agent-runtime-framework/workflows/write-tests.yaml

name: write-tests
version: 1
description: >
  Two-node spec-driven test writing workflow. First node writes tests from the spec
  (one test per requirement, edge cases, property tests where applicable). Second node
  reviews coverage — checking every numbered requirement has a corresponding test and
  flagging any gaps.

  Output: test files committed to the agent-repo branch; coverage gap report in the
  review node's output artifact.

params:
  required:
    spec_file:
      type: string
      description: "Path to the spec file in the repo (e.g. spec/my-feature.md)"
    project_id:
      type: string
      description: "Target project identifier"
    repo_url:
      type: string
      description: "Git repo URL containing the spec"
    agent_repo_url:
      type: string
      description: "Agent repo URL for branch-per-task output persistence"
  optional:
    task_description:
      type: string
      default: ""
      description: "Additional context about what is being tested (supplements the spec)"
    test_output_dir:
      type: string
      default: "tests/"
      description: "Directory to write test files into (default: tests/)"
    test_framework:
      type: string
      default: "pytest"
      description: "Test framework to use (default: pytest)"
    writer_harness:
      type: string
      default: "test-writing-opus-repo/v1"
      description: "Harness for the test-writing node (default: test-writing-opus-repo/v1)"
    reviewer_harness:
      type: string
      default: "planning-minimax-repo/v1"
      description: "Harness for the coverage review node (default: planning-minimax-repo/v1)"

nodes:
  write_tests:
    name: "Write tests from spec"
    reference_branches:
      - repo_url: "{{ repo_url }}"
        branch: main
        name: main
    prompt: |
      You are writing a test suite from a spec file. Tests are the contract — they will
      be run against an agent's implementation. Write them now, before the implementation exists.

      ## Spec file
      Read the spec at `/workspace/reference/main/{{ spec_file }}`.

      {% if task_description %}
      ## Additional context
      {{ task_description }}
      {% endif %}

      ## Instructions
      1. Read the spec carefully. Identify every numbered requirement (e.g. MY-1, MY-2...).
      2. For each requirement, write at least one test function named `test_<req_id>_<short_description>`.
      3. Cover edge cases explicitly — empty inputs, boundary values, error paths.
      4. Add property-based tests (Hypothesis) where the requirement involves ranges or invariants.
      5. Write tests to `/workspace/project/{{ test_output_dir }}` — one file per logical group (mirrors spec sections).
      6. Use `{{ test_framework }}` conventions. Tests should fail immediately (no implementation exists).
      7. Do NOT write any implementation code. Only test files.

      After writing all tests, write a coverage summary to `/workspace/project/output.md`:
      - List every requirement ID from the spec
      - For each: which test function(s) cover it
      - Note any requirements you could not write a test for (and why)
    harness: "{{ writer_harness }}"
    requirements:
      min_scores:
        spec_adherence: 9
        test_pass_rate: 8

  review_coverage:
    name: "Review test coverage"
    depends_on: [write_tests]
    reference_branches:
      - repo_url: "{{ repo_url }}"
        branch: main
        name: main
    prompt: |
      You are reviewing the coverage of a freshly written test suite against its spec.

      ## Spec file
      Read the spec at `/workspace/reference/main/{{ spec_file }}`.

      ## Test summary written by the previous agent
      <<ARTIFACT:write_tests:output>>

      ## Instructions
      1. Read the spec and extract every numbered requirement.
      2. Cross-reference each requirement against the test summary above.
      3. For each requirement, determine: fully covered / partially covered / not covered.
      4. Flag any test functions that appear to test behaviour NOT in the spec (over-specification).

      Write your review to `/workspace/project/output.md` as:

      ```json
      {
        "covered": ["REQ-1", "REQ-2"],
        "partial": [{"id": "REQ-3", "reason": "happy path only, error case missing"}],
        "missing": ["REQ-4", "REQ-5"],
        "over_specified": ["test_something_not_in_spec"],
        "summary": "one paragraph"
      }
      ```

      Then list specific, actionable improvements for any partial or missing coverage.
    harness: "{{ reviewer_harness }}"
    requirements:
      min_scores:
        complexity: 8
        spec_adherence: 9