modify: 流式输出

README.md

@@ -264,6 +264,93 @@ async def upload(file: UploadFile = File(...)):
 
 > **约定**：插件 `__init__.py` 中导入 `router` 实例（`from .routes import router`），网关通过 `getattr(module, "router", None)` 自动发现。
 
+### 流式端点（SSE）
+
+基于 Zenoh Query/Reply 原生"多回复"实现流式输出：Worker 的 `@rpc_method` 返回生成器时，
+框架逐块 `query.reply()` 推送（见 `utils/worker` README「流式端点」），网关以 SSE
+（`text/event-stream`）逐块转发给 HTTP 客户端。**无额外端口、无额外进程、无新依赖**；
+未声明 `stream` 的端点行为与之前完全一致。
+
+#### TOML 配置
+
+在方法节中声明 `stream = true`（示例 `config/workers/example/stream_chat.toml`）：
+
+```toml
+[POST]
+summary = "模拟 AI 流式对话（SSE，逐 token 输出）"
+auth_required = false
+stream = true
+timeout = 300.0             # 流总寿命上限（秒，zenoh query deadline 硬上限）
+stream_idle_timeout = 10.0  # 网关侧连续无数据块的最大间隔（秒）
+params = ["prompt: str", "tokens: int"]
+```
+
+| 字段 | 默认值 | 说明 |
+| --- | --- | --- |
+| `stream` | `false` | 流式端点：以 SSE（`text/event-stream`）输出 |
+| `timeout` | `3.0` | 流总寿命上限（秒）。**流式端点必须配大**（如 300s），到期后 zenoh 丢弃后续回复 |
+| `stream_idle_timeout` | `10.0` | 空闲超时（秒）：超过该间隔无新数据块则网关终止流 |
+
+> `timeout`（总寿命硬上限）与 `stream_idle_timeout`（空闲超时）是两回事，流式场景两个都要配。
+
+#### 请求与响应
+
+- 请求与普通端点一致（GET 走 query/path 参数，POST/PUT/PATCH 走 body 模型），鉴权依赖同样生效
+- 响应为 `text/event-stream`，每块一个 `data: {json}\n\n` 事件（SSE 标准分帧）
+- 响应头：`Cache-Control: no-cache`、`X-Accel-Buffering: no`（配合反代关闭缓冲）
+- OpenAPI 不声明流式端点的响应 schema（逐块 JSON dict，无法用单一模型描述）
+
+```bash
+curl -N -X POST localhost:8000/api/v1/calc/stream_chat \
+  -H 'Content-Type: application/json' -d '{"prompt":"你好","tokens":3}'
+# data: {"token":"你好·1","index":0}
+# data: {"token":"你好·2","index":1}
+# data: {"token":"你好·3","index":2}
+# data: {"done":true}
+```
+
+#### 错误语义
+
+| 场景 | 表现 |
+| --- | --- |
+| 无可用 worker（首个数据块前） | HTTP 503（与普通端点一致） |
+| Worker 中途异常 / 流式端点初始化失败 | SSE error 事件 `data: {"error":"..."}` 收尾（HTTP 200 已提交，无法再改状态码） |
+| 空闲超时 | SSE error 事件 `data: {"error":"流式空闲超时 ..."}` 收尾 |
+| 客户端断开 | 网关终止迭代，Worker 侧 reply 失败自动停流，不空转 |
+
+#### 部署注意
+
+生产环境经 nginx 反代时需关闭缓冲，否则 SSE 会被整段缓冲、失去逐块即时性：
+
+```nginx
+location /api/v1/ {
+    proxy_buffering off;
+}
+```
+
+#### 本地联调前注意
+
+流式能力在 `chongming-worker` 框架（`utils/worker/`，独立仓库）。**本地未 push 的框架改动
+不会自动生效**——venv 里安装的是 `uv sync` 从 git 源拉取的旧版副本，旧版 `@rpc_method`
+不认 `stream` 参数，会报 `TypeError: rpc_method() got an unexpected keyword argument 'stream'`
+并连锁导致契约校验失败（启动终止）。本地联调时先以可编辑方式装入 venv：
+
+```bash
+uv pip install -e utils/worker
+```
+
+正式发布仍走「开发与发布检查清单」流程（工具包 push → `uv lock --upgrade-package
+chongming-worker` → `uv sync`，可编辑安装会被锁文件版本替换）。
+
+#### 测试
+
+```
+uv run python test_stream_worker.py      # Worker 框架流式回复单测
+uv run python test_stream_gateway.py     # 网关 call_stream 单测
+uv run python test_stream_e2e_zenoh.py   # 真实 Zenoh 会话端到端（peer 模式，无需 router）
+uv run python test_stream_route.py       # 路由层 SSE 输出与兼容性回归（非流式端点不变）
+```
+
 ---
 
 ## 进程插件与混合部署
@@ -450,6 +537,9 @@ python publisher.py example add '{"a":3,"b":5}'  # 调用 add
 5. 重启服务
 ```
 
+流式端点（SSE）在此基础上额外两步：TOML 方法节声明 `stream = true` 并配大 `timeout`；
+`@rpc_method(..., stream=True)` 函数返回生成器（yield 逐块），详见上文「流式端点（SSE）」。
+
 ### 常用命令
 
 ```bash
@@ -566,6 +656,8 @@ uv pip install -e utils/<name>            # 安装/更新工具包子包
 | `internal`           | `<操作>.toml`         | `true` 则仅限内部 RPC，不注册 HTTP 路由 |
 | `cacheable`          | `<操作>.toml`         | 端点是否可缓存                          |
 | `summary`            | `<操作>.toml`         | 端点描述（用于 OpenAPI / 日志）         |
+| `stream`             | `<操作>.toml`         | `true` 则流式输出（SSE），需同时配大 `timeout` |
+| `stream_idle_timeout`| `<操作>.toml`         | 流式空闲超时（秒，默认 10），超时无新数据块则终止流 |
 
 ---
 

src/chongming/app/core/route_generator.py

@@ -5,15 +5,17 @@
 为每个端点生成带有正确 Pydantic 类型注解的处理函数，确保 OpenAPI 文档
 正确反映参数类型、响应结构，并注册到 components/schemas。
 """
-from typing import Any, Dict, List, Optional
+from typing import Any, AsyncGenerator, Dict, List, Optional
 from inspect import Parameter, Signature
 
+import orjson
 from fastapi import FastAPI, HTTPException, APIRouter, Query, Path as FastAPIPath, Request, Depends
+from fastapi.responses import StreamingResponse
 from pydantic import create_model, Field, BaseModel
 
 from chongming_worker.route_config import WORKER_CONFIG_DIR, load_worker_routes_from_dir
 
-from .worker_manager import WorkerManager
+from .worker_manager import WorkerManager, StreamIdleTimeoutError
 from .logger import get_logger
 from .auth import store_user_to_request
 
@@ -92,6 +94,10 @@ class RouteConfig:
         self.cacheable: bool = data.get("cacheable", False)
         self.auth_required: bool = data.get("auth_required", True)
         self.internal: bool = data.get("internal", False)
+        # 流式端点：以 SSE（text/event-stream）逐块输出
+        self.stream: bool = data.get("stream", False)
+        # 流式空闲超时（秒）：连续未收到数据块的最大间隔（timeout 为流总寿命上限）
+        self.stream_idle_timeout: float = data.get("stream_idle_timeout", 10.0)
 
     def parse_params(self) -> Dict[str, str]:
         """解析 params 列表为 {name: type} 字典"""
@@ -353,6 +359,116 @@ def _make_query_endpoint(worker_manager: WorkerManager, rc: RouteConfig, worker_
     return endpoint
 
 
+# 流式端点响应头：禁止缓存；通知反向代理（nginx）关闭缓冲保证 SSE 即时性
+_STREAM_HEADERS = {
+    "Cache-Control": "no-cache",
+    "X-Accel-Buffering": "no",
+}
+
+
+def _make_stream_endpoint(
+    worker_manager: WorkerManager,
+    rc: RouteConfig,
+    worker_type: str,
+    path_params: List[str] = (),
+    query_params: Optional[Dict[str, str]] = None,
+    RequestModel: Optional[type[BaseModel]] = None,
+):
+    """
+    创建流式端点（TOML 中 stream = true）：以 SSE（text/event-stream）逐块输出。
+
+    请求参数形态与普通端点一致（GET 走 query/path 参数，POST/PUT/PATCH 走 body 模型）。
+    错误语义:
+      - 初始错误（无可用 worker 等）-> HTTP 503
+      - 流中错误（Worker 返回 {"error": ...} 收尾块 / 空闲超时）-> SSE error 事件
+        （此时 HTTP 200 已提交，无法改状态码）
+    不校验响应模型：流式输出是逐块 JSON dict。
+    """
+    path = rc.path
+    subject = rc.subject
+    http_method = rc.method
+    timeout = rc.timeout
+    idle_timeout = rc.stream_idle_timeout
+    param_names = list((query_params or {}).keys())
+
+    def build_payload(request: Request, body=None, kwargs=None) -> Dict[str, Any]:
+        """构造信封协议 payload（与普通端点一致）"""
+        meta = {"method": http_method}
+        user_info = getattr(request.state, "user", None)
+        if user_info:
+            meta["user_info"] = user_info
+        if body is not None:
+            data = body.model_dump()
+        else:
+            data = {k: kwargs[k] for k in param_names}
+        return {"meta": meta, "data": data}
+
+    def _sse_frame(data: Dict[str, Any]) -> str:
+        return f"data: {orjson.dumps(data).decode('utf-8')}\n\n"
+
+    async def _sse_body(gen) -> AsyncGenerator[str, None]:
+        """SSE 分帧；流中异常转为 SSE error 事件（HTTP 200 已提交）"""
+        try:
+            async for chunk in gen:
+                yield f"data: {chunk.decode('utf-8')}\n\n"
+        except StreamIdleTimeoutError as e:
+            logger.warning("路由 %s 流式空闲超时: %s", path, e)
+            yield _sse_frame({"error": str(e)})
+        except Exception as e:
+            logger.error("路由 %s 流式中断: %s", path, e)
+            yield _sse_frame({"error": "内部服务器错误"})
+
+    async def _start_stream(payload: Dict[str, Any]) -> StreamingResponse:
+        try:
+            gen = await worker_manager.call_stream(
+                worker_type=worker_type,
+                subject=subject,
+                payload=payload,
+                timeout=timeout,
+                idle_timeout=idle_timeout,
+            )
+        except RuntimeError as e:
+            logger.warning("路由 %s [%s] 流式调用失败: %s", path, worker_type, e)
+            raise HTTPException(status_code=503, detail=str(e))
+        return StreamingResponse(
+            _sse_body(gen),
+            media_type="text/event-stream",
+            headers=_STREAM_HEADERS,
+        )
+
+    if RequestModel is not None:
+        async def endpoint(request: Request, body: RequestModel) -> StreamingResponse:  # type: ignore
+            return await _start_stream(build_payload(request, body=body))
+        return endpoint
+
+    # GET/DELETE 形态
+    if not param_names:
+        async def _simple_endpoint(request: Request) -> StreamingResponse:
+            return await _start_stream(build_payload(request, kwargs=None))
+        return _simple_endpoint
+
+    async def endpoint(request: Request, **kwargs: Any) -> StreamingResponse:
+        return await _start_stream(build_payload(request, kwargs=kwargs))
+
+    # 附加类型注解与签名（与 _make_query_endpoint 一致），保证 OpenAPI 参数文档正确
+    params: List[Parameter] = [
+        Parameter("request", Parameter.POSITIONAL_OR_KEYWORD, annotation=Request)
+    ]
+    annotations: Dict[str, Any] = {}
+    for name, type_str in (query_params or {}).items():
+        py_type = _parse_python_type(type_str)
+        annotations[name] = py_type
+        if name in path_params:
+            params.append(Parameter(name, Parameter.KEYWORD_ONLY, default=FastAPIPath(...), annotation=py_type))
+        else:
+            params.append(Parameter(name, Parameter.KEYWORD_ONLY, default=Query(...), annotation=py_type))
+
+    endpoint.__annotations__ = annotations
+    endpoint.__signature__ = Signature(params, return_annotation=StreamingResponse)  # type: ignore
+
+    return endpoint
+
+
 def _register_single_route(
     router: APIRouter,
     worker_manager: WorkerManager,
@@ -391,16 +507,41 @@ def _register_single_route(
     request_model_name = f"{worker_type}_{clean_path}_{method_tag}_Request"
 
     # 生成响应模型
-    ResponseModel = generate_response_model(
+    if rc.stream:
-        rc.response_model, response_model_name
+        # 流式端点：逐块 SSE 输出，不校验响应模型（OpenAPI 不声明响应 schema）
-    )
+        ResponseModel = None
-
+        if rc.method in ("POST", "PUT", "PATCH"):
-    if rc.method in ("POST", "PUT", "PATCH"):
+            # body 形态：RequestModel 传给端点做请求体校验
+            RequestModel = generate_request_model(
+                param_spec, request_model_name
+            )
+            endpoint = _make_stream_endpoint(
+                worker_manager, rc, worker_type, path_params, query_params, RequestModel
+            )
+        else:
+            # GET/DELETE 形态：query/path 参数走签名注解；
+            # RequestModel 仅注册到 extra_schemas 供 OpenAPI 展示（与普通 GET 一致）
+            if param_spec:
+                RequestModel = generate_request_model(
+                    param_spec, request_model_name
+                )
+                if extra_schemas is not None and request_model_name not in extra_schemas:
+                    extra_schemas[request_model_name] = RequestModel
+            endpoint = _make_stream_endpoint(
+                worker_manager, rc, worker_type, path_params, query_params, None
+            )
+    elif rc.method in ("POST", "PUT", "PATCH"):
+        ResponseModel = generate_response_model(
+            rc.response_model, response_model_name
+        )
         RequestModel = generate_request_model(
             param_spec, request_model_name
         )
         endpoint = _make_body_endpoint(worker_manager, rc, worker_type, RequestModel)
     else:
+        ResponseModel = generate_response_model(
+            rc.response_model, response_model_name
+        )
         # 对 GET 端点也生成 Request 模型并注册到 extra_schemas
         if param_spec:
             RequestModel = generate_request_model(

src/chongming/app/core/worker_manager.py

@@ -2,7 +2,7 @@ import asyncio
 import random
 import json
 import orjson
-from typing import Any, Dict, List, Optional
+from typing import Any, AsyncGenerator, Dict, List, Optional
 import zenoh
 from chongming_cache import Cache
 from .logger import get_logger
@@ -12,6 +12,22 @@ logger = get_logger("worker_manager")
 _SENTINEL = object()  # 哨兵值，用于标记"No reply received"
 
 
+class StreamIdleTimeoutError(TimeoutError):
+    """流式调用空闲超时：在 idle_timeout 秒内未收到任何数据块"""
+
+
+def _next_reply(iterator):
+    """线程安全地获取迭代器的下一个元素。
+
+    用 for 循环 + 哨兵代替直接 next()，避免 StopIteration 在
+    asyncio.to_thread 中传播的问题（与 call() 的 _get_first 同模式）。
+    迭代耗尽时返回 _SENTINEL。
+    """
+    for item in iterator:
+        return item
+    return _SENTINEL
+
+
 class WorkerManager:
     """
     统一 Worker 管理器
@@ -130,6 +146,114 @@ class WorkerManager:
             return False
         return True
 
+    async def _raise_no_worker(self, worker_type: str) -> None:
+        """
+        无可用 Worker 时的统一诊断：列出当前已知的所有 worker 类型并抛 RuntimeError。
+
+        供 call() / call_stream() 共用，保证两类调用错误信息一致。
+        """
+        async with self._lock:
+            all_known = list(self._workers_cache.keys())
+        local_known = list(self._local_workers.keys())
+        all_types = sorted(set(all_known + local_known))
+        msg = (
+            f"类型 '{worker_type}' 没有可用 Worker。"
+            f"当前已知的 Worker 类型: {all_types if all_types else '(无)'}。"
+            f"请检查: 1) config/workers/config.toml 是否配置了该类型 "
+            f"2) 插件初始化是否成功（查看启动日志中的 '加载 Worker 插件失败' 错误）"
+            f"3) Worker 进程是否正常运行"
+        )
+        logger.warning(msg)
+        raise RuntimeError(msg)
+
+    async def call_stream(
+        self,
+        worker_type: str,
+        subject: str,
+        payload: Dict[str, Any],
+        timeout: float = 300.0,
+        idle_timeout: float = 10.0,
+    ) -> AsyncGenerator[bytes, None]:
+        """
+        流式调用：消费 Worker 的多回复流，逐块产出 JSON 字节。
+
+        与 call() 的区别:
+          - 不合并回复（ConsolidationMode.NONE），逐块 yield，实现流式传输
+          - 不重试（流一旦开始输出无法安全重放，中途失败只能重建）
+          - 超时模型: timeout = 流总寿命上限（zenoh query deadline，硬上限，
+            流式端点须配大如 300s）；idle_timeout = 连续无数据块的最大间隔
+          - 错误约定: 块内含 "error" 键（Worker 收尾错误块）或 reply.err
+            （zenoh 层错误）均为流的终止信号，转发后结束
+
+        Args:
+            worker_type: Worker 类型标识（如 "example"）
+            subject: 调用的主题（如 "stream_chat"）
+            payload: 请求参数（信封格式，由路由层构造）
+            timeout: 流总寿命上限（秒），需大于业务最长生成时长
+            idle_timeout: 空闲超时（秒），超时抛 StreamIdleTimeoutError
+
+        Yields:
+            bytes: 每个回复块的 JSON 字节
+
+        Raises:
+            RuntimeError: 无可用 worker
+            StreamIdleTimeoutError: 空闲超时
+        """
+        # 急切解析 worker：无可用时立即抛错，让路由层映射 HTTP 503
+        # （异步生成器函数体在首次迭代才执行，故这里用普通 async 函数返回内部生成器）
+        worker_expr = await self.get_worker(worker_type)
+        if not worker_expr:
+            await self._raise_no_worker(worker_type)
+
+        full_key = f"{worker_expr}/{subject}"
+        reply_iter = self.session.get(
+            full_key,
+            payload=orjson.dumps(payload),
+            consolidation=zenoh.ConsolidationMode.NONE,
+            timeout=timeout,
+        )
+
+        async def _stream():
+            # 逐块消费；zenoh reply 迭代器是同步阻塞的，必须放线程执行，
+            # 避免阻塞事件循环（与 call() 的 _get_first 同模式）
+            while True:
+                try:
+                    reply = await asyncio.wait_for(
+                        asyncio.to_thread(_next_reply, reply_iter),
+                        timeout=idle_timeout,
+                    )
+                except asyncio.TimeoutError:
+                    raise StreamIdleTimeoutError(
+                        f"Worker {worker_expr} 流式空闲超时 ({idle_timeout}s 无数据)"
+                    ) from None
+
+                if reply is _SENTINEL:
+                    break
+
+                if reply.ok:  # type: ignore
+                    data = bytes(reply.ok.payload) if reply.ok.payload else b""  # type: ignore
+                    if not data:
+                        continue
+                    decoded = orjson.loads(data)
+                    if isinstance(decoded, dict) and decoded.get("error"):
+                        # Worker 错误收尾块：转发后终止流
+                        yield data
+                        return
+                    yield data
+                else:
+                    # zenoh 层错误回复（如 queryable 异常）：转发后终止流
+                    error_payload = reply.err.payload  # type: ignore
+                    error_msg = str(error_payload) if error_payload else "unknown error"
+                    logger.warning(
+                        f"Worker {worker_expr} 流式返回错误: {error_msg}"
+                    )
+                    yield orjson.dumps(
+                        {"error": f"Worker {worker_expr} 返回错误: {error_msg}"}
+                    )
+                    return
+
+        return _stream()
+
     async def call(
         self,
         worker_type: str,
@@ -166,20 +290,7 @@ class WorkerManager:
         # 2. 获取可用 worker
         worker_expr = await self.get_worker(worker_type)
         if not worker_expr:
-            # 给出诊断信息：列出当前已知的所有 worker 类型
+            await self._raise_no_worker(worker_type)
-            async with self._lock:
-                all_known = list(self._workers_cache.keys())
-            local_known = list(self._local_workers.keys())
-            all_types = sorted(set(all_known + local_known))
-            msg = (
-                f"类型 '{worker_type}' 没有可用 Worker。"
-                f"当前已知的 Worker 类型: {all_types if all_types else '(无)'}。"
-                f"请检查: 1) config/workers/config.toml 是否配置了该类型 "
-                f"2) 插件初始化是否成功（查看启动日志中的 '加载 Worker 插件失败' 错误）"
-                f"3) Worker 进程是否正常运行"
-            )
-            logger.warning(msg)
-            raise RuntimeError(msg)
 
