deepseek-ai/deepseek-harness · error

invalid escalation: sandbox_permissions requires a justifica

Error message

invalid escalation: sandbox_permissions requires a justification

What it means

Error "invalid escalation: sandbox_permissions requires a justification" thrown in deepseek-ai/deepseek-harness.

Source

Thrown at packages/sandbox/sandbox/src/escalation.ts:53

 * escalate TO (`read-only` is the floor; nothing escalates to it). Advertised
 * whenever the mounted capability confines: cutting the enum down to the modes
 * wider than the composition's DEFAULT would strand a session whose effective
 * mode sits below it (a `danger-full-access` default would advertise nothing
 * while a narrower-switched session stays confined with no lever).
 */
export const ESCALATION_TARGETS: readonly SandboxMode[] = ['workspace-write', 'danger-full-access']

/**
 * Validate the escalation argument pairing a tool schema cannot express:
 * `sandbox_permissions` and `justification` travel together — an approval
 * prompt without a reason, or a reason driving nothing, is a malformed ask —
 * and the justification must be a non-empty sentence.
 * @param sandboxPermissions - the raw `sandbox_permissions` argument, if given.
 * @param justification - the raw `justification` argument, if given.
 */
export function validateEscalationArgs(sandboxPermissions: string | undefined, justification: string | undefined): void {
  if (sandboxPermissions !== undefined && justification === undefined) {
    throw new Error('invalid escalation: sandbox_permissions requires a justification')
  }
  if (justification !== undefined && sandboxPermissions === undefined) {
    throw new Error('invalid escalation: justification is only valid together with sandbox_permissions')
  }
  if (justification !== undefined && justification.trim().length === 0) {
    throw new Error('invalid justification: expected a non-empty sentence')
  }
}

/**
 * The model-facing denial marker — the one vocabulary both enforcing families
 * teach and report, so the model recognizes a policy denial identically
 * whether the kernel refused a bash file effect or the filesystem provider's
 * fence refused a mutation.
 * @param mode - the mode the denied call ran under.
 * @returns the marker line, exactly as the model sees it.
 */
export function sandboxDenialMarker(mode: SandboxMode): string {

View on GitHub (pinned to b150a551b8)

Solutions

1. Include a non-empty justification string with the sandbox_permissions request.

When it happens

Trigger: Thrown at packages/sandbox/sandbox/src/escalation.ts:53 when the library encounters an invalid state.

Common situations: See trigger scenarios.

AI-assisted analysis of deepseek-ai/deepseek-harness@b150a551b8 (2026-08-24). Data as JSON: /api/errors/6a693f37030ea838. Report an issue: GitHub.