Struct OpenAIResponsesProvider 

pub struct OpenAIResponsesProvider { /* private fields */ }

Available on crate feature openai only.

OpenAI Responses API provider.

This provider uses the /v1/responses endpoint for OpenAI models that expose agentic workflows over the Responses API.

Implementations

impl OpenAIResponsesProvider

pub fn new(api_key: String, model: String) -> OpenAIResponsesProvider

Create a new OpenAI Responses API provider.

pub fn with_base_url( api_key: String, model: String, base_url: String, ) -> OpenAIResponsesProvider

Create a provider with a custom base URL.

pub fn with_extra_headers( self, headers: Vec<(String, String)>, ) -> OpenAIResponsesProvider

Add extra HTTP headers applied to every request.

Used by OpenAIProvider’s transparent Responses-API reroute to forward its BYOK / gateway auth headers (e.g. cf-aig-authorization) so a rerouted request authenticates correctly.

pub fn gpt56(api_key: String) -> OpenAIResponsesProvider

Create a provider using the GPT-5.6 alias, which routes to GPT-5.6 Sol.

pub fn gpt56_sol(api_key: String) -> OpenAIResponsesProvider

Create a provider using GPT-5.6 Sol (frontier reasoning and coding).

pub fn gpt56_terra(api_key: String) -> OpenAIResponsesProvider

Create a provider using GPT-5.6 Terra (balanced intelligence and cost).

pub fn gpt56_luna(api_key: String) -> OpenAIResponsesProvider

Create a provider using GPT-5.6 Luna (cost-sensitive, high-volume work).

pub fn gpt53_codex(api_key: String) -> OpenAIResponsesProvider

Create a provider using GPT-5.3-Codex (latest codex model).

pub fn codex(api_key: String) -> OpenAIResponsesProvider

Create a provider using the latest Codex model.

pub fn with_thinking(self, thinking: ThinkingConfig) -> OpenAIResponsesProvider

Set the provider-owned thinking configuration for this model.

pub fn with_reasoning( self, reasoning: OpenAIReasoningConfig, ) -> OpenAIResponsesProvider

Set exact OpenAI reasoning and related response controls.

Calling this after with_thinking replaces the legacy provider-owned thinking configuration.

pub fn with_reasoning_effort( self, effort: ReasoningEffort, ) -> OpenAIResponsesProvider

Set the reasoning effort level.

Trait Implementations

impl Clone for OpenAIResponsesProvider

fn clone(&self) -> OpenAIResponsesProvider

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl LlmProvider for OpenAIResponsesProvider

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

where 'life0: 'async_trait, OpenAIResponsesProvider: 'async_trait,

Non-streaming chat completion.

fn chat_stream( &self, request: ChatRequest, ) -> Pin<Box<dyn Stream<Item = Result<StreamDelta, Error>> + Send + '_>>

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

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

List the models the provider currently exposes, queried live from the provider’s own model-listing endpoint.

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<(), Error>

Validate a thinking configuration against the provider/model capabilities.

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

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.