Show task tokens and usage estimates in the agent command center (#44970)

## What changed

- Display input/output token counts and estimated credits and USD cost in task details. Prefer live token totals, falling back to complete totals from usage breakdowns.
- Fetch estimates for the selected task on a one-minute cadence for supported Business and Enterprise plans. Cache results, preserve prior nonzero estimates when a response reports zero, and stop fetching when the capability is unavailable.
- Clear cached usage and discard pending results on account changes, reconnects, or missed server events. Prioritize activity and usage over the original prompt when space is limited.

## Testing

Add a rendering snapshot and tests covering caching, stale results, unavailable usage, token resets, and incomplete usage breakdowns.

GitOrigin-RevId: b72c96053557389fdc723a70fab0dab841a52e49
This commit is contained in:
Eric Traut
2026-09-12 04:29:48 +00:00
committed by copyberry
parent 7efb0262d6
commit aee8a55ab6
15 changed files with 533 additions and 4 deletions
+2 -2
View File
@@ -32,7 +32,7 @@ use codex_utils_absolute_path::AbsolutePathBuf;
const TOKEN_ACTIVITY_FETCH_TIMEOUT: std::time::Duration =
std::time::Duration::from_secs(/*secs*/ 15);
const THREAD_USAGE_FETCH_TIMEOUT: std::time::Duration =
pub(super) const THREAD_USAGE_FETCH_TIMEOUT: std::time::Duration =
std::time::Duration::from_secs(/*secs*/ 65);
const RATE_LIMIT_RESET_REQUEST_TIMEOUT: std::time::Duration =
std::time::Duration::from_secs(/*secs*/ 15);
@@ -844,7 +844,7 @@ pub(super) async fn fetch_account_token_activity(
.wrap_err("account/usage/read failed in TUI")
}
async fn fetch_thread_usage(
pub(super) async fn fetch_thread_usage(
request_handle: AppServerRequestHandle,
thread_id: ThreadId,
) -> Result<ThreadUsageOutcome> {