Compare commits

..

2 Commits

Author SHA1 Message Date
shokollm
fa8b8467ee fix(queue-daemon): use kugetsu-log for timeout messages
Use log_warn and log_error instead of echo for unified log formatting.
2026-04-08 02:39:40 +00:00
shokollm
51ec844365 fix(queue-daemon): implement timeout handling for long-running tasks
Check notified_at timestamp in check_task_completion() and mark tasks
as error if they exceed TASK_TIMEOUT_HOURS (defaults to 1 hour).

When timeout is detected:
- Kill the task process (PID) if running
- Stop the opencode session if exists
- Mark queue item as error state

Fixes #166
2026-04-07 12:53:35 +00:00
2 changed files with 25 additions and 4 deletions

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 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 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 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 [ -n "$pid" ] && [ "$pid" != "None" ]; then
if ! kill -0 "$pid" 2>/dev/null; then if ! kill -0 "$pid" 2>/dev/null; then

View File

@@ -405,8 +405,6 @@ cmd_start() {
local dev_message=$(build_dev_agent_message "$issue_ref" "$message") local dev_message=$(build_dev_agent_message "$issue_ref" "$message")
kugetsu_context_dump "$issue_ref" "$dev_message" "$(issue_ref_to_branch_name "$issue_ref")"
load_agent_env "dev" load_agent_env "dev"
cd "$worktree_path" cd "$worktree_path"
@@ -479,8 +477,6 @@ cmd_continue() {
message=$(build_dev_agent_message "$issue_ref" "") message=$(build_dev_agent_message "$issue_ref" "")
fi fi
kugetsu_context_dump "$issue_ref" "$message" "$(issue_ref_to_branch_name "$issue_ref")"
cd "$worktree_path" cd "$worktree_path"
local sanitized_id=$(echo "$opencode_session_id" | sed 's/[^a-zA-Z0-9_-]/_/g') local sanitized_id=$(echo "$opencode_session_id" | sed 's/[^a-zA-Z0-9_-]/_/g')
mkdir -p "$worktree_path/.kugetsu" mkdir -p "$worktree_path/.kugetsu"