mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-11 05:11:49 +01:00
520 lines
44 KiB
TypeScript
520 lines
44 KiB
TypeScript
import assert from "node:assert/strict";
|
|
import { createHash } from "node:crypto";
|
|
import { readFile, writeFile } from "node:fs/promises";
|
|
import path from "node:path";
|
|
import { noiseExceedingPairedWins } from "./native-ingestion-performance-gates.mjs";
|
|
import { H5_MODE, H5_PROTOCOL, H5_WORKLOAD_SHA256, H5_BASELINE_REVISIONS, ORIGINAL_BUDGETS, assessH5Arm, requireH5Candidate } from "../tests/e2e/fixtures/native-ingestion-h5.mjs";
|
|
import { validateArmInventory } from "./native-ingestion-h5-inventory.mjs";
|
|
|
|
// Each manifest entry points at native-ingestion-evidence JSON attachments
|
|
// from two isolated compiled-app runs. Run the variants in alternating order;
|
|
// timestamps here are never reconstructed from screenshots or success text.
|
|
const arg = (name: string) => process.argv.find(value => value.startsWith(`--${name}=`))?.slice(name.length + 3);
|
|
const manifestPath = arg("pairs");
|
|
assert.ok(manifestPath, "Pass --pairs=<JSON manifest of baselineFile/candidateFile pairs>");
|
|
const phase = arg("phase") ?? "compare", expectation = arg("expect") ?? "improvement";
|
|
const h5 = arg("observation-mode") === H5_MODE;
|
|
assert.ok(arg("observation-mode") === undefined || h5, "Unknown observation mode");
|
|
const candidatePolicy = arg("candidate-policy");
|
|
assert.ok(["aa", "compare"].includes(phase));
|
|
assert.ok(["improvement", "nonregression"].includes(expectation));
|
|
const manifest = JSON.parse(await readFile(manifestPath, "utf8")) as Array<{ baselineFile: string; candidateFile: string;
|
|
baselinePlaywrightFile?: string; candidatePlaywrightFile?: string; baselineInventoryFile?: string; candidateInventoryFile?: string }>;
|
|
assert.ok(manifest.length >= 5, "At least five actual paired application runs are required");
|
|
if (h5) assert.equal(manifest.length, 5, "H5 requires exactly five prospectively registered pairs");
|
|
const load = async (file: string) => JSON.parse(await readFile(path.resolve(path.dirname(manifestPath), file), "utf8"));
|
|
async function owningResult(reportPath: string, evidence?: any) {
|
|
const bytes = await readFile(reportPath);
|
|
const report = JSON.parse(bytes.toString("utf8")), tests: any[] = [];
|
|
assert.deepEqual(report.errors ?? [], [], "Owning Playwright report has a global error");
|
|
const visit = (value: any) => {
|
|
if (Array.isArray(value)) for (const child of value) visit(child);
|
|
else if (value && typeof value === "object") {
|
|
if (Array.isArray(value.results) && Object.hasOwn(value, "expectedStatus")) tests.push(value);
|
|
for (const [key, child] of Object.entries(value)) if (key !== "results") visit(child);
|
|
}
|
|
};
|
|
visit(report); assert.equal(tests.length, 1, "One complete owning test is required; no partial selection");
|
|
const test = tests[0]; assert.equal(test.results.length, 1, "No retry or omitted owning attempt");
|
|
assert.equal(test.expectedStatus, "passed");
|
|
const result = test.results[0], attachments = result.attachments.filter((item: any) => item.name === "native-ingestion-evidence");
|
|
assert.ok(result.error === undefined || result.error === null, "Owning Playwright attempt has an error");
|
|
assert.equal(attachments.length, 1, "Owning result must carry this exact evidence attachment");
|
|
const attachment = attachments[0];
|
|
const attached = attachment.body ? JSON.parse(Buffer.from(attachment.body, "base64").toString("utf8"))
|
|
: JSON.parse(await readFile(path.resolve(path.dirname(reportPath), attachment.path), "utf8"));
|
|
if (evidence) assert.deepEqual(attached, evidence, "Playwright result belongs to a different evidence arm");
|
|
return { evidence: attached, owner: { reportFile: reportPath, reportSha256: createHash("sha256").update(bytes).digest("hex"),
|
|
status: result.status, retry: result.retry, errors: result.errors, startedAt: result.startTime,
|
|
durationMs: result.duration, timeoutMs: test.timeout } };
|
|
}
|
|
async function loadArm(file: string, playwrightFile?: string, inventoryFile?: string) {
|
|
const evidence = await load(file);
|
|
if (!h5) return evidence;
|
|
assert.ok(playwrightFile, "H5 requires each arm's independent owning Playwright JSON report");
|
|
evidence.owningPlaywright = (await owningResult(path.resolve(path.dirname(manifestPath!), playwrightFile), evidence)).owner;
|
|
assert.ok(inventoryFile, "H5 requires each arm's exact full artifact inventory sidecar");
|
|
evidence.armInventory = await validateArmInventory(path.resolve(path.dirname(manifestPath!), inventoryFile),
|
|
{ evidence, owningPlaywright: evidence.owningPlaywright });
|
|
return evidence;
|
|
}
|
|
const pairs = await Promise.all(manifest.map(async entry => ({ baseline: await loadArm(entry.baselineFile, entry.baselinePlaywrightFile, entry.baselineInventoryFile),
|
|
candidate: await loadArm(entry.candidateFile, entry.candidatePlaywrightFile, entry.candidateInventoryFile) })));
|
|
const h5Assessments: any[] = [];
|
|
if (h5) {
|
|
if (phase === "compare") {
|
|
assert.ok(["final-b2", "cursor-nonregression"].includes(candidatePolicy ?? ""), "H5 requires an explicit candidate SLA policy");
|
|
assert.equal(expectation, candidatePolicy === "cursor-nonregression" ? "nonregression" : "improvement");
|
|
}
|
|
for (const pair of pairs) {
|
|
assert.ok(Object.values(H5_BASELINE_REVISIONS).includes(pair.baseline.sourceRevision), "H5 baseline must use the prospectively frozen B0 or B1 revision");
|
|
const baselineVariant = pair.baseline.sourceRevision === H5_BASELINE_REVISIONS.B0 ? "B0" : "B1";
|
|
assert.equal(pair.baseline.armInventory.variant, baselineVariant, "Baseline inventory role differs from its frozen revision");
|
|
if (phase === "aa") assert.equal(pair.candidate.armInventory.variant, baselineVariant, "A/A must use the same baseline inventory role");
|
|
if (phase === "compare" && candidatePolicy === "cursor-nonregression") {
|
|
assert.equal(pair.baseline.sourceRevision, H5_BASELINE_REVISIONS.B0, "Cursor policy requires B0→B1");
|
|
assert.equal(pair.candidate.sourceRevision, H5_BASELINE_REVISIONS.B1, "Cursor policy requires B0→B1");
|
|
assert.equal(pair.candidate.armInventory.variant, "B1", "Cursor policy cannot stand in for final B2 acceptance");
|
|
} else if (phase === "compare") {
|
|
assert.equal(pair.candidate.armInventory.variant, "B2", "Final policy requires the qualified B2 inventory role");
|
|
assert.ok(!Object.values(H5_BASELINE_REVISIONS).includes(pair.candidate.sourceRevision), "Final B2 must differ from both frozen baselines");
|
|
}
|
|
const baseline = assessH5Arm(pair.baseline, pair.baseline.owningPlaywright);
|
|
const candidate = assessH5Arm(pair.candidate, pair.candidate.owningPlaywright);
|
|
// The only prospectively known baseline workload SLA miss is loaded streaming.
