Struct AnthropicProvider 

pub struct AnthropicProvider {
    pub api_key: String,
    pub base_url: String,
    pub model: String,
    pub thinking_budget_tokens: Option<u32>,
}

HTTP-based Anthropic Claude provider

Fields

api_key: String

base_url: String

model: String

thinking_budget_tokens: Option<u32>

Optional: enable Anthropic “extended thinking” in non-streaming calls. When set, we inject the thinking field into the request body.

Trait Implementations

impl LlmProvider for AnthropicProvider

fn call<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<String, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Call the LLM with a prompt and return the generated text. For backward compatibility, this returns just the text.

fn call_with_usage<'life0, 'life1, 'async_trait>( &'life0 self, prompt: &'life1 str, ) -> Pin<Box<dyn Future<Output = Result<LlmCallResponse, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait,

Call the LLM with a prompt and return the response with token usage. Default implementation calls call and returns unknown usage.

fn call_with_tools<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, prompt: &'life1 str, tools: Option<&'life2 [Value]>, ) -> Pin<Box<dyn Future<Output = Result<LlmCallResponse, AppError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait,

Call the LLM with a prompt and optional tool schemas.