         full_key = f"{worker_expr}/{subject}"
         payload_bytes = orjson.dumps(payload)

test_stream_e2e_zenoh.py

@@ -0,0 +1,180 @@
+"""
+真实 Zenoh 会话下的流式端到端测试（peer 模式，无需 router）
+
+单进程内起两个 Zenoh 会话（listen + connect），跑通完整生产链路:
+  @rpc_method(stream=True) 注册 -> create_worker 声明 Queryable
+  -> WorkerManager.call_stream 消费多回复 -> 逐块到达
+
+验证:
+  1. 流式方法：3+1 块按序到达（真实 Zenoh 多回复 + ConsolidationMode.NONE）
+  2. 流式中途异常：{"error": ...} 收尾块转发后终止
+  3. 非流式方法：仍是单回复（兼容性回归）
+  4. generate_route_configs 输出 stream 标记、非流式不含
+  5. decorators 对生成器函数的调用不消费生成器
+
+运行: uv run python test_stream_e2e_zenoh.py
+"""
+import asyncio
+import importlib.util
+import logging
+import sys
+import types
+from pathlib import Path
+
+import orjson
+import zenoh
+
+REPO_ROOT = Path(__file__).resolve().parent
+sys.path.insert(0, str(REPO_ROOT / "utils" / "worker" / "src"))
+sys.path.insert(0, str(REPO_ROOT / "src"))
+
+# ---- 网关依赖隔离（同 test_stream_gateway）：桩掉 chongming 包链与 chongming_cache ----
+_pkg = types.ModuleType("chongming")
+_pkg.__path__ = []
+_app = types.ModuleType("chongming.app")
+_app.__path__ = []
+_core = types.ModuleType("chongming.app.core")
+_core.__path__ = []
+_logger_stub = types.ModuleType("chongming.app.core.logger")
+_logger_stub.get_logger = lambda name: logging.getLogger(name)
+_cache_stub = types.ModuleType("chongming_cache")
+_cache_stub.Cache = object
+for mod in (_pkg, _app, _core, _logger_stub, _cache_stub):
+    sys.modules[mod.__name__] = mod
+
+_wm_path = REPO_ROOT / "src" / "chongming" / "app" / "core" / "worker_manager.py"
+_spec = importlib.util.spec_from_file_location(
+    "chongming.app.core.worker_manager", _wm_path
+)
+_wm_mod = importlib.util.module_from_spec(_spec)
+sys.modules["chongming.app.core.worker_manager"] = _wm_mod
+_spec.loader.exec_module(_wm_mod)  # type: ignore[union-attr]
+
+WorkerManager = _wm_mod.WorkerManager
+StreamIdleTimeoutError = _wm_mod.StreamIdleTimeoutError
+
+from chongming_worker import clear_registry, rpc_method  # noqa: E402
+from chongming_worker.decorators import generate_route_configs  # noqa: E402
+from chongming_worker.runtime import create_worker  # noqa: E402
+
+failures = []
+
+
+def check(name, cond, detail=""):
+    status = "PASS" if cond else "FAIL"
+    print(f"[{status}] {name}" + (f" — {detail}" if detail else ""))
+    if not cond:
+        failures.append(name)
+
+
+LISTEN_PORT = 7447
+LISTEN = f"tcp/127.0.0.1:{LISTEN_PORT}"
+
+
+def open_session(listen=None):
+    """peer 模式会话：worker 侧 listen，网关侧 connect（显式端点，禁用组播）"""
+    c = zenoh.Config()
+    c.insert_json5("scouting/multicast/enabled", "false")
+    if listen:
+        c.insert_json5("listen/endpoints", f'["{listen}"]')
+    else:
+        c.insert_json5("connect/endpoints", f'["{LISTEN}"]')
+    return zenoh.open(c)
+
+
+async def run_checks():
+    clear_registry()
+
+    # ---- 流式端点（返回异步生成器）----
+    @rpc_method(subject="streamtest.echo", method="POST", stream=True)
+    async def echo_stream(prompt: str = "hi", tokens: int = 3):
+        for i in range(tokens):
+            await asyncio.sleep(0.01)
+            yield {"token": f"{prompt}-{i}"}
+        yield {"done": True}
+
+    # ---- 流式端点：中途异常（框架应发 {"error": ...} 收尾块）----
+    @rpc_method(subject="streamtest.fail", method="POST", stream=True)
+    async def fail_stream():
+        yield {"token": "a"}
+        raise ValueError("mid-boom")
+
+    # ---- 非流式端点（兼容性对照）----
+    @rpc_method(subject="streamtest.add", method="GET")
+    async def add(a: float, b: float):
+        return a + b
+
+    # 1. 配置生成：流式标记
+    configs = generate_route_configs("streamtest")
+    stream_cfg = next(c for c in configs if c["subject"] == "streamtest.echo")
+    check("generate_route_configs 输出 stream 标记", stream_cfg.get("stream") is True)
+    add_cfg = next(c for c in configs if c["subject"] == "streamtest.add")
+    check("非流式配置不含 stream 标记", "stream" not in add_cfg)
+
+    # 2. 真实 Zenoh 会话（peer 模式，无 router）
+    session_worker = open_session(listen=LISTEN)
+    session_gw = open_session()
+
+    # 3. 启动真实 Worker（create_worker 声明 Queryable）
+    worker_task = asyncio.create_task(
+        create_worker(session_worker, "streamtest", "w1")
+    )
+    await asyncio.sleep(0.5)  # 等待 queryable 在 peer 间可见
+
+    try:
+        # 4. 网关 WorkerManager.call_stream 真实消费流式端点
+        wm = WorkerManager(session_gw)
+        wm.register_worker("streamtest", "w1")
+
+        async def _consume(subject, data, idle_timeout=2.0):
+            gen = await wm.call_stream(
+                "streamtest", subject,
+                {"meta": {"method": "POST"}, "data": data},
+                timeout=10.0, idle_timeout=idle_timeout,
+            )
+            return [orjson.loads(b) async for b in gen]
+
+        chunks = await _consume("streamtest.echo", {"prompt": "hi", "tokens": 3})
+        check(
+            "流式 3+1 块按序到达（真实多回复）",
+            chunks == [
+                {"token": "hi-0"}, {"token": "hi-1"}, {"token": "hi-2"}, {"done": True},
+            ],
+            f"chunks={chunks}",
+        )
+
+        # 5. 流式中途异常：错误块收尾
+        chunks = await _consume("streamtest.fail", {})
+        check(
+            "流式中途异常 error 块收尾",
+            chunks == [{"token": "a"}, {"error": "mid-boom"}],
+            f"chunks={chunks}",
+        )
+
+        # 6. 非流式兼容：call() 仍单回复
+        result = await wm.call(
+            "streamtest", "streamtest.add",
+            {"meta": {"method": "GET"}, "data": {"a": 2, "b": 3}},
+            timeout=10.0,
+        )
+        check("非流式 call() 正常单回复", result == 5.0, f"result={result}")
+
+        # 7. 负载均衡路径兼容：liveliness 发现的 worker 也能流式（同 call）
+        worker_expr = await wm.get_worker("streamtest")
+        check("get_worker 仍可解析本地 worker", worker_expr is not None)
+
+    finally:
+        worker_task.cancel()
+        await asyncio.gather(worker_task, return_exceptions=True)
+        session_gw.close()
+        session_worker.close()
+
+
+def run():
+    asyncio.run(run_checks())
+    print(f"\n结果: {len(failures)} 个失败")
+    return 1 if failures else 0
+
+
+if __name__ == "__main__":
+    sys.exit(run())

