#!/usr/bin/env bash
# Weekly paper-library harvest.
#
# Deliberately thin: it calls the API and reports what came back. All the
# logic lives in the server, so this file never needs to change when the
# harvest does.
#
# The token lives in /etc/clawmates/library.token (root-only). It is a
# long-lived operator session; rotate by replacing the file.
set -uo pipefail

TOKEN_FILE=/etc/clawmates/library.token
[ -r "$TOKEN_FILE" ] || { echo "library: no token at $TOKEN_FILE"; exit 1; }
TOKEN=$(cat "$TOKEN_FILE")

RESP=$(docker run --rm --network clawmates_core curlimages/curl:latest \
  -s -m 1800 -X POST \
  -H "Authorization: Bearer $TOKEN" \
  -H "Content-Type: application/json" \
  -d '{"per_topic":5}' \
  http://clawmates_server_1:8080/api/library/runs)

echo "library: $RESP" | head -c 2000

# Report health explicitly. A run that shelved nothing is normal for a
# mature library; a run that ERRORED is not, and the two look identical
# if you only count papers.
echo "$RESP" | python3 -c '
import json, sys
try:
    d = json.load(sys.stdin)
except Exception as e:
    print("library: unreadable response (%s)" % e)
    sys.exit(1)
shelved = len(d.get("shelved", []))
healthy = d.get("healthy", False)
# Backslashes are avoided inside this program on purpose: it is embedded in a
# single-quoted shell string, and an escaped quote here does not survive the
# shell. The first version used one inside an f-string, crashed on every run,
# and systemd reported a FAILED unit for a harvest that had actually shelved
# 15 papers and pushed them. A false failure destroys trust in the signal as
# surely as a false success.
print("library: %d candidates, %d already held, %d shelved, healthy=%s, pushed=%s, branch=%s" % (
    d.get("candidates", 0), d.get("already_had", 0), shelved,
    healthy, d.get("pushed"), d.get("branch")))
for f in d.get("failed", []):
    print("library: FAILED %s" % f)
sys.exit(0 if healthy else 1)
'