Merge remote-tracking branch 'origin/master' into feat/adr0016-type-build-check

This commit is contained in:
imccyu
2026-06-22 00:35:51 +08:00
365 changed files with 13601 additions and 7241 deletions

View File

@@ -0,0 +1,29 @@
# @deepseek-ai/dsh-bash-local
Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `LocalBashExecutor` spawns `bash -c <command>` per call in its own process group, collects bounded output with full-stream spill files, and escalates kills SIGTERM→SIGKILL across the whole group.
## Config
```yaml
- id: bash
name: '@deepseek-ai/dsh-bash-local'
config:
cwd: /path/to/workspace # default: process.cwd()
timeoutMs: 120000 # default foreground timeout
maxTimeoutMs: 600000 # cap for per-call overrides
maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk
```
## Behavior (and where it came from)
Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi; the notable choices:
- **Spawn per call, no shell state** — every call is a fresh non-login `bash -c` (deterministic; no rc files). All four surveyed tools spawn per call. `XXX(stateful-shell)` in `src/run.ts` records the two proven stateful designs (Claude Code's cwd-only persistence; Codex's PTY exec sessions) for when real workflows demand them.
- **Process-group kills with escalation** — children are spawned `detached` (own process group); kills send SIGTERM to the group, then SIGKILL after a 3s grace (OpenCode's escalation; pipelines and subshells die with the parent). ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
- **Tail-keep truncation + spill files** — output beyond `maxOutputBytes` keeps the in-memory TAIL (errors/results cluster at the end — pi/OpenCode rationale) while the FULL stream is appended to a temp file whose path is reported when available. If the final spill close reports a delayed writeback failure, the executor still returns the tail but withholds the path rather than advertising a possibly incomplete file.
- **Model-friendly env** — `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results.
- **Background tasks** — `start()` returns immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), `readOutput()` is incremental with whole-stream byte offsets, and disposal kills everything. The spec's opaque `owner` token is stored on the tracked task and returned by `ownerOf(id)` — the executor never interprets it (the consumer's access policy does), and because it lives with the task here it survives a `tool-bash` HMR reload.
## Sandboxing
`TODO(permissions/sandbox)`: execution policy does NOT belong in this package. Wrap the `tools/execute` waterfall (veto/ask) or implement a sandboxing `BashExecutor` — see docs/architecture.md § plugin checklist. Reference points: Claude Code wraps commands in sandbox-exec/bubblewrap; Codex applies seatbelt/landlock plus an execpolicy prefix-rule engine.

View File

@@ -0,0 +1,35 @@
{
"name": "@deepseek-ai/dsh-bash-local",
"description": "Local-subprocess implementation of the DeepSeek Harness bash executor seam",
"version": "0.0.1",
"private": true,
"type": "module",
"main": "lib/index.js",
"types": "lib/types/index.d.ts",
"exports": {
".": {
"types": "./lib/types/index.d.ts",
"default": "./lib/index.js"
},
"./src/*": "./src/*",
"./package.json": "./package.json"
},
"files": [
"lib/index.js",
"lib/types/**/*.d.ts",
"lib/types/**/*.d.ts.map",
"src"
],
"license": "BSD-3-Clause",
"peerDependencies": {
"@deepseek-ai/dsh-bash": "^0.0.1",
"cordis": "^4.0.0-rc.6"
},
"dependencies": {
"schemastery": "^3.18.0"
},
"devDependencies": {
"@deepseek-ai/dsh-bash": "workspace:^",
"cordis": "^4.0.0-rc.6"
}
}

View File

@@ -0,0 +1,226 @@
/**
* `LocalBashExecutor`: the local-subprocess implementation of the
* `@deepseek-ai/dsh-bash` executor seam. Spawns `bash -c` per call in its
* own process group (see `./run.ts` for the plumbing and the agent-tool
* survey notes), tracks background tasks, and kills everything on dispose.
*
* TODO(permissions/sandbox): execution policy does NOT belong here — wrap
* the `tools/execute` waterfall (see docs/architecture.md § plugin
* checklist) or implement a sandboxing `BashExecutor`. Reference points:
* Claude Code wraps commands in sandbox-exec/bubblewrap; Codex applies
* seatbelt/landlock plus an execpolicy prefix-rule engine.
*
* @module @deepseek-ai/dsh-bash-local
*/
import { Context } from 'cordis'
import z from 'schemastery'
import { BashExecutor, BashTaskId } from '@deepseek-ai/dsh-bash'
import type { BashExecRequest, BashExecSpec, BashRunResult, BashTask, BashTaskRead, OwnerToken } from '@deepseek-ai/dsh-bash'
import { runBash } from './run'
import type { RunInternals, RunningBash } from './run'
export { DEFAULT_GRACE_MS, ENV_OVERRIDES, killGroup, OutputCollector, runBash } from './run'
export type { RunInternals, RunningBash, SpawnOutcome, SpawnSpec } from './run'
/** Plugin config (all optional — `static Config` supplies the defaults). */
export interface Config {
/** Default working directory for commands (default: process.cwd()). */
cwd?: string
/** Default foreground timeout in milliseconds. */
timeoutMs?: number
/** Upper bound for per-call timeout overrides. */
maxTimeoutMs?: number
/** Per-stream in-memory output cap; overflow spills to a temp file. */
maxOutputBytes?: number
}
/** The shape after schemastery applied the defaults (cwd has none). */
type ResolvedConfig = Required<Omit<Config, 'cwd'>> & Pick<Config, 'cwd'>
function assertPositiveFinite(name: string, value: number): void {
if (!Number.isFinite(value) || value <= 0) {
throw new Error(`bash-local: ${name} must be a positive finite number`)
}
}
interface TrackedTask extends BashTask {
running: RunningBash
/** Whole-stream byte offsets already delivered via {@link LocalBashExecutor.readOutput}. */
stdoutOffset: number
stderrOffset: number
/** Opaque owner token from the {@link BashExecSpec} (the consumer's isolation key). */
owner: OwnerToken | undefined
}
/**
* Local-subprocess bash executor. Defaults follow the agent-tool survey
* consensus: 120s default / 600s max timeout (Claude Code, OpenCode), 64KB
* in-memory output with full-stream spill files (pi, OpenCode),
* process-group SIGTERM→SIGKILL kills (OpenCode).
*/
export class LocalBashExecutor extends BashExecutor {
static Config: z<Config> = z.object({
cwd: z.string(),
timeoutMs: z.number().default(120_000),
maxTimeoutMs: z.number().default(600_000),
maxOutputBytes: z.number().default(64_000),
})
private tasks = new Map<BashTaskId, TrackedTask>()
private nextTaskId = 1
/** Test seam: timer/spill knobs forwarded to runBash. */
internals: RunInternals = {}
/** Validated config (schemastery applied the defaults before construction). */
readonly config: ResolvedConfig
constructor(ctx: Context, config: Config) {
super(ctx)
// schemastery (static Config) has already filled the defaulted fields;
// the cast records that runtime fact for exactOptionalPropertyTypes.
this.config = config as ResolvedConfig
assertPositiveFinite('timeoutMs', this.config.timeoutMs)
assertPositiveFinite('maxTimeoutMs', this.config.maxTimeoutMs)
assertPositiveFinite('maxOutputBytes', this.config.maxOutputBytes)
ctx.effect(() => async () => {
// Kill every live process group and WAIT for the processes to close so
// nothing outlives the fiber (HMR safety) — a TERM-trapping child is
// held until the SIGKILL escalation lands. The base class already
// silenced listeners, so these kills complete without notices.
const pending: Promise<void>[] = []
for (const task of this.tasks.values()) {
if (task.status === 'running') {
task.status = 'killed'
task.running.kill()
pending.push(task.done)
}
}
this.tasks.clear()
await Promise.all(pending)
}, 'local bash teardown')
}
/**
* Resolve a request into a fully-specified spec: fill `workdir` from
* `config.cwd` (else `process.cwd()`), and `timeoutMs` from
* `config.timeoutMs`, capped at `config.maxTimeoutMs`. The tool layer calls
* this before {@link run}/{@link start}, so those methods receive explicit
* values and never re-default.
*/
resolve(request: BashExecRequest): BashExecSpec {
if (request.timeoutMs !== undefined) assertPositiveFinite('request.timeoutMs', request.timeoutMs)
const timeoutMs = Math.min(request.timeoutMs ?? this.config.timeoutMs, this.config.maxTimeoutMs)
return {
command: request.command,
workdir: request.workdir ?? this.config.cwd ?? process.cwd(),
timeoutMs,
...request.signal ? { signal: request.signal } : {},
// Carry the owner through verbatim (required-but-nullable on the spec):
// the executor never interprets it — the consumer's access policy does.
owner: request.owner,
}
}
async run(spec: BashExecSpec): Promise<BashRunResult> {
const outcome = await runBash({
command: spec.command,
cwd: spec.workdir,
timeoutMs: spec.timeoutMs,
maxOutputBytes: this.config.maxOutputBytes,
signal: spec.signal,
}, this.internals).done
return { ...outcome, timeoutMs: spec.timeoutMs }
}
start(spec: BashExecSpec): BashTask {
// No timeout for background tasks (matches Claude Code, which detaches
// the timeout when backgrounding); callers stop tasks via kill() — or
// via spec.signal, which the seam contract honors for background runs
// too (runBash wires it to the group kill). spec.timeoutMs is ignored
// here by design.
const running = runBash({
command: spec.command,
cwd: spec.workdir,
timeoutMs: 0,
maxOutputBytes: this.config.maxOutputBytes,
signal: spec.signal,
}, this.internals)
const id = BashTaskId(`bash-${this.nextTaskId++}`)
const task: TrackedTask = {
id,
command: spec.command,
status: 'running',
exitCode: null,
signal: null,
owner: spec.owner,
running,
stdoutOffset: 0,
stderrOffset: 0,
done: running.done.then((outcome) => {
// Abort-killed tasks report as killed, not completed.
if (task.status === 'running') task.status = outcome.aborted ? 'killed' : 'completed'
task.exitCode = outcome.exitCode
task.signal = outcome.signal
this.notifyTaskDone(task)
}, (error: unknown) => {
// Spawn-level failure (bad workdir, …): the task never ran. String()
// suffices — runBash only rejects with Error instances.
task.status = 'killed'
task.running.stderr.push(Buffer.from(`spawn failed: ${String(error)}`))
this.notifyTaskDone(task)
}),
}
this.tasks.set(id, task)
return task
}
get(id: BashTaskId): BashTask | undefined {
return this.tasks.get(id)
}
ownerOf(id: BashTaskId): OwnerToken | undefined {
// Unknown id and known-but-ownerless both read as undefined — the consumer
// treats undefined as "open" and a truly unknown id fails at readOutput/kill.
return this.tasks.get(id)?.owner
}
list(): BashTask[] {
return [...this.tasks.values()]
}
readOutput(id: BashTaskId): BashTaskRead {
const task = this.tasks.get(id)
if (!task) throw new Error(`unknown bash task "${id}"`)
const out = task.running.stdout.readFrom(task.stdoutOffset)
const err = task.running.stderr.readFrom(task.stderrOffset)
task.stdoutOffset = out.nextOffset
task.stderrOffset = err.nextOffset
// Single newline between sections: stdout chunks usually end with one
// already; add it only when missing.
const separator = out.text.length > 0 && !out.text.endsWith('\n') ? '\n' : ''
const delta = out.text
+ (err.text.length > 0 ? `${separator}[stderr]\n${err.text}` : '')
return {
task,
delta,
lossy: out.lossy || err.lossy,
...out.spillPath !== undefined ? { stdoutSpillPath: out.spillPath } : {},
...err.spillPath !== undefined ? { stderrSpillPath: err.spillPath } : {},
}
}
kill(id: BashTaskId): boolean {
const task = this.tasks.get(id)
if (!task) throw new Error(`unknown bash task "${id}"`)
if (task.status !== 'running') return false
task.status = 'killed'
task.running.kill()
return true
}
}
export default LocalBashExecutor

View File

@@ -0,0 +1,341 @@
/**
* Process plumbing for the local bash executor: spawn, output collection
* with tail-keep + spill-to-disk truncation, and process-group kill with
* SIGTERM→SIGKILL escalation.
*
* Everything here is deliberately free of Cordis concepts so it can be unit
* tested in isolation; `LocalBashExecutor` owns lifecycle and configuration.
*
* Design notes (surveyed against Claude Code, OpenCode, Codex, and pi — see
* the package README): spawn-per-call with `detached: true` so the child
* leads its own process group; kills target the group (`kill(-pid)`) so
* pipelines and subshells die with the parent. SIGTERM first, SIGKILL after a
* grace period (OpenCode's escalation; Codex/pi jump straight to SIGKILL).
*
* @module dsh-bash-local/run
*/
import { spawn } from 'node:child_process'
import { randomBytes } from 'node:crypto'
import { closeSync, mkdtempSync, openSync, writeSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import type { CollectedOutput } from '@deepseek-ai/dsh-bash'
/**
* Model-friendly environment overrides: disable colors, pagers, and
* interactive terminal features that would garble tool output (the same set
* Codex hardcodes; Claude Code achieves it via TERM=dumb).
*/
export const ENV_OVERRIDES = {
NO_COLOR: '1',
TERM: 'dumb',
PAGER: 'cat',
GIT_PAGER: 'cat',
} as const
/**
* Credential-shaped env vars are NOT forwarded to commands (the harness's
* own DEEPSEEK_API_KEY must not leak into `env` output, tool results, or
* spill files). Same default pattern as Codex's env policy; a future config
* can whitelist specific vars when a workflow genuinely needs one.
*/
export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
/** process.env minus credential-shaped vars, plus the model-friendly overrides. */
export function childEnv(): NodeJS.ProcessEnv {
const env: NodeJS.ProcessEnv = {}
for (const [key, value] of Object.entries(process.env)) {
if (!SENSITIVE_ENV_PATTERN.test(key)) env[key] = value
}
return { ...env, ...ENV_OVERRIDES }
}
/** What to run and under which limits (resolved — no defaults in here). */
export interface SpawnSpec {
command: string
cwd: string
/** Kill the process group after this many milliseconds. 0 = no timeout. */
timeoutMs: number
/** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */
maxOutputBytes: number
/** Abort signal — kills the process group when fired. */
signal?: AbortSignal | undefined
}
/** Raw outcome of one closed process (before result shaping). */
export interface SpawnOutcome {
exitCode: number | null
signal: NodeJS.Signals | null
timedOut: boolean
aborted: boolean
stdout: CollectedOutput
stderr: CollectedOutput
}
/** Injectable knobs so tests can exercise escalation/spill without long waits. */
export interface RunInternals {
/** Grace period between SIGTERM and SIGKILL on the process group. */
graceMs?: number
/** Directory for spill files (defaults to the OS temp dir). */
spillDir?: string
}
/** Default SIGTERM→SIGKILL grace period (matches OpenCode's 3s). */
export const DEFAULT_GRACE_MS = 3_000
let spillCounter = 0
let defaultSpillDir: string | undefined
/**
* The default spill location: a private (0700) per-process directory under
* the OS tmpdir, created lazily. Predictable world-readable paths would let
* other local users read command output or pre-create symlinks.
*/
function privateSpillDir(): string {
defaultSpillDir ??= mkdtempSync(join(tmpdir(), 'dsh-bash-'))
return defaultSpillDir
}
/**
* Collects one stream with a bounded in-memory tail. The FULL stream is
* always recoverable: on first overflow a spill file is created and every
* chunk (including those already collected) is appended there.
*
* Tail-keep rationale (pi/OpenCode): errors and final results cluster at the
* end of command output; the spill file covers the head.
*/
export class OutputCollector {
private chunks: Buffer[] = []
private bytes = 0
private dropped = false
private spillFd: number | undefined
private spillFile: string | undefined
/** Total bytes ever pushed (not just retained). */
private total = 0
constructor(
private readonly maxBytes: number,
private readonly label: string,
private readonly spillDir: string,
) {}
push(chunk: Buffer): void {
this.total += chunk.length
const overflows = this.bytes + chunk.length > this.maxBytes
if (overflows || this.spillFd !== undefined) this.spillAll(chunk)
this.chunks.push(chunk)
this.bytes += chunk.length
while (this.bytes > this.maxBytes && this.chunks.length > 1) {
// Drop whole chunks from the head; pipe chunks are small (≤64KiB), so
// the retained tail tracks the cap closely enough for a model-facing
// truncation boundary. (length > 1 was just checked — shift() returns.)
const head = this.chunks.shift() as Buffer
this.bytes -= head.length
this.dropped = true
}
if (this.bytes > this.maxBytes && this.chunks.length === 1) {
// A single chunk larger than the cap: keep its tail.
const only = this.chunks[0] as Buffer
this.chunks[0] = only.subarray(only.length - this.maxBytes)
this.bytes = this.maxBytes
this.dropped = true
}
}
/** Open the spill file lazily and append `chunk` (and any prior chunks once). */
private spillAll(chunk: Buffer): void {
if (this.spillFd === undefined) {
// Random suffix + O_EXCL + no-follow-equivalent ('wx' fails on any
// existing path, symlink or not) + owner-only mode: defeats spill-path
// prediction and symlink planting in shared tmp dirs.
this.spillFile = join(
this.spillDir,
`dsh-bash-${process.pid}-${++spillCounter}-${randomBytes(6).toString('hex')}-${this.label}.log`,
)
this.spillFd = openSync(this.spillFile, 'wx', 0o600)
for (const prior of this.chunks) writeSync(this.spillFd, prior)
}
writeSync(this.spillFd, chunk)
}
// TODO(snapshot-scope): `snapshot()` has one internal caller (`finalize()` at
// the bottom of this file) and `totalBytes` is read only by a test. The live
// background-poll path goes through `readFrom()`, so inline snapshot() into
// finalize() and drop or privatize the totalBytes getter.
/** Read the collected tail without finalizing (the final-result snapshot). */
snapshot(): CollectedOutput {
return {
text: Buffer.concat(this.chunks).toString('utf8'),
truncated: this.dropped,
...this.spillFile !== undefined ? { spillPath: this.spillFile } : {},
}
}
/** Total bytes ever pushed (including bytes dropped from memory). */
get totalBytes(): number {
return this.total
}
/**
* Incremental read in whole-stream byte coordinates: returns everything
* pushed since `fromByte`. When `fromByte` has already slid out of the
* in-memory tail window, the read is `lossy` — it returns the whole
* retained tail and the gap is only recoverable from the spill file.
*/
readFrom(fromByte: number): { text: string; nextOffset: number; lossy: boolean; spillPath?: string } {
const windowStart = this.total - this.bytes
const buffer = Buffer.concat(this.chunks)
const lossy = fromByte < windowStart
const slice = lossy ? buffer : buffer.subarray(fromByte - windowStart)
return {
text: slice.toString('utf8'),
nextOffset: this.total,
lossy,
...this.spillFile !== undefined ? { spillPath: this.spillFile } : {},
}
}
/** Close the spill file (if any) and return the final output. */
finalize(): CollectedOutput {
if (this.spillFd !== undefined) {
try {
closeSync(this.spillFd)
} catch {
// close can surface delayed writeback failures (for example EIO/ENOSPC)
// after writeSync appeared to succeed. Keep finalize total so runBash's
// close handler still resolves, but stop advertising a spill file that
// may be missing its tail.
this.spillFile = undefined
}
this.spillFd = undefined
}
return this.snapshot()
}
}
/**
* Send `sig` to the process GROUP led by `pid` (requires the child to have
* been spawned with `detached: true`). NEVER throws: kills race process exit
* by design (ESRCH), and the other failure modes (EPERM from setuid
* children, …) fire inside timer callbacks where a throw would crash the
* host process — a kill that cannot be delivered is reported by the process
* NOT dying, which callers already handle via escalation/timeouts. No-op for
* non-positive pids (spawn never started a process).
*/
export function killGroup(pid: number, sig: NodeJS.Signals): void {
if (pid <= 0) return
try {
process.kill(-pid, sig)
} catch {
// Swallow: see contract above.
}
}
/**
* A live bash child process: the promise resolves when the process closes;
* `kill()` starts the SIGTERM→grace→SIGKILL escalation on its group.
*/
export interface RunningBash {
/** Process id (group leader); -1 when the spawn itself failed. */
readonly pid: number
/** stdout/stderr collectors (live — background polling reads incrementally). */
readonly stdout: OutputCollector
readonly stderr: OutputCollector
/** Resolves when the process closes; rejects only for spawn-level failures. */
readonly done: Promise<SpawnOutcome>
/** Begin SIGTERM→grace→SIGKILL on the process group. Idempotent. */
kill(): void
}
/**
* Spawn `bash -c <command>` in its own process group and collect output.
*
* Outcome semantics: the returned promise REJECTS only for spawn-level
* failures (bad cwd → ENOENT, missing binary, pre-aborted signal); every
* runtime outcome — nonzero exit, timeout kill, abort kill, signal death —
* RESOLVES with a {@link SpawnOutcome} describing what happened, so callers
* shape one consistent report for the model.
*
* XXX(stateful-shell): per the agent-tool survey there are two proven
* stateful designs worth revisiting — Claude Code persists ONLY cwd between
* calls (captures `pwd -P` after each command), and Codex keeps whole PTY
* exec sessions addressable via session ids + stdin writes. We deliberately
* spawn a fresh non-login `bash -c` per call for determinism (no rc files,
* no inherited shell state); revisit when real workflows demand it.
*/
export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningBash {
const graceMs = internals.graceMs ?? DEFAULT_GRACE_MS
const spillDir = internals.spillDir ?? privateSpillDir()
if (spec.signal?.aborted) {
throw new Error(`aborted before spawn: ${String(spec.signal.reason ?? 'aborted')}`)
}
const child = spawn('bash', ['-c', spec.command], {
cwd: spec.cwd,
env: childEnv(),
stdio: ['ignore', 'pipe', 'pipe'],
detached: true,
})
const stdout = new OutputCollector(spec.maxOutputBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.maxOutputBytes, 'stderr', spillDir)
child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) })
child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) })
let timedOut = false
let aborted = false
let killTimer: NodeJS.Timeout | undefined
let graceTimer: NodeJS.Timeout | undefined
// pid is undefined when the spawn itself fails (bad cwd, missing binary);
// the 'error' handler rejects `done` and kills become no-ops via pid -1.
const pid = child.pid ?? -1
const kill = (): void => {
if (graceTimer !== undefined) return // escalation already in flight
killGroup(pid, 'SIGTERM')
graceTimer = setTimeout(() => { killGroup(pid, 'SIGKILL') }, graceMs)
}
if (spec.timeoutMs > 0) {
killTimer = setTimeout(() => {
timedOut = true
kill()
}, spec.timeoutMs)
}
const onAbort = (): void => {
aborted = true
kill()
}
spec.signal?.addEventListener('abort', onAbort, { once: true })
const done = new Promise<SpawnOutcome>((resolve, reject) => {
child.on('error', (error) => {
// Spawn-level failure (ENOENT cwd, EACCES, …): no close event with
// meaningful output follows; clean up and reject.
cleanup()
reject(error)
})
child.on('close', (exitCode, signal) => {
cleanup()
resolve({
exitCode,
signal,
timedOut,
aborted,
stdout: stdout.finalize(),
stderr: stderr.finalize(),
})
})
function cleanup(): void {
if (killTimer !== undefined) clearTimeout(killTimer)
if (graceTimer !== undefined) clearTimeout(graceTimer)
spec.signal?.removeEventListener('abort', onAbort)
}
})
return { pid, stdout, stderr, done, kill }
}

