Windows 兼容性修复 + Dify API 适配 + 企微 WS 加载优化 (#2470)

* fix: Windows fsync requires write access to file descriptor

- _fsync_file: os.O_RDONLY -> os.O_RDWR (Windows _commit() requires write access)
- _fsync_directory: tolerate OSError on fsync and os.open (chmod 0o700 blocks access on Windows)

* fix: Dify SSE empty data lines and upload response format mismatch

- Skip malformed/flushed SSE data lines (JSONDecodeError)
- Accept HTTP 200 besides 201 for file upload response
- Unwrap data wrapper in upload response (resp.get('data', resp))

* feat: WeCom WS mode sends empty initial stream frame for loading spinner

Send an empty reply_stream frame immediately after stream session
creation so the WeCom client shows its built-in loading indicator
while the pipeline processes the message (e.g. RAG retrieval).

* fix(compat): harden Windows, Dify, and WeCom changes

* fix(migration): clean interrupted SQLite temp files

---------

Co-authored-by: Hyu <chenhyu@proton.me>

src/langbot/libs/dify_service_api/v1/client.py

@@ -1,13 +1,14 @@
 from __future__ import annotations
 
 import asyncio
-import httpx
-import typing
 import json
+import os
+import typing
+from pathlib import Path
+
+import httpx
 
 from .errors import DifyAPIError
-from pathlib import Path
-import os
 
 _MAX_DIFY_RESPONSE_BYTES = 1024 * 1024
 _MAX_DIFY_SSE_LINE_BYTES = 1024 * 1024
@@ -15,6 +16,32 @@ _MAX_DIFY_STREAM_BYTES = 16 * 1024 * 1024
 _MAX_DIFY_UPLOAD_BYTES = 10 * 1024 * 1024
 
 
+def _decode_sse_data(line: bytes) -> dict[str, typing.Any] | None:
+    data = line[5:].strip()
+    if not data or data == b'[DONE]':
+        return None
+    try:
+        payload = json.loads(data.decode('utf-8'))
+    except (json.JSONDecodeError, UnicodeDecodeError) as exc:
+        raise DifyAPIError('Dify SSE data line is not valid JSON') from exc
+    if not isinstance(payload, dict):
+        raise DifyAPIError('Dify SSE event is not a JSON object')
+    return payload
+
+
+def _decode_upload_response(body: bytes) -> dict[str, typing.Any]:
+    try:
+        response = json.loads(body)
+    except (json.JSONDecodeError, UnicodeDecodeError) as exc:
+        raise DifyAPIError('Dify upload response is not valid JSON') from exc
+    if not isinstance(response, dict):
+        raise DifyAPIError('Dify upload response is not a JSON object')
+    payload = response.get('data', response)
+    if not isinstance(payload, dict) or not isinstance(payload.get('id'), str) or not payload['id']:
+        raise DifyAPIError('Dify upload response does not contain a valid file id')
+    return payload
+
+
 async def _read_limited_response(
     response: httpx.Response,
     *,
@@ -56,16 +83,16 @@ async def _iter_sse_json(
             line = raw_line.rstrip(b'\r').strip()
             if not line or not line.startswith(b'data:'):
                 continue
-            payload = json.loads(line[5:].decode('utf-8', errors='replace'))
-            if isinstance(payload, dict):
+            payload = _decode_sse_data(line)
+            if payload is not None:
                 yield payload
         if len(buffer) > _MAX_DIFY_SSE_LINE_BYTES:
             raise DifyAPIError('Dify SSE event exceeds the runtime limit')
 
     line = bytes(buffer).rstrip(b'\r').strip()
     if line.startswith(b'data:'):
-        payload = json.loads(line[5:].decode('utf-8', errors='replace'))
-        if isinstance(payload, dict):
+        payload = _decode_sse_data(line)
+        if payload is not None:
             yield payload
 
 
@@ -242,7 +269,7 @@ class AsyncDifyServiceClient:
         file: httpx._types.FileTypes,
         user: str,
         timeout: float = 30.0,
-    ) -> str:
+    ) -> dict[str, typing.Any]:
         # 处理 Path 对象
         if isinstance(file, Path):
             if not file.exists():
@@ -271,6 +298,6 @@ class AsyncDifyServiceClient:
             timeout=timeout,
         ) as response:
             body = await _read_limited_response(response)
-            if response.status_code != 201:
+            if response.status_code not in (200, 201):
                 raise DifyAPIError(f'{response.status_code} {body.decode(errors="replace")}')
-        return json.loads(body)
+        return _decode_upload_response(body)

src/langbot/libs/wecom_ai_bot_api/ws_client.py

@@ -936,6 +936,13 @@ class WecomBotWsClient:
                     'chat_type': message_data.get('type', 'single'),
                 }
                 self._prune_stream_state()
+                # Send an initial empty stream frame so the WeCom client
+                # shows its built-in loading spinner while the pipeline
+                # processes the message (e.g. RAG retrieval).
+                try:
+                    await self.reply_stream(req_id, stream_id, '', finish=False)
+                except Exception:
+                    await self.logger.warning(f'Failed to send initial stream frame: {traceback.format_exc()}')
             message_data['stream_id'] = stream_id
             message_data['req_id'] = req_id