Struct AnthropicFoundryClient 

pub struct AnthropicFoundryClient { /* private fields */ }

An Anthropic Messages API transport for Claude models hosted on Azure AI Foundry (POST {base_url}{path}).

See the module docs for how this relates to AnthropicClient and for the caveats around the default path/anthropic_version.

Implementations

impl AnthropicFoundryClient

pub fn with_token_credential( base_url: impl Into<String>, model: impl Into<String>, credential: Arc<dyn TokenCredential>, ) -> Self

Create a client authenticating via a TokenCredential (Microsoft Entra ID) against a Foundry Anthropic deployment’s base_url.

pub fn with_scope(self, scope: impl Into<String>) -> Self

Override the Entra ID scope requested for the bearer token (default DEFAULT_SCOPE).

pub fn with_path(self, path: impl Into<String>) -> Self

Override the path suffix appended to base_url (default DEFAULT_PATH). See the module docs for why this may need adjusting per deployment.

pub fn with_anthropic_version( self, anthropic_version: impl Into<String>, ) -> Self

Override the anthropic_version sent in the request body (default ANTHROPIC_FOUNDRY_VERSION). See the module docs for why this may need adjusting per deployment.

pub fn with_max_tokens(self, max_tokens: u32) -> Self

Override the default max_tokens sent when ChatOptions::max_tokens is unset (the Anthropic Messages API requires this field).

pub fn model(&self) -> &str

The default model id.

Trait Implementations

impl ChatClient for AnthropicFoundryClient

fn get_streaming_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatStream>> + Send + 'async_trait>>

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

Get a streaming response.

Whether (and how) a given Foundry Anthropic deployment streams is one more thing this crate can’t assume stably across deployments (see the module docs), so this calls the same non-streaming endpoint ChatClient::get_response does and adapts the complete ChatResponse into a single ChatResponseUpdate — the same tactic crate::bedrock::AnthropicBedrockClient::get_streaming_response and crate::vertex::AnthropicVertexClient::get_streaming_response use. Callers driving this client through ChatResponse::from_updates still get a correct aggregated result; they just don’t see partial text arrive incrementally.

fn get_response<'life0, 'async_trait>( &'life0 self, messages: Vec<Message>, options: ChatOptions, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse>> + Send + 'async_trait>>

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

Get a complete (non-streaming) response.

fn model(&self) -> Option<&str>

The default model id for this client, if any.

impl Clone for AnthropicFoundryClient

fn clone(&self) -> AnthropicFoundryClient

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for AnthropicFoundryClient

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.