fix: reduce grpo training runtime

fix: parse chat completions in rewards

fix: emit prompt column for grpo trainer

fix: add grpo warnings compatibility attr

fix: select writable cache root at startup

fix: write grpo checkpoints to tmp in space

fix: use writable runtime dirs before training imports

fix: comprehensive torchao dtype + register_constant shims

fix: shim register_constant before importing unsloth (no-op safe for non-torchao training)

fix: verbose step-by-step logs, catch BaseException with full traceback

fix: capture transformers/TRL logging into UI via logging.Handler

fix: remove runtime unsloth install, verify import at startup

fix: read pip output in chunks splitting on and

feat: stream pip output live to UI logs during unsloth install

fix: install unsloth to /app/pkgs (writable), detect torch version for git extra

fix: capture unsloth install errors, try PyPI then git fallback

fix: replace demo.load(every=) with gr.Timer for Gradio 4.x compat

fix: space_runner installs unsloth at click-time on live GPU

feat: training space with manual start UI