feat(node2): Full DAGI integration - 50 agents synced
- Created sync-node2-dagi-agents.py script to sync agents from agents_city_mapping.yaml - Synced 50 DAGI agents across 10 districts: - Leadership Hall (4): Solarius, Sofia, PrimeSynth, Nexor - System Control (6): Monitor, Strategic Sentinels, Vindex, Helix, Aurora, Arbitron - Engineering Lab (5): ByteForge, Vector, ChainWeaver, Cypher, Canvas - Marketing Hub (6): Roxy, Mira, Tempo, Harmony, Faye, Storytelling - Finance Office (4): Financial Analyst, Accountant, Budget Planner, Tax Advisor - Web3 District (5): Smart Contract Dev, DeFi Analyst, Tokenomics Expert, NFT Specialist, DAO Governance - Security Bunker (7): Shadelock, Exor, Penetration Tester, Security Monitor, Incident Responder, Shadelock Forensics, Exor Forensics - Vision Studio (4): Iris, Lumen, Spectra, Video Analyzer - R&D Lab (6): ProtoMind, LabForge, TestPilot, ModelScout, BreakPoint, GrowCell - Memory Vault (3): Somnia, Memory Manager, Knowledge Indexer - Fixed Swapper config to use swapper_config_node2.yaml with 8 models - Created TASK_PHASE_NODE2_FULL_DAGI_INTEGRATION_v1.md NODE2 now shows: - 50 agents in DAGI Router Card - 8 models in Swapper Service (gpt-oss, phi3, starcoder2, mistral-nemo, gemma2, deepseek-coder, qwen2.5-coder, deepseek-r1) - Full isolation from NODE1
This commit is contained in:
Apple
@@ -1,75 +1,83 @@
|
||||
# Swapper Configuration for Node #1 (Production Server)
|
||||
# Swapper Configuration for Node #2 (Development Node)
|
||||
# Single-active LLM scheduler
|
||||
# Hetzner GEX44 - NVIDIA RTX 4000 SFF Ada (20GB VRAM)
|
||||
# Auto-generated configuration with all available Ollama models
|
||||
# MacBook Pro M4 Max - Apple Silicon (40-core GPU, 64GB RAM)
|
||||
# Auto-generated configuration with available Ollama models
|
||||
|
||||
swapper:
|
||||
mode: single-active
|
||||
max_concurrent_models: 1
|
||||
model_swap_timeout: 300
|
||||
gpu_enabled: true
|
||||
metal_acceleration: false # NVIDIA GPU, not Apple Silicon
|
||||
metal_acceleration: true # Apple Silicon GPU acceleration
|
||||
# Модель для автоматичного завантаження при старті (опціонально)
|
||||
# Якщо не вказано - моделі завантажуються тільки за запитом
|
||||
# Рекомендовано: qwen3-8b (основна модель) або qwen2.5-3b-instruct (легка модель)
|
||||
default_model: qwen3-8b # Модель активується автоматично при старті
|
||||
# Рекомендовано: gpt-oss:latest (швидка модель) або phi3:latest (легка модель)
|
||||
default_model: gpt-oss:latest # Модель активується автоматично при старті
|
||||
|
||||
models:
|
||||
# Primary LLM - Qwen3 8B (High Priority) - Main model from INFRASTRUCTURE.md
|
||||
qwen3-8b:
|
||||
path: ollama:qwen3:8b
|
||||
# Fast LLM - GPT-OSS 20B (High Priority) - Main model for general tasks
|
||||
gpt-oss-latest:
|
||||
path: ollama:gpt-oss:latest
|
||||
type: llm
|
||||
size_gb: 4.87
|
||||
size_gb: 13.0
|
||||
priority: high
|
||||
description: "Primary LLM for general tasks and conversations"
|
||||
description: "Fast LLM for general tasks and conversations (20.9B params)"
|
||||
|
||||
# Vision Model - Qwen3-VL 8B (High Priority) - For image processing
|
||||
qwen3-vl-8b:
|
||||
path: ollama:qwen3-vl:8b
|
||||
type: vision
|
||||
size_gb: 5.72
|
||||
priority: high
|
||||
