openai/codex
1
0
Fork 0
mirror of https://github.com/openai/codex.git synced 2026-11-01 19:33:35 +00:00
Code Issues Packages Projects Releases Wiki Activity

Preserve reasoning token accounting across resume and fork (#57839)

Browse Source 
## Why

Resuming or forking a thread loses the session flag indicating that reported token usage already includes retained reasoning. Counting that reasoning again can trigger automatic compaction too early.

## What changed

Persist `last_usage_includes_reasoning` with `TokenUsageInfo` and use it when estimating context usage. Record the flag with completed sampling and compaction usage, and mark local estimates as including reasoning. Older records without the field retain the existing accounting behavior.

## Testing

Add coverage for saved inclusive, exclusive, and legacy token counts. Extend the encrypted-reasoning compaction test to verify the compaction threshold for live, forked, and cold-resumed threads.

GitOrigin-RevId: 9f22262a693111ec0406dce11804eb4844ad8983
This commit is contained in:
andrewgu-oai
2026-10-28 21:22:06 +00:00
committed by copyberry
parent b91f2515f5
commit c62e9df39f
20 changed files with 191 additions and 91 deletions
Download Patch File Download Diff File Expand all files Collapse all files
codex-rs/app-server/src/bespoke_event_handling.rs
+1
View File
@@ -3721,6 +3721,7 @@ mod tests {
total_tokens: 200,
codex_rollout_budget_units: None,
},
last_usage_includes_reasoning: None,
last_token_usage: TokenUsage {
input_tokens: 10,
cached_input_tokens: 5,
codex-rs/app-server/tests/common/rollout.rs
+1
View File
@@ -125,6 +125,7 @@ pub fn create_fake_rollout_with_token_usage(
total_tokens: 150,
codex_rollout_budget_units: None,
},
last_usage_includes_reasoning: None,
last_token_usage: TokenUsage {
input_tokens: 70,
cached_input_tokens: 10,
codex-rs/app-server/tests/suite/v2/thread_resume.rs
+3
View File
@@ -4250,6 +4250,7 @@ async fn cold_paginated_resume_restores_usage_without_loading_turns() -> Result<
total_tokens: 150,
..Default::default()
},
last_usage_includes_reasoning: None,
last_token_usage: TokenUsage {
input_tokens: 70,
output_tokens: 20,
@@ -4361,6 +4362,7 @@ async fn cold_paginated_resume_omits_usage_when_its_turn_is_ambiguous() -> Resul
total_tokens: 150,
..Default::default()
},
last_usage_includes_reasoning: None,
last_token_usage: TokenUsage {
total_tokens: 90,
..Default::default()
@@ -4645,6 +4647,7 @@ async fn thread_resume_token_usage_replay_can_belong_to_interrupted_turn() -> Re
total_tokens: 230,
codex_rollout_budget_units: None,
},
last_usage_includes_reasoning: None,
last_token_usage: TokenUsage {
input_tokens: 90,
cached_input_tokens: 30,