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/tests/test_main_endpoints.py

@@ -4,6 +4,7 @@ import importlib
 import os
 import sys
 from pathlib import Path
+from types import SimpleNamespace
 
 from fastapi.testclient import TestClient
 
@@ -158,6 +159,35 @@ def test_post_ocr_mocked(monkeypatch):
     assert "OCR result text" in body
 
 
+def test_post_video_ocr_merges_ocr_and_asr(monkeypatch):
+    async def fake_ocr(*args, **kwargs):
+        return "画面文字"
+
+    async def fake_asr(*args, **kwargs):
+        return SimpleNamespace(text="音频转写")
+
+    monkeypatch.setattr(job_handlers, "call_vlm_ocr", fake_ocr)
+    monkeypatch.setattr(job_handlers, "generate_asr_response", fake_asr)
+    monkeypatch.setattr(job_handlers, "extract_audio_wav_bytes", lambda _path: b"fake wav")
+
+    video_b64 = base64.b64encode(b"pretend video data").decode()
+    with TestClient(main.app) as client:
+        with client.stream("POST", "/v1/ocr", headers=HEADERS, json={
+            "image": video_b64,
+            "filename": "sample.mp4",
+            "language": "auto",
+            "media_type": "video",
+            "mime_type": "video/mp4",
+        }) as resp:
+            assert resp.status_code == 200
+            body = "".join(resp.iter_text())
+
+    assert "视频画面 OCR" in body
+    assert "视频音频 ASR" in body
+    assert "画面文字" in body
+    assert "音频转写" in body
+
+
 def test_post_convert_txt_returns_markdown():
     content = base64.b64encode(b"hello world").decode()
     with TestClient(main.app) as client: