feat(multimodal): 实现本地模型管线与请求用量配置

backend/tests/conftest.py

@@ -19,5 +19,19 @@ def _isolate_data_dir(tmp_path, monkeypatch):
     monkeypatch.setenv("APP_VAULT_PATH", str(tmp_path / "vault"))
     # 清除 lru 缓存，让本次测试内的 get_settings() 读到临时目录
     get_settings.cache_clear()
+    # Unit tests explicitly inject deterministic embeddings. Production uses real models.
+    from app import container as container_module
+    from app.services import note_service
+    from app.retrieval.engine import engine
+    from app.retrieval.embedding import HashEmbeddingProvider
+    from app.providers.routing import ModelRoutingService
+    def test_routing(providers, credentials):
+        return ModelRoutingService(providers, credentials, local_embedding=HashEmbeddingProvider())
+    monkeypatch.setattr(container_module, "_local_model_routing", test_routing)
+    monkeypatch.setattr(container_module.container.model_routing, "local_embedding", HashEmbeddingProvider())
+    monkeypatch.setattr(note_service, "embedding", HashEmbeddingProvider())
+    test_embedding = HashEmbeddingProvider()
+    monkeypatch.setattr(engine, "embedding", test_embedding)
+    monkeypatch.setattr(engine, "_routed_defaults", (test_embedding, engine.vector_store))
     yield
     get_settings.cache_clear()

backend/tests/test_local_models.py

@@ -0,0 +1,86 @@
+import asyncio
+import hashlib
+import json
+import sys
+from pathlib import Path
+
+import httpx
+import pytest
+
+from app.local_models import manager
+from app.local_models.runtime import Runtime
+from app.providers.base import ProviderError
+
+
+def test_download_resumes_partial_and_checks_digest(monkeypatch):
+    payload = b'verified-model-weights'
+    entry = {'path':'model.safetensors','size':len(payload),'hash':hashlib.sha256(payload).hexdigest(),
+             'algorithm':'sha256','url':'https://fixture.invalid/weights'}
+    async def manifest(client, spec):
+        return [entry]
+    monkeypatch.setattr(manager, '_manifest', manifest)
+    path = manager.model_path('bekko')
+    path.mkdir(parents=True)
+    (path/'model.safetensors.partial').write_bytes(payload[:5])
+    requests = []
+    def respond(request):
+        requests.append(request)
+        assert request.headers['range'] == 'bytes=5-'
+        return httpx.Response(206, headers={'content-range':f'bytes 5-{len(payload)-1}/{len(payload)}'},content=payload[5:])
+    original = httpx.AsyncClient
+    monkeypatch.setattr(manager.httpx,'AsyncClient',lambda **kwargs:original(**kwargs,transport=httpx.MockTransport(respond)))
+    asyncio.run(manager._download('bekko'))
+    assert manager.read_state('bekko')['status'] == 'installed'
+    assert (path/'model.safetensors').read_bytes() == payload
+    assert manager.valid_file(path/'model.safetensors',entry)
+    (path/'model.safetensors').write_bytes(b'x'*len(payload))
+    assert not manager.valid_file(path/'model.safetensors',entry)
+    assert len(requests) == 1
+
+
+def test_local_model_missing_is_explicit():
+    with pytest.raises(ProviderError) as error:
+        asyncio.run(Runtime().infer('qwen3-asr','transcription',{'source':'missing.wav'}))
+    assert error.value.code == 'LOCAL_MODEL_NOT_INSTALLED'
+
+
+def test_cancel_reaps_active_model_process(monkeypatch):
+    import app.local_models.runtime as module
+    monkeypatch.setattr(module,'read_state',lambda key:{'status':'installed'})
+    monkeypatch.setattr(module,'interpreter',lambda:Path(sys.executable))
+    class Input:
+        def write(self, value):
+            request = json.loads(value)
+            assert request['config']['device'] == 'cpu'
+        async def drain(self):
+            pass
+        def close(self):
+            pass
+    class Process:
+        returncode = None
+        stdin = Input()
+        def __init__(self):
+            self.stdout = asyncio.StreamReader()
+            self.killed = False
+        def kill(self):
+            self.killed = True
+            self.returncode = -9
+            self.stdout.feed_eof()
+        async def wait(self):
+            return self.returncode
+    async def scenario():
+        started = asyncio.Event()
+        process = Process()
+        async def spawn(*args, **kwargs):
+            assert kwargs['env']['HF_HUB_OFFLINE'] == '1'
+            started.set()
+            return process
+        monkeypatch.setattr(module.asyncio,'create_subprocess_exec',spawn)
+        runtime = Runtime()
+        task = asyncio.create_task(runtime.infer('qwen3-asr','transcription',{'source':'fixture.wav'}))
+        await started.wait()
+        task.cancel()
+        with pytest.raises(asyncio.CancelledError):
+            await task
+        assert process.killed and not runtime.active
+    asyncio.run(scenario())

