القائمة
Backend development for CHAPPiE. Use when working on FastAPI APIs, vLLM brain, Cerebras integration, training daemon, or backend_wrapper.py.
التثبيت باستخدام Codex أو Claude انسخ هذا Prompt والصقه في Codex أو Claude أو مساعد آخر ليراجع صفحة Skill ويثبّتها لك.
استنادا إلى تصنيف SOC المهني
CHAPPiE's brain, memory, and life simulation architecture. Use when modifying core pipelines, brain agents, steering, or global workspace.
CHAPPiE's configuration system. Use when adding new settings, modifying config.py, updating schemas, or working with CHAPPIE_CONFIG.json.
CHAPPiE's React frontend. Use when modifying UI pages, components, Tailwind styling, or the chat streaming experience.
CHAPPiE's prompt engineering. Use when modifying system prompts, emotion templates, generation budget instructions, or Cerebras formatting prompts.
CHAPPiE testing strategy. Use when writing or running tests, CI/CD, or validating changes before push.
Führt ein vollständiges CHAPPiE-Update durch: git pull, Dienste neustarten, Tests, Health-Check, Reparatur bei Bedarf.
| name | chappie-backend |
| description | Backend development for CHAPPiE. Use when working on FastAPI APIs, vLLM brain, Cerebras integration, training daemon, or backend_wrapper.py. |
| File | Role |
|---|---|
api/main.py | App entry, routers, root JSON endpoint |
api/routers/*.py | chat, system, memory, runtime, training, context |
api/schemas.py | Pydantic models |
web_infrastructure/backend_wrapper.py | Main CHAPPiE backend class |
brain/vllm_brain.py | vLLM OpenAI-compatible client |
brain/base_brain.py | Abstract base + GenerationConfig |
Chappies_Trainingspartner/daemon_manager.py | Subprocess daemon control |
llama-3.1-8b)_format_via_cerebras)backend_wrapper.py (~line 602)<cot> + <antwort> tagged blocksimport sys
from unittest.mock import MagicMock
# Mock all brain dependencies before import
sys.modules["ollama"] = MagicMock()
sys.modules["cerebras"] = MagicMock()
sys.modules["chromadb"] = MagicMock()
# Then import from brain.vllm_brain directly
repetition_penalty muss via extra_body, nicht direkt als Keywordenable_thinking=True für Qwen3.5 Modelle (in _prepare_extra_body)_detect_reasoning_loop() in vllm_brain.pyconfig.config.settings → update_from_ui() persistiert