nisse/.gitea/workflows/ci.yml

name: CI
# Three levels of testing:
#   - every PR: lint, unit tests (16 property walks), integration tests, and
#     the smoke end-to-end tests (`smoke` marker);
#   - a PR labelled e2e:full, a push to main and a manual run: all 48 walks
#     and the whole end-to-end suite;
#   - a published release: the full set again before its image (release.yml).
on:
  # Only main on push. A PR branch is already covered by the pull_request
  # event, and running both fired two identical suites concurrently — which
  # doubled the LLM tokens the live tests spend and tripped the proxy's
  # per-minute limit.
  push:
    branches: [main]
  pull_request:
    # labeled: adding e2e:full runs the full set; any other label, nothing.
    types: [opened, synchronize, reopened, labeled]
  # Manual re-run, e.g. after rotating a credential or raising a budget cap.
  workflow_dispatch:

# A newer run for the same PR or branch cancels the one it supersedes: there
# is one runner, so a stale run would hold it (and the GPU) to the end. Adding
# a label other than e2e:full starts a run whose jobs all skip; it gets a
# group of its own, so it can't cancel the real one.
#
# Gitea triggers on `labeled` but hands the workflow its own name for the
# action, `label_updated` (and `synchronized` for a push), so each check
# below accepts both. Nor does it say which label was added
# (`github.event.label` is empty), so a label event counts when the PR now
# has e2e:full; adding another label to an e2e:full PR restarts its run.
concurrency:
  group: >-
    ${{ github.workflow }}-${{ github.head_ref || github.ref }}${{
    ((github.event.action == 'labeled' || github.event.action == 'label_updated')
    && !contains(github.event.pull_request.labels.*.name, 'e2e:full'))
    && format('-label-{0}', github.run_id) || '' }}
  cancel-in-progress: true

env:
  # Full on e2e:full, and outside PRs.
  FULL: ${{ github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'e2e:full') }}

jobs:
  checks:
    if: >-
      (github.event.action != 'labeled' && github.event.action != 'label_updated')
      || contains(github.event.pull_request.labels.*.name, 'e2e:full')
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - name: Install uv
        run: |
          curl -LsSf https://astral.sh/uv/install.sh | sh
          echo "$HOME/.local/bin" >> "$GITHUB_PATH"

      - name: Sync workspace
        run: uv sync --all-packages

      - name: Install sshd
        # The tests reach "the build VM" over real SSH, through a throwaway
        # sshd the test fixture starts (nisse_dev/testing.py). Skipped when the image has it; otherwise from
        # a kernel.org mirror: archive.ubuntu.com has been slow enough to add
        # minutes to every job.
        run: scripts/ci-sshd.sh

      - name: Lint
        run: uv run ruff check .

      - name: Format check
        run: uv run ruff format --check .

      - name: Unit tests
        # Across the runner's cores (pytest-xdist). On a PR, 16 property
        # walks from a seed that moves with the run number; all 48 otherwise.
        env:
          NISSE_WALK_SEEDS: ${{ env.FULL == 'true' && '48' || '16' }}
          NISSE_WALK_FIRST: ${{ env.FULL == 'true' && '0' || github.run_number }}
        run: uv run pytest -n auto -m "not integration and not e2e"

      - name: Integration tests
        # Everything but the secrets is in tests/integration/nisse-test.yaml,
        # which refers to these by name. A missing secret fails the live
        # tests that need it; it is never quietly turned into a skip.
        env:
          NISSE_LLM_TOKEN: ${{ secrets.NISSE_LLM_TOKEN }}
          NISSE_MATRIX_TOKEN: ${{ secrets.NISSE_MATRIX_TOKEN }}
          NISSE_GITEA_TOKEN: ${{ secrets.NISSE_GITEA_TOKEN }}
          # The test operator, who makes each run's repository (and its deploy
          # key) and deletes it afterwards.
          NISSE_OPERATOR_TOKEN: ${{ secrets.NISSE_OPERATOR_TOKEN }}
        run: uv run pytest -m "integration and not e2e" -rs

  e2e:
    # The end-to-end suite (scripts/e2e.sh): the whole agent against real
    # services, every role on a local model, so it spends nothing but keeps
    # the RTX 4090 busy: ~10 minutes for the smoke tests, ~25+ for all. On
    # PRs and manual runs, and only after the checks pass: a PR that's red
    # already doesn't spend the GPU. A newer push cancels a run it supersedes
    # (concurrency, above). Locally, run only what you're writing (-k) or
    # diagnosing (--lf).
    if: >-
      github.event_name != 'push'
      && ((github.event.action != 'labeled' && github.event.action != 'label_updated')
      || contains(github.event.pull_request.labels.*.name, 'e2e:full'))
    needs: checks
    runs-on: ubuntu-latest
    timeout-minutes: 90
    steps:
      - uses: actions/checkout@v4

      - name: Install uv
        run: |
          curl -LsSf https://astral.sh/uv/install.sh | sh
          echo "$HOME/.local/bin" >> "$GITHUB_PATH"

      - name: Sync workspace
        run: uv sync --all-packages

      - name: Install sshd
        # The build VM is a throwaway sshd here (scripts/e2e.sh --local). Skipped when the image has it; otherwise from
        # a kernel.org mirror: archive.ubuntu.com has been slow enough to add
        # minutes to every job.
        run: scripts/ci-sshd.sh

      - name: End-to-end tests
        env:
          NISSE_LLM_TOKEN: ${{ secrets.NISSE_LLM_TOKEN }}
          NISSE_MATRIX_TOKEN: ${{ secrets.NISSE_MATRIX_TOKEN }}
          NISSE_GITEA_TOKEN: ${{ secrets.NISSE_GITEA_TOKEN }}
          NISSE_OPERATOR_TOKEN: ${{ secrets.NISSE_OPERATOR_TOKEN }}
          NISSE_E2E_RUNS: /tmp/nisse-e2e-runs
        run: |
          if [ "$FULL" = true ]; then
            scripts/e2e.sh --local -v
          else
            scripts/e2e.sh --local -v -m "e2e and smoke"
          fi