kingwl
9aaa4a871f
Review fixes (ds-review-bot on #623): - overrideOf (both knobs) rejects a seedLength past the log end before slicing: a malformed durable boundary would otherwise empty the own-switch slice until the log outgrew it, letting a wide baseline shadow a REAL later tightening. Malformed durable metadata fails loud, never open. - The session-query derived index carries the two baseline fields end to end: schema columns on both session tables (SESSION_QUERY_SQLITE_SCHEMA _VERSION 6 — derived, rebuilds in place), inserts, header selects, the candidates CTE, rowHeader, sameHeader, and the cross-source assertSessionHeadersCompatible — so a search hit's header keeps the child's inherited confinement and conflicting live/persisted baselines reject. Red-first: out-of-range seedLength tests in both policy suites; baseline round-trip and live/persisted baseline-conflict tests in the session-query sqlite suite.
233 lines
10 KiB
TypeScript
233 lines
10 KiB
TypeScript
/**
|
|
* Tests for the sandbox-policy home: the deployment default (mode +
|
|
* workspaceRoot) the service exposes, and the per-session `sandbox/mode`
|
|
* override kit (fold + write path) both enforcing families read.
|
|
*/
|
|
|
|
import { mkdirSync, mkdtempSync, realpathSync, rmSync, symlinkSync } from 'node:fs'
|
|
import { tmpdir } from 'node:os'
|
|
import { join, resolve, sep } from 'node:path'
|
|
import { describe, expect, it } from 'vitest'
|
|
import { Context } from 'cordis'
|
|
import { Session, SessionId } from '@deepseek-ai/dsh-session'
|
|
import SandboxPolicyService, { SANDBOX_MODES, effectiveSandboxMode, setSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
|
|
|
|
async function mounted(config: { mode?: 'read-only' | 'workspace-write' | 'danger-full-access'; workspaceRoot?: string } = {}) {
|
|
const ctx = new Context()
|
|
await ctx.plugin(SandboxPolicyService, config)
|
|
return ctx
|
|
}
|
|
|
|
function session(id: string, cwd?: string): Session {
|
|
const sessionId = SessionId(id)
|
|
return new Session(sessionId, undefined, {
|
|
version: 0,
|
|
id: sessionId,
|
|
createdAt: 0,
|
|
...cwd === undefined ? {} : { cwd },
|
|
})
|
|
}
|
|
|
|
describe('SandboxPolicyService', () => {
|
|
it('defaults to read-only under the process cwd', async () => {
|
|
const ctx = await mounted()
|
|
expect(ctx.sandboxPolicy.defaultMode).toBe('read-only')
|
|
expect(ctx.sandboxPolicy.workspaceRoot).toBe(resolve(process.cwd()))
|
|
})
|
|
|
|
it('carries a configured mode and resolves the workspace root absolute', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write', workspaceRoot: '/ws/../ws/./sub' })
|
|
expect(ctx.sandboxPolicy.defaultMode).toBe('workspace-write')
|
|
expect(ctx.sandboxPolicy.workspaceRoot).toBe(resolve('/ws/../ws/./sub'))
|
|
})
|
|
|
|
it('resolves the deployment policy for an agentless call', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write', workspaceRoot: '/fallback' })
|
|
expect(ctx.sandboxPolicy.resolve()).toEqual({
|
|
mode: 'workspace-write',
|
|
workspaceRoot: resolve('/fallback'),
|
|
})
|
|
})
|
|
|
|
it('resolves each session mode and cwd together without changing the fallback', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write', workspaceRoot: '/fallback' })
|
|
const first = session('sess-first', '/projects/first')
|
|
const second = session('sess-second', '/projects/second')
|
|
setSandboxMode(second, 'read-only')
|
|
|
|
expect(ctx.sandboxPolicy.resolve({ session: first })).toEqual({
|
|
mode: 'workspace-write',
|
|
workspaceRoot: resolve('/projects/first'),
|
|
})
|
|
expect(ctx.sandboxPolicy.resolve({ session: second })).toEqual({
|
|
mode: 'read-only',
|
|
workspaceRoot: resolve('/projects/second'),
|
|
})
|
|
expect(ctx.sandboxPolicy.resolve()).toEqual({
|
|
mode: 'workspace-write',
|
|
workspaceRoot: resolve('/fallback'),
|
|
})
|
|
})
|
|
|
|
it.skipIf(process.platform === 'win32')('resolves a symlink-sensitive session cwd with POSIX component semantics', async () => {
|
|
const root = mkdtempSync(join(tmpdir(), 'dsh-policy-cwd-'))
|
|
try {
|
|
const lexical = join(root, 'lexical')
|
|
const physical = join(root, 'physical')
|
|
const child = join(physical, 'child')
|
|
mkdirSync(lexical)
|
|
mkdirSync(child, { recursive: true })
|
|
const link = join(lexical, 'link')
|
|
symlinkSync(child, link, 'dir')
|
|
const cwd = `${link}${sep}..`
|
|
const ctx = await mounted({ mode: 'workspace-write', workspaceRoot: '/fallback' })
|
|
|
|
expect(ctx.sandboxPolicy.resolve({ session: session('sess-symlink-parent', cwd) })).toEqual({
|
|
mode: 'workspace-write',
|
|
workspaceRoot: realpathSync.native(physical),
|
|
})
|
|
} finally {
|
|
rmSync(root, { recursive: true, force: true })
|
|
}
|
|
})
|
|
|
|
it('lets an approved mode outrank the session mode while retaining its root', async () => {
|
|
const ctx = await mounted({ workspaceRoot: '/fallback' })
|
|
const active = session('sess-approved', '/projects/approved')
|
|
setSandboxMode(active, 'read-only')
|
|
expect(ctx.sandboxPolicy.resolve({ session: active, mode: 'danger-full-access' })).toEqual({
|
|
mode: 'danger-full-access',
|
|
workspaceRoot: resolve('/projects/approved'),
|
|
})
|
|
})
|
|
|
|
it('uses the configured root when a session has no cwd', async () => {
|
|
const ctx = await mounted({ workspaceRoot: '/fallback' })
|
|
expect(ctx.sandboxPolicy.resolve({ session: session('sess-no-cwd') }).workspaceRoot).toBe(resolve('/fallback'))
|
|
})
|
|
|
|
it('rejects a mode outside the closed vocabulary at load', async () => {
|
|
const ctx = new Context()
|
|
// schemastery rejects the union violation when the plugin loads.
|
|
await expect(ctx.plugin(SandboxPolicyService, { mode: 'yolo' as never })).rejects.toThrow()
|
|
})
|
|
|
|
it('unregisters cleanly from a child fiber (HMR safety)', async () => {
|
|
const ctx = new Context()
|
|
const fiber = await ctx.plugin(SandboxPolicyService, {})
|
|
expect(ctx.sandboxPolicy).toBeDefined()
|
|
await fiber.dispose()
|
|
expect(ctx.get('sandboxPolicy')).toBeUndefined()
|
|
})
|
|
})
|
|
|
|
describe('the sandbox/mode session kit', () => {
|
|
it('SANDBOX_MODES lists every mode for advertisement and validation', () => {
|
|
expect(SANDBOX_MODES).toEqual(['read-only', 'workspace-write', 'danger-full-access'])
|
|
})
|
|
|
|
it('effectiveSandboxMode folds to the last switch, or undefined without one', () => {
|
|
const session = new Session(SessionId('sess-fold'))
|
|
expect(effectiveSandboxMode(session.events)).toBeUndefined()
|
|
setSandboxMode(session, 'workspace-write')
|
|
setSandboxMode(session, 'read-only')
|
|
expect(effectiveSandboxMode(session.events)).toBe('read-only')
|
|
})
|
|
|
|
it('setSandboxMode appends exactly one sandbox/mode event per switch', () => {
|
|
const session = new Session(SessionId('sess-write'))
|
|
setSandboxMode(session, 'danger-full-access')
|
|
const modeEvents = session.events.filter(e => e.type === 'sandbox/mode')
|
|
expect(modeEvents).toHaveLength(1)
|
|
expect(modeEvents[0]?.data).toEqual({ mode: 'danger-full-access' })
|
|
})
|
|
})
|
|
|
|
describe('delegation inheritance (overrideOf over the header baseline)', () => {
|
|
/** A session whose header carries the delegation-inheritance baseline. */
|
|
function inheritedSession(id: string, meta: { sandboxMode?: string; seedLength?: number } = {}): Session {
|
|
const sessionId = SessionId(id)
|
|
return new Session(sessionId, undefined, {
|
|
version: 0,
|
|
id: sessionId,
|
|
createdAt: 0,
|
|
...meta.sandboxMode === undefined ? {} : { sandboxMode: meta.sandboxMode },
|
|
...meta.seedLength === undefined ? {} : { seedLength: meta.seedLength },
|
|
})
|
|
}
|
|
|
|
it('overrideOf folds the session log and never falls back to the deployment default', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write' })
|
|
const parent = session('sess-inherit-parent')
|
|
setSandboxMode(parent, 'workspace-write')
|
|
setSandboxMode(parent, 'read-only')
|
|
|
|
expect(ctx.sandboxPolicy.overrideOf(parent)).toBe('read-only')
|
|
// undefined, NOT the deployment default — a child whose header froze the
|
|
// default would stop following the LIVE default across resumes.
|
|
expect(ctx.sandboxPolicy.overrideOf(session('sess-inherit-unswitched'))).toBeUndefined()
|
|
})
|
|
|
|
it('overrideOf reads the header baseline when the log has no own switch', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write' })
|
|
const child = inheritedSession('sess-inherit-baseline', { sandboxMode: 'read-only' })
|
|
|
|
expect(ctx.sandboxPolicy.overrideOf(child)).toBe('read-only')
|
|
// resolve() consumes the same chain, so enforcement sees the baseline.
|
|
expect(ctx.sandboxPolicy.resolve({ session: child }).mode).toBe('read-only')
|
|
})
|
|
|
|
it('a seed-carried stale switch loses to the baseline; an OWN later switch wins over it', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write' })
|
|
// The fork seed carried the parent's OLD workspace-write switch (one
|
|
// event, so seedLength 1); the delegation-time baseline is read-only.
|
|
const child = inheritedSession('sess-inherit-slice', { sandboxMode: 'read-only', seedLength: 1 })
|
|
setSandboxMode(child, 'workspace-write')
|
|
expect(ctx.sandboxPolicy.overrideOf(child)).toBe('read-only')
|
|
// A switch the child makes ITSELF (after the seed boundary) outranks it.
|
|
setSandboxMode(child, 'danger-full-access')
|
|
expect(ctx.sandboxPolicy.overrideOf(child)).toBe('danger-full-access')
|
|
})
|
|
|
|
it('rejects a header baseline outside the closed mode vocabulary (durable boundary)', async () => {
|
|
const ctx = await mounted()
|
|
const child = inheritedSession('sess-inherit-invalid', { sandboxMode: 'yolo' })
|
|
|
|
expect(() => ctx.sandboxPolicy.overrideOf(child)).toThrow(/sandboxMode/)
|
|
})
|
|
|
|
it('rejects a malformed baseline even when an own switch would win (validation is unconditional)', async () => {
|
|
const ctx = await mounted()
|
|
const child = inheritedSession('sess-inherit-invalid-own', { sandboxMode: 'yolo' })
|
|
// A corrupt or foreign durable record must fail loud on EVERY read — an
|
|
// own override must not paper over the malformed header.
|
|
setSandboxMode(child, 'read-only')
|
|
|
|
expect(() => ctx.sandboxPolicy.overrideOf(child)).toThrow(/sandboxMode/)
|
|
})
|
|
|
|
it('a generic SessionStore.fork child (seedLength, NO baseline) keeps its seed-carried override', async () => {
|
|
const ctx = await mounted({ mode: 'workspace-write' })
|
|
// The public fork path sets seedLength but captures no delegation
|
|
// baseline; the seed boundary must not discard the replayed policy state
|
|
// it exists to subsume — with nothing to subsume it, seeded switches ARE
|
|
// the child's inherited truth.
|
|
const child = inheritedSession('sess-generic-fork', { seedLength: 1 })
|
|
setSandboxMode(child, 'read-only')
|
|
|
|
expect(ctx.sandboxPolicy.overrideOf(child)).toBe('read-only')
|
|
expect(ctx.sandboxPolicy.resolve({ session: child }).mode).toBe('read-only')
|
|
})
|
|
|
|
it('rejects a seed boundary past the log end instead of silently ignoring own switches', async () => {
|
|
const ctx = await mounted()
|
|
// A malformed durable seedLength beyond the log would make the own-switch
|
|
// slice empty until the log grows past it — a wide baseline would then
|
|
// shadow a REAL later tightening. Fail loud at the durable boundary.
|
|
const child = inheritedSession('sess-inherit-oob', { sandboxMode: 'danger-full-access', seedLength: 100 })
|
|
setSandboxMode(child, 'read-only')
|
|
|
|
expect(() => ctx.sandboxPolicy.overrideOf(child)).toThrow(/seedLength/)
|
|
})
|
|
})
|