feat: add MiniMax as LLM provider

Add MiniMax (api.minimax.io) as a fifth LLM provider option alongside
Anthropic, OpenAI, Gemini, and Codex. MiniMax offers an
OpenAI-compatible Chat Completions API with the M2.5 model (204K
context window).

Changes:
- lib/llm/minimax.mjs: new provider using raw fetch (no SDK)
- lib/llm/index.mjs: register MiniMax in the factory
- .env.example, crucix.config.mjs, README.md: document the new option
- test/llm-minimax.test.mjs: 10 unit tests (node:test)
- test/llm-minimax-integration.test.mjs: live API integration test

Usage:
  LLM_PROVIDER=minimax
  LLM_API_KEY=sk-...
  LLM_MODEL=MiniMax-M2.5          # optional, this is the default

.env.example

@@ -31,12 +31,12 @@ REFRESH_INTERVAL_MINUTES=15
 
 # === LLM Layer (optional) ===
 # Enables AI-enhanced trade ideas and breaking news Telegram alerts.
-# Provider options: anthropic | openai | gemini | codex
+# Provider options: anthropic | openai | gemini | codex | minimax
 LLM_PROVIDER=
 # Not needed for codex (uses ~/.codex/auth.json)
 LLM_API_KEY=
 # Optional override. Each provider has a sensible default:
-# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex
+# anthropic: claude-sonnet-4-6 | openai: gpt-5.4 | gemini: gemini-3.1-pro | codex: gpt-5.3-codex | minimax: MiniMax-M2.5
 LLM_MODEL=
 
 # === Telegram Alerts (optional, requires LLM) ===