feat(showcase): /showcase page + precomputed bundle + READMEs + video script

fix(collector): persist task cursor across PPO updates - was resetting to 0 each update so only first IC_ROLLOUTS tasks were ever trained on; now round-robins full shard (3 rollouts x 60 updates = 180 visits over 127-task shard = full coverage); also log first/last 5 task ids at startup so coverage is visible

feat(train): make HF_TOKEN optional + continuous live ETA heartbeat during rollouts

feat(kaggle): 3 sharded training notebooks + local-critic mode + LoRA merge

feat(phases): realistic 3x12 configs for phase2/3 launchers

fix(hfjob): bitsandbytes 0.45.5 to avoid triton.ops removal

fix(hfjob): pin transformers/peft/bnb stack — skip unsloth (gemma3n compile crash)

fix(hfjob): install unsloth_zoo + datasets/sentencepiece deps that unsloth needs

fix(hfjob): use python3 interpreter (HF transformers image has no python alias)

feat(train): warm-start adapter loading + IC_TASK_MODE (curated/all/hard) + phase2/phase3 launchers

feat(train): live tqdm+ETA, per-update HF Hub checkpoint upload, HF Jobs entrypoint + launcher

feat(phase8-10): saboteur+slack+replay, 381 scenarios, Colab Unsloth+Qwen72B critic, push helpers

feat: actor-critic PPO trainer + multi-page analytics dashboard

feat: AWS EKS backend + S3 checkpoints + CloudWatch logs + 4 new tasks + 4 new reward signals + ENV.md

feat: real K8s backend via kind + EXEC_KUBECTL action + 9 fault injectors + /k8s/* endpoints + --local training preset + RUNBOOK

first commit