feat(multimodal): 补齐阶段F运行管理与收尾验收

backend/app/contracts.py

@@ -1050,6 +1050,7 @@ class TranscriptEditRequest(Contract):
 
 
 class TranscriptNoteRequest(Contract):
+    update_existing: bool = False
     title: str = Field(min_length=1, max_length=200)
     folder: str | None = None
     include_timestamps: bool = True

backend/app/local_model_routes.py

@@ -1,4 +1,6 @@
+import asyncio
 from fastapi import APIRouter
+from app.services import model_diagnostics
 from app.local_models import manager
 from app.local_models.runtime import RuntimeConfig, configuration, configure, interpreter, runtime
 
@@ -7,9 +9,10 @@ router = APIRouter(prefix="/api/local-models", tags=["Local models"])
 
 @router.get("")
 async def list_models():
-    return {**manager.describe(), "runtime_installed": interpreter().is_file(), "config": configuration(),
+    items, diagnostics = await asyncio.gather(asyncio.to_thread(manager.describe), asyncio.to_thread(model_diagnostics.recent))
+    return {**items, "runtime_installed": interpreter().is_file(), "config": configuration(),
             "active_models": list(runtime.active.values()), "queued_requests": len(runtime.waiters),
-            "last_inference": runtime.diagnostics[-1] if runtime.diagnostics else None}
+            "last_inference": diagnostics[-1] if diagnostics else None}
 
 
 @router.put("/config")
@@ -34,5 +37,5 @@ async def delete(key: str):
 
 @router.get("/diagnostics")
 async def diagnostics():
-    return {"items": runtime.diagnostics, "config": configuration(), "scope": "current_process",
+    return {"items": await asyncio.to_thread(model_diagnostics.recent), "config": configuration(), "scope": "application_last_200_attempts",
             "contains": "model_revision_device_timing_resources_only"}

backend/app/local_models/manager.py

@@ -49,8 +49,20 @@ def task_key(key):
     return str(model_path(key)), key
 
 
+def disk_bytes(key):
+    total = 0
+    try:
+        root = model_path(key).resolve()
+        for path in root.rglob("*"):
+            if not path.is_symlink() and path.is_file() and path.resolve().is_relative_to(root):
+                total += path.stat().st_size
+    except OSError:
+        return None
+    return total
+
+
 def describe():
-    return {"items": [{**spec.public(), **read_state(key)} for key, spec in CATALOG.items()]}
+    return {"items": [{**spec.public(), **read_state(key), "disk_bytes": disk_bytes(key)} for key, spec in CATALOG.items()]}
 
 
 async def download(key):

backend/app/local_models/runtime.py

@@ -4,8 +4,10 @@ from __future__ import annotations
 import asyncio
 import json
 import os
+import time
 from contextlib import closing
 from contextvars import ContextVar
+from functools import wraps
 from pathlib import Path
 from typing import Literal
 
@@ -31,6 +33,18 @@ class RuntimeConfig(BaseModel):
 
 runtime_context = ContextVar("runtime_config", default=None)
 runtime_progress = ContextVar("runtime_progress", default=None)
+embedding_priority = ContextVar("embedding_priority", default=0)
+
+
+def background_embeddings(operation):
+    @wraps(operation)
+    async def wrapped(*args, **kwargs):
+        token = embedding_priority.set(20)
+        try:
+            return await operation(*args, **kwargs)
+        finally:
+            embedding_priority.reset(token)
+    return wrapped
 
 
 def configuration():
@@ -75,28 +89,81 @@ class Runtime:
         return any(target in paths for paths in self.active_files.values())
 
     async def infer(self, key, operation, payload, *, priority=10):
-        if read_state(key)["status"] != "installed":
-            raise ProviderError("LOCAL_MODEL_NOT_INSTALLED", "请先在模型配置中下载本地模型。")
-        if not interpreter().is_file():
-            raise ProviderError("LOCAL_RUNTIME_NOT_INSTALLED", "请先运行本地模型 CPU/CUDA 安装脚本。")
-        config = configuration()
+        from app.services import model_diagnostics
+        config = configuration().model_copy(deep=True)
         self.counter += 1
         ticket = (priority, self.counter)
         self.waiters.append(ticket)
-        process = None
-        attempt = None
+        queued_at = time.monotonic()
+        reason = None
+        from app.services.usage_service import usage_context
+        from uuid import uuid4
+        context = dict(usage_context.get() or {})
+        context.setdefault("request_id", uuid4().hex)
+        usage_token = usage_context.set(context)
         try:
-            # One resident model at a time prevents overlapping CPU/GPU allocations.
             while self.active or ticket != min(self.waiters):
                 await asyncio.sleep(0.05)
             self.waiters.remove(ticket)
             self.active[ticket] = key
             self.active_files[ticket] = {str(Path(payload[name]).resolve()) for name in ("source", "reference") if payload.get(name)}
-            # Deletion may have occurred while this request was queued.
-            if read_state(key)["status"] != "installed":
-                raise ProviderError("LOCAL_MODEL_NOT_INSTALLED", "模型文件已被删除。")
-            from app.services.usage_service import UsageAttempt
-            attempt = UsageAttempt("local-models", CATALOG[key].repository, "local", operation, source="local")
+            queue_seconds = time.monotonic() - queued_at
+            # Keep the reservation while replacing a failed CUDA process with CPU.
+            for device in (["cuda", "cpu"] if config.device == "cuda" else ["cpu"]):
+                started = time.monotonic()
+                diagnostics = dict(model=CATALOG[key].repository, revision=CATALOG[key].revision,
+                    operation=operation, source="local", requested_device=config.device,
+                    attempted_device=device, queue_seconds=queue_seconds, fallback_reason=reason, request_id=context["request_id"])
+                try:
+                    result = await self._execute(key, operation, payload, config.model_copy(update={"device": device}), diagnostics)
+                    diagnostics.update(result.get("diagnostics", {}))
+                    diagnostics.update(requested_device=config.device, status="completed")
+                    if reason:
+                        diagnostics["fallback_reason"] = reason
+                    return result["result"]
+                except asyncio.CancelledError:
+                    diagnostics.update(status="cancelled", error_code="LOCAL_MODEL_CANCELLED")
+                    raise
+                except ProviderError as exc:
+                    diagnostics.update(status="failed", error_code=exc.code)
+                    if device == "cuda" and exc.code in {"LOCAL_CUDA_INIT_FAILED", "LOCAL_CUDA_OOM"}:
+                        reason = exc.code
+                        callback = runtime_progress.get()
+                        if callback:
+                            callback({"reset": True, "progress": 0})
+                        continue
+                    raise
+                except Exception:
+                    diagnostics.update(status="failed", error_code="LOCAL_MODEL_INVALID_RESPONSE")
+                    raise ProviderError("LOCAL_MODEL_INVALID_RESPONSE", "本地模型返回无效数据。") from None
+                finally:
+                    diagnostics["requested_device"] = config.device
+                    diagnostics["elapsed_seconds"] = time.monotonic() - started
+                    self.diagnostics.append(model_diagnostics.record(**diagnostics))
+                    self.diagnostics = self.diagnostics[-100:]
+        except asyncio.CancelledError:
+            if ticket not in self.active:
+                model_diagnostics.record(model=CATALOG[key].repository, operation=operation,
+                    source="local", status="cancelled", error_code="LOCAL_QUEUE_CANCELLED",
+                    requested_device=config.device, queue_seconds=time.monotonic() - queued_at)
+            raise
+        finally:
+            if ticket in self.waiters:
+                self.waiters.remove(ticket)
+            self.active.pop(ticket, None)
+            self.active_files.pop(ticket, None)
+            usage_context.reset(usage_token)
+
+    async def _execute(self, key, operation, payload, config, diagnostics):
+        if read_state(key)["status"] != "installed":
+            raise ProviderError("LOCAL_MODEL_NOT_INSTALLED", "请先下载本地模型。")
+        if not interpreter().is_file():
+            raise ProviderError("LOCAL_RUNTIME_NOT_INSTALLED", "请先安装本地模型运行环境。")
+        from app.services.usage_service import UsageAttempt
+        attempt = UsageAttempt("local-models", CATALOG[key].repository, "local", operation, source="local")
+        diagnostics.update(attempt_id=attempt.attempt_id, request_id=attempt.request_id)
+        process = None
+        try:
             env = {**os.environ, "HF_HUB_OFFLINE": "1", "TRANSFORMERS_OFFLINE": "1",
                    "HF_HUB_DISABLE_TELEMETRY": "1", "OMP_NUM_THREADS": str(config.cpu_threads),
                    "PYTHONIOENCODING": "utf-8"}
@@ -118,8 +185,6 @@ class Runtime:
                 process.stdin.close()
                 final = None
                 while line := await process.stdout.readline():
-                    if len(line) > 16 * 1024 * 1024:
-                        raise ProviderError("LOCAL_MODEL_INVALID_RESPONSE", "本地模型输出超限。")
                     message = json.loads(line)
                     if "progress" in message:
                         callback = runtime_progress.get()
@@ -137,26 +202,19 @@ class Runtime:
                 raise ProviderError("LOCAL_MODEL_PROCESS_FAILED", "本地模型进程退出，请检查依赖与资源预算。")
             if not isinstance(result, dict):
                 raise ProviderError("LOCAL_MODEL_INVALID_RESPONSE", "本地模型进程未返回有效结果。")
+            diagnostics.update(result.get("diagnostics", {}))
             if "error_code" in result:
                 raise ProviderError(result["error_code"], result.get("message", "本地推理失败。"))
             attempt.observe(result)
             attempt.completed = True
-            self.diagnostics.append({"model": CATALOG[key].repository, "revision": CATALOG[key].revision,
-                                     **result.get("diagnostics", {})})
-            self.diagnostics = self.diagnostics[-100:]
-            return result["result"]
+            return result
         finally:
-            if ticket in self.waiters:
-                self.waiters.remove(ticket)
             if process is not None and process.returncode is None:
                 process.kill()
                 await process.wait()
             if process is not None and hasattr(process, "close"):
                 await process.close()
-            self.active.pop(ticket, None)
-            self.active_files.pop(ticket, None)
-            if attempt:
-                attempt.persist()
+            attempt.persist()
 
 
 runtime = Runtime()
@@ -188,7 +246,7 @@ class LocalEmbedding:
         config = (self._config or configuration()).model_copy(deep=True)
         token = runtime_context.set(config)
         try:
-            return await runtime.infer(config.embedding_model, "embedding", {"texts": texts}, priority=0)
+            return await runtime.infer(config.embedding_model, "embedding", {"texts": texts}, priority=embedding_priority.get())
         finally:
             runtime_context.reset(token)
 

backend/app/local_models/worker.py

@@ -76,16 +76,25 @@ def voice_embedding(model, audio, device):
         return torch.nn.functional.normalize(vector, dim=0)
 
 
+class CudaInitializationError(RuntimeError):
+    pass
+
+
 def run(request):
     import torch
     import psutil
     config, payload = request["config"], request["payload"]
     torch.set_num_threads(config["cpu_threads"])
     requested = config["device"]
-    device = "cuda:0" if requested == "cuda" and torch.cuda.is_available() else "cpu"
-    if device != "cpu":
-        total = torch.cuda.get_device_properties(0).total_memory
-        torch.cuda.set_per_process_memory_fraction(min(1.0, config["gpu_memory_limit_mb"] * 1024 ** 2 / total))
+    try:
+        device = "cuda:0" if requested == "cuda" and torch.cuda.is_available() else "cpu"
+        if device != "cpu":
+            torch.cuda.init()
+            total = torch.cuda.get_device_properties(0).total_memory
+            torch.cuda.set_per_process_memory_fraction(min(1.0, config["gpu_memory_limit_mb"] * 1024 ** 2 / total))
+    except Exception as exc:
+        raise CudaInitializationError() from exc
+    request["_actual_device"] = device
     process = psutil.Process()
     peak = [0]
     stop = threading.Event()
@@ -102,6 +111,7 @@ def run(request):
     path, operation = request["model_path"], request["operation"]
     try:
         usage = {}
+        audio_seconds = None
         if operation == "embedding":
             from sentence_transformers import SentenceTransformer
             model = SentenceTransformer(path, device=device, local_files_only=True, trust_remote_code=False,
@@ -116,6 +126,7 @@ def run(request):
                 device_map=device, attn_implementation="sdpa", max_inference_batch_size=1, max_new_tokens=512)
             loaded = time.monotonic()
             audio = decode(payload["source"])
+            audio_seconds = len(audio) / 16000
             regions = speech_regions(audio)
             language = {"zh": "Chinese", "en": "English", "ja": "Japanese", "yue": "Cantonese"}.get(payload.get("language"), payload.get("language"))
             segments = []
@@ -154,7 +165,7 @@ def run(request):
             result = {"speakers": speakers}
         else:
             raise ValueError("Unknown inference operation")
-        return {"result": result, "usage": usage, "diagnostics": {"requested_device": requested, "actual_device": device,
+        return {"result": result, "usage": usage, "audio_seconds": audio_seconds, "diagnostics": {"requested_device": requested, "actual_device": device,
                 "fallback_reason": "CUDA_UNAVAILABLE" if requested == "cuda" and device == "cpu" else None,
                 "load_seconds": loaded - started, "inference_seconds": time.monotonic() - loaded,
                 "peak_memory_bytes": max(peak[0], process.memory_info().rss), "operation": operation}}
@@ -170,6 +181,16 @@ if __name__ == "__main__":
             response = run(request)
         except (ImportError, ModuleNotFoundError):
             response = {"error_code": "LOCAL_RUNTIME_DEPENDENCY_MISSING", "message": "本地模型运行依赖不完整，请重新运行安装脚本。"}
-        except Exception:
-            response = {"error_code": "LOCAL_INFERENCE_FAILED", "message": "本地推理失败，请检查媒体格式、模型和设备配置。"}
+        except Exception as exc:
+            # Only device failures allow the host to retry once in a fresh CPU process.
+            import torch
+            cuda_failure = isinstance(exc, CudaInitializationError)
+            cuda_oom = request.get("_actual_device") == "cuda:0" and isinstance(exc, torch.cuda.OutOfMemoryError)
+            if cuda_failure or cuda_oom:
+                response = {"error_code": "LOCAL_CUDA_OOM" if cuda_oom else "LOCAL_CUDA_INIT_FAILED",
+                            "message": "CUDA 运行失败，将释放进程并重试 CPU。"}
+            else:
+                response = {"error_code": "LOCAL_INFERENCE_FAILED", "message": "本地推理失败，请检查媒体格式、模型和设备配置。"}
+    if "error_code" in response:
+        response["diagnostics"] = {"requested_device": request["config"]["device"], "actual_device": request.get("_actual_device", "unknown")}
     sys.stdout.buffer.write((json.dumps(response, ensure_ascii=False, allow_nan=False) + "\n").encode("utf-8"))

backend/app/media_routes.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 
 import asyncio
 import json
+import hashlib
 from contextlib import closing
 from pathlib import Path
 from uuid import uuid4
@@ -22,14 +23,17 @@ MEDIA_SUFFIXES = {".wav", ".mp3", ".flac", ".ogg", ".m4a", ".mp4", ".webm", ".tx
 
 
 @router.post("/attachments", status_code=201)
-async def upload_attachment(request: Request, filename: str = Query(min_length=1, max_length=255)):
+async def upload_attachment(request: Request, filename: str = Query(min_length=1, max_length=255),
+                            idempotency_key: str | None = Header(None, min_length=16, max_length=100, pattern=r"^[a-zA-Z0-9_-]+$")):
     suffix = Path(filename).suffix.lower()
     if suffix not in MEDIA_SUFFIXES:
         raise ApiError(422, "UNSUPPORTED_MEDIA", "Unsupported attachment extension.")
-    attachment_id = f"media_{uuid4().hex}{suffix}"
+    identity = hashlib.sha256(idempotency_key.encode()).hexdigest() if idempotency_key else uuid4().hex
+    attachment_id = f"media_{identity}{suffix}"
     destination = attachment_path(attachment_id)
     destination.parent.mkdir(parents=True, exist_ok=True)
-    temporary = destination.with_suffix(destination.suffix + ".upload")
+    temporary = destination.with_suffix(destination.suffix + f".{uuid4().hex}.upload")
+    digest = hashlib.sha256()
     size = 0
     try:
         with temporary.open("xb") as stream:
@@ -37,10 +41,15 @@ async def upload_attachment(request: Request, filename: str = Query(min_length=1
                 size += len(chunk)
                 if size > MAX_UPLOAD_BYTES:
                     raise ApiError(413, "ATTACHMENT_TOO_LARGE", "Attachment exceeds 25 MiB.")
+                digest.update(chunk)
                 stream.write(chunk)
         if not size:
             raise ApiError(422, "EMPTY_ATTACHMENT", "Attachment is empty.")
-        temporary.replace(destination)
+        if destination.exists():
+            if hashlib.sha256(destination.read_bytes()).digest() != digest.digest():
+                raise ApiError(409, "IDEMPOTENCY_CONFLICT", "同一上传标识不能用于不同附件。")
+        else:
+            temporary.replace(destination)
     finally:
         temporary.unlink(missing_ok=True)
     return {"attachment_id": attachment_id, "filename": Path(filename).name, "size": size}

backend/app/provider_preview_routes.py

@@ -1,12 +1,67 @@
 from fastapi import APIRouter
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 from app.contracts import ProviderCreateRequest, ProviderConfig, ModelRequest, Message, MessageRole
 from app.providers.factory import ProviderFactory
-from app.request_overrides import apply_overrides
+from app.request_overrides import RequestOverride, apply_overrides
 
 router = APIRouter(prefix="/api/providers", tags=["Providers"])
 
