GitNexus/.github/workflows/ci-tests.yml

name: Tests

on:
  workflow_call:

permissions:
  contents: read

jobs:
  # Ubuntu full-suite coverage, sharded. Each shard writes a vitest blob report
  # (carrying its slice of V8 coverage) with thresholds forced OFF — a single
  # shard's partial coverage can't meet the gate. The coverage-merge job below
  # reduces the blobs and enforces the real thresholds on the combined coverage.
  # FTS self-installs per shard (test/helpers/fts-availability.ts), so sharding
  # the full suite across fresh runners is safe. Shard count: shard-plan.cov_total.
  tests:
    name: ubuntu / coverage ${{ matrix.shard }}/${{ needs.shard-plan.outputs.cov_total }}
    needs: shard-plan
    runs-on: ubuntu-latest
    timeout-minutes: 25
    strategy:
      fail-fast: false
      matrix:
        shard: ${{ fromJSON(needs.shard-plan.outputs.cov_shards) }}
    # Fail loudly (don't silently skip) if the FTS extension is unavailable, so
    # FTS-dependent lbug integration suites are guaranteed to run in CI.
    env:
      GITNEXUS_REQUIRE_FTS: '1'
    steps:
      # persist-credentials: false — runs tests + uploads a blob artifact; the
      # default-persisted token must not be capturable through it (zizmor
      # credential-persistence / artipacked audit). The job never pushes.
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'
      # Warm-cache the FTS extension (same per-OS key as the cross-platform job)
      # and install it up front, so every coverage shard has FTS in ~/.lbdb before
      # any test module loads. The file-path FTS gate (extension-binary-real)
      # resolves the extension at module load and can't self-install, so sharding
      # could otherwise drop it into a shard with no installer sibling.
      - name: Cache LadybugDB FTS extension
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v5
        with:
          path: ~/.lbdb/extension
          key: lbug-fts-${{ runner.os }}-${{ hashFiles('gitnexus/package-lock.json') }}
      - name: Ensure FTS + VECTOR extensions installed
        run: npx tsx scripts/ensure-fts.ts
        working-directory: gitnexus
      - name: Run sharded tests with coverage (blob)
        # Shard via env var (not `${{ }}` inlined into the shell) so it isn't a
        # template-injection sink; shell: bash makes "$SHARD" expand uniformly.
        # Thresholds forced to 0 — the merge job enforces the real gate on the
        # MERGED coverage; a single shard's partial coverage would always fail.
        shell: bash
        env:
          SHARD: ${{ matrix.shard }}/${{ needs.shard-plan.outputs.cov_total }}
        run: >-
          npx vitest run
          --shard="$SHARD"
          --reporter=default
          --reporter=blob
          --coverage
          --coverage.thresholds.lines=0
          --coverage.thresholds.functions=0
          --coverage.thresholds.branches=0
          --coverage.thresholds.statements=0
        working-directory: gitnexus
      - name: Upload coverage blob
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: coverage-blob-${{ matrix.shard }}
          path: gitnexus/.vitest-reports/
          # .vitest-reports is a dotdir; upload-artifact excludes hidden files by
          # default, which would upload an empty artifact and break the merge.
          include-hidden-files: true
          retention-days: 5

  # Merge the sharded coverage blobs into one report and enforce the real
  # thresholds on the combined ('new') coverage — `vitest --mergeReports` re-runs
  # nothing, it just reduces the stored blobs. Also emits the merged
  # test-results.json and runs the (unsharded) web + docker suites, so the
  # `test-reports` artifact keeps the exact shape ci-report.yml consumes for its
  # base-branch ('baseline') vs new coverage delta.
  coverage-merge:
    name: ubuntu / coverage merge
    needs: tests
    runs-on: ubuntu-latest
    timeout-minutes: 15
    env:
      GITNEXUS_REQUIRE_FTS: '1'
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'
      - name: Download coverage blobs
        uses: actions/download-artifact@3e5f45b2cfb9172054b4087a40e8e0b5a5461e7c # v8
        with:
          pattern: coverage-blob-*
          path: gitnexus/.vitest-reports
          merge-multiple: true
      - name: Merge coverage + enforce thresholds
        run: >-
          npx vitest --mergeReports
          --reporter=default
          --reporter=json
          --outputFile=test-results.json
          --coverage
          --coverage.reporter=json-summary
          --coverage.reporter=json
          --coverage.reporter=text
          --coverage.thresholdAutoUpdate=false
        working-directory: gitnexus
      # gitnexus-shared already built by setup-gitnexus above
      - name: Install gitnexus-web dependencies
        run: npm ci
        working-directory: gitnexus-web
      - name: Run gitnexus-web unit tests
        run: >-
          npx vitest run
          --reporter=default
          --reporter=json
          --outputFile=web-test-results.json
        working-directory: gitnexus-web
      - name: Run docker-server integration tests
        run: node --test docker-server.test.mjs
      - name: Upload test reports
        if: always()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a # v7.0.1
        with:
          name: test-reports
          path: |
            gitnexus/coverage/coverage-summary.json
            gitnexus/coverage/coverage-final.json
            gitnexus/test-results.json
            gitnexus-web/web-test-results.json
          retention-days: 5

  # Single source of truth for the platform-sensitive shard count. TOTAL below
  # generates both the shard index list (the matrix) and the /N denominator (job
  # name + --shard arg), so they can't drift — bump the shard count by editing
  # TOTAL alone. Checkout-free (ubuntu ships jq), so no credential surface.
  shard-plan:
    runs-on: ubuntu-latest
    outputs:
      shards: ${{ steps.gen.outputs.shards }}
      total: ${{ steps.gen.outputs.total }}
      cov_shards: ${{ steps.gen.outputs.cov_shards }}
      cov_total: ${{ steps.gen.outputs.cov_total }}
    steps:
      - id: gen
        run: |
          TOTAL=3         # cross-platform (windows/macOS) shards per OS
          COV_TOTAL=3     # ubuntu coverage shards (merged before thresholds)
          if [ "$TOTAL" -lt 1 ] || [ "$COV_TOTAL" -lt 1 ]; then
            echo "shard totals must be >= 1" >&2; exit 1
          fi
          {
            echo "shards=$(jq -nc --argjson n "$TOTAL" '[range(1; $n + 1)]')"
            echo "total=$TOTAL"
            echo "cov_shards=$(jq -nc --argjson n "$COV_TOTAL" '[range(1; $n + 1)]')"
            echo "cov_total=$COV_TOTAL"
          } >> "$GITHUB_OUTPUT"

