feat(sandbox): cross-family file sandbox — one policy home, sandboxed fs provider, fs escalation parity

Extend SandboxMode enforcement from bash to the filesystem tools, the sandbox
RFC's deferred cross-family phase.

- dsh-sandbox-policy (new, ctx.sandboxPolicy): the single home for the
  deployment default mode + workspaceRoot and the per-session override event,
  renamed bash/sandbox-mode -> sandbox/mode and moved here with its fold/setter.
  Decouples the bash seam from dsh-session.
- dsh-fs-sandbox (new): SandboxedFileSystem extends LocalFileSystem and fences
  write/edit by the per-call mode (read-only denies, workspace-write contains to
  the workspace + temp roots via the shared writableRoots, danger passes
  through); reads pass through. Structured FS_SANDBOX_DENIED; in-lock parent
  re-canonicalization. A policy fence in trusted code, not a kernel boundary.
- dsh-sandbox: the shared escalation kit (writableRoots, the strictly-wider
  ladder, denial/hint markers, approveEscalation) both tool families use;
  approveEscalation takes a structural approver so dsh-sandbox gains no
  approval/agent dependency, and both tools stay duplication-free.
- tool-fs: write/edit advertise sandbox_permissions/justification under a
  confining ctx.fs, map FS_SANDBOX_DENIED to the shared [sandbox: ...] marker,
  and resolve the same one-approved-wider retry.
- examples/acp-agent: composes sandbox-policy + fs-sandbox, drops the gating
  that disabled the fs stack under confined modes.

RFC docs/rfc/implemented/feature/2026-07-14-cross-family-fs-sandbox.md; the old
sandbox RFC's In-process/deferred/FAQ sections updated to shipped fact.
This commit is contained in:
kingwl
2026-07-14 20:05:57 +08:00
parent c3137b5474
commit 2dc62497ce
100 changed files with 2238 additions and 385 deletions
+35 -8
View File
@@ -20,6 +20,7 @@ import type {} from '@deepseek-ai/dsh-fs'
import type {} from '@deepseek-ai/dsh-system-prompt'
import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts'
import { sessionCwd } from './session-cwd.ts'
import type { FsSandboxSurface } from './sandbox.ts'
/** Validated `edit` arguments after defaulting. */
interface EditInput {
@@ -29,6 +30,20 @@ interface EditInput {
replaceAll: boolean
}
/**
* The `edit` tool's validated argument shape: the base parameters plus the two
* escalation fields, advertised only under a confining `ctx.fs` (absent from
* the schema otherwise, so the validator rejects them before `execute`).
*/
interface EditToolArgs {
file_path: string
old_string: string
new_string: string
replace_all?: boolean
sandbox_permissions?: string
justification?: string
}
/**
* Validate value constraints the schema DSL can't express: a non-blank
* `file_path`, a non-empty `old_string`, and `old_string !== new_string`
@@ -63,8 +78,9 @@ export function formatEditOutput(displayPath: string, replaceAll: boolean): stri
/**
* Register the `edit` tool and its system-prompt guidance.
* @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service.
* @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping).
*/
export function applyEditTool(ctx: Context): void {
export function applyEditTool(ctx: Context, sandbox: FsSandboxSurface): void {
ctx.systemPrompt.section({
name: 'tool:edit',
order: 102,
@@ -79,21 +95,32 @@ export function applyEditTool(ctx: Context): void {
old_string: { type: 'string', required: true, description: 'Literal text to replace. Must match exactly.' },
new_string: { type: 'string', required: true, description: 'Literal replacement text. Use an empty string to delete the match.' },
replace_all: { type: 'boolean', description: 'Replace all matches. Defaults to false; when false, old_string must appear exactly once.' },
...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {},
},
async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
async execute(args: EditToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
const input = parseEditArgs(args)
// Resolve the per-call sandbox mode (escalation grant > session override
// > backend default) BEFORE anything executes.
const sandboxMode = await sandbox.stampMode('edit', args, exec)
const cwd = sessionCwd(exec)
const target = await ctx.fs.resolve(input.filePath, cwd !== undefined ? { cwd } : undefined)
// Single-slot decision: the policy plugin returns { version: vObserved } or
// throws FS_NOT_OBSERVED; the bare default is undefined (unconditional edit).
