1b3bca9902
Three-layer architecture implementation: - Layer 1: Thin Hermes profile (profile.yaml, < 50 lines) - Layer 2: Claw Code runtime (harness.py, tool_registry.py) - Layer 3: Gemma via Ollama (ollama_client.py) Features: - Tool registry with pattern matching (/time, /status, /echo, /ollama_list) - Full routing between tool execution and intelligence layer - Ollama client with streaming and chat support - Comprehensive integration test suite (12 tests) - Connection to localhost:11434 using gemma3:4b model
63 lines
3.0 KiB
Markdown
63 lines
3.0 KiB
Markdown
# Archon Architecture Proof-of-Concept
|
|
|
|
A three-layer architecture separating identity, runtime logic, and intelligence.
|
|
|
|
## Architecture Overview
|
|
|
|
```
|
|
┌─────────────────────────────────────────────────────────────┐
|
|
│ Layer 1: Hermes Profile (Thin) │
|
|
│ - Identity & routing only │
|
|
│ - No intelligence or reasoning logic │
|
|
│ - Pure configuration (< 50 lines) │
|
|
└─────────────────────────────────────────────────────────────┘
|
|
│
|
|
▼
|
|
┌─────────────────────────────────────────────────────────────┐
|
|
│ Layer 2: Claw Code Runtime │
|
|
│ - All business logic lives here │
|
|
│ - Tool registry and execution │
|
|
│ - Message routing and orchestration │
|
|
└─────────────────────────────────────────────────────────────┘
|
|
│
|
|
▼
|
|
┌─────────────────────────────────────────────────────────────┐
|
|
│ Layer 3: Gemma 4 via Ollama │
|
|
│ - The actual intelligence │
|
|
│ - Local inference at localhost:11434 │
|
|
│ - Model: gemma3:4b (available) / gemma4:4b (target) │
|
|
└─────────────────────────────────────────────────────────────┘
|
|
```
|
|
|
|
## Files
|
|
|
|
| File | Purpose |
|
|
|------|---------|
|
|
| `profile.yaml` | Thin Hermes layer - identity only |
|
|
| `runtime/harness.py` | Claw Code runtime stub |
|
|
| `runtime/tool_registry.py` | Tool definitions and registry |
|
|
| `ollama_client.py` | Gemma 4 interface layer |
|
|
| `test_integration.py` | End-to-end integration test |
|
|
|
|
## Quick Start
|
|
|
|
```bash
|
|
# Run integration test
|
|
python3 test_integration.py
|
|
|
|
# Test Ollama connection
|
|
python3 ollama_client.py "Hello, Gemma!"
|
|
```
|
|
|
|
## Design Principles
|
|
|
|
1. **Profile is THIN** - Only identity, no logic
|
|
2. **Runtime owns everything** - All intelligence orchestration
|
|
3. **Local inference** - No external API dependencies
|
|
4. **Testable** - Full integration test coverage
|
|
|
|
## Epic Reference
|
|
|
|
Implements Epic #370: Archon Architecture
|
|
Dispatch #371: Proof-of-Concept Implementation
|