Files
rea/experiments/analysis-efficiency/command-observation-queries.mjs
T
gensokyo-dev 17f581ff75 perf(reverse): add retained GDB and objdump summaries (#5614)
Add opt-in retained GDB and objdump summaries using the shared analysis-view layer. Preserve default complete Evidence, ordered records, provenance and completion facts.

Validate real Bash disassembly, whole-client context costs, CLI publication and cleanup; retain the original measured cohorts and explicit coverage limitations.

Closes #5584.
2026-10-21 01:20:52 +08:00

213 lines
7.0 KiB
JavaScript

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 { createRequire } from "node:module";
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 { createRetainedQueryCaller } from "./retained-query-calls.mjs";
import { finalizeRetainedQueryReceipt } from "./retained-query-finalization.mjs";
const { values } = parseArgs({
options: {
runtime: { type: "string" },
input: { type: "string" },
oracle: { type: "string" },
output: { type: "string" },
provider: { type: "string" },
symbol: { type: "string" },
detail: { type: "string", default: "complete" },
warm: { type: "boolean", default: false },
},
});
for (const key of ["runtime", "input", "oracle", "output"])
assert.equal(values[key], resolve(values[key]));
assert.ok(["gdb", "objdump"].includes(values.provider));
assert.ok(["complete", "summary"].includes(values.detail));
const oracle = JSON.parse(await readFile(values.oracle, "utf8"));
assert.ok(oracle.symbols.some((row) => row.name === values.symbol));
const inputBytes = await readFile(values.input);
assert.equal(
createHash("sha256").update(inputBytes).digest("hex"),
oracle.artifact_sha256,
);
const require = createRequire(join(values.runtime, "package.json"));
const { Client } = await import(
pathToFileURL(require.resolve("@modelcontextprotocol/client"))
);
const { StdioClientTransport } = await import(
pathToFileURL(require.resolve("@modelcontextprotocol/client/stdio"))
);
await mkdir(values.output, { mode: 0o700 });
const account = await mkdtemp(join(tmpdir(), "rea-command-views-"));
const client = new Client({ name: "command-observation-task", 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",
},
stderr: "pipe",
});
const serverLog = createWriteStream(join(values.output, "server.log"));
const serverLogFinished = finished(serverLog);
serverLogFinished.catch(() => {});
transport.stderr?.pipe(serverLog);
const transcript = [];
const report = {
question:
"Read architecture and the complete byte-annotated disassembly of one selected native function; export complete Evidence. No inferior execution.",
provider: values.provider,
symbol: values.symbol,
detail: values.detail,
warm: values.warm,
calls: [],
observations: [],
};
const call = createRetainedQueryCaller(client, (receipt, event) => {
report.calls.push(receipt);
transcript.push(event);
});
let sessionId;
try {
await client.connect(transport);
const catalog = await client.listTools();
await writeFile(join(values.output, "catalog.json"), JSON.stringify(catalog));
const definitions = new Map(catalog.tools.map((tool) => [tool.name, tool]));
const originalCall = client.callTool.bind(client);
client.callTool = (input, options) =>
originalCall(input, {
...options,
timeout: 60000,
toolDefinition: definitions.get(input.name),
});
const observe = async (name, input, phase = name) => {
const response = await call(name, input, phase);
assert.ok(!response.isError, JSON.stringify(response));
report.observations.push({
name,
phase,
evidence: response.structuredContent,
});
return response.structuredContent;
};
const completeParents = [];
const disassemble = async (phase) => {
const selection = values.detail === "summary" ? { detail: "summary" } : {};
const result =
values.provider === "gdb"
? await observe(
"gdb_console",
{
session_id: sessionId,
command: `disassemble /r ${values.symbol}`,
...selection,
},
phase,
)
: await observe(
"inspect_with_objdump",
{
path: values.input,
operation: "disassemble",
symbol: values.symbol,
...selection,
},
phase,
);
completeParents.push(result);
};
if (values.provider === "gdb") {
const started = await observe("start_gdb_session", {});
sessionId = started.session_id;
for (const command of [
"set auto-load off",
"set debuginfod enabled off",
`file ${values.input}`,
"show architecture",
])
await observe("gdb_console", { session_id: sessionId, command });
} else
await observe("inspect_with_objdump", {
path: values.input,
operation: "file_headers",
});
await disassemble("disassembly:fresh");
if (values.warm) await disassemble("disassembly:repeat");
if (sessionId) {
await observe("close_gdb_session", { session_id: sessionId });
sessionId = undefined;
}
await observe("export_evidence_bundle", {
path: join(values.output, "evidence.json"),
});
const bundle = JSON.parse(
await readFile(join(values.output, "evidence.json"), "utf8"),
);
for (const delivered of completeParents) {
const parent =
values.detail === "complete"
? delivered
: bundle.records.find(
(record) =>
record.evidence_id ===
delivered.normalized_result.parent_evidence_id,
);
assert.ok(parent);
assert.equal(parent.normalized_result.completion_status, "complete");
assert.equal(parent.normalized_result.output_truncated, false);
if (values.provider === "gdb") assert.equal(parent.subject, null);
else assert.equal(parent.subject.digest.sha256, oracle.artifact_sha256);
if (values.detail === "summary") {
const selected = delivered.normalized_result.summary;
const { available_counts: counts, ...facts } = selected;
const { console, target, log, ...records } = parent.normalized_result;
assert.deepEqual(
values.provider === "gdb" ? facts : selected,
values.provider === "gdb" ? records : parent.normalized_result,
);
if (values.provider === "gdb")
assert.equal(counts.console_utf16_units, console.length);
assert.equal(delivered.raw_result, null);
}
}
report.status = "passed";
} catch (error) {
report.status = "failed";
report.failure = String(error?.stack ?? error);
process.exitCode = 1;
} finally {
if (sessionId)
try {
const closed = await call(
"close_gdb_session",
{ session_id: sessionId },
"cleanup:gdb",
);
assert.ok(!closed.isError);
} catch (error) {
report.gdb_cleanup_failure = String(error);
process.exitCode = 1;
}
if (
!(await finalizeRetainedQueryReceipt({
report,
client,
transport,
account,
serverLog,
serverLogFinished,
output: values.output,
transcript,
}))
)
process.exitCode = 1;
}