mirror of
https://github.com/openai/codex.git
synced 2026-08-23 13:09:46 +00:00
7ece061767
## Why Project instructions must respect the selected environment's filesystem read permissions. Tightening those permissions for a later turn must not allow previously cached instructions to reach the model. ## What changed - Apply each environment's filesystem sandbox while discovering and reading `AGENTS.md` files. - Fail thread or turn setup when sandboxing blocks a discovered instruction file, while allowing a restricted project with no instructions to start. - Clear cached instructions before refresh and include the Windows sandbox level in the cache key. - Ignore inaccessible ancestor marker probes so readable instructions in the selected working directory can still load. ## Testing Added coverage for restricted projects, denied instruction files, cache invalidation after permissions tighten, and unreadable ancestor markers. GitOrigin-RevId: 6ea1a27b9c873a6260e4f87d42ae1317a6a4ae4b