/.github/workflows/harness.yml

name: Harness (E2E)

# Runs the end-to-end harnesses for agents, services, flows, and provider
# conformance. The default job uses deterministic mock LLMs and needs no
# secrets. A second job runs the same harnesses against the live provider set and
# skips providers whose secrets are absent, so scheduled conformance
# remains safe in no-key forks while still failing configured providers that drift.

on:
  push:
    branches: ["**"]
  pull_request:
    branches: ["**"]
  schedule:
    - cron: "17 6 * * *" # daily, so the world is exercised even without changes
  workflow_dispatch:

jobs:
  harness:
    name: Harnesses (mock LLM)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-go@v5
        with:
          go-version: stable
          cache: true
      - name: Build
        run: go build ./...
      - name: 0→1 scaffold contract
        run: go test ./cmd/micro/cli/new -run TestZeroToOneContract -count=1
      - name: Universe end-to-end (asserts; exits non-zero on failure)
        run: go run ./internal/harness/universe
      - name: Agent-flow harness
        run: go run ./internal/harness/agent-flow
      - name: 0→hero run/chat/inspect reference scenario
        run: ./internal/harness/zero-to-hero-ci/run.sh

  harness-live:
    name: Provider harnesses (live LLM conformance)
    runs-on: ubuntu-latest
    # Only on the daily schedule or a manual run — never automatically on
    # every push/PR, so changes don't quietly burn API credits. Trigger it
    # by hand (Actions → Harness → Run workflow) when changing the agent,
    # flow, or AI internals and you want a real-model check.
    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-go@v5
        with:
          go-version: stable
          cache: true
      - name: Agent provider conformance matrix
        env:
          GO_MICRO_AGENT_CONFORMANCE_LIVE: "1"
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
          ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}
        run: go test ./agent -run TestAgentProviderConformanceMatrix -count=1 -v
      - name: Provider conformance against live models
        env:
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          GEMINI_API_KEY: ${{ secrets.GEMINI_API_KEY }}
          GROQ_API_KEY: ${{ secrets.GROQ_API_KEY }}
          MISTRAL_API_KEY: ${{ secrets.MISTRAL_API_KEY }}
          TOGETHER_API_KEY: ${{ secrets.TOGETHER_API_KEY }}
          ATLASCLOUD_API_KEY: ${{ secrets.ATLASCLOUD_API_KEY }}
        run: |
          go run ./internal/harness/provider-conformance \
            -summary-json provider-conformance-summary.json \
            -summary-markdown provider-conformance-summary.md \
            -capabilities-markdown provider-capabilities.md
      - name: Publish provider conformance summary
        if: always()
        run: |
          if [ -f provider-conformance-summary.md ]; then
            cat provider-conformance-summary.md >> "$GITHUB_STEP_SUMMARY"
          fi
          if [ -f provider-capabilities.md ]; then
            {
              echo
              echo "## Registered provider capabilities"
              echo
              cat provider-capabilities.md
            } >> "$GITHUB_STEP_SUMMARY"
          fi
      - name: Upload provider conformance summary
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: provider-conformance
          path: |
            provider-conformance-summary.json
            provider-conformance-summary.md
            provider-capabilities.md
          if-no-files-found: ignore