mirror of
https://github.com/openai/codex.git
synced 2026-05-24 04:54:52 +00:00
370b13afc9
## Why Model catalog responses can now advertise a nullable `default_service_tier` for each model. Codex needs to preserve three distinct states all the way from config/app-server inputs to inference: - no explicit service tier, so the client may apply the current model catalog default when FastMode is enabled - explicit `default`, meaning the user intentionally wants standard routing - explicit catalog tier ids such as `priority`, `flex`, or future tiers Keeping those states distinct prevents the UI from showing one tier while core sends another, especially after model switches or app-server `thread/start` / `turn/start` updates. ## What Changed - Plumbed `default_service_tier` through model catalog protocol types, app-server model responses, generated schemas, model cache fixtures, and provider/model-manager conversions. - Added the request-only `default` service tier sentinel and normalized legacy config spelling so `fast` in `config.toml` still materializes as the runtime/request id `priority`. - Moved catalog default resolution to the TUI/client side, including recomputing the effective service tier when model/FastMode-dependent surfaces change. - Updated app-server thread lifecycle config construction so `serviceTier: null` preserves explicit standard-routing intent by mapping to `default` instead of internal `None`. - Kept core responsible for validating explicit tiers against the current model and stripping `default` before `/v1/responses`, without applying catalog defaults itself. ## Validation - `CARGO_INCREMENTAL=0 cargo build -p codex-cli` - `CARGO_INCREMENTAL=0 cargo test -p codex-app-server model_list` - `cargo test -p codex-tui service_tier` - `cargo test -p codex-protocol service_tier_for_request` - `cargo test -p codex-core get_service_tier` - `RUST_MIN_STACK=8388608 CARGO_INCREMENTAL=0 cargo test -p codex-core service_tier`
72 lines
2.5 KiB
Rust
72 lines
2.5 KiB
Rust
use std::sync::Arc;
|
|
|
|
use codex_app_server_protocol::Model;
|
|
use codex_app_server_protocol::ModelServiceTier;
|
|
use codex_app_server_protocol::ModelUpgradeInfo;
|
|
use codex_app_server_protocol::ReasoningEffortOption;
|
|
use codex_core::ThreadManager;
|
|
use codex_models_manager::manager::RefreshStrategy;
|
|
use codex_protocol::openai_models::ModelPreset;
|
|
use codex_protocol::openai_models::ReasoningEffortPreset;
|
|
|
|
pub async fn supported_models(
|
|
thread_manager: Arc<ThreadManager>,
|
|
include_hidden: bool,
|
|
) -> Vec<Model> {
|
|
thread_manager
|
|
.list_models(RefreshStrategy::OnlineIfUncached)
|
|
.await
|
|
.into_iter()
|
|
.filter(|preset| include_hidden || preset.show_in_picker)
|
|
.map(model_from_preset)
|
|
.collect()
|
|
}
|
|
|
|
fn model_from_preset(preset: ModelPreset) -> Model {
|
|
Model {
|
|
id: preset.id.to_string(),
|
|
model: preset.model.to_string(),
|
|
upgrade: preset.upgrade.as_ref().map(|upgrade| upgrade.id.clone()),
|
|
upgrade_info: preset.upgrade.as_ref().map(|upgrade| ModelUpgradeInfo {
|
|
model: upgrade.id.clone(),
|
|
upgrade_copy: upgrade.upgrade_copy.clone(),
|
|
model_link: upgrade.model_link.clone(),
|
|
migration_markdown: upgrade.migration_markdown.clone(),
|
|
}),
|
|
availability_nux: preset.availability_nux.map(Into::into),
|
|
display_name: preset.display_name.to_string(),
|
|
description: preset.description.to_string(),
|
|
hidden: !preset.show_in_picker,
|
|
supported_reasoning_efforts: reasoning_efforts_from_preset(
|
|
preset.supported_reasoning_efforts,
|
|
),
|
|
default_reasoning_effort: preset.default_reasoning_effort,
|
|
input_modalities: preset.input_modalities,
|
|
supports_personality: preset.supports_personality,
|
|
additional_speed_tiers: preset.additional_speed_tiers,
|
|
service_tiers: preset
|
|
.service_tiers
|
|
.into_iter()
|
|
.map(|service_tier| ModelServiceTier {
|
|
id: service_tier.id,
|
|
name: service_tier.name,
|
|
description: service_tier.description,
|
|
})
|
|
.collect(),
|
|
default_service_tier: preset.default_service_tier,
|
|
is_default: preset.is_default,
|
|
}
|
|
}
|
|
|
|
fn reasoning_efforts_from_preset(
|
|
efforts: Vec<ReasoningEffortPreset>,
|
|
) -> Vec<ReasoningEffortOption> {
|
|
efforts
|
|
.iter()
|
|
.map(|preset| ReasoningEffortOption {
|
|
reasoning_effort: preset.effort,
|
|
description: preset.description.to_string(),
|
|
})
|
|
.collect()
|
|
}
|