Cairn

Handle unsupported reasoning_effort errors from custom providers

NousResearch/hermes-agent · cluster 129002 · agent

Data as of

3 open items. Fix attempted, not merged.

The short answer

1open issue
2open PRs
3items grouped
Known?
Yes. 3 related items grouped here, 0 issues already closed.
Fix event
No fix has been merged to main. see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
1 issue and 2 PRs.

These items address how the system responds when custom or SGLang-compatible endpoints reject requests due to an unrecognized 'reasoning_effort' parameter. The work involves error classification fixes and potentially remapping or clamping the effort value rather than aborting.

Open issues1

  • Issue#129002Custom (OpenAI-compatible) provider hard-rejects reasoning_effort the seat config set: bot-mode DM resume dies at the provider gate — clamp/remap unsupported effort like other providers do

Open PRs2

  • PR#129013fix(error-classifier): recognize 'Unexpected reasoning effort' 400 from custom endpoints
  • PR#129089fix(classifier): recover from SGLang's "Unexpected reasoning effort" 400 instead of aborting
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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
0 PRs closed without merging

For your agent

The same facts, typed.

cluster/129002.json
cluster/129002.md