webclaw/env.example
Jacob Magar af304eda7f docs(noxa-9fw.4): describe gemini cli as primary llm backend
- Update CLAUDE.md: provider chain, LLM modules section, CLI examples
- Update env.example: add GEMINI_MODEL, reorder providers (Gemini first)
- Update noxa-llm/src/lib.rs crate doc comment
2026-04-11 07:36:19 -04:00

46 lines
1.2 KiB
Text

# ============================================
# Noxa Configuration
# Copy to .env and fill in your values
# ============================================
# --- LLM Providers ---
# Gemini CLI (primary provider — requires `gemini` binary on PATH)
# GEMINI_MODEL=gemini-2.5-pro # defaults to gemini-2.5-pro
# Ollama (fallback; local inference)
OLLAMA_HOST=http://localhost:11434
OLLAMA_MODEL=qwen3:8b
# OpenAI (optional cloud fallback)
# OPENAI_API_KEY — set your OpenAI key
# OPENAI_BASE_URL — defaults to https://api.openai.com/v1
# OPENAI_MODEL — defaults to gpt-4o-mini
# Anthropic (optional cloud fallback)
# ANTHROPIC_API_KEY — set your Anthropic key
# ANTHROPIC_MODEL — defaults to claude-sonnet-4-20250514
# --- Proxy ---
# Single proxy
# NOXA_PROXY=http://user:pass@host:port
# Proxy file (one per line: host:port:user:pass)
# NOXA_PROXY_FILE=/path/to/proxies.txt
# --- Server (noxa-server only) ---
# NOXA_PORT=3000
# NOXA_HOST=0.0.0.0
# NOXA_AUTH_KEY=your-auth-key
# NOXA_MAX_CONCURRENCY=50
# NOXA_JOB_TTL_SECS=3600
# NOXA_MAX_JOBS=100
# --- CLI LLM overrides ---
# NOXA_LLM_PROVIDER=ollama
# NOXA_LLM_MODEL=qwen3:8b
# NOXA_LLM_BASE_URL=http://localhost:11434
# --- Logging ---
# NOXA_LOG=info