feat(api): 访谈人格/回复长度策略、口述归一、背景语气与输入净稿全链路

Chat 访谈
- 新增 persona 系统(default / warm_listener / curious_guide)与 background_voice 语气层
- 回复长度由 compute_reply_plan 统一决策(brief / standard / expanded),融合信息密度启发式
- 输入净稿(input_normalize):编排层可选 rules/llm 归一用户口语后再喂模型与记忆检索
- 记忆证据注入:按用户话检索 memory evidence 并注入 prompt

Memoir 回忆录
- 口述归一(oral_normalize):segment 原文保留,story 管线取派生净稿作叙事输入
- segment 入队批次门闸:累计字数 + 最长等待秒数,减少零碎提交
- fidelity_check / prompts / narrative_agent 微调
- Alembic 0005:清理跨章节 story 外键

Infra
- Dockerfile 加入 ffmpeg
- pyproject.toml 新增依赖并同步 uv.lock
- .env.example / .env.production 补全新配置项

Tests
- 新增 test_background_voice、test_chat_input_normalize、test_experience_regressions
- 扩展 test_interview_prompts、test_interview_reply_length、test_story_route_oral_invariant

Made-with: Cursor
This commit is contained in:
Kevin
2026-03-31 23:55:26 +08:00
parent 42ae2a5e91
commit 69a673e6c6
44 changed files with 2998 additions and 259 deletions

View File

@@ -1,6 +1,9 @@
"""回忆录模块MemoirOrchestrator、各 Specialist Agent。"""
from app.agents.memoir.classification_agent import ClassificationAgent
from app.agents.memoir.classification_agent import (
ChapterClassifyResult,
ClassificationAgent,
)
from app.agents.memoir.extraction_agent import ExtractionAgent, ExtractionResult
from app.agents.memoir.fidelity_check_agent import FidelityCheckAgent
from app.agents.memoir.narrative_agent import NarrativeAgent
@@ -14,6 +17,7 @@ from app.agents.memoir.story_route_agent import (
)
__all__ = [
"ChapterClassifyResult",
"MemoirOrchestrator",
"PreparedMemoirBatches",
"StoryRouteAgent",