Add 5Hz LM planner (CoT-only mode)

Wraps acestep-5Hz-lm-1.7B as a Qwen3 causal LM that runs before the DiT.
Generates until </think>, parses the YAML metadata block, and returns
structured BPM, key/scale, time signature, language, and a rewritten caption
to use as DiT conditioning instead of the raw user input.

Author: Marenz

src/model.rs

@@ -5,8 +5,10 @@
 //! - [`encoder`] — condition encoder (lyric encoder, timbre encoder, text projector)
 //! - [`tokenizer`] — audio tokenizer (FSQ) and detokenizer
 //! - [`generation`] — top-level generation model combining all components
+//! - [`lm_planner`] — 5Hz LM planner (CoT-only), expands raw caption → structured metadata
 
 pub mod encoder;
 pub mod generation;
+pub mod lm_planner;
 pub mod tokenizer;
 pub mod transformer;