## Summary We've been seeing a number of issues and reports with our synthetic `apply_patch` tool, e.g. #802. Let's make this a real tool - in my anecdotal testing, it's critical for GPT-OSS models, but I'd like to make it the standard across GPT-5 and codex models as well. ## Testing - [x] Tested locally - [x] Integration test |
||
|---|---|---|
| .. | ||
| common | ||
| fixtures | ||
| cli_responses_fixture.sse | ||
| cli_stream.rs | ||
| client.rs | ||
| compact.rs | ||
| exec.rs | ||
| exec_stream_events.rs | ||
| live_cli.rs | ||
| prompt_caching.rs | ||
| seatbelt.rs | ||
| stream_error_allows_next_turn.rs | ||
| stream_no_completed.rs | ||