alexion
97c0eeb055
Add a second pure transform to the benchmark core: a `--leaderboard` mode that ranks per-skill results models into an index leaderboard, one row per skill carrying both verdicts, links out to each per-skill report, and sorts any red first (regressions above efficacy failures), then fragile-but-passing, then clean green. The fragile tier reuses the 0006 per-badge chips: the efficacy chip now carries its win count so the leaderboard reads it against the pass floor without recomputing margins, and fragility is scoped to the passing tier so a red row never carries a chip. The runner's SKILL.md gains the no-argument batch flow and the index invocation. The fixture test covers the tiered sort, the not-applicable Regression cell, and the per-skill links.
359 lines
19 KiB
Nix
359 lines
19 KiB
Nix
# Feeds the committed run-bundle fixtures through the benchmark skill's
|
|
# deterministic core and asserts the per-arm metrics, the per-case and
|
|
# skill-level Efficacy and Regression verdicts, and the rendered report — for
|
|
# both the three-arm shape and the degenerate two-arm "no previous version"
|
|
# shape.
|
|
# It also drives the longitudinal layer: the per-skill history append-and-trim,
|
|
# the two trend ribbons including the two-arm gap in the regression series, and
|
|
# the per-badge fragility chips on a clean run and a green-but-fragile one.
|
|
# Last it drives the all-skills leaderboard: the tiered sort, the not-applicable
|
|
# Regression cell, and the links out to each per-skill report.
|
|
# No LLM runs.
|
|
{
|
|
pkgs,
|
|
}:
|
|
let
|
|
core = ../skills/benchmark-skill/core/benchmark_core.py;
|
|
threeArm = ./fixtures/benchmark/three-arm-bundle.json;
|
|
twoArm = ./fixtures/benchmark/two-arm-bundle.json;
|
|
clean = ./fixtures/benchmark/clean-bundle.json;
|
|
fragile = ./fixtures/benchmark/fragile-bundle.json;
|
|
in
|
|
pkgs.runCommandLocal "benchmark-core-check"
|
|
{
|
|
nativeBuildInputs = [ pkgs.python3 ];
|
|
inherit core threeArm twoArm clean fragile;
|
|
}
|
|
''
|
|
fail() { echo "FAIL: $1" >&2; exit 1; }
|
|
|
|
# --- three-arm run --------------------------------------------------------
|
|
echo "the core scores a three-arm run and renders its report"
|
|
python3 "$core" "$threeArm" --json three.json --html three.html \
|
|
|| fail "the core exited non-zero on the three-arm bundle"
|
|
|
|
echo "the three-arm results model carries both verdicts, net margins, and metrics"
|
|
python3 - three.json <<'PY' || fail "a three-arm results-model assertion failed"
|
|
import json, sys
|
|
r = json.load(open(sys.argv[1]))
|
|
|
|
assert r["armShape"] == "three-arm", r["armShape"]
|
|
# Efficacy is red: dead-weight fails the wins floor and hard-gate-fail trips
|
|
# the gate. Regression is red: regressed-still-valuable loses twice to the
|
|
# previous version.
|
|
assert r["efficacyVerdict"] == "red", r["efficacyVerdict"]
|
|
assert r["regressionVerdict"] == "red", r["regressionVerdict"]
|
|
assert r["efficacyNetMargin"] == 12, r["efficacyNetMargin"]
|
|
assert r["regressionNetMargin"] == 3, r["regressionNetMargin"]
|
|
|
|
new = r["armMetrics"]["new"]
|
|
assert new["turns"] == 60, new["turns"]
|
|
assert new["rawTokens"] == 228000, new["rawTokens"]
|
|
assert new["costEquivalentTokens"] == 246000, new["costEquivalentTokens"]
|
|
assert abs(new["imputedCost"] - 1.23) < 1e-9, new["imputedCost"]
|
|
|
|
base = r["armMetrics"]["baseline"]
|
|
assert base["turns"] == 40, base["turns"]
|
|
assert base["rawTokens"] == 114000, base["rawTokens"]
|
|
assert base["costEquivalentTokens"] == 123000, base["costEquivalentTokens"]
|
|
|
|
prev = r["armMetrics"]["previous"]
|
|
assert prev["turns"] == 60, prev["turns"]
|
|
assert prev["rawTokens"] == 174000, prev["rawTokens"]
|
|
assert prev["costEquivalentTokens"] == 195500, prev["costEquivalentTokens"]
|
|
assert abs(prev["imputedCost"] - 0.9775) < 1e-9, prev["imputedCost"]