  # Platform-sensitive subset only — the full suite runs on Ubuntu above.
  # See gitnexus/scripts/cross-platform-tests.ts for the file list and
  # rationale for each included test.
  cross-platform:
    name: ${{ matrix.os }} (platform-sensitive) ${{ matrix.shard }}/${{ needs.shard-plan.outputs.total }}
    needs: shard-plan
    strategy:
      fail-fast: false
      matrix:
        # Ubuntu already covered by the coverage job above
        os: [windows-latest, macos-latest]
        # Shard the fixed file list across N runners per OS (N = TOTAL in the
        # shard-plan job). The suite is dominated by ~50 CLI/worker process
        # spawns and Windows is ~5x slower than macOS at those, so the unsharded
        # run crept past the 15-min watchdog in run-cross-platform.ts. vitest
        # shards by file COUNT, not runtime, so the heaviest spawn suites can
        # cluster on one shard. The busiest Windows shard has grown to the old
        # 15-minute watchdog (14m57s on the v1.6.10-rc.19 green run, one
        # observed timeout since — #2449), so the job env below raises the
        # per-shard watchdog to 20 minutes, still bounded by timeout-minutes.
        # Shard indices come from the shard-plan job (single source of truth):
        # its TOTAL drives this list and the /N in the job name + --shard arg.
        shard: ${{ fromJSON(needs.shard-plan.outputs.shards) }}
    runs-on: ${{ matrix.os }}
    timeout-minutes: 25
    # Same guarantee on the platform-sensitive runners: FTS-dependent suites in
    # the cross-platform subset must run, not silently skip.
    #
    # GITNEXUS_E2E_CLI=dist: the e2e suites spawn the CLI ~50 times; each spawn via
    # `node --import tsx src/cli/index.ts` re-transpiles the whole CLI, and Windows
    # is ~5x slower at process startup. `build: true` below produces a fresh dist
    # before tests, so opting these runners into the built CLI removes that
    # per-spawn transpile (see test/helpers/cli-entry.ts). Deliberately scoped to
    # THIS job: the Ubuntu coverage job leaves it unset, so it keeps exercising the
    # tsx-on-source path in CI (both entry points stay covered).
    env:
      GITNEXUS_REQUIRE_FTS: '1'
      # #2623: the win32 VECTOR gate is gone, so the vector suites genuinely
      # run here — require the extension so an unavailable VECTOR is a loud
      # failure, never a silent skip (same contract as GITNEXUS_REQUIRE_FTS).
      GITNEXUS_REQUIRE_VECTOR: '1'
      GITNEXUS_E2E_CLI: dist
      # #2449: hosted Windows runners intermittently push the busiest shard past
      # the default 15-minute watchdog. 20 minutes restores real headroom while
      # the 25-minute job timeout above still bounds a genuine hang.
      GITNEXUS_CROSS_PLATFORM_TIMEOUT_MINUTES: '20'
    steps:
      # persist-credentials: false — runs tests only, never pushes (zizmor
      # credential-persistence / artipacked audit).
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'
      # Warm-cache the installed LadybugDB FTS + VECTOR extensions
      # (~/.lbdb/extension) per OS + lockfile so a warm run skips the network
      # install entirely, and the parallel shards share one download across
      # runs. Pure reliability/speed: on a cache miss the tests self-install on
      # demand (see test/helpers/fts-availability.ts), so a miss just falls
      # back to install — never a correctness dependency. Keyed by lockfile
      # hash so a LadybugDB version bump re-installs; per-OS because the
      # extensions are native binaries. (Key name kept as lbug-fts for cache
      # continuity — the path covers every extension in the shared home.)
      - name: Cache LadybugDB FTS extension
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9 # v5
        with:
          path: ~/.lbdb/extension
          key: lbug-fts-${{ runner.os }}-${{ hashFiles('gitnexus/package-lock.json') }}
      - name: Ensure FTS + VECTOR extensions installed
        run: npx tsx scripts/ensure-fts.ts
        working-directory: gitnexus
      - name: Run platform-sensitive tests
        # Pass the shard through an env var (not `${{ }}` inlined into the shell)
        # so it isn't a template-injection sink (zizmor). shell: bash makes the
        # `"$SHARD"` expansion uniform across the windows + macOS matrix (the
        # default run shell is pwsh on Windows, where `$SHARD` would be empty).
        shell: bash
        env:
          SHARD: ${{ matrix.shard }}/${{ needs.shard-plan.outputs.total }}
        run: npx tsx scripts/run-cross-platform.ts --shard="$SHARD"
        working-directory: gitnexus

  # Tree-sitter ABI gate (#1922). Two halves, both blocking:
  #   1. Static, offline: assert every grammar's compiled ABI loads on the
  #      pinned runtime (check-tree-sitter-upgrade-readiness.py --assert-current).
  #   2. Dynamic: run the parser-loader ABI load-smoke on the OS matrix so an
  #      ABI-incompatible committed vendor prebuilt (e.g. Swift's — the static
  #      check introspects source, not the shipped .node) fails on the platform
  #      it ships to.
  abi-assert:
    name: tree-sitter ABI (${{ matrix.os }})
    strategy:
      fail-fast: false
      matrix:
        os: [ubuntu-latest, windows-latest, macos-latest]
    runs-on: ${{ matrix.os }}
    timeout-minutes: 20
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'

      - name: Assert installed + vendored grammar ABIs (static)
        shell: bash
        run: python3 .github/scripts/check-tree-sitter-upgrade-readiness.py --assert-current

      - name: Run parser-loader ABI load-smoke (dynamic)
        run: npx vitest run test/unit/parser-loader-abi.test.ts
        working-directory: gitnexus

  # End-to-end smoke test for the #1728 packaging fix: pack the published
  # tarball, install it globally into a temp prefix, and assert no junction
  # creation (the EPERM root cause) plus working CLI plus vendor cleanliness
  # (#836). Runs on windows-latest because that is the platform the fix
  # targets; the in-repo `npm ci` job above only exercises the dev-tree path
  # and skips the tarball reify step where the historical EPERM occurred.
  packaged-install-smoke:
    name: packaged install smoke (${{ matrix.os }})
    strategy:
      fail-fast: false
      matrix:
        os: [windows-latest, ubuntu-latest]
    runs-on: ${{ matrix.os }}
    timeout-minutes: 15
    steps:
      # persist-credentials: false — this job runs npm pack + npm install -g
      # from a tarball and never pushes back; the token in .git/config would
      # be at risk of leaking through any future artifact-upload step
      # (zizmor artipacked audit). Disable upfront.
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'

      - name: Pack gitnexus tarball
        shell: bash
        run: npm pack
        working-directory: gitnexus

      - name: Install gitnexus tarball into isolated prefix
        shell: bash
        run: |
          set -euo pipefail
          PREFIX="$RUNNER_TEMP/gitnexus-smoke"
          mkdir -p "$PREFIX"
          TARBALL=$(find . -maxdepth 1 -name 'gitnexus-*.tgz' -print -quit)
          if [ -z "$TARBALL" ]; then
            echo "ERROR: no gitnexus-*.tgz tarball found in $(pwd)" >&2
            exit 1
          fi
          echo "Installing $TARBALL into $PREFIX"
          npm install -g --prefix "$PREFIX" "./$TARBALL" --no-audit --no-fund
          echo "PREFIX=$PREFIX" >> "$GITHUB_ENV"
        working-directory: gitnexus

      - name: Assert no junctions or vendor build artifacts
        shell: bash
        run: |
          set -euo pipefail
          # Locate the installed gitnexus package across npm prefix layouts
          # (lib/node_modules on POSIX, node_modules on Windows).
          for candidate in "$PREFIX/lib/node_modules/gitnexus" "$PREFIX/node_modules/gitnexus"; do
            if [ -d "$candidate" ]; then
              INSTALLED="$candidate"
              break
            fi
          done
          if [ -z "${INSTALLED:-}" ]; then
            echo "ERROR: installed gitnexus package not found under $PREFIX" >&2
            ls -la "$PREFIX" || true
            exit 1
          fi
          echo "Installed package at: $INSTALLED"

          # #836 invariant: no node_modules/ or build/ under any vendor/*.
          BAD=$(find "$INSTALLED/vendor" \( -name node_modules -o -name build \) -print 2>/dev/null || true)
          if [ -n "$BAD" ]; then
            echo "ERROR: vendor tree contains forbidden build artifacts (#836):" >&2
            echo "$BAD" >&2
            exit 1
          fi

          # #1728 invariant: materialized grammar dirs are real directories,
          # not junctions/symlinks (which is what the EPERM regression created).
          for name in tree-sitter-dart tree-sitter-proto tree-sitter-swift; do
            entry="$INSTALLED/node_modules/$name"
            if [ ! -e "$entry" ]; then
              echo "WARN: $name not materialized (toolchain/prebuild may be unavailable on $RUNNER_OS)"
              continue
            fi
            if [ -L "$entry" ]; then
              echo "ERROR: $entry is a symlink/junction — #1728 regression" >&2
              exit 1
            fi
            if [ ! -d "$entry" ]; then
              echo "ERROR: $entry is not a directory" >&2
              exit 1
            fi
          done

      - name: Assert gitnexus --version works
        shell: bash
        run: |
          set -euo pipefail
          if [ "$RUNNER_OS" = "Windows" ]; then
            "$PREFIX/gitnexus.cmd" --version
          else
            "$PREFIX/bin/gitnexus" --version
          fi

  # Node engines-floor gate (#2372). A module that statically names an API
  # newer than the supported floor (e.g. `module.registerHooks`, added in
  # 22.15) fails to LINK on the floor — a class vitest/tsx transforms
  # structurally mask, and the default `node-version: 22` (resolves to latest)
  # never hits. Build the dist on 22.x, then import-link every module R1 names
  # as a load surface on the pinned engines floor (22.18.0, per package.json
  # `engines: ^22.18.0 || >=24.11.0`) so a regression fails here instead of
  # shipping to users on the minimum supported Node.
  node-floor-compat:
    name: node floor compat (22.18)
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      # persist-credentials: false — builds and import-links only, never pushes
      # (zizmor credential-persistence / artipacked audit).
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
        with:
          node-version: '22'
          cache: npm
          cache-dependency-path: gitnexus/package-lock.json
      - name: Build gitnexus-shared
        run: npm ci && npm run build
        working-directory: gitnexus-shared
      - name: Install and build gitnexus
        shell: bash
        run: |
          set -euo pipefail
          npm ci
          npm run build
        working-directory: gitnexus
      # Switch to the engines-floor Node AFTER building — native deps built on
      # 22.x load across the whole 22.x ABI line, and nothing installs after this
      # (so no package-manager cache is needed).
      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
        with:
          node-version: '22.18.0'
          package-manager-cache: false
      - name: Import-link the built dist on Node 22.18
        shell: bash
        run: |
          set -euo pipefail
          node --version
          node --version | grep -q '^v22\.18\.' || { echo "expected Node 22.18.x" >&2; exit 1; }
          for m in \
            core/embeddings/runtime-install \
            core/embeddings/onnxruntime-node-resolver \
            core/embeddings/onnxruntime-common-resolver \
            cli/embeddings \
            cli/analyze \
            cli/doctor \
            mcp/core/embedder; do
            echo "import dist/$m.js"
            node --input-type=module -e "await import('./dist/$m.js')"
          done
        working-directory: gitnexus

