mirror of
https://github.com/openai/codex.git
synced 2026-10-19 17:28:46 +00:00
## Why Confirming an Astra model selection recursively polled the large event dispatcher on the TUI thread's stack. ## What changed Unwrap `AstraSelectedFromModelPicker` before dispatching its model update, then trigger the sparkle afterward when eligible. Keep the eligibility check and model update in the same event so queued backend updates cannot turn a no-op confirmation into a sparkle. ## Testing Add a regression test that confirms `gpt-6-astra` with `XHigh` reasoning on a thread with a 4 MiB stack and checks the resulting model and reasoning effort. GitOrigin-RevId: 89df8b417a9fd0107ebb918edeb2d240b53d42bd