Add dataset bench and validation agents

README.md

@@ -27,8 +27,9 @@ Seg_Data_Server_Net/
 cd Seg_Data_Server_Net
 cp .env.example .env
 
-# Backend. The existing machine already has a seg_server env with FastAPI.
-conda run -n seg_server uvicorn app.main:app --app-dir backend --host 0.0.0.0 --port 8000
+# Backend. The deployment env is seg_smp so the API and task wrappers share
+# the same segmentation dependency stack.
+conda run -n seg_smp uvicorn app.main:app --app-dir backend --host 0.0.0.0 --port 8010
 
 # Frontend.
 cd frontend
@@ -37,7 +38,13 @@ npm run dev -- --host 0.0.0.0
 ```
 
 Open the Vite URL shown in the terminal. The frontend expects the backend at
-`http://localhost:8000` by default.
+`http://localhost:8010` by default.
+
+The web UI includes a dataset bench for creating upload workspaces, uploading
+images/labels/masks, and jumping into the existing rename, PNG conversion,
+resize, pair-check, label rebuild, transparent overlay, stitch, and video-frame
+jobs. Segmentation previews, YOLO heatmaps, and loss/metric artifacts are
+grouped on the results dashboard.
 
 ## Weight Sync
 
@@ -77,3 +84,15 @@ The backend exposes all current Seg capabilities as job types. Examples:
 
 Use `GET /api/catalog` to inspect supported models, algorithms, datasets, and
 task types discovered from the existing `Seg/` workspace.
+
+## Agents
+
+Run the local evaluation and validation agents before publishing changes:
+
+```bash
+PYTHONPATH=backend conda run -n seg_smp python scripts/run_agents.py --build
+```
+
+The validation agent checks catalog coverage, the new `seg_smp` env, GPU
+visibility, no-weight Git safety, backend tests, frontend build, and live
+backend/frontend endpoints when the services are running.