Akiragpu / modules /api.py

Commit History

  1. feat(api): skills funcionam via intencao direta no provider local⁠

    Isaac Quarenta
    958bee6
  2. fix: Akira responde 'entendi'/'hm' sem entender⁠

    Isaac Quarenta
    bd8eb23

  1. local-gpu: compact system prompt (3B can't follow huge prompts)

    Isaac Quarenta
    85d1c03
  2. fix: nvidia timeout 60s; hf_inference before llama in chain

    Isaac Quarenta
    8fd89b1
  3. persona: tom sério/curto estilo Kiami

    Isaac Quarenta
    b6444da
  4. nvidia: chain order ahead of mistral; timeout 60s

    Isaac Quarenta
    26cd4c0
  5. fix(app): eliminar crash ChatbotDataMessages 'ping' + spam asyncio; NVIDIA default deepseek-v4.1-flash⁠

    Isaac Quarenta
    cf29563
  6. feat(providers): NVIDIA NIM como provider extra (build.nvidia.com)⁠

    Isaac Quarenta
    c487576
  7. feat(botcore): PV simples espelha o index (buttonId, midia, filtros) + sync api/config⁠

    Isaac Quarenta
    42306bf

  1. Require explicit web search requests⁠

    Isaac Quarenta +1: Copilot
    9e310cf
  2. fix(persona): tom serio-coloquial-logico-racional + fim de respostas com aspas⁠

    Isaac Quarenta
    52cd142
  3. fix(persona): tom serio-coloquial-racional + declaracoes de afeto + strip de aspas em loop

    Isaac Quarenta
    e705438
  4. fix(chat+images): schnell primeiro no HF + interjeicoes/identidade sem web search

    Isaac Quarenta
    02995ae

  1. fix(chat): busca web com timeout 20s + aviso honesto quando nao ha resultados

    Isaac Quarenta
    ebe19ca
  2. fix(chat): gatilho de busca usa deve_pesquisar() (perguntas factuais/temporais tambem vao a web)

    Isaac Quarenta
    d53aaf8
  3. fix(chat): pesquisa web real no caminho Gradio - rewrite deixa de substituir a mensagem e injeta resultados da web

    Isaac Quarenta
    4ea6707
  4. fix(chat): anti-loop de saida (_collapse_repetition) + busca factual alargada + PG retry apos cooldown

    Isaac Quarenta
    08e22c7

  1. perf(ext-gpu): max 180 tokens + deteccao de tunel morto (ngrok 404)

    Isaac Quarenta
    0ba1a0c
  2. feat(chain): external_gpu provider na chain (skills+websearch+persona) + fix historico Gradio6 sem [brackets]

    Isaac Quarenta
    9340691
  3. fix(api): faltavam emotion_analyzer (property) e _warm_emotion_analyzer - __init__ rebentava ao inicio⁠

    Isaac Quarenta
    c2bb650
  4. fix(chat): singleton anti-veneno + _akira_reply defensivo (local_gpu_direct/graceful_sem_chaves) - fim do AttributeError providers

    Isaac Quarenta
    b5fc087
  5. perf(gpu): warmup da API fora da janela GPU + resposta curta na 1a chamada (load consome ~30s dos 60s do FREE)

    Isaac Quarenta
    ffe504c
  6. feat(chat): sem providers ativos responde ja com instrucao de Secrets (graceful_sem_chaves) em vez de recursar

    Isaac Quarenta
    b7e396f
  7. feat(zerogpu): free tier por defeito + anti-recursao graceful + circuit breaker PG⁠

    Isaac Quarenta
    89fb197

  1. fix(build): torch 2.8-2.13 (requisito ZeroGPU HF) + ativacao dinamica do provider local_gpu + mensagem de treino sem GPU dedicada

    Isaac Quarenta
    eebad89
  2. feat(gpu): migracao para Space Gradio GPU (Akiragpu/L4) - modelo local 4-bit em 1 prioridade da chain, QLoRA real, app.py Chat/Treino/Status

    Isaac Quarenta
    bfcd5c0
  3. Fix: Finalize isolation and continuity boost adjustments

    Isaac Quarenta
    7f96cab

  1. fix(contexto): dedup de contexto, isolamento por conversa e placeholder de busca⁠

    Isaac Quarenta
    04bb7b4
  2. Fix: placeholder search fallback, tighten loop detection, improve LSTM topic extraction and conditional injection

    Isaac Quarenta
    661822a

  1. fix(contexto): histórico cruza workers — grava conversation_id, fallback PG/usuario, repõe depth JEV, criatividade proactiva

    Isaac Quarenta
    9c7bd35
  2. fix(jev): boost de continuidade — follow-up encadeia tópico em curso (eleva depth +1.5 e recalcula consciousness)

    Isaac Quarenta
    7dcda01
  3. fix(jev): continuidade de topico — historico no preclassify + continuity boost System 2 + injecao de encadeamento no prompt

    Isaac Quarenta
    eb6ddb6
  4. fix(jev): gate consciência 1-10 define consciousness_10/depth_score antes do uso (fix NameError)

    Isaac Quarenta
    e604a26
  5. fix(jev): depth_score nao definido — NameError em /api/akira

    Isaac Quarenta
    499ca2c
  6. feat(jev): consciência 1-10 → System-1 rápido / System-2 consciente total

    Isaac Quarenta
    bc87f31

  1. feat(jev): System 1 vs System 2 control via depth score + intent criteria improvements

    Isaac Quarenta
    26ec51b
  2. fix(jev): defensive getattr for jev_client — evita AttributeError em workers paralelos

    Isaac Quarenta
    0d1d44d
  3. feat(jev): multi-key rotation (JEV_API_KEY/_2) + /debug/jev-status live ping

    Isaac Quarenta
    8bb3c4f
  4. fix(JEV): espelhar jev_client de LLMManager em AkiraAPI (corrigir AttributeError)

    Isaac Quarenta
    72406c5
  5. feat(jev): System One Model integration + loop_detector refactor for JEV hooks

    Isaac Quarenta
    6109de3
  6. feat(jev): add low-level noul/score/choice methods + jev_questions integration

    Isaac Quarenta
    3276d31
  7. feat(jev): System One Model integration — ultra-fast intent/emotion/routing/moderation

    Isaac Quarenta
    a2faf22

  1. fix(mistral): remove cooldown/blacklist para 403 Forbidden

    Isaac Quarenta
    c672f31
  2. fix(api): _rewrite_query None-safe + _cerebras_tools NameError + query rewrite guard

    Isaac Quarenta
    bf618dd

  1. fix(reply): REPLY Contexto peso máximo, IGNORE LSTM antigos, torna mais formal sobre citada

    Isaac Quarenta
    c0d8486

  1. fix(api): NameError lstm_ctx em _build_context_isolation_layer (free variable)⁠

    Isaac Quarenta
    43d1453
  2. fix: move explicit_mention_pattern and new_topic_signals to enclosing scope of _build_context_isolation_layer to fix NameError

    Isaac Quarenta
    5bed487
  3. fix(api): NameError explicit_mention_pattern em _build_context_isolation_layer⁠

    Isaac Quarenta
    5491f79
  4. fix(api): NameError is_bot_self_response não definido em akira_endpoint⁠

    Isaac Quarenta
    0a5646b
  5. fix(vision+reply+tokens): HF router free Qwen2-VL-7B, LSTM reply lock, max token largo 8192⁠

    Isaac Quarenta
    f0c12a5