 
+class RulesTransfer(BaseModel):
+    version: int = Field(default=1, ge=1, le=1)
+    request_overrides: list[RequestOverride] = Field(max_length=100)
+
+
+@router.post("/request-rules/validate")
+async def validate_rules(request: RulesTransfer):
+    return request
+
+
+class ProbeRequest(BaseModel):
+    provider: ProviderCreateRequest
+    stream: bool = True
+
+
+@router.post("/request-probe")
+async def probe(request: ProbeRequest):
+    """Explicit user-triggered inference; no vault context, tools or media uploads."""
+    import asyncio
+    from contextlib import aclosing
+    from app.container import container
+    from app.errors import ApiError
+    from app.providers.base import ProviderError
+    from app.providers.factory import UnsupportedProviderError
+    config = ProviderConfig(provider_id="request-probe", **request.provider.model_dump())
+    if not config.default_model:
+        raise ApiError(422, "MODEL_REQUIRED", "请填写要验证的模型 ID。")
+    try:
+        adapter = container.provider_factory.build(config)
+        model_request = ModelRequest(provider_id=config.provider_id, model=config.default_model,
+            messages=[Message(role=MessageRole.user, content="Reply with OK.")], max_tokens=32)
+        received = False
+        async with asyncio.timeout(45):
+            if request.stream:
+                async with aclosing(adapter.stream(model_request)) as events:
+                    async for event in events:
+                        if event.event.value in {"TextDelta", "ThinkingDelta"}:
+                            received = received or bool(str(event.data.get("text") or "").strip())
+                        if event.event.value == "Error":
+                            raise ProviderError("PROVIDER_PROBE_FAILED", "模型返回了错误事件。")
+            else:
+                response = await adapter.complete(model_request)
+                received = bool(response.text and response.text.strip())
+        if not received:
+            raise ApiError(422, "PROVIDER_EMPTY_RESPONSE", "请求未返回有效文本，不能标记验证通过。")
+    except ProviderError as exc:
+        raise ApiError(502, exc.code, "推理验证失败，请检查模型、凭据和自定义参数。") from exc
+    except TimeoutError as exc:
+        raise ApiError(504, "PROVIDER_TIMEOUT", "推理验证超时。") from exc
+    except UnsupportedProviderError as exc:
+        raise ApiError(422, "PROVIDER_TYPE_UNSUPPORTED", "该协议不支持推理验证。") from exc
+    return {"success": True, "stream": request.stream, "model": config.default_model,
+            "message": "当前请求配置已通过实际推理验证。"}
+
+
 class PreviewRequest(BaseModel):
     provider: ProviderCreateRequest
     stream: bool = True

backend/app/providers/routing.py

@@ -6,6 +6,8 @@ available only for explicitly injected tests and protocol fixtures.
 from __future__ import annotations
 
 import hashlib
+import asyncio
+import time
 import json
 import math
 from dataclasses import dataclass, field, replace
@@ -179,6 +181,7 @@ class ModelRoutingService:
         payload = apply_overrides(kwargs.get(field, {}), provider.request_overrides, capability)
         kwargs[field] = payload if field == "json" else {key: json.dumps(value) if isinstance(value, (dict, list, bool)) or value is None else value for key, value in payload.items()}
         attempt = UsageAttempt(binding.provider_id, binding.model, provider.provider_type.value, capability)
+        started = time.monotonic()
         try:
             async with httpx.AsyncClient(timeout=30, transport=self.transport) as client:
                 async with client.stream("POST", url, headers=headers, **kwargs) as response:
@@ -202,6 +205,11 @@ class ModelRoutingService:
             raise invalid_response() from exc
         finally:
             attempt.persist()
+            from app.services.model_diagnostics import record
+            task = asyncio.current_task()
+            status = "completed" if attempt.completed else ("cancelled" if task and task.cancelling() else "failed")
+            record(model=binding.model, operation=capability, source="api", status=status,
+                   attempt_id=attempt.attempt_id, request_id=attempt.request_id, elapsed_seconds=time.monotonic() - started)
         if not isinstance(data, dict) or data.get("error"):
             raise invalid_response()
         return data, url
@@ -255,6 +263,9 @@ class ModelRoutingService:
                                        model_id="api-" + hashlib.sha256(identity.encode()).hexdigest())
             except ProviderError as exc:
                 reason = exc.code
+                from app.services.model_diagnostics import record
+                record(model=binding.model, source="api", status="fallback", error_code=reason,
+                       fallback_reason=reason, operation="model_routing")
         from app.local_models.runtime import LocalEmbedding
         local_embedding = self.local_embedding.snapshot() if isinstance(self.local_embedding, LocalEmbedding) else self.local_embedding
         try:
@@ -314,6 +325,9 @@ class ModelRoutingService:
                 return RoutedTranscript(text=text, source="api", segments=segments)
             except ProviderError as exc:
                 reason = exc.code
+                from app.services.model_diagnostics import record
+                record(model=binding.model, source="api", status="fallback", error_code=reason,
+                       fallback_reason=reason, operation="model_routing")
         try:
             text = await self.local_speech.transcribe(source, language)
             if isinstance(text, RoutedTranscript):
@@ -346,6 +360,9 @@ class ModelRoutingService:
                 return SpeakerMatchResult(score=score, source="api")
             except ProviderError as exc:
                 reason = exc.code
+                from app.services.model_diagnostics import record
+                record(model=binding.model, source="api", status="fallback", error_code=reason,
+                       fallback_reason=reason, operation="model_routing")
         try:
             score = await self.local_speech.match(source, reference)
             if not finite_number(score) or not 0 <= score <= 1:

