 0 {
-		return ""
-	}
-	body := strings.Join(lines, "\n")
-	if maxRunes > 0 {
-		body = capUserVerbatimBody(body, maxRunes)
-	}
-	return wrapUserVerbatimBlock(UserVerbatimSectionHeading + "\n\n" + body)
-}
-
-func capUserVerbatimBody(body string, maxRunes int) string {
-	rs := []rune(body)
-	if len(rs) <= maxRunes {
-		return body
-	}
-	suffix := "\n\n...(用户原文锚点已达配置上限，更早轮次可能被截断；完整原文见 messages 表)..."
-	suffixRunes := []rune(suffix)
-	keep := maxRunes - len(suffixRunes)
-	if keep <= 0 {
-		return string(rs[:maxRunes])
-	}
-	return string(rs[:keep]) + suffix
-}
-
-func wrapUserVerbatimBlock(content string) string {
-	content = strings.TrimSpace(content)
-	if content == "" {
-		return ""
-	}
-	return UserVerbatimSectionStartMarker + "\n" + content + "\n" + UserVerbatimSectionEndMarker + "\n"
-}
-
-// ReplaceUserVerbatimAnchorSection 用 freshBlock 替换 content 中已有的用户原文锚点段。
-func ReplaceUserVerbatimAnchorSection(content, freshBlock string) (string, bool) {
-	content = strings.TrimSpace(content)
-	freshBlock = strings.TrimSpace(freshBlock)
-	if freshBlock == "" {
-		return content, false
-	}
-	start, ok := userVerbatimSectionStart(content)
-	if !ok {
-		return content, false
-	}
-	end, ok := userVerbatimSectionEnd(content, start)
-	if !ok {
-		return content, false
-	}
-	return strings.TrimSpace(content[:start] + freshBlock + content[end:]), true
-}
-
-func userVerbatimSectionStart(content string) (int, bool) {
-	idx := strings.Index(content, UserVerbatimSectionStartMarker)
-	if idx < 0 {
-		return 0, false
-	}
-	return idx, true
-}
-
-func userVerbatimSectionEnd(content string, start int) (int, bool) {
-	if start < 0 || start >= len(content) {
-		return 0, false
-	}
-	tail := content[start:]
-	idx := strings.LastIndex(tail, UserVerbatimSectionEndMarker)
-	if idx < 0 {
-		return 0, false
-	}
-	return start + idx + len(UserVerbatimSectionEndMarker), true
-}
-
-// RefreshUserVerbatimAnchorInMessages 在 summarization 等压缩后，用 freshBlock 刷新 system 中的用户原文锚点。
-// 若尚无锚点段，则追加到首条 system 消息；若无 system 消息则在开头插入一条。
-func RefreshUserVerbatimAnchorInMessages(msgs []adk.Message, freshBlock string) []adk.Message {
-	freshBlock = strings.TrimSpace(freshBlock)
-	if freshBlock == "" || len(msgs) == 0 {
-		return msgs
-	}
-
-	out := make([]adk.Message, len(msgs))
-	changed := false
-	for i, msg := range msgs {
-		if msg == nil || msg.Role != schema.System {
-			out[i] = msg
-			continue
-		}
-		newContent, ok := ReplaceUserVerbatimAnchorSection(msg.Content, freshBlock)
-		if !ok {
-			out[i] = msg
-			continue
-		}
-		cloned := *msg
-		cloned.Content = newContent
-		out[i] = &cloned
-		changed = true
-	}
-
-	if changed {
-		return out
-	}
-
-	for i, msg := range msgs {
-		if msg == nil || msg.Role != schema.System {
-			continue
-		}
-		cloned := *msg
-		cloned.Content = AppendSystemPromptBlock(cloned.Content, freshBlock)
-		out[i] = &cloned
-		return out
-	}
-
-	prefix := make([]adk.Message, 0, len(msgs)+1)
-	prefix = append(prefix, schema.SystemMessage(freshBlock))
-	return append(prefix, msgs...)
-}

internal/project/user_verbatim_anchor_test.go

@@ -1,96 +0,0 @@
-package project
-
-import (
-	"strings"
-	"testing"
-
-	"cyberstrike-ai/internal/database"
-
-	"github.com/cloudwego/eino/adk"
-	"github.com/cloudwego/eino/schema"
-)
-
-func TestBuildUserVerbatimAnchorBlock_MultiTurn(t *testing.T) {
-	msgs := []database.Message{
-		{Role: "user", Content: "目标 https://a.com 仅测 /api"},
-		{Role: "assistant", Content: "好的"},
-		{Role: "user", Content: "用 admin:test 登录"},
-	}
-	block := BuildUserVerbatimAnchorBlockFromMessages(msgs, 0)
-	if block == "" {
-		t.Fatal("expected non-empty block")
-	}
-	if !strings.Contains(block, UserVerbatimSectionStartMarker) {
-		t.Error("missing start marker")
-	}
-	if !strings.Contains(block, "[第1轮]") || !strings.Contains(block, "https://a.com") {
-		t.Error("missing first user turn")
-	}
-	if !strings.Contains(block, "[第2轮]") || !strings.Contains(block, "admin:test") {
-		t.Error("missing second user turn")
-	}
-	if strings.Contains(block, "好的") {
-		t.Error("assistant content should not appear")
-	}
-}
-
-func TestReplaceUserVerbatimAnchorSection(t *testing.T) {
-	old := "prefix\n\n" + wrapUserVerbatimBlock("## old\n\n[第1轮] a") + "\nsuffix"
-	newBlock := wrapUserVerbatimBlock(UserVerbatimSectionHeading + "\n\n[第1轮] b\n[第2轮] c")
-	out, ok := ReplaceUserVerbatimAnchorSection(old, newBlock)
-	if !ok {
-		t.Fatal("expected replace ok")
-	}
-	if !strings.Contains(out, "[第2轮] c") {
-		t.Errorf("expected new block, got %q", out)
-	}
-	if !strings.HasPrefix(strings.TrimSpace(out), "prefix") {
-		t.Error("prefix should remain")
-	}
-	if !strings.Contains(out, "suffix") {
-		t.Error("suffix should remain")
-	}
-}
-
-func TestRefreshUserVerbatimAnchorInMessages_ReplaceExisting(t *testing.T) {
-	oldBlock := wrapUserVerbatimBlock(UserVerbatimSectionHeading + "\n\n[第1轮] old")
-	msgs := []adk.Message{
-		schema.SystemMessage("instr\n\n" + oldBlock),
-		schema.UserMessage("hi"),
-	}
-	newBlock := wrapUserVerbatimBlock(UserVerbatimSectionHeading + "\n\n[第1轮] new")
-	out := RefreshUserVerbatimAnchorInMessages(msgs, newBlock)
-	if len(out) != 2 {
-		t.Fatalf("message count: got %d", len(out))
-	}
-	if !strings.Contains(out[0].Content, "[第1轮] new") {
-		t.Errorf("system content: %q", out[0].Content)
-	}
-	if strings.Contains(out[0].Content, "[第1轮] old") {
-		t.Error("old anchor should be replaced")
-	}
-}
-
-func TestRefreshUserVerbatimAnchorInMessages_InsertWhenMissing(t *testing.T) {
-	msgs := []adk.Message{
-		schema.SystemMessage("base instruction"),
-		schema.UserMessage("hi"),
-	}
-	block := wrapUserVerbatimBlock(UserVerbatimSectionHeading + "\n\n[第1轮] anchor")
-	out := RefreshUserVerbatimAnchorInMessages(msgs, block)
-	if !strings.Contains(out[0].Content, "[第1轮] anchor") {
-		t.Errorf("expected appended anchor, got %q", out[0].Content)
-	}
-}
-
-func TestBuildUserVerbatimAnchorBlock_MaxRunes(t *testing.T) {
-	long := strings.Repeat("字", 200)
-	block := BuildUserVerbatimAnchorBlock([]string{long}, 50)
-	body := block
-	if idx := strings.Index(body, UserVerbatimSectionStartMarker); idx >= 0 {
-		body = strings.TrimPrefix(body[idx+len(UserVerbatimSectionStartMarker):], "\n")
-	}
-	if len([]rune(body)) > 120 {
-		t.Errorf("expected capped body, got %d runes", len([]rune(body)))
-	}
-}

internal/reasoning/eino.go

@@ -26,6 +26,35 @@ const (
 	wireOutputConfig
 )
 
+// ApplyPlanExecutePlannerModelConfig configures the plan_execute planner/replanner
+// ChatModel. Those Eino agents call WithToolChoice(Forced); several gateways reject
+// thinking / reasoning fields on the same request (tool_choice required/object).
+// Executor should keep the normal ApplyToEinoChatModelConfig path.
+func ApplyPlanExecutePlannerModelConfig(cfg *einoopenai.ChatModelConfig, oa *config.OpenAIConfig) {
+	if cfg == nil || oa == nil {
+		return
+	}
+	offOA := *oa
+	offReasoning := oa.Reasoning
+	offReasoning.Mode = "off"
+	offOA.Reasoning = offReasoning
+	ApplyToEinoChatModelConfig(cfg, &offOA, nil)
+	clearReasoningFromChatModelConfig(cfg)
+}
+
+func clearReasoningFromChatModelConfig(cfg *einoopenai.ChatModelConfig) {
+	if cfg == nil {
+		return
+	}
+	cfg.ReasoningEffort = ""
+	if cfg.ExtraFields != nil {
+		for _, key := range []string{"thinking", "reasoning_effort", "output_config", "reasoning"} {
+			delete(cfg.ExtraFields, key)
+		}
+	}
+	applyThinkingDisabled(cfg)
+}
+
 // ApplyToEinoChatModelConfig merges reasoning-related options into cfg.
 // Precondition: cfg already has APIKey, BaseURL, Model, HTTPClient set.
 func ApplyToEinoChatModelConfig(cfg *einoopenai.ChatModelConfig, oa *config.OpenAIConfig, client *ClientIntent) {

internal/reasoning/eino_test.go

@@ -49,6 +49,30 @@ func TestApplyOpenAICompat_xhighExtraField(t *testing.T) {
 	}
 }
 
+func TestApplyPlanExecutePlannerModelConfig_stripsReasoningWhenGlobalOn(t *testing.T) {
+	cfg := &einoopenai.ChatModelConfig{}
+	oa := &config.OpenAIConfig{
+		BaseURL: "https://antchat.example.com/v1",
+		Model:   "minimax-m3",
+		Reasoning: config.OpenAIReasoningConfig{
+			Profile: "openai_compat",
+			Mode:    "on",
+			Effort:  "high",
+		},
+	}
+	ApplyPlanExecutePlannerModelConfig(cfg, oa)
+	if cfg.ReasoningEffort != "" {
+		t.Fatalf("expected ReasoningEffort cleared, got %q", cfg.ReasoningEffort)
+	}
+	th, ok := cfg.ExtraFields["thinking"].(map[string]any)
+	if !ok || th["type"] != "disabled" {
+		t.Fatalf("expected thinking disabled, got %#v", cfg.ExtraFields)
+	}
+	if _, ok := cfg.ExtraFields["reasoning_effort"]; ok {
+		t.Fatalf("expected reasoning_effort stripped, got %#v", cfg.ExtraFields)
+	}
+}
+
 func TestApplyReasoningOff_disablesThinking(t *testing.T) {
 	cfg := &einoopenai.ChatModelConfig{}
 	oa := &config.OpenAIConfig{

