open-standards/.github/workflows/standards-build.yml

name: standards workspaces build + test

# Build gate for every Rust workspace in the repo.
#
# It started as three. Then a toolchain bump compiled the rest for the first
# time and found FIVE more that did not build — smart-byte (47k LOC), openpay
# (six separate breakages across five crates), eoc, mesh and joule-ui — all
# broken by the same handful of upstream migrations (hmac -> KeyInit, reqwest
# feature-gating, cipher 0.4 -> 0.5, a struct gaining fields), and all invisible
# because nothing ever compiled them. Partial coverage is how that happens, so
# the matrix now covers everything.
#
# The original case, still the clearest: smart-byte-rs had never been compiled by
# anything, and it did not build. A single wrong `rand` pin — 0.10 against code
# written for 0.8, whose crypto stack requires rand_core 0.6 — silently disabled
# the entire identity pillar, BBS+ included. `cargo check` would have caught it
# on day one. An unbuilt standard is not a standard, so this workflow is the
# floor under every claim the specs make.
#
# One workflow with a matrix rather than sixteen files: the bootstrap step is
# identical everywhere, and a shared dependency change should rebuild all of
# them anyway. `fail-fast: false` so one red workspace does not mask the others.

# One run per branch at a time. A push supersedes the run before it.
#
# There is one `macos` runner and it is the dev Mac, so every macOS job in this
# repo queues on it. With no concurrency group, a session pushing four versions
# of a branch queued four complete sets of runs and every one of them had to
# drain: on 2026-10-05 a PR's 21 contexts settled none in 70 minutes behind a
# backlog of 25 runs, and the queue grew faster than it cleared. Only the newest
# commit's verdict is wanted, so the older runs are cancelled.
#
# Verified on this forge (Forgejo 16.0.5) in `ci-test` before being added here:
# the key parses, and a newer push moves an older run to `cancelled` even while
# it is still queued, which is the case that matters.
#
# `cancel-in-progress: true` also applies to `main`. That is deliberate and
# safe here: main advances by merge commits whose tree contains the commits
# before them, so the newer run covers the older one's changes.
concurrency:
  group: ${{ github.workflow }}-${{ github.ref }}
  cancel-in-progress: true

on:
  push:
    branches: [main]
  pull_request:

# Deliberately NO `paths:` filter.
#
# The first attempt used `**/*.rs` and `**/Cargo.toml`, and the workflow then
# silently did not fire — pushes touching exactly those files triggered other
# workflows but not this one, so `**`-prefixed globs evidently do not match here
# the way they do on GitHub. A build gate that quietly fails to run is worse than
# no gate at all: it reports nothing and everyone assumes green.
#
# This is the repo-wide floor. A push to main builds every workspace. A pull request
# builds the workspaces its own diff touches (the `plan` job, scripts/
# standards-touched.py): a workspace's own area, the areas of everything it depends on
# by path, any file outside them its sources name, and everything every leg shares (this
# file, the toolchain pin, the cargo configuration). Building all 17 for every pull
# request filled the one x86_64 runner's queue with builds no change could affect. The
# plan reads the pull request's diff, not the push delta, so a merge of main into a
# branch does not rebuild everything, and anything it cannot determine builds all.

jobs:
  # Which workspaces this change touches. The list of workspaces is here, one
  # `- { ... }` line each, read by scripts/standards-touched.py; the build job's
  # matrix is the entries it selects.
  plan:
    name: which workspaces this change touches
    runs-on: linux-arm64
    outputs:
      include: ${{ steps.plan.outputs.include }}
      any: ${{ steps.plan.outputs.any }}
      energy: ${{ steps.plan.outputs.energy }}
    env:
      WORKSPACES: |
          - { name: jcp-rs,           dir: jcp/jcp-rs,                            runner: linux, conformance: jcp-conformance, feature_tests: "-p jcp-energy --features nvml" }
          - { name: sandbox-rs,       dir: sandbox/sandbox-rs,                    runner: linux, conformance: sandbox-conformance }
          - { name: smart-byte-rs,    dir: smart-byte/smart-byte-rs,              runner: linux }
          - { name: openpay,          dir: openpay,                               runner: linux-arm64 }
          - { name: joule-code-rs,    dir: joule-code/joule-code-rs,              runner: linux-arm64, z3: true }
          - { name: map-rs,           dir: map/map-rs,                            runner: linux-arm64, conformance: map-conformance }
          - { name: aac-rs,           dir: aac/aac-rs,                            runner: linux-arm64, conformance: aac-conformance }
          - { name: joulecontract-rs, dir: joulecontract/joulecontract-rs,        runner: linux-arm64, z3: true }
          # Runner placement is by what a workspace actually needs, not by
          # habit. The dev Mac hosts BOTH the `macos` runner and the
          # `linux-arm64` colima VM, so it served 13 of this repo's 21
          # contexts while jetson-hub (`linux`) sat idle — which is why a PR's
          # macOS contexts could wait indefinitely while its `linux` ones
          # returned in minutes.
          #
          # `arl-rs`, `sense-rs`, `joulehook-rs` and `joule-ui-rs` moved to
          # `linux` on that basis: each has zero `target_os = "macos"` cfgs,
          # zero Apple dependencies, and zero Apple crates in its Cargo.lock,
          # so running them on macOS asserted nothing the repo relies on.
          # `jouledesk-rs` stays, because it does need it — `libwebrtc` and 19
          # Apple crates in its lockfile. `linux-arm64` placements stay too:
          # arm64 is the deployment target, and `jouleclaw-rs` needs
          # `+fp16`.
          - { name: jouledesk-rs,     dir: jouledesk/jouledesk-rs,                runner: macos }
          - { name: arl-rs,           dir: arl/arl-rs,                            runner: linux }
          - { name: sense-rs,         dir: sense/sense-rs,                        runner: linux }
          - { name: proof-rs,         dir: proof/proof-rs,                        runner: linux, z3: true, conformance: proof-conformance }
          - { name: joulehook-rs,     dir: joulehook/joulehook-rs,                runner: linux }
          - { name: eoc-rs,           dir: eoc/eoc-rs,                            runner: linux, feature_tests: "-p eoc-meter --features cuda" }
          # mesh-openai's `serve_example` test (the reference server seals what
          # its meter read, never a fixture's figure) has required-features
          # `server`, so `cargo test --workspace` builds none of it; naming the
          # package here is what runs it. Selecting mesh-engine-gguf alone
          # compiles mesh-openai with `server` but runs none of its tests.
          - { name: mesh-rs,          dir: mesh/mesh-rs,                          runner: linux-arm64, feature_tests: "-p mesh-engine-gguf -p mesh-openai --features mesh-engine-gguf/gguf,mesh-openai/server" }
          - { name: joule-ui-rs,      dir: joule-ui/joule-ui-rs,                  runner: linux }
          # jouleclaw-rs is the one entry whose runner IS a correctness choice.
          # It reaches candle → ug → gemm, which uses inline aarch64 assembly
          # (`fmla {0:v}.8h, ...`) requiring the ARMv8.2 FP16 extension.
          # `aarch64-apple-darwin` carries target_feature="fp16" in its baseline
          # because Apple Silicon guarantees it; `aarch64-unknown-linux-gnu`
          # baselines at ARMv8.0-A and does not, so the same asm fails to
          # ASSEMBLE — a codegen error `cargo check` never reaches. Verified on a
          # native arm64 Linux container (rustc 1.98.0): without the flag, 12
          # errors; with it, 4457 tests pass.
          #
          # CAPACITY: this is by far the largest entry — its target tree is
          # ~16 GB, against a 120 GB volume on tx-dev-linux-arm64 that already
          # holds ~74 GB of other workspaces' caches. If linux-arm64 jobs start
          # failing for no apparent reason, check `df -h /mnt/lima-colima-txarm`
          # on the txarm VM before suspecting the code: a full cache volume
          # fails whatever happens to be building, not whatever changed.
          - { name: jouleclaw-rs,     dir: jouleclaw/jouleclaw-rs,                runner: linux-arm64, rustflags: "-C target-feature=+fp16", cache_suffix: "-nodebug", feature_tests: "-p jouleclaw-energy --features rapl,nvml" }
    steps:
      - uses: actions/checkout@v5
        with:
          fetch-depth: 0
      - name: The decision fails closed (self-test)
        run: bash scripts/standards-touched-selftest.sh
      - id: plan
        name: Which workspaces this change touches
        run: |
          set -euo pipefail
          python3 scripts/standards-touched.py --github-output \
            "${{ github.event.pull_request.base.sha }}" \
            "${{ github.event.pull_request.head.sha }}"

  build:
    name: ${{ matrix.name }}
    needs: plan
    if: needs.plan.outputs.any == 'true'
    # Spread across the fleet's runners rather than pinning every job to `linux`.
    # For most of these the runner is a capacity choice, not a correctness one —
    # and 17 jobs on a single runner queue behind whatever else is using it.
    # `jouleclaw-rs` is the exception: see its matrix entry.
    runs-on: ${{ matrix.runner }}
    strategy:
      fail-fast: false
      matrix:
        include: ${{ fromJSON(needs.plan.outputs.include) }}
    steps:
      - uses: actions/checkout@v5

      # Three workspaces shell out to `z3`, and the runner image has no solver.
      #
      # This step used to be load-bearing for correctness: without a solver the
      # ladder escalated past its real rungs into a model STAND-IN that reported
      # Proved, so every goal on a solverless machine came back proved. That is
      # now fixed at the source — the real ladders hold decision procedures only
      # and an absent rung yields Unproved (proof-solvers `ladder_is_sound` and
      # `ladder_never_fabricates_a_proof_when_a_rung_is_absent`).
      #
      # So the suites pass with or without z3, and this step is kept purely for
      # COVERAGE: with a solver present the real T1 rung actually runs, and the
      # SMT paths are exercised rather than skipped. The absent-rung semantics
      # stay covered either way — that regression test uses a goal z3 cannot
      # parse, so it asserts the same thing on a machine that has one.
      #
      # joule-code-remediate's formal gate is the third. Its tests assert in both
      # branches, so they pass without a solver, and JOULE_FIX_EXPECT_Z3=1 below
      # makes a missing z3 fail them where this step installed one. Otherwise CI
      # would only ever run the no-solver branch.
      #
      # The z3 jobs are pinned to Linux runners deliberately: the macOS runner is
      # a host executor with no apt. `sudo` may or may not exist depending on
      # whether the container runs as root, so fall back to a bare invocation.
      - name: Install z3
        if: matrix.z3
        shell: bash
        run: |
          SUDO=""; [ "$(id -u)" -ne 0 ] && SUDO="sudo"
          $SUDO apt-get update -qq
          $SUDO apt-get install -y -qq z3
          z3 --version

      # The docker runner image ships no Rust at all, so rustup is bootstrapped
      # here. dtolnay/rust-toolchain cannot be used: it shells out to `rustup`,
      # which the image lacks. Harmless where cargo already exists.
      - name: Install Rust (workspace pin)
        shell: bash
        run: |
          export PATH="$HOME/.cargo/bin:$PATH"
          command -v rustup >/dev/null 2>&1 || \
            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"

      # jouleclaw-rs is the CAPACITY entry above. Linux embeds full DWARF in every
      # test binary, so with default debuginfo its aarch64 test target outgrows
      # the ~15 GB left on the shared txarm volume and the link fails with
      # "No space left on device" (reproduced with the same toolchain, flags and
      # image). Without debuginfo the same target is ~6 GB and the whole suite
      # passes. Panic messages keep their file:line: that comes from the panic
      # location, not from DWARF.
      #
      # Set through $GITHUB_ENV rather than a matrix field on purpose: a matrix
      # field would hand every other job CARGO_PROFILE_DEV_DEBUG="", which cargo
      # can reject. `cache_suffix` gives this job a fresh cache namespace so it
      # cannot restore a full-debuginfo target and hold both builds at once;
      # for every other job the suffix is empty and its key string is unchanged.
      - name: Trim debuginfo (arm64 jouleclaw)
        if: matrix.name == 'jouleclaw-rs'
        shell: bash
        run: echo "CARGO_PROFILE_DEV_DEBUG=0" >> "$GITHUB_ENV"

