Commit Graph

10 Commits

Author SHA1 Message Date
zoeissleeping 57e7a92cd1 fix: UI polish and provider fixes
- Add animate-pulse CSS animation for loading states
- Add Ctrl+I/Ctrl+B markdown shortcuts in chat input
- Improve chat input resize with mirror element
- Add reasoning duration display and shimmer effect
- Add confirmation dialog for deleting all models
- Simplify RowVirtualizerDynamic resize handling
- Fix DialogType imports (type -> value)
- Fix ollama cloud model name resolution
- Make vllm auth header optional
- Various icon and styling fixes
2026-05-11 17:44:00 -05:00
zoeissleeping 6ee5b2cbbe feat: add LongCat 2.0 Preview model 2026-05-11 17:43:43 -05:00
zoeissleeping a1aeed51e2 feat: add huggingface provider and new model logos
- Add HuggingFace as AI provider with model fetching
- Add Poolside, Tencent, and HuggingFace logo components
- Update model mappings for new providers
- Add @ai-sdk/huggingface dependency
- Bump longcat-ai-sdk-provider to 0.0.5
2026-05-11 17:43:02 -05:00
zoeissleeping 1d40812f2a refactor: extract provider logic into modular registry
Each AI provider now has its own module implementing a ProviderModule
interface with createGateway, getAuthHeaders, and fetchModels methods.
This replaces the monolithic switch statements in ai-provider.ts and
models.post.ts with a clean registry pattern.
2026-04-27 12:04:49 -05:00
zoeissleeping e2e3ac6e86 feat: ditch triplit, move to postgresql + drizzle orm 2026-04-08 17:03:07 -05:00
zoeissleeping 59bb7fbc12 Performance enhancements galore! New themining system
This is once again a huge commit, but its mostly performance
improvements along with some bug fixes and refactoring. It also includes
changes to the theming systems. I'm still not 100% happy with the
theming system, but its better than before.

Model fetching has been dramatically improved! Nearly all the important
computation and pre-processing has been moved to the server. This has
also somehow fixed the way model details are loaded, which was causing
many models to be missing their details despite models.dev having them.

The markdown renderer has once again been changed, but I'm mostly
certain that this is the last time major changes will be made to it. The
renderer is not spamming components, bloating memory usage, and its not
using a bug prone custom written chunking system.

There's also a lot more that I haven't mentioned and honestly forgot. I
need to get better commit hygiene tbh.
2026-02-20 00:20:50 -06:00
zoeissleeping d29f95bacf feat: add better provider support, icons, regen, and a lot more 2026-02-12 14:56:13 +00:00
zoeissleeping d5a5945c03 streaming, markdown, model selecting, and lots more 2026-02-02 23:16:06 -06:00
zoeissleeping 8c28946703 continue scaffolding and refine the basic foundation 2026-01-13 19:56:24 +00:00
zoeissleeping 0877cc10bd initial commit 2026-01-11 05:04:29 -06:00