Add global mood control file for centralized agent behavior#14380
Add global mood control file for centralized agent behavior#14380
Conversation
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
There was a problem hiding this comment.
Pull request overview
Introduces a centralized “team mood” prompt fragment (.github/workflows/shared/mood.md) and wires it into the agentic workflow import chain so fleet-wide behavioral guidance can be updated in one place and propagated via workflow recompilation.
Changes:
- Added
.github/workflows/shared/mood.mdcontaining the current release-mode guidance. - Updated agentic workflow frontmatter to import
shared/mood.md. - Recompiled workflow
.lock.ymlfiles so the resolved prompt content includes the mood section.
Reviewed changes
Copilot reviewed 295 out of 295 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
| .github/workflows/shared/mood.md | New shared global guidance content (“Team Mood”) to steer all agents consistently. |
| .github/workflows/*.md (agentic workflows) | Frontmatter updated to import shared/mood.md so every workflow picks up global guidance. |
| .github/workflows/*.lock.yml (compiled workflows) | Regenerated resolved manifests/prompt assembly to include the mood content at execution time. |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
|
CI run 34258 is failing in both
|
Implements a centralized behavioral control mechanism for all agentic workflows through a shared
mood.mdfile that can provide fleet-wide guidance or remain empty when no global direction is needed.Changes
.github/workflows/shared/mood.mdas global control fileUsage
The mood file is imported via frontmatter and its content is passed to agents during execution:
Update mood.md content and run
make recompileto propagate changes across all workflows. Currently configured for release mode (quality/stability focus).Architecture
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.