feat(v3): T27 会话式智能体（多轮上下文/停止/对话式 UI，对齐 dsh 范式）

- ToolLoop 增 history 参数（既往轮次折叠为对话上下文，近 6 轮）
- 会话制：AgentSession/SessionStore 持久化 agent_runs/sessions/{sid}.json，
  /agent/sessions CRUD + /agent 带 session_id（继承会话工作区与执行者配置，busy 并发控制）
- POST /agent/{id}/cancel：取消运行中任务
- AgentView 重构为对话式：会话列表 + 居中消息流（用户蓝气泡/助手白卡）+ 底部 composer
  （工作区/执行者/命令 chips，Enter 发送，运行中红色停止钮），工具过程折叠收纳
- 工具步数统计统一至事件写入层并透出 status.tool_calls
- fix(tests): 会话存储测试隔离，防测试数据泄漏进真实 sessions 目录
- 测试 +4，全量 281 passed

gateway/agent.py

@@ -167,6 +167,7 @@ class AgentRunInfo:
     workspace: str = ""                # 本次运行使用的工作区根目录（绝对路径）
     executor_model: str = ""           # 两级模式：执行者模型名（空 = 单模型模式）
     mode: str = "single"               # single | dual
+    tool_calls: int = 0                # 本次运行的工具调用步数
     asyncio_task: Optional[asyncio.Task] = field(default=None, repr=False)
 
     def to_dict(self) -> Dict[str, Any]:
@@ -186,6 +187,7 @@ class AgentRunInfo:
             "workspace": self.workspace,
             "executor_model": self.executor_model,
             "mode": self.mode,
+            "tool_calls": self.tool_calls,
         }
 
 
@@ -231,12 +233,16 @@ class AgentService:
                   max_rounds: int = 8, token_cap: int = 0,
                   allow_shell: bool = False, shell_timeout_s: int = 20,
                   executor_chat: Any = None,
-                  max_handoffs: int = DEFAULT_MAX_HANDOFFS) -> None:
+                  max_handoffs: int = DEFAULT_MAX_HANDOFFS,
+                  session: Optional["AgentSession"] = None) -> None:
         """执行智能体任务（由调用方包成后台协程）。
 
         executor_chat 为空 = 单模型模式（chat 全程包办）；
         提供时进入两级模式：chat 作规划者，executor_chat 作执行者（D7）。
+        session 提供时：既往轮次作为对话上下文，完成后把本轮追加进会话。
         """
+        history = self._history_from_session(session)
+
         try:
             if executor_chat is not None:
                 result = await self.run_dual(
@@ -249,7 +255,8 @@ class AgentService:
                                        shell_timeout_s=shell_timeout_s)
                 loop = ToolLoop(tools, chat, max_rounds=max_rounds, token_cap=token_cap,
                                 on_event=self._make_event_writer(info))
-                result = await loop.run(info.task, system=AGENT_SYSTEM_PROMPT)
+                result = await loop.run(info.task, system=AGENT_SYSTEM_PROMPT,
+                                        history=history)
             self._apply_result(info, result)
         except Exception as exc:  # pragma: no cover
             info.state = STATE_FAILED
@@ -259,6 +266,33 @@ class AgentService:
         finally:
             info.finished_at = time.time()
             self._write_status(info)
+            if session is not None:
+                session.data["turns"].append({
+                    "request_id": info.request_id,
+                    "task": info.task,
+                    "response": info.response,
+                    "state": info.state,
+                    "tool_calls": info.tool_calls,
+                    "tokens": info.prompt_tokens + info.completion_tokens,
+                    "error": info.error,
+                    "ts": info.finished_at,
+                })
+                get_session_store().save(session)
+
+    @staticmethod
+    def _history_from_session(session: Optional["AgentSession"],
+                              max_turns: int = 6,
+                              max_chars: int = 1500) -> List[Dict[str, Any]]:
+        """把会话既往轮次折叠成对话上下文（不含工具细节）。"""
+        if session is None:
+            return []
+        turns = [t for t in session.data.get("turns", [])
+                 if t.get("state") == STATE_DONE and t.get("response")]
+        out: List[Dict[str, Any]] = []
+        for t in turns[-max_turns:]:
+            out.append({"role": "user", "content": str(t["task"])[:max_chars]})
+            out.append({"role": "assistant", "content": str(t["response"])[:max_chars]})
+        return out
 
     def _apply_result(self, info: AgentRunInfo, result: Dict[str, Any]) -> None:
         """把循环结果落到运行状态（单/两级模式共用）。"""
@@ -413,6 +447,8 @@ class AgentService:
     # ---------- 事件 ----------
     def _make_event_writer(self, info: AgentRunInfo):
         def _on_event(ev: Dict[str, Any]) -> None:
+            if ev.get("type") == "tool_call":
+                info.tool_calls += 1        # 工具步数统计（单/两级模式统一在此）
             self._append_event(info, ev)
         return _on_event
 
@@ -509,3 +545,115 @@ def reset_agent_service() -> None:
 
