mirror of
https://github.com/morluto/rea.git
synced 2026-10-18 20:10:13 -05:00
* test(perf): pin genuine Fiddler captures and raw HTTP oracles Pin two public Microsoft SAZ captures with 13 and 1311 sessions, immutable source/digest/member coverage and predeclared caller-ordered transaction questions. Independently preserve stored HTTP headers, binary/empty bodies and archive coordinates; admit only known corpus bytes before ZIP allocation. Five reader regressions and both genuine selected-record checks pass. No production or performance-gain claim. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> * test(perf): measure SAZ selection and retained recovery workflows Add authenticated complete/ordinal/retained-page SDK experiments, fixed real-Codex prompts and independent cited-byte grading. Preserve actual failed RPCs and exact retained-reference recovery when complete MCP delivery exceeds its receive buffer. Verify selected CLI/MCP facts, parameters and semantic Evidence identity. Keep a genuine partial-message admission-negative probe. Focused 12 tests and 10 actual-Evidence grading cases pass; no formal model or gain claim yet. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> * test(perf): verify resolved SAZ Evidence selection parameters Distinguish omitted request ordinals from the complete resolved ordinal scope recorded by WebNetworkCaptureService. Share the expected sanitized Evidence representation between SDK checks and model grading; preserve original caller arguments. A focused regression and both saved genuine baseline RPCs confirm the correction. Keep original collector failures and costs unchanged; freeze a new driver before repeated measurements. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> * docs(perf): retain mixed SAZ whole-task costs and failure boundaries Record both SDK batches, twelve corrected workflows, all four actual Codex attempts, independent byte equivalence and verified payload-phase CPU/memory. Distinguish successful-analysis MCP transport limits from real provider timeouts and negative partial-message admission. Three model questions complete; the only completed pair saves 1.6 percent input but takes 2 percent longer, with no consistent benefit. Keep production APIs/defaults/cache unchanged and preserve all deviations, failed attempts and unknowns. Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com> --------- Co-authored-by: factory-droid[bot] <138933559+factory-droid[bot]@users.noreply.github.com> Co-authored-by: Kaoru0822 <208281322+kaoru0822-kitauji@users.noreply.github.com> Co-authored-by: gensokyo-dev <342580529+gensokyo-dev@users.noreply.github.com>
327 lines
12 KiB
JavaScript
327 lines
12 KiB
JavaScript
import assert from "node:assert/strict";
|
|
import { execFile } from "node:child_process";
|
|
import { readFile } from "node:fs/promises";
|
|
import { resolve } from "node:path";
|
|
import { fileURLToPath, pathToFileURL } from "node:url";
|
|
import { promisify } from "node:util";
|
|
|
|
const corpus = JSON.parse(
|
|
await readFile(new URL("./corpus.json", import.meta.url), "utf8"),
|
|
);
|
|
export const SAZ_ARTIFACTS = Object.fromEntries(
|
|
corpus.artifacts
|
|
.filter((entry) => entry.saz_question)
|
|
.map((entry) => [entry.id, entry]),
|
|
);
|
|
|
|
export function sazRequest(artifact, path, selection) {
|
|
const question = Object.hasOwn(SAZ_ARTIFACTS, artifact)
|
|
? SAZ_ARTIFACTS[artifact].saz_question
|
|
: undefined;
|
|
if (!question) throw new Error("Select a pinned SAZ question");
|
|
return {
|
|
capture_path: path,
|
|
format: "saz",
|
|
...(selection === "baseline"
|
|
? {}
|
|
: { record_ordinals: question.record_ordinals }),
|
|
sensitive_values: [],
|
|
};
|
|
}
|
|
|
|
export function verifySazOracleIdentity(artifact, oracle) {
|
|
assert.ok(
|
|
Object.hasOwn(SAZ_ARTIFACTS, artifact),
|
|
"Unknown pinned SAZ question",
|
|
);
|
|
const entry = SAZ_ARTIFACTS[artifact];
|
|
assert.equal(oracle.kind, "saz");
|
|
assert.equal(oracle.artifact, artifact);
|
|
assert.equal(oracle.sha256, entry.sha256, "Wrong immutable corpus");
|
|
assert.equal(oracle.total_records, entry.saz_question.total_records);
|
|
assert.deepEqual(oracle.record_ordinals, entry.saz_question.record_ordinals);
|
|
}
|
|
|
|
export function sazEvidenceParameters(input, totalRecords) {
|
|
return {
|
|
capture_path: input.capture_path,
|
|
format: input.format,
|
|
record_ordinals:
|
|
input.record_ordinals ??
|
|
Array.from({ length: totalRecords }, (_, index) => index),
|
|
sensitive_value_count: input.sensitive_values.length,
|
|
};
|
|
}
|
|
|
|
export function verifySazRecords(records, oracle) {
|
|
assert.equal(oracle.kind, "saz", "Wrong independent question");
|
|
assert.equal(
|
|
records.length,
|
|
oracle.records.length,
|
|
"Selected coverage differs",
|
|
);
|
|
return records.map((record, index) => {
|
|
const raw = oracle.records[index];
|
|
assert.equal(record.ordinal, raw.ordinal, "Caller order/ordinal differs");
|
|
assert.equal(
|
|
record.reported.session_id,
|
|
raw.session_id,
|
|
"Padded source identity differs",
|
|
);
|
|
assert.deepEqual(
|
|
record.location,
|
|
{ kind: "archive-members", members: raw.members },
|
|
"Original member coordinates differ",
|
|
);
|
|
for (const side of ["request", "response"]) {
|
|
const expected = raw[side],
|
|
reported = record.reported[side];
|
|
if (expected === null) {
|
|
assert.equal(reported, null, "Absent message invented");
|
|
assert.ok(
|
|
!record.binary_fields.some(
|
|
(field) => field.pointer === `/${side}/body`,
|
|
),
|
|
"Absent body invented",
|
|
);
|
|
continue;
|
|
}
|
|
assert.equal(reported.member, expected.member);
|
|
for (const field of side === "request"
|
|
? ["method", "url", "http_version"]
|
|
: ["status", "reason", "http_version"])
|
|
assert.equal(
|
|
reported[field],
|
|
expected[field],
|
|
"Stored HTTP start line differs",
|
|
);
|
|
const contentTypes = (headers) =>
|
|
headers.filter(
|
|
(header) => header.name.toLowerCase() === "content-type",
|
|
);
|
|
assert.deepEqual(
|
|
contentTypes(reported.headers),
|
|
contentTypes(expected.headers),
|
|
"Content-Type order/spelling/values differ",
|
|
);
|
|
const bodies = record.binary_fields.filter(
|
|
(field) => field.pointer === `/${side}/body`,
|
|
);
|
|
assert.equal(bodies.length, 1, "Stored body representation differs");
|
|
const body = bodies[0];
|
|
assert.equal(body.state, "retained", "Stored body unexpectedly unknown");
|
|
assert.equal(
|
|
body.representation,
|
|
"producer-bytes",
|
|
"Encoded source representation differs",
|
|
);
|
|
for (const field of ["bytes", "sha256", "content_base64"])
|
|
assert.equal(
|
|
body[field],
|
|
expected.body[field],
|
|
"Stored encoded body bytes differ",
|
|
);
|
|
assert.equal(
|
|
reported.body,
|
|
expected.body.text,
|
|
"UTF-8 projection or empty body differs",
|
|
);
|
|
}
|
|
const response = raw.response;
|
|
return {
|
|
ordinal: record.ordinal,
|
|
session_id: raw.session_id,
|
|
members: raw.members,
|
|
request:
|
|
raw.request === null
|
|
? null
|
|
: { method: raw.request.method, url: raw.request.url },
|
|
response:
|
|
response === null
|
|
? null
|
|
: {
|
|
status: response.status,
|
|
http_version: response.http_version,
|
|
content_types: response.headers.filter(
|
|
(header) => header.name.toLowerCase() === "content-type",
|
|
),
|
|
body: {
|
|
bytes: response.body.bytes,
|
|
sha256: response.body.sha256,
|
|
},
|
|
},
|
|
};
|
|
});
|
|
}
|
|
|
|
export async function measureSazEntry({ values, call, inputSha }) {
|
|
const runtime = (file) =>
|
|
pathToFileURL(resolve(values["runtime-root"], file)).href;
|
|
const { parseEvidence } = await import(runtime("dist/domain/evidence.js"));
|
|
const { inspectWebNetworkCaptureInputSchema, webNetworkCaptureSchema } =
|
|
await import(runtime("dist/domain/webNetworkCapture.js"));
|
|
const { inspectAnalysisViewInputSchema, analysisViewResultSchema } =
|
|
await import(runtime("dist/domain/analysisView/analysisView.js"));
|
|
const read = await promisify(execFile)(
|
|
"python3",
|
|
[
|
|
fileURLToPath(new URL("./saz-oracle.py", import.meta.url)),
|
|
values.artifact,
|
|
values.path,
|
|
],
|
|
{ maxBuffer: 2 * 1024 * 1024, timeout: 30_000 },
|
|
);
|
|
const oracle = JSON.parse(read.stdout);
|
|
verifySazOracleIdentity(values.artifact, oracle);
|
|
assert.equal(oracle.sha256, inputSha);
|
|
const input = inspectWebNetworkCaptureInputSchema.parse(
|
|
sazRequest(values.artifact, values.path, values["saz-selection"]),
|
|
);
|
|
const observations = [];
|
|
const checked = (evidence, schema) => {
|
|
evidence = parseEvidence(evidence);
|
|
assert.equal(evidence.subject.local_path, values.path);
|
|
assert.equal(evidence.subject.digest.sha256, inputSha);
|
|
const report = schema.parse(evidence.normalized_result);
|
|
observations.push({
|
|
evidence_id: evidence.evidence_id,
|
|
operation: evidence.operation,
|
|
parameters: evidence.parameters,
|
|
limitations: evidence.limitations,
|
|
coverage: report.coverage ?? {
|
|
total_records: report.total_records,
|
|
retained_records: report.records.length,
|
|
},
|
|
});
|
|
return report;
|
|
};
|
|
const readView = async (source, view) => {
|
|
const request = inspectAnalysisViewInputSchema.parse({ source, view });
|
|
const evidence = await call("inspect_analysis_view", request);
|
|
assert.equal(evidence.operation, "inspect_analysis_view");
|
|
assert.deepEqual(evidence.parameters, {
|
|
parent_evidence_id: source.evidence_id,
|
|
view: request.view,
|
|
});
|
|
const result = checked(evidence, analysisViewResultSchema);
|
|
assert.equal(result.kind, request.view.kind);
|
|
assert.equal(result.parent_evidence_id, source.evidence_id);
|
|
assert.equal(result.parent_operation, "inspect_web_network_capture");
|
|
assert.deepEqual(result.view, request.view);
|
|
return result;
|
|
};
|
|
let records, decoder;
|
|
if (values["saz-selection"] !== "retained") {
|
|
let evidence;
|
|
try {
|
|
evidence = await call("inspect_web_network_capture", input);
|
|
} catch (failure) {
|
|
const error = failure.value?.error;
|
|
const limits = error?.details?.reported_limits;
|
|
if (
|
|
values["saz-selection"] !== "baseline" ||
|
|
error?.code !== "resource_constraint" ||
|
|
error.details.operation !== "inspect_web_network_capture" ||
|
|
limits?.boundary !== "mcp-response" ||
|
|
!limits.evidence_reference
|
|
)
|
|
throw failure;
|
|
// Recover only the exact retained reference returned by this failed call.
|
|
// The failed RPC remains in the shared measurement log and task costs.
|
|
const source = limits.evidence_reference;
|
|
assert.equal(source.kind, "retained-evidence");
|
|
const summary = await readView(source, { kind: "summary" });
|
|
assert.equal(summary.summary.format, "saz");
|
|
assert.equal(summary.summary.total_records, oracle.total_records);
|
|
assert.equal(summary.summary.retained_records, oracle.total_records);
|
|
decoder = summary.summary.decoder;
|
|
records = [];
|
|
for (const ordinal of oracle.record_ordinals) {
|
|
const page = await readView(source, {
|
|
kind: "capture",
|
|
detail: "complete",
|
|
offset: ordinal,
|
|
limit: 1,
|
|
});
|
|
assert.equal(page.coverage.total, oracle.total_records);
|
|
assert.equal(page.items.length, 1);
|
|
records.push(page.items[0]);
|
|
}
|
|
}
|
|
if (evidence !== undefined) {
|
|
assert.equal(evidence.operation, "inspect_web_network_capture");
|
|
assert.deepEqual(
|
|
evidence.parameters,
|
|
sazEvidenceParameters(input, oracle.total_records),
|
|
);
|
|
const report = checked(evidence, webNetworkCaptureSchema);
|
|
assert.equal(report.format, "saz");
|
|
assert.equal(report.total_records, oracle.total_records);
|
|
assert.equal(
|
|
report.records.length,
|
|
values["saz-selection"] === "baseline"
|
|
? oracle.total_records
|
|
: oracle.records.length,
|
|
);
|
|
if (values["saz-selection"] === "baseline")
|
|
assert.deepEqual(
|
|
report.records.map((record) => record.ordinal),
|
|
Array.from({ length: oracle.total_records }, (_, index) => index),
|
|
);
|
|
records =
|
|
values["saz-selection"] === "baseline"
|
|
? oracle.record_ordinals.map((ordinal) =>
|
|
report.records.find((record) => record.ordinal === ordinal),
|
|
)
|
|
: report.records;
|
|
decoder = report.decoder;
|
|
}
|
|
} else {
|
|
const initial = await call("inspect_web_network_capture", {
|
|
...input,
|
|
detail: "summary",
|
|
});
|
|
const summary = checked(initial, analysisViewResultSchema);
|
|
assert.equal(summary.kind, "summary");
|
|
assert.equal(initial.operation, "inspect_analysis_view");
|
|
assert.deepEqual(initial.parameters, {
|
|
parent_evidence_id: summary.parent_evidence_id,
|
|
view: { kind: "summary" },
|
|
});
|
|
assert.equal(summary.summary.format, "saz");
|
|
assert.equal(summary.parent_operation, "inspect_web_network_capture");
|
|
assert.equal(summary.summary.total_records, oracle.total_records);
|
|
assert.equal(summary.summary.retained_records, oracle.records.length);
|
|
decoder = summary.summary.decoder;
|
|
const source = {
|
|
kind: "retained-evidence",
|
|
evidence_id: summary.parent_evidence_id,
|
|
};
|
|
const page = async (detail, offset, limit) => {
|
|
return readView(source, { kind: "capture", detail, offset, limit });
|
|
};
|
|
const preview = await page("preview", 0, 3);
|
|
assert.deepEqual(
|
|
preview.items.map((record) => record.ordinal),
|
|
oracle.record_ordinals,
|
|
);
|
|
const first = await page("complete", 0, 2),
|
|
next = await page("complete", 2, 2),
|
|
repeated = await page("complete", 0, 2);
|
|
assert.deepEqual(first.items, repeated.items);
|
|
assert.deepEqual(first.coverage, repeated.coverage);
|
|
assert.equal(first.coverage.next_offset, 2);
|
|
assert.equal(first.coverage.exhausted, false);
|
|
assert.equal(next.coverage.exhausted, true);
|
|
assert.equal(next.coverage.next_offset, null);
|
|
records = [...first.items, ...next.items];
|
|
}
|
|
return {
|
|
artifact_sha256: inputSha,
|
|
total_records: oracle.total_records,
|
|
decoder,
|
|
facts: verifySazRecords(records, oracle),
|
|
delivery_observations: observations,
|
|
};
|
|
}
|