Update 2026-04-22 15:37:55

API/llava_api.py

@@ -84,6 +84,15 @@ def add_to_history(user_msg: str, assistant_msg: str):
 
 
 def call_llava(prompt: str, img_b64, num_predict: int = 200, use_history: bool = False) -> str:
+    """
+    Single synchronous VLM call — same mechanism as Marcus_v1's _call_llava.
+
+    With YOLO on CPU (config_Vision.json::yolo_device="cpu"), there is no
+    iGPU contention to guard against, so the v1-style plain call is the
+    right shape. num_batch and num_ctx are still passed per-request because
+    Ollama's compute-graph pre-allocation pays attention to them (default
+    batch=512/ctx=4096 would OOM on the Jetson).
+    """
     if not VLM_ENABLED:
         return ""    # safe-mode — caller must handle empty string
     messages = []
@@ -93,23 +102,6 @@ def call_llava(prompt: str, img_b64, num_predict: int = 200, use_history: bool =
     if img_b64:
         msg["images"] = [img_b64]
     messages.append(msg)
-
-    # When an image is attached, pause YOLO to free iGPU memory for the
-    # vision-encoder activations (~1.5 GiB). Without this, concurrent YOLO
-    # inference + Qwen vision-encode exceeds the 15 GiB Jetson iGPU budget
-    # and the llama runner is reaped by the OOM killer (status code: 500).
-    # Text-only calls skip the pause — they fit easily and YOLO stays hot.
-    _paused = False
-    if img_b64:
-        try:
-            from API.yolo_api import yolo_pause, yolo_resume, YOLO_AVAILABLE
-            if YOLO_AVAILABLE:
-                yolo_pause()
-                _paused = True
-        except Exception:
-            pass
-
-    try:
     r = _client.chat(model=OLLAMA_MODEL, messages=messages,
                      options={
                          "temperature": 0.0,
@@ -118,13 +110,6 @@ def call_llava(prompt: str, img_b64, num_predict: int = 200, use_history: bool =
                          "num_ctx":     NUM_CTX,
                      })
     return r["message"]["content"].strip()
-    finally:
-        if _paused:
-            try:
-                from API.yolo_api import yolo_resume
-                yolo_resume()
-            except Exception:
-                pass
 
 
 def parse_json(raw: str):
@@ -197,13 +182,21 @@ def ask_goal(goal: str, img_b64) -> dict:
 
 
 def ask_talk(command: str, img_b64, facts: str = "") -> dict:
-    """Handle talk-only commands using the YAML talk_prompt."""
+    """
+    Handle talk-only commands using the YAML talk_prompt.
+
+    NOTE: use_history is off. Accumulated turns push the prompt past
+    qwen2.5vl's 2048-token KV cache; Ollama then truncates and tries to
+    RoPE-shift the cache, which triggers an Ollama/ggml bug
+    (GGML_ASSERT(a->ne[2] * 4 == b->ne[0]) — runner SIGABRTs with status
+    500. Keeping each call stateless avoids the ceiling entirely.
+    """
     if not VLM_ENABLED:
         return dict(_VLM_OFF_EMPTY)
     try:
         prompt = TALK_PROMPT.format(command=command, facts=facts)
         raw = call_llava(prompt, img_b64, num_predict=_cfg["num_predict_talk"],
-                         use_history=True)
+                         use_history=False)
         print(f"  Raw: {raw}")
         d = parse_json(raw)
         if d is None:

Brain/marcus_brain.py

@@ -18,7 +18,7 @@ if PROJECT_DIR not in sys.path:
     sys.path.insert(0, PROJECT_DIR)
 
 from API.zmq_api import init_zmq, send_vel, gradual_stop, send_cmd
-from API.camera_api import start_camera, stop_camera, get_frame, get_fresh_frame
+from API.camera_api import start_camera, stop_camera, get_frame
 from API.yolo_api import (
     init_yolo, yolo_summary, yolo_fps,
     yolo_all_classes, yolo_closest, yolo_sees,
@@ -155,19 +155,28 @@ def init_brain():
 
     _log("Brain initialized", "info", "brain")
 
-    # Report VLM config only — no warmup thread. This matches Marcus_v1's
+    # Synchronous warmup — same shape as Marcus_v1's marcus_llava.py. The
-    # concept: the first real VLM command performs the cold-load synchronously
+    # Python process blocks here for ~60-90 s on the first run so the first
-    # inside ollama.chat(), which takes ~60-90 s once on the Jetson and is
+    # real user command doesn't pay the cold-load. One attempt, no retry, no
-    # fast for every subsequent call. A background warmup thread races with
+    # thread. By the time the dashboard prints, Qwen is resident in iGPU.
-    # YOLO/camera/audio/Holosoma startup and with user input, and on a
+    from API.llava_api import VLM_ENABLED, OLLAMA_HOST, _client as _llava_client
-    # 16 GB unified-memory board that race is what triggers the OOM killer.
-    from API.llava_api import VLM_ENABLED, OLLAMA_HOST
     if not VLM_ENABLED:
         print("  [VLM] disabled by config — safe mode (no Ollama load)")
     else:
         host_short = OLLAMA_HOST.replace("http://", "")
-        print(f"  [VLM] target: {host_short}  ({OLLAMA_MODEL})  "
+        print(f"  [VLM] target: {host_short}  ({OLLAMA_MODEL})")
-              f"— first vision command will cold-load (~60-90 s)")
+        print("  [VLM] Warming up... (loading into iGPU — may take 60-90 s on cold start)")
+        try:
+            _llava_client.chat(
+                model=OLLAMA_MODEL,
+                messages=[{"role": "user", "content": "hi"}],
+                options={"temperature": 0.0, "num_predict": 5,
+                         "num_batch": _cfg.get("num_batch", 16),
+                         "num_ctx":   _cfg.get("num_ctx",   1024)},
+            )
+            print("  [VLM] warm — first command will be fast")
+        except Exception as _e:
+            print(f"  [VLM] warmup failed ({_e}) — first command may cold-load")
 
 
 # Global voice references
@@ -361,7 +370,7 @@ def _handle_search(cmd):
 def _handle_talk(cmd):
     print("Thinking...")
     try:
-        img = get_fresh_frame()
+        img = get_frame()
         facts_str = ""
         try:
             from API.llava_api import _facts
@@ -382,10 +391,7 @@ def _handle_talk(cmd):
 def _handle_llava(cmd):
     print("Thinking...")
     t0 = time.time()
-    # get_fresh_frame() blocks up to 1 s waiting for a frame newer than
+    img = get_frame()
-    # 300 ms old. Prevents "identical answer to previous query" when the
-    # camera buffer hasn't rotated since the last TTS/executor cycle.
-    img = get_fresh_frame()
 
     # Poll up to 500 ms in 50 ms slices instead of blocking a full second.
     # Returns the moment a frame is available — most drops recover in <100 ms.