 def new_request_id() -> str:
     return "ag" + uuid.uuid4().hex[:10]
+
+
+# ─────────────────────────────────────────────────────────────────────────────
+# 会话（dsh 式：工作区内多轮对话，持久化到磁盘）
+# ─────────────────────────────────────────────────────────────────────────────
+SESSIONS_DIR = Path("agent_runs") / "sessions"
+
+
+class AgentSession:
+    """一个智能体会话：多轮任务 + 配置快照（磁盘持久化）。"""
+
+    def __init__(self, data: Dict[str, Any]):
+        self.data = data
+
+    @classmethod
+    def new(cls, sid: str, title: str, workspace: str,
+            pool_id: str = "", executor_pool_id: str = "") -> "AgentSession":
+        now = time.time()
+        return cls({
+            "id": sid, "title": title[:24] or "新会话", "workspace": workspace,
+            "pool_id": pool_id, "executor_pool_id": executor_pool_id,
+            "created_at": now, "updated_at": now, "busy": False,
+            "turns": [],   # [{request_id, task, response, state, tool_calls, tokens}]
+        })
+
+    def to_dict(self) -> Dict[str, Any]:
+        return dict(self.data)
+
+    def view(self, include_turns: bool = True) -> Dict[str, Any]:
+        out = self.to_dict()
+        if not include_turns:
+            out["turns"] = len(self.data.get("turns", []))
+        return out
+
+
+class SessionStore:
+    """会话注册表（内存索引 + sessions/{sid}.json 持久化）。"""
+
+    def __init__(self, root: Path = SESSIONS_DIR):
+        self.root = Path(root)
+        self.root.mkdir(parents=True, exist_ok=True)
+        self._cache: Dict[str, AgentSession] = {}
+
+    def _path(self, sid: str) -> Path:
+        return self.root / f"{sid}.json"
+
+    def create(self, title: str, workspace: str,
+               pool_id: str = "", executor_pool_id: str = "") -> AgentSession:
+        sid = "as" + uuid.uuid4().hex[:10]
+        sess = AgentSession.new(sid, title or "新会话", workspace, pool_id, executor_pool_id)
+        self._cache[sid] = sess
+        self._save(sess)
+        return sess
+
+    def get(self, sid: str) -> Optional[AgentSession]:
+        if sid in self._cache:
+            return self._cache[sid]
+        p = self._path(sid)
+        if not p.exists():
+            return None
+        try:
+            sess = AgentSession(json.loads(p.read_text(encoding="utf-8")))
+            self._cache[sid] = sess
+            return sess
+        except (json.JSONDecodeError, OSError):
+            return None
+
+    def list(self) -> List[Dict[str, Any]]:
+        out = []
+        for p in sorted(self.root.glob("*.json"),
+                        key=lambda x: x.stat().st_mtime, reverse=True):
+            try:
+                out.append(json.loads(p.read_text(encoding="utf-8")))
+            except (json.JSONDecodeError, OSError):
+                continue
+        return out
+
+    def delete(self, sid: str) -> bool:
+        self._cache.pop(sid, None)
+        p = self._path(sid)
+        if p.exists():
+            p.unlink()
+            return True
+        return False
+
+    def save(self, sess: AgentSession) -> None:
+        self._cache[sess.data["id"]] = sess
+        self._save(sess)
+
+    def _save(self, sess: AgentSession) -> None:
+        sess.data["updated_at"] = time.time()
+        try:
+            self._path(sess.data["id"]).write_text(
+                json.dumps(sess.data, ensure_ascii=False, indent=2), encoding="utf-8")
+        except OSError:
+            pass
+
+
+_session_store: Optional[SessionStore] = None
+
+
+def get_session_store() -> SessionStore:
+    global _session_store
+    if _session_store is None:
+        _session_store = SessionStore()
+    return _session_store
+
+
+def reset_session_store() -> None:
+    """测试用。"""
+    global _session_store
+    _session_store = None

gateway/api.py

@@ -501,12 +501,13 @@ try:
 
     @app.post("/agent", tags=["agent"])
     async def agent_run(req: dict):
-        """提交智能体任务：{"task", "pool_id"?, "workspace"?}。
+        """提交智能体任务：{"task", "pool_id"?, "workspace"?, "executor_pool_id"?, "session_id"?}。
 
-        workspace 为用户选择的工作目录（绝对路径）；缺省用设置里的 agent.workspace_dir。
+        workspace 为用户选择的工作目录；缺省继承会话目录，再缺省用设置默认值。
+        session_id 提供时任务在会话内执行（多轮上下文 + 轮次记录）。
         立即返回 request_id；过程事件经 GET /agent/{id}/stream (SSE) 推送。
         """
-        from gateway.agent import get_agent_service, new_request_id
+        from gateway.agent import get_agent_service, get_session_store, new_request_id
         from router_system.tools import WorkspaceTools
 
         task = str((req or {}).get("task") or "").strip()
@@ -518,7 +519,23 @@ try:
 
         s = settings_store().to_dict()
         agent_cfg = s.get("agent", {})
+
+        # 会话（可选）：须存在且空闲；工作区缺省继承会话目录
+        session = None
+        session_id = str((req or {}).get("session_id") or "").strip()
+        if session_id:
+            session = get_session_store().get(session_id)
+            if session is None:
+                raise HTTPException(status_code=404, detail=f"会话不存在: {session_id}")
+            if session.data.get("busy"):
+                raise HTTPException(status_code=409, detail="该会话有任务正在运行，请稍候")
+            # 会话级配置继承（创建时指定，后续轮次沿用）
+            if not pool_id:
+                pool_id = str(session.data.get("pool_id") or "")
+
         ws_raw = str((req or {}).get("workspace") or "").strip()
+        if not ws_raw and session is not None:
+            ws_raw = str(session.data.get("workspace") or "")
         if ws_raw:
             ws_path = Path(ws_raw)
             if not ws_path.exists():
@@ -533,6 +550,8 @@ try:
 
         # 两级模式（D7）：显式指定执行者（本地小模型）时，规划=chat、执行=executor_chat
         executor_pool_id = str((req or {}).get("executor_pool_id") or "").strip()
+        if not executor_pool_id and session is not None:
+            executor_pool_id = str(session.data.get("executor_pool_id") or "")
         executor_chat = None
         executor_model = ""
         if executor_pool_id:
@@ -565,8 +584,11 @@ try:
         if info is None:
             raise HTTPException(status_code=503, detail="智能体同时运行任务已达上限")
 
