Initial video AI analysis project

tests/test_vlm_client.py

@@ -0,0 +1,85 @@
+import base64
+import json
+import tempfile
+import unittest
+from pathlib import Path
+
+from video_ai_analysis_poc.vlm_client import infer_clip
+
+
+class VlmClientTests(unittest.TestCase):
+    def test_infer_clip_uses_config_prompt_url_and_data_uri_images(self):
+        with tempfile.TemporaryDirectory() as tmp:
+            output_dir = Path(tmp)
+            frame_path = output_dir / "frames" / "video-abc" / "000001.jpg"
+            frame_path.parent.mkdir(parents=True)
+            frame_path.write_bytes(b"jpg-bytes")
+            calls = []
+
+            def http_post(url, payload, timeout_seconds):
+                calls.append((url, payload, timeout_seconds))
+                return {
+                    "status": 200,
+                    "body": {
+                        "choices": [
+                            {
+                                "message": {
+                                    "content": json.dumps(
+                                        {"screen_time": "10:00:01", "events": []}
+                                    )
+                                }
+                            }
+                        ]
+                    },
+                }
+
+            result = infer_clip(
+                {
+                    "clip_id": "video-abc_c000001",
+                    "frame_times": [
+                        {
+                            "frame_path": "frames/video-abc/000001.jpg",
+                            "offset_seconds": 0.0,
+                            "timecode": "00:00:00",
+                        }
+                    ],
+                },
+                output_dir,
+                {
+                    "api_base_url": "http://localhost:8679/",
+                    "chat_completions_path": "/v1/chat/completions",
+                    "model": "memai-zhengxin-v3-20260413",
+                    "timeout_seconds": 17,
+                    "max_tokens": 256,
+                    "temperature": 0,
+                    "image_transport": "data_uri",
+                },
+                {
+                    "system": "system prompt from config",
+                    "user": "user prompt from config",
+                },
+                http_post=http_post,
+            )
+
+        self.assertEqual(result["raw_response"], '{"screen_time": "10:00:01", "events": []}')
+        self.assertEqual(len(calls), 1)
+        url, payload, timeout_seconds = calls[0]
+        self.assertEqual(url, "http://localhost:8679/v1/chat/completions")
+        self.assertEqual(timeout_seconds, 17)
+        self.assertEqual(payload["model"], "memai-zhengxin-v3-20260413")
+        self.assertEqual(payload["messages"][0]["role"], "system")
+        self.assertEqual(payload["messages"][0]["content"], "system prompt from config")
+        user_content = payload["messages"][1]["content"]
+        self.assertEqual(user_content[0], {"type": "text", "text": "user prompt from config"})
+        self.assertEqual(user_content[1]["type"], "image_url")
+        expected_data = base64.b64encode(b"jpg-bytes").decode("ascii")
+        self.assertEqual(
+            user_content[1]["image_url"]["url"],
+            f"data:image/jpeg;base64,{expected_data}",
+        )
+        self.assertEqual(result["http_status"], 200)
+        self.assertIsInstance(result["latency_ms"], int)
+
+
+if __name__ == "__main__":
+    unittest.main()