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

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 04:51:54 +02:00 · 2026-04-08 02:39:40 +00:00 · 2026-04-08 04:22:00 +02:00 · 2026-04-08 02:17:27 +00:00 · 2026-04-08 01:04:43 +00:00 · 2026-04-07 12:53:35 +00:00
3 changed files with 28 additions and 1 deletions
--- a/.gitignore
+++ b/.gitignore
@@ -4,3 +4,4 @@ results/
 */results/
 *.pyc

+.kugetsu/
--- 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
+            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 "$pid" 2>/dev/null; then
--- a/skills/kugetsu/scripts/kugetsu-session.sh
+++ b/skills/kugetsu/scripts/kugetsu-session.sh
@@ -488,7 +488,6 @@ cmd_continue() {
    else
        message=$(build_dev_agent_message "$issue_ref" "$message")
    fi
-    fi
    
    local worktree_status=$(ensure_worktree "$issue_ref")
    if [ "$worktree_status" = "error" ]; then
@@ -502,6 +501,8 @@ cmd_continue() {
        exit 1
    fi
    
+    kugetsu_context_dump "$issue_ref" "$message" "$(issue_ref_to_branch_name "$issue_ref")"
+    
    local session_file=$(issue_ref_to_filename "$issue_ref")
    local session_path="$SESSIONS_DIR/$session_file"
    local opencode_session_id=$(python3 -c "import json; print(json.load(open('$session_path')).get('opencode_session_id', ''))" 2>/dev/null || echo "")
Author	SHA1	Message	Date
shoko	44c84280f8	Merge pull request 'fix(queue-daemon): implement timeout handling for long-running tasks' (#228 ) from fix/issue-166 into main	2026-04-08 04:51:54 +02:00
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
shoko	a65e9d6d28	Merge pull request 'feat(session): integrate kugetsu_context_dump into delegation flow' (#229 ) from fix/issue-212 into main	2026-04-08 04:22:00 +02:00
shokollm	c9eb8badea	feat(session): add kugetsu_context_dump call in cmd_continue Integrates the existing kugetsu_context_dump() function to capture the initial user prompt before forking the agent. Closes #212	2026-04-08 02:17:27 +00:00
shokollm	24dd91d0e1	fix: remove duplicate fi in cmd_continue	2026-04-08 01:04:43 +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