// No stat — the bare default never manufactures a version basis.
const intent = await ctx.waterfall('fs/edit-intent', target, exec, () => undefined)
const outcome = await ctx.fs.editText(
target,
{ oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll },
intent,
exec.signal,
)
let outcome
try {
outcome = await ctx.fs.editText(
target,
{ oldString: input.oldString, newString: input.newString, replaceAll: input.replaceAll },
intent,
exec.signal,
sandboxMode,
)
} catch (error: unknown) {
// A sandbox denial becomes the shared [sandbox: …] marker; any other error passes through.
throw sandbox.mapError(error, sandboxMode)
}
// Record the observed version (a no-op when no policy plugin listens).
ctx.emit('fs/observed', target, outcome.version, exec)
// The result-time applied-hunk diff (before→after with context lines). An
+10 -2
View File
@@ -24,10 +24,12 @@
import type { Context } from 'cordis'
import z from 'schemastery'
import type {} from '@deepseek-ai/dsh-user-approval'
import { applyReadTool, READ_LIMIT, STREAM_MIN_SIZE } from './read.ts'
import { applyWriteTool } from './write.ts'
import { applyEditTool } from './edit.ts'
import { READ_MAX_BYTES, READ_MAX_LINE_LENGTH } from './read-render.ts'
import { FsSandboxSurface } from './sandbox.ts'
export { READ_LIMIT, STREAM_MIN_SIZE, applyReadTool, parseReadArgs } from './read.ts'
export type { ReadToolCaps } from './read.ts'
@@ -37,6 +39,8 @@ export { READ_MAX_BYTES, READ_MAX_LINE_LENGTH, buildWindow, formatReadOutput } f
export type { FileReadOutcome, FileTextLine, ReadWindow, WindowResult } from './read-render.ts'
export { DIFF_CONTEXT, computeHunkDiffs, diffsFromMeta } from './diff.ts'
export type { FsDiffMeta } from './diff.ts'
export { FsSandboxSurface } from './sandbox.ts'
export type { EscalationSchemaFields, FsEscalationArgs } from './sandbox.ts'
/** Cordis plugin name used by loader diagnostics. */
export const name = 'tool-fs'
@@ -87,6 +91,10 @@ export function apply(ctx: Context, config: Config): void {
maxBytes: resolved.readMaxBytes,
streamMinSize: resolved.readStreamMinSize,
})
applyWriteTool(ctx)
applyEditTool(ctx)
// One escalation surface shared by both mutating tools: advertisement gating,
// per-call mode stamping, and denial-marker mapping, all keyed off whether
// the mounted ctx.fs confines (ctx.fs.sandboxMode).
const sandbox = new FsSandboxSurface(ctx)
applyWriteTool(ctx, sandbox)
applyEditTool(ctx, sandbox)
}
+132
View File
@@ -0,0 +1,132 @@
/**
* The sandbox-escalation surface shared by the `write` and `edit` tools: the
* per-call mode stamp, the advertised escalation fields, and the denial-marker
* mapping — all delegating the vocabulary and the fail-closed approval
* sequence to `@deepseek-ai/dsh-sandbox` (the same pieces `@deepseek-ai/dsh-tool-bash`
* uses), so bash and fs escalate identically. Built ONCE per plugin from
* `ctx.fs.sandboxMode` (the capability fact — is a confining backend mounted?)
* and shared by both mutating tools.
