Merge remote-tracking branch 'origin/master' into worktree/dsbench-patch

# Conflicts:
#	packages/bash/bash-local/README.md
#	packages/bash/bash-local/src/index.ts
#	packages/bash/bash-local/src/run.ts
#	packages/bash/bash-local/tests/run.spec.ts
#	packages/examples/agent-spine-demo/README.md
#	packages/examples/agent-spine-demo/src/index.ts
#	packages/ui/jsonrpc/README.md
#	packages/ui/jsonrpc/src/server.ts
This commit is contained in:
Yichen Jiang
2026-07-19 14:53:03 +08:00
876 changed files with 48016 additions and 13119 deletions

View File

@@ -24,8 +24,8 @@ Design surveyed against the bash tools of Claude Code, OpenCode, Codex, and pi;
- **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 the `graceMs` grace (default 3s — OpenCode's escalation; pipelines and subshells die with the parent). After the main shell exits, inherited stdout/stderr pipes receive the same bounded drain grace so a surviving descendant cannot hold the command open indefinitely. ESRCH is tolerated; daemons that re-parent away from the group can still survive — same caveat as the surveyed tools.
- **Tail-keep truncation + bounded 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. A stream larger than `maxSpillBytes` discards its now-incomplete spill and returns only the marked truncated tail. If the final spill close reports a delayed writeback failure, the executor likewise withholds the path rather than advertising an incomplete file.
- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`), then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. This scrub is the security control that keeps the harness's *ambient* credentials out of a spawned command. A spec's `env` is merged LAST (after the scrub), so a caller's explicit entry — a value it already holds — wins even on a credential-shaped name. The spec's `stdin`, when supplied, is written to the child and closed; with none supplied, fd 0 is `/dev/null` — the exact pre-seam default, so a command that probes stdin's file type is unaffected. Both `env`/`stdin` are set by in-process plugins (the hooks bridges); the model-facing tool doesn't expose them. See [the bash-stdin-env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md).
- **Tail-keep truncation + bounded 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. A foreground `BashExecRequest.stdoutMaxBytes` can raise stdout's capture budget for one trusted caller; stderr and background tasks still use `maxOutputBytes`. A stream larger than `maxSpillBytes` discards its now-incomplete spill and returns only the marked truncated tail. If the final spill close reports a delayed writeback failure, the executor likewise withholds the path rather than advertising an incomplete file.
- **Model-friendly env + credential scrub** — `process.env` minus credential-shaped vars (`*KEY*`/`*SECRET*`/`*TOKEN*`) and all ambient `DSH_*` names, then `NO_COLOR=1 TERM=dumb PAGER=cat GIT_PAGER=cat` (Codex's hardcoded set) so pagers and ANSI color don't garble results. A spec's ordinary `env` is merged after the scrub but rejects `DSH_*`; managed `dshEnv` rejects ordinary names and merges last, preventing stale nested-harness identity. Supplied stdin is written and closed; otherwise fd 0 is `/dev/null`. See the [stdin/env RFC](../../../docs/rfc/implemented/architecture/2026-06-30-bash-stdin-env-trusted-plugin-surface.md) and [managed environment RFC](../../../docs/rfc/implemented/feature/2026-07-10-agent-session-identity-and-log-location.md).
- **Background processes** — `start()` returns a live `BashProcess` handle immediately, no timeout applies (Claude Code detaches timeouts when backgrounding), the handle's `readOutput()` is incremental with whole-stream byte offsets, and disposal kills every running process and awaits its exit. Everything task-shaped (ids, ownership, polling, notices) lives in the generic [`ctx.tasks` runtime](../../tasks/tasks/README.md), which the tool layer registers the handle with — this executor never sees a session or a registry.
## Model Experience

