chore: consolidate install, fix CLI portability, normalize LLM responses

- Point requirements.txt to pyproject.toml as single source of truth
- Resolve welcome.txt path relative to module for CLI portability
- Include cli/static files in package build
- Extract shared normalize_content for OpenAI Responses API and
  Gemini 3 list-format responses into base_client.py
- Update README install and CLI usage instructions

tradingagents/llm_clients/base_client.py

@@ -2,6 +2,25 @@ from abc import ABC, abstractmethod
 from typing import Any, Optional
 
 
+def normalize_content(response):
+    """Normalize LLM response content to a plain string.
+
+    Multiple providers (OpenAI Responses API, Google Gemini 3) return content
+    as a list of typed blocks, e.g. [{'type': 'reasoning', ...}, {'type': 'text', 'text': '...'}].
+    Downstream agents expect response.content to be a string. This extracts
+    and joins the text blocks, discarding reasoning/metadata blocks.
+    """
+    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
+
+
 class BaseLLMClient(ABC):
     """Abstract base class for LLM clients."""
 

tradingagents/llm_clients/google_client.py

@@ -2,30 +2,19 @@ from typing import Any, Optional
 
 from langchain_google_genai import ChatGoogleGenerativeAI
 
-from .base_client import BaseLLMClient
+from .base_client import BaseLLMClient, normalize_content
 from .validators import validate_model
 
 
 class NormalizedChatGoogleGenerativeAI(ChatGoogleGenerativeAI):
     """ChatGoogleGenerativeAI with normalized content output.
 
-    Gemini 3 models return content as list: [{'type': 'text', 'text': '...'}]
+    Gemini 3 models return content as list of typed blocks.
     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))
+        return normalize_content(super().invoke(input, config, **kwargs))
 
 
 class GoogleClient(BaseLLMClient):

tradingagents/llm_clients/openai_client.py

@@ -3,9 +3,21 @@ from typing import Any, Optional
 
 from langchain_openai import ChatOpenAI
 
-from .base_client import BaseLLMClient
+from .base_client import BaseLLMClient, normalize_content
 from .validators import validate_model
 
+
+class NormalizedChatOpenAI(ChatOpenAI):
+    """ChatOpenAI with normalized content output.
+
+    The Responses API returns content as a list of typed blocks
+    (reasoning, text, etc.). This normalizes to string for consistent
+    downstream handling.
+    """
+
+    def invoke(self, input, config=None, **kwargs):
+        return normalize_content(super().invoke(input, config, **kwargs))
+
 # Kwargs forwarded from user config to ChatOpenAI
 _PASSTHROUGH_KWARGS = (
     "timeout", "max_retries", "reasoning_effort",
@@ -66,7 +78,7 @@ class OpenAIClient(BaseLLMClient):
         if self.provider == "openai":
             llm_kwargs["use_responses_api"] = True
 
-        return ChatOpenAI(**llm_kwargs)
+        return NormalizedChatOpenAI(**llm_kwargs)
 
     def validate_model(self) -> bool:
         """Validate model for the provider."""