|
|
const allowed = new Set(["burst512:streaming120", "invocation:observed-total-duration900"]);
|
|
for (const miss of baseline.misses) assert.ok(allowed.has(miss), "Unknown baseline deadline failure needs diagnosis");
|
|
if (phase === "aa") for (const miss of candidate.misses) assert.ok(allowed.has(miss), "Unknown A/A deadline failure needs diagnosis");
|
|
let candidateSlaPolicyError;
|
|
if (phase === "compare") {
|
|
try { requireH5Candidate(candidatePolicy, baseline, candidate); }
|
|
catch (error) { candidateSlaPolicyError = error instanceof Error ? error.message : String(error); }
|
|
}
|
|
h5Assessments.push({ baseline, candidate, candidateSlaPolicyError, candidateSlaPolicyPassed: !candidateSlaPolicyError,
|
|
owningPlaywright: { baseline: pair.baseline.owningPlaywright, candidate: pair.candidate.owningPlaywright } });
|
|
}
|
|
}
|
|
const workloads = [
|
|
{ name: "paced", runs: 1, events: 128, intervalMs: 25, prelude: 0, stop: false },
|
|
{ name: "burst16", runs: 1, events: 16, intervalMs: 0, prelude: 0, stop: false },
|
|
{ name: "burst128", runs: 10, events: 128, intervalMs: 0, prelude: 0, stop: false },
|
|
{ name: "burst512", runs: 100, events: 512, intervalMs: 0, prelude: 0, stop: false },
|
|
{ name: "existing-history", runs: 10, events: 128, intervalMs: 0, prelude: 1000, stop: false },
|
|
{ name: "operator-stop", runs: 1, events: 512, intervalMs: 100, prelude: 0, stop: true },
|
|
];
|
|
const names = workloads.map(item => item.name);
|
|
const median = (values: number[]) => [...values].sort((a, b) => a - b)[Math.floor(values.length / 2)]!;
|
|
const first = pairs[0];
|
|
const sha256 = (value: unknown) => typeof value === "string" && /^[a-f0-9]{64}$/.test(value);
|
|
const uuid = (value: unknown) => typeof value === "string" && /^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$/i.test(value);
|
|
for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const) {
|
|
const report = pair[arm];
|
|
assert.equal(report.protocolVersion, h5 ? H5_PROTOCOL : "v4-remote-streaming-original-local-stop-clock-stream",
|
|
h5 ? "Fresh browser acceptance requires its qualified H5 observation protocol" : "Fresh browser acceptance requires the qualified v4 mixed clock protocol");
|
|
assert.equal(report.transport, "sandbox-remote-with-local-stop", "V4 requires remote streaming and the original local Stop transport");
|
|
assert.deepEqual(report.transportPolicy, { streaming: "sandbox-remote", operatorStop: "local",
|
|
realCloudStop: "Separate required qualification; fake-plugin void receipts grant no remote Stop authority" }, "Missing explicit transport and real cloud Stop qualification policy");
|
|
assert.deepEqual(report.resourceBudgets, { providerReadinessMs: 300_000, fullInvocationMs: 900_000,
|
|
streamingMs: 120_000, terminalDrainageMs: 180_000, stopAcknowledgementMs: 30_000, remoteLeaseCleanupMs: 30_000 },
|
|
"Keep the prospectively registered remote setup/resource budgets and existing streaming/control timeouts");
|
|
const remote = report.remote;
|
|
assert.equal(remote?.transport, "sandbox-remote", "Missing normal remote runtime provenance");
|
|
assert.equal(remote?.plugin?.pluginKey, "paperclip.fake-sandbox-provider", "Missing normal remote plugin provenance");
|
|
assert.equal(remote?.selection, "Normal plugin install + sandbox environment + agent defaultEnvironmentId; no runtime resolver override",
|
|
"Use normal API remote environment selection");
|
|
assert.ok(uuid(remote.environmentId) && uuid(report.companyId), "Missing actual remote company/environment identity");
|
|
assert.ok(remote.agentIds?.length > 0 && remote.agentIds.every(uuid), "Missing actual remote agent selection");
|
|
assert.deepEqual(Object.keys(remote.plugin.assetHashes ?? {}).sort(), ["lease-cleanup.js", "manifest.js", "plugin.js", "worker.js"]);
|
|
for (const [file, hash] of Object.entries(remote.plugin.assetHashes)) {
|
|
assert.ok(sha256(hash), "Missing actual provider plugin build fingerprint");
|
|
assert.equal(hash, first.baseline.remote.plugin.assetHashes[file], "Provider cleanup build changed across matched samples");
|
|
}
|
|
const local = report.local;
|
|
assert.equal(local?.transport, "local", "Missing normal local Stop runtime provenance");
|
|
assert.equal(local?.selection, "Normal local environment + separate control agent defaultEnvironmentId; existing test-only Codex leaf command fixture",
|
|
"Use normal local Stop environment selection");
|
|
assert.ok(uuid(local.environmentId) && uuid(local.controlAgentId) && local.environmentId !== remote.environmentId
|
|
&& !remote.agentIds.includes(local.controlAgentId), "Local Stop needs a separate normal control agent and environment");
|
|
for (const field of ["commandSha256", "loaderSha256"]) {
|
|
assert.ok(sha256(local[field]), "Missing original local provider command provenance");
|
|
assert.equal(local[field], first.baseline.local[field], "Local Stop fixture changed across matched samples");
|
|
}
|
|
assert.equal(remote.revision, report.sourceRevision);
|
|
assert.equal(remote.buildRevision, report.compiledBuildRevision);
|
|
assert.equal(remote.tls?.peerVerification, true, "Remote TLS peer verification is required");
|
|
assert.equal(typeof remote.runnerPublicUrl, "string", "Missing actual remote WSS endpoint");
|
|
const endpoint = new URL(remote.runnerPublicUrl);
|
|
assert.equal(endpoint.protocol, "wss:", "Actual remote endpoint must use verified WSS");
|
|
assert.equal(endpoint.hostname, "127.0.0.1", "Use the owned loopback remote fixture endpoint");
|
|
assert.ok(Number(endpoint.port) > 0 && !endpoint.username && !endpoint.password && !endpoint.search && !endpoint.hash,
|
|
"Use the recorded owned remote fixture endpoint without overrides");
|
|
for (const value of [remote.tls?.caSha256, remote.tls?.serverCertificateSha256, remote.runner?.sha256,
|
|
remote.provider?.nodeSha256, remote.provider?.wrapperSha256, remote.provider?.fixtureSha256]) {
|
|
assert.ok(sha256(value), "Missing remote TLS, daemon or provider artifact fingerprint");
|
|
}
|
|
assert.equal(remote.provider.fixtureSha256, report.fixtureSha256, "Staged provider fixture changed");
|
|
assert.ok(remote.runner.metadata?.prpTransportModes?.includes("dial_wss"), "Remote daemon must support verified WSS");
|
|
for (const [group, field] of [["runner", "sha256"], ["provider", "nodeSha256"], ["provider", "wrapperSha256"], ["provider", "fixtureSha256"]]) {
|
|
assert.equal(remote[group][field], first.baseline.remote[group][field], "Remote provider/daemon artifact changed across matched samples");
|
|
}
|
|
assert.equal(report.admissionProtocol, "two-at-a-time-provider-and-clock-readiness-before-common-epoch", "Use the qualified pre-measurement admission protocol");
|
|
assert.equal(report.setupActivationConcurrency, 2, "Keep the qualified setup activation concurrency of two");
|
|
assert.equal(report.setupReadinessPollingMs, 50, "Keep the qualified setup readiness observation interval");
|
|
assert.equal(report.complete, true); assert.equal(report.qualificationOnly, false, "Smoke cannot qualify performance");
|
|
assert.equal(report.cleanup?.complete, true, "Acceptance requires completed fixture cleanup");
|
|
assert.deepEqual(report.cleanup?.errors, [], "Acceptance rejects fixture cleanup errors");
|
|
assert.notEqual(report.diagnosticOnly, true, "Diagnostic profiles cannot qualify unprofiled performance");
|
|
assert.notEqual(report.performanceAcceptanceEligible, false, "Profile-only evidence cannot qualify performance");
|
|
assert.equal(report.browserRecording?.trace, "off", "Acceptance requires browser trace capture off");
|
|
assert.equal(report.browserRecording?.video, "off", "Acceptance requires browser video capture off");
|
|
assert.equal(report.browserRecording?.screencast, false, "Acceptance requires browser screencast capture off");
|
|
assert.equal(report.serverArtifact, "compiled", "Performance acceptance requires the compiled server and shipped UI");
|
|
assert.ok(report.serverEntrySha256 && report.measurementSha256);
|
|
assert.equal(report.compiledBuildRevision, report.sourceRevision, "Compiled build stamp does not match the measured revision");
|
|
assert.ok(Object.keys(report.compiledHotPathHashes ?? {}).length >= 3, "Missing compiled ingestion/runtime fingerprints");
|
|
assert.equal(report.sourceRevision, first[arm].sourceRevision, "Every sample must cover the same revision per arm");
|
|
assert.equal(report.serverEntrySha256, first[arm].serverEntrySha256, "Compiled artifact changed between samples");
|
|
assert.deepEqual(report.compiledHotPathHashes, first[arm].compiledHotPathHashes, "Compiled ingestion/runtime changed between samples");
|
|
if (h5) for (const field of ["manifestFileSha256", "aggregateSha256", "qualifiedReceiptSha256", "inventorySummarySha256", "revision"])
|
|
assert.equal(report.armInventory[field], first[arm].armInventory[field], "Full qualified artifact inventory changed between samples");
|
|
assert.equal(report.measurementSha256, first.baseline.measurementSha256, "Fixture/observer protocol changed between runs");
|
|
if (phase === "aa") assert.equal(report.sourceRevision, first.baseline.sourceRevision, "A/A must use one source revision");
|
|
for (const name of names) {
|
|
const result = report.cases.find((item: any) => item.name === name);
|
|
assert.ok(result, `Missing fixed workload ${name}`);
|
|
const fixed = workloads.find(item => item.name === name)!;
|
|
for (const field of ["runs", "events", "intervalMs", "prelude", "stop"] as const) assert.equal(result[field], fixed[field], `Fixed workload changed: ${name}.${field}`);
|
|
assert.equal(result.transport, result.stop ? "local" : "sandbox-remote", "Wrong per-case transport; fake-plugin does not qualify remote Stop");
|
|
assert.equal(result.environmentId, result.stop ? local.environmentId : remote.environmentId, "Wrong per-case normal environment");
|
|
assert.equal(result.setupActivationConcurrency, 2, "Keep each case's qualified setup activation concurrency of two");
|
|
assert.equal(result.persistedAfterReload, true);
|
|
assert.equal(result.matchedVisibleClocks, result.visible?.length, "Every observed marker needs its original provider clock");
|
|
assert.ok(result.matchedVisibleClocks >= (result.stop ? 3 : result.events), "Missing foreground render/clock observations");
|
|
if (name === "paced") {
|
|
assert.ok(result.interChunkGaps?.count >= 1, "Paced streaming needs observed inter-chunk paint gaps");
|
|
assert.equal(result.interChunkGaps.paintCount, result.interChunkGaps.count + 1);
|
|
}
|
|
if (result.prelude) {
|
|
assert.equal(result.preludeProof?.individualDeltas, result.prelude, "Existing history requires independently stored prelude deltas");
|
|
assert.equal(result.preludeProof?.uniqueSourceIdentities, result.prelude);
|
|
assert.ok(result.preludeProof?.verifiedAtMs < result.epochMs, "Verify retained prelude before releasing measured emission");
|
|
}
|
|
assert.equal(result.durable.length, result.runs, "Every background run needs independent delta persistence proof");
|
|
assert.equal(result.runIds?.length, result.runs, "Every remote participant needs its actual run identity");
|
|
assert.ok(result.runIds.every(uuid), "Missing actual remote run UUID");
|
|
assert.equal(new Set(result.runIds).size, result.runs, "Duplicate remote run identity");
|
|
assert.deepEqual(result.durable.map((proof: any) => proof.runId).sort(), [...result.runIds].sort(), "Durable proof run set mismatch");
|
|
const authority = result.controllerAuthority;
|
|
assert.equal(authority?.checkedBeforeMeasuredEpoch, true, "Missing controller authority proof before the measured epoch");
|
|
assert.equal(authority?.kind, result.stop ? "host-file-journal" : "database-controller-checkpoint", "Wrong checkpoint authority for actual transport");
|
|
assert.equal(authority?.observedReadOnly, "on", "Remote authority proof must observe a read-only transaction");
|
|
assert.equal(authority?.observedIsolation, "repeatable read", "Remote authority proof must observe repeatable-read isolation");
|
|
assert.ok(Number.isSafeInteger(authority?.checkedAtMs) && authority.checkedAtMs > 0
|
|
&& Number.isSafeInteger(authority.connectionClosedAtMs) && authority.connectionClosedAtMs > 0
|
|
&& authority.checkedAtMs <= authority.connectionClosedAtMs && authority.connectionClosedAtMs < result.epochMs,
|
|
"Close the actual remote authority snapshot before the measured epoch");
|
|
assert.equal(authority.rows?.length, result.runs, "Every remote run needs its controller checkpoint and lease proof");
|
|
assert.deepEqual(authority.rows.map((row: any) => row.run_id).sort(), [...result.runIds].sort(), "Remote authority run set mismatch");
|
|
assert.equal(new Set(authority.rows.map((row: any) => row.issue_id)).size, result.runs, "Duplicate remote issue authority");
|
|
const authorityByRun = new Map<string, any>();
|
|
for (const row of authority.rows) {
|
|
assert.ok(uuid(row.issue_id) && uuid(row.lease_id), "Missing actual task/lease UUID");
|
|
assert.equal(row.company_id, report.companyId, "Remote authority company mismatch");
|
|
assert.equal(row.environment_id, result.environmentId, "Remote authority environment mismatch");
|
|
assert.equal(row.runtime_mode, "native");
|
|
if (!result.stop) {
|
|
assert.ok(remote.agentIds.includes(row.agent_id), "Remote run did not use its normal remote agent");
|
|
assert.equal(row.provider, "fake-plugin");
|
|
assert.match(row.provider_lease_id, /^fake-plugin:\/\//);
|
|
assert.equal(row.checkpoint_part, "header", "Missing actual database controller checkpoint header");
|
|
assert.ok(Number.isSafeInteger(row.checkpoint_header_bytes) && row.checkpoint_header_bytes > 0);
|
|
} else {
|
|
assert.equal(row.agent_id, local.controlAgentId, "Stop did not use its separate local control agent");
|
|
assert.equal(row.provider, "local", "Stop requires its normal local lease");
|
|
assert.equal(row.provider_lease_id, null); assert.equal(row.checkpoint_part, null, "Local Stop must retain host-file authority without a database header");
|
|
assert.ok(BigInt(String(row.process_identity_seq)) > 0n);
|
|
assert.equal(row.process_identity_source_event_id, null, "Local identity must be server-authored");
|
|
assert.equal(row.process_identity?.targetKind, "local");
|
|
assert.equal(row.process_identity?.processPid, row.process_pid);
|
|
assert.equal(row.process_identity?.processGroupId, row.process_group_id);
|
|
assert.equal(row.process_identity?.processStartedAt, row.process_started_at);
|
|
assert.ok(uuid(row.admitted_execution_workspace_id), "Missing actual admitted local workspace binding");
|
|
}
|
|
authorityByRun.set(row.run_id, row);
|
|
}
|
|
assert.equal(result.providerClocks?.length, result.runs, "Every actual provider needs its wrapper launcher and PID");
|
|
assert.deepEqual(result.providerClocks.map((clock: any) => clock.runId).sort(), [...result.runIds].sort());
|
|
assert.equal(new Set(result.providerClocks.map((clock: any) => clock.providerPid)).size, result.runs);
|
|
for (const clock of result.providerClocks) {
|
|
assert.equal(clock.launcher, result.stop ? "host-local" : "staged-remote", "Actual wrapper launcher does not match transport");
|
|
assert.ok(Number.isSafeInteger(clock.providerPid) && clock.providerPid > 1, "Missing actual provider PID");
|
|
const stream = result.clockEvidence?.find((stream: any) => stream.nonce === clock.nonce);
|
|
assert.equal(stream?.launcher, clock.launcher, "Clock hello launcher proof missing");
|
|
assert.equal(stream?.providerPid, clock.providerPid, "Clock hello provider PID proof missing");
|
|
assert.equal(result.durable.find((proof: any) => proof.runId === clock.runId)?.token, clock.nonce);
|
|
}
|
|
assert.equal(result.participants, result.runs, "Every provider GET must remain open before the common epoch");
|
|
assert.ok(Number.isSafeInteger(result.setupReadinessStartedAtMs) && result.setupReadinessStartedAtMs > 0);
|
|
assert.equal(result.readinessDeadlineMs, result.setupReadinessStartedAtMs + report.resourceBudgets.providerReadinessMs,
|
|
"Keep one unchanged shared readiness deadline");
|
|
assert.ok(Number.isSafeInteger(result.allReadyObservedAtMs) && result.allReadyObservedAtMs >= result.setupReadinessStartedAtMs
|
|
&& result.allReadyObservedAtMs <= result.readinessDeadlineMs && result.allReadyObservedAtMs < result.epochMs,
|
|
"All actual providers and clocks must be ready before the epoch and shared deadline");
|
|
assert.ok(authority.checkedAtMs >= result.allReadyObservedAtMs, "Check actual controller authority after every provider is ready");
|
|
assert.equal(result.activations?.length, result.runs, "Every actual participant needs its setup activation timing");
|
|
assert.deepEqual(result.activations.map((entry: any) => entry.index).sort((a: number, b: number) => a - b),
|
|
Array.from({ length: result.runs }, (_, index) => index), "Setup activation indices must cover every participant once");
|
|
const waves = result.activationWaves;
|
|
assert.equal(waves?.length, Math.ceil((result.runs - 1) / 2), "Background setup must use bounded waves of two");
|
|
for (let waveIndex = 0; waveIndex < waves.length; waveIndex++) {
|
|
const wave = waves[waveIndex], firstIndex = 1 + waveIndex * 2;
|
|
const indices = Array.from({ length: Math.min(2, result.runs - firstIndex) }, (_, offset) => firstIndex + offset);
|
|
assert.equal(wave.index, waveIndex); assert.deepEqual(wave.indices, indices, "Wrong setup wave participants");
|
|
assert.deepEqual(wave.statuses, indices.map(() => "fulfilled"), "A failed or unfinished setup wave cannot qualify");
|
|
assert.ok(Number.isSafeInteger(wave.startedAtMs) && Number.isSafeInteger(wave.settledAtMs)
|
|
&& wave.startedAtMs >= (waveIndex ? waves[waveIndex - 1].settledAtMs : result.setupReadinessStartedAtMs)
|
|
&& wave.settledAtMs >= wave.startedAtMs && wave.settledAtMs <= result.allReadyObservedAtMs,
|
|
"Finish the whole setup wave before starting the next one");
|
|
}
|
|
for (const activation of result.activations) {
|
|
const row = authority.rows.find((row: any) => row.issue_id === activation.issueId);
|
|
assert.ok(row, "Setup activation task must match actual controller authority");
|
|
const clock = result.providerClocks.find((clock: any) => clock.runId === row.run_id);
|
|
assert.equal(activation.token, clock.nonce, "Setup activation must match its actual provider clock");
|
|
assert.equal(activation.status, "fulfilled", "An unfinished setup activation cannot qualify");
|
|
for (const field of ["startedAtMs", "requestSettledAtMs", "providerReadyAtMs", "clockHelloAtMs", "readinessObservedAtMs", "settledAtMs"]) {
|
|
assert.ok(Number.isSafeInteger(activation[field]) && activation[field] > 0 && activation[field] < result.epochMs,
|
|
"Missing actual pre-epoch activation/readiness timing");
|
|
}
|
|
assert.ok(activation.requestSettledAtMs >= activation.startedAtMs && activation.providerReadyAtMs >= activation.startedAtMs
|
|
&& activation.clockHelloAtMs >= activation.startedAtMs
|
|
&& activation.readinessObservedAtMs >= Math.max(activation.requestSettledAtMs, activation.providerReadyAtMs, activation.clockHelloAtMs)
|
|
&& activation.settledAtMs >= activation.readinessObservedAtMs && activation.settledAtMs <= result.allReadyObservedAtMs,
|
|
"Actual provider GET and hello must precede observed readiness");
|
|
const stream = result.clockEvidence.find((stream: any) => stream.nonce === activation.token);
|
|
assert.equal(stream.hello, true, "Every actual provider needs its clock hello");
|
|
for (const field of ["providerReadyAtMs", "clockHelloAtMs", "readinessObservedAtMs"]) assert.equal(stream[field], activation[field], "Readiness metadata must match actual clock observations");
|
|
if (activation.index === 0) assert.equal(activation.waveIndex, null);
|
|
else {
|
|
const waveIndex = Math.floor((activation.index - 1) / 2), wave = waves[waveIndex];
|
|
assert.equal(activation.waveIndex, waveIndex);
|
|
assert.ok(activation.startedAtMs >= wave.startedAtMs && activation.settledAtMs <= wave.settledAtMs,
|
|
"Keep each activation inside its settled setup wave");
|
|
}
|
|
}
|
|
assert.equal(result.settledAtMs, result.epochMs + result.drainThroughTerminalMs, "Terminal timing boundary changed");
|
|
if (result.stop) {
|
|
assert.equal(result.stopAcknowledgedAtMs, result.stopRequestedAtMs + result.stopThroughAcknowledgementMs, "Stop acknowledgement timing boundary changed");
|
|
const row = authority.rows[0], journal = authority.localJournal, before = result.localProcesses;
|
|
assert.equal(journal?.schema, "paperclip.runner.durable.control-plane-state.v1", "Missing owned local journal authority");
|
|
assert.ok(sha256(journal.sha256) && journal.bytes > 0 && Number.isSafeInteger(journal.checkedAtMs)
|
|
&& journal.checkedAtMs < result.epochMs, "Verify actual local file journal before the measured epoch");
|
|
assert.notEqual(journal.checkpointEventPolicy, "control-v1", "Preserve the original local raw transport recovery policy");
|
|
for (const [field, expected] of [["runId", row.run_id], ["runnerInstanceId", row.runner_instance_id],
|
|
["normalizedSessionId", row.native_session_id], ["environmentLeaseId", row.admitted_execution_workspace_id]]) assert.equal(journal.identity?.[field], expected, "Local journal identity mismatch");
|
|
assert.ok(before && before.hostname === row.process_identity.hostname && before.runnerPid === row.process_pid
|
|
&& before.processGroupId === row.process_group_id && before.providerPid === result.providerClocks[0].providerPid,
|
|
"Local observed process ownership mismatch");
|
|
assert.ok(before.runnerAlive && before.groupAlive && before.providerAlive && Number.isSafeInteger(before.checkedAtMs)
|
|
&& before.checkedAtMs < result.epochMs, "Independently observe all owned local processes before emission");
|
|
const stopped = result.localStopProof, database = stopped?.database, after = database?.rows?.[0];
|
|
assert.ok(stopped && Number.isSafeInteger(stopped.checkedAtMs) && stopped.checkedAtMs >= result.stopAcknowledgedAtMs
|
|
&& stopped.checkedAtMs >= result.settledAtMs, "Verify local physical Stop after timing boundaries");
