mirror of
https://github.com/deepseek-ai/deepseek-harness
synced 2026-08-15 21:04:50 +00:00
fix: byte-exact value/error caps + write-callback contract (agent review)
Two [P1] review findings on the worker runtime:
- maxValueBytes gated and sliced the rendered fallback by UTF-16 code
units, so a multibyte string ("€€€€" under a 4-byte cap) crossed whole
and a truncated multibyte rendering could still run ~3x over budget.
New truncateUtf8Bytes cuts at code-point boundaries under a real byte
budget; prepareValue's fallback and the host's forged-error-text bound
both use it, and the VALUE_RENDER_SLACK comment drops its now-obsolete
"sliced by characters" wrinkle.
- The patched stream write dropped Node's optional encoding/callback
arguments, so a program awaiting flush completion
(write(chunk, resolve)) hung to the wall ceiling and misreported as a
timeout. The shim now fires the callback asynchronously once the chunk
is admitted — including for writes the exhausted budget drops.
This commit is contained in:
@@ -1,6 +1,6 @@
|
||||
import { describe, expect, it } from 'vitest'
|
||||
import { EventEmitter } from 'node:events'
|
||||
import { LogBuffer, makeConsoleShim, makeNamespaces, captureStreamWrites, prepareValue, runWorkerMain, wireReplies } from '@deepseek-ai/dsh-code-runtime-worker/src/bootstrap.ts'
|
||||
import { LogBuffer, makeConsoleShim, makeNamespaces, captureStreamWrites, prepareValue, runWorkerMain, truncateUtf8Bytes, wireReplies } from '@deepseek-ai/dsh-code-runtime-worker/src/bootstrap.ts'
|
||||
import type { BootstrapPort, PatchableStream, PendingCall } from '@deepseek-ai/dsh-code-runtime-worker/src/bootstrap.ts'
|
||||
import type { ReplyMessage, WorkerToHost } from '@deepseek-ai/dsh-code-runtime-worker/src/protocol.ts'
|
||||
import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
|
||||
@@ -90,6 +90,27 @@ describe('captureStreamWrites', () => {
|
||||
expect(seen[0]).toMatchObject({ source: 'stdout' })
|
||||
expect(underlying).toBe('after')
|
||||
})
|
||||
|
||||
it('invokes the write callback asynchronously, in both optional-encoding shapes', async () => {
|
||||
const buffer = new LogBuffer(1_000, () => {})
|
||||
const stream: PatchableStream = { write: () => true }
|
||||
captureStreamWrites(buffer, stream, 'stdout')
|
||||
const calls: (Error | null | undefined)[] = []
|
||||
stream.write('two-arg', (error?: Error | null) => calls.push(error))
|
||||
stream.write('three-arg', 'utf8', (error?: Error | null) => calls.push(error))
|
||||
// Node's contract: the callback fires after the write call returns.
|
||||
expect(calls).toEqual([])
|
||||
await new Promise<void>(resolve => stream.write('awaited flush', resolve))
|
||||
expect(calls).toEqual([null, null])
|
||||
})
|
||||
|
||||
it('still fires the callback for a write the exhausted budget drops', async () => {
|
||||
const buffer = new LogBuffer(4, () => {})
|
||||
const stream: PatchableStream = { write: () => true }
|
||||
captureStreamWrites(buffer, stream, 'stdout')
|
||||
stream.write('this write overflows the budget and is dropped')
|
||||
await new Promise<void>(resolve => stream.write('also dropped', resolve))
|
||||
})
|
||||
})
|
||||
|
||||
describe('prepareValue', () => {
|
||||
@@ -118,6 +139,34 @@ describe('prepareValue', () => {
|
||||
expect(typeof value).toBe('string')
|
||||
expect(value).toContain('more items')
|
||||
})
|
||||
|
||||
it('caps a multibyte string by UTF-8 bytes, not UTF-16 length', () => {
|
||||
// 4 code units but 12 UTF-8 bytes: a length-counting cap would pass the
|
||||
// full string through untruncated.
|
||||
expect(prepareValue('€€€€', 4)).toEqual({ value: '€… [truncated]' })
|
||||
})
|
||||
|
||||
it('caps a multibyte rendering by UTF-8 bytes too', () => {
|
||||
// Wire size (24-byte string inside an array) exceeds the cap, so the
|
||||
// value crosses as its rendering — whose truncation must also be
|
||||
// byte-exact: "[ '" (3 bytes) + two € (6 bytes) = 9; a third € would
|
||||
// overflow the 10-byte budget.
|
||||
expect(prepareValue(['€€€€€€€€'], 10)).toEqual({ value: "[ '€€… [truncated]" })
|
||||
})
|
||||
})
|
||||
|
||||
describe('truncateUtf8Bytes', () => {
|
||||
it('returns a fitting string whole', () => {
|
||||
expect(truncateUtf8Bytes('fits', 4)).toBe('fits')
|
||||
})
|
||||
|
||||
it('cuts at a code-point boundary, never mid-surrogate-pair', () => {
|
||||
// Each 😀 is one code point, two code units, four UTF-8 bytes: a 5-byte
|
||||
// budget fits exactly one — and never leaves a lone surrogate behind.
|
||||
const cut = truncateUtf8Bytes('😀😀', 5)
|
||||
expect(cut).toBe('😀')
|
||||
expect(Buffer.byteLength(truncateUtf8Bytes('😀😀', 3), 'utf8')).toBe(0)
|
||||
})
|
||||
})
|
||||
|
||||
describe('makeNamespaces', () => {
|
||||
|
||||
@@ -221,6 +221,29 @@ describe('WorkerCodeRuntime — budgets and containment (real workers)', () => {
|
||||
expect(result.value).toBe(`${'y'.repeat(64)}… [truncated]`)
|
||||
})
|
||||
|
||||
it('caps a multibyte return value by UTF-8 bytes, not string length', async () => {
|
||||
// 4 code units, 12 UTF-8 bytes: a length-counting cap would let the full
|
||||
// string cross. The worker's byte-exact capped rendering then passes the
|
||||
// host re-cap unchanged (cap + marker is exactly the granted slack).
|
||||
const { runtime } = await setup({ maxValueBytes: 4 })
|
||||
const result = await runtime.run({ program: 'return "€€€€"', bindings: [] })
|
||||
expect(result.value).toBe('€… [truncated]')
|
||||
})
|
||||
|
||||
it('completes a program that awaits its write callback, capturing the chunk', async () => {
|
||||
// Node's write(chunk[, encoding][, callback]) contract: dropping the
|
||||
// callback would leave this promise pending until the wall ceiling and
|
||||
// misreport a completed program as a timeout.
|
||||
const { runtime } = await setup({ maxWallMs: 2_000 })
|
||||
const result = await runtime.run({
|
||||
program: 'await new Promise(resolve => process.stdout.write("flushed", resolve)); return "done"',
|
||||
bindings: [],
|
||||
})
|
||||
expect(result.error).toBeUndefined()
|
||||
expect(result.value).toBe('done')
|
||||
expect(result.logs).toContainEqual({ source: 'stdout', text: 'flushed' })
|
||||
})
|
||||
|
||||
it('caps a huge container whose bounded rendering is small (wire size, not rendering, is what counts)', async () => {
|
||||
const { runtime } = await setup()
|
||||
const result = await runtime.run({ program: 'return new Array(50_000).fill(7)', bindings: [] })
|
||||
@@ -340,6 +363,21 @@ describe('WorkerCodeRuntime — hostile programs (real workers)', () => {
|
||||
expect(result.error).toEqual({ kind: 'exception', message: 'fake failure' })
|
||||
})
|
||||
|
||||
it('byte-bounds forged multibyte error text at the host', async () => {
|
||||
// Forged error text bypasses the worker entirely; the host bound is a
|
||||
// BYTE bound (two € = 6 bytes fit an 8-byte cap, a third would not).
|
||||
const { runtime } = await setup({ maxValueBytes: 8 })
|
||||
const result = await runtime.run({
|
||||
program: `
|
||||
const { parentPort } = await import('node:worker_threads');
|
||||
parentPort.postMessage({ type: 'done', error: { message: '€'.repeat(1000) } });
|
||||
for (;;) {}
|
||||
`,
|
||||
bindings: [],
|
||||
})
|
||||
expect(result.error).toEqual({ kind: 'exception', message: '€€' })
|
||||
})
|
||||
|
||||
it('answers a binding whose resolution cannot be cloned with a failure reply', async () => {
|
||||
const { runtime } = await setup()
|
||||
const result = await runtime.run({
|
||||
|
||||
Reference in New Issue
Block a user