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_llm.py

@@ -299,3 +299,4 @@ def test_call_vlm_ocr(monkeypatch):
     image_part = [p for p in content_parts if p.get("type") == "image_url"]
     assert len(image_part) == 1
     assert image_part[0]["image_url"]["url"].startswith("data:image/png;base64,")
+    assert captured["json"]["options"]["think"] is False

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:

backend/tests/test_pro_completions.py

@@ -35,7 +35,7 @@ def _payload():
         "privacy_mode": True,
         "user_preferences": {
             "language": "zh",
-            "currency": "CNY",
+            "country": "CN",
             "timezone": "Asia/Shanghai",
         },
     }
@@ -43,7 +43,7 @@ def _payload():
 
 def test_pro_queue_full_returns_429(monkeypatch):
     async def fake_queue_job(*args, **kwargs):
-        raise job_system.QueueFullError("pro_completion queue is full")
+        raise job_system.QueueFullError("pro_completion", 8)
 
     monkeypatch.setattr(main, "_queue_job", fake_queue_job)
     with TestClient(main.app) as client:
@@ -79,13 +79,13 @@ def test_pro_prompt_accepts_serialized_preferences():
         instruction="expand",
         preferences={
             "language": "zh",
-            "currency": "CNY",
+            "country": "CN",
             "timezone": "Asia/Shanghai",
         },
     )
 
     assert "Preferred language: zh" in user_prompt
-    assert "Preferred currency: CNY" in user_prompt
+    assert "Preferred country: CN" in user_prompt
     assert "Preferred timezone: Asia/Shanghai" in user_prompt
 
 

backend/tests/test_web_search.py

@@ -17,6 +17,7 @@ if str(BACKEND_DIR) not in sys.path:
 
 import job_handlers  # type: ignore
 import job_system  # type: ignore
+import llm  # type: ignore
 import risk_control  # type: ignore
 import session_store  # type: ignore
 import audit_store  # type: ignore
@@ -55,10 +56,14 @@ def test_web_search_route_returns_done(monkeypatch):
             return {"content": '["vector database comparison", "pinecone weaviate qdrant"]'}
         if tag.endswith("-webu"):
             return {"content": '["https://example.com/a", "https://example.com/b"]'}
-        if tag.endswith("-webf"):
-            return {"content": "第一段\n\n第二段"}
         raise AssertionError(f"unexpected tag: {tag}")
 
+    async def fake_stream_ollama_events(prompt, system_prompt=None, tag="", **kwargs):  # noqa: ARG001
+        if not tag.endswith("-webf"):
+            raise AssertionError(f"unexpected stream tag: {tag}")
+        yield "content", "第一段\n\n"
+        yield "content", "第二段"
+
     async def fake_searxng_search(query, *, limit):  # noqa: ARG001
         return [
             {
@@ -83,6 +88,7 @@ def test_web_search_route_returns_done(monkeypatch):
     monkeypatch.setattr(job_handlers, "call_ollama", fake_call_ollama)
     monkeypatch.setattr(job_handlers, "_searxng_search", fake_searxng_search)
     monkeypatch.setattr(job_handlers, "_firecrawl_scrape", fake_firecrawl_scrape)
+    monkeypatch.setattr(llm, "stream_ollama_events", fake_stream_ollama_events)
 
     with TestClient(main.app) as client:
         with client.stream("POST", "/v1/web-search", headers=HEADERS, json=_payload()) as resp: