Open
Conversation
Add onCompactionUsage callback to ConversationManager so token usage from LLM-based compaction is reported to the agent's cost tracker. Previously these calls were invisible to metering.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
When conversation compaction runs (
compactWithLlm()), it calls an LLM to summarize older messages. These tokens were never reported to the agent's cost tracker, making cost reports incomplete for long-running agents with compaction enabled.Fix
onCompactionUsagecallback toConversationManagerOptionscompactWithLlm()now calls the callback withInferenceUsageafter each compaction LLM callAgentwires this callback to itsupdateCostTracking()methodImpact
Agents with
conversationCompactionenabled will now include compaction costs inresult.totalCost. No change for agents without compaction.Test plan
bun run build— all 3 packages compile cleanbun run test— all 364 tests pass