feat: surgery pipeline API, video inference, voice confirm, and tests

- Add FastAPI routes for surgery start/end, results, pending confirmation (WAV upload), and health checks.
- Implement RTSP/Hikvision capture, consumable classification, session manager, MinIO/Baidu voice resolution, and DB persistence.
- Add documentation (client API, video backends, staging checklist) and sample camera/RTSP config.
- Add pytest suite (API contract, session manager, voice, repositories, pipeline persistence) and httpx dev dependency.
- Replace deprecated HTTP_422_UNPROCESSABLE_ENTITY with HTTP_422_UNPROCESSABLE_CONTENT.
- Fix SurgeryPipeline DB reads to use an explicit transaction with autobegin disabled.

Made-with: Cursor

tests/test_voice_confirm.py

@@ -0,0 +1,19 @@
+from app.services.voice_confirm import build_prompt_text, parse_voice_choice
+
+
+def test_parse_voice_choice_substring() -> None:
+    assert parse_voice_choice("用的是纱布对吧", ["纱布", "缝线"]) == "纱布"
+
+
+def test_parse_voice_choice_numeric() -> None:
+    assert parse_voice_choice("第2个", ["纱布", "缝线", "钳子"]) == "缝线"
+
+
+def test_parse_voice_choice_negative() -> None:
+    assert parse_voice_choice("不是", ["纱布", "缝线"]) is None
+
+
+def test_build_prompt_contains_options() -> None:
+    text = build_prompt_text([("纱布", 0.4), ("缝线", 0.3)])
+    assert "纱布" in text
+    assert "缝线" in text