Added macro economic analyst - 2

FRED_MACRO_INTEGRATION.md

@@ -1,7 +1,7 @@
 # FRED API Macro Data Integration
 
 ## Summary
-Added FRED (Federal Reserve Economic Data) API support to the TradingAgents vendor methods system for macroeconomic analysis.
+Added FRED (Federal Reserve Economic Data) API support to the TradingAgents vendor methods system for macroeconomic analysis, including a new **Macro Analyst** agent.
 
 ## Files Added
 
@@ -24,9 +24,22 @@ New module providing FRED API integration with the following functions:
 - **`get_fed_calendar_and_minutes(curr_date)`** - Federal Reserve meeting calendar and policy updates
 - **`get_macro_economic_summary(curr_date, lookback_days=90)`** - Complete macro economic analysis combining all components
 
+### 2. `tradingagents/agents/analysts/macro_analyst.py`
+New macro analyst agent that uses FRED API tools to analyze economic conditions:
+- Analyzes Federal Reserve policy and economic indicators
+- Evaluates inflation, employment, and growth trends
+- Assesses Treasury yield curve and recession signals
+- Provides market implications and trading considerations
+
+### 3. `tradingagents/agents/utils/macro_data_tools.py`
+Tool wrapper functions for LangChain integration:
+- **`get_economic_indicators(curr_date, lookback_days)`** - Comprehensive economic indicators
+- **`get_yield_curve(curr_date)`** - Treasury yield curve with inversion analysis
+- **`get_fed_calendar(curr_date)`** - Fed meeting calendar and policy updates
+
 ## Files Modified
 
-### 2. `tradingagents/dataflows/interface.py`
+### 4. `tradingagents/dataflows/interface.py`
 Updated vendor routing system to include FRED macro data:
 
 **Added Imports:**
@@ -71,6 +84,76 @@ VENDOR_LIST = [
 },
 ```
 
+### 5. `tradingagents/agents/__init__.py`
+Added macro analyst to exports:
+```python
+from .analysts.macro_analyst import create_macro_analyst
+
+__all__ = [
+    # ... existing exports ...
+    "create_macro_analyst",
+]
+```
+
+### 6. `tradingagents/agents/utils/agent_utils.py`
+Added macro tool imports:
+```python
+from tradingagents.agents.utils.macro_data_tools import (
+    get_economic_indicators,
+    get_yield_curve,
+    get_fed_calendar
+)
+```
+
+### 7. `tradingagents/graph/setup.py`
+Added macro analyst option to graph setup:
+```python
+def setup_graph(
+    self, selected_analysts=["market", "social", "news", "fundamentals"]
+):
+    """Set up and compile the agent workflow graph.
+
+    Args:
+        selected_analysts (list): List of analyst types to include. Options are:
+            - "market": Market analyst
+            - "social": Social media analyst
+            - "news": News analyst
+            - "fundamentals": Fundamentals analyst
+            - "macro": Macro economic analyst  # New!
+    """
+    # ... existing analyst setup ...
+    
+    if "macro" in selected_analysts:
+        analyst_nodes["macro"] = create_macro_analyst(
+            self.quick_thinking_llm
+        )
+        delete_nodes["macro"] = create_msg_delete()
+        tool_nodes["macro"] = self.tool_nodes["macro"]
+```
+
+### 8. `tradingagents/graph/trading_graph.py`
+Added macro tools import and tool node:
+```python
+from tradingagents.agents.utils.agent_utils import (
+    # ... existing imports ...
+    get_economic_indicators,
+    get_yield_curve,
+    get_fed_calendar
+)
+
+def _create_tool_nodes(self) -> Dict[str, ToolNode]:
+    return {
+        # ... existing tool nodes ...
+        "macro": ToolNode(
+            [
+                get_economic_indicators,
+                get_yield_curve,
+                get_fed_calendar,
+            ]
+        ),
+    }
+```
+
 ## Configuration Required
 
 To use FRED API features, set the FRED API key via:
@@ -92,6 +175,22 @@ To use FRED API features, set the FRED API key via:
 
 ## Usage Examples
 
+### Enable Macro Analyst in Graph
+
+```python
+from tradingagents.graph.trading_graph import TradingAgentsGraph
+
+# Create graph with macro analyst enabled
+graph = TradingAgentsGraph(
+    selected_analysts=["market", "fundamentals", "macro"],  # Include "macro"
+    debug=True,
+    config=your_config
+)
+
+# Run analysis
+result = graph.propagate("AAPL", "2025-10-06")
+```
+
 ### Via Vendor Routing System
 
 ```python
@@ -165,11 +264,12 @@ All functions return formatted markdown strings suitable for LLM analysis:
 
 Changes were made with minimal modifications to existing code:
 
-1. ✅ **New file only** - `macro_utils.py` is a new addition
+1. ✅ **New files only** - `macro_utils.py`, `macro_analyst.py`, `macro_data_tools.py` are new additions
-2. ✅ **Additive changes** - Only added new entries to existing dictionaries
+2. ✅ **Additive changes** - Only added new entries to existing dictionaries and imports
 3. ✅ **No breaking changes** - Existing functionality unchanged
-4. ✅ **Follows existing patterns** - Uses same vendor routing architecture as other data sources
+4. ✅ **Follows existing patterns** - Uses same vendor routing and analyst architecture
-5. ✅ **Consistent naming** - Follows existing naming conventions (`get_*` pattern)
+5. ✅ **Consistent naming** - Follows existing naming conventions (`get_*`, `create_*_analyst` patterns)
+6. ✅ **Optional feature** - Macro analyst is opt-in via `selected_analysts` parameter
 
 ## Testing
 

tradingagents/agents/__init__.py

@@ -6,6 +6,7 @@ from .analysts.fundamentals_analyst import create_fundamentals_analyst
 from .analysts.market_analyst import create_market_analyst
 from .analysts.news_analyst import create_news_analyst
 from .analysts.social_media_analyst import create_social_media_analyst
+from .analysts.macro_analyst import create_macro_analyst
 
 from .researchers.bear_researcher import create_bear_researcher
 from .researchers.bull_researcher import create_bull_researcher
@@ -29,6 +30,7 @@ __all__ = [
     "create_bull_researcher",
     "create_research_manager",
     "create_fundamentals_analyst",
+    "create_macro_analyst",
     "create_market_analyst",
     "create_neutral_debator",
     "create_news_analyst",

tradingagents/agents/analysts/macro_analyst.py

@@ -0,0 +1,78 @@
+from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
+import time
+import json
+from tradingagents.agents.utils.agent_utils import get_economic_indicators, get_yield_curve, get_fed_calendar
+from tradingagents.dataflows.config import get_config
+
+
+def create_macro_analyst(llm):
+    def macro_analyst_node(state):
+        current_date = state["trade_date"]
+        ticker = state["company_of_interest"]
+        company_name = state["company_of_interest"]
+
+        tools = [
+            get_economic_indicators,
+            get_yield_curve,
+            get_fed_calendar,
+        ]
+
+        system_message = (
+            "You are a macro economic analyst tasked with analyzing Federal Reserve data, economic indicators, and macroeconomic trends. "
+            "Your objective is to write a comprehensive report detailing current economic conditions, monetary policy implications, and their impact on financial markets. "
+            "Analyze key indicators such as:\n"
+            "- Federal Funds Rate and monetary policy trajectory\n"
+            "- Inflation indicators (CPI, PPI)\n"
+            "- Employment data (unemployment rate, payrolls)\n"
+            "- Treasury yield curve and inversion signals\n"
+            "- Economic growth indicators (GDP, PMI)\n"
+            "- Market volatility (VIX)\n\n"
+            "Provide detailed analysis of:\n"
+            "1. Current economic cycle positioning\n"
+            "2. Federal Reserve policy stance and likely direction\n"
+            "3. Inflation and employment trends\n"
+            "4. Yield curve implications for recession risk\n"
+            "5. Market implications and trading considerations\n\n"
+            "Use the available tools: `get_economic_indicators` for comprehensive economic data, "
+            "`get_yield_curve` for Treasury yields and inversion analysis, and `get_fed_calendar` for FOMC schedule and policy trajectory. "
+            "Make sure to provide detailed, actionable insights rather than generic summaries. "
+            "Append a Markdown table at the end summarizing key macro indicators and their implications."
+        )
+
+        prompt = ChatPromptTemplate.from_messages(
+            [
+                (
+                    "system",
+                    "You are a helpful AI assistant, collaborating with other assistants."
+                    " Use the provided tools to progress towards answering the question."
+                    " If you are unable to fully answer, that's OK; another assistant with different tools"
+                    " will help where you left off. Execute what you can to make progress."
+                    " If you or any other assistant has the FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** or deliverable,"
+                    " prefix your response with FINAL TRANSACTION PROPOSAL: **BUY/HOLD/SELL** so the team knows to stop."
+                    " You have access to the following tools: {tool_names}.\n{system_message}"
+                    "For your reference, the current date is {current_date}. The company we want to look at is {ticker}",
+                ),
+                MessagesPlaceholder(variable_name="messages"),
+            ]
+        )
+
+        prompt = prompt.partial(system_message=system_message)
+        prompt = prompt.partial(tool_names=", ".join([tool.name for tool in tools]))
+        prompt = prompt.partial(current_date=current_date)
+        prompt = prompt.partial(ticker=ticker)
+
+        chain = prompt | llm.bind_tools(tools)
+
+        result = chain.invoke(state["messages"])
+
+        report = ""
+
+        if len(result.tool_calls) == 0:
+            report = result.content
+
+        return {
+            "messages": [result],
+            "macro_report": report,
+        }
+
+    return macro_analyst_node

