Scheduler

WASP's scheduler runs 23 background jobs that keep the agent active, learning, and aware — even when no user is interacting.

Job Registry

Job Name	Interval	Purpose
health_check	5 min	Monitor Redis, Postgres, Ollama, disk, RAM, CPU
reflection	6 hours	LLM-driven memory reflection and synthesis
memory_cleanup	24 hours	Remove old episodic memories, orphaned data
snapshot	24 hours	Full memory snapshot to /data/memory/
reminder_checker	30 sec	Fire due reminders, trigger agent goals for recurring reminders
monitor_checker	5 min	Check price/RSS monitors for threshold violations
proactive	1 hour	Send proactive suggestions based on user context
promotion	12 hours	Promote frequent episodic memories to semantic
checkin	1 hour	Periodic user check-in messages
custom_task_runner	1 min	Execute user-defined scheduled tasks
subscription_checker	5 min	Check price/RSS subscriptions for alerts
goal_tick	15 sec	Advance active goal execution (up to 3 steps per tick)
goal_meta_reflection	5 min	Analyze goal health, detect storms, log meta-state
agent_tick	15 sec	Advance active sub-agent goals
dream	1 hour (gated)	Consolidate memories, reflect, prefetch data
autonomous	30 min	Evaluate system state and generate proactive goals
digest	24 hours	Generate daily digest for user
cpi_monitor	5 min	Compute Cognitive Pressure Index
self_integrity	6 hours	Cross-check self-model vs actual performance
perception	15 min	Monitor crypto prices for significant moves
behavioral_learner	2 min	Process user corrections into behavioral rules
world_model	15 min	Update entity states from world_timeline
skill_evolution	6 hours	Synthesize new skills from recurring patterns

Job Architecture

Jobs implement a simple interface:

class BaseJob:
    async def run(self) -> None:
        """Execute the job's logic."""
        ...

The Scheduler manages all jobs:

• Tracks last run time per job in Redis (scheduler:last_run:{job})
• Logs scheduler.job_complete with job name and duration in ms
• Handles exceptions without crashing other jobs

Key Jobs Explained

health_check (5 min)

Uses HealthMonitor to check:

• Redis: PING
• PostgreSQL: simple SELECT
• Ollama: /api/tags endpoint
• Disk: usage percentage
• RAM: percent used
• CPU: percent used

When thresholds exceeded, SelfHealer triggers remediation (disk cleanup, Ollama restart, etc.).

reminder_checker (30 sec)

Checks Redis for due reminders. For recurring reminders with an agent_id, calls agent_orchestrator.create_agent_goal() to restart the cycle. Regular reminders fire a Telegram message.

dream (1 hour, gated)

The Dream Mode job activates only when:

• User has been inactive for more than 2 hours
• Time is between 1 AM and 7 AM local, OR inactive for 4+ hours
• Has not run in the last 6 hours

When activated, Dream Mode:

1. Runs the PromotionEngine (episodic → semantic promotion)
2. Extracts KG entities from recent memories
3. Generates an LLM reflection on recent events
4. Pre-fetches crypto prices for monitored assets
5. Logs to the dream_log table

autonomous (30 min)

The AutonomousGoalGeneratorJob evaluates system state:

1. Checks critical thresholds (disk >95%, RAM >95%) — no LLM needed
2. For non-critical situations, asks the LLM for proactive recommendations
3. If action is warranted: calls goal_orchestrator.create_goal() with priority=3
4. Rate-limited: max 1 autonomous goal per hour, 5 per day

perception (15 min)

BackgroundPerceptionJob monitors crypto assets in the Knowledge Graph:

• Fetches current prices
• Compares vs last known price in the temporal model
• If change >4%, asks LLM whether to notify
• Sends Telegram alert if notable (max 3/day, respects quiet hours)

behavioral_learner (2 min)

Checks Redis behavioral:pending queue for user corrections:

• Correction detection patterns: "estás alucinando", "eso está mal", etc.
• LLM analyzes the correction and extracts a rule
• Rule saved to behavioral_rules table
• Rule injected into every future system prompt

skill_evolution (6 hours)

Analyzes skill_patterns table for recurring multi-skill sequences:

• Minimum 5 occurrences required (configurable)
• LLM synthesizes a new composite skill from the pattern
• AST validation ensures generated code is safe
• New skill registered and available immediately

Scheduler State

View job status in the dashboard at /scheduler.

Query last run times:

docker exec agent-redis redis-cli KEYS "scheduler:last_run:*" | sort

Quiet Hours

Jobs that send Telegram notifications respect quiet hours:

• Default: no notifications between 11 PM and 8 AM
• Configurable via PROACTIVE_QUIET_START and PROACTIVE_QUIET_END

Disabling Jobs

Individual jobs cannot be disabled without code changes, but the entire scheduler can be disabled:

# In .env
SCHEDULER_ENABLED=false

Or disable specific features to skip registration of their jobs:

SKILL_EVOLUTION_ENABLED=false  # Skips skill_evolution job
WORLD_MODEL_ENABLED=false      # Skips world_model job
VECTOR_MEMORY_ENABLED=false    # Skips vector_index job