Fix `ThirdPartyTimeoutError` swallowing in `yfinance` dataflows (#127)

In dataflow API wrappers, generic `except Exception` handlers were swallowing
timeout exceptions (like `requests.exceptions.Timeout` and `ThirdPartyTimeoutError`),
preventing upstream retry logic and proper error handling from functioning correctly.

This patch:
- Adds explicit catching of `requests.exceptions.Timeout` to raise as `ThirdPartyTimeoutError` in `yfinance` wrapper modules (`y_finance.py`, `yfinance_news.py`, `yfinance_scanner.py`).
- Adds explicit catching and re-raising of `ThirdPartyTimeoutError` before generic exception handlers across the dataflows.
- Retains existing exception inheritance logic to avoid backward compatibility breaks.
- Updates `TestEnsureIndexesInInit` to use the explicit `ensure_indexes()` call per lazy loading changes.

Co-authored-by: google-labs-jules[bot] <161369871+google-labs-jules[bot]@users.noreply.github.com>
Co-authored-by: aguzererler <6199053+aguzererler@users.noreply.github.com>

tests/unit/test_pr106_review_fixes.py

@@ -454,6 +454,10 @@ class TestEnsureIndexesInInit(unittest.TestCase):
 
             store = MongoReportStore("mongodb://localhost:27017", run_id="test")
 
+            # Indexes are now created lazily, not in __init__.
+            # Explicitly call ensure_indexes() to test index creation logic.
+            store.ensure_indexes()
+
             # create_index should have been called at least 4 times
             # (the indexes from ensure_indexes)
             self.assertGreaterEqual(mock_col.create_index.call_count, 4)

tradingagents/dataflows/alpha_vantage_indicator.py

@@ -1,7 +1,7 @@
 from datetime import datetime
 from typing import Dict, Any
 from dateutil.relativedelta import relativedelta
-from .alpha_vantage_common import _make_api_request
+from .alpha_vantage_common import _make_api_request, ThirdPartyTimeoutError
 
 
 SUPPORTED_INDICATORS = {
@@ -221,6 +221,8 @@ def get_indicator(
             f"{INDICATOR_DESCRIPTIONS.get(indicator, 'No description available.')}"
         )
 
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         print(f"Error getting Alpha Vantage indicator data for {indicator}: {e}")
         return f"Error retrieving {indicator} data: {str(e)}"

tradingagents/dataflows/y_finance.py

@@ -4,7 +4,9 @@ from datetime import datetime
 from dateutil.relativedelta import relativedelta
 import pandas as pd
 import yfinance as yf
+import requests
 import os
+from .finnhub_common import ThirdPartyTimeoutError
 from .stockstats_utils import StockstatsUtils, YFinanceError, _clean_dataframe, _load_or_fetch_ohlcv, yf_retry
 
 logger = logging.getLogger(__name__)
@@ -293,6 +295,10 @@ def get_fundamentals(
 
         return header + "\n".join(lines)
 
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out retrieving fundamentals for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error retrieving fundamentals for {ticker}: {str(e)}"
 
@@ -323,6 +329,10 @@ def get_balance_sheet(
         
         return header + csv_string
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out retrieving balance sheet for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error retrieving balance sheet for {ticker}: {str(e)}"
 
@@ -353,6 +363,10 @@ def get_cashflow(
         
         return header + csv_string
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out retrieving cash flow for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error retrieving cash flow for {ticker}: {str(e)}"
 
@@ -383,6 +397,10 @@ def get_income_statement(
         
         return header + csv_string
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out retrieving income statement for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error retrieving income statement for {ticker}: {str(e)}"
 
@@ -407,5 +425,9 @@ def get_insider_transactions(
         
         return header + csv_string
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out retrieving insider transactions for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error retrieving insider transactions for {ticker}: {str(e)}"

tradingagents/dataflows/yfinance_news.py

@@ -1,8 +1,10 @@
 """yfinance-based news data fetching functions."""
 
 import yfinance as yf
+import requests
 from datetime import datetime
 from dateutil.relativedelta import relativedelta
+from .finnhub_common import ThirdPartyTimeoutError
 
 
 def _extract_article_data(article: dict) -> dict:
@@ -98,6 +100,10 @@ def get_news_yfinance(
 
         return f"## {ticker} News, from {start_date} to {end_date}:\n\n{news_str}"
 
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching news for {ticker}")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching news for {ticker}: {str(e)}"
 
@@ -186,5 +192,9 @@ def get_global_news_yfinance(
 
         return f"## Global Market News, from {start_date} to {curr_date}:\n\n{news_str}"
 
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching global news")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching global news: {str(e)}"

tradingagents/dataflows/yfinance_scanner.py

@@ -1,8 +1,10 @@
 """yfinance-based scanner data fetching functions for market-wide analysis."""
 
 import yfinance as yf
+import requests
 from datetime import datetime
 from typing import Annotated
+from .finnhub_common import ThirdPartyTimeoutError
 
 
 def get_market_movers_yfinance(
@@ -72,6 +74,10 @@ def get_market_movers_yfinance(
         
         return "\n".join(lines) + "\n"
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching market movers")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching market movers for {category}: {str(e)}"
 
@@ -151,6 +157,10 @@ def get_market_indices_yfinance() -> str:
         
         return "\n".join(lines) + "\n"
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching market indices")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching market indices: {str(e)}"
 
@@ -238,6 +248,10 @@ def get_sector_performance_yfinance() -> str:
 
         return "\n".join(lines) + "\n"
 
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching sector performance")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching sector performance: {str(e)}"
 
@@ -338,6 +352,10 @@ def get_industry_performance_yfinance(
         
         return "\n".join(lines) + "\n"
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching industry performance")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching industry performance for sector '{sector_key}': {str(e)}"
 
@@ -399,5 +417,9 @@ def get_topic_news_yfinance(
         
         return "\n".join(lines) + "\n"
         
+    except requests.exceptions.Timeout:
+        raise ThirdPartyTimeoutError(f"Request timed out fetching news for topic '{topic}'")
+    except ThirdPartyTimeoutError:
+        raise
     except Exception as e:
         return f"Error fetching news for topic '{topic}': {str(e)}"