View File

@@ -0,0 +1,307 @@
import { mkdtempSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { describe, expect, it, vi } from 'vitest'
import { Context } from 'cordis'
import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
import { BashTaskId } from '@deepseek-ai/dsh-bash'
const spillDir = mkdtempSync(join(tmpdir(), 'dsh-bash-exec-spec-'))
async function setup(config: ConstructorParameters<typeof LocalBashExecutor>[1] = {}) {
const ctx = new Context()
await ctx.plugin(LocalBashExecutor, config)
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
return { ctx, bash }
}
/** Poll until a pid no longer exists. */
async function waitGone(pid: number, timeoutMs = 5_000): Promise<void> {
const deadline = Date.now() + timeoutMs
while (Date.now() < deadline) {
try {
process.kill(pid, 0)
} catch {
return
}
await new Promise(resolve => setTimeout(resolve, 20))
}
throw new Error(`pid ${pid} still alive after ${timeoutMs}ms`)
}
describe('LocalBashExecutor.run', () => {
it('resolves with output and the effective timeout', async () => {
const { bash } = await setup({ timeoutMs: 5_000 })
const result = await bash.run(bash.resolve({ command: 'echo hi' }))
expect(result.exitCode).toBe(0)
expect(result.stdout.text).toBe('hi\n')
expect(result.timeoutMs).toBe(5_000)
})
it('uses config cwd, overridable per call', async () => {
const { bash } = await setup({ cwd: '/tmp' })
const fromConfig = await bash.run(bash.resolve({ command: 'pwd' }))
expect(fromConfig.stdout.text.trim()).toMatch(/\/tmp$/)
const fromCall = await bash.run(bash.resolve({ command: 'pwd', workdir: '/' }))
expect(fromCall.stdout.text.trim()).toBe('/')
})
it('defaults cwd to process.cwd()', async () => {
const { bash } = await setup()
const result = await bash.run(bash.resolve({ command: 'pwd' }))
expect(result.stdout.text.trim()).toBe(process.cwd())
})
it('caps per-call timeouts at maxTimeoutMs', async () => {
const { bash } = await setup({ timeoutMs: 1_000, maxTimeoutMs: 2_000 })
const result = await bash.run(bash.resolve({ command: 'true', timeoutMs: 99_999 }))
expect(result.timeoutMs).toBe(2_000)
})
it('rejects invalid numeric config and timeout overrides', async () => {
await expect(setup({ timeoutMs: Number.NaN })).rejects.toThrow(/timeoutMs/)
await expect(setup({ maxTimeoutMs: 0 })).rejects.toThrow(/maxTimeoutMs/)
await expect(setup({ maxOutputBytes: -1 })).rejects.toThrow(/maxOutputBytes/)
const { bash } = await setup()
expect(() => bash.resolve({ command: 'true', timeoutMs: Number.NaN })).toThrow(/request\.timeoutMs/)
expect(() => bash.resolve({ command: 'true', timeoutMs: -1 })).toThrow(/request\.timeoutMs/)
})
it('per-call timeout takes precedence under the cap and kills on expiry', async () => {
const { bash } = await setup({ timeoutMs: 60_000 })
const result = await bash.run(bash.resolve({ command: 'sleep 60', timeoutMs: 100 }))
expect(result.timedOut).toBe(true)
expect(result.timeoutMs).toBe(100)
})
it('propagates abort signals', async () => {
const { bash } = await setup()
const controller = new AbortController()
const pending = bash.run(bash.resolve({ command: 'sleep 60', signal: controller.signal }))
setTimeout(() => { controller.abort() }, 50)
const result = await pending
expect(result.aborted).toBe(true)
})
it('rejects on spawn failure (bad workdir)', async () => {
const { bash } = await setup()
await expect(bash.run(bash.resolve({ command: 'true', workdir: '/nonexistent-dsh' }))).rejects.toThrow(/ENOENT/)
})
})
describe('LocalBashExecutor background tasks', () => {
it('start returns immediately with a registered running task', async () => {
const { bash } = await setup()
const before = Date.now()
const task = bash.start(bash.resolve({ command: 'sleep 0.2; echo done' }))
expect(Date.now() - before).toBeLessThan(150)
expect(task.status).toBe('running')
expect(bash.get(task.id)).toBe(task)
expect(bash.list()).toContain(task)
await task.done
expect(task.status).toBe('completed')
expect(task.exitCode).toBe(0)
})
it('assigns sequential ids', async () => {
const { bash } = await setup()
const first = bash.start(bash.resolve({ command: 'true' }))
const second = bash.start(bash.resolve({ command: 'true' }))
expect(first.id).toBe('bash-1')
expect(second.id).toBe('bash-2')
await Promise.all([first.done, second.done])
})
it('readOutput returns increments without re-delivery', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'echo first; sleep 0.3; echo second' }))
await new Promise(resolve => setTimeout(resolve, 150))
const first = bash.readOutput(task.id)
expect(first.delta).toBe('first\n')
expect(first.lossy).toBe(false)
await task.done
const second = bash.readOutput(task.id)
expect(second.delta).toBe('second\n')
const third = bash.readOutput(task.id)
expect(third.delta).toBe('')
})
it('readOutput marks stderr sections', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'echo out; echo err >&2' }))
await task.done
const read = bash.readOutput(task.id)
expect(read.delta).toBe('out\n[stderr]\nerr\n')
})
it('readOutput reports stderr-only deltas without a leading newline', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'echo err >&2' }))
await task.done
expect(bash.readOutput(task.id).delta).toBe('[stderr]\nerr\n')
})
it('readOutput flags lossy reads and reports spill paths', async () => {
const { bash } = await setup({ maxOutputBytes: 100 })
