# Spark Executor MCP — environment template
# Copy to .env and edit. .env is gitignored.
#
# All env vars in this file are read by common/config.py (the single source
# of truth for application config). The only exception is the GUNICORN_*
# block at the bottom — those are read by gunicorn.conf.py.

# --- Data persistence ---
# Base directory for connections.json, pending_jobs.json, loguru logs/,
# and (by default) jobs/. Mount this from the host in production so
# state survives container restarts. The default ./data/ is fine in dev.
#
# SPARK_EXECUTOR_DATA_DIR=./data
# SPARK_EXECUTOR_DATA_DIR=/var/lib/spark-executor/data

# --- Job files (LLM-generated PySpark) ---
# Where generate_job_file writes PySpark source. Defaults to
# <SPARK_EXECUTOR_DATA_DIR>/jobs. Override to point at a larger disk
# (e.g. /var/spark-jobs) when the data volume is small.
#
# SPARK_EXECUTOR_JOBS_DIR=./data/jobs
# SPARK_EXECUTOR_JOBS_DIR=/var/spark-jobs

# --- YARN REST client ---
# Fallback URL when a Job's yarn_rm_url (snapshotted from its Connection
# at prepare_submit_job time) is unset. Set this OR per-Connection via
# save_connection.
#
# Examples:
#   YARN_RESOURCE_MANAGER_URL=http://yarn-rm.prod.internal:8088
#   YARN_RESOURCE_MANAGER_URL=https://yarn-rm.staging.example.com:8088
YARN_RESOURCE_MANAGER_URL=

# --- Loguru file sinks ---
# Base directory for loguru output. Subdirs debug/ and info/ are created
# automatically; rotated daily, gzipped, kept 30 days. Defaults to
# <SPARK_EXECUTOR_DATA_DIR>/logs. Override to point at a dedicated log
# volume (e.g. /var/log/spark-executor) or a network mount.
#
# SPARK_EXECUTOR_LOG_DIR=./data/logs
# SPARK_EXECUTOR_LOG_DIR=/var/log/spark-executor

# --- Loguru verbosity ---
# For stderr + the info-level file sink. The debug-level file sink
# always captures full DEBUG (audit trail regardless of level).
#   DEBUG - default; full verbosity
#   INFO  - quieter; recommended for production
#
# SPARK_EXECUTOR_LOG_LEVEL=DEBUG
# SPARK_EXECUTOR_LOG_LEVEL=INFO

# --- Optional: JVM flags forwarded to spark-submit ---
# Useful for proxies, custom truststores, or driver memory caps.
# SPARK_SUBMIT_OPTS=-Dhttps.proxyHost=proxy.corp -Dhttps.proxyPort=3128

# --- Java + Spark install paths ---
# Where the openjdk-17-jre-headless JDK lives, and where the Spark
# distribution was extracted during the image build. Defaults match the
# Dockerfile's ENTRYPOINT script. Override if you mount a different
# Java (e.g. /usr/lib/jvm/java-17-openjdk-arm64 on some ARM hosts) or
# a pre-installed Spark from a host volume (e.g. /opt/spark-3.5.1-bin-hadoop3).
#
# The container's docker-entrypoint.sh re-derives PATH from these values
# at every start, so overriding them here actually changes which `java`
# and `spark-submit` binaries the gunicorn process picks up.
#
# JAVA_HOME=/usr/lib/jvm/java-17-openjdk-amd64
# SPARK_HOME=/opt/spark

# --- Gunicorn process model (see gunicorn.conf.py; NOT read by common/config.py) ---
# Defaults shown. These are read by gunicorn directly, not by the app.
# GUNICORN_WORKERS=2
# GUNICORN_THREADS=1
# GUNICORN_TIMEOUT=120         # generous; yarn logs can be slow
# GUNICORN_GRACEFUL_TIMEOUT=30
# GUNICORN_KEEPALIVE=5
# GUNICORN_BIND=0.0.0.0:8000
# GUNICORN_LOGLEVEL=info