Coder/deepseek-harness
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge remote-tracking branch 'origin/master' into feat/loader-entry-disabled-interpolation

Browse Source 
# Conflicts:
#	.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.i18n.yaml
#	.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.md
#	.agents/notes/implemented/feature/2026-08-01-windows-pwsh-default.zh.md
This commit is contained in:
Huanqi Cao
2026-08-11 15:33:09 +08:00
parent 1b2a5c55dd c172faed37
commit 2a6658252c
325 changed files with 7030 additions and 1683 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
packages/acp/acp/src/index.ts
View File

@@ -252,6 +252,10 @@ export function apply(ctx: Context, config: AcpConfig): void {
assertOpen()
validateSessionParams(params)
const sessionId = SessionId(randomUUID())
// No preset composition: the ACP bundle keeps the model-facing rows in
// the host plane, so this agent reads them from the global layer. A
// deployment that configures a roster has to join one here first
// (@deepseek-ai/dsh-agent-presets README, "Composing a child agent").
const handle = await agents.create({
sessionId,
meta: { cwd: params.cwd },

4
packages/bash/pwsh-sandbox/README.i18n.yaml
View File

@@ -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/pwsh-sandbox/README.md
README.md: bd506d011fa6167ddf7d6fe0565e475979ad0ec2
README.zh.md: e9aa380302037be3c9dd07331035544299bf3bec
README.md: c47409c122ffce264f53fc41c786da015fdaab6b
README.zh.md: 5b14185a71943d0a0a50f0bae353a3e22d0f1fb2

4
packages/bash/pwsh-sandbox/README.md
View File

@@ -30,5 +30,5 @@ None directly; the denial surface belongs to the tool layer.
## Known Limitations and Deferred Work
- **Reads are unrestricted** on Windows (the ACL runner restricts writes only); the read boundary is documented in `@deepseek-ai/dsh-sandbox-windows-acl`.
- **The Windows workspace-write temp area is the real temp directory** (`GetTempPathW`). This is a deliberate backend-defined choice, the same decision Landlock makes (`readWrite: ['/tmp', ...]`): the seam's "backend-defined temp area" permits it, and the escape probe in `tests/acl.e2e.ts` lives outside the temp tree for exactly that reason. A per-run private temp (bwrap's `--tmpfs /tmp` semantics) would additionally need an environment-block rewrite in the runner; it is an optional future hardening, not a correctness gap.
- **Windows read-only is strict zero-grant** — not even the NUL device is writable; `> $null` redirection still works (documented in the backend package).
- **Windows workspace-write temp authority is private** per live session/workspace pair; agentless calls receive a fresh private directory per invocation. The ambient temp root is never granted, and the runner rewrites TMP/TEMP to the private directory before spawning.
- **Windows read-only grants no explicit writable root but remains partial** because the restricted token must retain Everyone. Objects whose DACL grants Everyone write access — including compatible opens of the NUL device — remain ambient authority; PowerShell's `> $null` redirection still works without opening NUL.

4
packages/bash/pwsh-sandbox/README.zh.md
View File

@@ -30,5 +30,5 @@
## 已知限制与后续工作
- **Windows 上读不受限**（ACL runner 只限写）；读边界文档在 `@deepseek-ai/dsh-sandbox-windows-acl`。
- **Windows workspace-write 的临时区域是真实临时目录**（`GetTempPathW`）。这是有意为之的后端自定义选择，与 Landlock 的决策（`readWrite: ['/tmp', ...]`）同类：seam 的 "backend-defined temp area" 词汇表允许它，`tests/acl.e2e.ts` 的逃逸探针也正是因此位于 temp 树之外。按运行创建私有临时目录（bwrap `--tmpfs /tmp` 的语义）还需 runner 改写环境块——这是可选的进一步加固，而非正确性缺口。
- **Windows read-only 是严格零授权**——连 NUL 设备都不可写；`> $null` 重定向不受影响（后端包有文档）。
- **Windows workspace-write 的临时权限按每个活跃的会话/工作区对私有**；无 agent（智能体）的调用每次都获得一个新的私有目录。环境临时根目录绝不会被授权，runner 会在 spawn 前将 TMP/TEMP 重写为该私有目录。
- **Windows read-only 不授予任何显式可写根目录，但仍为部分强制执行**，因为受限令牌必须保留 Everyone。DACL 向 Everyone 授予写访问的对象——包括以兼容方式打开的 NUL 设备——仍构成环境权限来源；PowerShell 的 `> $null` 重定向仍可工作，且不会打开 NUL。

44
packages/bash/pwsh-sandbox/tests/acl.e2e.ts
View File

@@ -2,9 +2,9 @@
* Real-backend end-to-end: LocalSandboxProvider (win32 chain → the
* windows-acl runner), SandboxPolicyService, and SandboxPwshExecutor with
* REAL pwsh spawns confined through the runner — the debug-instance
* verification of both modes: read-only denies every write (not even NUL),
* workspace-write allows the workspace and temp while denying escape writes,
* and denial/classification facts ride the settled result.
* verification of both modes on ordinary user-owned paths: read-only denies
* writes, workspace-write allows its promised roots while denying escape
* writes, and the partial-enforcement/denial facts ride the settled result.
*/
import { spawnSync } from 'node:child_process'
@@ -29,21 +29,19 @@ function pwshAvailable(): boolean {
describe.skipIf(!isWin32 || !pwshAvailable())('pwsh-sandbox real ACL confinement', () => {
let scratchRoot!: string
let writableDir!: string
let isolatedTemp!: string
let outsideTempDir!: string
let secretFile!: string
let escapeFile!: string
let executor!: SandboxPwshExecutor
beforeAll(async () => {
// The escape probe must live OUTSIDE every legitimately granted tree: the
// provider's workspace-write grants the workspace plus the REAL temp dir
// (the 'backend-defined temp area', same as Landlock granting /tmp), so a
// scratch dir under temp would inherit the grant and the probe would be a
// false pass. A mkdtemp under the profile is removed by afterAll.
// The workspace escape sits under the profile. A separate directory under
// the ambient temp root proves that the root itself is not granted: the
// runner creates its own private child and rewrites TMP/TEMP to it.
scratchRoot = mkdtempSync(join(homedir(), 'dsh-pwsh-sandbox-e2e-'))
writableDir = join(scratchRoot, 'writable')
mkdirSync(writableDir)
isolatedTemp = mkdtempSync(join(tmpdir(), 'dsh-pwsh-sandbox-e2e-temp-'))
outsideTempDir = mkdtempSync(join(tmpdir(), 'dsh-pwsh-sandbox-e2e-outside-temp-'))
secretFile = join(scratchRoot, 'secret.txt')
writeFileSync(secretFile, 'top secret - must stay readable to prove the read boundary')
escapeFile = join(scratchRoot, 'escaped.txt')
@@ -58,15 +56,15 @@ describe.skipIf(!isWin32 || !pwshAvailable())('pwsh-sandbox real ACL confinement
afterAll(() => {
rmSync(scratchRoot, { recursive: true, force: true })
rmSync(isolatedTemp, { recursive: true, force: true })
rmSync(outsideTempDir, { recursive: true, force: true })
})
it('read-only: every write denied (workspace, temp, NUL), reads fine, denial facts ride the result', async () => {
it('read-only: ordinary path writes denied, reads fine, partial and denial facts ride the result', async () => {
const policy: SandboxExecutionPolicy = { mode: 'read-only', workspaceRoot: writableDir }
const probe = [
"$ErrorActionPreference='SilentlyContinue';",
`try{Set-Content -Path '${writableDir}\\ro-write.txt' -Value ok -ErrorAction Stop;'TARGET-WRITE: OK'}catch{'TARGET-WRITE: DENIED'};`,
`try{Set-Content -Path '${isolatedTemp}\\ro-write.txt' -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};`,
`try{Set-Content -Path '${outsideTempDir}\\ro-write.txt' -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};`,
`try{Set-Content -Path '${escapeFile}' -Value ok -ErrorAction Stop;'ESCAPE-WRITE: OK'}catch{'ESCAPE-WRITE: DENIED'};`,
`try{Get-Content '${secretFile}' -ErrorAction Stop | Out-Null;'SECRET-READ: OK'}catch{'SECRET-READ: DENIED'}`,
].join('')
@@ -78,7 +76,7 @@ describe.skipIf(!isWin32 || !pwshAvailable())('pwsh-sandbox real ACL confinement
expect(result.stdout.text).toContain('SECRET-READ: OK')
expect(existsSync(join(writableDir, 'ro-write.txt'))).toBe(false)
// A self-caught denial keeps the command exit 0: no denial fact.
expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'full' })
expect(result.sandbox).toEqual({ mode: 'read-only', denied: false, enforcement: 'partial' })
// A raw failing write must classify as a denial of the ACL dialect.
const denied = await executor.run(executor.resolve({
@@ -86,26 +84,34 @@ describe.skipIf(!isWin32 || !pwshAvailable())('pwsh-sandbox real ACL confinement
sandboxPolicy: policy,
}))
expect(denied.exitCode).not.toBe(0)
expect(denied.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'full' })
expect(denied.sandbox).toEqual({ mode: 'read-only', denied: true, enforcement: 'partial' })
}, 60_000)
it('workspace-write: workspace and temp writable, escape denied, reads fine', async () => {
it('workspace-write: workspace and private temp writable, ambient temp and escape denied', async () => {
const policy: SandboxExecutionPolicy = { mode: 'workspace-write', workspaceRoot: writableDir }
const probe = [
"$ErrorActionPreference='SilentlyContinue';",
`try{Set-Content -Path '${writableDir}\\ww-write.txt' -Value ok -ErrorAction Stop;'TARGET-WRITE: OK'}catch{'TARGET-WRITE: DENIED'};`,
`try{Set-Content -Path '${isolatedTemp}\\ww-write.txt' -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};`,
"try{Set-Content -Path (Join-Path $env:TEMP 'ww-write.txt') -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};",
`try{Set-Content -Path '${outsideTempDir}\\ww-write.txt' -Value ok -ErrorAction Stop;'AMBIENT-TEMP-WRITE: OK'}catch{'AMBIENT-TEMP-WRITE: DENIED'};`,
`try{Set-Content -Path '${escapeFile}' -Value ok -ErrorAction Stop;'ESCAPE-WRITE: OK'}catch{'ESCAPE-WRITE: DENIED'};`,
`try{Get-Content '${secretFile}' -ErrorAction Stop | Out-Null;'SECRET-READ: OK'}catch{'SECRET-READ: DENIED'}`,
`try{Get-Content '${secretFile}' -ErrorAction Stop | Out-Null;'SECRET-READ: OK'}catch{'SECRET-READ: DENIED'};`,
"'TEMP-PATH: ' + $env:TEMP",
].join('')
const result = await executor.run(executor.resolve({ command: probe, sandboxPolicy: policy }))
expect(result.exitCode, `stderr: ${result.stderr.text}`).toBe(0)
expect(result.stdout.text).toContain('TARGET-WRITE: OK')
expect(result.stdout.text).toContain('TEMP-WRITE: OK')
expect(result.stdout.text).toContain('AMBIENT-TEMP-WRITE: DENIED')
expect(result.stdout.text).toContain('ESCAPE-WRITE: DENIED')
expect(result.stdout.text).toContain('SECRET-READ: OK')
expect(existsSync(join(writableDir, 'ww-write.txt'))).toBe(true)
expect(existsSync(join(outsideTempDir, 'ww-write.txt'))).toBe(false)
expect(existsSync(escapeFile)).toBe(false)
expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'full' })
const privateTemp = result.stdout.text.match(/^TEMP-PATH: (.+)$/mu)?.[1]?.trim()
expect(privateTemp).toBeDefined()
expect(privateTemp?.startsWith(tmpdir())).toBe(true)
expect(existsSync(privateTemp ?? '')).toBe(false)
expect(result.sandbox).toEqual({ mode: 'workspace-write', denied: false, enforcement: 'partial' })
}, 60_000)
})

4
packages/bash/tool-pwsh/README.i18n.yaml
View File

@@ -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/tool-pwsh/README.md
README.md: 3fd5a53946e2b101d6ef4457e312e52f4db5f3a8
README.zh.md: c06b4354b6973a6ff196cda7c49966c7c40e0a90
README.md: 4126e718c569f17fb8be465351b2576970e93c63
README.zh.md: aba669733a7ecb9924287abb298bb9a154b5afa7

2
packages/bash/tool-pwsh/README.md
View File

@@ -120,7 +120,7 @@ Append-only; newly visible content follows the reusable request prefix and does
## Known Limitations and Deferred Work
- **ConstrainedLanguage and named-pipe capture under the Windows sandbox** — when the [Windows ACL sandbox](../../sandbox/sandbox-windows-acl/README.md) confines a call (read-only or workspace-write), the restricted token puts pwsh into ConstrainedLanguage mode: `Add-Type`, non-core .NET statics (`[System.IO.*]::`, `[math]::`), COM objects, and reflection fail with "only core types" errors, and the mode cannot be lifted from inside. The same modes deny named-pipe opens, so a piped-stdio spawn inside a confined command fails with EPERM. The tool description teaches both contracts to the model; the backend README owns the full limitations.
- **Language mode and named-pipe capture under the Windows sandbox** — under the [Windows ACL sandbox](../../sandbox/sandbox-windows-acl/README.md), read-only pwsh starts in ConstrainedLanguage because its temp write denial makes PowerShell's AppLocker probe fail closed: `Add-Type`, non-core .NET statics (`[System.IO.*]::`, `[math]::`), COM objects, and reflection fail with "only core types" errors, and the mode cannot be lifted from inside. Workspace-write's private temp lets the probe complete, so it stays in FullLanguage unless host policy says otherwise. Both confined modes deny named-pipe opens, so a piped-stdio spawn inside a confined command fails with EPERM. The tool description teaches both contracts to the model; the backend README owns the full limitations.
- **No persistent shell or PTY** — every call starts a fresh `pwsh -Command`; the PTY backends are Linux/macOS-only today, and a Windows ConPTY persistent shell is roadmap work.
- **PowerShell-dialect contract** — the model must write PowerShell (native paths, `$env:` variables), not bash; there is no dialect translation.
- **Session-cwd identity is not canonicalized** — the workdir base is the session header cwd as-is, unlike the bash tool's sandbox-root-canonicalized identity. Under a confining executor the policy's workspace root IS canonicalized (by the shared policy service), so the workdir and the confinement root can diverge when the raw session cwd differs from its canonical form — a parity gap deferred to the shared shell-tool base extraction.

2
packages/bash/tool-pwsh/README.zh.md
View File

@@ -120,7 +120,7 @@ ack 是固定短行；任务输出按读取有界。
## Known Limitations and Deferred Work
- **Windows sandbox 下的 ConstrainedLanguage 与 named-pipe 捕获** — 当 [Windows ACL sandbox](../../sandbox/sandbox-windows-acl/README.md) 隔离某次调用（read-only 或 workspace-write）时，受限令牌使 pwsh 进入 ConstrainedLanguage 模式：`Add-Type`、非核心 .NET 静态调用（`[System.IO.*]::`、`[math]::`）、COM 对象与反射都会以“only core types”错误失败，且该模式无法从内部解除。这两种模式同样会拒绝 named-pipe 打开，因此受限命令内的管道 stdio spawn 以 EPERM 失败。工具描述把这两个约定教给模型；后端 README 负责完整的限制说明。
- **Windows 沙箱下的语言模式与 named-pipe 捕获** — 在 [Windows ACL 沙箱](../../sandbox/sandbox-windows-acl/README.md) 下，read-only pwsh 会以 ConstrainedLanguage 启动，因为临时目录写入被拒绝，导致 PowerShell 的 AppLocker 探针失败并按 fail-closed 处理：`Add-Type`、非核心 .NET 静态调用（`[System.IO.*]::`、`[math]::`）、COM 对象与反射都会以“only core types”错误失败，且该模式无法从内部解除。workspace-write 的私有临时目录使探针得以完成，因此除非主机策略另有规定，否则它保持 FullLanguage。两种受限模式都拒绝 named-pipe 打开，因此受限命令内的管道 stdio spawn 以 EPERM 失败。工具描述把这两个约定教给模型；后端 README 负责完整的限制说明。
- **无持久 shell 或 PTY** — 每次调用都启动全新的 `pwsh -Command`；PTY 后端目前仅限 Linux/macOS，Windows ConPTY 持久 shell 属于路线图工作。
- **PowerShell 方言约定** — 模型必须写 PowerShell（原生路径、`$env:` 变量），而不是 bash；没有方言翻译。
- **会话 cwd 身份不做规范化** — workdir 基座直接取会话头 cwd 原值，不同于 bash 工具经 sandbox-root 规范化的身份。在隔离执行器下，策略的工作区根**会**被规范化（由共享的策略服务完成），因此当原始会话 cwd 与其规范化形态不同时，workdir 与隔离根可能不一致——这一 parity 差距留待共享 shell 工具基座提取时解决。

8
packages/bash/tool-pwsh/src/index.ts
View File

@@ -114,18 +114,18 @@ function pwshDescription(backgroundEnabled: boolean, escalationModes: readonly S
+ 'On Windows a force-killed command settles as `[exit code: 1]` without a signal marker — treat it as an interruption, not a command failure. '
+ background
if (escalationModes.length === 0) return base
// The CLM and named-pipe contracts below are Windows-restricted-token
// The language-mode and named-pipe contracts below are Windows-restricted-token
// behavior, but the gate is 'any confining executor is mounted'
// (escalationModes non-empty). The conflation is safe today because every
// shipped composition pairing tool-pwsh with a confining executor is
// win32-only; a future POSIX pwsh-sandbox composition must gate both
// sentences on the platform instead (tracked in the pwsh-tool-and-executor
// Agent Note).
return base + ' Under the Windows sandbox, pwsh runs in PowerShell ConstrainedLanguage mode (read-only and '
+ 'workspace-write): prefer cmdlets and core types (`[string]`, `[datetime]`, `[regex]`, `[guid]`); '
return base + ' Under the Windows sandbox, read-only pwsh runs in PowerShell ConstrainedLanguage mode, while '
+ 'workspace-write stays in FullLanguage unless host policy says otherwise. In read-only, prefer cmdlets and core types (`[string]`, `[datetime]`, `[regex]`, `[guid]`); '
+ '.NET static calls (`[System.IO.*]::`, `[math]::`), `Add-Type`, COM objects, and reflection fail '
+ 'with "only core types" errors. `-f` formatting, property access, and core cmdlets work. '
+ 'In the same modes, programs cannot open named pipes, so a command that captures another '
+ 'In both confined modes, programs cannot open named pipes, so a command that captures another '
+ 'program\'s output through piped stdio (Node.js `child_process.spawn`/`exec` with the default '
+ '`stdio: \'pipe\'`) fails with EPERM, while `stdio: \'inherit\'` and `stdio: \'ignore\'` spawns '
+ 'work and PowerShell\'s own pipelines are unaffected. That EPERM is the documented boundary: '

3
packages/bash/tool-pwsh/tests/tools.spec.ts
View File

@@ -559,7 +559,8 @@ describe('sandbox escalation through ctx.approval', () => {
expect(properties['sandbox_permissions']?.enum).toEqual(['workspace-write', 'danger-full-access'])
expect(schema.description).toContain('approval prompt')
expect(schema.description).toContain('ConstrainedLanguage')
expect(schema.description).toContain('named pipes')
expect(schema.description).toContain('workspace-write stays in FullLanguage')
expect(schema.description).toContain('In both confined modes, programs cannot open named pipes')
expect(schema.description).toContain('fails with EPERM')
for (const args of [

13
packages/bundle/base/cordis.patch.yml
View File

@@ -170,18 +170,12 @@
mode: !!js process.env.DSH_PERMISSION_MODE ?? 'workspace-write'
workspaceRoot: !!js process.cwd()
# POSIX shell executor and its win32 twin: bash has no Windows runner, so
# each row gates itself on platform and exactly one shell stack mounts per
# host (both executors register the same 'bash' service).
- id: bash-sandbox
name: '@deepseek-ai/dsh-bash-sandbox'
disabled: !!js process.platform === 'win32'
config:
timeoutMs: 60000
# The confined PowerShell executor, mounted on win32 only. Its config keeps
# the schema defaults (a 120s timeout); the 60s pin above is the bash
# executor's own knob, not a shared shell policy.
- id: pwsh-sandbox
name: '@deepseek-ai/dsh-pwsh-sandbox'
disabled: !!js process.platform !== 'win32'
@@ -208,7 +202,6 @@
- id: bash-env
name: '@deepseek-ai/dsh-bash-env'
# The dialect tools gate with their executors: one shell tool per host.
- id: tool-bash
name: '@deepseek-ai/dsh-tool-bash'
disabled: !!js process.platform === 'win32'
@@ -328,12 +321,16 @@
toolName: subagent
backgroundMode: continuable
# Fork stays one-shot: a continuable child's `report` tool and prompt
# section precede the inherited history a fork exists to reuse; one-shot
# fork children install neither, keeping the parent's request prefix.
# See .agents/notes/implemented/architecture/2026-08-10-fork-children-stay-one-shot.md.
- id: tool-subagent-fork
name: '@deepseek-ai/dsh-tool-subagent'
config:
provider: fork
toolName: subagent_fork
backgroundMode: continuable
backgroundMode: one-shot
# Optional direct-child return channel; absent from roots and one-shot agents.
- id: tool-subagent-report

4
packages/bundle/headless/src/index.ts
View File

@@ -106,6 +106,10 @@ async function run(ctx: Context, task: string, io: HeadlessIo): Promise<void> {
if (agents === undefined || defaultModel === undefined || sessions === undefined) return
const selection = defaultModel.currentSelection()
// This bundle composes no preset roster, so the model-facing rows sit in the
// host plane and the agent reads them from the global layer. A deployment
// that DOES configure one has to join it here first
// (@deepseek-ai/dsh-agent-presets README, "Composing a child agent").
const { agent } = await agents.create({
sessionId: SessionId(`session-${randomUUID()}`),
meta: { cwd: process.cwd() },

8
packages/bundle/web-app/cordis.patch.yml
View File

@@ -309,8 +309,12 @@
- id: plan-mode
disabled: true
- id: token-meter
disabled: true
# The token METER stays on the host plane; only the compaction backend that
# reads it moves. It owns the context-meter projection units, and that table is
# process-wide, so preset ownership would make the meter a function of which
# presets happen to be mounted rather than a per-session fact. Same criterion as
# `tasks` and `goals`; the reasoning has one home in
# `.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md`.
- id: compact-basic
disabled: true

6
packages/client/connection/src/client/fixture.ts
View File

@@ -2834,6 +2834,12 @@ function createFixtureWorld(options: FixtureOptions): FixtureWorld {
})
return Promise.resolve({ accepted: true })
},
// Satisfies the ApiProxy contract type only: the browser export button
// fetches GET /api/session.export directly (window.fetch), so this stub is
// never reached through the fixture's dispatch.
downloads: {
sessionLog: () => Promise.resolve(new Response('fixture mode does not serve session export', { status: 404 })),
},
}
const rpc: ClientConnectionRpc = {

4
packages/client/ui-agent-preset/README.i18n.yaml
View File

@@ -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/client/ui-agent-preset/README.md
README.md: 008066114e9c49e5c74299979e24c27a4c9621c9
README.zh.md: e07d5994ae196cd03be7818fe4ade1aafda9aa55
README.md: 3b0db5a3eedca256a00b65a3bd2738f22c0eb62e
README.zh.md: 6f3c350f973119c201572f2c03145338b5cc5b00

4
packages/client/ui-agent-preset/README.md
View File

@@ -36,6 +36,8 @@ A fourth surface, its own settings page (`settings.section` id `agent-presets`,
The browser edits no composition text. Editing YAML in a web textarea was a weak surface (no completion, no highlighting, no diff), so a new preset is a host-side copy of an existing one — the dialog collects an id (it becomes the directory name, which is why it must be named up front and cannot change later) and an optional display name, and `{ from, id, name? }` is all that crosses the wire. Everything else — description, composition, skills — is edited in the preset's own files, and the page's other job is getting the user TO those files: the copy completes by opening the new directory, and every custom row keeps a location action. Where the host has no desktop opener (`hasDocument: false` on the roster; remote and container deployments), the same actions answer the directory as text on the row instead of offering a button that would spawn into nothing.
A preset publishes its own description, of any length, and the grid sizes every card row alike — so an unbounded description would set the height of the whole roster. Cards clamp it to four lines and offer the rest in a tooltip, attached only while the text is actually cut off. The clamp is CSS, so the whole description stays in the accessibility tree whatever the card shows.
A shipped preset opens in the read-only viewer. It is the known-good composition a copy starts from, so reading it is the point; it offers no location and no delete — its install is overwritten by upgrades and is not the user's to manage. The intro carries the guidance a create button used to imply: duplicate an existing preset and make it yours, or let the agent draft one in Creator mode.
Beside copying sits the conversational entry: when the roster carries the self-referential `cordis` preset, a dashed add-card (the Models page's affordance) stages it and starts a new session — the section closes the settings panel through the shell's owner-prop `close` and the new-session chip's own applier composes the blank session the workspace flow produces. The seat keeps a late roster load from regressing the display: staged pick first, then the composition the current session already carries, then the deployment default.
@@ -44,7 +46,7 @@ The dialog mirrors the host's own containment rule (`[a-z0-9][a-z0-9-]*`) and re
Deleting removes the preset directory. Sessions already composed from it keep running — a composition is mounted once at session creation and nothing re-reads the file.
A roster row carrying `broken` (the host's shape check found the composition missing or unloadable) renders as a marked card: red border, a Broken badge, the reason verbatim, the body disabled — it cannot become the default — and duplication disabled, since a copy of a broken preset is another broken preset. A broken custom row keeps its location and delete actions, because the files are where it gets fixed and deleting is how a ghost directory (composition deleted by hand, directory still blocking the id) is cleared; a broken shipped row withholds the viewer too — there is no readable composition to show. The two pickers (the General row and the new-session chip) drop broken presets entirely: they choose the NEXT session's composition, and offering one that cannot compose would only defer the failure to the session start.
A roster row carrying `broken` (the host's shape check found the composition missing or unloadable) renders as a marked card: red border, a "Failed to load" badge (what discovery observed, not a claim that the files are damaged — the usual cause is a composition the user just edited or deleted), the reason verbatim, the body disabled — it cannot become the default — and duplication disabled, since a copy of a broken preset is another broken preset. A broken custom row keeps its location and delete actions, because the files are where it gets fixed and deleting is how a ghost directory (composition deleted by hand, directory still blocking the id) is cleared; a broken shipped row withholds the viewer too — there is no readable composition to show. The two pickers (the General row and the new-session chip) drop broken presets entirely: they choose the NEXT session's composition, and offering one that cannot compose would only defer the failure to the session start.
Setting the default writes the `agent-presets` settings namespace, which the host exposes to configuration clients ([`dsh-apiproxy`](../../host/apiproxy/README.md) keeps an explicit allowlist — a namespace outside it makes a picker move and then silently forget).

4
packages/client/ui-agent-preset/README.zh.md
View File

@@ -36,6 +36,8 @@ preset 文件提供一套未国际化的 `name` 与 `description`，Web 将其
浏览器不再编辑任何组装文本。在网页文本域里编 YAML 是弱功能（无补全、无高亮、无 diff），因此新 preset 是宿主端对既有 preset 的一次复制——对话框只收集一个 id（它将成为目录名，所以必须当场取好、事后无法更改）与一个可选显示名，跨越传输层的只有 `{ from, id, name? }`。其余一切——描述、组装、skills——都在 preset 自己的文件里编辑，而本页的另一职责正是把用户送到那些文件面前：复制以打开新目录作为收尾，每张自定义卡片也保有一个位置操作。宿主没有桌面打开器时（名单上的 `hasDocument: false`；远程与容器部署），同样的操作改为把目录以文本显示在卡片上，而不是提供一个点了没反应的按钮。
preset 自行发布描述，长度不限，而网格让每一行卡片等高——因此不加约束的描述会决定整份名单的高度。卡片把描述截断为四行，其余内容由 tooltip 承载，且仅在文本确实被裁切时才挂载。截断由 CSS 完成，因此无论卡片显示多少，完整描述始终留在无障碍树中。
随附 preset 在只读查看器中打开。它是副本据以出发的已知良好组装，因此能读到它正是意义所在；它不提供位置也不提供删除——它的安装目录会被升级覆盖，不归用户管理。开篇引导语承担了从前创建按钮所暗示的信息：复制一份既有预设改成自己的，或用「创造模式」让 Agent 帮你创建。
复制旁边是对话式入口：名单携带自指的 `cordis` preset 时，一张虚线添加卡（模型页的同款样式）会暂存它并开启新会话——分区经外壳的 owner-prop `close` 关闭设置面板，新会话 chip 自己的应用器负责组装工作区流程产出的空白会话。seat 会防止晚到的名单加载回退显示：暂存选择优先，其次是当前会话已携带的组装，最后才是部署默认值。
@@ -44,7 +46,7 @@ preset 文件提供一套未国际化的 `name` 与 `description`，Web 将其
删除会移除整个 preset 目录。已据其组装的会话继续运行——组装在会话创建时挂载一次，此后没有任何东西会重新读取该文件。
名单行携带 `broken`（宿主的形状检查发现组装缺失或不可加载）时渲染为标记卡片：红色边框、「已损坏」徽记、原样展示的原因、卡片主体禁用——它不能成为默认——复制也禁用，因为损坏 preset 的副本只是又一个损坏的 preset。损坏的自定义行保留位置与删除动作：文件正是修复它的地方，而删除正是清掉幽灵目录（组装文件被手动删除、目录仍占着 id）的方式；损坏的内置行连查看器也不提供——没有可读的组装可展示。两个选择器（通用设置行与新会话 chip）则完全不列出损坏的 preset：它们选的是下一个会话的组装，列出无法组装的选项只会把失败推迟到会话启动。
名单行携带 `broken`（宿主的形状检查发现组装缺失或不可加载）时渲染为标记卡片：红色边框、「加载失败」徽记（discovery 观察到的事实，而非断言文件已损坏——常见起因是用户刚编辑或删除了组装文件）、原样展示的原因、卡片主体禁用——它不能成为默认——复制也禁用，因为损坏 preset 的副本只是又一个损坏的 preset。损坏的自定义行保留位置与删除动作：文件正是修复它的地方，而删除正是清掉幽灵目录（组装文件被手动删除、目录仍占着 id）的方式；损坏的内置行连查看器也不提供——没有可读的组装可展示。两个选择器（通用设置行与新会话 chip）则完全不列出损坏的 preset：它们选的是下一个会话的组装，列出无法组装的选项只会把失败推迟到会话启动。
设置默认值写入的是 `agent-presets` settings 命名空间，宿主需将其暴露给配置客户端（[`dsh-apiproxy`](../../host/apiproxy/README.md) 维护一份显式白名单——不在其中的命名空间会让选择器动一下然后悄悄忘记）。

15
packages/client/ui-agent-preset/src/client/AgentPresetSection.module.css
View File

@@ -161,15 +161,28 @@
color: var(--dsw-alias-bg-layer-3);
}
/* Bounded to four lines. A preset publishes its own description, so one long
one would otherwise stretch every card in its grid row (`.cards` sizes rows
1fr). Clamping is CSS alone: the whole text stays in the DOM for assistive
tech, and the card offers it on hover when it is actually cut off. The
description does not grow to fill the card — `-webkit-line-clamp` on a
flex-stretched box leaves the clamp height and the box height disagreeing,
so `.cardId` takes the free space with an auto margin instead. */
.cardDesc {
font-size: 13px;
line-height: 1.55;
color: var(--dsw-alias-label-secondary);
flex: 1;
min-height: 42px;
display: -webkit-box;
-webkit-box-orient: vertical;
-webkit-line-clamp: 4;
overflow: hidden;
/* A user-authored description may carry an unbreakable path or URL. */
overflow-wrap: anywhere;
}
.cardId {
margin-top: auto;
font-family: var(--dsw-font-mono, ui-monospace, SFMono-Regular, Menlo, monospace);
font-size: 11px;
color: var(--dsw-alias-label-dimmed);

39
packages/client/ui-agent-preset/src/client/AgentPresetSection.tsx
View File

@@ -10,10 +10,10 @@
* mounted once at session creation and nothing re-reads the file.
*/
import { useEffect } from 'react'
import { useEffect, useLayoutEffect, useRef, useState } from 'react'
import type { ReactNode } from 'react'
import {
Button, IconBrowseOutline16, IconCopyOutline16, IconFolderOpenOutline16, IconPlusOutline16, IconTrashOutline16, Modal,
Button, IconBrowseOutline16, IconCopyOutline16, IconFolderOpenOutline16, IconPlusOutline16, IconTrashOutline16, Modal, Tooltip,
} from '@deepseek-ai/dsh-client-ui-primitives'
import type { SnapshotStore } from '@deepseek-ai/dsh-client-runtime/client'
import type { InjectFace, PropsLocale, PropsRuntime } from '@deepseek-ai/dsh-client-ui-slots'
@@ -137,6 +137,39 @@ function CopyDialog({ state, t, actions }: CopyDialogProps): ReactNode {
)
}
/**
* Render one card's description, clamped by CSS and offered in full on hover.
* The tooltip is attached only while the text is actually cut off, so a short
* description does not answer a hover with a bubble repeating the card.
* @param props.text - the description as rendered, already localized.
* @returns the description element, tooltip-anchored while it overflows.
*/
function CardDescription({ text }: { text: string }): ReactNode {
const ref = useRef<HTMLSpanElement | null>(null)
const [truncated, setTruncated] = useState(false)
useLayoutEffect(() => {
const el = ref.current
/* v8 ignore next -- the ref is attached before layout effects run. */
if (el === null) return
const measure = () => { setTruncated(el.scrollHeight > el.clientHeight) }
measure()
// Card width follows the settings pane, which resizes with the window.
if (typeof ResizeObserver === 'undefined') return
const observer = new ResizeObserver(measure)
observer.observe(el)
return () => { observer.disconnect() }
}, [text])
return (
// Capped near the card's own width: the default half-viewport bubble would
// spill a description out of the settings dialog and across the app behind it.
<Tooltip label={text} side="bottom" delayMs={400} disabled={!truncated} maxWidth={360}>
{/* The empty title stops the card body's native tooltip from climbing to
this span: a cut-off description answers with one bubble, not two. */}
<span ref={ref} className={css.cardDesc} title="">{text}</span>
</Tooltip>
)
}
/**
* Render the Agent presets section content column.
* @param props - composed slot props.
@@ -247,7 +280,7 @@ export function AgentPresetSection(props: AgentPresetSectionProps): ReactNode {
</span>
{row.isDefault ? <span className={css.inUse}>{t('inUse')}</span> : null}
</span>
<span className={css.cardDesc}>{text.description ?? t('noDescription')}</span>
<CardDescription text={text.description ?? t('noDescription')} />
{row.broken === undefined
? null
: <span className={css.cardBrokenReason} role="alert">{row.broken}</span>}

8
packages/client/ui-agent-preset/src/client/locales.ts
View File

@@ -57,8 +57,8 @@ export const en: Record<AgentPresetSettingsKey, string> = {
builtInGroup: 'Built-in',
customGroup: 'Custom',
noDescription: 'No description.',
brokenBadge: 'Broken',
brokenNoCopy: 'Broken presets cannot be duplicated',
brokenBadge: 'Failed to load',
brokenNoCopy: 'A preset that failed to load cannot be duplicated',
copyOf: 'Copied from',
composition: 'Composition (agent.cordis.yml)',
cancel: 'Cancel',
@@ -117,8 +117,8 @@ export const zh: Record<AgentPresetSettingsKey, string> = {
builtInGroup: '内置',
customGroup: '自定义',
noDescription: '暂无描述。',
brokenBadge: '已损坏',
brokenNoCopy: '预设已损坏，无法复制',
brokenBadge: '加载失败',
brokenNoCopy: '预设加载失败，不能复制',
copyOf: '复制自',
composition: '组装（agent.cordis.yml）',
cancel: '取消',

69
packages/client/ui-agent-preset/tests/section.spec.tsx
View File

@@ -6,8 +6,8 @@
* action follows the host's desktop capability.
*/
import { cleanup, fireEvent, render, screen, waitFor, within } from '@testing-library/react'
import { afterEach, describe, expect, it, vi } from 'vitest'
import { act, cleanup, fireEvent, render, screen, waitFor, within } from '@testing-library/react'
import { afterEach, beforeEach, describe, expect, it, vi } from 'vitest'
import { bindSnapshotSelector } from '@deepseek-ai/dsh-client-web-react'
import { createSnapshotStore } from '@deepseek-ai/dsh-client-runtime/client'
import { AgentPresetSection } from '../src/client/AgentPresetSection.tsx'
@@ -452,3 +452,68 @@ describe('deleting a preset', () => {
expect(actions.remove).not.toHaveBeenCalled()
})
})
describe('a long card description', () => {
/** jsdom has no ResizeObserver; the description watches its own box through one. */
class ResizeObserverStub {
observe(): void {}
unobserve(): void {}
disconnect(): void {}
}
const LONG = '始终用简体中文交流的友好通用助手，提供持久 bash 与文件编辑能力。'.repeat(8)
/** Force the clamp to report an overflow: jsdom lays nothing out, so both heights are 0. */
function clamp(overflowing: boolean): void {
vi.spyOn(Element.prototype, 'scrollHeight', 'get').mockReturnValue(overflowing ? 400 : 80)
vi.spyOn(Element.prototype, 'clientHeight', 'get').mockReturnValue(80)
}
beforeEach(() => { vi.stubGlobal('ResizeObserver', ResizeObserverStub) })
afterEach(() => {
vi.unstubAllGlobals()
vi.restoreAllMocks()
})
it('offers the whole description on hover once the card cuts it off', () => {
clamp(true)
vi.useFakeTimers()
try {
renderSection({ rows: [{ id: 'zh', trust: 'user', isDefault: false, name: '中文助手', description: LONG }] })
fireEvent.mouseEnter(within(rowFor('zh')).getByText(LONG))
act(() => { vi.advanceTimersByTime(400) })
expect(screen.getByRole('tooltip').textContent).toBe(LONG)
} finally {
vi.useRealTimers()
}
})
it('stays quiet when the description already fits', () => {
clamp(false)
vi.useFakeTimers()
try {
renderSection({ rows: [{ id: 'zh', trust: 'user', isDefault: false, name: '中文助手', description: '短描述。' }] })
fireEvent.mouseEnter(within(rowFor('zh')).getByText('短描述。'))
act(() => { vi.advanceTimersByTime(400) })
// A bubble repeating what is already fully on the card is noise.
expect(screen.queryByRole('tooltip')).toBeNull()
} finally {
vi.useRealTimers()
}
})
it('renders where the runtime has no ResizeObserver', () => {
vi.unstubAllGlobals()
clamp(true)
expect(() => {
renderSection({ rows: [{ id: 'zh', trust: 'user', isDefault: false, description: LONG }] })
}).not.toThrow()
// The first measurement does not depend on the observer.
expect(within(rowFor('zh')).getByText(LONG).getAttribute('title')).toBe('')
})
})

