> Documentation index: [/llms.txt](/llms.txt). Every page as one file: [/llms-full.txt](/llms-full.txt).

# Context and compaction

Context and compaction [#context-and-compaction]

A model can only read so much at once, so when a chat grows long its earlier part is condensed into a summary and the chat carries on.

The context ring [#the-context-ring]

After the first reply, a small ring appears in the composer next to the model picker. It fills as the chat grows.

<img alt="The context ring's tooltip in the composer: Context usage with the tokens used out of the model's window, and Click to view summary" src="__img0" />

| Ring                | Meaning                                                                        |
| ------------------- | ------------------------------------------------------------------------------ |
| Grey, partly filled | How close the chat is to being compacted. A full ring means compaction is due. |
| Yellow              | The chat is over the point where it gets compacted.                            |

Point at the ring to see **Context usage** and the tokens in use out of the model's full context window. Select it to open the summary.

The window size depends on the model; a platform admin sets it for each model, and a model added without one counts as 128,000 tokens.

When a chat is compacted [#when-a-chat-is-compacted]

| Trigger                                                                  | What happens                                                                                                                                                                          |
| ------------------------------------------------------------------------ | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
| After a reply, the chat uses more than 80% of the model's context window | The chat so far is summarized. The notice &#x2A;*Chat history compacted.** appears, with the size the context was reduced from.                                                       |
| You send **/compact**                                                    | The same, right away. The **/compact** message itself is not kept.                                                                                                                    |
| One reply grows past that point while the agent works                    | Older tool results are shortened first. If that is not enough, earlier turns are folded into a summary and the notice &#x2A;*Chat history summarized.** appears. The reply continues. |
| A tool returns a very large result                                       | The model gets only its start and end. The agent can still open the full result from a file in its sandbox.                                                                           |
| The model refuses a request as too long                                  | The reply ends with an error, and the chat is compacted so your next message fits. The notice reads &#x2A;*Chat history compacted after context overflow.**                           |

<img alt="The end of a reply followed by the Chat history compacted. notice" src="__img1" />

Compaction changes only what the model reads:

* You still see every message in the chat.
* From then on, the agent reads the summary and the messages that came after it.
* Details that did not make it into the summary are no longer in the agent's view. Repeat anything important, or attach the file again.
* The summary is written by the chat's own model.

Read the summary [#read-the-summary]

Select the context ring. **Compaction summary** shows when the summary was last updated and what it holds, such as the context the agent carries forward, your original request and the files it worked on.

<img alt="The Compaction summary window with the context carried forward and the original request" src="__img2" />

A chat that was never compacted shows &#x2A;*No compacted summary yet.**

Keep long work manageable [#keep-long-work-manageable]

* Start a new chat for an unrelated task; the old chat keeps its history.
* Send **/compact** before a new phase of work in the same chat, so the agent starts it from a short summary.
* Put the files the agent should keep using in the Library and mention them with &#x2A;*@**, instead of pasting long text. See [Mentions and commands](/docs/platform/chat/mentions-and-commands).