Phase 1: Repository & Infrastructure Setup
- Renamed directories: codex-rs -> llmx-rs, codex-cli -> llmx-cli
- Updated package.json files:
- Root: llmx-monorepo
- CLI: @llmx/llmx
- SDK: @llmx/llmx-sdk
- Updated pnpm workspace configuration
- Renamed binary: codex.js -> llmx.js
- Updated environment variables: CODEX_* -> LLMX_*
- Changed repository URLs to valknar/llmx
🤖 Generated with Claude Code
This commit is contained in:
87
llmx-rs/core/src/openai_model_info.rs
Normal file
87
llmx-rs/core/src/openai_model_info.rs
Normal file
@@ -0,0 +1,87 @@
|
||||
use crate::model_family::ModelFamily;
|
||||
|
||||
// Shared constants for commonly used window/token sizes.
|
||||
pub(crate) const CONTEXT_WINDOW_272K: i64 = 272_000;
|
||||
pub(crate) const MAX_OUTPUT_TOKENS_128K: i64 = 128_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/// override this in config.toml, as this information can get out of date.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,
|
||||
|
||||
/// Maximum number of output tokens that can be generated for the model.
|
||||
pub(crate) max_output_tokens: 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, max_output_tokens: i64) -> Self {
|
||||
Self {
|
||||
context_window,
|
||||
max_output_tokens,
|
||||
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, 32_000)),
|
||||
"gpt-oss-120b" => Some(ModelInfo::new(96_000, 32_000)),
|
||||
// https://platform.openai.com/docs/models/o3
|
||||
"o3" => Some(ModelInfo::new(200_000, 100_000)),
|
||||
|
||||
// https://platform.openai.com/docs/models/o4-mini
|
||||
"o4-mini" => Some(ModelInfo::new(200_000, 100_000)),
|
||||
|
||||
// https://platform.openai.com/docs/models/codex-mini-latest
|
||||
"codex-mini-latest" => Some(ModelInfo::new(200_000, 100_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, 32_768)),
|
||||
|
||||
// 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, 16_384)),
|
||||
|
||||
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-05-13
|
||||
"gpt-4o-2024-05-13" => Some(ModelInfo::new(128_000, 4_096)),
|
||||
|
||||
// https://platform.openai.com/docs/models/gpt-4o?snapshot=gpt-4o-2024-11-20
|
||||
"gpt-4o-2024-11-20" => Some(ModelInfo::new(128_000, 16_384)),
|
||||
|
||||
// https://platform.openai.com/docs/models/gpt-3.5-turbo
|
||||
"gpt-3.5-turbo" => Some(ModelInfo::new(16_385, 4_096)),
|
||||
|
||||
_ if slug.starts_with("gpt-5-codex") => {
|
||||
Some(ModelInfo::new(CONTEXT_WINDOW_272K, MAX_OUTPUT_TOKENS_128K))
|
||||
}
|
||||
|
||||
_ if slug.starts_with("gpt-5") => {
|
||||
Some(ModelInfo::new(CONTEXT_WINDOW_272K, MAX_OUTPUT_TOKENS_128K))
|
||||
}
|
||||
|
||||
_ if slug.starts_with("codex-") => {
|
||||
Some(ModelInfo::new(CONTEXT_WINDOW_272K, MAX_OUTPUT_TOKENS_128K))
|
||||
}
|
||||
|
||||
_ => None,
|
||||
}
|
||||
}
|
||||
Reference in New Issue
Block a user