chore: add ninja-build and build-essential to package requirements; update README and documentation to reflect changes in model configuration and local Transformers usage

chore: update base model to NVIDIA-Nemotron-3-Nano-4B-BF16 across configurations and documentation; adjust max sequence length to 2048; upgrade GitHub Actions cache to v5

docs: reorganize documentation structure and workflow

feat: expand coach summary training pipeline

fix: align coach summary Modal training with current TRL API

feat: add Modal pipeline for coach summary training

feat: add coach summary LoRA config and provider plumbing

feat: prepare filtered public fitness style corpus

feat: build Pozify-native coach summary SFT datasets

feat: ingest real exercise dataset into knowledge artifacts

Fix exercise router baseline artifact publishing

feat(pose)!: use coco17 3d router features

build: use python 3.10 and torch 2.11

pioritize BiLSTM model

Add issue 10 training release assets

Add temporal router model selection

Implement exercise classifier router