🤖 fix: omit providerMetadata from compaction summary to fix context display #762
+7
−4
Conversation
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
…isplay The compaction API response's providerMetadata contains cacheCreationInputTokens from the pre-compaction context, which inflates the context usage display until the next message is sent. By omitting providerMetadata from the summary message, context usage correctly shows just the compaction output tokens. The historicalUsage field still preserves full cost accounting from pre-compaction messages. _Generated with mux_
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 compaction, context usage was inflated because the summary message's
providerMetadatacontainedcacheCreationInputTokensfrom the pre-compaction context.This fix omits
providerMetadatafrom the compaction summary message. Context usage now correctly shows just the compaction output tokens until the next API request. Because the auto-compaction checker uses the context usage, this correctly hides the auto-compaction warning after a compaction.Cost tracking remains accurate via the
historicalUsagefield.Generated with
mux