代码提交

offline-backend-20260512/backend/packages/harness/deerflow/agents/ai_writing/nodes/researcher.py

@@ -349,7 +349,10 @@ async def _search_notebook(
     results: list[Material] = []
     mat_idx = 0
     try:
-        async with httpx.AsyncClient(timeout=20) as client:
+        # trust_env=False：笔记后端是内网/本机地址，但模型走公网，部署常设
+        # HTTP_PROXY/HTTPS_PROXY；httpx 默认会把这个内网请求也走代理 → 不可达。
+        # 强制忽略代理 env、直连（与内网 ES 检索同款修法）。
+        async with httpx.AsyncClient(timeout=20, trust_env=False) as client:
             for kw in keywords[:_NOTEBOOK_MAX_KEYWORDS]:
                 logger.info("[notebook-search] POST kw=%r body=%s", kw, {
                     "query": kw,

offline-backend-20260512/backend/packages/harness/deerflow/agents/ai_writing/search/intranet_stub.py

@@ -113,8 +113,19 @@ class IntranetSearchProvider(BaseSearchProvider):
             "ok": False,
             "count": 0,
         }
+        # 排查用：每次真实调用都打一行请求明细（端点 / 知识库 / 检索词 / 超时），
+        # 内网复现时直接看后端日志即可知道"到底请求了哪个地址、用什么参数"。
+        logger.info(
+            "[intranet-search] POST endpoint=%s kb=%s timeout=%ss query=%r",
+            self.endpoint, self.knowledge_base_name, self.timeout, query,
+        )
         try:
-            async with httpx.AsyncClient(timeout=self.timeout) as client:
+            # trust_env=False：**关键**。内网 ES 是内网地址，但本部署的模型走公网，
+            # 服务器通常设了 HTTP_PROXY/HTTPS_PROXY 出公网；httpx 默认 trust_env=True
+            # 会把这个内网请求也套用公网代理 → 代理到不了内网 IP → 连接被重置/空回复，
+            # 表现为「接口异常」。强制忽略代理 env、直连内网（与 multi_agent.py 的回环
+            # 调用同款修法）。
+            async with httpx.AsyncClient(timeout=self.timeout, trust_env=False) as client:
                 resp = await client.post(self.endpoint, json=payload)
                 call["http_status"] = getattr(resp, "status_code", None)
                 resp.raise_for_status()
@@ -122,23 +133,31 @@ class IntranetSearchProvider(BaseSearchProvider):
                 data = resp.json()
         except httpx.HTTPStatusError as e:
             # 非 2xx：接口有响应但状态码异常，把响应体一并暴露给前端
-            logger.warning("intranet search failed for query=%r: %s", query, e)
+            body_for_log = e.response.text if e.response is not None else ""
+            logger.warning(
+                "[intranet-search] HTTP error endpoint=%s query=%r status=%s body=%s",
+                self.endpoint, query, getattr(e.response, "status_code", None), _raw_snippet(body_for_log),
+            )
             message = f"{type(e).__name__}: {e}"
             self.errors.append(message)
-            body = e.response.text if e.response is not None else ""
             call.update({
                 "status": "http_error",
                 "error": message,
                 "http_status": getattr(e.response, "status_code", None),
             })
-            snippet = _raw_snippet(body)
+            snippet = _raw_snippet(body_for_log)
             if snippet:
                 call["raw_response"] = snippet
-            self._record_raw(body)
+            self._record_raw(body_for_log)
             return []
         except Exception as e:
-            # 连接失败 / 超时 / JSON 解析失败等；JSON 解析失败时 raw_text 已是接口响应体
-            logger.warning("intranet search failed for query=%r: %s", query, e)
+            # 连接失败 / 超时 / JSON 解析失败等；JSON 解析失败时 raw_text 已是接口响应体。
+            # 打出异常类型，便于区分 ConnectError / ConnectTimeout / ReadTimeout /
+            # RemoteProtocolError(空回复) / JSONDecodeError(返回非 JSON) 等具体根因。
+            logger.warning(
+                "[intranet-search] request failed endpoint=%s query=%r error=%s: %s",
+                self.endpoint, query, type(e).__name__, e,
+            )
             message = f"{type(e).__name__}: {e}"
             self.errors.append(message)
             call.update({"status": "error", "error": message})
@@ -187,6 +206,10 @@ class IntranetSearchProvider(BaseSearchProvider):
             self._record_raw(raw_text)
             return []
 
+        logger.info(
+            "[intranet-search] OK endpoint=%s query=%r http_status=%s raw_items=%s",
+            self.endpoint, query, call.get("http_status"), len(items) if isinstance(items, list) else 0,
+        )
         results: List[SearchResult] = []
         for i, item in enumerate(items[:max_results]):
             if not isinstance(item, dict):