      # aac-rs builds its page sets in its tests (tools/pagesets: build.py,
      # phrases/build.py) and checks them against the committed catalogue
      # (catalog.py --check, below). Those need Python 3.11+ with PyYAML; the
      # runner image has Python 3.10 and no PyYAML, and with neither the
      # tests would only report that they could not build anything. uv puts
      # a Python 3.12 and PyYAML in a venv of the job's own, on Linux or
      # macOS; the tests use it through AAC_PYTHON and fail, not skip, when
      # CI is set and there is none. Verified in catthehacker/ubuntu:act-22.04
      # on arm64: Python 3.12.15, PyYAML 6.0.3.
      - name: Python 3.11+ and PyYAML for the page sets
        if: matrix.name == 'aac-rs'
        shell: bash
        run: |
          export PATH="$HOME/.local/bin:$HOME/.cargo/bin:$PATH"
          command -v uv >/dev/null 2>&1 || curl -LsSf https://astral.sh/uv/install.sh | sh
          uv venv -q --python 3.12 "$HOME/.pagesets-py"
          uv pip install -q --python "$HOME/.pagesets-py/bin/python" pyyaml
          "$HOME/.pagesets-py/bin/python" -c 'import sys, yaml; assert sys.version_info >= (3, 11); print(sys.version, "PyYAML", yaml.__version__)'
          echo "AAC_PYTHON=$HOME/.pagesets-py/bin/python" >> "$GITHUB_ENV"

      - name: Cache cargo registry + target
        uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            ${{ matrix.dir }}/target
          key: standards-${{ matrix.name }}${{ matrix.cache_suffix }}-${{ hashFiles(format('{0}/Cargo.lock', matrix.dir), 'rust-toolchain.toml') }}
          restore-keys: |
            standards-${{ matrix.name }}${{ matrix.cache_suffix }}-

      # --all-targets is load-bearing: a plain `cargo check` does not build test
      # targets, and smart-byte's dev-dependencies drifted independently of its
      # normal ones (rand_chacha 0.10 against rand 0.8). The library compiled
      # while the tests did not.
      - name: Check (all targets)
        working-directory: ${{ matrix.dir }}
        env:
          RUSTFLAGS: ${{ matrix.rustflags }}
        run: cargo check --workspace --all-targets

      - name: Test
        working-directory: ${{ matrix.dir }}
        env:
          RUSTFLAGS: ${{ matrix.rustflags }}
          # Where z3 was installed above, its absence is a failure, not a skip.
          JOULE_FIX_EXPECT_Z3: ${{ matrix.z3 && '1' || '' }}
        run: cargo test --workspace

      # The NVML backends sit behind features no workspace member enables
      # (jcp-energy `nvml`, eoc-meter `cuda`, jouleclaw-energy `nvml`), so the
      # step above never compiles them, let alone runs their tests. Here they
      # build and their tests run, as do mesh-rs's feature-gated tests (the
      # gguf engines; mesh-openai's `server` and its serve_example test). The container has no GPU and Docker masks
      # powercap, so the hardware tests take their "unavailable, and the
      # oracle agrees" branch; the rule's unit tests run in full.
      - name: Feature-gated energy tests
        if: matrix.feature_tests
        working-directory: ${{ matrix.dir }}
        env:
          RUSTFLAGS: ${{ matrix.rustflags }}
        run: cargo test ${{ matrix.feature_tests }}

