vllm.parser.engine.parser_engine_config ¶

@dataclass(frozen=True)
class ParserEngineConfig:
    """Declarative description of a model's tool-call / reasoning format.

    The engine feeds terminals from the incremental lexer into the
    transition table and emits the corresponding semantic events.
    Content tokens (text between terminals) are classified by the
    current state via ``content_events``.
    """

    name: str

    # A terminal may carry several spellings; the first spelling is the canonical one.
    terminals: Mapping[str, str | tuple[str, ...]] = field(default_factory=dict)

    token_id_terminals: dict[str, str] = field(default_factory=dict)

    transitions: dict[tuple[ParserState, str], Transition] = field(
        default_factory=dict,
    )

    content_events: dict[ParserState, EventType] = field(
        default_factory=lambda: {
            ParserState.CONTENT: EventType.TEXT_CHUNK,
            ParserState.REASONING: EventType.REASONING_CHUNK,
            ParserState.TOOL_NAME: EventType.TOOL_NAME,
            ParserState.TOOL_ARGS: EventType.ARG_VALUE_CHUNK,
        },
    )

    initial_state: ParserState = ParserState.CONTENT

    arg_converter: Callable[[str, bool], str] | None = None

    stream_arg_deltas: bool = True

    tool_args_json: bool = True

    arg_structural_chars: frozenset[str] | None = None

    # Special tokens exempt from auto-drop but not state-machine terminals.
    preserve_tokens: frozenset[str] = field(default_factory=frozenset)

    # Special tokens delimiting conversation turns in the prompt only
    # considers reasoning markers after the last boundary token.
    turn_boundary_tokens: frozenset[str] = field(default_factory=frozenset)

    # Prevents trailing-whitespace accumulation across multi-turn conversations.
    strip_trailing_reasoning_whitespace: bool = True

    # Drop content that is entirely whitespace when tool calls follow.
    drop_whitespace_only_content_before_tools: bool = True

    # .strip() content text when tool calls are present.
    strip_content_whitespace_with_tools: bool = True

    # Reject tool calls whose names are absent from the request tools.
    validate_tool_names: bool = False

    def terminal_literal(self, name: str) -> str | None:
        """Canonical spelling of terminal *name*, or ``None`` if undeclared."""
        value = self.terminals.get(name)
        if isinstance(value, tuple):
            return value[0] if value else None
        return value

    @property
    def terminal_literals(self) -> frozenset[str]:
        """Every declared spelling across all terminals."""
        return frozenset(
            lit
            for value in self.terminals.values()
            for lit in ((value,) if isinstance(value, str) else value)
        )

    @cached_property
    def terminal_defs(self):
        from vllm.parser.engine.incremental_lexer import terminals_from_literals

        return terminals_from_literals(self.terminals)

    @cached_property
    def lexer_shape(self):
        from vllm.parser.engine.incremental_lexer import LexerShape

        return LexerShape(self.terminal_defs)