[FEATURE]: Silent/background compaction — don't stream summary output to the terminal #8963

Closed
opened 2026-02-16 18:11:16 -05:00 by yindo · 2 comments
Owner

Originally created by @Rohansguliani on GitHub (Feb 10, 2026).

Originally assigned to: @thdxr on GitHub.

Feature hasn't been suggested before.

  • I have verified this feature I'm about to request hasn't been suggested before.

Describe the enhancement you want to request

Problem

When auto-compaction triggers, the entire summarization process streams visibly into the terminal window. The user has to sit and watch the summary text render in real-time before they can continue working. This is disruptive and slow — especially since compaction uses the same primary model as the active session by default.

There's no reason the user needs to see the compaction summary being generated. It's an internal housekeeping operation, not something the user asked for or needs to read.

Current behavior

The compaction summary streams token-by-token into the chat window, just like a normal assistant response. This:

  • Interrupts the user's flow — you're mid-thought and suddenly the terminal is filled with a summary you didn't ask for
  • Is slow — it uses the primary model by default, so it takes as long as a real response
  • Adds visual noise — the summary text is not actionable for the human; it's internal context for the AI

Expected behavior

Compaction should run silently in the background. The user should see at most a brief indicator (e.g., "Compacting context..." → "Done"), not the full streamed output of the summary.

Suggestion

  • Stream compaction in the background without rendering output to the chat
  • Show a minimal status indicator (spinner, progress bar, or a one-liner like "Context compacted")
  • Optionally, make this configurable (e.g., compaction.silent: true) for users who do want to watch it

Not a duplicate

The flagged issues are about different things:

  • #6228 — disabling per-message summary generation (the small summaries, not compaction)
  • #11930 — configurable compaction threshold and model selection
  • #12479 — token waste from re-summarizing already-summarized messages

This issue is specifically about the terminal UX: compaction output should not stream visibly into the user's chat window.

Environment

  • opencode 0.0.0-dev-202602020741
  • macOS
Originally created by @Rohansguliani on GitHub (Feb 10, 2026). Originally assigned to: @thdxr on GitHub. ### Feature hasn't been suggested before. - [x] I have verified this feature I'm about to request hasn't been suggested before. ### Describe the enhancement you want to request ## Problem When auto-compaction triggers, the entire summarization process streams visibly into the terminal window. The user has to sit and watch the summary text render in real-time before they can continue working. This is disruptive and slow — especially since compaction uses the same primary model as the active session by default. There's no reason the user needs to see the compaction summary being generated. It's an internal housekeeping operation, not something the user asked for or needs to read. ## Current behavior The compaction summary streams token-by-token into the chat window, just like a normal assistant response. This: - **Interrupts the user's flow** — you're mid-thought and suddenly the terminal is filled with a summary you didn't ask for - **Is slow** — it uses the primary model by default, so it takes as long as a real response - **Adds visual noise** — the summary text is not actionable for the human; it's internal context for the AI ## Expected behavior Compaction should run silently in the background. The user should see at most a brief indicator (e.g., "Compacting context..." → "Done"), not the full streamed output of the summary. ## Suggestion - Stream compaction in the background without rendering output to the chat - Show a minimal status indicator (spinner, progress bar, or a one-liner like "Context compacted") - Optionally, make this configurable (e.g., `compaction.silent: true`) for users who do want to watch it ## Not a duplicate The flagged issues are about different things: - **#6228** — disabling per-message summary generation (the small summaries, not compaction) - **#11930** — configurable compaction threshold and model selection - **#12479** — token waste from re-summarizing already-summarized messages This issue is specifically about the **terminal UX**: compaction output should not stream visibly into the user's chat window. ## Environment - opencode `0.0.0-dev-202602020741` - macOS
yindo added the needs:compliance label 2026-02-16 18:11:16 -05:00
yindo closed this issue 2026-02-16 18:11:16 -05:00
Author
Owner

@github-actions[bot] commented on GitHub (Feb 10, 2026):

This issue doesn't fully meet our contributing guidelines.

What needs to be fixed:

  • Feature Request template requires a verification checkbox ("I have verified this feature hasn't been suggested before"). Please add this checkbox to your issue.
  • The title should follow the format [FEATURE]: description instead of Feature: description

Please edit this issue to address the above within 2 hours, or it will be automatically closed.


This issue might be a duplicate of existing issues. Please check:

  • #6228: [FEATURE]: Configuration option to disable message summary generation (related feature about controlling summary behavior)
  • #11930: Feature: Configurable compaction threshold and model (related compaction configuration)
  • #12479: [FEATURE]: Session compaction includes already-summarized messages, wasting tokens (related compaction efficiency)

If you believe this was flagged incorrectly, please let a maintainer know.

@github-actions[bot] commented on GitHub (Feb 10, 2026): <!-- issue-compliance --> This issue doesn't fully meet our [contributing guidelines](../blob/dev/CONTRIBUTING.md). **What needs to be fixed:** - Feature Request template requires a verification checkbox ("I have verified this feature hasn't been suggested before"). Please add this checkbox to your issue. - The title should follow the format `[FEATURE]: description` instead of `Feature: description` Please edit this issue to address the above within **2 hours**, or it will be automatically closed. --- This issue might be a duplicate of existing issues. Please check: - #6228: [FEATURE]: Configuration option to disable message summary generation (related feature about controlling summary behavior) - #11930: Feature: Configurable compaction threshold and model (related compaction configuration) - #12479: [FEATURE]: Session compaction includes already-summarized messages, wasting tokens (related compaction efficiency) If you believe this was flagged incorrectly, please let a maintainer know.
Author
Owner

@github-actions[bot] commented on GitHub (Feb 10, 2026):

This issue has been automatically closed because it was not updated to meet our contributing guidelines within the 2-hour window.

Feel free to open a new issue that follows our issue templates.

@github-actions[bot] commented on GitHub (Feb 10, 2026): This issue has been automatically closed because it was not updated to meet our [contributing guidelines](../blob/dev/CONTRIBUTING.md) within the 2-hour window. Feel free to open a new issue that follows our issue templates.
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: anomalyco/opencode#8963