18 lines
1.6 KiB
Markdown
18 lines
1.6 KiB
Markdown
# System Specification: 4-Tier Hierarchical Multi-Model Architecture
|
|
|
|
**Project:** `manual_slop` (or equivalent Agentic Co-Dev Prototype)
|
|
|
|
**Core Philosophy:** Token Economy, Strict Memory Siloing, and Human-In-The-Loop (HITL) Execution.
|
|
|
|
## 1. Architectural Overview
|
|
|
|
This system rejects the "monolithic black-box" approach to agentic coding. Instead of passing an entire codebase into a single expensive context window, the architecture mimics a senior engineering department. It uses a 4-Tier hierarchy where cognitive load and context are aggressively filtered from top to bottom.
|
|
|
|
Expensive, high-reasoning models manage metadata and architecture (Tier 1 & 2), while cheap, fast models handle repetitive syntax and error parsing (Tier 3 & 4).
|
|
|
|
### 1.1 Core Paradigms
|
|
|
|
* **Token Firewalling:** Error logs and deep history are never allowed to bubble up to high-tier models. The system relies heavily on abstracted AST views (Skeleton, Curated) rather than raw code when context allows.
|
|
* **Context Amnesia:** Worker agents (Tier 3) have their trial-and-error histories wiped upon task completion to prevent context ballooning and hallucination.
|
|
* **The Execution Clutch (HITL):** Agents operate based on Archetype Trust Scores defined in configuration. Trusted patterns run in `Auto` mode; untrusted or complex refactors run in `Step` mode, pausing before tool execution for human review and JSON history mutation.
|
|
* **Interface-Driven Development (IDD):** The architecture inherently prioritizes the creation of contracts (stubs, schemas) before implementation, allowing workers to proceed in parallel without breaking cross-module boundaries. |