[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

src/engines/onnx_engine.pyx

@@ -23,7 +23,7 @@ cdef class OnnxEngine(InferenceEngine):
         self.model_inputs = self.session.get_inputs()
         self.input_name = self.model_inputs[0].name
         self.input_shape = self.model_inputs[0].shape
-        if self.input_shape[0] not in (-1, None, "N"):
+        if isinstance(self.input_shape[0], int) and self.input_shape[0] > 0:
             self.max_batch_size = self.input_shape[0]
         constants_inf.log(f'AI detection model input: {self.model_inputs} {self.input_shape}')
         model_meta = self.session.get_modelmeta()