const task = bash.start(bash.resolve({ command: 'for i in $(seq 1 100); do printf "line-%04d\\n" $i; done' }))
await task.done
const read = bash.readOutput(task.id)
// Window slid past offset 0 → lossy, spill path points at the full stream.
expect(read.lossy).toBe(true)
expect(read.stdoutSpillPath).toBeDefined()
})
it('readOutput throws for unknown ids', async () => {
const { bash } = await setup()
expect(() => bash.readOutput(BashTaskId('nope'))).toThrow(/unknown bash task "nope"/)
})
it('kill terminates the process group and reports status killed', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'sleep 60' }))
expect(bash.kill(task.id)).toBe(true)
await task.done
expect(task.status).toBe('killed')
expect(task.signal).toBe('SIGTERM')
})
it('kill returns false for finished tasks and throws for unknown ids', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'true' }))
await task.done
expect(bash.kill(task.id)).toBe(false)
expect(() => bash.kill(BashTaskId('nope'))).toThrow(/unknown bash task "nope"/)
})
it('notifies onTaskDone listeners on completion', async () => {
const { bash } = await setup()
const seen: [string, string][] = []
bash.onTaskDone(task => void seen.push([task.id, task.status]))
const task = bash.start(bash.resolve({ command: 'true' }))
await task.done
expect(seen).toEqual([[task.id, 'completed']])
})
it('notifies onTaskDone for killed tasks too', async () => {
const { bash } = await setup()
const listener = vi.fn()
bash.onTaskDone(listener)
const task = bash.start(bash.resolve({ command: 'sleep 60' }))
bash.kill(task.id)
await task.done
expect(listener).toHaveBeenCalledWith(task)
expect(task.status).toBe('killed')
})
it('marks tasks killed when the background spawn itself fails', async () => {
const { bash } = await setup()
const listener = vi.fn()
bash.onTaskDone(listener)
const task = bash.start(bash.resolve({ command: 'true', workdir: '/nonexistent-dsh' }))
await task.done
expect(task.status).toBe('killed')
expect(listener).toHaveBeenCalledWith(task)
expect(bash.readOutput(task.id).delta).toContain('spawn failed')
})
it('readOutput adds a separator only when stdout lacks a trailing newline', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'printf out; echo err >&2' }))
await task.done
expect(bash.readOutput(task.id).delta).toBe('out\n[stderr]\nerr\n')
})
it('readOutput reports stderr spill paths', async () => {
const { bash } = await setup({ maxOutputBytes: 100 })
const task = bash.start(bash.resolve({ command: 'for i in $(seq 1 100); do printf "line-%04d\\n" $i >&2; done' }))
await task.done
const read = bash.readOutput(task.id)
expect(read.lossy).toBe(true)
expect(read.stderrSpillPath).toBeDefined()
expect(read.delta).toContain('[stderr]')
})
it('disposing with already-finished tasks only kills the running ones', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
const finished = bash.start(bash.resolve({ command: 'true' }))
await finished.done
const running = bash.start(bash.resolve({ command: 'sleep 60' }))
await fiber.dispose()
await running.done
expect(finished.status).toBe('completed')
expect(running.signal).toBe('SIGTERM')
expect(bash.list()).toEqual([])
})
it('disposing the executor fiber kills running tasks (no orphans)', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
const listener = vi.fn()
bash.onTaskDone(listener)
const task = bash.start(bash.resolve({ command: 'sleep 60' }))
const running = bash.get(task.id)!
await new Promise(resolve => setTimeout(resolve, 50))
// Grab the pid before dispose clears the registry.
const pid = (running as unknown as { running: { pid: number } }).running.pid
await fiber.dispose()
await waitGone(pid)
expect(bash.list()).toEqual([])
// Listener silenced by base-class teardown — no late notifications.
expect(listener).not.toHaveBeenCalled()
})
})
describe('review fixes: lifecycle hardening', () => {
it('start honors a pre-aborted or later-aborted AbortSignal', async () => {
const { bash } = await setup()
const controller = new AbortController()
const task = bash.start(bash.resolve({ command: 'sleep 60', signal: controller.signal }))
controller.abort()
await task.done
expect(task.status).toBe('killed')
expect(task.signal).toBe('SIGTERM')
})
it('a throwing onTaskDone listener does not reject task.done or starve later listeners', async () => {
const { bash } = await setup()
const errorSpy = vi.spyOn(console, 'error').mockImplementation(() => undefined)
const second = vi.fn()
try {
bash.onTaskDone(() => { throw new Error('listener bug') })
bash.onTaskDone(second)
const task = bash.start(bash.resolve({ command: 'true' }))
await expect(task.done).resolves.toBeUndefined()
expect(second).toHaveBeenCalledWith(task)
expect(errorSpy).toHaveBeenCalled()
} finally {
errorSpy.mockRestore()
}
})
it('dispose AWAITS a TERM-trapping process (SIGKILL escalation included)', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
const task = bash.start(bash.resolve({ command: 'trap \'\' TERM; sleep 60' }))
await new Promise(resolve => setTimeout(resolve, 100))
const pid = (task as unknown as { running: { pid: number } }).running.pid
await fiber.dispose()
// Disposal itself waited: the pid must already be gone, no grace left.
expect(() => process.kill(pid, 0)).toThrow()
expect(task.status).toBe('killed')
})
})

