Struct DefaultProvider 

pub struct DefaultProvider { /* private fields */ }

Default provider that makes minimal assumptions.

This provider assumes:

• Standard OpenAI-compatible API path: /chat/completions (the /v1 prefix comes from the backend URL’s base_path)
• Model names are passed through as-is
• No special request/response transformations needed

Use this as a fallback for providers not explicitly supported.

The backend_name field preserves the backend name from the config (e.g., "qwen", "yi") so that logging and diagnostics can identify which backend a request was routed to, even though the provider implementation is the generic default.

Implementations

impl DefaultProvider

pub fn new(backend_name: &str) -> Self

Create a new DefaultProvider with the original backend name.

The backend_name is the name the user specified in config.json (e.g., "qwen", "yi-lightning"). It is preserved for logging and diagnostics; the provider type is always "default".

Trait Implementations

impl Default for DefaultProvider

fn default() -> Self

Returns the “default value” for a type.

impl Provider for DefaultProvider

fn name(&self) -> &'static str

Returns "default" to indicate this is the generic fallback provider.

fn display_name(&self) -> &str

Returns the original backend name from config (e.g., "qwen", "yi-lightning"), making it easy to identify which backend a request was routed to in logs and diagnostics.

fn chat_completions_path(&self) -> String

Get the chat completions path for this provider.

fn transform_request(&self, _request: &mut ChatRequest)

Transform request before sending to provider.

fn transform_response(&self, _response: &mut ChatResponse)

Transform response after receiving from provider.

fn transform_stream_chunk(&self, _chunk: &mut ChatStreamChunk)

Transform streaming chunk in real-time.

fn normalize_model(&self, model: String) -> String

Normalize model name from Responses API to provider’s format.