mirror of https://github.com/openai/codex.git synced 2026-08-23 13:09:46 +00:00

Files

jif 5a0d0929e2 Keep response streams alive through connection failures (#37485 )

## What changed

- Classify HTTP connection failures separately from other network errors without exposing request URLs.
- For sampling requests, retry connection failures with exponential delays from 5 to 60 seconds and show a `Reconnecting... waiting for network` stream error.
- Preserve the normal stream retry budget while waiting for the provider to become reachable. Keep the existing bounded retry behavior for other retryable errors.

## Testing

- Verify connection errors are classified without leaking URL contents.
- Verify a turn recovers after its provider becomes reachable and still applies the configured retry limit to a subsequent incomplete stream.

GitOrigin-RevId: 646553290c865a1332abd30c4a64ed9266bbfc6f

2026-08-07 18:33:46 +00:00

src

Keep response streams alive through connection failures (#37485 )

2026-08-07 18:33:46 +00:00

BUILD.bazel

Extract shared HTTP transport into codex-http-client (#31323 )

2026-07-07 01:12:24 +00:00

Cargo.toml

Extract shared HTTP transport into codex-http-client (#31323 )

2026-07-07 01:12:24 +00:00

README.md

Extract shared HTTP transport into codex-http-client (#31323 )

2026-07-07 01:12:24 +00:00

README.md

codex-client

Higher-level request policy layered on codex-http-client without any Codex/OpenAI API awareness.

Provides retry utilities (RetryPolicy, RetryOn, run_with_retry, backoff) that callers plug into for unary and streaming calls.
Supplies the sse_stream helper to turn byte streams into raw SSE data: frames with idle timeouts and surfaced stream errors.
Defines the request telemetry callback used by higher-level clients.
Re-exports the low-level HTTP types temporarily so consumers can migrate to codex-http-client incrementally.