mirror of
https://github.com/morluto/rea.git
synced 2026-11-15 11:13:21 +00:00
morluto
b3657c557f
* refactor(cli): run one-shot commands through one shared owner scripts/rea.mjs and the test CLI session worker each implemented the one-shot command sequence: argument normalization, output admission, configuration errors, version documents, the Amp scope refusal, and result delivery. The worker copy had drifted: it never rendered formatted version reports or the Amp refusal. Move the sequence into src/cliOneShot.ts. Both callers supply a host for their streams, exit and resource ownership. The launcher keeps closed-pipe status, worker shutdown and process exit; the session worker captures output per command. The cliOutput bundle entry is superseded and removed. The dispatcher test now replaces only the command runtime, so output admission runs production code. A new parity test compares the file session with a fresh process. * test(cli): bundle the one-shot entry in the runtime bundle fixture * perf(tests): run plain CLI commands on the file's shared process `cli.run` in `cliTest` files started a fresh compiled CLI for every command, about 0.45s and 260 MB each before any work. The file-scoped session already existed, but callers had to opt in through `runFileCli` or `sharedCliRun`, so 1,300 call sites still spawned. Make the fixture choose: `cli.run` uses the shared process when it reports the command exactly as a fresh process would, and starts one otherwise (stdin, explicit deadlines, MCP and MCP doctor routing, NODE_OPTIONS, or enabled logging). `freshProcess: true` keeps explicit process-level checks. The session worker now presents the launcher's entrypoint, so registration identity matches a fresh process. `runFileCli` and `sharedCliRun` are superseded and removed; their call sites use `cli.run`, and paired fresh/shared checks use `freshProcess`. * style(tests): format the managed member summary call site * test(cli): give each shared-session command an empty stdin The shared CLI process reads session frames from its own stdin. A command that reads stdin without supplied input, such as `compare-wasm-interfaces - --json`, read that pipe and hung, where a fresh process receives EOF. The worker now presents an ended, empty stdin to each command and restores its own afterwards. The parity test compared the routed path with itself after cli.run began choosing the session. It now compares a fresh process with the session directly, including the `mcp add` refusal and a command reading absent stdin. * test(cli): keep default command logging and launcher checks on fresh processes environment-serve and environment-build log at info when REA_LOG_LEVEL is unset, through a logger that writes to stderr directly. The shared CLI process captures only process.stderr writes, so routed runs lost those lines. Declare the default-logging commands beside the command names, have infoLogger read that set, and start a fresh process for them. The log-level precedence checks compared the shared process with itself after routing; their fresh side now passes freshProcess: true.
542 lines
16 KiB
TypeScript
542 lines
16 KiB
TypeScript
import { writeFile } from "node:fs/promises";
|
|
import { join } from "node:path";
|
|
import { expect } from "vitest";
|
|
|
|
import { parseEvidence } from "../../../src/domain/evidence.js";
|
|
import { createWebTextArtifact } from "../../../src/domain/webContentArtifact.js";
