forked from Rockachopa/Timmy-time-dashboard
a719c7538d
## 1. MCP (Model Context Protocol) Implementation ### Registry (src/mcp/registry.py) - Tool registration with JSON schemas - Dynamic tool discovery - Health tracking per tool - Metrics collection (latency, error rates) - @register_tool decorator for easy registration ### Server (src/mcp/server.py) - MCPServer class implementing MCP protocol - MCPHTTPServer for FastAPI integration - Standard endpoints: list_tools, call_tool, get_schema ### Schemas (src/mcp/schemas/base.py) - create_tool_schema() helper - Common parameter types - Standard return types ### Bootstrap (src/mcp/bootstrap.py) - Automatic tool module loading - Status reporting ## 2. MCP-Compliant Tools (src/tools/) | Tool | Purpose | Category | |------|---------|----------| | web_search | DuckDuckGo search | research | | read_file | File reading | files | | write_file | File writing (confirmation) | files | | list_directory | Directory listing | files | | python | Python code execution | code | | memory_search | Vector memory search | memory | All tools have proper schemas, error handling, and MCP registration. ## 3. Event Bus (src/events/bus.py) - Async publish/subscribe pattern - Pattern matching with wildcards (agent.task.*) - Event history tracking - Concurrent handler execution - Module-level singleton for system-wide use ## 4. Sub-Agents (src/agents/) All agents inherit from BaseAgent with: - Agno Agent integration - MCP tool registry access - Event bus connectivity - Structured logging ### Agent Roster | Agent | Role | Tools | Purpose | |-------|------|-------|---------| | Seer | Research | web_search, read_file, memory_search | Information gathering | | Forge | Code | python, write_file, read_file | Code generation | | Quill | Writing | write_file, read_file, memory_search | Content creation | | Echo | Memory | memory_search, read_file, write_file | Context retrieval | | Helm | Routing | memory_search | Task routing decisions | | Timmy | Orchestrator | All tools | Coordination & user interface | ### Timmy Orchestrator - Analyzes user requests - Routes to appropriate sub-agent - Handles direct queries - Manages swarm coordination - create_timmy_swarm() factory function ## 5. Integration All components wired together: - Tools auto-register on import - Agents connect to event bus - MCP server provides HTTP API - Ready for dashboard integration ## Tests - All 973 existing tests pass - New components tested manually - Import verification successful Next steps: Cascade Router, Self-Upgrade Loop, Dashboard integration
82 lines
2.4 KiB
Python
82 lines
2.4 KiB
Python
"""Echo Agent — Memory and context management.
|
|
|
|
Capabilities:
|
|
- Memory retrieval
|
|
- Context synthesis
|
|
- User profile management
|
|
- Conversation history
|
|
"""
|
|
|
|
from typing import Any
|
|
|
|
from agents.base import BaseAgent
|
|
|
|
|
|
ECHO_SYSTEM_PROMPT = """You are Echo, a memory and context management specialist.
|
|
|
|
Your role is to remember, retrieve, and synthesize information from the past.
|
|
|
|
## Capabilities
|
|
|
|
- Search past conversations
|
|
- Retrieve user preferences
|
|
- Synthesize context from multiple sources
|
|
- Manage user profile
|
|
|
|
## Guidelines
|
|
|
|
1. **Be accurate** — Only state what we actually know
|
|
2. **Be relevant** — Filter for context that matters now
|
|
3. **Be concise** — Summarize, don't dump everything
|
|
4. **Acknowledge uncertainty** — Say when memory is unclear
|
|
|
|
## Tool Usage
|
|
|
|
- Use memory_search to find relevant past context
|
|
- Use read_file to access vault files
|
|
- Use write_file to update user profile
|
|
|
|
## Response Format
|
|
|
|
Provide memory retrieval in this structure:
|
|
- Direct answer (what we know)
|
|
- Context (relevant past discussions)
|
|
- Confidence (certain/likely/speculative)
|
|
- Source (where this came from)
|
|
|
|
You work for Timmy, the sovereign AI orchestrator. Be the keeper of institutional knowledge.
|
|
"""
|
|
|
|
|
|
class EchoAgent(BaseAgent):
|
|
"""Memory and context specialist."""
|
|
|
|
def __init__(self, agent_id: str = "echo") -> None:
|
|
super().__init__(
|
|
agent_id=agent_id,
|
|
name="Echo",
|
|
role="memory",
|
|
system_prompt=ECHO_SYSTEM_PROMPT,
|
|
tools=["memory_search", "read_file", "write_file"],
|
|
)
|
|
|
|
async def execute_task(self, task_id: str, description: str, context: dict) -> Any:
|
|
"""Execute a memory retrieval task."""
|
|
# Extract what to search for
|
|
prompt = f"Search memory and provide relevant context:\n\nTask: {description}\n\nSynthesize findings clearly."
|
|
|
|
result = await self.run(prompt)
|
|
|
|
return {
|
|
"task_id": task_id,
|
|
"agent": self.agent_id,
|
|
"result": result,
|
|
"status": "completed",
|
|
}
|
|
|
|
async def recall(self, query: str, include_sources: bool = True) -> str:
|
|
"""Quick memory recall."""
|
|
sources = "with sources" if include_sources else ""
|
|
prompt = f"Recall information about: {query} {sources}\n\nProvide relevant context from memory."
|
|
return await self.run(prompt)
|