hermes - 💡(How to fix) Fix but the main model's compression threshold was [2 comments, 2 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
NousResearch/hermes-agent#17690Fetched 2026-04-30 06:46:04
View on GitHub
Comments
2
Participants
2
Timeline
5
Reactions
0
Author
Participants
Timeline (top)
labeled ×3commented ×2
RAW_BUFFERClick to expand / collapse

Why is there this warning? How to fix it doesn't work.

⚠ Compression model (gpt-5.5) context is 256,000 tokens, but the main model's compression threshold was 500,000 tokens. Auto-lowered this session's threshold to 256,000 tokens so compression can run. To make this permanent, edit config.yaml — either:

  1. Use a larger compression model: auxiliary: compression: model: <model-with-500,000+-context>
  2. Lower the compression threshold: compression: threshold: 0.25

extent analysis

TL;DR

Edit the config.yaml file to either use a larger compression model or lower the compression threshold to match the compression model's context.

Guidance

  • The warning occurs because the compression model's context (256,000 tokens) is lower than the main model's compression threshold (500,000 tokens).
  • To fix this, you can either update the config.yaml file to use a larger compression model with a context of 500,000+ tokens.
  • Alternatively, you can lower the compression threshold to 0.25 in the config.yaml file to match the current compression model's context.

Example

compression:
  threshold: 0.25

or

auxiliary:
  compression:
    model: <model-with-500,000+-context>

Notes

The exact model name with a 500,000+ context is not specified, so you will need to find a suitable replacement model.

Recommendation

Apply workaround: edit the config.yaml file to lower the compression threshold to 0.25, as this is a simpler change that can be made immediately.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

hermes - 💡(How to fix) Fix but the main model's compression threshold was [2 comments, 2 participants]