Files
project-lyra/lyra/config.py
T
serversdown 43697f8340 fix: ntfy ping is her personal text to Brian, by her decision — not a thought dump
Feedback: the push broadcast her raw internal thought ("Eelis Parssinen's
victory is a reminder...") — read like a journal entry, not her texting him.

Now the flow matches the intent: she thinks/journals, then *decides* "I should
tell Brian about this." think() asks for an optional `reach_out` — a real text
message addressed TO him in her own voice, written only when she chooses to. The
ping sends that message (title "Lyra", like a text from her), never the internal
thought. No reach_out = nothing sent (most thoughts stay hers).

- Pinging decoupled from the salience score: her decision (a reach_out) drives it,
  not a threshold. PING_SALIENCE is now an optional floor (default 0.0).
- Defensive: reject the placeholder echo ("reach_out"), too-short junk, or the
  thought pasted back as the message.
- notify.push: title now optional (omitted -> cleaner text-style notification).

Verified live: 3 passes kept private; a decided reach-out lands as a personal
text. Suite 67 green, ruff clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
2026-06-22 01:39:11 +00:00

73 lines
3.5 KiB
Python

"""Environment-driven configuration."""
from __future__ import annotations
import os
from dataclasses import dataclass
from pathlib import Path
from dotenv import load_dotenv
load_dotenv()
@dataclass(frozen=True)
class Config:
local_base_url: str
local_model: str
mi50_base_url: str # OpenAI-compatible llama.cpp server on the MI50 box
mi50_model: str
openai_api_key: str
cloud_model: str # cloud model for bulk/consolidation work (cheap)
chat_model: str # cloud model for live chat (stronger; persona fidelity)
embed_backend: str # "cloud" (OpenAI) or "local" (Ollama)
embed_model: str # OpenAI embedding model
local_embed_model: str # Ollama embedding model
embed_base_url: str # Ollama endpoint for embeddings (own box, decoupled from local chat)
summary_backend: str # "local" or "cloud" — backend used to compact memory
db_path: Path
# Proactive reach-out (ntfy push). Empty ntfy_url disables pinging.
ntfy_url: str # base url, e.g. "http://10.0.0.41:8090"
ntfy_topic: str # topic to publish to, e.g. "lyra"
web_url: str # base url of the Lyra web app, for push tap-through links
timezone: str # IANA tz for quiet hours / local time
ping_salience: float # min thought salience to push (eager = ~0.7)
ping_cooldown_min: int # min minutes between pushes (eager = 0)
ping_quiet_hours: str # local "start-end" 24h window to stay silent, e.g. "1-9"
# External input feed (her #1: react to the world). Comma-separated RSS/Atom URLs.
feeds: tuple[str, ...]
feed_react_prob: float # chance a would-be new thread reacts to a feed item instead
def _csv(name: str, default: str) -> tuple[str, ...]:
raw = os.getenv(name, default)
return tuple(u.strip() for u in raw.split(",") if u.strip())
def load() -> Config:
return Config(
local_base_url=os.getenv("LOCAL_BASE_URL", "http://localhost:11434"),
local_model=os.getenv("LOCAL_MODEL", "qwen2.5:7b-instruct"),
mi50_base_url=os.getenv("MI50_BASE_URL", "http://10.0.0.42:8080/v1"),
mi50_model=os.getenv("MI50_MODEL", "local-gpu"),
openai_api_key=os.getenv("OPENAI_API_KEY", ""),
cloud_model=os.getenv("CLOUD_MODEL", "gpt-4o-mini"),
chat_model=os.getenv("CHAT_MODEL", "gpt-4o"),
embed_backend=os.getenv("EMBED_BACKEND", "cloud").lower(),
embed_model=os.getenv("EMBED_MODEL", "text-embedding-3-small"),
local_embed_model=os.getenv("LOCAL_EMBED_MODEL", "nomic-embed-text"),
# Embeddings can live on their own always-on box, separate from the local
# chat backend. Defaults to LOCAL_BASE_URL so existing setups are unchanged.
embed_base_url=os.getenv("EMBED_BASE_URL", os.getenv("LOCAL_BASE_URL", "http://localhost:11434")),
summary_backend=os.getenv("SUMMARY_BACKEND", "local").lower(),
db_path=Path(os.getenv("LYRA_DB_PATH", "data/lyra.db")),
ntfy_url=os.getenv("NTFY_URL", "").rstrip("/"),
ntfy_topic=os.getenv("NTFY_TOPIC", "lyra"),
web_url=os.getenv("LYRA_WEB_URL", "").rstrip("/"),
timezone=os.getenv("LYRA_TIMEZONE", "America/New_York"),
ping_salience=float(os.getenv("PING_SALIENCE", "0.0")), # her decision drives pinging; optional floor
ping_cooldown_min=int(os.getenv("PING_COOLDOWN_MIN", "0")),
ping_quiet_hours=os.getenv("PING_QUIET_HOURS", "1-9"),
feeds=_csv("LYRA_FEEDS", "https://hnrss.org/frontpage,https://www.pokernews.com/rss.php"),
feed_react_prob=float(os.getenv("FEED_REACT_PROB", "0.5")),
)