| name: cloud-native-devops-env |
| version: "1.0.0" |
| description: > |
| Debug broken GitHub Actions workflows, Dockerfiles, and Kubernetes manifests. |
| AI agents identify and fix cloud-native deployment pipeline issues. |
| |
| author: Krishna |
| license: MIT |
| tags: |
| - devops |
| - docker |
| - github-actions |
| - kubernetes |
| - debugging |
| - infrastructure |
| - cloud-native |
|
|
| environment: |
| type: text |
| observation_space: structured |
| action_space: structured |
| max_steps: 10 |
|
|
| tasks: |
| - id: dockerfile_syntax |
| name: Dockerfile Syntax Errors |
| description: Fix syntax and instruction errors in Dockerfiles |
| difficulty: easy |
| num_scenarios: 5 |
|
|
| - id: dockerfile_runtime |
| name: Dockerfile Runtime Errors |
| description: Fix runtime/container execution issues in Dockerfiles |
| difficulty: medium |
| num_scenarios: 5 |
|
|
| - id: workflow_syntax_structure |
| name: Workflow Syntax and Structure |
| description: Fix GitHub Actions YAML syntax and job structure issues |
| difficulty: easy |
| num_scenarios: 5 |
|
|
| - id: workflow_secrets_permissions |
| name: Workflow Secrets and Permissions |
| description: Fix secret wiring, env usage, and permissions in workflows |
| difficulty: medium |
| num_scenarios: 5 |
|
|
| - id: ci_docker_integration |
| name: CI and Docker Build Integration |
| description: Debug combined workflow and Docker build integration failures |
| difficulty: medium-hard |
| num_scenarios: 5 |
|
|
| - id: multi_stage_pipeline_matrix |
| name: Multi-Stage Pipeline and Matrix |
| description: Debug complex multi-stage and matrix CI/CD pipelines |
| difficulty: hard |
| num_scenarios: 5 |
|
|
| - id: k8s_pod_failures |
| name: Kubernetes Pod Failures |
| description: Fix Kubernetes pod failures including CrashLoopBackOff, ImagePullBackOff, and resource issues |
| difficulty: medium |
| num_scenarios: 5 |
|
|
| - id: k8s_networking |
| name: Kubernetes Service & Ingress Issues |
| description: Fix Kubernetes networking issues including Service selectors, port mismatches, and Ingress configuration |
| difficulty: hard |
| num_scenarios: 5 |
|
|
| - id: pipeline_build_deploy |
| name: CI/CD Build & Push Pipeline |
| description: Debug GHA-to-Docker-to-Registry pipeline failures across multiple files |
| difficulty: hard |
| num_scenarios: 5 |
|
|
| - id: pipeline_full_stack |
| name: Full Stack Deployment Pipeline |
| description: Debug complex multi-error deployment pipelines across GHA workflows, Dockerfiles, and Kubernetes manifests |
| difficulty: expert |
| num_scenarios: 5 |
|
|
| graders: |
| dockerfile_syntax: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| dockerfile_runtime: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| workflow_syntax_structure: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| workflow_secrets_permissions: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| ci_docker_integration: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| multi_stage_pipeline_matrix: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| k8s_pod_failures: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| k8s_networking: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| pipeline_build_deploy: |
| type: deterministic |
| score_range: [0.0, 1.0] |
| pipeline_full_stack: |
| type: deterministic |
| score_range: [0.0, 1.0] |
|
|
| baseline: |
| script: inference.py |
| expected_scores: |
| dockerfile_syntax: 0.70 |
| dockerfile_runtime: 0.55 |
| workflow_syntax_structure: 0.65 |
| workflow_secrets_permissions: 0.50 |
| ci_docker_integration: 0.45 |
| multi_stage_pipeline_matrix: 0.30 |
| k8s_pod_failures: 0.50 |
| k8s_networking: 0.40 |
| pipeline_build_deploy: 0.35 |
| pipeline_full_stack: 0.20 |
|
|
| resources: |
| vcpu: 2 |
| memory: 8gb |
| timeout: 1200 |
|
|