*
* @module @deepseek-ai/dsh-tool-fs/sandbox
*/
import type { Context } from 'cordis'
import type { ToolExecution } from '@deepseek-ai/dsh-tools'
import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
import { ESCALATION_TARGETS, approveEscalation, escalationHintMarker, sandboxDenialMarker, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox'
import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
import { FsError } from '@deepseek-ai/dsh-fs'
/** The two escalation arguments a mutating tool may carry (advertised only under a confining backend). */
export interface FsEscalationArgs {
sandbox_permissions?: string
justification?: string
}
/** The schema fields for the escalation arguments, spread into a tool's `parameters` when a confining backend is mounted. */
export interface EscalationSchemaFields {
sandbox_permissions: { type: 'string'; enum: string[]; description: string }
justification: { type: 'string'; description: string }
}
/**
* The filesystem escalation surface: advertisement gating, per-call mode
* stamping (folding the session's `sandbox/mode` override), the one-approved
* wider retry, and denial-marker mapping. A pure product of `ctx` at plugin
* apply time.
*/
export class FsSandboxSurface {
/** The escalation targets this composition advertises (`[]` when no confining backend is mounted). */
readonly escalationModes: readonly SandboxMode[]
/** The backend's default mode, or `undefined` when `ctx.fs` does not confine. */
private readonly defaultMode: SandboxMode | undefined
constructor(private readonly ctx: Context) {
this.defaultMode = ctx.fs.sandboxMode
this.escalationModes = this.defaultMode === undefined ? [] : ESCALATION_TARGETS
}
/**
* The escalation schema fields for a mutating tool's `parameters`. Call it
* only under a confining backend (guard on {@link escalationModes}); the
* enum pins the closed target vocabulary, the strict-wider check happens per
* call at execution.
* @returns the two escalation parameter specs.
*/
schemaFields(): EscalationSchemaFields {
return {
sandbox_permissions: {
type: 'string',
enum: [...this.escalationModes],
description: 'The wider sandbox mode this file operation needs. Only valid as a one-shot retry '
+ 'of an operation the sandbox just denied; requires justification and user approval.',
},
justification: {
type: 'string',
description: 'Required with sandbox_permissions: one sentence for the user explaining '
+ 'why this exact file operation needs the wider access.',
},
}
}
/**
* The session's standing mode override for an ordinary (non-escalating)
* call — the `sandbox/mode` fold of the calling agent's log. Undefined for a
* non-confining backend and for agent-less callers.
*/
private sessionOverride(exec: ToolExecution): SandboxMode | undefined {
if (this.defaultMode === undefined || exec.agent === undefined) return undefined
return effectiveSandboxMode(exec.agent.session.events)
}
/**
* The mode to STAMP onto this mutation: an approved escalation grant (a
* strictly wider retry resolved through `ctx.approval` before anything
* executes), else the session's standing override, else `undefined` (the
* backend applies its own default). Validates the escalation argument
* pairing first.
* @param toolName - the mutating tool's name, for the approval audit trail.
* @param args - the call's escalation arguments.
* @param exec - the tool-execution context (agent, callId, signal).
* @returns the mode to pass to the mutation, or undefined for the backend default.
*/
async stampMode(toolName: string, args: FsEscalationArgs, exec: ToolExecution): Promise<SandboxMode | undefined> {
validateEscalationArgs(args.sandbox_permissions, args.justification)
if (args.sandbox_permissions === undefined || args.justification === undefined) {
return this.sessionOverride(exec)
}
if (this.escalationModes.length === 0) {
throw new Error('sandbox_permissions is not available in this composition (no sandboxing filesystem to escalate)')
}
const effectiveMode = (this.sessionOverride(exec) ?? this.defaultMode) as SandboxMode
return approveEscalation(
{ requestedMode: args.sandbox_permissions, justification: args.justification, effectiveMode, subject: 'operation' },
{
approver: this.ctx.get('approval'),
agent: exec.agent,
callId: exec.callId,
toolName,
...exec.signal ? { signal: exec.signal } : {},
},
)
}
/**
* Map a thrown provider error for the model: a `FS_SANDBOX_DENIED` becomes an
* error whose text is the shared `[sandbox: …]` denial marker plus the
* same-turn escalation hint, so a policy denial reads identically to bash's;
* any other error passes through unchanged. A `FS_SANDBOX_DENIED` only arises
* under a confining backend, which always advertises the escalation fields,
* so the hint always applies here.
