mirror of
https://github.com/paperclipai/paperclip.git
synced 2026-11-11 05:11:49 +01:00
Qualify remote ingestion streaming with original local Stop coverage
This commit is contained in:
Dotta committed
1 parent
2d962322ea
commit
5f5328952f
9 files changed
+477
-177
No files matched your search
@@ -32,8 +32,10 @@ const sha256 = (value: unknown) => typeof value === "string" && /^[a-f0-9]{64}$/
|
||||
const uuid = (value: unknown) => typeof value === "string" && /^[a-f0-9]{8}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{4}-[a-f0-9]{12}$/i.test(value);
|
||||
for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const) {
|
||||
const report = pair[arm];
|
||||
assert.equal(report.protocolVersion, "v3-supported-remote-original-clock-stream", "Fresh browser acceptance requires the qualified v3 remote clock protocol");
|
||||
assert.equal(report.transport, "sandbox-remote", "V3 requires the supported sandbox remote transport");
|
||||
assert.equal(report.protocolVersion, "v4-remote-streaming-original-local-stop-clock-stream", "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");
|
||||
@@ -43,6 +45,22 @@ for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const)
|
||||
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");
|
||||
@@ -85,6 +103,8 @@ for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const)
|
||||
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.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");
|
||||
@@ -103,7 +123,8 @@ for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const)
|
||||
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 remote database controller authority proof");
|
||||
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
|
||||
@@ -115,36 +136,108 @@ for (const pair of pairs) for (const arm of ["baseline", "candidate"] as const)
|
||||
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 remote task/lease UUID");
|
||||
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, remote.environmentId, "Remote authority environment mismatch");
|
||||
assert.equal(row.environment_id, result.environmentId, "Remote authority environment mismatch");
|
||||
assert.equal(row.runtime_mode, "native");
|
||||
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);
|
||||
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(Number.isSafeInteger(row.process_identity_seq) && row.process_identity_seq > 0);
|
||||
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.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
|
||||
&& (!result.stop || result.remoteLeasesCheckedAtMs >= result.stopAcknowledgedAtMs), "Verify remote leases after recorded timing boundaries");
|
||||
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.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");
|
||||
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);
|
||||
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(after.process_stopped_seq > 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 === "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");
|
||||
&& 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) {
|
||||
@@ -179,7 +272,8 @@ const measurements = names.flatMap(name => {
|
||||
});
|
||||
});
|
||||
const result: Record<string, any> = {
|
||||
scope: "Compiled-app deterministic-provider/browser acceptance; live-provider qualification remains separate",
|
||||
scope: "Compiled-app remote streaming and original local Stop performance; additional real cloud Stop qualification is required separately",
|
||||
transportPolicy: first.baseline.transportPolicy, additionalRealCloudStopQualificationRequired: true,
|
||||
protocolVersion: first.baseline.protocolVersion, transport: first.baseline.transport,
|
||||
resourceBudgets: first.baseline.resourceBudgets,
|
||||
phase, expectation, pairCount: pairs.length, baselineRevision: first.baseline.sourceRevision,
