feat(memory): async LLM context summary injection on trim

- Unified flush + context injection into a single async LLM call
  (flush_from_messages accepts context_summary_callback)
- Fixed response parsing bug: handle generator returns and Claude-format
  dicts from bot.call_with_tools, which previously caused all LLM
  summaries to silently fail (falling back to rule-based extraction)
- Removed standalone context summary prompts and methods; reuse the
  existing [DAILY]/[MEMORY] summarization pipeline
- Updated docs (zh/en/ja) to reflect the new injection behavior
This commit is contained in:
zhayujie
2026-04-13 20:13:05 +08:00
parent da97e948ca
commit 33cf1bc4c3
9 changed files with 187 additions and 67 deletions

View File

@@ -19,7 +19,7 @@ description: CowAgent 的长期记忆系统 — 文件持久化、自动写入
Agent 通过以下机制自动将对话内容持久化为长期记忆:
- **上下文裁剪时** — 当对话轮次或 token 超出配置上限时,裁剪最早一半的上下文,使用 LLM 将被裁剪的内容总结为关键信息写入当天记忆文件
- **上下文裁剪时** — 当对话轮次或 token 超出配置上限时,裁剪最早一半的上下文,使用 LLM 将被裁剪的内容总结为关键信息写入当天记忆文件,并将摘要异步注入到保留的上下文中,帮助模型保持对话连贯性
- **每日定时总结** — 每天 23:55 自动触发一次全量总结,防止低活跃日无记忆留存(内容无变化时自动跳过)
- **API 上下文溢出时** — 当模型 API 返回上下文溢出错误时,紧急保存当前对话摘要