  # ── Dedicated benchmark gate ─────────────────────────────────────
  # The cross-language `*-pipeline-benchmark.test.ts` suites are gated behind
  # GITNEXUS_BENCH (they generate synthetic codebases at scale), so the main
  # coverage job above SKIPS them — their O(n^2) scaling guards never ran in CI.
  # Run them here with GITNEXUS_BENCH=1, alongside the Python scope-capture and
  # import-resolution fingerprint + scaling guards (PR #1918 P2a).
  #
  # `--no-file-parallelism` is REQUIRED: these suites measure wall-clock and peak
  # heap, so parallel forks both skew the timings and OOM the worker pool — they
  # must run one file at a time.
  #
  # go-pipeline-benchmark.test.ts is deliberately NOT included: its
  # worker-pool (#1848) suite spins a real worker pool that exits unexpectedly
  # under vitest's fork pool (reproduced in validation), which would make this
  # gate flaky. Go is already guarded by its non-gated O(n^2) tripwire (runs in
  # the main coverage job) plus its golden capture-parity test.
  benchmarks:
    name: benchmarks (GITNEXUS_BENCH)
    runs-on: ubuntu-latest
    timeout-minutes: 25
    steps:
      # persist-credentials: false — this job only runs npm + vitest benchmarks
      # and never pushes; the default-persisted token in .git/config would be at
      # risk of leaking through an artifact upload (zizmor credential-persistence
      # / artipacked audit). Mirrors the packaged-install-smoke job below.
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: ./.github/actions/setup-gitnexus
        with:
          build: 'true'

      - name: Python scope-capture + import-resolution fingerprint / scaling guards
        run: |
          node --import tsx bench/python-scope/measure.mjs --check
          node --import tsx bench/python-scope/import-target-fingerprint.mjs --check
        working-directory: gitnexus

      - name: Cross-language scope-capture fingerprint + scaling guards
        # Build-free: asserts emit<Lang>ScopeCaptures output is unchanged
        # (fingerprint) and stays linear (scaling < 1.5) for go/csharp/rust/php/
        # ruby/cobol. Catches an O(n^2) re-regression without the worker pool.
        run: node --import tsx bench/scope-capture/measure.mjs --check
        working-directory: gitnexus

      - name: Callable-value-flow target-index guards (#2693)
        # Build-free: asserts buildGraphTargetIndex resolves an unchanged target
        # set (fingerprint), stays linear in def count, and that the #2693
        # widened gate — which now considers VALUE bindings, a population that
        # outnumbers callables in real source — stays within its measured
        # overhead of the pre-#2693 callable-only cost. The overhead budget also
        # guards the DESIGN: value bindings are joined to their callable node by
        # position, never by name through resolveDefGraphId, whose label-agnostic
        # simpleKey fallback would alias a binding onto any same-named callable.
        run: node --import tsx bench/callable-value-flow/measure.mjs --check
        working-directory: gitnexus

      - name: C++ qualified-namespace resolution guards (#2788)
        # Build-free: asserts resolveCppQualifiedNamespaceMember resolves an
        # unchanged symbol set (fingerprint) and that per-call-site cost stays
        # independent of corpus size. Rationale and history: see the header of
        # bench/cpp-qualified-ns/measure.mjs.
        run: node --import tsx bench/cpp-qualified-ns/measure.mjs --check
        working-directory: gitnexus

