feat(discovery): add mean_reversion pipeline for RSI oversold scanner

The rsi_oversold scanner is a contrarian signal, not a momentum signal —
it fires on short-term panic pullbacks within uptrends and expects a 3-7 day
bounce. Keeping it in the momentum pipeline conflates two fundamentally
different signal types and could cause the ranker to misprice it.

Changes:
- Add mean_reversion pipeline (priority 6, deep_dive_budget 5) to default_config.py
- Move rsi_oversold scanner from pipeline="momentum" to pipeline="mean_reversion"
  in both default_config.py and rsi_oversold.py

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

tradingagents/dataflows/discovery/scanners/rsi_oversold.py

@@ -39,7 +39,7 @@ class RSIOversoldScanner(BaseScanner):
     """
 
     name = "rsi_oversold"
-    pipeline = "momentum"
+    pipeline = "mean_reversion"
     strategy = "mean_reversion_bounce"
 
     def __init__(self, config: Dict[str, Any]):

tradingagents/default_config.py

@@ -110,6 +110,12 @@ DEFAULT_CONFIG = {
                 "deep_dive_budget": 5,
             },
             "events": {"enabled": True, "priority": 5, "deep_dive_budget": 3},
+            "mean_reversion": {
+                "enabled": True,
+                "priority": 6,
+                "ranker_prompt": "mean_reversion_ranker.txt",
+                "deep_dive_budget": 5,
+            },
         },
         # ========================================
         # OHLCV CACHE (populated nightly by prefetch workflow)
@@ -273,7 +279,7 @@ DEFAULT_CONFIG = {
             },
             "rsi_oversold": {
                 "enabled": True,
-                "pipeline": "momentum",
+                "pipeline": "mean_reversion",
                 "limit": 10,
                 "max_tickers": 0,  # 0 = no cap (nightly cache makes full universe fast)
                 "rsi_period": 2,  # Connors RSI(2): most sensitive to short-term pullbacks