Merge remote-tracking branch 'origin/master' into simpl-a1-drop-image

# Conflicts:
#	docs/architecture.md
#	packages/compact/compact-basic/README.md
This commit is contained in:
Tianyi Cui
2026-07-04 21:12:33 +08:00
112 changed files with 1825 additions and 835 deletions

View File

@@ -12,6 +12,7 @@ Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `L
timeoutMs: 120000 # default foreground timeout
maxTimeoutMs: 600000 # cap for per-call overrides
maxOutputBytes: 64000 # per-stream in-memory cap; overflow spills to disk
graceMs: 3000 # SIGTERM→SIGKILL escalation grace on kills
```
## Behavior (and where it came from)
@@ -19,7 +20,7 @@ Local-subprocess implementation of the `@deepseek-ai/dsh-bash` executor seam: `L
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.
- **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). 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 + 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).
- **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.

View File

@@ -17,7 +17,7 @@ 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.ts'
import { DEFAULT_GRACE_MS, runBash } from './run.ts'
import type { RunInternals, RunningBash } from './run.ts'
export { DEFAULT_GRACE_MS, ENV_OVERRIDES, killGroup, OutputCollector, runBash } from './run.ts'
@@ -33,6 +33,8 @@ export interface Config {
maxTimeoutMs?: number
/** Per-stream in-memory output cap; overflow spills to a temp file. */
maxOutputBytes?: number
/** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
graceMs?: number
}
/** The shape after schemastery applied the defaults (cwd has none). */
@@ -57,7 +59,7 @@ interface TrackedTask extends BashTask {
* 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).
* process-group SIGTERM→SIGKILL kills with a 3s grace (OpenCode).
*/
export class LocalBashExecutor extends BashExecutor {
static Config: z<Config> = z.object({
@@ -65,11 +67,12 @@ export class LocalBashExecutor extends BashExecutor {
timeoutMs: z.number().default(120_000),
maxTimeoutMs: z.number().default(600_000),
maxOutputBytes: z.number().default(64_000),
graceMs: z.number().default(DEFAULT_GRACE_MS),
})
private tasks = new Map<BashTaskId, TrackedTask>()
private nextTaskId = 1
/** Test seam: timer/spill knobs forwarded to runBash. */
/** Test seam: spill knobs forwarded to runBash. */
internals: RunInternals = {}
/** Validated config (schemastery applied the defaults before construction). */
@@ -83,6 +86,7 @@ export class LocalBashExecutor extends BashExecutor {
assertPositiveFinite('timeoutMs', this.config.timeoutMs)
assertPositiveFinite('maxTimeoutMs', this.config.maxTimeoutMs)
assertPositiveFinite('maxOutputBytes', this.config.maxOutputBytes)
assertPositiveFinite('graceMs', this.config.graceMs)
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
@@ -132,6 +136,7 @@ export class LocalBashExecutor extends BashExecutor {
cwd: spec.workdir,
timeoutMs: spec.timeoutMs,
maxOutputBytes: this.config.maxOutputBytes,
graceMs: this.config.graceMs,
signal: spec.signal,
stdin: spec.stdin,
env: spec.env,
@@ -150,6 +155,7 @@ export class LocalBashExecutor extends BashExecutor {
cwd: spec.workdir,
timeoutMs: 0,
maxOutputBytes: this.config.maxOutputBytes,
graceMs: this.config.graceMs,
signal: spec.signal,
stdin: spec.stdin,
env: spec.env,

View File

@@ -73,6 +73,8 @@ export interface SpawnSpec {
timeoutMs: number
/** Per-stream in-memory cap; overflow spills to disk (tail kept in memory). */
maxOutputBytes: number
/** Grace period between the SIGTERM and the SIGKILL escalation on a kill. */
graceMs: number
/** Abort signal — kills the process group when fired. */
signal?: AbortSignal | undefined
/**
@@ -100,15 +102,13 @@ export interface SpawnOutcome {
stderr: CollectedOutput
}
/** Injectable knobs so tests can exercise escalation/spill without long waits. */
/** Injectable knobs so tests can exercise spill behavior without the OS tmpdir. */
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). */
/** Default SIGTERM→SIGKILL grace period (the `graceMs` config; matches OpenCode's 3s). */
export const DEFAULT_GRACE_MS = 3_000
let spillCounter = 0
@@ -292,7 +292,6 @@ export interface RunningBash {
* 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) {
@@ -331,7 +330,7 @@ export function runBash(spec: SpawnSpec, internals: RunInternals = {}): RunningB
const kill = (): void => {
if (graceTimer !== undefined) return // escalation already in flight
killGroup(pid, 'SIGTERM')
graceTimer = setTimeout(() => { killGroup(pid, 'SIGKILL') }, graceMs)
graceTimer = setTimeout(() => { killGroup(pid, 'SIGKILL') }, spec.graceMs)
}
if (spec.timeoutMs > 0) {

View File

@@ -11,9 +11,10 @@ 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)
// A short kill grace via the REAL config path, so escalation tests stay fast.