|
||||
@@ -193,8 +287,9 @@ 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);
|
||||
assert.equal(noise.protocolVersion, result.protocolVersion, "Noise report uses a different remote protocol");
|
||||
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.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");
|
||||
|
||||
@@ -76,41 +76,73 @@ const workloads = [
|
||||
];
|
||||
function browserReport(revision, latency) {
|
||||
const companyId = "00000000-0000-4000-8000-000000000001", environmentId = "00000000-0000-4000-8000-000000000002";
|
||||
const localEnvironmentId = "00000000-0000-4000-8000-000000000003", controlAgentId = "00000000-0000-4000-8000-000000000004";
|
||||
const remoteAgentId = "00000000-0000-4000-8000-000000000005";
|
||||
const id = (kind, caseIndex, index) => `00000000-0000-4000-8000-${(kind * 100000 + caseIndex * 1000 + index).toString(16).padStart(12, "0")}`;
|
||||
return { protocolVersion: "v3-supported-remote-original-clock-stream", transport: "sandbox-remote", companyId,
|
||||
const transportPolicy = { streaming: "sandbox-remote", operatorStop: "local",
|
||||
realCloudStop: "Separate required qualification; fake-plugin void receipts grant no remote Stop authority" };
|
||||
return { protocolVersion: "v4-remote-streaming-original-local-stop-clock-stream", transport: "sandbox-remote-with-local-stop", transportPolicy, companyId,
|
||||
resourceBudgets: { providerReadinessMs: 300000, fullInvocationMs: 900000, streamingMs: 120000,
|
||||
terminalDrainageMs: 180000, stopAcknowledgementMs: 30000, remoteLeaseCleanupMs: 30000 },
|
||||
remote: { transport: "sandbox-remote", revision, buildRevision: revision, environmentId,
|
||||
local: { transport: "local", environmentId: localEnvironmentId, controlAgentId,
|
||||
selection: "Normal local environment + separate control agent defaultEnvironmentId; existing test-only Codex leaf command fixture",
|
||||
commandSha256: "6".repeat(64), loaderSha256: "7".repeat(64) },
|
||||
remote: { transport: "sandbox-remote", revision, buildRevision: revision, environmentId, agentIds: [remoteAgentId],
|
||||
runnerPublicUrl: "wss://127.0.0.1:32100",
|
||||
selection: "Normal plugin install + sandbox environment + agent defaultEnvironmentId; no runtime resolver override",
|
||||
plugin: { pluginKey: "paperclip.fake-sandbox-provider" }, tls: { peerVerification: true, caSha256: "e".repeat(64), serverCertificateSha256: "f".repeat(64) },
|
||||
plugin: { pluginKey: "paperclip.fake-sandbox-provider", assetHashes: Object.fromEntries(["worker.js", "plugin.js", "manifest.js", "lease-cleanup.js"].map(file => [file, "5".repeat(64)])) },
|
||||
tls: { peerVerification: true, caSha256: "e".repeat(64), serverCertificateSha256: "f".repeat(64) },
|
||||
runner: { sha256: "d".repeat(64), metadata: { prpTransportModes: ["dial_wss"] } },
|
||||
provider: { nodeSha256: "b".repeat(64), wrapperSha256: "c".repeat(64), fixtureSha256: "a".repeat(64) } },
|
||||
fixtureSha256: "a".repeat(64), admissionProtocol: "sequential-provider-and-clock-readiness-before-common-epoch", setupReadinessPollingMs: 50, complete: true, cleanup: { complete: true, errors: [] }, qualificationOnly: false, diagnosticOnly: false, performanceAcceptanceEligible: true, browserRecording: { trace: "off", video: "off", screencast: false },
|
||||
sourceRevision: revision, compiledBuildRevision: revision, serverArtifact: "compiled", serverEntrySha256: `${revision}-compiled`,
|
||||
measurementSha256: "synthetic-fixed-fixture", compiledHotPathHashes: { append: "append", port: "port", runtime: "runtime" },
|
||||
cases: workloads.map((workload, caseIndex) => ({ ...workload, stop: Boolean(workload.stop), persistedAfterReload: true,
|
||||
epochMs: 1000, preludeProof: workload.prelude ? { individualDeltas: workload.prelude, uniqueSourceIdentities: workload.prelude, verifiedAtMs: 999 } : undefined,
|
||||
settledAtMs: 1000 + latency, stopRequestedAtMs: workload.stop ? 1000 : undefined,
|
||||
stopAcknowledgedAtMs: workload.stop ? 1000 + latency : undefined, remoteLeasesCheckedAtMs: 1001 + latency,
|
||||
runIds: Array.from({ length: workload.runs }, (_, index) => id(1, caseIndex, index)),
|
||||
controllerAuthority: { checkedBeforeMeasuredEpoch: true, checkedAtMs: 998, connectionClosedAtMs: 999,
|
||||
observedReadOnly: "on", observedIsolation: "repeatable read", rows: Array.from({ length: workload.runs }, (_, index) => ({
|
||||
run_id: id(1, caseIndex, index), issue_id: id(2, caseIndex, index), company_id: companyId,
|
||||
lease_id: id(3, caseIndex, index), environment_id: environmentId, runtime_mode: "native", provider: "fake-plugin",
|
||||
provider_lease_id: `fake-plugin://${id(1, caseIndex, index)}/fixture`, checkpoint_part: "header", checkpoint_header_bytes: 256,
|
||||
})) },
|
||||
remoteLeases: Array.from({ length: workload.runs }, (_, index) => ({ id: id(3, caseIndex, index), runId: id(1, caseIndex, index),
|
||||
companyId, environmentId, provider: "fake-plugin", providerLeaseId: `fake-plugin://${id(1, caseIndex, index)}/fixture`,
|
||||
status: "released", cleanupStatus: "success", releasedAt: "2026-11-03T00:00:00.000Z" })),
|
||||
visible: Array(workload.stop ? 3 : workload.events).fill({}), matchedVisibleClocks: workload.stop ? 3 : workload.events,
|
||||
firstVisibleAfterEmissionMs: latency, emissionToVisible: { medianMs: latency, p95Ms: latency },
|
||||
interChunkGaps: { paintCount: workload.events, count: workload.events - 1, medianMs: latency, maxMs: latency },
|
||||
intendedToVisible: { p95Ms: latency }, drainThroughTerminalMs: latency,
|
||||
stopThroughTerminalMs: latency, stopThroughAcknowledgementMs: latency,
|
||||
durable: Array.from({ length: workload.runs }, (_, index) => ({ runId: id(1, caseIndex, index), token: String(index), ordered: true,
|
||||
uniqueSourceIdentities: workload.stop ? 3 : workload.events, individualDeltas: workload.stop ? 3 : workload.events, matchedSourceClocks: workload.stop ? 3 : workload.events })),
|
||||
})) };
|
||||
cases: workloads.map((workload, caseIndex) => {
|
||||
const stop = Boolean(workload.stop), actualEnvironmentId = stop ? localEnvironmentId : environmentId;
|
||||
const launcher = stop ? "host-local" : "staged-remote", pid = 20000 + caseIndex * 1000;
|
||||
const snapshot = { checkedBeforeMeasuredEpoch: true, checkedAtMs: 998, connectionClosedAtMs: 999,
|
||||
observedReadOnly: "on", observedIsolation: "repeatable read", kind: stop ? "host-file-journal" : "database-controller-checkpoint" };
|
||||
const rows = Array.from({ length: workload.runs }, (_, index) => ({
|
||||
run_id: id(1, caseIndex, index), issue_id: id(2, caseIndex, index), company_id: companyId,
|
||||
agent_id: stop ? controlAgentId : remoteAgentId,
|
||||
lease_id: id(3, caseIndex, index), environment_id: actualEnvironmentId, runtime_mode: "native", provider: stop ? "local" : "fake-plugin",
|
||||
provider_lease_id: stop ? null : `fake-plugin://${id(1, caseIndex, index)}/fixture`,
|
||||
checkpoint_part: stop ? null : "header", checkpoint_header_bytes: stop ? null : 256,
|
||||
runner_instance_id: id(6, caseIndex, index), native_session_id: id(7, caseIndex, index), admitted_execution_workspace_id: id(8, caseIndex, index),
|
||||
...(stop ? { process_pid: pid - 1, process_group_id: pid - 1, process_started_at: "2026-11-03T00:00:00.000Z",
|
||||
process_identity_seq: 1, process_identity_source_event_id: null,
|
||||
process_identity: { targetKind: "local", hostname: "fixture-host", processPid: pid - 1, processGroupId: pid - 1,
|
||||
processStartedAt: "2026-11-03T00:00:00.000Z" } } : {}),
|
||||
}));
|
||||
const lease = { id: rows[0].lease_id, heartbeatRunId: rows[0].run_id, companyId, environmentId: localEnvironmentId,