      - name: Receiver-resolution drop guards
        # NOT build-free: this one runs the real pipeline, so it needs dist/
        # (the setup action above builds). ~2m15s.
        #
        # Two arms, because neither gates alone. The count arm asserts the
        # call-only drop count per language — call-only because Case 0's
        # recorder gates on the receiver's punctuation, not on what the
        # reference is, so property reads would inflate it by ~20%. The shape
        # arm asserts the state of each receiver spelling by EDGE PRESENCE,
        # which is the only arm that can see shapes the recorder is blind to:
        # they emit no edge AND no drop, so fixing them moves the count by zero.
        #
        # `repos[0]` is no longer among them (#2766): Case 0's gate now accepts
        # a minted receiver chain instead of testing the receiver's punctuation,
        # so subscript receivers record a drop and ARE countable. 13 shapes moved
        # INVISIBLE -> VISIBLE that way. `?.` and explicit type args remain
        # invisible on some languages, so the shape arm still earns its keep.
        #
        # The check is EXACT-MATCH, which is strictly stronger than a ratchet:
        # the count cannot rise without a deliberate rebaseline, and the
        # rebaseline path demands the movement be explained. No separate
        # drop-ratchet gate is needed on top of this.
        run: node --import tsx bench/receiver-resolution/measure.mjs --check
        working-directory: gitnexus

      - name: Scope-emission guards (#2699)
        # Build-free: asserts the JS/TS scope set is unchanged. Block scopes are
        # what make `let`/`const` in sibling blocks distinct bindings, but a
        # scope per `statement_block` triples the count and deepens every
        # scope-chain walk in every function for no semantic gain. Two emit-side
        # filters drop the waste — function-body blocks (the Function scope
        # already covers them) and blocks that declare nothing — and this gate
        # fails if either regresses. Counts are exact, so it catches a change
        # wall-clock CI could never resolve from noise.
        run: node --import tsx bench/scope-emission/measure.mjs --check
        working-directory: gitnexus

      - name: CFG construction time / disk / memory guards (#2081 M1)
        # Build-free: asserts collectFunctionCfgs output is unchanged
        # (fingerprint) and that wall-time, cfgSideChannel disk bytes, AND
        # retained heap all stay sub-quadratic for the straight-line /
        # many-functions / branchy scenarios. Catches an O(n^2) re-regression in
        # the per-function CFG builder (e.g. an extendBlock concat chain) and a
        # memory/disk blow-up. --expose-gc enables the retained-heap measurement.
        run: node --expose-gc --import tsx bench/cfg/measure.mjs --check
        working-directory: gitnexus

      - name: Emit-persistence throughput / byte-identity guards (#2203)
        # Build-free: asserts streamAllCSVsToDisk output is byte-identical
        # (order-independent CSV-line fingerprint — the #2203 U2/U3 emit
        # optimisations must not change graph content) and that emit wall-time
        # stays linear in node+edge count. The LadybugDB COPY half needs a real
        # DB, so its timing lives in the runtime PROF_LBUG_LOAD breakdown.
        run: node --import tsx bench/emit-persistence/measure.mjs --check
        working-directory: gitnexus

      - name: Streaming PDG-emit byte-identity / bounded-RSS guards (#2202)
        # Build-free: asserts the streaming PdgEmitSink emits a CSV row SET
        # byte-identical to the whole-graph streamAllCSVsToDisk emit, AND that
        # the in-memory graph retains zero BasicBlock nodes (the O(chunk) peak-RSS
        # bound that unblocks full-kernel-scale repos). Fails on fingerprint drift
        # or any resident BasicBlock.
        run: node --import tsx bench/emit-persistence/measure-streaming.mjs --check
        working-directory: gitnexus

      - name: Cross-language pipeline benchmarks (GITNEXUS_BENCH, serial)
        # cpp-adl-benchmark.test.ts is not a `*-pipeline-benchmark.test.ts` but
        # belongs here for the same reason: it is skipIf-gated on GITNEXUS_BENCH,
        # so it had never run in CI and the PR #1990 ADL emit-scaling guard it
        # holds was dead. ~45s of test time.
        env:
          GITNEXUS_BENCH: '1'
        run: >-
          npx vitest run --no-file-parallelism
          test/integration/cobol-pipeline-benchmark.test.ts
          test/integration/csharp-pipeline-benchmark.test.ts
          test/integration/cpp-adl-benchmark.test.ts
          test/integration/instance-ownership-pipeline-benchmark.test.ts
          test/integration/spring-bean-resource-benchmark.test.ts
          test/integration/rust-pipeline-benchmark.test.ts
          test/integration/php-pipeline-benchmark.test.ts
          test/integration/ruby-pipeline-benchmark.test.ts
        working-directory: gitnexus

