# Compaction of a conversation is failing

**URL:** <https://community.osaurus.ai/t/compaction-of-a-conversation-is-failing/33>\
**Category:** Support\
**Tags:** macos, bug\
**Created:** [October 3, 2026, 5:27pm UTC](https://community.osaurus.ai/t/compaction-of-a-conversation-is-failing/33 "2026-10-03T17:27:26Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![BugsBunny](https://sea1.discourse-cdn.com/flex045/user_avatar/community.osaurus.ai/bugsbunny/32/34_2.png) [@BugsBunny](https://community.osaurus.ai/u/BugsBunny)\
**Post date:** [October 3, 2026, 5:27pm UTC](https://community.osaurus.ai/t/compaction-of-a-conversation-is-failing/33/1 "2026-10-03T17:27:26Z")

</div>

![Image 2026-10-03 at 09.57](https://us1.discourse-cdn.com/flex045/uploads/osaurus/original/1X/fe4b080134625e11622b0cac2e421dba2fb4242e.png)

I’ve been getting this compaction error in a conversation that has now grown to 626k and is beyond my Qwen 3.8 27B model. So I pointed the compaction to Sol 6.0 that has a context of 1M and still get the above.

This was not an issue for versions 0.25.14 and earlier, but I started this conversation in 0.25.15 and this issue is persisting in 0.25.16 and 0.25.17.

Previously, I noticed that capturing the context limit for API endpoints does not get an accurate size from the model as I believe the value pair returns a different value than what Osaurus expects.

For example, I’ll point to OpenAI GPT Sol 6 and it should allow for 1m context, but Osaurus thinks this is unknown and defaults to the “Unknown-Model Metadata Fallback (tokens)” and I’ve left the “Context Window Cap (tokens)” blank.

It would be great if I could use a model in conversation that uses 128k-262k and a compaction model that uses a larger size (1m) to ensure I’m not trimming my conversation, but actually compacting it, so I can keep my conversation going.