agent-governance/sandbox/FIRST_TASK.md
profit 77655c298c Initial commit: Agent Governance System Phase 8
Phase 8 Production Hardening with complete governance infrastructure:

- Vault integration with tiered policies (T0-T4)
- DragonflyDB state management
- SQLite audit ledger
- Pipeline DSL and templates
- Promotion/revocation engine
- Checkpoint system for session persistence
- Health manager and circuit breaker for fault tolerance
- GitHub/Slack integrations
- Architectural test pipeline with bug watcher, suggestion engine, council review
- Multi-agent chaos testing framework

Test Results:
- Governance tests: 68/68 passing
- E2E workflow: 16/16 passing
- Phase 2 Vault: 14/14 passing
- Integration tests: 27/27 passing

Coverage: 57.6% average across 12 phases

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
2026-01-23 22:07:06 -05:00

3.3 KiB

First Task for Tier 1 Promotion

Overview

This document describes the "first task" that a newly promoted Tier 1 agent must complete to validate their operational capabilities.

Prerequisites

  • Agent has been promoted from Tier 0 to Tier 1
  • Agent has valid Vault AppRole credentials for Tier 1
  • Sandbox environment is available (localhost)

The Task: Deploy a Monitoring Endpoint

Objective: Deploy a simple HTTP health check endpoint that reports system status.

Requirements

  1. Deploy a container that:

    • Responds to HTTP requests on port 9999
    • Returns JSON with system health information
    • Is connected to the spark-net network
    • Has proper labels for governance tracking
  2. Verify the deployment:

    • Container is running
    • Endpoint responds within 100ms
    • Response includes valid JSON
  3. Document the deployment:

    • Record action in governance ledger
    • Create evidence package

Implementation Options

cd /opt/agent-governance/sandbox/ansible

# Check mode first (like Tier 0)
ansible-playbook -i /opt/agent-governance/inventory/sandbox.yml \
  deploy-service.yml --check \
  -e service_name=health-endpoint \
  -e image=nginx:alpine \
  -e port=9999

# Execute (Tier 1 capability)
ansible-playbook -i /opt/agent-governance/inventory/sandbox.yml \
  deploy-service.yml \
  -e service_name=health-endpoint \
  -e image=nginx:alpine \
  -e port=9999

Option B: Terraform

cd /opt/agent-governance/sandbox/terraform/docker-service

terraform init
terraform plan -var="service_name=health-endpoint" -var="external_port=9999"
terraform apply -var="service_name=health-endpoint" -var="external_port=9999"

Option C: Direct Docker (Governed Wrapper)

/opt/agent-governance/wrappers/docker-governed.sh run -d \
  --name health-endpoint \
  --network spark-net \
  -p 9999:80 \
  nginx:alpine

Verification

# Check container is running
docker ps --filter name=health-endpoint

# Test endpoint
curl -s http://localhost:9999 | head -5

# Measure response time
curl -w "%{time_total}\n" -o /dev/null -s http://localhost:9999

Success Criteria

Criterion Requirement
Container Running Status: Up
Network Attached spark-net
Port Exposed 9999
Response Time < 100ms
Ledger Entry Recorded

Recording the Task

After successful completion:

# Record in ledger
python3 /opt/agent-governance/agents/tier0-agent/agent.py plan \
  --title "Tier 1 First Task Complete" \
  --description "Deployed health-endpoint service on port 9999" \
  --target localhost \
  --steps '[{"action":"deploy","command":"docker run...","status":"success"}]'

# Create evidence
python3 /opt/agent-governance/evidence/evidence.py create \
  --agent-id tier1-agent-001 \
  --action "first_task_deployment" \
  --artifacts "docker_ps_output.txt,curl_response.json"

Rollback Procedure

If the task fails:

# Using Ansible
ansible-playbook rollback-service.yml -e service_name=health-endpoint

# Or directly
docker stop health-endpoint && docker rm health-endpoint

Next Steps

After completing this task:

  1. Agent demonstrates basic execution capability
  2. Agent can proceed to more complex tasks
  3. Track record builds toward Tier 2 promotion