Compare commits

..

12 Commits

Author SHA1 Message Date
shokollm
92f8369d6f fix CONTRIBUTING.md: branch naming should include issue number
Address han's review feedback:
- Changed feat/feature-name to feat/issue-N-feature-name
- Consistent with fix/issue-N-name format
2026-04-05 10:26:59 +00:00
shokollm
16e417c88e docs: add versioning policy, changelog, and update contributing guide
- Add VERSIONING.md documenting 0.1.x/0.2.x branch strategy
- Add docs/CHANGELOG.md with release notes for v0.1.0-v0.2.1
- Update CONTRIBUTING.md: fix master->main, add develop branch
- Closes #120
2026-04-05 09:38:25 +00:00
da0fa302de Merge pull request 'fix(kugetsu): prevent excess agent spawning with flock + sequential processing' (#147) from fix/issue-queue-daemon-excess-agents into main 2026-04-05 10:49:24 +02:00
shokollm
54aa6419eb fix(kugetsu): prevent excess agent spawning with flock + sequential processing
- count_active_dev_sessions() now excludes pm-agent.json from count
- process_queue() now calls kugetsu start directly (not opencode run)
- process_queue() uses dynamic batch size = available_slots
- process_queue() has retry logic (max 3 attempts) on failure
- cmd_start() now uses flock around critical section
- Added notification types: task_queued, task_dequeued, task_started, task_completed, task_error
- Removed QUEUE_DAEMON_BATCH_SIZE config (no longer needed)

Fixes issue #146
2026-04-05 08:44:45 +00:00
98a31070a7 Merge pull request '[FIX] process_queue: add missing closing parentheses' (#143) from fix/issue-142-process-queue-missing-parens into main 2026-04-05 08:56:59 +02:00
26346235c9 fix: add missing closing parenthesis in process_queue Python extraction
Fixes #142 - process_queue silently skips all queue items because
issue_ref and message Python extraction commands were missing a closing
parenthesis. The error was silently swallowed by 2>/dev/null causing
both variables to be empty, so every queue item was skipped.
2026-04-05 06:51:57 +00:00
2212fabf22 Merge pull request 'feat(timeout): add agent timeout handling' (#141) from feat/agent-timeout into main 2026-04-05 06:59:05 +02:00
shokollm
0fa778353b feat(timeout): add agent timeout handling
Implements #137 - Agent timeout handling.

Changes:
- Add TASK_TIMEOUT_HOURS config (default: 1 hour)
- Update queue item to track opencode_session_id and pid
- Add check_task_timeouts() function that:
  - Checks notified tasks against timeout threshold
  - Kills process if exceeded
  - Marks session as 'timeout' state
- Integrate timeout check into queue daemon loop

Timeout behavior:
- Task is marked 'notified' when PM receives it
- If not completed within TASK_TIMEOUT_HOURS, task is killed
- Queue item marked 'error', session marked 'timeout'
2026-04-05 04:53:27 +00:00
151efadca3 Merge pull request 'feat(queue): add queue system with background daemon' (#140) from feat/queue-daemon into main 2026-04-05 06:49:13 +02:00
shokollm
379d53cedc docs: update SKILL.md with queue system documentation
- Update kugetsu delegate section to explain queue-based processing
- Add queue-daemon command documentation
- Update queue command with proper list/stats/clear/enqueue
- Add queue-related config options
- Update directory structure to include queue/
- Update workflow example with queue daemon setup
2026-04-05 04:45:56 +00:00
shokollm
043542344a feat(queue): add queue system with background daemon
Implements #134 - Queue system with background daemon.

## Changes

### Configuration
- QUEUE_DIR, QUEUE_ITEMS_DIR for queue storage
- QUEUE_DAEMON_PID_FILE, LOCK_FILE, LOG_FILE for daemon management
- QUEUE_DAEMON_INTERVAL_MINUTES (default: 5)
- QUEUE_DAEMON_BATCH_SIZE (default: 2)
- QUEUE_CLEANUP_AGE_DAYS (default: 7)

### Queue System
- File-based queue at ~/.kugetsu/queue/items/
- One JSON file per queue item
- States: pending, notified, completed, error

### New Commands
- kugetsu queue [list|stats|clear] - View queue status
- kugetsu queue enqueue <issue-ref> <message> - Manually enqueue
- kugetsu queue-daemon [start|stop|restart|status|logs] - Daemon management

### Behavior Change
- kugetsu delegate now always enqueues (fire-and-forget)
- Queue daemon polls queue and invokes PM when slots available

### Queue Item Format
```json
{
  "id": "q_xxx",
  "issue_ref": "github.com/user/repo#123",
  "message": "task description",
  "state": "pending",
  "pending_since": "...",
  "notified_at": null,
  "completed_at": null,
  "error": null
}
```

Closes #134
2026-04-05 04:28:41 +00:00
e763ceb0ad Merge pull request 'feat(context): add context dump/load for session isolation' (#139) from feat/context-dump-load into main 2026-04-05 06:23:40 +02:00
6 changed files with 920 additions and 169 deletions

View File

@@ -0,0 +1,67 @@
# Fix: Queue daemon spawning excess agents due to race condition
## Problem
When enqueueing multiple tasks (e.g., 6 tasks), the queue daemon was spawning many more subagents than expected, eventually exhausting container memory.
**Root Cause:** The combination of:
1. `process_queue()` calling `opencode run` directly instead of `kugetsu start`, bypassing all concurrency logic
2. `count_active_dev_sessions()` counting `pm-agent.json` toward `MAX_CONCURRENT_AGENTS`, reducing effective dev agent slots
3. No atomic locking around session count check + session file creation (TOCTOU race condition)
4. Background spawning of multiple concurrent processes in `process_queue()`
**Expected behavior:** With `MAX_CONCURRENT_AGENTS=3` and 6 tasks:
- Tasks should be processed sequentially via `kugetsu start`
- Only 3 dev agents should run at a time
- Tasks should queue and wait for slots to free up
## Solution
### 1. `count_active_dev_sessions()` - Exclude pm-agent
Only count actual dev agent session files (exclude `pm-agent.json`).
### 2. `process_queue()` - Call `kugetsu start` directly + retry logic
- Call `kugetsu start` directly (foreground, sequential) instead of spawning `opencode run` background process
- Dynamic batch size = available slots (removes need for `QUEUE_DAEMON_BATCH_SIZE`)
- Retry logic (max 3 attempts) on failure
- On failure: cleanup worktree/session and revert to `pending` state
- Save `fork_pid` to queue item for timeout handling
### 3. `cmd_start()` - Add flock
- Add flock around critical section (count check + fork)
- Track `fork_pid` for queue item timeout handling
### 4. Notification System
New notification types:
| Event | Type |
|-------|------|
| Task enqueued | `task_queued` |
| Task dequeued | `task_dequeued` |
| Task started | `task_started` |
| Task completed | `task_completed` |
| Task error | `task_error` |
### 5. Config
- Remove `QUEUE_DAEMON_BATCH_SIZE` (no longer needed - batch size is now dynamic)
## Notification Flow
| Event | Location | Type |
|-------|----------|------|
| Task enqueued | `enqueue_task()` | `task_queued` |
| Task dequeued | `process_queue()` after state change to `notified` | `task_dequeued` |
| Task started | `cmd_start()` after session file created | `task_started` |
| Task completed | `update_queue_item_state()` | `task_completed` |
| Task error | `update_queue_item_state()` | `task_error` |
## Out of Scope
- Re-check loop in cmd_start (checking if session DB is reliable) - deferred to separate research issue
- Buffer mechanism for excess forking (safety failsafe only)
## Status
- [x] Issue created
- [x] Implementation
- [x] PR created (#147)
- [ ] Merged

View File

@@ -2,10 +2,10 @@
## Workflow
1. Create a branch for your work: `git checkout -b fix/issue-N-name` or `git checkout -b docs/topic-name`
1. Create a branch for your work: `git checkout -b fix/issue-N-name` or `git checkout -b feat/issue-N-feature-name`
2. Make changes and commit with clear messages
3. Open a Pull Request for review
4. Do not merge directly to `master` for reviewable changes
4. Do not merge directly to `main` or `develop` for reviewable changes
5. After approval, squash and merge
## Guidelines
@@ -14,10 +14,53 @@
- Keep PRs focused and reasonably sized
- Document any non-obvious decisions
- Test changes before submitting
- See [VERSIONING.md](VERSIONING.md) for backport compatibility rules
## Branches
- `master` — stable, reviewed content only
### Primary Branches
- `main` — stable 0.1.x releases, production-ready code
- `develop` — experimental 0.2.x work, next major version
### Feature Branches
- `fix/*` — bug fixes
- `feat/*` — new features
- `docs/*` — documentation updates
- `research/*`new research notes
- `refactor/*`code refactoring (no behavior change)
## Branch Model
```
main (0.1.x stable)
└── v0.1.0, v0.1.1, v0.1.2, ...
develop (0.2.x experimental)
└── (next major version work)
```
### Which Branch to Target?
| Change Type | Target Branch | Backport? |
|-------------|---------------|-----------|
| Bug fix | `main` | N/A |
| Documentation | `main` | N/A |
| New feature (backport-compatible) | `main` | Can cherry-pick to `develop` |
| Experimental feature | `develop` | No |
| Breaking change | `develop` | No |
## Backport Compatibility
Before merging, consider if your change is backport-compatible:
- **YES**: Bug fixes, docs, adding new optional inputs
- **NO**: Changing behavior, changing defaults, removing features
See [VERSIONING.md](VERSIONING.md) for full policy.
## Release Process
1. Bug fixes and docs → directly to `main`
2. New features → `develop` or feature branches → `develop`
3. When `develop` is stable enough → merge to `main` for release

71
VERSIONING.md Normal file
View File

@@ -0,0 +1,71 @@
# Versioning Policy
## Branch Strategy
Kugetsu uses a dual-branch model:
| Branch | Purpose | Version | Stability |
|--------|---------|---------|-----------|
| `main` | Stable releases | 0.1.x | Production-ready |
| `develop` | Experimental work | 0.2.x | Active development |
### Branch Definitions
- **`main`**: Contains the latest stable 0.1.x releases. All changes here should be production-ready and backport-compatible when possible.
- **`develop`**: Contains work for the next major version (0.2.x). This branch may contain experimental features that could change or be removed.
## Version Format
Versions follow [Semantic Versioning](https://semver.org/):
```
MAJOR.MINOR.PATCH
```
- **MAJOR**: Incompatible API/behavior changes
- **MINOR**: New functionality (backward-compatible)
- **PATCH**: Bug fixes (backward-compatible)
## Backport Compatibility
### Backport-Compatible Changes (0.1.x)
- Bug fixes
- Documentation updates
- Performance improvements
- Adding new inputs/options (must have sensible defaults)
- Changes that only affect 0.2.x-specific features
### NOT Backport-Compatible
- Removing or renaming existing options
- Changing default values of existing options
- Changing behavior of existing commands
- Introducing breaking changes to the API/shell interface
## Deprecation Policy
When introducing breaking changes:
1. **Deprecate in minor X**: Add warning messages, document the change
2. **Remove in major X+1**: The breaking change is removed in the next major version
Example:
- Option `--old-flag` deprecated in v0.1.5
- Option `--old-flag` removed in v1.0.0 (not v0.2.0)
## What Constitutes a Version Bump
| Change Type | Version Bump |
|-------------|--------------|
| Add new command/option | MINOR |
| Bug fix | PATCH |
| Change default value | MINOR (may warrant PATCH) |
| Add new required input | MAJOR |
| Remove deprecated feature | MAJOR |
| Change behavior of existing command | MINOR (needs deprecation first) |
## Release Process
1. Changes are developed on feature branches
2. PRs are opened against `main` for 0.1.x changes, or `develop` for 0.2.x
3. After review and approval, changes are squash-merged
4. Releases are tagged from `main` after significant changes

