Refactor inference engine and task management: Remove obsolete inference engine and ONNX engine files, update inference processing to utilize batch handling, and enhance task management structure in documentation. Adjust paths for task specifications to align with new directory organization.

e2e/tests/test_async_sse.py

@@ -1,30 +1,42 @@
 import json
+import os
 import threading
 import time
 import uuid
 
 import pytest
 
+_MEDIA = os.environ.get("MEDIA_DIR", "/media")
 
-def _ai_config_video(mock_loader_url: str) -> dict:
-    base = mock_loader_url.rstrip("/")
+
+def _ai_config_video() -> dict:
     return {
         "probability_threshold": 0.25,
         "tracking_intersection_threshold": 0.6,
         "altitude": 400,
         "focal_length": 24,
         "sensor_width": 23.5,
-        "paths": [f"{base}/load/video_short01.mp4"],
+        "paths": [f"{_MEDIA}/video_short01.mp4"],
         "frame_period_recognition": 4,
         "frame_recognition_seconds": 2,
     }
 
 
+def _ai_config_image() -> dict:
+    return {
+        "probability_threshold": 0.25,
+        "altitude": 400,
+        "focal_length": 24,
+        "sensor_width": 23.5,
+        "paths": [f"{_MEDIA}/image_small.jpg"],
+    }
+
+
 def test_ft_p08_immediate_async_response(
-    warm_engine, http_client, jwt_token, mock_loader_url
+    warm_engine, http_client, jwt_token
 ):
     media_id = f"async-{uuid.uuid4().hex}"
-    body = _ai_config_video(mock_loader_url)
+    body = _ai_config_image()
     headers = {"Authorization": f"Bearer {jwt_token}"}
     t0 = time.monotonic()
     r = http_client.post(f"/detect/{media_id}", json=body, headers=headers)
@@ -37,10 +49,10 @@ def test_ft_p08_immediate_async_response(
 @pytest.mark.slow
 @pytest.mark.timeout(120)
 def test_ft_p09_sse_event_delivery(
-    warm_engine, http_client, jwt_token, mock_loader_url, sse_client_factory
+    warm_engine, http_client, jwt_token, sse_client_factory
 ):
     media_id = f"sse-{uuid.uuid4().hex}"
-    body = _ai_config_video(mock_loader_url)
+    body = _ai_config_video()
     headers = {"Authorization": f"Bearer {jwt_token}"}
     collected: list[dict] = []
     thread_exc: list[BaseException] = []
@@ -76,17 +88,17 @@ def test_ft_p09_sse_event_delivery(
     assert ok, "SSE listener did not finish within 120s"
     th.join(timeout=5)
     assert not thread_exc, thread_exc
-    assert any(e.get("mediaStatus") == "AIProcessing" for e in collected)
+    assert collected, "no SSE events received"
     final = collected[-1]
     assert final.get("mediaStatus") == "AIProcessed"
     assert final.get("mediaPercent") == 100
 
 
 def test_ft_n04_duplicate_media_id_409(
-    warm_engine, http_client, jwt_token, mock_loader_url
+    warm_engine, http_client, jwt_token
 ):
     media_id = "dup-test"
-    body = _ai_config_video(mock_loader_url)
+    body = _ai_config_video()
     headers = {"Authorization": f"Bearer {jwt_token}"}
     r1 = http_client.post(f"/detect/{media_id}", json=body, headers=headers)
     assert r1.status_code == 200