Merge refreshed schema DSL into canonical tool outputs

# Conflicts:
#	packages/bash/tool-bash/tests/tools.spec.ts

packages/bash/bash-local/src/index.ts

@@ -109,10 +109,10 @@ export class LocalBashExecutor extends BashExecutor {
       ...request.stdin !== undefined ? { stdin: request.stdin } : {},
       ...request.env !== undefined ? { env: request.env } : {},
       ...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
-      // Carry a sandbox-mode override through verbatim: this executor never
+      // Carry a sandbox policy 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,
+      sandboxPolicy: request.sandboxPolicy,
     }
   }
 

packages/bash/bash-sandbox/README.md

@@ -16,7 +16,7 @@ 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`. Spawn failures also pass through settlement, so confined background handles retain their mode/enforcement facts and release per-process accounting.
-- **Deployment default, per-call policy.** The DEFAULT mode + workspace root are owned by [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) (one home both enforcing families read), not this executor's config; `resolve()` stamps the default 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 Agent Note § Escalation](../../../.agents/notes/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.
+- **Deployment fallback, per-call policy.** [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) resolves a complete `SandboxExecutionPolicy` for every tool call: the calling session supplies its mode override and immutable cwd root, while deployment config supplies the fallbacks for agentless calls. An approved escalation changes only that policy's mode; its session root stays attached. `resolve()` carries the policy onto the spec, so overlapping commands from different projects run, classify, and report under their own roots and modes. 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/).
 
@@ -29,12 +29,12 @@ Deny-only at the seam: a denial is a reported fact, and this executor never nego
   name: '@deepseek-ai/dsh-sandbox-policy'
   config:
     mode: read-only
-    workspaceRoot: !!js process.cwd()
+    workspaceRoot: !!js process.cwd() # fallback for calls without a session cwd
 - id: bash
   name: '@deepseek-ai/dsh-bash-sandbox'
 ```
 
-The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent); see [the acp-agent example's default composition](../../../examples/acp-agent/) for the runnable demo.
+The keyless consumer-integration proofs are `tests/bwrap.e2e.ts`, `tests/landlock.e2e.ts`, and `tests/seatbelt.e2e.ts` (the real provider + real runner driven through `ctx.bash`, world-verified, each self-skipping where its runner is absent). The agent-spine e2e additionally drives two concurrent sessions in one Cordis context and proves each real bash tool call can write only its own project. See [the acp-agent example's default composition](../../../examples/acp-agent/) for the runnable demo.
 
 ## Model Experience
 

packages/bash/bash-sandbox/src/index.ts

@@ -3,14 +3,15 @@
  * `ctx.sandbox`, inherits local process mechanics, and reports the selected
  * mode, enforcement, and denial facts. Runner failure means the command never
  * ran: foreground calls throw `SANDBOX_UNAVAILABLE`, while settled background
- * processes carry `runnerFailed`. The tool owns approval and passes per-call modes.
+ * processes carry `runnerFailed`. The tool owns approval and passes a complete
+ * per-call policy.
  * @module @deepseek-ai/dsh-bash-sandbox
  */
 
 import { Context } from 'cordis'
 import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash'
 import { SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
-import type { ConfinedSandboxMode, SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedSandboxMode, SandboxEnforcement, SandboxExecutionPolicy, SandboxMode, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
 import type {} from '@deepseek-ai/dsh-sandbox-policy'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
 import type { Config as LocalConfig } from '@deepseek-ai/dsh-bash-local'
@@ -18,21 +19,19 @@ import { classifyDenial, classifyRunnerFailure, matchesSignature, shellQuote } f
 
 /**
  * Plugin config: the local executor's knobs, verbatim. The sandbox policy —
- * the default mode and the `workspace-write` boundary root — is NOT here: it
- * lives on `ctx.sandboxPolicy` (`@deepseek-ai/dsh-sandbox-policy`), the one
- * home both enforcing families read, so bash and fs can never confine to
- * different roots. The runner choice is likewise the `ctx.sandbox` provider's
- * config, not this executor's.
+ * the default mode and fallback `workspace-write` root — is NOT here: it lives
+ * on `ctx.sandboxPolicy` (`@deepseek-ai/dsh-sandbox-policy`), which resolves
+ * each calling session's mode and cwd for both enforcing families. The runner
+ * choice is likewise the `ctx.sandbox` provider's config, not this executor's.
