inference fixed, port changed to 7860

Dockerfile

@@ -12,11 +12,11 @@ COPY baseline_runner.py .
 COPY inference.py .
 COPY openenv.yaml .
 
-# HuggingFace Spaces expects port 8000
-EXPOSE 8000
+# HuggingFace Spaces expects port 7860
+EXPOSE 7860
 
 # Health check
 HEALTHCHECK --interval=30s --timeout=10s --retries=3 \
-    CMD python -c "import requests; requests.get('http://localhost:8000/')" || exit 1
+    CMD python -c "import requests; requests.get('http://localhost:7860/')" || exit 1
 
-CMD ["python", "-m", "uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "8000"]
+CMD ["python", "-m", "uvicorn", "server.app:app", "--host", "0.0.0.0", "--port", "7860"]

README.md

@@ -4,7 +4,7 @@ emoji: 🔧
 colorFrom: blue
 colorTo: green
 sdk: docker
-app_port: 8000
+app_port: 7860
 pinned: false
 ---
 
@@ -296,12 +296,12 @@ This ensures:
 
 ```bash
 # 1. Start an episode
-curl -X POST http://localhost:8000/reset \
+curl -X POST http://localhost:7860/reset \
   -H "Content-Type: application/json" \
   -d '{"task_id": "k8s_pod_failures", "scenario_id": "oom_killed"}'
 
 # 2. Fix the memory limit (any reasonable value works — simulator validates structurally)
-curl -X POST http://localhost:8000/step \
+curl -X POST http://localhost:7860/step \
   -H "Content-Type: application/json" \
   -d '{
     "action": {
@@ -325,7 +325,7 @@ curl -X POST http://localhost:8000/step \
 
 ```bash
 pip install -r requirements.txt
-python -m uvicorn server.app:app --host 0.0.0.0 --port 8000
+python -m uvicorn server.app:app --host 0.0.0.0 --port 7860
 ```
 
 ### Run Tests
@@ -338,7 +338,7 @@ pytest tests/ -v
 
 ```bash
 docker build -t cloud-native-devops-env .
-docker run -p 8000:8000 cloud-native-devops-env
+docker run -p 7860:7860 cloud-native-devops-env
 ```
 
 ### Baseline Inference (with LLM)

inference.py

@@ -56,7 +56,7 @@ from openai import OpenAI
 API_BASE_URL = os.getenv("API_BASE_URL") or "https://router.huggingface.co/v1"
 MODEL_NAME = os.getenv("MODEL_NAME") or "meta-llama/Llama-3.1-70B-Instruct"
 API_KEY = os.getenv("HF_TOKEN") or os.getenv("API_KEY")
-ENV_URL = os.getenv("ENV_URL", "http://localhost:8000")
+ENV_URL = os.getenv("ENV_URL", "http://localhost:7860")
 LOCAL_IMAGE_NAME = os.getenv("LOCAL_IMAGE_NAME")
 BENCHMARK = "cloud_native_devops"
 MAX_STEPS = 8  # leave 2 steps buffer before env hard-limit of 10
@@ -72,18 +72,29 @@ Your job is to:
 
 When you identify a fix, respond with a JSON object in this exact format:
 {
+  "action_type": "YOUR_CHOSEN_ACTION_TYPE",
   "reasoning": "Brief explanation of the bug and fix",
   "edits": [
     {
       "file_path": "path/to/file",
-      "old_content": "exact broken line or block",
-      "new_content": "corrected line or block"
+      "line_number": 5,               // Only needed for replace_line, add_line, delete_line, add_block
+      "old_content": "exactly broken", // Only needed for edit_file, delete_block
+      "new_content": "corrected block" // Not needed for delete_line, delete_block
     }
   ]
 }
 
-To create a new file (e.g. a missing ConfigMap), use an empty old_content:
+Available action_type values for edits:
+- "edit_file" (requires old_content and new_content)
+- "replace_line" (requires line_number and new_content)
+- "add_line" (requires line_number and new_content)
+- "delete_line" (requires line_number)
+- "add_block" (requires line_number and new_content)
+- "delete_block" (requires old_content)
+
+To create a new file (e.g. a missing ConfigMap), use "edit_file" with empty old_content:
 {
+  "action_type": "edit_file",
   "reasoning": "Create missing ConfigMap manifest",
   "edits": [
     {
@@ -95,10 +106,10 @@ To create a new file (e.g. a missing ConfigMap), use an empty old_content:
 }
 
 If you believe all issues are fixed and want to submit, respond with:
-{"action": "submit"}
+{"action_type": "submit"}
 
 If you need a hint, respond with:
-{"action": "hint"}
+{"action_type": "request_hint"}
 
 Rules:
 - Match old_content EXACTLY as it appears in the file (whitespace matters)
@@ -217,20 +228,26 @@ def parse_llm_response(text: str) -> Dict[str, Any]:
 
 def build_action(parsed: Dict[str, Any]) -> Dict[str, Any]:
     """Convert parsed LLM response to environment action format."""
-    if parsed.get("action") == "submit":
+    action_type = parsed.get("action_type")
+
+    # Backwards compatibility and standard aliases
+    if parsed.get("action") == "submit" or action_type == "submit":
         return {"action_type": "submit"}
-    if parsed.get("action") == "hint":
+    if parsed.get("action") == "hint" or action_type == "request_hint":
         return {"action_type": "request_hint"}
 
     edits = parsed.get("edits", [])
-    if not edits:
+    if not edits and not action_type:
         return {"action_type": "submit"}
 
+    action_str = action_type if action_type else "edit_file"
+
     return {
-        "action_type": "edit_file",
+        "action_type": action_str,
         "edits": [
             {
                 "file_path": e.get("file_path", ""),
+                "line_number": e.get("line_number"),
                 "old_content": e.get("old_content", ""),
                 "new_content": e.get("new_content", ""),
             }
@@ -384,7 +401,7 @@ def main():
         print(f"[DEBUG] Environment status: {health.get('status', 'unknown')}", flush=True)
     except Exception as e:
         print(f"[DEBUG] Cannot connect to environment at {ENV_URL}: {e}", flush=True)
-        print("[DEBUG] Start the server first: python -m uvicorn server.app:app --host 0.0.0.0 --port 8000", flush=True)
+        print("[DEBUG] Start the server first: python -m uvicorn server.app:app --host 0.0.0.0 --port 7860", flush=True)
         sys.exit(1)
 
     client = create_client()

server/app.py

@@ -234,7 +234,7 @@ async def run_baseline(request: Optional[BaselineRequest] = None):
 
 
 def main():
-    uvicorn.run(app, host="0.0.0.0", port=8000)
+    uvicorn.run(app, host="0.0.0.0", port=7860)
 
 
 if __name__ == "__main__":

server/static/index.html

@@ -428,12 +428,12 @@
         </div>
         <div class="code-block">
 <span class="comment"># 1. Get a broken K8s deployment with OOMKilled pods</span>
-<span class="cmd">curl</span> -X POST <span class="url">http://localhost:8000/reset</span> \
+<span class="cmd">curl</span> -X POST <span class="url">http://localhost:7860/reset</span> \
   -H <span class="flag">"Content-Type: application/json"</span> \
   -d '{"task_id": "k8s_pod_failures", "scenario_id": "oom_killed"}'
 
 <span class="comment"># 2. Bump the memory limit from 64Mi to 256Mi</span>
-<span class="cmd">curl</span> -X POST <span class="url">http://localhost:8000/step</span> \
+<span class="cmd">curl</span> -X POST <span class="url">http://localhost:7860/step</span> \
   -H <span class="flag">"Content-Type: application/json"</span> \
   -d '{"action": {"action_type": "edit_file", "edits": [{"file_path": "k8s/deployment.yaml", "old_content": "memory: \"64Mi\"", "new_content": "memory: \"256Mi\""}]}}'
 

server/tasks/pipeline_build_deploy.py

@@ -128,7 +128,7 @@ class PipelineBuildDeployTask(BaseTask):
                         "COPY requirements.txt .\n"
                         "RUN pip install -r requirements.txt\n"
                         "COPY . .\n"
-                        "EXPOSE 8000\n"
+                        "EXPOSE 7860\n"
                         'CMD ["python", "app.py"]\n'
                     ),
                 },
@@ -275,7 +275,7 @@ class PipelineBuildDeployTask(BaseTask):
                         "WORKDIR /app\n"
                         "COPY . .\n"
                         "RUN echo $APP_VERSION > /app/version.txt\n"
-                        "EXPOSE 8000\n"
+                        "EXPOSE 7860\n"
                         'CMD ["python", "app.py"]\n'
                     ),
                 },
@@ -341,7 +341,7 @@ class PipelineBuildDeployTask(BaseTask):
                         "COPY requirements.txt .\n"
                         "RUN pip install -r requirements.txt\n"
                         "COPY . .\n"
-                        "EXPOSE 8000\n"
+                        "EXPOSE 7860\n"
                         'CMD ["uvicorn", "main:app", "--host", "0.0.0.0"]\n'
                     ),
                 },

server/tasks/pipeline_full.py

@@ -299,8 +299,8 @@ class PipelineFullTask(BaseTask):
                         "COPY requirements.txt .\n"
                         "RUN pip install -r requirements.txt\n"
                         "COPY . .\n"
-                        "EXPOSE 8000\n"
-                        'CMD ["gunicorn", "app:app", "-b", "0.0.0.0:8000"]\n'
+                        "EXPOSE 7860\n"
+                        'CMD ["gunicorn", "app:app", "-b", "0.0.0.0:7860"]\n'
                     ),
                 },
                 {
@@ -330,7 +330,7 @@ class PipelineFullTask(BaseTask):
                         "      - name: api\n"
                         "        image: ghcr.io/myorg/myapp:latest\n"
                         "        ports:\n"
-                        "        - containerPort: 8000\n"
+                        "        - containerPort: 7860\n"
                         "        resources:\n"
                         "          limits:\n"
                         '            memory: "64Mi"\n'

server/tasks/task_1_build_errors.py

@@ -70,7 +70,7 @@ class DockerfileSyntaxTask(BaseTask):
                         "COPY requirements.txt .\n"
                         "RUN pip install -r requirements.txt\n"
                         "COPY . .\n"
-                        "EXPOSE 8000\n"
+                        "EXPOSE 7860\n"
                         'CMD ["python", "app.py"]'
                     ),
                 },

smoke_test.py

@@ -2,7 +2,7 @@
 
 Usage:
   .\\.venv\\Scripts\\python.exe smoke_test.py
-  .\\.venv\\Scripts\\python.exe smoke_test.py --mode live --base-url http://127.0.0.1:8000
+  .\\.venv\\Scripts\\python.exe smoke_test.py --mode live --base-url http://127.0.0.1:7860
 
 Modes:
   - inprocess (default): uses FastAPI TestClient, no running server needed.
@@ -227,7 +227,7 @@ def run_smoke(client: EndpointClient) -> int:
 def main() -> int:
     parser = argparse.ArgumentParser(description="Smoke test Cloud-Native DevOps Debug FastAPI server")
     parser.add_argument("--mode", choices=["inprocess", "live"], default="inprocess")
-    parser.add_argument("--base-url", default="http://127.0.0.1:8000")
+    parser.add_argument("--base-url", default="http://127.0.0.1:7860")
     args = parser.parse_args()
 
     if args.mode == "inprocess":