blog: reword env reward and HOME wording; clarify worker roles (no simulator/synthetic phrasing).

Update blog.md (rubric crosswalk); add outputs/agent_project_knowledge.json for reviewers.

README: link blog.md as Hub long-form writeup (replace TODO).

Add blog.md (ReleaseOps build log and technical context).

README + API: add YouTube pitch link (Shorts)

Add demo flow HTML for /ui/flow

Add GRPO walkthrough notebook to Hub; link from README and / API

README: GitHub raw image URLs (Hub blocks plain PNG git); gitignore images/*.png

Set HF_HOME and HF_DATASETS_CACHE for writable caches on Space

Set TORCHINDUCTOR cache dirs before torch import (HF Space no passwd uids)

Work around torch mega-cache double registration on Space imports

fix: durable outputs under /data, unbuffered training logs, relaxed deps

fix: Update eval API to support subfolder and fix default model ID

feat: Expose eval API endpoint

Enhance TorchGenerator to support optional subfolder for model loading

Post-training push to Hugging Face Hub: --hub-model-repo and pilot query params

write_test: explain repo vs container; add download_url and list_files

Add /outputs/write_test to create simpllll.csv and report hf_token env presence

Document HF token via Space secrets, ENV.example, and operational curl for pilot and push_to_hub

Add 8-bit Adam + gradient checkpointing for bf16 training to fit 1.7B on L4

Add --bf16 flag and expose it via /train/pilot for bigger models

Allow model_name override on /train/pilot and raise num_generations cap

Force Qwen3 chat template to disable thinking mode via tokenizer patch

Fix reward_func reading wrong env layer for tool_calls counters

Nuclear reward shaping: silent rollouts get flat -3, active rollouts floor at +1

Crush-signal reward shaping to force exploration over silence

Fix reward collapse: floor exploration loss, bonus per-call and per-terminal

Live training visualization + aggressive reward shaping to prevent 'do nothing' collapse

Add compact training summary endpoint

Use Qwen3 model for TRL OpenEnv tool parsing

Add jmespath for TRL tool parsing

Adapt GRPO config to installed TRL API

Add browser-accessible GRPO training endpoints

Add Space root health landing route

Install git for Space dependency builds

Add Hugging Face Space metadata

Deploy ReleaseOps Arena GPU Space

initial commit