Files
clawdbot/docs/concepts/compaction.md
2026-01-27 12:21:02 +00:00

50 lines
2.1 KiB
Markdown
Raw Permalink Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
---
summary: "Context window + compaction: how Moltbot keeps sessions under model limits"
read_when:
- You want to understand auto-compaction and /compact
- You are debugging long sessions hitting context limits
---
# Context Window & Compaction
Every model has a **context window** (max tokens it can see). Long-running chats accumulate messages and tool results; once the window is tight, Moltbot **compacts** older history to stay within limits.
## What compaction is
Compaction **summarizes older conversation** into a compact summary entry and keeps recent messages intact. The summary is stored in the session history, so future requests use:
- The compaction summary
- Recent messages after the compaction point
Compaction **persists** in the sessions JSONL history.
## Configuration
See [Compaction config & modes](/concepts/compaction) for the `agents.defaults.compaction` settings.
## Auto-compaction (default on)
When a session nears or exceeds the models context window, Moltbot triggers auto-compaction and may retry the original request using the compacted context.
Youll see:
- `🧹 Auto-compaction complete` in verbose mode
- `/status` showing `🧹 Compactions: <count>`
Before compaction, Moltbot can run a **silent memory flush** turn to store
durable notes to disk. See [Memory](/concepts/memory) for details and config.
## Manual compaction
Use `/compact` (optionally with instructions) to force a compaction pass:
```
/compact Focus on decisions and open questions
```
## Context window source
Context window is model-specific. Moltbot uses the model definition from the configured provider catalog to determine limits.
## Compaction vs pruning
- **Compaction**: summarises and **persists** in JSONL.
- **Session pruning**: trims old **tool results** only, **in-memory**, per request.
See [/concepts/session-pruning](/concepts/session-pruning) for pruning details.
## Tips
- Use `/compact` when sessions feel stale or context is bloated.
- Large tool outputs are already truncated; pruning can further reduce tool-result buildup.
- If you need a fresh slate, `/new` or `/reset` starts a new session id.