Model Configuration
Task-level model lists, selector controls, and token guardrails in the desktop client.
Vibe Manager treats model selection as a task-level decision. Each workflow ships with a default model and an allowed list, and the desktop client exposes these options through a toggle that prevents sending prompts that exceed the active context window.
Task-driven defaults
Default models and allowed alternatives are stored server-side in the application configuration. Each task type - such as implementation plans, merges, prompt generation, or voice transcription - defines a preferred model, a list of allowed options, and token limits that the desktop app reads at runtime.
Selector toggle in the client
The Implementation Plans panel renders allowed models with the ModelSelectorToggle. The toggle displays each allowed model, tracks the active selection, and checks whether the estimated prompt plus planned output tokens fit within the model’s advertised context window before allowing a switch.
If a model cannot support the total token requirement, the toggle disables the button and surfaces a tooltip with the computed overage, keeping reviewers within safe limits before they send work to an agent.
Prompt estimation
Token counts are calculated through the token estimation command. The panel submits the session id, task description, relevant files, and the selected model so the backend can return system, user, and total token values. These numbers feed directly into the selector guardrails and let teams spot over-limit prompts before copying them into another tool.