      # The page-set packages are not committed; their catalogue is, naming
      # each package by its content. Any change to what they are built from —
      # the sources, the app's translations and gloss audits, the symbol
      # index and sprites, the navigation words, vocabulary.rs, i18n.rs, the
      # language packs — changes the packages, and the committed catalogue
      # must change with them (catalog.py --write), or the app would offer
      # packages it would then refuse to use.
      - name: Page-set catalogue is current
        if: matrix.name == 'aac-rs'
        working-directory: ${{ matrix.dir }}
        shell: bash
        run: |
          "$AAC_PYTHON" tools/pagesets/catalog.py --check
          "$AAC_PYTHON" tools/pagesets/phrases/build.py --check

      # Run each standard's conformance suite.
      #
      # These suites live in a binary's `main()`, not in `#[test]`, so
      # `cargo test` never executes them — verified, not assumed:
      # `cargo test -p aac-conformance` runs **0 tests** while
      # `cargo run -p aac-conformance` runs **40 checks**; map is 1 test vs 15
      # checks. Same shape for jcp, proof and sandbox. The suites include
      # negative vectors (`C-neg`, `Cneg`), which are the ones that catch a
      # verifier ACCEPTING what it must reject.
      #
      # This is the `main()` instance of the same bug as a feature-gated test:
      # the code compiles under `--all-targets`, reports nothing, and looks
      # covered. Compiling a suite is not running it.
      #
      # `--bin` is explicit because these crates also ship a `gen-vectors`
      # binary; `cargo run -p <crate>` is ambiguous with two binaries and fails
      # rather than choosing — which is how this step would silently never run.
      #
      # No path argument: these binaries take none. They check the
      # implementation against in-code expectations, which is a different claim
      # from validating the published `conformance/v1` files on disk.
      #
      # That second claim is made elsewhere, by tests inside the reference
      # implementations that read `conformance/v1` off disk, which the `Test`
      # step above already runs — so it needs no entry here and a missing
      # `conformance:` key is not evidence a standard's pack is unchecked.
      #
      # Deliberately not "a `tests/pack.rs` in each conformance crate": that
      # is the convention in several of them, not a rule, and some crates read
      # the pack from a test named something else or from another crate
      # entirely. So counting files by that name does not audit pack coverage,
      # and finding a crate without one is not a finding. The question is
      # which tests read the published bytes:
      #
      #   grep -rl --include=*.rs -E 'conformance/v[0-9]' <standard>/
      #
      # That mistake has been made here twice, both times concluding standards
      # were uncovered when they were not.
      #
      # `joule-code` is deliberately absent from that key. Its verifier does read
      # the published pack, but it requires a `verify <pack-dir>` argument and
      # prints usage with a non-zero exit when given none, so it cannot be
      # invoked by this step's no-argument form. It has its own workflow,
      # `joule-code-conformance.yml`, plus a `tests/pack.rs` that the `Test` step
      # above runs — the latter because that workflow is `paths:`-filtered to
      # `joule-code/**`, while the crate depends on `jcp-*` across workspaces.
      - name: Conformance suite
        if: matrix.conformance
        working-directory: ${{ matrix.dir }}
        env:
          RUSTFLAGS: ${{ matrix.rustflags }}
        run: cargo run -q -p ${{ matrix.conformance }} --bin ${{ matrix.conformance }}

