CLI can now BE the brain:
- brain_mode_set: switch gateway to external mode
- queue_get: poll incoming player commands
- queue_complete: send response back to player
- tool_execute: call any gateway tool directly (rcon, display, npc, etc.)
28 MCP tools total. When in external mode, Opus in the CLI
processes player commands instead of Codex/Anthropic.
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Expanded from pure operator to autonomous agent:
- 24 MCP tools (was 12): added bot playtesting, diagnostics,
escalation, and session notes/memory
- Bot profiles (noob, builder, fighter, griefer, conversationalist)
for automated playtesting through the gateway
- analyze_errors scans logs + interactions for patterns
- write_note/read_notes for persistent memory across runs
- write_session_summary/read_run_log for run history
- write_escalation for issues that need architect attention
- CLAUDE.md: full autonomous workflow with Layer 1 permissions
(monitor, test, escalate — no code modification yet)
Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Claude Code