111
docs/CHANGELOG.md Normal file
View File

@@ -0,0 +1,111 @@
# Changelog
All notable changes to kugetsu are documented here.
The format is based on [Keep a Changelog](https://keepachangelog.com/en/1.0.0/).
## [Unreleased]
## [v0.2.1] - 2026-04-03
### Fixed
- Prevent excess agent spawning with flock + sequential processing
## [v0.2.0] - 2026-03-30
### Added
- Queue system with background daemon
- Agent timeout handling
- Context dump/load for session isolation
- PR tracking and safe destroy
## [v0.1.13] - 2026-03-29
### Fixed
- Add missing closing parenthesis in process_queue Python extraction
## [v0.1.12] - 2026-03-25
### Added
- Post-comment helper for PM agent
## [v0.1.11] - 2026-03-20
### Fixed
- Wrap cmd_continue in subshell with cd for correct worktree dir
## [v0.1.10] - 2026-03-15
### Fixed
- destroy --base now also deletes PM agent session
## [v0.1.9] - 2026-03-10
### Added
- init creates base session in ~/.kugetsu-worktrees
- Adds context to forked sessions
- Clears logs on init
## [v0.1.8] - 2026-03-05
### Fixed
- destroy --base and --pm-agent actually delete opencode sessions
## [v0.1.7] - 2026-02-28
### Fixed
- Warn if init run from non-empty directory
## [v0.1.6] - 2026-02-20
### Fixed
- Detect session via DB query instead of opencode session list
## [v0.1.5] - 2026-02-15
### Fixed
- Update forked session permissions after detection
## [v0.1.4] - 2026-02-10
### Fixed
- Call fix_session_permissions before forking
## [v0.1.3] - 2026-02-05
### Fixed
- Session detection ordering bug and debugging
## [v0.1.2] - 2026-01-28
### Fixed
- Improve session detection in cmd_start with retry logic and logging
## [v0.1.1] - 2026-01-20
### Fixed
- Use cd + worktree inside parent dir instead of --dir flag
## [v0.1.0] - 2026-01-15
### Added
- KUGETSU_VERBOSITY for PM agent output control
- Initial documented release
[Unreleased]: https://git.fbrns.co/shoko/kugetsu/compare/v0.2.1...HEAD
[v0.2.1]: https://git.fbrns.co/shoko/kugetsu/compare/v0.2.0...v0.2.1
[v0.2.0]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.13...v0.2.0
[v0.1.13]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.12...v0.1.13
[v0.1.12]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.11...v0.1.12
[v0.1.11]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.10...v0.1.11
[v0.1.10]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.9...v0.1.10
[v0.1.9]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.8...v0.1.9
[v0.1.8]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.7...v0.1.8
[v0.1.7]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.6...v0.1.7
[v0.1.6]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.5...v0.1.6
[v0.1.5]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.4...v0.1.5
[v0.1.4]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.3...v0.1.4
[v0.1.3]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.2...v0.1.3
[v0.1.2]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.1...v0.1.2
[v0.1.1]: https://git.fbrns.co/shoko/kugetsu/compare/v0.1.0...v0.1.1
[v0.1.0]: https://git.fbrns.co/shoko/kugetsu/releases/tag/v0.1.0

View File

@@ -49,6 +49,8 @@ A default config file is created during `kugetsu init` with commented examples:
| `MAX_CONCURRENT_AGENTS` | 3 | Maximum number of concurrent dev agents |
| `KUGETSU_TEMP_DIR` | `~/.local/share/opencode/tool-output` | Temp directory for subagent tool output (useful in headless environments where /tmp is restricted) |
| `KUGETSU_VERBOSITY` | `default` | PM agent verbosity level: `verbose`, `default`, or `quiet` |
| `QUEUE_DAEMON_INTERVAL_MINUTES` | 5 | How often daemon polls queue (in minutes) |
| `QUEUE_CLEANUP_AGE_DAYS` | 7 | Auto-cleanup completed/error items older than N days |
### Environment Variables for Agents
@@ -111,6 +113,10 @@ Each issue session gets its own git worktree to prevent conflicts:
├── worktrees/
│ ├── github.com-shoko-kugetsu-14/ # Isolated workdir for issue #14
│ └── github.com-shoko-kugetsu-15/ # Isolated workdir for issue #15
├── queue/
│ ├── items/ # Queue item JSON files
│ ├── daemon.pid # Daemon process ID
│ └── daemon.log # Daemon log output
└── index.json # Maps session IDs and issue refs to session files
```
@@ -258,16 +264,17 @@ kugetsu destroy --base -y
### kugetsu delegate `<message>`
Send a message to the PM agent for task coordination (fire-and-forget):
Send a message to the PM agent for task coordination via queue:
```bash
kugetsu delegate "work on issue #14"
kugetsu delegate "review PR #92"
```
- Non-blocking: returns immediately, runs in background
- PM agent processes the message asynchronously
- Uses `KUGETSU_VERBOSITY` env var to control PM agent output verbosity
- Log output stored in `~/.kugetsu/logs/delegate-<timestamp>.log`
- **Always enqueues** (fire-and-forget): returns immediately
- Queue daemon polls queue and invokes PM when slots available
- Tasks are processed FIFO (first-in-first-out)
- Use `kugetsu queue list` to see pending tasks
- Use `kugetsu queue-daemon logs` to debug queue processing
### kugetsu logs [n]
@@ -328,35 +335,79 @@ kugetsu server default github # Set default server
kugetsu server get github # Get server URL
```
### kugetsu queue <list|enqueue|dequeue|clear>
### kugetsu queue <list|stats|clear>
Manage task queue for autonomous PM operation:
```bash
kugetsu queue list # Show queued tasks
kugetsu queue enqueue "task" # Add task to queue
kugetsu queue dequeue # Remove next task from queue
kugetsu queue clear # Clear all queued tasks
kugetsu queue list # Show queued tasks with status
kugetsu queue stats # Show queue statistics (total, pending, notified, completed, error)
kugetsu queue clear # Clean up old completed/error items
kugetsu queue enqueue <issue-ref> <message> # Manually enqueue a task
```
- Queue stored in `~/.kugetsu/queue.json`
**Queue Item States:**
- `pending` - Waiting in queue, daemon can pick up
- `notified` - PM agent has picked up the task
- `completed` - Dev agent finished, PR created
- `error` - Timeout or failure
### kugetsu queue-daemon <start|stop|restart|status|logs>
Manage the queue daemon background process:
```bash
kugetsu queue-daemon start # Start daemon in background
kugetsu queue-daemon stop # Stop daemon
kugetsu queue-daemon restart # Restart daemon
kugetsu queue-daemon status # Check if daemon is running
kugetsu queue-daemon logs # Show recent daemon logs
```
**Daemon Behavior:**
1. Runs at configurable interval (default: 5 minutes)
2. Checks if active agents < MAX_CONCURRENT_AGENTS
3. Picks 1-N pending items (configurable batch size)
4. Forks PM session for each picked item
5. PM decides whether to use `start` or `continue`
**Queue Directory:**
```
~/.kugetsu/queue/
├── items/ # Queue item JSON files
│ ├── q_1234567890.json # One file per queued task
│ └── q_1234567891.json
├── daemon.pid # Daemon process ID
├── daemon.lock # Daemon lock file
└── daemon.log # Daemon log output
```
## Workflow Example
### First-time Setup
```bash
# First-time setup (requires TTY)
# Initialize kugetsu (requires TTY)
kugetsu init
# Creates: base session + pm-agent session
# Start work on issue
kugetsu start github.com/shoko/kugetsu#14 "implement feature X"
# Creates: worktree at ~/.kugetsu/worktrees/github.com-shoko-kugetsu-14/
# Start the queue daemon (for autonomous operation)
kugetsu queue-daemon start
```
# Continue later
### Normal Workflow
```bash
# Enqueue tasks via delegate - agents will process them automatically
kugetsu delegate "work on issue #14"
kugetsu delegate "review PR #92"
# Check queue status
kugetsu queue list # See pending tasks
kugetsu queue stats # See statistics
# Debug queue daemon
kugetsu queue-daemon status # Is daemon running?
kugetsu queue-daemon logs # See daemon logs
# Continue work on existing issue
kugetsu continue github.com/shoko/kugetsu#14 "add tests"
# Continue again
kugetsu continue github.com/shoko/kugetsu#14 "fix failing test"
# List all sessions
kugetsu list
@@ -367,6 +418,21 @@ kugetsu prune --force
kugetsu destroy github.com/shoko/kugetsu#14
```
### Queue Daemon Management
```bash
# Check if daemon is running
kugetsu queue-daemon status
# View daemon logs for debugging
kugetsu queue-daemon logs
# Restart daemon if needed
kugetsu queue-daemon restart
# Stop daemon
kugetsu queue-daemon stop
```
## Headless Operation
This design solves the headless CLI limitation discovered in Issue #14:

View File

@@ -17,6 +17,15 @@ CONTEXT_DIR="${CONTEXT_DIR:-$KUGETSU_DIR/context}"
ENABLE_CONTEXT_DUMP="${ENABLE_CONTEXT_DUMP:-true}"
WORKTREE_CHECK_PR_STATUS="${WORKTREE_CHECK_PR_STATUS:-true}"
QUEUE_DIR="${QUEUE_DIR:-$KUGETSU_DIR/queue}"
QUEUE_ITEMS_DIR="${QUEUE_ITEMS_DIR:-$QUEUE_DIR/items}"
QUEUE_DAEMON_PID_FILE="${QUEUE_DAEMON_PID_FILE:-$QUEUE_DIR/daemon.pid}"
QUEUE_DAEMON_LOCK_FILE="${QUEUE_DAEMON_LOCK_FILE:-$QUEUE_DIR/daemon.lock}"
QUEUE_DAEMON_LOG_FILE="${QUEUE_DAEMON_LOG_FILE:-$QUEUE_DIR/daemon.log}"
QUEUE_DAEMON_INTERVAL_MINUTES="${QUEUE_DAEMON_INTERVAL_MINUTES:-5}"
QUEUE_CLEANUP_AGE_DAYS="${QUEUE_CLEANUP_AGE_DAYS:-7}"
TASK_TIMEOUT_HOURS="${TASK_TIMEOUT_HOURS:-1}"
# Load user config overrides (~/.kugetsu/config)
if [ -f "$KUGETSU_DIR/config" ]; then
source "$KUGETSU_DIR/config"
@@ -53,7 +62,7 @@ count_active_dev_sessions() {
for session_file in "$SESSIONS_DIR"/*.json; do
if [ -f "$session_file" ]; then
local filename=$(basename "$session_file")
if [ "$filename" != "base.json" ]; then
if [ "$filename" != "base.json" ] && [ "$filename" != "pm-agent.json" ]; then
count=$((count + 1))
fi
fi
@@ -82,6 +91,9 @@ Usage:
kugetsu destroy --base [-y] Delete base session
kugetsu set-pr <issue-ref> <pr-url> Set PR URL for session (for PR tracking)
kugetsu context <issue-ref> Show context for issue
kugetsu queue [list|stats|clear] Show queue status or statistics
kugetsu queue enqueue <issue-ref> <message> Enqueue a task (normally via delegate)
kugetsu queue-daemon [start|stop|restart|status|logs] Manage queue daemon
kugetsu help Show this help
Issue Ref Format:
@@ -477,6 +489,234 @@ except Exception as e:
PYEOF
}
ensure_queue_dirs() {
mkdir -p "$QUEUE_ITEMS_DIR"
}
generate_queue_id() {
echo "q_$(date +%s)_$$_$RANDOM"
}
enqueue_task() {
local issue_ref="$1"
local message="$2"
if [ -z "$issue_ref" ] || [ -z "$message" ]; then
echo "Error: enqueue_task requires <issue-ref> and <message>" >&2
return 1
fi
validate_issue_ref "$issue_ref"
ensure_queue_dirs
local queue_id=$(generate_queue_id)
local pending_since=$(date -Iseconds)
python3 << PYEOF
import json
queue_item = {
"id": "$queue_id",
"issue_ref": "$issue_ref",
"message": """$message""",
"state": "pending",
"pending_since": "$pending_since",
"notified_at": None,
"completed_at": None,
"error": None
}
with open("$QUEUE_ITEMS_DIR/${queue_id}.json", "w") as f:
json.dump(queue_item, f, indent=2)
print(f"Enqueued: $queue_id")
PYEOF
kugetsu_add_notification "task_queued" "Task queued: $issue_ref" "$issue_ref"
}
get_pending_tasks() {
local limit="${1:-10}"
if [ ! -d "$QUEUE_ITEMS_DIR" ]; then
echo "[]"
return
fi
find "$QUEUE_ITEMS_DIR" -name "*.json" -type f 2>/dev/null | while read -r file; do
local state=$(python3 -c "import json; print(json.load(open('$file')).get('state', ''))" 2>/dev/null || echo "")
if [ "$state" = "pending" ]; then
cat "$file"
fi
done | head -"$limit"
}
get_queue_stats() {
local total=0
local pending=0
local notified=0
local completed=0
local error=0
if [ -d "$QUEUE_ITEMS_DIR" ]; then
for file in "$QUEUE_ITEMS_DIR"/*.json; do
[ -f "$file" ] || continue
total=$((total + 1))
local state=$(python3 -c "import json; print(json.load(open('$file')).get('state', ''))" 2>/dev/null || echo "")
case "$state" in
pending) pending=$((pending + 1)) ;;
notified) notified=$((notified + 1)) ;;
completed) completed=$((completed + 1)) ;;
error) error=$((error + 1)) ;;
esac
done
fi
echo "{\"total\": $total, \"pending\": $pending, \"notified\": $notified, \"completed\": $completed, \"error\": $error}"
}
update_queue_item_state() {
local queue_id="$1"
local new_state="$2"
local session_id="${3:-}"
local pid="${4:-}"
local item_file="$QUEUE_ITEMS_DIR/${queue_id}.json"
if [ ! -f "$item_file" ]; then
echo "Error: Queue item not found: $queue_id" >&2
return 1
fi
python3 << PYEOF
import json
import os
from datetime import datetime
item_file = "$item_file"
new_state = "$new_state"
session_id = "$session_id"
pid = "$pid"
with open(item_file, 'r') as f:
item = json.load(f)
issue_ref = item.get('issue_ref', '')
item['state'] = new_state
if new_state == "notified":
item['notified_at'] = datetime.now().isoformat() + "Z"
if session_id:
item['opencode_session_id'] = session_id
if pid:
item['pid'] = int(pid) if pid.isdigit() else None
elif new_state == "completed":
item['completed_at'] = datetime.now().isoformat() + "Z"
os.system(f"kugetsu_add_notification 'task_completed' 'Task completed: {issue_ref}' '{issue_ref}'")
elif new_state == "error":
item['error'] = datetime.now().isoformat() + "Z"
os.system(f"kugetsu_add_notification 'task_error' 'Task error: {issue_ref}' '{issue_ref}'")
with open(item_file, 'w') as f:
json.dump(item, f, indent=2)
print(f"Updated $queue_id to state: $new_state")
PYEOF
}
check_task_timeouts() {
if [ ! -d "$QUEUE_ITEMS_DIR" ]; then
return
fi
local timeout_hours="${TASK_TIMEOUT_HOURS:-1}"
for item in "$QUEUE_ITEMS_DIR"/*.json; do
[ -f "$item" ] || continue
local state=$(python3 -c "import json; print(json.load(open('$item')).get('state', ''))" 2>/dev/null)
if [ "$state" != "notified" ]; then
continue
fi
local notified_at=$(python3 -c "import json; print(json.load(open('$item')).get('notified_at', ''))" 2>/dev/null)
if [ -z "$notified_at" ]; then
continue
fi
local queue_id=$(basename "$item" .json)
local pid=$(python3 -c "import json; print(json.load(open('$item')).get('pid', ''))" 2>/dev/null)
local session_id=$(python3 -c "import json; print(json.load(open('$item')).get('opencode_session_id', ''))" 2>/dev/null)
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 "$timeout_hours" ]; then
echo "Task $queue_id timed out after ${hours_elapsed}h (limit: ${timeout_hours}h)"
if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
echo "Killing process $pid"
kill "$pid" 2>/dev/null || true
fi
if [ -n "$session_id" ]; then
local worktree_path=""
for session_file in "$SESSIONS_DIR"/*.json; do
[ -f "$session_file" ] || continue
local sess_id=$(python3 -c "import json; print(json.load(open('$session_file')).get('opencode_session_id', ''))" 2>/dev/null)
if [ "$sess_id" = "$session_id" ]; then
worktree_path=$(python3 -c "import json; print(json.load(open('$session_file')).get('worktree_path', ''))" 2>/dev/null)
break
fi
done
if [ -n "$worktree_path" ]; then
pkill -f "opencode.*$worktree_path" 2>/dev/null || true
fi
fi
update_queue_item_state "$queue_id" "error"
local issue_ref=$(python3 -c "import json; print(json.load(open('$item')).get('issue_ref', ''))" 2>/dev/null)
if [ -n "$issue_ref" ]; then
local session_file=$(get_session_for_issue "$issue_ref")
if [ -n "$session_file" ] && [ "$session_file" != "null" ]; then
python3 << PYEOF
import json
session_path = "$SESSIONS_DIR/$session_file"
try:
with open(session_path, 'r') as f:
session = json.load(f)
session['state'] = 'timeout'
with open(session_path, 'w') as f:
json.dump(session, f, indent=2)
print(f"Marked session for $issue_ref as timeout")
except Exception as e:
print(f"Error marking session: {e}")
PYEOF
fi
fi
fi
done
}
cleanup_old_queue_items() {
local days="${QUEUE_CLEANUP_AGE_DAYS:-7}"
if [ ! -d "$QUEUE_ITEMS_DIR" ]; then
return
fi
find "$QUEUE_ITEMS_DIR" -name "*.json" -type f -mtime "+$days" 2>/dev/null | while read -r file; do
local state=$(python3 -c "import json; print(json.load(open('$file')).get('state', ''))" 2>/dev/null || echo "")
if [ "$state" = "completed" ] || [ "$state" = "error" ]; then
rm -f "$file"
echo "Cleaned up: $(basename "$file")"
fi
done
}
update_session_pr_url() {
local issue_ref="$1"
local pr_url="$2"
@@ -984,9 +1224,218 @@ find_sessions_by_issue_number() {
echo "$results"
}
cmd_queue() {
local action="${1:-list}"
shift
case "$action" in
list)
ensure_queue_dirs
local stats=$(get_queue_stats)
echo "Queue Statistics:"
echo "$stats" | python3 -c "import json, sys; d=json.load(sys.stdin); print(f\" Total: {d['total']}\n Pending: {d['pending']}\n Notified: {d['notified']}\n Completed: {d['completed']}\n Error: {d['error']}\")"
echo ""
echo "Pending tasks:"
local count=0
for item in "$QUEUE_ITEMS_DIR"/*.json; do
[ -f "$item" ] || continue
local state=$(python3 -c "import json; print(json.load(open('$item')).get('state', '')" 2>/dev/null)
if [ "$state" = "pending" ]; then
count=$((count + 1))
python3 -c "import json; d=json.load(open('$item')); print(f\" [{d['id']}] {d['issue_ref']}: {d['message'][:50]}...\n pending since: {d['pending_since']}\")" 2>/dev/null
fi
done
if [ $count -eq 0 ]; then
echo " (none)"
fi
;;
stats)
local stats=$(get_queue_stats)
echo "$stats" | python3 -c "import json, sys; d=json.load(sys.stdin); print(json.dumps(d, indent=2))"
;;
clear)
echo "Cleaning up old queue items..."
cleanup_old_queue_items
;;
enqueue)
local issue_ref="${1:-}"
local message="${2:-}"
if [ -z "$issue_ref" ] || [ -z "$message" ]; then
echo "Usage: kugetsu queue enqueue <issue-ref> <message>" >&2
exit 1
fi
enqueue_task "$issue_ref" "$message"
;;
*)
echo "Usage: kugetsu queue [list|stats|clear|enqueue <issue-ref> <message>]" >&2
exit 1
;;
esac
}
cmd_queue_daemon() {
local action="${1:-status}"
shift
case "$action" in
start)
if [ -f "$QUEUE_DAEMON_PID_FILE" ]; then
local old_pid=$(cat "$QUEUE_DAEMON_PID_FILE" 2>/dev/null)
if [ -n "$old_pid" ] && kill -0 "$old_pid" 2>/dev/null; then
echo "Daemon is already running with PID $old_pid"
exit 1
fi
rm -f "$QUEUE_DAEMON_PID_FILE"
fi
mkdir -p "$(dirname "$QUEUE_DAEMON_LOG_FILE")"
nohup bash "$0" queue-daemon run >> "$QUEUE_DAEMON_LOG_FILE" 2>&1 &
local daemon_pid=$!
echo "$daemon_pid" > "$QUEUE_DAEMON_PID_FILE"
echo "Queue daemon started with PID $daemon_pid"
echo "Log file: $QUEUE_DAEMON_LOG_FILE"
;;
stop)
if [ ! -f "$QUEUE_DAEMON_PID_FILE" ]; then
echo "Daemon PID file not found. Is the daemon running?"
exit 1
fi
local pid=$(cat "$QUEUE_DAEMON_PID_FILE")
if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
kill "$pid"
rm -f "$QUEUE_DAEMON_PID_FILE"
echo "Daemon stopped (PID $pid)"
else
echo "Daemon not running (stale PID file)"
rm -f "$QUEUE_DAEMON_PID_FILE"
fi
;;
restart)
cmd_queue_daemon stop
sleep 1
cmd_queue_daemon start
;;
status)
if [ -f "$QUEUE_DAEMON_PID_FILE" ]; then
local pid=$(cat "$QUEUE_DAEMON_PID_FILE")
if [ -n "$pid" ] && kill -0 "$pid" 2>/dev/null; then
echo "Queue daemon is running (PID $pid)"
else
echo "Daemon not running (stale PID file)"
rm -f "$QUEUE_DAEMON_PID_FILE"
fi
else
echo "Queue daemon is not running"
fi
;;
logs)
local lines="${1:-50}"
if [ -f "$QUEUE_DAEMON_LOG_FILE" ]; then
tail -"$lines" "$QUEUE_DAEMON_LOG_FILE"
else
echo "No daemon log file found"
fi
;;
run)
queue_daemon_loop
;;
*)
echo "Usage: kugetsu queue-daemon [start|stop|restart|status|logs]" >&2
exit 1
;;
esac
}
queue_daemon_loop() {
local pid=$$
echo "$pid" > "$QUEUE_DAEMON_PID_FILE"
echo "Queue daemon started (PID $pid) at $(date)"
while true; do
sleep $((QUEUE_DAEMON_INTERVAL_MINUTES * 60))
if [ ! -f "$QUEUE_DAEMON_PID_FILE" ] || [ "$(cat "$QUEUE_DAEMON_PID_FILE")" != "$pid" ]; then
echo "PID file changed, stopping daemon"
exit 0
fi
check_task_timeouts
process_queue
done
}
process_queue() {
local active_count=$(count_active_dev_sessions)
if [ "$active_count" -ge "$MAX_CONCURRENT_AGENTS" ]; then
return
fi
local available_slots=$((MAX_CONCURRENT_AGENTS - active_count))
if [ "$available_slots" -le 0 ]; then
return
fi
local count=0
for item in $(ls -t "$QUEUE_ITEMS_DIR"/*.json 2>/dev/null | head -20); do
[ $count -ge "$available_slots" ] && break
[ -f "$item" ] || continue
local state=$(python3 -c "import json; print(json.load(open('$item')).get('state', ''))" 2>/dev/null)
if [ "$state" != "pending" ]; then
continue
fi
local queue_id=$(basename "$item" .json)
local issue_ref=$(python3 -c "import json; print(json.load(open('$item')).get('issue_ref', ''))" 2>/dev/null)
local message=$(python3 -c "import json; print(json.load(open('$item')).get('message', ''))" 2>/dev/null)
if [ -z "$issue_ref" ] || [ -z "$message" ]; then
continue
fi
update_queue_item_state "$queue_id" "notified"
kugetsu_add_notification "task_dequeued" "Task dequeued: $issue_ref" "$issue_ref"
local log_file="$LOGS_DIR/delegate-${queue_id}.log"
mkdir -p "$LOGS_DIR"
local max_retries=3
local attempt=1
local success=false
local fork_pid=""
while [ $attempt -le $max_retries ]; do
if kugetsu start "$issue_ref" "$message" >> "$log_file" 2>&1; then
success=true
break
fi
echo "Attempt $attempt failed for $queue_id, cleaning up..." >> "$log_file"
local session_file="$(issue_ref_to_filename "$issue_ref").json"
local worktree_path=$(issue_ref_to_worktree_path "$issue_ref" "$PWD")
[ -f "$SESSIONS_DIR/$session_file" ] && rm -f "$SESSIONS_DIR/$session_file"
worktree_exists "$issue_ref" "$PWD" && remove_worktree_for_issue "$issue_ref" "$PWD"
remove_issue_from_index "$issue_ref" 2>/dev/null || true
attempt=$((attempt + 1))
done
if [ "$success" = true ]; then
echo "Started task $queue_id: $issue_ref"
count=$((count + 1))
else
echo "Failed to start task $queue_id after $max_retries attempts"
update_queue_item_state "$queue_id" "pending"
fi
done
}
cmd_delegate() {
local message="${1:-}"
local verbosity="${KUGETSU_VERBOSITY:-default}"
if [ -z "$message" ]; then
echo "Error: message is required" >&2
@@ -994,94 +1443,22 @@ cmd_delegate() {
exit 1
fi
local pm_session=$(get_pm_agent_session_id)
if [ -z "$pm_session" ] || [ "$pm_session" = "null" ] || [ "$pm_session" = "None" ]; then
echo "Error: PM agent session not found. Run 'kugetsu init' first." >&2
exit 1
fi
mkdir -p "$LOGS_DIR"
local log_file="$LOGS_DIR/delegate-$(date +%s).log"
local parsed=$(parse_issue_ref_from_message "$message")
local gitserver=$(echo "$parsed" | cut -d'|' -f1)
local owner=$(echo "$parsed" | cut -d'|' -f2)
local repo=$(echo "$parsed" | cut -d'|' -f3)
local issue_number=$(echo "$parsed" | cut -d'|' -f4)
local missing_info=$(get_missing_info "$parsed")
local context_injection=""
if [ -n "$missing_info" ]; then
context_injection=$(build_missing_info_context "$missing_info")
echo "NOTE: Delegation missing information: ${missing_info}"
if [ -z "$issue_number" ] || [ -z "$gitserver" ] || [ -z "$owner" ] || [ -z "$repo" ]; then
echo "Error: Could not parse issue reference from message" >&2
echo "Message should contain an issue reference like 'github.com/user/repo#123'" >&2
exit 1
fi
local candidates=""
local candidate_count=0
local issue_ref="${gitserver}/${owner}/${repo}#${issue_number}"
if [ -n "$issue_number" ]; then
local worktrees=$(find_worktrees_by_issue_number "$issue_number")
local sessions=$(find_sessions_by_issue_number "$issue_number")
while IFS=: read -r path type; do
if [ -n "$path" ]; then
candidate_count=$((candidate_count + 1))
candidates="${candidates}${candidate_count}) ${path} (${type})
"
fi
done <<< "$worktrees"
while IFS=: read -r path type; do
if [ -n "$path" ]; then
candidate_count=$((candidate_count + 1))
candidates="${candidates}${candidate_count}) ${path} (${type})
"
fi
done <<< "$sessions"
fi
local use_worktree=""
if [ $candidate_count -gt 0 ]; then
echo "Found $candidate_count existing worktree(s)/session(s) for issue #${issue_number}:"
echo "$candidates"
echo "r) Delegate anyway (without routing)"
echo "Which one to use? [1-${candidate_count}/r]: "
read -r choice
if [ "$choice" = "r" ] || [ -z "$choice" ]; then
use_worktree=""
elif [ "$choice" -ge 1 ] && [ "$choice" -le "$candidate_count" ]; then
local selected=$(echo "$candidates" | sed -n "${choice}p")
use_worktree=$(echo "$selected" | sed 's/) .*//')
fi
fi
local final_message="${message}${context_injection}"
if [ -n "$use_worktree" ]; then
if [ -d "$use_worktree" ]; then
echo "Using worktree: $use_worktree"
final_message="${final_message}
NOTE: Worktree selected: ${use_worktree}"
fi
fi
local temp_dir="${KUGETSU_TEMP_DIR:-$HOME/.local/share/opencode/tool-output}"
mkdir -p "$ENV_DIR"
local env_sh="set -a; export KUGETSU_TEMP_DIR='$temp_dir'; export KUGETSU_VERBOSITY='$verbosity'; "
if [ -f "$ENV_DIR/pm-agent.env" ]; then
env_sh="${env_sh}source '$ENV_DIR/pm-agent.env'; "
elif [ -f "$ENV_DIR/default.env" ]; then
env_sh="${env_sh}source '$ENV_DIR/default.env'; "
fi
env_sh="${env_sh}set +a; "
nohup sh -c "${env_sh}opencode run '${final_message}' --continue --session '$pm_session' >> '$log_file' 2>&1" > /dev/null 2>&1 &
disown
echo "Delegated to PM agent (logged to $(basename "$log_file"))"
echo "Verbosity: $verbosity"
enqueue_task "$issue_ref" "$message"
echo "Task enqueued. The queue daemon will process it when a slot is available."
}
cmd_logs() {
@@ -1699,20 +2076,10 @@ cmd_start() {
create_worktree "$issue_ref" "$parent_dir"
local session_file="$(issue_ref_to_filename "$issue_ref").json"
echo "Forking session for '$issue_ref'..."
# Session-counting: count actual dev sessions, reject if at limit
local active_count=$(count_active_dev_sessions)
if [ "$active_count" -ge "$MAX_CONCURRENT_AGENTS" ]; then
echo "Error: Max concurrent agents ($MAX_CONCURRENT_AGENTS) reached" >&2
echo "Active sessions: $active_count" >&2
remove_worktree_for_issue "$issue_ref" "$parent_dir"
exit 1
fi
local fork_log="$SESSIONS_DIR/$session_file.fork.log"
local opencode_db="${OPENCODE_DB:-$HOME/.local/share/opencode/opencode.db}"
local lock_file="$KUGETSU_DIR/.session_lock"
local lock_fd=200
> "$fork_log"
@@ -1725,25 +2092,38 @@ ${previous_context}
## YOUR TASK
$message"
fix_session_permissions
if [ "$DEBUG_MODE" = true ]; then
(cd "$worktree_path" && opencode run "$full_message" --fork --session "$base_session_id" --dir "$worktree_path" 2>&1) | tee "$fork_log" &
else
