mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-13 00:19:03 +02:00
Transcript ingest now respects the same trust store as code import — the gate existed only in gstack-gbrain-sync's runCodeImport, so memory-ingest happily ingested transcripts from deny-listed repos. preparePages filters prepared transcript pages through ONE batch policy lookup (new 'get --batch' verb on bin/gstack-gbrain-repo-policy — the script owns URL normalization; the client adds repoPolicyTierBatch, one spawn for all distinct remotes, so large corpora never pay a 10s-timeout subprocess per remote). Outcomes match code-import semantics: read-only → clean skip (skipped_policy_readonly), deny → counted refusal (skipped_policy_deny), corrupted/unreadable store → HARD ERROR before any write (state, staging, egress receipt, and import all untouched) with the recovery command named — policy corruption must never read as successful ingestion. Artifacts are never policy-filtered (their git_remote is a project slug, not a remote). Fixes #2392. Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
153 lines
6.1 KiB
TypeScript
153 lines
6.1 KiB
TypeScript
/**
|
|
* lib/gbrain-repo-policy-client — batch trust-tier lookup (#2392).
|
|
*
|
|
* Covers the `get --batch` verb of bin/gstack-gbrain-repo-policy (bash level:
|
|
* multiple urls in, per-line verdicts out, input order preserved) and the
|
|
* TypeScript client `repoPolicyTierBatch` (ONE spawn, dedup, fast paths, and
|
|
* the whole-batch `unreadable` classification on a corrupt store).
|
|
*
|
|
* Each test uses a temp GSTACK_HOME so nothing leaks into the user's real
|
|
* ~/.gstack. The client is exercised against the REAL bash script — the
|
|
* script owns URL normalization, so stub stores are seeded through its own
|
|
* `set` verb.
|
|
*/
|
|
|
|
import { describe, test, expect, beforeEach, afterEach } from "bun:test";
|
|
import * as fs from "fs";
|
|
import * as path from "path";
|
|
import * as os from "os";
|
|
import { spawnSync } from "child_process";
|
|
|
|
import { repoPolicyTierBatch } from "../lib/gbrain-repo-policy-client";
|
|
|
|
const ROOT = path.resolve(import.meta.dir, "..");
|
|
const BIN = path.join(ROOT, "bin", "gstack-gbrain-repo-policy");
|
|
|
|
let tmpHome: string;
|
|
|
|
function env(): NodeJS.ProcessEnv {
|
|
return { ...process.env, GSTACK_HOME: tmpHome };
|
|
}
|
|
|
|
function run(args: string[], input?: string) {
|
|
const res = spawnSync(BIN, args, { env: env(), encoding: "utf-8", input });
|
|
return {
|
|
stdout: res.stdout || "",
|
|
stderr: res.stderr || "",
|
|
status: res.status ?? -1,
|
|
};
|
|
}
|
|
|
|
function policyFile(): string {
|
|
return path.join(tmpHome, "gbrain-repo-policy.json");
|
|
}
|
|
|
|
beforeEach(() => {
|
|
tmpHome = fs.mkdtempSync(path.join(os.tmpdir(), "gbrain-policy-client-"));
|
|
});
|
|
|
|
afterEach(() => {
|
|
fs.rmSync(tmpHome, { recursive: true, force: true });
|
|
});
|
|
|
|
describe("bin/gstack-gbrain-repo-policy get --batch (bash level)", () => {
|
|
test("multiple urls in, per-line verdicts out, input order preserved", () => {
|
|
expect(run(["set", "https://github.com/foo/bar.git", "deny"]).status).toBe(0);
|
|
expect(run(["set", "git@github.com:baz/qux.git", "read-only"]).status).toBe(0);
|
|
expect(run(["set", "https://github.com/rw/repo", "read-write"]).status).toBe(0);
|
|
|
|
const r = run(
|
|
["get", "--batch"],
|
|
// Mixed URL forms — the script's normalize() collapses them to the
|
|
// stored keys. `nope/never` has no entry → none.
|
|
"git@github.com:foo/bar.git\nhttps://github.com/nope/never\nhttps://github.com/baz/qux\nhttps://github.com/rw/repo.git\n",
|
|
);
|
|
expect(r.status).toBe(0);
|
|
expect(r.stdout).toBe("deny\nnone\nread-only\nread-write\n");
|
|
});
|
|
|
|
test("no store on disk: every line is none, and no file is created", () => {
|
|
const r = run(["get", "--batch"], "https://github.com/a/a\nhttps://github.com/b/b\n");
|
|
expect(r.status).toBe(0);
|
|
expect(r.stdout).toBe("none\nnone\n");
|
|
expect(fs.existsSync(policyFile())).toBe(false);
|
|
});
|
|
|
|
test("corrupt store: hard error (exit 2), NOT quarantined, names recovery", () => {
|
|
fs.writeFileSync(policyFile(), "not valid json{", { mode: 0o600 });
|
|
const r = run(["get", "--batch"], "https://github.com/foo/bar\n");
|
|
expect(r.status).toBe(2);
|
|
expect(r.stderr).toContain("corrupt");
|
|
expect(r.stderr).toContain("gstack-gbrain-repo-policy list");
|
|
// Unlike interactive `get`, batch must never quarantine-and-proceed —
|
|
// that would bypass a set deny policy on an unattended ingest run.
|
|
expect(fs.readFileSync(policyFile(), "utf-8")).toBe("not valid json{");
|
|
expect(
|
|
fs.readdirSync(tmpHome).find((f) => f.includes(".corrupt-")),
|
|
).toBeUndefined();
|
|
});
|
|
|
|
test("legacy allow entries migrate to read-write on batch read", () => {
|
|
fs.writeFileSync(
|
|
policyFile(),
|
|
JSON.stringify({ "github.com/foo/bar": "allow" }),
|
|
{ mode: 0o600 },
|
|
);
|
|
const r = run(["get", "--batch"], "https://github.com/foo/bar\n");
|
|
expect(r.status).toBe(0);
|
|
expect(r.stdout).toBe("read-write\n");
|
|
});
|
|
});
|
|
|
|
describe("repoPolicyTierBatch (TypeScript client)", () => {
|
|
test("maps each input url to its verdict, dedup included", () => {
|
|
expect(run(["set", "https://github.com/foo/bar", "deny"]).status).toBe(0);
|
|
expect(run(["set", "https://github.com/baz/qux", "read-only"]).status).toBe(0);
|
|
|
|
const verdicts = repoPolicyTierBatch(
|
|
[
|
|
"github.com/foo/bar", // canonical form, as memory-ingest passes it
|
|
"github.com/baz/qux",
|
|
"github.com/nope/never",
|
|
"github.com/foo/bar", // duplicate — dedup keeps ONE map entry
|
|
],
|
|
env(),
|
|
);
|
|
expect(verdicts.size).toBe(3);
|
|
expect(verdicts.get("github.com/foo/bar")).toEqual({ tier: "deny" });
|
|
expect(verdicts.get("github.com/baz/qux")).toEqual({ tier: "read-only" });
|
|
expect(verdicts.get("github.com/nope/never")).toEqual({ tier: "none" });
|
|
});
|
|
|
|
test("no store on disk: every url is tier none with no error (fast path)", () => {
|
|
const verdicts = repoPolicyTierBatch(["github.com/a/a", "github.com/b/b"], env());
|
|
expect(verdicts.get("github.com/a/a")).toEqual({ tier: "none" });
|
|
expect(verdicts.get("github.com/b/b")).toEqual({ tier: "none" });
|
|
expect(fs.existsSync(policyFile())).toBe(false);
|
|
});
|
|
|
|
test("empty url list returns an empty map without spawning", () => {
|
|
const verdicts = repoPolicyTierBatch([], env());
|
|
expect(verdicts.size).toBe(0);
|
|
});
|
|
|
|
test("corrupt store: EVERY url maps to { tier: none, error: unreadable }", () => {
|
|
fs.writeFileSync(policyFile(), "not valid json{", { mode: 0o600 });
|
|
const verdicts = repoPolicyTierBatch(["github.com/foo/bar", "github.com/baz/qux"], env());
|
|
expect(verdicts.get("github.com/foo/bar")).toEqual({ tier: "none", error: "unreadable" });
|
|
expect(verdicts.get("github.com/baz/qux")).toEqual({ tier: "none", error: "unreadable" });
|
|
});
|
|
|
|
test("store unreadable on disk (chmod 000): whole batch classified unreadable", () => {
|
|
if (process.platform === "win32" || process.getuid?.() === 0) return; // chmod semantics differ
|
|
expect(run(["set", "https://github.com/foo/bar", "deny"]).status).toBe(0);
|
|
fs.chmodSync(policyFile(), 0o000);
|
|
try {
|
|
const verdicts = repoPolicyTierBatch(["github.com/foo/bar"], env());
|
|
expect(verdicts.get("github.com/foo/bar")).toEqual({ tier: "none", error: "unreadable" });
|
|
} finally {
|
|
fs.chmodSync(policyFile(), 0o600);
|
|
}
|
|
});
|
|
});
|