description: "Vision model for image understanding and processing"
|
||||
|
||||
# Qwen2.5 7B Instruct (High Priority)
|
||||
qwen2.5-7b-instruct:
|
||||
path: ollama:qwen2.5:7b-instruct-q4_K_M
|
||||
# Lightweight LLM - Phi3 3.8B (High Priority) - Fast responses
|
||||
phi3-latest:
|
||||
path: ollama:phi3:latest
|
||||
type: llm
|
||||
size_gb: 4.36
|
||||
size_gb: 2.2
|
||||
priority: high
|
||||
description: "Qwen2.5 7B Instruct model"
|
||||
description: "Lightweight LLM for fast responses (3.8B params)"
|
||||
|
||||
# Lightweight LLM - Qwen2.5 3B Instruct (Medium Priority)
|
||||
qwen2.5-3b-instruct:
|
||||
path: ollama:qwen2.5:3b-instruct-q4_K_M
|
||||
type: llm
|
||||
size_gb: 1.80
|
||||
# Code Specialist - StarCoder2 3B (Medium Priority) - Code engineering
|
||||
starcoder2-3b:
|
||||
path: ollama:starcoder2:3b
|
||||
type: code
|
||||
size_gb: 1.7
|
||||
priority: medium
|
||||
description: "Lightweight LLM for faster responses"
|
||||
description: "Code specialist model for code engineering (3B params)"
|
||||
|
||||
# Math Specialist - Qwen2 Math 7B (High Priority)
|
||||
qwen2-math-7b:
|
||||
path: ollama:qwen2-math:7b
|
||||
type: math
|
||||
size_gb: 4.13
|
||||
priority: high
|
||||
description: "Specialized model for mathematical tasks"
|
||||
|
||||
# Lightweight conversational LLM - Mistral Nemo 2.3B (Medium Priority)
|
||||
mistral-nemo-2_3b:
|
||||
path: ollama:mistral-nemo:2.3b-instruct
|
||||
# Reasoning Model - Mistral Nemo 12.2B (High Priority) - Advanced reasoning
|
||||
mistral-nemo-12b:
|
||||
path: ollama:mistral-nemo:12b
|
||||
type: llm
|
||||
size_gb: 1.60
|
||||
size_gb: 7.1
|
||||
priority: high
|
||||
description: "Advanced reasoning model for complex tasks (12.2B params)"
|
||||
|
||||
# Reasoning Model - Gemma2 27B (Medium Priority) - Strategic reasoning
|
||||
gemma2-27b:
|
||||
path: ollama:gemma2:27b
|
||||
type: llm
|
||||
size_gb: 15.0
|
||||
priority: medium
|
||||
description: "Fast low-cost replies for monitor/service agents"
|
||||
|
||||
# Compact Math Specialist - Qwen2.5 Math 1.5B (Medium Priority)
|
||||
qwen2_5-math-1_5b:
|
||||
path: ollama:qwen2.5-math:1.5b
|
||||
type: math
|
||||
size_gb: 1.20
|
||||
priority: medium
|
||||
description: "Lightweight math model for DRUID/Nutra micro-calculations"
|
||||
description: "Reasoning model for strategic tasks (27.2B params)"
|
||||
|
||||
# Code Specialist - DeepSeek Coder 33B (High Priority) - Advanced code tasks
|
||||
deepseek-coder-33b:
|
||||
path: ollama:deepseek-coder:33b
|
||||
type: code
|
||||
size_gb: 18.0
|
||||
priority: high
|
||||
description: "Advanced code specialist model (33B params)"
|
||||
|
||||
# Code Specialist - Qwen2.5 Coder 32B (High Priority) - Advanced code tasks
|
||||
qwen2.5-coder-32b:
|
||||
path: ollama:qwen2.5-coder:32b
|
||||
type: code
|
||||
size_gb: 19.0
|
||||
priority: high
|
||||
description: "Advanced code specialist model (32.8B params)"
|
||||
|
||||
# Reasoning Model - DeepSeek R1 70B (High Priority) - Strategic reasoning (large model)
|
||||
deepseek-r1-70b:
|
||||
path: ollama:deepseek-r1:70b
|
||||
type: llm
|
||||
size_gb: 42.0
|
||||
priority: high
|
||||
description: "Strategic reasoning model (70.6B params, quantized)"
|
||||
|
||||
storage:
|
||||
models_dir: /app/models
|
||||
@@ -77,5 +85,6 @@ storage:
|
||||
