A feature request to exclude sensitive files from OpenAI Codex is still open as of late August 2025. The request emphasizes the need for a mechanism to prevent specific files from being read or sent to the model, addressing privacy and efficiency concerns in coding projects.
A feature request was submitted to OpenAI Codex, seeking a mechanism to explicitly mark files and paths that should not be read or sent to the model. This request is particularly aimed at ensuring sensitive information remains protected within coding environments.
The proposed configuration includes both repository-specific (.codexignore) and global ignore files to maintain consistency across teams and projects. It highlights the importance of a deterministic approach that can be shared rather than relying on documentation alone.
There are two primary use cases highlighted in the discussion: preventing sensitive data from being exposed to the model and excluding large or irrelevant files from processing. This could significantly improve both security and performance for developers using Codex.
Despite the initial suggestion being closed for a Rust implementation, as of late August 2025, no equivalent feature appears to have been realized in Codex. The need to revisit this feature request emphasizes ongoing community interest and potential usability challenges.
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
A feature request to exclude sensitive files from OpenAI Codex is still open as of late August 2025. The request emphasizes the need for a mechanism to prevent specific files from being read or sent to the model, addressing privacy and efficiency concerns in coding projects.