2026-10-27 19:59:37 -07:00
1 changed files with 527 additions and 0 deletions
@@ -0,0 +1,527 @@
 #!/usr/bin/env bats
 # Seam: the Qwen3.8-Flash-Next five-bit campaign (feat/qwen38-w5nl64).
 #
 # The campaign converts the vendor BF16 checkpoint into a w5nl64a8h .rad on
 # dankserver while frank-archon keeps serving. Every gate that protects the box
 # or the result lives in a script under scripts/, and each gate is tested here
 # through that script's own exit status and printed output — no engine, no GPU,
 # no network. Fixtures are synthetic; the expected numbers are worked examples,
 # not values recomputed the way the script computes them.
 #
 # Seams under test (the campaign's public boundaries):
 #   scripts/download-qwen38-bf16.sh      fetch/verify of the BF16 checkpoint
 #   scripts/grams-to-imatrix.py          calibration recording -> imatrix GGUF
 #   scripts/derive-protected-experts.py  --target-count sweep + the parity law
 #   scripts/build-qwen38-bf16-rad.sh     the reference container's convert argv
 #   scripts/run-qwen38-bf16.sh           the drained-serve argv, mode selection
 #   scripts/convert-qwen38-w5nl64.sh     the arm driver's refusal gates
 #   scripts/kld-gate-qwen38.sh           the three-anchor interval law
 #   scripts/deploy-plan.py               campaign files must deploy nothing
 load helpers
 DOWNLOAD="$REPO_ROOT/scripts/download-qwen38-bf16.sh"
 PLANNER="$REPO_ROOT/scripts/deploy-plan.py"
 # make_shard <dir> <name> <total-bytes> — a REAL safetensors file whose size on
 # disk is exactly <total-bytes>: 8-byte header length, JSON header, tensor data.
 # Real, because the verifier reads each shard's own header to learn how many
 # bytes it claims to be, which is the only per-file truth available offline.
 make_shard() {
    mkdir -p "$1"
    python3 - "$1/$2" "$3" <<'PY'
 import json, struct, sys
 path, want = sys.argv[1], int(sys.argv[2])
 payload = max(0, want - 96)
 header = b""
 for _ in range(16):
    # The header is part of the file, so its own length moves the target: solve
    # payload = want - 8 - len(header(payload)) by fixed-point iteration.
    header = json.dumps({"w": {"dtype": "F32", "shape": [payload // 4],
                               "data_offsets": [0, payload]}},
                        separators=(",", ":")).encode()
    want_payload = want - 8 - len(header)
    if want_payload == payload:
        break
    if want_payload < 0:
        raise SystemExit("fixture too small to carry a header")
    payload = want_payload
 else:
    raise SystemExit("fixture header never converged")
 with open(path, "wb") as f:
    f.write(struct.pack("<Q", len(header)) + header + b"\x00" * payload)
 PY
 }
 # make_index <dir> <shard>... — a safetensors index that references them
 make_index() {
    local dir="$1"; shift
    python3 - "$dir/model.safetensors.index.json" "$@" <<'PY'
 import json, sys
 out, names = sys.argv[1], sys.argv[2:]
 json.dump({"metadata": {"total_size": 0},
           "weight_map": {f"model.layers.{i}.attn.q.weight": n
                          for i, n in enumerate(names)}},
          open(out, "w"))
 PY
 }
 # three_fixture <dir> — three valid 1000-byte shards plus the index naming them
 three_fixture() {
    make_shard "$1" model-00001-of-00003.safetensors 1000
    make_shard "$1" model-00002-of-00003.safetensors 1000
    make_shard "$1" model-00003-of-00003.safetensors 1000
    make_index "$1" model-00001-of-00003.safetensors \
                  model-00002-of-00003.safetensors \
                  model-00003-of-00003.safetensors
 }
 # --- download / verify -------------------------------------------------------
@test "the checkpoint verifier accepts a complete checkpoint and reports its footprint" {
    C="$BATS_TEST_TMPDIR/complete"
    three_fixture "$C"
    # 3 x 1000 bytes of shards. The index file itself is deliberately not
    # counted, so a Hub-side edit to a config file cannot fail this gate.
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 0 ]
    [[ "$output" == *"VERIFY_OK"*"3 shards"*"3000 bytes"* ]]
 }
@test "the verifier names the shard whose own header disagrees with its size on disk" {
    C="$BATS_TEST_TMPDIR/truncated"
    three_fixture "$C"
    # Cut the tail, keep the header: that is a torn transfer, which is what the
    # box actually gets from an interrupted fetch. Zero-filling instead would
    # destroy the header and be caught as "not a safetensors file" — a different
    # gate, and it would prove nothing about the size check.
    python3 -c 'import sys
 p = sys.argv[1]
 keep = open(p, "rb").read(400)
 open(p, "wb").write(keep)' "$C/model-00002-of-00003.safetensors"
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 1 ]
    [[ "$output" == *"TRUNCATED"*"model-00002-of-00003.safetensors"* ]]
 }
@test "the verifier refuses a missing shard and names it" {
    C="$BATS_TEST_TMPDIR/missing"
    three_fixture "$C"
    mv "$C/model-00003-of-00003.safetensors" "$C/hidden.bin"
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 1 ]
    [[ "$output" == *"MISSING"*"model-00003-of-00003.safetensors"* ]]
 }
@test "the verifier refuses when the shard census disagrees with the expected count" {
    # The fragment law this repo learned the hard way: large quants ship as
    # .partNofM fragments and a naive glob reports success on a partial tree.
    C="$BATS_TEST_TMPDIR/count"
    three_fixture "$C"
    make_shard "$C" model-00004-of-00004.safetensors 1000
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 1 ]
    [[ "$output" == *"SHARD_COUNT"*"4"*"3"* ]]
 }
@test "the verifier refuses a shard the index names that never landed" {
    C="$BATS_TEST_TMPDIR/orphan-index"
    three_fixture "$C"
    rm "$C/model-00003-of-00003.safetensors"
    make_index "$C" model-00001-of-00003.safetensors \
                  model-00002-of-00003.safetensors \
                  model-00003-of-00003.safetensors
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 2 --bytes 2000
    [ "$status" -eq 1 ]
    [[ "$output" == *"MISSING"*"model-00003-of-00003.safetensors"* ]]
 }
@test "the verifier treats an HTTP error body written as a shard as a failure, not a download" {
    # curl -o FILE exits 0 on 401/403 and writes the error body; three shards
    # of identical tiny size must never look like a checkpoint.
    C="$BATS_TEST_TMPDIR/errorbody"
    mkdir -p "$C"
    for n in 1 2 3; do
        printf '{"error":"You are not logged in"}' \
            > "$C/model-0000${n}-of-00003.safetensors"
    done
    make_index "$C" model-00001-of-00003.safetensors \
                  model-00002-of-00003.safetensors \
                  model-00003-of-00003.safetensors
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 1 ]
    [[ "$output" == *"NOT_SAFETENSORS"* ]]
 }
@test "the verifier refuses a shard census whose bytes do not total what the Hub declared" {
    # Every shard header can be self-consistent and the tree still be the wrong
    # payload: the total is the cross-check against the Hub's declared size.
    C="$BATS_TEST_TMPDIR/wrongtotal"
    three_fixture "$C"
    run bash "$DOWNLOAD" --no-hub --dir "$C" --shards 3 --bytes 2500
    [ "$status" -eq 1 ]
    [[ "$output" == *"TOTAL_BYTES"*"3000"*"2500"* ]]
 }
@test "the fetch path refuses when the destination cannot hold the checkpoint" {
    # The campaign's peak-disk law starts at the fetch: the BF16 checkpoint and
    # the reference container built from it are both ~335 GiB, and the tree that
    # does not fit is discovered hours into a transfer.
    C="$BATS_TEST_TMPDIR/tiny"
    three_fixture "$C"
    run env FRANK_QWEN38_MIN_FREE_MIB=999999999 \
        bash "$DOWNLOAD" --fetch --no-hub --dir "$C" --shards 3 --bytes 3000
    [ "$status" -eq 2 ]
    [[ "$output" == *"REFUSED"*"free"* ]]
 }
 # --- deployment scoping ------------------------------------------------------
@test "the campaign tooling deploys nothing: merging it cannot drain frank-archon" {
