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:
cassirer-openai
2026-11-13 04:36:03 +00:00
committed by copyberry
parent aa5f492031
commit b8dde1eb40
26 changed files with 599 additions and 442 deletions
+1 -1
View File
@@ -311,7 +311,7 @@ mod job {
prompt.output_schema_strict = true;
let (result, token_usage) = context
.stream_stage_one_prompt(config, &prompt, stage_one_context)
.stream_stage_one_prompt(config, prompt, stage_one_context)
.await?;
let output = StageOneOutput::parse(&result, config.memories.version)?;
+2 -2
View File
@@ -319,7 +319,7 @@ impl MemoryStartupContext {
pub(crate) async fn stream_stage_one_prompt(
&self,
config: &Config,
prompt: &Prompt,
prompt: Prompt,
context: &StageOneRequestContext,
) -> anyhow::Result<(String, Option<TokenUsage>)> {
let installation_id = resolve_installation_id(&config.codex_home).await?;
@@ -364,7 +364,7 @@ impl MemoryStartupContext {
.await;
let mut stream = client_session
.stream(
prompt,
&Arc::new(prompt),
&context.model_info,
&context.session_telemetry,
context.reasoning_effort.clone(),
+1 -1
View File
@@ -725,7 +725,7 @@ async fn memories_startup_phase1_uses_live_thread_service_tier_and_detached_meta
context
.stream_stage_one_prompt(
&test.config,
&codex_core::Prompt::default(),
codex_core::Prompt::default(),
&request_context,
)
.await?;