IMPLEMENTATION COMPLETE: Successfully integrated Google Gemini CLI as mixed agent type in Hive distributed AI platform. ## Phase 4 Achievements: ✅ Enhanced MCP tools with CLI agent support ✅ Added hive_register_cli_agent, hive_get_cli_agents tools ✅ Updated HiveClient interface for CLI agent management ✅ Mixed agent type coordination via MCP ✅ Comprehensive error handling and user feedback ## Key Features: - CLI agent registration with health checks - Mixed agent dashboard (🤖 Ollama + ⚡ CLI) - Predefined agent quick setup (walnut-gemini, ironwood-gemini) - SSH-based task execution with connection pooling - Complete backward compatibility ## Technical Stack: - MCP Tools: CLI agent management interface - HiveClient: Enhanced API client with CLI support - TypeScript: Full type safety for mixed agent operations - Error Handling: Comprehensive CLI connectivity validation ## Production Ready: ✅ 16 MCP tools with CLI agent coverage ✅ Mixed agent type task coordination ✅ Health monitoring and statistics collection ✅ Robust SSH execution with timeout handling ✅ Integration tested and validated Ready for hybrid AI orchestration: 5 Ollama + 2 CLI agents 🤖 Generated with [Claude Code](https://claude.ai/code) Co-Authored-By: Claude <noreply@anthropic.com>
31 lines
1.3 KiB
Python
31 lines
1.3 KiB
Python
from sqlalchemy import Column, Integer, String, DateTime, JSON
|
|
from sqlalchemy.sql import func
|
|
from ..core.database import Base
|
|
|
|
class Agent(Base):
|
|
__tablename__ = "agents"
|
|
|
|
id = Column(String, primary_key=True, index=True)
|
|
endpoint = Column(String, nullable=False)
|
|
model = Column(String, nullable=False)
|
|
specialty = Column(String, nullable=False)
|
|
max_concurrent = Column(Integer, default=2)
|
|
current_tasks = Column(Integer, default=0)
|
|
agent_type = Column(String, default="ollama") # "ollama" or "cli"
|
|
cli_config = Column(JSON, nullable=True) # CLI-specific configuration
|
|
created_at = Column(DateTime(timezone=True), server_default=func.now())
|
|
updated_at = Column(DateTime(timezone=True), onupdate=func.now())
|
|
|
|
def to_dict(self):
|
|
return {
|
|
"id": self.id,
|
|
"endpoint": self.endpoint,
|
|
"model": self.model,
|
|
"specialty": self.specialty,
|
|
"max_concurrent": self.max_concurrent,
|
|
"current_tasks": self.current_tasks,
|
|
"agent_type": self.agent_type,
|
|
"cli_config": self.cli_config,
|
|
"created_at": self.created_at.isoformat() if self.created_at else None,
|
|
"updated_at": self.updated_at.isoformat() if self.updated_at else None
|
|
} |