backend/app/services/media_notes.py

@@ -19,8 +19,10 @@ async def create_transcript_note(job_id, options):
         job = require_job(job_id)
         if job.status != "completed":
             raise ApiError(409, "TRANSCRIPT_NOT_READY", "Only completed transcripts can become notes.")
-        options_hash = hashlib.sha256(options.model_dump_json().encode()).hexdigest()
+        options_hash = hashlib.sha256(options.model_copy(update={"update_existing": False}).model_dump_json(exclude={"update_existing"}).encode()).hexdigest()
         with closing(connect()) as conn:
+            conn.execute("CREATE TABLE IF NOT EXISTS media_note_baselines (note_id TEXT PRIMARY KEY, content_hash TEXT NOT NULL)")
+            previous = conn.execute("SELECT m.note_id,b.content_hash FROM media_notes m LEFT JOIN media_note_baselines b ON b.note_id=m.note_id WHERE m.job_id=? AND m.options_hash=? ORDER BY m.revision DESC LIMIT 1", (job_id, options_hash)).fetchone()
             row = conn.execute("SELECT note_id FROM media_notes WHERE job_id=? AND revision=? AND options_hash=?",
                                (job_id, job.revision, options_hash)).fetchone()
         if row:
@@ -44,15 +46,34 @@ async def create_transcript_note(job_id, options):
         if job.local_only:
             # Persist the indexing policy in the Vault, including later rebuilds.
             lines = ["---", "embedding_local_only: true", "---", "", *lines]
-        try:
-            note = await note_service.create_note(title=title, markdown="\n".join(lines), folder=options.folder, tags=["转写"])
-        except ApiError as exc:
-            if exc.code != "RESOURCE_CONFLICT" or "note_id" not in exc.details:
-                raise
-            # Recover a crash between successful note creation and linking the job.
-            note = await note_service.get_note(exc.details["note_id"])
-            if note is None or marker not in note.markdown:
-                raise
+        markdown = "\n".join(lines)
+        if options.update_existing:
+            if previous is None or previous[1] is None:
+                raise ApiError(409, "NOTE_UPDATE_BASELINE_MISSING", "没有可安全更新的导出记录，请先创建新笔记。")
+            current = await note_service.get_note(previous[0])
+            if current is None:
+                raise ApiError(404, "RESOURCE_NOT_FOUND", "已导出笔记不存在。")
+            # Recover a successful update if linking failed after the Vault write.
+            if current.markdown == markdown:
+                note = current
+            else:
+                note = await note_service.update_note(previous[0], markdown=markdown, expected_content_hash=previous[1])
+        else:
+            note = await _create_note(title, markdown, options, marker)
         with closing(connect()) as conn, transaction(conn):
             conn.execute("INSERT OR IGNORE INTO media_notes VALUES (?,?,?,?)", (job_id, job.revision, options_hash, note.note_id))
+            conn.execute("INSERT OR REPLACE INTO media_note_baselines VALUES (?,?)", (note.note_id, hashlib.sha256(markdown.encode()).hexdigest()))
         return note
+
+
+async def _create_note(title, markdown, options, marker):
+    try:
+        note = await note_service.create_note(title=title, markdown=markdown, folder=options.folder, tags=["转写"])
+    except ApiError as exc:
+        if exc.code != "RESOURCE_CONFLICT" or "note_id" not in exc.details:
+            raise
+        # Recover a crash between successful note creation and linking the job.
+        note = await note_service.get_note(exc.details["note_id"])
+        if note is None or marker not in note.markdown:
+            raise
+    return note

backend/app/services/model_diagnostics.py

@@ -0,0 +1,37 @@
+"""Bounded, durable diagnostics. No payloads, paths, exception text or credentials."""
+import json
+import logging
+import math
+from contextlib import closing
+from datetime import datetime, timezone
+
+from app.database.db import connect, transaction
+
+TEXT = {"model", "revision", "operation", "source", "requested_device", "actual_device",
+        "attempted_device", "fallback_reason", "error_code", "status", "request_id", "attempt_id"}
+NUMBERS = {"load_seconds", "inference_seconds", "elapsed_seconds", "peak_memory_bytes", "queue_seconds"}
+
+
+def connection():
+    conn = connect()
+    conn.execute("CREATE TABLE IF NOT EXISTS model_diagnostics (id INTEGER PRIMARY KEY AUTOINCREMENT, record_json TEXT NOT NULL)")
+    return conn
+
+
+def record(**values):
+    safe = {key: value[:240] for key, value in values.items() if key in TEXT and isinstance(value, str)}
+    safe.update({key: value for key, value in values.items()
+                 if key in NUMBERS and type(value) in (float, int) and math.isfinite(value) and value >= 0})
+    safe["timestamp"] = datetime.now(timezone.utc).isoformat()
+    try:
+        with closing(connection()) as conn, transaction(conn):
+            conn.execute("INSERT INTO model_diagnostics(record_json) VALUES (?)", (json.dumps(safe),))
+            conn.execute("DELETE FROM model_diagnostics WHERE id NOT IN (SELECT id FROM model_diagnostics ORDER BY id DESC LIMIT 200)")
+    except Exception:
+        logging.getLogger(__name__).warning("Model diagnostic persistence failed")
+    return safe
+
+
+def recent():
+    with closing(connection()) as conn:
+        return [json.loads(row[0]) for row in conn.execute("SELECT record_json FROM model_diagnostics ORDER BY id")]

backend/app/services/note_service.py

@@ -17,7 +17,7 @@ from app.contracts import Note, NoteBlock, NoteSummary
 from app.database.db import connect, transaction
 from app.errors import ApiError
 from app.knowledge.parser import ParsedNote, parse_note
-from app.local_models.runtime import LocalEmbedding
+from app.local_models.runtime import LocalEmbedding, background_embeddings
 from app.retrieval import routed_vectors
 from app.retrieval.vectorstore import SqliteVecStore, VectorRecord
 from app.services.coordination import serialized_vault_mutation
@@ -77,6 +77,7 @@ def _delete_markdown(rel_path: str) -> None:
 PreparedIndex = tuple[list[list[float]], routed_vectors.RemoteEmbeddings | None]
 
 
+@background_embeddings
 async def prepare_note_index(parsed: ParsedNote, *, strict=False) -> PreparedIndex:
     """Compute vectors before opening a write transaction (including API I/O)."""
     texts = [block.content for block in parsed.blocks]
@@ -180,13 +181,18 @@ async def get_note(note_id: str) -> Note | None:
 
