Files
4aa51bfe19 fix(reverse): reconcile cleanup ownership and mutation diagnostics (#2799)
* 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>
2026-10-14 04:47:34 +08:00

152 lines
5.1 KiB
TypeScript

import { Client, InMemoryTransport } from "@modelcontextprotocol/client";
import { expect, it, onTestFinished, vi } from "vitest";
import { AdbProvider } from "../../src/adb/AdbProvider.js";
import { parseEvidence } from "../../src/domain/evidence.js";
import { createServer } from "../../src/server/createServer.js";
import { createTestBinarySession } from "../fixtures/binarySession.js";
import {
execFileBytes,
execFileOutput,
} from "../../src/process/ExecFileOutput.js";
import { toolContract } from "../../src/contracts/toolContracts.js";
vi.mock("../../src/process/ExecFileOutput.js", async (importOriginal) => ({
...(await importOriginal<
typeof import("../../src/process/ExecFileOutput.js")
>()),
execFileOutput: vi.fn(),
execFileBytes: vi.fn(),
}));
it.each(["start_adb_app", "start_adb_activity"] as const)(
"%s retains launch evidence through MCP with isolated process mocks",
async (operation) => {
const starting =
"Starting: Intent { act=android.intent.action.MAIN cmp=com.example/.Main }\n";
let stdout = `${starting}Status: ok\nActivity: com.example/.Main\nWaitTime: 315\nComplete\n`;
let stderr = "";
const version =
"Android Debug Bridge version 1.0.41\nVersion 34.0.5-stub\n";
vi.mocked(execFileOutput).mockResolvedValue({
stdout: version,
stderr: "",
stdoutBytes: Buffer.byteLength(version),
stderrBytes: 0,
});
const calls: string[][] = [];
vi.mocked(execFileBytes).mockImplementation(async (_binary, args) => {
calls.push([...args]);
return args.includes("resolve-activity")
? {
stdout: Buffer.from("com.example/.Main\n"),
stderr: Buffer.alloc(0),
}
: { stdout: Buffer.from(stdout), stderr: Buffer.from(stderr) };
});
onTestFinished(() => {
vi.resetAllMocks();
});
const server = createServer(
{
kind: "session",
session: createTestBinarySession(() => {
throw new Error("must not start deep provider");
}),
},
{ adbDeviceAnalysis: new AdbProvider({ environment: {} }) },
);
onTestFinished(() => server.close());
const [clientTransport, serverTransport] =
InMemoryTransport.createLinkedPair();
await server.connect(serverTransport);
const client = new Client({ name: "adb-start-boundary", version: "0.0.0" });
onTestFinished(() => client.close());
await client.connect(clientTransport);
const input =
operation === "start_adb_app"
? { serial: "emulator-5554", package: "com.example" }
: {
serial: "emulator-5554",
action: "android.intent.action.MAIN",
component: "com.example/.Main",
};
const successful = await client.callTool({
name: operation,
arguments: input,
});
expect(successful.isError).not.toBe(true);
const evidence = toolContract(operation).outputSchema.parse(
parseEvidence(
JSON.parse(
(successful.content as { text?: string }[])
.map((part) => part.text ?? "")
.join(""),
),
),
);
expect(evidence.confidence).toBe("observed");
expect(evidence.normalized_result).toMatchObject({
started_activity: "act=android.intent.action.MAIN cmp=com.example/.Main",
reported_activity: "com.example/.Main",
reported_status: "ok",
});
expect(evidence.raw_result).toEqual({ stdout, stderr });
stdout = `${starting}Status: timeout\nActivity: com.example/.Main\nWaitTime: 10004\nComplete\n`;
const timedOut = await client.callTool({
name: operation,
arguments: input,
});
expect(timedOut.isError).toBe(true);
const failure = JSON.parse(
(timedOut.content as { text?: string }[])
.map((part) => part.text ?? "")
.join(""),
);
expect(failure.error).toMatchObject({
code: "unsupported_target",
details: {
captured_output: { stdout, stderr, truncated: false },
partial_observation: {
provider_id: "adb",
operation,
result: {
started_activity:
"act=android.intent.action.MAIN cmp=com.example/.Main",
reported_activity: "com.example/.Main",
reported_status: "timeout",
},
},
},
});
expect(failure).not.toHaveProperty("confidence");
stdout = starting;
stderr = "Error: Activity class does not exist\n";
const refused = await client.callTool({
name: operation,
arguments: input,
});
expect(refused.isError).toBe(true);
expect(
(refused.content as { text?: string }[])
.map((part) => part.text ?? "")
.join(""),
).toContain("Activity class does not exist");
expect(calls.filter((args) => args.includes("start"))).toEqual(
Array.from({ length: 3 }, () => [
"-s",
"emulator-5554",
"shell",
"am",
"start",
"-W",
...(operation === "start_adb_app"
? ["-n", "com.example/.Main"]
: ["-a", "android.intent.action.MAIN", "-n", "com.example/.Main"]),
]),
);
},
);