Struct RefreshingProvider 

pub struct RefreshingProvider<P, F> { /* private fields */ }

Wraps a provider with host-driven credential refresh on 401.

The inner provider is stored behind Arc<Mutex<P>> so it can be swapped atomically when the refresh callback produces a new provider. Cloning a wrapper is cheap — clones share the same inner state.

Metadata (model, provider, configured_thinking) and capability shaping (capabilities, default_max_tokens, validate_thinking_config, structured_output_support) are captured from the initial provider at construction time and assumed constant across refreshes (the refresh callback rebuilds the same provider shape with a fresh token, not a different model).

Implementations

impl<P, F, Fut> RefreshingProvider<P, F>

where P: LlmProvider + Clone + 'static, F: Fn() -> Fut + Send + Sync + 'static, Fut: Future<Output = Result<P>> + Send + 'static,

pub fn new(inner: P, refresh: F) -> Self

Build a wrapper from an initial provider and a refresh callback.

The refresh callback is invoked each time the inner provider emits a 401 response. It must be idempotent and safe to call concurrently. The callback should return a fully-built provider ready to use; typically it reads fresh credentials from its auth store and calls the inner provider’s constructor.

Trait Implementations

impl<P: Clone, F> Clone for RefreshingProvider<P, F>

fn clone(&self) -> Self

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl<P, F, Fut> LlmProvider for RefreshingProvider<P, F>

where P: LlmProvider + Clone + 'static, F: Fn() -> Fut + Send + Sync + 'static, Fut: Future<Output = Result<P>> + Send + 'static,

fn chat<'life0, 'async_trait>( &'life0 self, request: ChatRequest, ) -> Pin<Box<dyn Future<Output = Result<ChatOutcome>> + Send + 'async_trait>>

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

Non-streaming chat completion.

fn chat_stream(&self, request: ChatRequest) -> StreamBox<'_>

Streaming chat completion.

fn model(&self) -> &str

fn provider(&self) -> &'static str

fn configured_thinking(&self) -> Option<&ThinkingConfig>

Provider-owned thinking configuration, if any.

fn capabilities(&self) -> Option<&'static ModelCapabilities>

Canonical capability metadata for this provider/model, if known.

fn validate_thinking_config( &self, thinking: Option<&ThinkingConfig>, ) -> Result<()>

Validate a thinking configuration against the provider/model capabilities.

fn default_max_tokens(&self) -> u32

Default maximum output tokens for this provider/model when the caller does not explicitly override AgentConfig.max_tokens.

fn structured_output_support(&self) -> StructuredOutputSupport

How this provider satisfies a structured-output (ResponseFormat) request.

fn resolve_thinking_config( &self, request_thinking: Option<&ThinkingConfig>, ) -> Result<Option<ThinkingConfig>>

Resolve the effective thinking configuration for a request.