Struct ProviderDispatch 

pub struct ProviderDispatch { /* private fields */ }

Wraps a model provider so every call opens the correct attribution_span! automatically. See the module docs for the rationale and the CI gate that enforces routing through this type.

Implementations

impl ProviderDispatch

pub fn new(inner: Arc<dyn ModelProvider>) -> Self

Wrap an Arc<dyn ModelProvider> so its method calls open attribution_span!(&*inner) automatically.

pub fn from_ref(inner: &dyn ModelProvider) -> ProviderDispatchRef<'_>

Wrap a borrowed &dyn ModelProvider. Returns a ProviderDispatchRef for ergonomic chaining at call sites that don’t hold an Arc.

pub async fn chat( &self, request: ChatRequest<'_>, model: &str, temperature: Option<f64>, ) -> Result<ChatResponse>

Open attribution_span!(&*self.inner) + scope!(model: model) around the inner provider’s chat call.

pub fn stream_chat( &self, request: ChatRequest<'_>, model: &str, temperature: Option<f64>, options: StreamOptions, ) -> BoxStream<'static, StreamResult<StreamEvent>>

pub async fn simple_chat( &self, message: &str, model: &str, temperature: Option<f64>, ) -> Result<String>

pub async fn chat_with_system( &self, system_prompt: Option<&str>, message: &str, model: &str, temperature: Option<f64>, ) -> Result<String>

Wrap the inner provider’s chat_with_system.

pub async fn chat_with_history( &self, messages: &[ChatMessage], model: &str, temperature: Option<f64>, ) -> Result<String>

Wrap the inner provider’s chat_with_history.

pub async fn chat_with_tools( &self, messages: &[ChatMessage], tools: &[Value], model: &str, temperature: Option<f64>, ) -> Result<ChatResponse>

Wrap the inner provider’s chat_with_tools.

pub async fn list_models(&self) -> Result<Vec<String>>

pub async fn list_models_with_pricing(&self) -> Result<Vec<ModelInfo>>

Wrap the inner provider’s list_models_with_pricing. Same &*self.inner rationale as list_models.

pub async fn warmup(&self) -> Result<()>

Wrap the inner provider’s warmup. No model parameter, so attribution only.