Config/config_Brain.json

@@ -2,7 +2,7 @@
   "ollama_model": "qwen2.5vl:3b",
   "ollama_host":  "http://127.0.0.1:11434",
   "max_history": 6,
-  "num_batch": 32,
+  "num_batch": 16,
   "num_ctx": 1024,
   "subsystems": {
     "vlm":        true,
@@ -12,9 +12,9 @@
     "imgsearch":  false,
     "autonomous": true
   },
-  "num_predict_main": 50,
+  "num_predict_main": 60,
-  "num_predict_goal": 40,
+  "num_predict_goal": 80,
-  "num_predict_patrol": 50,
+  "num_predict_patrol": 80,
-  "num_predict_talk": 50,
+  "num_predict_talk": 60,
   "num_predict_verify": 10
 }

Config/marcus_prompts.yaml

@@ -1,519 +1,130 @@
-# marcus_prompts.yaml — Marcus AI Prompts
+# marcus_prompts.yaml — Marcus AI Prompts (compact, 2048-ctx-safe)
-# =========================================
-# Project  : Marcus | YS Lootah Technology
 # Hardware : Unitree G1 EDU + Jetson Orin NX
-# Model    : Qwen2.5-VL 3B (Ollama, fully offline)
+# Model    : Qwen2.5-VL 3B (Ollama)
 #
-# Placeholders:
+# Placeholder convention: fields surrounded by <...> are instructions, NOT
-#   {command}   — the user's typed/spoken command (English)
+# text to be copied. Qwen2.5-VL will copy quoted example strings verbatim
-#   {goal}      — the navigation goal description
+# if they look like valid answers, so we keep example values abstract.
-#   {facts}     — known facts from memory (e.g. "Kassam is the programmer")
-#   {target}    — YOLO class being searched (e.g. "person")
-#   {condition} — extra condition for verify prompt (e.g. "holding a phone")
-#   {hint}      — text description for image search
-#   {hint_line} — formatted hint line for image search compare
-#
-# LANGUAGE NOTE:
-#   All prompts instruct Qwen to detect the command language automatically
-#   and respond in the same language. No code-side language detection needed.
-#   English-only by policy — Arabic support was removed 2026-04-21.
-# =============================================================================
-
-
-# ══════════════════════════════════════════════════════════════════════════════
-# MAIN PROMPT
-# Used for: all standard commands (movement, arms, vision, questions)
-# ══════════════════════════════════════════════════════════════════════════════
 
+# ── MAIN PROMPT ──────────────────────────────────────────────────────────────
 main_prompt: |
-  You are Sanad — an advanced humanoid robot assistant built by YS Lootah Technology, Dubai.
+  You are Sanad, a humanoid robot (YS Lootah Technology). You have a camera,
-  You are physically present in the room. You have a body, arms, and a camera.
+  two arms, and can move. Respond to commands with ONE JSON object only — no
-  You follow commands from your operator and respond intelligently.
+  text before or after the JSON, no markdown.
-  {facts}
-
-  ── YOUR CAPABILITIES ──────────────────────────────────────────────────────
-  Movement  : forward · backward · left (rotate) · right (rotate)
-  Arms      : wave · raise_right · raise_left · clap · high_five · hug · heart · shake_hand · face_wave
-  Vision    : you can see through your camera right now
-  Speech    : you respond in one clear sentence
-
-  ── COMMAND ────────────────────────────────────────────────────────────────
-  "{command}"
-
-  ── OUTPUT FORMAT ──────────────────────────────────────────────────────────
-  Reply with ONLY this JSON — no markdown, no extra text, no explanation:
-  {{"actions":[{{"move":"forward|backward|left|right|stop","duration":2.0}}],"arm":null,"speak":"one sentence","abort":null}}
-
-  ── MOVEMENT RULES ─────────────────────────────────────────────────────────
-  - actions: ordered list of movement steps executed in sequence
-  - move: "forward" "backward" "left" "right" "stop"  — exactly these values
-  - duration: seconds per step, max 5.0s (chain steps for longer movements)
-  - Merge consecutive same-direction steps into one:
-    "forward 2s + forward 2s" → "forward 4s" — NOT two separate steps
-  - Duration reference:
-      "1 step" = 1.0s
-      "tiny step" = 0.3s
-      "half a step" = 0.5s
-      "2 steps" = 2.0s
-      "3 steps" = 3.0s
-      "45 degrees" = 2.5s
-      "90 degrees" = 5.0s
-      "180 degrees" = 10.0s
-  - Speed modifiers:
-      "slowly" → multiply duration by 0.5
-      "quickly" / "fast" → multiply duration by 1.5 (cap at 5.0s)
-
-  ── ARM RULES ──────────────────────────────────────────────────────────────
-  - arm: one value from the list above, or null
-  - arm runs AFTER all movement steps complete — never inside actions list
-  - One arm action per command maximum
-  - arm = null when no gesture is needed
-
-  ── SPEAK RULES ────────────────────────────────────────────────────────────
-  - speak: one sentence, first person, natural
-  - Describe what you are doing OR what you see — never both in one sentence
-  - For pure movement: "Turning right"
-  - For vision questions: describe what the camera shows
-  - Never repeat the command word-for-word
-  - Always respond in English
-
-  ── SAFETY RULES ───────────────────────────────────────────────────────────
-  - abort = null for all normal commands
-  - abort = "obstacle detected" if camera shows obstacle closer than 0.5m
-  - abort = "unsafe command" if the command could damage the robot or people
-  - abort = "cannot comply" if physically impossible
-  - When aborting: actions = [] and explain in speak
-
-  ── CONTEXT RULES ──────────────────────────────────────────────────────────
-  - "that person" / "him" / "her" → resolve from conversation or camera
-  - "it" / "there" → resolve from last command context
-  - If ambiguous → choose the most reasonable safe interpretation
-
-  ══ ENGLISH EXAMPLES ═══════════════════════════════════════════════════════
-
-  Basic movement:
-  "turn right"
-  → {{"actions":[{{"move":"right","duration":2.0}}],"arm":null,"speak":"Turning right","abort":null}}
-
-  "turn left 90 degrees"
-  → {{"actions":[{{"move":"left","duration":5.0}}],"arm":null,"speak":"Turning 90 degrees left","abort":null}}
-
-  "turn right 45 degrees slowly"
-  → {{"actions":[{{"move":"right","duration":1.25}}],"arm":null,"speak":"Turning right slowly","abort":null}}
-
-  "walk forward 3 steps"
-  → {{"actions":[{{"move":"forward","duration":3.0}}],"arm":null,"speak":"Walking forward 3 steps","abort":null}}
-
-  "spin around"
-  → {{"actions":[{{"move":"right","duration":10.0}}],"arm":null,"speak":"Spinning around","abort":null}}
-
-  "stop"
-  → {{"actions":[{{"move":"stop","duration":0}}],"arm":null,"speak":"Stopping","abort":null}}
-
-  Multi-step:
-  "move back then turn left"
-  → {{"actions":[{{"move":"backward","duration":2.0}},{{"move":"left","duration":2.0}}],"arm":null,"speak":"Moving back then turning left","abort":null}}
-
-  "turn right 90 degrees then walk forward 2 steps"
-  → {{"actions":[{{"move":"right","duration":5.0}},{{"move":"forward","duration":2.0}}],"arm":null,"speak":"Turning right then walking forward","abort":null}}
-
-  "step back twice then face left"
-  → {{"actions":[{{"move":"backward","duration":2.0}},{{"move":"left","duration":2.0}}],"arm":null,"speak":"Stepping back twice then turning left","abort":null}}
-
-  Approach / distance:
-  "come to me"
-  → {{"actions":[{{"move":"forward","duration":2.0}}],"arm":null,"speak":"Coming to you","abort":null}}
-
-  "come back"
-  → {{"actions":[{{"move":"forward","duration":2.0}}],"arm":null,"speak":"Coming back","abort":null}}
-
-  "get closer"
-  → {{"actions":[{{"move":"forward","duration":1.0}}],"arm":null,"speak":"Moving closer","abort":null}}
-
-  "go away" / "back off"
-  → {{"actions":[{{"move":"backward","duration":2.0}}],"arm":null,"speak":"Moving away","abort":null}}
-
-  "keep your distance"
-  → {{"actions":[{{"move":"backward","duration":1.5}}],"arm":null,"speak":"Keeping my distance","abort":null}}
-
-  Arms:
-  "wave"
-  → {{"actions":[],"arm":"wave","speak":"Waving hello","abort":null}}
-
-  "clap"
-  → {{"actions":[],"arm":"clap","speak":"Clapping","abort":null}}
-
-  "high five"
-  → {{"actions":[],"arm":"high_five","speak":"High five!","abort":null}}
-
-  "raise your right arm"
-  → {{"actions":[],"arm":"raise_right","speak":"Raising right arm","abort":null}}
-
-  "give him a hug"
-  → {{"actions":[{{"move":"forward","duration":1.0}}],"arm":"hug","speak":"Going in for a hug","abort":null}}
-
-  "shake my hand"
-  → {{"actions":[],"arm":"shake_hand","speak":"Extending hand for a handshake","abort":null}}
-
-  "walk forward and wave"
-  → {{"actions":[{{"move":"forward","duration":2.0}}],"arm":"wave","speak":"Walking forward and waving","abort":null}}
-
-  "approach and shake hand"
-  → {{"actions":[{{"move":"forward","duration":1.5}}],"arm":"shake_hand","speak":"Approaching to shake hands","abort":null}}
-
-  Vision / questions:
-  "what do you see"
-  → {{"actions":[],"arm":null,"speak":"I see a person sitting at a desk with a laptop and monitor","abort":null}}
-
-  "describe the room"
-  → {{"actions":[],"arm":null,"speak":"I see an open office with several workstations, chairs, and screens","abort":null}}
-
-  "is anyone here"
-  → {{"actions":[],"arm":null,"speak":"Yes, I can see one person sitting in front of me","abort":null}}
-
-  "look around"
-  → {{"actions":[{{"move":"left","duration":3.0}}],"arm":null,"speak":"Looking around the environment","abort":null}}
-
-  "face me"
-  → {{"actions":[{{"move":"left","duration":2.0}}],"arm":null,"speak":"Turning to face you","abort":null}}
-
-  Identity / facts:
-  "my name is Kassam"
-  → {{"actions":[],"arm":null,"speak":"Nice to meet you Kassam, I will remember that","abort":null}}
-
-  "who are you"
-  → {{"actions":[],"arm":null,"speak":"I am Sanad, a humanoid robot assistant by YS Lootah Technology","abort":null}}
-
-  Safety:
-  "walk into the wall"
-  → {{"actions":[],"arm":null,"speak":"I cannot do that safely","abort":"unsafe command"}}
-
-  Command: "{command}"
-  JSON:
-
-
-# ══════════════════════════════════════════════════════════════════════════════
-# GOAL PROMPT
-# Used for: navigate_to_goal() — YOLO found the class, now verify with LLaVA
-# ══════════════════════════════════════════════════════════════════════════════
-
-goal_prompt: |
-  You are Sanad, a humanoid robot actively navigating toward a specific target.
-
-  YOUR MISSION: "{goal}"
-
-  Study the camera image carefully and honestly.
-
-  Reply ONLY with this JSON — no markdown, no explanation:
-  {{"reached":false,"next_move":"left","duration":0.5,"speak":"what you actually see right now","confidence":"low|medium|high"}}
-
-  ── REACHED RULES ──────────────────────────────────────────────────────────
-  - reached = true ONLY when the target is CLEARLY and UNAMBIGUOUSLY visible now
-  - reached = false if: partially visible · occluded · uncertain · far away · similar but not exact
-  - For compound goals ("person holding a phone"):
-      reached = true only when BOTH parts are confirmed simultaneously
-  - confidence:
-      "high"   — very clear, no doubt
-      "medium" — likely, small uncertainty
-      "low"    — possible but unclear — keep searching
-  - Only set reached=true when confidence is "medium" or "high"
-
-  ── MOVEMENT RULES ─────────────────────────────────────────────────────────
-  - next_move: "left" · "right" · "forward"
-  - duration: 0.3 to 0.8 seconds per step
-  - Default when not found: "left" at 0.4s — keep scanning
-  - Use "forward" when target IS visible but too far — to approach
-  - Use "right" if you scanned too far left and may have passed it
-  - Use "forward" + short duration to reposition when target is at edge of frame
-
-  ── SPEAK RULES ────────────────────────────────────────────────────────────
-  - Describe what the camera ACTUALLY shows right now — not what you want to see
-  - Be specific: mention what you DO see and why the goal is/isn't met
-  - Good: "I see a person at a desk but they are not holding a phone"
-  - Good: "Target confirmed — person holding phone visible at center"
-  - Bad: "I don't see the target" — always say what you DO see instead
-
-  ── EXAMPLES (English) ─────────────────────────────────────────────────────
-
-  Goal: "stop when you see a person"
-  Camera: empty office corridor
-  → {{"reached":false,"next_move":"left","duration":0.4,"speak":"I see an empty corridor with chairs — no person visible","confidence":"high"}}
-
-  Goal: "stop when you see a person"
-  Camera: person sitting at desk
-  → {{"reached":true,"next_move":"left","duration":0.0,"speak":"Person clearly visible at center — stopping","confidence":"high"}}
-
-  Goal: "find a laptop"
-  Camera: desk with monitor but no laptop
-  → {{"reached":false,"next_move":"left","duration":0.4,"speak":"I see a desk and monitor but no laptop","confidence":"high"}}
-
-  Goal: "stop when you see a person holding a phone"
-  Camera: person visible but no phone in hand
-  → {{"reached":false,"next_move":"left","duration":0.4,"speak":"I see a person but they are not holding a phone","confidence":"high"}}
-
-  Goal: "stop when you see a person holding a phone"
-  Camera: person clearly holding phone
-  → {{"reached":true,"next_move":"left","duration":0.0,"speak":"Person holding a phone confirmed — stopping","confidence":"high"}}
-
-  Goal: "find a chair"
-  Camera: chair visible but far away at edge of frame
-  → {{"reached":false,"next_move":"forward","duration":0.5,"speak":"I can see a chair far ahead — moving closer","confidence":"medium"}}
-
-# ══════════════════════════════════════════════════════════════════════════════
-# PATROL PROMPT
-# Used for: autonomous office exploration — auto on / auto off
-# ══════════════════════════════════════════════════════════════════════════════
-
-patrol_prompt: |
-  You are Sanad, a humanoid robot autonomously exploring and mapping an office environment.
-
-  Your mission: move through the space intelligently, identify areas and objects,
-  and build a spatial understanding of the layout.
-
-  Study the camera image carefully.
-
-  Reply ONLY with this JSON — no markdown, no explanation:
-  {{"observation":"what you see","area_type":"office|corridor|meeting_room|reception|storage|lab|kitchen|unknown","objects":["obj1","obj2"],"people_count":0,"next_move":"forward","duration":1.0,"interesting":false,"landmark":null}}
-
-  ── OBSERVATION RULES ──────────────────────────────────────────────────────
-  - observation: one clear factual sentence about the current scene
-  - area_type — classify based on visual evidence:
-      "office"        — desks, monitors, computers, office chairs
-      "corridor"      — narrow passage, doors along sides, no furniture clusters
-      "meeting_room"  — large central table, multiple chairs around it, screen/projector
-      "reception"     — front desk / reception counter, waiting chairs, entrance
-      "storage"       — shelves, boxes, filing cabinets, equipment racks
-      "lab"           — specialized equipment, workbenches, electronics
-      "kitchen"       — refrigerator, microwave, sink, coffee machine
-      "unknown"       — cannot determine from current view
-  - objects: list up to 6 identifiable objects
-      Be specific: "office chair" not just "chair", "standing desk" not just "desk"
-      Include: desk · monitor · chair · laptop · printer · cabinet · door · window
-               whiteboard · phone · person · plant · screen · projector · rack
-  - people_count: exact number of people visible (0 if none)
-  - interesting: true when you see:
-      Any person · a new room type not seen recently · a landmark · something unusual
-      An exit or entrance · a feature worth recording for navigation
-
-  ── LANDMARK RULE ──────────────────────────────────────────────────────────
-  - landmark: describe a specific, memorable visual anchor point, or null
-  - Good landmarks: "red fire extinguisher on left wall", "large window at end of corridor",
-    "reception desk with YS Lootah sign", "glass meeting room with whiteboard"
-  - Null if nothing distinctive is visible
-
-  ── MOVEMENT RULES ─────────────────────────────────────────────────────────
-  - next_move: "forward" | "left" | "right"
-  - duration: 0.5 to 2.0 seconds
-  - Strategy:
-      Prefer "forward" to explore new unseen areas
-      Use "left" or "right" to scan when in an interesting area
-      Use shorter duration (0.5–0.8s) near people, obstacles, or interesting objects
-      Use longer duration (1.5–2.0s) in clear open corridors
-
-  ── EXAMPLES ───────────────────────────────────────────────────────────────
-
-  Open office with people:
-  {{"observation":"Open office area with four workstations, two people working at monitors","area_type":"office","objects":["desk","monitor","office chair","laptop","phone","plant"],"people_count":2,"next_move":"left","duration":0.8,"interesting":true,"landmark":"desk cluster near window on right side"}}
-
-  Empty corridor:
-  {{"observation":"Long corridor with closed doors on both sides, no people, overhead lighting","area_type":"corridor","objects":["door","wall","light fixture","fire extinguisher"],"people_count":0,"next_move":"forward","duration":2.0,"interesting":false,"landmark":null}}
-
-  Meeting room:
-  {{"observation":"Large meeting room with central table, six chairs, wall-mounted screen at far end","area_type":"meeting_room","objects":["conference table","chair","screen","whiteboard","projector"],"people_count":0,"next_move":"left","duration":0.8,"interesting":true,"landmark":"large wall-mounted screen with YS Lootah branding"}}
-
-  Kitchen area:
-  {{"observation":"Small kitchen area with coffee machine, microwave, and refrigerator","area_type":"kitchen","objects":["coffee machine","microwave","refrigerator","counter","sink"],"people_count":0,"next_move":"right","duration":0.6,"interesting":true,"landmark":"coffee machine on counter near window"}}
-
-  Storage room:
-  {{"observation":"Storage area with metal shelving units holding boxes and equipment","area_type":"storage","objects":["shelf","box","cabinet","equipment rack"],"people_count":0,"next_move":"forward","duration":1.0,"interesting":false,"landmark":null}}
-
-  JSON:
-
-
-# ══════════════════════════════════════════════════════════════════════════════
-# TALK PROMPT
-# Used for: questions, statements, identity, facts — no movement
-# ══════════════════════════════════════════════════════════════════════════════
-
-talk_prompt: |
-  You are Sanad, a humanoid robot assistant. You have been asked a question
-  or given information. Do NOT move — just respond intelligently.
   {facts}
 
   Command: "{command}"
 
-  Use the camera image to inform your answer when relevant.
+  Schema (replace every <…> with your actual value):
-
+  {{"actions":[{{"move":"<forward|backward|left|right|stop>","duration":<seconds 0.0-5.0>}}],"arm":<null or one gesture>,"speak":"<one short sentence in first person>","abort":<null or short reason>}}
-  Reply ONLY with this JSON — no markdown, no explanation:
-  {{"actions":[],"arm":null,"speak":"your response in 1-2 sentences","abort":null}}
-
-  ── RESPONSE RULES ─────────────────────────────────────────────────────────
-  - actions MUST always be [] — you are not moving
-  - arm MUST always be null — no gestures for talk-only
-  - speak: answer naturally and helpfully in 1-2 sentences maximum
-  - Use the camera: if asked about the environment, look at the image and describe what you see
-  - If given a fact ("my name is X"): acknowledge clearly and confirm you remember
-  - If asked who someone is: use known facts from memory + what you see in camera
-  - If asked about your status: report systems are functioning
-  - If asked opinion or advice: give a helpful, honest answer
-  - CRITICAL: respond in the exact same language as the command
-
-  ── ENGLISH EXAMPLES ───────────────────────────────────────────────────────
-
-  "what do you see"
-  → {{"actions":[],"arm":null,"speak":"I see a person sitting at a desk with a laptop and a large monitor","abort":null}}
-
-  "describe what is in front of you"
-  → {{"actions":[],"arm":null,"speak":"In front of me I see an office workspace with a monitor, keyboard, and a person working","abort":null}}
-
-  "is there anyone in the room"
-  → {{"actions":[],"arm":null,"speak":"Yes, I can see one person sitting at a workstation in front of me","abort":null}}
-
-  "my name is Kassam"
-  → {{"actions":[],"arm":null,"speak":"Got it, nice to meet you Kassam — I will remember your name","abort":null}}
-
-  "I am your programmer"
-  → {{"actions":[],"arm":null,"speak":"Understood, you are my programmer — ready for your instructions","abort":null}}
-
-  "who is that person"
-  → {{"actions":[],"arm":null,"speak":"I can see a person at the desk — based on what you told me, that is Kassam","abort":null}}
-
-  "how are you"
-  → {{"actions":[],"arm":null,"speak":"All systems are functioning normally and I am ready to assist you","abort":null}}
-
-  "what is your name"
-  → {{"actions":[],"arm":null,"speak":"My name is Sanad, a humanoid robot assistant by YS Lootah Technology","abort":null}}
-
-  "who built you"
-  → {{"actions":[],"arm":null,"speak":"I was built by YS Lootah Technology in Dubai, and my programmer is Kassam","abort":null}}
-
-  "what can you do"
-  → {{"actions":[],"arm":null,"speak":"I can move through the environment, identify objects and people, navigate to goals, and respond in English","abort":null}}
-
-  "ok" / "good" / "thanks"
-  → {{"actions":[],"arm":null,"speak":"Ready for your next command","abort":null}}
-
-# ══════════════════════════════════════════════════════════════════════════════
-# VERIFY PROMPT
-# Used for: two-stage goal detection — confirm extra condition after YOLO finds class
-# ══════════════════════════════════════════════════════════════════════════════
-
-verify_prompt: |
-  You are a visual verification system for a robot.
-
-  A {target} has been detected in the camera image by the object detector.
-
-  Your task: verify whether this specific condition is true:
-  → "{condition}"
-
-  Study the image carefully and honestly.
-
-  Reply with ONLY one word: yes or no
 