|
|
|
|
# Cost-table rows render in arm order: new-skill, previous-version, no-skill.
|
|
assert [a["id"] for a in r["arms"]] == ["new", "previous", "baseline"], \
|
|
[a["id"] for a in r["arms"]]
|
|
|
|
cases = {c["name"]: c for c in r["cases"]}
|
|
# Authored order is preserved, never reshuffled by verdict.
|
|
assert [c["name"] for c in r["cases"]] == [
|
|
"clean-both", "regressed-still-valuable", "dead-weight", "hard-gate-fail"
|
|
]
|
|
|
|
a = cases["clean-both"]
|
|
assert a["efficacyPassed"] is True
|
|
assert a["regressionPassed"] is True
|
|
assert a["comparisons"]["efficacy"]["trials"] == ["WIN", "WIN", "WIN", "WIN", "TIE"]
|
|
assert a["comparisons"]["regression"]["trials"] == ["TIE", "TIE", "WIN", "TIE", "TIE"]
|
|
|
|
# Efficacy green but regression red — the exact crossing this feature exists
|
|
# to catch: still beats no-skill, yet degraded from the released version.
|
|
b = cases["regressed-still-valuable"]
|
|
assert b["efficacyPassed"] is True
|
|
assert b["regressionPassed"] is False
|
|
assert b["comparisons"]["regression"]["losses"] == 2
|
|
assert b["comparisons"]["regression"]["flaggedLosses"] == [0, 1]
|
|
|
|
# Efficacy red but regression green — already dead weight, but the edit did
|
|
# not make it worse.
|
|
c = cases["dead-weight"]
|
|
assert c["efficacyPassed"] is False
|
|
assert c["regressionPassed"] is True
|
|
assert c["comparisons"]["efficacy"]["wins"] == 0
|
|
assert c["comparisons"]["efficacy"]["losses"] == 1
|
|
assert c["comparisons"]["efficacy"]["flaggedLosses"] == [2]
|
|
assert c["comparisons"]["regression"]["wins"] == 3
|
|
|
|
# The hard gate fails efficacy outright but does not gate regression, which
|
|
# is judged purely on losses.
|
|
d = cases["hard-gate-fail"]
|
|
assert d["hardFailed"] is True
|
|
assert d["efficacyPassed"] is False
|
|
assert d["regressionPassed"] is True
|
|
assert d["comparisons"]["efficacy"]["wins"] == 5
|
|
print("three-arm results-model assertions passed")
|
|
PY
|
|
|
|
echo "the three-arm report shows both badges, the three-row table, and evidence"
|
|
grep -q '<!doctype html>' three.html || fail "three-arm report is not self-contained"
|
|
grep -q 'Efficacy: RED' three.html || fail "three-arm report is missing the red Efficacy badge"
|
|
grep -q 'Regression: RED' three.html || fail "three-arm report is missing the red Regression badge"
|
|
grep -qi 'regress' three.html || fail "three-arm report is missing the verdict headline"
|
|
grep -q 'Cost-equiv tokens' three.html || fail "three-arm report is missing the cost table"
|
|
grep -q 'Previous version' three.html || fail "three-arm report is missing the previous-version row"
|
|
grep -q 'shared-context cache' three.html || fail "three-arm report is missing the cache footnote"
|
|
grep -q 'new-vs-no-skill' three.html || fail "three-arm footnote omits the new-vs-no-skill ratio"
|
|
grep -q 'new-vs-old' three.html || fail "three-arm footnote omits the new-vs-old ratio"
|
|
for name in clean-both regressed-still-valuable dead-weight hard-gate-fail; do
|
|
grep -q "$name" three.html || fail "three-arm report omits case $name"
|
|
done
|
|
grep -q 'class="cell LOSS"' three.html || fail "three-arm report is missing a LOSS cell"
|
|
grep -q 'Hard assertion failed' three.html || fail "three-arm report does not flag the hard failure"
|
|
grep -q ' open>' three.html || fail "three-arm report does not auto-expand a failing case"
|
|
grep -q 'class="cmps"' three.html || fail "three-arm report does not lay comparisons side by side"
|
|
# Evidence for the failed regression comparison: new vs previous on trial 1.
|
|
grep -q 'OUT-new-regressed-still-valuable-t0' three.html || fail "missing new evidence for the regression loss"
|
|
grep -q 'OUT-previous-regressed-still-valuable-t0' three.html || fail "missing previous evidence for the regression loss"
|
|
# Evidence for the failed efficacy comparison: new vs baseline on trial 3.
|
|
grep -q 'OUT-new-dead-weight-t2' three.html || fail "missing new evidence for the efficacy loss"
|
|
grep -q 'OUT-baseline-dead-weight-t2' three.html || fail "missing baseline evidence for the efficacy loss"
|
|
# A clean, collapsed case emits no losing-trial evidence.
|
|
if grep -q 'OUT-new-clean-both' three.html; then fail "a clean case leaked losing-trial evidence"; fi
|
|
|
|
# --- two-arm run ----------------------------------------------------------
|
|
echo "the core scores the degenerate two-arm run"
|
|
python3 "$core" "$twoArm" --json two.json --html two.html \
|
|
|| fail "the core exited non-zero on the two-arm bundle"
|
|
|
|
echo "the two-arm results model reads regression as not-applicable"
|
|
python3 - two.json <<'PY' || fail "a two-arm results-model assertion failed"
|
|
import json, sys
|
|
r = json.load(open(sys.argv[1]))
|
|
|
|
assert r["armShape"] == "two-arm", r["armShape"]
|
|
assert r["efficacyVerdict"] == "red", r["efficacyVerdict"]
|
|
assert r["regressionVerdict"] == "not-applicable", r["regressionVerdict"]
|
|
assert r["regressionNetMargin"] is None, r["regressionNetMargin"]
|
|
assert r["efficacyNetMargin"] == 9, r["efficacyNetMargin"]
|
|
|
|
new = r["armMetrics"]["new"]
|
|
assert new["turns"] == 45, new["turns"]
|
|
assert new["rawTokens"] == 171000, new["rawTokens"]
|
|
assert new["costEquivalentTokens"] == 184500, new["costEquivalentTokens"]
|
|
assert abs(new["imputedCost"] - 0.9225) < 1e-9, new["imputedCost"]
|
|
|
|
base = r["armMetrics"]["baseline"]
|
|
assert base["turns"] == 30, base["turns"]
|
|
assert base["rawTokens"] == 85500, base["rawTokens"]
|
|
assert base["costEquivalentTokens"] == 92250, base["costEquivalentTokens"]
|
|
|
|
assert "previous" not in r["armMetrics"], "two-arm run has no previous arm"
|
|
|
|
assert [c["name"] for c in r["cases"]] == [
|
|
"clean-pass", "regresses-baseline", "hard-gate-fail"
|
|
]
|
|
for c in r["cases"]:
|
|
assert c["regressionPassed"] is None, (c["name"], c["regressionPassed"])
|
|
|
|
b = {c["name"]: c for c in r["cases"]}["regresses-baseline"]
|
|
assert b["efficacyPassed"] is False
|
|
assert b["comparisons"]["efficacy"]["losses"] == 2
|
|
assert b["comparisons"]["efficacy"]["flaggedLosses"] == [3, 4]
|
|
|
|
h = {c["name"]: c for c in r["cases"]}["hard-gate-fail"]
|
|
assert h["hardFailed"] is True
|
|
print("two-arm results-model assertions passed")
|
|
PY
|
|
|
|
echo "the two-arm report reads Regression as not-applicable and drops the previous row"
|
|
grep -q 'Efficacy: RED' two.html || fail "two-arm report is missing the Efficacy badge"
|
|
grep -q 'Regression: N/A' two.html || fail "two-arm report does not read Regression as not-applicable"
|
|
grep -q 'new-vs-no-skill' two.html || fail "two-arm footnote omits the new-vs-no-skill ratio"
|
|
if grep -q 'new-vs-old' two.html; then fail "two-arm footnote names a new-vs-old ratio that does not apply"; fi
|
|
if grep -q 'Previous version' two.html; then fail "two-arm report shows a previous-version row"; fi
|
|
grep -q 'OUT-new-regresses-baseline-t3' two.html || fail "missing new evidence for the two-arm efficacy loss"
|
|
grep -q 'OUT-baseline-regresses-baseline-t3' two.html || fail "missing baseline evidence for the two-arm efficacy loss"
|
|
|
|
# --- clean run: fully collapsed, one narrowest-margin chip, ribbons ---------
|
|
echo "the core rests a clean run fully collapsed with a lone narrowest-margin chip"
|
|
python3 "$core" "$clean" --json clean.json --html clean.html --history clean.history.jsonl \
|
|
|| fail "the core exited non-zero on the clean bundle"
|
|
|
|
python3 - clean.json <<'PY' || fail "a clean-run assertion failed"
|
|
import json, sys
|
|
r = json.load(open(sys.argv[1]))
|
|
assert r["efficacyVerdict"] == "green", r["efficacyVerdict"]
|
|
assert r["regressionVerdict"] == "green", r["regressionVerdict"]
|
|
cases = {c["name"]: c for c in r["cases"]}
|
|
# The narrowest efficacy case (fewest wins) carries the chip, the roomy one does not.
|
|
assert [ch["axis"] for ch in cases["narrowest"]["chips"]] == ["efficacy"], cases["narrowest"]["chips"]
|
|
assert cases["roomy"]["chips"] == [], cases["roomy"]["chips"]
|
|
# The efficacy chip carries the case's win count, not merely its label text.
|
|
assert cases["narrowest"]["chips"][0]["wins"] == 3, cases["narrowest"]["chips"]
|
|
print("clean-run assertions passed")
|
|
PY
|
|
|
|
if grep -q ' open>' clean.html; then fail "a clean run did not rest fully collapsed"; fi
|
|
grep -q 'class="chip efficacy"' clean.html || fail "clean run omits the narrowest-margin efficacy chip"
|
|
if grep -q 'class="chip regression"' clean.html; then fail "clean run shows a spurious regression chip"; fi
|
|
grep -q 'class="ribbons"' clean.html || fail "clean run omits the trend ribbons"
|
|
grep -q 'class="spark"' clean.html || fail "clean run omits a sparkline"
|
|
grep -q 'class="ring"' clean.html || fail "clean run does not ring the current run"
|
|
|
|
# --- history append-and-trim and the two-ribbon window with a two-arm gap ---
|
|
echo "the core appends to and trims the per-skill history and plots the ribbon window"
|
|
python3 - seed.history.jsonl <<'PY' || fail "seeding the history fixture failed"
|
|
import json, sys
|
|
# 55 prior runs, all three-arm except the most recent, which is two-arm and so
|
|
# must plot a gap on the regression axis once it lands inside the 7-run window.
|
|
lines = []
|
|
for i in range(55):
|
|
two = i == 54
|
|
lines.append({
|
|
"generatedAt": f"seed-{i}",
|
|
"armShape": "two-arm" if two else "three-arm",
|
|
"efficacyNet": i % 5,
|
|
"efficacyPass": True,
|
|
"regressionNet": None if two else i % 3,
|
|
"regressionPass": None if two else True,
|
|
})
|
|
open(sys.argv[1], "w").write("".join(json.dumps(l) + "\n" for l in lines))
|
|
PY
|
|
|
|
python3 "$core" "$clean" --json trend.json --history seed.history.jsonl \
|
|
|| fail "the core exited non-zero on the seeded-history run"
|
|
|
|
python3 - seed.history.jsonl trend.json <<'PY' || fail "a history/trend assertion failed"
|
|
import json, sys
|
|
lines = [json.loads(l) for l in open(sys.argv[1]) if l.strip()]
|
|
# 55 prior + this run = 56, trimmed oldest-first back to the cap of 50.
|
|
assert len(lines) == 50, len(lines)
|
|
gens = [l["generatedAt"] for l in lines]
|
|
assert "seed-0" not in gens and "seed-5" not in gens, "oldest runs were not trimmed"
|
|
assert "seed-6" in gens and "seed-54" in gens, "recent runs were wrongly trimmed"
|
|
assert lines[-1]["armShape"] == "three-arm", lines[-1]
|
|
assert lines[-1]["efficacyNet"] == 8 and lines[-1]["regressionNet"] == 1, lines[-1]
|
|
|
|
t = json.load(open(sys.argv[2]))["trend"]
|
|
eff, reg = t["efficacy"]["points"], t["regression"]["points"]
|
|
assert len(eff) == 7 and len(reg) == 7, (len(eff), len(reg))
|
|
# Efficacy has a value every run, while regression breaks at the two-arm run.
|
|
assert all(p["net"] is not None for p in eff), "efficacy series should have no gaps"
|
|
assert eff[-1]["current"] and reg[-1]["current"], "the current run is ringed on both axes"
|
|
assert reg[5]["net"] is None, [p["net"] for p in reg]
|
|
assert reg[-1]["net"] is not None, "the current three-arm run has a regression dot"
|
|
assert t["regression"]["applicable"] == 6, t["regression"]["applicable"]
|
|
print("history/trend assertions passed")
|
|
PY
|
|
|
|
# --- green-but-fragile run: independent per-badge chips, both on one case ----
|
|
echo "the core chips each fragility axis independently, and both on a doubly-fragile case"
|
|
python3 "$core" "$fragile" --json fragile.json --html fragile.html \
|
|
|| fail "the core exited non-zero on the fragile bundle"
|
|
|
|
python3 - fragile.json <<'PY' || fail "a fragility-chip assertion failed"
|
|
import json, sys
|
|
r = json.load(open(sys.argv[1]))
|
|
assert r["efficacyVerdict"] == "green" and r["regressionVerdict"] == "green"
|
|
cases = {c["name"]: c for c in r["cases"]}
|
|
# One case is both the narrowest efficacy margin and at exactly one regression
|
|
# loss, so it carries both chips.
|
|
# The others carry at most their own axis.
|
|
assert {ch["axis"] for ch in cases["both"]["chips"]} == {"efficacy", "regression"}, cases["both"]["chips"]
|
|
assert [ch["axis"] for ch in cases["reg-only"]["chips"]] == ["regression"], cases["reg-only"]["chips"]
|
|
assert cases["none"]["chips"] == [], cases["none"]["chips"]
|
|
print("fragility-chip assertions passed")
|
|
PY
|
|
|
|
grep -q 'class="chip efficacy"' fragile.html || fail "fragile run omits the efficacy chip"
|
|
grep -q 'class="chip regression"' fragile.html || fail "fragile run omits the regression chip"
|
|
|
|
# --- all-skills leaderboard: tiered sort, the N/A cell, and per-skill links ---
|
|
echo "the core ranks per-skill results into a tiered index leaderboard"
|
|
# A synthetic clean-green skill whose narrowest efficacy margin sits above the
|
|
# floor, so it is the one input that reaches the clean-green tier. The four
|
|
# scored models above supply the other tiers: three-arm regresses (tier 0),
|
|
# two-arm fails efficacy with regression not-applicable (tier 1), and the
|
|
# clean and fragile green runs are both one flip from failing (tier 2).
|
|
python3 - robust.results.json leaky.results.json <<'PY' || fail "writing the leaderboard fixtures failed"
|
|
import json, sys
|
|
# A clean-green skill whose narrowest efficacy margin clears the floor, the
|
|
# one input that reaches the clean-green tier.
|
|
json.dump({
|
|
"skill": "robust-skill",
|
|
"efficacyVerdict": "green",
|
|
"regressionVerdict": "green",
|
|
"cases": [{"chips": [{"axis": "efficacy", "wins": 5}]}],
|
|
}, open(sys.argv[1], "w"))
|
|
# An efficacy-red skill whose still-green regression axis sits one loss from
|
|
# regressing, so it carries a regression chip yet belongs in the red tier.
|
|
json.dump({
|
|
"skill": "leaky-skill",
|
|
"efficacyVerdict": "red",
|
|
"regressionVerdict": "green",
|
|
"cases": [{"chips": [{"axis": "regression"}]}],
|
|
}, open(sys.argv[2], "w"))
|
|
PY
|
|
|
|
python3 "$core" --leaderboard \
|
|
three.json two.json clean.json fragile.json robust.results.json leaky.results.json \
|
|
--json board.json --html board.html \
|
|
|| fail "the core exited non-zero rendering the leaderboard"
|
|
|
|
python3 - board.json <<'PY' || fail "a leaderboard assertion failed"
|
|
import json, sys
|
|
rows = json.load(open(sys.argv[1]))
|
|
|
|
# Any red first — regressions above efficacy failures, efficacy failures
|
|
# ordered by name — then fragile-passing by name, then clean green.
|
|
assert [r["skill"] for r in rows] == [
|
|
"sample-skill", "leaky-skill", "sample-skill-2arm",
|
|
"clean-skill", "fragile-skill", "robust-skill",
|
|
], [r["skill"] for r in rows]
|
|
assert [r["tier"] for r in rows] == [0, 1, 1, 2, 2, 3], [r["tier"] for r in rows]
|
|
|
|
by = {r["skill"]: r for r in rows}
|
|
# The regressed skill outranks the merely-efficacy-failed ones.
|
|
assert by["sample-skill"]["regressionVerdict"] == "red"
|
|
# A skill with no previous version reads not-applicable in its Regression cell.
|
|
assert by["sample-skill-2arm"]["regressionVerdict"] == "not-applicable"
|
|
assert by["sample-skill-2arm"]["efficacyVerdict"] == "red"
|
|
# The fragile tier reuses the per-badge chips: a floor-bound efficacy margin,
|
|
# a case one loss from regressing, or both.
|
|
assert by["clean-skill"]["fragileAxes"] == ["efficacy"], by["clean-skill"]
|
|
assert by["fragile-skill"]["fragileAxes"] == ["efficacy", "regression"], by["fragile-skill"]
|
|
assert by["robust-skill"]["fragileAxes"] == [], by["robust-skill"]
|
|
# A red skill carries no fragility chip even when a still-passing axis is at
|
|
# its edge, so the chip stays the marker of the fragile-but-passing tier.
|
|
assert by["leaky-skill"]["fragileAxes"] == [], by["leaky-skill"]
|
|
# Every row links out to its per-skill report, keyed by skill name.
|
|
for r in rows:
|
|
assert r["href"] == r["skill"] + ".html", r
|
|
print("leaderboard assertions passed")
|
|
PY
|
|
|
|
echo "the leaderboard is self-contained and links out to each per-skill report"
|
|
grep -q '<!doctype html>' board.html || fail "the leaderboard is not self-contained"
|
|
for skill in sample-skill sample-skill-2arm clean-skill fragile-skill robust-skill leaky-skill; do
|
|
grep -q "href=\"$skill.html\"" board.html || fail "the leaderboard omits the link to $skill"
|
|
done
|
|
grep -q '>N/A<' board.html || fail "the leaderboard omits the not-applicable Regression cell"
|
|
grep -q 'near regressing' board.html || fail "the leaderboard omits the regression fragility chip"
|
|
grep -q 'narrow efficacy' board.html || fail "the leaderboard omits the efficacy fragility chip"
|
|
|
|
touch "$out"
|
|
''
|