await ctx.plugin(LocalBashExecutor, { graceMs: 200, ...config })
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
bash.internals = { spillDir }
return { ctx, bash }
}
@@ -80,12 +81,22 @@ describe('LocalBashExecutor.run', () => {
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/)
await expect(setup({ graceMs: 0 })).rejects.toThrow(/graceMs/)
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('kill escalation uses the configured graceMs (a TERM-trapping task dies by SIGKILL)', async () => {
const { bash } = await setup() // setup pins graceMs: 200 via config
const task = bash.start(bash.resolve({ command: 'trap \'\' TERM; sleep 60' }))
await new Promise(resolve => setTimeout(resolve, 100))
bash.kill(task.id)
await task.done
expect(task.signal).toBe('SIGKILL')
})
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 }))
@@ -271,9 +282,9 @@ describe('LocalBashExecutor background tasks', () => {
it('disposing with already-finished tasks only kills the running ones', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const fiber = await ctx.plugin(LocalBashExecutor, { graceMs: 200 })
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
bash.internals = { spillDir }
const finished = bash.start(bash.resolve({ command: 'true' }))
await finished.done
@@ -288,9 +299,9 @@ describe('LocalBashExecutor background tasks', () => {
it('disposing the executor fiber kills running tasks (no orphans)', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const fiber = await ctx.plugin(LocalBashExecutor, { graceMs: 200 })
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
bash.internals = { spillDir }
const listener = vi.fn()
bash.onTaskDone(listener)
@@ -337,9 +348,9 @@ describe('review fixes: lifecycle hardening', () => {
it('dispose AWAITS a TERM-trapping process (SIGKILL escalation included)', async () => {
const ctx = new Context()
const fiber = await ctx.plugin(LocalBashExecutor, {})
const fiber = await ctx.plugin(LocalBashExecutor, { graceMs: 200 })
const bash = ctx.bash as LocalBashExecutor
bash.internals = { spillDir, graceMs: 200 }
bash.internals = { spillDir }
const task = bash.start(bash.resolve({ command: 'trap \'\' TERM; sleep 60' }))
await new Promise(resolve => setTimeout(resolve, 100))

View File

@@ -28,6 +28,7 @@ function spec(command: string, overrides: Partial<Parameters<typeof runBash>[0]>
cwd: process.cwd(),
timeoutMs: 0,
maxOutputBytes: 64_000,
graceMs: 3_000,
...overrides,
}
}
@@ -106,7 +107,7 @@ describe('runBash', () => {
})
it('escalates to SIGKILL when SIGTERM is trapped', async () => {
const running = runBash(spec('trap \'\' TERM; echo ready; sleep 60'), { graceMs: 200 })
const running = runBash(spec('trap \'\' TERM; echo ready; sleep 60', { graceMs: 200 }))
await waitForStdout(running, 'ready\n')
running.kill()
const result = await running.done

View File

@@ -77,16 +77,32 @@ export abstract class BashExecutor extends Service {
* call this, then pass the result to {@link run}/{@link start} — keeping
* defaulting in the implementation that owns the config while the seam type
* stays explicit (no hidden `?? default` inside run/start).
* @param request - the caller's request; omitted fields get this
* implementation's defaults, capped fields are clamped.
* @returns the fully-specified spec to hand to {@link run}/{@link start}.
