mirror of
https://github.com/openai/codex.git
synced 2026-10-25 18:28:38 +00:00
Ahmed Ibrahim
cee37a32b2
This PR moves `ModelsFamily` to `openai_models`. It also propagates `ModelsManager` to session services and use it to drive model family. We also make `derive_default_model_family` private because it's a step towards what we want: one place that gives model configuration. This is a second step at having one source of truth for models information and config: `ModelsManager`. Next steps would be to remove `ModelsFamily` from config. That's massive because it's being used in 41 occasions mostly pre launching `codex`. Also, we need to make `find_family_for_model` private. It's also big because it's being used in 21 occasions ~ all tests.
84 lines
3.3 KiB
Rust
84 lines
3.3 KiB
Rust
use crate::openai_models::model_family::ModelFamily;
|
|
|
|
// Shared constants for commonly used window/token sizes.
|
|
pub(crate) const CONTEXT_WINDOW_272K: i64 = 272_000;
|
|
|
|
/// Metadata about a model, particularly OpenAI models.
|
|
/// We may want to consider including details like the pricing for
|
|
/// input tokens, output tokens, etc., though users will need to be able to
|
|
/// override this in config.toml, as this information can get out of date.
|
|
/// Though this would help present more accurate pricing information in the UI.
|
|
#[derive(Debug)]
|
|
pub(crate) struct ModelInfo {
|
|
/// Size of the context window in tokens. This is the maximum size of the input context.
|
|
pub(crate) context_window: i64,
|
|
|
|
/// Token threshold where we should automatically compact conversation history. This considers
|
|
/// input tokens + output tokens of this turn.
|
|
pub(crate) auto_compact_token_limit: Option<i64>,
|
|
}
|
|
|
|
impl ModelInfo {
|
|
const fn new(context_window: i64) -> Self {
|
|
Self {
|
|
context_window,
|
|
auto_compact_token_limit: Some(Self::default_auto_compact_limit(context_window)),
|
|
}
|
|
}
|
|
|
|
const fn default_auto_compact_limit(context_window: i64) -> i64 {
|
|
(context_window * 9) / 10
|
|
}
|
|
}
|
|
|
|
pub(crate) fn get_model_info(model_family: &ModelFamily) -> Option<ModelInfo> {
|
|
let slug = model_family.slug.as_str();
|
|
match slug {
|
|
// OSS models have a 128k shared token pool.
|
|
// Arbitrarily splitting it: 3/4 input context, 1/4 output.
|
|
// https://openai.com/index/gpt-oss-model-card/
|
|
"gpt-oss-20b" => Some(ModelInfo::new(96_000)),
|
|
"gpt-oss-120b" => Some(ModelInfo::new(96_000)),
|
|
// https://platform.openai.com/docs/models/o3
|
|
"o3" => Some(ModelInfo::new(200_000)),
|
|
|
|
// https://platform.openai.com/docs/models/o4-mini
|
|
"o4-mini" => Some(ModelInfo::new(200_000)),
|
|
|
|
// https://platform.openai.com/docs/models/codex-mini-latest
|
|
"codex-mini-latest" => Some(ModelInfo::new(200_000)),
|
|
|
|
// As of Jun 25, 2025, gpt-4.1 defaults to gpt-4.1-2025-04-14.
|
|
// https://platform.openai.com/docs/models/gpt-4.1
|
|
"gpt-4.1" | "gpt-4.1-2025-04-14" => Some(ModelInfo::new(1_047_576)),
|
|
|
|
// As of Jun 25, 2025, gpt-4o defaults to gpt-4o-2024-08-06.
|
|
// https://platform.openai.com/docs/models/gpt-4o
|
|
"gpt-4o" | "gpt-4o-2024-08-06" => Some(ModelInfo::new(128_000)),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-05-13
|
|
"gpt-4o-2024-05-13" => Some(ModelInfo::new(128_000)),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-11-20
|
|
"gpt-4o-2024-11-20" => Some(ModelInfo::new(128_000)),
|
|
|
|
// https://platform.openai.com/docs/models/gpt-3.5-turbo
|
|
"gpt-3.5-turbo" => Some(ModelInfo::new(16_385)),
|
|
|
|
_ if slug.starts_with("gpt-5-codex")
|
|
|| slug.starts_with("gpt-5.1-codex")
|
|
|| slug.starts_with("gpt-5.1-codex-max") =>
|
|
{
|
|
Some(ModelInfo::new(CONTEXT_WINDOW_272K))
|
|
}
|
|
|
|
_ if slug.starts_with("gpt-5") => Some(ModelInfo::new(CONTEXT_WINDOW_272K)),
|
|
|
|
_ if slug.starts_with("codex-") => Some(ModelInfo::new(CONTEXT_WINDOW_272K)),
|
|
|
|
_ if slug.starts_with("exp-") => Some(ModelInfo::new(CONTEXT_WINDOW_272K)),
|
|
|
|
_ => None,
|
|
}
|
|
}
|