Add hidden ZeroGPU probe endpoint

docs/SPACE_VLM_REPORT.md

@@ -1,50 +1,26 @@
 # Space VLM Validation Report
 
-- Generated at: 2026-06-06 04:55 UTC
+- Generated at: 2026-06-06 05:19:42 UTC
 - Space URL: https://huggingface.co/spaces/build-small-hackathon/ObjectverseDiary
 - Space repo: `build-small-hackathon/ObjectverseDiary`
-- Overall status: FAIL
+- Overall status: NOT RUN
 - Vision backend expected: `minicpm-v`
 - Text backend expected: `mock`
 
-## Attempt 1: Paid L4
+## Space Configuration
 
-- Requested configuration:
-  - `hardware`: `l4x1`
-  - `OBJECTVERSE_VISION_BACKEND`: `minicpm-v`
-  - `VISION_MODEL_ID`: `openbmb/MiniCPM-V-2_6`
-  - `OBJECTVERSE_TEXT_BACKEND`: `mock`
-- Result: failed before validation.
-- Error: `HfHubHTTPError: 402 Payment Required`
-- Meaning: Hugging Face requires billing or pre-paid credits for the `build-small-hackathon` organization before it can use paid `l4x1` hardware.
-- Safety outcome: mock-safe rollback was run after the failed hardware request.
-
-## Attempt 2: ZeroGPU
+- Applied configuration: not changed by this run.
 
-- Local compatibility update:
-  - Added optional `@spaces.GPU` support through `src/utils/zero_gpu.py`.
-  - Wrapped the Gradio generation callback with `@zero_gpu(duration=180)`.
-  - Uploaded the ZeroGPU-compatible app code to the Space.
-- Requested configuration:
-  - `hardware`: `zero-a10g`
-  - `OBJECTVERSE_VISION_BACKEND`: `minicpm-v`
-  - `VISION_MODEL_ID`: `openbmb/MiniCPM-V-2_6`
+- Rollback configuration:
+  - `repo_id`: `build-small-hackathon/ObjectverseDiary`
+  - `hardware`: `cpu-basic`
+  - `OBJECTVERSE_VISION_BACKEND`: `mock`
   - `OBJECTVERSE_TEXT_BACKEND`: `mock`
-- Result: Space reached `RUNNING` on `zero-a10g`, and `/config` was reachable, but the validation request did not return within the practical waiting window.
-- Observed logs: app startup only; no model load or inference error was shown in the fetched Space logs.
-- Safety outcome: the stuck local validation process was terminated, then mock-safe rollback was run.
-- Post-rollback runtime check: Space is `RUNNING` with `hardware=cpu-basic` and `requested_hardware=cpu-basic`.
 
 ## Results
 
-- Coffee mug: NOT RUN to completion
-- Computer keyboard: NOT RUN to completion
-- Running shoe: NOT RUN to completion
-
 ## Notes
 
 - Test images are temporary public Wikimedia Commons assets and are not committed.
-- Text generation remains mock during this validation plan.
-- No tokens, secrets, or private file paths are recorded in this report.
-- The validation script now has configuration-failure reporting, Gradio config retry, rollback-on-validation-failure, and per-prediction timeout protection.
-- Next unblock step: enable billing/pre-paid credits for the Hugging Face organization, or debug the ZeroGPU queue/request path with a smaller VLM or a minimal ZeroGPU probe before retrying full MiniCPM-V validation.
+- No tokens, secrets, or private file paths should be recorded in this report.
+- If validation fails, switch `OBJECTVERSE_VISION_BACKEND` back to `mock` to keep the demo usable.

src/ui/layout.py

@@ -89,6 +89,8 @@ def build_app() -> gr.Blocks:
         )
 
         result_state = gr.State()
+        zero_gpu_probe_button = gr.Button(visible=False)
+        zero_gpu_probe_output = gr.JSON(visible=False)
 
         with gr.Row(elem_id="archive-main-grid", elem_classes=["archive-grid"]):
             with gr.Column(scale=4, elem_classes=["archive-panel", "intake-panel"]):
@@ -210,6 +212,12 @@ def build_app() -> gr.Blocks:
             inputs=[chat_input, chatbot, result_state],
             outputs=[chatbot, chat_input],
         )
+        zero_gpu_probe_button.click(
+            fn=zero_gpu_probe,
+            inputs=[],
+            outputs=[zero_gpu_probe_output],
+            api_name="zero_gpu_probe",
+        )
 
     return demo
 
@@ -376,3 +384,19 @@ def chat_with_object(
     history.append({"role": "user", "content": clean_message})
     history.append({"role": "assistant", "content": reply})
     return history, ""
+
+
+@zero_gpu(duration=30)
+def zero_gpu_probe() -> dict[str, Any]:
+    try:
+        import torch
+    except Exception as exc:
+        return {"torch_import": False, "error": f"{type(exc).__name__}: {exc}"}
+
+    cuda_available = torch.cuda.is_available()
+    return {
+        "torch_import": True,
+        "cuda_available": cuda_available,
+        "device_count": torch.cuda.device_count(),
+        "device_name": torch.cuda.get_device_name(0) if cuda_available else "",
+    }