*/
abstract resolve(request: BashExecRequest): BashExecSpec
/** Run a command in the foreground; resolves when it finishes. */
/**
* Run a command in the foreground; resolves when it finishes.
* @param spec - a resolved spec from {@link resolve}, never a raw request.
* @returns the outcome; nonzero exits, timeout kills, and abort kills
* resolve with a descriptive result rather than reject.
*/
abstract run(spec: BashExecSpec): Promise<BashRunResult>
/** Start a background task and return its handle immediately. */
/**
* Start a background task and return its handle immediately.
* @param spec - a resolved spec from {@link resolve}, never a raw request.
* @returns the live task handle; completion fires {@link onTaskDone}.
*/
abstract start(spec: BashExecSpec): BashTask
/** Look up a background task by id. */
/**
* Look up a background task by id.
* @param id - the task id to look up.
* @returns the tracked task, or undefined for an id this executor never issued.
*/
abstract get(id: BashTaskId): BashTask | undefined
/**
@@ -101,24 +117,38 @@ export abstract class BashExecutor extends Service {
* loudly at the subsequent {@link readOutput}/{@link kill} ("unknown task").
* Storing ownership in the executor (disposed with ITS fiber) — not in the
* tool plugin — is what makes ownership survive a `tool-bash` HMR reload.
* @param id - the background task id to look up ownership for.
* @returns the token recorded at start, verbatim; undefined for an unknown
* id or a known-but-ownerless task.
*/
abstract ownerOf(id: BashTaskId): OwnerToken | undefined
/** All tracked background tasks (insertion order). */
/**
* All tracked background tasks (insertion order).
* @returns every task this executor started, running or finished.
*/
abstract list(): BashTask[]
/** Read output produced since the previous read. Throws for unknown ids. */
/**
* Read output produced since the previous read. Throws for unknown ids.
* @param id - the task to read from.
* @returns the incremental read; consecutive reads never re-deliver output.
*/
abstract readOutput(id: BashTaskId): BashTaskRead
/**
* Kill a running background task. Returns false when it had already
* finished (no-op). Throws for unknown ids.
* @param id - the task to kill.
* @returns true when this call killed it, false when it had already finished.
*/
abstract kill(id: BashTaskId): boolean
/**
* Register a background-task completion listener (disposed with the
* calling fiber). Listeners never fire after this service is disposed.
* @param listener - called exactly once per task completion.
* @returns the disposer that unregisters the listener.
*/
onTaskDone(listener: BashTaskListener): () => void {
const dispose = this.ctx.effect(() => {

View File

@@ -21,8 +21,8 @@ async function setup() {
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(AgentRegistry)
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir, graceMs: 200 }
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, graceMs: 200 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir }
await ctx.plugin(ToolBash)
return ctx
}
@@ -184,8 +184,8 @@ describe('bash tool', () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(LocalBashExecutor, { maxOutputBytes: 100 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir, graceMs: 200 }
await ctx.plugin(LocalBashExecutor, { maxOutputBytes: 100, graceMs: 200 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir }
await ctx.plugin(ToolBash)
const result = await call(ctx, 'bash', { command: 'for i in $(seq 1 100); do printf "line-%04d\\n" $i; done', description: 'test command' })
expect(text(result)).toContain('[output truncated; full output: ')
@@ -316,8 +316,8 @@ describe('background tools', () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(LocalBashExecutor, { maxOutputBytes: 100 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir, graceMs: 200 }
await ctx.plugin(LocalBashExecutor, { maxOutputBytes: 100, graceMs: 200 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir }
await ctx.plugin(ToolBash)
const started = await call(ctx, 'bash', { command: 'for i in $(seq 1 200); do printf "line-%04d\\n" $i; done', description: 'test command', run_in_background: true })
@@ -568,8 +568,8 @@ describe('background task ownership (cross-session isolation)', () => {
const ctx = new Context()
await ctx.plugin(SystemPrompt)
await ctx.plugin(ToolRegistry)
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir, graceMs: 200 }
await ctx.plugin(LocalBashExecutor, { timeoutMs: 10_000, graceMs: 200 })
;(ctx.bash as LocalBashExecutor).internals = { spillDir }
const fiber = await ctx.plugin(ToolBash)
const a = fakeAgent('sess-a')