Migrate model preset #7542
Migrate model preset #7542
Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
codex/codex-rs/core/src/sandboxing/assessment.rs
Lines 16 to 18 in 801e2f4
Fix sandbox assessment ReasoningEffort import
The sandbox assessment module still imports ReasoningEffort from codex_protocol::config_types, but this enum was removed from that module in this commit (it now lives under openai_models). As a result the codex-core crate no longer compiles because the import at this location cannot be resolved. Update the import to the new module so builds succeed again.
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| description: "Latest Codex-optimized flagship for deep and fast reasoning.".to_string(), | ||
| default_reasoning_effort: ReasoningEffort::Medium, | ||
| supported_reasoning_efforts: &[ | ||
| ReasoningEffortPreset { | ||
| effort: ReasoningEffort::Low, | ||
| description: "Fast responses with lighter reasoning", | ||
| }, | ||
| ReasoningEffortPreset { | ||
| effort: ReasoningEffort::Medium, | ||
| description: "Balances speed and reasoning depth for everyday tasks", | ||
| }, | ||
| supported_reasoning_efforts: vec
For the default gpt-5.1-codex-max preset the default_reasoning_effort remains Medium, but the supported_reasoning_efforts list now only contains High and XHigh. This means the default effort is no longer in the supported set and lower-effort choices disappear from the advertised model list, even though Medium is still configured as the default. Clients consuming these presets will be unable to pick the prior default effort for the main model. Please restore the missing efforts or realign the default with the supported list.
Useful? React with 👍 / 👎.
There was a problem hiding this comment.
Bad merge. Thanks codex
codex-rs/core/src/rollout/policy.rs
Outdated
| | EventMsg::Warning(_) | ||
| | EventMsg::TaskStarted(_) | ||
| | EventMsg::TaskComplete(_) | ||
| | EventMsg::AvailableModels(_) |
There was a problem hiding this comment.
| | EventMsg::AvailableModels(_) | |
| | EventMsg::ListModelsResponse(_) |
pakrym-oai
left a comment
pakrym-oai
left a comment
There was a problem hiding this comment.
Let's add a test for the new OP.
openai_modelsin/corePRESETSunder itModelPreset,ModelUpgrade,ReasoningEffortPreset,ReasoningEffortPreset, andReasoningEffortPresettoprotocolOp::ListModelsandEventMsg::AvailableModelsNext steps:
app-serverandtuito use the introduced Operation