AI agent
Control Agent usage and cost
Use provider-side limits, Kition Cloud credits, smaller context, explicit model choices, and the Stop control without relying on nonexistent budget-routing features.
Updated
By Kition Docs
Verified against Kition 0.2.0 (7d49036f) on 2026-11-06
Know who meters the request
Do not use a fixed “cost per task” estimate from old documentation. Check the selected provider’s current usage records and your Kition credit balance.
- Kition Cloud usage consumes Kition credits shown in your Kition Account
- Bring-your-own-provider usage is billed and rate-limited by that provider or gateway
- Tool loops can make several model requests for one user message
- Model pricing, token rules, and quotas can change without a Kition release
Controls that exist
- Choose the active provider and model from the Agent model picker
- Attach only the documents, folders, and files needed for the task
- Use a new chat when old conversation history is no longer relevant
- Stop a task that is looping, using the wrong context, or heading toward an unwanted action
- Rely on the per-turn step limit: a turn stops after a fixed number of model steps
- Set spend limits and alerts in the external provider console when available
- Use Top up credits for Kition Cloud models
Controls that do not exist
- No Agent monthly dollar cap setting
- No per-session or per-tool token budget control
- No model-routing rules by tool, task, context length, or subagent
- No automatic routing between several external providers
- No Agent concurrency slider
Reduce unnecessary context
A focused Context tray is easier to verify and can reduce repeated input. Prefer a few directly relevant documents over a broad folder when the task is narrow.
Local folders are read-only and capped at eight per session, but what the Agent reads from them is model-visible for the active run. Remove them from the tray when the task no longer needs them.
Use small checkpoints
- Ask for a read-only inventory before requesting writes
- Use Draft edits and review a large kit change before merging it
- Split research, drafting, and final writes into separate turns
- Verify provider usage after the first representative task
- Stop and revise early instead of letting an incorrect tool loop continue
Implementation sources
- kition@7d49036f: src/features/agent/lib/agentConfig.ts
- kition@7d49036f: src/features/agent/hooks/useWorkspaceAgent.ts
- kition@7d49036f: src/features/agent/components/AgentAiComposer.tsx
- kition@7d49036f: crates/kition-agent/src/turn.rs
- kition@7d49036f: crates/kition-agent/src/sources.rs
- kition@7d49036f: src/services/desktopSettings.ts
Related pages
Switch the active provider and model
Understand the device-wide model selection that Kition saves when you sync a provider or use the Agent model picker.
Agent chat basics
Open a workspace-scoped chat, attach only the context you need, choose a model, and review the streamed work and the files it changed.
Agent tool calls
Read the runtime tool names, how availability is decided, and the inputs, outputs, errors, and changed files shown in the Agent timeline.