# Context management and cost saving

> How clai prevents context bloat through tool output truncation, selective recall, and rate-limit recovery.

Canonical URL: https://www.clai.chat/docs/v0.1/concepts/context-and-cost/ · Version: 0.1 · Updated: 2026-10-21

Full site index: https://www.clai.chat/llms.txt

Long agentic sessions and verbose shell commands can quickly exhaust token budgets. `clai` keeps token usage predictable through built-in context controls.

## Tool output truncation and recall

When a builtin tool (such as `bash` or `rg`) or an MCP tool produces output exceeding the configured inline threshold, `clai` truncates the message sent to the model and stores the full payload locally. The model can then inspect specific line or byte ranges on demand using the `recall` tool instead of re-sending megabytes of log output on every turn.

## Scoped profiles and tool filtering

Rather than exposing every MCP server and builtin tool on every query, use `-t="<glob>"` or profile `tools` allowlists so the model only receives schemas for the tools relevant to the task.

## Rate-limit backoff and partial conversation recovery

When a vendor returns a rate-limit error, `clai` parses the vendor's retry window and backs off automatically. If you cancel a streaming query or tool loop with `Ctrl+C`, `clai` preserves the partial conversation state so you can resume with `clai -c` without paying to regenerate completed steps.