feat: add video OCR/ASR, DOCX/PDF export, input block and risk config updates

- Video pipeline: video file OCR via VLM plus audio track ASR, integrated
  into job_handlers with progress emit per phase. New media_utils.py for
  audio extraction from video files.
- Document export: richExport.js replaces inline docx builder; DOCX and PDF
  export buttons are now enabled in MilkdownEditor. File size limit raised to
  100 MB.
- Input block: new InputBlockCrepe.vue component with inputBlockPlugin.ts
  and inputBlock.js for custom user-input nodes in the editor.
- Risk config: added Vite dev server ports (5173) to CORS allowlist and
  increased OCR max input from 10 MB to 100 MB.
- TTS/ASR refactor: simplified tts_asr.py model loading and warmup logic.
- Test coverage: updated tests for llm, main endpoints, pro completions and
  web search modules.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/main.py

@@ -106,6 +106,8 @@ class OCRRequest(BaseModel):
     image: str
     filename: str = "image.jpg"
     language: str = "auto"
+    media_type: str = "image"
+    mime_type: str | None = None
 
 
 class ConvertRequest(BaseModel):
@@ -281,8 +283,10 @@ def _register_handlers() -> None:
     确保 Redis 重连或实例重建后处理器不会丢失。"""
     global _handlers_registered
     manager = get_job_manager()
-    # 强制清空旧 handlers，避免重复注册累积
-    manager.handlers.clear()
+    # 强制清空旧 handlers，避免重复注册累积；测试替身只暴露 register_handler。
+    handlers = getattr(manager, "handlers", None)
+    if handlers is not None:
+        handlers.clear()
     manager.register_handler("completion", completion_handler)
     manager.register_handler("pro_completion", pro_completion_handler)
     manager.register_handler("web_search", web_search_handler)
@@ -294,7 +298,8 @@ def _register_handlers() -> None:
     _handlers_registered = True
     
     # 打印注册信息便于调试
-    logger.info("handlers registered: %s", list(manager.handlers.keys()))tered: %s", list(manager.handlers.keys()))
+    registered = list(getattr(manager, "handlers", {}).keys())
+    logger.info("handlers registered: %s", registered)
 
 
 def _sse(event: str, data: dict) -> str:
@@ -623,16 +628,28 @@ async def ocr_image(request: Request, req: OCRRequest, auth: dict = Security(_au
     except Exception as exc:
         return JSONResponse({"error": str(exc)}, status_code=500)
     if len(image_bytes) > config.ocr_max_input_bytes:
-        return JSONResponse({"error": "图片过大，无法执行 OCR"}, status_code=400)
+        return JSONResponse({"error": "文件过大，无法执行 OCR/视频解析"}, status_code=400)
     input_path = persist_temp_input(image_bytes, os.path.splitext(req.filename)[1] or ".img")
     try:
         identity, payload = await _prepare_llm_payload(
             request,
             job_type="ocr",
-            request_body={"filename": req.filename, "language": req.language, "image_bytes": len(image_bytes)},
+            request_body={
+                "filename": req.filename,
+                "language": req.language,
+                "media_type": req.media_type,
+                "mime_type": req.mime_type,
+                "image_bytes": len(image_bytes),
+            },
             raw_size=len(image_bytes),
-            token_source_text=f"{req.filename}:{len(image_bytes)}:{req.language}",
-            extra_payload={"input_path": input_path, "filename": req.filename, "language": req.language},
+            token_source_text=f"{req.filename}:{req.media_type}:{req.mime_type}:{len(image_bytes)}:{req.language}",
+            extra_payload={
+                "input_path": input_path,
+                "filename": req.filename,
+                "language": req.language,
+                "media_type": req.media_type,
+                "mime_type": req.mime_type,
+            },
         )
         job_id = await _queue_job("ocr", payload, identity.request_id)
     except RiskRejected as exc: