Agents:
- architect: Central coordinator with full access
- hst: Tags API server (tzrtech.org)
- deck: Personal server (tzzrdeck.me)
- corp: Enterprise server (tzzrcorp.me)
- locker: R2 storage gateway
- runpod: GPU endpoints manager
Servers configured:
- deck (72.62.1.113)
- corp (92.112.181.188)
- hst (72.62.2.84)
All agents use claude/opus model.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
- Fix AttributeError when servers: or agents: is empty/None in config.yaml
- Use `or {}` pattern to safely handle None values
- Orchestrator CLI now starts correctly with minimal config
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
Deployed AI context tables across 3 servers (architect, deck, corp).
Complete documentation of schema, functions, triggers and initial data.
- 4 tables per server: ai_context, ai_conversations, ai_learnings, ai_tasks
- 13 indexes for optimal query performance
- 2 functions and 2 triggers for automation
- Initial system configuration data inserted
All deployments completed successfully.
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-Authored-By: Claude Sonnet 4.5 <noreply@anthropic.com>
Changes:
- claude_provider.py: Added --dangerously-skip-permissions flag
- docs/DEPLOYMENT.md: Full deployment documentation
Why:
- Claude CLI blocks --dangerously-skip-permissions with root
- Created non-root user "orchestrator" to run agents without confirmations
- Service now runs as User=orchestrator
Architecture:
- /home/orchestrator/orchestrator/ - Orchestrator code
- /opt/architect-app-v2/ - Web panel
- User orchestrator owns SSH keys and can execute commands