  */
 export type Config = LocalConfig
 
 /**
  * Registers as `ctx.bash` in place of the local executor and requires a
  * `ctx.sandbox` provider plus `ctx.sandboxPolicy`; the tool layer is
- * unchanged. The policy default (mode + workspace root) is the fallback,
- * while a session override or approved one-shot escalation may select each
- * call's mode. The prompt does not state the standing mode; `result.sandbox`
- * reports the mode and enforcement actually used.
+ * unchanged. Tool calls pass the calling session's resolved policy; direct
+ * calls fall back to deployment policy. The prompt does not state the standing
+ * mode; `result.sandbox` reports the mode and enforcement actually used.
  */
 export class SandboxBashExecutor extends LocalBashExecutor {
   static inject = ['sandbox', 'sandboxPolicy']
@@ -42,7 +41,6 @@ export class SandboxBashExecutor extends LocalBashExecutor {
   // verbatim (the config catalog walks the inherited static).
 
   private readonly mode: SandboxMode
-  private readonly workspaceRoot: string
   /**
    * Per-process confinement facts retained until settlement. Providers may
    * vary enforcement and diagnostic dialect between overlapping calls, so a
@@ -58,11 +56,9 @@ export class SandboxBashExecutor extends LocalBashExecutor {
 
   constructor(ctx: Context, config: Config) {
     super(ctx, config)
-    // The sandbox default (mode + workspaceRoot) is the one shared policy home
-    // both enforcing families read; injecting sandboxPolicy guarantees it is
-    // constructed first. workspaceRoot arrives already resolved absolute.
+    // The default mode is the capability fact used for schema advertisement;
+    // actual tool executions carry their resolved per-call policy.
     this.mode = ctx.sandboxPolicy.defaultMode
-    this.workspaceRoot = ctx.sandboxPolicy.workspaceRoot
   }
 
   /** The configured default mode — the capability fact the tool layer reads. */
@@ -71,24 +67,22 @@ export class SandboxBashExecutor extends LocalBashExecutor {
   }
 
   /**
-   * Stamp the effective mode onto the spec — the request's explicit override
-   * (an approved escalation), else this executor's configured default — so
-   * defaulting stays an explicit resolve step and `run()`/`start()` read the
-   * spec, never the config.
+   * Stamp a complete per-call policy onto the spec. Tool calls supply the
+   * calling session's resolved mode and root; lower-level callers fall back to
+   * the deployment policy.
    */
   override resolve(request: BashExecRequest): BashExecSpec {
-    return { ...super.resolve(request), sandboxMode: request.sandboxMode ?? this.mode }
+    return { ...super.resolve(request), sandboxPolicy: request.sandboxPolicy ?? this.ctx.sandboxPolicy.resolve() }
   }
 
   override async run(spec: BashExecSpec): Promise<BashRunResult> {
-    // resolve() always stamps the mode; the cast records that invariant
-    // (mirrors the constructor's config casts).
-    const mode = spec.sandboxMode as SandboxMode
+    const policy = spec.sandboxPolicy as SandboxExecutionPolicy
+    const { mode } = policy
     if (mode === 'danger-full-access') {
       const result = await super.run(spec)
       return { ...result, sandbox: { mode, denied: false } }
     }
-    const confined = this.confine(spec.command, mode)
+    const confined = this.confine(spec.command, { ...policy, mode })
     const result = await super.run({ ...spec, command: confined.command })
     // Runner failure outranks denial because the command did not run. Throw the
     // same fail-closed error as confine-time discovery with the first stderr line.
@@ -99,11 +93,11 @@ export class SandboxBashExecutor extends LocalBashExecutor {
   }
 
   override start(spec: BashExecSpec): BashProcess {
-    // Same stamped-by-resolve invariant as run().
-    const mode = spec.sandboxMode as SandboxMode
+    const policy = spec.sandboxPolicy as SandboxExecutionPolicy
+    const { mode } = policy
     if (mode === 'danger-full-access') return super.start(spec)
     // Install facts synchronously; promise settlement cannot run before start() returns.
-    const confined = this.confine(spec.command, mode)
+    const confined = this.confine(spec.command, { ...policy, mode })
     const proc = super.start({ ...spec, command: confined.command })
     const { enforcement, denialSignatures, runnerFailureSignatures } = confined
     this.processFacts.set(proc, { mode, enforcement, denialSignatures, runnerFailureSignatures })
@@ -138,13 +132,13 @@ export class SandboxBashExecutor extends LocalBashExecutor {
    * `exec`s into the runner, so no extra shell lingers). Provider errors
    * (fail-closed `SANDBOX_UNAVAILABLE`) propagate to the caller unchanged.
    */
-  private confine(command: string, mode: ConfinedSandboxMode): {
+  private confine(command: string, policy: SandboxPolicy): {
     command: string
     enforcement: SandboxEnforcement
     denialSignatures: readonly string[]
     runnerFailureSignatures: readonly string[]
   } {
-    const confined = this.ctx.sandbox.confine(['bash', '-c', command], { mode, workspaceRoot: this.workspaceRoot })
+    const confined = this.ctx.sandbox.confine(['bash', '-c', command], policy)
     return {
       command: `exec ${confined.argv.map(shellQuote).join(' ')}`,
       enforcement: confined.enforcement,

packages/bash/bash-sandbox/tests/bwrap.e2e.ts

@@ -89,7 +89,7 @@ describe.skipIf(!bwrapUsable)('bash-sandbox: real bwrap confinement through ctx.
     expect(strict.exitCode).not.toBe(0)
     expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
     expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
-    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    const retried = await bash.run(bash.resolve({ command, sandboxPolicy: { mode: 'workspace-write', workspaceRoot: workdir } }))
     expect(retried.exitCode).toBe(0)
     expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
     expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')

packages/bash/bash-sandbox/tests/landlock.e2e.ts

@@ -94,7 +94,7 @@ describe.skipIf(!landlockUsable)('bash-sandbox: real Landlock confinement throug
     expect(strict.exitCode).not.toBe(0)
     expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: enforcement })
     expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
-    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    const retried = await bash.run(bash.resolve({ command, sandboxPolicy: { mode: 'workspace-write', workspaceRoot: workdir } }))
     expect(retried.exitCode).toBe(0)
     expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: enforcement })
     expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')

packages/bash/bash-sandbox/tests/sandbox.spec.ts

@@ -12,7 +12,7 @@ import { describe, expect, it, vi } from 'vitest'
 import { Context } from 'cordis'
 import type { BashRunResult, CollectedOutput } from '@deepseek-ai/dsh-bash'
 import { SANDBOX_UNAVAILABLE, SandboxProvider, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
-import type { ConfinedArgv, SandboxMode, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
+import type { ConfinedArgv, SandboxExecutionPolicy, SandboxMode, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
 import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
 import { classifyDenial, classifyRunnerFailure, shellQuote } from '../src/helpers.ts'
@@ -72,6 +72,10 @@ function runResult(exitCode: number | null, stderr: string): BashRunResult {
   return { exitCode, signal: null, timedOut: false, aborted: false, timeoutMs: 1000, stdout: output(''), stderr: output(stderr) }
 }
 
+function executionPolicy(mode: SandboxMode, workspaceRoot = resolve(process.cwd())): SandboxExecutionPolicy {
+  return { mode, workspaceRoot }
+}
+
 describe('the provider hand-off', () => {
   it('hands the provider the exact bash argv and the per-call policy, and runs the returned argv', async () => {
     const { bash, calls } = await setup()
@@ -147,30 +151,31 @@ describe('danger-full-access', () => {
   })
 })
 
-describe('per-call sandboxMode override (the escalation mechanism)', () => {
+describe('per-call sandbox policy (the session and escalation carrier)', () => {
   it('exposes the configured default as the capability fact, and resolve() stamps it', async () => {
     const { bash } = await setup()
     expect(bash.sandboxMode).toBe('read-only')
-    expect(bash.resolve({ command: 'true' }).sandboxMode).toBe('read-only')
+    expect(bash.resolve({ command: 'true' }).sandboxPolicy).toEqual(executionPolicy('read-only'))
   })
 
-  it('an explicit override outranks the default at resolve(), and the wrap policy follows it', async () => {
+  it('an explicit policy outranks the default at resolve(), and the wrap follows its mode and root', async () => {
     const { bash, calls } = await setup()
-    expect(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }).sandboxMode).toBe('workspace-write')
-    await bash.run(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }))
+    const explicit = executionPolicy('workspace-write', '/session/project')
+    expect(bash.resolve({ command: 'true', sandboxPolicy: explicit }).sandboxPolicy).toEqual(explicit)
+    await bash.run(bash.resolve({ command: 'true', sandboxPolicy: explicit }))
     await bash.run(bash.resolve({ command: 'true' }))
-    expect(calls.map(call => call.policy.mode)).toEqual(['workspace-write', 'read-only'])
+    expect(calls.map(call => call.policy)).toEqual([explicit, executionPolicy('read-only')])
   })
 
   it('an escalated run reports the mode it ACTUALLY ran under', async () => {
     const { bash } = await setup()
-    const result = await bash.run(bash.resolve({ command: 'true', sandboxMode: 'workspace-write' }))
+    const result = await bash.run(bash.resolve({ command: 'true', sandboxPolicy: executionPolicy('workspace-write') }))
     expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
   })
 
   it('escalating to danger-full-access bypasses the provider entirely — the grant, not a probe, is the authority there', async () => {
     const { bash, calls } = await setup()
-    const result = await bash.run(bash.resolve({ command: 'echo free', sandboxMode: 'danger-full-access' }))
+    const result = await bash.run(bash.resolve({ command: 'echo free', sandboxPolicy: executionPolicy('danger-full-access') }))
     expect(result.stdout.text).toBe('free\n')
     expect(result.sandbox).toEqual({ mode: 'danger-full-access', denied: false })
     expect(calls).toHaveLength(0)
@@ -181,7 +186,7 @@ describe('per-call sandboxMode override (the escalation mechanism)', () => {
     // once — anything keyed off the configured default would misreport the
     // escalated one at its settle stamp.
     const { bash } = await setup()
-    const escalated = bash.start(bash.resolve({ command: 'sleep 0.3; echo "x: Permission denied" >&2; exit 1', sandboxMode: 'workspace-write' }))
+    const escalated = bash.start(bash.resolve({ command: 'sleep 0.3; echo "x: Permission denied" >&2; exit 1', sandboxPolicy: executionPolicy('workspace-write') }))
     const plain = bash.start(bash.resolve({ command: 'true' }))
     await plain.done
     await escalated.done
@@ -191,7 +196,7 @@ describe('per-call sandboxMode override (the escalation mechanism)', () => {
 
   it('an escalated danger-full-access background task carries no facts (nothing confined it)', async () => {
     const { bash, calls } = await setup()
-    const task = bash.start(bash.resolve({ command: 'echo bg-free', sandboxMode: 'danger-full-access' }))
+    const task = bash.start(bash.resolve({ command: 'echo bg-free', sandboxPolicy: executionPolicy('danger-full-access') }))
     await task.done
     expect(task.sandbox).toBeUndefined()
     expect(task.readOutput().delta).toContain('bg-free')

packages/bash/bash-sandbox/tests/seatbelt.e2e.ts

@@ -91,7 +91,7 @@ describe.skipIf(!seatbeltUsable)('bash-sandbox: real Seatbelt confinement throug
     expect(strict.exitCode).not.toBe(0)
     expect(strict.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
     expect(existsSync(join(workdir, 'escalated.txt'))).toBe(false)
-    const retried = await bash.run(bash.resolve({ command, sandboxMode: 'workspace-write' }))
+    const retried = await bash.run(bash.resolve({ command, sandboxPolicy: { mode: 'workspace-write', workspaceRoot: workdir } }))
     expect(retried.exitCode).toBe(0)
     expect(retried.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
     expect(readFileSync(join(workdir, 'escalated.txt'), 'utf8')).toBe('escalated')

packages/bash/bash/README.md

@@ -27,7 +27,7 @@ Implementations subclass `BashExecutor` and implement the abstract methods. Disp
 
 ## Vocabulary
 
-`BashExecRequest` (command, workdir?, timeoutMs?, stdoutMaxBytes?, signal?, stdin?, env?, dshEnv?, sandboxMode?) resolves to `BashExecSpec` (command, workdir, timeoutMs, stdoutMaxBytes, signal?, stdin?, env?, dshEnv?, sandboxMode) before execution. `stdoutMaxBytes` is a trusted foreground-run capture budget for consumers that must parse complete bounded stdout; the model-facing bash tool does not expose it. `sandboxMode` is optional on the request and required-but-nullable on the resolved spec: it carries an approved one-shot escalation or the session's standing override; a sandboxing executor stamps its configured default when absent, while a non-sandboxing executor carries the field and confines nothing.
+`BashExecRequest` (command, workdir?, timeoutMs?, stdoutMaxBytes?, signal?, stdin?, env?, dshEnv?, sandboxPolicy?) resolves to `BashExecSpec` (command, workdir, timeoutMs, stdoutMaxBytes, signal?, stdin?, env?, dshEnv?, sandboxPolicy) before execution. `stdoutMaxBytes` is a trusted foreground-run capture budget for consumers that must parse complete bounded stdout; the model-facing bash tool does not expose it. `sandboxPolicy` is optional on the request and required-but-nullable on the resolved spec: it carries the complete per-call mode and workspace root. The sandbox tool path resolves it from the calling session through `ctx.sandboxPolicy`; a direct sandbox-executor caller falls back to deployment policy, while a non-sandboxing executor carries the field and confines nothing.
 
 The per-session sandbox-mode override vocabulary (the `'sandbox/mode'` event, the `effectiveSandboxMode(events)` fold, and the `setSandboxMode(session, mode)` write path) is NOT here — it is policy state shared by every enforcing family, owned by [`@deepseek-ai/dsh-sandbox-policy`](../../sandbox/sandbox-policy/). `run()` returns `BashRunResult`; `start()` returns `BashProcess`, whose incremental read and kill methods are adapted by `dsh-tool-bash` into a generic task registration. A sandboxing executor stamps `BashSandboxInfo` on foreground results and settled process handles. See `src/types.ts` and [core-data-structures/bash.md](../../../docs/core-data-structures/bash.md).
 

packages/bash/bash/src/types.ts

@@ -4,7 +4,7 @@
  * @module dsh-bash/types
  */
 
-import type { SandboxEnforcement, SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import type { SandboxEnforcement, SandboxExecutionPolicy, SandboxMode } from '@deepseek-ai/dsh-sandbox'
 
 /** Namespace prefix reserved for DeepSeek Harness-managed child environment facts. */
 export const DSH_ENV_PREFIX = 'DSH_' as const
@@ -75,8 +75,8 @@ export interface BashExecRequest {
    * reject non-`DSH_*` names supplied through this managed channel.
    */
   dshEnv?: DshEnvironment | undefined
-  /** Explicit per-call sandbox mode override. */
-  sandboxMode?: SandboxMode | undefined
+  /** Fully resolved per-call sandbox policy; sandboxing executors default it. */
+  sandboxPolicy?: SandboxExecutionPolicy | undefined
 }
 
 /**
@@ -106,8 +106,8 @@ export interface BashExecSpec {
   env?: Record<string, string> | undefined
   /** Managed `DSH_*` snapshot; implementations reject ordinary names. */
   dshEnv?: DshEnvironment | undefined
-  /** Resolved sandbox mode; ignored by executors that do not confine. */
-  sandboxMode: SandboxMode | undefined
+  /** Resolved sandbox policy; ignored by executors that do not confine. */
+  sandboxPolicy: SandboxExecutionPolicy | undefined
 }
 
 /** One captured stream: the (possibly truncated) text plus recovery info. */

packages/bash/bash/tests/service.spec.ts

@@ -17,7 +17,7 @@ class StubExecutor extends BashExecutor {
       timeoutMs: request.timeoutMs ?? 1000,
       stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000,
       ...request.signal ? { signal: request.signal } : {},
-      sandboxMode: request.sandboxMode,
+      sandboxPolicy: request.sandboxPolicy,
     }
   }
 
@@ -55,7 +55,7 @@ describe('BashExecutor service seam', () => {
     const ctx = new Context()
     await ctx.plugin(StubExecutor)
     const spec = ctx.bash.resolve({ command: 'echo hi' })
-    expect(spec).toEqual({ command: 'echo hi', workdir: '/stub', timeoutMs: 1000, stdoutMaxBytes: 64_000, sandboxMode: undefined })
+    expect(spec).toEqual({ command: 'echo hi', workdir: '/stub', timeoutMs: 1000, stdoutMaxBytes: 64_000, sandboxPolicy: undefined })
 
     const result = await ctx.bash.run(spec)
     expect(result.exitCode).toBe(0)

packages/bash/tool-bash/README.md

@@ -17,12 +17,12 @@ The plugin also contributes the `tool:bash` prompt section (order 105): check th
 | `command` | string (required) | Run via `bash -c`. No state persists between calls — use `workdir`, not `cd`. |
 | `description` | string (required) | One-line, active-voice summary of the command (5-10 words), for UI/log display only — no effect on execution. |
 | `timeoutMs` | number | Timeout override in milliseconds. The executor applies its configured default and cap. |
-| `workdir` | string | Working directory for this call. Defaults to the calling agent's session cwd (`session.header.cwd`) so each session runs in its own workspace; a relative `workdir` is resolved against that session cwd. |
+| `workdir` | string | Working directory for this call. Defaults to the filesystem identity of the calling agent's session cwd (`session.header.cwd`) so each session runs in its own workspace; a relative `workdir` is resolved against that same identity. |
 | `run_in_background` | boolean | Return a task id immediately; no timeout applies. |
 | `sandbox_permissions` | string enum | ADVERTISED ONLY when the mounted executor sandboxes (`ctx.bash.sandboxMode` reports a confining default): the wider mode a denied command needs, from the closed target vocabulary `workspace-write`/`danger-full-access` (never cut down to the executor's default — the effective mode is per-session; strict widening is checked at execution against it, and a non-widening request fails without prompting anyone). |
 | `justification` | string | Required together with `sandbox_permissions` (each without the other is a validation error): one sentence for the user explaining why this exact command needs the wider access. |
 
-`command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer (from the calling agent's `session.header.cwd`) BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`.
+`command`, `workdir`, and `timeoutMs` are resolved against the executor's config defaults via `ctx.bash.resolve()` before execution, so the executor seam (`BashExecSpec`) receives explicit `workdir`/`timeoutMs` values. The workdir default is applied in the tool layer from the calling agent's `session.header.cwd` BEFORE `resolve()` — the per-session cwd must come from `exec.agent`, since N sessions share one executor; only when no session cwd is available does the executor fall back to its own config / `process.cwd()`. When sandbox policy is present, the tool reuses its already-canonical `workspaceRoot` as the workdir base so confinement and process launch cannot resolve the same session spelling differently.
 
 ### Managed shell environment
 

packages/bash/tool-bash/src/index.ts

@@ -19,9 +19,9 @@ import type {} from '@deepseek-ai/dsh-session-persistence'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import type {} from '@deepseek-ai/dsh-tasks'
 import type {} from '@deepseek-ai/dsh-user-approval'
-import type { SandboxMode } from '@deepseek-ai/dsh-sandbox'
-import { ESCALATION_TARGETS, approveEscalation, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox'
-import { effectiveSandboxMode } from '@deepseek-ai/dsh-sandbox-policy'
+import type { SandboxExecutionPolicy, SandboxMode } from '@deepseek-ai/dsh-sandbox'
+import { ESCALATION_TARGETS, approveEscalation, canonicalPath, validateEscalationArgs } from '@deepseek-ai/dsh-sandbox'
+import type { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { DSH_ENV_PREFIX } from '@deepseek-ai/dsh-bash'
 import type { BashRunResult, DshEnvironment, DshEnvironmentKey } from '@deepseek-ai/dsh-bash'
 import { DSH_HOME_ENV, resolveDshHome } from '@deepseek-ai/dsh-paths'
@@ -300,11 +300,18 @@ function presentBashResult(args: unknown, result: ToolResult): ToolResultView |
 }
 
 /**
- * Resolve an explicit workdir first, making a relative one session-cwd-relative;
- * otherwise use the session cwd and leave executor defaulting as the fallback.
+ * Resolve an explicit workdir first, making a relative one session-workspace-relative;
+ * otherwise use the filesystem identity of the session cwd and leave executor
+ * defaulting as the fallback. A resolved sandbox-policy root wins so workdir
+ * and confinement use the exact same per-call identity.
  */
-function resolveWorkdir(modelWorkdir: string | undefined, exec: { agent?: Agent }): string | undefined {
-  const sessionCwd = exec.agent?.session.header.cwd
+function resolveWorkdir(
+  modelWorkdir: string | undefined,
+  exec: { agent?: Agent },
+  policyWorkspaceRoot?: string,
+): string | undefined {
+  const headerCwd = exec.agent?.session.header.cwd
+  const sessionCwd = policyWorkspaceRoot ?? (headerCwd === undefined ? undefined : canonicalPath(headerCwd))
   if (modelWorkdir === undefined) return sessionCwd
   if (sessionCwd !== undefined && !isAbsolute(modelWorkdir)) {
     return resolvePath(sessionCwd, modelWorkdir)
@@ -363,9 +370,14 @@ export function apply(ctx: Context, config: Config = {}): void {
   const backgroundEnabled = config.enableRunInBackground ?? true
   const defaultMode = ctx.bash.sandboxMode
   const escalationModes: readonly SandboxMode[] = defaultMode === undefined ? [] : ESCALATION_TARGETS
+  const sandboxPolicy: SandboxPolicyService | undefined = defaultMode === undefined ? undefined : ctx.get('sandboxPolicy')
+  if (defaultMode !== undefined && sandboxPolicy === undefined) {
+    throw new Error('tool-bash: the mounted bash executor confines but ctx.sandboxPolicy is missing')
+  }
 
-  const sessionOverride = (exec: ToolExecution): SandboxMode | undefined =>
-    defaultMode === undefined || exec.agent === undefined ? undefined : effectiveSandboxMode(exec.agent.session.events)
+  /** Resolve the complete standing policy for this call when a confining executor is mounted. */
+  const resolveSandboxPolicy = (exec: ToolExecution): SandboxExecutionPolicy | undefined =>
+    sandboxPolicy?.resolve(exec.agent === undefined ? {} : { session: exec.agent.session })
 
   /**
    * Resolve a sandbox-escalation request through `ctx.approval` BEFORE
@@ -375,14 +387,19 @@ export function apply(ctx: Context, config: Config = {}): void {
    * guard (the fields are unadvertised without a sandboxing executor, yet
    * schema validation checks advertised keys only, so an unadvertised
    * `sandbox_permissions` still reaches execute) and the approval ingredients
-   * — the seam is consumed opportunistically (`ctx.get`) so a deployment
-   * without it degrades per call.
+   * The shared policy resolver is required whenever the executor advertises
+   * confinement, so a split composition fails at tool-plugin load.
    */
-  const approveBashEscalation = (mode: string, justification: string, exec: ToolExecution): Promise<SandboxMode> => {
+  const approveBashEscalation = (
+    mode: string,
+    justification: string,
+    exec: ToolExecution,
+    standingPolicy: SandboxExecutionPolicy | undefined,
+  ): Promise<SandboxMode> => {
     if (escalationModes.length === 0) {
       throw new Error('sandbox_permissions is not available in this composition (no sandboxing executor to escalate)')
     }
-    const effectiveMode = (sessionOverride(exec) ?? defaultMode) as SandboxMode
+    const effectiveMode = (standingPolicy as SandboxExecutionPolicy).mode
     return approveEscalation(
       { requestedMode: mode, justification, effectiveMode, subject: 'command' },
       {
@@ -493,17 +510,21 @@ export function apply(ctx: Context, config: Config = {}): void {
     async execute(args: BashToolArgs, exec) {
       validateBashArgs(args)
       // Description is display metadata; workdir defaults to the caller's session.
-      const sandboxMode = args.sandbox_permissions !== undefined && args.justification !== undefined
-        ? await approveBashEscalation(args.sandbox_permissions, args.justification, exec)
-        : sessionOverride(exec)
-      const workdir = resolveWorkdir(args.workdir, exec)
+      const standingPolicy = resolveSandboxPolicy(exec)
+      const approvedMode = args.sandbox_permissions !== undefined && args.justification !== undefined
+        ? await approveBashEscalation(args.sandbox_permissions, args.justification, exec, standingPolicy)
+        : undefined
+      const policy = approvedMode === undefined
+        ? standingPolicy
+        : { ...(standingPolicy as SandboxExecutionPolicy), mode: approvedMode }
+      const workdir = resolveWorkdir(args.workdir, exec, standingPolicy?.workspaceRoot)
       const dshEnv = bashEnv.collect(exec)
       const request = {
         command: args.command,
         ...workdir !== undefined ? { workdir } : {},
         ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
         dshEnv,
-        ...sandboxMode !== undefined ? { sandboxMode } : {},
+        ...policy !== undefined ? { sandboxPolicy: policy } : {},
       }
       if (args.run_in_background === true) {
         // Undeclared keys are allowed, so schema omission also needs enforcement.