View File

@@ -0,0 +1,339 @@
import { mkdtempSync, readFileSync, statSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { describe, expect, it, vi } from 'vitest'
import { killGroup, OutputCollector, runBash } from '@deepseek-ai/dsh-bash-local'
const { failNextClose } = vi.hoisted(() => ({ failNextClose: { value: false } }))
vi.mock('node:fs', async (importOriginal) => {
const actual = await importOriginal<typeof import('node:fs')>()
return {
...actual,
closeSync(fd: number): void {
if (failNextClose.value) {
failNextClose.value = false
throw Object.assign(new Error('simulated EIO on close'), { code: 'EIO' })
}
actual.closeSync(fd)
},
}
})
const spillDir = mkdtempSync(join(tmpdir(), 'dsh-bash-spec-'))
function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]> = {}) {
return {
command,
cwd: process.cwd(),
timeoutMs: 0,
maxOutputBytes: 64_000,
...overrides,
}
}
/** Poll until a pid no longer exists (kill(pid, 0) throws ESRCH). */
async function waitGone(pid: number, timeoutMs = 5_000): Promise<void> {
const deadline = Date.now() + timeoutMs
while (Date.now() < deadline) {
try {
process.kill(pid, 0)
} catch {
return
}
await new Promise(resolve => setTimeout(resolve, 20))
}
throw new Error(`pid ${pid} still alive after ${timeoutMs}ms`)
}
describe('runBash', () => {
it('captures stdout on success', async () => {
const result = await runBash(spec('echo hello')).done
expect(result.exitCode).toBe(0)
expect(result.signal).toBeNull()
expect(result.timedOut).toBe(false)
expect(result.aborted).toBe(false)
expect(result.stdout.text).toBe('hello\n')
expect(result.stdout.truncated).toBe(false)
expect(result.stderr.text).toBe('')
})
it('captures stderr separately', async () => {
const result = await runBash(spec('echo oops >&2')).done
expect(result.exitCode).toBe(0)
expect(result.stdout.text).toBe('')
expect(result.stderr.text).toBe('oops\n')
})
it('captures both streams', async () => {
const result = await runBash(spec('echo out; echo err >&2')).done
expect(result.stdout.text).toBe('out\n')
expect(result.stderr.text).toBe('err\n')
})
it('reports non-zero exit codes', async () => {
const result = await runBash(spec('exit 42')).done
expect(result.exitCode).toBe(42)
expect(result.signal).toBeNull()
})
it('applies model-friendly env overrides', async () => {
const result = await runBash(spec('echo "$NO_COLOR/$TERM/$PAGER"')).done
expect(result.stdout.text).toBe('1/dumb/cat\n')
})
it('runs in the requested cwd', async () => {
const result = await runBash(spec('pwd', { cwd: '/tmp' })).done
expect(result.stdout.text.trim()).toMatch(/\/tmp$/)
})
it('kills with SIGTERM on timeout', async () => {
const start = Date.now()
const result = await runBash(spec('sleep 60', { timeoutMs: 100 })).done
expect(Date.now() - start).toBeLessThan(5_000)
expect(result.timedOut).toBe(true)
expect(result.signal).toBe('SIGTERM')
expect(result.exitCode).toBeNull()
})
it('escalates to SIGKILL when SIGTERM is trapped', async () => {
const result = await runBash(
spec('trap \'\' TERM; sleep 60', { timeoutMs: 100 }),
{ graceMs: 200 },
).done
expect(result.timedOut).toBe(true)
expect(result.signal).toBe('SIGKILL')
})
it('kills the whole process group (grandchildren die too)', async () => {
// The subshell writes the sleep's pid then waits on it; killing the
// group must take the sleep down with bash.
const pidFile = join(spillDir, `grandchild-${Date.now()}.pid`)
const running = runBash(spec(`sleep 60 & echo $! > ${pidFile}; wait`))
await new Promise(resolve => setTimeout(resolve, 300))
const grandchild = Number(readFileSync(pidFile, 'utf8').trim())
expect(grandchild).toBeGreaterThan(0)
running.kill()
const result = await running.done
expect(result.signal).toBe('SIGTERM')
await waitGone(grandchild)
})
it('aborts via AbortSignal mid-run', async () => {
const controller = new AbortController()
const running = runBash(spec('sleep 60', { signal: controller.signal }))
setTimeout(() => { controller.abort('user cancelled') }, 50)
const result = await running.done
expect(result.aborted).toBe(true)
expect(result.signal).toBe('SIGTERM')
})
it('throws when the signal is already aborted before spawn', () => {
const controller = new AbortController()
controller.abort('too late')
expect(() => runBash(spec('echo hi', { signal: controller.signal })))
.toThrow(/aborted before spawn: too late/)
})
it('rejects with a spawn error for a nonexistent cwd', async () => {
await expect(runBash(spec('echo hi', { cwd: '/nonexistent-dir-dsh-test' })).done)
.rejects.toThrow(/ENOENT/)
})
it('kill() is idempotent (second call does not restart escalation)', async () => {
const running = runBash(spec('sleep 60'))
running.kill()
running.kill()
const result = await running.done
expect(result.signal).toBe('SIGTERM')
})
})
describe('output truncation and spill', () => {
it('keeps the tail and spills the full stream to disk', async () => {
// 200 numbered lines of ~10 bytes; cap at 500 bytes keeps a late tail.
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(true)
expect(result.stdout.text.length).toBeLessThanOrEqual(500)
expect(result.stdout.text).toContain('line-0200')
expect(result.stdout.text).not.toContain('line-0001')
expect(result.stdout.spillPath).toBeDefined()
const full = readFileSync(result.stdout.spillPath!, 'utf8')
expect(full).toContain('line-0001')
expect(full).toContain('line-0200')
})
it('does not truncate output exactly at the cap', async () => {
const result = await runBash(
spec('printf "%.0sx" $(seq 1 500)', { maxOutputBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(false)
expect(result.stdout.text.length).toBe(500)
expect(result.stdout.spillPath).toBeUndefined()
})
