# LLM provider (OpenAI-compatible endpoint)
LLM_BASE_URL=http://localhost:11434/v1/
# For Ollama, API key is not required but a placeholder is needed.
LLM_API_KEY=ollama

# Default model for inline completions (e.g., gpt-oss:20b, qwen3:8b)
LLM_MODEL=gpt-oss:20b

# Pro-tier model (defaults to LLM_MODEL if unset)
PRO_LLM_MODEL=gpt-oss:20b

# Vision model for OCR (e.g., qwen3-vl:30b, llava)
VLM_MODEL=qwen3-vl:30b

# API key for the FastAPI app (change in production)
API_KEY=your-secret-key-here

# PRO completion timeout (seconds)
PRO_COMPLETION_TIMEOUT=1200

# Concurrency limits
STANDARD_CONCURRENCY_LIMIT=5
PRO_CONCURRENCY_LIMIT=20

# Legacy fallback: if LLM_BASE_URL is not set, OLLAMA_HOST will be auto-converted to /v1/ path
#OLLAMA_HOST=http://localhost:11434

# TTS/ASR settings (see README for full list)
TTS_ASR_DEVICE=auto