# intern-decision — copy to /opt/docker/compose/intern-decision/.env on fv-ml1 (mode 0600).
# Built on fv-ml1 from services/intern-decision-serve (see README "Building").
IMAGE=intern-decision-serve:0.1.0
PORT=8033
HOST_IP=10.251.50.54
# fv-ml1 GPU 1 = the utility card (vllm-coder, erp, meromero, scriberr).
GPU_ID=1
# HARD torch-allocator cap: the single knob that holds the container's WHOLE nvidia-smi footprint
# (CUDA context included) inside GPU 1's budget next to scriberr (infra-ops, 2026-09-30):
#   GPU 1 nvidia-smi Free >= 15,400 MiB  =  our card peak 9,876 (cap 9.0 GiB + 660 MiB outside the
#   allocator, measured) + scriberr's peak 5,496, rounded up. README "VRAM".
VRAM_CAP_GIB=9.0
# Tokens per CALL (state + up to 16 questions), checked BEFORE the forward pass: a longer call is a
# clear 422. 7,168 is the largest call measured to fit under VRAM_CAP_GIB=9.0. Change the two TOGETHER,
# and re-measure (README "VRAM"): a larger value would let a call reach the cap and return 503.
MAX_TOKENS=7168
# >= 32 characters; source of truth: secret get intern-decision/api-token
INTERN_DECISION_API_TOKEN=