Struct FallbackProvider 

pub struct FallbackProvider { /* private fields */ }

An LlmProvider that fails over across an ordered list of backends.

Construct with a primary, then layer secondaries with with_fallback (or build the whole chain at once with from_providers).

Implementations

impl FallbackProvider

pub fn new(primary: Arc<dyn LlmProvider>) -> Self

Create a fallback chain with a single primary provider (no secondaries yet).

pub fn with_fallback(self, provider: Arc<dyn LlmProvider>) -> Self

Append a secondary provider to the end of the failover order.

pub fn from_providers( primary: Arc<dyn LlmProvider>, fallbacks: impl IntoIterator<Item = Arc<dyn LlmProvider>>, ) -> Self

Build a chain from a primary and an ordered iterator of secondaries.

pub fn len(&self) -> usize

Total number of providers in the chain (primary + secondaries).

pub const fn is_empty(&self) -> bool

Always false — a chain always has at least the primary.

Trait Implementations

impl LlmProvider for FallbackProvider

fn list_models<'life0, 'async_trait>( &'life0 self, ) -> Pin<Box<dyn Future<Output = Result<Vec<ModelInfo>>> + Send + 'async_trait>>

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

Delegate live model discovery to the primary provider so wrapping in a fallback never silently loses list_models.

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 model_features(&self) -> Option<&'static ModelFeatures>

API-shape feature metadata for this provider/model, when known.

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

Validate a thinking configuration against the provider/model capabilities.

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

Resolve the effective thinking configuration for a request.

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.