[FEATURE] compact conversation tool
Status Closed — not planned
Maintainer reply None cached
Activity 8 comments · opened Oct 1, 2025 · closed Jan 18, 2026
Preflight Checklist
- [x] I have searched existing requests and this feature hasn't been requested yet
- [x] This is a single feature request (not multiple features)
Problem Statement
Long context window worsens the quality. I often make multi phased plans in which the past context could be distilled. I would want to instruct Claude code when (and how) to compact the conversation when moving on to the next phase.
Proposed Solution
Provide claude code tool that the plan can instruct claude to compact the conversation.
Alternative Solutions
_No response_
Priority
High - Significant impact on productivity
Feature Category
Interactive mode (TUI)
Use Case Example
- come up with a big plan, multiple phases
- the plan could instruct in the end of each phase (or beginning of the next one) to compact the conversation
- this could help claude to better stay on track.
Additional Context
_No response_
8 Comments
This issue has been inactive for 30 days. If the issue is still occurring, please comment to let us know. Otherwise, this issue will be automatically closed in 30 days for housekeeping purposes.
I still think exposing compact in more flexible manner would make Claude Code more powerful and support wider range of use cases.
This would be a very valuable feature for complex workflows. See my initial request - #5643
@dicksontsai would you mind taking a look? Folks have been asking for this for a while, see https://github.com/anthropics/claude-code/issues/2873 as well. Thanks in advance!
I am bumping this because this is a feature I would like, tremendously. Like, Anthropic has absolutely no idea how ballistic my workflow could be if CC could invoke compaction on its own.
This issue has been automatically closed due to 60 days of inactivity. If you're still experiencing this issue, please open a new issue with updated information.
This issue was closed incorrectly despite recent human comments. This behavior of the bot is reported at https://github.com/anthropics/claude-code/issues/16497. Please upvote that issue, so maybe it gets noticed.
This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.