litellm/litellm-rust/crates/llms/src/lib.rs
yujonglee 05cf428761
feat(rust): settle EdenAI Messages reported cost (#45698)
* feat(edenai): settle native Messages reported cost

* test(rust): add live EdenAI Messages contract cases

* refactor(rust): settle call cost once as an ExecutionFacts variant

The route now decides Cost (Reported, CacheHit or Deferred) from the
result source and the provider's reported figure. The legacy callback
adapter only projects a Reported amount onto provider_reported_cost and
no longer writes response_cost, which the Python calculator derives

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>

* refactor(rust): keep EdenAI wire shaping independent of Invoke

* style(rust): format cost settlement imports

* fix(rust): trust provider costs without bypassing configured pricing

* fix(rust): clear untrusted response costs before spend settlement

---------

Co-authored-by: Claude Fable 5.1 <noreply@anthropic.com>
2026-10-12 17:39:08 -07:00

20 lines
374 B
Rust

pub mod anthropic;
pub mod aws_textract;
pub mod azure_ai;
pub mod base_llm;
pub mod bedrock;
pub mod bedrock_mantle;
pub mod cohere;
pub mod deepseek;
pub mod edenai;
mod error;
pub mod minimax;
pub mod mistral;
pub mod openai;
pub mod openai_like;
pub mod openrouter;
pub mod reducto;
pub mod tencent;
pub mod vertex_ai;
pub use error::{Error, ErrorDetail, ErrorSource};