Menu
CHAPPiE's React frontend. Use when modifying UI pages, components, Tailwind styling, or the chat streaming experience.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
CHAPPiE's brain, memory, and life simulation architecture. Use when modifying core pipelines, brain agents, steering, or global workspace.
Backend development for CHAPPiE. Use when working on FastAPI APIs, vLLM brain, Cerebras integration, training daemon, or backend_wrapper.py.
CHAPPiE's configuration system. Use when adding new settings, modifying config.py, updating schemas, or working with CHAPPIE_CONFIG.json.
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-frontend |
| description | CHAPPiE's React frontend. Use when modifying UI pages, components, Tailwind styling, or the chat streaming experience. |
useQuery, useMutation)frontend/src/pages/)| Page | File | Key Features |
|---|---|---|
| Chat | chat-page.tsx | Token streaming, message queue, thinking animation, CoT/Answer boxes |
| Settings | settings-page.tsx | All 40+ settings, emotion sliders, neural mapping, auto-save |
| Memories | memories-page.tsx | LTM search, STM buffer, session history, cleanup/wipe |
| Life | life-page.tsx | Homeostasis, needs, world model (refetchInterval: 3s) |
| Growth | growth-page.tsx | Planning, forecast, social arcs (refetchInterval: 3s) |
| Training | training-page.tsx | Daemon control, logs, config (refetchInterval: 5s) |
| Debug | debug-page.tsx | Metadata, debug entries (refetchInterval: 2s) |
processMessage() → SSE stream via api.sendMessageStream()event: token events with token_type: "answer"|"reasoning"turn_finished → final message with metadata (formatted_cot, formatted_answer)autoScrollRef tracks user positionautoScrollRef.current = trueformatted_cot from metadataformatted_answer (preferred) or raw contentwhitespace-pre-line for formatted text with line breaksrounded-none (square corners) everywhereember (primary), pine (success), night (bg), ink (darkest), mist (text)shadow-glass for card-like elementstext-[10px] uppercase tracking-widest for labels../lib/format → parseEmotionalText() in frontend/src/lib/format.ts