swap_dir: /app/swap
|
||||
|
||||
ollama:
|
||||
url: http://ollama:11434 # From Docker container to Ollama service
|
||||
url: http://localhost:11434 # Native Ollama on MacBook (via Pieces OS or brew)
|
||||
timeout: 300
|
||||
|
||||
|
||||
81
services/swapper-service/config/swapper_config.yaml.backup
Normal file
81
services/swapper-service/config/swapper_config.yaml.backup
Normal file
@@ -0,0 +1,81 @@
|
||||
# Swapper Configuration for Node #1 (Production Server)
|
||||
# Single-active LLM scheduler
|
||||
# Hetzner GEX44 - NVIDIA RTX 4000 SFF Ada (20GB VRAM)
|
||||
# Auto-generated configuration with all available Ollama models
|
||||
|
||||
swapper:
|
||||
mode: single-active
|
||||
max_concurrent_models: 1
|
||||
model_swap_timeout: 300
|
||||
gpu_enabled: true
|
||||
metal_acceleration: false # NVIDIA GPU, not Apple Silicon
|
||||
# Модель для автоматичного завантаження при старті (опціонально)
|
||||
# Якщо не вказано - моделі завантажуються тільки за запитом
|
||||
# Рекомендовано: qwen3-8b (основна модель) або qwen2.5-3b-instruct (легка модель)
|
||||
default_model: qwen3-8b # Модель активується автоматично при старті
|
||||
|
||||
models:
|
||||
# Primary LLM - Qwen3 8B (High Priority) - Main model from INFRASTRUCTURE.md
|
||||
qwen3-8b:
|
||||
path: ollama:qwen3:8b
|
||||
type: llm
|
||||
size_gb: 4.87
|
||||
priority: high
|
||||
description: "Primary LLM for general tasks and conversations"
|
||||
|
||||
# Vision Model - Qwen3-VL 8B (High Priority) - For image processing
|
||||
qwen3-vl-8b:
|
||||
path: ollama:qwen3-vl:8b
|
||||
type: vision
|
||||
size_gb: 5.72
|
||||
priority: high
|
||||
description: "Vision model for image understanding and processing"
|
||||
|
||||
# Qwen2.5 7B Instruct (High Priority)
|
||||
qwen2.5-7b-instruct:
|
||||
path: ollama:qwen2.5:7b-instruct-q4_K_M
|
||||
type: llm
|
||||
size_gb: 4.36
|
||||
priority: high
|
||||
description: "Qwen2.5 7B Instruct model"
|
||||
|
||||
# Lightweight LLM - Qwen2.5 3B Instruct (Medium Priority)
|
||||
qwen2.5-3b-instruct:
|
||||
path: ollama:qwen2.5:3b-instruct-q4_K_M
|
||||
type: llm
|
||||
size_gb: 1.80
|
||||
priority: medium
|
||||
description: "Lightweight LLM for faster responses"
|
||||
|
||||
# Math Specialist - Qwen2 Math 7B (High Priority)
|
||||
qwen2-math-7b:
|
||||
path: ollama:qwen2-math:7b
|
||||
type: math
|
||||
size_gb: 4.13
|
||||
priority: high
|
||||
description: "Specialized model for mathematical tasks"
|
||||
|
||||
# Lightweight conversational LLM - Mistral Nemo 2.3B (Medium Priority)
|
||||
mistral-nemo-2_3b:
|
||||
path: ollama:mistral-nemo:2.3b-instruct
|
||||
type: llm
|
||||
size_gb: 1.60
|
||||
priority: medium
|
||||
description: "Fast low-cost replies for monitor/service agents"
|
||||
|
||||
# Compact Math Specialist - Qwen2.5 Math 1.5B (Medium Priority)
|
||||
qwen2_5-math-1_5b:
|
||||
path: ollama:qwen2.5-math:1.5b
|
||||
type: math
|
||||
size_gb: 1.20
|
||||
priority: medium
|
||||
description: "Lightweight math model for DRUID/Nutra micro-calculations"
|
||||
|
||||
storage:
|
||||
models_dir: /app/models
|
||||
cache_dir: /app/cache
|
||||
swap_dir: /app/swap
|
||||
|
||||
ollama:
|
||||
url: http://ollama:11434 # From Docker container to Ollama service
|
||||
timeout: 300
|
||||
Reference in New Issue
Block a user