mirror of
https://github.com/openai/codex.git
synced 2026-11-17 22:10:37 +00:00
Move rollout trace recording to a background worker (#61253)
## Why Recording inference starts synchronously serializes prompts and writes trace payloads before model work can proceed. Defer that work so inference dispatch can continue while the trace is recorded. ## What changed - Use one worker per trace bundle to write events in submission order, with up to eight pending jobs. - Share prepared prompts and encoded requests with the worker, and build remote compaction snapshots there. Write payloads before publishing events that reference them. - Add `TraceWriter::flush` and `ThreadTraceContext::flush` for live reads. Drain accepted jobs and seal the bundle on shutdown; suppress the closing marker after a recording failure. ## Testing Add tests for deferred prompt serialization, ordered start and completion events, shutdown draining, and serialization failures that preserve earlier evidence without publishing a closing marker. Verify compaction snapshots are built on the worker and skipped when tracing is disabled. GitOrigin-RevId: 32fd787bb1d281f1814df2f08c73b667628f8add
This commit is contained in:
committed by
copyberry
parent
aa5f492031
commit
b8dde1eb40
@@ -291,7 +291,7 @@ struct RemoteCompactionV2Output {
|
||||
async fn run_remote_compaction_request_v2(
|
||||
sess: &Session,
|
||||
step_context: &StepContext,
|
||||
prompt: &Prompt,
|
||||
prompt: &Arc<Prompt>,
|
||||
responses_metadata: &CodexResponsesMetadata,
|
||||
transport: &mut CompactionRequestTransport<'_>,
|
||||
submitted_audio: Option<&crate::context_manager::rejected_audio::SubmittedFileAudio>,
|
||||
|
||||
Reference in New Issue
Block a user