Cairn
NousResearch/hermes-agent

Vision model detection and routing improvements

Cluster 14744 · agent. Data as of

1 open item. Fix attempted, not merged.

The short answer

0open issues
1open PR
4items grouped
Known?
Yes. 4 related items grouped here, 1 issue already closed.
Fix event
No fix has been merged to main. 2 PRs closed without merging; see the attempts below.
Tracker
The maintainers' tracker marks this unresolved. That is separate from the fix event.
Still open
0 issues and 1 PR.

These items address how vision-capable models are identified and selected, including probing Ollama's API for capability metadata, skipping non-vision models during fallback, and ensuring the correct runtime model is used during auto-detection.

Open issues0

No open issues.

Open PRs1

  • PR#15441fix(agent): skip non-vision models in vision auto-detection fallback (#14744)

2 PRs closed without merging

From the close comments: done elsewhere 1 · other 1

  • #19804 fix(agent): use runtime model for vision auto-detection (#14744) · done elsewhere → 3800972
  • #33047 feat(vision): probe Ollama /api/show for vision capability on catalog miss · other → #14744, #17940, #14592
Closed issues · 1
  • Closed#14744[Bug]: `vision_analyze` fails on Ollama Cloud because vision auto-detection falls through to non-vision models
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(structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.50: 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
1
Attempts
2 PRs closed without merging

For your agent

The same facts, typed.

cluster/14744.json
cluster/14744.md