fix: compact session after memory flush to prevent repeated flush loops - #3
Merged
Conversation
After the flush prompt triggers and Claude saves to memory, the session wasn't being compacted. On the next agent run, totalTokens would still be in the flush zone, re-triggering the flush prompt. Claude would respond "already saved" repeatedly until enough tokens accumulated to hit the hard compaction threshold. Now the agent compacts immediately after flush completes at end_turn, keeping the context within budget for subsequent runs. https://claude.ai/code/session_01NBsR2zaf5D3k63CU9bfQia
If a session was already bloated past 200K tokens (e.g. from the repeated flush loop), the LLM call would fail with a 400 error before the agent loop could reach any compaction logic. Now the agent estimates history tokens before entering the loop and compacts upfront if needed, self-healing the session on the next message. https://claude.ai/code/session_01NBsR2zaf5D3k63CU9bfQia
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
After the flush prompt triggers and Claude saves to memory, the session
wasn't being compacted. On the next agent run, totalTokens would still
be in the flush zone, re-triggering the flush prompt. Claude would
respond "already saved" repeatedly until enough tokens accumulated to
hit the hard compaction threshold.
Now the agent compacts immediately after flush completes at end_turn,
keeping the context within budget for subsequent runs.
https://claude.ai/code/session_01NBsR2zaf5D3k63CU9bfQia