fix(sandbox): round 7 align spawn evidence

packages/bash/bash-sandbox/README.i18n.yaml

@@ -2,5 +2,5 @@
 # side as of the last confirmed-consistent state. Both languages carry equal authority;
 # after editing either side, bring the other along and re-record with:
 #   pnpm run verify-translation-pairing --write packages/bash/bash-sandbox/README.md
-README.md: 0fe8feaa0efda4111e997292a9741fffb6b55635
-README.zh.md: 43f6a209473839df7cbcfbefe4d11e29ff3de4b0
+README.md: 2f69ea66251f00c74779f1decc69abc6003a4398
+README.zh.md: fc4afb554442dfaf806292f30ddf9c495c427831

packages/bash/bash-sandbox/README.md

@@ -17,7 +17,7 @@ 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.** Before a process starts, a rejection is attributed to the runner only when the caller-owned workdir is independently usable and the error carries Node spawn provenance for provider argv[0] plus an executable-class code. This covers missing, non-executable, and unloadable runners, including a script whose shebang interpreter is unavailable; an invalid or unusable workdir, resource failure, unrelated syscall, or unstructured rejection retains the local executor's command-start failure semantics. Foreground execution and a synchronous background start throw `SANDBOX_UNAVAILABLE` with the original spawn detail, while asynchronous background settlement stamps `runnerFailed: true` and `denied: false`. After a process starts, a rule's optional exit-code gate and a remaining fatal stderr line must both match after exact informational-line exclusions. A match outranks denial; foreground execution throws `SANDBOX_UNAVAILABLE` with the matched fatal line, while a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`. Confined background handles retain their mode/enforcement facts and release per-process accounting in either path.
+- **Runner attribution is conservative.** Before a process starts, a rejection is attributed to the runner only when the caller-owned workdir is independently usable and Node reports `ENOENT` or `EACCES` with positive provenance for provider argv[0]. This covers a missing runner, a non-executable runner, or an executable script whose shebang interpreter is unavailable. A bare `syscall: 'spawn'` without an exact error path, any other code, an invalid or unusable workdir, a resource failure, an unrelated syscall, or an unstructured rejection retains the local executor's command-start failure semantics. Foreground execution throws `SANDBOX_UNAVAILABLE` with the original spawn detail, while asynchronous background settlement stamps `runnerFailed: true` and `denied: false`. If a `SubprocessService` synchronously throws the same provenanced `ENOENT`/`EACCES` shape, background start throws `SANDBOX_UNAVAILABLE`; other synchronous errors propagate unchanged. After a process starts, a rule's optional exit-code gate and a remaining fatal stderr line must both match after exact informational-line exclusions. A match outranks denial; foreground execution throws `SANDBOX_UNAVAILABLE` with the matched fatal line, while a settled background process stamps `process.sandbox.runnerFailed`, which the bash producer renders through generic `task_output`. Confined background handles retain their mode/enforcement facts and release per-process accounting in either path.
 - **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 static bash tool description separately owns denial and escalation guidance.
 - **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/).
@@ -72,7 +72,7 @@ Append-only; newly visible content follows the reusable request prefix and does
 
 #### What the model sees
 
-If no runner can enforce a confined mode, the foreground call propagates the [`SANDBOX_UNAVAILABLE` error owned by `dsh-sandbox`](../../sandbox/sandbox/README.md#confinement-error-indirectly). A runner-attributable spawn failure supplies the original spawn error as detail; a rejection without executable-class argv[0] evidence remains an ordinary command-start error. A settled runner failure supplies the matched fatal stderr line and preserves the original stderr collection.
+If no runner can enforce a confined mode, the foreground call propagates the [`SANDBOX_UNAVAILABLE` error owned by `dsh-sandbox`](../../sandbox/sandbox/README.md#confinement-error-indirectly). A runner-attributable spawn failure supplies the original spawn error as detail; a rejection without `ENOENT`/`EACCES` argv[0] evidence remains an ordinary command-start error. A settled runner failure supplies the matched fatal stderr line and preserves the original stderr collection. When present, the appended `Runner failure: <detail>` is the authoritative diagnosis; the preceding backend-install text is the generic `SANDBOX_UNAVAILABLE` prefix.
 
 #### Token effect
 
@@ -86,5 +86,5 @@ Append-only; newly visible content follows the reusable request prefix and does
 
 - **Confinement covers file effects only** — network access and process visibility are unchanged, so the modes are not a general-purpose security sandbox.
 - **Denials are inferred from failed-command stderr** — backend signatures make the inference portable, but a matching application error can be classified as a denial and a denial omitted from the retained tail can be missed.
-- **A background runner failure has no immediate error channel** — it is recorded on the settled process and surfaces when the caller reads the generic task with `task_output`.
+- **An asynchronously observed background runner failure has no immediate error channel** — it is recorded on the settled process and surfaces when the caller reads the generic task with `task_output`; a provenanced synchronous `SubprocessService` throw instead fails `start()` immediately.
 - **`danger-full-access` deliberately bypasses `ctx.sandbox`** — it is an explicit unconfined mode, not a wider sandbox profile.

packages/bash/bash-sandbox/README.zh.md

@@ -17,7 +17,7 @@
 语义：
 
 - **拒绝是结果事实。** 如果一次失败运行的 stderr 包含所选后端自身的拒绝方言，即提供方在每次包装时加上的特征（bwrap 下的 EROFS 文本、Landlock 下的 EACCES、Seatbelt 下的 EPERM），则结果报告 `BashRunResult.sandbox.denied: true`（从已收集的 stderr 尾部进行保守分类）。每次受限制运行还会携带执行时模式（`result.sandbox.mode`）与提供方强制执行完整性（`result.sandbox.enforcement`：`full`，或在较旧 Landlock ABI 上为 `partial`）。
-- **Runner 失败是沙箱失败，绝不是命令失败。** 进程启动前，只有当调用方拥有的 workdir 经独立验证可用，并且错误带有 Node 为提供方 argv[0] 报告的 spawn 来源信息和可执行文件类错误码时，才会将拒绝归因于 runner。这样可以识别缺失、不可执行或无法加载的 runner，包括 shebang 解释器不可用的脚本；无效或不可用的 workdir、资源失败、无关 syscall 或无结构拒绝仍保留本地执行器的命令启动失败语义。前台执行与同步的后台启动会抛出 `SANDBOX_UNAVAILABLE` 并附带原始 spawn 错误详情，异步后台结算则会标记 `runnerFailed: true` 和 `denied: false`。进程启动后，先按整行精确匹配排除信息性行，随后规则的可选退出码门控和余下 stderr 中的一行致命诊断必须同时匹配。匹配结果优先于拒绝；前台执行会抛出 `SANDBOX_UNAVAILABLE` 并附带匹配到的致命行，已结算的后台进程则会标记 `process.sandbox.runnerFailed`，Bash 结果生成方通过通用 `task_output` 渲染它。无论走哪条路径，受限制的后台句柄都会保留自身的模式／强制执行事实，并释放每进程计数。
+- **Runner 归因是保守的。** 进程启动前，只有当调用方拥有的 workdir 经独立验证可用，并且 Node 报告 `ENOENT` 或 `EACCES`，且带有明确指向提供方 argv[0] 的来源信息时，才会将拒绝归因于 runner。这样可以识别缺失的 runner、不可执行的 runner，或 shebang 解释器不可用的可执行脚本。没有精确错误路径的裸 `syscall: 'spawn'`、任何其他错误码、无效或不可用的 workdir、资源失败、无关 syscall 或无结构拒绝仍保留本地执行器的命令启动失败语义。前台执行会抛出 `SANDBOX_UNAVAILABLE` 并附带原始 spawn 错误详情，异步后台结算则会标记 `runnerFailed: true` 和 `denied: false`。如果 `SubprocessService` 同步抛出同样带有来源信息的 `ENOENT`／`EACCES` 形态，后台启动会抛出 `SANDBOX_UNAVAILABLE`；其他同步错误原样传播。进程启动后，先按整行精确匹配排除信息性行，随后规则的可选退出码门控和余下 stderr 中的一行致命诊断必须同时匹配。匹配结果优先于拒绝；前台执行会抛出 `SANDBOX_UNAVAILABLE` 并附带匹配到的致命行，已结算的后台进程则会标记 `process.sandbox.runnerFailed`，Bash 结果生成方通过通用 `task_output` 渲染它。无论走哪条路径，受限制的后台句柄都会保留自身的模式／强制执行事实，并释放每进程计数。
 - **部署回退，每次调用策略。** [`ctx.sandboxPolicy`](../../sandbox/sandbox-policy/) 为每次工具调用解析完整的 `SandboxExecutionPolicy`：调用会话提供自身的模式覆盖与不可变 cwd 根目录，部署配置则为无 agent（智能体）调用提供回退。已批准的升权只更改该策略的模式，会话根目录仍然附着其上。`resolve()` 把策略带入 spec，因此来自不同项目的重叠命令会在各自的根目录与模式下运行、分类和报告。能力事实 `ctx.bash.sandboxMode` 报告已配置的默认值，因此工具层只在装载该执行器时才公布升权；静态 bash 工具描述则单独负责拒绝与升级引导。
 - **只限制文件影响。** 设计上不限制网络与进程可见性：模式词汇不会声称覆盖后端未强制执行的范围。
 - 进程机制（spawn、进程组终止、输出收集／spill、后台句柄、凭证清理）继承自 [`dsh-bash-local`](../bash-local/)；runner 选择位于 [`dsh-sandbox-local`](../../sandbox/sandbox-local/)。
@@ -72,7 +72,7 @@
 
