fix: 修复热点摘要超长上下文并统一 Windows 启动文档

为 http_request 增加响应体截断与头部精简，避免门户首页触发 LLM 上下文超限；同时新增政务/媒体及教育批量 Agent 脚本，并将 Windows 启停说明合并为唯一指南，补充本次超时故障复盘与标准重启流程。

Made-with: Cursor

backend/app/core/config.py

@@ -34,6 +34,9 @@ class Settings(BaseSettings):
     LOCAL_FILE_READ_MAX_BYTES: int = 2_097_152   # 单次读取上限（默认 2MB）
     LOCAL_FILE_WRITE_MAX_BYTES: int = 2_097_152  # 单次写入内容上限（UTF-8 字节）
 
+    # http_request 工具：写入 LLM 上下文的响应体最大字符数（HTML/JSON 过大时截断，避免超过模型 context）
+    HTTP_REQUEST_MAX_BODY_CHARS: int = 32_000
+
     # 图片 OCR（file_read 对 png/jpg 等）：Tesseract 可执行文件路径，Windows 示例 C:/Program Files/Tesseract-OCR/tesseract.exe
     TESSERACT_CMD: str = ""
     # 自定义 tessdata 目录（内含 chi_sim.traineddata 等）。留空时若 LOCAL_FILE_TOOLS_ROOT/tessdata 下存在 .traineddata 则自动使用

backend/app/services/builtin_tools.py

@@ -67,11 +67,74 @@ def _resolve_path_under_workspace(file_path: str) -> Tuple[Optional[Path], Optio
     return p, None
 
 
+_HTTP_RESPONSE_HEADER_ALLOWLIST = frozenset(
+    {
+        "content-type",
+        "content-length",
+        "content-encoding",
+        "date",
+        "last-modified",
+        "location",
+        "server",
+        "cache-control",
+    }
+)
+
+
+def _compact_http_response_headers(response: httpx.Response) -> Dict[str, str]:
+    """减少 Set-Cookie 等大字段进入 LLM 上下文。"""
+    out: Dict[str, str] = {}
+    for key, value in response.headers.multi_items():
+        lk = key.lower()
+        if lk in ("set-cookie", "cookie"):
+            continue
+        if lk in _HTTP_RESPONSE_HEADER_ALLOWLIST:
+            out[key] = value if len(value) <= 2048 else value[:2048] + "..."
+    if not out:
+        n = 0
+        for key, value in response.headers.multi_items():
+            lk = key.lower()
+            if lk in ("set-cookie", "cookie"):
+                continue
+            if n >= 12:
+                break
+            out[key] = value if len(value) <= 512 else value[:512] + "..."
+            n += 1
+    return out
+
+
+def _truncate_http_body_for_tool(body: Any, max_chars: int) -> Tuple[Any, bool, Optional[str]]:
+    """
+    将 HTTP 正文限制在 max_chars 字符以内，避免门户首页等大 HTML 撑爆模型 context。
+    返回 (可能被截断后的 body, 是否截断, 说明文案)
+    """
+    if max_chars <= 0:
+        max_chars = 32_000
+    note: Optional[str] = None
+    if isinstance(body, str):
+        if len(body) <= max_chars:
+            return body, False, None
+        note = (
+            f"正文已截断：原始约 {len(body)} 字符，仅保留前 {max_chars} 字符。"
+            "门户/频道首页通常过大，摘要请优先使用具体文章页 URL。"
+        )
+        return body[:max_chars], True, note
+    try:
+        serialized = json.dumps(body, ensure_ascii=False)
+    except (TypeError, ValueError):
+        serialized = str(body)
+    if len(serialized) <= max_chars:
+        return body, False, None
+    note = f"JSON 响应已截断：序列化长度约 {len(serialized)} 字符，仅保留前 {max_chars} 字符。"
+    return serialized[:max_chars], True, note
+
+
 async def http_request_tool(
     url: str,
     method: str = "GET",
     headers: Optional[Dict[str, str]] = None,
-    body: Any = None
+    body: Any = None,
+    max_body_chars: Optional[int] = None,
 ) -> str:
     """
     HTTP请求工具
@@ -81,12 +144,18 @@ async def http_request_tool(
         method: HTTP方法 (GET, POST, PUT, DELETE)
         headers: 请求头
         body: 请求体（POST/PUT时使用）
+        max_body_chars: 响应正文写入工具结果的最大字符数；默认读取配置 HTTP_REQUEST_MAX_BODY_CHARS
     
     Returns:
         JSON格式的响应结果
     """
     try:
-        async with httpx.AsyncClient(timeout=30.0) as client:
+        limit = max_body_chars
+        if limit is None:
+            limit = int(getattr(settings, "HTTP_REQUEST_MAX_BODY_CHARS", 32_000) or 32_000)
+        limit = max(4096, min(limit, 200_000))
+
+        async with httpx.AsyncClient(timeout=30.0, follow_redirects=True) as client:
             method_upper = method.upper()
             
             if method_upper == "GET":
@@ -103,15 +172,20 @@ async def http_request_tool(
             # 尝试解析JSON响应
             try:
                 response_body = response.json()
-            except:
+            except Exception:
                 response_body = response.text
-            
-            result = {
+
+            truncated_body, truncated, trunc_note = _truncate_http_body_for_tool(response_body, limit)
+            result: Dict[str, Any] = {
                 "status_code": response.status_code,
-                "headers": dict(response.headers),
-                "body": response_body
+                "headers": _compact_http_response_headers(response),
+                "body": truncated_body,
             }
-            
+            if truncated:
+                result["body_truncated"] = True
+                if trunc_note:
+                    result["truncation_note"] = trunc_note
+
             return json.dumps(result, ensure_ascii=False)
     except Exception as e:
         logger.error(f"HTTP请求工具执行失败: {str(e)}")
@@ -1036,7 +1110,14 @@ HTTP_REQUEST_SCHEMA = {
                 "body": {
                     "type": "object",
                     "description": "请求体（POST/PUT时使用，可选）"
-                }
+                },
+                "max_body_chars": {
+                    "type": "integer",
+                    "description": (
+                        "响应正文写入结果的最大字符数（可选）。"
+                        "门户首页等大 HTML 默认会按平台配置截断；摘要单篇文章可适当调大（如 80000），仍可能受模型总上下文限制。"
+                    ),
+                },
             },
             "required": ["url", "method"]
         }