BerriAI/litellm · error · ValueError

Missing required parameter: display_width_px or display_heig

Error message

Missing required parameter: display_width_px or display_height_px

What it means

For computer-use tools, LiteLLM reads display_width_px and display_height_px from tool['function']['parameters'] and requires both to be non-None. If either key is missing or explicitly null, this ValueError is raised during request transformation, before the API call.

Source

Thrown at litellm/llms/anthropic/chat/transformation.py:695

                input_schema=input_anthropic_schema,
                type="custom",
            )

            _description: Final = tool["function"].get("description")
            if _description is not None:
                _tool["description"] = _description

            returned_tool = _tool

        elif tool["type"].startswith("computer_"):
            ## check if all required 'display_' params are given
            if "parameters" not in tool["function"]:
                raise ValueError("Missing required parameter: parameters")

            _display_width_px: Final[int | None] = tool["function"]["parameters"].get("display_width_px")
            _display_height_px: Final[int | None] = tool["function"]["parameters"].get("display_height_px")
            if _display_width_px is None or _display_height_px is None:
                raise ValueError("Missing required parameter: display_width_px or display_height_px")

            _computer_tool: Final = AnthropicComputerTool(
                type=tool["type"],
                name=tool["function"].get("name", "computer"),
                display_width_px=_display_width_px,
                display_height_px=_display_height_px,
            )

            _display_number: Final = tool["function"]["parameters"].get("display_number")
            if _display_number is not None:
                _computer_tool["display_number"] = _display_number

            returned_tool = _computer_tool
        elif any(tool["type"].startswith(t) for t in ANTHROPIC_HOSTED_TOOLS):
            function_name_obj: Final = tool.get("name", tool.get("function", {}).get("name"))
            if function_name_obj is None or not isinstance(function_name_obj, str):
                raise ValueError("Missing required parameter: name")
            function_name: Final = function_name_obj

View on GitHub (pinned to 6c2dcb801b)

Solutions

1. Set both display_width_px and display_height_px to integers in the parameters dict.
2. Derive them from the actual environment/screenshot (e.g. image.size) rather than hardcoding when automating a real screen.
3. Add a pre-flight assertion for computer_ tools so the failure is caught at build time.
4. Note display_number is optional — only the two dimensions are mandatory.

Example fix

# before
"parameters": {"display_number": 0}

# after
"parameters": {
    "display_width_px": 1024,
    "display_height_px": 768,
    "display_number": 0,  # optional
}

def validate_display_dims(tools):
    for t in tools:
        if str(t.get("type", "")).startswith("computer_"):
            p = t["function"]["parameters"]
            for k in ("display_width_px", "display_height_px"):
                if not isinstance(p.get(k), int):
                    raise ValueError(f"{t['type']}: {k} must be a set integer")
    return tools

def has_display_dims(tool) -> bool:
    p = tool.get("function", {}).get("parameters", {})
    return isinstance(p.get("display_width_px"), int) and isinstance(p.get("display_height_px"), int)

When it happens

Trigger: A computer_ tool whose parameters dict exists but lacks display_width_px/display_height_px, or sets one to None; e.g. {'parameters': {'display_number': 0}} only.

Common situations: Copy-pasted computer-use snippets from older Anthropic examples that did not include dimensions; dynamically built parameter dicts where the dimension keys are conditionally omitted; screenshots/vision code that forgot to pass the actual screen size.

Related errors

• Missing required parameter: parameters
• Missing required parameter: name
• Tool search tool must have a valid name
• Advisor tool must have a valid model
• Unsupported tool type: {tool['type']}

AI-assisted analysis of BerriAI/litellm@6c2dcb801b (2026-08-15). Data as JSON: /api/errors/b3376f08e0f4a8bb. Report an issue: GitHub.