Critical Fix: Align internal port to 8000 to satisfy OpenEnv library requirements

Dockerfile

@@ -10,11 +10,11 @@ RUN pip install --no-cache-dir --timeout 120 -r requirements.txt
 COPY . .
 
 # Expose port
-EXPOSE 7860
+EXPOSE 8000
 
 # Liveness probe — validator checks this
 HEALTHCHECK --interval=30s --timeout=10s --start-period=10s --retries=3 \
-  CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:7860/health')"
+  CMD python -c "import urllib.request; urllib.request.urlopen('http://localhost:8000/health')"
 
 # Start server
-CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]
+CMD ["uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "8000"]

inference.py

@@ -316,7 +316,7 @@ async def main() -> None:
                     env = PolicyEvolverEnv(base_url=base_url, provider=provider)
                     await env.connect()
                 else:
-                    local_url = os.environ.get("ENV_BASE_URL", "http://127.0.0.1:7860")
+                    local_url = os.environ.get("ENV_BASE_URL", "http://127.0.0.1:8000")
                     env = PolicyEvolverEnv(base_url=local_url)
                     # For local testing, we might want to check connection immediately or let run_episode handle it
             except Exception as e:

server/app.py

@@ -106,7 +106,7 @@ def run_baseline_route():
             "API_KEY": os.environ.get("API_KEY", ""),
             "API_BASE_URL": os.environ.get("API_BASE_URL", ""),
             "MODEL_NAME": os.environ.get("MODEL_NAME", "llama-3.1-8b-instant"),
-            "ENV_BASE_URL": "http://127.0.0.1:7860",
+            "ENV_BASE_URL": "http://127.0.0.1:8000",
         }
         
         result = subprocess.run(
@@ -401,7 +401,7 @@ async def startup_event():
 
 def main():
     # Sync with Hugging Face and local requirements
-    uvicorn.run("server.app:app", host="0.0.0.0", port=7860, reload=False)
+    uvicorn.run("server.app:app", host="0.0.0.0", port=8000, reload=False)
 
 if __name__ == "__main__":
     main()