Fix benchmark output saving: add results dir and print errors

Dockerfile

@@ -12,6 +12,9 @@ COPY pyproject.toml .
 RUN pip install --no-cache-dir . 2>/dev/null || pip install --no-cache-dir \
     fastapi uvicorn pydantic openai requests packaging gradio python-dotenv
 
+# Make sure results directory exists and is writable by any user
+RUN mkdir -p results && chmod 777 results
+
 # Copy project files
 COPY . .
 

inference.py

@@ -333,8 +333,8 @@ def main() -> None:
         from server.benchmark_store import append_result
         append_result(MODEL_NAME, MODEL_NAME, scores)
         print(f"💾 Results saved (avg: {avg:.4f})", flush=True)
-    except Exception:
-        pass
+    except Exception as e:
+        print(f"⚠️ Failed to save results to disk: {e}", flush=True)
 
 
 if __name__ == "__main__":

server/app.py

@@ -573,8 +573,8 @@ def run_benchmark(body: dict):
         # Persist to disk via benchmark_store
         try:
             append_result(model_name, model_id, scores)
-        except Exception:
-            pass
+        except Exception as e:
+            print(f"Failed to append result: {e}", flush=True)
         yield f"data: {json.dumps({'type': 'done', 'result': result})}\n\n"
 
     return StreamingResponse(event_stream(), media_type="text/event-stream")