calesthio/OpenMontage · error · ValueError

prompt is required

Error message

prompt is required

What it means

Raised by the static `_prompt(inputs)` helper: it reads `inputs['prompt']`, stringifies, strips whitespace, and if the result is empty the call is rejected before any paid Kling request. Kling's generation endpoints require a non-empty text prompt, so this is a deliberate pre-flight check to avoid spending credits on a call the API would reject anyway.

Source

Thrown at tools/video/kling_official_video.py:694

            "video_urls",
        ):
            count += len(inputs.get(key) or [])
        for key in (
            "reference_image_url",
            "reference_image_path",
            "reference_tail_image_url",
            "reference_tail_image_path",
            "reference_video_url",
        ):
            if inputs.get(key):
                count += 1
        return count

    @staticmethod
    def _prompt(inputs: dict[str, Any]) -> str:
        prompt = str(inputs.get("prompt") or "").strip()
        if not prompt:
            raise ValueError("prompt is required")
        return prompt

    @staticmethod
    def _first_output_url(outputs: list[dict[str, Any]]) -> str:
        for item in outputs:
            try:
                return KlingOfficialVideo._output_url(item)
            except ValueError:
                continue
        raise ValueError(f"Kling video response contained no downloadable URL: {outputs}")

View on GitHub (pinned to 95e1c3d0ab)

Solutions

1. Set a non-empty `prompt` string in the inputs dict
2. If the prompt comes from a variable, add a check that it is non-empty before invoking the tool
3. Verify the exact key name is `prompt` per the tool's schema — not `text`, `description`, or `negative_prompt`

Example fix

// before
inputs = {"model": "kling-v2-master", "duration": 5}
// after
inputs = {"model": "kling-v2-master", "duration": 5, "prompt": "A cinematic drone shot over foggy mountains at dawn"}

prompt = str(inputs.get("prompt") or "").strip()
if not prompt:
    raise ValueError("prompt is required before calling kling_official_video")

def has_prompt(inputs: dict) -> bool:
    return bool(str(inputs.get("prompt") or "").strip())

try:
    result = kling.execute(inputs)
except ValueError as e:
    if "prompt is required" in str(e):
        raise RuntimeError(f"upstream produced empty prompt for inputs keys: {sorted(inputs)}") from e
    raise

When it happens

Trigger: Calling kling_official_video with `prompt` omitted, set to `None`, set to `""`, or containing only whitespace; passing the prompt under a wrong key (e.g. `text` or `description`) so `inputs.get('prompt')` returns nothing.

Common situations: Agents composing inputs programmatically where an upstream variable was never filled; prompt-key typos; image-to-video flows where the developer assumed the reference image alone suffices and no prompt is needed (this tool still requires one).

Related errors

• prompt is required
• video_list items must be objects
• prompt is required for text_to_video
• prompt references <<<image_{max(existing_numbers)}>>> but on
• Image Omni prompt placeholders must start at <<<image_1>>>

AI-assisted analysis of calesthio/OpenMontage@95e1c3d0ab (2026-08-15). Data as JSON: /api/errors/6d09a208aed53c5f. Report an issue: GitHub.