OpenHands / OpenHands/software-agent-sdk
Make shell more permissive to reduce "combined heredoc" rejections
Nobody has claimed this yet.
- Dominant language
- Python
- Stars
- 1.1k
- Forks
- 539
- Avg merge
- 1d 19h
- Merged PRs (30d)
- 137
Description
Problem
Agents frequently hit this message when trying to write files/scripts via heredocs:
The shell rejected my combined heredoc; I'll apply the model edit directly.
This was observed on gpt-5.6, but has been reported to happen across other models as well.
Proposed change
Investigate making the SDK shell more permissive so that combined/valid heredoc commands are accepted instead of rejected, reducing unnecessary fallback to direct model edits.
Context
Raised in a Slack thread where multiple users reported seeing this repeatedly.
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Research direction
The issue names no implementation files or tests. Search the repository for the “combined heredoc” rejection message and the shell command validation entry point, then reproduce a valid combined heredoc; done means valid heredoc commands are accepted and regression coverage demonstrates that unnecessary fallback rejection is avoided.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, shell
- Domain
- tooling
- Issue type
- Bug
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Active
- Clarity
- Needs clarification
- Newbie friendliness
- 45/100