merge: feat/deep-compression-inplace

.gitignore

@@ -42,3 +42,6 @@ doc/
 # Host workspace config (local, use .example)
 config/host_workspaces.json
 config/custom_models.json
+
+# Claude Code local artifacts (settings, worktrees)
+.claude/

AGENTS.md

@@ -5,6 +5,8 @@
 
 这份文档基于当前仓库实际代码重写。若与未来代码冲突，以代码为准并及时更新本文档。
 
+> 和用户交流时默认使用中文。
+
 ## 1) 当前项目结构（按代码现状）
 
 - **后端入口**

CLAUDE.md

@@ -2,6 +2,8 @@
 
 This file provides guidance to Claude Code (claude.ai/code) when working with code in this repository.
 
+> 和用户交流时默认使用中文。
+
 ## Project Overview
 
 多用户 AI Agent 系统，为每个登录用户提供独立的 Docker 容器环境。支持终端交互、文件操作、对话管理和实时监控。主要用于学习和实验"智能体 + 真实 Dev Workflow"，代码大量由 AI 生成。
@@ -9,14 +11,22 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 ## Core Architecture
 
 ### Entry Points
-- **CLI模式**: `python main.py` - 启动命令行交互式 Agent
-- **Web模式**: `python web_server.py` - 启动 Flask Web 服务器（主链路为 REST 任务轮询，默认端口 8091）
+- **统一入口**: `python main.py` - 当前实现默认进入 Web 启动流程（thinking_mode=True）
+- **推荐 Web 入口**: `python -m server.app` - 封装并转发到 `server/app_legacy.py`，主链路为 REST 任务轮询，默认端口 8091
+- **兼容入口**: `python web_server.py` - 已标记 deprecated，但仍可启动
 
 ### Key Components
 
+**server/** (Flask 业务主线，chat/task 以 REST 任务轮询为主，Socket.IO 用于兼容与实时辅助通道)
+- `app.py` / `app_legacy.py` - Web 服务入口与遗留实现
+- `chat.py` / `chat_flow*.py` - 对话与任务流编排（runner / tool_loop / stream_loop / task_main 等拆分）
+- `goal_flow.py` - 自主目标循环
+- `deep_compression.py` - 上下文深度压缩
+- `tasks.py` / `monitor.py` / `conversation.py` / `files.py` / `auth.py` / `admin.py` - 任务、监控、对话、文件、认证、管理接口
+
 **core/**
-- `MainTerminal` - CLI 主终端，处理用户输入和 AI 对话循环
-- `WebTerminal` - Web 终端，继承 MainTerminal，支持轮询任务与实时通道兼容能力
+- `MainTerminal` (`main_terminal.py`) - CLI 主终端，处理用户输入和 AI 对话循环；逻辑拆分到 `core/main_terminal_parts/*`（commands / context / tools / tools_execution / tools_policy / tools_read 等）
+- `WebTerminal` (`web_terminal.py`) - Web 终端，继承 MainTerminal，支持轮询任务与实时通道兼容能力
 - `tool_config.py` - 定义所有工具的配置和分类
 
 **modules/**
@@ -37,7 +47,12 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 - `terminal_factory.py` - 终端类型工厂
 
 **static/**
-- Vue 前端（聊天主链路使用 REST 任务轮询，保留 Socket.IO 兼容能力），包含对话流、终端输出、资源监控面板
+- Vue 3 + TS 前端（`static/src/`，分层为 `app/` `stores/` `components/` `composables/`），聊天主链路使用 REST 任务轮询，保留 Socket.IO 兼容能力，包含对话流、终端输出、资源监控面板
+- 监控动画核心文件：`static/src/components/chat/monitor/MonitorDirector.ts`（动画与场景执行）、`static/src/stores/monitor.ts`（事件队列与状态机）
+
+**cli/**
+- React 19 + Ink 6 + TypeScript CLI 前端（正在重写中），连接现有本地 Web API（默认 `127.0.0.1:8091`），不是独立 agent runtime
+- 关键文件：`cli/src/App.tsx`、`cli/src/components.tsx`、`cli/src/eventMapper.ts`、`cli/src/api.ts`
 
 **docker/**
 - `terminal.Dockerfile` - 终端容器镜像构建配置
@@ -46,22 +61,62 @@ This file provides guidance to Claude Code (claude.ai/code) when working with co
 
 ### Build & Run
 ```bash
-# 安装依赖（需要在项目根目录创建 requirements.txt）
-pip install flask flask-socketio flask-cors openai python-dotenv tiktoken lxml
+# 安装 Python 依赖
+pip install -r requirements.txt
 
 # 构建终端镜像
 docker build -f docker/terminal.Dockerfile -t my-agent-shell:latest .
 
-# CLI 模式
+# 统一入口（默认进入 Web 启动流程）
 python main.py
 
-# Web 模式
+# 推荐 Web 启动
+python -m server.app
+# 可选参数
+python -m server.app --path ./project --port 8091 --debug --thinking-mode
+
+# 兼容启动方式（deprecated）
 python web_server.py
-# 或指定端口和思考模式
-python web_server.py --port 8091 --thinking-mode
 ```
 
-### Testing & Debugging
+### Frontend (根目录 Vue)
+```bash
+npm install
+# 构建（默认只看最后 5 行，减少 Vite 构建资源列表等无关输出）
+npm run build --silent 2>&1 | tail -n 5
+# 开发监听（当前脚本是 build watch）
+npm run dev
+# Lint
+npm run lint
+```
+
+### CLI (React / Ink)
+```bash
+npm --prefix cli install
+# 开发启动
+npm run cli            # 或 npm --prefix cli run dev
+# 构建
+npm run cli:build
+# 类型检查
+npm run cli:typecheck
+# 可执行命令名（构建后）：agents / agents-cli
+```
+
+### Testing
+```bash
+# 主要离线冒烟用例（unittest）
+python -m unittest test.test_server_refactor_smoke
+
+# 改动后端接口适配（如 server/chat.py）时补充
+python3 -m py_compile server/chat.py
+
+# CLI 最小可复现验证
+npm --prefix cli run typecheck
+npm --prefix cli run build
+```
+> 仓库未发现 `pytest.ini`/`pyproject.toml`/`tox.ini`，不要默认要求 `pytest` 作为唯一入口。`test/test_system_message.py` 依赖外部 `MOONSHOT_API_KEY` 与网络，不属于离线稳定用例。
+
+### Debugging
 ```bash
 # 查看容器状态
 docker ps -a | grep agent-term
@@ -139,9 +194,18 @@ tail -f logs/container_stats.log
 
 ### Adding New Tools
 
-1. 在 `MainTerminal` 添加 `handle_<tool_name>` 方法
-2. 在 `core/tool_config.py` 的 `define_tools()` 中注册工具
-3. 如果需要在流式输出中处理，在 `web_server.py` 添加特殊逻辑
+1. 在 `core/main_terminal_parts/tools_execution.py`（及相关 `tools_*.py`）实现执行逻辑
+2. 在 `core/tool_config.py` / `core/main_terminal_parts/tools_definition.py` 中注册工具定义
+3. 如需在任务流/流式输出中特殊处理，在 `server/chat_flow*.py` 对应环节添加逻辑
+
+### 代码修改约定
+
+- **最小改动原则**：只改与需求直接相关文件，避免顺手重构。
+- **文件编辑方式**：优先使用原生文件编辑工具，尽量不要用 `bash`/`python` 脚本批量改文件。
+- **后端改动优先级**：先改 `modules/`、`server/` 内对应模块，最后才动入口。
+- **前端改动优先级**：按 `static/src` 现有分层改（`app/` `stores/` `components/` `composables/`）。
+- **CLI 改动优先级**：优先在 `cli/src/App.tsx`、`cli/src/components.tsx`、`cli/src/eventMapper.ts`、`cli/src/api.ts` 内做最小闭环修改。
+- 涉及 monitor 动画/事件联动时，至少同步检查 `MonitorDirector.ts` 与 `stores/monitor.ts`。
 
 ### Working with Containers
 
@@ -192,16 +256,21 @@ terminal.delete_conversation(conversation_id)
 
