langchain-ai/deepagents · error · ValueError

ask_user requires at least one question

Error message

ask_user requires at least one question

What it means

`_validate_questions` raises ValueError when the ask_user call receives an empty question list. The ask_user tool exists to collect answers, so at least one question must be submitted.

Source

Thrown at libs/code/deepagents_code/_ask_user_types.py:368

    Per-question rules live on `ValidatedQuestion`; this covers the one rule
    about the list itself. Attached both to the tool's `questions` parameter
    and to `AskUserRequest.questions`, so the client re-validation boundary
    rejects an empty list too — `AskUserMenu([])` would otherwise build a
    titled prompt with no question widgets and nothing focusable.

    Args:
        questions: The parsed `questions` argument to check.

    Returns:
        The same `questions`, unchanged.

    Raises:
        ValueError: If the list is empty.
    """
    if not questions:
        msg = "ask_user requires at least one question"
        raise ValueError(msg)
    return questions


class AskUserRequest(TypedDict):
    """Request payload sent via interrupt when asking the user questions."""

    type: Literal["ask_user"]
    """Discriminator tag, always `'ask_user'`."""

    questions: Annotated[list[ValidatedQuestion], AfterValidator(_validate_questions)]
    """Questions to present to the user.

    `ValidatedQuestion` rather than `Question`, and carrying
    `_validate_questions`, so every rule the tool applies also applies where
    `tui.textual_adapter` re-validates this payload. A choice question with no
    `choices` would otherwise reach the client and degrade to a text box, and
    an empty list would render a prompt with no questions in it.
    """

View on GitHub (pinned to a1af029e6e)

Solutions

1. Always pass at least one validated question to ask_user
2. If questions are built dynamically, skip the ask_user call entirely when the list is empty instead of sending it
3. Check the model's tool-call arguments for an omitted/empty `questions` array and reinforce the tool description
4. Guard the call site with a length check before invoking the tool

Example fix

# before
ask_user(questions=[])
# after
questions = build_questions(context)
if questions:
    ask_user(questions=questions)
else:
    proceed_without_input()

if not questions:
    raise ValueError("ask_user requires at least one question")

def has_questions(questions: list) -> bool:
    return len(questions) > 0

try:
    ask_user(questions=questions)
except ValueError as exc:
    if "requires at least one question" in str(exc):
        # skip asking and proceed with defaults
        ...
    else:
        raise

When it happens

Trigger: An agent invoking `ask_user` with `questions: []`, or code building an `AskUserRequest` from a dynamically filtered list that ended up empty — raised at libs/code/deepagents_code/_ask_user_types.py:368.

Common situations: An LLM emitting an empty questions array in the tool call; logic that filters questions by some condition and passes the (possibly empty) remainder; template code with a loop that appends nothing before submitting.

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
• {question_type} question {question_text!r} must not define '
• 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/ce18a051b498a08a. Report an issue: GitHub.