ARIA / brain /orchestrator.py

Commit History

  1. Mozg odpowiada tylko na podpisane wywolania; bez placu zabaw; awaria to blad, nie pozegnanie⁠

    8f9bde4

  1. aria: fix instruction-leak (frame+lang moved into system msg, convo ends on real user turn); react ~every 3rd msg; 'byt'->'inteligencja'; 400-char limit⁠

    Malina +1: Claude Opus 4.8
    2e61db0
  2. Update brain/orchestrator.py

    Verified signature
    18d0fde
  3. brain: switch to aya-expanse-32b (your 32B/gemma-4 weren't available; gemma-4 broke Aria entirely)⁠

    Malina +1: Claude Opus 4.8
    5ea523e
  4. zmiana na google/gemma-4-31b-it

    Verified signature
    11e098d
  5. fix zmiany modelu

    Verified signature
    09c43be
  6. Model change to Qwen/Qwen2.5-14B-Instruct

    Verified signature
    b6af9cd
  7. Tescik 2

    Verified signature
    113d2e6
  8. Tescik

    Verified signature
    fec9e45
  9. brain: force reply language to match user's last message (was defaulting to Polish on English)⁠

    Malina +1: Claude Opus 4.8
    961d1cd
  10. aria: fix role mixup in rehydrated history; reliable language-matched idle nudges; anti-echo⁠

    Malina +1: Claude Opus 4.8
    1308d69
  11. aria: randomized two-bubble farewell on inference failure (12 leave + 11 bye per lang)⁠

    Malina +1: Claude Opus 4.8
    98ca451
  12. brain: bill inference to NextNeural org via bill_to (was charging personal token owner)⁠

    Malina +1: Claude Opus 4.8
    988cdc2
  13. aria: casual sign-off on inference failure instead of robotic error⁠

    Malina +1: Claude Opus 4.8
    466ef03
  14. aria: 27B model, messenger style (lowercase, no period), 25s idle nudges, cluster tuning⁠

    Malina +1: Claude Opus 4.8
    8a87a60

  1. fix(brain): use Qwen2.5-VL-72B-Instruct (7B-VL not offered by any provider)⁠

    Malina +1: Claude Opus 4.8
    8e49975

  1. ARIA: event-driven multimodal agent (brain + Cloudflare backend + Messenger UI)⁠

    Malina +1: Claude Opus 4.8
    4131875