mirror of
https://github.com/openai/codex.git
synced 2026-10-25 15:56:38 +00:00
## Summary This adds focused coverage for the simpler same-connection scalar request path. The exec-server connection already supports multiple in-flight JSON-RPC scalar requests on one connection. This test locks in that behavior by sending two normal requests before reading either response, without adding a batch frame or any new API surface. ## What changed - Added a processor-level test that initializes an exec-server connection. - Sends two scalar `environment/info` requests back-to-back on the same connection. - Verifies both responses come back on the same connection by request id. Checked locally with: - `just test -p codex-exec-server connection_accepts_pipelined_scalar_requests`