backend/tests/test_media_jobs.py

@@ -0,0 +1,104 @@
+"""Durability, cancellation and optimistic editing without model downloads."""
+import asyncio
+from contextlib import closing
+
+import pytest
+from fastapi.testclient import TestClient
+
+from app.contracts import TranscriptEditRequest
+from app.database.db import connect
+from app.errors import ApiError
+from app.services import transcription_service as jobs
+from app.services.attachment_service import attachment_path
+
+
+def text_attachment():
+    path = attachment_path("lecture.txt")
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text("原始识别内容", encoding="utf-8")
+    return path
+
+
+def test_idempotency_edit_history_and_event_replay():
+    text_attachment()
+
+    async def scenario():
+        first = await jobs.create_transcription("lecture.txt", idempotency_key="submit-1")
+        repeated = await jobs.create_transcription("lecture.txt", idempotency_key="submit-1")
+        assert first.job_id == repeated.job_id
+        assert first.status == "completed"
+        with pytest.raises(ApiError) as conflict:
+            await jobs.create_transcription("lecture.txt", language="en", idempotency_key="submit-1")
+        assert conflict.value.code == "IDEMPOTENCY_CONFLICT"
+        revised = jobs.edit(first.job_id, TranscriptEditRequest(revision=1, text="校对内容"))
+        assert revised.original_text == "原始识别内容"
+        assert revised.revision == 2
+        with pytest.raises(ApiError) as stale:
+            jobs.edit(first.job_id, TranscriptEditRequest(revision=1, text="覆盖"))
+        assert stale.value.code == "VERSION_CONFLICT"
+        with closing(connect()) as conn:
+            assert conn.execute("SELECT COUNT(*) FROM media_revisions").fetchone()[0] == 1
+        events = jobs.events(first.job_id)
+        assert [e["event"] for e in events] == ["Queued", "TranscriptionStarted", "Completed", "Revised"]
+        assert jobs.events(first.job_id, events[-2]["sequence"]) == events[-1:]
+
+    asyncio.run(scenario())
+
+
+def test_cancel_before_start_retry_and_restart_recovery():
+    text_attachment()
+
+    async def scenario():
+        job = await jobs.create_transcription("lecture.txt", wait=False)
+        cancelled = await jobs.cancel(job.job_id)
+        assert cancelled.status == "cancelled"
+        next_job = await jobs.retry(job.job_id)
+        assert next_job.previous_job_id == job.job_id
+        assert next_job.job_id != job.job_id
+        await jobs._tasks[jobs.task_key(next_job.job_id)]
+        assert jobs.require_job(next_job.job_id).status == "completed"
+        # Simulate a persisted job left behind by a stopped process.
+        cancelled.status = "running"
+        jobs.save(cancelled, "TranscriptionStarted")
+        jobs.recover_interrupted()
+        assert jobs.require_job(job.job_id).error_code == "TRANSCRIPTION_INTERRUPTED"
+
+    asyncio.run(scenario())
+
+
+def test_controlled_upload_and_async_http_flow():
+    from app.main import app
+    with TestClient(app) as client:
+        assert client.post("/api/media/attachments?filename=a.wav", content=b"").status_code == 422
+        uploaded = client.post("/api/media/attachments?filename=lecture.txt", content="真实转写文本".encode())
+        assert uploaded.status_code == 201
+        attachment_id = uploaded.json()["attachment_id"]
+        assert client.get(f"/api/media/attachments/{attachment_id}").content == "真实转写文本".encode()
+        response = client.post("/api/media/transcriptions", json={"attachment_id": attachment_id})
+        assert response.status_code == 202 and response.json()["status"] == "queued"
+        job_id = response.json()["job_id"]
+        events = client.get(f"/api/media/transcriptions/{job_id}/events")
+        assert "event: Completed" in events.text
+        assert client.get("/api/media/transcriptions").json()["page"]["total"] == 1
+        assert client.get(f"/api/media/transcriptions/{job_id}").json()["text"] == "真实转写文本"
+        assert client.get(f"/api/media/transcriptions/{job_id}/events", headers={"Last-Event-ID": "bad"}).status_code == 422
+
+
+def test_terminology_export_and_privacy_cleanup():
+    from app.main import app
+    text_attachment()
+    with TestClient(app) as client:
+        created = client.post('/api/media/transcriptions', json={'attachment_id':'lecture.txt','terminology':{'识别':'校对'}}).json()
+        job_id = created['job_id']
+        client.get(f'/api/media/transcriptions/{job_id}/events')
+        job = client.get(f'/api/media/transcriptions/{job_id}').json()
+        assert job['text'] == '原始校对内容' and job['original_text'] == '原始识别内容'
+        first = client.post(f'/api/media/transcriptions/{job_id}/notes', json={'title':'课程'}).json()
+        again = client.post(f'/api/media/transcriptions/{job_id}/notes', json={'title':'课程'}).json()
+        assert first['note_id'] == again['note_id']
+        response = client.delete('/api/media/attachments/lecture.txt')
+        assert first['note_id'] in response.json()['retained_note_ids']
+        cleaned = client.get(f'/api/media/transcriptions/{job_id}').json()
+        assert cleaned['text'] is None and cleaned['original_text'] is None and cleaned['corrections'] == []
+        assert client.post(f'/api/media/transcriptions/{job_id}/retry').status_code == 409
+        assert client.get('/api/media/attachments/lecture.txt').status_code == 404