tools/virustotal_search.yaml

@@ -0,0 +1,318 @@
+name: "virustotal_search"
+command: "python3"
+args:
+  - "-c"
+  - |
+    import sys
+    import json
+    import requests
+    import os
+    import time
+
+    # ==================== VirusTotal 配置 ====================
+    # 请在此处配置您的 VirusTotal API 密钥
+    # 您也可以在环境变量中设置：VT_API_KEY
+    # enable 默认为 false，需开启才能调用该MCP
+    VT_API_KEY = ""  # 请填写您的 VirusTotal API 密钥
+    # =======================================================
+
+    # VirusTotal API 基础 URL
+    BASE_URL = "https://www.virustotal.com/api/v3"
+
+    def parse_args():
+        """解析命令行参数"""
+        # 尝试从第一个参数读取 JSON 配置
+        if len(sys.argv) > 1:
+            try:
+                arg1 = str(sys.argv[1])
+                config = json.loads(arg1)
+                if isinstance(config, dict):
+                    return config
+            except (json.JSONDecodeError, TypeError, ValueError):
+                pass
+
+        # 传统位置参数方式
+        config = {}
+        if len(sys.argv) > 1:
+            config['domain'] = str(sys.argv[1])
+        if len(sys.argv) > 2:
+            try:
+                config['limit'] = int(sys.argv[2])
+            except (ValueError, TypeError):
+                pass
+        if len(sys.argv) > 3:
+            config['include_ips'] = sys.argv[3].lower() in ('true', '1', 'yes')
+        return config
+
+    def query_virustotal_subdomains(domain, api_key, limit=100, include_ips=False):
+        """
+        查询 VirusTotal 的子域名信息
+        
+        Args:
+            domain: 要查询的域名
+            api_key: VirusTotal API 密钥
+            limit: 返回结果数量限制
+            include_ips: 是否包含 IP 地址信息
+        
+        Returns:
+            dict: 包含查询结果的字典
+        """
+        # 构建 API 请求 URL
+        url = f"{BASE_URL}/domains/{domain}/subdomains"
+        
+        headers = {
+            "x-apikey": api_key,
+            "accept": "application/json"
+        }
+        
+        params = {
+            "limit": min(limit, 40)  # API 限制最大 40
+        }
+        
+        all_results = []
+        next_url = None
+        
+        try:
+            # 处理分页
+            while True:
+                if next_url:
+                    response = requests.get(next_url, headers=headers, timeout=30)
+                else:
+                    response = requests.get(url, headers=headers, params=params, timeout=30)
+                
+                response.raise_for_status()
+                data = response.json()
+                
+                # 提取子域名数据
+                if 'data' in data and data['data']:
+                    for item in data['data']:
+                        if 'id' in item:
+                            subdomain_info = {
+                                'subdomain': item['id'],
+                                'type': item.get('type', 'domain'),
+                            }
+                            
+                            # 如果 include_ips 为 True，尝试获取解析 IP
+                            if include_ips and 'attributes' in item:
+                                attributes = item.get('attributes', {})
+                                # 这里简化处理，实际可能需要额外的 API 调用
+                                subdomain_info['last_dns_records'] = attributes.get('last_dns_records', [])
+                            
+                            all_results.append(subdomain_info)
+                    
+                    # 检查是否有下一页
+                    if 'links' in data and 'next' in data['links'] and len(all_results) < limit:
+                        next_url = data['links']['next']
+                        # 避免请求过快
+                        time.sleep(0.5)
+                    else:
+                        break
+                else:
+                    break
+                
+                # 如果已达到限制，停止获取
+                if len(all_results) >= limit:
+                    break
+            
+            # 处理返回结果
+            if all_results:
+                return {
+                    "status": "success",
+                    "domain": domain,
+                    "total_found": len(all_results),
+                    "results": all_results[:limit],
+                    "message": f"成功获取 {len(all_results[:limit])} 个子域名"
+                }
+            else:
+                return {
+                    "status": "success",
+                    "domain": domain,
+                    "total_found": 0,
+                    "results": [],
+                    "message": f"未找到 {domain} 的子域名"
+                }
+                
+        except requests.exceptions.RequestException as e:
+            error_msg = str(e)
+            error_result = {
+                "status": "error",
+                "message": f"API 请求失败: {error_msg}",
+                "suggestion": "请检查网络连接、API 密钥是否正确，或 VirusTotal API 服务是否可用"
+            }
+            
+            # 处理特定 HTTP 状态码
+            if hasattr(e, 'response') and e.response:
+                status_code = e.response.status_code
+                if status_code == 401:
+                    error_result["message"] = "API 密钥无效或未授权"
+                    error_result["suggestion"] = "请检查 VirusTotal API 密钥是否正确，或在 https://www.virustotal.com/ 获取有效密钥"
+                elif status_code == 429:
+                    error_result["message"] = "API 请求频率超限"
+                    error_result["suggestion"] = "请稍后再试，VirusTotal API 有严格的速率限制（免费版每分钟4次）"
+                elif status_code == 404:
+                    error_result["message"] = f"域名 '{domain}' 不存在或未找到"
+            
+            return error_result
+
+    try:
+        config = parse_args()
+        
+        if not isinstance(config, dict):
+            error_result = {
+                "status": "error",
+                "message": f"参数解析错误: 期望字典类型，但得到 {type(config).__name__}",
+                "type": "TypeError"
+            }
+            print(json.dumps(error_result, ensure_ascii=False, indent=2))
+            sys.exit(1)
+        
+        # 获取 API 密钥（从配置或环境变量）
+        api_key = os.getenv('VT_API_KEY', VT_API_KEY).strip()
+        
+        if not api_key:
+            error_result = {
+                "status": "error",
+                "message": "缺少 VirusTotal API 密钥",
+                "required_config": ["VT_API_KEY"],
+                "note": "请在 YAML 文件的 VT_API_KEY 配置项中填写您的 VirusTotal API 密钥，或在环境变量 VT_API_KEY 中设置。API 密钥可在 https://www.virustotal.com/ 注册获取"
+            }
+            print(json.dumps(error_result, ensure_ascii=False, indent=2))
+            sys.exit(1)
+        
+        # 获取必需参数
+        domain = config.get('domain', '').strip()
+        if not domain:
+            error_result = {
+                "status": "error",
+                "message": "缺少必需参数: domain（要查询的域名）",
+                "required_params": ["domain"],
+                "examples": [
+                    "example.com",
+                    "google.com",
+                    "baidu.com"
+                ]
+            }
+            print(json.dumps(error_result, ensure_ascii=False, indent=2))
+            sys.exit(1)
+        
+        # 获取可选参数
+        limit = config.get('limit', 100)
+        try:
+            limit = int(limit)
+            if limit < 1:
+                limit = 100
+            elif limit > 1000:
+                limit = 1000  # 限制最大 1000
+        except (ValueError, TypeError):
+            limit = 100
+        
+        include_ips = config.get('include_ips', False)
+        if isinstance(include_ips, str):
+            include_ips = include_ips.lower() in ('true', '1', 'yes')
+        
+        # 执行查询
+        result = query_virustotal_subdomains(domain, api_key, limit, include_ips)
+        
+        # 输出结果
+        print(json.dumps(result, ensure_ascii=False, indent=2))
+        
+    except Exception as e:
+        error_result = {
+            "status": "error",
+            "message": f"执行出错: {str(e)}",
+            "type": type(e).__name__
+        }
+        print(json.dumps(error_result, ensure_ascii=False, indent=2))
+        sys.exit(1)
+
+enabled: false
+
+short_description: "VirusTotal 子域名查询工具，通过 VirusTotal API 被动收集域名子域名"
+
+description: |
+  VirusTotal 子域名查询工具，利用 VirusTotal 聚合的历史 DNS 数据来发现目标域名的子域名。
+  
+  **主要功能：**
+  - 被动子域名收集：从 VirusTotal 历史 DNS 数据中检索子域名
+  - 分页查询：支持大量子域名的获取
+  - IP 关联：可选包含 DNS 解析记录
+  - 去重处理：自动去重返回结果
+  
+  **使用场景：**
+  - 安全测试前期信息收集
+  - 企业网络资产发现
+  - 攻击面分析
+  - 威胁情报收集
+  - 渗透测试信息收集
+  
+  **数据来源：**
+  VirusTotal 聚合了来自多个来源的 DNS 数据，包括：
+  - 历史 DNS 解析记录
+  - 被动 DNS 数据库
+  - 证书透明度日志
+  - 安全扫描数据
+  
+  **注意事项：**
+  - **API 密钥必需**：需要在 VirusTotal 注册账号并获取 API 密钥
+  - **速率限制**：免费版 API 每分钟限制 4 次请求
+  - **数据时效性**：数据基于历史扫描记录，可能不是实时的
+  - **使用授权**：仅允许对您拥有合法授权的目标进行查询
+  - **配额限制**：免费版每月有查询配额限制
+
+parameters:
+  - name: "domain"
+    type: "string"
+    description: |
+      要查询的目标域名（必需）。
+      
+      **格式要求：**
+      - 仅输入主域名，不要包含协议头（http://）或路径
+      - 支持二级域名查询
+      
+      **示例值：**
+      - "example.com"
+      - "google.com"
+      - "baidu.com"
+      - "github.com"
+      
+      **注意事项：**
+      - 域名格式必须正确
+      - 查询结果可能包含跨域子域名
+    required: true
+    position: 2
+    format: "positional"
+  
+  - name: "limit"
+    type: "int"
+    description: |
+      返回结果数量限制（可选）。
+      
+      **说明：**
+      - 默认值：40
+      - 最大值：1000（API 限制）
+      - 建议值：100-500
+      
+      **注意事项：**
+      - 设置过大的值可能导致请求超时
+      - API 单次返回限制为 40 条，超过会自动分页
+    required: false
+    position: 3
+    format: "positional"
+    default: 40
+  
+  - name: "include_ips"
+    type: "bool"
+    description: |
+      是否包含 IP 地址信息（可选）。
+      
+      **说明：**
+      - true：在结果中包含 DNS 解析记录
+      - false：仅返回子域名列表
+      
+      **注意事项：**
+      - 包含 IP 信息会增加 API 调用次数
+      - 可能包含历史解析 IP，不一定准确
+    required: false
+    position: 4
+    format: "positional"
+    default: false

web/static/css/c2.css

@@ -33,6 +33,93 @@
     --c2-mono: 'SF Mono', 'Fira Code', 'JetBrains Mono', 'Cascadia Code', monospace;
 }
 
+html[data-theme="dark"] {
+    --c2-accent: #60a5fa;
+    --c2-accent-hover: #93c5fd;
+    --c2-accent-dim: rgba(96, 165, 250, 0.14);
+    --c2-accent-glow: rgba(96, 165, 250, 0.28);
+    --c2-green: #34d399;
+    --c2-green-dim: rgba(52, 211, 153, 0.14);
+    --c2-red: #f87171;
+    --c2-red-dim: rgba(248, 113, 113, 0.14);
+    --c2-amber: #fbbf24;
+    --c2-amber-dim: rgba(251, 191, 36, 0.14);
+    --c2-purple: #a78bfa;
+    --c2-purple-dim: rgba(167, 139, 250, 0.14);
+    --c2-surface: #111827;
+    --c2-surface-alt: #0b1120;
+    --c2-border: #263244;
+    --c2-border-hover: #3b4a63;
+    --c2-text: #e5e7eb;
+    --c2-text-dim: #a7b0c0;
+    --c2-text-muted: #6b7280;
+    --c2-shadow-sm: 0 1px 3px rgba(0,0,0,0.34);
+    --c2-shadow-md: 0 8px 24px rgba(0,0,0,0.38);
+    --c2-shadow-lg: 0 18px 48px rgba(0,0,0,0.45);
+}
+
+html[data-theme="dark"] .c2-modal,
+html[data-theme="dark"] .c2-modal-content,
+html[data-theme="dark"] .c2-tab-panel--card,
+html[data-theme="dark"] .c2-session-detail,
+html[data-theme="dark"] .c2-payload-card,
+html[data-theme="dark"] .c2-profile-card,
+html[data-theme="dark"] .c2-event-card,
+html[data-theme="dark"] .c2-task-row,
+html[data-theme="dark"] .c2-listener-card {
+    background: var(--c2-surface);
+    color: var(--c2-text);
+    border-color: var(--c2-border);
+}
+
+html[data-theme="dark"] .c2-listener-card:hover,
+html[data-theme="dark"] .c2-payload-card:hover,
+html[data-theme="dark"] .c2-profile-card:hover {
+    border-color: var(--c2-border-hover);
+}
+
+html[data-theme="dark"] .c2-session-chip,
+html[data-theme="dark"] .c2-listener-pill,
+html[data-theme="dark"] .c2-task-type-badge,
+html[data-theme="dark"] .c2-tab-btn {
+    background: var(--c2-surface-alt);
+    border-color: var(--c2-border);
+}
+
+html[data-theme="dark"] #page-c2-listeners,
+html[data-theme="dark"] #page-c2-sessions,
+html[data-theme="dark"] #page-c2-tasks,
+html[data-theme="dark"] #page-c2-payloads,
+html[data-theme="dark"] #page-c2-events,
+html[data-theme="dark"] #page-c2-profiles,
+html[data-theme="dark"] #page-c2-listeners .page-content,
+html[data-theme="dark"] #page-c2-sessions .page-content,
+html[data-theme="dark"] #page-c2-tasks .page-content,
+html[data-theme="dark"] #page-c2-payloads .page-content,
+html[data-theme="dark"] #page-c2-events .page-content,
+html[data-theme="dark"] #page-c2-profiles .page-content,
+html[data-theme="dark"] .c2-session-layout,
+html[data-theme="dark"] .c2-session-main {
+    background: var(--c2-surface-alt) !important;
+}
+
+html[data-theme="dark"] .c2-session-sidebar-wrap,
+html[data-theme="dark"] .c2-sessions-toolbar,
+html[data-theme="dark"] .c2-session-sidebar {
+    background: #0b1120 !important;
+    border-color: var(--c2-border) !important;
+}
+
+html[data-theme="dark"] .c2-session-main-empty {
+    background: transparent !important;
+    color: var(--c2-text-dim) !important;
+}
+
+html[data-theme="dark"] .c2-session-main-empty__icon {
+    background: var(--c2-accent-dim) !important;
+    border-color: rgba(96, 165, 250, 0.35) !important;
+}
+
 /* ============================================================================
    Form Controls (scoped to C2 pages)
    ============================================================================ */
@@ -533,7 +620,7 @@
     min-height: 0;
     overflow: hidden;
     padding: 12px 16px 16px;
-    background: linear-gradient(180deg, #f8fafc 0%, #ffffff 180px);
+    background: linear-gradient(180deg, var(--c2-surface-alt) 0%, var(--c2-surface) 180px);
     display: flex;
     flex-direction: column;
 }

web/static/i18n/en-US.json

@@ -39,6 +39,15 @@
     "version": "Current version",
     "toggleSidebar": "Collapse/expand sidebar"
   },
+  "theme": {
+    "system": "System",
+    "light": "Light",
+    "dark": "Dark",
+    "titleSystem": "Current: system theme. Click to switch to light.",
+    "titleLight": "Current: light theme. Click to switch to dark.",
+    "titleDark": "Current: dark theme. Click to switch to system.",
+    "toggle": "Toggle theme"
+  },
   "notifications": {
     "title": "Notifications",
     "empty": "No new events",
@@ -504,6 +513,12 @@
     "filterByProject": "Filter by project",
     "filterAllProjects": "All projects",
     "filterUnboundProjects": "Unbound",
+    "filterProjectSearch": "Search projects…",
+    "filterProjectSearchEmpty": "No matching projects",
+    "filterProjectSearchHint": "Type to search projects",
+    "filterProjectSearchMore": "Type to find more projects",
+    "filterProjectSearchLoading": "Searching…",
+    "filterProjectSearchFailed": "Failed to load projects. Try again.",
     "projectConversationsTitle": "{{name}} · Conversations",
     "unboundConversationsTitle": "Unbound conversations",
     "noProjectConversations": "No conversations in this project",
@@ -645,7 +660,10 @@
     "agentModeOrchSupervisor": "Supervisor",
     "hitlTitle": "Human-in-the-loop",
     "hitlCardSubtitle": "Approvals & allowlist",
-    "hitlReviewer": "Review",
+    "hitlReviewerLabel": "Reviewer",
+    "hitlReviewerHuman": "Human approval",
+    "hitlReviewerAgent": "Audit Agent",
+    "hitlReviewerHint": "Switch between human and Audit Agent anytime; rules and whitelist stay the same. You can pre-select even when HITL is off.",
     "hitlConfigTitle": "Collaboration mode config",
     "hitlModeLabel": "Mode",
     "hitlModeOff": "Off",
@@ -664,7 +682,89 @@
   },
   "hitl": {
     "pageTitle": "HITL approvals",
+    "pageReviewerLabel": "Current reviewer",
+    "pageReviewerHint": "Applies to the selected conversation. Without a conversation, saved locally for new chats. Takes effect immediately.",
+    "pageReviewerSaved": "Reviewer saved.",
+    "whitelistLabel": "Tool whitelist (no approval)",
+    "whitelistHint": "One per line or comma-separated. Saved to config.yaml global whitelist and takes effect immediately (synced with chat sidebar).",
+    "whitelistSaved": "Whitelist saved.",
+    "whitelistSaveFailed": "Failed to save whitelist",
+    "strategyLabel": "Audit strategy (prompt)",
+    "strategyHint": "Whitelisted tools skip approval. Other tools are judged by the model using this prompt when Audit Agent is selected.",
+    "strategyTabApproval": "Approval mode",
+    "strategyTabReviewEdit": "Review & edit mode",
+    "strategyHintApproval": "Whitelisted tools skip approval. In approval mode the Audit Agent only approves or rejects.",
+    "strategyHintReviewEdit": "In review & edit mode the Audit Agent may narrow parameters via editedArguments before approve; reject if parameters cannot be safely adjusted.",
+    "strategyReset": "Reset to default",
+    "strategySaved": "Audit strategy saved.",
+    "strategySaveFailed": "Failed to save audit strategy",
+    "tabPending": "Pending",
+    "tabLogs": "Audit logs",
+    "tabStrategy": "Audit strategy",
+    "tabWhitelist": "Tool whitelist",
     "pendingTitle": "Pending approvals",
+    "searchLabel": "Search",
+    "searchPlaceholder": "Tool, conversation, payload, comment…",
+    "searchApply": "Search",
+    "filterDecision": "Decision",
+    "filterDecidedBy": "Reviewer",
+    "filterAll": "All",
+    "decisionApprove": "Approve",
+    "decisionReject": "Reject",
+    "reviewerHuman": "Human",
+    "reviewerAgent": "Audit Agent",
+    "reviewerSystem": "System",
+    "reviewerManual": "Manual entry",
+    "logCreate": "New log",
+    "logModalTitle": "Audit log",
+    "logModalEdit": "Edit audit log",
+    "fieldConversation": "Conversation ID",
+    "fieldTool": "Tool name",
+    "fieldComment": "Comment",
+    "fieldPayload": "Payload (JSON)",
+    "fieldUserMessage": "User message",
+    "fieldThinking": "Thinking",
+    "fieldReasoning": "Reasoning chain",
+    "fieldPlanning": "Planning",
+    "colId": "ID",
+    "colTool": "Tool",
+    "colConversation": "Conversation",
+    "colDecision": "Decision",
+    "colDecidedBy": "Reviewer",
+    "colContext": "Context",
+    "colTime": "Time",
+    "colActions": "Actions",
+    "viewDetail": "Detail",
+    "logModalView": "Audit log detail",
+    "fieldExecutionResult": "Execution result",
+    "executionSuccess": "success",
+    "executionFailed": "failed",
+    "edit": "Edit",
+    "delete": "Delete",
+    "logsEmpty": "No audit logs",
+    "logsEmptyHint": "Records are created automatically when HITL approvals are approved or rejected.",
+    "pageInfo": "{{total}} total",
+    "prevPage": "Previous",
+    "nextPage": "Next",
+    "conversationRequired": "Conversation ID is required",
+    "toolRequired": "Tool name is required",
+    "saveFailed": "Save failed",
+    "deleteConfirm": "Delete this audit log?",
+    "deleteFailed": "Delete failed",
+    "retentionHint": "Audit logs are kept for {{days}} days, then purged automatically.",
+    "selectedCount": "{{count}} selected",
+    "selectAll": "Select all",
+    "deselectAll": "Deselect all",
+    "batchDelete": "Batch delete",
+    "batchDeleteConfirm": "Delete the selected {{count}} audit log(s)? This cannot be undone.",
+    "batchDeleteSuccess": "Successfully deleted {{count}} audit log(s)",
+    "batchDeleteFailed": "Batch delete failed",
+    "clearAll": "Clear all",
+    "clearAllConfirm": "Clear all {{count}} audit log(s) matching the current filters? This cannot be undone.",
+    "clearAllConfirmNoFilter": "No filters are set. This will clear all {{count}} audit log(s). This cannot be undone. Continue?",
+    "clearAllSuccess": "Cleared {{count}} audit log(s)",
+    "clearAllFailed": "Clear failed",
+    "selectLogsFirst": "Select audit logs to delete first",
     "loading": "Loading...",
     "emptyState": "No pending approvals",
     "dismiss": "Dismiss",
@@ -2087,11 +2187,27 @@
     "subIndexFilter": "Sub-index filter (optional)",
     "subIndexFilterPlaceholder": "e.g. prod, must match an indexing sub_indexes tag",
     "subIndexFilterHint": "Empty = no filter. When set, only rows whose sub_indexes contain this tag (legacy rows with empty sub_indexes still match).",
+    "ragPipelineHeader": "RAG pipeline (MultiQuery + Rerank)",
+    "ragPipelineHint": "MultiQuery and rerank are always on: LLM query rewrite → vector prefetch & fusion → HTTP rerank → dedupe & budget truncate.",
+    "multiQueryMaxQueries": "MultiQuery rewrite variant limit",
+    "multiQueryMaxQueriesPlaceholder": "4",
+    "multiQueryMaxQueriesHint": "Max LLM-generated retrieval variants (including paraphrases of the original query). Recommended 3–4, max 8.",
+    "rerankProvider": "Rerank provider",
+    "rerankProviderAuto": "Auto (infer from Base URL)",
+    "rerankProviderCohere": "Cohere-compatible API",
+    "rerankProviderHint": "DashScope uses gte-rerank; other compatible endpoints use /v1/rerank. Leave empty to infer from Base URL below.",
+    "rerankModel": "Rerank model (optional)",
+    "rerankModelPlaceholder": "Empty: DashScope→gte-rerank, Cohere→rerank-multilingual-v3.0",
+    "rerankBaseUrl": "Rerank Base URL (optional)",
+    "rerankBaseUrlPlaceholder": "Leave empty to reuse embedding / OpenAI base_url",
+    "rerankApiKey": "Rerank API Key (optional)",
+    "rerankApiKeyPlaceholder": "Leave empty to reuse embedding / OpenAI api_key",
+    "rerankApiKeyHint": "On rerank failure, results fall back to fusion order; search still works.",
     "postRetrieveHeader": "Post-retrieval (dedupe / budget)",
     "postRetrieveDedupeAuto": "Results are always deduped by normalized text (whitespace-collapsed bodies). No setting required.",
     "prefetchTopK": "Prefetch candidates (vector stage)",
-    "prefetchTopKPlaceholder": "0",
+    "prefetchTopKPlaceholder": "20",
-    "prefetchTopKHint": "0 = same as Top-K; larger values fetch more vector hits before dedupe/truncate (max 200).",
+    "prefetchTopKHint": "Vector candidates per MultiQuery variant; 0 uses built-in max(top_k×4, 20) (max 200).",
     "maxContextChars": "Max returned characters (Unicode)",
     "maxContextCharsPlaceholder": "0",
     "maxContextCharsHint": "0 = unlimited; keeps whole chunks in rank order until the budget is exceeded.",
@@ -2542,6 +2658,7 @@
     "conversationName": "Conversation name",
     "project": "Project",
     "noProject": "No project",
+    "unknownProject": "Unknown project",
     "filterByProject": "Filter by project",
     "lastTime": "Last activity",
     "action": "Action",

