📄️ System Design
The FirstBreath Vision System solves a critical scalability problem: Python threads cannot efficiently handle concurrent heavy AI inference loops due to the GIL (Global Interpreter Lock).
📄️ Camera Manager Service
Role: The Producer (I/O Bound)
📄️ Batch Inference Service
Role: The Consumer (Compute Bound / GPU)
📄️ Redis Worker Service
Role: The Logic Processor (CPU Bound)
📄️ Resilience & Crash Handling
The FirstBreath Vision system is designed to be resilient to network failures, camera crashes, and container restarts. This page details the robust crash handling and auto-recovery mechanisms implemented in the camera-manager service.
📄️ Database Evolution
The Camera Manager service operates with a high degree of autonomy, including the management of its own database schema. This page details the Declarative Migration System used to ensure the database structure is always aligned with the code.