Populate PromptResponse.usage from Codex token usage#210
Draft
simonrosenberg wants to merge 1 commit into
Draft
Conversation
Author
|
This PR also resolves #99 — it populates |
This was referenced Mar 30, 2026
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
This wires Codex token usage through to ACP prompt responses instead of dropping it at turn completion.
Specifically:
PromptResponsefrom the ACP prompt pathPromptResponse.usagefrom Codex token countsPromptResponse.usageas a per-turn delta from cumulative token usageUsageUpdate.usedto report cumulative tokens currently in context, not only the latest API callResolves #165
Resolves #99
Why
codex-acpcurrently emits barePromptResponse::new(stop_reason)responses, so ACP clients never receive per-turn token usage even though upstream Codex already exposes token counts.This breaks telemetry in ACP clients and benchmarks that rely on
PromptResponse.usage.Scope
This PR intentionally does not populate
UsageUpdate.cost.That remains a separate issue because the adapter does not appear to receive an authoritative cumulative cost signal from upstream Codex today.
Tracked separately in #209.
Testing
Added a targeted regression test for:
UsageUpdate.usedI could not run
cargo testlocally in this environment becausecargois not installed on this machine.