feat(storage): 增强文件上传功能并添加详细的指标追踪

- 在存储服务中新增 upload_file_with_metrics 方法，返回上传结果和详细指标
- 为上传操作添加完整的指标收集，包括 HTTP 尝试次数、重试次数、状态码等
- 集成 OpenTelemetry 追踪，记录文件上传的关键属性和错误标记
- 改进缓存写回逻辑，添加缓存写入失败的日志记录
- 支持 Rclone 上传方式的指标追踪和回退到 HTTP 的情况记录
- 优化本地文件大小检查，避免重复的文件系统调用
- 添加更详细的错误日志，包含上传方法、状态码和错误类型信息

services/storage.py

@@ -8,7 +8,7 @@
 import os
 import logging
 import subprocess
-from typing import Optional
+from typing import Any, Dict, Optional, Tuple
 from urllib.parse import unquote
 
 import requests
@@ -65,6 +65,22 @@ def _apply_http_replace_map(url: str) -> str:
 
 
 def upload_file(url: str, file_path: str, max_retries: int = 5, timeout: int = 60) -> bool:
+    """兼容旧接口：仅返回上传是否成功。"""
+    result, _ = upload_file_with_metrics(
+        url=url,
+        file_path=file_path,
+        max_retries=max_retries,
+        timeout=timeout,
+    )
+    return result
+
+
+def upload_file_with_metrics(
+    url: str,
+    file_path: str,
+    max_retries: int = 5,
+    timeout: int = 60
+) -> Tuple[bool, Dict[str, Any]]:
     """
     使用签名 URL 上传文件到 OSS
 
@@ -75,30 +91,54 @@ def upload_file(url: str, file_path: str, max_retries: int = 5, timeout: int = 6
         timeout: 超时时间（秒）
 
     Returns:
-        是否成功
+        (是否成功, 上传指标)
     """
+    metrics: Dict[str, Any] = {
+        "upload_method": "none",
+        "file_size_bytes": 0,
+        "content_type": "",
+        "http_attempts": 0,
+        "http_retry_count": 0,
+        "http_status_code": 0,
+        "http_replace_applied": False,
+        "rclone_attempted": False,
+        "rclone_succeeded": False,
+        "rclone_fallback_http": False,
+        "error_type": "",
+    }
+
     if not os.path.exists(file_path):
         logger.error(f"File not found: {file_path}")
-        return False
+        metrics["error_type"] = "file_not_found"
+        return False, metrics
 
     file_size = os.path.getsize(file_path)
+    metrics["file_size_bytes"] = file_size
     logger.info(f"Uploading: {file_path} ({file_size} bytes)")
 
     # 检查是否使用 rclone 上传
     if os.getenv("UPLOAD_METHOD") == "rclone":
+        metrics["rclone_attempted"] = True
         logger.debug(f"Uploading to: {url}")
         result = _upload_with_rclone(url, file_path)
+        metrics["rclone_succeeded"] = result
         if result:
-            return True
+            metrics["upload_method"] = "rclone"
+            return True, metrics
         # rclone 失败时回退到 HTTP
+        metrics["rclone_fallback_http"] = True
 
     # 应用 HTTP_REPLACE_MAP 替换 URL
     http_url = _apply_http_replace_map(url)
+    metrics["http_replace_applied"] = http_url != url
     content_type = _get_content_type(file_path)
+    metrics["content_type"] = content_type
+    metrics["upload_method"] = "rclone_fallback_http" if metrics["rclone_fallback_http"] else "http"
     logger.debug(f"Uploading to: {http_url} (Content-Type: {content_type})")
 
     retries = 0
     while retries < max_retries:
+        metrics["http_attempts"] = retries + 1
         try:
             with open(file_path, 'rb') as f:
                 with requests.put(
@@ -108,19 +148,30 @@ def upload_file(url: str, file_path: str, max_retries: int = 5, timeout: int = 6
                     timeout=timeout,
                     headers={"Content-Type": content_type}
                 ) as response:
+                    status_code = int(getattr(response, 'status_code', 0) or 0)
+                    metrics["http_status_code"] = status_code
                     response.raise_for_status()
                     logger.info(f"Upload succeeded: {file_path}")
-                    return True
+                    metrics["error_type"] = ""
+                    return True, metrics
 
         except requests.exceptions.Timeout:
             retries += 1
+            metrics["http_retry_count"] = retries
+            metrics["error_type"] = "timeout"
             logger.warning(f"Upload timed out. Retrying {retries}/{max_retries}...")
         except requests.exceptions.RequestException as e:
             retries += 1
+            metrics["http_retry_count"] = retries
+            metrics["error_type"] = "request_exception"
+            response_obj = getattr(e, 'response', None)
+            status_code = getattr(response_obj, 'status_code', 0) if response_obj is not None else 0
+            if isinstance(status_code, int) and status_code > 0:
+                metrics["http_status_code"] = status_code
             logger.warning(f"Upload failed ({e}). Retrying {retries}/{max_retries}...")
 
     logger.error(f"Upload failed after {max_retries} retries: {file_path}")
-    return False
+    return False, metrics
 
 
 def _upload_with_rclone(url: str, file_path: str) -> bool: