Files
boocode/apps/server/src/services/__tests__/grant_resolver.test.ts
indifferentketchup b52c5df705 v1.13.17-cross-repo-reads: on-demand read access to paths outside the project root
When the agent needed context from another repo, pathGuard rejected every read
with no recovery path. This batch adds a reactive request_read_access flow:
pathGuard's error now hints at the tool, the model emits a structured request,
the inference loop pauses (same mechanism as ask_user_input), the user picks
Allow/Deny via inline chips, and subsequent reads under the granted root succeed
for the rest of the session.

Schema: sessions.allowed_read_paths TEXT[] NOT NULL DEFAULT ARRAY[]::TEXT[]
(idempotent ADD COLUMN IF NOT EXISTS).

Grant unit (design D1): nearest registered projects.path ancestor →
nearest repo-shaped ancestor (.git/ / package.json / go.mod / Cargo.toml)
under PROJECT_ROOT_WHITELIST → else refuse. grant_resolver.ts walks
ancestors with a per-iteration whitelist invariant check so symlinked
input can't escape the whitelist mid-walk (Sam's checkpoint-1 ask).

Path-guard: optional extraRoots arg threaded from session.allowed_read_paths
through executeToolCall to view_file / list_dir / grep / find_files. The
ToolDef.execute signature gets an optional third param; non-FS tools
ignore it. view_file re-anchors the secret-guard check on basename(real)
whenever a relative path starts with "../" so .env / id_rsa* etc. still
deny across grant roots.

Endpoint: POST /api/chats/:id/grant_read_access mirrors /answer_user_input.
On 'allow' it re-resolves the grant root (state may have changed since
prompt — auto-falls to denial reason text on failure, not 500), array_appends
to sessions.allowed_read_paths with in-memory dedup, then publishes
tool_result + session_updated frames and enqueues the next assistant turn.

PATCH /api/sessions/:id allowed_read_paths supports revocation only. Zod
refines absolute + no traversal markers; runtime findUnauthorizedAdditions
guard rejects any entry not already present in the row, so a malicious
curl -X PATCH -d '{"allowed_read_paths":["/etc"]}' returns 400 instead of
bypassing the grant flow (Sam's compliance-review action item).

Frontend: RequestReadAccessCard renders pending (path + reason + Allow/Deny)
and answered (granted/denied summary with the resolved root) variants;
MessageList.flatten/group special-cases the tool name; SettingsPane adds a
per-session grants list with per-row revoke that PATCHes the shortened
array.

Tests: 11 grant_resolver, 8 path_guard, 8 sessions PATCH subset, including
explicit cases for symlink escape mid-walk, walk-bound termination at
whitelist root, /etc bypass attempt via PATCH, and nearest-project
disambiguation. 292 total server tests green.

Pairs with v1.13.16-xml-parser — the model now self-recovers from both
a wrong tool name AND from a refused path.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
2026-05-22 21:45:52 +00:00

200 lines
7.6 KiB
TypeScript

// v1.13.17-cross-repo-reads: resolveGrantRoot decision tree.
//
// Sam's dispatch note (2026-05-22): "in the project-root resolver ancestor
// walk, stop the moment parent exits PROJECT_ROOT_WHITELIST or hits
// filesystem root — check on every iteration, not just final parent.
// Symlinked input must not be able to escape the whitelist during the
// walk." The symlink-escape-mid-walk test below pins that invariant —
// without the per-iteration whitelist check, this case would walk OUTSIDE
// the whitelist root and return a phantom grant.
import { describe, it, expect, beforeAll, afterAll, vi } from 'vitest';
import { mkdtemp, rm, mkdir, writeFile, symlink } from 'node:fs/promises';
import { tmpdir } from 'node:os';
import { join } from 'node:path';
import { realpath } from 'node:fs/promises';
import { resolveGrantRoot } from '../grant_resolver.js';
import type { Sql } from '../../db.js';
let tmp: string;
let whitelist: string;
let project: string;
let fork: string;
let outside: string;
// Fake sql tag — returns the projects rows we want without touching a real
// database. The resolver only ever does a single SELECT, so a single-shot
// mock that returns the prepared rows on every invocation is enough.
function makeSql(rows: Array<{ path: string }>): Sql {
const tag = ((..._args: unknown[]) => Promise.resolve(rows)) as unknown as Sql;
return tag;
}
beforeAll(async () => {
tmp = await realpath(await mkdtemp(join(tmpdir(), 'boocode-gr-')));
whitelist = join(tmp, 'whitelist');
project = join(whitelist, 'boocode');
fork = join(whitelist, 'forks', 'codecontext');
outside = join(tmp, 'outside');
await mkdir(project, { recursive: true });
await mkdir(fork, { recursive: true });
await mkdir(outside, { recursive: true });
// Mark project as a repo (.git directory).
await mkdir(join(project, '.git'));
await writeFile(join(project, 'README.md'), 'project readme');
// Mark fork as a repo via go.mod (matches the proposal's example).
await writeFile(join(fork, 'go.mod'), 'module example.com/foo');
await writeFile(join(fork, 'main.go'), 'package main');
await writeFile(join(outside, 'secret.txt'), 'forbidden');
});
afterAll(async () => {
await rm(tmp, { recursive: true, force: true });
});
describe('resolveGrantRoot — happy paths', () => {
it('refuses when the requested path is already under projectRoot', async () => {
const result = await resolveGrantRoot(makeSql([]), join(project, 'README.md'), project, whitelist);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/already accessible/);
});
it('returns the project root when the path falls under a registered project', async () => {
// Register `fork` as a known project. Resolver should return the project
// ancestor (LONGEST match wins) rather than the repo-shape fallback.
const result = await resolveGrantRoot(
makeSql([{ path: fork }]),
join(fork, 'main.go'),
project,
whitelist,
);
expect(result.ok).toBe(true);
if (result.ok) {
expect(result.root).toBe(fork);
expect(result.source).toBe('project');
}
});
it('falls back to the nearest repo-shaped ancestor when no project matches', async () => {
const result = await resolveGrantRoot(
makeSql([]),
join(fork, 'main.go'),
project,
whitelist,
);
expect(result.ok).toBe(true);
if (result.ok) {
expect(result.root).toBe(fork);
expect(result.source).toBe('whitelist');
}
});
});
describe('resolveGrantRoot — refusals', () => {
it('refuses paths outside PROJECT_ROOT_WHITELIST', async () => {
const result = await resolveGrantRoot(
makeSql([]),
join(outside, 'secret.txt'),
project,
whitelist,
);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/outside permitted scope/);
});
it('refuses non-absolute paths', async () => {
const result = await resolveGrantRoot(makeSql([]), 'relative/path', project, whitelist);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/absolute/);
});
it('refuses missing paths without prompting', async () => {
const result = await resolveGrantRoot(
makeSql([]),
join(whitelist, 'nope'),
project,
whitelist,
);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/does not exist/);
});
it('refuses when no repo-shape marker is found before hitting the whitelist root', async () => {
// Build a directory tree under the whitelist that has NO repo markers
// all the way up to the whitelist root.
const plain = join(whitelist, 'plain-dir', 'nested');
await mkdir(plain, { recursive: true });
await writeFile(join(plain, 'just-a-file.txt'), 'x');
const result = await resolveGrantRoot(
makeSql([]),
join(plain, 'just-a-file.txt'),
project,
whitelist,
);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/no repo-shaped ancestor/);
});
it('does not grant the whitelist root itself as a fallback', async () => {
// Even if .git existed at the whitelist root (it doesn't), we'd refuse.
// Easier to assert: a path directly under whitelist with no repo marker.
const direct = join(whitelist, 'lone-file.txt');
await writeFile(direct, 'x');
const result = await resolveGrantRoot(makeSql([]), direct, project, whitelist);
expect(result.ok).toBe(false);
});
});
describe('resolveGrantRoot — symlink-escape-mid-walk guard (Sam 2026-05-22)', () => {
it('refuses a symlinked input whose realpath sits outside the whitelist', async () => {
// The symlink lives nominally inside the whitelist, but its target
// (realpath) is outside. The guard's first realpath() call normalizes
// and the up-front whitelist check refuses immediately.
const link = join(whitelist, 'escape-link');
try {
await symlink(outside, link);
const result = await resolveGrantRoot(
makeSql([]),
join(link, 'secret.txt'),
project,
whitelist,
);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/outside permitted scope/);
} finally {
await rm(link, { force: true });
}
});
it('walk loop terminates at the whitelist root, not at filesystem /', async () => {
// Construct a deep tree with NO repo markers anywhere. Without a bound,
// the walk would chase parents up to "/". The bound flips the loop into
// a refusal once the cursor equals the realpath'd whitelist root.
const deep = join(whitelist, 'a', 'b', 'c', 'd');
await mkdir(deep, { recursive: true });
await writeFile(join(deep, 'leaf.txt'), 'x');
const result = await resolveGrantRoot(makeSql([]), join(deep, 'leaf.txt'), project, whitelist);
expect(result.ok).toBe(false);
if (!result.ok) expect(result.reason).toMatch(/no repo-shaped ancestor/);
});
});
describe('resolveGrantRoot — nearest-project disambiguation', () => {
it('prefers the longest matching project path over a shorter ancestor', async () => {
const outer = whitelist;
const inner = fork; // /whitelist/forks/codecontext, deeper than outer
const result = await resolveGrantRoot(
makeSql([{ path: outer }, { path: inner }]),
join(fork, 'main.go'),
project,
whitelist,
);
expect(result.ok).toBe(true);
if (result.ok) expect(result.root).toBe(inner);
});
});
// Belt-and-suspenders: silence a known dynamic-import warning that vitest
// occasionally emits on transient fs operations in CI but never in dev.
vi.spyOn(console, 'warn').mockImplementation(() => {});