Agentswarm/.github/workflows/ci.yml

name: CI

on:
  push:
    branches: ["**"]
  pull_request:
    branches: ["**"]

jobs:
  guardrails:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      # Defense in depth: fail if secrets or heavy/generated dirs were ever committed.
      - name: Block secrets & node_modules
        run: |
          if git ls-files | grep -E '(^|/)\.env($|\.)|(^|/)secrets/|\.pem$|\.key$|\.p12$|\.pfx$|(^|/)id_rsa$|(^|/)id_ed25519$'; then
            echo "::error::Secret-like files are tracked — remove them and rotate any exposed credential."; exit 1
          fi
          if git ls-files | grep -E '(^|/)node_modules/'; then
            echo "::error::node_modules is tracked — it must be gitignored."; exit 1
          fi

      - name: Required standards files present
        run: |
          for f in CLAUDE.md PROJECT_STANDARD.md README.md; do
            test -f "$f" || { echo "::error::Missing required file: $f"; exit 1; }
          done

  tests:
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"

      - name: Install dependencies
        run: |
          python -m pip install --upgrade pip
          pip install -r orchestrator/requirements.txt -r agent/requirements.txt

      # Hermetic: in-memory store, planner forced offline by the tests — no model key needed.
      - name: Manager contract test
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-runtime-contract.py

      - name: Workflow mechanism smoke test
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-merge-smoke.py

      - name: End-to-end workflow test
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-workflow-e2e.py

      - name: Per-user agent cap (MAX_AGENTS_PER_USER)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-max-agents-per-user.py

      - name: Swarm agent launcher (plan/limit/key-resolve) (#16)
        run: python scripts/test-agent-launcher.py

      - name: Manager event-contract test
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-contract-events.py

      - name: Usage review-retry cost attribution (#16)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-usage-cost-phase.py

      - name: Review/rework client timeline events (#34)
        env: { REDIS_FAKE: "1", MAX_REVIEW_CYCLES: "2" }
        run: python scripts/test-review-timeline-events.py

      - name: Audit / lineage trace (replayable) (#17)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-audit-trace.py

      - name: Benchmark metric formulas (v2.1)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-benchmark-metrics.py

      - name: Benchmark collector
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-benchmark-collector.py

      - name: Baseline comparison
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-baseline-comparison.py

      - name: Code sandbox (in-pod test runner)
        run: python scripts/test-sandbox.py

      - name: Security boundary enforcement (secret/workspace/sandbox) (#19)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-security-boundary.py

      - name: Quality instrumentation (Group B)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-quality.py

      - name: Decision-engine pheromone library (τ)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-decision-engine.py

      - name: Dispatch scoring formulas
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-dispatch-score.py

      # --- decentralized swarm flow (the only flow; primitives are unconditional) ---
      - name: Swarm seeder (#6)
        run: python scripts/test-swarm-seed.py

      - name: Swarm self-selection dispatch
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-swarm-dispatch.py

      - name: Swarm autonomous task generation (#7)
        env: { REDIS_FAKE: "1", AGENT_PROPOSAL_BUDGET: "3" }
        run: python scripts/test-swarm-autonomous.py

      - name: Swarm task competition (#8)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-swarm-competition.py

      - name: Swarm cross-review (#11)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-swarm-cross-review.py

      - name: Swarm convergence (#12)
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-swarm-convergence.py

      - name: Swarm health guard
        env: { REDIS_FAKE: "1" }
        run: python scripts/test-swarm-guard.py

      # Pure-module unit tests for the swarm primitives (formulas/policies, infra-free).
      - name: Swarm primitive modules (unit)
        env: { REDIS_FAKE: "1" }
        run: |
          python scripts/test-autonomous-tasks.py
          python scripts/test-task-competition.py
          python scripts/test-cross-review.py
          python scripts/test-convergence.py

      # --- benchmark baseline runners + suite smoke (Group C, #21) ---
      # HEICODE_SANDBOX_ISOLATED: the runners grade generated code in the fail-closed sandbox; the
      # CI runner is ephemeral/isolated, so confirm isolation here (see security-boundary §8.1).
      - name: Benchmark runners (Group C)
        env: { HEICODE_SANDBOX_ISOLATED: "1" }
        run: python scripts/test-benchmark-runners.py

      # Offline = pipeline validation only (deterministic, no real G_E). Guards against regressions.
      - name: Benchmark suite smoke (offline)
        env: { HEICODE_SANDBOX_ISOLATED: "1" }
        run: python scripts/run-benchmark-suite.py --taskset coding-set-1