|
||||
provider: "local", providerLeaseId: null, status: "released", releasedAt: "2026-11-03T00:00:01.000Z", cleanupStatus: null };
|
||||
const localProcesses = { runnerPid: pid - 1, processGroupId: pid - 1, providerPid: pid, hostname: "fixture-host",
|
||||
checkedAtMs: 999, runnerAlive: true, groupAlive: true, providerAlive: true };
|
||||
return { ...workload, stop, transport: stop ? "local" : "sandbox-remote", environmentId: actualEnvironmentId, persistedAfterReload: true,
|
||||
epochMs: 1000, preludeProof: workload.prelude ? { individualDeltas: workload.prelude, uniqueSourceIdentities: workload.prelude, verifiedAtMs: 999 } : undefined,
|
||||
settledAtMs: 1000 + latency, stopRequestedAtMs: stop ? 1000 : undefined,
|
||||
stopAcknowledgedAtMs: stop ? 1000 + latency : undefined, remoteLeasesCheckedAtMs: stop ? undefined : 1001 + latency,
|
||||
runIds: rows.map(row => row.run_id), controllerAuthority: { ...snapshot, rows,
|
||||
...(stop ? { localJournal: { schema: "paperclip.runner.durable.control-plane-state.v1", sha256: "8".repeat(64), bytes: 512, checkedAtMs: 999,
|
||||
identity: { runId: rows[0].run_id, runnerInstanceId: rows[0].runner_instance_id, normalizedSessionId: rows[0].native_session_id, environmentLeaseId: rows[0].admitted_execution_workspace_id } } } : {}) },
|
||||
providerClocks: rows.map((row, index) => ({ runId: row.run_id, nonce: String(index), launcher, providerPid: pid + index })),
|
||||
clockEvidence: rows.map((row, index) => ({ nonce: String(index), launcher, providerPid: pid + index })),
|
||||
...(stop ? { localProcesses, localStopProof: { checkedAtMs: 1001 + latency, lease,
|
||||
processes: { ...localProcesses, runnerAbsent: true, groupAbsent: true, providerAbsent: true },
|
||||
database: { ...snapshot, checkedBeforeMeasuredEpoch: false, checkedAtMs: 1000 + latency, connectionClosedAtMs: 1000 + latency,
|
||||
rows: [{ ...rows[0], process_pid: null, process_group_id: null, process_started_at: null, status: "cancelled", cancellation_dispatch_state: "acknowledged",
|
||||
process_stopped_seq: 2, process_stopped_source_event_id: null, process_stopped: { processPid: pid - 1, processGroupId: pid - 1, processStartedAt: rows[0].process_started_at } }] } } }
|
||||
: { remoteLeases: rows.map(row => ({ id: row.lease_id, runId: row.run_id, companyId, environmentId, provider: "fake-plugin", providerLeaseId: row.provider_lease_id,
|
||||
status: "released", cleanupStatus: "success", releasedAt: "2026-11-03T00:00:00.000Z" })) }),
|
||||
visible: Array(stop ? 3 : workload.events).fill({}), matchedVisibleClocks: stop ? 3 : workload.events,
|
||||
firstVisibleAfterEmissionMs: latency, emissionToVisible: { medianMs: latency, p95Ms: latency },
|
||||
interChunkGaps: { paintCount: workload.events, count: workload.events - 1, medianMs: latency, maxMs: latency },
|
||||
intendedToVisible: { p95Ms: latency }, drainThroughTerminalMs: latency,
|
||||
stopThroughTerminalMs: latency, stopThroughAcknowledgementMs: latency,
|
||||
durable: rows.map((row, index) => ({ runId: row.run_id, token: String(index), ordered: true,
|
||||
uniqueSourceIdentities: stop ? 3 : workload.events, individualDeltas: stop ? 3 : workload.events, matchedSourceClocks: stop ? 3 : workload.events })),
|
||||
};
|
||||
}) };
|
||||
}
|
||||
|
||||
test("browser CLI rejects the three-pairs-above-noise counterexample and ineligible evidence", async () => {
|
||||
@@ -146,9 +178,18 @@ test("browser CLI rejects the three-pairs-above-noise counterexample and ineligi
|
||||
["profile", report => { report.diagnosticOnly = true; }, /Diagnostic profiles/],
|
||||
["profile-ineligible", report => { report.performanceAcceptanceEligible = false; }, /Profile-only evidence/],
|
||||
["missing-retained-prelude", report => { report.cases.find(row => row.prelude).preludeProof.individualDeltas--; }, /stored prelude deltas/],
|
||||
["legacy-protocol", report => { delete report.protocolVersion; }, /v3 remote clock protocol/],
|
||||
["old-local-protocol", report => { report.protocolVersion = "v2-compact-markers-original-clock-stream"; report.transport = "local"; }, /v3 remote clock protocol/],
|
||||
["wrong-transport", report => { report.transport = "local"; }, /sandbox remote transport/],
|
||||
["legacy-protocol", report => { delete report.protocolVersion; }, /v4 mixed clock protocol/],
|
||||
["old-local-protocol", report => { report.protocolVersion = "v2-compact-markers-original-clock-stream"; report.transport = "local"; }, /v4 mixed clock protocol/],
|
||||
["old-remote-protocol", report => { report.protocolVersion = "v3-supported-remote-original-clock-stream"; }, /v4 mixed clock protocol/],
|
||||
["wrong-transport", report => { report.transport = "local"; }, /original local Stop transport/],
|
||||
["missing-transport-policy", report => { delete report.transportPolicy; }, /explicit transport/],
|
||||
["fake-remote-stop", report => { report.cases[5].transport = "sandbox-remote"; }, /Wrong per-case transport/],
|
||||
["local-loaded-workload", report => { report.cases[3].transport = "local"; }, /Wrong per-case transport/],
|
||||
["wrong-case-environment", report => { report.cases[5].environmentId = report.remote.environmentId; }, /normal environment/],
|
||||
["missing-local-selection", report => { delete report.local; }, /local Stop runtime provenance/],
|
||||
["shared-control-agent", report => { report.local.controlAgentId = report.remote.agentIds[0]; }, /separate normal control agent/],
|
||||
["changed-local-command", report => { report.local.commandSha256 = "9".repeat(64); }, /Local Stop fixture changed/],
|
||||
["changed-provider-cleanup", report => { report.remote.plugin.assetHashes["lease-cleanup.js"] = "9".repeat(64); }, /Provider cleanup build changed/],
|
||||
["unregistered-resource-budget", report => { report.resourceBudgets.providerReadinessMs = 600000; }, /registered remote setup\/resource budgets/],
|
||||
["missing-normal-remote", report => { delete report.remote; }, /normal remote runtime provenance/],
|
||||
["missing-plugin", report => { delete report.remote.plugin; }, /plugin provenance/],
|
||||
@@ -169,6 +210,28 @@ test("browser CLI rejects the three-pairs-above-noise counterexample and ineligi
|
||||
["authority-wrong-environment", report => { report.cases[3].controllerAuthority.rows[99].environment_id = "other"; }, /environment mismatch/],
|
||||
["authority-wrong-provider", report => { report.cases[3].controllerAuthority.rows[99].provider = "fake"; }, /fake-plugin/],
|
||||
["authority-missing-checkpoint", report => { report.cases[3].controllerAuthority.rows[99].checkpoint_part = null; }, /checkpoint header/],
|
||||
["local-wrong-checkpoint-authority", report => { report.cases[5].controllerAuthority.kind = "database-controller-checkpoint"; }, /Wrong checkpoint authority/],
|
||||
["local-fake-database-header", report => { report.cases[5].controllerAuthority.rows[0].checkpoint_part = "header"; }, /host-file authority/],
|
||||
["missing-local-journal", report => { delete report.cases[5].controllerAuthority.localJournal; }, /owned local journal authority/],
|
||||
["local-journal-wrong-run", report => { report.cases[5].controllerAuthority.localJournal.identity.runId = "other"; }, /Local journal identity mismatch/],
|
||||
["local-journal-wrong-workspace", report => { report.cases[5].controllerAuthority.rows[0].admitted_execution_workspace_id = report.remote.environmentId; }, /Local journal identity mismatch/],
|
||||
["local-journal-bookkeeping-alias", report => { report.cases[5].controllerAuthority.localJournal.identity.environmentLeaseId = report.cases[5].controllerAuthority.rows[0].lease_id; }, /Local journal identity mismatch/],
|
||||
["local-missing-admitted-workspace", report => { delete report.cases[5].controllerAuthority.rows[0].admitted_execution_workspace_id; }, /admitted local workspace binding/],
|
||||
["local-journal-wrong-policy", report => { report.cases[5].controllerAuthority.localJournal.checkpointEventPolicy = "control-v1"; }, /original local raw transport/],
|
||||
["missing-wrapper-provenance", report => { delete report.cases[3].providerClocks; }, /wrapper launcher and PID/],
|
||||
["remote-used-local-wrapper", report => { report.cases[3].providerClocks[99].launcher = "host-local"; }, /wrapper launcher/],
|
||||
["local-used-remote-wrapper", report => { report.cases[5].providerClocks[0].launcher = "staged-remote"; }, /wrapper launcher/],
|
||||
["missing-hello-pid", report => { delete report.cases[3].clockEvidence[99].providerPid; }, /hello provider PID/],
|
||||
["missing-local-identity-event", report => { delete report.cases[5].controllerAuthority.rows[0].process_identity; }, /targetKind|local/],
|
||||
["provider-authored-local-identity", report => { report.cases[5].controllerAuthority.rows[0].process_identity_source_event_id = "provider-event"; }, /server-authored/],
|
||||
["missing-local-physical-proof", report => { delete report.cases[5].localStopProof; }, /physical Stop/],
|
||||
["local-provider-still-alive", report => { report.cases[5].localStopProof.processes.providerAbsent = false; }, /remains alive/],
|
||||
["local-group-still-alive", report => { report.cases[5].localStopProof.processes.groupAbsent = false; }, /false.*true|false !== true/],
|
||||
["local-database-ack-missing", report => { report.cases[5].localStopProof.database.rows[0].cancellation_dispatch_state = "pending"; }, /acknowledged/],
|
||||
["local-cleared-identity-no-receipt", report => { delete report.cases[5].localStopProof.database.rows[0].process_stopped_seq; }, /server stop receipt/],
|
||||
["local-provider-stop-receipt", report => { report.cases[5].localStopProof.database.rows[0].process_stopped_source_event_id = "provider"; }, /null/],
|
||||
["local-lease-cleanup-failed", report => { report.cases[5].localStopProof.lease.cleanupStatus = "failed"; }, /Local Stop lease cleanup/],
|
||||
["local-lease-wrong-binding", report => { report.cases[5].localStopProof.lease.heartbeatRunId = "other"; }, /other/],
|
||||
["missing-lease-cleanup", report => { delete report.cases[3].remoteLeases; }, /lease cleanup proof/],
|
||||
["lease-pending", report => { report.cases[3].remoteLeases[99].status = "pending_cleanup"; }, /cleanup remains unsettled/],
|
||||
["lease-wrong-binding", report => { report.cases[3].remoteLeases[99].providerLeaseId = "other"; }, /fake-plugin/],
|
||||
@@ -189,9 +252,10 @@ test("browser CLI rejects the three-pairs-above-noise counterexample and ineligi
|
||||
assert.notEqual(rejected.status, 0); assert.match(rejected.stderr, message);
|
||||
}
|
||||
for (const [name, change, message] of [
|
||||
["old-noise-protocol", report => { report.protocolVersion = "v2-compact-markers-original-clock-stream"; }, /different remote protocol/],
|
||||
["old-noise-protocol", report => { report.protocolVersion = "v2-compact-markers-original-clock-stream"; }, /different mixed protocol/],
|
||||
["local-noise-transport", report => { report.transport = "local"; }, /different transport/],
|
||||
["changed-noise-budget", report => { report.resourceBudgets.providerReadinessMs++; }, /budgets changed after A\/A/],
|
||||
["changed-noise-transport-policy", report => { report.transportPolicy.operatorStop = "sandbox-remote"; }, /Transport policy changed after A\/A/],
|
||||
]) {
|
||||
const changed = JSON.parse(await readFile(noise, "utf8")); change(changed);
|
||||
const file = await save(name + ".json", changed);
|
||||
|
||||
Reference in new issue
Block a user