Struct OpenAiResponsesModelProvider 

pub struct OpenAiResponsesModelProvider { /* private fields */ }

Implementations

impl OpenAiResponsesModelProvider

pub fn builder(alias: &str) -> OpenAiResponsesBuilder

Entry point. Only alias is required; every other field is set via a labelled chain method on the returned OpenAiResponsesBuilder.

Trait Implementations

impl Attributable for OpenAiResponsesModelProvider

fn role(&self) -> Role

fn alias(&self) -> &str

fn tool_provenance(&self) -> ToolProvenance

Classifies whether a tool implementation is first-party native code or an extension. The conservative default prevents a new wrapper from inheriting native presentation privileges accidentally.

impl ModelProvider for OpenAiResponsesModelProvider

fn default_base_url(&self) -> Option<&str>

Reports the instance’s resolved endpoint so callers can verify which host a responses provider will actually hit (e.g. a compat family’s default base vs. OpenAI’s).

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,

Configured Responses-wire aliases (custom/self-hosted endpoints using wire_api = "responses") have no default public fallback the way the OpenAI family does, so an unimplemented listing method here silently drops the configured endpoint in favor of a generic catalog. Probe the sibling /models endpoint next to the configured /responses URL, the same OpenAI-compatible convention OpenAiCompatibleModelProvider uses, so a credentialed or header-authenticated alias returns its own live models instead of an unrelated public list.

fn supports_single_tool_rounds(&self, _model: &str) -> bool

Whether every reachable route for this model honors a native one-call control. Prompt guidance and provider-executed tools do not establish support.

fn capabilities(&self) -> ProviderCapabilities

Query model_provider capabilities.

fn default_wire_api(&self) -> &str

Wire protocol variant. Either "responses" (OpenAI Codex-style) or "chat_completions" (everything else). Providers override to their native format.

fn supports_native_tools(&self) -> bool

Whether model_provider supports native tool calls over API.

fn supports_streaming(&self) -> bool

Whether model_provider supports streaming responses.

fn supports_streaming_tool_events(&self) -> bool

Whether model_provider can emit structured tool-call stream events.

fn chat_with_system<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, system_prompt: Option<&'life1 str>, message: &'life2 str, model: &'life3 str, temperature: Option<f64>, ) -> Pin<Box<dyn Future<Output = Result<String>> + Send + 'async_trait>>

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

One-shot chat with optional system prompt. See simple_chat for the temperature contract.

fn chat<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, request: ProviderChatRequest<'life1>, model: &'life2 str, temperature: Option<f64>, ) -> Pin<Box<dyn Future<Output = Result<ProviderChatResponse>> + Send + 'async_trait>>

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

Structured chat API for agent loop callers. See simple_chat for the temperature contract.

fn chat_with_tool_round_policy<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, request: ProviderChatRequest<'life1>, model: &'life2 str, temperature: Option<f64>, policy: ToolRoundPolicy, ) -> Pin<Box<dyn Future<Output = Result<ProviderChatResponse>> + Send + 'async_trait>>

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

Explicit per-request policy. Unsupported adapters retain their batch path.

fn stream_chat( &self, request: ProviderChatRequest<'_>, model: &str, temperature: Option<f64>, options: StreamOptions, ) -> BoxStream<'static, StreamResult<StreamEvent>>

Structured streaming chat interface. See simple_chat for the temperature contract.

fn stream_chat_with_tool_round_policy( &self, request: ProviderChatRequest<'_>, model: &str, temperature: Option<f64>, options: StreamOptions, policy: ToolRoundPolicy, ) -> BoxStream<'static, StreamResult<StreamEvent>>

fn has_stable_request_identity(&self, _model: &str) -> bool

Whether repeated requests for model are dispatched to one stable provider/model identity.

fn capabilities_for_model(&self, _model: &str) -> ProviderCapabilities

Query the effective capabilities for the model that will be dispatched.

fn vision_limited_by(&self, _model: &str) -> Option<String>

Name the entry that forced vision to false on this provider’s Self::capabilities_for_model, for providers that aggregate several named entries (e.g. a primary plus configured fallbacks) into one capability set. Returns None when this provider is not such an aggregate, or when nothing about it limits vision for model.

fn has_mixed_native_tool_support_for_model(&self, _model: &str) -> bool

Whether the selected request can reach both native-tool and text-only candidates.

fn default_temperature(&self) -> f64

Family-preferred temperature default. Override per family. Documented for introspection only; never use to convert None into a wire value.

fn default_max_tokens(&self) -> u32

Max output tokens used when the caller / config doesn’t set one.

fn default_timeout_secs(&self) -> u64

HTTP timeout (seconds) used when the caller / config doesn’t set one.

fn convert_tools(&self, tools: &[ToolSpec]) -> ToolsPayload

Convert tool specifications to provider-native format.

fn simple_chat<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, message: &'life1 str, model: &'life2 str, temperature: Option<f64>, ) -> Pin<Box<dyn Future<Output = Result<String, Error>> + Send + 'async_trait>>

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

Simple one-shot chat (single user message, no explicit system prompt). temperature == None means the field is omitted on the wire.

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

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

Fetch the list of available models with pricing data for this model_provider. Default delegates to list_models and returns no pricing. Concrete providers that receive pricing from their /models endpoint override this to return enriched data.

fn chat_with_history<'life0, 'life1, 'life2, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], model: &'life2 str, temperature: Option<f64>, ) -> Pin<Box<dyn Future<Output = Result<String, Error>> + Send + 'async_trait>>

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

Multi-turn conversation. See simple_chat for the temperature contract.

fn supports_vision(&self) -> bool

Whether model_provider supports multimodal vision input.

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

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

Warm up the HTTP connection pool.

fn chat_with_tools<'life0, 'life1, 'life2, 'life3, 'async_trait>( &'life0 self, messages: &'life1 [ChatMessage], _tools: &'life2 [Value], model: &'life3 str, temperature: Option<f64>, ) -> Pin<Box<dyn Future<Output = Result<ChatResponse, Error>> + Send + 'async_trait>>

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

Chat with tool definitions for native function calling support. See simple_chat for the temperature contract.

fn stream_chat_with_system( &self, _system_prompt: Option<&str>, _message: &str, _model: &str, _temperature: Option<f64>, _options: StreamOptions, ) -> Pin<Box<dyn Stream<Item = Result<StreamChunk, StreamError>> + Send>>

Streaming chat with optional system prompt. See simple_chat for the temperature contract.

fn stream_chat_with_history( &self, messages: &[ChatMessage], model: &str, temperature: Option<f64>, options: StreamOptions, ) -> Pin<Box<dyn Stream<Item = Result<StreamChunk, StreamError>> + Send>>

Streaming chat with history. See simple_chat for the temperature contract.