 ```
 agents/
-├── core/              # 核心终端和工具配置
+├── server/            # Flask 业务主线（chat/task/goal/monitor/auth ...）
+├── core/              # 核心终端与工具编排（main_terminal_parts/*）
 ├── modules/           # 独立功能模块
 ├── utils/             # 辅助工具
-├── config/            # 配置文件
-├── static/            # Web 前端
+├── config/            # 配置拆分（api/limits/terminal/paths ...，由 __init__ 聚合）
+├── static/            # Vue 3 + TS Web 前端
+├── cli/               # React + Ink CLI 前端（重写中）
 ├── docker/            # 容器镜像
 ├── prompts/           # 系统提示词
-├── users/             # 用户工作区
-├── data/              # 全局数据
-└── logs/              # 日志文件
+├── android-webview-app/ # Android WebView 客户端工程
+├── test/              # 测试用例
+├── docs/ / doc/       # 设计与发布文档
+├── users/             # 用户工作区（运行态，gitignored）
+├── data/              # 全局数据（运行态，gitignored）
+└── logs/              # 日志文件（运行态，gitignored）
 ```
 
 ## Development Tips
@@ -209,9 +278,32 @@ agents/
 - 修改系统提示词：编辑 `prompts/main_system.txt`
 - 调整工具限制：修改 `config/limits.py`
 - 容器镜像定制：编辑 `docker/terminal.Dockerfile` 并重新构建
-- 前端开发：`npm install && npm run dev` (在 `static/` 目录)
+- 前端开发：在项目根目录运行 `npm install && npm run dev`（build watch）
 - 查看详细执行流程：监控 `logs/debug_stream.log`
 
+## Permission Mode & Sandbox Execution (2026-05)
+
+完整说明文档：`docs/host_sandbox_and_permission_model.md`
+
+系统有两套独立但叠加的控制：
+
+### 权限模式 (Permission Mode)
+- `readonly` - `run_command` 在只读沙箱执行；`write_file`/`edit_file` 等写入类工具直接拒绝
+- `approval` - `run_command` 先走只读沙箱，权限拒绝（如 `Operation not permitted`/`Permission denied`）时触发前端审批，通过后仅该次命令以可写沙箱重试
+- `auto_approval` - 工作区内写入直接执行，工作区外写入进入审批；`run_command` 权限拒绝由后台审批智能体自动审核
+- `unrestricted` - 不做权限模式拦截，是否沙箱由执行环境决定
+
+### 执行环境 (Execution Mode)
+- `sandbox`（默认）- OS 沙箱执行（macOS: `sandbox-exec`，Linux: `bwrap + seccomp`，Windows: `WSL2`），支持会话级 TTL 自动回退 `direct -> sandbox`
+- `direct` - 宿主机直接执行（高风险，仅建议短时使用）
+
+### 路径授权语义
+- 前端路径授权分「可读可写」与「仅可读」：可读集合 = 可读可写 + 仅可读，可写集合 = 可读可写
+
+### 自动审批智能体
+- 配置文件：`config/auto_approval.json`（`name`/`url`/`key`/`model`/`extra_params`，及 `timeout_seconds`/`max_rounds`/`max_command_timeout`）
+- 调试开关：`modules/approval_agent.py` 中 `DEBUG_SAVE_APPROVAL_AGENT_TRANSCRIPT`，开启后写入 `logs/approval_agent/`
+
 ## Android Release Notes (Required for frontend update)
 
 当改动前端并准备发 Android WebView 壳版本时，必须同步完成：

core/main_terminal_parts/context.py

@@ -445,8 +445,15 @@ class MainTerminalContextMixin:
             # 添加对话历史（保留完整结构，包括tool_calls和tool消息）
             conversation = context["conversation"]
             replaced_tool_count = 0
+            deep_compacted_skipped = 0
             for idx, conv in enumerate(conversation):
                 metadata = conv.get("metadata") or {}
+                # 深压缩：被标记为 deep_compacted 的消息（整段已压缩前缀）原文保留在历史中用于展示，
+                # 但构建请求时整体跳过，不纳入上下文。由于按连续前缀整体标记，
+                # 不会出现 assistant.tool_calls 与其 tool 响应被拆散导致的配对悬空。
+                if metadata.get("deep_compacted"):
+                    deep_compacted_skipped += 1
+                    continue
                 if conv["role"] == "assistant":
                     # Assistant消息可能包含工具调用
                     message = {
@@ -523,6 +530,8 @@ class MainTerminalContextMixin:
             # 当前用户输入已经在conversation中了，不需要重复添加
             if shallow_replace_enabled:
                 print(f"[ContextCompression] build_messages 替换tool占位符: {replaced_tool_count} 条")
+            if deep_compacted_skipped:
+                print(f"[ContextCompression] build_messages 跳过已深压缩消息: {deep_compacted_skipped} 条")
             return messages
 
     def _load_agents_md_content(self) -> Optional[str]:

core/main_terminal_parts/tools_definition.py

@@ -162,6 +162,7 @@ class MainTerminalToolsDefinitionMixin:
                     # 更新分类为空列表，避免旧缓存
                     if "custom" in self.tool_categories_map:
                         self.tool_categories_map["custom"].tools = []
+                    self._refresh_disabled_tools()
                     return []
 
                 tools: List[Dict] = []
@@ -194,6 +195,7 @@ class MainTerminalToolsDefinitionMixin:
                 # 覆盖 custom 分类的工具列表
                 if "custom" in self.tool_categories_map:
                     self.tool_categories_map["custom"].tools = tool_ids
+                self._refresh_disabled_tools()
 
                 return tools
 

modules/personalization_manager.py

@@ -87,6 +87,8 @@ DEFAULT_PERSONALIZATION_CONFIG: Dict[str, Any] = {
     "shallow_compress_trigger_tool_calls_interval": None,
     "shallow_compress_keep_user_turn_tools": None,  # 保留最近N次用户输入后的工具不压缩（默认3）
     "deep_compress_trigger_tokens": None,
+    "deep_compress_form": "file",  # 深压缩形式：file-生成文件 / inject-直接注入文件全文
+    "deep_compress_behavior": "continue",  # 手动压缩行为：continue-注入并触发请求 / wait-仅插入等待用户
     "silent_tool_disable": True,  # 禁用工具时不向模型插入提示（默认开启）
     "enhanced_tool_display": True,  # 增强工具显示
     "versioning_restore_mode": "overwrite",  # 版本回溯模式固定为 overwrite
@@ -371,6 +373,20 @@ def sanitize_personalization_payload(
             max_value=MAX_COMPRESSION_TRIGGER_TOKENS,
         )
 
+    # 深压缩形式：file（生成文件，引导语提示位置）/ inject（直接注入文件全文）
+    deep_form = data.get("deep_compress_form", base.get("deep_compress_form"))
+    if isinstance(deep_form, str) and deep_form.strip().lower() in ("file", "inject"):
+        base["deep_compress_form"] = deep_form.strip().lower()
+    else:
+        base["deep_compress_form"] = "file"
+
+    # 手动压缩行为：continue（注入并触发请求）/ wait（仅插入等待用户）
+    deep_behavior = data.get("deep_compress_behavior", base.get("deep_compress_behavior"))
+    if isinstance(deep_behavior, str) and deep_behavior.strip().lower() in ("continue", "wait"):
+        base["deep_compress_behavior"] = deep_behavior.strip().lower()
+    else:
+        base["deep_compress_behavior"] = "continue"
+
     if "shallow_compress_trigger_tool_calls_interval" in data:
         base["shallow_compress_trigger_tool_calls_interval"] = _sanitize_optional_int(
             data.get("shallow_compress_trigger_tool_calls_interval"),

server/context.py

@@ -63,6 +63,19 @@ def _set_terminal_workspace_label(terminal: WebTerminal, label: Optional[str]) -
         pass
 
 
+def _apply_workspace_personalization_preferences(terminal: WebTerminal, workspace) -> None:
+    """Apply persisted workspace personalization after policy/workspace resolution."""
+    try:
+        config = load_personalization_config(workspace.data_dir)
+        terminal.apply_personalization_preferences(config)
+        if has_request_context():
+            session["run_mode"] = getattr(terminal, "run_mode", session.get("run_mode"))
+            session["thinking_mode"] = getattr(terminal, "thinking_mode", session.get("thinking_mode"))
+            session["model_key"] = getattr(terminal, "model_key", session.get("model_key"))
+    except Exception as exc:
+        debug_log(f"[Personalization] 应用工作区偏好失败: {exc}")
+
+
 def _ensure_workspace_skills_synced(terminal: WebTerminal, workspace) -> None:
     """
     确保工作区 skills 已按当前个性化配置完成同步。
@@ -300,6 +313,7 @@ def get_user_resources(username: Optional[str] = None, workspace_id: Optional[st
         except Exception as exc:
             debug_log(f"[admin_policy][host_mode] 应用失败: {exc}")
 
+        _apply_workspace_personalization_preferences(terminal, workspace)
         _ensure_workspace_skills_synced(terminal, workspace)
         write_host_workspace_debug(
             "context.get_user_resources.host.return",
@@ -437,6 +451,7 @@ def get_user_resources(username: Optional[str] = None, workspace_id: Optional[st
         except Exception as exc:
             debug_log(f"[admin_policy] 应用失败: {exc}")
 
+    _apply_workspace_personalization_preferences(terminal, workspace)
     _ensure_workspace_skills_synced(terminal, workspace)
     return terminal, workspace
 

server/conversation.py

@@ -1147,7 +1147,7 @@ def restore_conversation_versioning_checkpoint(conversation_id, terminal: WebTer
 @api_login_required
 @with_terminal
 def compress_conversation(conversation_id, terminal: WebTerminal, workspace: UserWorkspace, username: str):
-    """深层压缩指定对话，生成 compact 文件并切换到新对话。"""
+    """深层压缩指定对话（in-place）：生成 compact 文件、标记历史前缀为已压缩，按设置决定是否续接。"""
     try:
         policy = resolve_admin_policy(get_current_user_record())
         if policy.get("ui_blocks", {}).get("block_compress_conversation"):
@@ -1167,36 +1167,34 @@ def compress_conversation(conversation_id, terminal: WebTerminal, workspace: Use
