feat: add Amazon Bedrock provider support

Add BedrockClient using langchain-aws ChatBedrockConverse, enabling
TradingAgents to use Bedrock-hosted models (Claude, Kimi, Qwen, GLM, etc.)
via IAM Role authentication without API keys.

Usage:
  config['llm_provider']    = 'bedrock'
  config['deep_think_llm']  = 'us.anthropic.claude-sonnet-4-5-20251001-v1:0'
  config['quick_think_llm'] = 'us.amazon.nova-lite-v1:0'

Requires: langchain-aws>=0.2.0

pyproject.toml

@@ -13,6 +13,7 @@ dependencies = [
     "backtrader>=1.9.78.123",
     "langchain-anthropic>=0.3.15",
     "langchain-experimental>=0.3.4",
+    "langchain-aws>=0.2.0",
     "langchain-google-genai>=2.1.5",
     "langchain-openai>=0.3.23",
     "langgraph>=0.4.8",

tradingagents/llm_clients/bedrock_client.py

@@ -0,0 +1,32 @@
+from typing import Any, Optional
+
+from langchain_aws import ChatBedrockConverse
+
+from .base_client import BaseLLMClient
+from .validators import validate_model
+
+
+class BedrockClient(BaseLLMClient):
+    """Client for Amazon Bedrock models (Claude, Kimi, Qwen, GLM, etc.)."""
+
+    def __init__(self, model: str, base_url: Optional[str] = None, **kwargs):
+        super().__init__(model, base_url, **kwargs)
+
+    def get_llm(self) -> Any:
+        """Return configured ChatBedrockConverse instance."""
+        llm_kwargs = {"model_id": self.model}
+
+        if "region_name" in self.kwargs:
+            llm_kwargs["region_name"] = self.kwargs["region_name"]
+        if "max_tokens" in self.kwargs:
+            llm_kwargs["max_tokens"] = self.kwargs["max_tokens"]
+        if "callbacks" in self.kwargs:
+            llm_kwargs["callbacks"] = self.kwargs["callbacks"]
+        if "timeout" in self.kwargs:
+            llm_kwargs["timeout"] = self.kwargs["timeout"]
+
+        return ChatBedrockConverse(**llm_kwargs)
+
+    def validate_model(self) -> bool:
+        """Validate model for Bedrock (pass-through, model IDs are flexible)."""
+        return True

tradingagents/llm_clients/factory.py

@@ -4,6 +4,7 @@ from .base_client import BaseLLMClient
 from .openai_client import OpenAIClient
 from .anthropic_client import AnthropicClient
 from .google_client import GoogleClient
+from .bedrock_client import BedrockClient
 
 
 def create_llm_client(
@@ -46,4 +47,7 @@ def create_llm_client(
     if provider_lower == "google":
         return GoogleClient(model, base_url, **kwargs)
 
+    if provider_lower == "bedrock":
+        return BedrockClient(model, base_url, **kwargs)
+
     raise ValueError(f"Unsupported LLM provider: {provider}")