updated environment with multi-agent DB integration

complete almost

complete almost

pin vllm<=0.18.0 to fix TRL importance-sampling ratio collapse

Drop max_prompt_length from GRPOConfig (removed in newer TRL)

Add GRPO training scaffolding (Module 5 rollout_func pattern) + plot artifacts

Merge branch 'main' of https://github.com/Hard007ik/ShopManagerEng

shop manage eng phase 2 first

Add LICENSE file

Delete Apache License from LICENSE file

Include Apache License 2.0

solve inference again 2

solve inference again

again inferecnce updated

resolving inference

inference updated for 3 task

yaml updated

updated server/app.py as per submit validation

updated url in inference.py

fix: resolve relative import error for Docker deployment

feat: jewelry shop RL environment with market, warehouse, and showroom phases