it('settles with the tail and no spill path when final spill close fails', async () => {
failNextClose.value = true
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
{ spillDir },
).done
expect(failNextClose.value).toBe(false)
expect(result.exitCode).toBe(0)
expect(result.stdout.truncated).toBe(true)
expect(result.stdout.text).toContain('line-0200')
expect(result.stdout.spillPath).toBeUndefined()
})
})
describe('OutputCollector', () => {
it('keeps the tail of a single oversized chunk', () => {
const collector = new OutputCollector(10, 'test', spillDir)
collector.push(Buffer.from('0123456789abcdef'))
const out = collector.finalize()
expect(out.text).toBe('6789abcdef')
expect(out.truncated).toBe(true)
expect(readFileSync(out.spillPath!, 'utf8')).toBe('0123456789abcdef')
})
it('readFrom returns increments and flags lossy reads', () => {
const collector = new OutputCollector(10, 'test', spillDir)
collector.push(Buffer.from('aaaaa'))
const first = collector.readFrom(0)
expect(first.text).toBe('aaaaa')
expect(first.lossy).toBe(false)
expect(first.nextOffset).toBe(5)
collector.push(Buffer.from('bbbbb'))
const second = collector.readFrom(first.nextOffset)
expect(second.text).toBe('bbbbb')
expect(second.lossy).toBe(false)
// Push enough to slide the window past the last offset.
collector.push(Buffer.from('c'.repeat(20)))
const third = collector.readFrom(second.nextOffset)
expect(third.lossy).toBe(true)
expect(third.text).toBe('c'.repeat(10))
expect(third.spillPath).toBeDefined()
})
it('tracks totalBytes across drops', () => {
const collector = new OutputCollector(4, 'test', spillDir)
collector.push(Buffer.from('aaaa'))
collector.push(Buffer.from('bbbb'))
expect(collector.totalBytes).toBe(8)
expect(collector.finalize().text).toBe('bbbb')
})
it('contains close failures and drops the spill path', () => {
const collector = new OutputCollector(4, 'closefail', spillDir)
collector.push(Buffer.from('aaaa'))
collector.push(Buffer.from('bbbb'))
expect(collector.snapshot().spillPath).toBeDefined()
failNextClose.value = true
let out: ReturnType<typeof collector.finalize>
expect(() => { out = collector.finalize() }).not.toThrow()
expect(failNextClose.value).toBe(false)
expect(out!.text).toBe('bbbb')
expect(out!.truncated).toBe(true)
expect(out!.spillPath).toBeUndefined()
})
})
describe('killGroup', () => {
it('ignores non-positive pids', () => {
expect(() => { killGroup(-1, 'SIGTERM') }).not.toThrow()
expect(() => { killGroup(0, 'SIGTERM') }).not.toThrow()
})
it('swallows ESRCH for vanished groups', async () => {
const running = runBash(spec('true'))
await running.done
expect(() => { killGroup(running.pid, 'SIGTERM') }).not.toThrow()
})
})
describe('abort edge cases', () => {
it('reports a fallback reason for reason-less pre-aborted signals', () => {
// Real AbortControllers always set a DOMException reason; signal-like
// objects from other libraries may not — the fallback covers them.
const bare = {
aborted: true,
reason: undefined,
addEventListener() {},
removeEventListener() {},
} as unknown as AbortSignal
expect(() => runBash(spec('echo hi', { signal: bare })))
.toThrow(/aborted before spawn: aborted/)
})
it('reports an externally self-killed command without the timeout marker', async () => {
const result = await runBash(spec('kill -TERM $$')).done
expect(result.signal).toBe('SIGTERM')
expect(result.timedOut).toBe(false)
expect(result.aborted).toBe(false)
})
})
describe('review fixes: env scrubbing and spill hardening', () => {
it('scrubs credential-shaped env vars from child processes', async () => {
process.env.DSH_TEST_API_KEY = 'super-secret'
process.env.DSH_TEST_TOKEN = 'also-secret'
process.env.DSH_TEST_PLAIN = 'visible'
try {
const result = await runBash(spec('echo "[${DSH_TEST_API_KEY:-absent}|${DSH_TEST_TOKEN:-absent}|${DSH_TEST_PLAIN:-absent}]"')).done
expect(result.stdout.text.trim()).toBe('[absent|absent|visible]')
} finally {
delete process.env.DSH_TEST_API_KEY
delete process.env.DSH_TEST_TOKEN
delete process.env.DSH_TEST_PLAIN
}
})
it('creates spill files with owner-only permissions and random names', async () => {
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
{ spillDir },
).done
const path = result.stdout.spillPath!
expect(path).toMatch(/dsh-bash-\d+-\d+-[0-9a-f]{12}-stdout\.log$/)
const mode = statSync(path).mode & 0o777
expect(mode).toBe(0o600)
})
it('defaults spills into a private per-process directory', async () => {
const result = await runBash(
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { maxOutputBytes: 500 }),
).done
const dir = dirname(result.stdout.spillPath!)
expect(dir).toMatch(/dsh-bash-/)
const mode = statSync(dir).mode & 0o777
expect(mode).toBe(0o700)
})
it('killGroup never throws, even for EPERM-style failures', () => {
const spy = vi.spyOn(process, 'kill').mockImplementation(() => {
throw Object.assign(new Error('EPERM'), { code: 'EPERM' })
})
try {
expect(() => { killGroup(12345, 'SIGTERM') }).not.toThrow()
} finally {
spy.mockRestore()
}
})
it('honors AbortSignal on background-style runs (no timeout)', async () => {
const controller = new AbortController()
const running = runBash(spec('sleep 60', { timeoutMs: 0, signal: controller.signal }))
setTimeout(() => { controller.abort() }, 50)
const result = await running.done
expect(result.aborted).toBe(true)
expect(result.signal).toBe('SIGTERM')
})
})

View File

@@ -0,0 +1,27 @@
{
"extends": "../../../tsconfig.base.json",
"compilerOptions": {
"rootDir": "src",
"outDir": "lib/types"
},
"include": [
"src"
],
"references": [
{
"path": "../../../vendor/cosmokit"
},
{
"path": "../../../vendor/cordis"
},
{
"path": "../../../vendor/schemastery"
},
{
"path": "../../util/brand"
},
{
"path": "../../bash/bash"
}
]
}