             status_code = 404 if "不存在" in result.get("error", "") else (409 if result.get("in_progress") else 400)
             return jsonify(result), status_code
 
-        new_conversation_id = result["compressed_conversation_id"]
-
-        load_result = terminal.load_conversation(new_conversation_id)
-
+        # in-place 压缩：对话 id 不变。通知前端当前对话内容已变化（历史前缀被标记），刷新展示。
+        load_result = terminal.load_conversation(normalized_id)
         if load_result.get("success"):
             socketio.emit('conversation_list_update', {
                 'action': 'compressed',
-                'conversation_id': new_conversation_id
-            }, room=f"user_{username}")
-            socketio.emit('conversation_changed', {
-                'conversation_id': new_conversation_id,
-                'title': load_result.get('title', '压缩后的对话'),
-                'messages_count': load_result.get('messages_count', 0)
+                'conversation_id': normalized_id
             }, room=f"user_{username}")
             socketio.emit('conversation_loaded', {
-                'conversation_id': new_conversation_id,
+                'conversation_id': normalized_id,
                 'clear_ui': True
             }, room=f"user_{username}")
 
+        compress_behavior = str(result.get("compress_behavior") or "continue").strip().lower()
         response_payload = {
             "success": True,
-            "compressed_conversation_id": new_conversation_id,
+            "in_place": True,
+            "compressed_conversation_id": normalized_id,
             "compact_file": result.get("compact_file"),
             "summary_failed": result.get("summary_failed", False),
             "guide_message": result.get("guide_message"),
+            "compress_form": result.get("compress_form"),
+            "compress_behavior": compress_behavior,
             "load_result": load_result
         }
 
         guide_message = (result.get("guide_message") or "").strip()
-        if guide_message:
+        if guide_message and compress_behavior == "continue":
+            # 继续工作：创建续接任务，自动发送引导语并触发请求（同一对话）。
             try:
                 from .tasks import task_manager
                 workspace_id = session.get("workspace_id") or "default"
@@ -1205,7 +1203,7 @@ def compress_conversation(conversation_id, terminal: WebTerminal, workspace: Use
                     workspace_id,
                     guide_message,
                     images=[],
-                    conversation_id=new_conversation_id,
+                    conversation_id=normalized_id,
                     videos=[],
                     message_source="compression_handoff",
                 )
@@ -1217,6 +1215,21 @@ def compress_conversation(conversation_id, terminal: WebTerminal, workspace: Use
                 debug_log(f"[Compression] 自动发送引导消息失败: {exc}")
                 response_payload["auto_task_started"] = False
                 response_payload["auto_task_error"] = str(exc)
+        elif guide_message and compress_behavior == "wait":
+            # 等待用户：只把引导语作为 user 消息追加进历史，不触发请求。
+            try:
+                terminal.context_manager.add_conversation(
+                    role="user",
+                    content=guide_message,
+                    metadata={"message_source": "compression_handoff"},
+                )
+                response_payload["auto_task_started"] = False
+                response_payload["guide_inserted"] = True
+            except Exception as exc:
+                debug_log(f"[Compression] 追加引导语消息失败: {exc}")
+                response_payload["auto_task_started"] = False
+                response_payload["guide_inserted"] = False
+                response_payload["guide_insert_error"] = str(exc)
         else:
             response_payload["auto_task_started"] = False
 

server/deep_compression.py

@@ -6,8 +6,6 @@ from datetime import datetime
 from pathlib import Path
 from typing import Any, Dict, List, Optional, Tuple
 
-from modules.versioning_manager import ConversationVersioningManager
-
 
 SUMMARY_PROMPT = (
     "由于当前对话过长，系统正在自动压缩。请你基于已有上下文输出一份可继续执行的工作总结，要求：\n"
@@ -18,7 +16,9 @@ SUMMARY_PROMPT = (
     "5) 工具调用中的重要结果/错误与修复\n"
     "6) 当前未完成事项与下一步计划（可直接执行）\n"
     "7) 风险与注意事项\n"
-    "请使用中文，结构清晰，尽量具体，不要省略关键上下文。"
+    "请使用中文，结构清晰，尽量具体，不要省略关键上下文。\n"
+    "不要考虑过往对话，只考虑当前对话任务。\n"
+    "禁止调用任何工具，必须直接输出总结内容。"
 )
 
 GUIDE_USER_MESSAGE_TEMPLATE = "当前对话已经被自动压缩（第{count}次）。请阅读{path}并继续工作"
@@ -68,6 +68,7 @@ def _normalize_deep_compression_records(metadata: Dict[str, Any]) -> List[Dict[s
 
 
 def _build_guide_message(*, compression_index: int, compact_file: str, previous_records: List[Dict[str, Any]]) -> str:
+    """生成文件模式的引导语：仅提示压缩文件位置，由模型自行阅读。"""
     base = GUIDE_USER_MESSAGE_TEMPLATE.format(count=compression_index, path=compact_file)
     if not previous_records:
         return base
@@ -81,6 +82,41 @@ def _build_guide_message(*, compression_index: int, compact_file: str, previous_
     return "\n".join(lines).strip()
 
 
+def _read_compact_file_content(project_path: Path, relative_path: str) -> str:
+    """读取 compact 文件全文，读取失败时返回空串。"""
+    rel = str(relative_path or "").strip()
+    if not rel:
+        return ""
+    try:
+        target = (Path(project_path) / rel).resolve()
+        return target.read_text(encoding="utf-8").strip()
+    except Exception:
+        return ""
+
+
+def _build_inject_guide_message(
+    *,
+    project_path: Path,
+    compression_index: int,
+    current_record: Dict[str, Any],
+    previous_records: List[Dict[str, Any]],
+) -> str:
+    """生成直接注入模式的引导语：把历次压缩文件全文按顺序拼入正文，不提及文件位置。"""
+    lines: List[str] = [f"当前对话已被第{compression_index}次压缩，以下为历次压缩的完整工作总结，请据此继续工作。"]
+    all_records = list(previous_records) + [current_record]
+    for rec in all_records:
+        count = int(rec.get("count") or 0)
+        rel_path = str(rec.get("compact_file") or "").strip()
+        if count <= 0 or not rel_path:
+            continue
+        content = _read_compact_file_content(project_path, rel_path)
+        lines.append("")
+        lines.append(f"第{count}次压缩：")
+        lines.append(content or "（压缩文件内容读取失败）")
+    return "\n".join(lines).strip()
+
+
+
 def _extract_text_only(content: Any) -> str:
     if content is None:
         return ""
@@ -162,10 +198,14 @@ async def _generate_summary(web_terminal, prompt: str, retries: int = 5) -> Tupl
     # build_messages 不会自动附加 user_input，压缩总结必须显式注入
     if prompt and isinstance(prompt, str):
         messages = list(messages) + [{"role": "user", "content": prompt}]
+    # 关键：总结请求必须与"用户正常发一条消息"完全无差别，才能 100% 命中前缀缓存。
+    # 因此 tools 必须照常传入（缺失 tools 字段会改变请求前缀、破坏缓存）。
+    # 模型即便返回 tool_calls 也会被忽略——我们只取 content；prompt 已要求其直接输出总结。
+    tools = web_terminal.define_tools()
     for _ in range(max(1, retries)):
         try:
             response_text = ""
-            async for chunk in web_terminal.api_client.chat(messages, tools=None, stream=False):
+            async for chunk in web_terminal.api_client.chat(messages, tools=tools, stream=False):
                 if not isinstance(chunk, dict):
                     continue
                 choices = chunk.get("choices") or []
@@ -236,6 +276,33 @@ def _write_compact_file(
     return str(file_path.relative_to(project_path))
 
 
+def _mark_history_compacted(history: List[Dict[str, Any]], *, round_index: int, now: str) -> int:
+    """把当前对话历史中所有尚未标记的消息打上 deep_compacted 标记（in-place）。
+
+    深压缩按"整段前缀"处理：本次压缩时，历史里所有还没被标记的消息整体视为已压缩前缀。
+    这天然保证 assistant.tool_calls 与其 tool 响应被一并标记/排除，不会出现配对悬空。
+    原文保留在 metadata 中，持久化与重新加载时照常显示，仅在 build_messages 构建请求时被跳过。
+    返回本次新标记的消息条数。
+    """
+    if not isinstance(history, list):
+        return 0
+    marked = 0
+    for msg in history:
+        if not isinstance(msg, dict):
+            continue
+        metadata = msg.get("metadata")
+        if not isinstance(metadata, dict):
+            metadata = {}
+        if metadata.get("deep_compacted"):
+            continue
+        metadata["deep_compacted"] = True
+        metadata["deep_compacted_round"] = round_index
+        metadata["deep_compacted_at"] = now
+        msg["metadata"] = metadata
+        marked += 1
+    return marked
+
+
 async def run_deep_compression(
     *,
     web_terminal,
@@ -253,12 +320,33 @@ async def run_deep_compression(
