bb16d3a5c9
访谈与阶段 - 新增 app/agents/stage_constants.py：集中 CHAT_STAGES、章节分类/顺序、阶段到默认 memoir 类别等，与 MemoirState 默认槽位顺序对齐；减少散落在 prompts 内的重复常量。 - 新增 app/agents/chat/prompt_context.py：以 ChatPromptContext 汇总 guided 系统提示所需字段（阶段、槽位、轮次、人设、记忆证据、回复长度模式、背景声线、职业等），统一走 get_guided_conversation_prompt。 - 大幅收敛 app/agents/chat/prompts_conversation.py；调整 prompts.py、stage_prompts.py、stage_detection.py；同步 interview_agent、profile_agent、helpers 与 state_schema，使对话侧构造提示的方式一致、可测。 回忆录流水线 - memoir/prompts.py 删除已迁至 stage_constants / 独立模板的大段常量与图片占位相关逻辑；classification / extraction / fidelity / narrative agents 与 orchest（全量历史仍可用于计数，注入模型时按轮次与字符上限截断）、image_prompt_fallback_disabled。 - dependencies 增加 get_llm_provider_fast（LRU 缓存，可与默认共用密钥与 base_url）。 任务与编排 - memoir_tasks：prepare_batches 注入 llm_fast；开启独立快档模型时打结构化日志。 - chapter_cover_tasks、story_image_tasks：与图片 prompt / JSON 工具路径或策略变更对齐（import 与行为一致）。 - story_pipeline_sync 等小处同步。 其它核心 - langchain_llm、text_normalize 随上述调用链微调。 开发者体验 - .cursor/settings.json：启用 redis-development、postman 插件。 测试 - 新增 test_image_prompt_policy：覆盖「禁止回退」等图片 prompt 策略。 - 更新 test_interview_prompts、test_interview_reply_length、test_experience_regressions、test_json_and_memory_utils，匹配新常量位置、json_utils 与对话/长度行为。
104 lines
2.9 KiB
Python
104 lines
2.9 KiB
Python
"""LLM JSON 输出校验（memory 富化）。"""
|
||
|
||
from __future__ import annotations
|
||
|
||
import json
|
||
from typing import Any, TypeVar
|
||
|
||
from pydantic import BaseModel, Field, field_validator
|
||
|
||
TModel = TypeVar("TModel", bound=BaseModel)
|
||
|
||
|
||
class ExtractedFactItem(BaseModel):
|
||
fact_type: str = "event"
|
||
subject: str | None = None
|
||
predicate: str | None = None
|
||
object_json: Any = None
|
||
confidence: float = Field(default=0.75, ge=0.0, le=1.0)
|
||
source_chunk_id: str | None = None
|
||
|
||
@field_validator("fact_type", mode="before")
|
||
@classmethod
|
||
def _coerce_fact_type(cls, v: object) -> str:
|
||
ft = str(v or "event").strip() or "event"
|
||
if ft not in ("person", "event", "relation", "place", "milestone"):
|
||
return "event"
|
||
return ft
|
||
|
||
|
||
class FactsExtractionPayload(BaseModel):
|
||
facts: list[ExtractedFactItem] = Field(default_factory=list)
|
||
|
||
|
||
class SessionSummaryPayload(BaseModel):
|
||
summary: str = ""
|
||
|
||
|
||
class RollingSummaryPayload(BaseModel):
|
||
rolling_summary: str = ""
|
||
|
||
|
||
class TimelineEventItem(BaseModel):
|
||
event_year: int | None = None
|
||
event_date: str | None = None
|
||
title: str = ""
|
||
description: str | None = None
|
||
source_fact_ids: list[str] = Field(default_factory=list)
|
||
|
||
@field_validator("source_fact_ids", mode="before")
|
||
@classmethod
|
||
def _coerce_sf(cls, v: object) -> list[str]:
|
||
if v is None:
|
||
return []
|
||
if isinstance(v, str):
|
||
return [v] if v else []
|
||
if isinstance(v, list):
|
||
return [str(x) for x in v if x]
|
||
return []
|
||
|
||
|
||
class TimelineEventsPayload(BaseModel):
|
||
events: list[TimelineEventItem] = Field(default_factory=list)
|
||
|
||
|
||
def parse_json_payload(raw: str, model: type[TModel]) -> TModel | None:
|
||
"""解析 invoke_json_object 返回的 JSON 字符串。"""
|
||
from app.core.json_utils import extract_json_payload
|
||
|
||
try:
|
||
cleaned = extract_json_payload(raw)
|
||
data = json.loads(cleaned)
|
||
return model.model_validate(data)
|
||
except (json.JSONDecodeError, ValueError, TypeError):
|
||
return None
|
||
|
||
|
||
def facts_payload_to_dicts(payload: FactsExtractionPayload) -> list[dict]:
|
||
out: list[dict] = []
|
||
for item in payload.facts:
|
||
d = item.model_dump()
|
||
scid = d.get("source_chunk_id")
|
||
if scid is not None and not isinstance(scid, str):
|
||
d["source_chunk_id"] = str(scid)
|
||
out.append(d)
|
||
return out
|
||
|
||
|
||
def timeline_payload_to_dicts(payload: TimelineEventsPayload) -> list[dict]:
|
||
out: list[dict] = []
|
||
for ev in payload.events:
|
||
title = (ev.title or "").strip()
|
||
if not title:
|
||
continue
|
||
out.append(
|
||
{
|
||
"event_year": ev.event_year,
|
||
"event_date": ev.event_date,
|
||
"title": title,
|
||
"description": ev.description,
|
||
"source_fact_ids": ev.source_fact_ids or [],
|
||
}
|
||
)
|
||
return out[:20]
|