Nov 13 2 days ago

1. 20:52

   Forward project context through a dedicated Gradio input instead of filtered chat history

   SEE7
   Verified signature

   d2287b7
2. 20:50

   Hold partial Harmony markers to keep streamed text monotonic

   SEE7
   Verified signature

   7610b69
3. 20:46

   Stream Thinking content as a stable prefix and strip Harmony role transitions

   SEE7
   Verified signature

   effa79e
4. 20:44

   Handle native Mxfp4Config objects during startup validation

   SEE7
   Verified signature

   434757e
5. 20:40

   Use supported native GPT-OSS attention for model loading

   SEE7
   Verified signature

   5065e85
6. 20:39

   Pin AstheralPlus Space to published trained MXFP4 checkpoint

   SEE7
   Verified signature

   3578bc8
7. 20:26

   Implement 20.9B native reasoning inference and persistent project workspaces

   SEE7
   Verified signature

   84979ea
8. 15:19

   Remove public account/model headers and visitor OAuth checks; keep server quota guard with retries

   SEE7
   Verified signature

   ffd5312
9. 15:10

   Add coding workspace, text/code references, per-model profiles and Continue reply

   SEE7
   Verified signature

   4b43fe7
10. 05:17

    Allow 4096-token replies and 110-second generation with 180-second quota reserve

    SEE7
    Verified signature

    7244dd9
11. 04:57

    Pin Astheral chat to tested V3 weights; preserve UI and quota guard

    SEE7
    Verified signature

    92a2cd2
12. 03:47

    Register the GGUF ZeroGPU handler during application startup

    SEE7
    Verified signature

    9c78f5e
13. 03:46

    Add private GGUF upload, model selection and quota-guarded CUDA inference

    SEE7
    Verified signature

    b66be8b
14. 03:38

    Serve llama-ui routes directly without Gradio SSR interception

    SEE7
    Verified signature

    766c469
15. 03:34

    Install real llama-ui with streaming Astheral ZeroGPU adapter and existing quota guard

    SEE7
    Verified signature

    66474d0
16. 03:22

    Pause GPU generation before final three minutes of included quota

    SEE7
    Verified signature

    8ff525a
17. 03:15

    Correct Gradio examples for response settings inputs

    SEE7
    Verified signature

    94f80ad
18. 03:13

    Deploy private Astheral demo with real weights on ZeroGPU

    SEE7
    Verified signature

    0339afd