test_stream_gateway.py

@@ -0,0 +1,246 @@
+"""
+网关 call_stream 单测（依赖隔离：桩掉 chongming 包链与 chongming_cache）
+
+直接加载 src/chongming/app/core/worker_manager.py 模块（避开 chongming.app
+整链导入与 config.toml 依赖），验证:
+  1. 多块顺序产出（ConsolidationMode.NONE 逐块消费）
+  2. Worker 错误收尾块 {"error": ...}：转发后终止流
+  3. zenoh 错误回复（reply.err）：转发错误块后终止流
+  4. 空闲超时：抛 StreamIdleTimeoutError
+  5. 无可用 worker：抛 RuntimeError
+  6. 兼容性回归：call()（非流式路径）仍只取第一个回复
+
+运行: uv run python test_stream_gateway.py
+"""
+import asyncio
+import importlib.util
+import logging
+import sys
+import time
+import types
+from pathlib import Path
+from types import SimpleNamespace
+
+import orjson
+import zenoh
+
+REPO_ROOT = Path(__file__).resolve().parent
+
+# ---- 依赖隔离：桩掉网关包链（chongming.app 顶层导入 fastapi/uvicorn/config）----
+_pkg = types.ModuleType("chongming")
+_pkg.__path__ = []
+_app = types.ModuleType("chongming.app")
+_app.__path__ = []
+_core = types.ModuleType("chongming.app.core")
+_core.__path__ = []
+_logger_stub = types.ModuleType("chongming.app.core.logger")
+_logger_stub.get_logger = lambda name: logging.getLogger(name)
+_cache_stub = types.ModuleType("chongming_cache")
+_cache_stub.Cache = object  # WorkerManager 仅作类型标注使用
+for mod in (_pkg, _app, _core, _logger_stub, _cache_stub):
+    sys.modules[mod.__name__] = mod
+
+_wm_path = REPO_ROOT / "src" / "chongming" / "app" / "core" / "worker_manager.py"
+_spec = importlib.util.spec_from_file_location(
+    "chongming.app.core.worker_manager", _wm_path
+)
+_wm_mod = importlib.util.module_from_spec(_spec)
+sys.modules["chongming.app.core.worker_manager"] = _wm_mod
+_spec.loader.exec_module(_wm_mod)  # type: ignore[union-attr]
+
+WorkerManager = _wm_mod.WorkerManager
+StreamIdleTimeoutError = _wm_mod.StreamIdleTimeoutError
+
+failures = []
+
+
+def check(name, cond, detail=""):
+    status = "PASS" if cond else "FAIL"
+    print(f"[{status}] {name}" + (f" — {detail}" if detail else ""))
+    if not cond:
+        failures.append(name)
+
+
+class FakeReply:
+    """模拟 zenoh.Reply：ok / err 二选一"""
+
+    def __init__(self, payload=None, error=None):
+        if error is None:
+            self.ok = SimpleNamespace(payload=payload)
+            self.err = None
+        else:
+            self.ok = None
+            self.err = SimpleNamespace(payload=error)
+
+
+class FakeSession:
+    """模拟 zenoh.Session.get()：返回 reply 迭代器（可迭代对象）"""
+
+    def __init__(self, reply_source):
+        self._reply_source = reply_source
+        self.get_calls = []
+
+    def get(self, key_expr, payload, consolidation=None, timeout=None):
+        self.get_calls.append((str(key_expr), payload, consolidation, timeout))
+        return iter(self._reply_source)
+
+
+def make_manager(replies, worker_id="worker-0"):
+    wm = WorkerManager(FakeSession(replies))
+    wm.register_worker("example", worker_id)
+    return wm
+
+
+def test_idle_timeout():
+    # 模拟阻塞式 reply 迭代器：每个 __next__ 阻塞 0.3s（首个块 0.3s 后才到达），
+    # 而空闲超时仅 0.05s -> 应抛 StreamIdleTimeoutError
+    class BlockingReplyIterator:
+        def __init__(self):
+            self._done = False
+
+        def __iter__(self):
+            return self
+
+        def __next__(self):
+            time.sleep(0.3)
+            if self._done:
+                raise StopIteration
+            self._done = True
+            return FakeReply(payload=orjson.dumps({"token": "slow"}))
+
+    wm = WorkerManager(FakeSession(BlockingReplyIterator()))
+
+
+def collect_stream(wm, idle_timeout=1.0):
+    """消费 call_stream 全部块并返回解码后的列表"""
+
+    async def _run():
+        gen = await wm.call_stream(
+            "example", "stream_chat", {"meta": {"method": "POST"}, "data": {}},
+            timeout=5.0, idle_timeout=idle_timeout,
+        )
+        return [orjson.loads(b) async for b in gen]
+
+    return asyncio.run(_run())
+
+
+def test_multiple_chunks():
+    replies = [
+        FakeReply(payload=orjson.dumps({"token": "a"})),
+        FakeReply(payload=orjson.dumps({"token": "b"})),
+    ]
+    wm = make_manager(replies)
+    chunks = collect_stream(wm)
+    check("多块顺序产出", chunks == [{"token": "a"}, {"token": "b"}])
+    check(
+        "使用 ConsolidationMode.NONE",
+        wm.session.get_calls[0][2] is zenoh.ConsolidationMode.NONE,
+    )
+    check("key_expr 正确", wm.session.get_calls[0][0] == "worker/example/worker-0/stream_chat")
+
+
+def test_error_chunk_terminates():
+    replies = [
+        FakeReply(payload=orjson.dumps({"token": "a"})),
+        FakeReply(payload=orjson.dumps({"error": "boom"})),
+        FakeReply(payload=orjson.dumps({"token": "c"})),  # 不应被消费
+    ]
+    wm = make_manager(replies)
+    chunks = collect_stream(wm)
+    check("错误块转发后终止", chunks == [{"token": "a"}, {"error": "boom"}])
+
+
+def test_err_reply_terminates():
+    replies = [
+        FakeReply(payload=orjson.dumps({"token": "a"})),
+        FakeReply(error="oops"),
+    ]
+    wm = make_manager(replies)
+    chunks = collect_stream(wm)
+    check(
+        "reply.err 转发错误块后终止",
+        chunks == [{"token": "a"}, {"error": "Worker worker/example/worker-0 返回错误: oops"}],
+    )
+
+
+def test_idle_timeout():
+    # 模拟阻塞式 reply 迭代器：每个 __next__ 阻塞 0.3s（首个块 0.3s 后才到达），
+    # 而空闲超时仅 0.05s -> 应抛 StreamIdleTimeoutError
+    class BlockingReplyIterator:
+        def __init__(self):
+            self._done = False
+
+        def __iter__(self):
+            return self
+
+        def __next__(self):
+            time.sleep(0.3)
+            if self._done:
+                raise StopIteration
+            self._done = True
+            return FakeReply(payload=orjson.dumps({"token": "slow"}))
+
+    wm = WorkerManager(FakeSession(BlockingReplyIterator()))
+    wm.register_worker("example", "worker-0")
+
+    async def _run():
+        gen = await wm.call_stream(
+            "example", "stream_chat", {}, timeout=5.0, idle_timeout=0.05
+        )
+        async for _ in gen:
+            pass
+
+    try:
+        asyncio.run(_run())
+        check("空闲超时抛 StreamIdleTimeoutError", False)
+    except StreamIdleTimeoutError as e:
+        check("空闲超时抛 StreamIdleTimeoutError", True, str(e))
+
+
+def test_no_worker():
+    wm = WorkerManager(FakeSession([]))  # 未注册任何 worker
+
+    async def _run():
+        gen = await wm.call_stream("missing", "x", {})
+        async for _ in gen:
+            pass
+
+    try:
+        asyncio.run(_run())
+        check("无 worker 抛 RuntimeError", False)
+    except RuntimeError as e:
+        check("无 worker 抛 RuntimeError", True, str(e)[:30])
+
+
+def test_call_compat_first_reply_only():
+    """兼容性回归：非流式 call() 仍只取第一个回复，行为不变"""
+    replies = [
+        FakeReply(payload=orjson.dumps({"result": 1})),
+        FakeReply(payload=orjson.dumps({"result": 2})),
+    ]
+    wm = make_manager(replies)
+
+    async def _run():
+        return await wm.call(
+            "example", "stream_chat", {"meta": {"method": "POST"}, "data": {}},
+            timeout=5.0,
+        )
+
+    result = asyncio.run(_run())
+    check("call() 仍只取第一个回复（非流式兼容）", result == {"result": 1})
+
+
+def run():
+    test_multiple_chunks()
+    test_error_chunk_terminates()
+    test_err_reply_terminates()
+    test_idle_timeout()
+    test_no_worker()
+    test_call_compat_first_reply_only()
+
+    print(f"\n结果: {len(failures)} 个失败")
+    return 1 if failures else 0
+
+
+if __name__ == "__main__":
+    sys.exit(run())