    # Existence is asserted first: a planner that plans nothing because the
    # files vanished would otherwise pass.
    [ -f "$REPO_ROOT/scripts/download-qwen38-bf16.sh" ]
    run python3 "$PLANNER" --target dankserver --paths \
        scripts/download-qwen38-bf16.sh \
        scripts/build-qwen38-bf16-rad.sh \
        scripts/run-qwen38-bf16.sh \
        scripts/convert-qwen38-w5nl64.sh \
        scripts/kld-gate-qwen38.sh \
        scripts/grams-to-imatrix.py \
        scripts/recipes/qwen4exp-qwen38-w5nl64-bf16trunk.recipe \
        tests/qwen38_campaign.bats
    [ "$status" -eq 0 ]
    [ -z "$output" ]
 }
 # --- protected experts -------------------------------------------------------
 DERIVE="$REPO_ROOT/scripts/derive-protected-experts.py"
 APPLY="$REPO_ROOT/scripts/apply-protected-cast.sh"
 CONVERT="$REPO_ROOT/scripts/convert-qwen38-w5nl64.sh"
 GATE="$REPO_ROOT/scripts/kld-gate-qwen38.sh"
 TEMPLATE="$REPO_ROOT/scripts/recipes/qwen4exp-qwen38-w5nl64-bf16trunk.recipe"
 # make_gram <dir> <layer> <expert> <energy> <rows> — a RADGRAM2 down-Gram whose
 # trace (its down-input energy) is <energy> and whose routing count is <rows>.
 make_gram() {
    python3 - "$@" <<'PY'
 import os, struct, sys
 d, layer, e, energy, rows = sys.argv[1:6]
 os.makedirs(d, exist_ok=True)
 hdr = struct.pack("<8sIIQI4x", b"RADGRAM2", 2, 0, int(rows), 0)
 mat = struct.pack("<4f", float(energy), 0.0, 0.0, 0.0)
 with open(os.path.join(d, f"gram.r0.blk.{layer}.ffn_down_exps.{e}.bin"), "wb") as f:
    f.write(hdr + mat)
 PY
 }
 # eight_grams <dir> — one layer, eight experts inside rank half 0, energies
 # 60/15/10/8/4/2/1/0.5 against equal routing. Under the default bars (3% of the
 # layer's energy AND 3x its routing share) exactly ONE expert is disproportionate,
 # so the parity law has to hand it a partner.
 eight_grams() {
    local d="$1"
    make_gram "$d" 0 0 60 100
    make_gram "$d" 0 1 15 100
    make_gram "$d" 0 2 10 100
    make_gram "$d" 0 3 8 100
    make_gram "$d" 0 4 4 100
    make_gram "$d" 0 5 2 100
    make_gram "$d" 0 6 1 100
    make_gram "$d" 0 7 0.5 100
 }
 cast_count() { grep -c 'cast dtype=bf16' <<< "$output"; }
@test "the bar-only pass keeps the disproportionate expert and repairs the odd rank half" {
    C="$BATS_TEST_TMPDIR/calib"
    eight_grams "$C"
    run python3 "$DERIVE" "$C"
    [ "$status" -eq 0 ]
    # e0 holds 59.7% of the layer's energy on 12.5% of the routing: the only expert
    # that clears three times its routing share. e1 joins it because half 0 was odd.
    [ "$(cast_count)" -eq 2 ]
    [[ "$output" == *"blk.0.ffn_*_exps.0.weight"* ]]
    [[ "$output" == *"blk.0.ffn_*_exps.1.weight"* ]]
    [[ "$output" != *"ffn_*_exps.2.weight"* ]]
    [[ "$output" == *"half 0 odd -> added e1"* ]]
 }
@test "--target-count lands the byte bill that was asked for, and never buys more" {
    # The count is a disk and VRAM decision (each protected expert costs bf16 twice,
    # once per rank half's copy), so landing it matters as much as not missing it.
    C="$BATS_TEST_TMPDIR/calib"
    eight_grams "$C"
    run python3 "$DERIVE" "$C" --target-count 6
    [ "$status" -eq 0 ]
    [ "$(cast_count)" -eq 6 ]
    [[ "$output" == *"count fill -> added e2"* ]]
    [[ "$output" != *"ffn_*_exps.6.weight"* ]]
    # the energy share the set bottoms out at is the bar the campaign paid for
    [[ "$output" == *"total protected: 6 (target 6, energy cutoff"* ]]
 }
@test "--target-count cannot invent experts: the pool's ceiling is reported, not padded" {
    C="$BATS_TEST_TMPDIR/calib"
    eight_grams "$C"
    run python3 "$DERIVE" "$C" --target-count 20
    [ "$status" -eq 0 ]
    [ "$(cast_count)" -eq 8 ]
    [[ "$output" == *"total protected: 8 (target 20"* ]]
 }
@test "a protected set that cannot be made even is refused instead of emitted" {
    # One disproportionate expert in half 0, its only companion in half 1: no
    # candidate could make half 0 even, and an odd half hands the four-bit GEMM two
    # tables that are not equal. Refusing is the only honest answer.
    C="$BATS_TEST_TMPDIR/calib"
    make_gram "$C" 0 0 100 100
    make_gram "$C" 0 300 1 1000
    run python3 "$DERIVE" "$C"
    [ "$status" -eq 2 ]
    [[ "$output" == *"PARITY LAW BROKEN"* ]]
    [[ "$output" == *"blk.0 half 0 holds 1"* ]]
    [ "$(cast_count)" -eq 0 ]
 }
@test "the splice rewrites the run's copy above the expert rule and refuses a second run" {
    C="$BATS_TEST_TMPDIR/calib"
    eight_grams "$C"
    W="$BATS_TEST_TMPDIR/recipe-work.recipe"
    cp "$TEMPLATE" "$W"
    run env PY=python3 TRASH_DIR="$BATS_TEST_TMPDIR/trash" bash "$APPLY" "$C" "$W" 0
    [ "$status" -eq 0 ]
    grep -q "derive-protected-experts.py rewrote" "$W"
    # The derived lines must precede the expert rule: the first rule whose glob
    # matches a weight decides it, so a cast line below the expert line never fires.
    cast_line=$(grep -n 'cast dtype=bf16' "$W" | head -1 | cut -d: -f1)
    expert_line=$(grep -n 'ffn_\*_exps\.\*\.weight' "$W" | head -1 | cut -d: -f1)
    [ "$cast_line" -lt "$expert_line" ]
    # The committed template stays the clean, reviewable baseline.
    ! grep -q "derive-protected-experts.py rewrote" "$TEMPLATE"
    # A second run on the same copy would derive from a recording it already spent.
    run env PY=python3 TRASH_DIR="$BATS_TEST_TMPDIR/trash" bash "$APPLY" "$C" "$W" 0
    [ "$status" -ne 0 ]
    [[ "$output" == *"refusing to re-derive"* ]]
 }
@test "the splice refuses before touching the recipe when the count is not reached" {
    C="$BATS_TEST_TMPDIR/calib"
    eight_grams "$C"
    W="$BATS_TEST_TMPDIR/recipe-work.recipe"
    cp "$TEMPLATE" "$W"
    run env PY=python3 TRASH_DIR="$BATS_TEST_TMPDIR/trash" bash "$APPLY" "$C" "$W" 20
    [ "$status" -eq 1 ]
    [[ "$output" == *"target was 20"* ]]
    ! grep -q "derive-protected-experts.py rewrote" "$W"
 }
 # --- the arm driver ----------------------------------------------------------
 # drv_fixture <dir> — the smallest tree the driver's gates accept: a checkpoint
 # with its index and tokenizer, three grams, an imatrix inside the campaign dir
 # the container mounts, and an empty output dir.
 drv_fixture() {
    local d="$1"
    mkdir -p "$d/ck/Qwen3.8-Flash-Next" "$d/campaign" "$d/calib" "$d/out"
    : > "$d/ck/Qwen3.8-Flash-Next/model.safetensors.index.json"
    : > "$d/ck/Qwen3.8-Flash-Next/tokenizer.json"
    make_gram "$d/calib" 0 0 60 100
    make_gram "$d/calib" 0 1 15 100
    make_gram "$d/calib" 0 2 10 100
    # four experts, not three: a thin pool that cannot be made even trips the parity
    # audit, and this fixture is meant to reach the later gates
    make_gram "$d/calib" 0 3 8 100
    : > "$d/campaign/imatrix.gguf"
