Struct ReloadableProvider 

pub struct ReloadableProvider { /* private fields */ }

An LLMProvider wrapper that always delegates to the latest provider stored in a shared lock.

This prevents stale provider snapshots after runtime config changes (provider/model/proxy), while keeping the call sites ergonomic (Arc<dyn LLMProvider>).

Implementations

impl ReloadableProvider

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

Trait Implementations

impl LLMProvider for ReloadableProvider

fn chat_stream<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, messages: &'life1 [Message], tools: &'life2 [ToolSchema], max_output_tokens: Option<u32>, model: &'life3 str, ) -> Pin<Box<dyn Future<Output = Result<LLMStream>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait,

Stream chat completion from the LLM

fn chat_stream_with_options<'life0, 'life1, 'life2, 'life3, 'life4, 'async_trait>( &'life0 self, messages: &'life1 [Message], tools: &'life2 [ToolSchema], max_output_tokens: Option<u32>, model: &'life3 str, options: Option<&'life4 LLMRequestOptions>, ) -> Pin<Box<dyn Future<Output = Result<LLMStream>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait, 'life1: 'async_trait, 'life2: 'async_trait, 'life3: 'async_trait, 'life4: 'async_trait,

Stream chat completion with optional request-level controls.

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

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

Lists available models from this provider

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

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

Lists available models with optional token limit metadata.