     if metadata.get("compression_in_progress"):
         return {"success": False, "error": "对话正在压缩中", "in_progress": True}
 
-    old_title = conv_data.get("title") or "未命名"
-    source_versioning = metadata.get("versioning") if isinstance(metadata.get("versioning"), dict) else {}
-    source_versioning_enabled = bool(source_versioning.get("enabled"))
-    source_tracking_mode = ConversationVersioningManager.normalize_tracking_mode(
-        source_versioning.get("tracking_mode")
-    )
+    # 读取个性化压缩设置：
+    # - compress_form: file（生成文件，引导语提示位置） / inject（把历次压缩文件全文注入引导语）
+    # - compress_behavior: continue（注入引导语并触发请求） / wait（仅注入引导语，等待用户）
+    #   compress_behavior 仅作用于手动压缩；自动深压缩永远继续工作。
+    try:
+        from modules.personalization_manager import load_personalization_config
+        pconfig = load_personalization_config(workspace.data_dir) or {}
+    except Exception:
+        pconfig = {}
+    compress_form = str(pconfig.get("deep_compress_form") or "file").strip().lower()
+    if compress_form not in ("file", "inject"):
+        compress_form = "file"
+    compress_behavior = str(pconfig.get("deep_compress_behavior") or "continue").strip().lower()
+    if compress_behavior not in ("continue", "wait"):
+        compress_behavior = "continue"
+    if mode != "manual":
+        compress_behavior = "continue"
+
+    # in-place 压缩全程操作"当前对话"的内存历史：总结、标记、状态写入都依赖
+    # cm.conversation_history / cm.conversation_metadata。若当前对话不是目标对话，
+    # 必须先切换过去，否则总结会基于错误历史、压缩状态也会写错对话。
+    if getattr(cm, "current_conversation_id", None) != conversation_id:
+        try:
+            web_terminal.load_conversation(conversation_id)
+        except Exception as exc:
+            return {"success": False, "error": f"加载目标对话失败: {exc}"}
+
     compression_count = int(metadata.get("compression_count", 0) or 0)
     previous_records = _normalize_deep_compression_records(metadata)
     previous_max_count = max([int(item.get("count") or 0) for item in previous_records], default=0)
@@ -313,124 +401,102 @@ async def run_deep_compression(
     cm.set_compression_state(
         in_progress=True,
         mode=mode,
-        stage="creating_new_conversation",
+        stage="marking_history",
         job_id=job_id,
     )
 
-    new_conv_id = cm.conversation_manager.create_conversation(
-        project_path=str(workspace.project_path),
-        thinking_mode=bool(metadata.get("thinking_mode", False)),
-        run_mode=metadata.get("run_mode") or ("thinking" if metadata.get("thinking_mode") else "fast"),
-        initial_messages=[],
-        model_key=metadata.get("model_key"),
-        has_images=False,
-        has_videos=False,
-        metadata_overrides={
-            "compression_count": target_count,
-            "title_locked": True,
-            "skip_auto_title_generation": True,
-        }
+    # === in-place 压缩：不创建/切换新对话，只把当前对话历史前缀打上 deep_compacted 标记 ===
+    # 当前对话已在函数开头对齐为目标对话，这里直接对内存历史打标。
+    now_iso = datetime.now().isoformat()
+    marked_count = _mark_history_compacted(
+        cm.conversation_history or [],
+        round_index=target_count,
+        now=now_iso,
     )
+    # 标记后立即持久化历史（标记写在每条消息的 metadata 中）。
+    try:
+        cm.save_current_conversation()
+    except Exception as exc:
+        _emit(sender, "system_message", {"content": f"压缩标记保存失败：{exc}"})
+
+    # 关键：重置 current_context_tokens，避免自动压缩续接后阈值判断仍读到压缩前的大值而陷入死循环。
+    # 真实上下文长度会在下一次 API 响应后被重新写入。
+    try:
+        cm.conversation_manager.update_token_statistics(
+            conversation_id,
+            input_tokens=0,
+            output_tokens=0,
+            total_tokens=0,
+            current_context_tokens=0,
+        )
+    except Exception as exc:
+        _emit(sender, "system_message", {"content": f"压缩后重置上下文统计失败：{exc}"})
+
     current_record = {
         "count": target_count,
         "compact_file": relative_compact_path,
-        "created_at": datetime.now().isoformat(),
+        "created_at": now_iso,
         "source_conversation_id": conversation_id,
-        "compressed_conversation_id": new_conv_id,
+        "compressed_conversation_id": conversation_id,
     }
     all_records = previous_records + [current_record]
-    cm.conversation_manager.update_conversation_metadata(
-        new_conv_id,
-        {
-            "compression_count": target_count,
-            "deep_compression_records": all_records,
-            "last_deep_compression_record": current_record,
-        },
-    )
 
-    if source_versioning_enabled:
-        try:
-            vm = ConversationVersioningManager(
-                project_path=workspace.project_path,
-                data_dir=workspace.data_dir,
-                conversation_id=new_conv_id,
-            )
-            vm_meta = vm.set_enabled(
-                enabled=True,
-                mode="overwrite",
-                tracking_mode=source_tracking_mode,
-            )
-            new_conv_data = cm.conversation_manager.load_conversation(new_conv_id) or {}
-            snapshot_payload = {
-                "conversation_id": new_conv_id,
-                "title": new_conv_data.get("title"),
-                "metadata": new_conv_data.get("metadata") or {},
-                "messages": new_conv_data.get("messages") or [],
-                "message_index": -1,
-                "run_status": "initial",
-            }
-            init_result = vm.ensure_initial_checkpoint(
-                workspace_path=str(workspace.project_path),
-                conversation_snapshot=snapshot_payload,
-                tracking_mode=source_tracking_mode,
-            )
-            init_row = init_result.get("row") or {}
-            last_commit = init_row.get("commit") or vm_meta.get("last_commit")
-            cm.conversation_manager.update_conversation_metadata(
-                new_conv_id,
-                {
-                    "versioning": {
-                        "enabled": True,
-                        "mode": "overwrite",
-                        "tracking_mode": source_tracking_mode,
-                        "updated_at": datetime.now().isoformat(),
-                        "last_commit": last_commit,
-                        "last_input_seq": int(vm_meta.get("last_input_seq") or 0),
-                    }
-                },
-            )
-        except Exception:
-            pass
+    # 构建引导语（按压缩形式）。inject 模式读取历次压缩文件全文，文件仍会生成，只是不提及位置。
+    if compress_form == "inject":
+        guide_message = _build_inject_guide_message(
+            project_path=Path(workspace.project_path),
+            compression_index=target_count,
+            current_record=current_record,
+            previous_records=previous_records,
+        )
+    else:
+        guide_message = _build_guide_message(
+            compression_index=target_count,
+            compact_file=relative_compact_path,
+            previous_records=previous_records,
+        )
 
-    cm.conversation_manager.update_conversation_title(new_conv_id, f"{old_title}对话 压缩后")
-    web_terminal.load_conversation(new_conv_id)
-    guide_message = _build_guide_message(
-        compression_index=target_count,
-        compact_file=relative_compact_path,
-        previous_records=previous_records,
-    )
+    # 更新对话 metadata：压缩记录 + 清理压缩状态标记（同一对话，无切换）。
+    meta_updates = {
+        "compression_count": target_count,
+        "deep_compression_records": all_records,
+        "last_deep_compression_record": current_record,
+        "compression_in_progress": False,
+        "compression_mode": None,
+        "compression_stage": None,
+        "compression_job_id": None,
+        "compression_error": summary_fail_reason,
+        "compression_resume_payload": None,
+        "is_ultra_long_conversation": False,
+    }
+    cm.conversation_manager.update_conversation_metadata(conversation_id, meta_updates)
+    # 同步内存中的 metadata，保证后续在同一对话内的判断读到最新值。
+    try:
+        if getattr(cm, "current_conversation_id", None) == conversation_id and isinstance(cm.conversation_metadata, dict):
+            cm.conversation_metadata.update(meta_updates)
+    except Exception:
+        pass
 
-    # 清理旧对话压缩状态
-    cm.conversation_manager.update_conversation_metadata(
-        conversation_id,
-        {
-            "compression_in_progress": False,
-            "compression_mode": None,
-            "compression_stage": None,
-            "compression_job_id": None,
