Files
reverse-engineering-anything/tests/boundary/mcp/contextEvidenceOverflow.test.ts
T
morlutoandCursor Agent 106ba1730f fix!: preserve address context resource recovery (#8424)
* fix: retain address context cleanup failures

* fix!: preserve address context input errors

BREAKING CHANGE: Strict clients that cached the previous full inspect_address_context output schema must refresh tools/list and accept the typed error field on unavailable facets.

* test: use session contract for address context

* fix!: preserve address context resource recovery

BREAKING CHANGE: Clients validating unavailable context facets against a cached strict full output schema must refresh tools/list to accept resource_constraint errors.

* fix: expose authenticated records refused by the evidence ledger (#8426)

* fix: preserve completed evidence on retention refusal

* fix: preserve context when unretained evidence exceeds delivery limits

* fix(mcp): recover oversized context from session evidence

* fix(evidence): preserve completed atomic write results

* fix(cli): preserve caller path in unretained evidence

* style(test): format CLI help default annotations (#9280)

---------

Co-authored-by: Cursor Agent <cursoragent@cursor.com>
2026-11-07 23:34:20 +08:00

332 lines
11 KiB
TypeScript

import { readFile, writeFile } from "node:fs/promises";
import { join } from "node:path";
import { Client, InMemoryTransport } from "@modelcontextprotocol/client";
import { expect, it } from "vitest";
import { createTestProviderRouter } from "../../fixtures/binarySession.js";
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
import { parseMcpToolError } from "../../fixtures/mcpToolError.js";
import { createAnalysisExecution } from "../../../src/application/AnalysisProvider.js";
import { BinarySession } from "../../../src/application/binary/BinarySession.js";
import { InvestigationRecords } from "../../../src/application/investigation/InvestigationRecords.js";
import { createAnalysisProfile } from "../../../src/domain/analysisProfile.js";
import { err, ok } from "../../../src/domain/result.js";
import { AnalysisCapabilityUnavailableError } from "../../../src/domain/analysisErrorCore.js";
import { createServer } from "../../../src/server/createServer.js";
const verifyContext = (
content: unknown,
twoLarge: boolean,
session: BinarySession,
): void => {
expect(content).toMatchObject({
result: {
name: { state: "available", value: "entry" },
procedure: {
state: "unavailable",
error: {
code: "resource_constraint",
details: {
partial_observation_omitted: {
reason: "mcp-response-limit",
retention: "unretained",
original_response_bytes_at_least: expect.any(Number),
evidence_id: expect.stringMatching(/^ev_[a-f0-9]{64}$/u),
},
},
},
},
},
});
const procedureDetails = (
content as {
result: {
procedure: {
error: {
details: {
partial_observation_omitted: { evidence_id: string };
};
};
};
};
}
).result.procedure.error.details;
expect(procedureDetails).not.toHaveProperty("partial_observation");
expect(procedureDetails).not.toHaveProperty("evidence_reference");
expect(
session.hasEvidence(
procedureDetails.partial_observation_omitted.evidence_id,
),
).toBe(false);
const smallFacet = twoLarge ? "inline_comment" : "comment";
expect(content).toMatchObject({
result: {
[smallFacet]: {
state: "unavailable",
error: {
code: "resource_constraint",
details: {
partial_observation: {
kind: "unretained-evidence",
evidence: {
operation: smallFacet,
normalized_result: "short note",
},
},
},
},
},
...(twoLarge
? {
comment: {
state: "unavailable",
error: {
details: {
partial_observation_omitted: {
reason: "mcp-response-limit",
retention: "unretained",
},
},
},
},
}
: {}),
},
});
};
it.each([
["compact", false],
["full", false],
["compact", true],
] as const)(
"keeps context and smaller partials when unretained observations exceed the MCP budget (%s, two large=%s)",
async (profile, twoLarge) => {
const identity = {
id: "fixture",
name: "Fixture analysis provider",
version: "1",
};
const directory = await createTestTempDirectory("rea-context-capacity-");
const target = join(directory, "fixture.com");
await writeFile(target, Buffer.from([0xb8, 0, 0x4c, 0xcd, 0x21]));
const router = createTestProviderRouter(
() => ({
execute: async (operation) => {
if (operation === "address_name")
return ok(createAnalysisExecution("entry", identity));
if (operation === "comment")
return ok(
createAnalysisExecution(
twoLarge ? "g".repeat(6 * 1024 * 1024) : "short note",
identity,
),
);
if (operation === "inline_comment" && twoLarge)
return ok(createAnalysisExecution("short note", identity));
if (operation === "resolve_containing_procedure")
return ok(
createAnalysisExecution(
{
query_address: "0x100",
found: true,
procedure: {
address: "0x100",
name: "f".repeat(6 * 1024 * 1024),
classification: null,
body: { available: false, reason: "not recorded" },
},
},
identity,
),
);
return err(
new AnalysisCapabilityUnavailableError(
identity.id,
operation,
"not provided",
),
);
},
close: async () => ok(null),
}),
{
resolveAnalysisProfile: async () =>
ok({ profile: createAnalysisProfile(identity, { fixture: true }) }),
},
);
const records = new InvestigationRecords({
maximumRepresentationBytes: 8000,
});
const session = new BinarySession(router, records);
const server = createServer(
{ kind: "session", session },
{
environment: {
...process.env,
REA_MCP_TOOL_FAMILIES: "session",
REA_MCP_OUTPUT_SCHEMA_PROFILE: profile,
},
},
);
const client = new Client({ name: "context-capacity", version: "1" });
const [clientTransport, serverTransport] =
InMemoryTransport.createLinkedPair();
try {
await server.connect(serverTransport);
await client.connect(clientTransport);
const definitions = new Map(
(await client.listTools()).tools.map((tool) => [tool.name, tool]),
);
const call = (name: string, args: Record<string, string>) => {
const toolDefinition = definitions.get(name);
if (toolDefinition === undefined)
throw new Error(`Tool ${name} was not advertised`);
return client.callTool({ name, arguments: args }, { toolDefinition });
};
expect(
(
await call("open_binary", {
path: target,
format: "dos-com",
provider_id: "fixture",
})
).isError,
).not.toBe(true);
const arguments_ = { document: "fixture", address: "0x100" };
const response = await call("inspect_address_context", arguments_);
expect(response.isError).not.toBe(true);
verifyContext(response.structuredContent, twoLarge, session);
const bundle = await client.callTool({
name: "get_evidence_bundle",
arguments: { detail: "complete" },
});
expect(bundle.structuredContent).toMatchObject({
result: {
records: [{ operation: "address_name", normalized_result: "entry" }],
},
});
} finally {
await client.close();
await server.close();
await session.close();
}
},
);
it.each([true, false])(
"recovers retained context facets when possible (profile=%s)",
async (profile) => {
const identity = {
id: "fixture",
name: "Fixture analysis provider",
version: "1",
};
const target = join(
await createTestTempDirectory("rea-context-oversize-success-"),
"fixture.com",
);
await writeFile(target, Buffer.from([0xb8, 0, 0x4c, 0xcd, 0x21]));
const router = createTestProviderRouter(
() => ({
execute: async (operation) =>
operation === "health"
? ok(createAnalysisExecution(null, identity))
: operation === "address_name"
? ok(
createAnalysisExecution(
"x".repeat(6 * 1024 * 1024),
identity,
),
)
: err(
new AnalysisCapabilityUnavailableError(
identity.id,
operation,
"not provided",
),
),
close: async () => ok(null),
}),
profile
? {
resolveAnalysisProfile: async () =>
ok({
profile: createAnalysisProfile(identity, { fixture: true }),
}),
}
: {},
);
const session = new BinarySession(router);
const server = createServer(
{ kind: "session", session },
{ environment: { ...process.env, REA_MCP_TOOL_FAMILIES: "session" } },
);
const client = new Client({
name: "context-oversize-success",
version: "1",
});
const [ct, st] = InMemoryTransport.createLinkedPair();
try {
await server.connect(st);
await client.connect(ct);
const opened = await client.callTool({
name: "open_binary",
arguments: { path: target, format: "dos-com" },
});
expect(opened.isError, JSON.stringify(opened.content)).not.toBe(true);
const result = await client.callTool({
name: "inspect_address_context",
arguments: { address: "0x100", document: "fixture" },
});
expect(result.isError).toBe(true);
const error = parseMcpToolError(result).error;
expect(error).toMatchObject({
code: "resource_constraint",
details: { reported_limits: { boundary: "mcp-response" } },
});
expect(error.remediation.action).toContain("get_evidence_bundle");
expect(error.remediation.action).toContain("export_evidence_bundle");
expect(error.remediation.action).toContain("may not have been retained");
const advertised = new Set(
(await client.listTools()).tools.map((tool) => tool.name),
);
expect(advertised.has("get_evidence_bundle")).toBe(true);
expect(advertised.has("export_evidence_bundle")).toBe(true);
expect(advertised.has("address_name")).toBe(false);
const summary = await client.callTool({
name: "get_evidence_bundle",
arguments: {
detail: "summary",
filters: { operation: "address_name" },
},
});
expect(summary.isError).not.toBe(true);
expect(summary.structuredContent).toMatchObject({
result: { matching_records: profile ? 1 : 0 },
});
const path = join(
await createTestTempDirectory("rea-context-recover-"),
"evidence.json",
);
const exported = await client.callTool({
name: "export_evidence_bundle",
arguments: { path },
});
expect(exported.isError).not.toBe(true);
const bundle = JSON.parse(await readFile(path, "utf8")) as {
records: { operation: string; normalized_result: unknown }[];
};
const record = bundle.records.find(
(entry) => entry.operation === "address_name",
);
if (profile)
expect(record?.normalized_result).toBe("x".repeat(6 * 1024 * 1024));
else expect(record).toBeUndefined();
} finally {
await client.close();
await server.close();
await session.close();
}
},
);