Files
reverse-engineering-anything/tests/boundary/mcp/reverseEngineeringPartialMcp.test.ts
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

508 lines
16 KiB
TypeScript

import pino from "pino";
import { mkdtemp, rm, symlink, writeFile } from "node:fs/promises";
import { tmpdir } from "node:os";
import { dirname, join } from "node:path";
import { expect, it, vi } from "vitest";
import { TestReverseEngineeringService as ReverseEngineeringService } from "../../support/reverseEngineeringService.js";
import { AnalysisInputError } from "../../../src/domain/analysisErrorCore.js";
import {
createBinarySessionTargets,
createCacheProvider,
createTestBinarySession,
} from "../../fixtures/binarySession.js";
import type { AnalysisOperationPort } from "../../../src/application/AnalysisProvider.js";
import { EvidenceIntegrityError } from "../../../src/domain/evidenceErrors.js";
import { err, ok } from "../../../src/domain/result.js";
import type { WithAdmittedAnalysis } from "../../../src/server/analysisAdmission.js";
import { createToolResultDelivery } from "../../../src/server/toolResult.js";
import { registerReverseEngineeringTools } from "../../../src/server/registerReverseEngineeringTools.js";
import {
createReverseEngineeringMcpHarness,
invokeWithLiveSignal,
} from "../../support/reverseEngineeringMcpHarness.js";
const createTimedOutRizinService = (): ReverseEngineeringService =>
new ReverseEngineeringService({
run: async () => {
throw Object.assign(new Error("timed out"), {
stdout: "partial provider output",
stderr: "",
code: "ETIMEDOUT",
signal: null,
killed: true,
});
},
});
it("records partial Evidence and references it in the original MCP error", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const service = createTimedOutRizinService();
const recordEvidence = vi.fn(() => ok("added" as const));
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
recordEvidence,
);
const invoke = handler("execute_rizin_command");
const response = (await invokeWithLiveSignal(invoke, {
path: "package.json",
command: "iI",
})) as {
readonly isError?: boolean;
readonly structuredContent?: {
readonly error?: {
readonly details?: Readonly<Record<string, unknown>>;
};
};
};
expect(response.isError).toBe(true);
expect(recordEvidence).toHaveBeenCalledTimes(1);
expect(response.structuredContent?.error?.details).toMatchObject({
partial_observation: {
kind: "retained-evidence",
evidence_id: expect.any(String),
},
});
});
it("admits Rizin mutation after invalidating before dispatch", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const events: string[] = [];
const service = new ReverseEngineeringService({
run: async () => {
events.push("dispatch");
return { stdout: "rizin output", stderr: "" };
},
});
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
undefined,
() => events.push("invalidate"),
async (_path, _signal, operation) => {
events.push("admit");
return ok(await operation());
},
);
const invoke = handler("execute_rizin_command");
await invoke(
{ path: "package.json", command: "iI" },
{ mcpReq: { signal: new AbortController().signal } },
);
expect(events).toEqual(["admit", "invalidate", "dispatch"]);
});
it("invalidates the snapshot in the legacy Rizin admission path", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const invalidateSnapshot = vi.fn();
const service = new ReverseEngineeringService({
run: async () => ({ stdout: "rizin output", stderr: "" }),
});
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
undefined,
invalidateSnapshot,
);
const invoke = handler("execute_rizin_command");
const response = (await invokeWithLiveSignal(invoke, {
path: "package.json",
command: "iI",
})) as { readonly isError?: boolean };
expect(response.isError).not.toBe(true);
expect(invalidateSnapshot).toHaveBeenCalledOnce();
});
it("skips snapshot invalidation for malformed Rizin input", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const invalidateSnapshot = vi.fn();
const executeRizinCommand = vi.fn(async () =>
err(new AnalysisInputError("execute_rizin_command")),
);
const service = {
executeRizinCommand,
} as unknown as ReverseEngineeringService;
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
undefined,
invalidateSnapshot,
);
const invoke = handler("execute_rizin_command");
const response = (await invokeWithLiveSignal(invoke, {
path: "package.json",
})) as { readonly isError?: boolean };
expect(response.isError).toBe(true);
expect(executeRizinCommand).toHaveBeenCalledOnce();
expect(invalidateSnapshot).not.toHaveBeenCalled();
});
it("delivers failed Rizin execution after external admission", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const service = new ReverseEngineeringService({
run: async () => {
throw new Error("Rizin command failed");
},
});
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
undefined,
undefined,
async (_path, _signal, operation) => ok(await operation()),
);
const invoke = handler("execute_rizin_command");
const response = (await invokeWithLiveSignal(invoke, {
path: "package.json",
command: "iI",
})) as { readonly isError?: boolean };
expect(response.isError).toBe(true);
});
it("preserves the Rizin operation error when analysis retirement also fails", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const service = {
retryCleanup: async () => ok(null),
executeRizinCommand: async () =>
err(new AnalysisInputError("execute_rizin_command")),
} as unknown as ReverseEngineeringService;
const observedOperationResult = vi.fn();
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
undefined,
undefined,
async (_path, _signal, operation, rebindFailure) => {
const result = await operation();
observedOperationResult(result);
return err(rebindFailure(result, new AnalysisInputError("rebind")));
},
);
const invoke = handler("execute_rizin_command");
const response = (await invoke(
{ path: "package.json", command: "iI" },
{ mcpReq: { signal: new AbortController().signal } },
)) as {
readonly isError?: boolean;
readonly structuredContent?: {
readonly error?: {
readonly code?: string;
readonly details?: { readonly reason?: string };
};
};
};
expect(response.isError).toBe(true);
expect(observedOperationResult).toHaveBeenCalledWith(
expect.objectContaining({ ok: false }),
);
expect(response.structuredContent?.error).toMatchObject({
code: "invalid_request",
});
});
it.each(["success", "timeout"])(
"retains %s output and requires reopening after a symlink command",
async (outcome) => {
const [target] = await createBinarySessionTargets();
const alias = join(dirname(target), "active-target-alias.hop");
await symlink(target, alias);
const session = createTestBinarySession(createCacheProvider([]));
expect((await session.open(target)).ok).toBe(true);
expect(session.activeTarget()?.path).toBe(target);
const originalDigest = session.activeTarget()?.sha256;
const { server, handler } = createReverseEngineeringMcpHarness();
const service = new ReverseEngineeringService({
run: async () => {
await writeFile(alias, "changed by Rizin");
if (outcome === "timeout")
throw Object.assign(new Error("timed out"), {
stdout: "partial analysis output",
stderr: "timeout diagnostics",
code: "ETIMEDOUT",
signal: null,
killed: true,
});
return { stdout: "partial analysis output", stderr: "" };
},
});
const recordEvidence = vi.fn(() => ok("added" as const));
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
recordEvidence,
undefined,
() => session.invalidateSnapshotForExternalMutation(),
(path, signal, operation, rebindFailure) =>
session.withAdmittedExternalMutation(
path,
signal,
operation,
rebindFailure,
),
);
const invoke = handler("execute_rizin_command");
const response = (await invoke(
{ path: alias, command: "wx 00 @ 0" },
{ mcpReq: { signal: new AbortController().signal } },
)) as {
readonly isError?: boolean;
readonly structuredContent?: {
readonly error?: {
readonly code?: string;
readonly details?: Readonly<Record<string, unknown>>;
};
};
};
expect(response.isError ?? false).toBe(outcome === "timeout");
if (outcome === "timeout") {
expect(response.structuredContent?.error?.code).toBe("provider_timeout");
expect(response.structuredContent?.error?.details).toMatchObject({
captured_output: {
stdout: "partial analysis output",
stderr: "timeout diagnostics",
},
});
expect(response.structuredContent?.error?.details).toMatchObject({
partial_observation: {
kind: "retained-evidence",
evidence_id: expect.any(String),
},
});
}
expect(recordEvidence).toHaveBeenCalledTimes(1);
expect(session.activeTarget()).toBeUndefined();
expect((await session.execute("address_name", {})).ok).toBe(false);
expect((await session.open(target)).ok).toBe(true);
expect(session.activeTarget()?.sha256).not.toBe(originalDigest);
await session.close();
await rm(dirname(target), { recursive: true, force: true });
},
);
it("preserves a partial MCP error without claiming failed Evidence retention", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const service = createTimedOutRizinService();
const recordEvidence = vi.fn((_evidence: unknown) =>
err(new EvidenceIntegrityError("retention failed")),
);
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
recordEvidence,
);
const invoke = handler("execute_rizin_command");
const response = (await invokeWithLiveSignal(invoke, {
path: "package.json",
command: "iI",
})) as {
readonly isError?: boolean;
readonly structuredContent?: {
readonly error?: {
readonly details?: Readonly<Record<string, unknown>>;
};
};
};
expect(response.isError).toBe(true);
expect(response.structuredContent?.error?.details).toMatchObject({
partial_observation: expect.objectContaining({
operation: "execute_rizin_command",
}),
});
expect(
JSON.stringify(response.structuredContent?.error?.details),
).not.toContain("retained-evidence");
});
it("delivers pathless objdump capability Evidence and input errors through its named tool", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const service = new ReverseEngineeringService({
run: async () => ({ stdout: "objdump output", stderr: "" }),
});
const delivery = createToolResultDelivery(2 * 1024 * 1024);
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
delivery,
);
const context = { mcpReq: { signal: new AbortController().signal } };
const objdump = handler("inspect_with_objdump");
const rizin = handler("execute_rizin_command");
const success = (await objdump(
{ path: "package.json", operation: "file_headers" },
context,
)) as { readonly isError?: boolean };
const architectures = (await objdump(
{ operation: "architectures" },
context,
)) as {
readonly isError?: boolean;
};
const objdumpFailure = (await objdump({}, context)) as {
readonly isError?: boolean;
};
const failure = (await rizin({}, context)) as {
readonly isError?: boolean;
readonly structuredContent?: {
readonly error?: { readonly code?: string };
};
};
const cancelled = new AbortController();
cancelled.abort();
const cancelledContext = { mcpReq: { signal: cancelled.signal } };
const cancelledObjdump = (await objdump(
{ path: "package.json", operation: "file_headers" },
cancelledContext,
)) as { readonly isError?: boolean };
const cancelledRizin = (await rizin(
{ path: "package.json", command: "iI" },
cancelledContext,
)) as { readonly isError?: boolean };
expect(success.isError).not.toBe(true);
expect(architectures.isError).not.toBe(true);
expect(objdumpFailure.isError).toBe(true);
expect(failure.isError).toBe(true);
expect(cancelledObjdump.isError).toBe(true);
expect(cancelledRizin.isError).toBe(true);
});
it("does not treat a malformed partial observation as retained Evidence", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const invalidError = Object.assign(
new AnalysisInputError("execute_rizin_command"),
{ partialObservation: { evidence_id: 42 } },
);
const service = {
inspectWithObjdump: async () => err(invalidError),
executeRizinCommand: async () => err(invalidError),
} as unknown as ReverseEngineeringService;
const recordEvidence = vi.fn(() => ok("added" as const));
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
recordEvidence,
);
const invoke = handler("execute_rizin_command");
const response = (await invoke(
{ path: "package.json", command: "iI" },
{ mcpReq: { signal: new AbortController().signal } },
)) as { readonly isError?: boolean };
expect(response.isError).toBe(true);
expect(recordEvidence).not.toHaveBeenCalled();
});
it("keeps provider execution and Evidence recording inside analysis admission", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const events: string[] = [];
const service = new ReverseEngineeringService({
run: async () => {
events.push("provider");
return { stdout: "objdump output", stderr: "" };
},
});
const recordEvidence = vi.fn(() => {
events.push("record");
return ok("added" as const);
});
const admission: WithAdmittedAnalysis = async (_name, _signal, operation) => {
events.push("admission-start");
const result = await operation({} as AnalysisOperationPort);
events.push("admission-end");
return ok(result);
};
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
recordEvidence,
admission,
);
const invoke = handler("inspect_with_objdump");
await invoke(
{ path: "package.json", operation: "file_headers" },
{ mcpReq: { signal: new AbortController().signal } },
);
expect(events).toEqual([
"admission-start",
"provider",
"record",
"admission-end",
]);
});
it("returns admission failures without invoking a reverse-engineering provider", async () => {
const { server, handler } = createReverseEngineeringMcpHarness();
const inspectWithObjdump = vi.fn();
const service = {
inspectWithObjdump,
executeRizinCommand: vi.fn(),
} as unknown as ReverseEngineeringService;
const admission: WithAdmittedAnalysis = async () =>
err(new AnalysisInputError("inspect_with_objdump"));
registerReverseEngineeringTools(
server,
service,
pino({ enabled: false }),
createToolResultDelivery(2 * 1024 * 1024),
undefined,
admission,
);
const invoke = handler("inspect_with_objdump");
const response = (await invoke(
{ path: "package.json", operation: "file_headers" },
{ mcpReq: { signal: new AbortController().signal } },
)) as { readonly isError?: boolean };
expect(response.isError).toBe(true);
expect(inspectWithObjdump).not.toHaveBeenCalled();
});