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:
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")
|
||||
|
||||
@@ -2366,6 +2366,15 @@ _SKILL_NAME_ZH_SYSTEM_PROMPT = (
|
||||
)
|
||||
|
||||
|
||||
class SkillNameZhModelError(Exception):
|
||||
"""The LLM call backing skill-name generation failed (a *model-side* problem).
|
||||
|
||||
Distinguishes a genuine model failure (timeout / API error / unbuildable
|
||||
model) — which must be surfaced to the user as "大模型报错导致无法补全" — from
|
||||
the model merely returning an unusable name (callers get ``None`` instead).
|
||||
"""
|
||||
|
||||
|
||||
def _clean_generated_name_zh(raw: str) -> str | None:
|
||||
"""Normalise an LLM-produced Chinese name: first line, strip quotes/punct, cap length."""
|
||||
if not raw:
|
||||
@@ -2388,24 +2397,45 @@ def _clean_generated_name_zh(raw: str) -> str | None:
|
||||
return text or None
|
||||
|
||||
|
||||
async def _generate_skill_name_zh(skill: Skill, app_config: AppConfig, model: Any = None) -> str | None:
|
||||
def _resolve_skill_name_zh_model_name(app_config: AppConfig, model_name: str | None) -> str | None:
|
||||
"""Pick the model name for skill-name generation.
|
||||
|
||||
An explicit ``model_name`` (user-selected in the UI) wins; otherwise fall
|
||||
back to the curator/security-scan model setting (itself falling back to the
|
||||
main model when unset).
|
||||
"""
|
||||
if model_name and model_name.strip():
|
||||
return model_name.strip()
|
||||
if app_config.skill_evolution and app_config.skill_evolution.curator:
|
||||
return app_config.skill_evolution.curator.model_name
|
||||
return None
|
||||
|
||||
|
||||
async def _generate_skill_name_zh(skill: Skill, app_config: AppConfig, model: Any = None, *, model_name: str | None = None) -> str | None:
|
||||
"""Generate a Chinese display name for ``skill`` via the LLM.
|
||||
|
||||
Reuses the curator/security-scan model setting (falls back to the main model).
|
||||
Returns None when the model is unconfigured, the call times out/fails, or the
|
||||
output cannot be normalised into a short Chinese name.
|
||||
An explicit ``model_name`` lets the caller pick the model; otherwise it
|
||||
reuses the curator/security-scan model setting (falls back to the main
|
||||
model). Returns ``None`` only when the model replies but the output cannot be
|
||||
normalised into a short Chinese name. Raises :class:`SkillNameZhModelError`
|
||||
when the model itself fails (cannot be built / times out / API error), so the
|
||||
caller can tell the user it was a *model* problem.
|
||||
"""
|
||||
user_prompt = (
|
||||
f"技能英文名:{skill.name}\n"
|
||||
f"功能描述:{skill.description or '(无描述)'}\n\n"
|
||||
"请为该技能起一个中文名称。"
|
||||
)
|
||||
try:
|
||||
from deerflow.models import create_chat_model
|
||||
if model is None:
|
||||
try:
|
||||
from deerflow.models import create_chat_model
|
||||
|
||||
if model is None:
|
||||
model_name = app_config.skill_evolution.curator.model_name if app_config.skill_evolution and app_config.skill_evolution.curator else None
|
||||
model = create_chat_model(name=model_name, thinking_enabled=False, app_config=app_config)
|
||||
resolved = _resolve_skill_name_zh_model_name(app_config, model_name)
|
||||
model = create_chat_model(name=resolved, thinking_enabled=False, app_config=app_config)
|
||||
except Exception as e:
|
||||
logger.warning("Skill name_zh model build failed for %s", skill.name, exc_info=True)
|
||||
raise SkillNameZhModelError(str(e) or "无法初始化所选大模型") from e
|
||||
try:
|
||||
response = await asyncio.wait_for(
|
||||
model.ainvoke(
|
||||
[
|
||||
@@ -2416,12 +2446,13 @@ async def _generate_skill_name_zh(skill: Skill, app_config: AppConfig, model: An
|
||||
),
|
||||
timeout=30,
|
||||
)
|
||||
return _clean_generated_name_zh(str(getattr(response, "content", "") or ""))
|
||||
except asyncio.TimeoutError:
|
||||
except asyncio.TimeoutError as e:
|
||||
logger.warning("Skill name_zh LLM call timed out for %s", skill.name)
|
||||
except Exception:
|
||||
raise SkillNameZhModelError("大模型响应超时(30 秒)") from e
|
||||
except Exception as e:
|
||||
logger.warning("Skill name_zh LLM call failed for %s", skill.name, exc_info=True)
|
||||
return None
|
||||
raise SkillNameZhModelError(str(e) or "大模型调用失败") from e
|
||||
return _clean_generated_name_zh(str(getattr(response, "content", "") or ""))
|
||||
|
||||
|
||||
async def _persist_skill_name_zh(
|
||||
@@ -2475,6 +2506,13 @@ class SkillNameZhBulkResponse(BaseModel):
|
||||
generated: list[SkillNameZhResponse] = Field(default_factory=list, description="本次成功生成中文名的技能")
|
||||
failed: list[str] = Field(default_factory=list, description="生成失败的技能英文名")
|
||||
skipped: int = Field(default=0, description="已有中文名而被跳过的技能数")
|
||||
model_error: str | None = Field(default=None, description="若有技能因大模型报错而失败,这里给出代表性的报错信息")
|
||||
|
||||
|
||||
class GenerateSkillNameZhRequest(BaseModel):
|
||||
"""Optional body for skill-name generation: pick the model to use."""