  # ── The macOS energy backends are exercised NOWHERE otherwise ─────────────
  #
  # Five crates carry an Apple Silicon IOReport energy meter: jcp-energy,
  # proof-cascade, eoc-meter, jouleclaw-energy and sandbox-meter. Each is
  # behind `#[cfg(target_os = "macos")]` (jouleclaw-energy also behind its
  # `ioreport` feature), and every workspace holding one is pinned to a linux
  # runner above. A platform-gated test on a single-platform runner is zero
  # coverage, and it is indistinguishable from passing.
  #
  # What this job checks, and why it used to flake. On macOS 27 an unprivileged
  # reader does not see the IOReport "Energy Model" CPU rails (`CPU Energy`,
  # `DIE_<n>_CPU Energy`) move under load. They are republished only in rare
  # lumps: on the M3 Ultra both dies held for over 22 minutes, then jumped
  # about 1.3 kJ each in a single 100 ms sample. On the M5 Max the GPU rail
  # stays live. The old jcp-energy test asserted that the *summed* rails
  # advanced during a CPU burn, and the GPU rail satisfied that whenever
  # something drew on screen. It passed by day and failed at night. The
  # 2026-09-19 zero that "healed" by 09-21 was this effect, not a recovery.
  #
  # Every meter now uses IOReport only when the CPU rail itself keeps
  # advancing while the probe burns CPU: in at least 5 sample intervals, at
  # least 4 in every 5, over at least 300 ms. A lump is published in steps (one
  # was caught as +61.8 kJ, then +3.4 J 64 ms later), so two advancing
  # intervals are still just a lump. Otherwise the meter falls back to its
  # estimator rung. Its tests assert against an independent oracle that reads
  # the CPU rail directly, so this job is deterministic:
  #   - green while each meter declines a rail that does not keep moving;
  #   - red if any meter selects one;
  #   - on a host whose rail is live, red unless CPU work meters non-zero.
  #
  # Each step fails unless its test printed the `ioreport liveness:` line. That
  # line is the only proof the platform-gated test ran and asserted a branch,
  # rather than a filter, a feature or a cfg leaving zero tests to pass. It goes
  # to stderr and is captured on success, hence `--nocapture` and `2>&1`.
  macos-energy-backend:
    name: macOS energy backends
    # Runs when the change touches a workspace whose energy backend it tests (the plan's
    # `energy`), and on every push to main.
    needs: plan
    if: needs.plan.outputs.energy == 'true'
    runs-on: macos
    steps:
      - uses: actions/checkout@v4

      - name: Install Rust (workspace pin)
        shell: bash
        run: |
          export PATH="$HOME/.cargo/bin:$PATH"
          command -v rustup >/dev/null 2>&1 || \
            curl --proto '=https' --tlsv1.2 -sSf https://sh.rustup.rs | sh -s -- -y --profile minimal
          echo "$HOME/.cargo/bin" >> "$GITHUB_PATH"

      - name: Cache cargo registry + targets
        uses: actions/cache@v4
        with:
          path: |
            ~/.cargo/registry
            ~/.cargo/git
            jcp/jcp-rs/target
            proof/proof-rs/target
            eoc/eoc-rs/target
            jouleclaw/jouleclaw-rs/target
            sandbox/sandbox-rs/target
            joule-code/joule-code-rs/target
          key: standards-macos-energy-${{ hashFiles('jcp/jcp-rs/Cargo.lock', 'proof/proof-rs/Cargo.lock', 'eoc/eoc-rs/Cargo.lock', 'jouleclaw/jouleclaw-rs/Cargo.lock', 'sandbox/sandbox-rs/Cargo.lock', 'joule-code/joule-code-rs/Cargo.lock', 'rust-toolchain.toml') }}
          restore-keys: |
            standards-macos-energy-

      # Each crate's lib tests plus its integration tests. Each crate has a
      # tests/ file that checks the liveness probe runs exactly once per process,
      # and that check only holds in a fresh process. `--lib` would skip it.
      - name: jcp-energy
        shell: bash
        working-directory: jcp/jcp-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p jcp-energy -- --nocapture 2>&1 | tee "$log"
          grep -q 'ioreport liveness:' "$log"

      - name: proof-cascade
        shell: bash
        working-directory: proof/proof-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p proof-cascade -- --nocapture 2>&1 | tee "$log"
          grep -q 'ioreport liveness:' "$log"

      - name: eoc-meter
        shell: bash
        working-directory: eoc/eoc-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p eoc-meter -- --nocapture 2>&1 | tee "$log"
          grep -q 'ioreport liveness:' "$log"

