feat(config): expose sampling temperature and document reproducibility

Adds a cross-provider temperature config (and TRADINGAGENTS_TEMPERATURE),
forwarded to every LLM client when set, so runs can be made less variable
on models that honor it. Adds a README "Reproducibility" section that
separates the sources of run-to-run variation, what users can control
(temperature, non-reasoning model, pinned date), and what is inherent to
LLM-driven analysis, and notes that the identity and verified-data fixes
already removed the "different companies / fabricated prices" variance.

#178 #168

tradingagents/graph/trading_graph.py

@@ -155,6 +155,13 @@ class TradingAgentsGraph:
             if effort:
                 kwargs["effort"] = effort
 
+        # Sampling temperature is cross-provider: forward it whenever set.
+        # float() here so a value coming from a TRADINGAGENTS_TEMPERATURE env
+        # string ("0.2") works the same as a programmatic float.
+        temperature = self.config.get("temperature")
+        if temperature is not None and temperature != "":
+            kwargs["temperature"] = float(temperature)
+
         return kwargs
 
     def _create_tool_nodes(self) -> Dict[str, ToolNode]: