[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_health_engine.py

@@ -1,6 +1,10 @@
+import json
+import threading
 import time
+import uuid
 
 import pytest
+import sseclient
 
 _DETECT_TIMEOUT = 60
 
@@ -39,11 +43,44 @@ class TestHealthEngineStep02LazyInit:
             f"engine already initialized (aiAvailability={before['aiAvailability']}); "
             "lazy-init test must run before any test that triggers warm_engine"
         )
+
+        cid = str(uuid.uuid4())
+        headers = {**auth_headers, "X-Channel-Id": cid}
+        done = threading.Event()
+        connected = threading.Event()
+
+        def _listen():
+            try:
+                with http_client.get(
+                    f"/detect/events/{cid}",
+                    stream=True,
+                    timeout=_DETECT_TIMEOUT + 2,
+                    headers=auth_headers,
+                ) as resp:
+                    resp.raise_for_status()
+                    connected.set()
+                    for ev in sseclient.SSEClient(resp).events():
+                        if not ev.data or not str(ev.data).strip():
+                            continue
+                        data = json.loads(ev.data)
+                        if data.get("mediaStatus") in ("AIProcessed", "Error"):
+                            break
+            except Exception:
+                pass
+            finally:
+                connected.set()
+                done.set()
+
+        th = threading.Thread(target=_listen, daemon=True)
+        th.start()
+        connected.wait(timeout=5)
+
         files = {"file": ("lazy.jpg", image_small, "image/jpeg")}
-        r = http_client.post("/detect/image", files=files, headers=auth_headers, timeout=_DETECT_TIMEOUT)
-        r.raise_for_status()
-        body = r.json()
-        assert isinstance(body, list)
+        r = http_client.post("/detect/image", files=files, headers=headers, timeout=_DETECT_TIMEOUT)
+        assert r.status_code == 202
+        done.wait(timeout=_DETECT_TIMEOUT)
+        th.join(timeout=2)
+
         after = _get_health(http_client)
         _assert_active_ai(after)
 
@@ -61,13 +98,49 @@ class TestHealthEngineStep03Warmed:
         assert data.get("errorMessage") is None
 
     def test_ft_p_15_onnx_cpu_detect(self, http_client, image_small, auth_headers):
+        cid = str(uuid.uuid4())
+        headers = {**auth_headers, "X-Channel-Id": cid}
+        all_detections = []
+        done = threading.Event()
+        connected = threading.Event()
+
+        def _listen():
+            try:
+                with http_client.get(
+                    f"/detect/events/{cid}",
+                    stream=True,
+                    timeout=_DETECT_TIMEOUT + 2,
+                    headers=auth_headers,
+                ) as resp:
+                    resp.raise_for_status()
+                    connected.set()
+                    for ev in sseclient.SSEClient(resp).events():
+                        if not ev.data or not str(ev.data).strip():
+                            continue
+                        data = json.loads(ev.data)
+                        if data.get("mediaStatus") == "AIProcessing":
+                            all_detections.extend(data.get("annotations", []))
+                        if data.get("mediaStatus") in ("AIProcessed", "Error"):
+                            break
+            except Exception:
+                pass
+            finally:
+                connected.set()
+                done.set()
+
+        th = threading.Thread(target=_listen, daemon=True)
+        th.start()
+        connected.wait(timeout=5)
+
         files = {"file": ("onnx.jpg", image_small, "image/jpeg")}
-        r = http_client.post("/detect/image", files=files, headers=auth_headers, timeout=_DETECT_TIMEOUT)
+        r = http_client.post("/detect/image", files=files, headers=headers, timeout=_DETECT_TIMEOUT)
         r.raise_for_status()
-        body = r.json()
-        assert isinstance(body, list)
-        if body:
-            d = body[0]
+        assert r.status_code == 202
+        done.wait(timeout=_DETECT_TIMEOUT)
+        th.join(timeout=2)
+
+        if all_detections:
+            d = all_detections[0]
             for k in (
                 "centerX",
                 "centerY",