|
|
import { stableWebScriptKey } from "../../../src/domain/webInventory.js";
|
|
import type { WebMcpDiscovery } from "../../../src/domain/webMcpDiscovery.js";
|
|
import {
|
|
type CompareWebCapturesInput,
|
|
type WebCaptureDiff,
|
|
webCaptureDiffSchema,
|
|
} from "../../../src/domain/webCaptureDiffSchemas.js";
|
|
import { connectLocalToolsMcp } from "../../fixtures/localToolsMcp.js";
|
|
import {
|
|
passiveNetworkCapture,
|
|
withPassiveDroppedEvents,
|
|
} from "../../fixtures/passiveNetworkCapture.js";
|
|
import { createTestTempDirectory } from "../../fixtures/temporaryDirectory.js";
|
|
import { cliTest } from "../../support/cli/cliFixture.js";
|
|
|
|
type Capture = {
|
|
inspection: CompareWebCapturesInput["before"]["inspection"];
|
|
webmcp?: WebMcpDiscovery | null;
|
|
};
|
|
type Case = {
|
|
name: string;
|
|
before: Capture;
|
|
after: Capture;
|
|
dimension: keyof WebCaptureDiff["dimensions"];
|
|
status: "changed" | "unknown" | "unchanged";
|
|
};
|
|
const cases: Case[] = [];
|
|
const add = (
|
|
name: string,
|
|
before: Capture,
|
|
after: Capture,
|
|
dimension: Case["dimension"],
|
|
status: Case["status"],
|
|
) => cases.push({ name, before, after, dimension, status });
|
|
const unselectedCapture = (paths: readonly string[] = []) => {
|
|
const capture = passiveNetworkCapture(paths);
|
|
capture.completeness.excluded.push({
|
|
section: "json_body_shapes",
|
|
reason: "not_approved",
|
|
count: null,
|
|
});
|
|
for (const request of capture.network.requests)
|
|
request.body_shapes.status = "not_approved";
|
|
return capture;
|
|
};
|
|
const full = unselectedCapture(["/a", "/a"]);
|
|
full.network.requests[1]!.status = 503;
|
|
for (const retained of [0, 1]) {
|
|
const omitted = structuredClone(full);
|
|
omitted.network.requests = [omitted.network.requests[retained]!];
|
|
const partial = withPassiveDroppedEvents(omitted, { network_requests: 1 });
|
|
add(
|
|
`heterogeneous HTTP omission ${retained}`,
|
|
{ inspection: full },
|
|
{ inspection: partial },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
add(
|
|
`heterogeneous HTTP omission ${retained} reversed`,
|
|
{ inspection: partial },
|
|
{ inspection: full },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
}
|
|
const changedResponse = structuredClone(full);
|
|
const small = unselectedCapture(["/a"]);
|
|
const largerPartial = withPassiveDroppedEvents(
|
|
unselectedCapture(["/a", "/b"]),
|
|
{ network_requests: 1 },
|
|
);
|
|
add(
|
|
"partial inventory retains a request absent from complete peer",
|
|
{ inspection: small },
|
|
{ inspection: largerPartial },
|
|
"network",
|
|
"changed",
|
|
);
|
|
add(
|
|
"partial inventory retains a request absent from complete peer reversed",
|
|
{ inspection: largerPartial },
|
|
{ inspection: small },
|
|
"network",
|
|
"changed",
|
|
);
|
|
changedResponse.network.requests[1]!.status = 404;
|
|
add(
|
|
"complete heterogeneous HTTP change",
|
|
{ inspection: full },
|
|
{ inspection: changedResponse },
|
|
"network",
|
|
"changed",
|
|
);
|
|
const partialChanged = withPassiveDroppedEvents(changedResponse, {
|
|
network_requests: 1,
|
|
});
|
|
add(
|
|
"observed HTTP value absent from complete peer",
|
|
{ inspection: full },
|
|
{ inspection: partialChanged },
|
|
"network",
|
|
"changed",
|
|
);
|
|
add(
|
|
"two partial HTTP groups cannot prove correspondence",
|
|
{ inspection: withPassiveDroppedEvents(full, { network_requests: 1 }) },