* @param error - the error thrown by the mutation.
* @param stampedMode - the mode stamped onto the call (names the mode in the marker).
* @returns the error to throw — the marker error for a sandbox denial, else the original.
*/
mapError(error: unknown, stampedMode: SandboxMode | undefined): unknown {
if (!(error instanceof FsError) || error.code !== 'FS_SANDBOX_DENIED') return error
// A FS_SANDBOX_DENIED only arises under a confining backend, so defaultMode
// (hence the resolved mode) is defined here.
const mode = (stampedMode ?? this.defaultMode) as SandboxMode
return new Error(`${sandboxDenialMarker(mode)}\n${escalationHintMarker('operation')}`)
}
}
+29 -3
View File
@@ -20,6 +20,7 @@ import type {} from '@deepseek-ai/dsh-fs'
import type {} from '@deepseek-ai/dsh-system-prompt'
import { computeHunkDiffs, diffsFromMeta, type FsDiffMeta } from './diff.ts'
import { sessionCwd } from './session-cwd.ts'
import type { FsSandboxSurface } from './sandbox.ts'
/**
* Validate value constraints the schema DSL can't express: only a non-blank
@@ -47,11 +48,24 @@ ${verb} file
</content>`
}
/**
* The `write` tool's validated argument shape: the base parameters plus the
* two escalation fields, advertised only under a confining `ctx.fs` (absent
* from the schema otherwise, so the validator rejects them before `execute`).
*/
interface WriteToolArgs {
file_path: string
content: string
sandbox_permissions?: string
justification?: string
}
/**
* Register the `write` tool and its system-prompt guidance.
* @param ctx - the plugin context; registrations are effects scoped to it, and execution uses its `fs` service.
* @param sandbox - the shared sandbox-escalation surface (advertisement, mode stamping, denial mapping).
*/
export function applyWriteTool(ctx: Context): void {
export function applyWriteTool(ctx: Context, sandbox: FsSandboxSurface): void {
ctx.systemPrompt.section({
name: 'tool:write',
order: 101,
@@ -64,15 +78,27 @@ export function applyWriteTool(ctx: Context): void {
parameters: {
file_path: { type: 'string', required: true, description: 'Path to write, resolved by the filesystem backend.' },
content: { type: 'string', required: true, description: 'Full UTF-8 text content to write.' },
...sandbox.escalationModes.length > 0 ? sandbox.schemaFields() : {},
},
async execute(args, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
async execute(args: WriteToolArgs, exec): Promise<{ content: ContentBlock[]; meta?: FsDiffMeta }> {
const input = parseWriteArgs(args)
// Resolve the per-call sandbox mode (escalation grant > session override
// > backend default) BEFORE anything executes; an escalating call
// resolves approval here and throws its distinct text on any non-grant.
const sandboxMode = await sandbox.stampMode('write', args, exec)
const cwd = sessionCwd(exec)
const target = await ctx.fs.resolve(input.filePath, cwd !== undefined ? { cwd } : undefined)
// Single-slot decision: the policy plugin produces createIfAbsent/
// replaceIfVersion; the bare default is undefined (unconditional). No stat.
const intent = await ctx.waterfall('fs/write-intent', target, exec, () => undefined)
const outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal)
let outcome: FsWriteOutcome
try {
outcome = await ctx.fs.writeText(target, input.content, intent, exec.signal, sandboxMode)
} catch (error: unknown) {
// A sandbox denial becomes the shared [sandbox: …] marker (the model
// recognizes it from bash); any other error passes through.
throw sandbox.mapError(error, sandboxMode)
}
// Record the observed version (a no-op when no policy plugin listens).
ctx.emit('fs/observed', target, outcome.version, exec)
// Attach a contextual hunk as `meta` ONLY for an overwrite (a before-version