# Context management and cost saving

> How clai bounds a run: a token stop-loss with a handover, tool-call budgets, tool filtering by glob, and lookback that reads only what it needs.

Canonical URL: https://www.clai.chat/docs/concepts/context-and-cost/ · Version: 1.0 · Updated: 2026-10-22

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

A long agentic run can spend tokens without doing work. `clai` bounds the run in four places, and each bound is a flag or a config key that you can see and change.

## Token stop-loss with a handover

`stoploss.max-tokens` in `textConfig.json`, or `-mt` (`-max-tokens`) for one run, sets a token budget. When a step crosses the budget, `clai` finishes that step's tool batch and then adds a handover message. The handover starts a fresh wrap-up phase: the model is told to finish the work with what it has.

The wrap-up phase has its own tool allowance, `stoploss.max-tool-calls-after-handover`. Once that allowance is spent, further tool calls are refused. A refused call never reaches its executor: the model reads the refusal text as the tool result, so it stops asking and writes up the answer.

`0` means unlimited for both keys. A run with no budget is possible; it is not the default advice.

## Tool-call budgets

`max-tool-calls` in `textConfig.json`, or `-mtc` (`-max-tool-calls`) for one run, caps the number of tool calls before the handover. The controller counts a whole batch before it runs any of it, so a refusal cannot leave half a batch executed.

## Tool filtering

Every tool schema costs tokens on every turn. `-t` (`-tools`) takes `'*'` for all tools, or a comma-separated list of tool names and globs:

```sh
clai -t="rg,file_tree,mcp_git_*" q "Show what changed in internal/cli"
```

A profile's `tools` field does the same for a saved workflow, so a profile that reviews Go code carries only the tools that review Go code. See [Profiles and setup](/docs/guides/profiles/).

## Lookback reads what it needs

`-lb` (`-lookback`) lets the model see that recent conversations exist and search them. It reads a descriptor first, then one conversation, then one message. A large conversation is not loaded until the model asks for it. Without `-lb`, the run carries no conversation history and every turn costs only the current prompt.

## Where to look next

- [Configuration](/docs/reference/configuration/) names `stoploss` and the rest of `textConfig.json`.
- [MCP and tools](/docs/guides/mcp-and-tools/) shows tool filtering against MCP servers.
- [Errors and troubleshooting](/docs/reference/errors/) lists the errors a rate limit or a context overflow produces.