cassirer-openai b8dde1eb40 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

2026-11-13 04:36:03 +00:00

..

src

Move rollout trace recording to a background worker (#61253)

2026-11-13 04:36:03 +00:00

templates

Add dedicated memory v2 consolidation and read prompts (#43813)

2026-09-08 12:58:11 +00:00

BUILD.bazel

build: run buildifier from just fmt (#28125)

2026-06-13 21:43:39 -07:00

Cargo.toml

Use thread runtime auth for Guardian Decisions and memory quota checks (#60064)

2026-11-07 05:50:00 +00:00