name: pod-crashloop-remediation
description: Diagnose and remediate pods in CrashLoopBackOff
version: "1.0"

trigger:
  - alert:
      match:
        alertname: KubePodCrashLooping
  - manual: true
    inputs:
      - name: namespace
        description: Pod namespace
        required: true
      - name: pod
        description: Pod name (or prefix)
        required: true

defaults:
  model: sonnet

steps:
  - name: identify-pod
    agent: k8s-diagnostician
    model: haiku
    task: |
      Identify the crashing pod:
      - Namespace: {{ inputs.namespace | default(alert.labels.namespace) }}
      - Pod: {{ inputs.pod | default(alert.labels.pod) }}

      Get pod details:
      - Current status and restart count
      - Last restart reason
      - Container statuses
    output: pod_info

  - name: analyze-logs
    agent: k8s-diagnostician
    model: sonnet
    task: |
      Analyze pod logs for crash cause:
      - Get current container logs (last 50 lines)
      - Get previous container logs if available
      - Look for error patterns:
        - OOMKilled (exit code 137)
        - Segfault (exit code 139)
        - Application errors
        - Configuration errors
        - Dependency failures

      Pod info: {{ steps.identify-pod.output }}
    output: log_analysis

  - name: check-resources
    agent: prometheus-analyst
    model: haiku
    task: |
      Check resource usage before crash:
      - Memory usage trend (last 30 min)
      - CPU usage trend (last 30 min)
      - Compare to resource limits

      Pod: {{ steps.identify-pod.output.pod_name }}
      Namespace: {{ steps.identify-pod.output.namespace }}
    output: resource_analysis

  - name: check-dependencies
    agent: k8s-diagnostician
    model: haiku
    task: |
      Check pod dependencies:
      - ConfigMaps and Secrets exist?
      - PVCs bound?
      - Service account valid?
      - Init containers completed?

      Pod info: {{ steps.identify-pod.output }}
    output: dependency_check

  - name: diagnose-and-recommend
    agent: k8s-orchestrator
    model: sonnet
    task: |
      Analyze all findings and determine root cause:

      Evidence:
      - Pod info: {{ steps.identify-pod.output }}
      - Log analysis: {{ steps.analyze-logs.output }}
      - Resource usage: {{ steps.check-resources.output }}
      - Dependencies: {{ steps.check-dependencies.output }}

      Determine:
      1. Root cause (OOM, config error, dependency, application bug, etc.)
      2. Severity (auto-recoverable, needs intervention, critical)
      3. Recommended actions

      Action classification:
      - [SAFE] Restart pod, clear stuck jobs
      - [CONFIRM] Increase resources, modify config
      - [FORBIDDEN] Delete PVC, delete namespace
    output: diagnosis

  - name: apply-safe-remediation
    condition: "{{ steps.diagnose-and-recommend.output.has_safe_action }}"
    agent: k8s-diagnostician
    model: haiku
    task: |
      Apply safe remediation actions:
      {{ steps.diagnose-and-recommend.output.safe_actions }}

      Report what was done.
    output: safe_actions_result

  - name: propose-confirm-actions
    condition: "{{ steps.diagnose-and-recommend.output.has_confirm_action }}"
    agent: k8s-orchestrator
    model: haiku
    task: |
      Present actions requiring confirmation:

      {{ steps.diagnose-and-recommend.output.confirm_actions }}

      For each action, explain:
      - What will change
      - Potential impact
      - Rollback option
    output: confirm_proposal
    confirm: true

outputs:
  - diagnosis
  - safe_actions_result
  - confirm_proposal

notifications:
  on_complete:
    summary: |
      CrashLoop remediation for {{ steps.identify-pod.output.pod_name }}:
      - Root cause: {{ steps.diagnose-and-recommend.output.root_cause }}
      - Actions taken: {{ steps.safe_actions_result.actions | default('none') }}
      - Pending approval: {{ steps.confirm_proposal | default('none') }}