-            "compression_error": summary_fail_reason,
-            "compression_resume_payload": None,
-            "is_ultra_long_conversation": True,
-        },
-    )
-    _emit(sender, "conversation_resolved", {
-        "source_conversation_id": conversation_id,
-        "conversation_id": new_conv_id,
-        "title": f"{old_title}对话 压缩后",
-        "created": True,
-    })
     _emit(sender, "compression_finished", {
         "source_conversation_id": conversation_id,
-        "conversation_id": new_conv_id,
+        "conversation_id": conversation_id,
         "in_progress": False,
         "compact_file": relative_compact_path,
+        "marked_count": marked_count,
+        "compress_form": compress_form,
+        "compress_behavior": compress_behavior,
         "job_id": job_id,
     })
 
     return {
         "success": True,
-        "compressed_conversation_id": new_conv_id,
+        "in_place": True,
+        "compressed_conversation_id": conversation_id,
         "compact_file": relative_compact_path,
+        "marked_count": marked_count,
+        "compress_form": compress_form,
+        "compress_behavior": compress_behavior,
         "summary_failed": bool(summary_fail_reason),
         "guide_message": guide_message,
     }
+

static/src/app/methods/message.ts

@@ -1057,6 +1057,7 @@ export const messageMethods = {
 
       if (response.ok && result.success) {
         this.compressionStage = 'switching';
+        // in-place 压缩：对话 id 不变，重新加载以刷新“已压缩历史”展示。
         const newId = result.compressed_conversation_id;
         if (newId) {
           await this.loadConversation(newId, { force: true });
@@ -1064,6 +1065,7 @@ export const messageMethods = {
         const guideMessage = (result.guide_message || '').trim();
         const autoTaskStarted = !!result.auto_task_started;
         const autoTaskId = result.auto_task_id;
+        const compressBehavior = String(result.compress_behavior || 'continue');
         if (autoTaskStarted && autoTaskId) {
           const { useTaskStore } = await import('../../stores/task');
           const taskStore = useTaskStore();
@@ -1079,6 +1081,11 @@ export const messageMethods = {
           if (typeof this.monitorShowPendingReply === 'function') {
             this.monitorShowPendingReply();
           }
+        } else if (compressBehavior === 'wait') {
+          // 等待用户：后端已把引导语作为 user 消息追加进历史，这里仅刷新展示，不触发请求。
+          if (newId) {
+            await this.loadConversation(newId, { force: true });
+          }
         } else if (guideMessage) {
           await this.sendAutoUserMessage(guideMessage);
         }
@@ -1089,7 +1096,7 @@ export const messageMethods = {
         debugLog('对话压缩完成:', result);
         this.uiPushToast({
           title: '压缩完成',
-          message: '已生成压缩后的新对话',
+          message: '已压缩较早的对话内容',
           type: 'success',
           duration: 2200
         });

static/src/app/methods/taskPolling.ts

@@ -2427,8 +2427,10 @@ export const taskPollingMethods = {
     this.compressionMode = '';
     this.compressionStage = '';
     this.compressionError = '';
+    // in-place 压缩：对话 id 不变。重新加载该对话以刷新“已压缩历史”的展示；
+    // 若返回的 id 与当前不一致（兼容旧行为）也按其加载。
     const newId = data?.conversation_id;
-    if (newId && newId !== this.currentConversationId) {
+    if (newId) {
       await this.loadConversation(newId, { force: true });
     }
     this.conversationsOffset = 0;
@@ -2436,13 +2438,11 @@ export const taskPollingMethods = {
       await this.loadConversationsList();
     }
     await this.refreshRunningWorkspaceTasks?.();
-    // 压缩会把同一个后台任务从旧 conversation 迁移到新 conversation。
-    // 切换对话时本地轮询会被清理，这里必须立即按新会话恢复轮询，
-    // 否则后续进度需要手动刷新页面才会继续显示。
+    // 续接任务仍在同一对话内运行，恢复轮询以持续显示进度。
     await this.restoreTaskState?.();
     this.uiPushToast({
       title: '压缩完成',
-      message: '已自动切换到压缩后的新对话',
+      message: '已压缩较早的对话内容',
       type: 'success',
       duration: 2400
     });

static/src/components/input/InputComposer.vue

@@ -8,8 +8,10 @@
           :class="{
             'goal-mode-banner--running': goalRunning,
             'goal-mode-banner--done': goalCompleted && !goalRunning,
-            'goal-mode-banner--clickable': goalRunning || goalCompleted
+            'goal-mode-banner--clickable': goalRunning || goalCompleted,
+            'goal-mode-banner--collapsed': goalBannerCollapsed
           }"
+          :title="goalBannerCollapsed ? goalBannerTitle : undefined"
           @click.stop="goalRunning || goalCompleted ? $emit('open-goal-dialog') : null"
         >
           <span class="goal-mode-banner__dot" aria-hidden="true"></span>
@@ -1040,6 +1042,18 @@ const hasRuntimeLayoutExpansion = computed(() => {
 
 const goalCompleted = computed(() => String(props.goalProgress?.status || '').toLowerCase() === 'done');
 
+// 当消息队列非空或 skill 选择菜单展开时，把目标横幅收起为仅圆点，
+// 让队列/菜单紧贴输入框，不再被横幅顶高。队列清空且无 skill 选择时自动恢复。
+const goalBannerCollapsed = computed(
+  () => runtimeQueuedMessagesForRender.value.length > 0 || skillSlashMenuOpen.value
+);
+
+const goalBannerTitle = computed(() => {
+  if (props.goalRunning) return '目标模式运行中';
+  if (goalCompleted.value) return '目标模式完成';
+  return '目标模式已就绪';
+});
+
 const collectComposerVisualHeight = () => {
   const root = inputAreaRoot.value;
   const shell = compactInputShell.value;
@@ -1049,7 +1063,9 @@ const collectComposerVisualHeight = () => {
   const shellRect = shell.getBoundingClientRect();
   let top = shellRect.top;
   let bottom = shellRect.bottom;
-  const nodes = root.querySelectorAll('.runtime-queue-list:not(.runtime-queue-list--empty), .skill-slash-menu, .goal-mode-banner');
+  // 收起态横幅是脱离流、浮在角上的小圆点，不应计入为聊天区预留的高度，
+  // 否则会把消息区可滚动范围顶高。故排除 .goal-mode-banner--collapsed。
+  const nodes = root.querySelectorAll('.runtime-queue-list:not(.runtime-queue-list--empty), .skill-slash-menu, .goal-mode-banner:not(.goal-mode-banner--collapsed)');
   nodes.forEach((node) => {
     if (!(node instanceof HTMLElement)) return;
     const rect = node.getBoundingClientRect();
@@ -1258,6 +1274,13 @@ watch(
   }
 );
 
+// skill 菜单开关会切换目标横幅收起/展开态，需重新上报高度，
+// 否则展开回来时聊天区预留高度不会同步恢复。
+watch(goalBannerCollapsed, async () => {
+  await nextTick();
+  emitComposerHeight();
+});
+
 onMounted(() => {
   if (hasSkillMarkdownLink.value) {
     renderRichEditor();
@@ -1321,6 +1344,30 @@ onBeforeUnmount(() => {
   background: color-mix(in srgb, var(--theme-surface-soft, #fffaf0) 92%, var(--claude-text-tertiary, #a59a86) 8%);
   border: 1px solid var(--theme-chip-border, rgba(118, 103, 84, 0.2));
   user-select: none;
+  transition: gap 0.2s ease, padding 0.2s ease;
+}
+/* 收起态：仅保留圆点与外圈，文字消失、右侧收拢，圆点位置（左侧 padding）不变。
+   关键：切到 absolute 脱离文档流，避免横幅占用一行流高度把队列/skill 菜单顶起来；
+   锚定在输入框上方 6px、左 4px，与展开时的视觉位置一致，圆点位置不变。 */
+.goal-mode-banner--collapsed {
+  position: absolute;
+  left: 4px;
+  bottom: calc(100% + 6px);
+  z-index: 2;
+  margin: 0;
+  gap: 0;
+  padding-right: 10px;
+}
+.goal-mode-banner__text {
+  overflow: hidden;
+  white-space: nowrap;
+  max-width: 200px;
+  opacity: 1;
+  transition: max-width 0.2s ease, opacity 0.18s ease;
+}
+.goal-mode-banner--collapsed .goal-mode-banner__text {
+  max-width: 0;
+  opacity: 0;
 }
 .goal-mode-banner--running {
   color: var(--claude-accent, #da7756);

static/src/components/personalization/ExperienceOnboarding.vue

@@ -5,7 +5,7 @@
         <div class="exp-header">
           <div>
             <div class="title">第一次使用？选择适合您的模式</div>
-            <div class="subtitle">速度、联网与工具范围各不相同，随时可在个人空间切换。</div>
+            <div class="subtitle">速度、联网与工具范围各不相同，随时可在个人空间切换</div>
           </div>
           <button class="confirm-btn" type="button" @click="confirmSelection">确认并开始</button>
         </div>
@@ -57,28 +57,28 @@ const modes = [
     id: 'fast',
     badge: '极速',
     title: '快速回答',
-    desc: '快速回答您的问题，会上网搜索，不会写文件。',
+    desc: '快速回答您的问题，会上网搜索，不会写文件',
     icon: `<svg viewBox="0 0 24 24" stroke="currentColor" fill="none" stroke-width="2"><path d="M13 2 5 14h6l-2 8 10-12h-6z"/></svg>`
   },
   {
     id: 'thinking',
     badge: '思考',
     title: '思考后再答',
-    desc: '经过思考后完成任务，会上网搜索，不会写文件，回复时间较长。',
+    desc: '经过思考后完成任务，会上网搜索，不会写文件，回复时间较长',
