af-llm 0.4.0

//! `af-llm` — unified async LLM access for the Agent Factory platform.
//!
//! Provider-neutral model transport and request types. Provides:
//!
//! - [`LlmClient`] — async chat completions against any OpenAI-compatible
//!   endpoint, with a hard per-request timeout and a shared
//!   [`CircuitBreaker`].
//! - Strongly-typed request/response models ([`CompletionRequest`],
//!   [`CompletionResponse`], [`ChatMessage`], [`Tool`], …) — the Pydantic
//!   equivalent, validated at the wire boundary.
//! - [`parse_json`] — pull structured output out of fenced LLM text into any
//!   `serde` type.
//!
//! # Example
//!
//! ```no_run
//! use af_llm::{LlmClient, LlmConfig, CompletionRequest, ChatMessage};
//!
//! # async fn run() -> af_llm::Result<()> {
//! let client = LlmClient::new(LlmConfig::new("http://localhost:4000/v1", ""))?;
//! let req = CompletionRequest::new(
//!     "deepseek/deepseek-chat",
//!     vec![ChatMessage::user("Say hi in one word.")],
//! );
//! let resp = client.complete_stream_single_attempt(&req, |_, _| {}).await?;
//! println!("{:?}", resp.first_content());
//! # Ok(())
//! # }
//! ```

#![deny(missing_docs)]
#![deny(rustdoc::broken_intra_doc_links)]

pub mod circuit_breaker;
pub mod client;
pub mod error;
pub mod json;
pub mod stream;
pub mod types;

pub use circuit_breaker::{CircuitBreaker, State as CircuitState, Status as CircuitStatus};
pub use client::{LlmClient, LlmConfig, DEFAULT_TIMEOUT};
pub use error::{LlmError, Result};
pub use json::{parse_json, strip_code_fence};
pub use stream::StreamDelta;
pub use types::{
    AssistantBlock, ChatMessage, Choice, CompletionRequest, CompletionResponse, FinishReason,
    FunctionCall, FunctionDef, ReasoningEffort, Role, StreamOptions, Tool, ToolCall, ToolChoice,
    Usage,
};