Cairn
NousResearch/hermes-agent

Ollama reasoning/thinking control and propagation fixes

Cluster 46131 · 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.

These issues and pull requests address passing reasoning_effort or think=false to Ollama and related custom providers to suppress or control thinking/reasoning mode. A recurring concern is that reasoning settings were silently ignored, causing models to run in unintended reasoning modes.

Open issues1

  • Issue#46131Fix: Ollama reasoning models return empty content — send reasoning_effort to disable thinking

Open PRs1

  • PR#46489fix(transports): promote Ollama reasoning field to content when content is empty

1 PR closed without merging

From the close comments: other 1

  • #105996 fix(transport): enforce reasoning output floor so tight max_tokens can't starve the answer · other → fcd7df3, #9452
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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/46131.json
cluster/46131.md