# Case Forge — HF Space runtime (Gradio app on ZeroGPU).
#
# App inference runs in-Space on ZeroGPU (free): base Qwen3-4B + the published LoRA,
# merged at first GPU call, generating via transformers under @spaces.GPU.
# Heavy/offline work (corpus generation, training, LoRA merge) runs on Modal — NOT here.

gradio>=6
spaces                 # ZeroGPU (@spaces.GPU) — no-op locally
transformers>=4.49
peft>=0.13             # load + merge_and_unload the adapter
accelerate>=1
torch
jsonschema>=4          # full structural validation of the output contract