LlmCall.Dialect.OpenAI.Chat (llm_call v0.1.0)

Copy Markdown View Source

OpenAI Chat Completions (POST /v1/chat/completions).

OpenAI-compatible providers use this codec too; their differences belong in LlmCall.Request.provider_options and the transport's base URL, not in a new protocol.

System instructions become a leading system message. Tool results become role: "tool" messages, emitted before the message's remaining content because OpenAI requires them directly after the assistant tool call.

usage.prompt_tokens_details carries both cache counters (read and write), and reasoning_effort accepts none, minimal, low, medium, high, xhigh, and max; the model decides which it honours.

The deprecated message.function_call and delta.function_call are not decoded into ToolCalls: OpenAI replaced them with tool_calls, and only the old shape is kept as Content.Raw, so a legacy provider's call is visible but not dispatchable through LlmCall.Response.tool_calls/1.

Summary

Functions

Validates the request and encodes it as a POST to the codec's @path.

Functions

encode_request(request, config)

@spec encode_request(LlmCall.Request.t(), LlmCall.Config.t()) ::
  {:ok, LlmCall.EncodedRequest.t()} | {:error, LlmCall.Error.t()}

Validates the request and encodes it as a POST to the codec's @path.