feat(core): add Groq/OpenAI-compatible LlmClient

New jarvis-core::llm module providing a blocking client for
OpenAI-compatible chat completions endpoints (Groq by default).

- LlmClient::new / from_env (GROQ_TOKEN, GROQ_BASE_URL, GROQ_MODEL)
- complete(messages, max_tokens) -> String
- thiserror-based LlmError / ConfigError
- gated behind a new llm feature, included in default jarvis_app

Not yet wired into the wake-word/intent loop; that lands in v0.3.

crates/jarvis-core/src/lib.rs

@@ -48,6 +48,9 @@ pub mod audio_buffer;
 #[cfg(feature = "lua")]
 pub mod lua;
 
+#[cfg(feature = "llm")]
+pub mod llm;
+
 // shared statics
 // pub static APP_DIR: Lazy<PathBuf> = Lazy::new(|| std::env::current_dir().unwrap());
 pub static APP_DIR: Lazy<PathBuf> = Lazy::new(|| {