langchain-ai/deepagents · error · ValueError

{question_type} question {question_text!r} must not define '

Error message

{question_type} question {question_text!r} must not define 'choices'

What it means

The counterpart of error 17: `_validate_question` raises ValueError when a NON-choice question type (e.g. free text) defines a `choices` list. Only choice-type questions may carry choices; extra ones on free-text questions are rejected.

Source

Thrown at libs/code/deepagents_code/_ask_user_types.py:265

    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(
            description=(
                "Question type. 'text' for free-form input, 'multiple_choice' for "
                "picking exactly one predefined option, 'multi_select' for picking "

View on GitHub (pinned to a1af029e6e)

Solutions

1. Remove the `choices` key from free-text questions
2. Verify `question_type` is spelled correctly so choice questions are recognized as choice types
3. If the agent generates the question dict, constrain the schema/examples so choices only appear for choice types
4. Move the option list into a `multiple_choice` or `multi_select` question instead of decorating a text question

Example fix

// before
{"question_type": "text", "text": "Describe the bug?", "choices": [{"value": "a"}]}
// after
{"question_type": "text", "text": "Describe the bug?"}

if q["question_type"] not in CHOICE_QUESTION_TYPES and q.get("choices"):
    raise ValueError(f"{q['question_type']} question must not define 'choices'")

def choices_match_type(q: dict) -> bool:
    is_choice = q.get("question_type") in CHOICE_QUESTION_TYPES
    return is_choice == bool(q.get("choices"))

try:
    ask_user(questions=questions)
except ValueError as exc:
    if "must not define 'choices'" in str(exc):
        questions = [{k: v for k, v in q.items() if k != "choices"} for q in questions]
        ask_user(questions=questions)
    else:
        raise

When it happens

Trigger: An ask_user question whose `question_type` is not in CHOICE_QUESTION_TYPES but whose dict includes a non-empty `choices` key — raised at libs/code/deepagents_code/_ask_user_types.py:265.

Common situations: An LLM adding a `choices` field to every question regardless of type; reusing one question-building helper that always attaches choices; a `question_type` typo that makes a choice question classify as free text.

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

• question text must not be blank
• choice has a blank 'value': {choice!r}
• {question_type} question {question_text!r} requires a non-em
• 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/faba10e164b6fd38. Report an issue: GitHub.