tradingagents/agents/utils/agent_utils.py

@@ -19,6 +19,11 @@ from tradingagents.agents.utils.news_data_tools import (
     get_insider_transactions,
     get_global_news
 )
+from tradingagents.agents.utils.macro_data_tools import (
+    get_economic_indicators,
+    get_yield_curve,
+    get_fed_calendar
+)
 
 def create_msg_delete():
     def delete_messages(state):

tradingagents/agents/utils/macro_data_tools.py

@@ -0,0 +1,82 @@
+from typing import Annotated
+from langchain_core.tools import tool
+
+
+@tool
+def get_economic_indicators(
+    curr_date: Annotated[str, "Current date in yyyy-mm-dd format"],
+    lookback_days: Annotated[int, "How many days to look back for data"] = 90,
+):
+    """
+    Retrieve comprehensive economic indicators report from FRED including:
+    - Federal Funds Rate
+    - Consumer Price Index (CPI) and Producer Price Index (PPI)
+    - Unemployment Rate and Nonfarm Payrolls
+    - GDP Growth Rate
+    - ISM Manufacturing PMI
+    - Consumer Confidence
+    - VIX (Market Volatility)
+    
+    Args:
+        curr_date (str): Current date in yyyy-mm-dd format
+        lookback_days (int): How many days to look back for data
+        
+    Returns:
+        str: Comprehensive economic indicators report with analysis
+    """
+    from tradingagents.dataflows.interface import route_to_vendor
+    
+    result = route_to_vendor(
+        "get_economic_indicators",
+        curr_date=curr_date,
+        lookback_days=lookback_days
+    )
+    return str(result)
+
+
+@tool
+def get_yield_curve(
+    curr_date: Annotated[str, "Current date in yyyy-mm-dd format"],
+):
+    """
+    Retrieve US Treasury yield curve data from FRED with inversion analysis.
+    Includes yields for 1M, 3M, 6M, 1Y, 2Y, 3Y, 5Y, 7Y, 10Y, 20Y, and 30Y maturities.
+    Provides 2Y-10Y spread analysis and yield curve interpretation.
+    
+    Args:
+        curr_date (str): Current date in yyyy-mm-dd format
+        
+    Returns:
+        str: Treasury yield curve data with analysis and recession signals
+    """
+    from tradingagents.dataflows.interface import route_to_vendor
+    
+    result = route_to_vendor(
+        "get_yield_curve",
+        curr_date=curr_date
+    )
+    return str(result)
+
+
+@tool
+def get_fed_calendar(
+    curr_date: Annotated[str, "Current date in yyyy-mm-dd format"],
+):
+    """
+    Retrieve Federal Reserve meeting calendar and recent policy updates.
+    Includes FOMC meeting schedule, recent Fed Funds rate history,
+    and key policy considerations.
+    
+    Args:
+        curr_date (str): Current date in yyyy-mm-dd format
+        
+    Returns:
+        str: Fed calendar, meeting schedule, and policy trajectory
+    """
+    from tradingagents.dataflows.interface import route_to_vendor
+    
+    result = route_to_vendor(
+        "get_fed_calendar",
+        curr_date=curr_date
+    )
+    return str(result)

tradingagents/graph/setup.py

@@ -48,6 +48,7 @@ class GraphSetup:
                 - "social": Social media analyst
                 - "news": News analyst
                 - "fundamentals": Fundamentals analyst
+                - "macro": Macro economic analyst
         """
         if len(selected_analysts) == 0:
             raise ValueError("Trading Agents Graph Setup Error: no analysts selected!")
@@ -85,6 +86,13 @@ class GraphSetup:
             delete_nodes["fundamentals"] = create_msg_delete()
             tool_nodes["fundamentals"] = self.tool_nodes["fundamentals"]
 
+        if "macro" in selected_analysts:
+            analyst_nodes["macro"] = create_macro_analyst(
+                self.quick_thinking_llm
+            )
+            delete_nodes["macro"] = create_msg_delete()
+            tool_nodes["macro"] = self.tool_nodes["macro"]
+
         # Create researcher and manager nodes
         bull_researcher_node = create_bull_researcher(
             self.quick_thinking_llm, self.bull_memory

tradingagents/graph/trading_graph.py

@@ -33,7 +33,10 @@ from tradingagents.agents.utils.agent_utils import (
     get_news,
     get_insider_sentiment,
     get_insider_transactions,
-    get_global_news
+    get_global_news,
+    get_economic_indicators,
+    get_yield_curve,
+    get_fed_calendar
 )
 
 from .conditional_logic import ConditionalLogic
@@ -155,6 +158,14 @@ class TradingAgentsGraph:
                     get_income_statement,
                 ]
             ),
+            "macro": ToolNode(
+                [
+                    # Macroeconomic analysis tools
+                    get_economic_indicators,
+                    get_yield_curve,
+                    get_fed_calendar,
+                ]
+            ),
         }
 
     def propagate(self, company_name, trade_date):