docs/architecture.mmd

flowchart TD
    subgraph Input ["1. Visual Input"]
        Image["👁️ Image / Screen Pixels"]
    end

    subgraph VisionEncoder ["2. 7B Vision Encoder"]
        Encoder["📷 Vision Encoder\n(Outputs 3,584-dim Vision Tokens)"]
    end

    subgraph ChiasmBridge ["3. ChiasmBridge (libchiasm.so)"]
        Bridge["🌉 Isomorphic Subspace Projection\n(CUDA VRAM Translation 3,584 -> 5,120)"]
    end

    subgraph TargetLLM ["4. Target Cognitive LLM"]
        LLM["🐺 24B LLM (kalos:24b)\n(Receives 5,120-dim Visual Tokens)"]
    end

    Image --> Encoder
    Encoder -->|3,584-dim Tokens| Bridge
    Bridge -->|5,120-dim Tokens| LLM
    LLM --> Response["💬 Multimodal Visual Perception & Response"]