.env_example

# ==============================================================================
# Complexa Environment Configuration
#
# Setup:
#   complexa init              # Creates .env from this template
#   # Edit .env with your values, then:
#   complexa init <uv|docker>  # Generates env.sh for your runtime
#   source env.sh              # Activates the environment
#
# WARNING: .env contains sensitive credentials.
# Do NOT commit .env to version control!
# ==============================================================================

# ==============================================================================
# USER CONFIGURATION — Edit these to match your setup
# ==============================================================================

# Credentials (SENSITIVE — fill in your values)
GITLAB_TOKEN=TOKEN_HERE
WANDB_API_KEY=YOUR_WANDB_KEY
WANDB_ENTITY=YOUR_WANDB_ENTITY
HF_TOKEN=HF_TOKEN_HERE

# Local paths (host-side) — set these to your machine's paths
LOCAL_CODE_PATH=/path/to/Proteina-Complexa
LOCAL_DATA_PATH=/path/to/PFM_data
LOCAL_CACHE_DIR=${LOCAL_CODE_PATH}/.cache
LOCAL_CHECKPOINT_PATH=${LOCAL_CODE_PATH}/checkpoints

# Custom docker mounts (comma-separated "host_path:container_path" pairs, leave empty for none)
DOCKER_MOUNTS=

# Logging
LOGURU_LEVEL=INFO

# Cluster access
CLUSTER_USER=USER_NAME_HERE

# ==============================================================================
# DOCKER SETTINGS — Typically unchanged
# ==============================================================================

# Registry
REGISTRY=registry.example.com
REGISTRY_USER='$oauthuser'

# Docker image and container
DOCKER_IMAGE=registry.example.com/org/repo:tag
CONTAINER_NAME=proteina-dev
DOCKERFILE_PATH=env/docker/Dockerfile

# Docker-side paths (container-internal)
DOCKER_REPO_PATH=/workspace/Proteina-Complexa
DOCKER_DATA_PATH=/workspace/data/PFM_data
DOCKER_PYTHONPATH=/workspace/Proteina-Complexa/src
DOCKER_CHECKPOINT_PATH=/workspace/Proteina-Complexa/checkpoints
DOCKER_CACHE_DIR=/workspace/Proteina-Complexa/.cache
DOCKER_HF_HOME=/workspace/Proteina-Complexa/community_models/ckpts
DOCKER_HF_HUB_CACHE=${DOCKER_CACHE_DIR}/huggingface/hub

# ==============================================================================
# MODEL CHECKPOINTS — Derived from LOCAL_CODE_PATH, rarely need changes
# ==============================================================================

USE_V2_COMPLEXA_ARCH=False

# Community model checkpoints
COMMUNITY_MODELS_PATH=${LOCAL_CODE_PATH}/community_models
ESM_DIR=${COMMUNITY_MODELS_PATH}/ckpts/ESM2
AF2_DIR=${COMMUNITY_MODELS_PATH}/ckpts/AF2
RF3_DIR=${COMMUNITY_MODELS_PATH}/ckpts/RF3
RF3_CKPT_PATH=${RF3_DIR}/rf3_foundry_01_24_latest_remapped.ckpt

# ==============================================================================
# EXTERNAL TOOLS — Runtime-specific paths to tool executables
# ==============================================================================
# Python code reads the base names (FOLDSEEK_EXEC, SC_EXEC, etc.) via os.getenv().
# The base names default to UV paths. Change them to DOCKER_* if needed.
UV_VENV=${LOCAL_CODE_PATH}/.venv

# UV runtime tools (default for local development with .venv)
UV_FOLDSEEK_EXEC=${UV_VENV}/bin/foldseek
UV_RF3_EXEC_PATH=${UV_VENV}/bin/rf3
UV_SC_EXEC=${LOCAL_CODE_PATH}/env/docker/internal/sc
UV_MMSEQS_EXEC=${UV_VENV}/bin/mmseqs
UV_DSSP_EXEC=${LOCAL_CODE_PATH}/env/docker/internal/dssp
UV_TMOL_PATH=${UV_VENV}/lib/python3.12/site-packages/tmol

