aiwg/agentic/code/addons/agent-persistence/gates/recovery-escalation-gate.yaml

Cognitive architecture for AI-augmented software development with structured memory, ensemble validation, and closed-loop correction. FAIR-aligned artifacts, 84% cost reduction via human-in-the-loop, standards adopted by 100+ organizations.

# Recovery Escalation Gate
# Triggered when agent exhausts recovery attempts (3 max)
# Based on REF-057 Agent Laboratory and UC-AP-004 Recovery Protocol
# Issue: #262

$schema: "https://aiwg.io/schemas/hitl-gate/v1"

id: "GATE-AP-RECOVERY"
name: "Recovery Escalation Gate"
description: |
  Human intervention required after agent exhausts 3 recovery attempts.
  Presents full recovery history and requests human debugging/guidance.
  This gate implements the ESCALATE stage of PAUSE→DIAGNOSE→ADAPT→RETRY→ESCALATE protocol.

gate_type: approval

trigger:
  type: threshold_breach
  threshold: 3
  pattern: "recovery_attempts >= 3"
  description: "Triggered when agent reaches max recovery attempts without resolving issue"

behavior:
  mode: TERMINATE  # MUST stop execution pending human response
  timeout: 172800  # 48 hours
  timeout_action: escalate

  notification:
    channels:
      - cli
      - issue_comment
    urgency: high
    message_template: |
      ## Recovery Escalation Required

      **Gate**: GATE-AP-RECOVERY
      **Pattern**: {{pattern_type}}
      **Severity**: {{severity}}
      **Attempts**: {{recovery_attempts}} / 3

      Agent has exhausted recovery attempts. Human debugging required.

presentation:
  summary_template: |
    ╭─────────────────────────────────────────────────────────────╮
    │ HUMAN INTERVENTION REQUIRED                                 │
    │ Recovery Escalation Gate: GATE-AP-RECOVERY                  │
    ├─────────────────────────────────────────────────────────────┤
    │ Context:                                                    │
    │   • Task: {{task_description}}                              │
    │   • Pattern: {{pattern_type}} ({{severity}})                │
    │   • Recovery Attempts: {{recovery_attempts}} / 3            │
    │   • Agent: {{agent_name}}                                   │
    │                                                              │
    │ Detection Details:                                          │
    │   • File(s): {{affected_files}}                             │
    │   • Original Error: {{original_error}}                      │
    │   • Detection Time: {{detection_timestamp}}                 │
    │                                                              │
    │ Recovery History:                                           │
    │   {{recovery_attempts_summary}}                             │
    │                                                              │
    │ Current State:                                              │
    │   • Tests: {{test_status}}                                  │
    │   • Coverage: {{coverage_status}}                           │
    │   • Confidence: {{agent_confidence}}                        │
    ├─────────────────────────────────────────────────────────────┤
    │ Options:                                                    │
    │   [a] Approve - Override and allow agent to continue        │
    │   [r] Reject - Require manual fix from human                │
    │   [t] Retry - Reset counter, give agent another chance      │
    │   [v] View - Show detailed recovery attempt logs            │
    │   [d] Delegate - Assign to different agent                  │
    │   [q] Abort - Stop task entirely                            │
    ╰─────────────────────────────────────────────────────────────╯

  artifacts_to_show:
    - ".aiwg/persistence/recoveries/{{session_id}}-recovery.yaml"
    - "{{affected_files}}"

  questions:
    - id: "decision"
      question: "How should we proceed?"
      options:
        - "Approve - Let agent continue (I've fixed it externally)"
        - "Reject - I will fix this manually"
        - "Retry - Reset counter for 3 more attempts"
        - "Abort - Stop this task entirely"
      required: true

    - id: "guidance"
      question: "Provide guidance to agent (optional):"
      options: []  # Free text
      required: false

    - id: "root_cause"
      question: "Did you identify the root cause?"
      options:
        - "Yes - Configuration issue"
        - "Yes - Agent capability limit"
        - "Yes - Task specification unclear"
        - "No - Still investigating"
      required: false

  context_window: 200  # Show more context for debugging

cost_tracking:
  track_enabled: true
  metrics:
    - time_to_decision
    - revision_count
    - escalation_resolution_time
    - recovery_success_rate
  baseline_comparison: autonomous

audit:
  log_decision: true
  log_rationale: true
  require_signature: false
  retention_days: 90
  additional_fields:
    - recovery_session_id
    - pattern_type
    - severity
    - attempts_before_escalation
    - human_guidance_provided
    - resolution_outcome

# Integration with Recovery Orchestrator
integration:
  triggered_by: recovery_orchestrator
  triggers_on:
    - recovery_attempts >= 3
    - confidence < 0.5
    - severity == "CRITICAL"
    - infinite_loop_detected
    - non_deterministic_failure

  state_preservation:
    snapshot_path: ".aiwg/checkpoints/recovery-{{session_id}}.json"
    iteration_history: ".aiwg/persistence/recoveries/{{session_id}}-recovery.yaml"
    preserve_working_files: true

  on_approval:
    action: resume_task
    inject_human_guidance: true
    reset_recovery_counter: false
    log_override: true

  on_rejection:
    action: halt_task
    preserve_state: true
    assign_to_human: true
    create_manual_task: true

  on_retry:
    action: reset_and_resume
    reset_recovery_counter: true
    inject_reinforcement: true
    max_resets: 1  # Can only reset once per task

  on_abort:
    action: terminate_task
    cleanup_working_files: false
    log_abandonment: true

# References
references:
  requirements:
    - "@.aiwg/requirements/use-cases/UC-AP-004-enforce-recovery-protocol.md"
  architecture:
    - "@.aiwg/architecture/agent-persistence-sad.md"
    - "@.aiwg/architecture/decisions/ADR-AP-002-rule-enforcement-strategy.md"
  rules:
    - "@.claude/rules/hitl-gates.md"
    - "@.claude/rules/hitl-patterns.md"
    - "@.claude/rules/anti-laziness.md"
  agents:
    - "@.claude/agents/recovery-orchestrator.md"
  research:
    - "@.aiwg/research/findings/REF-057-agent-laboratory.md"
    - "@.aiwg/research/findings/agentic-laziness-research.md"

# Issue tracking
issues:
  - "#262"  # HITL Gate Integration
  - "#96"   # HITL Gates Implementation