packages/bash/tool-bash/tests/tools.spec.ts

@@ -17,6 +17,7 @@ import * as ToolTasks from '@deepseek-ai/dsh-tool-tasks'
 import ApprovalService from '@deepseek-ai/dsh-user-approval'
 import type { ApprovalOutcome } from '@deepseek-ai/dsh-user-approval'
 import { LocalBashExecutor } from '@deepseek-ai/dsh-bash-local'
+import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
 import * as ToolBash from '@deepseek-ai/dsh-tool-bash'
 import { processOutcome } from '../src/background.ts'
 import { renderProcessRead, renderResult } from '../src/render.ts'
@@ -107,12 +108,12 @@ class RecordingSandboxExecutor extends BashExecutor {
       stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000,
       timeoutMs: request.timeoutMs ?? 1000,
       ...request.signal ? { signal: request.signal } : {},
-      sandboxMode: request.sandboxMode ?? 'read-only',
+      sandboxPolicy: request.sandboxPolicy ?? { mode: 'read-only', workspaceRoot: process.cwd() },
     }
   }
 
   run(spec: BashExecSpec): Promise<BashRunResult> {
-    this.modes.push(spec.sandboxMode)
+    this.modes.push(spec.sandboxPolicy?.mode)
     return Promise.resolve({
       exitCode: 0,
       signal: null,
@@ -122,7 +123,7 @@ class RecordingSandboxExecutor extends BashExecutor {
       stdout: { text: 'ok', truncated: false },
       stderr: { text: '', truncated: false },
       sandbox: {
-        mode: spec.sandboxMode ?? 'read-only',
+        mode: spec.sandboxPolicy?.mode ?? 'read-only',
         denied: false,
         ...spec.command === 'without optional sandbox facts'
           ? {}
@@ -132,13 +133,13 @@ class RecordingSandboxExecutor extends BashExecutor {
   }
 
   start(spec: BashExecSpec): BashProcess {
-    this.modes.push(spec.sandboxMode)
+    this.modes.push(spec.sandboxPolicy?.mode)
     return {
       status: 'completed',
       exitCode: 0,
       signal: null,
       done: Promise.resolve(),
-      sandbox: { mode: spec.sandboxMode ?? 'read-only', denied: false },
+      sandbox: { mode: spec.sandboxPolicy?.mode ?? 'read-only', denied: false },
       readOutput: () => ({ delta: '', lossy: false }),
       kill: () => false,
     }
@@ -155,7 +156,7 @@ class CountingStartExecutor extends BashExecutor {
       workdir: request.workdir ?? '/x',
       timeoutMs: request.timeoutMs ?? 0,
       stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000,
-      sandboxMode: request.sandboxMode,
+      sandboxPolicy: request.sandboxPolicy,
     }
   }
 
@@ -181,6 +182,7 @@ async function setupSandboxed(withApproval = false) {
   await ctx.plugin(AgentRegistry)
   await ctx.plugin(TaskService)
   await ctx.plugin(ToolTasks)
+  await ctx.plugin(SandboxPolicyService, {})
   await ctx.plugin(RecordingSandboxExecutor)
   if (withApproval) await ctx.plugin(ApprovalService)
   await ctx.plugin(ToolBash)
@@ -553,6 +555,14 @@ describe('sandbox escalation through the generic task producer', () => {
     justification: 'the command needs workspace writes',
   }
 
+  it('fails load when a confining executor has no shared sandbox-policy resolver', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(RecordingSandboxExecutor)
+    await expect(ctx.plugin(ToolBash)).rejects.toThrow('tool-bash: the mounted bash executor confines but ctx.sandboxPolicy is missing')
+  })
+
   it('advertises the sandbox fields and validates their pairing', async () => {
     const { ctx } = await setupSandboxed()
     const schema = ctx.tools.schemas().find(item => item.name === 'bash')!
@@ -1033,7 +1043,7 @@ describe('the model-facing bash tool builds its request from named args only (no
         ...request.stdin !== undefined ? { stdin: request.stdin } : {},
         ...request.env !== undefined ? { env: request.env } : {},
         ...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
-        sandboxMode: request.sandboxMode,
+        sandboxPolicy: request.sandboxPolicy,
       }
     }
     run(): Promise<BashRunResult> {