|
|
assert.equal(database?.kind, "host-file-journal"); assert.equal(database?.observedReadOnly, "on");
|
|
assert.equal(database?.observedIsolation, "repeatable read"); assert.equal(database?.rows?.length, 1);
|
|
assert.equal(database?.checkedBeforeMeasuredEpoch, false);
|
|
assert.ok(Number.isSafeInteger(database.checkedAtMs) && database.checkedAtMs >= result.stopAcknowledgedAtMs
|
|
&& Number.isSafeInteger(database.connectionClosedAtMs) && database.connectionClosedAtMs >= database.checkedAtMs
|
|
&& database.connectionClosedAtMs <= stopped.checkedAtMs, "Local stopped database proof predates acknowledgement");
|
|
for (const field of ["run_id", "company_id", "environment_id", "lease_id", "agent_id", "provider", "provider_lease_id",
|
|
"admitted_execution_workspace_id", "process_identity_seq", "process_identity_source_event_id"]) assert.equal(after?.[field], row[field], "Local stopped database identity mismatch");
|
|
assert.equal(after.status, "cancelled"); assert.equal(after.cancellation_dispatch_state, "acknowledged");
|
|
if (!after.process_pid && !after.process_group_id) {
|
|
assert.ok(BigInt(String(after.process_stopped_seq)) > BigInt(String(row.process_identity_seq)), "Cleared local process identity needs its server stop receipt");
|
|
assert.equal(after.process_stopped_source_event_id, null);
|
|
assert.equal(after.process_stopped?.processPid, before.runnerPid);
|
|
assert.equal(after.process_stopped?.processGroupId, before.processGroupId);
|
|
assert.equal(after.process_stopped?.processStartedAt, row.process_identity.processStartedAt);
|
|
} else {
|
|
assert.equal(after.process_pid, before.runnerPid); assert.equal(after.process_group_id, before.processGroupId);
|
|
}
|
|
for (const field of ["runnerPid", "processGroupId", "providerPid", "hostname"]) assert.equal(stopped.processes?.[field], before[field]);
|
|
assert.equal(stopped.processes.runnerAbsent, true); assert.equal(stopped.processes.groupAbsent, true);
|
|
assert.equal(stopped.processes.providerAbsent, true, "Local provider remains alive after Stop");
|
|
const lease = stopped.lease;
|
|
assert.equal(lease?.id, row.lease_id); assert.equal(lease?.companyId, report.companyId);
|
|
assert.equal(lease?.environmentId, local.environmentId); assert.equal(lease?.heartbeatRunId, row.run_id);
|
|
assert.equal(lease?.provider, "local"); assert.equal(lease?.providerLeaseId, null);
|
|
assert.ok(["released", "expired", "failed"].includes(lease.status) && lease.releasedAt
|
|
&& lease.cleanupStatus !== "failed", "Local Stop lease cleanup remains unsettled");
|
|
assert.equal(result.remoteLeases, undefined, "Local Stop cannot claim fake remote cleanup");
|
|
} else {
|
|
assert.equal(result.localStopProof, undefined, "Streaming cannot claim a local Stop proof");
|
|
assert.equal(result.remoteLeases?.length, result.runs, "Every remote run needs post-timing lease cleanup proof");
|
|
assert.deepEqual(result.remoteLeases.map((lease: any) => lease.runId).sort(), [...result.runIds].sort(), "Remote cleanup run set mismatch");
|
|
assert.ok(Number.isSafeInteger(result.remoteLeasesCheckedAtMs) && result.remoteLeasesCheckedAtMs >= result.settledAtMs,
|
|
"Verify remote leases after recorded timing boundaries");
|
|
for (const lease of result.remoteLeases) {
|
|
const row = authorityByRun.get(lease.runId);
|
|
assert.equal(lease.id, row.lease_id); assert.equal(lease.companyId, report.companyId);
|
|
assert.equal(lease.environmentId, remote.environmentId); assert.equal(lease.provider, row.provider);
|
|
assert.equal(lease.providerLeaseId, row.provider_lease_id);
|
|
assert.ok(["released", "expired", "failed"].includes(lease.status) && lease.releasedAt
|
|
&& lease.cleanupStatus === "success", "Remote lease cleanup remains unsettled");
|
|
if (lease.terminationReceipt) {
|
|
const receipt = lease.terminationReceipt;
|
|
assert.equal(receipt.schema, "paperclip.remote-termination.v1");
|
|
assert.equal(receipt.companyId, report.companyId); assert.equal(receipt.runId, lease.runId);
|
|
assert.equal(receipt.leaseId, lease.id); assert.equal(receipt.provider, lease.provider);
|
|
assert.equal(receipt.providerLeaseId, lease.providerLeaseId);
|
|
assert.ok(["stopped", "destroyed"].includes(receipt.state), "Invalid recorded remote termination receipt");
|
|
}
|
|
}
|
|
}
|
|
for (const proof of result.durable) {
|
|
assert.equal(proof.ordered, true); assert.equal(proof.uniqueSourceIdentities, proof.individualDeltas);
|
|
assert.equal(proof.matchedSourceClocks, proof.individualDeltas, "Every durable measured delta needs an original provider clock");
|
|
if (!result.stop) assert.equal(proof.individualDeltas, result.events);
|
|
}
|
|
const reference = first.baseline.cases.find((item: any) => item.name === name);
|
|
for (const field of ["runs", "events", "intervalMs", "prelude", "stop"]) assert.equal(result[field], reference[field], `Workload changed: ${name}.${field}`);
|
|
}
|
|
}
|
|
let originalH4cConfirmation: Record<string, any> | undefined;
|
|
if (h5 && phase === "compare" && candidatePolicy === "final-b2") {
|
|
originalH4cConfirmation = { required: true, passed: false, reason: "Later unchanged original H4c full functional proof is pending" };
|
|
if (arg("original-h4c-proof")) {
|
|
try {
|
|
assert.ok(arg("original-h4c-inventory"), "Original H4c proof requires its full artifact inventory sidecar");
|
|
const { evidence: proof, owner } = await owningResult(path.resolve(arg("original-h4c-proof")!));
|
|