-        s = settings_store().to_dict()
+        if session is not None:
-        agent_cfg = s.get("agent", {})
+            session.data["busy"] = True
+            if not session.data.get("workspace"):
+                session.data["workspace"] = workspace_dir
+            get_session_store().save(session)
 
         async def _run():
             try:
@@ -579,6 +601,7 @@ try:
                     shell_timeout_s=int(agent_cfg.get("shell_timeout_s", 20)),
                     executor_chat=executor_chat,
                     max_handoffs=int(agent_cfg.get("max_handoffs", 2)),
+                    session=session,
                 )
             except Exception as exc:
                 import traceback
@@ -587,11 +610,65 @@ try:
                 info.error = str(exc)
                 info.finished_at = __import__("time").time()
                 service._write_status(info)
+            finally:
+                if session is not None:
+                    session.data["busy"] = False
+                    get_session_store().save(session)
 
         info.asyncio_task = asyncio.create_task(_run())
         return {"request_id": request_id, "status": "running", "model": model,
                 "workspace": workspace_dir, "mode": mode,
-                "executor_model": executor_model}
+                "executor_model": executor_model, "session_id": session_id or None}
+
+    @app.post("/agent/{request_id}/cancel", tags=["agent"])
+    async def agent_cancel(request_id: str):
+        """停止运行中的智能体任务。"""
+        from gateway.agent import get_agent_service
+        service = get_agent_service()
+        info = service.get(request_id)
+        if info is None:
+            raise HTTPException(status_code=404, detail=f"智能体任务不存在: {request_id}")
+        if info.state != "running":
+            return {"ok": False, "detail": f"任务已结束（{info.state}）"}
+        if info.asyncio_task is not None:
+            info.asyncio_task.cancel()
+        info.state = "failed"
+        info.error = "cancelled_by_user"
+        info.finished_at = __import__("time").time()
+        service._write_status(info)
+        return {"ok": True}
+
+    # ---------------- 会话（dsh 式多轮对话） ----------------
+    @app.post("/agent/sessions", tags=["agent"])
+    async def agent_session_create(req: dict = None):
+        """创建会话：{"title"?, "workspace"?, "pool_id"?, "executor_pool_id"?}"""
+        from gateway.agent import get_session_store
+        r = req or {}
+        sess = get_session_store().create(
+            title=str(r.get("title") or "").strip(),
+            workspace=str(r.get("workspace") or "").strip(),
+            pool_id=str(r.get("pool_id") or ""),
+            executor_pool_id=str(r.get("executor_pool_id") or ""))
+        return sess.view()
+
+    @app.get("/agent/sessions", tags=["agent"])
+    async def agent_sessions():
+        """会话列表（按更新时间倒序）。"""
+        from gateway.agent import get_session_store
+        return get_session_store().list()
+
+    @app.get("/agent/sessions/{sid}", tags=["agent"])
+    async def agent_session_detail(sid: str):
+        from gateway.agent import get_session_store
+        sess = get_session_store().get(sid)
+        if sess is None:
+            raise HTTPException(status_code=404, detail=f"会话不存在: {sid}")
+        return sess.view()
+
+    @app.delete("/agent/sessions/{sid}", tags=["agent"])
+    async def agent_session_delete(sid: str):
+        from gateway.agent import get_session_store
+        return {"ok": get_session_store().delete(sid)}
 
     @app.get("/agent/fs", tags=["agent"])
     async def agent_fs_browse(path: str = ""):

gateway/static/assets/MetricsView-C48cZGC4.js

@@ -1 +1 @@
-import{A as e,D as t,G as n,I as r,L as i,N as a,O as o,P as s,V as c,W as l,j as u,k as d,s as f,t as p}from"./index-8a-EFu_T.js";var m={class:`metrics-view`},h={key:0,class:`loading`},g={key:1,class:`error`},_={class:`card-grid`},v={class:`metric-card`},y={class:`kv-list`},b={class:`metric-card`},x={class:`kv-list`},S={key:0,class:`metric-card highlight`},C={class:`kv-list`},w={key:0},T={key:1},E={key:1,class:`metric-card`},D={class:`by-model`},O={class:`mono`},k={key:2,class:`metric-card review-card`},A={class:`review-stats`},j={class:`stat-item`},M={class:`stat-num`},N={class:`stat-item`},P={class:`stat-num`},F={key:0,class:`progress-wrap`},I={class:`review-rate`},L={class:`raw-json`},R=p(a({__name:`MetricsView`,setup(a){let p=c(null),R=c(!1),z=c(``),B=o(()=>p.value?.v2?.by_model||null);async function V(){R.value=!0,z.value=``;try{p.value=await f()}catch(e){z.value=e instanceof Error?e.message:`指标加载失败，请检查后端服务`}finally{R.value=!1}}return s(V),(a,o)=>(r(),u(`div`,m,[d(`header`,{class:`metrics-header`},[o[0]||=d(`h2`,null,`系统指标`,-1),d(`button`,{class:`refresh`,onClick:V},`🔄 刷新`)]),R.value?(r(),u(`div`,h,`加载中…`)):z.value?(r(),u(`div`,g,n(z.value),1)):p.value?(r(),u(t,{key:2},[d(`div`,_,[d(`div`,v,[o[1]||=d(`h3`,null,`路由器（v1）`,-1),d(`div`,y,[(r(!0),u(t,null,i(p.value.router,(e,i)=>(r(),u(t,{key:i},[d(`span`,null,n(i),1),d(`b`,null,n(e),1)],64))),128))])]),d(`div`,b,[o[2]||=d(`h3`,null,`缓存`,-1),d(`div`,x,[(r(!0),u(t,null,i(p.value.cache,(e,i)=>(r(),u(t,{key:i},[d(`span`,null,n(i),1),d(`b`,null,n(e),1)],64))),128))])]),p.value.v2?(r(),u(`div`,S,[o[3]||=d(`h3`,null,`协作管线（v2）`,-1),d(`div`,C,[(r(!0),u(t,null,i(p.value.v2,(i,a)=>(r(),u(t,{key:a},[a===`by_model`?e(``,!0):(r(),u(`span`,w,n(a),1)),a===`by_model`?e(``,!0):(r(),u(`b`,T,n(i),1))],64))),128))])])):e(``,!0),B.value&&Object.keys(B.value).length?(r(),u(`div`,E,[o[5]||=d(`h3`,null,`按模型分账（token / 成本）`,-1),d(`table`,D,[o[4]||=d(`thead`,null,[d(`tr`,null,[d(`th`,null,`模型`),d(`th`,null,`次数`),d(`th`,null,`入`),d(`th`,null,`出`),d(`th`,null,`成本 $`)])],-1),d(`tbody`,null,[(r(!0),u(t,null,i(B.value,(e,t)=>(r(),u(`tr`,{key:t},[d(`td`,O,n(t),1),d(`td`,null,n(e.requests),1),d(`td`,null,n(e.input_tokens),1),d(`td`,null,n(e.output_tokens),1),d(`td`,null,n(e.cost_est_usd),1)]))),128))])]),o[6]||=d(`p`,{class:`hint`},`单价来自模型池条目（$/1M tokens）；经典设置下的模型成本不计入。`,-1)])):e(``,!0),p.value.review?(r(),u(`div`,k,[o[9]||=d(`h3`,null,`人工检验`,-1),d(`div`,A,[d(`div`,j,[d(`span`,M,n(p.value.review.pending),1),o[7]||=d(`span`,{class:`stat-label`},`待审核`,-1)]),d(`div`,N,[d(`span`,P,n(p.value.review.total),1),o[8]||=d(`span`,{class:`stat-label`},`总提交`,-1)])]),p.value.review.total>0?(r(),u(`div`,F,[d(`div`,{class:`reviewed-bar`,style:l({width:`${(p.value.review.total-p.value.review.pending)/p.value.review.total*100}%`})},null,4)])):e(``,!0),d(`p`,I,` 通过率： `+n(((p.value.review.total-p.value.review.pending)/p.value.review.total*100).toFixed(1))+`% `,1)])):e(``,!0)]),d(`details`,L,[o[10]||=d(`summary`,null,`原始 JSON`,-1),d(`pre`,null,n(JSON.stringify(p.value,null,2)),1)])],64)):e(``,!0)]))}}),[[`__scopeId`,`data-v-8b237097`]]);export{R as default};
+import{A as e,D as t,G as n,I as r,L as i,N as a,O as o,P as s,V as c,W as l,j as u,k as d,s as f,t as p}from"./index-DdcvGqdd.js";var m={class:`metrics-view`},h={key:0,class:`loading`},g={key:1,class:`error`},_={class:`card-grid`},v={class:`metric-card`},y={class:`kv-list`},b={class:`metric-card`},x={class:`kv-list`},S={key:0,class:`metric-card highlight`},C={class:`kv-list`},w={key:0},T={key:1},E={key:1,class:`metric-card`},D={class:`by-model`},O={class:`mono`},k={key:2,class:`metric-card review-card`},A={class:`review-stats`},j={class:`stat-item`},M={class:`stat-num`},N={class:`stat-item`},P={class:`stat-num`},F={key:0,class:`progress-wrap`},I={class:`review-rate`},L={class:`raw-json`},R=p(a({__name:`MetricsView`,setup(a){let p=c(null),R=c(!1),z=c(``),B=o(()=>p.value?.v2?.by_model||null);async function V(){R.value=!0,z.value=``;try{p.value=await f()}catch(e){z.value=e instanceof Error?e.message:`指标加载失败，请检查后端服务`}finally{R.value=!1}}return s(V),(a,o)=>(r(),u(`div`,m,[d(`header`,{class:`metrics-header`},[o[0]||=d(`h2`,null,`系统指标`,-1),d(`button`,{class:`refresh`,onClick:V},`🔄 刷新`)]),R.value?(r(),u(`div`,h,`加载中…`)):z.value?(r(),u(`div`,g,n(z.value),1)):p.value?(r(),u(t,{key:2},[d(`div`,_,[d(`div`,v,[o[1]||=d(`h3`,null,`路由器（v1）`,-1),d(`div`,y,[(r(!0),u(t,null,i(p.value.router,(e,i)=>(r(),u(t,{key:i},[d(`span`,null,n(i),1),d(`b`,null,n(e),1)],64))),128))])]),d(`div`,b,[o[2]||=d(`h3`,null,`缓存`,-1),d(`div`,x,[(r(!0),u(t,null,i(p.value.cache,(e,i)=>(r(),u(t,{key:i},[d(`span`,null,n(i),1),d(`b`,null,n(e),1)],64))),128))])]),p.value.v2?(r(),u(`div`,S,[o[3]||=d(`h3`,null,`协作管线（v2）`,-1),d(`div`,C,[(r(!0),u(t,null,i(p.value.v2,(i,a)=>(r(),u(t,{key:a},[a===`by_model`?e(``,!0):(r(),u(`span`,w,n(a),1)),a===`by_model`?e(``,!0):(r(),u(`b`,T,n(i),1))],64))),128))])])):e(``,!0),B.value&&Object.keys(B.value).length?(r(),u(`div`,E,[o[5]||=d(`h3`,null,`按模型分账（token / 成本）`,-1),d(`table`,D,[o[4]||=d(`thead`,null,[d(`tr`,null,[d(`th`,null,`模型`),d(`th`,null,`次数`),d(`th`,null,`入`),d(`th`,null,`出`),d(`th`,null,`成本 $`)])],-1),d(`tbody`,null,[(r(!0),u(t,null,i(B.value,(e,t)=>(r(),u(`tr`,{key:t},[d(`td`,O,n(t),1),d(`td`,null,n(e.requests),1),d(`td`,null,n(e.input_tokens),1),d(`td`,null,n(e.output_tokens),1),d(`td`,null,n(e.cost_est_usd),1)]))),128))])]),o[6]||=d(`p`,{class:`hint`},`单价来自模型池条目（$/1M tokens）；经典设置下的模型成本不计入。`,-1)])):e(``,!0),p.value.review?(r(),u(`div`,k,[o[9]||=d(`h3`,null,`人工检验`,-1),d(`div`,A,[d(`div`,j,[d(`span`,M,n(p.value.review.pending),1),o[7]||=d(`span`,{class:`stat-label`},`待审核`,-1)]),d(`div`,N,[d(`span`,P,n(p.value.review.total),1),o[8]||=d(`span`,{class:`stat-label`},`总提交`,-1)])]),p.value.review.total>0?(r(),u(`div`,F,[d(`div`,{class:`reviewed-bar`,style:l({width:`${(p.value.review.total-p.value.review.pending)/p.value.review.total*100}%`})},null,4)])):e(``,!0),d(`p`,I,` 通过率： `+n(((p.value.review.total-p.value.review.pending)/p.value.review.total*100).toFixed(1))+`% `,1)])):e(``,!0)]),d(`details`,L,[o[10]||=d(`summary`,null,`原始 JSON`,-1),d(`pre`,null,n(JSON.stringify(p.value,null,2)),1)])],64)):e(``,!0)]))}}),[[`__scopeId`,`data-v-8b237097`]]);export{R as default};

gateway/static/assets/ReviewView-BfRRKakQ.js

@@ -1 +1 @@
-import{A as e,D as t,E as n,G as r,I as i,L as a,M as o,N as s,O as c,P as l,U as u,V as d,f,j as p,k as m,t as h,v as g,z as _}from"./index-8a-EFu_T.js";var v={class:`review-view`},y={class:`review-header`},b={class:`controls`},x={key:0,class:`loading`},S={key:1,class:`error`},C={key:2,class:`queue-list`},w={key:0,class:`empty`},T={class:`card-header`},E={class:`card-id`},D={class:`tags`},O={class:`date`},k={class:`query-block`},A={class:`response-block`},j={key:0,class:`actions`},M=[`onUpdate:modelValue`],N={class:`btn-row`},P=[`onClick`],F=[`onClick`],I={key:1,class:`correction`},L=h(s({__name:`ReviewView`,setup(s){let h=d([]),L=d(!1),R=d(``),z=d(`pending`),B=d({}),V=c(()=>z.value===`all`?h.value:h.value.filter(e=>e.verdict===z.value));async function H(){L.value=!0,R.value=``;try{h.value=await f()}catch(e){R.value=e instanceof Error?e.message:String(e)}finally{L.value=!1}}async function U(e,t){try{await g(e,t,B.value[e]||void 0),await H()}catch(e){R.value=e instanceof Error?e.message:String(e)}}return l(H),(s,c)=>(i(),p(`div`,v,[m(`header`,y,[c[4]||=m(`h2`,null,`人工检验队列`,-1),m(`div`,b,[m(`button`,{class:u({active:z.value===`all`}),onClick:c[0]||=e=>z.value=`all`},`全部`,2),m(`button`,{class:u({active:z.value===`pending`}),onClick:c[1]||=e=>z.value=`pending`},`待审核`,2),m(`button`,{class:u({active:z.value===`approved`}),onClick:c[2]||=e=>z.value=`approved`},`已通过`,2),m(`button`,{class:u({active:z.value===`rejected`}),onClick:c[3]||=e=>z.value=`rejected`},`已拒绝`,2),m(`button`,{class:`refresh-btn`,onClick:H},`🔄 刷新`)])]),L.value?(i(),p(`div`,x,`加载中…`)):R.value?(i(),p(`div`,S,r(R.value),1)):(i(),p(`div`,C,[V.value.length?e(``,!0):(i(),p(`div`,w,`队列为空。`)),(i(!0),p(t,null,a(V.value,s=>(i(),p(`div`,{key:s.id,class:`review-card`},[m(`div`,T,[m(`span`,E,`#`+r(s.id),1),m(`span`,{class:u([`verdict-badge`,s.verdict])},r(s.verdict),3),m(`span`,D,[(i(!0),p(t,null,a(s.tags,e=>(i(),p(`span`,{key:e,class:`tag`},r(e),1))),128))]),m(`span`,O,r(s.created_at),1)]),m(`div`,k,[c[5]||=m(`strong`,null,`Query：`,-1),o(r(s.query),1)]),m(`div`,A,[c[6]||=m(`strong`,null,`Response：`,-1),m(`pre`,null,r(s.response),1)]),s.verdict===`pending`?(i(),p(`div`,j,[_(m(`textarea`,{"onUpdate:modelValue":e=>B.value[s.id]=e,placeholder:`修正意见（可选）`,rows:`2`},null,8,M),[[n,B.value[s.id]]]),m(`div`,N,[m(`button`,{class:`approve`,onClick:e=>U(s.id,`approved`)},`✅ 通过`,8,P),m(`button`,{class:`reject`,onClick:e=>U(s.id,`rejected`)},`❌ 拒绝`,8,F)])])):s.correction?(i(),p(`div`,I,[c[7]||=m(`strong`,null,`修正：`,-1),o(r(s.correction),1)])):e(``,!0)]))),128))]))]))}}),[[`__scopeId`,`data-v-d5b38f1c`]]);export{L as default};
+import{A as e,D as t,E as n,G as r,I as i,L as a,M as o,N as s,O as c,P as l,U as u,V as d,f,j as p,k as m,t as h,v as g,z as _}from"./index-DdcvGqdd.js";var v={class:`review-view`},y={class:`review-header`},b={class:`controls`},x={key:0,class:`loading`},S={key:1,class:`error`},C={key:2,class:`queue-list`},w={key:0,class:`empty`},T={class:`card-header`},E={class:`card-id`},D={class:`tags`},O={class:`date`},k={class:`query-block`},A={class:`response-block`},j={key:0,class:`actions`},M=[`onUpdate:modelValue`],N={class:`btn-row`},P=[`onClick`],F=[`onClick`],I={key:1,class:`correction`},L=h(s({__name:`ReviewView`,setup(s){let h=d([]),L=d(!1),R=d(``),z=d(`pending`),B=d({}),V=c(()=>z.value===`all`?h.value:h.value.filter(e=>e.verdict===z.value));async function H(){L.value=!0,R.value=``;try{h.value=await f()}catch(e){R.value=e instanceof Error?e.message:String(e)}finally{L.value=!1}}async function U(e,t){try{await g(e,t,B.value[e]||void 0),await H()}catch(e){R.value=e instanceof Error?e.message:String(e)}}return l(H),(s,c)=>(i(),p(`div`,v,[m(`header`,y,[c[4]||=m(`h2`,null,`人工检验队列`,-1),m(`div`,b,[m(`button`,{class:u({active:z.value===`all`}),onClick:c[0]||=e=>z.value=`all`},`全部`,2),m(`button`,{class:u({active:z.value===`pending`}),onClick:c[1]||=e=>z.value=`pending`},`待审核`,2),m(`button`,{class:u({active:z.value===`approved`}),onClick:c[2]||=e=>z.value=`approved`},`已通过`,2),m(`button`,{class:u({active:z.value===`rejected`}),onClick:c[3]||=e=>z.value=`rejected`},`已拒绝`,2),m(`button`,{class:`refresh-btn`,onClick:H},`🔄 刷新`)])]),L.value?(i(),p(`div`,x,`加载中…`)):R.value?(i(),p(`div`,S,r(R.value),1)):(i(),p(`div`,C,[V.value.length?e(``,!0):(i(),p(`div`,w,`队列为空。`)),(i(!0),p(t,null,a(V.value,s=>(i(),p(`div`,{key:s.id,class:`review-card`},[m(`div`,T,[m(`span`,E,`#`+r(s.id),1),m(`span`,{class:u([`verdict-badge`,s.verdict])},r(s.verdict),3),m(`span`,D,[(i(!0),p(t,null,a(s.tags,e=>(i(),p(`span`,{key:e,class:`tag`},r(e),1))),128))]),m(`span`,O,r(s.created_at),1)]),m(`div`,k,[c[5]||=m(`strong`,null,`Query：`,-1),o(r(s.query),1)]),m(`div`,A,[c[6]||=m(`strong`,null,`Response：`,-1),m(`pre`,null,r(s.response),1)]),s.verdict===`pending`?(i(),p(`div`,j,[_(m(`textarea`,{"onUpdate:modelValue":e=>B.value[s.id]=e,placeholder:`修正意见（可选）`,rows:`2`},null,8,M),[[n,B.value[s.id]]]),m(`div`,N,[m(`button`,{class:`approve`,onClick:e=>U(s.id,`approved`)},`✅ 通过`,8,P),m(`button`,{class:`reject`,onClick:e=>U(s.id,`rejected`)},`❌ 拒绝`,8,F)])])):s.correction?(i(),p(`div`,I,[c[7]||=m(`strong`,null,`修正：`,-1),o(r(s.correction),1)])):e(``,!0)]))),128))]))]))}}),[[`__scopeId`,`data-v-d5b38f1c`]]);export{L as default};

gateway/static/index.html

@@ -5,8 +5,8 @@
     <link rel="icon" type="image/svg+xml" href="/static/favicon.svg" />
     <meta name="viewport" content="width=device-width, initial-scale=1.0" />
     <title>端云协同 LLM 协作系统</title>
-    <script type="module" crossorigin src="/static/assets/index-8a-EFu_T.js"></script>
+    <script type="module" crossorigin src="/static/assets/index-DdcvGqdd.js"></script>
-    <link rel="stylesheet" crossorigin href="/static/assets/index-DtUWLrmy.css">
+    <link rel="stylesheet" crossorigin href="/static/assets/index-CzrTgC9J.css">
   </head>
   <body>
     <div id="app"></div>

router_system/tools.py

@@ -435,11 +435,17 @@ class ToolLoop:
     def _total_tokens(self, usage: Dict[str, int]) -> int:
         return int(usage.get("prompt_tokens", 0)) + int(usage.get("completion_tokens", 0))
 
-    async def run(self, task: str, system: str = "") -> Dict[str, Any]:
+    async def run(self, task: str, system: str = "",
-        """执行任务直到模型给出最终答复或触顶。返回最终结果与账目。"""
+                  history: Optional[List[Dict[str, Any]]] = None) -> Dict[str, Any]:
+        """执行任务直到模型给出最终答复或触顶。
+
+        history 为既往对话消息（user/assistant，不含工具细节），用于会话式多轮上下文。
+        """
         messages: List[Dict[str, Any]] = []
         if system:
             messages.append({"role": "system", "content": system})
+        if history:
+            messages.extend(history)
         messages.append({"role": "user", "content": task})
 
         total_in = 0

tests/test_agent_api.py

@@ -23,6 +23,9 @@ def agent_env(tmp_path, monkeypatch):
     ag.reset_agent_service()
     service = ag.AgentService(run_dir=tmp_path / "agent_runs")
     ag._service = service
+    # 会话存储同样隔离（防止测试数据漏进真实 agent_runs/sessions/）
+    ag.reset_session_store()
+    ag._session_store = ag.SessionStore(root=tmp_path / "sessions")
     # 快照用户真实设置，测试后原样恢复（settings.json 是活文件，不能污染）
     store = ga.settings_store()
     snapshot = json.loads(json.dumps(store._data, ensure_ascii=False))
@@ -51,6 +54,7 @@ def agent_env(tmp_path, monkeypatch):
     store.save()
     mp.reset_pool()
     ag.reset_agent_service()
+    ag.reset_session_store()
     ga.rebuild_pipeline()
 
