I’ve been asked a lot why I keep Claude Code auto-compact turned off. Here’s why 👇
@dani_avila735K followers
105,916 views
34 Comments
Comments from the original post on X (Twitter)

@hakanderyal
I’m on the other side of that. Most of the sessions I use get through 2 or 3 compactions. But Opus with plan mode only goes off rails after 4 or 5, and that’s not every time. Plan gets referenced back after every compact automatically. It’s the key part.
4 likes

@BrandGrowthOS
Same lesson I learned with prompt management. Auto-compact feels like a safety net until it triggers mid-session and erases the exact context the agent needed. Configuration discipline beats reactive failsafes.
4 likes

@iLukin
Why not use?
2 likes

@f_butz
similar experience. /clear + document the plan in markdown beats auto-compact for me. you control what survives, not the algorithm.
1 like

@alex_d_morris
you could try using subagents more - mine usually have precise prompts and die by pushing to a db or local store. if you use subagents properly your context compaction doesn't affect much @steve_yegge
1 like

@DomiYoung___
Is the ui of Web the same as the terminal?
1 like

@ironcarbs
great take, I also have compact turned off after playing around with the config and analyzing the context window limits
1 like

@michaelvessia
I did the same pre-opus 4.5 but I've found my issues with performance degradation post-compaction to have gone away, or it's at least improved to the point where it's not driving me crazy
1 like

@DgtlDev
Got it. Thx

@eyyupsayli
Mine is turned off as well. My process generally calls multiple agents, so they all have separate context windows. I use the main context as a manager. Even if I hit the limit, the API throws an error, and I switch the model to Sonnet 1M to continue and finish the work. Or you can copy the discussion /clear and copy that to continue.

@ViktorB01
Also skills.

@blackboxai
That makes sense. Auto-compaction is a symptom of weak context hygiene, not a solution. When context is structured intentionally, you preserve signal and avoid surprise drops mid-workflow. That’s exactly the direction we optimize for, explicit context, scoped runs, predictable behavior. Do check out our latest release on multi agent Blackbox CLI.

@ziran_pu
Analysis: Initial request: My response: (loop summarize) Files created. Errors/ Issues. Commits made. Primary request and intent. Key technical concepts. Files and code sections. Errors and fixes. Problem solving. All users messages. Current work. Optional next steps.

@AndreBuckingham
i use "handover to self" md created at 5%-7% then compact manually, and have done a whole refactor in one "session" with no issues through four five compactions... Have been thinking about making something local that can serve that function but for now the handover-to-self. md works perfectly for better continuity after compactions... that and four other "working md´s" eliminate this issue for me

@karanjagtiani04
Totally get that. Context loss is a pain, especially mid-session. A solid config can really make a difference. How do you manage the balance between keeping context and performance?

@AnalyticsGenius
I just used my research backed tools I built that handle context across swarms significantly more efficiently and don’t ever worry about it

@Bencera
Lost context is just lost dreams.

@zby
You don’t need to turn it off if you never reach the limit!

@magicwithAI
Interesting.. thanks for sharing.

@Barthazian
just wat I needed been getting compacted too much and keep spoiling the iterations














