Files
rea/tests/support/ownedRizinCommandEvidenceTests.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

205 lines
6.1 KiB
TypeScript

import { rm } from "node:fs/promises";
import { expect, it, vi } from "vitest";
import { OwnedCommandFailure } from "../../src/process/OwnedCommand.js";
import { TestReverseEngineeringService } from "./reverseEngineeringService.js";
import {
createArtifact,
providerSnapshot,
} from "./reverseEngineeringCompositionFixtures.js";
const registerOwnedRizinCommandOutcomeTests = (options: {
readonly sweepTokenOwnedProcesses: boolean;
}): void => {
it.each([
["normal exit", providerSnapshot(), "complete", 0, false],
[
"non-zero exit",
providerSnapshot({ exitCode: 7, diagnosticTruncated: true }),
"complete",
7,
true,
],
[
"signal termination",
providerSnapshot({
exitCode: null,
signal: "SIGSEGV",
diagnosticTruncated: true,
}),
"unknown",
null,
true,
],
[
"signal termination with a numeric exit snapshot",
providerSnapshot({ exitCode: 7, signal: "SIGSEGV" }),
"unknown",
null,
false,
],
[
"signal termination without truncation",
providerSnapshot({ exitCode: null, signal: "SIGTERM" }),
"unknown",
null,
false,
],
[
"unknown exit status",
providerSnapshot({ exitCode: null }),
"unknown",
null,
false,
],
] as const)(
"maps an owned command %s into provider Evidence",
async (_name, snapshot, completion, exitCode, outputTruncated) => {
const { directory, path } = await createArtifact();
const runOwned = vi.fn(async () => snapshot);
const service = new TestReverseEngineeringService({
runOwned,
environment: { REA_RIZIN_COMMAND: "rizin-test" },
});
try {
const result = await service.executeRizinCommand({
path,
command: "iI",
});
expect(runOwned).toHaveBeenCalledOnce();
expect(runOwned).toHaveBeenCalledWith(
expect.objectContaining({
command: "rizin-test",
arguments: expect.arrayContaining(["-q", "-c", "iI"]),
expectedCommand: null,
env: expect.objectContaining({ REA_RIZIN_COMMAND: "rizin-test" }),
hostEnvironment: {},
...(options.sweepTokenOwnedProcesses
? { sweepTokenOwnedProcesses: true }
: {}),
}),
{
timeoutMs: 120_000,
diagnosticBytes: 16 * 1024 * 1024,
acceptNonZeroExit: true,
},
{ signal: expect.any(AbortSignal) },
);
expect(result).toMatchObject({
ok: true,
value: {
raw_result: {
stdout: "captured owned output",
completion_status: completion,
exit_code: exitCode,
output_truncated: outputTruncated,
},
},
});
if (!result.ok) throw new Error("Expected provider Evidence");
expect(result.value.parameters).toMatchObject({
command: "iI",
provider_executable: "rizin-test",
command_arguments: expect.arrayContaining(["-q", "-c", "iI"]),
});
expect(result.value.locations).toContainEqual({
kind: "artifact-path",
path,
});
} finally {
await rm(directory, { recursive: true, force: true });
}
},
);
};
const registerOwnedRizinCommandFailureTests = (): void => {
it.each([
["cancelled", "AnalysisCancelledError", "ABORT_ERR"],
["timeout", "AnalysisTimeoutError", "ETIMEDOUT"],
["output-limit", "evidence", "ERR_CHILD_PROCESS_STDIO_MAXBUFFER"],
["process", "evidence", 7],
] as const)(
"maps an owned command %s failure while retaining its snapshot",
async (reason, expected, mappedCode) => {
const { directory, path } = await createArtifact();
const snapshot = providerSnapshot({
...(reason === "process" ? { exitCode: 7 } : {}),
...(reason === "output-limit"
? {}
: reason === "cancelled"
? {}
: { diagnosticTruncated: true }),
});
const service = new TestReverseEngineeringService({
runOwned: async () => {
throw new OwnedCommandFailure(
reason,
"owned command failed",
snapshot,
reason === "timeout" ? "cleanup pending" : null,
undefined,
reason === "timeout" ? ["run-id", "pid:7"] : [],
);
},
});
try {
const result = await service.executeRizinCommand({
path,
command: "iI",
});
if (expected === "evidence") {
expect(result).toMatchObject({
ok: true,
value: {
raw_result: {
stdout: "captured owned output",
exit_code: mappedCode === 7 ? 7 : null,
completion_status:
reason === "output-limit" ? "unknown" : "complete",
output_truncated: true,
},
},
});
} else {
expect(result).toMatchObject({
ok: false,
error: {
_tag: expected,
partialObservation: {
raw_result: {
stdout: "captured owned output",
exit_code: null,
completion_status: "unknown",
output_truncated: reason !== "cancelled",
},
},
...(reason === "timeout"
? {
cleanup: {
reason: "cleanup pending",
resources: ["run-id", "pid:7"],
},
}
: {}),
},
});
if (result.ok) throw new Error("Expected a tagged command failure");
}
} finally {
await rm(directory, { recursive: true, force: true });
}
},
);
};
export const registerOwnedRizinCommandEvidenceTests = (options: {
readonly sweepTokenOwnedProcesses: boolean;
}): void => {
registerOwnedRizinCommandOutcomeTests(options);
registerOwnedRizinCommandFailureTests();
};