test_stream_route.py

@@ -0,0 +1,221 @@
+"""
+网关路由层流式端点单测（依赖隔离：桩掉 chongming 包链、auth 与 chongming_cache）
+
+直接加载 src/chongming/app/core/route_generator.py，用 FastAPI TestClient 验证:
+  1. 流式 POST 端点：SSE 输出（media_type / 逐块 data: 帧 / 响应头）
+  2. 流式 GET 端点：query 参数正确透传到 payload
+  3. 初始错误（无可用 worker）-> HTTP 503
+  4. 流中空闲超时 -> SSE error 事件（HTTP 200 已提交）
+  5. 兼容性回归：非流式端点输出与改动前一致（JSON 响应）
+  6. 非流式端点仍走原 call() 逻辑（不误入流式分支）
+
+运行: uv run python test_stream_route.py
+"""
+import importlib.util
+import logging
+import sys
+import types
+from pathlib import Path
+
+import orjson
+from fastapi import FastAPI
+from fastapi.testclient import TestClient
+
+REPO_ROOT = Path(__file__).resolve().parent
+sys.path.insert(0, str(REPO_ROOT / "src"))
+sys.path.insert(0, str(REPO_ROOT / "utils" / "worker" / "src"))
+
+# ---- 依赖隔离：桩掉 chongming 包链 / auth / chongming_cache ----
+_pkg = types.ModuleType("chongming")
+_pkg.__path__ = []
+_app = types.ModuleType("chongming.app")
+_app.__path__ = []
+_core = types.ModuleType("chongming.app.core")
+_core.__path__ = []
+_logger_stub = types.ModuleType("chongming.app.core.logger")
+_logger_stub.get_logger = lambda name: logging.getLogger(name)
+_auth_stub = types.ModuleType("chongming.app.core.auth")
+_auth_stub.store_user_to_request = lambda x: x  # 仅用于 Depends，桩掉鉴权
+_cache_stub = types.ModuleType("chongming_cache")
+_cache_stub.Cache = object
+for mod in (_pkg, _app, _core, _logger_stub, _auth_stub, _cache_stub):
+    sys.modules[mod.__name__] = mod
+
+# 加载真实 worker_manager（route_generator 依赖其 StreamIdleTimeoutError）
+_wm_path = REPO_ROOT / "src" / "chongming" / "app" / "core" / "worker_manager.py"
+_wm_spec = importlib.util.spec_from_file_location(
+    "chongming.app.core.worker_manager", _wm_path
+)
+_wm_mod = importlib.util.module_from_spec(_wm_spec)
+sys.modules["chongming.app.core.worker_manager"] = _wm_mod
+_wm_spec.loader.exec_module(_wm_mod)  # type: ignore[union-attr]
+
+# 加载真实 route_generator
+_rg_path = REPO_ROOT / "src" / "chongming" / "app" / "core" / "route_generator.py"
+_rg_spec = importlib.util.spec_from_file_location(
+    "chongming.app.core.route_generator", _rg_path
+)
+_rg_mod = importlib.util.module_from_spec(_rg_spec)
+sys.modules["chongming.app.core.route_generator"] = _rg_mod
+_rg_spec.loader.exec_module(_rg_mod)  # type: ignore[union-attr]
+
+register_route_group = _rg_mod.register_route_group
+StreamIdleTimeoutError = _wm_mod.StreamIdleTimeoutError
+
+failures = []
+
+
+def check(name, cond, detail=""):
+    status = "PASS" if cond else "FAIL"
+    print(f"[{status}] {name}" + (f" — {detail}" if detail else ""))
+    if not cond:
+        failures.append(name)
+
+
+class FakeWorkerManager:
+    """模拟 WorkerManager：call() 同步返回；call_stream() 逐块产出"""
+
+    def __init__(self, chunks=None, stream_error=None):
+        self.chunks = chunks if chunks is not None else [{"token": "a"}, {"token": "b"}, {"done": True}]
+        self.stream_error = stream_error  # "no_worker" | "idle" | None
+        self.call_payloads = []
+        self.stream_payloads = []
+
+    async def call(self, worker_type, subject, payload, timeout=3.0, retries=1, cacheable=False):
+        self.call_payloads.append((worker_type, subject, payload))
+        data = payload["data"]
+        return {"result": data.get("a", 0) + data.get("b", 0)}
+
+    async def call_stream(self, worker_type, subject, payload, timeout=300.0, idle_timeout=10.0):
+        if self.stream_error == "no_worker":
+            raise RuntimeError(f"类型 '{worker_type}' 没有可用 Worker。")
+        self.stream_payloads.append((worker_type, subject, payload))
+
+        async def _gen():
+            if self.stream_error == "idle":
+                yield orjson.dumps({"token": "a"})
+                raise StreamIdleTimeoutError("流式空闲超时 (0.1s 无数据)")
+            for c in self.chunks:
+                yield orjson.dumps(c)
+
+        return _gen()
+
+
+def build_app(fwm):
+    app = FastAPI()
+    routes = [
+        # 流式 POST（body 参数）
+        {
+            "subject": "streamtest.chat", "path": "/stream/chat", "method": "POST",
+            "params": ["prompt: str", "tokens: int"], "summary": "sse chat",
+            "stream": True, "timeout": 300.0, "stream_idle_timeout": 1.0,
+            "auth_required": False,
+        },
+        # 流式 GET（query 参数）
+        {
+            "subject": "streamtest.progress", "path": "/stream/progress", "method": "GET",
+            "params": ["job_id: str", "interval: float"], "summary": "sse progress",
+            "stream": True, "timeout": 60.0, "auth_required": False,
+        },
+        # 非流式对照（兼容性回归）
+        {
+            "subject": "streamtest.add", "path": "/calc/add", "method": "GET",
+            "params": ["a: float", "b: float"], "summary": "add",
+            "timeout": 3.0, "auth_required": False,
+        },
+        {
+            "subject": "streamtest.echo", "path": "/calc/echo", "method": "POST",
+            "params": ["msg: str"], "summary": "echo",
+            "timeout": 3.0, "auth_required": False,
+        },
+    ]
+    register_route_group(app, fwm, "streamtest", routes, prefix="/api/v1")
+    return TestClient(app)
+
+
+def test_stream_post_sse():
+    fwm = FakeWorkerManager()
+    client = build_app(fwm)
+    r = client.post("/api/v1/stream/chat", json={"prompt": "hi", "tokens": 3})
+    check("流式 POST 状态码 200", r.status_code == 200, str(r.status_code))
+    check(
+        "SSE media_type",
+        r.headers["content-type"].startswith("text/event-stream"),
+        r.headers.get("content-type", ""),
+    )
+    check(
+        "SSE 逐块 data: 帧",
+        r.text
+        == 'data: {"token":"a"}\n\ndata: {"token":"b"}\n\ndata: {"done":true}\n\n',
+        repr(r.text),
+    )
+    check("防缓冲响应头", r.headers.get("cache-control") == "no-cache")
+    check(
+        "body 参数透传",
+        fwm.stream_payloads[0][2]["data"] == {"prompt": "hi", "tokens": 3},
+    )
+
+
+def test_stream_get_query_params():
+    fwm = FakeWorkerManager()
+    client = build_app(fwm)
+    r = client.get("/api/v1/stream/progress?job_id=job-1&interval=0.5")
+    check("流式 GET 状态码 200", r.status_code == 200)
+    check(
+        "GET query 参数透传",
+        fwm.stream_payloads[0][2]["data"] == {"job_id": "job-1", "interval": 0.5},
+        str(fwm.stream_payloads[0][2]["data"]),
+    )
+    check("GET 流式输出 SSE", r.text.startswith("data: "), repr(r.text[:40]))
+
+
+def test_stream_no_worker_503():
+    fwm = FakeWorkerManager(stream_error="no_worker")
+    client = build_app(fwm)
+    r = client.post("/api/v1/stream/chat", json={"prompt": "hi", "tokens": 1})
+    check("初始错误（无 worker）-> 503", r.status_code == 503, str(r.status_code))
+
+
+def test_stream_idle_timeout_sse_event():
+    fwm = FakeWorkerManager(stream_error="idle")
+    client = build_app(fwm)
+    r = client.post("/api/v1/stream/chat", json={"prompt": "hi", "tokens": 1})
+    check("空闲超时保持 200（已提交）", r.status_code == 200)
+    check(
+        "空闲超时转为 SSE error 事件",
+        r.text == 'data: {"token":"a"}\n\ndata: {"error":"流式空闲超时 (0.1s 无数据)"}\n\n',
+        repr(r.text),
+    )
+
+
+def test_non_stream_compat():
+    """兼容性回归：非流式端点走原 call() 逻辑，输出不变"""
+    fwm = FakeWorkerManager()
+    client = build_app(fwm)
+
+    r = client.get("/api/v1/calc/add?a=2&b=3")
+    check("非流式 GET 仍为 JSON 响应", r.status_code == 200 and r.json() == {"result": 5.0},
+          f"status={r.status_code} body={r.text}")
+
+    r = client.post("/api/v1/calc/echo", json={"msg": "hello"})
+    check("非流式 POST 仍为 JSON 响应",
+          r.status_code == 200 and r.json() == {"result": 0.0},
+          f"status={r.status_code} body={r.text}")
+
+    check("非流式调用未进入 call_stream", len(fwm.stream_payloads) == 0)
+    check("非流式调用仍走 call()", len(fwm.call_payloads) == 2)
+
+
+def run():
+    test_stream_post_sse()
+    test_stream_get_query_params()
+    test_stream_no_worker_503()
+    test_stream_idle_timeout_sse_event()
+    test_non_stream_compat()
+
+    print(f"\n结果: {len(failures)} 个失败")
+    return 1 if failures else 0
+
+
+if __name__ == "__main__":
+    sys.exit(run())

