Major upgrade:
- deps.dev GetDependencies: full tree in one call (direct + transitive)
- deps.dev GetVersion: cross-ecosystem package→repo mapping (7 ecosystems)
- deps.dev GetProject: OSSF Scorecard health data per project
- Direct vs transitive column (✅ vs ⛓️)
- Health column from Scorecard Maintained check
- Actionable minimum: '💡 Sponsoring just N people covers all funded deps'
- Graceful fallback to registry APIs if deps.dev unavailable
Inspired by jshchnz/tribute, adds:
- Link verification: every funding URL is fetched before presenting
- Web search fallback: finds funding even without FUNDING.yml
- How Verified column: transparency about data source
- 5 ecosystems: npm, Python, Rust, Go, Ruby (was npm-only)
- Corporate-maintained package detection
- No Verified Funding Found section for unfunded deps
Teaches Copilot how to scan a repo's dependencies and find which ones
accept sponsorship via GitHub Sponsors, Open Collective, etc.
Workflow:
1. Fetch package.json from target repo
2. Resolve each dep to source GitHub repo via npm registry
3. Check npm funding field + .github/FUNDING.yml
4. Group by maintainer, present report with sponsor links
Tested against expressjs/express: found 9/28 deps sponsorable (32%)
across 3 funding destinations.
Adds a Copilot CLI skill that teaches absolute beginners how to use
GitHub Copilot CLI through guided, interactive lessons right in the
terminal. Features:
- Dual-track learning: Developer (8 lessons) and Non-Developer (7 lessons)
- Interactive exercises using ask_user
- SQL-based progress tracking
- On-demand Q&A with live doc fetching
- Beginner-friendly with CLI glossary and fallback handling
Source repo: https://github.com/DUBSOpenHub/copilot-cli-quickstart
The samples page never called setupModal(), so the close button,
Escape key, and backdrop click handlers were never registered.
Add the missing setupModal() call matching all other pages.
Add a new cookbook recipe that generates WCAG accessibility reports using
the Playwright MCP server. Includes streaming output, structured report
formatting, and optional Playwright test generation.
- C#, TypeScript, Python, and Go implementations
- Markdown documentation for each language
- Updated cookbook.yml, copilot-sdk README, and package.json
- Add WorkingDirectory/working_directory to pin sessions to project root
- Add OnPermissionRequest/on_permission_request for unattended operation
- Add tool execution event logging for visibility
- Add See Also cross-links to error-handling and persisting-sessions
- Add best practices for WorkingDirectory and permission auto-approval
- Consistent across all 4 languages (Node.js, Python, .NET, Go)
Git operations (commit, push) belong in the prompt instructions, not
hardcoded in the loop orchestrator. The SDK recipes should focus purely
on the SDK API: create client, create session, send prompt, destroy.
- Introduced new agents: gem-chrome-tester, gem-devops, gem-documentation-writer, gem-implementer, gem-orchestrator, gem-planner, gem-researcher, and gem-reviewer.
- Updated README.collections.md to include the new Gem Team Multi-Agent Orchestration collection.
- Created gem-team.collection.yml and gem-team.md for structured documentation of the multi-agent orchestration framework.
- Each agent includes detailed descriptions, workflows, operating rules, and final anchors for clarity on their functionalities and usage.
- Move session.On handler outside loop to prevent handler accumulation (C#)
- Use TrySetResult instead of SetResult to avoid duplicate-set exceptions (C#)
- Wrap CreateSessionAsync in broader try/finally so client always stops (C#)
- Fix PersistentRalphLoop to use maxIterations parameter instead of hardcoded 10
- Align model name to gpt-5.1-codex-mini across all doc snippets
- Fix completion promise DONE -> COMPLETE in usage snippet
- Replace Claude references with generic model terminology
All 5 Python recipes and their markdown docs used a synchronous,
kwargs-based API that doesn't match the real github-copilot-sdk:
- client.start() -> await client.start() (all methods are async)
- create_session(model=...) -> create_session(SessionConfig(model=...))
- session.send(prompt=...) -> session.send(MessageOptions(prompt=...))
- session.wait_for_idle() -> session.send_and_wait() (wait_for_idle doesn't exist)
- event['type']/event['data']['content'] -> event.type/event.data.content
- All code wrapped in async def main() + asyncio.run(main())
Verified all imports resolve against github-copilot-sdk.
Add iterative RALPH-loop (Read, Act, Log, Persist, Halt) pattern
implementations for all four supported languages:
- C#/.NET: ralph-loop.cs with documentation
- Node.js/TypeScript: ralph-loop.ts with documentation
- Python: ralph_loop.py with documentation (async API)
- Go: ralph-loop.go with documentation
Each recipe demonstrates:
- Self-referential iteration where AI reviews its own output
- Completion promise detection to halt the loop
- Max iteration safety limits
- File persistence between iterations
Verified against real Copilot SDK APIs:
- Python: fully verified end-to-end with github-copilot-sdk
- Node.js: fully verified end-to-end with @github/copilot-sdk
- C#: compiles and runs successfully with GitHub.Copilot.SDK
- Go: compiles against github.com/github/copilot-sdk/go v0.1.23
