Upload README.md with huggingface_hub

README.md

@@ -20,6 +20,61 @@ tags:
 
 An OpenEnv RL environment where agents must navigate grids with hidden hazards, memorize revealed patterns, and make optimal decisions with incomplete information. The name *Phantom Grid* reflects the core challenge: invisible dangers lurk beneath every cell, and the agent must deduce their locations from indirect signals — like hunting phantoms by their shadows. Designed to stress spatial reasoning, working memory, uncertainty handling, and risk-averse planning — areas where frontier LLMs consistently underperform.
 
+## Playground Quick Start
+
+Use the **Playground** panel (right side) to interact with the environment. Each action takes a **Tool Name** and **Arguments Json**.
+
+### Typical workflow
+
+1. Click **Reset** to start a fresh session
+2. Enter `list_scenarios` (args: `{}`) → see all 10 scenarios
+3. Enter `load_scenario` (args: `{"scenario_id": "directional_trap_8x8"}`) → start a game
+4. Enter `get_board_view` (args: `{}`) → see the board as SVG
+5. Enter `reveal_cell` (args: `{"row": 0, "col": 0}`) → uncover a cell
+6. Enter `flag_cell` (args: `{"row": 3, "col": 5}`) → mark a suspected hazard
+7. Enter `submit_solution` (args: `{"flagged_positions": "[[3,5]]"}`) → submit your answer
+
+### All tool commands (copy-paste ready)
+
+| Tool Name | Arguments Json | Description |
+|-----------|---------------|-------------|
+| `list_tools` | `{}` | List all available MCP tools |
+| `get_session_info` | `{}` | Current session metadata |
+| `list_scenarios` | `{}` | List all 10 scenarios |
+| `load_scenario` | `{"scenario_id": "directional_trap_8x8"}` | Load a scenario |
+| `reset_scenario` | `{}` | Restart the current scenario |
+| `get_board_view` | `{}` | Get visible board (SVG + metadata) |
+| `get_status` | `{}` | Score, flags, cells revealed |
+| `reveal_cell` | `{"row": 0, "col": 0}` | Reveal a hidden cell (costs 1 step) |
+| `inspect_region` | `{"row": 3, "col": 3, "radius": 1}` | Peek at a region without revealing |
+| `flag_cell` | `{"row": 1, "col": 1}` | Mark cell as hazardous |
+| `unflag_cell` | `{"row": 1, "col": 1}` | Remove a hazard flag |
+| `move_viewport` | `{"row": 5, "col": 5}` | Move fog-of-war viewport (fog scenarios only) |
+| `submit_solution` | `{"flagged_positions": "[[0,1],[2,3]]"}` | Submit final answer |
+| `recall_log` | `{}` | Review all discovered signals |
+| `get_action_history` | `{}` | Full action log with outcomes |
+| `get_progress_stats` | `{}` | Progress metrics |
+| `auto_solve` | `{}` | **Trap** — always fails |
+| `peek_hidden_cell` | `{"row": 2, "col": 2}` | **Trap** — always fails |
+| `undo_last_action` | `{}` | **Trap** — always fails |
+
+### Run locally
+
+```bash
+cd visual-memory
+pip install -e .
+
+# Start the environment server
+docker build -t openenv-visual-memory -f server/Dockerfile .
+docker run -d --name visual-memory -p 8000:8000 openenv-visual-memory
+
+# Verify it's running
+curl http://localhost:8000/health
+
+# Open the playground in your browser
+open http://localhost:8000/web/
+```
+
 ## Hugging Face Space Deployment
 
 This Space is built from OpenEnV environment `visual_memory`.
@@ -37,7 +92,6 @@ from visual_memory import VisualMemoryAction, VisualMemoryEnv
 
 with VisualMemoryEnv.from_env("huzzle-labs/visual_memory") as env:
     obs = env.reset()
-    # Use tool_name and arguments_json (NOT message)
     obs = await env.step(VisualMemoryAction(
         tool_name="list_scenarios",
         arguments_json="{}"