Fix user commands in terminal with function calling

[enyst]

End-user friendly description of the problem this fixes or functionality that this introduces

• Include this change in the Release Notes. If checked, you must provide an end-user friendly description for your change below
  Fix agent crash when terminal commands are sent and function calling is enabled

---

Give a summary of what the PR does, explaining any non-trivial design decisions

When function calling is enabled, the agent expected all CmdRunAction to be "tools", but if they were sent by the user in the terminal, they were not, they were regular command actions.

This PR proposes to convert them into Messages as usual pre-function calling. Since they have source 'user', same as the next observation, and potentially more (a user message in chat probably follows too), they all get added to the same Message with role='user' when sent to the LLM.

(Outdated now)
On a side note, the concatenation... worked too well, so much so that Claude felt the need to help the human:

Prompt:

----------

... # other stuff done by the agent

----------

pwd
OBSERVATION:
/workspace[Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.12/bin/python]
openhands@openhands-workspace:/workspace $ 
[Command finished with exit code 0]
print 5
print 55
hi there

LLM response:

23:56:25 - openhands:INFO: agent_controller.py:513
ACTION
[Agent Controller 6368bb2f-c5b4-4dc0-aea9-a973fe1afbc0] CmdRunAction (source=None)
THOUGHT: I notice you're trying to type commands but they seem to be jumbled together. Let me help you with the proper command. If you want to see the current working directory, you can use:
COMMAND:
pwd

😅

Maybe we should insert some mini-separators?
Done.

---

Link of any specific issues this addresses
Fix #4783

---

To run this PR locally, use the following command:

docker run -it --rm   -p 3000:3000   -v /var/run/docker.sock:/var/run/docker.sock   --add-host host.docker.internal:host-gateway   -e SANDBOX_RUNTIME_CONTAINER_IMAGE=docker.all-hands.dev/all-hands-ai/runtime:98c8b26-nikolaik   --name openhands-app-98c8b26   docker.all-hands.dev/all-hands-ai/openhands:98c8b26

[diwu-sf]

Awesome that you're fixing this, I was just about to file a bug on this exact problem.

What if the user bash messages are just never shown to the LLM?
I'm not sure how much value showing ad-hoc shell commands and outputs to LLM would help with the task.
E.g. user is just running git status in workspace to skim what files agent changed, etc..

[enyst]

It's a good question, it could go either way. It happens in the same time with the task, and we know we need to tell the agent when the user is making modifications, rather than just looking. 🤔

Please take a look also at the slack discussion.

[diwu-sf]

Yes, it could go either way, made a UX suggestion to just have a checkbox on top of the terminal tab to let user decide whether his commands should be shown to the LLM

[enyst]

Currently:

----------

COMMAND:
pwd
OBSERVATION:
/workspace
[Python Interpreter: /openhands/poetry/openhands-ai-5O4_aCHf-py3.12/bin/python]
openhands@openhands-workspace:/workspace $ 
[Command finished with exit code 0]
print 99 ?

----------

I'll help you print the number 99 using Python in the IPython environment.

[xingyaoww]

Otherwise LGTM! Thanks a bunch for this!