fix(acp): restore v2 usage updates - #29
Merged
Merged
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Restore ACP v2 context usage notifications so clients receive provider-reported context occupancy and window size. This makes the TUI context gauge visible again while continuing to suppress updates when the provider does not report a meaningful window.
Motivation
The ACP v2 migration left
AgentEvent::UsageUpdatedunhandled in the server adapter. Provider usage remained present in the canonical transcript, but ACP clients never received it.Technical details
Usage translation
The Kit observer translates token totals and the provider's context-window metadata into an ACP v2
UsageUpdatebefore delegating other events to AgentKit. It intentionally omits the optional ACP cost because AgentKit reports per-turn cost while ACP defines this field as cumulative session cost.Coverage
The regression test verifies that usage without a known context window is suppressed and that known usage is emitted with the expected numerator and denominator.