web/static/i18n/zh-CN.json

@@ -39,6 +39,15 @@
     "version": "当前版本",
     "toggleSidebar": "折叠/展开侧边栏"
   },
+  "theme": {
+    "system": "跟随系统",
+    "light": "浅色",
+    "dark": "暗色",
+    "titleSystem": "当前：跟随系统主题。点击切换为浅色。",
+    "titleLight": "当前：浅色主题。点击切换为暗色。",
+    "titleDark": "当前：暗色主题。点击切换为跟随系统。",
+    "toggle": "切换主题"
+  },
   "notifications": {
     "title": "事件通知",
     "empty": "暂无新事件",
@@ -492,6 +501,12 @@
     "filterByProject": "按项目筛选",
     "filterAllProjects": "全部项目",
     "filterUnboundProjects": "未绑定项目",
+    "filterProjectSearch": "搜索项目…",
+    "filterProjectSearchEmpty": "没有匹配的项目",
+    "filterProjectSearchHint": "输入关键字搜索项目",
+    "filterProjectSearchMore": "更多项目请输入关键字搜索",
+    "filterProjectSearchLoading": "搜索中…",
+    "filterProjectSearchFailed": "加载项目失败，请重试",
     "projectConversationsTitle": "{{name}} · 对话",
     "unboundConversationsTitle": "未绑定项目",
     "noProjectConversations": "该项目暂无对话",
@@ -633,7 +648,10 @@
     "agentModeOrchSupervisor": "Supervisor",
     "hitlTitle": "人机协同",
     "hitlCardSubtitle": "审批与白名单",
-    "hitlReviewer": "Review",
+    "hitlReviewerLabel": "审批方",
+    "hitlReviewerHuman": "人工审批",
+    "hitlReviewerAgent": "审计 Agent",
+    "hitlReviewerHint": "可在人工与审计 Agent 之间随时切换；规则与白名单不变。人机协同为「关闭」时也可预先选择。",
     "hitlConfigTitle": "协同模式配置",
     "hitlModeLabel": "模式",
     "hitlModeOff": "关闭",
@@ -642,7 +660,7 @@
     "hitlSensitiveTools": "敏感工具（逗号分隔）",
     "hitlWhitelistTools": "白名单工具（免审批，逗号分隔）",
     "hitlWhitelistPlaceholder": "例：read_file, grep 或每行一个工具名（与 config 全局白名单合并）",
-    "hitlWhitelistHint": "每行一个或逗号分隔；与 config 中全局白名单合并展示。",
+    "hitlWhitelistHint": "白名单内工具免审批；每行一个或逗号分隔，与 config 全局白名单合并。",
     "hitlApply": "应用",
     "hitlApplyOkSync": "人机协同配置已保存并同步到服务器。",
     "hitlApplyOkWhitelistYaml": "免审批工具已合并进 config.yaml 并生效。协同模式、超时等仍须选中会话后再点「应用」才会写入服务器。",
@@ -652,7 +670,89 @@
   },
   "hitl": {
     "pageTitle": "人机协同审批",
+    "pageReviewerLabel": "当前审批方",
+    "pageReviewerHint": "作用于当前选中会话；未选会话时保存到本机，新建会话时沿用。切换后立即生效。",
+    "pageReviewerSaved": "审批方已保存。",
+    "whitelistLabel": "免审批工具白名单",
+    "whitelistHint": "每行一个或逗号分隔；保存后写入 config.yaml 全局白名单并立即生效（与聊天侧栏同步展示）。",
+    "whitelistSaved": "白名单已保存。",
+    "whitelistSaveFailed": "保存白名单失败",
+    "strategyLabel": "审计策略（提示词）",
+    "strategyHint": "白名单内工具免审批；其余工具在审批方为「审计 Agent」时，由模型按此提示词自主裁决。",
+    "strategyTabApproval": "审批模式",
+    "strategyTabReviewEdit": "审查编辑模式",
+    "strategyHintApproval": "白名单内工具免审批；审批模式下审计 Agent 仅裁决通过/拒绝。",
+    "strategyHintReviewEdit": "审查编辑模式下审计 Agent 可通过 editedArguments 收窄参数后放行；无法安全改参时应拒绝。",
+    "strategyReset": "恢复默认",
+    "strategySaved": "审计策略已保存。",
+    "strategySaveFailed": "保存审计策略失败",
+    "tabPending": "待审计",
+    "tabLogs": "审计日志",
+    "tabStrategy": "审计策略",
+    "tabWhitelist": "工具白名单",
     "pendingTitle": "待处理审批",
+    "searchLabel": "搜索",
+    "searchPlaceholder": "工具名、会话 ID、载荷、备注…",
+    "searchApply": "搜索",
+    "filterDecision": "决策",
+    "filterDecidedBy": "审批方",
+    "filterAll": "全部",
+    "decisionApprove": "通过",
+    "decisionReject": "拒绝",
+    "reviewerHuman": "人工",
+    "reviewerAgent": "审计 Agent",
+    "reviewerSystem": "系统",
+    "reviewerManual": "手动录入",
+    "logCreate": "新建日志",
+    "logModalTitle": "审计日志",
+    "logModalEdit": "编辑审计日志",
+    "fieldConversation": "会话 ID",
+    "fieldTool": "工具名",
+    "fieldComment": "备注",
+    "fieldPayload": "载荷 (JSON)",
+    "fieldUserMessage": "用户原话",
+    "fieldThinking": "本轮思考",
+    "fieldReasoning": "推理链",
+    "fieldPlanning": "规划",
+    "colId": "ID",
+    "colTool": "工具",
+    "colConversation": "会话",
+    "colDecision": "决策",
+    "colDecidedBy": "审批方",
+    "colContext": "上下文",
+    "colTime": "时间",
+    "colActions": "操作",
+    "viewDetail": "详情",
+    "logModalView": "审计日志详情",
+    "fieldExecutionResult": "执行结果",
+    "executionSuccess": "成功",
+    "executionFailed": "失败",
+    "edit": "编辑",
+    "delete": "删除",
+    "logsEmpty": "暂无审计日志",
+    "logsEmptyHint": "人机协同审批通过或拒绝后会自动记录在此。",
+    "pageInfo": "共 {{total}} 条",
+    "prevPage": "上一页",
+    "nextPage": "下一页",
+    "conversationRequired": "请填写会话 ID",
+    "toolRequired": "请填写工具名",
+    "saveFailed": "保存失败",
+    "deleteConfirm": "确定删除这条审计日志？",
+    "deleteFailed": "删除失败",
+    "retentionHint": "审计日志保留 {{days}} 天，超期自动清理",
+    "selectedCount": "已选择 {{count}} 项",
+    "selectAll": "全选",
+    "deselectAll": "取消全选",
+    "batchDelete": "批量删除",
+    "batchDeleteConfirm": "确定删除选中的 {{count}} 条审计日志？此操作不可恢复。",
+    "batchDeleteSuccess": "成功删除 {{count}} 条审计日志",
+    "batchDeleteFailed": "批量删除失败",
+    "clearAll": "清空",
+    "clearAllConfirm": "确定清空当前筛选条件下的全部 {{count}} 条审计日志？此操作不可恢复。",
+    "clearAllConfirmNoFilter": "未设置筛选条件，将清空全部 {{count}} 条审计日志。此操作不可恢复，是否继续？",
+    "clearAllSuccess": "已清空 {{count}} 条审计日志",
+    "clearAllFailed": "清空失败",
+    "selectLogsFirst": "请先选择要删除的审计日志",
     "loading": "加载中...",
     "emptyState": "暂无待审批项",
     "dismiss": "忽略",
@@ -2075,11 +2175,27 @@
     "subIndexFilter": "子索引过滤（可选）",
     "subIndexFilterPlaceholder": "如 prod，与索引 sub_indexes 一致",
     "subIndexFilterHint": "留空不过滤；填写后仅检索向量行 sub_indexes 中含该标签的结果（未打标旧行仍保留）。",
+    "ragPipelineHeader": "RAG 管线（MultiQuery + Rerank）",
+    "ragPipelineHint": "MultiQuery 与精排始终启用：LLM 改写多路检索 → 向量预取与融合 → HTTP 精排 → 去重与预算截断。",
+    "multiQueryMaxQueries": "MultiQuery 改写变体上限",
+    "multiQueryMaxQueriesPlaceholder": "4",
+    "multiQueryMaxQueriesHint": "LLM 生成的检索变体数量上限（含原问语义覆盖）；建议 3~4，最大 8。",
+    "rerankProvider": "精排提供商",
+    "rerankProviderAuto": "自动（按 Base URL 推断）",
+    "rerankProviderCohere": "Cohere 兼容 API",
+    "rerankProviderHint": "DashScope 使用 gte-rerank；其他兼容端点走 /v1/rerank。留空时按下方 Base URL 自动推断。",
+    "rerankModel": "精排模型（可选）",
+    "rerankModelPlaceholder": "留空：DashScope→gte-rerank，Cohere→rerank-multilingual-v3.0",
+    "rerankBaseUrl": "精排 Base URL（可选）",
+    "rerankBaseUrlPlaceholder": "留空则复用嵌入 / OpenAI 的 base_url",
+    "rerankApiKey": "精排 API Key（可选）",
+    "rerankApiKeyPlaceholder": "留空则复用嵌入 / OpenAI 的 api_key",
+    "rerankApiKeyHint": "精排失败时自动降级为融合排序，检索仍可用。",
     "postRetrieveHeader": "检索后处理（去重 / 预算）",
     "postRetrieveDedupeAuto": "检索结果会自动按正文规范化去重（合并仅空白不同的重复片段），无需配置。",
     "prefetchTopK": "预取候选数（向量阶段）",
-    "prefetchTopKPlaceholder": "0",
+    "prefetchTopKPlaceholder": "20",
-    "prefetchTopKHint": "0 表示与 Top-K 相同；大于 Top-K 时先多取候选再经去重/截断回到 Top-K（上限 200）。",
+    "prefetchTopKHint": "每条 MultiQuery 变体的向量候选数；0 表示内置 max(top_k×4, 20)（上限 200）。",
     "maxContextChars": "返回内容最大字符数（Unicode）",
     "maxContextCharsPlaceholder": "0",
     "maxContextCharsHint": "0 表示不限制；按检索顺序整段保留 chunk，超出则丢弃后续。",
@@ -2530,6 +2646,7 @@
     "conversationName": "对话名称",
     "project": "项目",
     "noProject": "无项目",
+    "unknownProject": "未知项目",
     "filterByProject": "按项目筛选",
     "lastTime": "最近一次对话时间",
     "action": "操作",

web/static/js/audit.js

@@ -22,7 +22,7 @@ const AUDIT_ACTIONS_BY_CATEGORY = {
     task: ['create_queue', 'start_queue', 'delete_queue', 'pause_queue', 'rerun_queue', 'delete_batch_task'],
     tool: ['execution_delete', 'execution_delete_batch'],
     file: ['upload', 'delete'],
-    hitl: ['decision'],
+    hitl: ['decision', 'audit_strategy_update'],
     role: ['create', 'update', 'delete'],
     skill: ['create', 'update', 'delete'],
     agent: ['markdown_create', 'markdown_update', 'markdown_delete']

web/static/js/dashboard.js

@@ -1707,7 +1707,7 @@ window.navigateToVulnerabilitiesWithFilter = navigateToVulnerabilitiesWithFilter
 
 // 漏洞严重程度分布：半环形（donut）渲染
 // 几何参数固定，便于配合 viewBox 0 0 560 320 的 SVG 容器
-// 段间分隔由 CSS 的白色 stroke 完成，不再使用 gapRad
+// 段间分隔由 gapRad 几何间隙完成，不使用描边，避免浅色/暗色下白边或黑边过重
 var SEVERITY_DONUT_CFG = {
     // viewBox 0 0 480 260：整体保持紧凑，但环厚回到「黄金比例」附近，
     // 让弧带本身有视觉分量，又不像最早那版那样占太多空间。
@@ -1717,7 +1717,7 @@ var SEVERITY_DONUT_CFG = {
     rOuter: 165,
     rInner: 115,    // 环厚 = 50（介于原 90 和上一版 35 之间，自然且有质感）
     labelOffset: 14,
-    gapRad: 0.012
+    gapRad: 0.022
 };
 
 // 三段渐变：[高光浅调, 中段饱和色, 深色边缘] —— 做出类似 3D 釉面的层次
@@ -1759,28 +1759,66 @@ function severityLabel(id) {
     return SEVERITY_DEFAULT_LABELS[id] || id;
 }
 
