[AZ-180] Refactor detection event handling and improve SSE support

- Updated the detection image endpoint to require a channel ID for event streaming.
- Introduced a new endpoint for streaming detection events, allowing clients to receive real-time updates.
- Enhanced the internal buffering mechanism for detection events to manage multiple channels.
- Refactored the inference module to support the new event handling structure.

Made-with: Cursor

e2e/tests/test_resource_limits.py

@@ -8,28 +8,16 @@ import pytest
 @pytest.mark.slow
 @pytest.mark.timeout(120)
 def test_nft_res_lim_03_max_detections_per_frame(
-    warm_engine, http_client, image_dense, auth_headers
+    warm_engine, image_detect, image_dense
 ):
-    r = http_client.post(
-        "/detect/image",
-        files={"file": ("img.jpg", image_dense, "image/jpeg")},
-        headers=auth_headers,
-        timeout=120,
-    )
-    assert r.status_code == 200
-    body = r.json()
-    assert isinstance(body, list)
-    assert len(body) <= 300
+    detections, _ = image_detect(image_dense, "img.jpg", timeout=120)
+    assert isinstance(detections, list)
+    assert len(detections) <= 300
 
 
 @pytest.mark.slow
-def test_nft_res_lim_04_log_file_rotation(warm_engine, http_client, image_small, auth_headers):
-    http_client.post(
-        "/detect/image",
-        files={"file": ("img.jpg", image_small, "image/jpeg")},
-        headers=auth_headers,
-        timeout=60,
-    )
+def test_nft_res_lim_04_log_file_rotation(warm_engine, image_detect, image_small):
+    image_detect(image_small, "img.jpg", timeout=60)
     candidates = [
         Path(__file__).resolve().parent.parent / "logs",
         Path("/app/Logs"),