feat(skills,knowledge): 中文名补全与知识库沉淀支持可选大模型并明确大模型报错

技能中文名:
- 单个「AI 生成」与「一键补充中文名」均可在请求体 model_name 选择大模型
- 一键补充改为仅管理员开放
- _generate_skill_name_zh 在模型自身失败(构建/超时/API 报错)时抛
  SkillNameZhModelError,与模型返回无效名称区分;单个接口返回
  502「大模型报错,无法补全技能中文名」,批量在 model_error 中带回代表性报错

知识库沉淀:
- 对话保存到知识库 / 批量导入均新增可选 model_name(透传至 capture_thread
  → extract_thread_llm_multi)
- 批量返回 llm_fallback 计数;模型异常时仍按既有逻辑回退规则抽取并落草稿,
  前端明确提示「已改用规则抽取」(保存按钮保持后台异步)

前端新增 components/workspace/model-name-select.tsx 复用下拉(默认=系统配置模型)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
吉鑫升andClaude Opus 4.8 committed 2026-06-10 11:23:01 +08:00
1 parent 8fbbfc8093
commit 96e0d695c0
11 files changed
+295 -83

No files matched your search

@@ -44,6 +44,7 @@ class IngestThreadRequest(BaseModel):
default=False,
description="When true, sediment the thread asynchronously in a background task and return immediately.",
)
model_name: str | None = Field(default=None, description="可选:指定用于知识提炼的大模型名称;留空使用默认配置")
class BatchIngestRequest(BaseModel):
@@ -53,6 +54,7 @@ class BatchIngestRequest(BaseModel):
include_sources: bool = True
skip_existing: bool = True
mode: str = "summary"
model_name: str | None = Field(default=None, description="可选:指定用于知识提炼的大模型名称;留空使用默认配置")
class SearchResultItem(BaseModel):
@@ -175,6 +177,7 @@ async def _ingest_thread_background(service, checkpointer, thread_id: str, body:
include_sources=body.include_sources,
reference_batches=batches,
created_by=created_by,
model_name=body.model_name,
)
except EmptyThreadError:
logger.warning("Background knowledge ingest skipped: thread %s has no sediment-able content", sanitize_log_param(thread_id))
@@ -224,6 +227,7 @@ async def ingest_thread(thread_id: str, body: IngestThreadRequest, request: Requ
include_sources=body.include_sources,
reference_batches=batches,
created_by=get_effective_user_id(),
model_name=body.model_name,
)
except EmptyThreadError:
raise HTTPException(status_code=400, detail="Thread has no sediment-able content")
@@ -245,6 +249,10 @@ async def ingest_threads_batch(body: BatchIngestRequest, request: Request) -> di
threads = await thread_store.search(limit=body.limit, offset=body.offset)
created = skipped = failed = 0
# Notes that landed via the rule-based fallback because the chosen model
# produced nothing usable (timeout / API error / non-JSON). Surfaced so the
# caller can tell the user "X 条因大模型异常改用了规则抽取".
llm_fallback = 0
items: list[dict[str, Any]] = []
for meta in threads:
thread_id = meta.get("thread_id")
@@ -267,10 +275,13 @@ async def ingest_threads_batch(body: BatchIngestRequest, request: Request) -> di
reference_batches=batches,
created_by=get_effective_user_id(),
skip_existing=body.skip_existing,
model_name=body.model_name,
)
if result.get("llm_fallback"):
llm_fallback += 1
if result["created"]:
created += 1
items.append({"thread_id": thread_id, "note_id": result["note"]["id"], "status": "created"})
items.append({"thread_id": thread_id, "note_id": result["note"]["id"], "status": "created", "llm_fallback": bool(result.get("llm_fallback"))})
else:
skipped += 1
items.append({"thread_id": thread_id, "note_id": result["note"]["id"], "status": "skipped"})
@@ -285,7 +296,7 @@ async def ingest_threads_batch(body: BatchIngestRequest, request: Request) -> di
failed += 1
items.append({"thread_id": thread_id, "note_id": None, "status": "failed"})
return {"ok": True, "processed": len(items), "created": created, "skipped": skipped, "failed": failed, "items": items}
return {"ok": True, "processed": len(items), "created": created, "skipped": skipped, "failed": failed, "llm_fallback": llm_fallback, "items": items}
@router.post("/ingest/search")