docs: rename models/README.md to models/modelREADME.md to avoid confusion with root README

AGENTS.md

@@ -36,7 +36,7 @@ Indonesian (`karung`=sack, `truk`=truck); YOLO class names are English
   (`src/counting.py`). Same line geometry + 30px dedup for sacks and boxes.
 - All weights live in `models/` (`.pt`/`.onnx` tracked; `.engine` gitignored —
   rebuild via `export_model.py`; per-mode detector/filter matrix in
-  `models/README.md`). Verified classes: `truck-detector`={truck},
+  `models/modelREADME.md`). Verified classes: `truck-detector`={truck},
   `model_karung_truk`/`v4-best`={sack,truck}, `karung-dimuat-*-seg-200e`=
   {person,sack} (seg; persons drawn, never counted), `best`={sack},
   `yolo11n-…-sack+box`={sack,box}. `predict.py` auto-picks `MODEL_PATH` env, else

README.md

@@ -52,7 +52,7 @@ add SQLite persistence, live-frame publishing to `/dev/shm`, and zone polygons.
 
 ## Models
 
-All weights live in `models/` (see [`models/README.md`](models/README.md) for the
+All weights live in `models/` (see [`models/modelREADME.md`](models/modelREADME.md) for the
 per-mode detector/filter matrix).
 
 | File | Classes | Role |

deploy_to_jetson.py

@@ -1,7 +1,7 @@
 import paramiko
 import os
 
-# Production loads .engine weights from models/ (see models/README.md).
+# Production loads .engine weights from models/ (see models/modelREADME.md).
 # .pt/.onnx stay local-only (dev/export) — not synced to save bandwidth.
 MODEL_ENGINES = [
     "v4-best.engine",

docs/configuration.md

@@ -21,7 +21,7 @@ Template: `.env.example`. Production values live in `.env` (git-ignored).
 | `FLASK_DEBUG` | `false` | Flask debug |
 | `RTSP_URL` | — | Camera stream URL |
 | `MODEL_PATH` | auto (`models/v4-best.engine` > `.pt` > `v4-best (1).pt` > `models/model_karung_truk.engine` > `.pt`) | Override combined-model weights (`predict.py`) |
-| `MODEL_MODE` | `B` | Model pipeline mode A/B/C/D (see `models/README.md`); also settable via `--model-mode` or dashboard (applies on restart) |
+| `MODEL_MODE` | `B` | Model pipeline mode A/B/C/D (see `models/modelREADME.md`); also settable via `--model-mode` or dashboard (applies on restart) |
 | `BATCH_MERGE_THRESHOLD_SECONDS` | `300` | Merge window for adjacent batches |
 
 On Windows dev machines these resolve to `d:/Belajar/menghitung karung/...`.

docs/deployment.md

@@ -30,7 +30,7 @@ services and checks status + ports (5000/5721). Run from the dev machine.
 ## TensorRT export
 On the Jetson (needs CUDA): `python3 export_model.py models/<name>.pt` exports to
 FP16 `.engine` next to the `.pt` (default: karung-dimuat seg model). Production
-loads `.engine` only — see `models/README.md` for which weights each mode uses.
+loads `.engine` only — see `models/modelREADME.md` for which weights each mode uses.
 
 ## Runtime data files
 - SQLite `jetson_counter.db`: `batches(counting_date, batch_number, camera_name,

docs/models.md

@@ -7,7 +7,7 @@ see `export_model.py` / `export_v4.py`).
 ## Inventory
 
 All weights live in `models/` — full per-mode detector/filter matrix in
-[`models/README.md`](../models/README.md).
+[`models/modelREADME.md`](../models/modelREADME.md).
 
 | File | Classes | Task | Used by |
 |---|---|---|---|

export_model.py

@@ -3,7 +3,7 @@ import torch
 import os
 import sys
 
-# All weights live in models/ (see models/README.md).
+# All weights live in models/ (see models/modelREADME.md).
 MODELS_DIR = os.path.join(os.path.dirname(os.path.abspath(__file__)), "models")
 
 def main():

predict.py

@@ -444,7 +444,7 @@ last_seen_near_person_frame = {}
 blocked_due_to_duplicate = {}
 
 # --- Model Paths ---
-# All weights live in models/ (see models/README.md for mode/filter matrix).
+# All weights live in models/ (see models/modelREADME.md for mode/filter matrix).
 # Model gabungan karung + truk terbaru (v4-best TensorRT / PyTorch)
 _BASE_DIR = os.path.dirname(os.path.abspath(__file__))
 _MODELS_DIR = os.path.join(_BASE_DIR, "models")

src/config.py

@@ -17,7 +17,7 @@ class Config:
     local_rtsp: str = ""
     jetson_rtsp: str = ""
 
-    # Model paths (canonical production weights in models/; see models/README.md)
+    # Model paths (canonical production weights in models/; see models/modelREADME.md)
     sack_model_path: str = "./models/best.engine"
     truck_model_path: str = "./models/truck-detector.engine"