View File

@@ -96,15 +96,22 @@ export class LocalBashExecutor extends BashExecutor {
this.config.maxTimeoutMs,
'bash-local: request.timeoutMs',
)
const stdoutMaxBytes = request.stdoutMaxBytes ?? this.config.maxOutputBytes
assertPositiveFinite('request.stdoutMaxBytes', stdoutMaxBytes)
return {
command: request.command,
workdir: request.workdir ?? this.config.cwd ?? process.cwd(),
timeoutMs,
stdoutMaxBytes,
...request.signal ? { signal: request.signal } : {},
// Explicit environment values are merged after credential scrubbing in run.ts.
// Carry stdin/ordinary env/trusted dshEnv through verbatim — optional,
// no config default. run.ts owns the scrub and merge order.
...request.stdin !== undefined ? { stdin: request.stdin } : {},
...request.env !== undefined ? { env: request.env } : {},
// Local execution carries this override for sandboxing subclasses.
...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
// Carry a sandbox-mode override through verbatim: this executor never
// confines, so the field is inert here (the seam contract) — a
// sandboxing subclass overrides resolve() to stamp its default instead.
sandboxMode: request.sandboxMode,
}
}
@@ -115,12 +122,14 @@ export class LocalBashExecutor extends BashExecutor {
const outcome = await runBash({
command: spec.command,
cwd: spec.workdir,
maxOutputBytes: this.config.maxOutputBytes,
stdoutMaxBytes: spec.stdoutMaxBytes,
stderrMaxBytes: this.config.maxOutputBytes,
maxSpillBytes: this.config.maxSpillBytes,
graceMs: this.config.graceMs,
signal: d.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals).done
// Only this executor's timeout reason counts as timedOut; outer deadlines count as aborts.
const timedOut = timeoutOf(d.signal, 'BASH_TIMEOUT') !== undefined
@@ -133,12 +142,14 @@ export class LocalBashExecutor extends BashExecutor {
const running = runBash({
command: spec.command,
cwd: spec.workdir,
maxOutputBytes: this.config.maxOutputBytes,
stdoutMaxBytes: this.config.maxOutputBytes,
stderrMaxBytes: this.config.maxOutputBytes,
maxSpillBytes: this.config.maxSpillBytes,
graceMs: this.config.graceMs,
signal: spec.signal,
stdin: spec.stdin,
env: spec.env,
dshEnv: spec.dshEnv,
}, this.internals)
let stdoutOffset = 0

