Compare commits

...

9 Commits

Author SHA1 Message Date
shokollm
3deae2dd81 fix(shell): address shellcheck warnings, standardize error handling, add retry logic
- Fix shellcheck SC2155 (separate variable assignment from declaration)
- Replace ! bool && bool pattern with [ "$bool" = true ] && [ "$bool2" = true ]
- Add retry logic for git clone with configurable attempts
- Add retry logic for opencode session fork
- Add NETWORK_RETRY_ATTEMPTS and NETWORK_RETRY_DELAY_SECONDS config vars
- Add retry_with_backoff helper function in kugetsu-config.sh
- Replace subshell cd with git -C for safer directory handling
2026-04-08 04:47:01 +00:00
41c56a859c Merge pull request 'refactor: use JSON file exchange instead of stdout parsing' (#234) from fix/issue-119 into main 2026-04-08 05:35:11 +02:00
shokollm
dd903bb8aa refactor: use JSON file exchange instead of stdout parsing
Replace fragile patterns like:
  python3 -c "import json; print(json.load(...))" | grep
  echo "$json" | python3 -c "import sys,json; ...
2026-04-08 03:11:18 +00:00
efb1e34a7b Merge pull request 'fix: add PR merge conflict check to dev agent workflow' (#233) from fix/issue-229-pr-conflict-check into main 2026-04-08 04:56:02 +02:00
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
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
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
6 changed files with 209 additions and 27 deletions

1
.gitignore vendored
View File

@@ -4,3 +4,4 @@ results/
*/results/ */results/
*.pyc *.pyc
.kugetsu/

View File

@@ -26,6 +26,9 @@ QUEUE_DAEMON_INTERVAL_MINUTES="${QUEUE_DAEMON_INTERVAL_MINUTES:-5}"
QUEUE_CLEANUP_AGE_DAYS="${QUEUE_CLEANUP_AGE_DAYS:-7}" QUEUE_CLEANUP_AGE_DAYS="${QUEUE_CLEANUP_AGE_DAYS:-7}"
TASK_TIMEOUT_HOURS="${TASK_TIMEOUT_HOURS:-1}" TASK_TIMEOUT_HOURS="${TASK_TIMEOUT_HOURS:-1}"
NETWORK_RETRY_ATTEMPTS="${NETWORK_RETRY_ATTEMPTS:-3}"
NETWORK_RETRY_DELAY_SECONDS="${NETWORK_RETRY_DELAY_SECONDS:-5}"
# Load user config overrides (~/.kugetsu/config) # Load user config overrides (~/.kugetsu/config)
if [ -f "$KUGETSU_DIR/config" ]; then if [ -f "$KUGETSU_DIR/config" ]; then
source "$KUGETSU_DIR/config" source "$KUGETSU_DIR/config"
@@ -87,3 +90,24 @@ set_debug_mode() {
echo "${filtered_args[@]}" echo "${filtered_args[@]}"
} }
retry_with_backoff() {
local max_attempts="${1:-$NETWORK_RETRY_ATTEMPTS}"
local delay_seconds="${2:-$NETWORK_RETRY_DELAY_SECONDS}"
local command="$3"
local remaining_attempts=$max_attempts
while [ $remaining_attempts -gt 0 ]; do
if eval "$command"; then
return 0
fi
remaining_attempts=$((remaining_attempts - 1))
if [ $remaining_attempts -gt 0 ]; then
log "warn" "retry_with_backoff" "Command failed, $remaining_attempts retries remaining. Waiting ${delay_seconds}s..."
sleep "$delay_seconds"
delay_seconds=$((delay_seconds * 2))
fi
done
log "error" "retry_with_backoff" "Command failed after $max_attempts attempts"
return 1
}

View File

@@ -139,6 +139,77 @@ validate_issue_ref() {
fi fi
} }
read_json_file() {
local file_path="$1"
if [ -f "$file_path" ]; then
cat "$file_path"
else
echo "{}"
fi
}
write_json_file() {
local file_path="$1"
local json_content="$2"
local temp_file="$file_path.tmp.$$"
printf '%s' "$json_content" > "$temp_file"
if ! python3 -c "import json; json.load(open('$temp_file'))" 2>/dev/null; then
echo "Error: write_json_file would create malformed JSON: $file_path" >&2
rm -f "$temp_file"
return 1
fi
mv "$temp_file" "$file_path"
}
get_json_value() {
local file_path="$1"
local key="$2"
local default="${3:-}"
if [ ! -f "$file_path" ]; then
echo "$default"
return
fi
python3 -c "import json; print(json.load(open('$file_path')).get('$key', '$default'))" 2>/dev/null || echo "$default"
}
set_json_value() {
local file_path="$1"
local key="$2"
local value="$3"
if [ ! -f "$file_path" ]; then
printf '{"%s": "%s"}\n' "$key" "$value" > "$file_path"
return
fi
python3 << PYEOF
import json
import sys
file_path = "$file_path"
key = "$key"
value = "$value"
try:
with open(file_path, 'r') as f:
data = json.load(f)
except:
data = {}
data[key] = value
with open(file_path, 'w') as f:
json.dump(data, f, indent=2)
print(f"Set $key = $value in $file_path")
PYEOF
}
update_session_pr_url() { update_session_pr_url() {
local issue_ref="$1" local issue_ref="$1"
local pr_url="$2" local pr_url="$2"