+function isDashboardDarkTheme() {
+    return document.documentElement.getAttribute('data-theme') === 'dark';
+}
+
+function ensureSeverityDonutThemeObserver() {
+    if (severityDonutState.themeObserver) return;
+    severityDonutState.themeObserver = new MutationObserver(function (mutations) {
+        for (var i = 0; i < mutations.length; i++) {
+            if (mutations[i].attributeName === 'data-theme') {
+                renderSeverityDonut(severityDonutState.bySeverity, severityDonutState.total);
+                break;
+            }
+        }
+    });
+    severityDonutState.themeObserver.observe(document.documentElement, {
+        attributes: true,
+        attributeFilter: ['data-theme']
+    });
+}
+
 function ensureSeverityDonutDefs() {
     var defsEl = document.getElementById('dashboard-severity-donut-defs');
-    if (!defsEl || defsEl.hasChildNodes()) return;
+    if (!defsEl) return;
+    var dark = isDashboardDarkTheme();
     var html = '';
     html += '<linearGradient id="donut-track-face" x1="0%" y1="0%" x2="0%" y2="100%">';
-    html += '<stop offset="0%" stop-color="#f8fafc"/>';
+    if (dark) {
-    html += '<stop offset="55%" stop-color="#e8eef5"/>';
+        html += '<stop offset="0%" stop-color="#334155"/>';
-    html += '<stop offset="100%" stop-color="#dce5ef"/>';
+        html += '<stop offset="55%" stop-color="#1e293b"/>';
+        html += '<stop offset="100%" stop-color="#172033"/>';
+    } else {
+        html += '<stop offset="0%" stop-color="#f8fafc"/>';
+        html += '<stop offset="55%" stop-color="#e8eef5"/>';
+        html += '<stop offset="100%" stop-color="#dce5ef"/>';
+    }
     html += '</linearGradient>';
     html += '<radialGradient id="donut-track-vignette" cx="50%" cy="85%" r="75%" fx="50%" fy="85%">';
-    html += '<stop offset="0%" stop-color="#ffffff" stop-opacity="0.35"/>';
+    if (dark) {
-    html += '<stop offset="70%" stop-color="#ffffff" stop-opacity="0"/>';
+        html += '<stop offset="0%" stop-color="#0f172a" stop-opacity="0.55"/>';
+        html += '<stop offset="70%" stop-color="#0f172a" stop-opacity="0"/>';
+    } else {
+        html += '<stop offset="0%" stop-color="#ffffff" stop-opacity="0.35"/>';
+        html += '<stop offset="70%" stop-color="#ffffff" stop-opacity="0"/>';
+    }
     html += '</radialGradient>';
     html += '<radialGradient id="donut-inner-gloss" cx="35%" cy="75%" r="55%">';
-    html += '<stop offset="0%" stop-color="#ffffff" stop-opacity="0.45"/>';
+    if (dark) {
-    html += '<stop offset="55%" stop-color="#ffffff" stop-opacity="0.08"/>';
+        html += '<stop offset="0%" stop-color="#94a3b8" stop-opacity="0.10"/>';
-    html += '<stop offset="100%" stop-color="#ffffff" stop-opacity="0"/>';
+        html += '<stop offset="55%" stop-color="#94a3b8" stop-opacity="0.03"/>';
+        html += '<stop offset="100%" stop-color="#94a3b8" stop-opacity="0"/>';
+    } else {
+        html += '<stop offset="0%" stop-color="#ffffff" stop-opacity="0.45"/>';
+        html += '<stop offset="55%" stop-color="#ffffff" stop-opacity="0.08"/>';
+        html += '<stop offset="100%" stop-color="#ffffff" stop-opacity="0"/>';
+    }
     html += '</radialGradient>';
     html += '<filter id="donut-segment-soften" x="-18%" y="-18%" width="136%" height="136%" color-interpolation-filters="sRGB">';
     html += '<feGaussianBlur in="SourceAlpha" stdDeviation="0.8" result="blur"/>';
     html += '<feOffset dx="0" dy="1.5" in="blur" result="off"/>';
-    html += '<feFlood flood-color="#0f172a" flood-opacity="0.13" result="flood"/>';
+    html += '<feFlood flood-color="' + (dark ? '#000000' : '#0f172a') + '" flood-opacity="' + (dark ? '0.28' : '0.13') + '" result="flood"/>';
     html += '<feComposite in="flood" in2="off" operator="in" result="shadow"/>';
     html += '<feMerge><feMergeNode in="shadow"/><feMergeNode in="SourceGraphic"/></feMerge>';
     html += '</filter>';
@@ -1808,17 +1846,17 @@ function renderSeverityDonut(bySeverity, total) {
     severityDonutState.total = total || 0;
     severityDonutState.hoverId = null;
 
+    ensureSeverityDonutThemeObserver();
+
     var cfg = SEVERITY_DONUT_CFG;
     ensureSeverityDonutDefs();
 
     // 背景轨迹（完整半环）：双层填充营造凹槽 + 高光
-    if (!trackEl.hasChildNodes()) {
+    var trackPath = halfRingPath(cfg.cx, cfg.cy, cfg.rOuter, cfg.rInner);
-        var trackPath = halfRingPath(cfg.cx, cfg.cy, cfg.rOuter, cfg.rInner);
+    trackEl.innerHTML =
-        trackEl.innerHTML =
+        '<path class="donut-track-shadow" d="' + trackPath + '"/>' +
-            '<path class="donut-track-shadow" d="' + trackPath + '"/>' +
+        '<path class="donut-track" fill="url(#donut-track-face)" d="' + trackPath + '"/>' +
-            '<path class="donut-track" fill="url(#donut-track-face)" d="' + trackPath + '"/>' +
+        '<path class="donut-track-vignette" fill="url(#donut-track-vignette)" d="' + trackPath + '"/>';
-            '<path class="donut-track-vignette" fill="url(#donut-track-vignette)" d="' + trackPath + '"/>';
-    }
 
     var ids = ['critical', 'high', 'medium', 'low', 'info'];
     var severities = ids.map(function (id) {

web/static/js/i18n.js

@@ -154,6 +154,9 @@
         }
         applyTranslations(document);
         updateLangLabel();
+        if (typeof window.refreshThemeToggleLabel === 'function') {
+            window.refreshThemeToggleLabel();
+        }
         try {
             window.__locale = lang;
         } catch (e) { /* ignore */ }
@@ -180,6 +183,9 @@
         await loadLanguageResources(initialLang);
         applyTranslations(document);
         updateLangLabel();
+        if (typeof window.refreshThemeToggleLabel === 'function') {
+            window.refreshThemeToggleLabel();
+        }
         try {
             window.__locale = i18next.language || initialLang;
         } catch (e) { /* ignore */ }

web/static/js/monitor.js

@@ -172,6 +172,24 @@ function einoMainStreamPlanningTitle(responseData) {
     return prefix + '📝 ' + plan;
 }
 
+/**
+ * Eino 未捕获助手正文占位文案；终态 response 不应覆盖已有流式 buffer。
+ */
+function isEinoEmptyResponsePlaceholder(text) {
+    if (text == null) return false;
+    const s = String(text);
+    return s.indexOf('no assistant text was captured') !== -1
+        || s.indexOf('未捕获到助手文本输出') !== -1;
+}
+
+function resolveFinalAssistantResponseText(finalMessage, streamState) {
+    const buf = streamState && streamState.buffer != null ? String(streamState.buffer).trim() : '';
+    if (isEinoEmptyResponsePlaceholder(finalMessage) && buf) {
+        return streamState.buffer;
+    }
+    return finalMessage;
+}
+
 /**
  * 主通道 response 结束时：将流式占位条目固化为 planning（与后端 flushResponsePlan 落库类型一致），
  * 避免 integrateProgressToMCPSection 快照前删除占位导致「助手输出」仅刷新后才出现。
@@ -181,8 +199,9 @@ function finalizeMainResponseStreamItem(streamState, finalMessage, responseData)
     const item = document.getElementById(streamState.itemId);
     if (!item || !item.parentNode) return false;
 
-    const fullText = (finalMessage != null && String(finalMessage).trim() !== '')
+    const resolved = resolveFinalAssistantResponseText(finalMessage, streamState);
-        ? String(finalMessage)
+    const fullText = (resolved != null && String(resolved).trim() !== '')
+        ? String(resolved)
         : (streamState.buffer || '');
     if (!String(fullText).trim()) {
         item.parentNode.removeChild(item);
@@ -2414,19 +2433,20 @@ function handleStreamEvent(event, progressElement, progressId,
             const streamState = responseStreamStateByProgressId.get(progressId);
             const existingAssistantId = streamState?.assistantId || getAssistantId();
             let assistantIdFinal = existingAssistantId;
+            const bubbleText = resolveFinalAssistantResponseText(event.message, streamState);
 
             if (!assistantIdFinal) {
-                assistantIdFinal = addMessage('assistant', event.message, mcpIds, progressId);
+                assistantIdFinal = addMessage('assistant', bubbleText, mcpIds, progressId);
                 setAssistantId(assistantIdFinal);
             } else {
                 setAssistantId(assistantIdFinal);
-                updateAssistantBubbleContent(assistantIdFinal, event.message, true);
+                updateAssistantBubbleContent(assistantIdFinal, bubbleText, true);
             }
 
             // 将 response_start/response_delta 占位固化为 planning，与后端落库一致后再快照过程详情
             if (streamState && streamState.itemId) {
                 finalizeMainResponseStreamItem(streamState, event.message, responseData);
-            } else if (event.message && String(event.message).trim()) {
+            } else if (bubbleText && String(bubbleText).trim() && !isEinoEmptyResponsePlaceholder(event.message)) {
                 addTimelineItem(timeline, 'planning', {
                     title: typeof einoMainStreamPlanningTitle === 'function'
                         ? einoMainStreamPlanningTitle(responseData)
@@ -3440,6 +3460,28 @@ async function loadActiveTasks(showErrors = false) {
     }
 }
 
+function getActiveTaskDisplayName(task) {
+    const _t = function (k) { return typeof window.t === 'function' ? window.t(k) : k; };
+    const unnamedTaskText = _t('tasks.unnamedTask');
+    if (!task) return unnamedTaskText;
+    const title = (task.title || '').trim();
+    if (title) return title;
+    const message = (task.message || '').trim();
+    return message || unnamedTaskText;
+}
+
+function updateActiveTaskConversationTitle(conversationId, newTitle) {
+    const bar = document.getElementById('active-tasks-bar');
+    if (!bar || !conversationId) return;
+    const title = (newTitle || '').trim();
+    if (!title) return;
+    bar.querySelectorAll('.active-task-item[data-conversation-id="' + conversationId + '"] .active-task-message')
+        .forEach(function (el) {
+            el.textContent = title;
+        });
+}
+window.updateActiveTaskConversationTitle = updateActiveTaskConversationTitle;
+
 function renderActiveTasks(tasks) {
     const bar = document.getElementById('active-tasks-bar');
     if (!bar) return;
@@ -3500,13 +3542,17 @@ function renderActiveTasks(tasks) {
         };
         const statusText = statusMap[task.status] || _t('tasks.statusRunning');
         const isFinalStatus = ['failed', 'timeout', 'cancelled', 'completed'].includes(task.status);
-        const unnamedTaskText = _t('tasks.unnamedTask');
+        const taskDisplayName = getActiveTaskDisplayName(task);
         const stopTaskBtnText = _t('tasks.stopTask');
 
+        if (task && task.conversationId) {
+            item.dataset.conversationId = task.conversationId;
+        }
+
         item.innerHTML = `
             <div class="active-task-info">
                 <span class="active-task-status">${statusText}</span>
-                <span class="active-task-message">${escapeHtml(task.message || unnamedTaskText)}</span>
+                <span class="active-task-message">${escapeHtml(taskDisplayName)}</span>
             </div>
             <div class="active-task-actions">
                 ${timeText ? `<span class="active-task-time">${timeText}</span>` : ''}

web/static/js/projects.js

@@ -173,6 +173,65 @@ function rebuildProjectNameMap(list) {
     });
 }
 
+function rememberProjectsInNameMap(list) {
+    (list || []).forEach((p) => {
+        if (p && p.id) projectNameById[p.id] = p.name || p.id;
+    });
+}
+
+/** 与后端 projectListSearchPattern 对齐：name / description / id 子串匹配（忽略大小写） */
+function matchProjectSearchQuery(project, query) {
+    const q = String(query || '').trim().toLowerCase();
+    if (!q) return true;
+    const name = String(project.name || '').toLowerCase();
+    const desc = String(project.description || '').toLowerCase();
+    const id = String(project.id || '').toLowerCase();
+    return name.includes(q) || desc.includes(q) || id.includes(q);
+}
+
+function sortProjectsForPicker(projects) {
+    return [...projects].sort((a, b) => {
+        const ap = a.pinned ? 1 : 0;
+        const bp = b.pinned ? 1 : 0;
+        if (bp !== ap) return bp - ap;
+        const au = a.updated_at || a.updatedAt || '';
+        const bu = b.updated_at || b.updatedAt || '';
+        return String(bu).localeCompare(String(au));
+    });
+}
+
+/** 从已加载列表中筛选活跃项目（对话选择器 / 项目筛选下拉） */
+function filterActiveProjectsLocal(projects, query) {
+    const list = (projects || []).filter((p) => p && p.id && p.status !== 'archived');
+    const q = String(query || '').trim();
+    const filtered = q ? list.filter((p) => matchProjectSearchQuery(p, q)) : list;
+    return sortProjectsForPicker(filtered);
+}
+
+async function searchActiveProjects(query, opts = {}) {
+    const params = new URLSearchParams();
+    params.set('status', opts.status || 'active');
+    params.set('limit', String(opts.limit ?? (String(query || '').trim() ? PROJECT_PICKER_SEARCH_LIMIT : PROJECT_PICKER_INITIAL_LIMIT)));
+    params.set('offset', String(opts.offset ?? 0));
+    const q = String(query || '').trim();
+    if (q) params.set('search', q);
+    const res = await apiFetch(`/api/projects?${params}`);
+    if (!res.ok) throw new Error(tp('projects.loadProjectsFailed'));
+    const parsed = parseProjectsListResponse(await res.json());
+    rememberProjectsInNameMap(parsed.items);
+    return parsed;
+}
+
+async function fetchProjectSummary(projectId) {
+    const id = String(projectId || '').trim();
+    if (!id) return null;
+    const res = await apiFetch(`/api/projects/${encodeURIComponent(id)}`);
+    if (!res.ok) return null;
+    const project = await res.json();
+    if (project && project.id) rememberProjectsInNameMap([project]);
+    return project;
+}
+
 function getProjectsListPageSize() {
     try {
         const saved = parseInt(localStorage.getItem(PROJECTS_LIST_PAGE_SIZE_KEY), 10);
@@ -308,7 +367,15 @@ async function ensureProjectsLoaded(force) {
     return _projectsFetchPromise;
 }
 
+function isProjectsCacheReady() {
+    return _projectsListReady;
+}
+
 function prefetchProjectsForChat() {
+    const id = (resolveChatProjectSelection() || '').trim();
+    if (id && !projectNameById[id]) {
+        fetchProjectSummary(id).catch(() => {});
+    }
     ensureProjectsLoaded().catch(() => {});
 }
 
@@ -655,9 +722,12 @@ function updateProjectStatusPill(status) {
 
 function renderProjectDetailMeta(updatedAt) {
     const metaEl = document.getElementById('projects-detail-meta');
-    if (!metaEl) return;
+    const timeEl = document.getElementById('projects-detail-meta-time');
+    if (!metaEl || !timeEl) return;
     const time = formatProjectTime(updatedAt);
-    metaEl.textContent = tpFmt('projects.updatedPrefix', `Updated ${time}`, { time });
+    const full = tpFmt('projects.updatedPrefix', `Updated ${time}`, { time });
+    timeEl.textContent = time;
+    metaEl.title = full;
 }
 
 function refreshProjectDetailMetaI18n() {
@@ -2032,27 +2102,20 @@ function getChatProjectSelection() {
     return getActiveProjectId();
 }
 
-function isActiveChatProjectId(id) {
+/** 用于 UI：返回当前选中的项目 ID（有效性由 normalizeStaleChatProjectSelection 异步校验） */
-    if (!id) return false;
-    const source = projectsCacheAll.length ? projectsCacheAll : projectsCache;
-    return source.some((p) => p.id === id && p.status !== 'archived');
-}
-
-/** 用于 UI：无效/已删除/无可用项目时视为未绑定 */
 function resolveChatProjectSelection() {
-    const raw = getChatProjectSelection();
+    return getChatProjectSelection() || '';
-    if (!raw) return '';
-    if (!_projectsListReady) return raw;
-    return isActiveChatProjectId(raw) ? raw : '';
 }
 
 let _normalizingStaleProject = false;
 
-/** 项目列表加载后，清除 localStorage 或对话上残留的失效项目 ID */
+/** 清除 localStorage 或对话上残留的失效项目 ID */
 async function normalizeStaleChatProjectSelection() {
-    if (!_projectsListReady || _normalizingStaleProject) return;
+    if (_normalizingStaleProject) return;
-    const raw = getChatProjectSelection();
+    const raw = (getChatProjectSelection() || '').trim();
-    if (!raw || isActiveChatProjectId(raw)) return;
+    if (!raw) return;
+    const project = await fetchProjectSummary(raw);
+    if (project && project.id && project.status !== 'archived') return;
 
     _normalizingStaleProject = true;
     try {
@@ -2079,6 +2142,171 @@ async function normalizeStaleChatProjectSelection() {
     }
 }
 
+const PROJECT_PICKER_DEBOUNCE_MS = 100;
+const projectPickerPanelState = {
+    chat: { seq: 0, timer: null },
+    webshell: { seq: 0, timer: null },
+};
+
+function appendChatProjectPanelItem(list, project, selectedId, onSelect, tFn) {
+    const t = tFn || tp;
+    const isNone = !project.id;
+    const isSelected = isNone ? !selectedId : selectedId === project.id;
+    const desc = isNone
+        ? (project.description || '')
+        : (project.description || '').trim().slice(0, 80) || t('projects.sharedFactBoard');
+    const btn = document.createElement('button');
+    btn.type = 'button';
+    btn.className = 'role-selection-item-main' + (isSelected ? ' selected' : '');
+    btn.setAttribute('role', 'option');
+    btn.onclick = () => onSelect(project.id || '');
+    btn.innerHTML = `
+        <div class="role-selection-item-icon-main">${isNone ? '—' : '📁'}</div>
+        <div class="role-selection-item-content-main">
+            <div class="role-selection-item-name-main">${escapeHtml(project.name || t('common.untitled'))}</div>
+            <div class="role-selection-item-description-main">${escapeHtml(desc)}</div>
+        </div>
+        ${isSelected ? '<div class="role-selection-checkmark-main">✓</div>' : ''}
+    `;
+    list.appendChild(btn);
+}
+
+function appendChatProjectPanelMessage(list, className, text) {
+    const el = document.createElement('div');
+    el.className = className;
+    el.textContent = text;
+    list.appendChild(el);
+    return el;
+}
+
+function pickerMessage(t, key, fallback) {
+    const value = t(key);
+    if (!value || value === key) return fallback;
+    return value;
+}
+
+async function renderProjectPickerPanel(panelKey, config) {
+    const state = projectPickerPanelState[panelKey];
+    const list = document.getElementById(config.listId);
+    if (!list || !state) return;
+    const query = (document.getElementById(config.searchInputId)?.value || '').trim();
+    const seq = ++state.seq;
+    const selectedId = config.getSelectedId();
+    const t = config.t || tp;
+
+    const renderPinned = () => {
+        appendChatProjectPanelItem(
+            list,
+            {
+                id: '',
+                name: t('projects.noProject'),
+                description: t('projects.noProjectDescription'),
+            },
+            selectedId,
+            config.onSelect,
+            t
+        );
+    };
+
+    const needsFetch = !isProjectsCacheReady();
+    let loadingEl = null;
+    if (needsFetch) {
+        list.innerHTML = '';
+        renderPinned();
+        loadingEl = appendChatProjectPanelMessage(
+            list,
+            'chat-project-panel-loading',
+            pickerMessage(t, 'common.loading', '加载中…')
+        );
+    }
+
+    try {
+        const all = await ensureProjectsLoaded();
+        if (seq !== state.seq) return;
+
+        list.innerHTML = '';
+        renderPinned();
+        const projects = filterActiveProjectsLocal(all, query);
+        projects.forEach((p) => {
+            appendChatProjectPanelItem(list, p, selectedId, config.onSelect, t);
+        });
+
+        if (query && projects.length === 0) {
+            appendChatProjectPanelMessage(
+                list,
+                'chat-project-panel-empty',
+                pickerMessage(t, 'chat.filterProjectSearchEmpty', '没有匹配的项目')
+            );
+        }
+    } catch (e) {
+        if (seq !== state.seq) return;
+        list.innerHTML = '';
+        renderPinned();
+        appendChatProjectPanelMessage(
+            list,
+            'chat-project-panel-empty',
+            pickerMessage(t, 'chat.filterProjectSearchFailed', '加载项目失败，请重试')
+        );
+    } finally {
+        if (loadingEl && loadingEl.parentNode) loadingEl.remove();
+    }
+}
+
+function initProjectPickerPanelSearch(panelKey, searchInputId, onSearch) {
+    const input = document.getElementById(searchInputId);
+    if (!input || input.dataset.pickerBound === panelKey) return;
+    input.dataset.pickerBound = panelKey;
+    input.addEventListener('input', onSearch);
+    input.addEventListener('keydown', (e) => {
+        if (e.key === 'Escape') {
+            if (panelKey === 'chat' && typeof closeChatProjectPanel === 'function') {
+                closeChatProjectPanel();
+            } else if (panelKey === 'webshell' && typeof wsCloseProjectPanel === 'function') {
+                wsCloseProjectPanel();
+            }
+        }
+    });
+}
+
+function clearProjectPickerPanelSearch(panelKey, searchInputId) {
+    const state = projectPickerPanelState[panelKey];
+    if (!state) return;
+    state.seq += 1;
+    if (state.timer) {
+        clearTimeout(state.timer);
+        state.timer = null;
+    }
+    const input = document.getElementById(searchInputId);
+    if (input) input.value = '';
+}
+
+function scheduleProjectPickerPanelSearch(panelKey, loadFn) {
+    const state = projectPickerPanelState[panelKey];
+    if (!state) return;
+    if (state.timer) clearTimeout(state.timer);
+    state.timer = setTimeout(() => {
+        state.timer = null;
+        loadFn();
+    }, PROJECT_PICKER_DEBOUNCE_MS);
+}
+
+async function loadChatProjectPanelList() {
+    await renderProjectPickerPanel('chat', {
+        listId: 'chat-project-list',
+        searchInputId: 'chat-project-search',
+        getSelectedId: resolveChatProjectSelection,
+        onSelect: (projectId) => selectChatProject(projectId),
+    });
+}
+
+async function ensureChatProjectButtonLabel() {
+    const id = (resolveChatProjectSelection() || '').trim();
+    if (id && !projectNameById[id]) {
+        await fetchProjectSummary(id);
+    }
+    updateChatProjectButtonLabel();
+}
+
 function updateChatProjectButtonLabel() {
     const textEl = document.getElementById('chat-project-text');
     if (!textEl) return;
@@ -2086,56 +2314,13 @@ function updateChatProjectButtonLabel() {
     textEl.textContent = id && projectNameById[id] ? projectNameById[id] : tp('projects.noProject');
 }
 
-function renderChatProjectPanelList() {
-    const list = document.getElementById('chat-project-list');
-    if (!list) return;
-    const selected = resolveChatProjectSelection();
-    const source = projectsCacheAll.length ? projectsCacheAll : projectsCache;
-    const activeProjects = source.filter((p) => p.status !== 'archived');
-    const items = [{ id: '', name: tp('projects.noProject'), description: tp('projects.noProjectDescription') }, ...activeProjects];
-    if (!items.length) {
-        list.innerHTML = `<div class="chat-project-panel-empty">${escapeHtml(tp('projects.noProjectsClickCreate'))}</div>`;
-        return;
-    }
-    list.innerHTML = '';
-    items.forEach((p) => {
-        const isNone = !p.id;
-        const isSelected = isNone ? !selected : selected === p.id;
-        const desc = isNone
-            ? (p.description || '')
-            : (p.description || '').trim().slice(0, 80) || tp('projects.sharedFactBoard');
-        const projectId = p.id || '';
-        const btn = document.createElement('button');
-        btn.type = 'button';
-        btn.className = 'role-selection-item-main' + (isSelected ? ' selected' : '');
-        btn.setAttribute('role', 'option');
-        btn.onclick = () => {
-            selectChatProject(projectId);
-        };
-        btn.innerHTML = `
-                <div class="role-selection-item-icon-main">${isNone ? '—' : '📁'}</div>
-                <div class="role-selection-item-content-main">
-                    <div class="role-selection-item-name-main">${escapeHtml(p.name || tp('common.untitled'))}</div>
-                    <div class="role-selection-item-description-main">${escapeHtml(desc)}</div>
-                </div>
-                ${isSelected ? '<div class="role-selection-checkmark-main">✓</div>' : ''}
-            `;
-        list.appendChild(btn);
-    });
-}
-
 async function renderChatProjectPanel() {
-    const list = document.getElementById('chat-project-list');
+    initProjectPickerPanelSearch('chat', 'chat-project-search', () => {
-    if (!list) return;
+        scheduleProjectPickerPanelSearch('chat', () => loadChatProjectPanelList());
-    list.innerHTML = `<div class="chat-project-panel-loading">${escapeHtml(tp('common.loading'))}</div>`;
+    });
-    try {
+    clearProjectPickerPanelSearch('chat', 'chat-project-search');
-        await ensureProjectsLoaded();
+    await loadChatProjectPanelList();
-    } catch (e) {
+    requestAnimationFrame(() => document.getElementById('chat-project-search')?.focus());
-        console.warn(e);
-        list.innerHTML = `<div class="chat-project-panel-empty">${escapeHtml(tp('projects.loadFailedRetry'))}</div>`;
-        return;
-    }
-    renderChatProjectPanelList();
 }
 
 function closeChatProjectPanel() {
@@ -2146,6 +2331,7 @@ function closeChatProjectPanel() {
         btn.classList.remove('active');
         btn.setAttribute('aria-expanded', 'false');
     }
+    clearProjectPickerPanelSearch('chat', 'chat-project-search');
 }
 
 async function toggleChatProjectPanel() {
@@ -2213,15 +2399,14 @@ async function applyChatProjectSelection(projectId) {
 async function refreshChatProjectSelector() {
     if (!document.getElementById('chat-project-btn')) return;
     try {
-        await ensureProjectsLoaded();
         await normalizeStaleChatProjectSelection();
+        await ensureChatProjectButtonLabel();
     } catch (e) {
         console.warn(e);
     }
-    updateChatProjectButtonLabel();
     const panel = document.getElementById('chat-project-panel');
     if (panel && panel.style.display === 'flex') {
-        renderChatProjectPanelList();
+        await loadChatProjectPanelList();
     }
 }
 
@@ -2240,7 +2425,7 @@ function initChatProjectSelector() {
             renderProjectsPagination();
             updateChatProjectButtonLabel();
             const panel = document.getElementById('chat-project-panel');
-            if (panel && panel.style.display === 'flex') renderChatProjectPanelList();
+            if (panel && panel.style.display === 'flex') loadChatProjectPanelList();
             if (currentProjectId) {
                 refreshProjectDetailMetaI18n();
                 const source = projectsCacheAll.length ? projectsCacheAll : projectsCache;
@@ -2298,6 +2483,11 @@ window.onChatProjectChange = onChatProjectChange;
 window.toggleChatProjectPanel = toggleChatProjectPanel;
 window.closeChatProjectPanel = closeChatProjectPanel;
 window.selectChatProject = selectChatProject;
+window.renderProjectPickerPanel = renderProjectPickerPanel;
+window.initProjectPickerPanelSearch = initProjectPickerPanelSearch;
+window.clearProjectPickerPanelSearch = clearProjectPickerPanelSearch;
+window.scheduleProjectPickerPanelSearch = scheduleProjectPickerPanelSearch;
+window.loadChatProjectPanelList = loadChatProjectPanelList;
 window.prefetchProjectsForChat = prefetchProjectsForChat;
 window.ensureDefaultActiveProjectForNewChat = ensureDefaultActiveProjectForNewChat;
 window.getActiveProjectId = getActiveProjectId;
@@ -2334,5 +2524,10 @@ window.deleteProjectFactEdge = deleteProjectFactEdge;
 window.focusProjectFactGraphEdge = focusProjectFactGraphEdge;
 window.toggleProjectFactGraphConnectMode = toggleProjectFactGraphConnectMode;
 window.rebuildProjectNameMap = rebuildProjectNameMap;
+window.rememberProjectsInNameMap = rememberProjectsInNameMap;
+window.searchActiveProjects = searchActiveProjects;
+window.filterActiveProjectsLocal = filterActiveProjectsLocal;
+window.fetchProjectSummary = fetchProjectSummary;
 window.projectNameById = projectNameById;
 window.ensureProjectsLoaded = ensureProjectsLoaded;
+window.isProjectsCacheReady = isProjectsCacheReady;

web/static/js/router.js

@@ -335,7 +335,9 @@ async function initPage(pageId) {
             }
             break;
         case 'hitl':
-            if (typeof refreshHitlPending === 'function') {
+            if (typeof refreshHitlActivePanel === 'function') {
+                refreshHitlActivePanel();
+            } else if (typeof refreshHitlPending === 'function') {
                 refreshHitlPending();
             }
             break;

web/static/js/settings.js

@@ -389,10 +389,35 @@ async function loadConfig(loadTools = true) {
                 subIdxFilterInput.value = knowledge.retrieval?.sub_index_filter || '';
             }
 
