feat(llm): unify OpenAI-compatible providers behind a registry + generic endpoint

The OpenAI-compatible family (openai, xAI, DeepSeek, Qwen, GLM, MiniMax,
OpenRouter, Ollama) all speak the same Chat Completions API and differ only by
base_url, key, and two narrow wire-format quirks already isolated in subclasses.
Replace the scattered base-URL dict, key handling, and client-class branches with
one ProviderSpec registry that get_llm and the factory drive off; provider quirks
stay in their subclasses. Add a generic "openai_compatible" provider for any
OpenAI-compatible server (vLLM, LM Studio, llama.cpp, relays) via backend_url +
optional key — adding a provider is now one registry row. Native Anthropic/Google
keep their own clients (genuinely different APIs). Also fixes the env backend URL
being ignored when the provider was chosen interactively (#978).

tradingagents/llm_clients/factory.py

@@ -2,16 +2,6 @@ from typing import Optional
 
 from .base_client import BaseLLMClient
 
-# Providers that use the OpenAI-compatible chat completions API
-_OPENAI_COMPATIBLE = (
-    "openai", "xai", "deepseek",
-    "qwen", "qwen-cn",
-    "glm", "glm-cn",
-    "minimax", "minimax-cn",
-    "ollama", "openrouter",
-)
-
-
 def create_llm_client(
     provider: str,
     model: str,
@@ -38,10 +28,9 @@ def create_llm_client(
     """
     provider_lower = provider.lower()
 
-    if provider_lower in _OPENAI_COMPATIBLE:
-        from .openai_client import OpenAIClient
-        return OpenAIClient(model, base_url, provider=provider_lower, **kwargs)
-
+    # Native (non-OpenAI) APIs are matched first so their string check doesn't
+    # import the OpenAI client. Everything else is OpenAI-compatible and routes
+    # through the provider registry (single source of truth).
     if provider_lower == "anthropic":
         from .anthropic_client import AnthropicClient
         return AnthropicClient(model, base_url, **kwargs)
@@ -54,4 +43,8 @@ def create_llm_client(
         from .azure_client import AzureOpenAIClient
         return AzureOpenAIClient(model, base_url, **kwargs)
 
+    from .openai_client import OpenAIClient, is_openai_compatible
+    if is_openai_compatible(provider_lower):
+        return OpenAIClient(model, base_url, provider=provider_lower, **kwargs)
+
     raise ValueError(f"Unsupported LLM provider: {provider}")