Organize tools and move Python tests into tools/tests

tools/tests/test_openrouter_judge.py

@@ -0,0 +1,89 @@
+import os
+import unittest
+from unittest import mock
+
+import openrouter_judge as oj
+
+
+def _model(model_id, prompt, completion, *, image=True, response_format=True, batch=False):
+    return {
+        "id": model_id,
+        "architecture": {
+            "input_modalities": ["text", "image"] if image else ["text"],
+            "output_modalities": ["text"],
+        },
+        "supported_parameters": ["response_format"] if response_format else ["temperature"],
+        "pricing": {"prompt": str(prompt), "completion": str(completion)},
+    }
+
+
+class ModelSelectionTests(unittest.TestCase):
+    def test_candidates_are_image_json_models_sorted_by_price(self):
+        catalog = [
+            _model("expensive/model", 0.10, 0.40),
+            _model("cheap/model", 0.01, 0.02),
+            _model("text-only", 0.001, 0.001, image=False),
+            _model("no-json", 0.001, 0.001, response_format=False),
+            _model("batch/model:batch", 0.0001, 0.0001),
+        ]
+        self.assertEqual(oj.vision_candidates(catalog), ["cheap/model", "expensive/model"])
+
+    def test_explicit_model_wins_over_auto_and_env(self):
+        with mock.patch.dict(os.environ, {"GIG_LINE_JUDGE_MODEL": "env/model"}):
+            self.assertEqual(oj.resolve_models("explicit/model", catalog=[]),
+                             ["explicit/model"])
+
+    def test_auto_uses_env_override(self):
+        with mock.patch.dict(os.environ, {"GIG_LINE_JUDGE_MODEL": "env/model"}):
+            self.assertEqual(oj.resolve_models("auto", catalog=[]), ["env/model"])
+
+    def test_auto_uses_catalog_and_falls_back_offline(self):
+        catalog = [_model("cheap/model", 0.01, 0.02)]
+        self.assertEqual(oj.resolve_models("auto", catalog=catalog), ["cheap/model"])
+        self.assertEqual(oj.resolve_models("auto", catalog=[]), oj.FALLBACK_MODELS[:6])
+
+
+class FallbackTests(unittest.TestCase):
+    def test_fallback_switches_model_after_provider_error(self):
+        seen = []
+
+        def call(body):
+            seen.append(body["model"])
+            if body["model"] == "bad/model":
+                raise ValueError("OpenRouter HTTP 400: provider rejected image")
+            return {"ok": True}
+
+        model, payload = oj.call_with_fallback(
+            ["bad/model", "good/model"], lambda m: {"model": m}, call, attempts=1)
+        self.assertEqual(model, "good/model")
+        self.assertEqual(payload, {"ok": True})
+        self.assertEqual(seen, ["bad/model", "good/model"])
+
+    def test_auth_error_does_not_try_another_model(self):
+        seen = []
+
+        def call(body):
+            seen.append(body["model"])
+            raise ValueError("OpenRouter HTTP 401: API key not valid")
+
+        with self.assertRaises(ValueError):
+            oj.call_with_fallback(["one", "two"], lambda m: {"model": m}, call)
+        self.assertEqual(seen, ["one"])
+
+    def test_transient_error_retries_same_model(self):
+        seen = []
+
+        def call(body):
+            seen.append(body["model"])
+            if len(seen) == 1:
+                raise ValueError("OpenRouter HTTP 500")
+            return {"ok": True}
+
+        model, _ = oj.call_with_fallback(
+            ["one"], lambda m: {"model": m}, call, attempts=2)
+        self.assertEqual(model, "one")
+        self.assertEqual(seen, ["one", "one"])
+
+
+if __name__ == "__main__":
+    unittest.main()