langchain-ai/deepagents · error · ValueError

{question_type} question {question_text!r} requires a non-em

Error message

{question_type} question {question_text!r} requires a non-empty 'choices' list

What it means

`_validate_question` raises ValueError when a choice-type question (multiple choice / multi-select) has an empty or missing `choices` list. A choice question without options cannot be rendered, so a non-empty choices list is required.

Source

Thrown at libs/code/deepagents_code/_ask_user_types.py:262

    Args:
        question: The parsed `Question` to check.

    Returns:
        The same `question`, unchanged.

    Raises:
        ValueError: If the question violates one of the rules above.
    """
    question_type = question["type"]
    question_text = question["question"]
    choices = question.get("choices")
    if question_type in CHOICE_QUESTION_TYPES:
        if not choices:
            msg = (
                f"{question_type} question {question_text!r} requires a "
                f"non-empty 'choices' list"
            )
            raise ValueError(msg)
    elif choices:
        msg = f"{question_type} question {question_text!r} must not define 'choices'"
        raise ValueError(msg)
    return question


class Question(TypedDict):
    """A question to ask the user."""

    question: Annotated[
        str,
        AfterValidator(_validate_question_text),
        Field(description="The question text to display.", min_length=1),
    ]

    type: Annotated[
        QuestionType,
        Field(

View on GitHub (pinned to a1af029e6e)

Solutions

1. Provide at least one (validated) choice for every choice-type question
2. If options are computed at runtime, fall back to a free-text question type when the list is empty
3. Check the model's tool-call arguments — an omitted `choices` key means the schema wasn't followed; tighten the tool description
4. Validate upstream data before constructing the question to avoid runtime ValueError

Example fix

# before
{"question_type": "multiple_choice", "text": "Pick a DB?", "choices": []}
# after
{"question_type": "multiple_choice", "text": "Pick a DB?", "choices": [{"value": "postgres"}, {"value": "mysql"}]}

if q["question_type"] in CHOICE_QUESTION_TYPES and not q.get("choices"):
    raise ValueError(f"{q['question_type']} question requires non-empty 'choices'")

def has_choices(q: dict) -> bool:
    return not (q.get("question_type") in CHOICE_QUESTION_TYPES and not q.get("choices"))

try:
    ask_user(questions=questions)
except ValueError as exc:
    if "requires a non-empty 'choices' list" in str(exc):
        # regenerate the question with options or downgrade to free-text
        ...
    else:
        raise

When it happens

Trigger: An ask_user call with `question_type` in CHOICE_QUESTION_TYPES and `choices` set to `[]`, `None`, or omitted — raised at libs/code/deepagents_code/_ask_user_types.py:262.

Common situations: An LLM omitting the choices array in a tool call; code building questions from a dynamic option list that ended up empty (e.g. no available environments); template scaffolding with a placeholder empty list never filled.

Understand the failure class

Background: Schema validation failed / invalid input schema: payload rejected because its shape doesn't match the expected schema — this error's family across 28 libraries.

Related errors

• choice has a blank 'value': {choice!r}
• question text must not be blank
• {question_type} question {question_text!r} must not define '
• ask_user requires at least one question
• Could not parse embedded resource block. Block expected eith

AI-assisted analysis of langchain-ai/deepagents@a1af029e6e (2026-08-29). Data as JSON: /api/errors/8b659f55675a058c. Report an issue: GitHub.