Skip to content

[WIP][examples] fix: use shell to run cmd in sandbox#93

Open
ShengDev wants to merge 1 commit into
verl-project:mainfrom
ShengDev:fix/command-output
Open

[WIP][examples] fix: use shell to run cmd in sandbox#93
ShengDev wants to merge 1 commit into
verl-project:mainfrom
ShengDev:fix/command-output

Conversation

@ShengDev

Copy link
Copy Markdown
Contributor

What does this PR do?

During reward calculation, multiple commands are executed. The set -x option is used to echo each executed command to the output; however, by default, these traces are written to stderr. This results in execution outputs being split across stdout and stderr. To ensure correct parsing, all outputs — both command traces and their results — should be merged sequentially as expected.

This PR utilizes shell.run() over command.run() to execute commands in the openYuanrong sandbox, ensuring outputs are returned both sequentially and atomically.

Checklist Before Starting

  • Search for similar PRs or issues and paste at least one relevant link here: ...
  • Format the PR title as [{modules}] {type}: {description} (checked by CI)
    • {modules} may include core, interaction, model, env, tools, deployment, reward, dashboard, docs, examples, data, train, ci, build, deps, misc
    • If this PR involves multiple modules, separate them with , like [interaction, tools, docs]
    • {type} must be one of feat, fix, refactor, chore, test
    • If this PR breaks an API, config contract, workflow, or other compatibility boundary, add [BREAKING] to the beginning of the title
    • For a stacked PR series, you may prepend a progress marker such as [1/N]
    • Example: [BREAKING][deployment, docs] feat: simplify runtime env configuration

Test

manuel test is done in remote sandbox system

API and Usage Example

This PR does not change API. It changes the implemention of command execution

Design & Code Changes

This PR utilizes shell.run() over command.run() to execute commands in the openYuanrong sandbox, ensuring outputs are returned both sequentially and atomically.

examples/blackbox_recipes/claude_code/claude_code_runner.py
async def run utilizes shell.run() over command.run()

Checklist Before Submitting

  • Read the Contribute Guide
  • Run pre-commit install && pre-commit run --all-files --show-diff-on-failure --color=always
  • Add or update docs/examples for user-facing changes
  • Add tests or explain why tests are not practical
  • Confirm the PR title matches the required format
  • Confirm the placeholder text in this template has been replaced with real content

@gemini-code-assist

Copy link
Copy Markdown
Contributor

Caution

The consumer version of Gemini Code Assist on GitHub has been sunset. All code review activity has officially ceased.

@ShengDev ShengDev changed the title [example] fix: use shell to run cmd in sandbox [examples] fix: use shell to run cmd in sandbox Jul 24, 2026
@ShengDev
ShengDev force-pushed the fix/command-output branch from e96bb34 to c93d7e0 Compare July 24, 2026 03:34
Signed-off-by: sheng <sheng.gao.dev@gmail.com>
@ShengDev
ShengDev force-pushed the fix/command-output branch from c93d7e0 to 48893d0 Compare July 24, 2026 03:38
@ShengDev ShengDev changed the title [examples] fix: use shell to run cmd in sandbox [WIP][examples] fix: use shell to run cmd in sandbox Jul 24, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant