i/next-ai-draw-io
1
0
Fork 0
mirror of https://github.com/DayuanJiang/next-ai-draw-io.git synced 2026-01-03 06:42:27 +08:00
Code Issues Packages Projects Releases Wiki Activity
Files
3e053bc9046460c0c95889db8dee1bbde94f892f
next-ai-draw-io/app/api
History
Dayuan Jiang 03ac9a79de fix: detect models that don't support image input and return clear error (#474) 
Some models (Kimi K2, DeepSeek, Qwen text models) don't support image/vision
input. The AI SDK silently drops unsupported image parts, causing confusing
responses where the model acts as if no image was uploaded.

Added supportsImageInput() function to detect unsupported models by name,
and return a 400 error with clear guidance when users try to upload images
to these models.

Closes #469
2025-12-31 12:20:09 +09:00
..
chat
fix: detect models that don't support image input and return clear error (#474)
2025-12-31 12:20:09 +09:00
config
feat: add bring-your-own-API-key support (#186)
2025-12-09 17:50:07 +09:00
log-feedback
fix: use full IP for userId to prevent quota collision (#400)
2025-12-25 12:20:46 +09:00
log-save
refactor: simplify Langfuse integration with AI SDK 6 (#375)
2025-12-23 16:26:45 +09:00
validate-model
feat: add EdgeOne Pages as AI provider (#456)
2025-12-30 22:13:22 +09:00
verify-access-code
feat: verify access code with server before saving (#128)
2025-12-07 00:21:59 +09:00