feat(gradio): timeout fallback to bundled mock_ui charts and summary

feat: custom_hf without CUDA falls back to offline baseline

fix(custom_hf): prefer dtype over deprecated torch_dtype in from_pretrained

perf(ui): fewer Gradio steps + live STEPS_PER_EPISODE, tighter token cap

perf(space-ui): faster Gradio custom_hf — UI candidates=1, cap tokens, GenerationConfig

fix(hf-space): flatten requirements.txt — Spaces build only mounts this file

Space T4 + real HF path: split requirements, GPU defaults, API reset behavior

README/BLOG: hackathon theme fit line and HF Space Discussions mini-blog link

Finalize eval-friendly defaults: offline baseline, deterministic API reset, docs cleanup

docs+router: HF Space secret names; auto includes custom_hf only when HF_TOKEN set

fix(router): exclude custom_hf from auto chain so Space auto stays fast

perf(ui): default mock provider; auto tries NIM/OpenRouter before HF; cap HF router timeout 90s

fix(space): ProxyHeadersMiddleware + uvicorn proxy flags so Gradio redirects use https behind HF

fix(space): mount Gradio at / for HF iframe; disable SSR; curl path + blank UI notes; example step JSON

fix(api): Pydantic v2 step payload (exclude_none); env candidate_solutions; README Space API curl guide; Gradio API tab

Add story blog updates and submission-ready docs links

Finalize CPU-safe mock flow and verify live OpenEnv endpoints

fix(hf-cpu): slim requirements.txt for Spaces; requirements-train.txt for PyTorch/TRL; suggested_hardware cpu-basic

docs: Docker Hub image sanjay767676/forge

docs: Docker Hub pull/push/login; remove ghcr instructions

Add Dockerfile, Docker Compose, and GitHub Action to publish Docker image to GHCR

docs: hackathon badge links to judge guide; clarify video/slides vs mini-blog

security: remove secrets from .env.example (use HF Space secrets only)

fix(space): fastapi>=0.115.2 for Gradio 5.25; Pydantic v2 model_dump in API

fix(space): Gradio 5.25 + fastapi<0.113 for openenv-core websockets>=15

docs: NOTE 1/2 checklist, judges rubric link; OpenEnv FORGEOpenEnvironment + openenv-core

feat: inference router (HF/NIM/OpenRouter/mock); README aligned with judge rubric; chart axis labels

docs: judge-focused README; Colab notebook with repo clone step

Update .gitignore to broadly include outputs artifacts

Allow tracking of models and adapter configurations

Add remaining training artifacts and reports to tracking

Final hardening for 100% submission readiness

Submission checklist fix: track judge plots and reduce README overclaims

Submission audit fixes: loss curve export, README compliance links, robust training script fallback

NVIDIA NIM Support: Added NvidiaNIMProvider as a first-class inference mode

Fix Reporting Bug: Resolved NameError in train_unsloth.py report generation

Final Structural Fix: Preserved code in candidate rankings for authentic DPO export

Fix DPO Dataset Generation: Real preference pairs now exported from adversarial loop

Colab Automation: Added setup and execution shell scripts for one-click training

Real RL Training Layer: DPO Dataset Export + Unsloth Trainer + Training Report

Final High-Impact Upgrade: Real LLM Inference, Candidate Ranking, and HF API Support

Final Submission Upgrade: Advanced tier progression, professional README, and hackathon blog

Fix: Force Python 3.11 to resolve audioop ModuleNotFoundError

Update deployment URL to sanjay7676/Team404_FORGE

Fix: Add .git suffix to HF Space URL

Trigger deployment: Configuration verified

Improve deployment workflow robustness

Final polish: Added Hugging Face YAML header and completed submission checklist

Final submission assets: generated evidence, updated checklist, and judge narrative

Add Gradio app for Hugging Face Space and GitHub Actions auto-deploy workflow (sanitized)