mirror of
https://github.com/morluto/rea.git
synced 2026-11-09 00:07:18 +00:00
* feat(process): add owned debugger shutdown lifecycle * feat(reverse): add local inspection commands * feat(gdb): add persistent debugger integration * feat(cutter): add Cutter bridge integration * test(reverse): enforce complete integration coverage * fix(process): preserve debugger shutdown ownership * fix(reverse): retain evidence across interrupted commands * fix(gdb): honor captured provider environment * test(process): cover debugger shutdown retries * fix(reverse): retain evidence for interrupted providers * test(process): cover debugger shutdown retries * fix(reverse): retain evidence for interrupted providers * fix(server): snapshot provider environment at creation * fix(reverse): close review gaps with complete coverage * fix(reverse): address inspection review findings * fix(gdb): bound sessions and retain cleanup ownership * fix(ci): require reverse-tools quality lane * fix(process): unref inherited debugger output pipes * fix(reverse): address remaining PR 1960 findings * fix(gdb): address remaining PR 1961 findings * fix(reverse): account for unrestricted provider execution * fix(process): retain debugger ownership until safe shutdown * fix(process): preserve replacement debugger sessions * fix(reverse): preserve admission and output provenance * fix(process): retain exited debugger until output settles * fix(mcp): bound provider admission and debugger cleanup * fix(reverse): preserve failure provenance and classify E2BIG * fix(gdb): preserve startup cleanup and detach safety * fix(process): retain debugger ownership after detach failure * fix(reverse): preserve mutation and failure provenance * fix(gdb): address debugger review findings * fix(reverse): rebind sessions after external mutation * fix(process): cap debugger output after exit * fix(gdb): protect one-shot detach verification * feat(debugger): add reverse tool coverage gate * test(debugger): cover integrated failure paths * fix(gdb): bound and preserve session observations * fix(gdb): address review regressions * style: format merged integration files * fix(reverse): preserve session and output evidence * refactor(gdb): share repeated test and partial result setup * fix(gdb): invalidate TTY proof for Python aliases * fix(reverse): retain failure output byte counts * test(process): synchronize late debugger output * fix(gdb): invalidate TTY proof for wrapped commands * fix(gdb): recognize wit command abbreviation * test(reverse): wait for cancelled descendant readiness * test(reverse): bound descendant cancellation cleanup * style(reverse): format integration tests and adapters * style: format reverse engineering integration files * test(reverse): remove duplicate environment harness * test(gdb): share session startup assertions * fix(gdb): invalidate output proof for command abbreviations * test(reverse): share composition edge case scenarios * fix(ci): recognize verification and mutation tool entries * test(rizin): cover successful fake inferior detach * test(cli): align full output failure envelope * test(cli): isolate reverse command lifecycle service * test(process): share debugger output fixture setup * fix(binary): preserve high-bit Windows signature bytes * style(binary): format Windows signature parser * test(mcp): preserve call coverage in unchanged comparison * fix(ci): include reverse tools Vitest configs in lint cache * fix(mcp): preserve target content on delivery errors * ci: align duplication ceiling with expanded suite * test(reverse): allow signal admission mutants * fix(reverse): bound retained cleanup failures to process owners * fix(test): replace drifting mutation ranges with owned selectors * fix(reverse): admit persistent commands and retain cleanup ownership * fix(cutter): recover timed-out commands from exact receipts * fix(cutter): reject unsupported bridge request kinds * fix(ci): repair client format and shared verification fixtures * fix(native): preserve debugger cleanup ownership and bridge authentication * test(native): retain diagnostics without perfect coverage requirements * chore(licenses): refresh locked dependency inventory and notices * fix(test): exclude transient command locks from mutation sandboxes * fix(gdb): admit only platforms with safe detach verification * fix(cutter): retain bounded completion receipts until acknowledgement * fix(cutter): acknowledge commands rejected before UI dispatch * test(reverse): fail cancellation checks before fixture teardown * test(gdb): clean up the retained broken-stdin fixture owner * docs(test): clarify focused provider verification scope * fix(rizin): retain close cleanup failures * fix(gdb): wait for inferior stop and bound MI buffering * fix(cutter): retain failed receipt acknowledgements * fix(rizin): return retained session identity on rebind failure * fix(gdb): preserve startup cancellation and lossy status * fix(rizin): retain launch provenance and assemble frames once * fix(cutter): recover receipts across callers and bound discovery * docs: describe debugger evidence and bridge recovery * fix(process): keep cleanup incomplete while writers remain Stopping a debugger no longer reports success when inherited output streams stay open, so BinarySession cannot reopen a binary a child is still changing. Concurrent Cutter cleanup retries share one receipt acknowledgement instead of treating a consumed receipt as failure. * fix(debuggers): recover cleanup with captured process identities * fix(analysis): retire sessions after unrestricted commands * fix(cli): preserve completed evidence after cleanup recovery * fix(cutter): bound frame collection and coalesce cleanup * fix(windows): resolve selected provider paths absolutely * fix(gdb): report decoding loss in failed startup evidence * fix(rizin): scope decoding loss to collected command frames * test(mcp): cover snapshot retirement in reverse tools CI --------- Co-authored-by: Daniel Gonçalves Araujo <47118053+dandgabr@users.noreply.github.com> Co-authored-by: REA Maintainers <noreply@github.com> Co-authored-by: OpenAI Codex <codex@users.noreply.github.com> Co-authored-by: Cursor Agent <cursoragent@cursor.com>
261 lines
8.7 KiB
TypeScript
261 lines
8.7 KiB
TypeScript
import { Client, InMemoryTransport } from "@modelcontextprotocol/client";
|
|
import { chmod, writeFile } from "node:fs/promises";
|
|
import { createServer as createNetServer } from "node:net";
|
|
import { createHmac } from "node:crypto";
|
|
import { join } from "node:path";
|
|
import { expect, it, onTestFinished } from "vitest";
|
|
|
|
import {
|
|
createTestBinarySession,
|
|
createCacheProvider,
|
|
} from "../../fixtures/binarySession.js";
|
|
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
|
import { parseEvidence } from "../../../src/domain/evidence.js";
|
|
import { createServer } from "../../../src/server/createServer.js";
|
|
import { silentLogger } from "../../../src/logger.js";
|
|
|
|
const assertUncertainEvidence = async (
|
|
client: Client,
|
|
session: ReturnType<typeof createTestBinarySession>,
|
|
sessionId: string,
|
|
): Promise<void> => {
|
|
const uncertain = await client.callTool({
|
|
name: "cutter_command",
|
|
arguments: {
|
|
session_id: sessionId,
|
|
expected_generation: 3,
|
|
command: "Ps /tmp/uncertain.rzdb",
|
|
},
|
|
});
|
|
expect(uncertain.isError).toBe(true);
|
|
const uncertainText = uncertain.content
|
|
.filter(
|
|
(block): block is { type: "text"; text: string } => block.type === "text",
|
|
)
|
|
.map((block) => block.text)
|
|
.join("\n");
|
|
const uncertainError = JSON.parse(uncertainText) as {
|
|
error: { details: { partial_observation: { evidence_id: string } } };
|
|
};
|
|
const uncertainEvidence = session.evidenceById(
|
|
uncertainError.error.details.partial_observation.evidence_id,
|
|
);
|
|
expect(uncertainEvidence).toBeDefined();
|
|
if (uncertainEvidence === undefined)
|
|
throw new Error("partial Evidence missing");
|
|
expect(uncertainEvidence.normalized_result).toMatchObject({
|
|
execution_state: "unknown",
|
|
error: "transport-response-missing",
|
|
message: expect.stringContaining("do not retry automatically"),
|
|
document_generation: 3,
|
|
});
|
|
expect(uncertainEvidence.limitations).toContain(
|
|
"Command completion or its output could not be confirmed; " +
|
|
"do not retry automatically because the command may have produced " +
|
|
"partial or persistent effects.",
|
|
);
|
|
};
|
|
|
|
const assertNotStartedEvidenceAndAdmission = async (
|
|
client: Client,
|
|
sessionId: string,
|
|
): Promise<void> => {
|
|
const rejected = await client.callTool({
|
|
name: "cutter_command",
|
|
arguments: {
|
|
session_id: sessionId,
|
|
expected_generation: 3,
|
|
command: "Ps /tmp/not-started.rzdb",
|
|
},
|
|
});
|
|
expect(rejected.isError, JSON.stringify(rejected)).not.toBe(true);
|
|
expect(
|
|
parseEvidence(rejected.structuredContent).normalized_result,
|
|
).toMatchObject({
|
|
execution_state: "not_started",
|
|
error: "session-poisoned-after-ui-timeout",
|
|
});
|
|
|
|
const admitted = await client.callTool({
|
|
name: "cutter_command",
|
|
arguments: {
|
|
session_id: sessionId,
|
|
expected_generation: 3,
|
|
command: "iI",
|
|
},
|
|
});
|
|
expect(admitted.isError).not.toBe(true);
|
|
};
|
|
|
|
const createMcpBridge = async (
|
|
directory: string,
|
|
sessionId: string,
|
|
token: string,
|
|
): Promise<ReturnType<typeof createNetServer>> => {
|
|
let connectionOrdinal = 0;
|
|
const bridge = createNetServer((connection) => {
|
|
const ordinal = ++connectionOrdinal;
|
|
let payload = "";
|
|
let clientNonce = "";
|
|
let serverNonce = "";
|
|
connection.setEncoding("utf8");
|
|
connection.on("data", (chunk: string) => {
|
|
payload += chunk;
|
|
const newline = payload.indexOf("\n");
|
|
if (newline < 0) return;
|
|
const frame = JSON.parse(payload.slice(0, newline)) as Record<
|
|
string,
|
|
unknown
|
|
>;
|
|
payload = payload.slice(newline + 1);
|
|
if (frame.kind === "rea-auth-v2") {
|
|
clientNonce = String(frame.nonce);
|
|
serverNonce = `${ordinal.toString(16).padStart(16, "0")}${"c".repeat(48)}`;
|
|
const proof = createHmac("sha256", token)
|
|
.update(
|
|
`rea-cutter-server-v2:${sessionId}:${clientNonce}:${serverNonce}`,
|
|
)
|
|
.digest("hex");
|
|
connection.write(
|
|
`${JSON.stringify({ session_id: sessionId, nonce: serverNonce, proof })}\n`,
|
|
);
|
|
return;
|
|
}
|
|
const requestBytes = String(frame.request);
|
|
const request = JSON.parse(requestBytes) as Record<string, unknown>;
|
|
const expected = createHmac("sha256", token)
|
|
.update(
|
|
`rea-cutter-client-v2:${sessionId}:${clientNonce}:${serverNonce}:${requestBytes}`,
|
|
)
|
|
.digest("hex");
|
|
if (frame.proof !== expected) {
|
|
connection.destroy();
|
|
return;
|
|
}
|
|
if (request.command === "Ps /tmp/uncertain.rzdb") {
|
|
connection.destroy();
|
|
return;
|
|
}
|
|
const notStarted = request.command === "Ps /tmp/not-started.rzdb";
|
|
const status = request.kind === "status";
|
|
const response = JSON.stringify(
|
|
request.kind === "ack"
|
|
? { ok: true, acknowledged: false }
|
|
: {
|
|
ok: !notStarted,
|
|
...(notStarted
|
|
? {
|
|
execution_state: "not_started",
|
|
error: "session-poisoned-after-ui-timeout",
|
|
}
|
|
: {}),
|
|
session_id: request.session_id,
|
|
output: status ? undefined : "synthetic Cutter command output",
|
|
current_file: "/fixtures/sample.bin",
|
|
document_generation: 3,
|
|
...(status
|
|
? {
|
|
completed_connection: (ordinal - 1)
|
|
.toString(16)
|
|
.padStart(16, "0"),
|
|
completed_commands: [],
|
|
}
|
|
: {}),
|
|
cutter_version: "Cutter fixture version",
|
|
identity_status: "partial",
|
|
},
|
|
);
|
|
const responseProof = createHmac("sha256", token)
|
|
.update(
|
|
`rea-cutter-response-v2:${sessionId}:${clientNonce}:${serverNonce}:${response}`,
|
|
)
|
|
.digest("hex");
|
|
connection.end(`${JSON.stringify({ response, proof: responseProof })}\n`);
|
|
});
|
|
});
|
|
await new Promise<void>((resolve) => bridge.listen(0, "127.0.0.1", resolve));
|
|
const address = bridge.address();
|
|
if (address === null || typeof address === "string")
|
|
throw new Error("Expected an ephemeral IPv4 Cutter test bridge.");
|
|
await writeFile(
|
|
join(directory, `cutter-${process.pid}-${sessionId}.json`),
|
|
JSON.stringify({
|
|
session_id: sessionId,
|
|
pid: process.pid,
|
|
host: "127.0.0.1",
|
|
port: address.port,
|
|
token,
|
|
document_generation: 2,
|
|
current_file: null,
|
|
cutter_version: "Cutter fixture version",
|
|
identity_status: "partial",
|
|
}),
|
|
{ mode: 0o600 },
|
|
);
|
|
return bridge;
|
|
};
|
|
|
|
it("preserves live Cutter command Evidence and parity through the MCP boundary", async () => {
|
|
const directory = await createTestTempDirectory("rea-cutter-mcp-");
|
|
if (process.platform !== "win32") await chmod(directory, 0o700);
|
|
const sessionId = "27d3e3f1-f1e5-49ae-91ec-95af1f343a5a";
|
|
const token = "synthetic-cutter-bridge-token-for-mcp-test";
|
|
const bridge = await createMcpBridge(directory, sessionId, token);
|
|
onTestFinished(
|
|
async () => new Promise<void>((resolve) => bridge.close(() => resolve())),
|
|
);
|
|
const session = createTestBinarySession(createCacheProvider([]));
|
|
const server = createServer(
|
|
{ kind: "session", session },
|
|
{
|
|
logger: silentLogger,
|
|
providerEnvironment: { ...process.env, REA_CUTTER_BRIDGE_DIR: directory },
|
|
},
|
|
);
|
|
const client = new Client({ name: "cutter-mcp-boundary", version: "1" });
|
|
onTestFinished(async () => {
|
|
await client.close();
|
|
await server.close();
|
|
await session.close();
|
|
});
|
|
const [clientTransport, serverTransport] =
|
|
InMemoryTransport.createLinkedPair();
|
|
await server.connect(serverTransport);
|
|
await client.connect(clientTransport);
|
|
|
|
const discovery = await client.callTool({
|
|
name: "list_cutter_sessions",
|
|
arguments: {},
|
|
});
|
|
expect(discovery.isError).not.toBe(true);
|
|
expect(discovery.structuredContent).toMatchObject({
|
|
discovery_status: "sessions_found",
|
|
sessions: [{ session_id: sessionId, document_generation: 3 }],
|
|
});
|
|
|
|
const command = await client.callTool({
|
|
name: "cutter_command",
|
|
arguments: {
|
|
session_id: sessionId,
|
|
expected_generation: 3,
|
|
command: "iI",
|
|
},
|
|
});
|
|
expect(command.isError).not.toBe(true);
|
|
const evidence = parseEvidence(command.structuredContent);
|
|
expect(evidence).toMatchObject({
|
|
operation: "cutter_command",
|
|
provider: { id: "cutter.python-plugin" },
|
|
normalized_result: {
|
|
command: "iI",
|
|
output: "synthetic Cutter command output",
|
|
document_generation: 3,
|
|
cutter_version: "Cutter fixture version",
|
|
},
|
|
});
|
|
expect(session.evidenceById(evidence.evidence_id)).toEqual(evidence);
|
|
|
|
await assertNotStartedEvidenceAndAdmission(client, sessionId);
|
|
await assertUncertainEvidence(client, session, sessionId);
|
|
});
|