69
packages/client/ui-primitives/src/Tooltip.tsx
View File

@@ -1,7 +1,7 @@
// Hover/focus label bubble (figma tooltip pill: dark plate, white text).
// TODO: interaction is a placeholder (horizontal overflow clamps, but there
// is no vertical flip on viewport collision and no arrow) — visuals and
// behavior get a proper pass later.
// TODO: interaction is a placeholder (horizontal overflow clamps and a
// vertical collision flips the bubble to the other side, but there is no
// arrow) — visuals and behavior get a proper pass later.
// The anchor is the child element itself (cloneElement, no wrapper node), so
// attaching a tooltip never changes the anchor's layout context. The bubble is
// position:fixed and coordinates come from the anchor's rect at show time, so
@@ -33,10 +33,12 @@ type TooltipLabel = string | (() => string)
* @param props.delayMs - hover delay in milliseconds; keyboard focus remains immediate.
* @param props.disabled - suppress the bubble while true; the anchor renders identically so
* toggling never remounts it (which would cut its CSS transitions).
* @param props.maxWidth - bubble width cap in pixels, for labels long enough that the default
* half-viewport cap would render a slab wider than the surface the anchor sits on.
* @param props.children - a single anchor element; its own ref (callback or object) is forwarded alongside the tooltip's.
* @returns the cloned anchor plus a fixed-position bubble while hovered/focused.
*/
export function Tooltip({ label, side = 'right', delayMs = 0, disabled = false, children }: { label: TooltipLabel; side?: TooltipSide; delayMs?: number; disabled?: boolean; children: ReactElement<AnchorProps> }) {
export function Tooltip({ label, side = 'right', delayMs = 0, disabled = false, maxWidth, children }: { label: TooltipLabel; side?: TooltipSide; delayMs?: number; disabled?: boolean; maxWidth?: number; children: ReactElement<AnchorProps> }) {
const anchor = useRef<HTMLElement | null>(null)
// React 18 keeps the element's ref outside props; forward it so wrapping an
// anchor in Tooltip never silently severs the owner's ref.
@@ -46,33 +48,53 @@ export function Tooltip({ label, side = 'right', delayMs = 0, disabled = false,
if (typeof childRef === 'function') childRef(el)
else if (childRef != null) (childRef as MutableRefObject<HTMLElement | null>).current = el
}, [childRef])
const [pos, setPos] = useState<{ x: number; y: number } | null>(null)
// The anchor's edges rather than final coordinates: a vertical flip has to
// re-derive the bubble's own top from the opposite edge.
const [pos, setPos] = useState<{ x: number; top: number; bottom: number } | null>(null)
// Where the bubble actually sits, which is the requested side until the
// viewport refuses it.
const [placement, setPlacement] = useState<TooltipSide>(side)
const bubble = useRef<HTMLSpanElement | null>(null)
const resolvedLabel = pos === null
? null
: typeof label === 'function' ? label() : label
// Horizontal viewport clamp: fixed positioning knows nothing about edges, so
// a centered bubble near the right edge would clip. Each measurement resets
// the base position before applying a direct style offset, allowing a shorter
// label or wider viewport to release a previous clamp without another render.
const y = pos === null
? 0
: placement === 'right'
? pos.top + (pos.bottom - pos.top) / 2
: placement === 'top' ? pos.top - 8 : pos.bottom + 8
const EDGE_MARGIN = 12
// Viewport fit: fixed positioning knows nothing about edges, so a centered
// bubble near the right edge would clip and a long label under an anchor low
// on the page would run off the bottom. Horizontally the bubble slides back
// inside; vertically it flips to the opposite side, which is the only move
// that does not cover the anchor being read. Each measurement resets the base
// position first, so a shorter label or a larger viewport releases a previous
// adjustment without another render.
useLayoutEffect(() => {
if (pos === null) return
const clamp = () => {
const fit = () => {
const el = bubble.current
/* v8 ignore next -- pos is set only while the bubble is mounted. */
if (el === null) return
const EDGE_MARGIN = 12
el.style.left = `${pos.x}px`
const r = el.getBoundingClientRect()
let dx = 0
if (r.right > window.innerWidth - EDGE_MARGIN) dx = window.innerWidth - EDGE_MARGIN - r.right
if (r.left + dx < EDGE_MARGIN) dx = EDGE_MARGIN - r.left
el.style.left = `${pos.x + dx}px`
if (side === 'right') return
// Flip only into a side that genuinely fits, so an anchor with room on
// neither side keeps the requested placement instead of oscillating.
const fitsBelow = pos.bottom + 8 + r.height <= window.innerHeight - EDGE_MARGIN
const fitsAbove = pos.top - 8 - r.height >= EDGE_MARGIN
if (placement === 'bottom' && !fitsBelow && fitsAbove) setPlacement('top')
if (placement === 'top' && !fitsAbove && fitsBelow) setPlacement('bottom')
}
clamp()
window.addEventListener('resize', clamp)
return () => { window.removeEventListener('resize', clamp) }
}, [pos, resolvedLabel])
fit()
window.addEventListener('resize', fit)
return () => { window.removeEventListener('resize', fit) }
}, [placement, pos, resolvedLabel, side])
const showTimer = useRef<ReturnType<typeof setTimeout> | null>(null)
// Hover and focus are independent triggers: the bubble hides only after
// BOTH clear (hovering away from a focused anchor must not drop it).
@@ -100,11 +122,10 @@ export function Tooltip({ label, side = 'right', delayMs = 0, disabled = false,
/* v8 ignore next -- the ref is attached by event time: events fire on the cloned anchor. */
if (el === null) return
const r = el.getBoundingClientRect()
setPos(side === 'right'
? { x: r.right + 10, y: r.top + r.height / 2 }
: side === 'top'
? { x: r.left + r.width / 2, y: r.top - 8 }
: { x: r.left + r.width / 2, y: r.bottom + 8 })
// Every show starts from the requested side; the fit pass flips it only
// where this anchor's position demands it.
setPlacement(side)
setPos({ x: side === 'right' ? r.right + 10 : r.left + r.width / 2, top: r.top, bottom: r.bottom })
}
const showAfterHoverDelay = () => {
cancelShow()
@@ -132,7 +153,13 @@ export function Tooltip({ label, side = 'right', delayMs = 0, disabled = false,
onBlur: (e) => { children.props.onBlur?.(e); triggers.current.focus = false; hide() },
})}
{pos !== null && (
<span ref={bubble} className={css.bubble} data-side={side} style={{ left: pos.x, top: pos.y }} role="tooltip">
<span
ref={bubble}
className={css.bubble}
data-side={placement}
style={{ left: pos.x, top: y, ...maxWidth === undefined ? {} : { maxWidth } }}
role="tooltip"
>
{resolvedLabel}
</span>
)}

105
packages/client/ui-primitives/tests/tooltip.spec.tsx
View File

@@ -95,6 +95,18 @@ describe('Tooltip', () => {
const rect = (left: number, right: number): DOMRect =>
({ left, right, top: 0, bottom: 20, width: right - left, height: 20, x: left, y: 0, toJSON: () => ({}) })
it('caps the bubble width where the label would otherwise slab across the surface', () => {
render(
<Tooltip label="A description long enough to need a cap" side="bottom" maxWidth={360}>
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
// The stylesheet's half-viewport cap stays the default; this one overrides it.
expect(screen.getByRole('tooltip').style.maxWidth).toBe('360px')
})
it('clamps a bubble overflowing the right viewport edge back inside', () => {
const spy = vi.spyOn(Element.prototype, 'getBoundingClientRect').mockReturnValue(rect(900, 1100))
try {
@@ -161,19 +173,88 @@ describe('Tooltip', () => {
}
})
/** Anchor and bubble rects, so a placement test measures real room rather than jsdom's all-zero boxes. */
const placed = (anchorTop: number, anchorBottom: number, bubbleHeight: number) =>
vi.spyOn(Element.prototype, 'getBoundingClientRect').mockImplementation(function (this: Element) {
const [top, bottom] = this.getAttribute('role') === 'tooltip'
? [0, bubbleHeight]
: [anchorTop, anchorBottom]
return {
left: 100, right: 200, top, bottom, width: 100, height: bottom - top, x: 100, y: top, toJSON: () => ({}),
}
})
it('supports top placement for anchors at the viewport bottom', () => {
render(
<Tooltip label="Above" side="top">
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
const bubble = screen.getByRole('tooltip')
expect(bubble.getAttribute('data-side')).toBe('top')
// jsdom rects are all-zero: top placement lands at the -8 gutter and the
// zero-width measured rect clamps left to the 12px edge margin.
expect(bubble.style.left).toBe('12px')
expect(bubble.style.top).toBe('-8px')
const spy = placed(700, 720, 20)
try {
render(
<Tooltip label="Above" side="top">
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
const bubble = screen.getByRole('tooltip')
// There is room above, so the requested side stands: the bubble's own
// top sits at the anchor's top less the 8px gutter.
expect(bubble.getAttribute('data-side')).toBe('top')
expect(bubble.style.top).toBe('692px')
expect(bubble.style.left).toBe('150px')
} finally {
spy.mockRestore()
}
})
it('flips a bottom bubble above an anchor with no room below', () => {
// jsdom's viewport is 768 tall: a 300px bubble under an anchor ending at
// 700 would run off, and there is room for it above.
const spy = placed(600, 700, 300)
try {
render(
<Tooltip label="Tall" side="bottom">
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
const bubble = screen.getByRole('tooltip')
expect(bubble.getAttribute('data-side')).toBe('top')
expect(bubble.style.top).toBe('592px')
} finally {
spy.mockRestore()
}
})
it('flips a top bubble below an anchor with no room above', () => {
const spy = placed(10, 40, 100)
try {
render(
<Tooltip label="Tall" side="top">
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
const bubble = screen.getByRole('tooltip')
expect(bubble.getAttribute('data-side')).toBe('bottom')
expect(bubble.style.top).toBe('48px')
} finally {
spy.mockRestore()
}
})
it('keeps the requested side when neither side fits', () => {
// A bubble taller than the viewport has no home; oscillating between the
// two would be worse than honouring the request.
const spy = placed(300, 400, 900)
try {
render(
<Tooltip label="Huge" side="bottom">
<button type="button">anchor</button>
</Tooltip>,
)
fireEvent.mouseEnter(screen.getByText('anchor'))
expect(screen.getByRole('tooltip').getAttribute('data-side')).toBe('bottom')
} finally {
spy.mockRestore()
}
})
it('chains the anchor\'s own handlers ahead of the tooltip\'s', () => {

