Add --add-dir arguments (/tmp/, /tmp/gh-aw/, /tmp/gh-aw/agent/) to copilot engine default arguments #2048
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Problem
The copilot engine was only adding
/tmp/gh-aw/to its default--add-dirarguments, but not/tmp/gh-aw/agent/or the root/tmp/directory. This meant that the AI agent didn't have explicit access to:/tmp//tmp/gh-aw/agent/that is created by the workflow compiler viacreate_gh_aw_tmp_dir.shand recommended to agents intemp_folder_prompt.mdwith the instruction: "always use the/tmp/gh-aw/agent/directory for temporary files"Solution
Added
--add-dir /tmp/,--add-dir /tmp/gh-aw/, and--add-dir /tmp/gh-aw/agent/to the default copilot CLI arguments inGetExecutionSteps(). Now the copilot command includes all three directories:This ensures the AI agent has explicit access to:
/tmp/directory for general temporary file operations/tmp/gh-aw/directory for workflow-related files/tmp/gh-aw/agent/directory for agent-specific temporary filesThis aligns the CLI configuration with the instructions provided in the workflow prompts.
Changes
"--add-dir", "/tmp/","--add-dir", "/tmp/gh-aw/", and"--add-dir", "/tmp/gh-aw/agent/"to default argumentsTesting
Original prompt
💡 You can make Copilot smarter by setting up custom instructions, customizing its development environment and configuring Model Context Protocol (MCP) servers. Learn more Copilot coding agent tips in the docs.