nanobot

1,831 Commits 1 Branch 1 Tag

2 Commits

Include renames

Author	SHA1	Message	Date
chengyongruandXubin Ren	d03458f034	fix(agent): eliminate race condition in auto compact summary retrieval Make Consolidator.archive() return the summary string directly instead of writing to history.jsonl then reading back via get_last_history_entry(). This eliminates a race condition where concurrent _archive calls for different sessions could read each other's summaries from the shared history file (cross-user context leak in multi-user deployments). Also removes Consolidator.get_last_history_entry() — no longer needed.	2026-04-11 15:56:41 +08:00
chengyongruandXubin Ren	fb6dd111e1	feat(agent): auto compact — proactive session compression to reduce token cost and latency (#2982 ) When a user is idle for longer than a configured TTL, nanobot proactively compresses the session context into a summary. This reduces token cost and first-token latency when the user returns — instead of re-processing a long stale context with an expired KV cache, the model receives a compact summary and fresh input.	2026-04-11 15:56:41 +08:00

Author

SHA1

Message

Date

chengyongruandXubin Ren

d03458f034

fix(agent): eliminate race condition in auto compact summary retrieval

Make Consolidator.archive() return the summary string directly instead
of writing to history.jsonl then reading back via get_last_history_entry().
This eliminates a race condition where concurrent _archive calls for
different sessions could read each other's summaries from the shared
history file (cross-user context leak in multi-user deployments).

Also removes Consolidator.get_last_history_entry() — no longer needed.

2026-04-11 15:56:41 +08:00

chengyongruandXubin Ren

fb6dd111e1

feat(agent): auto compact — proactive session compression to reduce token cost and latency (#2982 )

When a user is idle for longer than a configured TTL, nanobot **proactively** compresses the session context into a summary. This reduces token cost and first-token latency when the user returns — instead of re-processing a long stale context with an expired KV cache, the model receives a compact summary and fresh input.

2026-04-11 15:56:41 +08:00