     icon: `<svg viewBox="0 0 24 24" stroke="currentColor" fill="none" stroke-width="2"><path d="M12 18V5"/><path d="M15 13a4.17 4.17 0 0 1-3-4 4.17 4.17 0 0 1-3 4"/><path d="M17.598 6.5A3 3 0 1 0 12 5a3 3 0 1 0-5.598 1.5"/><path d="M17.997 5.125a4 4 0 0 1 2.526 5.77"/><path d="M18 18a4 4 0 0 0 2-7.464"/><path d="M19.967 17.483A4 4 0 1 1 12 18a4 4 0 1 1-7.967-.517"/><path d="M6 18a4 4 0 0 1-2-7.464"/><path d="M6.003 5.125a4 4 0 0 0-2.526 5.77"/></svg>`
   },
   {
     id: 'research',
     badge: '研究',
     title: '多步骤研究',
-    desc: '多步骤思考与 20+ 工具完成复杂任务，回复时间可能很长。',
+    desc: '多步骤思考与 20+ 工具完成复杂任务，回复时间可能很长',
     icon: `<svg viewBox="0 0 24 24" stroke="currentColor" fill="none" stroke-width="2"><path d="M9 3v5l-4 9a2 2 0 0 0 1.8 3h10.4A2 2 0 0 0 19 17l-4-9V3"/><path d="M9 8h6"/></svg>`
   },
   {
     id: 'expert',
     badge: '专家',
     title: '全功能探索',
-    desc: '自由探索所有配置选项，适合智能体专家与从业者。',
+    desc: '自由探索所有配置选项，适合智能体专家与从业者',
     icon: `<svg viewBox="0 0 24 24" stroke="currentColor" fill="none" stroke-width="2"><path d="M3 9 12 5l9 4-9 4-9-4Z"/><path d="M6 10v5c0 .6.4 1.2 1 1.4l5 2.1 5-2.1c.6-.2 1-.8 1-1.4v-5"/><path d="M12 13v6"/></svg>`
   }
 ] as const;

static/src/components/personalization/PersonalizationDrawer.vue

@@ -90,7 +90,7 @@
                         <span class="settings-row-copy">
                           <span class="settings-row-title">自动生成对话标题</span>
                           <span class="settings-row-desc"
-                            >默认开启；关闭后标题将沿用首条消息。</span
+                            >默认开启；关闭后标题将沿用首条消息</span
                           >
                         </span>
                         <input
@@ -116,7 +116,7 @@
                         <span class="settings-row-copy">
                           <span class="settings-row-title">新手教程</span>
                           <span class="settings-row-desc"
-                            >通过高亮与说明窗了解主要功能入口和常用设置。</span
+                            >通过高亮与说明窗了解主要功能入口和常用设置</span
                           >
                         </span>
                         <button
@@ -160,7 +160,7 @@
                       <div class="settings-action-row danger-zone">
                         <span class="settings-row-copy">
                           <span class="settings-row-title">退出登录</span>
-                          <span class="settings-row-desc">结束当前账号会话。</span>
+                          <span class="settings-row-desc">结束当前账号会话</span>
                         </span>
                         <button
                           type="button"
@@ -181,7 +181,7 @@
                       <label class="settings-toggle-row">
                         <span class="settings-row-copy">
                           <span class="settings-row-title">启用个性化提示</span>
-                          <span class="settings-row-desc">开启后才会注入您的偏好。</span>
+                          <span class="settings-row-desc">开启后才会注入您的偏好</span>
                         </span>
                         <input
                           type="checkbox"
@@ -278,7 +278,7 @@
                         <span class="settings-row-copy">
                           <span class="settings-row-title">回答时必须考虑的信息</span>
                           <span class="settings-row-desc"
-                            >最多 {{ maxConsiderations }} 条，可拖动排序。</span
+                            >最多 {{ maxConsiderations }} 条，可拖动排序</span
                           >
                         </span>
                         <div class="settings-input-stack wide">
@@ -326,7 +326,7 @@
                       <div class="settings-select-row">
                         <span class="settings-row-copy">
                           <span class="settings-row-title">智能体交流风格</span>
-                          <span class="settings-row-desc">智能体和您交流时使用何种形式。</span>
+                          <span class="settings-row-desc">智能体和您交流时使用何种形式</span>
                         </span>
                         <div
                           class="settings-select-wrap"
@@ -351,7 +351,7 @@
                               :class="{ selected: form.communication_style === 'default' }"
                               @click="selectCommunicationStyle('default')"
                             >
-                              <strong>默认</strong><span>标准 AI 风格。</span
+                              <strong>默认</strong><span>标准 AI 风格</span
                               ><svg viewBox="0 0 24 24"><path d="M5 12.5 9.5 17 19 7" /></svg>
                             </button>
                             <button
@@ -360,7 +360,7 @@
                               :class="{ selected: form.communication_style === 'human_like' }"
                               @click="selectCommunicationStyle('human_like')"
                             >
-                              <strong>拟人</strong><span>像聊天一样模仿人类语言风格。</span
+                              <strong>拟人</strong><span>像聊天一样模仿人类语言风格</span
                               ><svg viewBox="0 0 24 24"><path d="M5 12.5 9.5 17 19 7" /></svg>
                             </button>
                           </div>
@@ -378,7 +378,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">默认模型</span
                           ><span class="settings-row-desc"
-                            >为新对话/登录后首次请求选择首选模型。</span
+                            >为新对话/登录后首次请求选择首选模型</span
                           ></span
                         >
                         <div
@@ -421,7 +421,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">默认运行模式</span
                           ><span class="settings-row-desc"
-                            >登录或新建任务时的初始运行模式。</span
+                            >登录或新建任务时的初始运行模式</span
                           ></span
                         >
                         <div
@@ -460,7 +460,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">思考频率</span
                           ><span class="settings-row-desc"
-                            >连续快速模式运行多少轮后，系统强制切换到思考模型。</span
+                            >连续快速模式运行多少轮后，系统强制切换到思考模型</span
                           ></span
                         >
                         <div class="settings-input-stack wide">
@@ -501,7 +501,7 @@
                       <div class="settings-select-row">
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">主题切换</span
-                          ><span class="settings-row-desc">在经典、明亮和夜间之间切换。</span></span
+                          ><span class="settings-row-desc">在经典、明亮和夜间之间切换</span></span
                         >
                         <div
                           class="settings-select-wrap"
@@ -538,7 +538,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">使用自定义称呼</span
                           ><span class="settings-row-desc"
-                            >对话区域使用个性化设置中的自称和称呼。</span
+                            >对话区域使用个性化设置中的自称和称呼</span
                           ></span
                         ><input
                           type="checkbox"
@@ -560,7 +560,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">增强工具显示</span
                           ><span class="settings-row-desc"
-                            >工具块显示格式化内容，关闭则显示原始 JSON。</span
+                            >工具块显示格式化内容，关闭则显示原始 JSON</span
                           ></span
                         ><input
                           type="checkbox"
@@ -581,7 +581,7 @@
                       <div class="settings-select-row">
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">堆叠块显示模式</span
-                          ><span class="settings-row-desc">选择思考/工具块的显示方式。</span></span
+                          ><span class="settings-row-desc">选择思考/工具块的显示方式</span></span
                         >
                         <div
                           class="settings-select-wrap"
@@ -619,7 +619,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">简略消息显示</span
                           ><span class="settings-row-desc"
-                            >审核、子智能体等紧凑系统消息的显示形式。</span
+                            >审核、子智能体等紧凑系统消息的显示形式</span
                           ></span
                         >
                         <div
@@ -665,7 +665,7 @@
                       <div class="settings-select-row">
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">默认权限</span
-                          ><span class="settings-row-desc">新建对话时的默认权限模式。</span></span
+                          ><span class="settings-row-desc">新建对话时的默认权限模式</span></span
                         >
                         <div
                           class="settings-select-wrap"
