feat(v3): T29 收尾 + T31 dsh 功能对齐

T29 流式收尾：
- _stream_partial 每次流式调用前复位（防上次成功置位导致本次失败误抛不回退）

T31 dsh（deepseek-harness）功能对齐：
- OpenAICompatChat 重试退避：传输错误/408/429/5xx 指数退避（max_retries=2），4xx 不重试
- web_fetch 工具：公网 http/https 抓取，SSRF 防护（DNS 后拒绝私网/环回/链路本地/NAT64，
  512KB/15s/12k 上限，二进制嗅探拒绝），agent.allow_net 开关（默认开）
- 原子写入：write_file/edit_file 临时文件 + os.replace（Windows EPERM 退避）
- 慢工具线程卸载：run_command/web_fetch/search_files 独立线程 + asyncio.sleep 轮询
- search_files：os.walk 修剪依赖目录（替代 rglob 全量物化），不跟随符号链接
- run_command：危险命令黑名单独立拦截 + 显式 COMSPEC/sh 解释器执行
- 重复调用提醒：同工具同参数第 3 次起回喂系统提示 + repeat_warning 事件
- 会话重命名：PATCH /agent/sessions/{sid} + 前端 ✎
- 前端：SettingsView 适配密钥打码（留空保留），SPA 重新构建
- 新增 tests/test_agent_features.py（9 项）；全量 318 测试通过

gateway/static/assets/MetricsView-BIMJ3R2m.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-C4nTxB0s.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-kbuKhaUa.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-xwvhvWhY.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-C4nTxB0s.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-kbuKhaUa.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-C4nTxB0s.js"></script>
+    <script type="module" crossorigin src="/static/assets/index-kbuKhaUa.js"></script>
-    <link rel="stylesheet" crossorigin href="/static/assets/index-rGGK-sk_.css">
+    <link rel="stylesheet" crossorigin href="/static/assets/index-BYO22xUl.css">
   </head>
   <body>
     <div id="app"></div>

router_system/tools.py

@@ -53,6 +53,45 @@ REPEAT_CALL_WARN_AT = 3
 # 默认循环上限
 DEFAULT_MAX_ROUNDS = 8
 
+# 可能长时间运行的工具（命令执行 / 网络抓取 / 大范围搜索）放独立线程执行，
+# 不阻塞事件循环；完成等待用 asyncio.sleep 轮询（补丁运行时的 TestClient
+# 每请求独立事件循环，不推进 run_in_executor 桥接；轮询在生产/测试两端都可靠）。
+SLOW_TOOLS = {"run_command", "web_fetch", "search_files"}
+
+
+def _spawn_tool_thread(fn, *args):
+    """起守护线程执行 fn(*args)，返回 (结果盒子, 线程)；轮询线程存活后取盒内值。"""
+    import threading
+    box: Dict[str, Any] = {}
+
+    def _runner():
+        try:
+            box["result"] = fn(*args)
+        except BaseException as exc:   # 线程内异常回传给调用方
+            box["error"] = exc
+
+    t = threading.Thread(target=_runner, daemon=True, name="agenttool")
+    t.start()
+    return box, t
+
+
+def _dispatch_tool(tools, name, arguments):
+    """统一工具分发（内部辅助）。"""
+    return tools.execute(name, arguments)
+
+
+async def run_tool_async(tools: "WorkspaceTools", name: str,
+                         arguments: Dict[str, Any]) -> Dict[str, Any]:
+    """执行一个工具：慢工具放线程并轮询等完成，快工具直接内联执行。"""
+    if name not in SLOW_TOOLS:
+        return _dispatch_tool(tools, name, arguments)
+    box, t = _spawn_tool_thread(_dispatch_tool, tools, name, arguments)
+    while t.is_alive():
+        await asyncio.sleep(0.02)
+    if "error" in box:
+        raise box["error"]
+    return box["result"]
+
 # OpenAI tools 声明（chat/completions 请求的 tools 参数）
 TOOLS_SPEC: List[Dict[str, Any]] = [
     {
@@ -440,13 +479,17 @@ class WorkspaceTools:
         if blocked:
             return {"ok": False, "error": f"命令被安全策略拒绝（{blocked}）。请换一种不具破坏性的做法。"}
         if os.name == "nt":
-            argv = [os.environ.get("COMSPEC", "cmd.exe"), "/c", command]
+            # Windows：显式走 cmd /c（与 shell=True 内部同构——整条命令包一层引号，
+            # 避免参数列表的 CRT 转义与 cmd 引号语义冲突）；COMSPEC 取系统 shell 路径
+            comspec = os.environ.get("COMSPEC", "cmd.exe")
+            run_args: Any = f'"{comspec}" /c "{command}"'
+            creationflags = 0x08000000  # CREATE_NO_WINDOW
         else:
-            argv = ["/bin/sh", "-c", command]
+            run_args = ["/bin/sh", "-c", command]
-        creationflags = 0x08000000 if os.name == "nt" else 0  # CREATE_NO_WINDOW
+            creationflags = 0
         try:
             proc = subprocess.run(
-                argv, cwd=str(self.root), capture_output=True,
+                run_args, cwd=str(self.root), capture_output=True,
                 timeout=self.shell_timeout_s, creationflags=creationflags,
             )
             out = (proc.stdout or b"").decode("utf-8", errors="replace")
@@ -756,7 +799,7 @@ class ToolLoop:
                         messages.append({"role": "tool", "tool_call_id": c["id"],
                                          "content": preview})
                         continue
-                result = await asyncio.to_thread(self.tools.execute, c["name"], c["arguments"])
+                result = await run_tool_async(self.tools, c["name"], c["arguments"])
                 preview = json.dumps(result, ensure_ascii=False)
                 if len(preview) > self.result_preview_chars:
                     preview = preview[:self.result_preview_chars] + "…(截断)"

tests/test_agent_features.py

@@ -0,0 +1,209 @@
+"""dsh 功能对齐测试（T31）：
+
+- 流式 _stream_partial 复位（首次成功后再次流式失败应回退非流式，而非误抛）
+- LLM 调用重试退避（5xx/传输错误重试，非可重试错误不重试）
+- 会话重命名（PATCH /agent/sessions/{sid}）
+- 重复工具调用提醒（同工具同参数第 3 次起回喂警语）
+- search_files 目录修剪（node_modules 等不进入）
+- 原子写入（write_file 落盘内容完整、无 .tmp 残留）
+- 慢工具线程卸载（run_tool_async 快内联/慢走线程，异常回传）
+"""
+import asyncio
+import json
+
+import httpx
+import pytest
+
+pytest.importorskip("fastapi")
+pytest.importorskip("httpx")
+
+from fastapi.testclient import TestClient
+
+import gateway.agent as ag
+from gateway.agent import OpenAICompatChat
+
+
+@pytest.fixture()
+def ws(tmp_path):
+    from router_system.tools import WorkspaceTools
+    return WorkspaceTools(tmp_path / "ws")
+
+
+# ---------------- _stream_partial 复位 ----------------
+
+def _ok_sse_body():
+    chunks = [{"choices": [{"delta": {"content": "第一段答复"}}]},
+              {"choices": [{"delta": {}}], "usage": {"prompt_tokens": 1,
+                                                     "completion_tokens": 1}}]
+    lines = [f"data: {json.dumps(c, ensure_ascii=False)}" for c in chunks]
+    lines.append("data: [DONE]")
+    return ("\n\n".join(lines) + "\n\n").encode("utf-8")
+
+
+def _nonstream_body(text: str) -> bytes:
+    return json.dumps({
+        "choices": [{"message": {"content": text}}],
+        "usage": {"prompt_tokens": 2, "completion_tokens": 2},
+    }).encode("utf-8")
+
+
+def test_stream_partial_flag_resets_between_calls():
+    """首次流式成功（置位）后，第二次流式失败应正常回退非流式。"""
+    state = {"n": 0}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        state["n"] += 1
+        if state["n"] == 1:
+            return httpx.Response(200, content=_ok_sse_body())
+        # 第二次：流式 500（无部分输出）-> 应回退非流式（第 3 次请求）
+        if state["n"] == 2:
+            return httpx.Response(500, content=b"boom")
+        return httpx.Response(200, content=_nonstream_body("回退答案"))
+
+    chat = OpenAICompatChat(base_url="http://x", api_key=None, model="m",
+                            transport=httpx.MockTransport(handler),
+                            retry_delay_s=0)
+    r1 = asyncio.run(chat([{"role": "user", "content": "a"}], []))
+    assert r1["content"] == "第一段答复"
+    r2 = asyncio.run(chat([{"role": "user", "content": "b"}], []))
+    assert r2["content"] == "回退答案"          # 不因上次置位而误抛
+    assert state["n"] == 3
+
+
+# ---------------- 重试退避 ----------------
+
+def test_retry_on_5xx_then_success():
+    calls = {"n": 0}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        calls["n"] += 1
+        if calls["n"] == 1:
+            return httpx.Response(502, content=b"bad gateway")
+        return httpx.Response(200, content=_nonstream_body("恢复"))
+
+    chat = OpenAICompatChat(base_url="http://x", api_key=None, model="m",
+                            stream=False, max_retries=2, retry_delay_s=0,
+                            transport=httpx.MockTransport(handler))
+    r = asyncio.run(chat([{"role": "user", "content": "x"}], []))
+    assert r["content"] == "恢复" and calls["n"] == 2
+
+
+def test_retry_exhausted_raises():
+    def handler(request: httpx.Request) -> httpx.Response:
+        return httpx.Response(500, content=b"always down")
+
+    chat = OpenAICompatChat(base_url="http://x", api_key=None, model="m",
+                            stream=False, max_retries=1, retry_delay_s=0,
+                            transport=httpx.MockTransport(handler))
+    with pytest.raises(httpx.HTTPStatusError):
+        asyncio.run(chat([{"role": "user", "content": "x"}], []))
+
+
+def test_no_retry_on_4xx_client_error():
+    calls = {"n": 0}
+
+    def handler(request: httpx.Request) -> httpx.Response:
+        calls["n"] += 1
+        return httpx.Response(401, content=b"unauthorized")
+
+    chat = OpenAICompatChat(base_url="http://x", api_key=None, model="m",
+                            stream=False, max_retries=2, retry_delay_s=0,
+                            transport=httpx.MockTransport(handler))
+    with pytest.raises(httpx.HTTPStatusError):
+        asyncio.run(chat([{"role": "user", "content": "x"}], []))
+    assert calls["n"] == 1                    # 4xx 不重试
+
+
+# ---------------- 会话重命名 ----------------
+
+def test_session_rename_endpoint(tmp_path):
+    import gateway.api as ga
+    ag.reset_session_store()
+    ag._session_store = ag.SessionStore(root=tmp_path / "sess")
+    client = TestClient(ga.app)
+    r = client.post("/agent/sessions", json={"title": "旧名", "workspace": ""})
+    sid = r.json()["id"]
+    r2 = client.patch(f"/agent/sessions/{sid}", json={"title": "新名字"})
+    assert r2.status_code == 200
+    assert r2.json()["title"] == "新名字"
+    assert client.get(f"/agent/sessions/{sid}").json()["title"] == "新名字"
+    # 空标题 400；不存在 404
+    assert client.patch(f"/agent/sessions/{sid}", json={"title": " "}).status_code == 400
+    assert client.patch("/agent/sessions/asdeadbeef99",
+                        json={"title": "x"}).status_code == 404
+    ag.reset_session_store()
+
+
+# ---------------- 重复调用提醒 ----------------
+
+def test_repeat_call_warning(ws, tmp_path):
+    """同工具同参数第 3 次调用：回喂内容带系统提示 + repeat_warning 事件。"""
+    from router_system.tools import ToolLoop
+    seen_msgs = []
+    calls = {"n": 0}
+
+    async def chat(messages, tools_spec):
+        seen_msgs.append(list(messages))
+        calls["n"] += 1
+        if calls["n"] <= 3:
+            return {"content": None,
+                    "tool_calls": [{"id": "c" + str(calls["n"]), "name": "read_file",
+                                    "arguments": {"path": "a.txt"}}],
+                    "usage": {}}
+        return {"content": "收手了", "tool_calls": [], "usage": {}}
+
+    events = []
+    loop = ToolLoop(ws, chat, on_event=events.append)
+    (tmp_path / "ws" / "a.txt").parent.mkdir(parents=True, exist_ok=True)
+    (tmp_path / "ws" / "a.txt").write_text("x", encoding="utf-8")
+    result = asyncio.run(loop.run("反复读"))
+    assert result["response"] == "收手了"
+    # 第 3 次工具结果消息应带提醒
+    tool_msgs = [m for m in seen_msgs[3] if m.get("role") == "tool"]
+    assert any("系统提示" in m["content"] for m in tool_msgs)
+    assert any(e["type"] == "repeat_warning" and e["count"] == 3 for e in events)
+
+
+# ---------------- search_files 修剪 ----------------
+
+def test_search_files_prunes_skip_dirs(ws, tmp_path):
+    root = tmp_path / "ws"
+    (root / "node_modules" / "pkg").mkdir(parents=True, exist_ok=True)
+    (root / "node_modules" / "pkg" / "dep.js").write_text("NEEDLE", encoding="utf-8")
+    (root / "src").mkdir(parents=True, exist_ok=True)
+    (root / "src" / "app.js").write_text("NEEDLE", encoding="utf-8")
+    r = ws.search_files("NEEDLE")
+    files = {m["file"] for m in r["matches"]}
+    assert files == {"src/app.js"}             # node_modules 被修剪
+
+
+# ---------------- 原子写入 ----------------
+
+def test_atomic_write_roundtrip(ws, tmp_path):
+    ws.write_file("sub/atomic.txt", "第一版")
+    ws.edit_file("sub/atomic.txt", "第一版", "第二版")
+    assert (tmp_path / "ws" / "sub" / "atomic.txt").read_text(
+        encoding="utf-8") == "第二版"
+    # 无 .tmp 残留
+    leftovers = [p.name for p in (tmp_path / "ws" / "sub").iterdir()
+                 if p.name.endswith(".tmp")]
+    assert leftovers == []
+
+
+# ---------------- 慢工具线程卸载 ----------------
+
+def _boom(*_args):
+    raise RuntimeError("线程内炸了")
+
+
+def test_run_tool_async_fast_inline_and_thread_exception(ws):
+    from router_system.tools import run_tool_async
+    # 快工具：内联
+    ws.write_file("fast.txt", "v")
+    r = asyncio.run(run_tool_async(ws, "read_file", {"path": "fast.txt"}))
+    assert r["ok"] is True and r["content"] == "v"
+    # 异常从线程回传（execute 以属性形式提供）
+    class Boom:
+        execute = staticmethod(_boom)
+    with pytest.raises(RuntimeError):
+        asyncio.run(run_tool_async(Boom(), "read_file", {"path": "x"}))