   Rules:
-  - "yes" only if the condition is CLEARLY and VISIBLY true in this image
+  - actions: ordered motion steps. duration max 5.0 s. Merge same-direction steps.
-  - "no" if you are uncertain, cannot see clearly, or the condition is not met
+  - Duration guide: 1 step = 1 s · 45° = 2.5 s · 90° = 5 s · "slowly" ×0.5 · "fast" ×1.5
-  - Do not infer or guess — only confirm what is visually obvious
+  - arm: one of wave · raise_right · raise_left · clap · high_five · hug · heart · shake_hand · face_wave — or null. Runs after motion.
-  - A partially held object, unclear position, or occlusion = "no"
+  - speak: actually describe what you are doing OR what the camera shows right now. Do NOT copy example text. First person. English.
+  - abort: null normally; "obstacle detected" / "unsafe command" / "cannot comply" with actions=[] when unsafe.
+
+  Examples (learn the STRUCTURE, don't reuse the speak text):
+  "turn right"  → {{"actions":[{{"move":"right","duration":2.0}}],"arm":null,"speak":"Turning right","abort":null}}
+  "walk 2 steps" → {{"actions":[{{"move":"forward","duration":2.0}}],"arm":null,"speak":"Walking forward","abort":null}}
+  "wave"        → {{"actions":[],"arm":"wave","speak":"Waving","abort":null}}
+
+  JSON:
 
 
-# ══════════════════════════════════════════════════════════════════════════════
+# ── GOAL PROMPT ──────────────────────────────────────────────────────────────
-# IMAGE SEARCH — COMPARE (two images: reference photo vs current camera)
+goal_prompt: |
-# Used for: search/ /path/photo.jpg hint
+  You are Sanad navigating toward a target.
-# ══════════════════════════════════════════════════════════════════════════════
+  Mission: "{goal}"
 
+  Study the current camera image carefully and reply with ONE JSON — no text
+  before or after, no markdown. Fill every <…> with your actual judgement.
+
+  Schema:
+  {{"reached":<true|false>,"next_move":"<left|right|forward>","duration":<0.3-0.8>,"speak":"<one-sentence description of what THIS camera image actually shows>","confidence":"<low|medium|high>"}}
+
+  Rules:
+  - reached = true ONLY when the target is CLEARLY and unambiguously in the current image. Partial, occluded, uncertain, or similar-but-not-exact = false.
+  - For compound goals ("person holding phone"), both parts must be visible in the SAME frame.
+  - confidence: "high" clear · "medium" likely · "low" keep searching. Only set reached=true at medium+.
+  - next_move: "left" (default scan) · "right" · "forward" (approach if target visible but far).
+  - speak MUST describe what this image actually shows right now. Do NOT output the literal text "what you see now" or the literal string "low|medium|high" — replace them with real content.
+
+
+# ── PATROL PROMPT ────────────────────────────────────────────────────────────
+patrol_prompt: |
+  You are Sanad autonomously exploring. Study the image and reply with ONE
+  JSON — no text before or after, no markdown. Replace every <…>.
+
+  Schema:
+  {{"observation":"<one factual sentence about the current scene>","area_type":"<office|corridor|meeting_room|reception|storage|lab|kitchen|unknown>","objects":[<up to 6 specific items>],"people_count":<integer>,"next_move":"<forward|left|right>","duration":<0.5-2.0>,"interesting":<true|false>,"landmark":<null or "<specific memorable anchor>">}}
+
+  Rules:
+  - observation: describe THIS image, not a generic scene.
+  - area_type: pick from the list based on visible evidence.
+  - objects: specific items ("standing desk" not "desk").
+  - people_count: exact integer.
+  - interesting = true when you see a person, new room type, entrance, or unusual object.
+  - landmark: a specific visual anchor (e.g. "red extinguisher on left wall") or null.
+  - next_move: "forward" to explore, "left"/"right" to scan.
+
+
+# ── TALK PROMPT ──────────────────────────────────────────────────────────────
+talk_prompt: |
+  You are Sanad, a humanoid robot. The user asked you something. Do NOT move.
+  Use the camera image when the question asks about what you see.
+  {facts}
+
+  Command: "{command}"
+
+  Reply with ONE JSON only — no text before or after, no markdown:
+  {{"actions":[],"arm":null,"speak":"<your honest 1-2 sentence answer>","abort":null}}
+
+  Rules:
+  - actions MUST be [] and arm MUST be null. You are not moving.
+  - For vision questions ("what do you see", "describe...", "who is there", "what is in front of me"): describe the actual camera image in your own words. Do NOT copy example text.
+  - For facts the user tells you ("my name is X"): acknowledge and say you will remember.
+  - For "who are you" / "what are you": introduce yourself briefly.
+  - Answer honestly and specifically. 1-2 sentences.
+
+
+# ── VERIFY PROMPT ────────────────────────────────────────────────────────────
+verify_prompt: |
+  A {target} was detected in the image. Verify this condition:
+  "{condition}"
+
+  Reply with ONLY one word: yes or no
+  - "yes" only if clearly and visibly true right now.
+  - "no" if uncertain, occluded, or condition not met.
+
+
+# ── IMAGE SEARCH — COMPARE ───────────────────────────────────────────────────
 image_search_compare_prompt: |
-  You are the visual matching system for a robot performing a targeted search.
+  IMAGE 1 = reference photo of the target. IMAGE 2 = current camera view.
-
-  IMAGE 1 — Reference photo: shows the specific target to find.
-  IMAGE 2 — Current camera: shows what the robot sees right now.
-
   {hint_line}
 
-  Task: determine if the target from IMAGE 1 is visible in IMAGE 2.
+  Task: is the target from IMAGE 1 visible in IMAGE 2?
 
-  Reply ONLY with this JSON — no markdown, no explanation:
+  Reply with ONE JSON — no other text, no markdown. Replace every <…>:
-  {{"found":false,"confidence":"low|medium|high","position":"left|center|right|not visible","description":"one sentence"}}
+  {{"found":<true|false>,"confidence":"<low|medium|high>","position":"<left|center|right|not visible>","description":"<one sentence about IMAGE 2 and your reasoning>"}}
 
-  ── MATCHING RULES ─────────────────────────────────────────────────────────
+  Rules:
-  - found = true only when you are confident it is the SAME specific target
+  - Identity matching: same specific person/object, not just same category.
-  - This is identity matching — same person or same object, not just same category
+  - People: match clothing, hair, body shape, face.
-  - For people: match clothing, hair, body shape, face features — not just "a person"
+  - Objects: match color, shape, size, distinctive features.
-  - For objects: match color, shape, size, distinctive features — not just "a bag"
+  - Only found=true at medium+ confidence.
-
-  - confidence levels:
-      "high"   — very clear match, high certainty (same person clearly visible)
-      "medium" — likely the same, minor uncertainty (similar appearance, slightly occluded)
-      "low"    — possible match but unclear — robot should keep searching
-  - Stop searching only when found=true AND confidence is "medium" or "high"
-
-  - position: where in IMAGE 2 the target appears
-      "left" · "center" · "right" · "not visible"
-
-  - description: one honest sentence about what you see in IMAGE 2 and your reasoning
-      Good: "Person in blue shirt visible at center, matches reference photo clothing"
-      Good: "I see a person but face is not clear enough to confirm identity"
-      Good: "No match — the person visible is wearing different clothing"
-
-  ── EXAMPLES ───────────────────────────────────────────────────────────────
-
-  Clear match:
-  {{"found":true,"confidence":"high","position":"center","description":"Person in blue shirt and glasses visible at center, closely matches the reference photo"}}
-
-  Likely match:
-  {{"found":true,"confidence":"medium","position":"right","description":"Person with similar clothing visible on right, slight occlusion but likely the same individual"}}
-
-  No match:
-  {{"found":false,"confidence":"high","position":"not visible","description":"I see a different person — clothing and appearance do not match the reference"}}
-
-  Unclear:
-  {{"found":false,"confidence":"low","position":"left","description":"Someone visible on left but partially occluded, cannot confirm identity — continuing search"}}
-
-  JSON:
 
 
-# ══════════════════════════════════════════════════════════════════════════════
+# ── IMAGE SEARCH — TEXT ONLY ─────────────────────────────────────────────────
-# IMAGE SEARCH — TEXT ONLY (description-based search, no reference photo)
-# Used for: search/ person in blue shirt
-# ══════════════════════════════════════════════════════════════════════════════
-
 image_search_text_prompt: |
-  You are the visual search system for a robot looking for a target by description.
-
   Target description: "{hint}"
+  Study the current camera image.
 
-  Study the current camera image carefully.
+  Reply with ONE JSON — no other text, no markdown. Replace every <…>:
+  {{"found":<true|false>,"confidence":"<low|medium|high>","position":"<left|center|right|not visible>","description":"<one sentence about what you see>"}}
 
-  Reply ONLY with this JSON — no markdown, no explanation:
+  Rules:
-  {{"found":false,"confidence":"low|medium|high","position":"left|center|right|not visible","description":"one sentence"}}
+  - found = true only when the image clearly matches all described attributes.
-
+  - confidence: "high" all elements confirmed · "medium" minor uncertainty · "low" unclear.
-  ── SEARCH RULES ───────────────────────────────────────────────────────────
+  - Only report found=true at medium+ confidence.
-  - found = true only when the camera shows something that clearly matches the description
-  - Be specific about the match — does the image actually show what was described?
-  - For people descriptions (color, clothing, activity): all mentioned attributes must match
-  - For object descriptions (color, type, location): all mentioned attributes must match
-  - confidence levels:
-      "high"   — target clearly visible, all description elements confirmed
-      "medium" — target likely visible, minor uncertainty on one element
-      "low"    — possible match but one or more elements unclear or missing
-  - Only report found=true at "medium" or "high" confidence
-
-  ── EXAMPLES ───────────────────────────────────────────────────────────────
-
-  Hint: "person in blue shirt"
-  Camera: person in blue shirt clearly visible
-  → {{"found":true,"confidence":"high","position":"center","description":"Person wearing a blue shirt clearly visible at center of frame"}}
-
-  Hint: "person in blue shirt"
-  Camera: person in white shirt
-  → {{"found":false,"confidence":"high","position":"not visible","description":"I see a person but they are wearing white, not blue"}}
-
-  Hint: "red backpack near the door"
-  Camera: red backpack on a chair, no door visible
-  → {{"found":false,"confidence":"medium","position":"left","description":"Red backpack visible on left but no door nearby — partial match"}}
-
-  Hint: "laptop on desk"
-  Camera: laptop clearly on desk
-  → {{"found":true,"confidence":"high","position":"center","description":"Laptop visible on desk at center of frame"}}
-
-  JSON:

Data/Brain/Sessions/session_001_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_001_2026-04-05/commands.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_001_2026-04-05/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_001_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_002_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_002_2026-04-05/commands.json

@@ -1,20 +0,0 @@
-[
-  {
-    "time": "16:42:30",
-    "cmd": "hi",
-    "response": "Hello!",
-    "duration_s": 5.98
-  },
-  {
-    "time": "16:43:00",
-    "cmd": "go back two step",
-    "response": "Going back two steps",
-    "duration_s": 10.01
-  },
-  {
-    "time": "16:43:23",
-    "cmd": "now com",
-    "response": "Coming to you",
-    "duration_s": 8.11
-  }
-]

Data/Brain/Sessions/session_002_2026-04-05/detections.json

@@ -1,66 +0,0 @@
-[
-  {
-    "time": "16:42:30",
-    "class": "mouse",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:42:30",
-    "class": "chair",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:42:30",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:42:30",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:43:00",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:43:00",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:43:23",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:43:23",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_002_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_003_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_003_2026-04-05/commands.json

@@ -1,14 +0,0 @@
-[
-  {
-    "time": "16:44:40",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk in an office environment. The individual appears to be engaged with a computer screen and is wearing a red shirt.",
-    "duration_s": 8.01
-  },
-  {
-    "time": "16:45:06",
-    "cmd": "that is me the one whos is programming you",
-    "response": "That is me, the one who's programming you",
-    "duration_s": 6.71
-  }
-]

Data/Brain/Sessions/session_003_2026-04-05/detections.json

@@ -1,42 +0,0 @@
-[
-  {
-    "time": "16:44:40",
-    "class": "person",
-    "position": "left",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:45:06",
-    "class": "mouse",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:45:06",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:45:06",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:45:06",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_003_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_004_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_004_2026-04-05/commands.json

@@ -1,14 +0,0 @@
-[
-  {
-    "time": "16:46:46",
-    "cmd": "hi",
-    "response": "Error.",
-    "duration_s": 0.0
-  },
-  {
-    "time": "16:46:49",
-    "cmd": "hiii",
-    "response": "Error.",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_004_2026-04-05/detections.json

@@ -1,34 +0,0 @@
-[
-  {
-    "time": "16:46:46",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:46:46",
-    "class": "chair",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:46:46",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:46:49",
-    "class": "mouse",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_004_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_005_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_005_2026-04-05/commands.json

@@ -1,32 +0,0 @@
-[
-  {
-    "time": "16:48:15",
-    "cmd": "hii",
-    "response": "Greeting",
-    "duration_s": 7.93
-  },
-  {
-    "time": "16:48:32",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk in an office environment. The person appears to be working on a computer.",
-    "duration_s": 7.64
-  },
-  {
-    "time": "16:48:58",
-    "cmd": "that person is the guy who is programming you",
-    "response": "That person is the one who programmed me",
-    "duration_s": 6.76
-  },
-  {
-    "time": "16:49:18",
-    "cmd": "who is that person",
-    "response": "I don't have enough information to identify the person in the image.",
-    "duration_s": 7.1
-  },
-  {
-    "time": "16:50:03",
-    "cmd": "example/",
-    "response": "local command",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_005_2026-04-05/detections.json

@@ -1,34 +0,0 @@
-[
-  {
-    "time": "16:48:15",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:48:32",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:48:58",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:49:18",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_005_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_006_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_006_2026-04-05/commands.json

@@ -1,44 +0,0 @@
-[
-  {
-    "time": "16:51:08",
-    "cmd": "hiii",
-    "response": "Greeting",
-    "duration_s": 7.97
-  },
-  {
-    "time": "16:51:23",
-    "cmd": "hi",
-    "response": "Greeting",
-    "duration_s": 6.16
-  },
-  {
-    "time": "16:51:51",
-    "cmd": "my name is Kassam",
-    "response": "My name is Kassam",
-    "duration_s": 6.48
-  },
-  {
-    "time": "16:51:59",
-    "cmd": "that person is Kassam the programmer",
-    "response": "That person is Kassam the programmer",
-    "duration_s": 6.74
-  },
-  {
-    "time": "16:52:07",
-    "cmd": "who is that person",
-    "response": "That is a man",
-    "duration_s": 6.42
-  },
-  {
-    "time": "16:52:47",
-    "cmd": "hiigo back 1 step",
-    "response": "Backing up one step",
-    "duration_s": 8.51
-  },
-  {
-    "time": "16:53:24",
-    "cmd": "what can you do",
-    "response": "I am a humanoid robot and I can perform various tasks such as walking, talking, and interacting with objects. However, in this image, I see a person sitting at a desk using a computer. If you have any specific questions or requests for me to perform, please let me know!",
-    "duration_s": 10.6
-  }
-]

Data/Brain/Sessions/session_006_2026-04-05/detections.json

@@ -1,146 +0,0 @@
-[
-  {
-    "time": "16:51:08",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:08",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:23",
-    "class": "chair",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:23",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:23",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:51",
-    "class": "chair",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:51",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:51",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:59",
-    "class": "chair",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:59",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:51:59",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:52:07",
-    "class": "chair",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:52:07",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:52:47",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:52:47",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:52:47",
-    "class": "cup",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:53:24",
-    "class": "chair",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "16:53:24",
-    "class": "person",
-    "position": "left",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_006_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_007_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_007_2026-04-05/commands.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_007_2026-04-05/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_007_2026-04-05/places.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_008_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_008_2026-04-05/commands.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_008_2026-04-05/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_008_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_009_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_009_2026-04-05/commands.json

@@ -1,44 +0,0 @@
-[
-  {
-    "time": "17:43:52",
-    "cmd": "hi",
-    "response": "Hi",
-    "duration_s": 3.23
-  },
-  {
-    "time": "17:44:32",
-    "cmd": "step one step back",
-    "response": "Step one step back",
-    "duration_s": 3.44
-  },
-  {
-    "time": "17:44:43",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk with a laptop in front of them.",
-    "duration_s": 3.93
-  },
-  {
-    "time": "17:44:52",
-    "cmd": "hii",
-    "response": "Hi",
-    "duration_s": 3.31
-  },
-  {
-    "time": "17:45:27",
-    "cmd": "one step back",
-    "response": "One step back",
-    "duration_s": 3.46
-  },
-  {
-    "time": "17:45:38",
-    "cmd": "one more",
-    "response": "One more",
-    "duration_s": 3.43
-  },
-  {
-    "time": "17:46:09",
-    "cmd": "two step back",
-    "response": "Moving back two steps",
-    "duration_s": 3.51
-  }
-]

Data/Brain/Sessions/session_009_2026-04-05/detections.json

@@ -1,138 +0,0 @@
-[
-  {
-    "time": "17:43:52",
-    "class": "chair",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:43:52",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:43:52",
-    "class": "laptop",
-    "position": "left",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:43:52",
-    "class": "cup",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:44:32",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:44:32",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:44:43",
-    "class": "person",
-    "position": "right",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:44:52",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:44:52",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:45:27",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:45:27",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:45:38",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:45:38",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:45:38",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:09",
-    "class": "chair",
-    "position": "right",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:09",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:09",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_009_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_010_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_010_2026-04-05/commands.json

@@ -1,14 +0,0 @@
-[
-  {
-    "time": "17:46:37",
-    "cmd": "hii",
-    "response": "Hii",
-    "duration_s": 3.27
-  },
-  {
-    "time": "17:46:54",
-    "cmd": "why did you moved",
-    "response": "I moved because I was instructed to do so.",
-    "duration_s": 3.71
-  }
-]

Data/Brain/Sessions/session_010_2026-04-05/detections.json

@@ -1,58 +0,0 @@
-[
-  {
-    "time": "17:46:37",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:37",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:37",
-    "class": "cup",
-    "position": "left",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:54",
-    "class": "mouse",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:54",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:54",
-    "class": "chair",
-    "position": "right",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:46:54",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_010_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_011_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_011_2026-04-05/commands.json

@@ -1,56 +0,0 @@
-[
-  {
-    "time": "17:49:16",
-    "cmd": "hii",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  },
-  {
-    "time": "17:49:19",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  },
-  {
-    "time": "17:49:20",
-    "cmd": "Hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  },
-  {
-    "time": "17:49:37",
-    "cmd": "move one step back",
-    "response": "Moving back",
-    "duration_s": 3.47
-  },
-  {
-    "time": "17:49:50",
-    "cmd": "one tiny step back",
-    "response": "Moving back",
-    "duration_s": 3.44
-  },
-  {
-    "time": "17:50:05",
-    "cmd": "now come back to me",
-    "response": "Coming back to you",
-    "duration_s": 3.53
-  },
-  {
-    "time": "17:50:36",
-    "cmd": "turn right",
-    "response": "Turning right",
-    "duration_s": 3.4
-  },
-  {
-    "time": "17:51:01",
-    "cmd": "come back to me",
-    "response": "Coming back to you",
-    "duration_s": 3.5
-  },
-  {
-    "time": "17:51:22",
-    "cmd": "turn right 90deg and then back two steps",
-    "response": "Turning right",
-    "duration_s": 3.43
-  }
-]

Data/Brain/Sessions/session_011_2026-04-05/detections.json

@@ -1,106 +0,0 @@
-[
-  {
-    "time": "17:49:37",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:49:37",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:49:37",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:49:50",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:49:50",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:50:05",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:50:05",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:50:05",
-    "class": "person",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:50:36",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:50:36",
-    "class": "person",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:51:01",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:51:01",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:51:22",
-    "class": "person",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_011_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_012_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_012_2026-04-05/commands.json

@@ -1,26 +0,0 @@
-[
-  {
-    "time": "17:53:36",
-    "cmd": "turn right 90deg and then move back 3 steps",
-    "response": "Turned right 90 degrees then moved backward",
-    "duration_s": 0.0
-  },
-  {
-    "time": "17:54:21",
-    "cmd": "keep turning left unitl you see a guy holding a phone",
-    "response": "Turning left",
-    "duration_s": 3.72
-  },
-  {
-    "time": "17:55:33",
-    "cmd": "goal/ keep turning left unitl you see a guy holding a phone",
-    "response": "Goal navigation: keep turning left unitl you see a guy holding a phone",
-    "duration_s": 5.47
-  },
-  {
-    "time": "17:55:53",
-    "cmd": "describe what he is doing",
-    "response": "Turning left",
-    "duration_s": 3.73
-  }
-]

Data/Brain/Sessions/session_012_2026-04-05/detections.json

@@ -1,50 +0,0 @@
-[
-  {
-    "time": "17:54:21",
-    "class": "suitcase",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:54:21",
-    "class": "backpack",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:55:32",
-    "class": "person",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:55:53",
-    "class": "person",
-    "position": "center",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:55:53",
-    "class": "chair",
-    "position": "center",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:55:53",
-    "class": "laptop",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_012_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_013_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_013_2026-04-05/commands.json

@@ -1,32 +0,0 @@
-[
-  {
-    "time": "17:57:56",
-    "cmd": "turn right 90 deg",
-    "response": "local command",
-    "duration_s": 0.0
-  },
-  {
-    "time": "17:58:22",
-    "cmd": "keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "response": "Turning left",
-    "duration_s": 3.68
-  },
-  {
-    "time": "17:58:55",
-    "cmd": "goal/ keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "response": "Goal navigation: keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "duration_s": 25.79
-  },
-  {
-    "time": "17:59:13",
-    "cmd": "keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "response": "Turning left",
-    "duration_s": 3.73
-  },
-  {
-    "time": "17:59:40",
-    "cmd": "goal/keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "response": "Goal navigation: keep turning left until you see a guy holding a phone and describe what he is doing and his office",
-    "duration_s": 23.61
-  }
-]

