inspector/clients/cli/__tests__/skills-verify-cli.test.ts
cliffhall 9a8488681e feat: Skills extension phase 3 — CLI, TUI, directory reads, frontmatter check
Closes #2248.

Completes SEP-2640 support across all three clients, and closes the one
obligation #2234 deliberately left open.

- `checkSkillFrontmatterMatch` compares a served SKILL.md's own YAML
  frontmatter against the entry the listing advertised, field by field. No
  digest can cover this: a digest is taken over the bytes the server served,
  so it proves the file was not altered in transit and says nothing about
  whether the listing described it honestly. Needs a real YAML parser; `yaml`
  was already a root dependency, so this adds no package — but it does newly
  put it on core/'s import graph, hence the three bundler `external` lists.

- `resources/directory/read`: result schemas defined against the normative
  text, `InspectorClient.readResourceDirectory`, a Directory section on the
  Skills screen, and `--method resources/directory/read` in the CLI. The
  client refuses the call locally when the server did not declare
  `directoryRead`, which is the SEP's MUST NOT. A child the directory lists
  but the entry does not is marked `not listed` rather than merged into the
  manifest — the SEP calls a directory result a live observation and forbids
  treating it as extending the manifest.

- CLI: `skills/list`, `skills/get` and `resources/directory/read`, plus
  `--verify` — one NDJSON report per skill, a summary on stderr, exit 7 on a
  violation. Reads are sequential; a conforming manifest may declare 512
  entries.

- TUI: a Skills pane, shown only when the server declares the extension. Each
  row carries its conformance verdict as a glyph as well as a colour, since
  the pane is read over ssh and through script(1). Enter verifies.

- `verifySkills` re-throws `AuthRecoveryRequiredError` rather than recording
  it per file: it says the session's authorization expired, so absorbing it
  would report N identical read failures and swallow the error the TUI and
  the web commands key off to reauthorize.

Two open questions settled, both in code comments where they will be found:
`skills/get` carries no caching attributes because SEP-2640 leaves the
question open in as many words, so requiring them would fail a conforming
server; and there is no `PagedSkillsState` because every consumer of this
list is a whole-catalog verdict — computed over page one of three, "this
server's skills conform" is not merely partial but wrong.

The fixture grows two skills, both for checks that were otherwise
undemonstrable: `lying-listing` (listing and file disagree, digest still
verifies) and `stale-manifest` (serves a file its manifest does not declare).

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01ND46Ci64DC3tzBy9aG81Nc
Signed-off-by: cliffhall <cliff@futurescale.com>
2026-09-07 18:10:37 -04:00

150 lines
4.5 KiB
TypeScript

import { describe, it, expect } from "vitest";
import { runCli } from "../src/cli.js";
import { consumeMethodOutcome } from "../src/handlers/consume-outcome.js";
import { EXIT_CODES } from "../src/error-handler.js";
/**
* `--verify`'s argument validation and its NDJSON consumption path (#2248).
*
* The validation sits with `--strict`'s, ahead of every short-circuit return in
* `parseArgs`, for the same reason: the returns below it never reach
* `runMethod`, so a check placed further down would let the flag be accepted
* and then silently ignored.
*/
describe("--verify argument validation", () => {
it("is rejected with a method other than skills/list or skills/get", async () => {
await expect(
runCli([
"node",
"cli",
"--cli",
"--method",
"tools/list",
"--verify",
"--server-url",
"http://127.0.0.1:1/mcp",
]),
).rejects.toThrow(
"--verify requires --method skills/list or --method skills/get.",
);
});
it.each([
["servers/list", ["--method", "servers/list"]],
["--list-stored-auth", ["--method", "servers/list", "--list-stored-auth"]],
])(
"is rejected on the %s short-circuit path, which never reaches the report",
async (_label, extra) => {
await expect(
runCli(["node", "cli", "--cli", "--verify", ...extra]),
).rejects.toThrow(
"--verify requires --method skills/list or --method skills/get.",
);
},
);
it("is accepted with skills/get", async () => {
// Reaches the connect and fails there — which is the point: the flag
// itself was not what was rejected.
await expect(
runCli([
"node",
"cli",
"--cli",
"--method",
"skills/get",
"--uri",
"skill://demo/SKILL.md",
"--verify",
"--server-url",
"http://127.0.0.1:1/mcp",
]),
).rejects.not.toThrow(/--verify requires/);
});
});
describe("consumeMethodOutcome NDJSON summary and exit code (#2248)", () => {
function captureStreams() {
let stdout = "";
let stderr = "";
const write = (sink: (s: string) => void) =>
((chunk: unknown, ...rest: unknown[]) => {
sink(typeof chunk === "string" ? chunk : String(chunk));
const cb = rest.find((r) => typeof r === "function") as
| (() => void)
| undefined;
cb?.();
return true;
}) as typeof process.stdout.write;
const originalOut = process.stdout.write;
const originalErr = process.stderr.write;
process.stdout.write = write((s) => (stdout += s));
process.stderr.write = write((s) => (stderr += s));
return {
get stdout() {
return stdout;
},
get stderr() {
return stderr;
},
restore() {
process.stdout.write = originalOut;
process.stderr.write = originalErr;
},
};
}
it("writes the summary to stderr so it cannot contaminate the NDJSON", async () => {
const streams = captureStreams();
try {
await consumeMethodOutcome(
{ kind: "ndjson", lines: [{ ok: true }], summary: "all good" },
{},
);
} finally {
streams.restore();
}
expect(JSON.parse(streams.stdout.trim())).toEqual({ ok: true });
expect(streams.stderr).toBe("all good\n");
});
it("throws the exit code AFTER writing the report", async () => {
// The report is the output a CI job reads; failing before writing it would
// give the reader an exit code and nothing to act on.
const streams = captureStreams();
let thrown: unknown;
try {
await consumeMethodOutcome(
{
kind: "ndjson",
lines: [{ ok: false }],
summary: "one failed",
exitCode: EXIT_CODES.SKILL_NONCONFORMANT,
},
{},
);
} catch (err) {
thrown = err;
} finally {
streams.restore();
}
expect(streams.stdout.trim()).toBe('{"ok":false}');
expect(thrown).toMatchObject({
exitCode: EXIT_CODES.SKILL_NONCONFORMANT,
envelope: { code: "skills_nonconformant" },
});
});
it("leaves an --app-info NDJSON outcome unchanged", async () => {
// No summary, no exit code — the field is additive and the older caller
// must behave exactly as before.
const streams = captureStreams();
try {
await consumeMethodOutcome({ kind: "ndjson", lines: [{ a: 1 }] }, {});
} finally {
streams.restore();
}
expect(streams.stderr).toBe("");
expect(streams.stdout.trim()).toBe('{"a":1}');
});
});