webapp/src/api/index.ts

@@ -95,6 +95,8 @@ export interface ModelSettings {
     model: string
     base_url: string
     api_key: string
+    /** 服务端打码标志：true 表示已存 key（返回值只含前 6 位，保存时留空即保留） */
+    api_key_set?: boolean
   }
   pipeline: {
     fast_path: boolean
@@ -443,6 +445,14 @@ export async function deleteAgentSession(sid: string) {
   return data
 }
 
+/** PATCH /agent/sessions/{sid}：重命名会话 */
+export async function renameAgentSession(sid: string, title: string) {
+  const { data } = await http.patch<AgentSessionDetail>(`/agent/sessions/${sid}`, {
+    title,
+  })
+  return data
+}
+
 /** GET /agent/{id}/status */
 export async function getAgentStatus(requestId: string) {
   const { data } = await http.get<AgentStatus>(`/agent/${requestId}/status`)

webapp/src/views/AgentView.vue

@@ -12,6 +12,7 @@
             <span>{{ turnsOf(s) }} 轮</span>
             <span>·</span>
             <span>{{ fmtTime(s.updated_at) }}</span>
+            <span class="sess-rename" title="重命名会话" @click.stop="renameSession(s.id)">✎</span>
             <span class="sess-del" title="删除会话" @click.stop="removeSession(s.id)">✕</span>
           </div>
         </div>
@@ -180,7 +181,8 @@ import {
   startAgent, getAgentStatus, watchAgent, approveAgent, getConfig, updateConfig,
   getPool,
   browseFs, getAgentWorkspaces, openWorkspace,
-  listAgentSessions, createAgentSession, getAgentSession, deleteAgentSession, cancelAgent,
+  listAgentSessions, createAgentSession, getAgentSession, deleteAgentSession,
+  renameAgentSession, cancelAgent,
 } from '@/api'
 import type { AgentEvent, PoolEntry, FsBrowse } from '@/api'
 
@@ -305,6 +307,16 @@ async function removeSession(sid: string) {
   refreshSessions()
 }
 