 #### 模型看到的内容
 
-如果没有 runner 能强制执行受限模式，前台调用会传播 [`SANDBOX_UNAVAILABLE` 错误](../../sandbox/sandbox/README.md#confinement-error-indirectly)；该错误由 `dsh-sandbox` 定义。可归因于 runner 的 spawn 失败会以原始 spawn 错误作为详细信息；没有 argv[0] 可执行文件类证据的拒绝仍是普通的命令启动错误。已结算的 runner 失败则以匹配到的致命 stderr 行作为详细信息，并保留原始 stderr 收集结果。
+如果没有 runner 能强制执行受限模式，前台调用会传播 [`SANDBOX_UNAVAILABLE` 错误](../../sandbox/sandbox/README.md#confinement-error-indirectly)；该错误由 `dsh-sandbox` 定义。可归因于 runner 的 spawn 失败会以原始 spawn 错误作为详细信息；没有 `ENOENT`／`EACCES` argv[0] 证据的拒绝仍是普通的命令启动错误。已结算的 runner 失败则以匹配到的致命 stderr 行作为详细信息，并保留原始 stderr 收集结果。如果追加了 `Runner failure: <detail>`，它就是权威诊断；前面的后端安装文本只是通用的 `SANDBOX_UNAVAILABLE` 前缀。
 
 #### Token 影响
 
@@ -86,5 +86,5 @@
 
 - **限制只覆盖文件影响**：网络访问与进程可见性不变，因此这些模式不是通用安全沙箱。
 - **拒绝从失败命令的 stderr 推断**：后端特征使该推断可跨平台使用，但包含相同后端特征的应用错误可能被分类为拒绝，也可能遗漏未出现在保留尾部中的拒绝。
-- **后台 runner 失败没有即时错误通道**：它记录在已结算进程上，并在调用方使用 `task_output` 读取通用任务时呈现。
+- **异步观测到的后台 runner 失败没有即时错误通道**：它记录在已结算进程上，并在调用方使用 `task_output` 读取通用任务时呈现；同步 `SubprocessService` 抛出带有来源信息的 `ENOENT`／`EACCES` 时，则会使 `start()` 立即失败。
 - **`danger-full-access` 有意绕过 `ctx.sandbox`**：它是显式无约束模式，不是更宽的沙箱 profile。

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

@@ -8,8 +8,8 @@ import { accessSync, constants, statSync } from 'node:fs'
 import type { BashRunResult } from '@deepseek-ai/dsh-bash'
 import type { RunnerFailureRule } from '@deepseek-ai/dsh-sandbox'
 
-/** Spawn codes that can describe an unavailable executable. */
-const EXECUTABLE_SPAWN_CODES = new Set(['EACCES', 'ENOENT', 'ENOEXEC', 'ENOTDIR', 'EPERM'])
+/** Node-local spawn codes proven to identify executable resolution or permission failure. */
+const EXECUTABLE_SPAWN_CODES = new Set(['EACCES', 'ENOENT'])
 
 /** Whether the caller-owned spawn cwd can be entered. */
 function isUsableWorkdir(path: string): boolean {
@@ -23,11 +23,14 @@ function isUsableWorkdir(path: string): boolean {
 }
 
 /**
- * Attribute only executable-class failures with positive Node argv[0]
- * provenance after independently ruling out the caller-owned cwd. A supplied
- * error path must exactly identify the runner; without one, the syscall must.
- * With a usable cwd, these codes describe resolution, permissions, or loading
- * of that argv[0], including a script whose shebang interpreter is unavailable.
+ * Attribute only Node ENOENT/EACCES failures with positive argv[0] provenance
+ * after independently ruling out the caller-owned cwd. A supplied error path
+ * must exactly identify the runner; without one, the syscall must. With a
+ * usable cwd, these codes describe resolution or execute permission for that
+ * argv[0] or its shebang interpreter.
+ * The workdir is checked at classification time, not atomically with spawn;
+ * concurrent path replacement may change attribution but cannot permit an
+ * unconfined execution.
  * @param error - the original spawn rejection.
  * @param runnerProgram - provider argv[0], the executable that establishes confinement.
  * @param workdir - the caller-owned spawn cwd, checked independently for usability.

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

@@ -10,7 +10,7 @@ import { join } from 'node:path'
 import { afterEach, describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
 import { LAUNCHER_FAILURE_EXIT } from 'node-addon-landlock-run'
-import { SANDBOX_UNAVAILABLE } from '@deepseek-ai/dsh-sandbox'
+import { SANDBOX_UNAVAILABLE, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
 import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
 import { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import { SandboxBashExecutor } from '@deepseek-ai/dsh-bash-sandbox'
@@ -108,6 +108,55 @@ describe('partial Landlock runner-failure classification', () => {
     expect(accounting.size).toBe(0)
   })
 
+  it('classifies a bare-name runner whose shebang interpreter is missing', async () => {
+    const dir = await mkdtemp(join(tmpdir(), 'dsh-bare-sandbox-runner-'))
+    tempDirs.push(dir)
+    const runner = 'bare-missing-interpreter-runner'
+    await writeFile(join(dir, runner), '#!/dsh-definitely-missing-sandbox-interpreter\nexit 0\n', { mode: 0o755 })
+    const bash = await setupConfiguredRunner(runner)
+    const request = { command: 'true', env: { PATH: dir } }
+
+    const error = await bash.run(bash.resolve(request)).catch((value: unknown) => value)
+    expect(error).toMatchObject({ name: 'SandboxUnavailableError', code: SANDBOX_UNAVAILABLE })
+    expect(error).toBeInstanceOf(Error)
+    expect((error as Error).message).toContain(`spawn ${runner} ENOENT`)
+
+    const task = bash.start(bash.resolve(request))
+    await task.done
+    expect(task.readOutput().delta).toContain(`spawn failed: Error: spawn ${runner} ENOENT`)
+    expect(task.sandbox).toEqual({
+      mode: 'read-only',
+      denied: false,
+      enforcement: 'full',
+      runnerFailed: true,
+    })
+  })
+
+  it('keeps a real malformed executable ENOEXEC as an ordinary spawn failure', async () => {
+    const dir = await mkdtemp(join(tmpdir(), 'dsh-malformed-sandbox-runner-'))
+    tempDirs.push(dir)
+    const runner = join(dir, 'malformed-runner')
+    await writeFile(runner, 'not a native executable or shebang script\n', { mode: 0o755 })
+    const bash = await setupConfiguredRunner(runner)
+
+    const foreground = await bash.run(bash.resolve({ command: 'true' })).catch((value: unknown) => value)
+    expect(foreground).toMatchObject({ code: 'ENOEXEC', syscall: 'spawn' })
+    expect((foreground as { path?: unknown }).path).toBeUndefined()
+    expect(foreground).not.toBeInstanceOf(SandboxUnavailableError)
+
+    let background: unknown
+    try {
+      bash.start(bash.resolve({ command: 'true' }))
+    } catch (error) {
+      background = error
+    }
+    expect(background).toMatchObject({ code: 'ENOEXEC', syscall: 'spawn' })
+    expect((background as { path?: unknown }).path).toBeUndefined()
+    expect(background).not.toBeInstanceOf(SandboxUnavailableError)
+    const accounting = (bash as unknown as { processFacts: Map<unknown, unknown> }).processFacts
+    expect(accounting.size).toBe(0)
+  })
+
   it.each([0, 1, 2, LAUNCHER_FAILURE_EXIT])(
     'keeps child exit %i ordinary when the partial-enforcement notice is the only runner line',
     async (exitCode) => {