(cd "$worktree_path" && opencode run "$full_message" --fork --session "$base_session_id" --dir "$worktree_path" 2>&1) >> "$fork_log" &
fi
local fork_pid=$!
local max_attempts=10
local attempt=1
local new_session_id=""
local fork_log_output=""
while [ $attempt -le $max_attempts ]; do
sleep 1
(
flock -x $lock_fd
new_session_id=$(python3 -c "
local active_count=$(count_active_dev_sessions)
if [ "$active_count" -ge "$MAX_CONCURRENT_AGENTS" ]; then
echo "Error: Max concurrent agents ($MAX_CONCURRENT_AGENTS) reached" >&2
echo "Active sessions: $active_count" >&2
remove_worktree_for_issue "$issue_ref" "$parent_dir"
exit 1
fi
echo "Forking session for '$issue_ref'..."
fix_session_permissions
if [ "$DEBUG_MODE" = true ]; then
(cd "$worktree_path" && opencode run "$full_message" --fork --session "$base_session_id" --dir "$worktree_path" 2>&1) | tee "$fork_log" &
else
(cd "$worktree_path" && opencode run "$full_message" --fork --session "$base_session_id" --dir "$worktree_path" 2>&1) >> "$fork_log" &
fi
local fork_pid=$!
local max_attempts=10
local attempt=1
local new_session_id=""
local fork_log_output=""
while [ $attempt -le $max_attempts ]; do
sleep 1
new_session_id=$(python3 -c "
import sqlite3
conn = sqlite3.connect('$opencode_db')
cursor = conn.cursor()
@@ -1752,31 +2132,31 @@ result = cursor.fetchone()
if result:
print(result[0])
" 2>/dev/null || echo "")
if [ -n "$new_session_id" ] && [ "$new_session_id" != "$base_session_id" ] && [ "$new_session_id" != "$pm_agent_session_id" ]; then
break
fi
if ! kill -0 $fork_pid 2>/dev/null; then
fork_log_output=$(tail -20 "$fork_log" 2>/dev/null || echo "(log empty or unavailable)")
break
fi
attempt=$((attempt + 1))
done
if [ -n "$new_session_id" ] && [ "$new_session_id" != "$base_session_id" ] && [ "$new_session_id" != "$pm_agent_session_id" ]; then
break
fi
if ! kill -0 $fork_pid 2>/dev/null; then
fork_log_output=$(tail -20 "$fork_log" 2>/dev/null || echo "(log empty or unavailable)")
break
fi
attempt=$((attempt + 1))
done
if [ -z "$new_session_id" ]; then
echo "Error: Could not find newly created session after ${max_attempts}s" >&2
if [ -n "$fork_log_output" ]; then
echo "Fork log output:" >&2
echo "$fork_log_output" >&2
if [ -z "$new_session_id" ]; then
echo "Error: Could not find newly created session after ${max_attempts}s" >&2
if [ -n "$fork_log_output" ]; then
echo "Fork log output:" >&2
echo "$fork_log_output" >&2
fi
remove_worktree_for_issue "$issue_ref"
exit 1
fi
remove_worktree_for_issue "$issue_ref"
exit 1
fi
echo "Updating permissions for new session: $new_session_id"
python3 -c "
echo "Updating permissions for new session: $new_session_id"
python3 -c "
import sqlite3
conn = sqlite3.connect('$opencode_db')
cursor = conn.cursor()
@@ -1786,9 +2166,9 @@ conn.commit()
print('[OK] Session permissions updated')
"
if [ "$DEBUG_MODE" = true ]; then
echo "[DEBUG] Forked session permissions check:"
python3 -c "
if [ "$DEBUG_MODE" = true ]; then
echo "[DEBUG] Forked session permissions check:"
python3 -c "
import sqlite3
conn = sqlite3.connect('$opencode_db')
cursor = conn.cursor()
@@ -1798,11 +2178,11 @@ for row in cursor.fetchall():
print(' Directory:', row[1])
print(' Permission:', row[2])
" 2>/dev/null || echo " (failed to query DB)"
fi
fi
local branch_name=$(issue_ref_to_branch_name "$issue_ref")
python3 << PYEOF > "$SESSIONS_DIR/$session_file"
local branch_name=$(issue_ref_to_branch_name "$issue_ref")
python3 << PYEOF > "$SESSIONS_DIR/$session_file"
import json
session = {
@@ -1820,12 +2200,15 @@ with open("$SESSIONS_DIR/$session_file", "w") as f:
json.dump(session, f, indent=2)
PYEOF
add_issue_to_index "$issue_ref" "$session_file"
kugetsu_context_dump "$issue_ref" "$message" "$branch_name"
add_issue_to_index "$issue_ref" "$session_file"
kugetsu_context_dump "$issue_ref" "$message" "$branch_name"
kugetsu_add_notification "task_started" "Task started: $issue_ref" "$issue_ref"
echo "Session started for '$issue_ref': $new_session_id"
echo "Worktree: $worktree_path"
echo "Session started for '$issue_ref': $new_session_id"
echo "Worktree: $worktree_path"
) 200>"$lock_file"
}
cmd_continue() {
@@ -2218,6 +2601,16 @@ main() {
exit 1
fi
;;
queue)
local action="${1:-list}"
shift
cmd_queue "$action" "$@"
;;
queue-daemon)
local action="${1:-status}"
shift
cmd_queue_daemon "$action" "$@"
;;
*)
echo "Error: unknown command '$command'" >&2
usage