mirror of
https://github.com/openai/codex.git
synced 2026-11-05 20:10:33 +00:00
jif
a805143486
## What changed Add the disabled-by-default `guardian_denial_reconsideration` feature to reconsider a synchronous Guardian denial once before publishing the final decision. The follow-up uses the same review session, evidence, model settings, and original deadline, without compacting the retained context. Only a valid second assessment replaces the denial. Invalid or failed follow-ups keep the original denial and discard the review session; cancellation and timeout retain their normal outcomes. Allow a custom developer message through `auto_review.experimental_denial_reconsideration_prompt`, limited to 1,000 UTF-8 bytes. Omitted or blank values use the built-in prompt, which grants no new authorization and preserves the security policy. ## Testing Add scenario coverage for feature gating, unchanged approvals, reconsidered approvals and denials, invalid assessments, failed follow-ups, custom prompts, and retained context. Extend cancellation coverage to reconsideration and config tests to prompt normalization and byte-limit validation. GitOrigin-RevId: 61c45d5a948e3e5684c4b4048d6e90fd3f1f2476
ThreadManager Sample
Small one-shot binary that starts a Codex thread with ThreadManager from
codex-core-api, submits a single user turn, and prints the final assistant
message.
Authentication uses the configured credential storage under CODEX_HOME, including
cli_auth_credentials_store, mcp_oauth_credentials_store, and
features.secret_auth_storage. Local managed authentication requirements and auth
routing settings are respected. This also applies to cargo run builds. Other
execution settings remain the sample's built-in configuration.
cargo run -p codex-thread-manager-sample -- "Say hello"
Use --model to override the configured default model:
cargo run -p codex-thread-manager-sample -- --model gpt-5.2 "Say hello"
The prompt can also be piped through stdin:
printf 'Say hello\n' | cargo run -p codex-thread-manager-sample