Add fully local conversational AI pipeline for Reachy Mini

Local STT (Qwen3-ASR), VLM (Gemma 4 26B-A4B), and TTS (Spark-TTS) running
on Apple Silicon via MLX, with bracket-tag action system for nod, shake,
wiggle, dance, photo, and pre-recorded emotions.

take_photo.sh

@@ -0,0 +1,24 @@
+#!/bin/bash
+# Take a photo from Reachy Mini camera and copy it locally
+# Usage: ./take_photo.sh [output_filename]
+
+OUTPUT="${1:-photo.jpg}"
+
+sshpass -p 'root' ssh -o StrictHostKeyChecking=no pollen@reachy-mini.local "/venvs/mini_daemon/bin/python -c \"
+from reachy_mini import ReachyMini
+import cv2
+import time
+
+with ReachyMini() as mini:
+    time.sleep(1)
+    for i in range(5):
+        frame = mini.media.get_frame()
+        if frame is not None:
+            cv2.imwrite('/tmp/photo.jpg', frame)
+            print('captured')
+            break
+        time.sleep(0.5)
+\""
+
+sshpass -p 'root' scp -o StrictHostKeyChecking=no pollen@reachy-mini.local:/tmp/photo.jpg "$OUTPUT"
+echo "Saved to $OUTPUT"