+            const mq = knowledge.retrieval?.multi_query || {};
+            const mqMaxInput = document.getElementById('knowledge-multi-query-max-queries');
+            if (mqMaxInput) {
+                const mqVal = parseInt(mq.max_queries, 10);
+                mqMaxInput.value = (!isNaN(mqVal) && mqVal > 0) ? mqVal : 4;
+            }
+            const rr = knowledge.retrieval?.rerank || {};
+            const rerankProviderSelect = document.getElementById('knowledge-rerank-provider');
+            if (rerankProviderSelect) {
+                const p = (rr.provider || '').toLowerCase();
+                rerankProviderSelect.value = (p === 'dashscope' || p === 'cohere') ? p : '';
+            }
+            const rerankModelInput = document.getElementById('knowledge-rerank-model');
+            if (rerankModelInput) {
+                rerankModelInput.value = rr.model || '';
+            }
+            const rerankBaseUrlInput = document.getElementById('knowledge-rerank-base-url');
+            if (rerankBaseUrlInput) {
+                rerankBaseUrlInput.value = rr.base_url || '';
+            }
+            const rerankApiKeyInput = document.getElementById('knowledge-rerank-api-key');
+            if (rerankApiKeyInput) {
+                rerankApiKeyInput.value = rr.api_key || '';
+            }
+
             const post = knowledge.retrieval?.post_retrieve || {};
             const prefetchInput = document.getElementById('knowledge-post-retrieve-prefetch-top-k');
             if (prefetchInput) {
-                prefetchInput.value = post.prefetch_top_k ?? 0;
+                prefetchInput.value = post.prefetch_top_k ?? 20;
             }
             const maxCharsInput = document.getElementById('knowledge-post-retrieve-max-chars');
             if (maxCharsInput) {
@@ -1273,8 +1298,25 @@ async function applySettings() {
                     return isNaN(val) ? 0.7 : val;
                 })(),
                 sub_index_filter: document.getElementById('knowledge-retrieval-sub-index-filter')?.value?.trim() || '',
+                multi_query: {
+                    max_queries: (() => {
+                        const v = parseInt(document.getElementById('knowledge-multi-query-max-queries')?.value, 10);
+                        if (isNaN(v) || v <= 0) return 4;
+                        return Math.min(8, v);
+                    })()
+                },
+                rerank: {
+                    provider: document.getElementById('knowledge-rerank-provider')?.value?.trim() || '',
+                    model: document.getElementById('knowledge-rerank-model')?.value?.trim() || '',
+                    base_url: document.getElementById('knowledge-rerank-base-url')?.value?.trim() || '',
+                    api_key: document.getElementById('knowledge-rerank-api-key')?.value?.trim() || ''
+                },
                 post_retrieve: {
-                    prefetch_top_k: parseInt(document.getElementById('knowledge-post-retrieve-prefetch-top-k')?.value, 10) || 0,
+                    prefetch_top_k: (() => {
+                        const raw = document.getElementById('knowledge-post-retrieve-prefetch-top-k')?.value;
+                        const v = parseInt(raw, 10);
+                        return isNaN(v) ? 20 : Math.max(0, v);
+                    })(),
                     max_context_chars: parseInt(document.getElementById('knowledge-post-retrieve-max-chars')?.value, 10) || 0,
                     max_context_tokens: parseInt(document.getElementById('knowledge-post-retrieve-max-tokens')?.value, 10) || 0
                 }

web/static/js/skills.js

@@ -650,7 +650,7 @@ async function viewSkill(skillId) {
                     <div style="margin-bottom: 8px;"><strong>${escapeHtml(pathLabel)}</strong> ${escapeHtml(sumSkill.path || '')}</div>
                     <div style="margin-bottom: 16px;"><strong>${escapeHtml(modTimeLabel)}</strong> ${escapeHtml(sumSkill.mod_time || '')}</div>
                     <div style="margin-bottom: 8px;"><strong>${escapeHtml(contentLabel)}</strong> <span style="opacity:0.8;font-size:12px;">${escapeHtml(_t('skills.summaryHint'))}</span></div>
-                    <pre id="skill-view-body" style="background: #f5f5f5; padding: 16px; border-radius: 4px; overflow-x: auto; white-space: pre-wrap; word-wrap: break-word;">${escapeHtml(sumSkill.content || '')}</pre>
+                    <pre id="skill-view-body" style="padding: 16px; border-radius: 4px; overflow-x: auto; white-space: pre-wrap; word-wrap: break-word; border: 1px solid var(--border-color);">${escapeHtml(sumSkill.content || '')}</pre>
                 </div>
                 <div class="modal-footer">
                     <button type="button" class="btn-secondary" data-skill-load-full>${escapeHtml(loadFullLabel)}</button>

web/static/js/tasks.js

@@ -181,7 +181,7 @@ function updateCompletedTasksHistory(currentTasks) {
             
             tasksState.completedTasksHistory.push({
                 conversationId: task.conversationId,
-                message: task.message || '未命名任务',
+                message: task.title || task.message || '未命名任务',
                 startedAt: task.startedAt,
                 status: finalStatus,
                 completedAt: new Date().toISOString()
@@ -537,7 +537,7 @@ function renderTaskItem(task, statusMap, isHistory = false) {
                     ` : '<div class="task-checkbox-placeholder"></div>'}
                     <span class="task-status ${status.class}">${status.text}</span>
                     ${isHistory ? '<span class="task-history-badge" title="' + _t('tasks.historyBadge') + '">📜</span>' : ''}
-                    <span class="task-message" title="${escapeHtml(task.message || _t('tasks.unnamedTask'))}">${escapeHtml(task.message || _t('tasks.unnamedTask'))}</span>
+                    <span class="task-message" title="${escapeHtml((task.title || task.message || _t('tasks.unnamedTask')))}">${escapeHtml((task.title || task.message || _t('tasks.unnamedTask')))}</span>
                 </div>
                 <div class="task-actions">
                     ${duration ? `<span class="task-duration" title="${_t('tasks.duration')}">⏱ ${duration}</span>` : ''}

web/static/js/theme.js

@@ -0,0 +1,140 @@
+(function () {
+    'use strict';
+
+    const STORAGE_KEY = 'cyberstrike-theme';
+    const THEMES = ['system', 'light', 'dark'];
+    const FALLBACK_LABELS = {
+        system: '跟随系统',
+        light: '浅色',
+        dark: '暗色'
+    };
+    const FALLBACK_TITLES = {
+        system: '当前：跟随系统主题。点击切换为浅色。',
+        light: '当前：浅色主题。点击切换为暗色。',
+        dark: '当前：暗色主题。点击切换为跟随系统。'
+    };
+    const TITLE_KEYS = {
+        system: 'titleSystem',
+        light: 'titleLight',
+        dark: 'titleDark'
+    };
+
+    const media = window.matchMedia ? window.matchMedia('(prefers-color-scheme: dark)') : null;
+
+    function themeText(key, fallback) {
+        if (typeof window.t === 'function') {
+            const value = window.t('theme.' + key);
+            if (value && value !== 'theme.' + key) {
+                return value;
+            }
+        }
+        return fallback;
+    }
+
+    function getLabel(preference) {
+        return themeText(preference, FALLBACK_LABELS[preference] || FALLBACK_LABELS.system);
+    }
+
+    function getTitle(preference) {
+        const titleKey = TITLE_KEYS[preference] || TITLE_KEYS.system;
+        return themeText(titleKey, FALLBACK_TITLES[preference] || FALLBACK_TITLES.system);
+    }
+
+    function normalizePreference(value) {
+        return THEMES.includes(value) ? value : 'system';
+    }
+
+    function readPreference() {
+        try {
+            return normalizePreference(localStorage.getItem(STORAGE_KEY));
+        } catch (err) {
+            return 'system';
+        }
+    }
+
+    function resolveTheme(preference) {
+        if (preference === 'dark' || preference === 'light') {
+            return preference;
+        }
+        return media && media.matches ? 'dark' : 'light';
+    }
+
+    function updateButton(preference, resolved) {
+        const btn = document.getElementById('theme-toggle-btn');
+        const label = document.getElementById('theme-toggle-label');
+        if (!btn) {
+            return;
+        }
+        btn.dataset.themePreference = preference;
+        btn.dataset.theme = resolved;
+        const title = getTitle(preference);
+        btn.title = title;
+        btn.setAttribute('aria-label', title);
+        if (label) {
+            label.textContent = getLabel(preference);
+        }
+    }
+
+    function applyTheme(preference) {
+        const normalized = normalizePreference(preference);
+        const resolved = resolveTheme(normalized);
+        const root = document.documentElement;
+        root.setAttribute('data-theme-preference', normalized);
+        root.setAttribute('data-theme', resolved);
+        root.style.colorScheme = resolved;
+        updateButton(normalized, resolved);
+    }
+
+    function savePreference(preference) {
+        const normalized = normalizePreference(preference);
+        try {
+            localStorage.setItem(STORAGE_KEY, normalized);
+        } catch (err) {
+            // Ignore storage failures; the current page can still apply the theme.
+        }
+        applyTheme(normalized);
+    }
+
+    window.setThemePreference = savePreference;
+    window.getThemePreference = readPreference;
+    window.cycleThemePreference = function () {
+        const current = readPreference();
+        const next = THEMES[(THEMES.indexOf(current) + 1) % THEMES.length];
+        savePreference(next);
+    };
+    window.refreshThemeToggleLabel = function () {
+        applyTheme(readPreference());
+    };
+
+    if (media) {
+        const onSystemThemeChange = function () {
+            if (readPreference() === 'system') {
+                applyTheme('system');
+            }
+        };
+        if (typeof media.addEventListener === 'function') {
+            media.addEventListener('change', onSystemThemeChange);
+        } else if (typeof media.addListener === 'function') {
+            media.addListener(onSystemThemeChange);
+        }
+    }
+
+    document.addEventListener('languagechange', function () {
+        applyTheme(readPreference());
+    });
+
+    function initTheme() {
+        applyTheme(readPreference());
+        if (window.i18nReady && typeof window.i18nReady.then === 'function') {
+            window.i18nReady.then(function () {
+                applyTheme(readPreference());
+            });
+        }
+    }
+
+    if (document.readyState === 'loading') {
+        document.addEventListener('DOMContentLoaded', initTheme);
+    } else {
+        initTheme();
+    }
+})();

web/static/js/webshell.js

@@ -362,6 +362,20 @@ function wsProjectT(key, fallback) {
     return fallback;
 }
 
+function wsProjectPickerT(key) {
+    var fallbacks = {
+        'projects.noProject': '无项目',
+        'projects.noProjectDescription': '不绑定项目黑板',
+        'projects.sharedFactBoard': '共享事实黑板',
+        'common.untitled': '未命名',
+        'common.loading': '加载中…',
+        'chat.filterProjectSearchEmpty': '没有匹配的项目',
+        'chat.filterProjectSearchMore': '更多项目请输入关键字搜索',
+        'chat.filterProjectSearchFailed': '加载项目失败，请重试',
+    };
+    return wsProjectT(key, fallbacks[key]);
+}
+
 function getWebshellAiConvId(conn) {
     if (!conn || !conn.id) return '';
     return webshellAiConvMap[conn.id] || '';
@@ -409,51 +423,32 @@ function wsUpdateProjectButtonLabel() {
     textEl.textContent = id && nameMap[id] ? nameMap[id] : wsProjectT('projects.noProject', '无项目');
 }
 
-async function wsRenderProjectPanelList() {
+async function wsLoadProjectPanelList() {
-    var list = document.getElementById('ws-project-list');
+    if (typeof window.renderProjectPickerPanel !== 'function') return;
-    if (!list || !webshellCurrentConn) return;
+    await window.renderProjectPickerPanel('webshell', {
-    var conn = webshellCurrentConn;
+        listId: 'ws-project-list',
-    var selected = wsResolveWebshellAiProjectSelection(conn);
+        searchInputId: 'ws-project-search',
-    var projects = [];
+        getSelectedId: function () {
-    try {
+            return webshellCurrentConn ? wsResolveWebshellAiProjectSelection(webshellCurrentConn) : '';
-        if (typeof window.fetchAllProjects === 'function') {
+        },
-            projects = await window.fetchAllProjects(false);
+        onSelect: function (projectId) { wsSelectProject(projectId); },
-        }
+        t: wsProjectPickerT,
-    } catch (e) {
-        list.innerHTML = '<div class="chat-project-panel-empty">' + escapeHtml(wsProjectT('projects.loadFailedRetry', '加载失败，请重试')) + '</div>';
-        return;
-    }
-    if (typeof window.rebuildProjectNameMap === 'function') {
-        window.rebuildProjectNameMap(projects);
-    }
-    var activeProjects = projects.filter(function (p) { return p.status !== 'archived'; });
-    var items = [{ id: '', name: wsProjectT('projects.noProject', '无项目'), description: wsProjectT('projects.noProjectDescription', '不绑定项目') }].concat(activeProjects);
-    list.innerHTML = '';
-    items.forEach(function (p) {
-        var isNone = !p.id;
-        var isSelected = isNone ? !selected : selected === p.id;
-        var desc = isNone
-            ? (p.description || '')
-            : ((p.description || '').trim().slice(0, 80) || wsProjectT('projects.sharedFactBoard', '共享事实黑板'));
-        var btn = document.createElement('button');
-        btn.type = 'button';
-        btn.className = 'role-selection-item-main' + (isSelected ? ' selected' : '');
-        btn.setAttribute('role', 'option');
-        btn.onclick = function () { wsSelectProject(p.id || ''); };
-        btn.innerHTML = '<div class="role-selection-item-icon-main">' + (isNone ? '—' : '📁') + '</div>' +
-            '<div class="role-selection-item-content-main">' +
-            '<div class="role-selection-item-name-main">' + escapeHtml(p.name || '未命名') + '</div>' +
-            '<div class="role-selection-item-description-main">' + escapeHtml(desc) + '</div></div>' +
-            (isSelected ? '<div class="role-selection-checkmark-main">✓</div>' : '');
-        list.appendChild(btn);
     });
 }
 
 async function wsRenderProjectPanel() {
-    var list = document.getElementById('ws-project-list');
+    if (typeof window.initProjectPickerPanelSearch === 'function') {
-    if (!list) return;
+        window.initProjectPickerPanelSearch('webshell', 'ws-project-search', function () {
-    list.innerHTML = '<div class="chat-project-panel-loading">' + escapeHtml(wsProjectT('common.loading', '加载中...')) + '</div>';
+            if (typeof window.scheduleProjectPickerPanelSearch === 'function') {
-    await wsRenderProjectPanelList();
+                window.scheduleProjectPickerPanelSearch('webshell', function () { wsLoadProjectPanelList(); });
+            }
+        });
+    }
+    if (typeof window.clearProjectPickerPanelSearch === 'function') {
+        window.clearProjectPickerPanelSearch('webshell', 'ws-project-search');
+    }
+    await wsLoadProjectPanelList();
+    requestAnimationFrame(function () { document.getElementById('ws-project-search')?.focus(); });
 }
 
 function wsCloseProjectPanel() {
@@ -464,6 +459,9 @@ function wsCloseProjectPanel() {
         btn.classList.remove('active');
         btn.setAttribute('aria-expanded', 'false');
     }
+    if (typeof window.clearProjectPickerPanelSearch === 'function') {
+        window.clearProjectPickerPanelSearch('webshell', 'ws-project-search');
+    }
 }
 
 async function wsToggleProjectPanel() {
@@ -2230,6 +2228,9 @@ function selectWebshell(id, stateReady) {
         '<svg width="16" height="16" viewBox="0 0 24 24" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M18 6L6 18M6 6l12 12" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round"/></svg></button>' +
         '</div>' +
         '<div class="chat-project-panel-body">' +
+        '<div class="chat-project-panel-search">' +
+        '<input type="search" id="ws-project-search" class="chat-project-panel-search-input" autocomplete="off" placeholder="' + escapeHtml(wsProjectT('projects.searchProjectsPlaceholder', '搜索项目…')) + '">' +
+        '</div>' +
         '<div id="ws-project-list" class="role-selection-list-main"></div>' +
         '<div class="chat-project-panel-footer">' +
         '<button type="button" class="role-selection-item-main chat-project-panel-create-btn" onclick="showNewProjectModalFromWebshellAi()">' +

web/templates/api-docs.html

@@ -6,6 +6,7 @@
     <title data-i18n="apiDocs.pageTitle">API 文档 - CyberStrikeAI</title>
     <link rel="icon" type="image/png" href="/static/logo.png">
     <link rel="stylesheet" href="/static/css/style.css">
+    <script src="/static/js/theme.js"></script>
     <style>
         /* 覆盖主CSS的overflow限制，允许API文档页面滚动 */
         body {
@@ -25,8 +26,23 @@
             position: relative;
             margin-bottom: 32px;
             padding-bottom: 24px;
+            padding-right: 280px;
             border-bottom: 2px solid var(--border-color);
         }
+
+        .api-docs-header-actions {
+            position: absolute;
+            top: 0;
+            right: 0;
+            display: flex;
+            align-items: center;
+            gap: 10px;
+        }
+
+        .api-docs-header-actions .theme-toggle-btn,
+        .api-docs-header-actions .lang-switcher-btn {
+            min-height: 36px;
+        }
         
