[Bug]: OpenHands stalls indefinitely after successful command
Is there an existing issue for the same bug?
- [x] I have checked the existing issues.
Describe the bug and reproduction steps
I was running a task, and it has stalled indefinitely with the three dots moving up and down.
The previous bash script finished successfully and wrote out about 200 lines of output.
In my log I saw this:
==============
[Agent Controller 094dda80f3fa493787c7c320a597f0db] LEVEL 0 LOCAL STEP 78 GLOBAL STEP 78
15:22:08 - ACTION
[Agent Controller 094dda80f3fa493787c7c320a597f0db] **CmdRunAction (source=EventSource.AGENT, is_input=False)**
THOUGHT: Now let's run the verification again:
COMMAND:
cd /workspace/prompt-based-reranker && python verify_ensemble.py
15:22:09 - OBSERVATION
[Agent Controller 094dda80f3fa493787c7c320a597f0db] **CmdOutputObservation (source=EventSource.AGENT, exit code=0, metadata={
"exit_code": 0,
"pid": -1,
"username": "root",
"hostname": "e595159ef0da",
"working_dir": "/workspace/prompt-based-reranker",
"py_interpreter_path": "/openhands/poetry/openhands-ai-5O4_aCHf-py3.12/bin/python",
"prefix": "",
"suffix": "\n[The command completed with exit code 0.]"
})**
--BEGIN AGENT OBSERVATION--
...
[The command completed with exit code 0.]
[Current working directory: /workspace/prompt-based-reranker]
[Python interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.12/bin/python]
[Command finished with exit code 0]
--END AGENT OBSERVATION--
==============
[Agent Controller 094dda80f3fa493787c7c320a597f0db] LEVEL 0 LOCAL STEP 79 GLOBAL STEP 79
INFO: 172.17.0.1:55280 - "GET /api/options/config HTTP/1.1" 200 OK
INFO: 172.17.0.1:55266 - "GET /api/conversations/094dda80f3fa493787c7c320a597f0db HTTP/1.1" 200 OK
INFO: 172.17.0.1:55258 - "GET /api/settings HTTP/1.1" 200 OK
15:23:24 - openhands:INFO: standalone_conversation_manager.py:83 - Conversation 094dda80f3fa493787c7c320a597f0db connected in 0.06486177444458008 seconds
15:23:24 - openhands:INFO: standalone_conversation_manager.py:64 - Reusing active conversation 094dda80f3fa493787c7c320a597f0db
INFO: 172.17.0.1:55292 - "GET /api/conversations/094dda80f3fa493787c7c320a597f0db/web-hosts HTTP/1.1" 200 OK
INFO: 172.17.0.1:55306 - "GET /api/conversations/094dda80f3fa493787c7c320a597f0db/vscode-url HTTP/1.1" 200 OK
INFO: 172.17.0.1:55294 - "GET /api/github/user HTTP/1.1" 200 OK
INFO: 172.17.0.1:55868 - "GET /api/settings HTTP/1.1" 200 OK
15:25:34 - openhands:INFO: standalone_conversation_manager.py:83 - Conversation 094dda80f3fa493787c7c320a597f0db connected in 0.022493362426757812 seconds
INFO: 172.17.0.1:55880 - "GET /api/conversations/094dda80f3fa493787c7c320a597f0db/list-files HTTP/1.1" 200 OK
INFO: 172.17.0.1:60710 - "GET /api/settings HTTP/1.1" 200 OK
INFO: 172.17.0.1:57870 - "GET /api/settings HTTP/1.1" 200 OK
OpenHands Installation
Docker command in README
OpenHands Version
0.22.0
Operating System
MacOS
Logs, Errors, Screenshots, and Additional Context
No response
I also have this quite often.
me too!
This issue is stale because it has been open for 30 days with no activity. Remove stale label or comment or this will be closed in 7 days.
@neubig I think this was resolved with your latest change to the timeout logic right?
I'm not very sure that this is the same problem, but I haven't seen this recently, so maybe we could close and re-open if it's still an issue?
Let's close and reopen if people encounter it. I also haven't seen this recently.