JetBrains + GitHub.com surface research (deferred to v0.5.0) #36

Context

Part of #10: Copilot client parity across surfaces. This is deferred until VS Code is solid.

Problem

After VS Code parity is achieved (#11, #12, #13, #14), we need to validate and document:

• JetBrains IDE: Agent spawning, file discovery, model selection
• GitHub.com Copilot: Chat vs. agent spawning, contextual access, limitations

Key Investigations (Deferred)

• JetBrains: How to spawn agents, what tools are available, filesystem access model
• GitHub.com: Does chat-based agent invocation differ from sub-agent spawning? What's the UX?
• Both: Can they read .ai-team/ files? What are the sandbox constraints?

Success Criteria

• Document JetBrains agent spawn mechanism
• Document GitHub.com agent invocation model
• Test .ai-team/ access on both surfaces
• Extend compatibility matrix (Add Ralph — built-in work monitor squad member #14) with JetBrains + GitHub.com columns
• Define graceful degradation for unsupported features

Timeline

• Deferred to v0.5.0 after VS Code parity is complete
• Unblocks: Broader Squad rollout across Copilot ecosystem

Related

• Parent: Copilot client parity: Squad works fully only on GitHub Copilot CLI #10 (Copilot client parity)
• Depends on: Add Ralph — built-in work monitor squad member #14 (compatibility matrix documented)
• Predecessor: Feature: Enable MCP use #11, Add @copilot coding agent as a Squad member type #12, Add @copilot coding agent as a Squad member type #13 (VS Code investigations must complete first)