codex

mirror of https://github.com/openai/codex.git synced 2026-09-20 12:47:38 +00:00

Files

vkg-oai c56dda711c Track WebSocket continuation modes and full-input send reasons (#46051 )

## Why

Per-socket metrics label resends after reconnect as initial requests, obscuring why full input was sent. Client telemetry can preserve that reason across reconnect failures and turn boundaries.

## What changed

- Add `codex.websocket.continuation` to count `response.create` send attempts, including failed sends, with `mode`, `reason`, and `phase` tags.
- Distinguish incremental continuations, fresh requests, restored history, closed connections, and other full-input sends. Track warmup and generation separately.
- Preserve the first continuation reset reason until the next send and identify resumed or forked history.
- Allow session telemetry to use a `MetricsClient` supplied through thread extensions and document the counter's semantics.

## Testing

Add metric assertions for incremental reuse, warmup, changed requests, account switches, reconnects, and resumed or forked history. Add a unit test for preserving reset reasons across repeated resets and turn boundaries.

GitOrigin-RevId: 29324f5e9d5677e0c6068f89b2256a92a5a0d157

2026-09-16 22:43:57 +00:00

events

Use explicit histogram buckets for Guardian context metrics (#44181 )

2026-09-09 15:48:39 +00:00

metrics

Track WebSocket continuation modes and full-input send reasons (#46051 )

2026-09-16 22:43:57 +00:00

config.rs

codex-otel: add configurable trace metadata (#21556 )

2026-05-07 16:06:57 -07:00

lib.rs

Expose global metrics installation in codex-otel (#42603 )