fix: push a FAILED notification when a scheduled run dies without reporting

sync pushes its result only from the end of a run it finished, so a crash or an early exit sent nothing, while the providers that survived kept pushing OK. The systemd unit now runs scheduling/run-sync.sh, which keeps the per-provider loop and pushes a high-priority failure, with the exception class only, for any run that exited non-zero without the app's own report. Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01LbnmGHnFqDjyhPcCg1SEfF
2026-10-05 07:14:16 -04:00
parent 64068bb19b
commit 23c6e1f512
4 changed files with 111 additions and 11 deletions
@@ -0,0 +1,83 @@
+#!/usr/bin/env bash
+# Run `ai-chat-exporter sync` once per provider — the ExecStart of the systemd
+# unit that install-systemd-timer.sh writes.
+#
+#   ./scheduling/run-sync.sh claude-code codex
+#
+# Every provider is attempted even after one fails, and the exit code is
+# non-zero if any failed — one ExecStart per provider would stop at the first.
+#
+# The app pushes its own ntfy result, but only from the end of a run it
+# finished. A crash, a non-zero exit before the sync starts (the terms-of-service
+# gate, a cache error) or a launcher that can't build its venv sends nothing, and
+# because each provider pushes separately, the providers that did succeed still
+# send "OK" — so a broken one looks like a quiet day. This script pushes a FAILED
+# notification for any run that exited non-zero without the app having reported
+# it. (Its "Sync completed with failures" banner prints right after its push.)
+#
+# The push carries the provider, the exit code and, for a crash, the exception's
+# class name — never its message. Same counts-only rule as src/notify.py: on a
+# public ntfy topic anyone who guesses the name can read it, and exception text
+# can carry conversation titles. The full traceback is in the journal.
+
+set -uo pipefail
+
+REPO="$(cd -- "$(dirname -- "${BASH_SOURCE[0]}")/.." && pwd)"
+LAUNCHER="$REPO/ai-chat-exporter"
+
+# NTFY_* as the app resolves them: the environment wins, then .env.
+env_value() {
+    local name=$1 value=${!1:-}
+    if [ -z "$value" ] && [ -f "$REPO/.env" ]; then
+        value=$(sed -n "s/^[[:space:]]*$name[[:space:]]*=[[:space:]]*//p" "$REPO/.env" | tail -n 1)
+        value=${value%%[[:space:]]#*}
+        value=${value%"${value##*[![:space:]]}"}
+        value=${value#[\"\']}
+        value=${value%[\"\']}
+    fi
+    printf '%s' "$value"
+}
+
+push_failure() {
+    local body=$1 topic server token policy
+    topic=$(env_value NTFY_TOPIC)
+    policy=$(env_value NTFY_NOTIFY | tr '[:upper:]' '[:lower:]')
+    if [ -z "$topic" ] || [ "$policy" = "off" ]; then
+        return 0
+    fi
+    server=$(env_value NTFY_SERVER)
+    server=${server:-https://ntfy.sh}
+    token=$(env_value NTFY_TOKEN)
+
+    local args=(-fsS --max-time 15 -o /dev/null
+        -H "Title: AI archive FAILED - $(hostname -s)"
+        -H "Tags: rotating_light" -H "Priority: high"
+        --data-binary "$body")
+    [ -n "$token" ] && args+=(-H "Authorization: Bearer $token")
+    curl "${args[@]}" "${server%/}/$topic" \
+        || echo "run-sync: could not send the failure notification" >&2
+}
+
+[ $# -eq 0 ] && set -- all
+
+rc=0
+for provider in "$@"; do
+    out=$(mktemp)
+    "$LAUNCHER" sync --provider "$provider" --joplin-optional 2>&1 | tee "$out"
+    status=${PIPESTATUS[0]}
+    if [ "$status" -ne 0 ]; then
+        rc=1
+        if ! grep -q "Sync completed with failures" "$out"; then
+            crash=$(grep -oE '^[A-Za-z_][A-Za-z0-9_.]*(Error|Exception)\b' "$out" | tail -n 1)
+            if [ -n "$crash" ]; then
+                reason="crashed ($crash)"
+            else
+                reason="exited $status before reporting a result"
+            fi
+            push_failure "$provider: $reason
+journalctl --user -u ${AICHAT_SYNC_UNIT:-aichat-sync} -n 100"
+        fi
+    fi
+    rm -f "$out"
+done
+exit "$rc"