Add a vision-model screenshot judge to the QA tooling

`tools/screen_designs.py judge` sends each capture together with its concept
mockup to a vision model and asks whether the capture realises the same screen and
layout intent. This covers what pixel/perceptual metrics cannot judge.

- Prompt explicitly ignores art style, fidelity, fonts, and placeholder text, since
  the references are stylised mockups.
- Verdicts are classed match / review (mismatch below --fail-confidence, default
  0.6) / diff (confident mismatch, exits non-zero) / unknown; --json, --only,
  --dry-run, --model supported.
- Reads the repo .env for OPENROUTER_API_KEY without overriding real env vars.
- Default judge model google/gemini-2.5-flash-lite; openai/gpt-4o-mini verified too.

Tests/docs
- 7 new offline tests in tools/test_screen_designs.py (request payload embeds both
  images, JSON/fenced/parts/non-JSON parsing, threshold classification, .env
  loading); 30 Python tests pass.
- Live run: 3 captures match, 3 review, 0 confident diffs.
- README, TODO section moved to DONE, MEMORY. Version 0.2.15.

tools/test_screen_designs.py

@@ -86,5 +86,97 @@ class ScreenDesignsTests(unittest.TestCase):
         self.assertTrue(any("aspect" in e for e in report["errors"]))
 
 
+class VisionJudgeTests(unittest.TestCase):
+    def setUp(self):
+        self.temp_dir = tempfile.TemporaryDirectory()
+        self.root = Path(self.temp_dir.name)
+        self.capture = self.root / "capture.png"
+        self.design = self.root / "design.png"
+        Image.new("RGB", (64, 36), (20, 30, 40)).save(self.capture)
+        Image.new("RGB", (64, 36), (200, 190, 180)).save(self.design)
+        self.screen = screen_designs.SCREENS[0]
+
+    def tearDown(self):
+        self.temp_dir.cleanup()
+
+    def test_judge_request_embeds_both_images(self):
+        body = screen_designs.build_judge_request(
+            "model-x", self.screen, self.capture, self.design)
+        self.assertEqual(body["model"], "model-x")
+        self.assertEqual(body["temperature"], 0)
+        self.assertEqual(body["response_format"], {"type": "json_object"})
+        parts = body["messages"][0]["content"]
+        self.assertEqual(parts[0]["type"], "text")
+        images = [p for p in parts if p["type"] == "image_url"]
+        self.assertEqual(len(images), 2, "design and capture are both attached")
+        for image in images:
+            self.assertTrue(image["image_url"]["url"].startswith(
+                "data:image/png;base64,"))
+        self.assertIn(self.screen["title"], parts[0]["text"])
+        self.assertIn("mockup", parts[0]["text"].lower())
+
+    def test_parse_plain_json_verdict(self):
+        payload = {"choices": [{"message": {"content":
+            '{"match": true, "confidence": 0.9, "differences": ["style"]}'}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertTrue(verdict["match"])
+        self.assertAlmostEqual(verdict["confidence"], 0.9)
+        self.assertEqual(verdict["differences"], ["style"])
+
+    def test_parse_fenced_json_verdict(self):
+        payload = {"choices": [{"message": {"content":
+            'Sure:\n```json\n{"match": false, "confidence": 0.7}\n```'}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertFalse(verdict["match"])
+        self.assertAlmostEqual(verdict["confidence"], 0.7)
+
+    def test_parse_content_parts(self):
+        payload = {"choices": [{"message": {"content": [
+            {"type": "text", "text": '{"match": true, "confidence": 0.5}'}]}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertTrue(verdict["match"])
+
+    def test_parse_non_json_is_unknown(self):
+        payload = {"choices": [{"message": {"content": "no idea"}}]}
+        verdict = screen_designs.parse_judge_response(payload)
+        self.assertIsNone(verdict["match"])
+        self.assertTrue(verdict["differences"])
+
+    def test_parse_missing_choices_is_unknown(self):
+        verdict = screen_designs.parse_judge_response({})
+        self.assertIsNone(verdict["match"])
+
+    def test_classify_thresholds(self):
+        self.assertEqual(screen_designs.classify(
+            {"match": True, "confidence": 0.1}), "match")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.9}), "bad")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.3}), "review")
+        self.assertEqual(screen_designs.classify(
+            {"match": None, "confidence": 0.0}), "unknown")
+        self.assertEqual(screen_designs.classify(
+            {"match": False, "confidence": 0.55}, threshold=0.5), "bad")
+
+    def test_env_file_does_not_override_existing(self):
+        env_path = self.root / ".env"
+        env_path.write_text('OPENROUTER_API_KEY=from-file\nOTHER=1\n',
+                            encoding="utf-8")
+        import os
+        old = os.environ.get("OPENROUTER_API_KEY")
+        os.environ["OPENROUTER_API_KEY"] = "from-env"
+        os.environ.pop("OTHER", None)
+        try:
+            screen_designs._load_env_file(env_path)
+            self.assertEqual(os.environ["OPENROUTER_API_KEY"], "from-env")
+            self.assertEqual(os.environ.get("OTHER"), "1")
+        finally:
+            if old is None:
+                os.environ.pop("OPENROUTER_API_KEY", None)
+            else:
+                os.environ["OPENROUTER_API_KEY"] = old
+            os.environ.pop("OTHER", None)
+
+
 if __name__ == "__main__":
     unittest.main()