fix(code-runtime): accept deeply nested JSON

This commit is contained in:
Tianyi Cui
2026-07-22 02:13:37 +08:00
parent 3f93d4ddbd
commit f2d86b232e
7 changed files with 119 additions and 44 deletions
@@ -22,7 +22,7 @@ Every field is validated and defaulted; `maxOutputBytes` is a safe integer of at
- **Type-strip host-side, in execution context** — the program is wrapped in an async-function shell, stripped with `node:module`'s `stripTypeScriptTypes` (erasable syntax only — `enum`/namespaces are rejected as a program `exception` and no worker spawns), and sliced back out byte-positioned; it then executes as the body of an `AsyncFunction`, so top-level `await`/`return` work.
- **The port assumes a hostile peer** — model code can reach `parentPort` and forge traffic, so every inbound message is shape-validated and REBUILT before anything reads it (`null`, primitives, junk types, and malformed payloads drop without a throw; forged extra fields never ride along), the host answers each call id at most once, resolves binding names as OWN properties only (a forged `constructor` cannot walk a prototype chain), drops post-settlement replies, and validates every binding resolution and completion as lossless JSON. Forged `log`/`done` messages cannot bypass the outer cap: the host repeats validation and accounts every admitted log plus the completion or diagnostic. Worker-side namespaces are null-prototype with `defineProperty`, so `__proto__`-shaped binding names are ordinary keys.
- **Two independent budgets, because the peer is hostile** — `computeMs` meters the worker's MEASURED busy time (`worker.performance.eventLoopUtilization()` polling): a hot loop cannot hide behind a pending decoy dispatch, and a program awaiting a slow tool accrues nothing. `maxWallMs` backstops what busy time cannot see (awaiting a promise nobody resolves). Both funnel into `worker.terminate()`, which ends hot synchronous loops too; heap overflow surfaces as the worker's OOM exit (`kind: 'worker-exit'`).
- **Intermediate binding values are complete JSON** — binding arguments and resolutions cross by structured clone after lossless-JSON validation and have no byte cap. They never enter the outer-output ledger or model context; provider/executor acquisition bounds and process/worker memory remain the limits.
- **Intermediate binding values are complete JSON** — binding arguments and resolutions cross by structured clone after iterative lossless-JSON validation and have no byte or call-stack depth cap. They never enter the outer-output ledger or model context; provider/executor acquisition bounds and process/worker memory remain the limits.
- **Logs stream eagerly into one outer ledger** — console/stdout/stderr text crosses the port in emission order, so a timed-out or killed program still shows what it printed. Native writes that bypass the patched stream slots arrive on pipes independent of the completion port; settlement therefore continues bounded pipe capture until worker termination completes before materializing the result. `maxOutputBytes` accounts the JSON serialization of the outer `logs` array plus the completion value or failure diagnostic. At or below the cap the exact value returns; a lossy completion is `invalid-output`, and a combined overflow is `output-limit` rather than a substituted inspected string. The failure retains the fitting captured prefix and later follows the normal outer `run_code` spill policy.
- **Empty environment** — the worker gets `env: {}` and `execArgv: []`: no ambient credentials (stronger than the scrubbed-env rule for spawned commands) and no inherited loader flags.
- **Dispose to quiescence** — teardown fails in-flight runs as `abort` and AWAITS each worker's exit before resolving.
@@ -40,71 +40,114 @@ function enumerableStringKeys(value: object): string[] | undefined {
if (keys.some(key => typeof key !== 'string' || !Object.prototype.propertyIsEnumerable.call(value, key))) return undefined
return keys as string[]
}
/* jscpd:ignore-end */
type SnapshotDestination =
| { kind: 'root' }
| { kind: 'array'; target: CodeJsonValue[]; index: number }
| { kind: 'object'; target: Record<string, CodeJsonValue>; key: string }
type SnapshotTask =
| { kind: 'visit'; value: unknown; destination: SnapshotDestination }
| { kind: 'array-item'; source: unknown[]; index: number; target: CodeJsonValue[] }
| { kind: 'object-property'; source: Record<string, unknown>; key: string; target: Record<string, CodeJsonValue> }
| { kind: 'leave'; source: object }
/**
* Validate and detach one worker-boundary value without loading another
* workspace package at runtime. This mirrors the session-owned canonical
* JSON boundary while remaining safe to import from the unbuilt worker.
* Its iterative traversal adds no JavaScript call-stack depth limit.
*
* @param value - the candidate completion value.
* @returns a detached lossless-JSON snapshot, or `undefined` when invalid.
*/
export function snapshotCodeJsonValue(value: unknown): CodeJsonValue | undefined {
const active = new Set<object>()
const within = <T extends CodeJsonValue>(source: object, build: () => T | undefined): T | undefined => {
if (active.has(source)) return undefined
active.add(source)
try {
return build()
} finally {
active.delete(source)
let root: CodeJsonValue | undefined
const assign = (destination: SnapshotDestination, item: CodeJsonValue): void => {
if (destination.kind === 'root') {
root = item
} else if (destination.kind === 'array') {
destination.target[destination.index] = item
} else {
Object.defineProperty(destination.target, destination.key, {
value: item,
enumerable: true,
configurable: true,
writable: true,
})
}
}
const copy = (candidate: unknown): CodeJsonValue | undefined => {
if (candidate === null) return null
if (typeof candidate === 'boolean' || typeof candidate === 'string') return candidate
const tasks: SnapshotTask[] = [{ kind: 'visit', value, destination: { kind: 'root' } }]
for (let task = tasks.pop(); task !== undefined; task = tasks.pop()) {
if (task.kind === 'leave') {
active.delete(task.source)
continue
}
if (task.kind === 'array-item') {
if (!Object.hasOwn(task.source, task.index)) return undefined
tasks.push({
kind: 'visit',
value: task.source[task.index],
destination: { kind: 'array', target: task.target, index: task.index },
})
continue
}
if (task.kind === 'object-property') {
tasks.push({
kind: 'visit',
value: task.source[task.key],
destination: { kind: 'object', target: task.target, key: task.key },
})
continue
}
const candidate = task.value
if (candidate === null) {
assign(task.destination, null)
continue
}
if (typeof candidate === 'boolean' || typeof candidate === 'string') {
assign(task.destination, candidate)
continue
}
if (typeof candidate === 'number') {
return Number.isFinite(candidate) && !Object.is(candidate, -0) ? candidate : undefined
if (!Number.isFinite(candidate) || Object.is(candidate, -0)) return undefined
assign(task.destination, candidate)
continue
}
if (typeof candidate !== 'object') return undefined
if (active.has(candidate)) return undefined
if (Array.isArray(candidate)) {
if (!hasPlainArrayPrototype(candidate)) return undefined
const length = candidate.length
if (Reflect.ownKeys(candidate).length !== length + 1) return undefined
return within(candidate, () => {
const result: CodeJsonValue[] = []
for (let index = 0; index < length; index++) {
if (!Object.hasOwn(candidate, index)) return undefined
const item = copy(candidate[index])
if (item === undefined) return undefined
result.push(item)
}
return result
})
const target: CodeJsonValue[] = []
assign(task.destination, target)
active.add(candidate)
tasks.push({ kind: 'leave', source: candidate })
for (let index = length - 1; index >= 0; index--) {
tasks.push({ kind: 'array-item', source: candidate, index, target })
}
continue
}
if (!hasPlainObjectPrototype(candidate)) return undefined
const keys = enumerableStringKeys(candidate)
if (keys === undefined) return undefined
return within(candidate, () => {
const result: Record<string, CodeJsonValue> = {}
for (const key of keys) {
const item = copy((candidate as Record<string, unknown>)[key])
if (item === undefined) return undefined
Object.defineProperty(result, key, {
value: item,
enumerable: true,
configurable: true,
writable: true,
})
}
return result
})
const target: Record<string, CodeJsonValue> = {}
assign(task.destination, target)
active.add(candidate)
tasks.push({ kind: 'leave', source: candidate })
for (let index = keys.length - 1; index >= 0; index--) {
const key = keys[index]
/* v8 ignore next -- the loop is bounded by the captured key count. */
if (key === undefined) return undefined
tasks.push({ kind: 'object-property', source: candidate as Record<string, unknown>, key, target })
}
}
return copy(value)
return root
}
/* jscpd:ignore-end */
@@ -74,6 +74,26 @@ describe('WorkerCodeRuntime — programs and bindings (real workers)', () => {
expect(calls).toEqual([{ n: 1 }])
})
it('bridges a deeply nested lossless JSON argument, resolution, and completion', async () => {
const { runtime } = await setup()
const result = await runtime.run({
program: `
let value = 'leaf';
for (let depth = 0; depth < 3_000; depth++) value = [value];
return await tools.echo(value);
`,
bindings: tools({ echo: async args => args }),
})
expect(result.error).toBeUndefined()
let cursor = result.value
for (let depth = 0; depth < 3_000; depth++) {
expect(Array.isArray(cursor)).toBe(true)
cursor = Array.isArray(cursor) ? cursor[0] : undefined
}
expect(cursor).toBe('leaf')
})
it('reports non-erasable syntax as an exception without spawning a worker', async () => {
const { runtime } = await setup()
const result = await runtime.run({ program: 'enum E { A }\nreturn 1', bindings: [] })
@@ -64,6 +64,18 @@ describe('snapshotCodeJsonValue', () => {
expect(snapshot[0]?.['__proto__']).toEqual({ safe: true })
})
it('accepts deeply nested valid JSON without using the JavaScript call stack', () => {
let value: unknown = 'leaf'
for (let depth = 0; depth < 5_000; depth++) value = [value]
let cursor = snapshotCodeJsonValue(value)
for (let depth = 0; depth < 5_000; depth++) {
expect(Array.isArray(cursor)).toBe(true)
cursor = Array.isArray(cursor) ? cursor[0] : undefined
}
expect(cursor).toBe('leaf')
})
it('rejects exotic containers, sparse arrays, cycles, and invalid children', () => {
class ExoticObject {
readonly value = 1