Read tool for kimi k2.5 on zen dose not work on images #11550

Activity

1. SirStisx

   added

   bugSomething isn't workingSomething isn't working

   on Feb 1, 2026
2. github-actions

   assigned

   fwang

   on Feb 1, 2026
3. github-actions

   added

   zenRelates to ZenRelates to Zen

   on Feb 1, 2026
4. github-actions commented on Feb 1, 2026

   

   github-actionsBot

   on Feb 1, 2026 – with GitHub Actions

   Contributor

   More actions

   This issue might be a duplicate of existing issues. Please check:

   • Images returned from Read tool don't work with OpenAI-compatible providers #11304: Images returned from Read tool don't work with OpenAI-compatible providers (Kimi K2.5 specifically mentioned)
   • Read tool fails to read image files even with vision-capable models (paste works) #11306: Read tool fails to read image files even with vision-capable models (paste works)
   • Read tool accesses JPEG file but vision model hallucinates incorrect description (no actual image content processed) #11437: Read tool accesses JPEG file but vision model receives base64 string instead

   These issues describe the exact same symptom - the Read tool returns base64-encoded images instead of letting vision-capable models handle them natively. This is particularly affecting OpenAI-compatible providers like Kimi K2.5 when accessed through Zen.

   Feel free to ignore if your case is different, but these related issues may provide additional context or workarounds.
5. rekram1-node

   closed this as completedin #11323on Feb 5, 2026