mirror of
https://github.com/openai/codex.git
synced 2026-05-01 20:02:05 +03:00
02e9006547
Add per-turn notice when a request is downgraded to a fallback model due
to cyber safety checks.
**Changes**
- codex-api: Emit a ServerModel event based on the openai-model response
header and/or response payload (SSE + WebSocket), including when the
model changes mid-stream.
- core: When the server-reported model differs from the requested model,
emit a single per-turn warning explaining the reroute to gpt-5.2 and
directing users to Trusted
Access verification and the cyber safety explainer.
- app-server (v2): Surface these cyber model-routing warnings as
synthetic userMessage items with text prefixed by Warning: (and document
this behavior).
32 lines
601 B
Rust
32 lines
601 B
Rust
mod account;
|
|
mod analytics;
|
|
mod app_list;
|
|
mod collaboration_mode_list;
|
|
mod compaction;
|
|
mod config_rpc;
|
|
mod connection_handling_websocket;
|
|
mod dynamic_tools;
|
|
mod experimental_api;
|
|
mod experimental_feature_list;
|
|
mod initialize;
|
|
mod model_list;
|
|
mod output_schema;
|
|
mod plan_item;
|
|
mod rate_limits;
|
|
mod request_user_input;
|
|
mod review;
|
|
mod safety_check_downgrade;
|
|
mod skills_list;
|
|
mod thread_archive;
|
|
mod thread_fork;
|
|
mod thread_list;
|
|
mod thread_loaded_list;
|
|
mod thread_read;
|
|
mod thread_resume;
|
|
mod thread_rollback;
|
|
mod thread_start;
|
|
mod thread_unarchive;
|
|
mod turn_interrupt;
|
|
mod turn_start;
|
|
mod turn_steer;
|