         .api-docs-header h1 {
             font-size: 2rem;
@@ -822,6 +838,114 @@
         .empty-state p {
             font-size: 0.875rem;
         }
+
+        html[data-theme="dark"] body {
+            background: var(--bg-secondary);
+        }
+
+        html[data-theme="dark"] .api-docs-container {
+            background: var(--bg-secondary);
+        }
+
+        html[data-theme="dark"] .api-docs-sidebar,
+        html[data-theme="dark"] .auth-info-section,
+        html[data-theme="dark"] .api-endpoint,
+        html[data-theme="dark"] .api-endpoint-header,
+        html[data-theme="dark"] .api-test-form,
+        html[data-theme="dark"] .api-response-example,
+        html[data-theme="dark"] .api-description pre,
+        html[data-theme="dark"] .api-description-detail .code-block,
+        html[data-theme="dark"] .api-description-detail .inline-code,
+        html[data-theme="dark"] .api-description code {
+            background: #111827;
+            border-color: #263244;
+        }
+
+        html[data-theme="dark"] .api-endpoint:hover {
+            box-shadow: 0 8px 24px rgba(0, 0, 0, 0.38);
+        }
+
+        html[data-theme="dark"] .api-group-link:hover {
+            background: rgba(96, 165, 250, 0.1);
+            color: var(--accent-hover);
+        }
+
+        html[data-theme="dark"] .api-group-link.active {
+            background: rgba(96, 165, 250, 0.16);
+            color: var(--accent-hover);
+        }
+
+        html[data-theme="dark"] .api-params-table th {
+            background: #0f172a;
+        }
+
+        html[data-theme="dark"] .api-test-input-group input,
+        html[data-theme="dark"] .api-test-input-group textarea {
+            background: #0f172a;
+            border-color: #2b374b;
+            color: var(--text-primary);
+        }
+
+        html[data-theme="dark"] .api-test-input-group input:focus,
+        html[data-theme="dark"] .api-test-input-group textarea:focus {
+            box-shadow: 0 0 0 3px rgba(96, 165, 250, 0.16);
+        }
+
+        html[data-theme="dark"] .api-test-result.success {
+            background: rgba(52, 211, 153, 0.14);
+            color: #6ee7b7;
+            border-color: rgba(52, 211, 153, 0.28);
+        }
+
+        html[data-theme="dark"] .api-test-result.error {
+            background: rgba(248, 113, 113, 0.14);
+            color: #fca5a5;
+            border-color: rgba(248, 113, 113, 0.28);
+        }
+
+        html[data-theme="dark"] .api-test-btn.secondary {
+            background: #111827;
+            border-color: #2b374b;
+            color: var(--text-primary);
+        }
+
+        html[data-theme="dark"] .api-test-btn.secondary:hover {
+            background: #1f2937;
+            border-color: var(--accent-color);
+        }
+
+        html[data-theme="dark"] .api-docs-header-actions .theme-toggle-btn,
+        html[data-theme="dark"] .api-docs-header-actions .lang-switcher-btn {
+            background: #111827;
+            border-color: #2b374b;
+            color: var(--text-primary);
+        }
+
+        html[data-theme="dark"] .api-docs-header-actions .theme-toggle-btn:hover,
+        html[data-theme="dark"] .api-docs-header-actions .lang-switcher-btn:hover {
+            background: #1f2937;
+            border-color: var(--accent-color);
+        }
+
+        html[data-theme="dark"] #token-status {
+            background: rgba(96, 165, 250, 0.12) !important;
+            border-left-color: var(--accent-color) !important;
+        }
+
+        @media (max-width: 768px) {
+            .api-docs-header {
+                padding-right: 0;
+                padding-bottom: 72px;
+            }
+
+            .api-docs-header-actions {
+                top: auto;
+                bottom: 16px;
+                left: 0;
+                right: 0;
+                justify-content: flex-end;
+            }
+        }
     </style>
 </head>
 <body>
@@ -837,7 +961,21 @@
                 <span data-i18n="apiDocs.title">API 文档</span>
             </h1>
             <p data-i18n="apiDocs.subtitle">CyberStrikeAI 平台 API 接口文档，支持在线测试</p>
-            <div class="api-docs-lang-switcher" style="position: absolute; top: 24px; right: 24px;">
+            <div class="api-docs-header-actions">
+                <button id="theme-toggle-btn" class="theme-toggle-btn btn-secondary" type="button" onclick="window.cycleThemePreference && window.cycleThemePreference()" data-i18n="theme.toggle" data-i18n-attr="title" title="切换主题" aria-label="切换主题">
+                    <svg class="theme-toggle-icon theme-toggle-icon--system" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                        <rect x="3" y="4" width="18" height="13" rx="2" stroke="currentColor" stroke-width="2"/>
+                        <path d="M8 21h8M12 17v4" stroke="currentColor" stroke-width="2" stroke-linecap="round"/>
+                    </svg>
+                    <svg class="theme-toggle-icon theme-toggle-icon--light" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                        <circle cx="12" cy="12" r="4" stroke="currentColor" stroke-width="2"/>
+                        <path d="M12 2v2M12 20v2M4 12H2M22 12h-2M5 5l1.5 1.5M17.5 17.5L19 19M19 5l-1.5 1.5M6.5 17.5L5 19" stroke="currentColor" stroke-width="2" stroke-linecap="round"/>
+                    </svg>
+                    <svg class="theme-toggle-icon theme-toggle-icon--dark" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                        <path d="M21 14.5A8.5 8.5 0 0 1 9.5 3a7 7 0 1 0 11.5 11.5z" stroke="currentColor" stroke-width="2" stroke-linejoin="round"/>
+                    </svg>
+                    <span id="theme-toggle-label">跟随系统</span>
+                </button>
                 <div class="lang-switcher">
                     <button type="button" class="btn-secondary lang-switcher-btn" onclick="typeof toggleLangDropdown === 'function' && toggleLangDropdown()" title="界面语言">
                         <span class="lang-switcher-icon">🌐</span>

web/templates/index.html

@@ -6,6 +6,23 @@
     <title>CyberStrikeAI</title>
     <link rel="icon" type="image/png" href="/static/logo.png">
     <link rel="shortcut icon" type="image/png" href="/static/favicon.ico">
+    <script>
+        (function () {
+            try {
+                var stored = localStorage.getItem('cyberstrike-theme') || 'system';
+                if (stored !== 'system' && stored !== 'light' && stored !== 'dark') {
+                    stored = 'system';
+                }
+                var prefersDark = window.matchMedia && window.matchMedia('(prefers-color-scheme: dark)').matches;
+                var resolved = stored === 'dark' || (stored !== 'light' && prefersDark) ? 'dark' : 'light';
+                document.documentElement.setAttribute('data-theme-preference', stored);
+                document.documentElement.setAttribute('data-theme', resolved);
+                document.documentElement.style.colorScheme = resolved;
+            } catch (e) {
+                document.documentElement.setAttribute('data-theme', 'light');
+            }
+        })();
+    </script>
     <link rel="stylesheet" href="/static/css/style.css">
     <link rel="stylesheet" href="/static/css/c2.css">
     <link rel="stylesheet" href="/static/vendor/xterm.css">
@@ -57,12 +74,26 @@
                             </svg>
                             <span data-i18n="header.apiDocs">API 文档</span>
                         </button>
-                                        <button class="openapi-doc-btn" onclick="window.open('https://github.com/Ed1s0nZ/CyberStrikeAI', '_blank')" data-i18n="header.github" data-i18n-attr="title" data-i18n-skip-text="true" title="GitHub">
+                        <button class="openapi-doc-btn" onclick="window.open('https://github.com/Ed1s0nZ/CyberStrikeAI', '_blank')" data-i18n="header.github" data-i18n-attr="title" data-i18n-skip-text="true" title="GitHub">
                                             <svg width="16" height="16" viewBox="0 0 98 96" fill="currentColor" xmlns="http://www.w3.org/2000/svg">
                                                 <path d="M48.854 0C21.839 0 0 22 0 49.217c0 21.756 13.993 40.172 33.405 46.69 2.427.49 3.316-1.059 3.316-2.362 0-1.141-.08-5.052-.08-9.127-13.59 2.934-16.42-5.867-16.42-5.867-2.184-5.704-5.42-7.17-5.42-7.17-4.448-3.015.324-3.015.324-3.015 4.934.326 7.523 5.052 7.523 5.052 4.367 7.496 11.404 5.378 14.235 4.074.404-3.178 1.699-5.378 3.074-6.6-10.839-1.141-22.243-5.378-22.243-24.283 0-5.378 1.94-9.778 5.014-13.2-.485-1.222-2.184-6.275.486-13.038 0 0 4.125-1.304 13.426 5.052a46.97 46.97 0 0 1 12.214-1.63c4.125 0 8.33.571 12.213 1.63 9.302-6.356 13.427-5.052 13.427-5.052 2.67 6.763.97 11.816.485 13.038 3.155 3.422 5.015 7.822 5.015 13.2 0 18.905-11.404 23.06-22.324 24.283 1.78 1.548 3.316 4.481 3.316 9.126 0 6.6-.08 11.897-.08 13.526 0 1.304.89 2.853 3.316 2.364 19.412-6.52 33.405-24.935 33.405-46.691C97.707 22 75.788 0 48.854 0z"/>
                                             </svg>
                                             <span data-i18n="header.github">GitHub</span>
                                         </button>
+                        <button id="theme-toggle-btn" class="theme-toggle-btn" type="button" onclick="window.cycleThemePreference && window.cycleThemePreference()" data-i18n="theme.toggle" data-i18n-attr="title" title="切换主题" aria-label="切换主题">
+                            <svg class="theme-toggle-icon theme-toggle-icon--system" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                                <rect x="3" y="4" width="18" height="13" rx="2" stroke="currentColor" stroke-width="2"/>
+                                <path d="M8 21h8M12 17v4" stroke="currentColor" stroke-width="2" stroke-linecap="round"/>
+                            </svg>
+                            <svg class="theme-toggle-icon theme-toggle-icon--light" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                                <circle cx="12" cy="12" r="4" stroke="currentColor" stroke-width="2"/>
+                                <path d="M12 2v2M12 20v2M4 12H2M22 12h-2M5 5l1.5 1.5M17.5 17.5L19 19M19 5l-1.5 1.5M6.5 17.5L5 19" stroke="currentColor" stroke-width="2" stroke-linecap="round"/>
+                            </svg>
+                            <svg class="theme-toggle-icon theme-toggle-icon--dark" width="16" height="16" viewBox="0 0 24 24" fill="none" aria-hidden="true" xmlns="http://www.w3.org/2000/svg">
+                                <path d="M21 14.5A8.5 8.5 0 0 1 9.5 3a7 7 0 1 0 11.5 11.5z" stroke="currentColor" stroke-width="2" stroke-linejoin="round"/>
+                            </svg>
+                            <span id="theme-toggle-label">跟随系统</span>
+                        </button>
                         <div class="lang-switcher">
                             <button class="btn-secondary lang-switcher-btn" onclick="toggleLangDropdown()" data-i18n="header.language" data-i18n-attr="title" data-i18n-skip-text="true" title="界面语言">
                                 <span class="lang-switcher-icon">🌐</span>
@@ -942,6 +973,19 @@
                                                 <option value="review_edit" data-i18n="chat.hitlModeReviewEdit">审查编辑</option>
                                             </select>
                                         </div>
+                                        <div class="hitl-config-field" id="hitl-reviewer-field">
+                                            <label class="hitl-config-label" data-i18n="chat.hitlReviewerLabel">审批方</label>
+                                            <div class="hitl-reviewer-toggle" role="group" aria-label="Reviewer">
+                                                <button type="button" class="hitl-reviewer-toggle-btn is-active" data-reviewer="human" aria-pressed="true">
+                                                    <span data-i18n="chat.hitlReviewerHuman">人工审批</span>
+                                                </button>
+                                                <button type="button" class="hitl-reviewer-toggle-btn" data-reviewer="audit_agent" aria-pressed="false">
+                                                    <span data-i18n="chat.hitlReviewerAgent">审计 Agent</span>
+                                                </button>
+                                            </div>
+                                            <input type="hidden" id="hitl-reviewer-select" value="human" />
+                                            <p class="hitl-config-hint" data-i18n="chat.hitlReviewerHint">可在人工与审计 Agent 之间随时切换；规则与白名单不变。人机协同为「关闭」时也可预先选择。</p>
+                                        </div>
                                         <div class="hitl-config-field hitl-config-field--tools">
                                             <label class="hitl-config-label" for="hitl-sensitive-tools" data-i18n="chat.hitlWhitelistTools">白名单工具（免审批，逗号分隔）</label>
                                             <textarea id="hitl-sensitive-tools" class="hitl-config-textarea" rows="3" spellcheck="false" autocomplete="off" data-i18n="chat.hitlWhitelistPlaceholder" data-i18n-attr="placeholder" placeholder=""></textarea>
@@ -1039,6 +1083,9 @@
                                             </button>
                                         </div>
                                         <div class="chat-project-panel-body">
+                                            <div class="chat-project-panel-search">
+                                                <input type="search" id="chat-project-search" class="chat-project-panel-search-input" autocomplete="off" data-i18n="projects.searchProjectsPlaceholder" data-i18n-attr="placeholder" placeholder="搜索项目…">
+                                            </div>
                                             <div id="chat-project-list" class="role-selection-list-main"></div>
                                             <div class="chat-project-panel-footer">
                                                 <button type="button" class="role-selection-item-main chat-project-panel-create-btn" onclick="showNewProjectModalFromChat()">
@@ -1160,13 +1207,177 @@
                     <div class="page-header">
                         <h2 data-i18n="hitl.pageTitle">人机协同审批</h2>
                         <div class="page-header-actions">
-                            <button class="btn-secondary" onclick="refreshHitlPending()" data-i18n="common.refresh">刷新</button>
+                            <button type="button" class="btn-secondary" id="hitl-refresh-btn" onclick="refreshHitlActivePanel()" data-i18n="common.refresh">刷新</button>
                         </div>
                     </div>
                     <div class="page-content">
-                        <div class="settings-section">
+                        <div class="hitl-page-reviewer-bar" id="hitl-page-reviewer-bar">
-                            <h3 data-i18n="hitl.pendingTitle">待处理审批</h3>
+                            <div class="hitl-page-reviewer-main">
+                                <span class="hitl-page-reviewer-label" data-i18n="hitl.pageReviewerLabel">当前审批方</span>
+                                <div class="hitl-reviewer-toggle hitl-reviewer-toggle--page" role="group" aria-label="Reviewer">
+                                    <button type="button" class="hitl-reviewer-toggle-btn is-active" data-reviewer="human" aria-pressed="true">
+                                        <span data-i18n="chat.hitlReviewerHuman">人工审批</span>
+                                    </button>
+                                    <button type="button" class="hitl-reviewer-toggle-btn" data-reviewer="audit_agent" aria-pressed="false">
+                                        <span data-i18n="chat.hitlReviewerAgent">审计 Agent</span>
+                                    </button>
+                                </div>
+                            </div>
+                            <p class="hitl-page-reviewer-hint" data-i18n="hitl.pageReviewerHint">作用于当前选中会话；未选会话时保存到本机，新建会话时沿用。切换后立即生效。</p>
+                        </div>
+                        <div class="hitl-page-tabs" role="tablist">
+                            <button type="button" class="hitl-page-tab hitl-page-tab--active" id="hitl-tab-pending" role="tab" aria-selected="true" onclick="switchHitlPageTab('pending')">
+                                <span data-i18n="hitl.tabPending">待审计</span>
+                                <span class="hitl-tab-badge" id="hitl-pending-count" hidden>0</span>
+                            </button>
+                            <button type="button" class="hitl-page-tab" id="hitl-tab-logs" role="tab" aria-selected="false" onclick="switchHitlPageTab('logs')">
+                                <span data-i18n="hitl.tabLogs">审计日志</span>
+                            </button>
+                            <button type="button" class="hitl-page-tab" id="hitl-tab-strategy" role="tab" aria-selected="false" onclick="switchHitlPageTab('strategy')">
+                                <span data-i18n="hitl.tabStrategy">审计策略</span>
+                            </button>
+                            <button type="button" class="hitl-page-tab" id="hitl-tab-whitelist" role="tab" aria-selected="false" onclick="switchHitlPageTab('whitelist')">
+                                <span data-i18n="hitl.tabWhitelist">工具白名单</span>
+                            </button>
+                        </div>
+
+                        <div id="hitl-panel-pending" class="hitl-page-panel">
+                            <div class="hitl-filters">
+                                <label>
+                                    <span data-i18n="hitl.searchLabel">搜索</span>
+                                    <input type="search" id="hitl-pending-search" class="hitl-filter-input" data-i18n="hitl.searchPlaceholder" data-i18n-attr="placeholder" placeholder="" onkeydown="if(event.key==='Enter')filterHitlPending()" />
+                                </label>
+                                <button type="button" class="btn-secondary" onclick="filterHitlPending()" data-i18n="hitl.searchApply">搜索</button>
+                            </div>
                             <div id="hitl-pending-list" class="hitl-pending-list"></div>
+                            <div id="hitl-pending-pagination" class="hitl-pending-pagination"></div>
+                        </div>
+
+                        <div id="hitl-panel-logs" class="hitl-page-panel" hidden>
+                            <div class="hitl-filters hitl-filters--logs">
+                                <label>
+                                    <span data-i18n="hitl.searchLabel">搜索</span>
+                                    <input type="search" id="hitl-logs-search" class="hitl-filter-input" data-i18n="hitl.searchPlaceholder" data-i18n-attr="placeholder" placeholder="" onkeydown="if(event.key==='Enter')filterHitlLogs()" />
+                                </label>
+                                <label>
+                                    <span data-i18n="hitl.filterDecision">决策</span>
+                                    <select id="hitl-logs-decision-filter" class="hitl-filter-select" onchange="filterHitlLogs()">
+                                        <option value="all" data-i18n="hitl.filterAll">全部</option>
+                                        <option value="approve" data-i18n="hitl.decisionApprove">通过</option>
+                                        <option value="reject" data-i18n="hitl.decisionReject">拒绝</option>
+                                    </select>
+                                </label>
+                                <label>
+                                    <span data-i18n="hitl.filterDecidedBy">审批方</span>
+                                    <select id="hitl-logs-decidedby-filter" class="hitl-filter-select" onchange="filterHitlLogs()">
+                                        <option value="all" data-i18n="hitl.filterAll">全部</option>
+                                        <option value="human" data-i18n="hitl.reviewerHuman">人工</option>
+                                        <option value="audit_agent" data-i18n="hitl.reviewerAgent">审计 Agent</option>
+                                        <option value="system" data-i18n="hitl.reviewerSystem">系统</option>
+                                        <option value="manual" data-i18n="hitl.reviewerManual">手动录入</option>
+                                    </select>
+                                </label>
+                                <button type="button" class="btn-secondary" onclick="filterHitlLogs()" data-i18n="hitl.searchApply">搜索</button>
+                                <button type="button" class="btn-secondary btn-delete" onclick="clearHitlLogs()" data-i18n="hitl.clearAll">清空</button>
+                            </div>
+                            <p id="hitl-logs-retention-hint" class="hitl-logs-retention-hint" hidden></p>
+                            <div id="hitl-logs-batch-actions" class="monitor-batch-actions" style="display: none;">
+                                <div class="batch-actions-info">
+                                    <span id="hitl-logs-selected-count" data-i18n="hitl.selectedCount" data-i18n-params='{"count":0}'>已选择 0 项</span>
+                                </div>
+                                <div class="batch-actions-buttons">
+                                    <button type="button" class="btn-secondary" onclick="selectAllHitlLogs()" data-i18n="hitl.selectAll">全选</button>
+                                    <button type="button" class="btn-secondary" onclick="deselectAllHitlLogs()" data-i18n="hitl.deselectAll">取消全选</button>
+                                    <button type="button" class="btn-secondary btn-delete" onclick="batchDeleteHitlLogs()" data-i18n="hitl.batchDelete">批量删除</button>
+                                </div>
+                            </div>
+                            <div id="hitl-logs-table-wrap" class="hitl-logs-table-wrap">
+                                <div class="loading-spinner" data-i18n="hitl.loading">加载中...</div>
+                            </div>
+                            <div id="hitl-logs-pagination" class="hitl-logs-pagination"></div>
+                        </div>
+
+                        <div id="hitl-panel-strategy" class="hitl-page-panel" hidden>
+                            <div class="hitl-page-strategy-bar" id="hitl-page-strategy-bar">
+                                <div class="hitl-page-strategy-header">
+                                    <span class="hitl-page-strategy-label" data-i18n="hitl.strategyLabel">审计策略</span>
+                                    <div class="hitl-page-strategy-actions">
+                                        <button type="button" class="btn-link" id="hitl-strategy-reset-btn" onclick="resetHitlAuditStrategy()" data-i18n="hitl.strategyReset">恢复默认</button>
+                                        <button type="button" class="btn-secondary" id="hitl-strategy-save-btn" onclick="saveHitlAuditStrategy()" data-i18n="common.save">保存</button>
+                                    </div>
+                                </div>
+                                <div class="hitl-strategy-subtabs" role="tablist" aria-label="Audit strategy mode">
+                                    <button type="button" class="hitl-strategy-subtab hitl-strategy-subtab--active" id="hitl-strategy-tab-approval" role="tab" aria-selected="true" data-strategy-mode="approval" onclick="switchHitlStrategyMode('approval')" data-i18n="hitl.strategyTabApproval">审批模式</button>
+                                    <button type="button" class="hitl-strategy-subtab" id="hitl-strategy-tab-review-edit" role="tab" aria-selected="false" data-strategy-mode="review_edit" onclick="switchHitlStrategyMode('review_edit')" data-i18n="hitl.strategyTabReviewEdit">审查编辑模式</button>
+                                </div>
+                                <p class="hitl-page-strategy-hint" id="hitl-strategy-hint-approval" data-i18n="hitl.strategyHintApproval">白名单内工具免审批；审批模式下审计 Agent 仅裁决通过/拒绝。</p>
+                                <p class="hitl-page-strategy-hint" id="hitl-strategy-hint-review-edit" hidden data-i18n="hitl.strategyHintReviewEdit">审查编辑模式下审计 Agent 可通过 editedArguments 收窄参数后放行；无法安全改参时应拒绝。</p>
+                                <textarea id="hitl-audit-agent-prompt" class="hitl-strategy-textarea" rows="14" spellcheck="false" autocomplete="off"></textarea>
+                                <textarea id="hitl-audit-agent-prompt-review-edit" class="hitl-strategy-textarea" rows="14" spellcheck="false" autocomplete="off" hidden></textarea>
+                                <div id="hitl-strategy-feedback" class="hitl-apply-feedback" role="status" aria-live="polite" hidden></div>
+                            </div>
+                        </div>
+
+                        <div id="hitl-panel-whitelist" class="hitl-page-panel" hidden>
+                            <div class="hitl-page-whitelist-bar" id="hitl-page-whitelist-bar">
+                                <div class="hitl-page-whitelist-header">
+                                    <span class="hitl-page-whitelist-label" data-i18n="hitl.whitelistLabel">免审批工具白名单</span>
+                                    <button type="button" class="btn-secondary" id="hitl-page-whitelist-save-btn" onclick="saveHitlPageWhitelist()" data-i18n="common.save">保存</button>
+                                </div>
+                                <p class="hitl-page-whitelist-hint" data-i18n="hitl.whitelistHint">每行一个或逗号分隔；保存后写入 config.yaml 全局白名单并立即生效（与聊天侧栏同步展示）。</p>
+                                <textarea id="hitl-page-sensitive-tools" class="hitl-page-whitelist-textarea" rows="6" spellcheck="false" autocomplete="off" data-i18n="chat.hitlWhitelistPlaceholder" data-i18n-attr="placeholder" placeholder=""></textarea>
+                                <div id="hitl-page-whitelist-feedback" class="hitl-apply-feedback" role="status" aria-live="polite" hidden></div>
+                            </div>
+                        </div>
+                    </div>
+                </div>
+
+                <div id="hitl-log-modal" class="modal" style="display:none" role="dialog" aria-modal="true" aria-labelledby="hitl-log-modal-title">
+                    <div class="modal-content hitl-log-modal-content">
+                        <div class="modal-header">
+                            <h3 id="hitl-log-modal-title" data-i18n="hitl.logModalView">审计日志详情</h3>
+                            <button type="button" class="modal-close" onclick="closeHitlLogModal()" aria-label="Close">&times;</button>
+                        </div>
+                        <div class="modal-body">
+                            <div id="hitl-log-context-readonly" class="hitl-log-readonly-section" hidden></div>
+                            <div id="hitl-log-execution-readonly" class="hitl-log-readonly-section" hidden></div>
+                            <dl class="hitl-log-detail-meta">
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colId">ID</dt>
+                                    <dd id="hitl-log-detail-id" class="hitl-log-detail-mono">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colTool">工具</dt>
+                                    <dd id="hitl-log-detail-tool">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colConversation">会话</dt>
+                                    <dd id="hitl-log-detail-conversation" class="hitl-log-detail-mono">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colDecision">决策</dt>
+                                    <dd id="hitl-log-detail-decision">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colDecidedBy">审批方</dt>
+                                    <dd id="hitl-log-detail-decided-by">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row">
+                                    <dt data-i18n="hitl.colTime">时间</dt>
+                                    <dd id="hitl-log-detail-time">—</dd>
+                                </div>
+                                <div class="hitl-log-detail-row hitl-log-detail-row--full" id="hitl-log-detail-comment-row" hidden>
+                                    <dt data-i18n="hitl.fieldComment">备注</dt>
+                                    <dd id="hitl-log-detail-comment">—</dd>
+                                </div>
+                            </dl>
+                            <div class="hitl-log-detail-payload" id="hitl-log-detail-payload-wrap" hidden>
+                                <div class="hitl-context-label" data-i18n="hitl.fieldPayload">载荷</div>
+                                <pre id="hitl-log-detail-payload" class="hitl-context-text"></pre>
+                            </div>
+                        </div>
+                        <div class="modal-footer">
+                            <button type="button" class="btn-secondary" onclick="closeHitlLogModal()" data-i18n="common.close">关闭</button>
                         </div>
                     </div>
                 </div>
@@ -1533,10 +1744,13 @@
                                                 <span class="projects-stat-chip projects-stat-chip--warn" id="project-stat-sparse" hidden>0 待补全</span>
                                             </div>
                                         </div>
-                                        <p id="projects-detail-meta" class="projects-detail-meta"></p>
                                         <p id="projects-detail-desc" class="projects-detail-desc" hidden></p>
                                     </div>
                                     <div class="projects-detail-header-actions">
+                                        <span id="projects-detail-meta" class="projects-detail-meta" aria-live="polite">
+                                            <svg class="projects-detail-meta-icon" width="13" height="13" viewBox="0 0 24 24" fill="none" stroke="currentColor" stroke-width="2" stroke-linecap="round" stroke-linejoin="round" aria-hidden="true"><circle cx="12" cy="12" r="10"/><polyline points="12 6 12 12 16 14"/></svg>
+                                            <span id="projects-detail-meta-time" class="projects-detail-meta-time"></span>
+                                        </span>
                                         <button type="button" class="btn-secondary btn-small" onclick="openVulnerabilitiesForProject()" data-i18n="projects.vulnerabilityManagement">漏洞管理</button>
                                         <button type="button" class="btn-primary btn-small" onclick="showAddFactModal()" data-i18n="projects.addFactCta">+ 添加事实</button>
                                     </div>
@@ -2826,14 +3040,46 @@
                                             <small class="form-hint" data-i18n="settingsBasic.subIndexFilterHint">留空表示不过滤；非空时仅检索 sub_indexes 含该标签的向量行（未打标旧数据仍会命中）。</small>
                                         </div>
 
