[codex] abort turns when rollout budgets expire (token budget 3/3) (#28707)

## Stack

Depends on #28494.

## Description

This PR propagates shared rollout-budget exhaustion through the existing
`CodexErr::TurnAborted` task result.

Each thread records its model usage against the same ledger. Once the
ledger is exhausted, that usage update and all later usage updates
return `TurnAborted`. The task wrapper emits the normal aborted-turn
event and lifecycle instead of completing the turn.

This is intentionally a soft boundary: there is no cross-thread
`Op::Interrupt` fanout. An in-flight thread can finish its current
response before it observes the exhausted ledger, but every thread
aborts at its next usage-accounting boundary.

## Tests

The integration coverage verifies that:

- the response that exhausts the budget aborts its turn;
- a later response also aborts because the shared ledger remains
exhausted; and
- sub-agent usage draws from the same shared ledger; and
- local and remote-v2 compaction abort without retrying or emitting a
generic error.

Local checks:

- `just test -p codex-core
exhausted_budget_aborts_current_and_later_turns`
- `just test -p codex-core subagent_usage_draws_from_the_shared_budget`
- `just test -p codex-core
abort_regular_task_emits_marker_before_turn_aborted`
- `just test -p codex-core
compaction_budget_exhaustion_aborts_without_error_or_retry`
- `just fix -p codex-core`
- `just fmt`
- `git diff --check`

The full workspace test suite was not run locally.
This commit is contained in:
rka-oai
2026-06-19 02:00:01 -07:00
committed by GitHub
parent 7abfcf220b
commit dac588f413
13 changed files with 266 additions and 69 deletions
+8 -4
View File
@@ -3410,17 +3410,19 @@ impl Session {
&self,
turn_context: &TurnContext,
token_usage: Option<&TokenUsage>,
) {
self.record_token_usage_info(turn_context, token_usage)
) -> CodexResult<()> {
let result = self
.record_token_usage_info(turn_context, token_usage)
.await;
self.send_token_count_event(turn_context).await;
result
}
pub(crate) async fn record_token_usage_info(
&self,
turn_context: &TurnContext,
token_usage: Option<&TokenUsage>,
) {
) -> CodexResult<()> {
if let Some(token_usage) = token_usage {
let token_info = {
let mut state = self.state.lock().await;
@@ -3434,7 +3436,7 @@ impl Session {
}
state.token_info()
};
self.record_rollout_budget_usage(token_usage);
let budget_result = self.record_rollout_budget_usage(token_usage);
if let Some(token_info) = token_info.as_ref() {
for contributor in self.services.extensions.token_usage_contributors() {
contributor
@@ -3447,7 +3449,9 @@ impl Session {
.await;
}
}
budget_result?;
}
Ok(())
}
pub(crate) async fn recompute_token_usage(&self, turn_context: &TurnContext) {