Changes

Modified the shared genaiscript workflow configuration to optimize GenAIScript execution with explicit token limits and disabled system scripts.

What Changed

Updated .github/workflows/shared/genaiscript.md to configure the GenAI prompt frontmatter with:

1. Token Limit: Added maxDataTokens: 8000 to explicitly set the token limit for models that support 8000 tokens
2. System Scripts: Added system: [] to disable all GenAIScript system scripts

Technical Details

The "Convert prompt to GenAI format" step now generates prompt files with the following frontmatter:

---
model: github:gpt-4o-mini
maxDataTokens: 8000
system: []
---

This is accomplished by adding two additional sed commands during the prompt conversion process:

• sed -i '3i maxDataTokens: 8000' - Inserts the token limit configuration
• sed -i '4i system: []' - Disables system scripts

Impact

All workflows that import shared/genaiscript.md are affected:

• issue-summarizer-genaiscript.md
• smoke-genaiscript.md

The compiled .lock.yml files have been automatically updated to reflect these changes.

Testing

✅ All unit tests pass
✅ Workflows compile successfully without errors
✅ Manual verification confirms correct frontmatter generation

💡 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.