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/job_handlers.py

@@ -14,6 +14,7 @@ import markitdown
 
 from audit_store import get_audit_store
 from llm import call_ollama, call_vlm_ocr, stream_ollama_events
+from media_utils import extract_audio_wav_bytes, is_video_filename
 from prompt import (
     build_completion_prompts,
     build_pro_completion_prompts,
@@ -720,14 +721,60 @@ async def ocr_handler(
     path = payload["input_path"]
     identity, risk, lock_keys = await _enter_llm_execution(payload, emit)
     try:
+        filename = payload.get("filename", "image.jpg")
+        language = payload.get("language", "auto")
+        media_type = payload.get("media_type", "image")
+        mime_type = payload.get("mime_type", "") or ""
+
         with open(path, "rb") as handle:
-            image_bytes = handle.read()
-        text = await call_vlm_ocr(image_bytes, payload.get("language", "auto"))
+            media_bytes = handle.read()
+
+        await emit("progress", {"phase": "ocr", "media_type": media_type})
+        ocr_text = await call_vlm_ocr(
+            media_bytes,
+            language,
+            mime_type=mime_type or "application/octet-stream",
+            media_type=media_type,
+        )
         if is_cancelled():
             raise asyncio.CancelledError()
-        await emit("result", {"text": text})
-        await _exit_llm_execution(payload, identity, risk, lock_keys, status="completed", actual_output_text=text)
-        return {"text": text, "filename": payload.get("filename", "image.jpg")}
+
+        result = {
+            "text": ocr_text,
+            "ocr_text": ocr_text,
+            "filename": filename,
+            "media_type": media_type,
+        }
+
+        if media_type == "video" or is_video_filename(filename, mime_type):
+            asr_text = ""
+            if generate_asr_response is not None:
+                try:
+                    await emit("progress", {"phase": "asr", "media_type": media_type})
+                    audio_bytes = await asyncio.to_thread(extract_audio_wav_bytes, path)
+                    asr_response = await generate_asr_response(audio_bytes, language)
+                    asr_text = getattr(asr_response, "text", "") or ""
+                except Exception as exc:
+                    asr_text = f"(音频解析失败: {exc})"
+            if ocr_text.strip() or asr_text.strip():
+                text_parts = []
+                if ocr_text.strip():
+                    text_parts.append(f"## 视频画面 OCR\n\n{ocr_text.strip()}")
+                if asr_text.strip():
+                    text_parts.append(f"## 视频音频 ASR\n\n{asr_text.strip()}")
+                result["text"] = "\n\n".join(text_parts)
+            result["asr_text"] = asr_text
+
+        await emit("result", result)
+        await _exit_llm_execution(
+            payload,
+            identity,
+            risk,
+            lock_keys,
+            status="completed",
+            actual_output_text=result["text"],
+        )
+        return result
     except asyncio.CancelledError:
         await _exit_llm_execution(payload, identity, risk, lock_keys, status="cancelled", error_code="cancelled")
         raise