Run any Skill in Manus with one click

chappie-config

Stars5

Forks0

UpdatedJune 22, 2026 at 10:55

CHAPPiE's configuration system. Use when adding new settings, modifying config.py, updating schemas, or working with CHAPPIE_CONFIG.json.

Installation

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.

Run Skill in Manus

Source

017pixel

017pixel/CHAPPiE

View GitHub Repository View Creator Repositories

Download

Run Skill in Manus

Related occupationsSOC

Based on SOC occupation classification

Software DevelopersComputer and Mathematical Occupations·SOC 15-1252

SKILL.md

readonly

name	chappie-config
description	CHAPPiE's configuration system. Use when adding new settings, modifying config.py, updating schemas, or working with CHAPPIE_CONFIG.json.

CHAPPiE Configuration System

Configuration Flow

CHAPPIE_CONFIG.json  →  config/root_config.py  →  config/config.py (Settings class)
                          ↓                            ↓
                    config/secrets.py          API: /settings endpoint
                    config/addSecrets.py       Frontend: settings-page.tsx

Key Files

File	Role
`config/config.py`	Settings class, LLMProvider enum, ALL config defaults
`config/root_config.py`	JSON file I/O for `CHAPPIE_CONFIG.json`
`CHAPPIE_CONFIG.example.json`	Template (not in git)
`config/secrets.py`	API keys (not in git)
`api/schemas.py`	SettingsSnapshot, SettingsUpdate Pydantic models
`api/routers/runtime.py`	`GET/POST /settings`, `_settings_snapshot()`

Adding a New Setting

Add attribute to Settings class in config/config.py
Add _get_val() call with default value
Add to update_from_ui() for persistence
Add to _export_root_values() for JSON export
Add field to SettingsSnapshot and SettingsUpdate in api/schemas.py
Add to _settings_snapshot() in api/routers/runtime.py
Add to frontend/src/pages/settings-page.tsx SETTINGS_DEFS array

Current Settings Groups

Group	Settings
Provider	llm_provider, vllm_model, ollama_model, cerebras_model
Generation	temperature, repetition_penalty, max_tokens, thinking/answer limits
Memory	memory_top_k, memory_min_relevance, stm_summary_threshold
Steering	enable_steering, steering_model
Intent	intent_provider, query_extraction_provider
Training	training_chappie_model

Provider Values

class LLMProvider(str, Enum):
    OLLAMA = "ollama"
    CEREBRAS = "cerebras"
    VLLM = "vllm"

Hot Reload

settings.update_from_ui() → updates in-memory values
backend.apply_runtime_settings(force=True) → rebuilds brain/intent processor
Settings persist via _persist_to_root_config() → writes to CHAPPIE_CONFIG.json

Key Rules

API keys NEVER in config.py — always in secrets.py or CHAPPIE_CONFIG.json
CHAPPIE_CONFIG.json is gitignored — never commit real config
Float settings use float() conversion, bool use bool(), int use int()
_parse_provider() handles "auto", None, and "" → returns None

More from this repository

same repository

chappie-architecture

017pixel/CHAPPiE

CHAPPiE's brain, memory, and life simulation architecture. Use when modifying core pipelines, brain agents, steering, or global workspace.

2026-06-225

chappie-backend

017pixel/CHAPPiE

Backend development for CHAPPiE. Use when working on FastAPI APIs, vLLM brain, Cerebras integration, training daemon, or backend_wrapper.py.

2026-06-225

chappie-frontend

017pixel/CHAPPiE

CHAPPiE's React frontend. Use when modifying UI pages, components, Tailwind styling, or the chat streaming experience.

2026-06-225

chappie-prompts

017pixel/CHAPPiE

CHAPPiE's prompt engineering. Use when modifying system prompts, emotion templates, generation budget instructions, or Cerebras formatting prompts.

2026-06-225

chappie-testing

017pixel/CHAPPiE

CHAPPiE testing strategy. Use when writing or running tests, CI/CD, or validating changes before push.

2026-06-225

chappie-update

017pixel/CHAPPiE

Führt ein vollständiges CHAPPiE-Update durch: git pull, Dienste neustarten, Tests, Health-Check, Reparatur bei Bedarf.

2026-06-225

CHAPPiE Configuration System

Configuration Flow

CHAPPIE_CONFIG.json → config/root_config.py → config/config.py (Settings class) ↓ ↓ config/secrets.py API: /settings endpoint config/addSecrets.py Frontend: settings-page.tsx

Key Files

File

Role

config/config.py

Settings class, LLMProvider enum, ALL config defaults

config/root_config.py

JSON file I/O for CHAPPIE_CONFIG.json

CHAPPIE_CONFIG.example.json

Template (not in git)

config/secrets.py

API keys (not in git)

api/schemas.py

SettingsSnapshot, SettingsUpdate Pydantic models

api/routers/runtime.py

GET/POST /settings, _settings_snapshot()

Adding a New Setting

Add attribute to Settings class in config/config.py

Add _get_val() call with default value

Add to update_from_ui() for persistence

Add to _export_root_values() for JSON export

Add field to SettingsSnapshot and SettingsUpdate in api/schemas.py

Add to _settings_snapshot() in api/routers/runtime.py

Add to frontend/src/pages/settings-page.tsx SETTINGS_DEFS array

Current Settings Groups

Group

Settings

Provider

llm_provider, vllm_model, ollama_model, cerebras_model

Generation

temperature, repetition_penalty, max_tokens, thinking/answer limits

Memory

memory_top_k, memory_min_relevance, stm_summary_threshold

Steering

enable_steering, steering_model

Intent

intent_provider, query_extraction_provider

Training

training_chappie_model

Provider Values

class LLMProvider(str, Enum): OLLAMA = "ollama" CEREBRAS = "cerebras" VLLM = "vllm"

Hot Reload

settings.update_from_ui() → updates in-memory values

backend.apply_runtime_settings(force=True) → rebuilds brain/intent processor

Settings persist via _persist_to_root_config() → writes to CHAPPIE_CONFIG.json

Key Rules

API keys NEVER in config.py — always in secrets.py or CHAPPIE_CONFIG.json

CHAPPIE_CONFIG.json is gitignored — never commit real config

Float settings use float() conversion, bool use bool(), int use int()

_parse_provider() handles "auto", None, and "" → returns None