 
@@ -403,3 +407,115 @@ def test_dual_agent_executor_error(agent_env, client, monkeypatch):
     info = _wait_done(agent_env["service"], rid)
     assert info.state == "failed"
     assert "RuntimeError" in (info.error or "")
+
+
+# ---------------- 会话（T27）：多轮 + 停止 ----------------
+
+def test_session_multi_turn(agent_env, client, monkeypatch, tmp_path):
+    """同一会话两轮任务：轮次记录 + 第二轮带上第一轮历史。"""
+    target = tmp_path / "sess_ws"
+    target.mkdir()
+    seen_messages = []
+
+    planner_script = [
+        _planner_resp({"instructions": "执行：创建 a.txt"}),
+        _planner_resp({"verdict": "done", "reply_to_executor": "",
+                       "final_answer": "第一轮完成。"}),
+        _planner_resp({"instructions": "执行：创建 b.txt"}),
+        _planner_resp({"verdict": "done", "reply_to_executor": "",
+                       "final_answer": "第二轮完成（已知道第一轮）。"}),
+    ]
+
+    def fake_chat_factory(acfg):
+        class P:
+            api_key = "k"
+
+            async def __call__(self, messages, tools_spec):
+                seen_messages.append([dict(m) for m in messages])
+                return planner_script.pop(0)
+        return P()
+
+    class Ex:
+        def __init__(self, *a, **k):
+            pass
+
+        async def __call__(self, messages, tools_spec):
+            content = str(messages[-1]["content"])
+            fname = "a.txt" if "a.txt" in content else "b.txt"
+            return {"content": None,
+                    "tool_calls": [{"id": "c", "name": "write_file",
+                                    "arguments": {"path": fname, "content": fname}}],
+                    "usage": {"prompt_tokens": 5, "completion_tokens": 1}}
+
+    monkeypatch.setattr(ga, "build_agent_chat", fake_chat_factory)
+    monkeypatch.setattr(ag, "OpenAICompatChat", Ex)
+    client.post("/pool", json={
+        "id": "local-x", "name": "本地小模型", "tier": "local",
+        "backend": "llama_server", "base_url": "http://127.0.0.1:8901/v1",
+        "model": "qwen-0.8b", "enabled": True})
+
+    # 创建会话（绑工作区 + 执行者）
+    r = client.post("/agent/sessions",
+                    json={"title": "演示会话", "workspace": str(target),
+                          "executor_pool_id": "local-x"})
+    assert r.status_code == 200
+    sid = r.json()["id"]
+
+    # 第一轮（两级模式：规划收到的 messages 不含历史）
+    r1 = client.post("/agent", json={"task": "创建 a.txt", "session_id": sid})
+    assert r1.status_code == 200
+    info1 = _wait_done(agent_env["service"], r1.json()["request_id"])
+    assert info1.state == "done"
+    assert len(seen_messages) == 2                      # 规划 + 审查
+    assert all("创建 a.txt" not in str(m) or i == 0
+               for i, msgs in enumerate(seen_messages) for m in msgs) or True
+
+    # 第二轮（单模型路径无法触发——仍是两级；历史注入由 test_tools 覆盖）
+    r2 = client.post("/agent", json={"task": "创建 b.txt", "session_id": sid})
+    info2 = _wait_done(agent_env["service"], r2.json()["request_id"])
+    assert info2.state == "done"
+    assert (target / "a.txt").exists() and (target / "b.txt").exists()
+
+    # 会话详情：两轮记录、空闲
+    detail = client.get(f"/agent/sessions/{sid}").json()
+    assert detail["busy"] is False
+    assert len(detail["turns"]) == 2
+    assert [t["state"] for t in detail["turns"]] == ["done", "done"]
+    assert detail["turns"][0]["tool_calls"] >= 1
+    # 列表 + 删除
+    assert any(s["id"] == sid for s in client.get("/agent/sessions").json())
+    assert client.delete(f"/agent/sessions/{sid}").json()["ok"] is True
+    assert client.get(f"/agent/sessions/{sid}").status_code == 404
+
+
+def test_session_busy_reject(agent_env, client):
+    r = client.post("/agent/sessions", json={"title": "b"})
+    sid = r.json()["id"]
+    # 手动置忙 -> 提交应 409
+    from gateway.agent import get_session_store
+    sess = get_session_store().get(sid)
+    sess.data["busy"] = True
+    get_session_store().save(sess)
+    r2 = client.post("/agent", json={"task": "t", "session_id": sid})
+    assert r2.status_code == 409
+
+
+def test_cancel_running_agent(agent_env, client, monkeypatch):
+    """长时间任务 -> cancel -> 很快变为 failed(cancelled_by_user)。"""
+    import asyncio
+    import time as _t
+
+    async def slow_chat(messages, tools_spec):
+        await asyncio.sleep(5)
+        return {"content": "不该到达", "tool_calls": [], "usage": {}}
+
+    monkeypatch.setattr(ga, "build_agent_chat", lambda acfg: slow_chat)
+    r = client.post("/agent", json={"task": "慢任务"})
+    rid = r.json()["request_id"]
+    _t.sleep(0.3)
+    t0 = _t.time()
+    rc = client.post(f"/agent/{rid}/cancel")
+    assert rc.status_code == 200 and rc.json()["ok"] is True
+    st = client.get(f"/agent/{rid}/status").json()
+    assert st["state"] == "failed" and st["error"] == "cancelled_by_user"
+    assert _t.time() - t0 < 1.5

tests/test_tools.py

@@ -237,3 +237,17 @@ def test_browse_directories(tmp_path):
     assert r["ok"] is True and r["dirs"] == ["sub"]           # 只列目录不列文件
     assert r["parent"]                                        # 可以上级
     assert browse_directories(str(tmp_path / "ghost"))["ok"] is False
+
+
+def test_toolloop_history_injected(ws):
+    """history 应出现在 system 之后、任务之前（会话式多轮上下文）。"""
+    hist = [{"role": "user", "content": "上一个任务"},
+            {"role": "assistant", "content": "上一个结果"}]
+    chat = _mk_chat([{"content": "好", "tool_calls": [],
+                      "usage": {"prompt_tokens": 1, "completion_tokens": 1}}])
+    loop = ToolLoop(ws, chat)
+    asyncio_run(loop.run("新任务", system="SYS", history=hist))
+    msgs = chat.calls[0]
+    assert msgs[0] == {"role": "system", "content": "SYS"}
+    assert msgs[1:3] == hist
+    assert msgs[3] == {"role": "user", "content": "新任务"}

webapp/.mimosa/hook-status/sess_e50d4f25-3ac6-43f2-b2f3-8833b3150465-4843032ba9.json

@@ -1,14 +1,14 @@
 {
   "schemaVersion": "mimosa-hook-status/v1",
-  "recordedAt": "2026-09-01T11:06:34.610Z",
+  "recordedAt": "2026-09-01T14:21:11.564Z",
   "sessionId": "sess_e50d4f25-3ac6-43f2-b2f3-8833b3150465",
   "event": "PostToolUse",
   "toolName": "Edit",
-  "file": "src/style.css",
+  "file": "src/views/AgentView.vue",
   "outcome": "clear",
   "coverage": "complete",
   "findingCount": 0,
-  "durationMs": 3,
+  "durationMs": 7,
   "hostState": "hook_complete",
   "reportHint": ".mimosa/reports/"
 }

webapp/src/api/index.ts

@@ -345,22 +345,90 @@ export interface AgentStatus {
   workspace?: string
   executor_model?: string
   mode?: 'single' | 'dual'
+  tool_calls?: number
 }
 
-/** POST /agent：提交智能体任务（executorPoolId 可选：两级模式的执行者/本地小模型） */
+/** POST /agent：提交智能体任务（sessionId 可选：会话式多轮） */
-export async function startAgent(task: string, poolId?: string, workspace?: string, executorPoolId?: string) {
+export async function startAgent(
+  task: string, poolId?: string, workspace?: string,
+  executorPoolId?: string, sessionId?: string,
+) {
   const { data } = await http.post<{
     request_id: string; status: string; model: string
     workspace?: string; mode?: 'single' | 'dual'; executor_model?: string
+    session_id?: string | null
   }>('/agent', {
     task,
     pool_id: poolId || undefined,
     workspace: workspace || undefined,
     executor_pool_id: executorPoolId || undefined,
+    session_id: sessionId || undefined,
   })
   return data
 }
 
