Function feature_create_bulk

mcp_server/feature_mcp.py:526–626

Create multiple features in a single operation. Features are assigned sequential priorities based on their order. All features start with passes=false. This is typically used by the initializer agent to set up the initial feature list from the app specification. Args:

(
    features: Annotated[list[dict], Field(description="List of features to create, each with category, name, description, and steps")]
)

@mcp.tool()
def feature_create_bulk(
    features: Annotated[list[dict], Field(description="List of features to create, each with category, name, description, and steps")]
) -> str:
    """Create multiple features in a single operation.

    Features are assigned sequential priorities based on their order.
    All features start with passes=false.

    This is typically used by the initializer agent to set up the initial
    feature list from the app specification.

    Args:
        features: List of features to create, each with:
            - category (str): Feature category
            - name (str): Feature name
            - description (str): Detailed description
            - steps (list[str]): Implementation/test steps
            - depends_on_indices (list[int], optional): Array indices (0-based) of
              features in THIS batch that this feature depends on. Use this instead
              of 'dependencies' since IDs aren't known until after creation.
              Example: [0, 2] means this feature depends on features at index 0 and 2.

    Returns:
        JSON with: created (int) - number of features created, with_dependencies (int)
    """
    try:
        # Use atomic transaction for bulk inserts to prevent priority conflicts
        with atomic_transaction(_session_maker) as session:
            # Get the starting priority atomically within the transaction
            result = session.execute(text("""
                SELECT COALESCE(MAX(priority), 0) FROM features
            """)).fetchone()
            start_priority = (result[0] or 0) + 1

            # First pass: validate all features and their index-based dependencies
            for i, feature_data in enumerate(features):
                # Validate required fields
                if not all(key in feature_data for key in ["category", "name", "description", "steps"]):
                    return json.dumps({
                        "error": f"Feature at index {i} missing required fields (category, name, description, steps)"
                    })

                # Validate depends_on_indices
                indices = feature_data.get("depends_on_indices", [])
                if indices:
                    # Check max dependencies
                    if len(indices) > MAX_DEPENDENCIES_PER_FEATURE:
                        return json.dumps({
                            "error": f"Feature at index {i} has {len(indices)} dependencies, max is {MAX_DEPENDENCIES_PER_FEATURE}"
                        })
                    # Check for duplicates
                    if len(indices) != len(set(indices)):
                        return json.dumps({
                            "error": f"Feature at index {i} has duplicate dependencies"
                        })
                    # Check for forward references (can only depend on earlier features)
                    for idx in indices:
                        if not isinstance(idx, int) or idx < 0: