Merge pull request 'fix(queue-daemon): implement timeout handling for long-running tasks' (#228) from fix/issue-166 into main

This commit was merged in pull request #228.
This commit is contained in:
2026-04-08 04:51:54 +02:00

View File

@@ -41,6 +41,31 @@ check_task_completion() {
local session_id=$(python3 -c "import json; print(json.load(open('$item')).get('opencode_session_id', ''))" 2>/dev/null)
local issue_ref=$(python3 -c "import json; print(json.load(open('$item')).get('issue_ref', ''))" 2>/dev/null)
local pid=$(python3 -c "import json; print(json.load(open('$item')).get('pid', ''))" 2>/dev/null)
local notified_at=$(python3 -c "import json; print(json.load(open('$item')).get('notified_at', ''))" 2>/dev/null)
local timed_out=false
if [ -n "$notified_at" ]; then
local notified_epoch=$(date -d "$notified_at" +%s 2>/dev/null || echo "0")
local now_epoch=$(date +%s)
local hours_elapsed=$(( (now_epoch - notified_epoch) / 3600 ))
if [ "$hours_elapsed" -ge "${TASK_TIMEOUT_HOURS:-1}" ]; then
timed_out=true
log_warn "queue-daemon" "Task $queue_id ($issue_ref) timed out after ${hours_elapsed}h"
fi
fi
if [ "$timed_out" = true ]; then
if [ -n "$pid" ] && [ "$pid" != "None" ]; then
kill "$pid" 2>/dev/null || true
fi
if [ -n "$session_id" ]; then
opencode session stop "$session_id" 2>/dev/null || true
fi
update_queue_item_state "$queue_id" "error"
log_error "queue-daemon" "Task $queue_id ($issue_ref) marked error — timeout after ${hours_elapsed}h"
release_lock "$issue_ref"
return
fi
if [ -n "$pid" ] && [ "$pid" != "None" ]; then
if ! kill -0 "$pid" 2>/dev/null; then