|
||||
|
||||
model_name: str | None = Field(default=None, description="可选:指定用于生成的大模型名称;留空使用默认配置")
|
||||
|
||||
|
||||
def _can_edit_skill_name_zh(skill: Skill, record: dict[str, Any] | None, user_id: str, *, is_admin: bool) -> bool:
|
||||
@@ -2521,15 +2559,17 @@ async def set_skill_name_zh(
|
||||
"/skills/{skill_name}/name-zh/generate",
|
||||
response_model=SkillNameZhResponse,
|
||||
summary="Generate Skill Chinese Name",
|
||||
description="用大模型为该技能生成一个中文名称并保存到数据库。",
|
||||
description="用大模型为该技能生成一个中文名称并保存到数据库。可在请求体里通过 model_name 指定使用的大模型。",
|
||||
)
|
||||
async def generate_skill_name_zh(
|
||||
skill_name: str,
|
||||
request: Request,
|
||||
body: GenerateSkillNameZhRequest | None = None,
|
||||
config: AppConfig = Depends(get_config),
|
||||
skill_store: SkillStore = Depends(get_skill_store),
|
||||
) -> SkillNameZhResponse:
|
||||
try:
|
||||
body = body or GenerateSkillNameZhRequest()
|
||||
skill_name = skill_name.replace("\r\n", "").replace("\n", "")
|
||||
user_id = _current_user_id(request)
|
||||
is_admin = _is_admin_user(request)
|
||||
@@ -2537,9 +2577,12 @@ async def generate_skill_name_zh(
|
||||
skill = next((s for s in skills if s.name == skill_name), None)
|
||||
if skill is None:
|
||||
raise HTTPException(status_code=404, detail=f"Skill '{skill_name}' not found")
|
||||
name_zh = await _generate_skill_name_zh(skill, config)
|
||||
try:
|
||||
name_zh = await _generate_skill_name_zh(skill, config, model_name=body.model_name)
|
||||
except SkillNameZhModelError as e:
|
||||
raise HTTPException(status_code=502, detail=f"大模型报错,无法补全技能中文名:{e}")
|
||||
if not name_zh:
|
||||
raise HTTPException(status_code=502, detail="模型未能生成有效的中文名称,请稍后重试或手动填写")
|
||||
raise HTTPException(status_code=502, detail="大模型未能生成有效的中文名称,请稍后重试或手动填写")
|
||||
stored = await _persist_skill_name_zh(skill, name_zh, skill_store, user_id, is_admin=is_admin)
|
||||
return SkillNameZhResponse(name=skill_name, name_zh=stored)
|
||||
except HTTPException:
|
||||
@@ -2553,26 +2596,27 @@ async def generate_skill_name_zh(
|
||||
"/skills/name-zh/generate-missing",
|
||||
response_model=SkillNameZhBulkResponse,
|
||||
summary="Bulk Generate Missing Skill Chinese Names",
|
||||
description="一键为库中所有尚未配置中文名称、且当前用户有权编辑的技能生成中文名(存数据库)。",
|
||||
description="管理员一键为库中所有尚未配置中文名称的技能生成中文名(存数据库)。可在请求体里通过 model_name 指定使用的大模型。",
|
||||
)
|
||||
async def generate_missing_skill_names_zh(
|
||||
request: Request,
|
||||
body: GenerateSkillNameZhRequest | None = None,
|
||||
config: AppConfig = Depends(get_config),
|
||||
skill_store: SkillStore = Depends(get_skill_store),
|
||||
) -> SkillNameZhBulkResponse:
|
||||
try:
|
||||
from deerflow.models import create_chat_model
|
||||
|
||||
body = body or GenerateSkillNameZhRequest()
|
||||
user_id = _current_user_id(request)
|
||||
is_admin = _is_admin_user(request)
|
||||
# 一键补充技能中文名仅对管理员开放。
|
||||
if not is_admin:
|
||||
raise HTTPException(status_code=403, detail="仅管理员可一键补充技能中文名")
|
||||
skills = get_or_new_skill_storage(app_config=config).load_skills(enabled_only=False)
