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/llm_clients/anthropic_client.py

@@ -14,18 +14,12 @@ class AnthropicClient(BaseLLMClient):
 
     def get_llm(self) -> Any:
         """Return configured ChatAnthropic instance."""
-        llm_kwargs = {
-            "model": self.model,
-            "max_tokens": self.kwargs.get("max_tokens", 4096),
-        }
+        llm_kwargs = {"model": self.model}
 
-        for key in ("timeout", "max_retries", "api_key"):
+        for key in ("timeout", "max_retries", "api_key", "max_tokens"):
             if key in self.kwargs:
                 llm_kwargs[key] = self.kwargs[key]
 
-        if "thinking_config" in self.kwargs:
-            llm_kwargs["thinking"] = self.kwargs["thinking_config"]
-
         return ChatAnthropic(**llm_kwargs)
 
     def validate_model(self) -> bool:

tradingagents/llm_clients/google_client.py

@@ -6,6 +6,28 @@ from .base_client import BaseLLMClient
 from .validators import validate_model
 
 
+class NormalizedChatGoogleGenerativeAI(ChatGoogleGenerativeAI):
+    """ChatGoogleGenerativeAI with normalized content output.
+
+    Gemini 3 models return content as list: [{'type': 'text', 'text': '...'}]
+    This normalizes to string for consistent downstream handling.
+    """
+
+    def _normalize_content(self, response):
+        content = response.content
+        if isinstance(content, list):
+            texts = [
+                item.get("text", "") if isinstance(item, dict) and item.get("type") == "text"
+                else item if isinstance(item, str) else ""
+                for item in content
+            ]
+            response.content = "\n".join(t for t in texts if t)
+        return response
+
+    def invoke(self, input, config=None, **kwargs):
+        return self._normalize_content(super().invoke(input, config, **kwargs))
+
+
 class GoogleClient(BaseLLMClient):
     """Client for Google Gemini models."""
 
@@ -20,14 +42,23 @@ class GoogleClient(BaseLLMClient):
             if key in self.kwargs:
                 llm_kwargs[key] = self.kwargs[key]
 
-        if "thinking_budget" in self.kwargs and self._is_preview_model():
-            llm_kwargs["thinking_budget"] = self.kwargs["thinking_budget"]
+        # Map thinking_level to appropriate API param based on model
+        # Gemini 3 Pro: low, high
+        # Gemini 3 Flash: minimal, low, medium, high
+        # Gemini 2.5: thinking_budget (0=disable, -1=dynamic)
+        thinking_level = self.kwargs.get("thinking_level")
+        if thinking_level:
+            model_lower = self.model.lower()
+            if "gemini-3" in model_lower:
+                # Gemini 3 Pro doesn't support "minimal", use "low" instead
+                if "pro" in model_lower and thinking_level == "minimal":
+                    thinking_level = "low"
+                llm_kwargs["thinking_level"] = thinking_level
+            else:
+                # Gemini 2.5: map to thinking_budget
+                llm_kwargs["thinking_budget"] = -1 if thinking_level == "high" else 0
 
-        return ChatGoogleGenerativeAI(**llm_kwargs)
-
-    def _is_preview_model(self) -> bool:
-        """Check if this is a preview model that supports thinking budget."""
-        return "preview" in self.model.lower()
+        return NormalizedChatGoogleGenerativeAI(**llm_kwargs)
 
     def validate_model(self) -> bool:
         """Validate model for Google."""

tradingagents/llm_clients/validators.py

@@ -1,58 +1,75 @@
-from typing import Dict, List
+"""Model name validators for each provider.
 
-VALID_MODELS: Dict[str, List[str]] = {
+Only validates model names - does NOT enforce limits.
+Let LLM providers use their own defaults for unspecified params.
+"""
+
+VALID_MODELS = {
     "openai": [
+        # GPT-5 series (2025)
+        "gpt-5.2",
+        "gpt-5.1",
+        "gpt-5",
+        "gpt-5-mini",
+        "gpt-5-nano",
+        # GPT-4.1 series (2025)
+        "gpt-4.1",
+        "gpt-4.1-mini",
+        "gpt-4.1-nano",
+        # o-series reasoning models
+        "o4-mini",
+        "o3",
+        "o3-mini",
+        "o1",
+        "o1-preview",
+        # GPT-4o series (legacy but still supported)
         "gpt-4o",
         "gpt-4o-mini",
-        "gpt-4-turbo",
-        "gpt-4",
-        "gpt-3.5-turbo",
-        "o1",
-        "o1-mini",
-        "o1-preview",
-        "o3-mini",
-        "gpt-5-nano",
-        "gpt-5-mini",
-        "gpt-5",
     ],
     "anthropic": [
-        "claude-3-5-sonnet-20241022",
-        "claude-3-5-haiku-20241022",
-        "claude-3-opus-20240229",
-        "claude-3-sonnet-20240229",
-        "claude-3-haiku-20240307",
+        # Claude 4.5 series (2025)
+        "claude-opus-4-5",
+        "claude-sonnet-4-5",
+        "claude-haiku-4-5",
+        # Claude 4.x series
+        "claude-opus-4-1-20250805",
         "claude-sonnet-4-20250514",
-        "claude-haiku-4-5-20251001",
-        "claude-opus-4-5-20251101",
+        # Claude 3.7 series
+        "claude-3-7-sonnet-20250219",
+        # Claude 3.5 series (legacy)
+        "claude-3-5-haiku-20241022",
+        "claude-3-5-sonnet-20241022",
     ],
     "google": [
-        "gemini-1.5-pro",
-        "gemini-1.5-flash",
-        "gemini-2.0-flash",
-        "gemini-2.0-flash-lite",
-        "gemini-2.5-pro-preview-05-06",
-        "gemini-2.5-flash-preview-05-20",
+        # Gemini 3 series (preview)
         "gemini-3-pro-preview",
         "gemini-3-flash-preview",
+        # Gemini 2.5 series
+        "gemini-2.5-pro",
+        "gemini-2.5-flash",
+        "gemini-2.5-flash-lite",
+        # Gemini 2.0 series
+        "gemini-2.0-flash",
+        "gemini-2.0-flash-lite",
     ],
     "xai": [
-        "grok-beta",
-        "grok-2",
-        "grok-2-mini",
-        "grok-3",
-        "grok-3-mini",
+        # Grok 4.1 series
+        "grok-4-1-fast",
+        "grok-4-1-fast-reasoning",
+        "grok-4-1-fast-non-reasoning",
+        # Grok 4 series
+        "grok-4",
+        "grok-4-0709",
+        "grok-4-fast-reasoning",
+        "grok-4-fast-non-reasoning",
     ],
-    "ollama": [],
-    "openrouter": [],
-    "vllm": [],
 }
 
 
 def validate_model(provider: str, model: str) -> bool:
-    """Validate that a model is supported by the provider.
+    """Check if model name is valid for the given provider.
 
-    For ollama, openrouter, and vllm, any model is accepted.
-    For other providers, checks against VALID_MODELS.
+    For ollama, openrouter, vllm - any model is accepted.
     """
     provider_lower = provider.lower()
 
@@ -60,10 +77,6 @@ def validate_model(provider: str, model: str) -> bool:
         return True
 
     if provider_lower not in VALID_MODELS:
-        return False
-
-    valid = VALID_MODELS[provider_lower]
-    if not valid:
         return True
 
-    return model in valid
+    return model in VALID_MODELS[provider_lower]