fix: stabilize background operations and large embedding results

backend/app/local_models/protocol.py

@@ -0,0 +1,11 @@
+"""Bound embedding result frames so large notes do not exceed pipe line limits."""
+import json
+
+
+def response_lines(response, operation):
+    if operation == 'embedding' and 'result' in response and 'error_code' not in response:
+        vectors = response['result']
+        for offset in range(0, len(vectors), 128):
+            yield json.dumps({'embedding_offset': offset, 'embedding_chunk': vectors[offset:offset + 128]}, allow_nan=False) + '\n'
+        response = {**response, 'result': [], 'embedding_count': len(vectors)}
+    yield json.dumps(response, ensure_ascii=False, allow_nan=False) + '\n'

backend/app/local_models/runtime.py

@@ -189,15 +189,30 @@ class Runtime:
                 await process.stdin.drain()
                 process.stdin.close()
                 final = None
+                vectors = []
                 while line := await process.stdout.readline():
                     message = json.loads(line)
-                    if "progress" in message:
+                    if "embedding_chunk" in message:
+                        chunk = message['embedding_chunk']
+                        if (operation != 'embedding' or not isinstance(chunk, list)
+                                or message.get('embedding_offset') != len(vectors)
+                                or len(vectors) + len(chunk) > len(payload.get('texts', []))):
+                            raise ProviderError('LOCAL_MODEL_INVALID_RESPONSE', '本地向量传输顺序或数量无效。')
+                        vectors.extend(chunk)
+                    elif "progress" in message:
                         callback = runtime_progress.get()
                         if callback:
                             callback(message)
                     else:
                         final = message
                 await process.wait()
+                if isinstance(final, dict) and 'embedding_count' in final:
+                    if (final['embedding_count'] != len(vectors)
+                            or len(vectors) != len(payload.get('texts', []))):
+                        raise ProviderError('LOCAL_MODEL_INVALID_RESPONSE', '本地向量传输不完整。')
+                    final['result'] = vectors
+                elif vectors:
+                    raise ProviderError('LOCAL_MODEL_INVALID_RESPONSE', '本地向量传输缺少结束标记。')
                 return final
             try:
                 result = await asyncio.wait_for(receive(), config.timeout_seconds)

backend/app/local_models/worker.py

@@ -216,4 +216,6 @@ if __name__ == "__main__":
                 response = {"error_code": "LOCAL_INFERENCE_FAILED", "message": "本地推理失败，请检查媒体格式、模型和设备配置。"}
     if "error_code" in response:
         response["diagnostics"] = {"requested_device": request["config"]["device"], "actual_device": request.get("_actual_device", "unknown")}
-    sys.stdout.buffer.write((json.dumps(response, ensure_ascii=False, allow_nan=False) + "\n").encode("utf-8"))
+    from protocol import response_lines
+    for line in response_lines(response, request['operation']):
+        sys.stdout.buffer.write(line.encode('utf-8'))