View File

@@ -34,6 +34,8 @@ release_lock() {
check_task_completion() { check_task_completion() {
local item="$1" local item="$1"
local queue_id=$(basename "$item" .json) local queue_id=$(basename "$item" .json)
local item_data=$(read_json_file "$item")
local state=$(python3 -c "import json; print(json.load(open('$item')).get('state', ''))" 2>/dev/null) local state=$(python3 -c "import json; print(json.load(open('$item')).get('state', ''))" 2>/dev/null)
[ "$state" = "notified" ] || return 0 [ "$state" = "notified" ] || return 0
@@ -41,6 +43,31 @@ check_task_completion() {
local session_id=$(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

@@ -13,7 +13,8 @@ count_active_dev_sessions() {
if [ -d "$SESSIONS_DIR" ]; then if [ -d "$SESSIONS_DIR" ]; then
for session_file in "$SESSIONS_DIR"/*.json; do for session_file in "$SESSIONS_DIR"/*.json; do
if [ -f "$session_file" ]; then if [ -f "$session_file" ]; then
local filename=$(basename "$session_file") local filename
filename=$(basename "$session_file")
if [ "$filename" != "base.json" ] && [ "$filename" != "pm-agent.json" ]; then if [ "$filename" != "base.json" ] && [ "$filename" != "pm-agent.json" ]; then
count=$((count + 1)) count=$((count + 1))
fi fi
@@ -239,23 +240,55 @@ create_session() {
return 1 return 1
fi fi
local before_json=$(opencode session list --format=json 2>/dev/null) local before_file
local before_set=$(echo "$before_json" | python3 -c "import sys,json; sessions=json.load(sys.stdin); print('|'.join(s['id'] for s in sessions))" 2>/dev/null || echo "|") before_file="$KUGETSU_DIR/sessions/before$$.json"
local after_file
after_file="$KUGETSU_DIR/sessions/after$$.json"
opencode run --fork --session "$base_session" "new session" >/dev/null 2>&1 opencode session list --format=json > "$before_file" 2>/dev/null || printf '{}' > "$before_file"
local fork_success=false
local attempt=0
local max_attempts="${NETWORK_RETRY_ATTEMPTS:-3}"
while [ $attempt -lt $max_attempts ] && [ "$fork_success" = false ]; do
attempt=$((attempt + 1))
if opencode run --fork --session "$base_session" "new session" >/dev/null 2>&1; then
fork_success=true
elif [ $attempt -lt $max_attempts ]; then
log "warn" "create_session" "Fork attempt $attempt failed, retrying..."
sleep "$((attempt * 2))"
fi
done
if [ "$fork_success" = false ]; then
log "error" "create_session" "Failed to fork session after $max_attempts attempts"
rm -f "$before_file" "$after_file"
return 1
fi
sleep 1 sleep 1
local after_json=$(opencode session list --format=json 2>/dev/null) opencode session list --format=json > "$after_file" 2>/dev/null || printf '{}' > "$after_file"
local after_sessions=$(echo "$after_json" | python3 -c "import sys,json; sessions=json.load(sys.stdin); [print(s['id']) for s in sessions]" 2>/dev/null || true)
local new_session_id="" local new_session_id
while IFS= read -r sess; do new_session_id=$(python3 << PYEOF
if [[ -n "$sess" ]] && [[ ! "$before_set" =~ \|${sess}\| ]]; then import json
new_session_id="$sess"
with open("$before_file", 'r') as f:
before = json.load(f)
with open("$after_file", 'r') as f:
after = json.load(f)
before_ids = set(s['id'] for s in before)
for s in after:
if s['id'] not in before_ids:
print(s['id'])
break break
fi PYEOF
done <<< "$after_sessions" )
rm -f "$before_file" "$after_file"
echo "$new_session_id" echo "$new_session_id"
} }
@@ -378,20 +411,20 @@ ensure_session() {
session_exists=true session_exists=true
fi fi
if $worktree_exists && $session_exists; then if [ "$worktree_exists" = true ] && [ "$session_exists" = true ]; then
log "info" "ensure_session" "Session already exists for $issue_ref" log "info" "ensure_session" "Session already exists for $issue_ref"
echo "continued" echo "continued"
return 0 return 0
fi fi
if ! $worktree_exists && $session_exists; then if [ "$worktree_exists" = false ] && [ "$session_exists" = true ]; then
log "warn" "ensure_session" "Session exists but worktree is missing. Removing stale session..." log "warn" "ensure_session" "Session exists but worktree is missing. Removing stale session..."
rm -f "$session_path" rm -f "$session_path"
remove_issue_from_index "$issue_ref" remove_issue_from_index "$issue_ref"
session_exists=false session_exists=false
fi fi
if ! $worktree_exists; then if [ "$worktree_exists" = false ]; then
local wt_status=$(ensure_worktree "$issue_ref") local wt_status=$(ensure_worktree "$issue_ref")
if [ "$wt_status" != "created" ] && [ "$wt_status" != "existed" ]; then if [ "$wt_status" != "created" ] && [ "$wt_status" != "existed" ]; then
log "error" "ensure_session" "Failed to ensure worktree for $issue_ref" log "error" "ensure_session" "Failed to ensure worktree for $issue_ref"
@@ -489,6 +522,8 @@ cmd_continue() {
exit 1 exit 1
fi fi
kugetsu_context_dump "$issue_ref" "$message" "$(issue_ref_to_branch_name "$issue_ref")"
local session_file=$(issue_ref_to_filename "$issue_ref") local session_file=$(issue_ref_to_filename "$issue_ref")
local session_path="$SESSIONS_DIR/$session_file" local session_path="$SESSIONS_DIR/$session_file"
local opencode_session_id=$(python3 -c "import json; print(json.load(open('$session_path')).get('opencode_session_id', ''))" 2>/dev/null || echo "") local opencode_session_id=$(python3 -c "import json; print(json.load(open('$session_path')).get('opencode_session_id', ''))" 2>/dev/null || echo "")

View File

@@ -76,7 +76,8 @@ create_worktree() {
exit 1 exit 1
fi fi
local worktree_parent_dir=$(dirname "$worktree_path") local worktree_parent_dir
worktree_parent_dir=$(dirname "$worktree_path")
mkdir -p "$worktree_parent_dir" mkdir -p "$worktree_parent_dir"
if worktree_exists "$issue_ref" "$parent_dir"; then if worktree_exists "$issue_ref" "$parent_dir"; then
@@ -85,15 +86,36 @@ create_worktree() {
fi fi
echo "Creating worktree at '$worktree_path'..." echo "Creating worktree at '$worktree_path'..."
git clone "$repo_url" "$worktree_path" 2>/dev/null || {
echo "Error: Failed to clone repository" >&2 local clone_success=false
local attempt=0
local max_attempts="${NETWORK_RETRY_ATTEMPTS:-3}"
while [ $attempt -lt $max_attempts ] && [ "$clone_success" = false ]; do
attempt=$((attempt + 1))
if [ $attempt -gt 1 ]; then
echo "Clone attempt $attempt of $max_attempts..."
sleep "$((attempt * 2))"
fi
if git clone "$repo_url" "$worktree_path" 2>/dev/null; then
clone_success=true
fi
done
if [ "$clone_success" = false ]; then
echo "Error: Failed to clone repository after $max_attempts attempts" >&2
exit 1 exit 1
} fi
echo "Creating branch '$branch_name'..." echo "Creating branch '$branch_name'..."
(cd "$worktree_path" && git checkout -b "$branch_name" origin/main 2>/dev/null || git checkout -b "$branch_name" main 2>/dev/null) || { if git -C "$worktree_path" checkout -b "$branch_name" origin/main 2>/dev/null; then
:
elif git -C "$worktree_path" checkout -b "$branch_name" main 2>/dev/null; then
:
else
echo "Warning: Could not checkout branch (may need to run from within worktree after session)" >&2 echo "Warning: Could not checkout branch (may need to run from within worktree after session)" >&2
} fi
echo "Worktree created at: $worktree_path" echo "Worktree created at: $worktree_path"
} }
@@ -145,15 +167,17 @@ check_pr_status() {
token="${GITEA_TOKEN:-}" token="${GITEA_TOKEN:-}"
fi fi
local response local response_file="$KUGETSU_DIR/.pr_status_response_$$.json"
if [ -n "$token" ]; then if [ -n "$token" ]; then
response=$(curl -s -H "Authorization: token $token" "$api_url" 2>/dev/null || echo "{}") curl -s -H "Authorization: token $token" "$api_url" > "$response_file" 2>/dev/null || printf '{}' > "$response_file"
else else
response=$(curl -s "$api_url" 2>/dev/null || echo "{}") curl -s "$api_url" > "$response_file" 2>/dev/null || printf '{}' > "$response_file"
fi fi
local state=$(echo "$response" | python3 -c "import json, sys; d=json.load(sys.stdin); print(d.get('state', 'unknown'))" 2>/dev/null || echo "unknown") local state=$(python3 -c "import json; print(json.load(open('$response_file')).get('state', 'unknown'))" 2>/dev/null || echo "unknown")
local merged=$(echo "$response" | python3 -c "import json, sys; d=json.load(sys.stdin); print('true' if d.get('merged', False) else 'false')" 2>/dev/null || echo "false") local merged=$(python3 -c "import json; print('true' if json.load(open('$response_file')).get('merged', False) else 'false')" 2>/dev/null || echo "false")
rm -f "$response_file"
if [ "$merged" = "true" ]; then if [ "$merged" = "true" ]; then
echo "merged" echo "merged"