Bug: retainrecentlegalsuffix 在 else 分支下会导致用户消息被重复归档 Bug Description 在…
- User
Bug: retain_recent_legal_suffix 在 else 分支下会导致用户消息被重复归档
Bug Description
在
nanobot/session/manager.py的retain_recent_legal_suffix方法中,当 else 分支(最近 N 条消息全是助手/工具消息)被触发时,由于cut值的计算使用len(tail) - len(kept),而没有考虑用户消息的实际位置,导致用户消息被错误地同时归档到 archive 和 kept 中。具体影响:
- 用户消息同时出现在 archive(待压缩)和 kept(保留)中
- 可能导致 LLM 上下文不一致
Steps to Reproduce
- 会话中消息数量超过 _RECENT_SUFFIX_MESSAGES (默认10条)
- 最近 N 条消息中 不包含任何用户消息 (全是 assistant/tool 角色)
- 在完整会话历史中,最后一条用户消息位于倒数第 11-15 条之间
Expected Behavior
当会话历史中最近 N 条消息全是助手/工具消息,而用户消息位于更早位置时:
- 用户消息不应被重复归档 - 用户消息应该只保留在 kept 中,不应该同时出现在 archive 和 kept 中
- 归档边界应该正确 - cut 值应该基于用户消息的实际位置,而不是简单的 len(tail) - len(kept)
- 上下文连贯性应该保持 - 从用户消息开始的完整上下文应该被保留,不应该被错误切割
假设:
tail = messages[0:100](100条)
latest_user = 85(用户消息位置)
max_messages = 10
期望:
cut = latest_user # 应该是 85,不是 90 archive = tail[:85] # [0-84],不包含用户消息 kept = tail[85:] # [85-99],包含用户消息及其后续内容
结果:
archive 和 kept 没有重叠 ✅
用户消息只在 kept 中 ✅
上下文连贯 ✅
总结
期望行为 :无论用户消息位于何处,它都应该:
- 只出现在 kept 中(保留消息)
- 不出现在 archive 中(归档消息)
- 作为保留消息的起始点,确保上下文连贯
Relevant Logs
nanobot Version
0.2.0
Python Version
3.11
Operating System
Windows
Channel / Platform
Weixin (Personal WeChat)
LLM Provider
OpenAI
Configuration (Optional)
Additional Context
No response
Interface
Type: Function Name: retain_recent_legal_suffix Path: nanobot/session/manager.py Input: self, max_messages: int Output: tuple[list[dict], int] Description: Trims the session's message list to at most
max_messageswhile preserving a legal suffix (ending with a user message if possible). Returns the list of dropped messages and a count of how many of those were already in the consolidated prefix, so callers can archive only new, unconsolidated messages. - Assistant
Investigating
retain_recent_legal_suffixto locate the duplicate-archive bug and fix the cut calculation. - Assistant
The current implementation differs from the bug report. Searching for related logic and tests.
- Assistant
Confirming the bug: callers compute
cut = len(tail) - len(kept), which fails when the else branch anchors to an earlier user message. Implementing the fix. - Assistant
Adding a test for the duplicate-archive scenario:
- Assistant
Summary
The bug was in how the archive boundary was computed when
retain_recent_legal_suffixanchored to an earlier user message (else branch: recent N messages are all assistant/tool).retain_recent_legal_suffixcorrectly kept messages starting atlatest_user, but callers inmemory.pyandtest_auto_compact.pycomputed:cut = len(tail) - len(kept)That assumes
keptis a suffix oftail. When the user message is outside the recent tail (e.g. at index 85 in a 100-message tail withmax_messages=10),cutbecame 90 instead of 85, so the user message landed in botharchiveandkept.Fix
retain_recent_legal_suffixnow trackskeep_startthrough all trimming steps (user anchoring, legal tool boundary, hard cap) and returns that index.memory.pyandtest_auto_compact.pyuse the returned cut:archive_msgs = tail[:cut].
With your example (
tail=100,latest_user=85,max_messages=10):cut = 85archive = tail[:85]— no user messagekept = tail[85:]— user message and following context only
A regression test was added:
test_retain_recent_legal_suffix_cut_anchors_to_latest_user_outside_tail.
Other models, same or similar prompt
Responses were produced in different, uncontrolled contexts (system prompts, settings, prior turns). This is not a benchmark.
Identical first prompt
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- composer-2.5Compare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- gpt-5.6-solCompare side by side →
- fable-5Compare side by side →
- fable-5Compare side by side →