fix(verifiers): centralize failure and cleanup ownership

Own operation results and exact rejections in withVerifierCleanup, including
undefined, null and independent cleanup failures. Remove the optional-primary
cleanup contract and migrate every caller, preserving returns, annotations,
signal restoration and dependent cleanup order.

Make Frida/JEB reporters fail on reasonless rejections and retain JEB fixture
files while provider cleanup is incomplete. Own the nested packaged WASM
verifier and expose its composite process/root cleanup capability for retry.
Update runnable docs and isolated fixture dependencies.

Validation: 547 focused cases in 20 files, eight isolated boundary unit checks,
static/build/docs/discovery gates and duplication check (3.58%). Node process,
SDK and descriptor cleanup are exercised; provider and packaging results in
orchestration tests are simulated. Pack/install subprocess ownership remains
with the existing shared package runner outside the nested-command change.
This commit is contained in:
morluto
2026-10-24 15:38:35 +08:00
parent 98ec00f406
commit 72ba1cd92b
48 changed files with 2380 additions and 1818 deletions
+14 -23
View File
@@ -10,7 +10,7 @@ import { parseArgs } from "node:util";
import { Client } from "@modelcontextprotocol/client";
import { StdioClientTransport } from "@modelcontextprotocol/client/stdio";
import { artifactCliEvidence } from "../../lib/artifact-e2e.mjs";
import { closeVerifierResources } from "../../lib/verifier-cleanup.mjs";
import { withVerifierCleanup } from "../../lib/verifier-cleanup.mjs";
import { PrivateRuntimeRoot } from "../../../dist/process/PrivateRuntimeRoot.js";
import {
OwnedCommandFailure,
@@ -82,9 +82,8 @@ const normalize = (rows) =>
),
}));
let temporary;
let primaryError;
let retainTemporary = false;
try {
await withVerifierCleanup(async () => {
await client.connect(transport);
transport.stderr?.resume();
const tools = (await client.listTools()).tools;
@@ -393,23 +392,15 @@ print(json.dumps(dict(tokenizer='cl100k_base',tiktoken_version=tiktoken.__versio
"First query is after shared artifact analysis; subsequent queries share one MCP session. Legacy item reads are serial; a concurrent legacy baseline is unmeasured. Filesystem/build warmness uncontrolled. Token costs count one post-change catalog, preparation request/summary and each request/structured reply once; client rendering, replay, reasoning, final answer and model latency are unmeasured. Preparation and parity/tokenization overhead are outside per-query elapsed times; external family-resource receipts include the complete verifier and children.",
})}\n`,
);
} catch (cause) {
primaryError = cause;
throw cause;
} finally {
await closeVerifierResources(
[
() => client.close(),
() => transport.close(),
async () => {
if (temporary === undefined) return;
if (retainTemporary)
throw new Error(
`Command cleanup is incomplete; retaining its private input/Evidence files at ${temporary.path}.`,
);
await temporary.close();
},
],
primaryError,
);
}
}, [
() => client.close(),
() => transport.close(),
async () => {
if (temporary === undefined) return;
if (retainTemporary)
throw new Error(
`Command cleanup is incomplete; retaining its private input/Evidence files at ${temporary.path}.`,
);
await temporary.close();
},
]);
+13 -22
View File
@@ -16,7 +16,7 @@ import {
OwnedCommandFailure,
runOwnedCommand,
} from "../../../dist/process/OwnedCommand.js";
import { closeVerifierResources } from "../../lib/verifier-cleanup.mjs";
import { withVerifierCleanup } from "../../lib/verifier-cleanup.mjs";
import {
matchesStructuredScopeExpectation,
structuredScopeExpectationsSchema,
@@ -122,7 +122,6 @@ const simulatedNativeEvidence = (path, sha256) =>
},
);
let temporary;
let primaryError;
let retainTemporary = false;
let report;
const ownedCommand = async (command, arguments_, timeoutMs = 60_000) => {
@@ -145,7 +144,7 @@ const ownedCommand = async (command, arguments_, timeoutMs = 60_000) => {
throw cause;
}
};
try {
await withVerifierCleanup(async () => {
const archiveSha256 = await fileDigest(values.artifact);
const companion = join(`${values.artifact}.unpacked`, values["addon-path"]);
let companionSha256 = null;
@@ -460,23 +459,15 @@ print(json.dumps(dict(tokenizer='cl100k_base',tiktoken_version=tiktoken.__versio
assert.ok(safeIdentity, "Native identity/linkage oracle failed");
assert.ok(safeApplicability, "File analysis applicability oracle failed");
}
} catch (cause) {
primaryError = cause;
throw cause;
} finally {
await closeVerifierResources(
[
() => client.close(),
() => transport.close(),
async () => {
if (retainTemporary)
throw new Error(
`Command cleanup incomplete; retaining owned inputs at ${temporary?.path}.`,
);
await temporary?.close();
},
],
primaryError,
);
}
}, [
() => client.close(),
() => transport.close(),
async () => {
if (retainTemporary)
throw new Error(
`Command cleanup incomplete; retaining owned inputs at ${temporary?.path}.`,
);
await temporary?.close();
},
]);
console.log(serialize(report));
+13 -22
View File
@@ -15,7 +15,7 @@ import {
OwnedCommandFailure,
runOwnedCommand,
} from "../../../dist/process/OwnedCommand.js";
import { closeVerifierResources } from "../../lib/verifier-cleanup.mjs";
import { withVerifierCleanup } from "../../lib/verifier-cleanup.mjs";
import { selectExportedJavaScriptFacts } from "../../lib/javascript-facts-reference.mjs";
const { values } = parseArgs({
@@ -56,7 +56,6 @@ const client = new Client({
version: "1",
});
let temporary;
let primaryError;
let retainTemporary = false;
let report;
const serialize = (value) => JSON.stringify(value);
@@ -106,7 +105,7 @@ const resourceSnapshot = async () => {
};
};
try {
await withVerifierCleanup(async () => {
const start = performance.now();
const artifactHash = createHash("sha256");
for await (const chunk of createReadStream(values.artifact))
@@ -344,23 +343,15 @@ try {
conditions:
"Fresh MCP and input hashing (file cache warmed); build/OS caches uncontrolled. First export sample includes export plus caller projection code, later samples reuse that immutable export. View samples precede diagnostic export. Task token projections include preparation, first answer, selected/full name/description/inputSchema catalog and the exact baseline program; exec tool schema, host rendering, output schemas, reasoning and billing unmeasured. At-answer cgroup counters include observer/startup overhead, before repeats/export diagnostics/parity/tokenization; final external observer measures all validation work. No application or native provider executes.",
};
} catch (cause) {
primaryError = cause;
throw cause;
} finally {
await closeVerifierResources(
[
() => client.close(),
() => transport.close(),
async () => {
if (retainTemporary)
throw new Error(
`Command cleanup incomplete; retaining owned inputs at ${temporary?.path}.`,
);
await temporary?.close();
},
],
primaryError,
);
}
}, [
() => client.close(),
() => transport.close(),
async () => {
if (retainTemporary)
throw new Error(
`Command cleanup incomplete; retaining owned inputs at ${temporary?.path}.`,
);
await temporary?.close();
},
]);
console.log(serialize(report));