feat: add multi-provider LLM support with thinking configurations

Models added:
- OpenAI: GPT-5.2, GPT-5.1, GPT-5, GPT-5 Mini, GPT-5 Nano, GPT-4.1
- Anthropic: Claude Opus 4.5/4.1, Claude Sonnet 4.5/4, Claude Haiku 4.5
- Google: Gemini 3 Pro/Flash, Gemini 2.5 Flash/Flash Lite
- xAI: Grok 4, Grok 4.1 Fast (Reasoning/Non-Reasoning)

Configs updated:
- Add unified thinking_level for Gemini (maps to thinking_level for Gemini 3,
  thinking_budget for Gemini 2.5; handles Pro's lack of "minimal" support)
- Add OpenAI reasoning_effort configuration
- Add NormalizedChatGoogleGenerativeAI for consistent response handling

Fixes:
- Fix Bull/Bear researcher display truncation
- Replace ChromaDB with BM25 for memory retrieval

tradingagents/dataflows/stockstats_utils.py

@@ -3,7 +3,7 @@ import yfinance as yf
 from stockstats import wrap
 from typing import Annotated
 import os
-from .config import get_config, DATA_DIR
+from .config import get_config
 
 
 class StockstatsUtils:
@@ -17,63 +17,45 @@ class StockstatsUtils:
             str, "curr date for retrieving stock price data, YYYY-mm-dd"
         ],
     ):
-        # Get config and set up data directory path
         config = get_config()
-        online = config["data_vendors"]["technical_indicators"] != "local"
 
-        df = None
-        data = None
+        today_date = pd.Timestamp.today()
+        curr_date_dt = pd.to_datetime(curr_date)
 
-        if not online:
-            try:
-                data = pd.read_csv(
-                    os.path.join(
-                        DATA_DIR,
-                        f"{symbol}-YFin-data-2015-01-01-2025-03-25.csv",
-                    )
-                )
-                df = wrap(data)
-            except FileNotFoundError:
-                raise Exception("Stockstats fail: Yahoo Finance data not fetched yet!")
+        end_date = today_date
+        start_date = today_date - pd.DateOffset(years=15)
+        start_date_str = start_date.strftime("%Y-%m-%d")
+        end_date_str = end_date.strftime("%Y-%m-%d")
+
+        # Ensure cache directory exists
+        os.makedirs(config["data_cache_dir"], exist_ok=True)
+
+        data_file = os.path.join(
+            config["data_cache_dir"],
+            f"{symbol}-YFin-data-{start_date_str}-{end_date_str}.csv",
+        )
+
+        if os.path.exists(data_file):
+            data = pd.read_csv(data_file)
+            data["Date"] = pd.to_datetime(data["Date"])
         else:
-            # Get today's date as YYYY-mm-dd to add to cache
-            today_date = pd.Timestamp.today()
-            curr_date = pd.to_datetime(curr_date)
-
-            end_date = today_date
-            start_date = today_date - pd.DateOffset(years=15)
-            start_date = start_date.strftime("%Y-%m-%d")
-            end_date = end_date.strftime("%Y-%m-%d")
-
-            # Get config and ensure cache directory exists
-            os.makedirs(config["data_cache_dir"], exist_ok=True)
-
-            data_file = os.path.join(
-                config["data_cache_dir"],
-                f"{symbol}-YFin-data-{start_date}-{end_date}.csv",
+            data = yf.download(
+                symbol,
+                start=start_date_str,
+                end=end_date_str,
+                multi_level_index=False,
+                progress=False,
+                auto_adjust=True,
             )
+            data = data.reset_index()
+            data.to_csv(data_file, index=False)
 
-            if os.path.exists(data_file):
-                data = pd.read_csv(data_file)
-                data["Date"] = pd.to_datetime(data["Date"])
-            else:
-                data = yf.download(
-                    symbol,
-                    start=start_date,
-                    end=end_date,
-                    multi_level_index=False,
-                    progress=False,
-                    auto_adjust=True,
-                )
-                data = data.reset_index()
-                data.to_csv(data_file, index=False)
-
-            df = wrap(data)
-            df["Date"] = df["Date"].dt.strftime("%Y-%m-%d")
-            curr_date = curr_date.strftime("%Y-%m-%d")
+        df = wrap(data)
+        df["Date"] = df["Date"].dt.strftime("%Y-%m-%d")
+        curr_date_str = curr_date_dt.strftime("%Y-%m-%d")
 
         df[indicator]  # trigger stockstats to calculate the indicator
-        matching_rows = df[df["Date"].str.startswith(curr_date)]
+        matching_rows = df[df["Date"].str.startswith(curr_date_str)]
 
         if not matching_rows.empty:
             indicator_value = matching_rows[indicator].values[0]