 }
 # run_drv <driver args and K=V overrides, any order> — the driver with every path
 # pointed at the fixture. Override words are separated out because `env` only
 # accepts assignments ahead of the command; later assignments win, so a test can
 # break exactly one input.
 run_drv() {
    local d="$BATS_TEST_TMPDIR/drv" assigns=() flags=() w
    for w in "$@"; do
        if [[ "$w" =~ ^[A-Za-z_][A-Za-z0-9_]*= ]]; then assigns+=("$w"); else flags+=("$w"); fi
    done
    run env CKPT="$d/ck/Qwen3.8-Flash-Next" CAMPAIGN="$d/campaign" STATE="$d/campaign" \
        CALIB="$d/calib" OUTDIR="$d/out" IMATRIX="$d/campaign/imatrix.gguf" \
        MIN_GRAMS=2 TARGET_COUNT=0 ${assigns[@]+"${assigns[@]}"} \
        bash "$CONVERT" ${flags[@]+"${flags[@]}"}
 }
@test "the dry run prints the plan and then the convert for every arm" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv --dry-run
    [ "$status" -eq 0 ]
    [[ "$output" == *"== arm cd3 =="* ]]
    [[ "$output" == *"== arm cd6 =="* ]]
    [[ "$output" == *"== arm ao1 =="* ]]
    # one --plan-only bill per arm, and one convert line per arm beside it
    [ "$(grep -c -- '--plan-only' <<< "$output")" -eq 3 ]
    [ "$(grep -c 'rad-convert' <<< "$output")" -eq 6 ]
    awk '/arm cd3/ {next}
         /qwen38-w5nl64-cd3\.rad/ { if ($0 ~ /--plan-only/) p = NR; else c = NR }
         END { exit !(p && c && p < c) }' <<< "$output"
 }
@test "the cd6 arm re-sends the whole expert option set with cd=6; the control sends none" {
    # --quant replaces the recipe line wholesale, so an override that forgot an
    # option would quietly convert with the default for it.
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv --arm cd3 --arm cd6 --dry-run
    [ "$status" -eq 0 ]
    cd6line=$(grep -- '-cd6\.rad --quant' <<< "$output" | head -1)
    [[ "$cd6line" == *"table=w5nl"* ]]
    [[ "$cd6line" == *"group=64"* ]]
    [[ "$cd6line" == *"scale=fp8_e4m3"* ]]
    [[ "$cd6line" == *"transform=fwht128"* ]]
    [[ "$cd6line" == *"calib=\$CALIB"* ]]
    [[ "$cd6line" == *",cd=6"* ]]
    cd3line=$(grep -- '-cd3\.rad' <<< "$output" | grep -v -- '--plan-only' | head -1)
    [[ "$cd3line" != *"--quant"* ]]
 }
@test "the ao1 arm carries act_order=1 and no cd=, because libquant refuses the pair" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv --arm ao1 --dry-run
    [ "$status" -eq 0 ]
    line=$(grep -- '-ao1\.rad --quant' <<< "$output" | head -1)
    [[ "$line" == *"act_order=1"* ]]
    [[ "$line" != *",cd="* ]]
 }
@test "the driver splices the protected plane into its own copy, never the template" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv --dry-run
    [[ "$output" == *"apply-protected-cast.sh $BATS_TEST_TMPDIR/drv/calib "* ]]
    [[ "$output" == *"/campaign/recipe-"* ]]
    [[ "$output" != *"$TEMPLATE"* ]]
 }
@test "the driver refuses while the BF16 reference container still holds the volume" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    : > "$BATS_TEST_TMPDIR/drv/out/qwen38-bf16.rad"
    run_drv --dry-run
    [ "$status" -eq 2 ]
    [[ "$output" == *"peak-disk"* ]]
 }
@test "a thin recording is refused: the driver never converts uncalibrated" {
    # rad-convert converts WITHOUT a calibration recording with one stderr note,
    # which is silently worse than a GPTQ run that failed.
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv MIN_GRAMS=9 --dry-run
    [ "$status" -eq 2 ]
    [[ "$output" == *"run-qwen38-bf16.sh calib"* ]]
 }
@test "an imatrix outside the mounted campaign dir is refused before any convert" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    mv "$BATS_TEST_TMPDIR/drv/campaign/imatrix.gguf" "$BATS_TEST_TMPDIR/imatrix.gguf"
    run_drv IMATRIX="$BATS_TEST_TMPDIR/imatrix.gguf" --dry-run
    [ "$status" -eq 2 ]
    [[ "$output" == *"not in the campaign dir"* ]]
 }
@test "the driver never overwrites an arm that already exists" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    : > "$BATS_TEST_TMPDIR/drv/out/qwen38-w5nl64-cd6.rad"
    run_drv --arm cd6 --dry-run
    [ "$status" -eq 2 ]
    [[ "$output" == *"move it to trash first"* ]]