|
||||
|
||||
# Existing name_zh values come from the DB. Admins see every row; others
|
||||
# see only the rows visible to them (owned / published / built-in).
|
||||
if is_admin:
|
||||
records = {r["name"]: r for r in await skill_store.list_all()}
|
||||
else:
|
||||
records = {r["name"]: r for r in await skill_store.list_visible(user_id)}
|
||||
# Admin sees every row, so existing name_zh values come from the full set.
|
||||
records = {r["name"]: r for r in await skill_store.list_all()}
|
||||
|
||||
pending: list[Skill] = []
|
||||
skipped = 0
|
||||
@@ -2581,32 +2625,36 @@ async def generate_missing_skill_names_zh(
|
||||
if record and record.get("name_zh"):
|
||||
skipped += 1
|
||||
continue
|
||||
# Skip skills the caller is not allowed to annotate (no error — bulk
|
||||
# is best-effort over what the user can edit).
|
||||
if not _can_edit_skill_name_zh(skill, record, user_id, is_admin=is_admin):
|
||||
continue
|
||||
pending.append(skill)
|
||||
|
||||
generated: list[SkillNameZhResponse] = []
|
||||
failed: list[str] = []
|
||||
model_error: str | None = None
|
||||
if pending:
|
||||
# Build the model once and reuse it for every skill.
|
||||
# Build the model once and reuse it for every skill. A build failure
|
||||
# is a model problem — fail fast with a clear message rather than
|
||||
# silently producing zero results.
|
||||
try:
|
||||
model_name = config.skill_evolution.curator.model_name if config.skill_evolution and config.skill_evolution.curator else None
|
||||
model = create_chat_model(name=model_name, thinking_enabled=False, app_config=config)
|
||||
except Exception:
|
||||
resolved_name = _resolve_skill_name_zh_model_name(config, body.model_name)
|
||||
model = create_chat_model(name=resolved_name, thinking_enabled=False, app_config=config)
|
||||
except Exception as e:
|
||||
logger.warning("Failed to build model for bulk name_zh generation", exc_info=True)
|
||||
model = None
|
||||
raise HTTPException(status_code=502, detail=f"大模型报错,无法补全技能中文名:{str(e) or '无法初始化所选大模型'}")
|
||||
|
||||
# Generate concurrently with a small bound to avoid overloading the model.
|
||||
semaphore = asyncio.Semaphore(4)
|
||||
|
||||
async def _one(skill: Skill) -> tuple[Skill, str | None]:
|
||||
async def _one(skill: Skill) -> tuple[Skill, str | None, str | None]:
|
||||
async with semaphore:
|
||||
return skill, await _generate_skill_name_zh(skill, config, model=model)
|
||||
try:
|
||||
return skill, await _generate_skill_name_zh(skill, config, model=model), None
|
||||
except SkillNameZhModelError as e:
|
||||
return skill, None, str(e)
|
||||
|
||||
results = await asyncio.gather(*[_one(s) for s in pending])
|
||||
for skill, name_zh in results:
|
||||
for skill, name_zh, err in results:
|
||||
if err and model_error is None:
|
||||
model_error = err
|
||||
if not name_zh:
|
||||
failed.append(skill.name)
|
||||
continue
|
||||
@@ -2617,7 +2665,7 @@ async def generate_missing_skill_names_zh(
|
||||
# Permission / persistence issue for this one skill — skip it.
|
||||
failed.append(skill.name)
|
||||
|
||||
return SkillNameZhBulkResponse(generated=generated, failed=failed, skipped=skipped)
|
||||
return SkillNameZhBulkResponse(generated=generated, failed=failed, skipped=skipped, model_error=model_error)
|
||||
except HTTPException:
|
||||
raise
|
||||
except Exception as e:
|
||||
|
||||
@@ -222,9 +222,13 @@ class KnowledgeService:
|
||||
reference_batches: list[dict[str, Any]] | None = None,
|
||||
created_by: str | None = None,
|
||||
skip_existing: bool = False,
|
||||
model_name: str | None = None,
|
||||
) -> dict[str, Any]:
|
||||
"""Sediment a thread into a knowledge note.
|
||||
|
||||
``model_name`` optionally overrides the configured extraction model for
|
||||
this one capture (falls back to ``config.extract_model_name``).
|
||||
|
||||
Returns ``{"note": <note>, "created": bool}``. Raises
|
||||
:class:`EmptyThreadError` when there is nothing worth keeping.
|
||||
"""
|
||||
@@ -269,7 +273,7 @@ class KnowledgeService:
|
||||
project_name=self.project_name,
|
||||
sources=sources,
|
||||
max_messages=self.config.max_thread_messages,
|
||||
model_name=self.config.extract_model_name,
|
||||
model_name=model_name or self.config.extract_model_name,
|
||||
max_input_chars=self.config.extract_max_input_chars,
|
||||
allow_multi=self.config.multi_note_enabled,
|
||||
)
|
||||
|
||||
Reference in new issue
Block a user