BF16-direct indexer: skip f32, strided octave + halftone projection

Replace chunked f32 streaming with BF16-direct path:
- read_tensor_bf16_raw: reusable Vec<u16> buffer, no f32 alloc (141 MB vs 424 MB)
- project_row_bf16_direct: inline BF16→f64, 136 bytes stack
- project_row_bf16_strided: octave stride + halftone drop (97% fewer conversions)
- stream_index_gguf_bf16: combined optimized indexer with octave_stride param
- HALFTONE_POS/HALFTONE_TO_BIN: compile-time position tables
- 3 new unit tests: halftone coverage, bf16_to_f64 accuracy, strided vs full

https://claude.ai/code/session_01HmdXNPit7QsTCfhJFef3Ee

Author: claude