fix(knowledge): 模型判定 should_ingest=false 时直接跳过,不再落草稿
日志显示寒暄/无效会话并非 LLM 调用失败,而是模型正确返回 should_ingest=false。 上一版把这种情况也当失败回退、堆成草稿,反而把无价值对话存进了库。 - llm_extractor: 模型显式 should_ingest=false 且无 notes → 抛 LLMRejectedIngest - capture_thread: 捕获后抛 EmptyThreadError → 整条跳过、不入库(寒暄/总结此页这类不再进库) - 仅当真正失败(API 报错 / 非 JSON)才回退规则抽取并落草稿 - 兼容包装 extract_thread_llm 吞掉该异常返回 None - 更新测试(should_ingest=false 跳过)+ CLAUDE.md Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
1 parent
4aef81284a
commit
76320ca5a3
3 files changed
+66
-33
No files matched your search
+42
-15
@@ -27,6 +27,23 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
_VALID_CATEGORIES = {"synthesis", "concepts", "references", "decision", "journal"}
|
||||
|
||||
|
||||
class LLMRejectedIngest(Exception):
|
||||
"""The LLM judged the conversation as having no knowledge value.
|
||||
|
||||
Raised (instead of returning ``[]``) when the model explicitly sets
|
||||
``should_ingest: false`` with no notes — so callers can *skip* ingestion
|
||||
entirely rather than falling back to the rule-based verbatim dump.
|
||||
"""
|
||||
|
||||
|
||||
def _is_falsey(value: Any) -> bool:
|
||||
if value is False:
|
||||
return True
|
||||
if isinstance(value, str):
|
||||
return value.strip().lower() in ("false", "0", "no")
|
||||
return False
|
||||
|
||||
_SYSTEM_PROMPT = """\
|
||||
你是知识库整理专家,遵循 obsidian-wiki 的 wiki-capture 规范,把一次对话提炼成\
|
||||
**陈述式知识(declarative knowledge)**,而不是聊天流水账。
|
||||
@@ -257,11 +274,18 @@ async def extract_thread_llm_multi(
|
||||
|
||||
note_dicts = _notes_from_data(data)
|
||||
if not note_dicts:
|
||||
reason = str(data.get("reason") or "")[:200]
|
||||
if _is_falsey(data.get("should_ingest")):
|
||||
# The model deliberately judged this conversation worthless (greeting,
|
||||
# meta chatter, no findings). Skip ingestion entirely — do NOT fall
|
||||
# back to the rule-based verbatim dump.
|
||||
logger.info("Knowledge LLM judged thread %s not worth ingesting: %s", thread_id, reason)
|
||||
raise LLMRejectedIngest(reason or "no knowledge value")
|
||||
logger.warning(
|
||||
"Knowledge LLM extraction for thread %s produced no notes (should_ingest=%s, reason=%r); using rule-based fallback",
|
||||
thread_id,
|
||||
data.get("should_ingest"),
|
||||
str(data.get("reason") or "")[:200],
|
||||
reason,
|
||||
)
|
||||
return []
|
||||
if not allow_multi:
|
||||
@@ -310,18 +334,21 @@ async def extract_thread_llm(
|
||||
Thin wrapper over :func:`extract_thread_llm_multi` that returns the first
|
||||
note, or ``None`` when nothing was produced.
|
||||
"""
|
||||
drafts = await extract_thread_llm_multi(
|
||||
messages,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
mode=mode,
|
||||
title=title,
|
||||
tags=tags,
|
||||
project_name=project_name,
|
||||
sources=sources,
|
||||
max_messages=max_messages,
|
||||
model_name=model_name,
|
||||
max_input_chars=max_input_chars,
|
||||
allow_multi=False,
|
||||
)
|
||||
try:
|
||||
drafts = await extract_thread_llm_multi(
|
||||
messages,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
mode=mode,
|
||||
title=title,
|
||||
tags=tags,
|
||||
project_name=project_name,
|
||||
sources=sources,
|
||||
max_messages=max_messages,
|
||||
model_name=model_name,
|
||||
max_input_chars=max_input_chars,
|
||||
allow_multi=False,
|
||||
)
|
||||
except LLMRejectedIngest:
|
||||
return None
|
||||
return drafts[0] if drafts else None
|
||||
@@ -247,25 +247,30 @@ class KnowledgeService:
|
||||
llm_attempted = self.config.llm_extract_enabled
|
||||
llm_fallback = False
|
||||
if llm_attempted:
|
||||
drafts = await llm_extractor.extract_thread_llm_multi(
|
||||
messages,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
mode=mode,
|
||||
title=title,
|
||||
tags=tags,
|
||||
project_name=self.project_name,
|
||||
sources=sources,
|
||||
max_messages=self.config.max_thread_messages,
|
||||
model_name=self.config.extract_model_name,
|
||||
max_input_chars=self.config.extract_max_input_chars,
|
||||
allow_multi=self.config.multi_note_enabled,
|
||||
)
|
||||
try:
|
||||
drafts = await llm_extractor.extract_thread_llm_multi(
|
||||
messages,
|
||||
thread_id=thread_id,
|
||||
thread_title=thread_title,
|
||||
mode=mode,
|
||||
title=title,
|
||||
tags=tags,
|
||||
project_name=self.project_name,
|
||||
sources=sources,
|
||||
max_messages=self.config.max_thread_messages,
|
||||
model_name=self.config.extract_model_name,
|
||||
max_input_chars=self.config.extract_max_input_chars,
|
||||
allow_multi=self.config.multi_note_enabled,
|
||||
)
|
||||
except llm_extractor.LLMRejectedIngest as exc:
|
||||
# The model judged this conversation worthless (greeting / meta
|
||||
# chatter). Skip ingestion entirely — do NOT dump the raw chat.
|
||||
raise EmptyThreadError(f"Thread {thread_id} judged not worth ingesting: {exc}") from exc
|
||||
if not drafts:
|
||||
# The LLM path was supposed to run but produced nothing usable
|
||||
# (API error / non-JSON / empty). We will fall back to the
|
||||
# rule-based extractor, which yields a low-quality verbatim dump
|
||||
# with no entities/tags — flag it so it lands as a draft.
|
||||
# (API error / non-JSON). We will fall back to the rule-based
|
||||
# extractor, which yields a low-quality verbatim dump with no
|
||||
# entities/tags — flag it so it lands as a draft.
|
||||
llm_fallback = True
|
||||
if not drafts:
|
||||
single = extractor.extract_thread(
|
||||
|
||||
Reference in new issue
Block a user