"""Filesystem layout shared by every step of the recipe.

The scripts read and write files at the locations defined here, so the four
numbered steps chain together against this package's own folders. Every path can
be overridden with an environment variable if you want a different workspace.

    base/    step 0 downloads the base model here (google/functiongemma-270m-it)
    data/    step 1 writes train.jsonl / val.jsonl here
    work/    step 2 keeps the LoRA adapter + training log here
    model/   step 3 writes the merged model here (this package ships it)
    onnx/    step 4 writes the Sentis-ready graph here (this package ships it)

The developer+tools prefix (fg_dev_block_home.txt) is written into model/ next
to the weights it is paired with — the Unity runtime loads the two together.
"""
import os

_HERE = os.path.dirname(os.path.abspath(__file__))
ROOT = os.environ.get("FG_ROOT", os.path.dirname(_HERE))   # package root (parent of scripts/)

BASE_MODEL = os.environ.get("FG_BASE",  os.path.join(ROOT, "base"))
DATA_DIR   = os.environ.get("FG_DATA",  os.path.join(ROOT, "data"))
WORK_DIR   = os.environ.get("FG_WORK",  os.path.join(ROOT, "work"))
MODEL_DIR  = os.environ.get("FG_MODEL", os.path.join(ROOT, "model"))
ONNX_DIR   = os.environ.get("FG_ONNX",  os.path.join(ROOT, "onnx"))

# derived file paths
TRAIN_JSONL = os.path.join(DATA_DIR, "train.jsonl")
VAL_JSONL   = os.path.join(DATA_DIR, "val.jsonl")
DEV_BLOCK   = os.path.join(MODEL_DIR, "fg_dev_block_home.txt")
LORA_DIR    = os.path.join(WORK_DIR, "lora_best")
TRAIN_LOG   = os.path.join(WORK_DIR, "train.log")
ONNX_FILE   = os.path.join(ONNX_DIR, "functiongemma_home.onnx")

# Optional: step 4 also copies the exported graph into a Unity project when this
# points at a destination .onnx path. Leave unset to skip the copy.
UNITY_ASSET = os.environ.get("FG_UNITY_ASSET", "")