Sycophant.WireProtocol.OpenAIResponses (sycophant v0.4.2)

Copy Markdown

Wire protocol adapter for the OpenAI Responses API format.

Encodes Sycophant Request structs into the POST /v1/responses JSON format and decodes responses back into Response structs. Uses items instead of messages, flat tool definitions, and extracts system messages into the instructions field.

Summary

Types

t()

Functions

param_schema()

Options

Types

t()

@type t() :: %{
  optional(:stop) => [binary()],
  optional(:include) => [binary()],
  optional(:cache_key) => binary(),
  optional(:store) => boolean(),
  optional(:metadata) => any(),
  optional(:max_tokens) => integer(),
  optional(:temperature) => float(),
  optional(:top_p) => float(),
  optional(:top_k) => integer(),
  optional(:reasoning_effort) =>
    :none | :minimal | :low | :medium | :high | :xhigh,
  optional(:reasoning_budget) => integer(),
  optional(:reasoning_summary) => :auto | :concise | :detailed | :none,
  optional(:service_tier) => binary(),
  optional(:tool_choice) => any(),
  optional(:parallel_tool_calls) => boolean(),
  optional(:top_logprobs) => integer(),
  optional(:cache_retention) => binary(),
  optional(:safety_identifier) => binary(),
  optional(:truncation) => :auto | :disabled,
  optional(:max_tool_calls) => integer(),
  optional(:stream_options) => any(),
  optional(:context_management) => any(),
  optional(:verbosity) => :low | :medium | :high,
  optional(:previous_response_id) => binary()
}

Functions

param_schema()

Options:

  • :stop (list of String.t/0) - Stop sequences

  • :include (list of String.t/0) - Additional output data to include in the response

  • :cache_key (String.t/0) - Cache key for prompt caching

  • :store (boolean/0) - Whether to store the response for later retrieval

  • :metadata (term/0) - Key-value metadata to attach to the response

  • :max_tokens (integer/0) - Maximum number of tokens to generate

  • :temperature (float/0) - Sampling temperature

  • :top_p (float/0) - Nucleus sampling threshold

  • :top_k (integer/0) - Top-K sampling

  • :reasoning_effort (:none | :minimal | :low | :medium | :high | :xhigh) - Extended thinking effort level

  • :reasoning_budget (integer/0) - Explicit reasoning token budget

  • :reasoning_summary (:auto | :concise | :detailed | :none) - How to summarize reasoning

  • :service_tier (String.t/0) - Service tier selection

  • :tool_choice (term/0) - Tool selection strategy

  • :parallel_tool_calls (boolean/0) - Allow parallel tool calls

  • :top_logprobs (integer/0) - Number of most likely tokens to return per position

  • :cache_retention ("in-memory" | "24h") - Cache retention policy

  • :safety_identifier (String.t/0) - Safety identifier for content filtering

  • :truncation (:auto | :disabled) - Context window overflow handling

  • :max_tool_calls (integer/0) - Maximum number of tool calls per response

  • :stream_options (term/0) - Options for streaming responses

  • :context_management (term/0) - Context management configuration

  • :verbosity (:low | :medium | :high) - Response verbosity level

  • :previous_response_id (String.t/0) - ID of a previous response to chain from