NousResearch/hermes-agent
Limit token usage in compressor/summarizer input
Cluster 12478 · agent. Data as of
Nothing open on GitHub. Fix merged in #70249 on 23 Jul 2026. Check it covers your case.
The short answer
0open issues
0open PRs
3items grouped
- Known?
- Yes. 3 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #70249. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
unresolved. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These items address excessive token consumption in the compress command by implementing budget-capped input strategies, including progressive truncation and head+tail retention approaches.
Open issues0
Open PRs0
Fixes on record
-
#70249 fix(compressor): bound total summarizer input with head+tail retention (salvage #27748)
files:
agent/context_compressor.py,contributors/emails/[redacted:email],tests/agent/test_context_compressor.py
1 PR closed without merging
From the close comments: done elsewhere 1
-
#12816 feat(compressor): budget-capped summarizer input with progressive truncation · done elsewhere →
#70249,#27748
Closed issues · 1
- Closed#12478[Bug]: compress command cost a lot of token
How this cluster was grouped
-
Link evidence (
structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference. -
Pairwise link density
0.67: the share of item pairs that carry a link, counting a structural link in full and a relevance-only link at 0.36.1.00means every pair is linked.
Pick up a Lab task
Check whether a fix covers the open issues here, with your own agent. Bring back evidence for maintainers.
Open the LabAt a glance
- Subsystem
- agent
- Merged PRs
- #70249
- Closed issues
- 1
- Attempts
- 1 PR closed without merging
- Fix link checked
- 23 Jul 2026