backend/tests/test_model_routing.py

@@ -641,9 +641,14 @@ def test_api_speech_failure_reports_reason_in_503_and_transcription_job(api):
     assert match.status_code == 503
     assert match.json()["error"]["code"] == "LOCAL_MODEL_NOT_INSTALLED"
     assert match.json()["error"]["details"] == {"fallback_reason": "PROVIDER_UNAVAILABLE"}
-    transcript = api.client.post("/api/media/transcriptions", json={"attachment_id": source.name, "language": "zh"})
-    assert transcript.status_code == 202
-    job = transcript.json()
+    with api.client:
+        transcript = api.client.post("/api/media/transcriptions", json={"attachment_id": source.name, "language": "zh"})
+        assert transcript.status_code == 202
+        job = transcript.json()
+        assert job["status"] == "queued"
+        stream = api.client.get(f"/api/media/transcriptions/{job['job_id']}/events")
+        assert "event: Failed" in stream.text
+        job = api.client.get(f"/api/media/transcriptions/{job['job_id']}").json()
     assert job["status"] == "failed" and job["error_code"] == "LOCAL_MODEL_NOT_INSTALLED"
     assert job["fallback_reason"] == "PROVIDER_UNAVAILABLE"
     assert api.client.get(f"/api/media/transcriptions/{job['job_id']}").json() == job
@@ -661,3 +666,15 @@ def test_out_of_float_range_json_number_is_invalid_remote_and_falls_back(rig, au
         result = run(media_call(rig, capability, audio))
         assert result.source == "local" and result.score == rig.speech.score
         assert result.fallback_reason == "PROVIDER_INVALID_RESPONSE"
+
+
+def test_remote_segments_are_validated_and_local_only_skips_api(rig, audio):
+    bind(rig, "transcription")
+    rig.http.handler = lambda request: response({"text":"内容", "segments":[{"start":0,"end":1.5,"text":"内容"}]})
+    result = run(rig.service.transcribe(audio[0], "zh"))
+    assert result.source == "api" and result.segments[0].end_time == 1.5
+    rig.http.handler = lambda request: response({"text":"内容", "segments":[{"start":2,"end":1,"text":"内容"}]})
+    assert run(rig.service.transcribe(audio[0], "zh")).fallback_reason == "PROVIDER_INVALID_RESPONSE"
+    count = len(rig.requests)
+    result = run(rig.service.transcribe(audio[0], "zh", local_only=True))
+    assert result.source == "local" and len(rig.requests) == count

