langchain-ai/langchain · error · ValueError

Expected is_optional to be a boolean. Got: {is_optional}

Error message

Expected is_optional to be a boolean. Got: {is_optional}

What it means

Raised in _create_template_from_message_type when a structured placeholder spec ["{name}", is_optional] is given but the second element is not a bool. LangChain explicitly type-checks the optional flag because truthy values like 1 or "yes" would silently behave as positional/keyword confusion later.

Source

Thrown at libs/core/langchain_core/prompts/chat.py:1395

                )
                raise ValueError(msg)
            var_name = template[1:-1]
            message = MessagesPlaceholder(variable_name=var_name, optional=True)
        else:
            try:
                var_name_wrapped, is_optional = template
            except ValueError as e:
                msg = (
                    "Unexpected arguments for placeholder message type."
                    " Expected either a single string variable name"
                    " or a list of [variable_name: str, is_optional: bool]."
                    f" Got: {template}"
                )
                raise ValueError(msg) from e

            if not isinstance(is_optional, bool):
                msg = f"Expected is_optional to be a boolean. Got: {is_optional}"
                raise ValueError(msg)  # noqa: TRY004

            if not isinstance(var_name_wrapped, str):
                msg = f"Expected variable name to be a string. Got: {var_name_wrapped}"
                raise ValueError(msg)  # noqa: TRY004
            if var_name_wrapped[0] != "{" or var_name_wrapped[-1] != "}":
                msg = (
                    f"Invalid placeholder template: {var_name_wrapped}."
                    " Expected a variable name surrounded by curly braces."
                )
                raise ValueError(msg)
            var_name = var_name_wrapped[1:-1]

            message = MessagesPlaceholder(variable_name=var_name, optional=is_optional)
    else:
        msg = (
            f"Unexpected message type: {message_type}. Use one of 'human',"
            f" 'user', 'ai', 'assistant', or 'system'."
        )

View on GitHub (pinned to e32fa9a52e)

Solutions

1. Coerce the flag to a real Python bool: bool(value) or fix the config to emit true/false.
2. When loading prompts from JSON, normalize with `spec[1] = bool(spec[1])` before calling from_messages.
3. Prefer the plain string form ("placeholder", "{name}") if you don't need to control optionality.

Example fix

# before
ChatPromptTemplate.from_messages([("placeholder", ["{history}", "true"])])

# after
ChatPromptTemplate.from_messages([("placeholder", ["{history}", True])])

def normalize_placeholder_spec(spec):
    name, optional = spec
    if not isinstance(optional, bool):
        spec[1] = bool(optional)
    return spec

def is_bool_optional(spec) -> bool:
    return len(spec) == 2 and isinstance(spec[1], bool)

When it happens

Trigger: `("placeholder", ["{history}", 1])`, `("placeholder", ["{history}", "true"])`, or `("placeholder", ["{history}", None])` inside from_messages.

Common situations: JSON/YAML-config-driven prompt definitions where booleans arrive as strings or 0/1 integers after deserialization; passing a numpy bool or an Optional flag from a config schema.

Related errors

• Expected variable name to be a string. Got: {var_name_wrappe
• Invalid placeholder template: {template}. Expected a variabl
• Unexpected arguments for placeholder message type. Expected
• Invalid placeholder template: {var_name_wrapped}. Expected a
• Unsupported message type: {type(message)}

AI-assisted analysis of langchain-ai/langchain@e32fa9a52e (2026-08-14). Data as JSON: /api/errors/f8603ad1cc541d05. Report an issue: GitHub.