|
|
{ inspection: partialChanged },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
|
|
const socket = unselectedCapture();
|
|
const initiatorBefore = unselectedCapture(["/a"]);
|
|
const initiatorAfter = structuredClone(initiatorBefore);
|
|
initiatorAfter.network.requests[0]!.initiator = {
|
|
type: "other",
|
|
url: null,
|
|
line: null,
|
|
column: null,
|
|
};
|
|
initiatorAfter.completeness.unavailable_sections.push("network_initiators");
|
|
add(
|
|
"unavailable initiator is not a changed request",
|
|
{ inspection: initiatorBefore },
|
|
{ inspection: initiatorAfter },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
const responseDespiteInitiator = structuredClone(initiatorAfter);
|
|
responseDespiteInitiator.network.requests[0]!.status = 503;
|
|
add(
|
|
"response change survives unavailable initiator",
|
|
{ inspection: initiatorBefore },
|
|
{ inspection: responseDespiteInitiator },
|
|
"network",
|
|
"changed",
|
|
);
|
|
socket.network.websocket_connections.push({
|
|
request_id: "local-socket",
|
|
url: "wss://app.example.test/live",
|
|
events: [1, 2, 3].map((bytes) => ({
|
|
direction: "received",
|
|
opcode: 1,
|
|
payload_bytes: bytes,
|
|
payload_shape: { format: "text", json_shape: null },
|
|
})),
|
|
});
|
|
for (const index of [0, 1, 2]) {
|
|
const omitted = structuredClone(socket);
|
|
omitted.network.websocket_connections[0]!.events.splice(index, 1);
|
|
const partial = withPassiveDroppedEvents(omitted, { websocket_frames: 1 });
|
|
add(
|
|
`WebSocket dropped frame ${index}`,
|
|
{ inspection: socket },
|
|
{ inspection: partial },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
add(
|
|
`WebSocket dropped frame ${index} reversed`,
|
|
{ inspection: partial },
|
|
{ inspection: socket },
|
|
"network",
|
|
"unknown",
|
|
);
|
|
}
|
|
// Same retained positions/directions/opcodes can describe entirely different
|
|
// original frames when both captures dropped a frame.
|
|
const leftSocket = structuredClone(socket);
|
|
leftSocket.network.websocket_connections[0]!.events.shift();
|
|
const rightSocket = structuredClone(socket);
|
|
rightSocket.network.websocket_connections[0]!.events.pop();
|
|
add(
|
|
"same-length partial WebSocket streams",
|
|
{ inspection: withPassiveDroppedEvents(leftSocket, { websocket_frames: 1 }) },
|
|
{
|
|
inspection: withPassiveDroppedEvents(rightSocket, { websocket_frames: 1 }),
|
|
},
|
|
"network",
|
|
"unknown",
|
|
);
|
|
const changedSocket = structuredClone(socket);
|
|
changedSocket.network.websocket_connections[0]!.events[1]!.payload_bytes = 4;
|
|
add(
|
|
"complete WebSocket payload change",
|
|
{ inspection: socket },
|
|
{ inspection: changedSocket },
|
|
"network",
|
|
"changed",
|
|
);
|
|
|
|
const inspection = unselectedCapture();
|
|
const discovery: WebMcpDiscovery = {
|
|
browser: inspection.browser,
|
|
target: {
|
|
target_id: "local-page",
|
|
url: inspection.target.url,
|
|
origin: inspection.target.origin!,
|
|
},
|
|
status: "available",
|
|
completeness: structuredClone(inspection.completeness),
|
|
limitations: [],
|
|
tools: {
|
|
total: 1,
|
|
items: [
|
|
{
|
|
tool_key: `webmcp_${"a".repeat(64)}`,
|
|
frame_id: "local-frame-a",
|
|
frame_url: inspection.target.url,
|
|
owner_origin: inspection.target.origin!,
|
|
name: "search",
|
|
description: "Search records",
|
|
declaration_kind: "imperative",
|
|
input_schema: null,
|
|
input_schema_sha256: null,
|
|
annotations: {
|
|
read_only: true,
|
|
untrusted_content: true,
|
|
consequential: false,
|
|
autosubmit: false,
|
|
},
|
|
registration_source: null,
|
|
trust: "page-declared-untrusted",
|
|
},
|
|
],
|
|
},
|
|
};
|
|
const renamed = structuredClone(discovery);
|
|
renamed.tools.items[0]!.tool_key = `webmcp_${"b".repeat(64)}`;
|
|
renamed.tools.items[0]!.frame_id = "local-frame-b";
|
|
add(
|
|
"WebMCP capture-local identity renamed",
|
|
{ inspection, webmcp: discovery },
|
|
{ inspection, webmcp: renamed },
|
|
"webmcp",
|
|
"unchanged",
|
|
);
|
|
const changedTool = structuredClone(renamed);
|
|
changedTool.tools.items[0]!.description = "Changed description";
|
|
add(
|
|
"WebMCP content change survives local identity rename",
|
|
{ inspection, webmcp: discovery },
|
|
{ inspection, webmcp: changedTool },
|
|
"webmcp",
|
|
"changed",
|
|
);
|
|
const knownSource = structuredClone(discovery);
|
|
knownSource.tools.items[0]!.registration_source = {
|
|
url: "https://app.example.test/app.js",
|
|
line: 12,
|
|
column: 3,
|
|
};
|
|
const malformedSource = structuredClone(discovery);
|
|
malformedSource.completeness.unavailable_sections.push("webmcp_tools");
|
|
malformedSource.completeness.excluded.push({
|
|
section: "webmcp_tools",
|
|
reason: "invalid_protocol_value",
|
|
count: 1,
|
|
});
|
|
for (const [name, before, after] of [
|
|
["WebMCP unknown registration source", knownSource, malformedSource],
|
|
["WebMCP unknown registration source reversed", malformedSource, knownSource],
|
|
] as const)
|
|
add(
|
|
name,
|
|
{ inspection, webmcp: before },
|
|
{ inspection, webmcp: after },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
const malformedChanged = structuredClone(malformedSource);
|
|
malformedChanged.tools.items[0]!.description = "Changed description";
|
|
add(
|
|
"WebMCP known description change despite unknown source",
|
|
{ inspection, webmcp: knownSource },
|
|
{ inspection, webmcp: malformedChanged },
|
|
"webmcp",
|
|
"changed",
|
|
);
|
|
const otherSource = structuredClone(knownSource);
|
|
otherSource.tools.items[0]!.registration_source!.line = 13;
|
|
add(
|
|
"WebMCP known registration source change",
|
|
{ inspection, webmcp: knownSource },
|
|
{ inspection, webmcp: otherSource },
|
|
"webmcp",
|
|
"changed",
|
|
);
|
|
const missingCoordinate = structuredClone(knownSource);
|
|
missingCoordinate.tools.items[0]!.registration_source!.line = null;
|
|
add(
|
|
"WebMCP unknown registration coordinate",
|
|
{ inspection, webmcp: knownSource },
|
|
{ inspection, webmcp: missingCoordinate },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
const malformedAnnotation = structuredClone(discovery);
|
|
malformedAnnotation.completeness = structuredClone(
|
|
malformedSource.completeness,
|
|
);
|
|
malformedAnnotation.tools.items[0]!.annotations.read_only = null;
|
|
add(
|
|
"WebMCP malformed annotation",
|
|
{ inspection, webmcp: discovery },
|
|
{ inspection, webmcp: malformedAnnotation },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
const knownSchema = structuredClone(discovery);
|
|
knownSchema.tools.items[0]!.input_schema = { type: "object" };
|
|
knownSchema.tools.items[0]!.input_schema_sha256 = "b".repeat(64);
|
|
const malformedSchema = structuredClone(discovery);
|
|
malformedSchema.completeness = structuredClone(malformedSource.completeness);
|
|
add(
|
|
"WebMCP malformed schema",
|
|
{ inspection, webmcp: knownSchema },
|
|
{ inspection, webmcp: malformedSchema },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
const droppedTools = structuredClone(discovery);
|
|
droppedTools.completeness = withPassiveDroppedEvents(inspection, {
|
|
webmcp_tools: 1,
|
|
}).completeness;
|
|
const partialChangedTools = structuredClone(changedTool);
|
|
partialChangedTools.completeness = structuredClone(droppedTools.completeness);
|
|
add(
|
|
"dropped WebMCP observations cannot establish equality",
|
|
{ inspection, webmcp: droppedTools },
|
|
{ inspection, webmcp: droppedTools },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
add(
|
|
"two partial WebMCP groups cannot prove modification",
|
|
{ inspection, webmcp: droppedTools },
|
|
{ inspection, webmcp: partialChangedTools },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
add(
|
|
"known WebMCP difference survives one complete inventory",
|
|
{ inspection, webmcp: discovery },
|
|
{ inspection, webmcp: partialChangedTools },
|
|
"webmcp",
|
|
"changed",
|
|
);
|
|
const duplicateOwner = structuredClone(discovery);
|
|
duplicateOwner.tools.total = 2;
|
|
duplicateOwner.tools.items.push({
|
|
...duplicateOwner.tools.items[0]!,
|
|
tool_key: `webmcp_${"c".repeat(64)}`,
|
|
frame_id: "duplicate-owner",
|
|
});
|
|
add(
|
|
"WebMCP complete duplicate owner count changes",
|
|
{ inspection, webmcp: duplicateOwner },
|
|
{ inspection, webmcp: renamed },
|
|
"webmcp",
|
|
"changed",
|
|
);
|
|
|
|
const script = unselectedCapture();
|
|
const duplicateRenamed = structuredClone(duplicateOwner);
|
|
duplicateRenamed.tools.items.reverse();
|
|
for (const [index, tool] of duplicateRenamed.tools.items.entries()) {
|
|
tool.frame_id = `new-owner-${index}`;
|
|
tool.tool_key = `webmcp_${String(index + 1).repeat(64)}`;
|
|
}
|
|
add(
|
|
"equal-count WebMCP duplicate owners stay unresolved",
|
|
{ inspection, webmcp: duplicateOwner },
|
|
{ inspection, webmcp: duplicateRenamed },
|
|
"webmcp",
|
|
"unknown",
|
|
);
|
|
script.scripts = {
|
|
total: 1,
|
|
items: [
|
|
{
|
|
script_key: `scr_${"a".repeat(64)}`,
|
|
frame_id: null,
|
|
url: "https://app.example.test/app.js",
|
|
origin: inspection.target.origin,
|
|
cdp_hash: null,
|
|
length: 1,
|
|
is_module: false,
|
|
language: "JavaScript",
|
|
source_map_url: null,
|
|
resource_reconciliation: {
|
|
status: "unmatched",
|
|
reason: "no_exact_sanitized_url",
|
|
},
|
|
source: {
|
|
included: true,
|
|
artifact: createWebTextArtifact("1", "text/javascript"),
|
|
},
|
|
},
|
|
],
|
|
};
|
|
const scriptChanged = structuredClone(script);
|
|
const scriptMissingModule = structuredClone(script);
|
|
scriptMissingModule.scripts.items[0]!.is_module = null;
|
|
scriptMissingModule.scripts.items[0]!.script_key = stableWebScriptKey(
|
|
scriptMissingModule.scripts.items[0]!,
|
|
);
|
|
add(
|
|
"missing script module metadata is unknown rather than removed and added",
|
|
{ inspection: script },
|
|
{ inspection: scriptMissingModule },
|
|
"scripts",
|
|
"unknown",
|
|
);
|
|
const scriptDifferentModule = structuredClone(script);
|
|
scriptDifferentModule.scripts.items[0]!.is_module = true;
|
|
scriptDifferentModule.scripts.items[0]!.script_key = stableWebScriptKey(
|
|
scriptDifferentModule.scripts.items[0]!,
|
|
);
|
|
add(
|
|
"known unequal script module metadata remains changed",
|
|
{ inspection: script },
|
|
{ inspection: scriptDifferentModule },
|
|
"scripts",
|
|
"changed",
|
|
);
|
|
scriptChanged.scripts.items[0]!.source = {
|
|
included: true,
|
|
artifact: createWebTextArtifact("2", "text/javascript"),
|
|
};
|
|
add(
|
|
"script retained digest change without producer hash",
|
|
{ inspection: script },
|
|
{ inspection: scriptChanged },
|
|
"scripts",
|
|
"changed",
|
|
);
|
|
add(
|
|
"script retained digest agreement",
|
|
{ inspection: script },
|
|
{ inspection: script },
|
|
"scripts",
|
|
"unchanged",
|
|
);
|
|
const unavailableScript = structuredClone(script);
|
|
unavailableScript.scripts.items[0]!.source = {
|
|
included: false,
|
|
reason: "not selected",
|
|
};
|
|
add(
|
|
"script digest unavailable",
|
|
{ inspection: script },
|
|
{ inspection: unavailableScript },
|
|
"scripts",
|
|
"unknown",
|
|
);
|
|
add(
|
|
"no source digest is unknown",
|
|
{ inspection: unavailableScript },
|
|
{ inspection: unavailableScript },
|
|
"scripts",
|
|
"unknown",
|
|
);
|
|
|
|
const expectComparison = (document: unknown, scenario: Case) => {
|
|
const evidence = parseEvidence(document);
|
|
expect(evidence.operation).toBe("compare_web_captures");
|
|
const result = webCaptureDiffSchema.parse(evidence.normalized_result);
|
|
expect(result.dimensions[scenario.dimension], scenario.name).toMatchObject({
|
|
status: scenario.status,
|
|
...(scenario.status === "changed" ? {} : { total_changes: 0, changes: [] }),
|
|
});
|
|
};
|
|
|
|
// The single MCP connection below exercises every semantic permutation. CLI
|
|
// subprocesses cover the distinct adapter outcomes without repeating startup
|
|
// for each reversed input or dropped-frame position.
|
|
const cliCaseNames = new Set([
|
|
"heterogeneous HTTP omission 0",
|
|
"partial inventory retains a request absent from complete peer",
|
|
"observed HTTP value absent from complete peer",
|
|
"same-length partial WebSocket streams",
|
|
"WebMCP capture-local identity renamed",
|
|
"WebMCP unknown registration source",
|
|
"WebMCP known description change despite unknown source",
|
|
"script retained digest change without producer hash",
|
|
"script digest unavailable",
|
|
]);
|
|
|
|
cliTest.for(cases.filter(({ name }) => cliCaseNames.has(name)))(
|
|
"CLI preserves capture correspondence: $name",
|
|
async (scenario, { cli }) => {
|
|
const directory = await createTestTempDirectory(
|
|
"rea-capture-correspondence-",
|
|
);
|
|
const paths = [
|
|
join(directory, "before.json"),
|
|
join(directory, "after.json"),
|
|
];
|
|
await Promise.all(
|
|
paths.map((path, index) =>
|
|
writeFile(
|
|
path,
|
|
JSON.stringify(index === 0 ? scenario.before : scenario.after),
|
|
),
|
|
),
|
|
);
|
|
const invocation = {
|
|
arguments: ["compare-web-captures", ...paths, "--json"],
|
|
environment: { REA_LOG_LEVEL: "silent" },
|
|
};
|
|
const response = await cli.run({
|
|
...invocation,
|
|
freshProcess: scenario.name === "heterogeneous HTTP omission 0",
|
|
});
|
|
expect(response.exitCode, response.stderr).toBe(0);
|
|
expectComparison(response.json, scenario);
|
|
},
|
|
);
|
|
|
|
cliTest(
|
|
"stdio MCP preserves capture correspondence on one connection",
|
|
async () => {
|
|
const mcp = await connectLocalToolsMcp();
|
|
for (const scenario of cases) {
|
|
const response = await mcp.call("compare_web_captures", {
|
|
before: scenario.before,
|
|
after: scenario.after,
|
|
});
|
|
expect(response.isError, JSON.stringify(response)).not.toBe(true);
|
|
expectComparison(response.structuredContent, scenario);
|
|
}
|
|
},
|
|
);
|