View File

@@ -11,7 +11,8 @@ import { randomBytes } from 'node:crypto'
import { closeSync, mkdtempSync, openSync, unlinkSync, writeSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import type { CollectedOutput } from '@deepseek-ai/dsh-bash'
import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
import type { CollectedOutput, DshEnvironment } from '@deepseek-ai/dsh-bash'
/**
* Model-friendly environment overrides: disable colors, pagers, and
@@ -34,26 +35,43 @@ export const ENV_OVERRIDES = {
export const SENSITIVE_ENV_PATTERN = /KEY|SECRET|TOKEN/i
/**
* Build a child environment by scrubbing credential-shaped ambient variables,
* applying model-friendly overrides, then merging trusted caller entries last.
*
* @param extra - caller-supplied entries merged last; an explicit entry wins even against the scrub and the overrides.
* Build a child environment from scrubbed ambient values, terminal overrides,
* ordinary caller entries, and a managed `DSH_*` snapshot. Ambient managed
* names are removed; ordinary and managed entries reject the other channel's
* namespace before `dshEnv` merges last.
* @param extra - caller entries; `DSH_*` names are rejected.
* @param dshEnv - managed entries; non-`DSH_*` names are rejected.
* @returns the environment to hand to `spawn` for the child process.
*/
export function childEnv(extra?: Record<string, string>): NodeJS.ProcessEnv {
export function childEnv(
extra?: Readonly<Record<string, string>>,
dshEnv?: DshEnvironment,
): NodeJS.ProcessEnv {
const env: NodeJS.ProcessEnv = {}
for (const [key, value] of Object.entries(process.env)) {
if (!SENSITIVE_ENV_PATTERN.test(key)) env[key] = value
if (!SENSITIVE_ENV_PATTERN.test(key) && !key.startsWith(DSH_ENV_PREFIX)) env[key] = value
}
return { ...env, ...ENV_OVERRIDES, ...extra }
for (const key of Object.keys(extra ?? {})) {
if (key.startsWith(DSH_ENV_PREFIX)) {
throw new Error(`ordinary bash env cannot set reserved variable "${key}"; use dshEnv`)
}
}
for (const key of Object.keys(dshEnv ?? {})) {
if (!key.startsWith(DSH_ENV_PREFIX)) {
throw new Error(`managed bash env cannot set ordinary variable "${key}"; use env`)
}
}
return { ...env, ...ENV_OVERRIDES, ...extra, ...dshEnv }
}
/** What to run and under which limits (resolved — no defaults in here). */
export interface SpawnSpec {
command: string
cwd: string
/** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */
maxOutputBytes: number
/** Stdout in-memory cap; overflow spills to disk (tail kept in memory). */
stdoutMaxBytes: number
/** Stderr in-memory cap; overflow spills to disk (tail kept in memory). */
stderrMaxBytes: number
/** Per-stream spill-file cap; larger streams retain only their in-memory tail. */
maxSpillBytes: number
/** Grace period for kill escalation and for inherited pipes after shell exit. */
@@ -73,12 +91,12 @@ export interface SpawnSpec {
*/
stdin?: string | undefined
/**
* Extra environment entries, merged onto the scrubbed env AFTER the
* credential scrub and the model-friendly overrides (so an explicit entry
* wins). Set by in-process plugins; the model-facing tool does not forward
* model input here.
* Ordinary environment entries merged after the credential scrub and
* terminal overrides. `DSH_*` names are rejected and belong in `dshEnv`.
*/
env?: Record<string, string> | undefined
/** Harness-owned entries; non-`DSH_*` names are rejected before spawn. */
dshEnv?: DshEnvironment | undefined
}
/**
@@ -313,13 +331,13 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
}
// Keep absent stdin as /dev/null; literal tuples preserve non-null output types.
const env = childEnv(spec.env)
const env = childEnv(spec.env, spec.dshEnv)
const child: ChildProcessByStdio<Writable | null, Readable, Readable> = spec.stdin !== undefined
? spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['pipe', 'pipe', 'pipe'], detached: true })
: spawn('bash', ['-c', spec.command], { cwd: spec.cwd, env, stdio: ['ignore', 'pipe', 'pipe'], detached: true })
const stdout = new OutputCollector(spec.maxOutputBytes, spec.maxSpillBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.maxOutputBytes, spec.maxSpillBytes, 'stderr', spillDir)
const stdout = new OutputCollector(spec.stdoutMaxBytes, spec.maxSpillBytes, 'stdout', spillDir)
const stderr = new OutputCollector(spec.stderrMaxBytes, spec.maxSpillBytes, 'stderr', spillDir)
child.stdout.on('data', (chunk: Buffer) => { stdout.push(chunk) })
child.stderr.on('data', (chunk: Buffer) => { stderr.push(chunk) })

View File

@@ -72,6 +72,23 @@ describe('LocalBashExecutor.run', () => {
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/)
expect(() => bash.resolve({ command: 'true', stdoutMaxBytes: Number.NaN })).toThrow(/request\.stdoutMaxBytes/)
expect(() => bash.resolve({ command: 'true', stdoutMaxBytes: -1 })).toThrow(/request\.stdoutMaxBytes/)
})
it('defaults stdoutMaxBytes to maxOutputBytes and lets foreground callers raise stdout only', async () => {
const { bash } = await setup({ maxOutputBytes: 100 })
expect(bash.resolve({ command: 'true' }).stdoutMaxBytes).toBe(100)
const result = await bash.run(bash.resolve({
command: 'printf "%.0sx" $(seq 1 500); printf "%.0se" $(seq 1 500) >&2',
stdoutMaxBytes: 500,
}))
expect(result.stdout.truncated).toBe(false)
expect(result.stdout.text).toBe('x'.repeat(500))
expect(result.stderr.truncated).toBe(true)
expect(result.stderr.text.length).toBeLessThanOrEqual(100)
})
it('per-call timeout takes precedence under the cap and kills on expiry', async () => {
@@ -111,21 +128,28 @@ describe('LocalBashExecutor.run', () => {
await expect(bash.run(bash.resolve({ command: 'true', workdir: '/nonexistent-dsh' }))).rejects.toThrow(/ENOENT/)
})
it('resolve() carries stdin/env onto the spec, and run() threads them to the command', async () => {
it('resolve() carries stdin/env/dshEnv onto the spec, and run() threads them to the command', async () => {
const { bash } = await setup()
const spec = bash.resolve({ command: 'cat; echo "[$DSH_SEAM_VAR]"', stdin: 'piped\n', env: { DSH_SEAM_VAR: 'env-ok' } })
// resolve() keeps the stdin/env fields verbatim (optional, no default).
const spec = bash.resolve({
command: 'cat; echo "[$SEAM_VAR][$DSH_SEAM_VAR]"',
stdin: 'piped\n',
env: { SEAM_VAR: 'env-ok' },
dshEnv: { DSH_SEAM_VAR: 'dsh-ok' },
})
// resolve() keeps the optional input/environment fields verbatim.
expect(spec.stdin).toBe('piped\n')
expect(spec.env).toEqual({ DSH_SEAM_VAR: 'env-ok' })
expect(spec.env).toEqual({ SEAM_VAR: 'env-ok' })
expect(spec.dshEnv).toEqual({ DSH_SEAM_VAR: 'dsh-ok' })
const result = await bash.run(spec)
expect(result.stdout.text).toBe('piped\n[env-ok]\n')
expect(result.stdout.text).toBe('piped\n[env-ok][dsh-ok]\n')
})
it('resolve() omits stdin/env when the request supplies neither', async () => {
it('resolve() omits stdin/env/dshEnv when the request supplies none', async () => {
const { bash } = await setup()
const spec = bash.resolve({ command: 'true' })
expect('stdin' in spec).toBe(false)
expect('env' in spec).toBe(false)
expect('dshEnv' in spec).toBe(false)
})
})
@@ -144,11 +168,12 @@ describe('LocalBashExecutor.start (background process handles)', () => {
it('threads stdin and extra env into a background process', async () => {
const { bash } = await setup()
const proc = bash.start(bash.resolve({
command: 'cat; echo "[$DSH_BG_VAR]"',
command: 'cat; echo "[$BG_VAR][$DSH_BG_VAR]"',
stdin: 'bg-stdin\n',
env: { DSH_BG_VAR: 'bg-env' },
env: { BG_VAR: 'bg-env' },
dshEnv: { DSH_BG_VAR: 'bg-dsh-env' },
}))
const output = await readUntil(proc, '[bg-env]')
const output = await readUntil(proc, '[bg-env][bg-dsh-env]')
expect(output).toContain('bg-stdin')
await proc.done
expect(proc.exitCode).toBe(0)

