Fix #274: Add warnings for OpenAI news/fundamentals hallucination risk

tests/__init__.py

@@ -0,0 +1,2 @@
+# Tests package
+

tests/test_openai_news_warnings.py

@@ -0,0 +1,124 @@
+"""
+Tests for OpenAI news dataflow functions to ensure proper warnings about hallucination risks.
+
+Issue #274: OpenAI is hallucinating and provides outdated news.
+The OpenAI vendor for news retrieval doesn't have reliable real-time web search access,
+so it may generate fake or outdated news based on its training data.
+"""
+
+import pytest
+import warnings
+from unittest.mock import Mock, patch
+from tradingagents.dataflows.openai import (
+    get_global_news_openai,
+    get_stock_news_openai,
+    get_fundamentals_openai,
+)
+
+
+class TestOpenAINewsWarnings:
+    """Test that OpenAI news functions emit appropriate warnings about hallucination risks."""
+
+    @patch("tradingagents.dataflows.openai.OpenAI")
+    @patch("tradingagents.dataflows.openai.get_config")
+    def test_get_global_news_emits_warning(self, mock_get_config, mock_openai_class):
+        """Test that get_global_news_openai emits a warning about potential hallucination."""
+        # Setup mocks
+        mock_config = {
+            "backend_url": "https://api.openai.com/v1",
+            "quick_think_llm": "gpt-4o-mini",
+        }
+        mock_get_config.return_value = mock_config
+
+        mock_client = Mock()
+        mock_openai_class.return_value = mock_client
+
+        # Mock the response
+        mock_response = Mock()
+        mock_response.output = [None, Mock(content=[Mock(text="Fake news content")])]
+        mock_client.responses.create.return_value = mock_response
+
+        # Test that a warning is emitted
+        with pytest.warns(UserWarning, match="may hallucinate|outdated|unreliable"):
+            result = get_global_news_openai("2024-11-14", look_back_days=7, limit=5)
+
+        assert result is not None
+
+    @patch("tradingagents.dataflows.openai.OpenAI")
+    @patch("tradingagents.dataflows.openai.get_config")
+    def test_get_stock_news_emits_warning(self, mock_get_config, mock_openai_class):
+        """Test that get_stock_news_openai emits a warning about potential hallucination."""
+        # Setup mocks
+        mock_config = {
+            "backend_url": "https://api.openai.com/v1",
+            "quick_think_llm": "gpt-4o-mini",
+        }
+        mock_get_config.return_value = mock_config
+
+        mock_client = Mock()
+        mock_openai_class.return_value = mock_client
+
+        # Mock the response
+        mock_response = Mock()
+        mock_response.output = [None, Mock(content=[Mock(text="Fake stock news")])]
+        mock_client.responses.create.return_value = mock_response
+
+        # Test that a warning is emitted
+        with pytest.warns(UserWarning, match="may hallucinate|outdated|unreliable"):
+            result = get_stock_news_openai("NVDA", "2024-11-01", "2024-11-14")
+
+        assert result is not None
+
+    @patch("tradingagents.dataflows.openai.OpenAI")
+    @patch("tradingagents.dataflows.openai.get_config")
+    def test_get_fundamentals_emits_warning(self, mock_get_config, mock_openai_class):
+        """Test that get_fundamentals_openai emits a warning about potential hallucination."""
+        # Setup mocks
+        mock_config = {
+            "backend_url": "https://api.openai.com/v1",
+            "quick_think_llm": "gpt-4o-mini",
+        }
+        mock_get_config.return_value = mock_config
+
+        mock_client = Mock()
+        mock_openai_class.return_value = mock_client
+
+        # Mock the response
+        mock_response = Mock()
+        mock_response.output = [None, Mock(content=[Mock(text="Fake fundamentals")])]
+        mock_client.responses.create.return_value = mock_response
+
+        # Test that a warning is emitted
+        with pytest.warns(UserWarning, match="may hallucinate|outdated|unreliable"):
+            result = get_fundamentals_openai("NVDA", "2024-11-14")
+
+        assert result is not None
+
+    def test_warning_message_content(self):
+        """Test that warning messages contain helpful information about alternatives."""
+        # This test verifies the warning message suggests using alternative vendors
+        with patch("tradingagents.dataflows.openai.OpenAI"), \
+             patch("tradingagents.dataflows.openai.get_config") as mock_get_config:
+
+            mock_get_config.return_value = {
+                "backend_url": "https://api.openai.com/v1",
+                "quick_think_llm": "gpt-4o-mini",
+            }
+
+            with warnings.catch_warnings(record=True) as w:
+                warnings.simplefilter("always")
+
+                try:
+                    get_global_news_openai("2024-11-14")
+                except Exception:
+                    pass  # We're only testing the warning, not the full execution
+
+                # Check that at least one warning was issued
+                assert len(w) > 0
+
+                # Check that the warning mentions alternatives
+                warning_text = str(w[0].message).lower()
+                assert any(keyword in warning_text for keyword in [
+                    "alpha_vantage", "google", "local", "alternative", "vendor"
+                ])
+

tradingagents/dataflows/openai.py

@@ -1,8 +1,50 @@
+import warnings
 from openai import OpenAI
 from .config import get_config
 
 
+def _warn_hallucination_risk(data_type="news", category="news_data", alternatives=None):
+    """
+    Emit a warning about potential hallucination when using OpenAI for data retrieval.
+
+    Args:
+        data_type: Type of data being retrieved (e.g., "news", "fundamental data")
+        category: Config category for vendor selection (e.g., "news_data", "fundamental_data")
+        alternatives: List of alternative vendor names (default: ["alpha_vantage", "google", "local"])
+    """
+    if alternatives is None:
+        alternatives = ["alpha_vantage", "google", "local"]
+
+    alternatives_str = "', '".join(alternatives)
+    warnings.warn(
+        f"OpenAI {data_type} vendor may hallucinate or provide outdated {data_type}. "
+        f"For reliable {data_type}, use alternative vendors: '{alternatives_str}'. "
+        f"Configure in config['data_vendors']['{category}'].",
+        UserWarning,
+        stacklevel=3
+    )
+
+
 def get_stock_news_openai(query, start_date, end_date):
+    """
+    Retrieve stock news using OpenAI's LLM.
+
+    WARNING: This function may hallucinate or provide outdated news because it relies on
+    the LLM's training data rather than real-time web search. For reliable, up-to-date news,
+    consider using alternative vendors such as 'alpha_vantage', 'google', or 'local'.
+
+    Configure alternative vendors in your config:
+        config["data_vendors"]["news_data"] = "alpha_vantage"  # or "google" or "local"
+
+    Args:
+        query: Stock ticker or search query
+        start_date: Start date in yyyy-mm-dd format
+        end_date: End date in yyyy-mm-dd format
+
+    Returns:
+        str: News content (may be hallucinated or outdated)
+    """
+    _warn_hallucination_risk(data_type="news", category="news_data")
     config = get_config()
     client = OpenAI(base_url=config["backend_url"])
 
@@ -38,6 +80,26 @@ def get_stock_news_openai(query, start_date, end_date):
 
 
 def get_global_news_openai(curr_date, look_back_days=7, limit=5):
+    """
+    Retrieve global news using OpenAI's LLM.
+
+    WARNING: This function may hallucinate or provide outdated news because it relies on
+    the LLM's training data rather than real-time web search. For reliable, up-to-date news,
+    consider using alternative vendors such as 'alpha_vantage', 'google', or 'local'.
+
+    Configure alternative vendors in your config:
+        config["data_vendors"]["news_data"] = "alpha_vantage"  # or "google" or "local"
+
+    Args:
+        curr_date: Current date in yyyy-mm-dd format
+        look_back_days: Number of days to look back (default: 7)
+        limit: Maximum number of articles to return (default: 5)
+
+    Returns:
+        str: News content (may be hallucinated or outdated)
+    """
+    _warn_hallucination_risk(data_type="news", category="news_data")
+
     config = get_config()
     client = OpenAI(base_url=config["backend_url"])
 
@@ -73,6 +135,29 @@ def get_global_news_openai(curr_date, look_back_days=7, limit=5):
 
 
 def get_fundamentals_openai(ticker, curr_date):
+    """
+    Retrieve fundamental data using OpenAI's LLM.
+
+    WARNING: This function may hallucinate or provide outdated data because it relies on
+    the LLM's training data rather than real-time data sources. For reliable, up-to-date
+    fundamental data, consider using alternative vendors such as 'alpha_vantage', 'yfinance', or 'local'.
+
+    Configure alternative vendors in your config:
+        config["data_vendors"]["fundamental_data"] = "alpha_vantage"  # or "yfinance" or "local"
+
+    Args:
+        ticker: Stock ticker symbol
+        curr_date: Current date in yyyy-mm-dd format
+
+    Returns:
+        str: Fundamental data (may be hallucinated or outdated)
+    """
+    _warn_hallucination_risk(
+        data_type="fundamental data",
+        category="fundamental_data",
+        alternatives=["alpha_vantage", "yfinance", "local"]
+    )
+
     config = get_config()
     client = OpenAI(base_url=config["backend_url"])