Omni.Dialects.OpenAICompletions (Omni v2.0.0)

Copy Markdown View Source

Dialect implementation for the OpenAI Chat Completions wire format.

See Omni.Dialect.Text for the behaviour specification and delta types.

Compat flags

The Chat Completions format is spoken by many providers, most with small deviations from OpenAI's own API. With no flags, the dialect behaves exactly like OpenAI's API; each flag describes one deviation. Set them on a provider's endpoint for this dialect, dialects: %{Omni.Dialects.OpenAICompletions => [compat: [...]]} (see Omni.Provider).

FlagDefault (OpenAI)Setting it
:max_tokens_field"max_completion_tokens"sends :max_tokens under this field
:thinking_effort_field"reasoning_effort"sends the effort level here (dots nest: "reasoning.effort")
:thinking_budget_fieldno budget sentsends a token budget here, for models that take one and list no effort values
:thinking_replay_formatearlier reasoning not sent backhow reasoning is sent back on assistant messages (below)
:thinking_toggle_formatoff is reasoning_effort: "none"; no on-switchhow thinking is switched on and off (below)
:output_format:json_schema:json_object: JSON mode, with the schema in the system prompt
:attachment_format:file:file_url: non-image files as file_url content parts
:omit[]never sends these: :cache, :thinking, :strict_schema
:extra_body%{}merges these literal fields into every request body

:thinking_toggle_format values:

  • :thinking_type - thinking: {type: "enabled" | "disabled"}

  • :enable_thinking - enable_thinking: true | false

  • :reasoning_enabled - reasoning: {enabled: true | false}

:thinking_replay_format values:

  • :none - reasoning is not sent back
  • :reasoning_content - sends the message's thinking text in a reasoning_content field on that assistant message
  • :reasoning - the same, in a reasoning field
  • :reasoning_details - captures reasoning_details from responses and sends them back on that assistant message; streamed fragments are merged into one entry per reasoning block when the stream completes
  • :content_chunks - sends the message's thinking as one leading {type: "thinking", thinking: [{type: "text", ...}]} part of a content array, before its text parts

Models that list effort values (see Omni.Model) take the effort, even when a toggle format is set; the toggle switches them off, and switches on models without effort values. Likewise a budget is sent only to models without effort values.