Cairn
NousResearch/hermes-agent

Token estimate underestimation in auto-compression preflight checks

Cluster 62605 · agent. Data as of

2 open items. Fix attempted, not merged.

The short answer

1open issue
1open PR
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. 1 PR closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 1 PR.

The members concern auto-compression where rough token estimates may underestimate actual prompt size, with one issue reporting the total exceeding context_length after 3 retries. Two pull requests propose adjustments (calibrating the preflight estimate against real usage, and adding a 15% margin to the system prompt estimate); their outcomes are not stated in the titles.

Open issues1

  • Issue#62605Auto-compression fails when rough token estimate underestimates actual prompt — total exceeds context_length after 3 retries

Open PRs1

  • PR#62612fix(compressor): add 15% safety margin to system prompt token estimate

1 PR closed without merging

From the close comments: other 1

  • #62649 fix(compression): calibrate rough preflight estimate against real usage (#62605) · other
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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. 1.00 means 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 Lab

At a glance

Subsystem
agent
Closed issues
0
Attempts
1 PR closed without merging

For your agent

The same facts, typed.

cluster/62605.json
cluster/62605.md