# Local backend (Ollama) — free, private. Point this at your home-lab Ollama.
LOCAL_BASE_URL=http://localhost:11434
LOCAL_MODEL=qwen2.5:7b-instruct

# MI50 backend — OpenAI-compatible llama.cpp server on the home-lab GPU box (CT202).
MI50_BASE_URL=http://10.0.0.42:8080/v1
MI50_MODEL=local-gpu

# Cloud backend (OpenAI) — higher quality, costs money.
OPENAI_API_KEY=
CLOUD_MODEL=gpt-4o-mini   # cheap model for bulk consolidation (summaries/profile/etc.)
CHAT_MODEL=gpt-4o         # stronger model for live chat (better persona fidelity)

# Embeddings: "cloud" (OpenAI) or "local" (Ollama). A database is tied to whichever
# backend created it — don't switch this against an existing DB (vector spaces differ).
EMBED_BACKEND=cloud
EMBED_MODEL=text-embedding-3-small
LOCAL_EMBED_MODEL=nomic-embed-text

# Backend used to compact old sessions into summaries ("local" keeps it free).
SUMMARY_BACKEND=local

# Where Lyra stores her memory.
LYRA_DB_PATH=data/lyra.db

# Optional: run embeddings on a separate always-on Ollama (decoupled from
# LOCAL_BASE_URL, which serves local chat). Defaults to LOCAL_BASE_URL if unset.
# EMBED_BASE_URL=http://127.0.0.1:11434

# --- Thought-loop reach-out (ntfy push) ---
# Leave NTFY_URL empty to disable proactive pings entirely.
NTFY_URL=
NTFY_TOPIC=lyra
LYRA_WEB_URL=
PING_SALIENCE=0.7        # min thought salience to push (eager)
PING_COOLDOWN_MIN=0      # min minutes between pushes (0 = none)
PING_QUIET_HOURS=1-9     # local hours to stay silent
LYRA_TIMEZONE=America/New_York

# --- External input feeds (RSS/Atom, comma-separated) ---
LYRA_FEEDS=https://hnrss.org/frontpage,https://www.pokernews.com/rss.php
FEED_REACT_PROB=0.5      # chance a new thought reacts to a feed item