infra_configure
Adjust runtime server settings like model selection, thinking depth, and temperature to optimize video research and analysis performance.
Instructions
Reconfigure the server at runtime — preset, model, thinking level, or temperature.
Changes take effect immediately for all subsequent tool calls.
Args: preset: Named model preset — resolves to a default_model + flash_model pair. model: Gemini model ID (takes precedence over preset's default_model). thinking_level: Thinking depth — "minimal", "low", "medium", or "high". temperature: Sampling temperature (0.0–2.0).
Returns: Dict with current_config, active_preset, and available_presets.
Input Schema
TableJSON Schema
| Name | Required | Description | Default |
|---|---|---|---|
| preset | No | Named model preset: "best" (3.1 Pro), "stable" (3 Pro), or "budget" (3 Flash) | |
| model | No | Gemini model ID override (takes precedence over preset) | |
| thinking_level | No | ||
| temperature | No | Sampling temperature | |
| auth_token | No | Optional infra auth token (required when INFRA_ADMIN_TOKEN is configured) |