+                                        <div class="settings-subsection-header">
+                                            <h5 data-i18n="settingsBasic.ragPipelineHeader">RAG 管线（MultiQuery + Rerank）</h5>
+                                        </div>
+                                        <p class="form-hint" style="margin: 0 0 12px 0;" data-i18n="settingsBasic.ragPipelineHint">MultiQuery 与精排始终启用：LLM 改写多路检索 → 向量预取与融合 → HTTP 精排 → 去重与预算截断。</p>
+                                        <div class="form-group">
+                                            <label for="knowledge-multi-query-max-queries" data-i18n="settingsBasic.multiQueryMaxQueries">MultiQuery 改写变体上限</label>
+                                            <input type="number" id="knowledge-multi-query-max-queries" min="1" max="8" data-i18n="settingsBasic.multiQueryMaxQueriesPlaceholder" data-i18n-attr="placeholder" placeholder="4" />
+                                            <small class="form-hint" data-i18n="settingsBasic.multiQueryMaxQueriesHint">LLM 生成的检索变体数量上限（含原问语义覆盖）；建议 3~4，最大 8。</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-rerank-provider" data-i18n="settingsBasic.rerankProvider">精排提供商</label>
+                                            <select id="knowledge-rerank-provider">
+                                                <option value="" data-i18n="settingsBasic.rerankProviderAuto">自动（按 Base URL 推断）</option>
+                                                <option value="dashscope">DashScope</option>
+                                                <option value="cohere" data-i18n="settingsBasic.rerankProviderCohere">Cohere 兼容 API</option>
+                                            </select>
+                                            <small class="form-hint" data-i18n="settingsBasic.rerankProviderHint">DashScope 使用 gte-rerank；其他兼容端点走 /v1/rerank。留空时按下方 Base URL 自动推断。</small>
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-rerank-model" data-i18n="settingsBasic.rerankModel">精排模型（可选）</label>
+                                            <input type="text" id="knowledge-rerank-model" data-i18n="settingsBasic.rerankModelPlaceholder" data-i18n-attr="placeholder" placeholder="留空：DashScope→gte-rerank，Cohere→rerank-multilingual-v3.0" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-rerank-base-url" data-i18n="settingsBasic.rerankBaseUrl">精排 Base URL（可选）</label>
+                                            <input type="text" id="knowledge-rerank-base-url" data-i18n="settingsBasic.rerankBaseUrlPlaceholder" data-i18n-attr="placeholder" placeholder="留空则复用嵌入 / OpenAI 的 base_url" />
+                                        </div>
+                                        <div class="form-group">
+                                            <label for="knowledge-rerank-api-key" data-i18n="settingsBasic.rerankApiKey">精排 API Key（可选）</label>
+                                            <input type="password" id="knowledge-rerank-api-key" data-i18n="settingsBasic.rerankApiKeyPlaceholder" data-i18n-attr="placeholder" placeholder="留空则复用嵌入 / OpenAI 的 api_key" />
+                                            <small class="form-hint" data-i18n="settingsBasic.rerankApiKeyHint">精排失败时自动降级为融合排序，检索仍可用。</small>
+                                        </div>
+
                                         <div class="settings-subsection-header">
                                             <h5 data-i18n="settingsBasic.postRetrieveHeader">检索后处理（去重 / 预算）</h5>
                                         </div>
                                         <p class="form-hint" style="margin: 0 0 12px 0;" data-i18n="settingsBasic.postRetrieveDedupeAuto">检索结果会自动按正文规范化去重（合并仅空白不同的重复片段），无需配置。</p>
                                         <div class="form-group">
                                             <label for="knowledge-post-retrieve-prefetch-top-k" data-i18n="settingsBasic.prefetchTopK">预取候选数（向量阶段）</label>
-                                            <input type="number" id="knowledge-post-retrieve-prefetch-top-k" min="0" max="200" data-i18n="settingsBasic.prefetchTopKPlaceholder" data-i18n-attr="placeholder" placeholder="0" />
+                                            <input type="number" id="knowledge-post-retrieve-prefetch-top-k" min="0" max="200" data-i18n="settingsBasic.prefetchTopKPlaceholder" data-i18n-attr="placeholder" placeholder="20" />
-                                            <small class="form-hint" data-i18n="settingsBasic.prefetchTopKHint">0 表示与 Top-K 相同；大于 Top-K 时先多取候选再经去重/截断回到 Top-K（上限 200）。</small>
+                                            <small class="form-hint" data-i18n="settingsBasic.prefetchTopKHint">每条 MultiQuery 变体的向量候选数；0 表示内置 max(top_k×4, 20)（上限 200）。</small>
                                         </div>
                                         <div class="form-group">
                                             <label for="knowledge-post-retrieve-max-chars" data-i18n="settingsBasic.maxContextChars">返回内容最大字符数（Unicode）</label>
@@ -4491,6 +4737,7 @@
 
     <script src="/static/vendor/i18next.min.js"></script>
     <script src="/static/js/i18n.js"></script>
+    <script src="/static/js/theme.js"></script>
     <script src="/static/js/builtin-tools.js"></script>
     <script src="/static/js/auth.js"></script>
     <script src="/static/js/modal.js"></script>
@@ -4521,4 +4768,3 @@
     <script src="/static/js/c2.js"></script>
 </body>
 </html>
-