Fix(windows): subprocess spawn compatibility for long promptsfix(windows): subprocess spawn compatibility for long prompts - #159
Open
lxq-ll wants to merge 1 commit into
Conversation
Three fixes for Windows native subprocess backend: 1. adapters.py: os.getuid() is Unix-only, use getattr fallback 2. subprocess_backend.py: CMD.exe truncates long prompts at newlines. Write full prompt to CLAWTEAM_INSTRUCTIONS.md and pass short -p. Handles both Claude (-p flag) and Codex (positional arg). 3. subprocess_backend.py: redirect stdout/stderr to log files under ~/.clawteam/logs/ instead of DEVNULL for debugging.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Three fixes for Windows native subprocess backend:
Testing
Verified on Windows 11 with a 2-agent DAG workflow (architect → coder → ) using Claude Code and Claude Code.
Before fix: agents received truncated prompts, exited immediately with "It looks like your message only contains a heading ## Identity".
After fix: agents read full instructions from file, complete tasks successfully.