Hi,
Currently my server have 4 H100. I'm following the instruction from deepswe to set up the environment. I'm now trying to use base model qwen3-4b and qwen3-8B insetad of Qwen3-32B first.
To run Kubernetes locally, we suggest installing [kind](https://kind.sigs.k8s.io/) and launching it with kind create cluster. However, please do note that this is not sufficient to launch a full training run.
But after using kind to set up the environment, I got the errors below. Could you please provide any insight on how to set up kubernetes in this case? Or if you have any other suggestio? Thanks for the help.
Bug:
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': 'f6fb8f3b-ccf7-416d-860f-f8c0b3e75f64', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 212d99fd-0bb9-4d44-99cc-84a904fc690a does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': 'f6fb8f3b-ccf7-416d-860f-f8c0b3e75f64', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 212d99fd-0bb9-4d44-99cc-84a904fc690a does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '22d6eff4-c2d4-4eb5-a817-5e6e24c8aa44', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 9e5a193a-e420-448f-899a-69e0deb4449e does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '22d6eff4-c2d4-4eb5-a817-5e6e24c8aa44', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 9e5a193a-e420-448f-899a-69e0deb4449e does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '8c3714f7-0db0-46aa-aec2-71091b2db85f', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod c1601f23-7f48-4c4b-aa61-8a5aa7d34edf does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '8c3714f7-0db0-46aa-aec2-71091b2db85f', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod c1601f23-7f48-4c4b-aa61-8a5aa7d34edf does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '9cf8fa45-0a69-4994-835e-f6f3a72a40f7', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod fd398aaa-aa6b-47d2-b31f-4d500f0d5e7c does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '9cf8fa45-0a69-4994-835e-f6f3a72a40f7', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod fd398aaa-aa6b-47d2-b31f-4d500f0d5e7c does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '925e33d7-7895-4089-8ee6-1f01706b3a17', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 06:41:00 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 2df38aec-0370-40e0-bddc-a9a196afe77d does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '925e33d7-7895-4089-8ee6-1f01706b3a17', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 06:41:00 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 2df38aec-0370-40e0-bddc-a9a196afe77d does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) NoneType: None
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 521, in launch_one_trajectory_task
(TaskRunner pid=837619) result = await self.run_agent_trajectory_with_retry(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 502, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) raise Exception(f"Trajectory {idx} cannot complete. Please check the log message")
(TaskRunner pid=837619) Exception: Trajectory 34 cannot complete. Please check the log message
(TaskRunner pid=837619) Exception in thread Thread-9 (runner):
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
(TaskRunner pid=837619) self.run()
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/threading.py", line 982, in run
(TaskRunner pid=837619) self._target(*self._args, **self._kwargs)
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/trainer/verl/agent_ppo_trainer.py", line 758, in runner
(TaskRunner pid=837619) asyncio.run(consume())
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 190, in run
(TaskRunner pid=837619) return runner.run(main)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 118, in run
(TaskRunner pid=837619) return self._loop.run_until_complete(task)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/trainer/verl/agent_ppo_trainer.py", line 754, in consume
(TaskRunner pid=837619) async for item in self.agent_execution_engine.trajectory_generator(timing_raw=timing_raw, mode=mode, meta_info=meta_info):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 546, in trajectory_generator
(TaskRunner pid=837619) raise e
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 541, in trajectory_generator
(TaskRunner pid=837619) result = await coro
(TaskRunner pid=837619) ^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 615, in _wait_for_one
(TaskRunner pid=837619) return f.result() # May raise f.exception().
(TaskRunner pid=837619) ^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 531, in launch_one_trajectory_task
(TaskRunner pid=837619) raise e
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 521, in launch_one_trajectory_task
(TaskRunner pid=837619) result = await self.run_agent_trajectory_with_retry(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 502, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) raise Exception(f"Trajectory {idx} cannot complete. Please check the log message")
(TaskRunner pid=837619) Exception: Trajectory 34 cannot complete. Please check the log message1
Hi,
Currently my server have 4 H100. I'm following the instruction from deepswe to set up the environment. I'm now trying to use base model qwen3-4b and qwen3-8B insetad of Qwen3-32B first.
To run Kubernetes locally, we suggest installing [kind](https://kind.sigs.k8s.io/) and launching it with kind create cluster. However, please do note that this is not sufficient to launch a full training run.But after using kind to set up the environment, I got the errors below. Could you please provide any insight on how to set up kubernetes in this case? Or if you have any other suggestio? Thanks for the help.
Bug:
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': 'f6fb8f3b-ccf7-416d-860f-f8c0b3e75f64', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 212d99fd-0bb9-4d44-99cc-84a904fc690a does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': 'f6fb8f3b-ccf7-416d-860f-f8c0b3e75f64', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 212d99fd-0bb9-4d44-99cc-84a904fc690a does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '22d6eff4-c2d4-4eb5-a817-5e6e24c8aa44', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 9e5a193a-e420-448f-899a-69e0deb4449e does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '22d6eff4-c2d4-4eb5-a817-5e6e24c8aa44', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 9e5a193a-e420-448f-899a-69e0deb4449e does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '8c3714f7-0db0-46aa-aec2-71091b2db85f', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod c1601f23-7f48-4c4b-aa61-8a5aa7d34edf does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '8c3714f7-0db0-46aa-aec2-71091b2db85f', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod c1601f23-7f48-4c4b-aa61-8a5aa7d34edf does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '9cf8fa45-0a69-4994-835e-f6f3a72a40f7', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod fd398aaa-aa6b-47d2-b31f-4d500f0d5e7c does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '9cf8fa45-0a69-4994-835e-f6f3a72a40f7', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 05:56:30 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod fd398aaa-aa6b-47d2-b31f-4d500f0d5e7c does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 533, in websocket_call
(TaskRunner pid=837619) client = WSClient(configuration, url, headers, capture_all, binary=binary)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 68, in init
(TaskRunner pid=837619) self.sock = create_websocket(configuration, url, headers)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 499, in create_websocket
(TaskRunner pid=837619) websocket.connect(url, **connect_opt)
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_core.py", line 268, in connect
(TaskRunner pid=837619) self.handshake_response = handshake(self.sock, url, *addrs, **options)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 66, in handshake
(TaskRunner pid=837619) status, resp = _get_resp_headers(sock)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/websocket/_handshake.py", line 158, in _get_resp_headers
(TaskRunner pid=837619) raise WebSocketBadStatusException(
(TaskRunner pid=837619) websocket._exceptions.WebSocketBadStatusException: Handshake status 400 Bad Request -+-+- {'audit-id': '925e33d7-7895-4089-8ee6-1f01706b3a17', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 06:41:00 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 2df38aec-0370-40e0-bddc-a9a196afe77d does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) During handling of the above exception, another exception occurred:
(TaskRunner pid=837619)
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 497, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) return await asyncio.wait_for(self.run_agent_trajectory_async(idx, application_id=application_id, seed=seed, mode=mode, **kwargs), timeout=7200)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 489, in wait_for
(TaskRunner pid=837619) return fut.result()
(TaskRunner pid=837619) ^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 203, in run_agent_trajectory_async
(TaskRunner pid=837619) observation, info = await loop.run_in_executor(self.executor, env.reset)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/concurrent/futures/thread.py", line 58, in run
(TaskRunner pid=837619) result = self.fn(*self.args, **self.kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/environments/swe/swe.py", line 108, in reset
(TaskRunner pid=837619) self.env.add_commands(R2EGYM_COMMAND_FILES)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/environment/env.py", line 106, in add_commands
(TaskRunner pid=837619) self.runtime.copy_to_container(cmd_file, container_path)
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 844, in copy_to_container
(TaskRunner pid=837619) return self._copy_to_container_kubernetes(src_path, dest_path)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/R2E-Gym/src/r2egym/agenthub/runtime/docker.py", line 806, in _copy_to_container_kubernetes
(TaskRunner pid=837619) resp = stream(
(TaskRunner pid=837619) ^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/stream.py", line 36, in _websocket_request
(TaskRunner pid=837619) out = api_method(*args, **kwargs)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 994, in connect_get_namespaced_pod_exec
(TaskRunner pid=837619) return self.connect_get_namespaced_pod_exec_with_http_info(name, namespace, **kwargs) # noqa: E501
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api/core_v1_api.py", line 1101, in connect_get_namespaced_pod_exec_with_http_info
(TaskRunner pid=837619) return self.api_client.call_api(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 348, in call_api
(TaskRunner pid=837619) return self.__call_api(resource_path, method,
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/client/api_client.py", line 180, in __call_api
(TaskRunner pid=837619) response_data = self.request(
(TaskRunner pid=837619) ^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/.venv/lib/python3.11/site-packages/kubernetes/stream/ws_client.py", line 543, in websocket_call
(TaskRunner pid=837619) raise ApiException(status=0, reason=str(e))
(TaskRunner pid=837619) kubernetes.client.exceptions.ApiException: (0)
(TaskRunner pid=837619) Reason: Handshake status 400 Bad Request -+-+- {'audit-id': '925e33d7-7895-4089-8ee6-1f01706b3a17', 'cache-control': 'no-cache, private', 'content-type': 'application/json', 'date': 'Fri, 23 Jan 2026 06:41:00 GMT', 'content-length': '185'} -+-+- b'{"kind":"Status","apiVersion":"v1","metadata":{},"status":"Failure","message":"pod 2df38aec-0370-40e0-bddc-a9a196afe77d does not have a host assigned","reason":"BadRequest","code":400}\n'
(TaskRunner pid=837619)
(TaskRunner pid=837619) NoneType: None
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 521, in launch_one_trajectory_task
(TaskRunner pid=837619) result = await self.run_agent_trajectory_with_retry(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 502, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) raise Exception(f"Trajectory {idx} cannot complete. Please check the log message")
(TaskRunner pid=837619) Exception: Trajectory 34 cannot complete. Please check the log message
(TaskRunner pid=837619) Exception in thread Thread-9 (runner):
(TaskRunner pid=837619) Traceback (most recent call last):
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/threading.py", line 1045, in _bootstrap_inner
(TaskRunner pid=837619) self.run()
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/threading.py", line 982, in run
(TaskRunner pid=837619) self._target(*self._args, **self._kwargs)
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/trainer/verl/agent_ppo_trainer.py", line 758, in runner
(TaskRunner pid=837619) asyncio.run(consume())
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 190, in run
(TaskRunner pid=837619) return runner.run(main)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/runners.py", line 118, in run
(TaskRunner pid=837619) return self._loop.run_until_complete(task)
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "uvloop/loop.pyx", line 1518, in uvloop.loop.Loop.run_until_complete
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/trainer/verl/agent_ppo_trainer.py", line 754, in consume
(TaskRunner pid=837619) async for item in self.agent_execution_engine.trajectory_generator(timing_raw=timing_raw, mode=mode, meta_info=meta_info):
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 546, in trajectory_generator
(TaskRunner pid=837619) raise e
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 541, in trajectory_generator
(TaskRunner pid=837619) result = await coro
(TaskRunner pid=837619) ^^^^^^^^^^
(TaskRunner pid=837619) File "/home/.local/share/uv/python/cpython-3.11.14-linux-x86_64-gnu/lib/python3.11/asyncio/tasks.py", line 615, in _wait_for_one
(TaskRunner pid=837619) return f.result() # May raise f.exception().
(TaskRunner pid=837619) ^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 531, in launch_one_trajectory_task
(TaskRunner pid=837619) raise e
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 521, in launch_one_trajectory_task
(TaskRunner pid=837619) result = await self.run_agent_trajectory_with_retry(
(TaskRunner pid=837619) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
(TaskRunner pid=837619) File "/home/code-rl/rllm/rllm/engine/agent_execution_engine.py", line 502, in run_agent_trajectory_with_retry
(TaskRunner pid=837619) raise Exception(f"Trajectory {idx} cannot complete. Please check the log message")
(TaskRunner pid=837619) Exception: Trajectory 34 cannot complete. Please check the log message1