Add Python image evaluation library callable via cpython bindings

Background

Image evaluation should be implemented as a clean Python library
callable directly from Go via the existing cpython bindings,
rather than as a subprocess bridge.

Proposed Approach

Create image_eval.py with a simple interface following the same
pattern as modeling/model.go:

def compare(reference_path, output_path):
# Returns dict with ssim, mse, psnr, is_grayscale, color_type

def passed(reference_path, output_path, threshold=0.80):
# Returns True if output passes quality threshold

Questions

1. Is this the right interface for the cpython bindings to consume?
2. Should this live in go-mfp or in the image evaluation repo?
3. Are there any constraints on what Python types can be returned
   via the cpython bindings?

Start by reviewing the existing cpython bindings in go-mfp and the interface pattern in modeling/model.go. Locate the image evaluation repository and determine where image_eval.py belongs, then resolve the proposed compare and passed interfaces and supported Python return types. Done means an agreed location, binding-compatible interface, and implementation plan.