Python class

TextGenerationResponseFormat

`TextGenerationResponseFormat`

class max.pipelines.modeling.types.pipeline_variants.TextGenerationResponseFormat

source

Bases: TypedDict

Represents the response format specification for a text generation request.

`grammar`

grammar: str | None

source

Grammar for constrained decoding.

When set with type="grammar", this takes precedence over json_schema. Used for model-specific constrained decoding formats like Kimi’s tool call grammar.

`grammar_enforced`

grammar_enforced: bool

source

Whether to actively enforce grammar via bitmask.

When True from the start, enforce grammar from the first token. When False initially (for tool_choice=auto without response_format), the grammar is compiled but not enforced until a tool call start token is detected.

`json_schema`

json_schema: dict[str, Any]

source

A JSON schema dictionary that defines the structure and validation rules for the generated response.

`requires_structured_output_flag`

requires_structured_output_flag: NotRequired[bool]

source

Whether this request requires --enable-structured-output to be set.

True when the constraint includes a user-supplied JSON schema (from response_format). False (or absent) for pure tool-call grammars derived from the model’s tool parser, which work without the operator flag because the grammar is server-controlled, not user-controlled.

Optional (defaults to False) so existing call sites that construct TextGenerationResponseFormat directly don’t need to be updated.

`tools_forced`

tools_forced: bool

source

Whether tool calling was forced (tool_choice=required or named function).

Controls whether grammar_enforced is True from the first generated token. Independent of the --enable-structured-output flag (which only gates user-supplied schemas; see requires_structured_output_flag).

`type`

type: str

source

The type of response format, for example, json_object or grammar.