Struct LlmClientAdapter 

pub struct LlmClientAdapter { /* private fields */ }

Bridges an LlmClient to the StreamClient trait.

Wraps an Arc<dyn LlmClient> so existing provider implementations can be used with the new StreamClient-based engine.

Implementations

impl LlmClientAdapter

pub fn new(client: Arc<dyn LlmClient>) -> Self

Wrap an existing LlmClient for use as a StreamClient.

pub fn inner(&self) -> &Arc<dyn LlmClient>

Get a reference to the inner LlmClient.

Trait Implementations

impl StreamClient for LlmClientAdapter

fn chat<'life0, 'life1, 'life2, 'life3, 'life4, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], tools: &'life2 [Value], reasoning: Option<&'life3 ReasoningConfig>, response_format: Option<&'life4 ResponseFormat>, ) -> Pin<Box<dyn Future<Output = AgentResult<String>> + Send + 'async_trait>>

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

Delegate to the inner client’s chat() for efficiency — avoids streaming when only the final text is needed.

fn stream<'life0, 'life1, 'life2, 'life3, 'life4, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], tools: &'life2 [Value], reasoning: Option<&'life3 ReasoningConfig>, response_format: Option<&'life4 ResponseFormat>, ) -> Pin<Box<dyn Future<Output = AgentResult<Pin<Box<dyn Stream<Item = AgentResult<StreamChunk>> + Send>>>> + Send + 'async_trait>>

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

Stream LLM response chunks from the provider.

fn capabilities(&self) -> LlmCapabilities

Return the provider’s capabilities.

fn model_name(&self) -> &str

The model name used by this client (e.g. “claude-sonnet”, “gpt-4o”). Default: “unknown”.