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

@@ -214,7 +214,7 @@ describe('fail closed', () => {
     }
   })
 
-  it('classifies synchronous ENOEXEC as runner loading failure in run() and start()', async () => {
+  it('keeps Node-shaped synchronous ENOEXEC ordinary in run() and start()', async () => {
     const runner = join(spillDir, 'malformed-runner')
     const { ctx, bash } = await setup({}, argv => ({
       argv: [runner, ...argv],
@@ -223,7 +223,33 @@ describe('fail closed', () => {
       runnerFailureRules: RUNNER_FAILURE,
     }))
     vi.spyOn(ctx.subprocess, 'spawn').mockImplementation(() => {
-      throw Object.assign(new Error('spawn ENOEXEC'), { code: 'ENOEXEC', syscall: 'spawn', path: runner })
+      throw Object.assign(new Error('spawn ENOEXEC'), { code: 'ENOEXEC', syscall: 'spawn' })
+    })
+
+    const foreground = await bash.run(bash.resolve({ command: 'true' })).catch((error: unknown) => error)
+    expect(foreground).toMatchObject({ code: 'ENOEXEC', syscall: 'spawn' })
+    expect(foreground).not.toBeInstanceOf(SandboxUnavailableError)
+
+    let background: unknown
+    try {
+      bash.start(bash.resolve({ command: 'true' }))
+    } catch (error) {
+      background = error
+    }
+    expect(background).toMatchObject({ code: 'ENOEXEC', syscall: 'spawn' })
+    expect(background).not.toBeInstanceOf(SandboxUnavailableError)
+  })
+
+  it('classifies a synchronous SubprocessService EACCES with exact runner provenance', async () => {
+    const runner = join(spillDir, 'unexecutable-runner')
+    const { ctx, bash } = await setup({}, argv => ({
+      argv: [runner, ...argv],
+      enforcement: 'full',
+      denialSignatures: UNIX_SIGNATURES,
+      runnerFailureRules: RUNNER_FAILURE,
+    }))
+    vi.spyOn(ctx.subprocess, 'spawn').mockImplementation(() => {
+      throw Object.assign(new Error('spawn EACCES'), { code: 'EACCES', syscall: 'spawn', path: runner })
     })
 
     await expect(bash.run(bash.resolve({ command: 'true' })))
@@ -359,7 +385,7 @@ describe('classifyDenial', () => {
 })
 
 describe('isRunnerSpawnFailure', () => {
-  it.each(['EACCES', 'ENOENT', 'ENOEXEC', 'ENOTDIR', 'EPERM'])(
+  it.each(['EACCES', 'ENOENT'])(
     'attributes executable-class spawn code %s to argv[0] once cwd ambiguity is eliminated',
     (code) => {
       const runner = join(spillDir, 'runner')
@@ -368,6 +394,15 @@ describe('isRunnerSpawnFailure', () => {
     },
   )
 
+  it.each(['ENOEXEC', 'ENOTDIR', 'EPERM'])(
+    'keeps unproven executable code %s ordinary despite synthetic argv[0] fields',
+    (code) => {
+      const runner = join(spillDir, 'runner')
+      const error = Object.assign(new Error('spawn failed'), { code, syscall: `spawn ${runner}`, path: runner })
+      expect(isRunnerSpawnFailure(error, runner, process.cwd())).toBe(false)
+    },
+  )
+
   it('requires a usable caller cwd before classifying absolute, bare, or relative runners', () => {
     const missingWorkdir = join(spillDir, 'missing-workdir')
     for (const [, runner] of RUNNER_FORMS) {
@@ -405,7 +440,7 @@ describe('isRunnerSpawnFailure', () => {
   it('accepts only syscall provenance compatible with the exact runner program', () => {
     const runner = join(spillDir, 'runner with spaces')
     const spawnError = (syscall: string, path?: string) =>
-      Object.assign(new Error('spawn failed'), { code: 'ENOEXEC', syscall, path })
+      Object.assign(new Error('spawn failed'), { code: 'ENOENT', syscall, path })
 
     expect(isRunnerSpawnFailure(spawnError('spawn', runner), runner, process.cwd())).toBe(true)
     expect(isRunnerSpawnFailure(spawnError(`spawn ${runner}`, runner), runner, process.cwd())).toBe(true)