Vision routing: prefer modalities.input over attachment flag
Cluster 18884 · agent. Data as of
Nothing open on GitHub. Fix merged in #21246 on 7 May 2026. Check it covers your case.
The short answer
- Known?
- Yes. 4 related items grouped here, 1 issue already closed.
- Fix event
- A fix was merged to main in PR #21246. Check it covers your case. No release data is tracked.
- Tracker
- The maintainers' tracker marks this
resolved, deciding PR #21246. That is separate from the fix event. - Still open
- Nothing open on GitHub.
These issues and PRs address a routing logic problem where the attachment flag incorrectly takes precedence over modalities.input for determining vision/image capability. A specific case involves mimo-v2.5-pro being wrongly marked as attachment:true despite being text-only.
Open issues0
Open PRs0
Fixes on record
-
#21246 fix(models): prefer modalities.input for vision routing (salvage #19190)
files:
agent/models_dev.py,tests/agent/test_image_routing.py,tests/agent/test_models_dev.py
2 PRs closed without merging
From the close comments: done elsewhere 1 · duplicate 1
Closed issues · 1
- Closed#18884[models.dev] mimo-v2.5-pro incorrectly marked as attachment:true — mimo-2.5-pro is text-only, mimo-2.5 is the omnimodal model
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structural links throughout): every member is connected by structural evidence: shared changed files, or a closing/superseded reference.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 0.36.1.00means 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
- #21246
- Closed issues
- 1
- Attempts
- 2 PRs closed without merging
- Fix link checked
- 7 May 2026