refactor: prune code runtime surface

This commit is contained in:
Tianyi Cui
2026-07-14 03:07:41 +08:00
parent 0236a12324
commit 01da49a3ab
19 changed files with 100 additions and 163 deletions
@@ -12,7 +12,6 @@
import { inspect } from 'node:util'
import { serialize } from 'node:v8'
import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
import { logTruncationMarker } from './protocol.ts'
import type { DoneMessage, ReplyMessage, WorkerBootData, WorkerToHost } from './protocol.ts'
@@ -33,12 +32,12 @@ export interface PatchableStream {
}
/**
* Ordered log capture under one shared byte budget, delivered to a sink as
* each entry lands (the real sink streams entries over the port eagerly, so
* Ordered text capture under one shared byte budget, delivered to a sink as
* each item lands (the real sink streams text over the port eagerly, so
* captured output survives a mid-run termination). Once the budget is
* exhausted it emits exactly one in-band marker entry (on the `stderr`
* diagnostics channel) and silently drops everything after — the cap is a
* blast-radius bound, so "how much was lost" intentionally stays unmeasured.
* exhausted it emits exactly one in-band marker and silently drops everything
* after. The cap is a blast-radius bound, so "how much was lost" intentionally
* stays unmeasured.
*/
export class LogBuffer {
private remaining: number
@@ -47,28 +46,28 @@ export class LogBuffer {
// under Node's native strip-only mode, which rejects non-erasable syntax —
// and parameter properties are non-erasable.
private readonly maxBytes: number
private readonly sink: (entry: CodeLogEntry) => void
private readonly sink: (text: string) => void
constructor(maxBytes: number, sink: (entry: CodeLogEntry) => void) {
constructor(maxBytes: number, sink: (text: string) => void) {
this.maxBytes = maxBytes
this.sink = sink
this.remaining = maxBytes
}
/**
* Emit one entry to the sink, charging its text against the budget (drops + marks once exhausted).
* @param entry - the log entry to deliver.
* Emit text to the sink, charging it against the budget (drops + marks once exhausted).
* @param text - the captured text to deliver.
*/
push(entry: CodeLogEntry): void {
push(text: string): void {
if (this.truncated) return
const cost = Buffer.byteLength(entry.text, 'utf8')
const cost = Buffer.byteLength(text, 'utf8')
if (cost > this.remaining) {
this.truncated = true
this.sink({ source: 'stderr', text: logTruncationMarker(this.maxBytes) })
this.sink(logTruncationMarker(this.maxBytes))
return
}
this.remaining -= cost
this.sink(entry)
this.sink(text)
}
}
@@ -89,7 +88,7 @@ export function makeConsoleShim(logs: LogBuffer): Record<(typeof CONSOLE_LEVELS)
args.map(arg => typeof arg === 'string' ? arg : inspect(arg, INSPECT_OPTIONS)).join(' ')
const shim = Object.create(null) as Record<(typeof CONSOLE_LEVELS)[number], (...args: unknown[]) => void>
for (const level of CONSOLE_LEVELS) {
shim[level] = (...args: unknown[]) => { logs.push({ source: 'console', level, text: render(args) }) }
shim[level] = (...args: unknown[]) => { logs.push(render(args)) }
}
return shim
}
@@ -104,17 +103,16 @@ export function makeConsoleShim(logs: LogBuffer): Record<(typeof CONSOLE_LEVELS)
* even for writes the exhausted budget drops.
* @param logs - the buffer captured writes are pushed into.
* @param stream - the stream whose `write` slot is patched.
* @param source - the log source the captured writes are attributed to.
* @returns the restore function (the in-process tests un-patch; the real
* worker never needs to).
*/
export function captureStreamWrites(logs: LogBuffer, stream: PatchableStream, source: 'stdout' | 'stderr'): () => void {
export function captureStreamWrites(logs: LogBuffer, stream: PatchableStream): () => void {
// The slot's VALUE is stored for restore and reassigned — never invoked
// detached, so the unbound-method concern does not apply.
// eslint-disable-next-line @typescript-eslint/unbound-method
const original = stream.write
stream.write = (chunk: unknown, ...rest: unknown[]): boolean => {
logs.push({ source, text: typeof chunk === 'string' ? chunk : String(chunk) })
logs.push(typeof chunk === 'string' ? chunk : String(chunk))
// Node's optional-encoding shape: the callback is whichever of the next
// two positions holds a function (a non-function there is the encoding).
const callback = [rest[0], rest[1]].find(
@@ -273,9 +271,9 @@ export async function runWorkerMain(
data: WorkerBootData,
streams: { stdout: PatchableStream; stderr: PatchableStream },
): Promise<void> {
const logs = new LogBuffer(data.maxLogBytes, (entry) => { port.postMessage({ type: 'log', entry }) })
captureStreamWrites(logs, streams.stdout, 'stdout')
captureStreamWrites(logs, streams.stderr, 'stderr')
const logs = new LogBuffer(data.maxLogBytes, (text) => { port.postMessage({ type: 'log', text }) })
captureStreamWrites(logs, streams.stdout)
captureStreamWrites(logs, streams.stderr)
const pending = new Map<number, PendingCall>()
wireReplies(port, pending)
@@ -18,7 +18,7 @@ import { fileURLToPath } from 'node:url'
import { Context } from 'cordis'
import z from 'schemastery'
import { CodeRuntime } from '@deepseek-ai/dsh-code-runtime'
import type { CodeBindingFunction, CodeLogEntry, CodeRunFailure, CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import type { CodeBindingFunction, CodeRunFailure, CodeRunRequest, CodeRunResult } from '@deepseek-ai/dsh-code-runtime'
import { prepareValue, truncateUtf8Bytes } from './bootstrap.ts'
import { logTruncationMarker } from './protocol.ts'
import type { ReplyMessage, WorkerBootData, WorkerToHost } from './protocol.ts'
@@ -118,10 +118,6 @@ function messageOf(error: unknown): string {
return error instanceof Error ? error.message : String(error)
}
/** The log sources / console levels the seam vocabulary admits, as runtime sets for inbound-message validation. */
const LOG_SOURCES = new Set<string>(['console', 'stdout', 'stderr'])
const LOG_LEVELS = new Set<string>(['log', 'info', 'warn', 'error', 'debug'])
/**
* Runtime shape gate for inbound port traffic. The peer runs MODEL CODE and
* can post anything — `null`, primitives, objects with poisoned fields — so
@@ -140,20 +136,8 @@ function parseWorkerMessage(raw: unknown): WorkerToHost | undefined {
return { type: 'call', id: m.id, global: m.global, name: m.name, args: m.args }
}
case 'log': {
const entry = m.entry
if (typeof entry !== 'object' || entry === null) return undefined
const e = entry as Record<string, unknown>
if (typeof e.text !== 'string') return undefined
if (typeof e.source !== 'string' || !LOG_SOURCES.has(e.source)) return undefined
if (e.level !== undefined && (typeof e.level !== 'string' || !LOG_LEVELS.has(e.level))) return undefined
return {
type: 'log',
entry: {
source: e.source as CodeLogEntry['source'],
...e.level !== undefined ? { level: e.level as Exclude<CodeLogEntry['level'], undefined> } : {},
text: e.text,
},
}
if (typeof m.text !== 'string') return undefined
return { type: 'log', text: m.text }
}
case 'done': {
if (m.error === undefined) return { type: 'done', ...m.value !== undefined ? { value: m.value } : {} }
@@ -299,8 +283,8 @@ export class WorkerCodeRuntime extends CodeRuntime {
return new Promise<CodeRunResult>((resolve) => {
let settled = false
const answered = new Set<number>()
const logs: CodeLogEntry[] = []
const strayLogs: CodeLogEntry[] = []
const logs: string[] = []
const strayLogs: string[] = []
// ONE host-side ledger for everything that lands in `logs`/`strayLogs`,
// whatever the path: honest port entries, FORGED port entries (model
@@ -310,26 +294,26 @@ export class WorkerCodeRuntime extends CodeRuntime {
// so the documented cap is one shared `maxLogBytes` however it is hit.
let logBudget = this.config.maxLogBytes
let logsTruncated = false
const admit = (entry: CodeLogEntry, sink: CodeLogEntry[]): void => {
const admit = (text: string, sink: string[]): void => {
if (logsTruncated) return
const cost = Buffer.byteLength(entry.text, 'utf8')
const cost = Buffer.byteLength(text, 'utf8')
if (cost > logBudget) {
logsTruncated = true
sink.push({ source: 'stderr', text: logTruncationMarker(this.config.maxLogBytes) })
sink.push(logTruncationMarker(this.config.maxLogBytes))
return
}
logBudget -= cost
sink.push(entry)
sink.push(text)
}
// No settled guard: `finish` snapshots the arrays when it resolves, so
// a chunk flushing after settlement mutates only the discarded buffers,
// and the ledger bounds that growth until the pipes close.
const captureStray = (source: 'stdout' | 'stderr') => (chunk: Buffer) => {
admit({ source, text: chunk.toString('utf8') }, strayLogs)
const captureStray = (chunk: Buffer): void => {
admit(chunk.toString('utf8'), strayLogs)
}
worker.stdout.on('data', captureStray('stdout'))
worker.stderr.on('data', captureStray('stderr'))
worker.stdout.on('data', captureStray)
worker.stderr.on('data', captureStray)
// Settlement: exactly one outcome wins; every path funnels through
// here, cleans up the timers/listeners, terminates the worker, and
@@ -404,7 +388,7 @@ export class WorkerCodeRuntime extends CodeRuntime {
// this listener would crash the host process. Junk drops silently.
const message = parseWorkerMessage(raw)
if (!message) return
if (message.type === 'log' && !settled) admit(message.entry, logs)
if (message.type === 'log' && !settled) admit(message.text, logs)
onCall(message)
onDone(message)
})
@@ -9,8 +9,6 @@
* @module @deepseek-ai/dsh-code-runtime-worker/src/protocol
*/
import type { CodeLogEntry } from '@deepseek-ai/dsh-code-runtime'
/** What the host hands the worker at spawn, via `workerData`. */
export interface WorkerBootData {
/** The type-stripped (plain JS) program body. */
@@ -36,10 +34,10 @@ export interface CallMessage {
args: unknown
}
/** Worker → host: one captured log entry, streamed eagerly so output survives a mid-run termination (timeout, abort, OOM). */
export interface LogMessage {
/** Worker → host: captured text, streamed eagerly so output survives a mid-run termination (timeout, abort, OOM). */
interface LogMessage {
type: 'log'
entry: CodeLogEntry
text: string
}
/**