Blueprint Overview¶
The blueprint is organized around the major systems inside an agent CLI, but the current teaching path is intentionally Python-first.
- Tool system
- Tool execution pipeline
- Query engine and conversation loop
- Bootstrap and startup
- Permission system
- Session and state management
- Multi-agent orchestration
- MCP integration
- Slash command system
- Terminal UI
- IDE bridge protocol
- Memory and cost tracking
Python-first route¶
- OpenAI Responses API
- Chapter 1: Tool System
- Chapter 3: Query Engine
- Chapter 5: Permissions
- Chapter 6: Session and State
- Chapter 8: MCP Integration
Reading tracks¶
Core runtime¶
- Chapter 1: Tool System
- Chapter 2: Tool Execution Pipeline
- Chapter 3: Query Engine
- Chapter 5: Permissions
- Chapter 6: Session and State
Expansion layers¶
- Chapter 7: Multi-Agent Orchestration
- Chapter 8: MCP Integration
- Chapter 9: Slash Commands
- Chapter 11: IDE Bridge
Advanced Patterns¶
- Streaming Formats -- Wire formats and streaming protocols for real-time token delivery
- YOLO Classifier -- Automatic tool-approval classification and trust scoring
- Model Pricing -- Token cost tracking, model selection, and budget-aware routing
- Hidden Modes -- Undocumented operational modes and internal feature flags
Operator experience¶
Chapter navigation¶
- Chapter 1: Tool System
- Chapter 2: Tool Execution Pipeline
- Chapter 3: Query Engine
- Chapter 4: Bootstrap
- Chapter 5: Permissions
- Chapter 6: Session and State
- Chapter 7: Multi-Agent Orchestration
- Chapter 8: MCP Integration
- Chapter 9: Slash Commands
- Chapter 10: Terminal UI
- Chapter 11: IDE Bridge
- Chapter 12: Memory and Cost
- Source Provenance
- Appendix
Use this section when¶
- you want the full architecture in one place
- you need a chapter-by-chapter reference
- you are mapping blueprint ideas to your own runtime
The main document still lives at Full Blueprint, but the chapter pages are now the recommended reading path.
How to use this section¶
- Use the chapter pages when you want Python-first implementation guidance.
- Use the full blueprint when you want the exact long-form walkthrough and source-level provenance.
- Use the build-better pages when you want to convert observations into design rules for your own harness.