Struct ExecutorAsyncOpenai 

pub struct ExecutorAsyncOpenai { /* private fields */ }

Executes non-streaming Chat Completions and returns the first choice’s text.

Task models override the configured default. Missing models, malformed chat data, and request/API failures return Err; missing choices or text produce an unsuccessful Response. Reported usage is total tokens, or zero if absent.

Sends the optional system instruction, prior user/assistant turns, and the current prompt as a user message, in that order.

Current limitations

• System entries in input history are discarded; use TaskChat::system for a persistent system instruction.
• Returned history currently duplicates the latest user prompt: it is kept from the request messages and appended again before the assistant reply.
• Schemas request strict JSON output named response; returned text is not locally parsed or validated against the schema.
• max_tokens is cast from u64 to u32 without range checking. Payload metadata is preserved in the task but is not sent to the model.

Implementations

impl ExecutorAsyncOpenai

pub fn from_env_or_default() -> Self

Creates a client without contacting the endpoint.

Reads OPENAI_API_URL (default http://127.0.0.1:8000/v1) and snapshots OPENAI_API_DEFAULT_MODEL. Authentication uses async-openai’s default configuration. Endpoint/model validity is checked only when executing.

Trait Implementations

impl Clone for ExecutorAsyncOpenai

fn clone(&self) -> ExecutorAsyncOpenai

Returns a duplicate of the value.

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

Performs copy-assignment from source.

impl Debug for ExecutorAsyncOpenai

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Executor for ExecutorAsyncOpenai

fn default_model(&self) -> &Arc<Option<String>>

Returns the fallback model used when a task does not specify one.

async fn execute(&self, task: Task) -> Result<Response>

Executes one task; Err indicates execution failed before a response.