View File

@@ -2,6 +2,7 @@ import { mkdtempSync, readFileSync, statSync, unlinkSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { dirname, join } from 'node:path'
import { describe, expect, it, vi } from 'vitest'
import type { DshEnvironment } from '@deepseek-ai/dsh-bash'
import { killGroup, OutputCollector, runBash } from '../src/run.ts'
import type { RunningBash } from '../src/run.ts'
@@ -36,7 +37,8 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
return {
command,
cwd: process.cwd(),
maxOutputBytes: 64_000,
stdoutMaxBytes: 64_000,
stderrMaxBytes: 64_000,
maxSpillBytes: 64 * 1024 * 1024,
graceMs: 3_000,
...overrides,
@@ -224,19 +226,19 @@ describe('stdin and extra env (set by in-process plugins)', () => {
expect(piped.stdout.text).toBe('socket\n')
})
it('merges extra env entries onto the scrubbed environment', async () => {
const result = await runBash(spec('echo "$DSH_EXTRA_ONE/$DSH_EXTRA_TWO"', {
env: { DSH_EXTRA_ONE: 'alpha', DSH_EXTRA_TWO: 'beta' },
it('merges ordinary extra env entries onto the scrubbed environment', async () => {
const result = await runBash(spec('echo "$EXTRA_ONE/$EXTRA_TWO"', {
env: { EXTRA_ONE: 'alpha', EXTRA_TWO: 'beta' },
})).done
expect(result.stdout.text).toBe('alpha/beta\n')
})
it('an explicit extra env entry overrides the model-friendly override and the scrub', async () => {
// TERM is a model-friendly OVERRIDE (dumb); an explicit extra entry wins.
// DSH_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit
// EXPLICIT_OVERRIDE_KEY matches the credential scrub pattern, yet an explicit
// entry is still honored — the scrub only drops AMBIENT process.env creds.
const result = await runBash(spec('echo "$TERM/$DSH_OVERRIDE_KEY"', {
env: { TERM: 'xterm-256color', DSH_OVERRIDE_KEY: 'explicit-wins' },
const result = await runBash(spec('echo "$TERM/$EXPLICIT_OVERRIDE_KEY"', {
env: { TERM: 'xterm-256color', EXPLICIT_OVERRIDE_KEY: 'explicit-wins' },
})).done
expect(result.stdout.text).toBe('xterm-256color/explicit-wins\n')
})
@@ -251,10 +253,24 @@ describe('stdin and extra env (set by in-process plugins)', () => {
})
describe('output truncation and spill', () => {
it('applies stdout and stderr caps independently', async () => {
const result = await runBash(
spec('printf "%.0sx" $(seq 1 500); printf "%.0se" $(seq 1 500) >&2', {
stdoutMaxBytes: 500,
stderrMaxBytes: 100,
}),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(false)
expect(result.stdout.text).toBe('x'.repeat(500))
expect(result.stderr.truncated).toBe(true)
expect(result.stderr.text.length).toBeLessThanOrEqual(100)
})
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 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(true)
@@ -269,7 +285,7 @@ describe('output truncation and spill', () => {
it('does not truncate output exactly at the cap', async () => {
const result = await runBash(
spec('printf "%.0sx" $(seq 1 500)', { maxOutputBytes: 500 }),
spec('printf "%.0sx" $(seq 1 500)', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(result.stdout.truncated).toBe(false)
@@ -280,7 +296,7 @@ describe('output truncation and spill', () => {
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 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
expect(failNextClose.value).toBe(false)
@@ -415,13 +431,13 @@ describe('abort edge cases', () => {
})
describe('environment and spill-file hardening', () => {
it('scrubs credential-shaped env vars from child processes', async () => {
it('scrubs credential-shaped and ambient DSH env vars from child processes', async () => {
process.env.DSH_TEST_API_KEY = 'super-secret'
process.env.DSH_TEST_TOKEN = 'also-secret'
process.env.DSH_TEST_PLAIN = 'visible'
try {
const result = await runBash(spec('echo "[${DSH_TEST_API_KEY:-absent}|${DSH_TEST_TOKEN:-absent}|${DSH_TEST_PLAIN:-absent}]"')).done
expect(result.stdout.text.trim()).toBe('[absent|absent|visible]')
expect(result.stdout.text.trim()).toBe('[absent|absent|absent]')
} finally {
delete process.env.DSH_TEST_API_KEY
delete process.env.DSH_TEST_TOKEN
@@ -429,9 +445,32 @@ describe('environment and spill-file hardening', () => {
}
})
it('injects only the current trusted DSH environment after scrubbing ambient values', async () => {
process.env.DSH_STALE = 'old-value'
try {
const result = await runBash(spec('echo "[${DSH_STALE:-absent}|$DSH_SHELL|$DSH_SESSION_ID]"', {
dshEnv: { DSH_SHELL: '1', DSH_SESSION_ID: 'current-session' },
})).done
expect(result.stdout.text.trim()).toBe('[absent|1|current-session]')
} finally {
delete process.env.DSH_STALE
}
})
it('rejects DSH variables on the ordinary env channel', () => {
expect(() => runBash(spec('true', { env: { DSH_WRONG_CHANNEL: 'bad' } })))
.toThrow(/DSH_WRONG_CHANNEL.*dshEnv/)
})
it('rejects ordinary variables on the managed env channel', () => {
const invalid = { PATH: '/wrong-channel' } as unknown as DshEnvironment
expect(() => runBash(spec('true', { dshEnv: invalid })))
.toThrow(/managed bash env.*PATH.*use env/)
})
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 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
{ spillDir },
).done
const path = result.stdout.spillPath!
@@ -442,7 +481,7 @@ describe('environment and spill-file hardening', () => {
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 }),
spec('for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', { stdoutMaxBytes: 500, stderrMaxBytes: 500 }),
).done
const dir = dirname(result.stdout.spillPath!)
expect(dir).toMatch(/dsh-bash-/)