rohitg00/ai-engineering-from-scratch · error · ValueError

; ".join(errors)

Error message

; ".join(errors)

What it means

Error "; ".join(errors)" thrown in rohitg00/ai-engineering-from-scratch.

Source

Thrown at certifications/claude/lessons/12-claude-agent-sdk-and-hooks/code/main.py:219

            errors.append("computerUse network allowlist cannot be empty")
        if not isinstance(display, dict) or any(
            not isinstance(display.get(field), int) or isinstance(display[field], bool) or display[field] <= 0
            for field in ("width", "height")
        ):
            errors.append("computerUse display dimensions must be positive integers")
        if computer.get("requireFreshScreenshotBeforeAction") is not True or computer.get("requireScreenshotAfterAction") is not True:
            errors.append("computerUse requires screenshots before and after actions")
        if not isinstance(computer.get("allowedActions"), list) or "screenshot" not in computer["allowedActions"]:
            errors.append("computerUse needs an explicit action allowlist")
        if not isinstance(approval, dict) or not REQUIRED_APPROVAL_RISKS <= set(approval.get("requiredRiskClasses", [])) or "credential-entry" not in set(approval.get("deniedRiskClasses", [])):
            errors.append("computerUse needs approval and denial risk boundaries")
    return errors


def evaluate_action(policy: dict[str, Any], tool_name: str, approved: bool) -> dict[str, Any]:
    errors = validate_policy(policy)
    if errors:
        raise ValueError("; ".join(errors))
    tool = next((item for item in policy["tools"] if item["name"] == tool_name), None)
    if tool is None:
        return {"allowed": False, "reason": "unknown tool"}
    if tool.get("approvalPolicy") == "per-action":
        return {"allowed": False, "reason": "per-action policy required"}
    if tool["approvalRequired"] and not approved:
        return {"allowed": False, "reason": "approval required"}
    return {"allowed": True, "reason": "policy and approval passed"}


class ComputerUseGuard:
    """Validate model-proposed UI actions against trusted harness state."""

    def __init__(self, policy: dict[str, Any]) -> None:
        errors = validate_policy(policy)
        if errors:
            raise ValueError("; ".join(errors))
        self.config = policy["computerUse"]

View on GitHub (pinned to 39ea8a1c6d)

When it happens

Trigger: Thrown at certifications/claude/lessons/12-claude-agent-sdk-and-hooks/code/main.py:219 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of rohitg00/ai-engineering-from-scratch@39ea8a1c6d (2026-08-26). Data as JSON: /api/errors/be3c20a0d7319e49. Report an issue: GitHub.