      # Double-gated: `cfg(all(feature = "ioreport", target_os = "macos"))`.
      # A macOS runner alone reaches none of it.
      - name: jouleclaw-energy (feature AND platform gated)
        shell: bash
        working-directory: jouleclaw/jouleclaw-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p jouleclaw-energy --features ioreport -- --nocapture 2>&1 | tee "$log"
          grep -q 'ioreport liveness:' "$log"

      - name: sandbox-meter
        shell: bash
        working-directory: sandbox/sandbox-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p sandbox-meter -- --nocapture 2>&1 | tee "$log"
          grep -q 'ioreport liveness:' "$log"
          # The tree meter's real-process tests (tests/tree_energy.rs) are
          # gated to Apple Silicon macOS too; each prints this line.
          grep -q 'tree meter:' "$log"

      # jcp-gateway meters each gated call on the upstream server's own
      # process tree with that meter. The jcp-rs matrix entry runs on Linux,
      # where there is no tree meter and every call is metered machine-wide,
      # so its real-process test (tests/upstream_tree.rs, Apple Silicon macOS
      # only) runs nowhere else. Each call it meters on a real server's tree
      # prints this line (the machine-wide fallback test prints another), so
      # the grep fails if a cfg or a filter left none of them to run.
      - name: jcp-gateway (upstream process tree)
        shell: bash
        working-directory: jcp/jcp-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p jcp-gateway -- --nocapture 2>&1 | tee "$log"
          grep -q 'upstream tree:' "$log"

      # proof-solvers reads each resident z3 decision off z3's own process
      # tree with that meter (tests/z3_tree.rs, Apple Silicon macOS only, on a
      # real z3: Homebrew's, on this runner's PATH). The proof-rs matrix entry
      # runs on Linux, where there is no tree meter, so these run nowhere
      # else. Each decision they meter prints this line; a missing z3, or a
      # per-process counter that is not live, prints another, and the grep
      # fails.
      - name: proof-solvers (resident z3 process tree)
        shell: bash
        working-directory: proof/proof-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p proof-solvers -- --nocapture 2>&1 | tee "$log"
          grep -q 'z3 tree meter:' "$log"

      # sandbox-proof's local inference proof meters the engine on its own
      # process tree, spawned suspended and read before it is reaped. Its
      # real-engine tests are gated to Apple Silicon macOS; each run they
      # meter prints this line.
      - name: sandbox-proof (local engine process tree)
        shell: bash
        working-directory: sandbox/sandbox-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p sandbox-proof -- --nocapture 2>&1 | tee "$log"
          grep -q 'local engine tree:' "$log"

      # joule-fix meters its L3 model on the model's own process tree. The
      # joule-code-rs matrix entry runs on linux-arm64, where there is no tree
      # meter, so its oracle test (the model's reading against the stand-in's
      # own energy count) takes its fallback branch there and runs nowhere
      # else. It prints this line only where it checked the reading.
      - name: joule-code-remediate (L3 model process tree)
        shell: bash
        working-directory: joule-code/joule-code-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p joule-code-remediate l3_ -- --nocapture 2>&1 | tee "$log"
          grep -q 'l3 model process:' "$log"

      # Feature AND platform gated: `fabric-meter`, which no other job passes,
      # and macOS. The fabric calibration rows' macOS stamp, and a CPU member
      # priced on this process's own counters against its own energy count
      # (tests/process_calibration.rs), each print their line only there.
      - name: jouleclaw-loader-gguf (fabric-meter, process calibration)
        shell: bash
        working-directory: jouleclaw/jouleclaw-rs
        run: |
          set -o pipefail
          log=$(mktemp)
          cargo test -p jouleclaw-loader-gguf --features "rayon fabric-meter" marginal_energy -- --nocapture 2>&1 | tee "$log"
          cargo test -p jouleclaw-loader-gguf --features "rayon fabric-meter" --test process_calibration -- --nocapture 2>&1 | tee -a "$log"
          grep -q 'calibration row stamped on macOS:' "$log"
          grep -q 'process calibration: CPU member' "$log"