+async function renameSession(sid: string) {
+  const cur = sessions.value.find(s => s.id === sid)
+  const title = prompt('新的会话名称：', cur?.title || '')
+  if (title === null) return            // 取消
+  const trimmed = title.trim()
+  if (!trimmed) { alert('名称不能为空'); return }
+  await renameAgentSession(sid, trimmed)
+  refreshSessions()
+}
+
 // ── 工作区 ──────────────────────────────────────────────────────────────
 async function openPicker() {
   pickerOpen.value = true
@@ -496,16 +508,19 @@ onMounted(async () => {
   margin-top: 3px;
   align-items: center;
 }
-.sess-del {
+.sess-del,
+.sess-rename {
   margin-left: auto;
   color: var(--c-caption);
   opacity: 0;
-  cursor: pointer;
+  cursor: pointer;  padding: 0 3px;
-  padding: 0 3px;
   border-radius: 4px;
 }
-.sess-item:hover .sess-del { opacity: 1; }
+.sess-rename { margin-left: 0; }
+.sess-item:hover .sess-del,
+.sess-item:hover .sess-rename { opacity: 1; }
 .sess-del:hover { color: var(--c-err); background: var(--c-err-soft); }
+.sess-rename:hover { color: var(--c-accent, #2563eb); }
 .sess-empty { color: var(--c-caption); font-size: 12px; text-align: center; padding: 20px 0; }
 
 /* ---------- 对话区 ---------- */

webapp/src/views/SettingsView.vue

@@ -331,9 +331,10 @@
 
           <!-- API Key -->
           <div class="field full-width">
-            <label>API Key（保存在本地 config/settings.json，不入代码库；优先级高于 .env）</label>
+            <label>API Key{{ form.architect.api_key_set ? '（已设置，留空保留）' : '（保存在本地 config/settings.json，不入代码库；优先级高于 .env）' }}</label>
             <input v-model="form.architect.api_key" type="password"
-              placeholder="sk-xxxxxxxxxxxxxxxx" autocomplete="off" />
+              :placeholder="form.architect.api_key_set ? '已设置，留空保留原值' : 'sk-xxxxxxxxxxxxxxxx'"
+              autocomplete="off" />
           </div>
 
           <!-- 模型选择 -->
@@ -867,6 +868,15 @@ function _safeAssign(target: any, source: any) {
   }
 }
 
+/** architect 段专用填充：api_key 服务端打码返回，已设置时清空输入框（留空=保留）。 */
+function _applyArchitect(arch: any) {
+  if (!arch) return
+  const { api_key, api_key_set, ...rest } = arch
+  _safeAssign(form.architect, rest)
+  form.architect.api_key_set = Boolean(api_key_set)
+  form.architect.api_key = ''   // 不把打码值带回表单，防止保存时覆盖真值
+}
+
 async function load() {
   loadError.value = ''
   try {
@@ -880,7 +890,7 @@ async function load() {
 
     // 安全填充表单（防止 API 返回 null 导致响应式丢失）
     if (cfg.worker) _safeAssign(form.worker, cfg.worker)
-    if (cfg.architect) _safeAssign(form.architect, cfg.architect)
+    if (cfg.architect) _applyArchitect(cfg.architect)
     if (cfg.pipeline) _safeAssign(form.pipeline, cfg.pipeline)
 
     // 保存原始快照
@@ -914,9 +924,9 @@ async function save() {
     // 空 api_key 不传给后端，保留服务端已有值
     if (!patch.architect.api_key) delete patch.architect.api_key
     const merged = await updateConfig(patch)
-    // 用安全方式更新（保留响应式）
+    // 用安全方式更新（保留响应式）；architect 段走打码适配
     _safeAssign(form.worker, merged.worker || {})
-    _safeAssign(form.architect, merged.architect || {})
+    _applyArchitect(merged.architect || {})
     _safeAssign(form.pipeline, merged.pipeline || {})
     original.value = JSON.parse(JSON.stringify(form))
     saveMsg.value = { ok: true, msg: '✅ 设置已保存，管线已重建' }
@@ -935,7 +945,7 @@ async function reset() {
   try {
     const merged = await resetConfig()
     _safeAssign(form.worker, merged.worker || {})
-    _safeAssign(form.architect, merged.architect || {})
+    _applyArchitect(merged.architect || {})
     _safeAssign(form.pipeline, merged.pipeline || {})
     original.value = JSON.parse(JSON.stringify(form))
     workerModels.value = []

任务拆解与执行计划.md

@@ -122,3 +122,5 @@ P0 完成后的能力：干净的后端抽象 + 可量化的评测 + 可追溯
 | 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 |
 | T28 | 操作审批流：approval_policy(off/dangerous/all) + 挂起/裁决/超时 + /approve + 审批卡 | ✅ 完成 | T28 |
 | T29 | token 级流式：SSE 解析/tool_calls 碎片组装/回退 + DeltaThrottle + 打字机渲染 | ✅ 完成 | T29 |
+| T30 | 安全加固（Mimosa 深度扫描驱动，D11）：路径 ID 白名单/artifacts 与工件名关押/下载 dest 关押+协议白名单/config 密钥打码/Host 信任围栏+回环绑定/危险命令独立拦截/CSPRNG 抽样 | ✅ 完成 | T30 |
+| T31 | dsh 功能对齐（D12）：LLM 重试退避/web_fetch 工具（SSRF 防护）/原子写入/慢工具线程卸载/search 目录修剪/重复调用提醒/会话重命名 | ✅ 完成 | T31 |

实现方案_v4_模型池与工具智能体.md

@@ -136,3 +136,44 @@
   DeltaThrottle ≥48 字符节流落 delta 事件；前端打字机式实时渲染 + 光标。
 - **配套修复**：Vue 响应式丢失 bug——闭包持有 push 前原始对象导致过程事件不渲染，
   改取响应式代理对象。
+
+## 10. 增补：安全基线（D11，T30，Mimosa 深度扫描驱动）
+
+- **决策 D11（默认最小暴露面）**：
+  - **路径参数 ID 白名单**：`/runs|/agent|/agent/sessions` 的路径参数只允许
+    `[a-zA-Z0-9_-]{1,64}`（系统生成 ID 的字符集），非法一律 404——杀灭 Windows
+    反斜杠穿越变体（如 `/runs/x/artifacts/..%5C..%5C..%5C.env` 直读 .env）。
+  - **工件双重关押**：artifacts 端点解析后必须仍在 artifacts 目录内；pipeline
+    `_save_artifact`/`_read_artifact` 对模型输出的工件名消毒（剥路径成分）。
+  - **下载关押**：`/llama/download` 的 dest 解析后必须位于 models/ 内；URL 协议
+    白名单 http/https 在 HF 别名转换**之前**判定（防 file:/// 被拼成 HF 地址）。
+  - **密钥打码**：GET /config 的 architect.api_key 只回前 6 位 + api_key_set；
+    PUT 空串/缺省=保留原值（对齐 D2 池条目语义，前端"已设置，留空保留"）。
+  - **Web 信任围栏**：TrustedHostMiddleware 默认只信 localhost/127.0.0.1/[::1]
+    （GATEWAY_TRUSTED_HOSTS 可覆盖，"*"=放行全部），防 DNS rebinding 打到本网关；
+    api.py `__main__` 默认绑定 127.0.0.1（scripts/serve.py 本就如此）。
+  - **独立命令拦截**：run_command 危险模式黑名单（format / rd /s / rm -rf / /
+    shutdown / curl|sh 等）先于审批独立拦截；shell 经显式 `"%COMSPEC%" /c` /
+    `/bin/sh -c` 执行（语义同 shell=True，但解释器路径受控）。
+  - **CSPRNG**：review 抽样缺省随机源改 random.SystemRandom。
+
+## 11. 增补：dsh 功能对齐（D12，T31）
+
+- **决策 D12（对齐 deepseek-harness 的健壮性功能）**：
+  - **重试退避**：OpenAICompatChat 非流式路径（含流式失败回退）对传输错误/
+    408/429/5xx 指数退避重试（max_retries=2、retry_delay_s=1.0）；4xx 不重试。
+  - **web_fetch 工具**：抓公网 http/https 文本，dsh web_fetch 同款 SSRF 防护——
+    DNS 解析后拒绝私网/环回/链路本地/保留/NAT64 地址；512KB/15s/12k 字符上限、
+    二进制嗅探拒绝；受 `agent.allow_net` 开关（默认开），归入只读工具集。
+  - **原子写入**：write_file/edit_file 走同目录临时文件 + os.replace（Windows
+    EPERM 退避一次后降级直写），防崩溃留半截文件。
+  - **慢工具线程卸载**：run_command/web_fetch/search_files 在独立守护线程执行
+    （asyncio.sleep 轮询等完成——补丁版 TestClient 的每请求独立事件循环不推进
+    run_in_executor 桥接，轮询在生产/测试两端都可靠），快工具保持内联。
+  - **search 修剪**：os.walk 修剪依赖/构建目录（替代 rglob 全量物化），不跟随
+    符号链接目录，限量行为不变。
+  - **重复调用提醒**：同工具同参数第 3 次起在回喂结果附系统提示 + repeat_warning
+    事件（防模型原地打转，dsh repeat-tool-reminder 同款）。
+  - **会话重命名**：`PATCH /agent/sessions/{sid}` + 前端会话列表 ✎ 按钮。
+  - **D10 收尾修复**：_stream_partial 每次流式调用前复位（防上次成功置位导致
+    本次失败误抛而不回退）。