openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-09 20:50:33 +00:00
Code Issues Packages Projects Releases Wiki Activity

Track prompt cache write token usage (#33454)

Browse Source 
## What changed

- Parse `cache_write_tokens` from response input token details and carry it through token usage aggregation.
- Expose `cache_write_input_tokens` in protocol, app-server, exec, and TypeScript SDK usage events, defaulting it to zero for compatibility with older payloads.
- Report cache-write usage in analytics, metrics, traces, and rollout data alongside existing cache-read usage.

## Testing

- Add coverage for response parsing, usage event output, aggregation, analytics, metrics, and telemetry fields.

GitOrigin-RevId: 634e4fbe3086a8923c0ee13b622573e7d9d221bd
This commit is contained in:
Eric Traut
2026-07-16 00:22:53 +00:00
committed by copyberry
parent 78d4a563f9
commit 2edad72de3
46 changed files with 207 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/exec/src/exec_events.rs
+3
View File
@@ -63,6 +63,9 @@ pub struct Usage {
pub input_tokens: i64,
/// The number of cached input tokens used during the turn.
pub cached_input_tokens: i64,
/// The number of input tokens written to the prompt cache during the turn.
#[serde(default)]
pub cache_write_input_tokens: i64,
/// The number of output tokens used during the turn.
pub output_tokens: i64,
/// The number of reasoning output tokens used during the turn.