Validate omitted GGUF strings without materializing discarded text while preserving full UTF-8 checks and retained Evidence. Record real-model costs and workflow coverage; preserve failed experiment receipts through cleanup. Fixes #5774.
244 lines
7.7 KiB
JavaScript
244 lines
7.7 KiB
JavaScript
/** Equivalent model tasks; inputs, expected reports and raw receipts stay outside Git. */
|
|
import assert from "node:assert/strict";
|
|
import { createHash } from "node:crypto";
|
|
import { createWriteStream } from "node:fs";
|
|
import { mkdir, mkdtemp, readFile, writeFile } from "node:fs/promises";
|
|
import { tmpdir } from "node:os";
|
|
import { join, resolve } from "node:path";
|
|
import { finished } from "node:stream/promises";
|
|
import { pathToFileURL } from "node:url";
|
|
import { parseArgs } from "node:util";
|
|
import { Client } from "@modelcontextprotocol/client";
|
|
import { StdioClientTransport } from "@modelcontextprotocol/client/stdio";
|
|
import { createRetainedQueryCaller } from "./retained-query-calls.mjs";
|
|
import {
|
|
finalizeRetainedQueryReceipt,
|
|
publishRetainedQueryReceipt,
|
|
} from "./retained-query-finalization.mjs";
|
|
|
|
const { values } = parseArgs({
|
|
options: {
|
|
...Object.fromEntries(
|
|
["runtime", "artifact", "expected", "output"].map((name) => [
|
|
name,
|
|
{ type: "string" },
|
|
]),
|
|
),
|
|
phase: { type: "boolean", default: false },
|
|
},
|
|
});
|
|
for (const name of ["runtime", "artifact", "expected", "output"])
|
|
assert.ok(values[name] && values[name] === resolve(values[name]), name);
|
|
const hash = (value) => createHash("sha256").update(value).digest("hex");
|
|
const expected = JSON.parse(await readFile(values.expected, "utf8"));
|
|
assert.equal(expected.artifact.path, values.artifact);
|
|
await mkdir(values.output, { mode: 0o700 });
|
|
const report = {
|
|
artifact_sha256: hash(await readFile(values.artifact)),
|
|
normalized_sha256: hash(JSON.stringify(expected)),
|
|
calls: [],
|
|
answers: [],
|
|
};
|
|
|
|
if (values.phase) {
|
|
const { ModelArtifactProvider } = await import(
|
|
pathToFileURL(join(values.runtime, "dist/model/ModelArtifactProvider.js"))
|
|
);
|
|
const provider = new ModelArtifactProvider();
|
|
try {
|
|
for (let index = 0; index < 7; index++) {
|
|
const sample = {
|
|
phase: index === 0 ? "fresh" : "repeat",
|
|
is_error: true,
|
|
};
|
|
const start = performance.now();
|
|
try {
|
|
const result = await provider.inspect({
|
|
path: values.artifact,
|
|
hash: "header",
|
|
});
|
|
sample.elapsed_ms = performance.now() - start;
|
|
assert.ok(result.ok, JSON.stringify(result));
|
|
assert.deepEqual(result.value, expected);
|
|
sample.is_error = false;
|
|
} catch (cause) {
|
|
sample.elapsed_ms ??= performance.now() - start;
|
|
sample.failure = String(cause?.stack ?? cause);
|
|
throw cause;
|
|
} finally {
|
|
report.calls.push(sample);
|
|
}
|
|
}
|
|
report.status = "passed";
|
|
} catch (cause) {
|
|
report.status = "failed";
|
|
report.failure = String(cause?.stack ?? cause);
|
|
process.exitCode = 1;
|
|
} finally {
|
|
report.cleanup_failures = [];
|
|
try {
|
|
await provider.close();
|
|
} catch (cause) {
|
|
report.cleanup_failures.push(`provider: ${String(cause)}`);
|
|
report.status = "failed";
|
|
}
|
|
if (!(await publishRetainedQueryReceipt({ report, output: values.output })))
|
|
process.exitCode = 1;
|
|
}
|
|
} else {
|
|
await runMcpTask();
|
|
}
|
|
|
|
async function runMcpTask() {
|
|
const account = await mkdtemp(join(tmpdir(), "rea-model-utf8-"));
|
|
const client = new Client({ name: "model-utf8-validation", version: "1" });
|
|
const transport = new StdioClientTransport({
|
|
command: process.execPath,
|
|
args: [join(values.runtime, "scripts/rea.mjs"), "mcp"],
|
|
env: {
|
|
HOME: account,
|
|
PATH: process.env.PATH,
|
|
NODE_OPTIONS: "--max-old-space-size=2048",
|
|
UV_THREADPOOL_SIZE: "1",
|
|
REA_LOG_LEVEL: "silent",
|
|
TMPDIR: account,
|
|
},
|
|
stderr: "pipe",
|
|
});
|
|
const serverLog = createWriteStream(join(values.output, "server.log"));
|
|
const serverLogFinished = finished(serverLog);
|
|
serverLogFinished.catch(() => {});
|
|
transport.stderr?.pipe(serverLog);
|
|
const transcript = [];
|
|
const call = createRetainedQueryCaller(client, (receipt, event) => {
|
|
report.calls.push(receipt);
|
|
transcript.push(event);
|
|
});
|
|
const observe = async (name, input, phase) => {
|
|
const reply = await call(name, input, phase);
|
|
assert.notEqual(reply.isError, true, JSON.stringify(reply));
|
|
assert.ok(reply.structuredContent);
|
|
return reply.structuredContent;
|
|
};
|
|
try {
|
|
await client.connect(transport);
|
|
const catalog = await client.listTools();
|
|
assert.equal(catalog.nextCursor, undefined);
|
|
await writeFile(
|
|
join(values.output, "catalog.json"),
|
|
JSON.stringify(catalog),
|
|
);
|
|
report.catalog_sha256 = hash(JSON.stringify(catalog));
|
|
report.catalog_tools = catalog.tools.length;
|
|
const definitions = new Map(catalog.tools.map((tool) => [tool.name, tool]));
|
|
const originalCall = client.callTool.bind(client);
|
|
client.callTool = (input, options) =>
|
|
originalCall(input, {
|
|
...options,
|
|
toolDefinition: definitions.get(input.name),
|
|
});
|
|
const keys = [
|
|
...new Set(expected.metadata.slice(0, 2).map((row) => row.key)),
|
|
];
|
|
const names = expected.tensors.slice(0, 2).map((row) => row.name);
|
|
const fields = [
|
|
"key",
|
|
"type",
|
|
"value",
|
|
"element_count",
|
|
"preview_complete",
|
|
];
|
|
const tensorFields = [
|
|
"name",
|
|
"type",
|
|
"shape",
|
|
"file_offset",
|
|
"byte_length",
|
|
];
|
|
const select = (rows, selectedFields) =>
|
|
rows.map((row) =>
|
|
Object.fromEntries(
|
|
["index", ...selectedFields].map((key) => [key, row[key]]),
|
|
),
|
|
);
|
|
const observations = [];
|
|
for (const phase of ["fresh", "repeat"]) {
|
|
const metadata = await observe(
|
|
"inspect_model_artifact",
|
|
{
|
|
path: values.artifact,
|
|
view: { collection: "metadata", keys, fields },
|
|
},
|
|
phase,
|
|
);
|
|
const parentId = metadata.normalized_result.parent_evidence_id;
|
|
assert.equal(typeof parentId, "string");
|
|
assert.deepEqual(
|
|
metadata.normalized_result.items,
|
|
select(
|
|
expected.metadata.filter((row) => keys.includes(row.key)),
|
|
fields,
|
|
),
|
|
);
|
|
const tensors = await observe(
|
|
"inspect_analysis_view",
|
|
{
|
|
source: { kind: "retained-evidence", evidence_id: parentId },
|
|
view: {
|
|
kind: "model-artifact",
|
|
collection: "tensors",
|
|
names,
|
|
fields: tensorFields,
|
|
},
|
|
},
|
|
`${phase}:tensors`,
|
|
);
|
|
assert.equal(tensors.normalized_result.parent_evidence_id, parentId);
|
|
assert.deepEqual(
|
|
tensors.normalized_result.items,
|
|
select(expected.tensors.slice(0, 2), tensorFields),
|
|
);
|
|
observations.push(parentId);
|
|
report.answers.push({
|
|
parent_evidence_id: parentId,
|
|
metadata: metadata.normalized_result.items,
|
|
tensors: tensors.normalized_result.items,
|
|
});
|
|
}
|
|
await observe(
|
|
"export_evidence_bundle",
|
|
{ path: join(values.output, "evidence.json") },
|
|
"export",
|
|
);
|
|
const bundle = JSON.parse(
|
|
await readFile(join(values.output, "evidence.json"), "utf8"),
|
|
);
|
|
for (const id of observations) {
|
|
const parent = bundle.records.find((record) => record.evidence_id === id);
|
|
assert.ok(parent);
|
|
assert.deepEqual(parent.normalized_result, expected);
|
|
}
|
|
assert.deepEqual(report.answers[0], report.answers[1]);
|
|
assert.equal(hash(await readFile(values.artifact)), report.artifact_sha256);
|
|
report.status = "passed";
|
|
} catch (cause) {
|
|
report.status = "failed";
|
|
report.failure = String(cause?.stack ?? cause);
|
|
process.exitCode = 1;
|
|
} finally {
|
|
if (
|
|
!(await finalizeRetainedQueryReceipt({
|
|
report,
|
|
client,
|
|
transport,
|
|
account,
|
|
serverLog,
|
|
serverLogFinished,
|
|
output: values.output,
|
|
transcript,
|
|
}))
|
|
)
|
|
process.exitCode = 1;
|
|
}
|
|
}
|