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

skills/kugetsu/SKILL.md

@@ -50,7 +50,6 @@ A default config file is created during `kugetsu init` with commented examples:
 | `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_DAEMON_BATCH_SIZE` | 2 | How many tasks daemon picks per poll |
 | `QUEUE_CLEANUP_AGE_DAYS` | 7 | Auto-cleanup completed/error items older than N days |
 
 ### Environment Variables for Agents