From 51ec8443656046cd0cabc247191de3b870fd8522 Mon Sep 17 00:00:00 2001
From: shokollm <270575765+shokollm@users.noreply.github.com>
Date: Tue, 7 Apr 2026 12:53:35 +0000
Subject: [PATCH] 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
---
 .../kugetsu/scripts/kugetsu-queue-daemon.sh   | 25 +++++++++++++++++++
 1 file changed, 25 insertions(+)

diff --git a/skills/kugetsu/scripts/kugetsu-queue-daemon.sh b/skills/kugetsu/scripts/kugetsu-queue-daemon.sh
index a36f1cb..34620d7 100644
--- a/skills/kugetsu/scripts/kugetsu-queue-daemon.sh
+++ b/skills/kugetsu/scripts/kugetsu-queue-daemon.sh
@@ -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
+            echo "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"
+        echo "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