# Context and compaction

See how full the agent's context window is, compact a long chat by hand or at a limit you set, and when Studio asks before a long idle chat goes on.

*Where in Studio: Composer → Context usage*

*Last updated: 2026-10-25*

The context window is what the agent holds in mind for its next turn: the instructions, its tools and the conversation so far. A long chat fills it. Compaction replaces the older part of the conversation with a summary, so the agent can keep going. The transcript you see in Studio stays whole; only what the agent carries shrinks.

## See how full it is

The small ring in the row under the composer fills as the window does. Click it to open **Context usage**.

![The Context usage panel: percent full, used and maximum tokens, the Compact button, the gauge and the window breakdown.](https://kelrova.com/docs/img/studio-chats/context-usage.png)

*Context usage with the gauge, the Compact button and the window breakdown.*

- **N% full** and **~used / max tokens** come from the agent's last turn.
- A tick on the gauge marks where the agent compacts by itself, when it reports that point.
- **What's in the window** breaks the window down as of the last turn.
- After a compaction the panel says **Compacted once** or **Compacted N times**.

Until the agent reports its window, the panel says **Context usage will appear after the active agent reports its context window.** The lower half of the panel shows what the chat has spent; see [Token usage](https://kelrova.com/docs/studio/reference/usage).

## Compact now

*Composer → Context usage → Compact*

For Claude Code and Codex chats, **Compact** sits at the end of the **N% full** row.

1. **Wait for the agent to finish**

   **Compact** works only while the agent is idle. During a run it is disabled with **Available when the agent is idle**.

2. **Compact**

   Choose **Compact**. It reads **Compacting…** while the agent works. The chat shows the compaction as a `/compact` message, and the gauge drops when it is done.

If it cannot start, the panel says **Couldn't start compaction. Try again.**

Compaction frees room in the window. It does not lower what the chat has spent, and the agent keeps only the summary of what came before.

## Compact automatically

*Settings → Agents → Claude Code or Codex → Auto compact*

Claude Code and Codex can compact on their own once the context reaches a limit you choose. The setting is synced across your devices.

1. **Open the agent**

   Open **Settings → Agents** and select **Claude Code** or **Codex** in the list.

2. **Turn on Auto compact**

   Switch on **Auto compact**. For Claude Code it reads "Compact chats and subagents at a token limit you choose, or earlier at Claude's own limit."

3. **Set the limit**

   Enter a token limit from 50,000 to 1,000,000. The field starts at 150,000. A value outside the range shows **Enter a limit from 50,000 to 1,000,000 tokens.**

The limit applies to that agent's chats and subagents. Under it, **Orchestrator auto compact** gives Orchestra chats their own limit, starting at 250,000. When that row is off, Orchestra chats use the limit above, or Kelrova's default. See [Limits and usage](https://kelrova.com/docs/studio/orchestra/limits).

![The Auto compact card on the Claude Code pane of Settings, Agents, with a token limit and the Orchestrator auto compact row.](https://kelrova.com/docs/img/studio-chats/auto-compact.png)

*The Auto compact card on the Claude Code pane, with the Orchestrator row.*

## Continue a long chat after a pause

Providers keep a recent conversation in a cache that makes the next turn cheaper. After a long pause the whole history may be processed again. So when a chat with at least 100,000 tokens of context has been idle, Studio asks before your next message goes out:

| Agent | Asks after |
| --- | --- |
| Claude Code | 1 hour idle |
| Codex | 30 minutes idle |

The question **Continue a long chat?** names the context size. Choose:

- **Continue** to send in this chat. Studio does not ask again until the chat has been idle that long once more.
- **New chat** to move your draft, files and voice notes to a new chat in the same project. Nothing is sent and the old transcript does not come along, so you can review the message first.
- **Cancel** to keep the draft and do nothing.

The timings are a rule of thumb for when the cache may have expired, not a price. Other agents do not ask.

## Keep the context small

- Start a new chat for a separate piece of work. A code chat can suggest this itself; see [The composer](https://kelrova.com/docs/studio/chats/composer#when-a-follow-up-looks-like-separate-work).
- In an Orchestra, the orchestrator hands reading and testing to its agents, so their work does not fill its own window. See [How Orchestra works](https://kelrova.com/docs/studio/orchestra/overview).

## Related

- [Token usage](https://kelrova.com/docs/studio/reference/usage)
- [Limits and usage](https://kelrova.com/docs/studio/orchestra/limits)
- [The composer](https://kelrova.com/docs/studio/chats/composer)
- [Connect your agents](https://kelrova.com/docs/studio/getting-started/agents)