# Docker runtime tools (set in Dockerfile; also used for SLURM Pyxis)
DOCKER_FOLDSEEK_EXEC=/workspace/.venv/bin/foldseek
DOCKER_RF3_EXEC_PATH=/workspace/.venv/bin/rf3
DOCKER_SC_EXEC=/usr/local/bin/sc
DOCKER_MMSEQS_EXEC=/workspace/.venv/bin/mmseqs
DOCKER_DSSP_EXEC=/usr/local/bin/dssp
DOCKER_TMOL_PATH=/workspace/.venv/lib/python3.12/site-packages/tmol

# Active tool paths — Python reads these via os.getenv()
# Default to UV; change to ${DOCKER_*} to switch local runtime
FOLDSEEK_EXEC=${UV_FOLDSEEK_EXEC}
RF3_EXEC_PATH=${UV_RF3_EXEC_PATH}
SC_EXEC=${UV_SC_EXEC}
MMSEQS_EXEC=${UV_MMSEQS_EXEC}
DSSP_EXEC=${UV_DSSP_EXEC}
TMOL_PATH=${UV_TMOL_PATH}
DATA_PATH=${LOCAL_DATA_PATH}

# Active checkpoint path — YAML configs use ${oc.env:CKPT_PATH}
CKPT_PATH=${LOCAL_CHECKPOINT_PATH}

# ==============================================================================
# SLURM CLUSTER SETTINGS
# ==============================================================================

# Login node to cluster
CLUSTER_HOST="login-node.example.com"
# Data copier node
CLUSTER_HOST_DC="data-copier-node.example.com"
CLUSTER_SSH_KEY=

# SLURM settings
CLUSTER_ACCOUNT="slurm_user"
CLUSTER_PARTITION="gpus"
CLUSTER_RUNTIME=docker  # Options: docker, uv

# Paths on cluster
# Root path for all cluster runs
CLUSTER_ROOT_REMOTE=
# base path for data
CLUSTER_DATA_PATH="/path/to/data"
CLUSTER_CACHE_DIR=

# Shared model directories on cluster (optional).
# When set, community_models, params, LigandMPNN, ProteinMPNN are stored here
# once and mounted into each container run instead of being rsynced per-run.
CLUSTER_SHARED_MODELS_PATH=
# Shared community model checkpoints subdirectory on cluster (optional, skips rsyncing ckpts)
CLUSTER_COMMUNITY_MODELS_REMOTE=

# Docker runtime settings (CLUSTER_RUNTIME=docker, uses Pyxis/Enroot on SLURM)
# Tool paths are the DOCKER_* values above — no separate CLUSTER_DOCKER_* needed
CLUSTER_CONTAINER_IMAGE=${DOCKER_IMAGE}
CLUSTER_CONTAINER_WORKSPACE=/workspace/Proteina-Complexa
# Custom container mounts (comma-separated "host_path:container_path" pairs, leave empty for none)
CLUSTER_DOCKER_MOUNTS=

# UV runtime settings (CLUSTER_RUNTIME=uv)
CLUSTER_UV_VENV=

# Cluster UV tool paths (CLUSTER_RUNTIME=uv)
CLUSTER_UV_FOLDSEEK_EXEC=${CLUSTER_UV_VENV}/bin/foldseek
CLUSTER_UV_RF3_EXEC_PATH=${CLUSTER_UV_VENV}/bin/rf3
CLUSTER_UV_SC_EXEC=${CLUSTER_UV_VENV}/bin/sc
CLUSTER_UV_MMSEQS_EXEC=${CLUSTER_UV_VENV}/bin/mmseqs
CLUSTER_UV_DSSP_EXEC=${CLUSTER_UV_VENV}/bin/dssp