Webwright skill is shell-unaware on Windows — bash heredocs loop/fail with code-specialist models (gpt-5-codex / gpt-5.3-codex)
Nobody has claimed this yet.
Assessment
- Difficulty
- 3/5
- Estimated time
- 1-2 days
- Newbie friendliness
- 42/100
- Issue type
- Bug
- Clarity
- Needs clarification
- Activity status
- Quiet
- Tech stack
- bash, powershell, python
- Domain
- cli, developer-experience, documentation
Research direction
Read reference/playwright_patterns.md and the Webwright skill instructions, then reproduce the inline-Python example under PowerShell on Windows. Trace where the skill assumes bash and compare the behavior with the reported Codex models. Done means PowerShell runs no longer invoke bash heredoc syntax or repeat the resulting parse failure.
Written by the indexing model from the issue text.
Description
Environment
Windows 11, Codex VS Code extension, Codex CLI 0.136.0-alpha.2
Detected shell (from environment_context): powershell
Webwright skill invoked via /webwright:run
Summary
The webwright skill instructs the agent to "drive the browser through one bash command at a time" and its reference (reference/playwright_patterns.md, the inline-Python example) demonstrates a bash heredoc (python - <<'PY' … PY). On Windows the shell is PowerShell, which cannot parse bash heredocs. Whether a run succeeds therefore depends entirely on the model being able to recognize this and deviate from the skill's examples.
Observed behavior (same machine, same skill, same shell)
gpt-5.5: recognizes it's on PowerShell, writes the script to a .py file and runs python file.py. Completes tasks in a few steps.
gpt-5-codex / gpt-5.3-codex: follow the skill's bash heredoc example literally, hit the PowerShell parse error, and retry the same broken syntax in a loop. A simple Wikipedia task took ~18 minutes; a moderately complex booking task looped for hours without converging.
Root cause
The skill's instructions and examples assume bash. Code-specialist models are tuned for tight, literal adherence to skill instructions, so they reproduce the bash heredoc verbatim instead of adapting to the reported powershell shell. There is no shell-awareness in the skill and no guardrail when the harness runs under a model that doesn't self-correct.
- Dominant language
- Python
- Stars
- 6k
- Forks
- 385
- PR merge metrics
- No merged PRs in 30d
Contributor guide
No contributing guide indexed for this repository
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.
More from microsoft/Webwright
-
Difficulty 2/5 1-3 hours Newbie friendliness 88/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 78/100
-
Difficulty 1/5 Under an hour Newbie friendliness 78/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 72/100
-
Difficulty 4/5 3-5 days Newbie friendliness 45/100
All issues in microsoft/Webwright
Similar issues
-
bug
Difficulty 2/5 1-3 hours Newbie friendliness 75/100
xinnan-tech/xiaozhi-fde-talk#263 ·
-
rules
Difficulty 1/5 Under an hour Newbie friendliness 90/100
-
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
huggingface/Repo2RLEnv#163 · 1 comment ·
-
Difficulty 1/5 Under an hour Newbie friendliness 95/100
huggingface/sentence-transformers#4074 ·
-
comp/dashboard invalid P3
Difficulty 2/5 1-3 hours Newbie friendliness 70/100
NousResearch/hermes-agent#121143 ·