OmniRoute/.github/workflows/nightly-mutation.yml

name: Nightly Mutation
on:
  schedule:
    - cron: "17 3 * * *"
  workflow_dispatch:

permissions:
  contents: read

jobs:
  stryker:
    name: Stryker mutation (batch ${{ matrix.batch.name }} — advisory)
    runs-on: ubuntu-latest
    # Mutation testing is expensive. History of the budget:
    #   - Full 8-module set TIMED OUT at the 180min cap (run 27705123780 = exactly 180min).
    #     The two god-files chatCore.ts/combo.ts dominated ~2/3 of the mutants and were
    #     removed from stryker.conf.json `mutate`.
    #   - The remaining 6 modules in 3 batches: auth.ts and accountFallback.ts are large; the
    #     a (auth+publicCreds) and b (accountFallback+error) batches still ran near the 180min
    #     cap (the perTest dry-run over ~130 covering test files is itself costly), so the two
    #     big modules are now ISOLATED into their own batches (a=auth, b=accountFallback).
    #   - Onda 3 / Fase 9 T5 re-add: combo.ts was split into 11 leaves; the 8 well-covered
    #     combo/* leaves are back in `mutate` (covered by the 24 combo-*.test.ts), grouped into
    #     2 batches (d=heavy, e=light). After #4204 (D7b) merged, the reset-aware quota pair
    #     quotaScoring/quotaStrategies was added as batch f. A covering-test audit then added the
    #     6 chatCore/* leaves with direct unit coverage as batch g. A follow-up then wrote dedicated
    #     unit tests for 6 more leaves and added them as batch h. A final follow-up added dedicated
    #     tests (no mock.module — fetch-override + crafted inputs + temp-DATA_DIR) for telemetryHelpers
    #     + memorySkillsInjection + semanticCache (its cache-HIT block now has a setCachedResponse
    #     fixture) as batch i — ALL 15/15 chatCore leaves are now mutated. See
    #     _mutate_godfiles_excluded_comment in stryker.conf.json.
    # 9 PARALLEL batches, each overriding the mutate set via `--mutate` (Stryker 9 CLI:
    # `-m, --mutate <comma-list>`; the conf's `mutate[]` remains the local-run default/union).
    #   - Cold-seeding budget (per-batch `timeout-minutes: ${{ matrix.batch.timeout || 180 }}`):
    #     a COLD run must COMPLETE once to write stryker-incremental.json (Stryker writes it only on
    #     a successful finish); a job cancelled at the cap writes nothing, so the next run is cold
    #     again — an infinite never-seeds loop. actions/cache is also branch-scoped, so each branch
    #     (incl. release) must seed its OWN cache via a run with enough headroom. Measured cold runs
    #     (run 27801802713): a/b never finished even isolated; c=180min CANCELLED (4 modules),
    #     d=180min CANCELLED (3 combo modules), g=142min, h=132min, e=66, f=45, i=33. So a/b/c/d get
    #     350min (job max 360) and g/h a 240min variance buffer; once seeded, later nightlies only
    #     re-test changed mutants and fit well under the default. NOTE: batch c's old "2 modules ~2h"
    #     assumption went stale when c grew to 4 modules — keep this budget in sync with the matrix.
    # Full coverage every night in parallel; wall-clock = the slowest batch's cold run until seeded.
    # Runs at stryker concurrency=4 with per-process DATA_DIR isolation
    # (tests/_setup/isolateDataDir.ts) — see _concurrency_comment in stryker.conf.json.
    strategy:
      fail-fast: false
      matrix:
        batch:
          # Per-batch `timeout` (minutes) tiers the cold-seeding budget by measured cost — see the
          # cold-run measurements in the comment above. Batches without the key default to 180.
          # a/b (large isolated modules) + c/d (4 and 3 modules, observed to exceed 180min cold) get
          # 350 (GitHub-hosted job max is 360); g/h (142/132min cold — within runner-variance distance
          # of the 180 cap) get a 240 buffer. e/f/i (33-66min) stay at the 180 default.
          - name: a
            mutate: "src/sse/services/auth.ts"
            timeout: 350
          - name: b
            mutate: "open-sse/services/accountFallback.ts"
            timeout: 350
          - name: c
            mutate: "src/server/authz/routeGuard.ts,src/shared/utils/circuitBreaker.ts,open-sse/utils/error.ts,open-sse/utils/publicCreds.ts"
            timeout: 350
          - name: d
            mutate: "open-sse/services/combo/comboStructure.ts,open-sse/services/combo/autoStrategy.ts,open-sse/services/combo/validateQuality.ts"
            timeout: 350
          - name: e
            mutate: "open-sse/services/combo/shadowRouting.ts,open-sse/services/combo/targetSorters.ts,open-sse/services/combo/comboPredicates.ts,open-sse/services/combo/rrState.ts,open-sse/services/combo/comboData.ts"
          - name: f
            mutate: "open-sse/services/combo/quotaScoring.ts,open-sse/services/combo/quotaStrategies.ts"
          - name: g
            mutate: "open-sse/handlers/chatCore/comboContextCache.ts,open-sse/handlers/chatCore/idempotency.ts,open-sse/handlers/chatCore/passthroughHelpers.ts,open-sse/handlers/chatCore/responseHeaders.ts,open-sse/handlers/chatCore/sanitization.ts,open-sse/handlers/chatCore/upstreamTimeouts.ts"
            timeout: 240
          - name: h
            mutate: "open-sse/handlers/chatCore/headers.ts,open-sse/handlers/chatCore/logTruncation.ts,open-sse/handlers/chatCore/memoryExtraction.ts,open-sse/handlers/chatCore/nonStreamingSse.ts,open-sse/handlers/chatCore/passthroughToolNames.ts,open-sse/handlers/chatCore/executorHelpers.ts"
            timeout: 240
          - name: i
            mutate: "open-sse/handlers/chatCore/telemetryHelpers.ts,open-sse/handlers/chatCore/memorySkillsInjection.ts,open-sse/handlers/chatCore/semanticCache.ts"
    # Per-batch budget: a/b/c/d override to 350min, g/h to 240min; the rest default to 180min.
    # `matrix.batch.timeout` is null for batches without the key -> `|| 180`.
    timeout-minutes: ${{ matrix.batch.timeout || 180 }}
    steps:
      - uses: actions/checkout@v6
        with:
          persist-credentials: false
      - uses: actions/setup-node@v6
        with:
          node-version: "24"
          cache: npm
      - run: npm ci
      - name: Restore Stryker incremental cache
        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae # v5.0.5
        with:
          path: reports/mutation/stryker-incremental.json
          key: stryker-incremental-${{ matrix.batch.name }}-${{ github.run_id }}
          restore-keys: stryker-incremental-${{ matrix.batch.name }}-
      - name: Run Stryker (advisory)
        id: stryker
        continue-on-error: true
        env:
          BATCH_MUTATE: ${{ matrix.batch.mutate }}
        run: npx stryker run --mutate "$BATCH_MUTATE"
      - name: Upload mutation report
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: mutation-report-${{ matrix.batch.name }}
          path: reports/mutation/
          if-no-files-found: warn
          retention-days: 14