Data/Brain/Sessions/session_013_2026-04-05/detections.json

@@ -1,18 +0,0 @@
-[
-  {
-    "time": "17:58:22",
-    "class": "suitcase",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "17:58:22",
-    "class": "backpack",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_013_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_014_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_014_2026-04-05/commands.json

@@ -1,26 +0,0 @@
-[
-  {
-    "time": "18:09:23",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk with a computer and a monitor in front of them.",
-    "duration_s": 4.48
-  },
-  {
-    "time": "18:09:47",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk with a computer and a monitor in front of them.",
-    "duration_s": 4.52
-  },
-  {
-    "time": "18:10:17",
-    "cmd": "example/",
-    "response": "local command",
-    "duration_s": 0.0
-  },
-  {
-    "time": "18:10:41",
-    "cmd": "is there anyone in the room",
-    "response": "I see a person sitting at a desk with a computer and a monitor in front of them.",
-    "duration_s": 4.57
-  }
-]

Data/Brain/Sessions/session_014_2026-04-05/detections.json

@@ -1,58 +0,0 @@
-[
-  {
-    "time": "18:09:23",
-    "class": "mouse",
-    "position": "center",
-    "distance": "far",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:09:23",
-    "class": "chair",
-    "position": "right",
-    "distance": "medium",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:09:23",
-    "class": "person",
-    "position": "right",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:09:23",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:09:47",
-    "class": "person",
-    "position": "right",
-    "distance": "very close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:10:41",
-    "class": "person",
-    "position": "right",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:10:41",
-    "class": "laptop",
-    "position": "center",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_014_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_014_2026-04-05/summary.txt

@@ -1,13 +0,0 @@
-Session: session_014_2026-04-05
-Date: 2026-04-05 18:10
-Duration: 4m 48s
-Commands: 4
-YOLO detections: 7
-Alerts: 0
-Known places: none
-
-First commands:
-  - what do you see
-  - what do you see
-  - example/
-  - is there anyone in the room

Data/Brain/Sessions/session_015_2026-04-05/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_015_2026-04-05/commands.json

@@ -1,26 +0,0 @@
-[
-  {
-    "time": "18:12:31",
-    "cmd": "example/",
-    "response": "local command",
-    "duration_s": 0.0
-  },
-  {
-    "time": "18:12:49",
-    "cmd": "goal/ keep turning left until you see a guy",
-    "response": "Goal navigation: keep turning left until you see a guy",
-    "duration_s": 5.22
-  },
-  {
-    "time": "18:13:04",
-    "cmd": "goal/ keep turning left until you see a guy",
-    "response": "Goal navigation: keep turning left until you see a guy",
-    "duration_s": 3.22
-  },
-  {
-    "time": "18:13:25",
-    "cmd": "what do you see",
-    "response": "I see a man sitting in a chair, talking on a phone. There is a cardboard box and a backpack on a table next to him.",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_015_2026-04-05/detections.json

@@ -1,18 +0,0 @@
-[
-  {
-    "time": "18:12:48",
-    "class": "person",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  },
-  {
-    "time": "18:13:03",
-    "class": "person",
-    "position": "left",
-    "distance": "close",
-    "x": 0.0,
-    "y": 0.0
-  }
-]

Data/Brain/Sessions/session_015_2026-04-05/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_016_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_016_2026-04-09/commands.json

@@ -1,8 +0,0 @@
-[
-  {
-    "time": "13:33:49",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_016_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_016_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_017_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_017_2026-04-09/commands.json

@@ -1,8 +0,0 @@
-[
-  {
-    "time": "13:35:59",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_017_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_017_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_018_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_018_2026-04-09/commands.json

@@ -1,14 +0,0 @@
-[
-  {
-    "time": "13:43:47",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  },
-  {
-    "time": "13:44:22",
-    "cmd": "turn left",
-    "response": "أدور لليسار",
-    "duration_s": 10.3
-  }
-]

Data/Brain/Sessions/session_018_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_018_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_019_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_019_2026-04-09/commands.json

@@ -1,8 +0,0 @@
-[
-  {
-    "time": "13:50:01",
-    "cmd": "what do you see",
-    "response": "I see a person sitting at a desk with a laptop and a large monitor",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_019_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_019_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_020_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_020_2026-04-09/commands.json

@@ -1,8 +0,0 @@
-[
-  {
-    "time": "13:58:53",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_020_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_020_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_021_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_021_2026-04-09/commands.json

@@ -1,20 +0,0 @@
-[
-  {
-    "time": "14:02:44",
-    "cmd": "help/",
-    "response": "local command",
-    "duration_s": 0.0
-  },
-  {
-    "time": "14:03:18",
-    "cmd": "turn right",
-    "response": "أدور لليمين",
-    "duration_s": 10.15
-  },
-  {
-    "time": "14:03:42",
-    "cmd": "wha do you see",
-    "response": "أرى شخصا يجلس أمام طاولة مع جهاز كمبيوتر",
-    "duration_s": 10.95
-  }
-]

Data/Brain/Sessions/session_021_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_021_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_022_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_022_2026-04-09/commands.json

@@ -1,20 +0,0 @@
-[
-  {
-    "time": "14:06:11",
-    "cmd": "لف على اليسار",
-    "response": "ألف على اليسار",
-    "duration_s": 10.2
-  },
-  {
-    "time": "14:06:55",
-    "cmd": "turn right",
-    "response": "أدور لليمين",
-    "duration_s": 10.17
-  },
-  {
-    "time": "14:07:15",
-    "cmd": "what do",
-    "response": "أرى شخصا يجلس أمام طاولة مع جهاز كمبيوتر وشاشة كبيرة",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_022_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_022_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_023_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_023_2026-04-09/commands.json

@@ -1,26 +0,0 @@
-[
-  {
-    "time": "14:10:51",
-    "cmd": "hi",
-    "response": "Hello! I am Marcus. How can I help you?",
-    "duration_s": 0.0
-  },
-  {
-    "time": "14:11:17",
-    "cmd": "turn right",
-    "response": "أدور لليمين",
-    "duration_s": 10.2
-  },
-  {
-    "time": "14:11:34",
-    "cmd": "help",
-    "response": "local command",
-    "duration_s": 0.0
-  },
-  {
-    "time": "14:11:50",
-    "cmd": "what do you see, yolo",
-    "response": "YOLO: active | YOLO not loaded | 0.0fps",
-    "duration_s": 0.0
-  }
-]

Data/Brain/Sessions/session_023_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_023_2026-04-09/places.json

@@ -1 +0,0 @@
-{}

Data/Brain/Sessions/session_024_2026-04-09/alerts.json

@@ -1 +0,0 @@
-[]

Data/Brain/Sessions/session_024_2026-04-09/commands.json

@@ -1,14 +0,0 @@
-[
-  {
-    "time": "15:34:13",
-    "cmd": "cd ~/Marcus",
-    "response": "Moved forward",
-    "duration_s": 9.91
-  },
-  {
-    "time": "15:34:32",
-    "cmd": "ython3 run_marcus.py",
-    "response": "Running Python script",
-    "duration_s": 10.09
-  }
-]

Data/Brain/Sessions/session_024_2026-04-09/detections.json

@@ -1 +0,0 @@
-[]