fix(tasks): close background task review findings

This commit is contained in:
Yichen Jiang
2026-07-13 16:29:50 +08:00
parent e2bc79a0ef
commit 351a2e42b3
14 changed files with 78 additions and 25 deletions
+1 -1
View File
@@ -13,7 +13,7 @@ Every command is confined by handing the provider the exact `['bash', '-c', comm
Semantics:
- **Denials are result facts.** A failed run whose stderr carries the selected backend's own denial dialect — the signatures the provider stamps on every wrap (EROFS text under bwrap, EACCES under Landlock, EPERM under Seatbelt) — is reported as `BashRunResult.sandbox.denied: true` (conservative classification, read from the collected stderr tail); every CONFINED run also carries the mode it executed under (`result.sandbox.mode`) and the provider's enforcement completeness (`result.sandbox.enforcement`: `full`, or `partial` on an older Landlock ABI).
- **Runner failures are sandbox failures, never command failures.** Foreground execution throws `SANDBOX_UNAVAILABLE`; a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`.
- **Runner failures are sandbox failures, never command failures.** Foreground execution throws `SANDBOX_UNAVAILABLE`; a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`. Spawn failures also pass through settlement, so confined background handles retain their mode/enforcement facts and release per-process accounting.
- **Config-time default, per-call policy.** The DEFAULT mode is fixed by this entry's config for the executor's lifetime; `resolve()` stamps it onto every spec, and an explicit request-level `sandboxMode` override — set by the tool layer only for a call whose wider mode a human granted through `ctx.approval` ([the sandbox RFC § Escalation](../../../docs/rfc/implemented/feature/2026-07-06-sandbox.md)) — makes THAT call run, classify, and report under its own mode while every neighbor keeps the default (background facts are stamped per task at settle). The capability fact `ctx.bash.sandboxMode` reports the configured default so the tool layer advertises escalation only when this executor is mounted. The model learns of the sandbox only through result facts — the static bash tool description explains the denial marker; there is no current-mode statement in the system prompt.
- **File effects only.** Network and process visibility are deliberately not restricted — the mode vocabulary does not pretend to cover what the backend does not enforce.
- Process mechanics (spawn, process-group kills, output collection/spill, background handles, credential scrub) are inherited from [`dsh-bash-local`](../bash-local/); runner selection lives in [`dsh-sandbox-local`](../../sandbox/sandbox-local/).
+4 -4
View File
@@ -164,8 +164,8 @@ export class SandboxBashExecutor extends LocalBashExecutor {
private readonly mode: SandboxMode
private readonly workspaceRoot: string
/**
* Per-task facts, keyed by task id from `start()` until the settle stamp
* consumes them: the mode the task runs under (per-call — an escalated task
* Per-process facts, keyed by handle from `start()` until the settle stamp
* consumes them: the mode the process runs under (per-call — an escalated task
* differs from its neighbors) plus its wrap facts. The seam returns facts
* PER WRAP — a provider may legally vary enforcement or dialect between
* calls — so overlapping background tasks must each classify against their
@@ -234,8 +234,8 @@ export class SandboxBashExecutor extends LocalBashExecutor {
// Sandbox facts are stamped at settle time by onProcessDone()
// (denial classification runs against the settled task's collected
// stderr). The map entry lands synchronously after spawn, strictly
// before the earliest possible settle (a process exit reaches us no
// sooner than the next tick).
// before the earliest possible settle (including a spawn rejection, whose
// promise reaction cannot run until this synchronous start call returns).
const confined = this.confine(spec.command, mode)
const proc = super.start({ ...spec, command: confined.command })
const { enforcement, denialSignatures, runnerFailureSignatures } = confined
@@ -246,6 +246,20 @@ describe('result facts', () => {
})
describe('background sandbox facts', () => {
it('stamps facts and releases accounting when background spawn fails', async () => {
const { bash } = await setup()
const missingWorkdir = join(mkdtempSync(join(tmpdir(), 'dsh-sandbox-missing-cwd-')), 'missing')
const task = bash.start(bash.resolve({ command: 'true', workdir: missingWorkdir }))
await task.done
expect(task.status).toBe('killed')
expect(task.readOutput().delta).toContain('spawn failed:')
expect(task.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
const accounting = (bash as unknown as { processFacts: Map<unknown, unknown> }).processFacts
expect(accounting.size).toBe(0)
})
it('stamps a settled denial: nonzero exit + permission stderr under a confined mode', async () => {
const { bash } = await setup()
const task = bash.start(bash.resolve({ command: 'echo "x: Permission denied" >&2; exit 1' }))