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).

README.md

@@ -157,6 +157,8 @@ For enterprise providers (e.g. Azure OpenAI, AWS Bedrock), copy `.env.enterprise
 
 For local models, configure Ollama with `llm_provider: "ollama"`. The default endpoint is `http://localhost:11434/v1`; set `OLLAMA_BASE_URL` to point at a remote `ollama-serve`. Pull models with `ollama pull <name>`, and pick "Custom model ID" in the CLI for any model not listed by default.
 
+For any other OpenAI-compatible server (vLLM, LM Studio, llama.cpp, or a custom relay), use `llm_provider: "openai_compatible"` and set the endpoint via `backend_url` (or `TRADINGAGENTS_LLM_BACKEND_URL`), e.g. `http://localhost:8000/v1` for vLLM or `http://localhost:1234/v1` for LM Studio. The model is whatever your server serves. No key is needed for local servers; set `OPENAI_COMPATIBLE_API_KEY` when the endpoint requires one.
+
 Alternatively, copy `.env.example` to `.env` and fill in your keys:
 ```bash
 cp .env.example .env