backend/tests/test_usage_overrides.py

@@ -0,0 +1,94 @@
+import asyncio
+import json
+from datetime import datetime, timedelta, timezone
+from contextlib import closing
+
+import httpx
+import pytest
+from pydantic import ValidationError
+
+from app.contracts import ModelRequest, ProviderConfig, ProviderType
+from app.providers.factory import ProviderFactory
+from app.request_overrides import RequestOverride, apply_overrides
+from app.services.usage_service import UsageAttempt, aggregate, connection
+
+
+def summary():
+    now = datetime.now(timezone.utc)
+    return aggregate(now - timedelta(days=1), now + timedelta(days=1))
+
+
+def test_cumulative_usage_deduplicates_and_missing_is_not_zero():
+    attempt = UsageAttempt("test", "chat", "openai_compatible")
+    attempt.observe({"usage": {"prompt_tokens": 100, "completion_tokens": 2, "prompt_tokens_details": {"cached_tokens": 75}}})
+    attempt.persist()
+    attempt.observe({"usage": {"completion_tokens": 5}})
+    attempt.observe({"usage": {"completion_tokens": 3}})
+    attempt.persist()
+    incomplete = UsageAttempt("test", "chat", "openai_compatible")
+    incomplete.persist()
+    result = summary()
+    assert result["request_count"] == 2
+    assert result["totals"]["input_tokens"] == 100
+    assert result["totals"]["output_tokens"] == 5
+    assert result["totals"]["cache_write_tokens"] is None
+    assert result["cache_hit_rate"] == .75
+    assert result["coverage"]["input_tokens"] == 1
+
+
+def test_anthropic_cache_is_added_once_and_raw_text_is_not_saved():
+    attempt = UsageAttempt("test", "claude", "anthropic_messages")
+    attempt.observe({"message": {"usage": {"input_tokens": 10, "cache_read_input_tokens": 80,
+        "cache_creation_input_tokens": 20, "output_tokens": 0, "secret": "private text"}}})
+    attempt.observe({"usage": {"output_tokens": 12}})
+    attempt.persist()
+    counts = summary()["totals"]
+    assert counts["input_tokens"] == 110 and counts["total_tokens"] == 122
+    assert counts["cache_miss_tokens"] == 10
+    with closing(connection()) as conn:
+        assert "private text" not in conn.execute("SELECT raw_json FROM model_usage").fetchone()[0]
+
+
+def test_override_rules_merge_and_respect_capability_and_stream():
+    rules = [RequestOverride(body={"stream_options": {"include_usage": True, "extra": 1}, "stop": ["one"]}),
+             RequestOverride(model="special", stream=True, body={"stream_options": {"extra": 2}, "stop": ["two"], "temperature": None}),
+             RequestOverride(capability="embedding", body={"dimensions": 384})]
+    base = {"model": "special", "messages": [], "stream": True}
+    result = apply_overrides(base, rules, "chat", stream=True)
+    assert result["stream_options"] == {"include_usage": True, "extra": 2}
+    assert result["stop"] == ["two"] and result["temperature"] is None
+    assert "dimensions" not in result and "stop" not in base
+    assert apply_overrides(base, rules, "chat")["stop"] == ["one"]
+
+
+@pytest.mark.parametrize("body", [{"model":"other"}, {"messages":[]}, {"tools":[]}, {"stream":False},
+    {"metadata":{"api_key":"hidden"}}, {"stream_options":{"include_usage": "false"}}])
+def test_unsafe_or_invalid_overrides_are_rejected(body):
+    with pytest.raises(ValidationError):
+        RequestOverride(body=body)
+
+
+def test_real_adapter_body_and_usage_persistence():
+    class Credentials:
+        def resolve(self, key):
+            return None
+    config = ProviderConfig(provider_id="wire", provider_type=ProviderType.openai_compatible, name="Wire", base_url="https://model.invalid/v1",
+        request_overrides=[RequestOverride(stream=True, body={"stream_options":{"include_usage":False},"enable_thinking":False})])
+    adapter = ProviderFactory(Credentials()).build(config)
+    captured = []
+    def respond(request):
+        captured.append(json.loads(request.content))
+        return httpx.Response(200, headers={"content-type":"text/event-stream"}, content=(
+            'data: {"choices":[{"delta":{"content":"ok"},"finish_reason":null}]}\n\n'
+            'data: {"choices":[],"usage":{"prompt_tokens":10,"completion_tokens":1}}\n\n'
+            'data: {"choices":[{"delta":{},"finish_reason":"stop"}]}\n\n'
+            'data: [DONE]\n\n'))
+    adapter.transport = httpx.MockTransport(respond)
+    async def consume():
+        return [event async for event in adapter.stream(ModelRequest(provider_id="wire", model="special", messages=[]))]
+    asyncio.run(consume())
+    assert captured[0]["enable_thinking"] is False
+    assert captured[0]["stream_options"]["include_usage"] is False
+    result = summary()
+    assert result["request_count"] == 1 and result["totals"]["input_tokens"] == 10
+    assert result["complete_requests"] == 1