feat: improve UX

[esifea]

Summary

• What changed: UX improvements
  • /rune:activate validates Vault token and enVector API key
  • Add recovery_hint filed to error responses for next steps
  • Dormant state tracks reason and time in config.json for detailed notification
  • Fix endpoint extraction and connection fit to macOS
    • Previous grep is possible to read envector.endpoint rather than vault.endpoint
    • /dev/tcp may not support according to activate.md
• Why: Users hard to know why Rune stopped working
• Scope: mcp/server/, agents/common/config.py, agents/{claude,gemini}/, commands/claude/, scripts/check-infrastructure.sh

Validation

• Tests run (or explain why not):
• Docs updated (if behavior/setup changed)

Cross-Agent Invariants

• scripts/bootstrap-mcp.sh remains the single source of truth for runtime prep (venv/deps/self-heal)
• No agent-specific script duplicates bootstrap/setup logic
• Agent-specific scripts remain thin adapters (registration/wiring only)
• Codex-only commands (codex mcp ...) are clearly separated from cross-agent/common instructions
• Claude/Gemini/OpenAI instructions do not include Codex-only commands
• SKILL.md, commands/rune/*.toml, and AGENT_INTEGRATION.md stay consistent on boundaries

Notes for Reviewers

• Risk areas: If ~/.rune/config.json is locked or corrupted, dormant reason is silently skipped
• Backward compatibility impact: None
• Follow-up work (if any):

[sunchuljung]

LGTM