test_stream_worker.py

@@ -0,0 +1,118 @@
+"""
+Worker 框架流式回复单测（不依赖真实 zenoh 会话）
+
+直接测 runtime.stream_replies_to_query（fake query 仅需 key_expr 与 reply）:
+  1. 异步生成器：多块顺序 reply，payload 为 orjson JSON
+  2. 同步生成器：同样逐块 reply
+  3. 生成器中途异常：{"error": ...} 收尾块后停流
+  4. reply 失败（查询已终止）：立即停流且不抛异常
+
+运行: uv run python test_stream_worker.py
+"""
+import asyncio
+import sys
+from pathlib import Path
+
+import orjson
+
+REPO_ROOT = Path(__file__).resolve().parent
+# 优先使用本地框架 checkout（即使 chongming_worker 已通过 uv 安装也以本地为准）
+sys.path.insert(0, str(REPO_ROOT / "utils" / "worker" / "src"))
+
+from chongming_worker.runtime import stream_replies_to_query  # noqa: E402
+
+failures = []
+
+
+def check(name, cond, detail=""):
+    status = "PASS" if cond else "FAIL"
+    print(f"[{status}] {name}" + (f" — {detail}" if detail else ""))
+    if not cond:
+        failures.append(name)
+
+
+class FakeQuery:
+    """仅实现 stream_replies_to_query 用到的两个接口（key_expr / reply）"""
+
+    def __init__(self, key_expr="worker/example/worker-0/example.stream_chat"):
+        self.key_expr = key_expr
+        self.replies = []
+        self.fail_reply = False
+
+    def reply(self, key_expr, payload):
+        if self.fail_reply:
+            raise RuntimeError("query terminated")
+        self.replies.append((key_expr, payload))
+
+
+def test_async_generator():
+    q = FakeQuery()
+
+    async def gen():
+        yield {"token": "a"}
+        yield {"token": "b"}
+
+    asyncio.run(stream_replies_to_query(q, gen()))
+    check("异步生成器逐块回复", len(q.replies) == 2)
+    check("回复 key_expr 正确", all(k == q.key_expr for k, _ in q.replies))
+    check(
+        "payload 为 JSON dict",
+        [orjson.loads(p) for _, p in q.replies] == [{"token": "a"}, {"token": "b"}],
+    )
+
+
+def test_sync_generator():
+    q = FakeQuery()
+
+    def gen():
+        yield {"n": 1}
+        yield {"n": 2}
+
+    asyncio.run(stream_replies_to_query(q, gen()))
+    check(
+        "同步生成器逐块回复",
+        [orjson.loads(p) for _, p in q.replies] == [{"n": 1}, {"n": 2}],
+    )
+
+
+def test_mid_stream_exception():
+    q = FakeQuery()
+
+    async def gen():
+        yield {"token": "a"}
+        raise ValueError("boom")
+
+    asyncio.run(stream_replies_to_query(q, gen()))
+    check("中途异常收尾 error 块", len(q.replies) == 2)
+    check("error 块内容", orjson.loads(q.replies[1][1]) == {"error": "boom"})
+
+
+def test_reply_failure_stops():
+    q = FakeQuery()
+    q.fail_reply = True
+    yielded = []
+
+    async def gen():
+        yielded.append("yield-1")
+        yield {"token": "a"}
+        yielded.append("yield-2")  # 首个块 reply 失败后不应被执行到
+        yield {"token": "b"}
+
+    # 不应抛异常，且首个块 reply 失败后立即停流
+    asyncio.run(stream_replies_to_query(q, gen()))
+    check("reply 失败不抛异常", True)
+    check("reply 失败后立即停流", yielded == ["yield-1"])
+
+
+def run():
+    test_async_generator()
+    test_sync_generator()
+    test_mid_stream_exception()
+    test_reply_failure_stops()
+
+    print(f"\n结果: {len(failures)} 个失败")
+    return 1 if failures else 0
+
+
+if __name__ == "__main__":
+    sys.exit(run())

uv.lock

@@ -486,7 +486,7 @@ source = { git = "http://124.71.68.6:3000/chongming/chongming-stream-manager.git
 [[package]]
 name = "chongming-worker"
 version = "0.2.0"
-source = { git = "http://124.71.68.6:3000/chongming/chongming-utils-worker.git#d8230bc0ca913a1253d9db9d9af231da9fa7c779" }
+source = { git = "http://124.71.68.6:3000/chongming/chongming-utils-worker.git#6dbdce177b2e44f2d0fd84df51d49bd690a8926b" }
 dependencies = [
     { name = "eclipse-zenoh" },
     { name = "pydantic" },