code-test.yml

name: Code Test

on:
  push:
    branches:
      - "release/v[0-9].[0-9]"
      - main
  pull_request:
    branches: [main]
    types: [synchronize, labeled]
  workflow_dispatch:

concurrency:
  group: code-test-${{ github.ref }}
  cancel-in-progress: true

jobs:
  # =============================================== check changes ====================================================
  check-changes:
    runs-on: ubuntu-latest
    outputs:
      file_filter: ${{ steps.filter.outputs.file_filter }}
    steps:
      - name: Checkout code
        uses: actions/checkout@v4

      - name: Fail if the PR does not have the 'run-ci' label
        if: github.event_name == 'pull_request' && !contains(github.event.pull_request.labels.*.name, 'run-ci')
        run: |
          echo "This pull request does not have the 'run-ci' label. Failing the workflow."
          exit 1

      - name: Fail if the PR is a draft
        if: github.event_name == 'pull_request' && github.event.pull_request.draft == true
        run: |
          echo "This pull request is a draft. Failing the workflow."
          exit 1

      - name: Detect file changes
        id: filter
        uses: dorny/paths-filter@v3
        with:
          filters: |
            file_filter:
              - '**/*.py'
              - 'tests/**'
              - '.github/workflows/*.yml'
              - '!docs/**'
              - '!README.md'
              - '*.yaml'
              - '*.toml'
              - '!ray_utils/**'
              - '!requirements/**'

  # =============================================== unit tests ====================================================

  unit-tests-cuda:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Install pytest
        run: |
          source switch_env reason
          uv pip install pytest

      - name: Run pytest
        timeout-minutes: 20
        run: |
          export PYTHONPATH=$(pwd):$(pwd)/megatron:$(pwd)/tests/unit_tests
          source switch_env reason
          pytest tests/unit_tests

      - name: Run doctest
        timeout-minutes: 20
        run: |
          source switch_env reason
          pytest --doctest-modules rlinf/scheduler

  unit-tests-cpu:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: ubuntu-latest
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Install dependencies
        run: |
          pip install uv
          uv venv
          source .venv/bin/activate
          UV_TORCH_BACKEND=auto uv sync
          uv pip install pytest

      - name: Run pytest
        timeout-minutes: 20
        run: |
          export PYTHONPATH=$(pwd):$(pwd)/megatron:$(pwd)/tests/unit_tests 
          source .venv/bin/activate
          pytest tests/unit_tests

  # =============================================== reason e2e tests ====================================================

  reason-qwen-grpo-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Megatron SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-mg-sgl

      - name: Megatron vLLM Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-mg-vllm

      - name: Megatron SGLang Pipeline mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-pipeline-mg-sgl

      - name: Megatron vLLM Pipeline mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-pipeline-mg-vllm

      - name: FSDP SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-fsdp-sgl

      - name: FSDP vLLM Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-fsdp-vllm


  reason-qwen-grpo-test-rollout-logprobs:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Megatron SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-mg-sgl-rollout-logprobs

      - name: Megatron vLLM Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-mg-vllm-rollout-logprobs

      - name: Megatron SGLang Pipeline mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-pipeline-mg-sgl-rollout-logprobs

      - name: Megatron vLLM Pipeline mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-pipeline-mg-vllm-rollout-logprobs

      - name: FSDP SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-fsdp-sgl-rollout-logprobs

      - name: FSDP vLLM Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-1.5b-grpo-collocated-fsdp-vllm-rollout-logprobs

  coding-online-rl-qwen-ppo-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: Install dependencies
        run: |
          pip install httpx asyncio fuzzywuzzy

      - name: SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/coding_online_rl/run.sh

  qwen-vl-grpo-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: FSDP SGLang Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-vl-3b-grpo-collocated-fsdp-sgl

      - name: FSDP vLLM Collocated mode
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/reasoning/run.sh qwen2.5-vl-3b-grpo-collocated-fsdp-vllm

  # =============================================== embodied e2e tests ====================================================

  embodied-maniskill-ppo-openvla-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: embodied
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
      - name: OpenVLA test
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env openvla
          bash tests/e2e_tests/embodied/run.sh maniskill_ppo_openvla
          
  embodied-maniskill-grpo-openvlaoft-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: embodied
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
      - name: OpenVLA test
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env openvla-oft
          cp -r /workspace/dataset/maniskill_assets/assets ${REPO_PATH}/rlinf/envs/maniskill/
          bash tests/e2e_tests/embodied/run.sh maniskill_grpo_openvlaoft

  embodied-libero-goal-grpo-openvlaoft-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: embodied
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
      - name: OpenVLA-OFT test
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env openvla-oft
          bash tests/e2e_tests/embodied/run.sh libero_goal_grpo_openvlaoft

  embodied-libero-130-grpo-openvlaoft-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: embodied
    steps:
      - name: Checkout code
        uses: actions/checkout@v5
      - name: OpenVLA-OFT test
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env openvla-oft
          bash tests/e2e_tests/embodied/run.sh libero_130_grpo_openvlaoft

  # =============================================== auto placement tests ====================================================

  static-auto-placement-test:
    needs: [check-changes]
    if: needs.check-changes.outputs.file_filter == 'true'
    runs-on: reason
    steps:
      - name: Checkout code
        uses: actions/checkout@v5

      - name: auto-placement
        timeout-minutes: 20
        run: |
          export REPO_PATH=$(pwd)
          source switch_env reason
          bash tests/e2e_tests/auto_placement/run.sh

# =============================================== finale ====================================================

  pr-test-finish:
    needs: [
      check-changes,

      # Unit tests
      unit-tests-cuda, unit-tests-cpu,

      # Reason e2e tests
      reason-qwen-grpo-test, reason-qwen-grpo-test-rollout-logprobs,
      coding-online-rl-qwen-ppo-test, qwen-vl-grpo-test,

      # Embodied e2e tests
      embodied-maniskill-ppo-openvla-test, embodied-maniskill-grpo-openvlaoft-test, embodied-libero-goal-grpo-openvlaoft-test,embodied-libero-130-grpo-openvlaoft-test,

      # Auto placement tests
      static-auto-placement-test
    ]
    if: always()
    runs-on: ubuntu-latest
    steps:
      # Refer to https://github.com/sgl-project/sglang/blob/main/.github/workflows/pr-test.yml
      - name: Check all dependent job statuses
        run: |
          # Convert the 'needs' context to a JSON string
          json_needs='${{ toJson(needs) }}'

          # Get a list of all job names from the JSON keys
          job_names=$(echo "$json_needs" | jq -r 'keys_unsorted[]')

          for job in $job_names; do
            # For each job, extract its result
            result=$(echo "$json_needs" | jq -r --arg j "$job" '.[$j].result')

            # Print the job name and its result
            echo "$job: $result"

            # Check for failure or cancellation and exit if found
            if [[ "$result" == "failure" || "$result" == "cancelled" ]]; then
              echo "The above jobs failed."
              exit 1
            fi
          done

          # If the loop completes, all jobs were successful
          echo "All jobs completed successfully"
          exit 0