  # Locked eval suite. setup-uv and uv itself are immutable so CI exercises
  # exactly the dependency graph developers run from eval/uv.lock.
  eval-tests:
    name: eval / locked pytest
    runs-on: ubuntu-latest
    timeout-minutes: 15
    steps:
      # persist-credentials: false — runs tests only, never pushes.
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
        with:
          version: '0.11.23'
          python-version: '3.13'
          enable-cache: true
          cache-dependency-glob: eval/uv.lock
      - run: uv run --locked --extra dev python -m pytest tests -q
        working-directory: eval

  # Native Linux ownership and Bubblewrap boundary. The environment flag makes
  # the real namespace test mandatory; a missing/blocked bwrap is a failure.
  eval-containment-linux:
    name: eval / containment (ubuntu)
    runs-on: ubuntu-latest
    timeout-minutes: 20
    env:
      GITNEXUS_REQUIRE_BWRAP_CANARY: '1'
      GITNEXUS_REQUIRE_CLAUDE_CANARY: '1'
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: actions/setup-node@820762786026740c76f36085b0efc47a31fe5020 # v7.0.0
        with:
          node-version: '22.18.0'
          cache: npm
          cache-dependency-path: |
            gitnexus/package-lock.json
            gitnexus-shared/package-lock.json
      - uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
        with:
          version: '0.11.23'
          python-version: '3.13'
          enable-cache: true
          cache-dependency-glob: eval/uv.lock
      - name: Install sandbox runtime and pinned Claude CLI
        run: |
          set -euo pipefail
          sudo apt-get update
          sudo apt-get install --yes --no-install-recommends bubblewrap socat
          apparmor_userns=/proc/sys/kernel/apparmor_restrict_unprivileged_userns
          if [[ -r "${apparmor_userns}" ]] && [[ "$(<"${apparmor_userns}")" == '1' ]]; then
            sudo sysctl -w kernel.apparmor_restrict_unprivileged_userns=0
          fi
          canary_runtime="${RUNNER_TEMP}/claude-canary"
          install -d -m 0700 "${canary_runtime}"
          install -m 0600 \
            .github/claude-canary-runtime/package.json \
            "${canary_runtime}/package.json"
          install -m 0600 \
            .github/claude-canary-runtime/package-lock.json \
            "${canary_runtime}/package-lock.json"
          npm ci \
            --prefix "${canary_runtime}" \
            --ignore-scripts=false \
            --audit=false \
            --fund=false
          node -e \
            "const p=require(process.argv[1]); if(p.version!=='2.1.214') process.exit(1)" \
            "${canary_runtime}/node_modules/@anthropic-ai/claude-code/package.json"
          test "$("${canary_runtime}/node_modules/@anthropic-ai/claude-code-linux-x64/claude" --version)" = \
            '2.1.214 (Claude Code)'
      - name: Build pinned shared runtime
        run: |
          npm ci
          npm run build
        working-directory: gitnexus-shared
      - name: Install and build pinned GitNexus runtime
        run: |
          npm ci
          npm run build
        working-directory: gitnexus
      - name: Prove process-tree and sandbox containment
        env:
          CLAUDE_CANARY_BIN: ${{ runner.temp }}/claude-canary/node_modules/@anthropic-ai/claude-code-linux-x64/claude
        run: >-
          uv run --locked --extra dev python -m pytest
          tests/test_process_control.py
          tests/test_proposer_sandbox.py
          tests/test_workflow_bench_sessions.py
          tests/test_ce_plugin_runtime.py -q
        working-directory: eval

  # Native Windows Job Object canary. POSIX-only tests skip by platform, while
  # the grandchild delayed-write test must execute and pass on this runner.
  eval-containment-windows:
    name: eval / containment (windows)
    runs-on: windows-latest
    timeout-minutes: 15
    steps:
      - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
        with:
          persist-credentials: false
      - uses: astral-sh/setup-uv@11f9893b081a58869d3b5fccaea48c9e9e46f990 # v8.3.2
        with:
          version: '0.11.23'
          python-version: '3.13'
          enable-cache: true
          cache-dependency-glob: eval/uv.lock
      - name: Prove Windows process-tree ownership
        run: >-
          uv run --locked --extra dev python -m pytest
          tests/test_process_control.py -q
        working-directory: eval