 }
@test "an unknown arm name is refused before the gates run" {
    # No fixture built: the name check must not need a checkpoint to exist.
    run_drv --arm cd9 --dry-run
    [ "$status" -eq 2 ]
    [[ "$output" == *"unknown arm: cd9"* ]]
 }
@test "the driver stops when the protected derivation cannot land the target" {
    drv_fixture "$BATS_TEST_TMPDIR/drv"
    run_drv PY=python3 TARGET_COUNT=20 --arm cd3
    [ "$status" -eq 1 ]
    [[ "$output" == *"target was 20"* ]]
    [[ "$output" == *"would convert unprotected"* ]]
    [[ "$output" != *"--entrypoint"* ]]
 }
 # --- the acceptance gate -----------------------------------------------------
 # kld_report <path> <model> <kl mean> <top1 fraction> — one score report, in the
 # shape `run-qwen38-bf16.sh score` writes: an `all` summary plus a per-source one.
 kld_report() {
    python3 - "$@" <<'PY'
 import json, sys
 path, model, kl, top1 = sys.argv[1:5]
 kl, top1 = float(kl), float(top1)
 group = {"kld": {"mean": kl, "p99_9": kl * 4}, "top1_agreement": top1, "positions": 50432}
 json.dump({"model": model, "all": group,
           "by_source": {"ops": dict(group, positions=20000)}}, open(path, "w"))
 PY
 }
 gate_case() { # gate_case <kl fp8> <kl iq4r> <kl cand> <top1 cand> [extra flags...]
    D="$BATS_TEST_TMPDIR/kl"
    mkdir -p "$D"
    kld_report "$D/fp8.json" fp8-native "$1" 0.981
    kld_report "$D/iq4r.json" iq4r-moe "$2" 0.962
    kld_report "$D/cand.json" w5nl64 "$3" "$4"
    run bash "$GATE" "$D/fp8.json" "$D/iq4r.json" "$D/cand.json" "${@:5}"
 }
@test "an arm strictly inside the interval that closes half the gap passes" {
    gate_case 0.0021 0.0190 0.0090 0.971
    [ "$status" -eq 0 ]
    [[ "$output" == *"closes 59.2%"* ]]
    [[ "$output" == *"KLD GATE PASS"* ]]
 }
@test "an arm worse than the served payload fails the interval and the recovery" {
    gate_case 0.0021 0.0190 0.0210 0.971
    [ "$status" -eq 1 ]
    [[ "$output" == *"[FAIL] 2."* ]]
    [[ "$output" == *"[FAIL] 3."* ]]
    [[ "$output" == *"KLD GATE FAIL"* ]]
 }
@test "anchors that are not ordered stop the gate: the instrument is wrong, not the arm" {
    # If the near-lossless FP8 release does not sit CLOSER to the bf16 reference
    # than the 4-bit payload does, the corpus, tokenizer or boot shape is broken and
    # no arm number can mean anything.
    gate_case 0.0300 0.0190 0.0120 0.971
    [ "$status" -eq 1 ]
    [[ "$output" == *"[FAIL] 1."* ]]
    [[ "$output" == *"gap is not positive"* ]]
 }
@test "an arm measured outside the interval fails even when it looks better" {
    # Closer to the reference than the achievable anchor is a measurement fault.
    gate_case 0.0021 0.0190 0.0010 0.971
    [ "$status" -eq 1 ]
    [[ "$output" == *"[FAIL] 2."* ]]
 }
@test "an arm that buys KL with top-1 agreement fails" {
    gate_case 0.0021 0.0190 0.0090 0.940
    [ "$status" -eq 1 ]
    [[ "$output" == *"[PASS] 3."* ]]
    [[ "$output" == *"[FAIL] 4."* ]]
 }
@test "--recover tightens the same numbers until they fail" {
    gate_case 0.0021 0.0190 0.0090 0.971 --recover 0.8
    [ "$status" -eq 1 ]
    [[ "$output" == *"needs 80%"* ]]
    [[ "$output" == *"[FAIL] 3."* ]]
 }
@test "a slice the report does not carry is named, not guessed at" {
    gate_case 0.0021 0.0190 0.0090 0.971 --slice code
    [ "$status" -eq 2 ]
    [[ "$output" == *"has no slice 'code'"* ]]
    [[ "$output" == *"it has: ops"* ]]
 }