 @serialized_vault_mutation
 async def update_note(
-    note_id: str, *, title: str | None = None, markdown: str | None = None, tags: list[str] | None = None
+    note_id: str, *, title: str | None = None, markdown: str | None = None, tags: list[str] | None = None, expected_content_hash: str | None = None
 ) -> Note:
     record = repository.get_note_record(note_id)
     if record is None:
         raise ApiError(404, "RESOURCE_NOT_FOUND", "note not found", {"note_id": note_id})
 
     old_md = _read_markdown(record.file_path)
+    if expected_content_hash is not None:
+        import hashlib
+        if hashlib.sha256(old_md.encode()).hexdigest() != expected_content_hash:
+            raise ApiError(409, "NOTE_CONTENT_CONFLICT", "笔记已被编辑，请保留现有内容或导出为新笔记。")
+
     new_md = old_md if markdown is None else markdown
     # PATCH 语义：tags=None 保持原标签；[] 清空；非空列表替换（区别于 create 的 frontmatter 推导）
     effective_tags = record.tags if tags is None else tags

backend/app/services/transcription_service.py

@@ -134,6 +134,10 @@ async def _execute(job_id, request, routing=None):
     from app.contracts import TranscriptSegment
     token = runtime_context.set(RuntimeConfig.model_validate(job.model_snapshot.get("local_runtime", {})))
     def progress(message):
+        if message.get("reset"):
+            job.segments = []; job.progress = 0
+            save(job, "AttemptRestarted")
+            return
         job.progress = max(0.0, min(0.99, message["progress"]))
         job.segments.append(TranscriptSegment.model_validate(message["segment"]))
         save(job, "SegmentReady")

backend/app/services/usage_service.py

@@ -3,6 +3,7 @@ from __future__ import annotations
 
 import json
 import logging
+import math
 from contextlib import closing
 from contextvars import ContextVar
 from datetime import datetime, timezone
@@ -53,6 +54,7 @@ class UsageAttempt:
         self.capability, self.source = capability, source
         self.started_at = datetime.now(timezone.utc).isoformat()
         self.raw = {}
+        self.audio_seconds = None
         self.completed = False
         context = usage_context.get() or {}
         self.request_id = context.get("request_id") or uuid4().hex
@@ -61,6 +63,9 @@ class UsageAttempt:
     def observe(self, data):
         if not isinstance(data, dict):
             return
+        duration = data.get("audio_seconds", data.get("duration"))
+        if self.capability in {"transcription", "speaker_matching"} and type(duration) in (int, float) and math.isfinite(duration) and 0 <= duration <= 7200:
+            self.audio_seconds = max(self.audio_seconds or 0, duration)
         values = [data.get("usage"), (data.get("message") or {}).get("usage") if isinstance(data.get("message"), dict) else None,
                   (data.get("response") or {}).get("usage") if isinstance(data.get("response"), dict) else None]
         if self.protocol == "ollama":
@@ -87,7 +92,7 @@ class UsageAttempt:
             miss = inputs - hit
         if hit is not None and inputs is not None and hit > inputs:
             hit, miss = None, None
-        return dict(input_tokens=inputs, output_tokens=outputs,
+        return dict(audio_seconds=self.audio_seconds, input_tokens=inputs, output_tokens=outputs,
                     total_tokens=inputs + outputs if inputs is not None and outputs is not None else first("total_tokens"),
                     cache_hit_tokens=hit, cache_miss_tokens=miss, cache_write_tokens=write,
                     reasoning_tokens=first("output_tokens_details.reasoning_tokens", "completion_tokens_details.reasoning_tokens"))
@@ -103,7 +108,7 @@ class UsageAttempt:
 
 
 def aggregate(start, end, provider_id=None, model=None, source=None):
-    query = "SELECT counters_json,completed FROM model_usage WHERE started_at>=? AND started_at<?"
+    query = "SELECT counters_json,completed,capability FROM model_usage WHERE started_at>=? AND started_at<?"
     args = [start.astimezone(timezone.utc).isoformat(), end.astimezone(timezone.utc).isoformat()]
     for column, value in (("provider_id", provider_id), ("model", model), ("source", source)):
         if value:
@@ -115,8 +120,14 @@ def aggregate(start, end, provider_id=None, model=None, source=None):
     totals = {key: None for key in METRICS}
     coverage = {key: 0 for key in METRICS}
     hits, eligible_input, cache_requests = 0, 0, 0
+    audio_requests, audio_covered, audio_seconds = 0, 0, None
     for row in rows:
+        if row[2] in {"transcription", "speaker_matching"}:
+            audio_requests += 1
         counts = json.loads(row[0])
+        if counts.get("audio_seconds") is not None:
+            audio_covered += 1
+            audio_seconds = (audio_seconds or 0) + counts["audio_seconds"]
         for key in METRICS:
             if counts.get(key) is not None:
                 totals[key] = (totals[key] or 0) + counts[key]
@@ -125,7 +136,7 @@ def aggregate(start, end, provider_id=None, model=None, source=None):
             hits += counts["cache_hit_tokens"]
             eligible_input += counts["input_tokens"] if counts.get("input_tokens") is not None else counts["cache_hit_tokens"] + counts["cache_miss_tokens"]
             cache_requests += 1
-    return {"totals": totals, "coverage": coverage, "request_count": len(rows),
+    return {"audio_request_count": audio_requests, "audio_seconds": audio_seconds, "audio_covered_requests": audio_covered, "totals": totals, "coverage": coverage, "request_count": len(rows),
             "complete_requests": sum(row[1] for row in rows), "cache_covered_requests": cache_requests,
             "cache_hit_rate": hits / eligible_input if eligible_input else None,
             "options": [dict(row) for row in options], "start": start, "end": end,

backend/scripts/install-model-runtime.ps1

@@ -1,9 +1,10 @@
 param(
-    [ValidateSet('cpu', 'cuda')][string]$Device = 'cpu'
+    [ValidateSet('cpu', 'cuda')][string]$Device = 'cpu',
+    [string]$RuntimeDirectory = ''
 )
 $ErrorActionPreference = 'Stop'
 $backendRoot = Split-Path $PSScriptRoot -Parent
-$runtimeRoot = Join-Path $backendRoot '.venv-models'
+$runtimeRoot = if ($RuntimeDirectory) { [IO.Path]::GetFullPath($RuntimeDirectory) } else { Join-Path $backendRoot '.venv-models' }
 $runtimePython = Join-Path $runtimeRoot 'Scripts/python.exe'
 if (!(Test-Path -LiteralPath $runtimePython)) {
     & uv venv --python 3.12 $runtimeRoot
@@ -11,7 +12,9 @@ if (!(Test-Path -LiteralPath $runtimePython)) {
 }
 # CPU is the default. CUDA wheels include the runtime, not the NVIDIA driver.
 $torchIndex = if ($Device -eq 'cuda') { 'https://download.pytorch.org/whl/cu128' } else { 'https://download.pytorch.org/whl/cpu' }
-& uv pip install --python $runtimePython --index-url $torchIndex 'torch==2.9.1' 'torchaudio==2.9.1'
+$wheelVariant = if ($Device -eq 'cuda') { 'cu128' } else { 'cpu' }
+# Pin the local version too: ==2.9.1 alone also accepts an already-installed CPU wheel.
+& uv pip install --python $runtimePython --index-url $torchIndex "torch==2.9.1+$wheelVariant" "torchaudio==2.9.1+$wheelVariant"
 if ($LASTEXITCODE -ne 0) { throw 'PyTorch 安装失败' }
 & uv pip install --python $runtimePython -r (Join-Path $PSScriptRoot 'model-requirements.lock') -c (Join-Path $PSScriptRoot 'model-requirements.txt')
 if ($LASTEXITCODE -ne 0) { throw '模型依赖安装失败' }