@@ -703,7 +703,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">允许根目录创建文件</span
                           ><span class="settings-row-desc"
-                            >关闭则禁止在工作区根目录创建文件。</span
+                            >关闭则禁止在工作区根目录创建文件</span
                           ></span
                         ><input
                           type="checkbox"
@@ -725,7 +725,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">AGENTS.md 自动注入</span
                           ><span class="settings-row-desc"
-                            >工作区根目录存在 AGENTS.md 时自动注入系统提示词。</span
+                            >工作区根目录存在 AGENTS.md 时自动注入系统提示词</span
                           ></span
                         ><input
                           type="checkbox"
@@ -752,7 +752,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">审核智能体主动取证</span
                           ><span class="settings-row-desc"
-                            >开启后审核智能体可运行只读命令（查看文件、跑测试）来核实目标是否达成；关闭则仅依据对话内容判断。</span
+                            >开启后可运行只读命令核实目标，关闭则仅依据对话判断</span
                           ></span
                         ><input
                           type="checkbox"
@@ -775,7 +775,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">最大自动续命轮数</span
                           ><span class="settings-row-desc"
-                            >目标模式下，主模型停下后最多自动继续的轮数（1-100）。</span
+                            >主模型停下后最多自动继续 1-100 轮</span
                           ></span
                         >
                         <input
@@ -797,7 +797,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">启用累计 token 上限</span
                           ><span class="settings-row-desc"
-                            >开启后，目标模式累计消耗（输入+输出）超过下方上限即停止。</span
+                            >累计输入输出超过上限时停止目标模式</span
                           ></span
                         ><input
                           type="checkbox"
@@ -816,7 +816,7 @@
                       <div v-if="goalTokenLimitEnabled" class="settings-select-row">
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">累计 token 上限</span
-                          ><span class="settings-row-desc">达到该累计消耗即停止目标模式。</span></span
+                          ><span class="settings-row-desc">达到该累计消耗即停止目标模式</span></span
                         >
                         <input
                           type="number"
@@ -843,7 +843,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">最近对话提示</span
                           ><span class="settings-row-desc"
-                            >把当前工作区最近若干个非空对话注入系统提示词。</span
+                            >把当前工作区最近若干个非空对话注入系统提示词</span
                           ></span
                         ><input
                           type="checkbox"
@@ -883,7 +883,7 @@
                         <div class="settings-group-title">
                           <span class="settings-row-title">上下文压缩策略</span
                           ><span class="settings-row-desc"
-                            >可分别控制自动浅层压缩与自动深层压缩。</span
+                            >可分别控制自动浅层压缩与自动深层压缩</span
                           >
                         </div>
                         <label class="settings-toggle-row inner"
@@ -995,6 +995,50 @@
                               "
                           /></label>
                         </div>
+                        <label class="settings-toggle-row inner"
+                          ><span class="settings-row-copy"
+                            ><span class="settings-row-title">深压缩直接注入</span
+                            ><span class="settings-row-desc"
+                              >开启后直接注入历次压缩全文，关闭则只提示文件位置</span
+                            ></span
+                          ><input
+                            type="checkbox"
+                            :checked="form.deep_compress_form === 'inject'"
+                            @change="
+                              personalization.updateField({
+                                key: 'deep_compress_form',
+                                value: $event.target.checked ? 'inject' : 'file'
+                              })
+                            " /><span class="fancy-check" aria-hidden="true"
+                            ><svg viewBox="0 0 64 64">
+                              <path
+                                d="M 0 16 V 56 A 8 8 90 0 0 8 64 H 56 A 8 8 90 0 0 64 56 V 8 A 8 8 90 0 0 56 0 H 8 A 8 8 90 0 0 0 8 V 16 L 32 48 L 64 16 V 8 A 8 8 90 0 0 56 0 H 8 A 8 8 90 0 0 0 8 V 56 A 8 8 90 0 0 8 64 H 56 A 8 8 90 0 0 64 56 V 16"
+                                pathLength="575.0541381835938"
+                                class="fancy-path"
+                              ></path></svg></span
+                        ></label>
+                        <label class="settings-toggle-row inner"
+                          ><span class="settings-row-copy"
+                            ><span class="settings-row-title">手动压缩后等待用户</span
+                            ><span class="settings-row-desc"
+                              >开启后手动压缩只插入引导语并等待输入，关闭则自动继续工作</span
+                            ></span
+                          ><input
+                            type="checkbox"
+                            :checked="form.deep_compress_behavior === 'wait'"
+                            @change="
+                              personalization.updateField({
+                                key: 'deep_compress_behavior',
+                                value: $event.target.checked ? 'wait' : 'continue'
+                              })
+                            " /><span class="fancy-check" aria-hidden="true"
+                            ><svg viewBox="0 0 64 64">
+                              <path
+                                d="M 0 16 V 56 A 8 8 90 0 0 8 64 H 56 A 8 8 90 0 0 64 56 V 8 A 8 8 90 0 0 56 0 H 8 A 8 8 90 0 0 0 8 V 16 L 32 48 L 64 16 V 8 A 8 8 90 0 0 56 0 H 8 A 8 8 90 0 0 0 8 V 56 A 8 8 90 0 0 8 64 H 56 A 8 8 90 0 0 64 56 V 16"
+                                pathLength="575.0541381835938"
+                                class="fancy-path"
+                              ></path></svg></span
+                        ></label>
                         <div class="settings-inline-actions right">
                           <button
                             type="button"
@@ -1012,7 +1056,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">静默禁用工具</span
                           ><span class="settings-row-desc"
-                            >禁用工具时不再注入提示消息，模型不会感知被禁用项。</span
+                            >禁用工具时不再注入提示消息，模型不会感知被禁用项</span
                           ></span
                         ><input
                           type="checkbox"
@@ -1034,7 +1078,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">工具意图提示</span
                           ><span class="settings-row-desc"
-                            >调用工具时先用简短文字告诉你要做什么。</span
+                            >调用工具时先用简短文字告诉你要做什么</span
                           ></span
                         ><input
                           type="checkbox"
@@ -1056,7 +1100,7 @@
                         ><span class="settings-row-copy"
                           ><span class="settings-row-title">Skill 提示系统</span
                           ><span class="settings-row-desc"
-                            >检测到特定关键词时自动提示模型阅读相关 skill。</span
+                            >检测到特定关键词时自动提示模型阅读相关 skill</span
                           ></span
                         ><input
                           type="checkbox"
@@ -1078,7 +1122,7 @@
                         <div class="settings-group-title">
                           <span class="settings-row-title">强约束系统</span
                           ><span class="settings-row-desc"
-                            >仅对个人空间中已启用的 skill 生效。</span
+                            >仅对个人空间中已启用的 skill 生效</span
                           >
                         </div>
                         <label class="settings-toggle-row inner"
@@ -1158,7 +1202,7 @@
                         <div class="settings-group-title">
                           <span class="settings-row-title">可用 Skills</span
                           ><span class="settings-row-desc"
-                            >勾选后会注入 system prompt，并同步到工作区的 skills/ 目录。</span
+                            >勾选后会注入 system prompt，并同步到工作区的 skills/ 目录</span
                           >
                         </div>
                         <div class="settings-check-grid">
@@ -1186,7 +1230,7 @@
                         <div class="settings-group-title">
                           <span class="settings-row-title">默认禁用工具类别</span
                           ><span class="settings-row-desc"
-                            >选择后，这些类别在新任务中保持关闭。</span
+                            >选择后，这些类别在新任务中保持关闭</span
                           >
                         </div>
                         <div class="settings-check-grid">
@@ -1222,7 +1266,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">图片压缩</span
                           ><span class="settings-row-desc"
-                            >发送图片或调用 view_image 时自动等比缩放。</span
+                            >发送图片或调用 view_image 时自动等比缩放</span
                           ></span
                         >
                         <div
@@ -1271,7 +1315,7 @@
                             <p class="usage-summary-eyebrow">对话用量</p>
                             <h3>用量统计</h3>
                             <p class="usage-summary-desc">
-                              累计统计所有对话的输入/输出 Token、对话数量、用户消息与工具调用。
+                              累计统计所有对话的输入/输出 Token、对话数量、用户消息与工具调用
                             </p>
                           </div>
                         </div>
@@ -1334,7 +1378,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">MCP 服务器管理</span
                           ><span class="settings-row-desc"
-                            >统一配置 MCP Server，集中管理工具扩展能力。</span
+                            >统一配置 MCP Server，集中管理工具扩展能力</span
                           ></span
                         ><button
                           type="button"
@@ -1348,7 +1392,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">管理员监控入口</span
                           ><span class="settings-row-desc"
-                            >展示配额趋势、容器运行、项目存储与上传安全。</span
+                            >展示配额趋势、容器运行、项目存储与上传安全</span
                           ></span
                         ><button
                           type="button"
@@ -1361,7 +1405,7 @@
                       <div class="settings-action-row">
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">API 管理</span
-                          ><span class="settings-row-desc">管理 API 调用与账户。</span></span
+                          ><span class="settings-row-desc">管理 API 调用与账户</span></span
                         ><button
                           type="button"
                           class="settings-secondary-button"
@@ -1374,7 +1418,7 @@
                         <span class="settings-row-copy"
                           ><span class="settings-row-title">自定义工具管理</span
                           ><span class="settings-row-desc"
-                            >在线创建/编辑自定义工具文件。</span
+                            >在线创建/编辑自定义工具文件</span
                           ></span
                         ><button
                           type="button"
@@ -1615,14 +1659,14 @@ const permissionModeOptions: Array<{
   label: string;
   desc: string;
 }> = [
-  { id: 'readonly', label: '只读', desc: '仅允许读取/检索类工具，修改操作将被拒绝。' },
-  { id: 'approval', label: '批准', desc: '对工作区文件进行修改的工具需人工批准后执行。' },
+  { id: 'readonly', label: '只读', desc: '仅允许读取/检索类工具，修改操作将被拒绝' },
+  { id: 'approval', label: '批准', desc: '对工作区文件进行修改的工具需人工批准后执行' },
   {
     id: 'auto_approval',
     label: '自动审核',
-    desc: '工作区内写入直通；高风险操作由后台审核智能体自动审批。'
+    desc: '工作区内写入直通；高风险操作由后台审核智能体自动审批'
   },
-  { id: 'unrestricted', label: '无限制', desc: '工具按常规流程直接执行。' }
+  { id: 'unrestricted', label: '无限制', desc: '工具按常规流程直接执行' }
 ];
 
 const policyStore = usePolicyStore();
@@ -2143,7 +2187,7 @@ const compactMessageDisplayOptions = [
   {
     id: 'brief',
     label: '简略信息',
-    desc: '仅以一行横线概要替代（如「目标审核完成」）',
+    desc: '用一行横线概要替代系统消息',
     value: 'brief' as const
   }
 ];

static/src/stores/personalization.ts

@@ -43,6 +43,8 @@ interface PersonalForm {
   shallow_compress_max_replace_per_round: number | null;
   shallow_compress_trigger_tool_calls_interval: number | null;
   deep_compress_trigger_tokens: number | null;
+  deep_compress_form: 'file' | 'inject';
+  deep_compress_behavior: 'continue' | 'wait';
   agents_md_auto_inject: boolean;
   allow_root_file_creation: boolean;
   theme: 'classic' | 'light' | 'dark';
@@ -134,6 +136,8 @@ const defaultForm = (): PersonalForm => ({
   shallow_compress_max_replace_per_round: null,
   shallow_compress_trigger_tool_calls_interval: null,
   deep_compress_trigger_tokens: null,
+  deep_compress_form: 'file',
+  deep_compress_behavior: 'continue',
   agents_md_auto_inject: false,
   allow_root_file_creation: false,
   theme: loadCachedTheme(),
@@ -339,6 +343,8 @@ export const usePersonalizationStore = defineStore('personalization', {
         deep_compress_trigger_tokens: this.normalizeCompressionNumber(
           data.deep_compress_trigger_tokens
         ),
+        deep_compress_form: data.deep_compress_form === 'inject' ? 'inject' : 'file',
+        deep_compress_behavior: data.deep_compress_behavior === 'wait' ? 'wait' : 'continue',
         agents_md_auto_inject: !!data.agents_md_auto_inject,
         allow_root_file_creation: !!data.allow_root_file_creation,
         theme: ['classic', 'light', 'dark'].includes(data.theme) ? data.theme : fallbackTheme,

test/test_server_refactor_smoke.py

@@ -51,6 +51,75 @@ class ServerRefactorSmokeTest(unittest.TestCase):
         self.assertTrue(callable(conversation.compute_workspace_storage))
         self.assertTrue(callable(conversation.collect_upload_events))
 
+    def test_custom_tools_refresh_disabled_after_dynamic_load(self):
+        from core.main_terminal_parts.tools_definition import MainTerminalToolsDefinitionMixin
+
+        class Registry:
+            def reload(self):
+                return [
+                    {
+                        "id": "demo_tool",
+                        "description": "Demo tool",
+                        "parameters": {"type": "object", "properties": {}},
+                    }
+                ]
+
+        class Terminal(MainTerminalToolsDefinitionMixin):
+            custom_tools_enabled = True
+            user_role = "admin"
+            custom_tool_registry = Registry()
+
+            def __init__(self):
+                self.tool_categories_map = {
+                    "custom": SimpleNamespace(
+                        tools=[],
+                        default_enabled=True,
+                        silent_when_disabled=False,
+                    )
+                }
+                self.tool_category_states = {"custom": False}
+                self.admin_forced_category_states = {}
+                self.disabled_tools = set()
+
+            def _refresh_disabled_tools(self):
+                disabled = set()
+                for key, category in self.tool_categories_map.items():
+                    if not self.tool_category_states.get(key, category.default_enabled):
+                        disabled.update(category.tools)
+                self.disabled_tools = disabled
+
+        terminal = Terminal()
+        custom_tools = terminal._build_custom_tools()
+
+        self.assertEqual(custom_tools[0]["function"]["name"], "demo_tool")
+        self.assertEqual(terminal.tool_categories_map["custom"].tools, ["demo_tool"])
+        self.assertIn("demo_tool", terminal.disabled_tools)
+
+    def test_context_applies_workspace_personalization_preferences(self):
+        import server.context as context
+
+        calls = []
+
+        class Terminal:
+            run_mode = "fast"
+            thinking_mode = False
+            model_key = None
+
+            def apply_personalization_preferences(self, config):
+                calls.append(config)
+
+        workspace = SimpleNamespace(data_dir="/tmp/workspace-data")
+        original_loader = context.load_personalization_config
+        try:
+            context.load_personalization_config = lambda data_dir: {
+                "disabled_tool_categories": ["custom"]
+            }
+            context._apply_workspace_personalization_preferences(Terminal(), workspace)
+        finally:
+            context.load_personalization_config = original_loader
+
+        self.assertEqual(calls, [{"disabled_tool_categories": ["custom"]}])
+
 
 if __name__ == "__main__":
     unittest.main()