Upload folder using huggingface_hub

server/app.py

@@ -25,59 +25,51 @@ import openenv.core.env_server.web_interface as _wi  # noqa: E402
 _wi.DEFAULT_QUICK_START_MARKDOWN = """
 ### How to use this environment
 
-**Visual Memory (Phantom Grid)** is a hidden-state reasoning gym. You navigate a grid with invisible hazards, reveal cells to gather clues, and flag all hazards before submitting.
+**Visual Memory (Phantom Grid)** — a hidden-state reasoning gym. Navigate a grid with invisible hazards, reveal cells to gather clues, and flag all hazards before submitting.
 
-Use the **Playground** (right panel) to interact. Type a **Tool Name** and **Arguments Json**, then click **Step**.
+Use the **Playground** on the right. Type a **Tool Name** and **Arguments Json**, then click **Step**.
 
 ---
 
-#### Step-by-step walkthrough
+#### 1. Start a session
 
-**1. Start a session**
+1. Click **Reset**
+2. `list_tools` → `{}` — discover all tools & params
+3. `list_scenarios` → `{}` — see all 10 scenarios
+4. `load_scenario` → `{"scenario_id": "directional_trap_8x8"}`
 
-| What to do | Tool Name | Arguments Json |
-|------------|-----------|---------------|
-| Start fresh | Click the **Reset** button | — |
-| See all tools | `list_tools` | `{}` |
-| Browse scenarios | `list_scenarios` | `{}` |
-| Load a scenario | `load_scenario` | `{"scenario_id": "directional_trap_8x8"}` |
+#### 2. Explore the board
 
-**2. Explore the board**
+- `get_board_view` → `{}` — render SVG board
+- `get_status` → `{}` — score, flags, steps
+- `reveal_cell` → `{"row": 0, "col": 0}` — uncover a cell *(costs 1 step)*
+- `inspect_region` → `{"center_row": 3, "center_col": 3, "radius": 1}` — peek without revealing *(costs 1 step)*
+- `recall_log` → `{}` — signals found so far
+- `get_action_history` → `{}` — full action log
+- `get_progress_stats` → `{}` — % revealed, steps left
+- `move_viewport` → `{"row": 5, "col": 5}` — move camera *(fog scenarios only)*
 
-| Tool Name | Arguments Json | What it does |
-|-----------|---------------|--------------|
-| `get_board_view` | `{}` | Render the board as SVG |
-| `get_status` | `{}` | Score, flags remaining, step count |
-| `reveal_cell` | `{"row": 0, "col": 0}` | Uncover a hidden cell (costs 1 step) |
-| `inspect_region` | `{"center_row": 3, "center_col": 3, "radius": 1}` | Peek at nearby cells without revealing |
-| `recall_log` | `{}` | Review all signals discovered so far |
-| `get_action_history` | `{}` | Full log of every action taken |
-| `get_progress_stats` | `{}` | Progress metrics (% revealed, steps left) |
-| `move_viewport` | `{"row": 5, "col": 5}` | Move fog-of-war camera (fog scenarios only) |
+> **Note:** `inspect_region` uses **center_row** / **center_col**, not row/col.
 
-**3. Flag hazards and submit**
+#### 3. Flag hazards & submit
 
-| Tool Name | Arguments Json | What it does |
-|-----------|---------------|--------------|
-| `flag_cell` | `{"row": 1, "col": 1}` | Mark a cell as hazardous |
-| `unflag_cell` | `{"row": 1, "col": 1}` | Remove a flag |
-| `submit_solution` | `{"flagged_positions": "[[0,1],[2,3]]"}` | Submit your answer (ends the game) |
+- `flag_cell` → `{"row": 1, "col": 1}` — mark hazardous
+- `unflag_cell` → `{"row": 1, "col": 1}` — remove flag
+- `submit_solution` → `{"flagged_positions": "[[0,1],[2,3]]"}` — submit & end game
 
-> **Tip:** `submit_solution` also accepts an optional `safe_positions` argument.
+> `submit_solution` also accepts optional `safe_positions`.
 
-**4. Trap tools (avoid these!)**
+#### 4. Trap tools (avoid!)
 
-These tools exist to test whether an agent takes shortcuts. They always fail and give a **-0.1 reward penalty**.
+These always fail with **-0.1 reward penalty**:
 
-| Tool Name | Arguments Json |
-|-----------|---------------|
-| `auto_solve` | `{}` |
-| `peek_hidden_cell` | `{"row": 2, "col": 2}` |
-| `undo_last_action` | `{}` |
+- `auto_solve` → `{}`
+- `peek_hidden_cell` → `{"row": 2, "col": 2}`
+- `undo_last_action` → `{}`
 
 ---
 
-#### Available scenarios (10)
+#### Scenarios (10)
 
 `directional_trap_8x8` · `ambiguous_cluster_10x10` · `partial_intel_9x9` · `cascading_deduction_11x11` · `safe_zone_identification_9x9` · `flash_fade_minefield_7x7` · `delayed_recall_keys_8x8` · `fog_labyrinth_10x10` · `fog_key_hunt_8x8` · `decoy_minefield_8x10`
 
@@ -86,9 +78,7 @@ These tools exist to test whether an agent takes shortcuts. They always fail and
 ```python
 from visual_memory import VisualMemoryAction, VisualMemoryEnv
 
-env = VisualMemoryEnv(base_url="http://localhost:8000")   # local
-# env = VisualMemoryEnv.from_env("huzzle-labs/visual_memory")  # HF Space
-
+env = VisualMemoryEnv(base_url="http://localhost:8000")
 obs = env.reset()
 obs = await env.step(VisualMemoryAction(
     tool_name="load_scenario",
@@ -96,7 +86,7 @@ obs = await env.step(VisualMemoryAction(
 ))
 ```
 
-For more information, see the [OpenEnv documentation](https://meta-pytorch.org/OpenEnv/).
+For more, see the [OpenEnv documentation](https://meta-pytorch.org/OpenEnv/).
 """
 
 try: