Generate an architecture diagram from a text prompt.

Args: prompt: Description of what to generate diagram_type: Type of diagram (architecture|data_flow|component|sequence|integration|infographic|c4_container|exec_infographic|generic) theme: Background theme (light|dark). Default: light — the portfolio-wide default (rep / marketing / CISO-facing output is the common case). Pass theme="dark" for a dark charcoal canvas. This single switch governs the background; you do NOT need to describe a background color in prompt. provider: LEAVE AS DEFAULT ("auto"). The server is responsible for picking the right provider and model for the diagram type — callers should describe what to draw and let the server decide how. The current default chain is OpenAI gpt-image-2 (primary) → Gemini (fallback). Override only if you have a specific provider/model comparison need. model: LEAVE UNSET unless you're explicitly benchmarking models. Server picks the right model for the chosen provider. resolution: Output resolution (1K|2K|4K) aspect_ratio: Output aspect ratio (16:9|1:1|9:16|4:3) style_reference: Style name or path to reference image output_path: Where to save the image (auto-generated if not provided) temperature: Generation creativity (0.0 to 2.0) quality: Output quality tier for OpenAI gpt-image-2 / gpt-image-1-mini (low|medium|high|auto). Cost scales dramatically: at 1536x1024 on gpt-image-2, low=$0.005, medium=$0.041, high=$0.165. Ignored by Gemini and legacy gpt-image-1.5. Default: auto.

Edit an existing diagram based on instructions.

Args: image_path: Path to the existing diagram image prompt: Edit instructions provider: Image generation provider (gemini|openai) resolution: Output resolution (auto-detect if not specified) reference_images: Additional reference image paths output_path: Where to save the result

List all available diagram templates with descriptions.

List configured providers with status, models, and health information.

List all available style reference images.

Get usage and cost report for diagram generations.

Args: days: Number of days to report on (default: 30) group_by: Group results by 'provider', 'diagram_type', or 'day'

Configure an API key for a provider (sets environment variable for current session).

Args: provider: Provider name (gemini|openai) api_key: The API key to set