backend/tests/test_multimodal_finalization.py

@@ -0,0 +1,221 @@
+"""Finalization regressions: device recovery, durable facts and guarded writes."""
+import asyncio
+import json
+import sys
+from contextlib import closing
+from datetime import datetime, timedelta, timezone
+from pathlib import Path
+
+import pytest
+from fastapi.testclient import TestClient
+
+from app.errors import ApiError
+from app.providers.base import ProviderError
+
+
+@pytest.mark.parametrize('code,retries', [('LOCAL_CUDA_OOM', True), ('LOCAL_CUDA_INIT_FAILED', True),
+                                          ('LOCAL_INFERENCE_FAILED', False), ('LOCAL_RUNTIME_DEPENDENCY_MISSING', False)])
+def test_cuda_retries_only_device_failures_in_reaped_process(monkeypatch, code, retries):
+    import app.local_models.runtime as module
+    from app.services import model_diagnostics
+    from app.services.usage_service import connection
+    monkeypatch.setattr(module, 'configuration', lambda: module.RuntimeConfig(device='cuda'))
+    monkeypatch.setattr(module, 'read_state', lambda key: {'status': 'installed'})
+    monkeypatch.setattr(module, 'interpreter', lambda: Path(sys.executable))
+    events = []
+
+    class Process:
+        def __init__(self):
+            from types import SimpleNamespace
+            self.stdin = SimpleNamespace(write=self.write, drain=self.drain, close=lambda: None)
+            self.stdout = asyncio.StreamReader()
+            self.returncode = None
+            self.device = None
+        def write(self, raw):
+            self.device = json.loads(raw)['config']['device']
+            events.append('start-' + self.device)
+            result = {'error_code': code} if self.device == 'cuda' else {'result': [[1, 0]], 'usage': {'input_tokens': 2}, 'diagnostics': {'actual_device': 'cpu'}}
+            self.stdout.feed_data((json.dumps(result) + '\n').encode())
+            self.stdout.feed_eof()
+        async def drain(self):
+            pass
+        async def close(self):
+            pass
+        async def wait(self):
+            self.returncode = 0
+            events.append('reaped-' + self.device)
+        def kill(self):
+            self.returncode = -9
+
+    async def spawn(*args, **kwargs):
+        if events:
+            assert events[-1] == 'reaped-cuda'
+        return Process()
+    monkeypatch.setattr(module.asyncio, 'create_subprocess_exec', spawn)
+
+    async def scenario():
+        runtime = module.Runtime()
+        if retries:
+            assert await runtime.infer('bekko', 'embedding', {'texts': ['private text']}) == [[1, 0]]
+        else:
+            with pytest.raises(ProviderError) as error:
+                await runtime.infer('bekko', 'embedding', {'texts': ['private text']})
+            assert error.value.code == code
+        assert not runtime.active and not runtime.waiters
+    asyncio.run(scenario())
+    assert events == (['start-cuda', 'reaped-cuda', 'start-cpu', 'reaped-cpu'] if retries else ['start-cuda', 'reaped-cuda'])
+    records = model_diagnostics.recent()
+    assert records[0]['error_code'] == code
+    assert 'private text' not in json.dumps(records)
+    if retries:
+        assert records[-1]['requested_device'] == 'cuda' and records[-1]['actual_device'] == 'cpu'
+        assert records[-1]['fallback_reason'] == code
+        assert records[0]['request_id'] == records[1]['request_id']
+        assert records[0]['attempt_id'] != records[1]['attempt_id']
+    with closing(connection()) as conn:
+        assert conn.execute('SELECT COUNT(*) FROM model_usage').fetchone()[0] == (2 if retries else 1)
+
+
+def test_cpu_failure_does_not_loop_and_interactive_precedes_index(monkeypatch):
+    import app.local_models.runtime as module
+    async def scenario():
+        runtime = module.Runtime()
+        entered, release = asyncio.Event(), asyncio.Event()
+        order = []
+        async def execute(key, operation, payload, config, diagnostics):
+            order.append(payload['name'])
+            if payload['name'] == 'running':
+                entered.set()
+                await release.wait()
+            return {'result': []}
+        monkeypatch.setattr(runtime, '_execute', execute)
+        first = asyncio.create_task(runtime.infer('bekko', 'embedding', {'name': 'running'}))
+        await entered.wait()
+        background = asyncio.create_task(runtime.infer('bekko', 'embedding', {'name': 'index'}, priority=20))
+        query = asyncio.create_task(runtime.infer('bekko', 'embedding', {'name': 'query'}, priority=0))
+        await asyncio.sleep(0)
+        release.set()
+        await asyncio.gather(first, background, query)
+        assert order == ['running', 'query', 'index']
+        calls = []
+        async def failed(key, operation, payload, config, diagnostics):
+            calls.append(config.device)
+            raise ProviderError('LOCAL_CUDA_OOM', 'simulated')
+        monkeypatch.setattr(runtime, '_execute', failed)
+        monkeypatch.setattr(module, 'configuration', lambda: module.RuntimeConfig(device='cuda'))
+        with pytest.raises(ProviderError):
+            await runtime.infer('bekko', 'embedding', {})
+        assert calls == ['cuda', 'cpu'] and not runtime.active
+    asyncio.run(scenario())
+
+
+def test_durable_diagnostics_are_bounded_and_disk_size_is_real():
+    from app.services import model_diagnostics
+    from app.local_models import manager
+    for index in range(205):
+        model_diagnostics.record(model='bekko', status='failed', error_code='TEST', payload='secret', elapsed_seconds=index)
+    records = model_diagnostics.recent()
+    assert len(records) == 200 and records[0]['elapsed_seconds'] == 5
+    assert 'secret' not in json.dumps(records)
+    path = manager.model_path('bekko')
+    path.mkdir(parents=True)
+    (path / 'weights.partial').write_bytes(b'1234567')
+    assert manager.disk_bytes('bekko') == 7
+
+
+def test_upload_key_replay_and_content_conflict():
+    from app.main import app
+    with TestClient(app) as client:
+        headers = {'Idempotency-Key': 'stable-upload-123456'}
+        first = client.post('/api/media/attachments?filename=lecture.txt', content=b'original', headers=headers)
+        again = client.post('/api/media/attachments?filename=lecture.txt', content=b'original', headers=headers)
+        assert first.status_code == again.status_code == 201
+        assert first.json()['attachment_id'] == again.json()['attachment_id']
+        assert client.post('/api/media/attachments?filename=lecture.txt', content=b'changed', headers=headers).status_code == 409
+        assert client.get('/api/media/attachments/' + first.json()['attachment_id']).content == b'original'
+
+
+def test_updated_transcript_note_keeps_identity_and_rejects_user_edits():
+    from app.contracts import TranscriptNoteRequest, TranscriptEditRequest, IndexRebuildRequest
+    from app.services import transcription_service as jobs, note_service, index_service
+    from app.services.media_notes import create_transcript_note
+    from app.services.attachment_service import attachment_path
+    path = attachment_path('lecture.txt')
+    path.parent.mkdir(parents=True, exist_ok=True)
+    path.write_text('original', encoding='utf-8')
+    async def scenario():
+        job = await jobs.create_transcription('lecture.txt', local_only=True)
+        options = TranscriptNoteRequest(title='Lecture')
+        first = await create_transcript_note(job.job_id, options)
+        await index_service.rebuild(IndexRebuildRequest())
+        jobs.edit(job.job_id, TranscriptEditRequest(revision=1, text='revised'))
+        update = options.model_copy(update={'update_existing': True})
+        second = await create_transcript_note(job.job_id, update)
+        assert first.note_id == second.note_id and 'revised' in second.markdown
+        assert 'embedding_local_only: true' in second.markdown
+        again = await create_transcript_note(job.job_id, update)
+        assert again.note_id == first.note_id
+        await note_service.update_note(first.note_id, markdown='User edits')
+        jobs.edit(job.job_id, TranscriptEditRequest(revision=2, text='third revision'))
+        with pytest.raises(ApiError) as error:
+            await create_transcript_note(job.job_id, update)
+        assert error.value.code == 'NOTE_CONTENT_CONFLICT'
+        assert (await note_service.get_note(first.note_id)).markdown == 'User edits'
+        copy = await create_transcript_note(job.job_id, options)
+        assert copy.note_id != first.note_id
+    asyncio.run(scenario())
+
+
+def test_audio_usage_is_separate_and_unknown_durations_stay_null():
+    from app.services.usage_service import UsageAttempt, aggregate
+    now = datetime.now(timezone.utc)
+    first = UsageAttempt('local', 'asr', 'local', 'transcription', source='local')
+    first.observe({'audio_seconds': 2.25, 'usage': {}})
+    first.persist(); first.persist()
+    unknown = UsageAttempt('remote', 'asr', 'openai_compatible', 'transcription')
+    unknown.persist()
+    result = aggregate(now - timedelta(days=1), now + timedelta(days=1))
+    assert result['audio_request_count'] == 2 and result['audio_covered_requests'] == 1
+    assert result['audio_seconds'] == 2.25 and result['totals']['input_tokens'] is None
+    remote = aggregate(now - timedelta(days=1), now + timedelta(days=1), source='api')
+    assert remote['audio_seconds'] is None
+
+
+def test_request_rule_import_rejects_credentials_and_host_fields():
+    from app.main import app
+    with TestClient(app) as client:
+        path = '/api/providers/request-rules/validate'
+        body = {'version': 1, 'request_overrides': [{'body': {'enable_thinking': False}}]}
+        assert client.post(path, json=body).status_code == 200
+        for bad in ({'api_key': 'secret'}, {'nested': {'authorization': 'secret'}}, {'stream': False}):
+            body['request_overrides'][0]['body'] = bad
+            assert client.post(path, json=body).status_code == 422
+
+
+@pytest.mark.parametrize('stream', [False, True])
+def test_inference_probe_uses_adapter_body_and_no_vault_context(monkeypatch, stream):
+    import httpx
+    from app.container import container
+    from app.main import app
+    original = container.provider_factory.build
+    requests = []
+    def respond(request):
+        data = json.loads(request.content)
+        requests.append(data)
+        assert data['enable_thinking'] is False and data['stream'] == stream
+        assert data['messages'] == [{'role': 'user', 'content': 'Reply with OK.'}]
+        assert not data.get('tools')
+        if stream:
+            return httpx.Response(200, text='data: {"choices":[{"delta":{"content":"OK"},"finish_reason":null}]}\n\ndata: [DONE]\n\n')
+        return httpx.Response(200, json={'choices': [{'message': {'role': 'assistant', 'content': 'OK'}, 'finish_reason': 'stop'}]})
+    def build(config):
+        adapter = original(config)
+        adapter.transport = httpx.MockTransport(respond)
+        return adapter
+    monkeypatch.setattr(container.provider_factory, 'build', build)
+    with TestClient(app) as client:
+        response = client.post('/api/providers/request-probe', json={'stream': stream, 'provider': {
+            'name': 'Probe', 'provider_type': 'openai_compatible', 'base_url': 'https://fixture.invalid/v1',
+            'default_model': 'test', 'request_overrides': [{'body': {'enable_thinking': False}}]}})
+        assert response.status_code == 200, response.text
+        assert len(requests) == 1