Upload

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

bolt_pet/config.py

@@ -0,0 +1,192 @@
+"""Environment configuration for the Bolt desktop pet.
+
+Same lightweight ".env next to the script" pattern as desk_client/bolt_desk.py
+in the main tmn-api repo, so this project can be copied anywhere (it does not
+import anything from that repo) and configured the same way.
+"""
+
+from __future__ import annotations
+
+import os
+import platform
+from pathlib import Path
+
+HERE = Path(__file__).resolve().parent.parent  # project root (one above bolt_pet/)
+
+
+def _load_env() -> None:
+    env_path = HERE / ".env"
+    if not env_path.exists():
+        return
+    for line in env_path.read_text(encoding="utf-8").splitlines():
+        line = line.strip()
+        if not line or line.startswith("#") or "=" not in line:
+            continue
+        key, _, value = line.partition("=")
+        os.environ.setdefault(key.strip(), value.strip())
+
+
+_load_env()
+
+
+def _node_name() -> str:
+    try:
+        return platform.node() or "desktop"
+    except Exception:
+        return "desktop"
+
+
+# ── server / identity ───────────────────────────────────────────────────────
+
+SERVER_URL = os.environ.get("BOLT_SERVER_URL", "").rstrip("/")
+API_KEY = os.environ.get("DESK_API_KEY", "")
+SESSION_ID = os.environ.get("DESK_SESSION_ID", "pet-" + _node_name())
+
+# ── wake word ────────────────────────────────────────────────────────────────
+# openWakeWord model trained specifically for "thunderbolt" — same pattern as
+# desk_client/bolt_desk.py's WAKE_MODEL_FILE (bolt.onnx / "hey bolt") in the
+# main repo, resolved relative to the project root so it sits next to .env.
+
+WAKE_MODEL_PATH = str(HERE / os.environ.get("WAKE_MODEL_FILE", "thunderbolt.onnx"))
+WAKE_WORD_THRESHOLD = float(os.environ.get("WAKE_WORD_THRESHOLD", "0.5"))
+# How often (independent of prediction, which runs every frame) the wake
+# listener yields control back to its caller via on_tick — e.g. the
+# heartbeat poll in controller.py during quiet stretches with no wake word.
+WAKE_CHECK_INTERVAL_SECONDS = float(os.environ.get("WAKE_CHECK_INTERVAL_SECONDS", "1.2"))
+
+# ── STT (Deepgram, same as bolt_desk.py) ────────────────────────────────────
+
+DEEPGRAM_API_KEY = os.environ.get("DEEPGRAM_API_KEY", "")
+DEEPGRAM_MODEL = os.environ.get("DEEPGRAM_MODEL", "nova-3")
+
+# ── TTS (ElevenLabs, requested as raw PCM so playback needs no external
+# player binary — cross-platform via sounddevice instead of shelling out to
+# mpv/ffplay like bolt_desk.py does on Linux) ───────────────────────────────
+
+ELEVENLABS_API_KEY = os.environ.get("ELEVENLABS_API_KEY", "")
+ELEVENLABS_VOICE_ID = os.environ.get("ELEVENLABS_VOICE_ID", "")
+ELEVENLABS_MODEL_ID = os.environ.get("ELEVENLABS_MODEL_ID", "eleven_flash_v2")
+# ElevenLabs PCM output formats are named pcm_<sample_rate>.
+TTS_SAMPLE_RATE = int(os.environ.get("TTS_SAMPLE_RATE", "24000"))
+
+# ── mic / VAD (same tuning knobs as bolt_desk.py) ───────────────────────────
+
+MIC_DEVICE = os.environ.get("MIC_DEVICE", "") or None  # sounddevice name/index
+SPEAKER_DEVICE = os.environ.get("SPEAKER_DEVICE", "") or None
+
+RMS_THRESHOLD = int(os.environ.get("VAD_RMS_THRESHOLD", "300"))
+SILENCE_END_SEC = float(os.environ.get("VAD_SILENCE_END_SEC", "1.2"))
+MAX_UTTERANCE_S = float(os.environ.get("VAD_MAX_UTTERANCE_SECONDS", "15"))
+MIN_UTTERANCE_S = float(os.environ.get("VAD_MIN_UTTERANCE_SECONDS", "0.4"))
+
+COMMAND_TIMEOUT_SECONDS = int(os.environ.get("COMMAND_TIMEOUT_SECONDS", "30"))
+HEARTBEAT_INTERVAL_SECONDS = float(os.environ.get("HEARTBEAT_INTERVAL_SECONDS", "60"))
+
+# ── barge-in (interrupt playback by talking over it) ────────────────────────
+# The mic stays live while the pet talks; sustained loud frames cut playback
+# short. The threshold is deliberately well above VAD_RMS_THRESHOLD because
+# the mic also hears the pet's own voice through the speakers — raise it
+# further (or set BARGE_IN=false) if playback keeps interrupting itself.
+
+BARGE_IN = os.environ.get("BARGE_IN", "true").lower() in ("1", "true", "yes", "on")
+BARGE_IN_RMS_THRESHOLD = int(os.environ.get("BARGE_IN_RMS_THRESHOLD", str(RMS_THRESHOLD * 4)))
+BARGE_IN_FRAMES = int(os.environ.get("BARGE_IN_FRAMES", "4"))  # consecutive loud frames (80ms each)
+
+# ── streaming TTS ───────────────────────────────────────────────────────────
+# ElevenLabs' /stream endpoint + chunked playback: the pet starts talking
+# after the first PCM chunk instead of after the whole clip is synthesized.
+
+TTS_STREAMING = os.environ.get("TTS_STREAMING", "true").lower() in ("1", "true", "yes", "on")
+
+# ── screen context ──────────────────────────────────────────────────────────
+# Appends the active window's title to what you say, so "what's this error?"
+# has a referent. The desk API takes text only, so this is a text annotation
+# (no screenshot upload).
+
+SCREEN_CONTEXT = os.environ.get("SCREEN_CONTEXT", "true").lower() in ("1", "true", "yes", "on")
+
+# ── quiet hours / do-not-disturb ────────────────────────────────────────────
+# Comma-separated HH:MM-HH:MM ranges (wrapping midnight is fine). While
+# napping the pet dims, stops wandering, and makes no proactive noise —
+# wake word and click-to-talk still work.
+
+QUIET_HOURS = os.environ.get("QUIET_HOURS", "")
+DND_ON_FULLSCREEN = os.environ.get("DND_ON_FULLSCREEN", "true").lower() in ("1", "true", "yes", "on")
+
+# ── desktop notification bridge ─────────────────────────────────────────────
+# Mirrors desktop notifications to the server so Bolt can react to them.
+# Off by default: every forwarded notification costs a converse() round trip.
+
+NOTIFICATION_BRIDGE = os.environ.get("NOTIFICATION_BRIDGE", "false").lower() in ("1", "true", "yes", "on")
+# Regex matched against "<app>: <summary> <body>"; empty means "everything".
+NOTIFICATION_FILTER = os.environ.get("NOTIFICATION_FILTER", "")
+NOTIFICATION_MIN_INTERVAL_SECONDS = float(os.environ.get("NOTIFICATION_MIN_INTERVAL_SECONDS", "60"))
+
+# ── conversation history ────────────────────────────────────────────────────
+
+HISTORY_LIMIT = int(os.environ.get("HISTORY_LIMIT", "100"))
+
+# ── push-to-talk ────────────────────────────────────────────────────────────
+# Global hotkey (needs `pynput`; unavailable on most Wayland sessions, in
+# which case it logs once and the wake word / tray still work). Empty to
+# disable.
+
+PUSH_TO_TALK_HOTKEY = os.environ.get("PUSH_TO_TALK_HOTKEY", "ctrl+alt+space")
+
+# ── wake-word tuning ────────────────────────────────────────────────────────
+# Scores this far below the threshold are recorded as "near misses" and shown
+# in the tray's wake-word tuner, so the threshold can be set from evidence.
+
+WAKE_NEAR_MISS_MARGIN = float(os.environ.get("WAKE_NEAR_MISS_MARGIN", "0.2"))
+WAKE_NEAR_MISS_LIMIT = int(os.environ.get("WAKE_NEAR_MISS_LIMIT", "40"))
+
+SAMPLE_RATE = 16000  # mic capture / STT rate
+FRAME_LEN = 1280  # 80ms @ 16kHz — matches bolt_desk.py's chunking
+
+# ── pet window ───────────────────────────────────────────────────────────────
+
+PET_SIZE = int(os.environ.get("PET_SIZE", "160"))  # on-screen pixel size (square)
+PET_START_X = os.environ.get("PET_START_X", "")  # blank = bottom-right of primary screen
+PET_START_Y = os.environ.get("PET_START_Y", "")
+PET_ALWAYS_ON_TOP = os.environ.get("PET_ALWAYS_ON_TOP", "true").lower() in ("1", "true", "yes", "on")
+IDLE_ANIMATION_FPS = float(os.environ.get("IDLE_ANIMATION_FPS", "6"))
+
+# ── wandering ────────────────────────────────────────────────────────────────
+# The pet strolls to a random spot on its own while idle. Only ever moves when
+# it's IDLE and not speaking/being dragged, so it never walks out from under a
+# speech bubble mid-sentence.
+
+PET_WANDER = os.environ.get("PET_WANDER", "true").lower() in ("1", "true", "yes", "on")
+# Average seconds of standing still between strolls (each wait is randomized
+# to 0.5x–1.5x this, so the pet doesn't move on an obvious metronome).
+PET_WANDER_INTERVAL_SECONDS = float(os.environ.get("PET_WANDER_INTERVAL_SECONDS", "45"))
+PET_WANDER_SPEED = float(os.environ.get("PET_WANDER_SPEED", "90"))  # pixels/second
+# Cap on how far one stroll can be, so it doesn't teleport across a 4K screen.
+PET_WANDER_MAX_DISTANCE = float(os.environ.get("PET_WANDER_MAX_DISTANCE", "600"))
+PET_WANDER_MARGIN = int(os.environ.get("PET_WANDER_MARGIN", "20"))  # keep off screen edges
+
+# ── mouse behaviour ─────────────────────────────────────────────────────────
+# The sprite is drawn in a square translucent window, so its transparent
+# corners would otherwise swallow clicks meant for whatever is underneath.
+# PET_SHAPED_INPUT masks the window's input region to the sprite's own opaque
+# pixels; PET_CLICK_THROUGH goes further and makes the whole pet ignore the
+# mouse (tray-only control until you turn it back off).
+
+PET_SHAPED_INPUT = os.environ.get("PET_SHAPED_INPUT", "true").lower() in ("1", "true", "yes", "on")
+PET_CLICK_THROUGH = os.environ.get("PET_CLICK_THROUGH", "false").lower() in ("1", "true", "yes", "on")
+# Snap flush to a screen edge when dropped/parked within this many pixels of it.
+PET_EDGE_SNAP = os.environ.get("PET_EDGE_SNAP", "true").lower() in ("1", "true", "yes", "on")
+PET_SNAP_MARGIN = int(os.environ.get("PET_SNAP_MARGIN", "48"))
+
+
+def is_configured() -> bool:
+    return bool(SERVER_URL and API_KEY)
+
+
+def missing_config() -> list[str]:
+    missing = []
+    if not SERVER_URL:
+        missing.append("BOLT_SERVER_URL")
+    if not API_KEY:
+        missing.append("DESK_API_KEY")
+    return missing