assert.equal(owner.status, "passed"); assert.equal(owner.retry, 0); assert.deepEqual(owner.errors, []);
|
|
assert.equal(owner.timeoutMs, ORIGINAL_BUDGETS.fullInvocationMs);
|
|
assert.ok(owner.durationMs > 0 && owner.durationMs < ORIGINAL_BUDGETS.fullInvocationMs);
|
|
assert.equal(proof.protocolVersion, "v4-remote-streaming-original-local-stop-clock-stream");
|
|
assert.equal(proof.observationMode, undefined, "Confirmation must use unchanged original H4c defaults");
|
|
assert.equal(proof.harnessProvenance?.sourceRevision, "7d7e7a88d562a95a1d407b76474763b666c181f5");
|
|
assert.equal(proof.harnessProvenance.sourceStatus, "");
|
|
assert.equal(proof.measurementSha256, "5db4129bbdc1fa38775121aff5d0e68a8a11762519e41cfdf36eacd90ba7256b");
|
|
assert.deepEqual(proof.resourceBudgets, ORIGINAL_BUDGETS);
|
|
assert.equal(proof.complete, true); assert.equal(proof.qualificationOnly, false); assert.equal(proof.diagnosticOnly, false);
|
|
assert.equal(proof.performanceAcceptanceEligible, true); assert.equal(proof.serverArtifact, "compiled");
|
|
assert.equal(proof.cleanup?.complete, true); assert.deepEqual(proof.cleanup.errors, []);
|
|
assert.deepEqual(proof.browserRecording, first.candidate.browserRecording);
|
|
assert.equal(proof.sourceRevision, first.candidate.sourceRevision); assert.equal(proof.compiledBuildRevision, first.candidate.compiledBuildRevision);
|
|
assert.equal(proof.serverEntrySha256, first.candidate.serverEntrySha256);
|
|
assert.deepEqual(proof.compiledHotPathHashes, first.candidate.compiledHotPathHashes);
|
|
assert.equal(proof.transport, first.candidate.transport); assert.deepEqual(proof.transportPolicy, first.candidate.transportPolicy);
|
|
assert.deepEqual(proof.cases.map((item: any) => item.name), names, "Original confirmation must include all six workloads");
|
|
for (const fixed of workloads) {
|
|
const item = proof.cases.find((item: any) => item.name === fixed.name);
|
|
for (const field of ["runs", "events", "intervalMs", "prelude", "stop"] as const) assert.equal(item[field], fixed[field]);
|
|
assert.equal(item.persistedAfterReload, true); assert.equal(item.durable.length, fixed.runs);
|
|
assert.equal(item.matchedVisibleClocks, item.visible.length);
|
|
assert.ok(item.visible.length >= (fixed.stop ? 3 : fixed.events));
|
|
assert.equal(item.runIds.length, fixed.runs); assert.equal(new Set(item.runIds).size, fixed.runs);
|
|
for (const row of item.durable) {
|
|
assert.equal(row.ordered, true); assert.equal(row.uniqueSourceIdentities, row.individualDeltas);
|
|
assert.equal(row.matchedSourceClocks, row.individualDeltas);
|
|
if (!fixed.stop) assert.equal(row.individualDeltas, fixed.events);
|
|
}
|
|
}
|
|
const latestCandidateEnd = Math.max(...pairs.map(pair => Date.parse(pair.candidate.owningPlaywright.startedAt) + pair.candidate.owningPlaywright.durationMs));
|
|
assert.ok(Date.parse(owner.startedAt) > latestCandidateEnd, "Original confirmation must follow all candidate arms");
|
|
assert.ok(pairs.every(pair => proof.companyId !== pair.baseline.companyId && proof.companyId !== pair.candidate.companyId), "Original confirmation needs a fresh disposable company/database");
|
|
const inventory = await validateArmInventory(path.resolve(arg("original-h4c-inventory")!), { evidence: proof, owningPlaywright: owner });
|
|
for (const field of ["manifestFileSha256", "aggregateSha256", "qualifiedReceiptSha256", "inventorySummarySha256", "revision"] as const)
|
|
assert.equal(inventory[field], first.candidate.armInventory[field], "Original confirmation used a different full qualified artifact inventory");
|
|
originalH4cConfirmation = { required: true, passed: true, owner, inventory, sourceRevision: proof.sourceRevision };
|
|
} catch (error) {
|
|
originalH4cConfirmation.reason = error instanceof Error ? error.message : String(error);
|
|
}
|
|
}
|
|
}
|
|
const metric = (item: any, key: string): number => key.split(".").reduce((value, part) => value[part], item);
|
|
const measurements = names.flatMap(name => {
|
|
const observed = first.baseline.cases.find((item: any) => item.name === name);
|
|
const keys = ["firstVisibleAfterEmissionMs", "emissionToVisible.medianMs", "drainThroughTerminalMs",
|
|
...(name === "paced" ? ["interChunkGaps.maxMs"] : []),
|
|
...(observed.emissionToVisible.p95Ms === undefined ? [] : ["emissionToVisible.p95Ms", "intendedToVisible.p95Ms"]),
|
|
...(observed.stop ? ["stopThroughTerminalMs", "stopThroughAcknowledgementMs"] : [])];
|
|
return keys.map(key => {
|
|
const samples = pairs.map(pair => {
|
|
const baseline = metric(pair.baseline.cases.find((item: any) => item.name === name), key);
|
|
const candidate = metric(pair.candidate.cases.find((item: any) => item.name === name), key);
|
|
assert.ok(Number.isFinite(baseline) && baseline > 0 && Number.isFinite(candidate) && candidate >= 0, `Invalid latency ${name}.${key}`);
|
|
return { baseline, candidate, improvementRelative: (baseline - candidate) / baseline };
|
|
});
|
|
return { name, metric: key, baselineMedianMs: median(samples.map(sample => sample.baseline)),
|
|
candidateMedianMs: median(samples.map(sample => sample.candidate)),
|
|
medianPairedImprovementRelative: median(samples.map(sample => sample.improvementRelative)),
|
|
candidateWins: samples.filter(sample => sample.improvementRelative > 0).length,
|
|
aaNoiseEnvelopeRelative: phase === "aa" ? Math.max(...samples.map(sample => Math.abs(sample.improvementRelative))) : undefined,
|
|
samples };
|
|
});
|
|
});
|
|
const result: Record<string, any> = {
|
|
scope: "Compiled-app remote streaming and original local Stop performance; additional real cloud Stop qualification is required separately",
|
|
transportPolicy: first.baseline.transportPolicy, additionalRealCloudStopQualificationRequired: true,
|
|
admissionProtocol: first.baseline.admissionProtocol, setupActivationConcurrency: first.baseline.setupActivationConcurrency,
|
|
protocolVersion: first.baseline.protocolVersion, transport: first.baseline.transport,
|
|
resourceBudgets: first.baseline.resourceBudgets,
|
|
phase, expectation, pairCount: pairs.length, baselineRevision: first.baseline.sourceRevision,
|
|
candidateRevision: first.candidate.sourceRevision, measurementSha256: first.baseline.measurementSha256,
|
|
gatesSha256: createHash("sha256").update(await readFile(new URL("./native-ingestion-performance-gates.mjs", import.meta.url))).digest("hex"),
|
|
comparatorSha256: createHash("sha256").update(await readFile(new URL(import.meta.url))).digest("hex"),
|
|
manifestSha256: createHash("sha256").update(await readFile(manifestPath)).digest("hex"), measurements,
|
|
primaryLoadedWorkload: "burst512", complete: true,
|
|
...(h5 ? { observationMode: H5_MODE, workloadSha256: H5_WORKLOAD_SHA256, candidatePolicy, h5Assessments,
|
|
artifactInventories: { baseline: first.baseline.armInventory, candidate: first.candidate.armInventory }, originalH4cConfirmation,
|
|
originalProtocolAcceptance: "Baseline SLA misses are retained; H5 complete observation is not H4c PASS",
|
|
finalUnchangedH4cFunctionalPassRequired: candidatePolicy === "final-b2" } : {}),
|
|
};
|
|
if (phase === "compare") {
|
|
assert.ok(arg("noise-report"), "Comparison requires its frozen A/A --noise-report");
|
|
const noise = JSON.parse(await readFile(arg("noise-report")!, "utf8"));
|
|
assert.equal(noise.phase, "aa"); assert.equal(noise.complete, true);
|
|
if (h5) {
|
|
assert.equal(noise.observationMode, H5_MODE); assert.equal(noise.workloadSha256, H5_WORKLOAD_SHA256);
|
|
assert.equal(noise.h5Assessments?.length, 5, "Fresh complete H5 A/A outcomes are required");
|
|
for (const field of ["manifestFileSha256", "aggregateSha256", "qualifiedReceiptSha256", "inventorySummarySha256", "revision"])
|
|
assert.equal(noise.artifactInventories?.baseline?.[field], result.artifactInventories.baseline[field], "Baseline inventory changed after H5 A/A");
|
|
}
|
|
assert.equal(noise.protocolVersion, result.protocolVersion, "Noise report uses a different mixed protocol");
|
|
assert.equal(noise.transport, result.transport, "Noise report uses a different transport");
|
|
assert.deepEqual(noise.transportPolicy, result.transportPolicy, "Transport policy changed after A/A calibration");
|
|
assert.equal(noise.admissionProtocol, result.admissionProtocol, "Admission protocol changed after A/A calibration");
|
|
assert.equal(noise.setupActivationConcurrency, result.setupActivationConcurrency, "Setup activation concurrency changed after A/A calibration");
|
|
assert.deepEqual(noise.resourceBudgets, result.resourceBudgets, "Resource budgets changed after A/A calibration");
|
|
assert.equal(noise.baselineRevision, result.baselineRevision); assert.equal(noise.measurementSha256, result.measurementSha256);
|
|
assert.equal(noise.gatesSha256, result.gatesSha256, "Acceptance gates changed after A/A calibration");
|
|
assert.equal(noise.comparatorSha256, result.comparatorSha256, "Comparator changed after A/A calibration");
|
|
assert.ok(noise.pairCount >= 5);
|
|
result.gates = measurements.map(item => {
|
|
const control = noise.measurements.find((entry: any) => entry.name === item.name && entry.metric === item.metric);
|
|
assert.ok(control);
|
|
const improvementRequired = expectation === "improvement" && item.name === "burst512"
|
|
&& ["emissionToVisible.p95Ms", "intendedToVisible.p95Ms", "drainThroughTerminalMs"].includes(item.metric);
|
|
const noRegression = -item.medianPairedImprovementRelative <= control.aaNoiseEnvelopeRelative;
|
|
const paired = noiseExceedingPairedWins(item.samples.map(sample => sample.improvementRelative), control.aaNoiseEnvelopeRelative);
|
|
const improvement = paired.pairedWinRequirementPassed
|
|
&& item.medianPairedImprovementRelative > control.aaNoiseEnvelopeRelative;
|
|
return { name: item.name, metric: item.metric, improvementRequired, noiseEnvelopeRelative: control.aaNoiseEnvelopeRelative,
|
|
noiseExceedingPairedWins: paired.noiseExceedingPairedWins, requiredPairedWins: paired.requiredPairedWins,
|
|
passed: improvementRequired ? improvement : noRegression };
|
|
});
|
|
result.performancePassed = result.gates.every((entry: any) => entry.passed)
|
|
&& (!h5 || h5Assessments.every(entry => entry.candidateSlaPolicyPassed));
|
|
result.acceptancePassed = result.performancePassed && (!originalH4cConfirmation || originalH4cConfirmation.passed);
|
|
}
|
|
if (arg("output")) await writeFile(arg("output")!, JSON.stringify(result, null, 2));
|
|
console.log(JSON.stringify(result, null, 2));
|
|
if (process.argv.includes("--require-performance")) {
|
|
assert.equal(h5, true, "H5 performance-only gating is explicit; original H4c remains unchanged");
|
|
assert.equal(phase, "compare");
|
|
assert.equal(result.performancePassed, true, "H5 performance/SLA gates failed; retain results and diagnose");
|
|
}
|
|
if (process.argv.includes("--require-acceptance")) {
|
|
assert.equal(phase, "compare", "A/A calibrates noise; it is not performance acceptance");
|
|
assert.equal(result.acceptancePassed, true, "Browser performance acceptance failed; retain results and diagnose");
|
|
}
|