Skip to content

docs: add content policies section and refine ADR wording #1838

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
WilliamBerryiii wants to merge 1 commit into
base: feat/1637-l9-prompt-builder
Choose a base branch
from
Open

docs: add content policies section and refine ADR wording #1838

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
9 changes: 9 additions & 0 deletions CODE_OF_CONDUCT.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -21,6 +21,15 @@ Resources:
* Contact [opencode@microsoft.com](mailto:opencode@microsoft.com) with questions or concerns
* Employees can reach out at [aka.ms/opensource/moderation-support](https://aka.ms/opensource/moderation-support)

## Content Policies

This project follows Microsoft's published policies for AI output and community conduct:

* AI output and prohibited content categories: [Microsoft Enterprise AI Services Code of Conduct](https://learn.microsoft.com/legal/ai-code-of-conduct)
* Contributor conduct (including responsible use of AI-generated content): [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
* GitHub-platform conduct for issues, discussions, and reviews: [GitHub Acceptable Use Policies](https://docs.github.com/site-policy/acceptable-use-policies/github-acceptable-use-policies)
* Microsoft brand and trademark use: [Microsoft Trademark and Brand Guidelines](https://www.microsoft.com/legal/intellectualproperty/trademarks)

---

🤖 Crafted with precision by ✨Copilot following brilliant human instruction, then carefully refined by our team of discerning human reviewers.
4 changes: 2 additions & 2 deletions .../planning/adrs/0001-adopt-phase-gated-adr-creator-aligned-with-peer-planners.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -122,7 +122,7 @@ ADR templates without forking the agent?
| Decision driver | Option A | Option B | Option C | Option D |
|--------------------------------------|----------|----------|----------|----------|
| Standards fidelity + disclaimer | Yes | No | Partial | No |
| Peer-planner consistency | Yes | No | No | Trap |
| Peer-planner consistency | Yes | No | No | Pitfall |
| Thin-orchestrator maintainability | Yes | No | Partial | No |
| BYO template support | Yes | No | Partial | No |
| Coaching quality (load-before-act) | Yes | Partial | No | Partial |
Expand Down Expand Up @@ -192,7 +192,7 @@ Compliance with this decision is confirmed by four mechanisms:
### Option C

* Good, because each agent can optimize for its specific output shape.
* Bad, because three agents duplicate identity logic (state machine, six-step protocol, Govern autonomy prompt), exactly the maintenance trap the thin-orchestrator driver names.
* Bad, because three agents duplicate identity logic (state machine, six-step protocol, Govern autonomy prompt), exactly the maintenance pitfall the thin-orchestrator driver names.
* Bad, because no shared `state.json` schema; resuming a session requires knowing which agent owned it.
* Bad, because MADR v4 text and Y-Statement formula end up duplicated across agents, creating drift risk identical to Option B.
* Neutral, because contributors writing one ADR shape can ignore the others; cognitive load per session is similar to Option A.
Expand Down
2 changes: 1 addition & 1 deletion ...nning/adrs/0002-adopt-vally-as-agent-and-skill-behavior-evaluation-framework.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -170,7 +170,7 @@ its tag-routed grader catalog matches the multi-suite design, and it is npm-
and GitHub-Actions-native so it fits existing PR CI and local `npm run`
workflows.

`vyta/beval` (Option B) is treated as **complementary rather than rejected**: it
`vyta/beval` (Option B) is treated as complementary rather than rejected. It
targets a different layer (runtime, multi-turn agentic behavior with scored
multi-dimensional metrics and persona-driven conversation simulation over
ACP/A2A) and is being integrated through open pull requests. It does not
Expand Down