feat(provider): 完成阶段E协议适配、国内预设与模型路由

backend/app/services/index_service.py

@@ -94,6 +94,8 @@ async def rebuild(request: IndexRebuildRequest) -> IndexJob:
         created_at=datetime.now(timezone.utc),
     ))
     try:
+        # Deleting blocks also cascades every space in routed_block_vectors;
+        # index_note repopulates only the currently successful API space.
         repository.clear_all()
         await vector_store.clear()
         for rel, folder, markdown, created, updated in docs:

backend/app/services/note_service.py

@@ -16,6 +16,7 @@ from app.database.db import connect, transaction
 from app.errors import ApiError
 from app.knowledge.parser import ParsedNote, parse_note
 from app.retrieval.embedding import HashEmbeddingProvider
+from app.retrieval import routed_vectors
 from app.retrieval.vectorstore import SqliteVecStore, VectorRecord
 from app.services.coordination import serialized_vault_mutation
 from app.services.vault_paths import (
@@ -78,7 +79,11 @@ async def index_note(parsed: ParsedNote) -> None:
     半提交状态。替换元数据时拿到旧 block_id：清理已删除/内容变化的旧向量，只为新增
     block 写向量（内容未变的 block 其向量仍有效，无需重复写入）。
     """
-    vectors = await embedding.embed_documents([block.content for block in parsed.blocks])
+    texts = [block.content for block in parsed.blocks]
+    vectors = await embedding.embed_documents(texts)
+    # Network I/O stays outside the write transaction. The hash index remains
+    # complete even when the optional API route fails or changes vector spaces.
+    remote = await routed_vectors.embed_remote(texts)
     conn = connect()
     try:
         with transaction(conn):
@@ -105,6 +110,7 @@ async def index_note(parsed: ParsedNote) -> None:
                 if block.block_id in missing_ids
             ]
             await vector_store.upsert(records, conn=conn)
+            routed_vectors.store_remote(conn, [block.block_id for block in parsed.blocks], remote)
             repository.set_index_meta(
                 {"embedding_model": embedding.model_id, "embedding_dim": str(embedding.dim)},
                 conn=conn,

backend/app/services/transcription_service.py

@@ -1,37 +1,59 @@
-"""转写适配层；第一阶段消费文本附件或桌面 Host 预生成的旁路文本。"""
+"""转写作业：API 优先，本地模型回退；保留已有 Host 文本入口。"""
 
 from __future__ import annotations
 
 from collections import OrderedDict
 from datetime import datetime, timezone
-from pathlib import Path
 from uuid import uuid4
 
 from app.contracts import TranscriptionJob
+from app.errors import ApiError
 from app.services.attachment_service import attachment_path
 
 _jobs: OrderedDict[str, TranscriptionJob] = OrderedDict()
 MAX_JOBS = 100
 
 
-def create_transcription(attachment_id: str, language: str | None = None) -> TranscriptionJob:
-    # TODO(ai-core): 第二阶段接入本地 ASR 队列后，保留相同 Job 契约替换此同步降级实现。
-    del language  # 预生成 transcript 暂不需要语言识别。
+async def create_transcription(attachment_id: str, language: str | None = None, *, diarization: bool = False) -> TranscriptionJob:
+    from app.container import container
+
     source = attachment_path(attachment_id)
-    transcript = source if source.suffix.lower() in {".txt", ".md"} else Path(f"{source}.txt")
     job = TranscriptionJob(
         job_id=f"transcription_{uuid4().hex}",
         attachment_id=attachment_id,
-        status="completed" if transcript.is_file() else "failed",
-        text=transcript.read_text(encoding="utf-8") if transcript.is_file() else None,
-        error_code=None if transcript.is_file() else "TRANSCRIPTION_BACKEND_UNAVAILABLE",
-        error_message=(
-            None
-            if transcript.is_file()
-            else "No host-generated transcript is available; local speech models are phase two."
-        ),
+        status="processing",
         created_at=datetime.now(timezone.utc),
     )
+    try:
+        if diarization:
+            # Speaker verification and diarization are different capabilities.
+            raise ApiError(501, "DIARIZATION_NOT_IMPLEMENTED", "说话人分离将在阶段 F 接入，当前不能忽略 diarization 请求。")
+        transcript = source if source.suffix.lower() in {".txt", ".md"} else attachment_path(f"{attachment_id}.txt")
+        # A saved transcript remains an explicit import path, never faked ASR.
+        if transcript.is_file() and (source == transcript or container.model_routing.configuration().transcription is None):
+            with transcript.open("rb") as handle:
+                content = handle.read(1024 * 1024 + 1)
+            if len(content) > 1024 * 1024:
+                raise ApiError(413, "TRANSCRIPT_TOO_LARGE", "Transcript exceeds 1 MiB.")
+            job.text = content.decode("utf-8")
+            if not job.text.strip():
+                raise ApiError(422, "TRANSCRIPT_EMPTY", "Transcript is empty.")
+            job.source = "sidecar"
+        else:
+            result = await container.model_routing.transcribe(source, language)
+            job.text = result.text
+            job.source = result.source
+            job.fallback_reason = result.fallback_reason
+        job.status = "completed"
+    except ApiError as exc:
+        job.status = "failed"
+        job.error_code = exc.code
+        job.error_message = exc.message
+        job.fallback_reason = exc.details.get("fallback_reason")
+    except (OSError, UnicodeError):
+        job.status = "failed"
+        job.error_code = "TRANSCRIPT_UNREADABLE"
+        job.error_message = "Transcript could not be read."
     _jobs[job.job_id] = job
     while len(_jobs) > MAX_JOBS:
         _jobs.popitem(last=False)