Add microphone picker and device management features

- Implement `list_input_devices` to retrieve and filter input-capable audio devices.
- Create `MicPickerDialog` for selecting and saving microphone settings.
- Add `set_env_value` function to update .env file with selected microphone index.
- Update UI components to integrate microphone selection functionality.
- Enhance tests for microphone device handling and environment variable management.

bolt_pet/config.py

@@ -9,6 +9,7 @@ from __future__ import annotations
 
 import os
 import platform
+import re
 from pathlib import Path
 
 HERE = Path(__file__).resolve().parent.parent  # project root (one above bolt_pet/)
@@ -29,6 +30,26 @@ def _load_env() -> None:
 _load_env()
 
 
+def set_env_value(key: str, value: str) -> None:
+    """Write *key=value* into .env, in place — replacing (or uncommenting)
+    an existing line for it, appending a new one otherwise. Used by the tray's
+    microphone picker so a device pick survives a restart without hand-editing
+    the file. Settings read once at import time (like MIC_DEVICE) still need
+    that restart to take effect; this only updates the file and os.environ."""
+    env_path = HERE / ".env"
+    lines = env_path.read_text(encoding="utf-8").splitlines() if env_path.exists() else []
+    pattern = re.compile(rf"^\s*#?\s*{re.escape(key)}\s*=")
+    new_line = f"{key}={value}"
+    for i, line in enumerate(lines):
+        if pattern.match(line):
+            lines[i] = new_line
+            break
+    else:
+        lines.append(new_line)
+    env_path.write_text("\n".join(lines) + "\n", encoding="utf-8")
+    os.environ[key] = value
+
+
 def _node_name() -> str:
     try:
         return platform.node() or "desktop"
@@ -115,7 +136,22 @@ DIALOGUE_VOICES = os.environ.get("DIALOGUE_VOICES", "")
 
 # ── mic / VAD (same tuning knobs as bolt_desk.py) ───────────────────────────
 
-MIC_DEVICE = os.environ.get("MIC_DEVICE", "") or None  # sounddevice name/index
+def _mic_device(raw: str):
+    """sounddevice treats an int index and a string name very differently: a
+    string is matched as a (fragile, often ambiguous) substring against every
+    device name, while an int is used as-is. .env only ever gives us a
+    string, so a numeric one — what the tray's mic picker saves, since the
+    same physical device usually shows up once per host API (MME,
+    DirectSound, WASAPI, ...) under the same name — has to be cast back to
+    int here, or it goes through the substring path and matches nothing (or
+    everything) instead."""
+    raw = raw.strip()
+    if not raw:
+        return None
+    return int(raw) if raw.lstrip("-").isdigit() else raw
+
+
+MIC_DEVICE = _mic_device(os.environ.get("MIC_DEVICE", ""))
 SPEAKER_DEVICE = os.environ.get("SPEAKER_DEVICE", "") or None
 
 RMS_THRESHOLD = int(os.environ.get("VAD_RMS_THRESHOLD", "300"))