Skip to content

docs: non-interactive compact now #4543

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
dianed-square merged 1 commit into from
Sep 5, 2025
Merged

docs: non-interactive compact now #4543

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
1 change: 1 addition & 0 deletions documentation/docs/guides/sessions/session-management.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -56,6 +56,7 @@ In your first session, Goose prompts you to [set up an LLM (Large Language Model
| New Session in Current Directory | `Cmd+N` | `Ctrl+N` |
| New Session in Different Directory | `Cmd+O` | `Ctrl+O` |
| Focus Goose Window | `Cmd+Option+Shift+G` | `Ctrl+Alt+Shift+G` |
| Toggle Sidebar | `Cmd+B` | `Ctrl+B` |

</TabItem>
<TabItem value="cli" label="Goose CLI">
Expand Down
23 changes: 11 additions & 12 deletions documentation/docs/guides/sessions/smart-context-management.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,13 +11,13 @@ import { PanelLeft } from 'lucide-react';

When working with [Large Language Models (LLMs)](/docs/getting-started/providers), there are limits to how much conversation history they can process at once. Goose provides smart context management features to help handle context and conversation limits so you can maintain productive sessions. Here are some key concepts:

- **Context Length**: The amount of conversation history the LLM can consider
- **Context Length**: The amount of conversation history the LLM can consider, also referred to as the context window
Copy link
Contributor Author

@dianed-square dianed-square Sep 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I think these terms are used interchangeably

- **Context Limit**: The maximum number of tokens the model can process
- **Context Management**: How Goose handles conversations approaching these limits
- **Turn**: One complete prompt-response interaction between Goose and the LLM

## How Goose Manages Context
Goose uses a two-tierd approach to context management:
Goose uses a two-tiered approach to context management:

1. **Auto-Compaction**: Proactively summarizes conversation when approaching token limits
2. **Context Strategies**: Backup strategy used if the context limit is still exceeded after auto-compaction
Expand All @@ -37,10 +37,9 @@ export GOOSE_AUTO_COMPACT_THRESHOLD=0.6
```

When you reach the auto-compaction threshold:
1. Goose will automatically start summarizing the conversation to make room.
2. You'll see a message that says **"Auto-compacted context: X → Y tokens (Z% reduction)"**
3. Once complete, previous messages in your conversation remain visible, but only the summary is included in the active context for Goose.
4. Continue the session with the summarized context in place.
1. Goose will automatically start compacting the conversation to make room.
2. Once complete, you'll see a confirmation message that the conversation was compacted and summarized.
Copy link
Contributor Author

@dianed-square dianed-square Sep 5, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Currently different messages in Desktop v CLI

3. Continue the session. Your previous conversation remains visible, but only the compacted conversion is included in the active context for Goose.

### Manual Compaction
You can also trigger compaction manually before reaching context or token limits:
Expand All @@ -49,12 +48,12 @@ You can also trigger compaction manually before reaching context or token limits
<TabItem value="ui" label="Goose Desktop" default>

1. Point to the token usage indicator dot next to the model name at the bottom of the app
2. Click <ScrollText className="inline" size={16} /> `Summarize now` in the context window that appears
2. Confirm the summarization in the modal
3. View or edit the generated summary if needed
2. Click <ScrollText className="inline" size={16} /> `Compact now` in the context window that appears
3. Once complete, you'll see a confirmation message that the conversation was compacted and summarized.
4. Continue the session. Your previous conversation remains visible, but only the compacted conversion is included in the active context for Goose.

:::note
Before the scroll icon appears, you must send at least one message in the chat. Simply starting a new session won't trigger it.
:::info
You must send at least one message in the chat before the `Compact now` button is enabled.
:::

</TabItem>
Expand Down Expand Up @@ -89,7 +88,7 @@ When auto-compaction is disabled, or if a conversation still exceeds the context
<Tabs groupId="interface">
<TabItem value="ui" label="Goose Desktop" default>

Goose Desktop exclusively uses summarization to manage context, preserving key information while reducing size.
Goose Desktop exclusively uses summarization by compacting the conversation to manage context, preserving key information while reducing size.

</TabItem>
<TabItem value="cli" label="Goose CLI">
Expand Down