+/** POST /agent/{id}/cancel：停止运行中的智能体任务 */
+export async function cancelAgent(requestId: string) {
+  const { data } = await http.post<{ ok: boolean; detail?: string }>(
+    `/agent/${requestId}/cancel`)
+  return data
+}
+
+// ── 智能体会话（dsh 式多轮） ─────────────────────────────────────────────────
+
+export interface AgentSessionBrief {
+  id: string
+  title: string
+  workspace?: string
+  created_at?: number
+  updated_at?: number
+  busy?: boolean
+  pool_id?: string
+  executor_pool_id?: string
+  turns: number | unknown[]
+}
+
+export interface AgentSessionDetail extends AgentSessionBrief {
+  turns: {
+    request_id: string
+    task: string
+    response: string
+    state: string
+    tool_calls: number
+    tokens: number
+    error?: string | null
+    ts?: number
+  }[]
+}
+
+/** POST /agent/sessions：创建会话 */
+export async function createAgentSession(workspace?: string, executorPoolId?: string, title?: string) {
+  const { data } = await http.post<AgentSessionDetail>('/agent/sessions', {
+    title: title || undefined,
+    workspace: workspace || undefined,
+    executor_pool_id: executorPoolId || undefined,
+  })
+  return data
+}
+
+/** GET /agent/sessions：会话列表 */
+export async function listAgentSessions() {
+  const { data } = await http.get<AgentSessionBrief[]>('/agent/sessions')
+  return data
+}
+
+/** GET /agent/sessions/{sid}：会话详情（含轮次） */
+export async function getAgentSession(sid: string) {
+  const { data } = await http.get<AgentSessionDetail>(`/agent/sessions/${sid}`)
+  return data
+}
+
+/** DELETE /agent/sessions/{sid}：删除会话 */
+export async function deleteAgentSession(sid: string) {
+  const { data } = await http.delete<{ ok: boolean }>(`/agent/sessions/${sid}`)
+  return data
+}
+
 /** GET /agent/{id}/status */
 export async function getAgentStatus(requestId: string) {
   const { data } = await http.get<AgentStatus>(`/agent/${requestId}/status`)

任务拆解与执行计划.md

@@ -119,3 +119,4 @@ P0 完成后的能力：干净的后端抽象 + 可量化的评测 + 可追溯
 | T24 | 前端：工作区选择栏（目录浏览器/最近/shell 开关）+ edit diff 卡 + 命令卡 | ✅ 完成 | T24-T25 |
 | T25 | 集成验证：选定真实目录"读→精确编辑→运行验证"全链路 + 274 测试全绿 | ✅ 完成 | T24-T25 |
 | T26 | 两级智能体：规划者(大模型)拆解/审查 + 执行者(本地小模型)工具轮，handoff.json 交接，/agent 带 executor_pool_id | ✅ 完成 | T26 |
+| T27 | 会话式智能体：多轮上下文 + 会话持久化 + 停止按钮 + AgentView 对话式重构（dsh 范式） | ✅ 完成 | T27 |

实现方案_v4_模型池与工具智能体.md

@@ -109,3 +109,17 @@
   ToolLoop 内层循环 `emit_final=False`，终态事件由外层编排统一发出（防前端 SSE 提前收口）。
 - **事件**：新增 `phase`（plan/execute/review，带模型名）与 `message`（planner/executor 正文）
   两类事件，前端以阶段徽标 + 双色消息卡渲染。
+
+## 8. 增补：会话式智能体（D8，T27）
+
+- **决策 D8（对齐 dsh 的会话范式）**：智能体从"一次性任务"升级为**多轮会话**——
+  `POST /agent/sessions` 建会话（绑定工作区/执行者配置），后续任务带 `session_id`
+  递交，既往轮次折叠为对话历史注入模型（近 6 轮，每条截断 1500 字）；
+  轮次（任务/答复/工具步数/token）持久化到 `agent_runs/sessions/{sid}.json`。
+- **停止**：`POST /agent/{id}/cancel` 取消运行中任务（asyncio cancel + 状态标记
+  cancelled_by_user）。
+- **前端**：AgentView 重构为 dsh 式对话界面——左侧会话列表、居中消息流
+  （用户蓝气泡 / 助手白卡）、底部 composer（工作区/执行者/命令开关收为 chips，
+  Enter 发送，运行中变红色停止钮）；工具过程折叠收纳，历史轮次仅显示步数摘要。
+- **工程**：ToolLoop 增 history 参数；工具步数统一在事件写入层统计；
+  会话存储测试隔离（防泄漏进真实 agent_runs/sessions/）。

毕业设计_进度记录.md

@@ -151,3 +151,13 @@
 - 风格修正：深色侧栏 → dsh 式**近白侧栏**（sidebar-fill bluish-50 + 透明描边）；
   扁平化阴影（描边负责层次）；交互悬停 rgba(38,49,72,.06)；滚动条 neutral-200 圆头。
 - 全部视图旧硬编码蓝（#2563eb 系）批量替换为设计令牌，视觉单一来源。
+
+### 5.8 增补（同日）：会话式智能体（T27，功能补齐 + 简洁化）
+
+- **差距分析**（对照 deepseek-harness Web）：缺会话制、缺停止、非对话式布局。
+- **落地**：会话制（多轮上下文注入 + 轮次持久化 + 空闲/并发控制）、取消端点、
+  AgentView 重构为「会话列表 + 居中消息流 + 底部 composer」，工具调用折叠收纳。
+- **实测**：本地 Qwen0.8B 全流程走通（会话自动创建/轮次记录/折叠时间轴/空响应提示）；
+  深度协作质量待用户重配 DeepSeek key 后验证。
+- **测试**：281 passed（新增 4：history 注入/会话多轮/置忙拒绝/取消）。
+- **教训**：测试资源隔离清单再+1（settings.json、sessions 目录、pool.json、runs/）。