18ee24818b
Sync template from 29ac25b → v0.9.0 (29 template commits). Due to template's _subdirectory migration, new files were manually rendered rather than auto-merged by copier. New files: - .claude/CLAUDE.md + coding_philosophy.md (agent instructions) - extract utils.py: SQLite state tracking for extraction runs - extract/transform READMEs: architecture & pattern documentation - infra/supervisor: systemd service + orchestration script - Per-layer model READMEs (raw, staging, foundation, serving) Also fixes copier-answers.yml (adds 4 feature toggles, removes stale payment_provider key) and scopes CLAUDE.md gitignore to root only. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
48 lines
1.6 KiB
Bash
48 lines
1.6 KiB
Bash
#!/bin/sh
|
|
# Padelnomics Supervisor — continuous pipeline orchestration.
|
|
# Inspired by TigerBeetle's CFO supervisor: simple, resilient, easy to understand.
|
|
# https://github.com/tigerbeetle/tigerbeetle/blob/main/src/scripts/cfo_supervisor.sh
|
|
#
|
|
# Environment variables (set in systemd EnvironmentFile or .env):
|
|
# LANDING_DIR — local path for extracted landing data
|
|
# DUCKDB_PATH — path to DuckDB lakehouse file
|
|
# ALERT_WEBHOOK_URL — optional ntfy.sh / Slack / Telegram webhook for failures
|
|
|
|
set -eu
|
|
|
|
readonly REPO_DIR="/opt/padelnomics"
|
|
|
|
while true
|
|
do
|
|
(
|
|
if ! [ -d "$REPO_DIR/.git" ]; then
|
|
echo "Repository not found at $REPO_DIR — bootstrap required!"
|
|
exit 1
|
|
fi
|
|
|
|
cd "$REPO_DIR"
|
|
|
|
# Pull latest code
|
|
git fetch origin master
|
|
git switch --discard-changes --detach origin/master
|
|
uv sync
|
|
|
|
# Extract
|
|
LANDING_DIR="${LANDING_DIR:-/data/padelnomics/landing}" \
|
|
DUCKDB_PATH="${DUCKDB_PATH:-/data/padelnomics/lakehouse.duckdb}" \
|
|
uv run --package padelnomics_extract extract
|
|
|
|
# Transform
|
|
LANDING_DIR="${LANDING_DIR:-/data/padelnomics/landing}" \
|
|
DUCKDB_PATH="${DUCKDB_PATH:-/data/padelnomics/lakehouse.duckdb}" \
|
|
uv run --package sqlmesh_padelnomics sqlmesh run --select-model "serving.*"
|
|
|
|
) || {
|
|
if [ -n "${ALERT_WEBHOOK_URL:-}" ]; then
|
|
curl -s -d "Padelnomics pipeline failed at $(date)" \
|
|
"$ALERT_WEBHOOK_URL" 2>/dev/null || true
|
|
fi
|
|
sleep 600 # back off 10 min on failure
|
|
}
|
|
done
|