EVA App v2.3.0 (Dec 12, 2025)

Multiple scenario support: Support for common scenarios that can be applied across multiple cameras and custom scenarios optimized for individual cameras has been added. Each camera can apply both scenarios simultaneously for more precise settings.
Detection Zone Settings: Moving away from full-screen detection, users can now freely define specific zones and apply custom scenarios to those zones.
Maintain monitoring state: When Eva App restarts, the previous monitoring state is automatically restored.
New camera settings: When connecting via RTSP, you can see read-only settings such as brightness, contrast, saturation, hue, gain, exposure, convert_rgb, white balance temperature, and rectification.
Image Guided Detection: Image-based detection has been enhanced. Previously complex image management processes have been streamlined to enable intuitive image selection, labeling, registration, modification and deletion. Additionally, embedding vector data saved through Image Guided Detection can now be reused even after Eva App restart.
UX/UI Improvements
A slider bar UI has been applied to the detection sensitivity (target threshold) settings.
UI Terminology Updates: For clarity, terminology has been updated to:
alert interval → detection interval
feedback_similarity_threshold → false detection cutoff
threshold → Detection Sensitivity

RTSP Streaming Memory Optimization: Optimized browser memory usage by leveraging Improved blob handling and JavaScript GC algorithms.
Backend → Agent Metadata Structure Improvement: LLM and Visual performance have been improved by refining the metadata structure transmitted to the Agent.

Fixed an issue where the “Sending..” button in the chat window did not disappear: If a type conversion error occurs while processing the Agent response, an appropriate error message is now displayed.