4
packages/client/ui-trajectory/README.i18n.yaml
View File

@@ -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/client/ui-trajectory/README.md
README.md: d3786b6460c5df7eaa6d24e68c80025e7fb29ae4
README.zh.md: 5eb1451b9a3a9896d5486fcf5c8d9cf30d6159a0
README.md: e82b2cc9d4a65c3095aeee7002fb6c43a43b695d
README.zh.md: a1ba62393c2aae3f6baa7c481dd80f04dbbb477d

2
packages/client/ui-trajectory/README.md
View File

@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. Scrollable Summary regions keep their scrollbar thumbs transparent until the region is hovered or contains keyboard focus, without changing the reserved scroll geometry. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. Long ledgers open at the current tail, load one older page when the user reaches the loaded range's top, and mount only the visible row window plus a small overscan; request-only separators share the next measurable virtual item, while semantic row keys and ARIA indexes survive prepends. Selection, timeline navigation, folding, search, and Request totals cover the currently loaded window. The ledger covers records with an explicit loading row until the initial tail is positioned and while an older page is pending. A fixed Overview above the ledger projects real record start/duration timing from left to right; when earlier records remain unloaded and the viewport includes the loaded domain's start, a neutral ellipsis control identifies the omitted prefix and loads one earlier page without assigning unknown history fabricated duration. Assistant spans divide recorded TTFT from decoding, and a 500 ms hover reveals exact clock and duration details. Dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full loaded ledger. Wheel gestures zoom the time domain. A right-button click clears the selected interval, while a right-button drag pans an already zoomed viewport without changing it. The initial view and streaming updates stay at the tail; scrolling upward suspends following so new records do not interrupt inspection of earlier rows. Content-only stream frames preserve virtual row keys and heights, reuse measurements, and do not issue repeated tail-scroll writes. Completed replies retain assembled blocks, timing, and usage in Trajectory target State, while the shared Session window keeps the raw Events. Trajectory asks the conversation shell to float the composer over the full-height ledger, while its responsive vertical scrollers reserve the composer's live height so final rows remain reachable. Trajectory-owned Definitions assemble business records, including cancellation-frozen Assistant and Tool records, from the shared Session window, so Trajectory neither reads nor changes the Chat conversation snapshot. The package provides no service and declares no Context merge; it registers target-specific Event Definitions, a Trajectory view builder, and one tab in the conversation's `'conversation.view'` slot ring. Contract: api-contracts v3 §8.
Trajectory renders a turn-aware event ledger with selectable User, Assistant, Tool, and nested Subtool records. Thick rules mark Turn boundaries, compact inline markers identify Steps, and the main ledger keeps only index, event, and content; selection opens a local inspector for token usage, duration, Input, Output, and Timing. Scrollable Summary regions keep their scrollbar thumbs transparent until the region is hovered or contains keyboard focus, without changing the reserved scroll geometry. A standalone compaction request appears chronologically in its own `Between turns` section, while a numbered compaction remains inside its owning turn. Long ledgers open at the current tail, load one older page when the user reaches the loaded range's top, and mount only the visible row window plus a small overscan; request-only separators share the next measurable virtual item, while semantic row keys and ARIA indexes survive prepends. Selection, timeline navigation, folding, search, and Request totals cover the currently loaded window. The ledger covers records with an explicit loading row until the initial tail is positioned and while an older page is pending. A fixed Overview above the ledger projects real record start/duration timing from left to right; when earlier records remain unloaded and the viewport includes the loaded domain's start, a neutral ellipsis control identifies the omitted prefix and loads one earlier page without assigning unknown history fabricated duration. Assistant spans divide recorded TTFT from decoding, and a 500 ms hover reveals exact clock and duration details. Dragging an interval focuses the ledger on every record active at any point in that inclusive range, while clearing the selection restores the full loaded ledger. Wheel gestures zoom the time domain. A right-button click clears the selected interval, while a right-button drag pans an already zoomed viewport without changing it. The initial view and streaming updates stay at the tail; scrolling upward suspends following so new records do not interrupt inspection of earlier rows. Content-only stream frames preserve virtual row keys and heights, reuse measurements, and do not issue repeated tail-scroll writes. The toolbar's Export button downloads the session log — the root plus every subagent descendant — as a ZIP streamed by the host (`GET /api/session.export`): every file is the session's stored artifact text verbatim (`session.jsonl` at the root, `subagents/<id>/session.jsonl` for descendants; no manifest, byte-identical to the backend's durable artifact), and every image any included log references sits under `media/<attachmentId>.<ext>`. Fixture mode (no host) answers 404 for the export. Completed replies retain assembled blocks, timing, and usage in Trajectory target State, while the shared Session window keeps the raw Events. Trajectory asks the conversation shell to float the composer over the full-height ledger, while its responsive vertical scrollers reserve the composer's live height so final rows remain reachable. Trajectory-owned Definitions assemble business records, including cancellation-frozen Assistant and Tool records, from the shared Session window, so Trajectory neither reads nor changes the Chat conversation snapshot. The package provides no service and declares no Context merge; it registers target-specific Event Definitions, a Trajectory view builder, and one tab in the conversation's `'conversation.view'` slot ring. Contract: api-contracts v3 §8.
## Model Experience

2
packages/client/ui-trajectory/README.zh.md
View File

@@ -2,7 +2,7 @@
[English](README.md) | 中文
Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。可滚动的概述区域默认保持滚动条滑块透明，直到鼠标悬停该区域或其中包含键盘焦点时才显示，同时不改变滚动条预留的几何空间。独立运行的压缩（compaction）请求会按时间顺序显示在自己的 `Between turns` 区段中，而带编号的压缩仍位于其所属轮次内。长记录表打开时定位于当前尾部，用户到达已加载范围顶部时加载一页更早的历史，并且只挂载可见行窗口和少量额外缓冲行；仅含请求的分隔行并入下一个具备可测高度的虚拟项，语义行键和 ARIA 索引在向前补页后保持不变。选择、时间线导航、折叠、搜索和请求汇总只覆盖当前已加载的窗口。初始尾部完成定位前以及更早页面仍在等待时，记录表会用明确的加载行遮住真实记录。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；仍有更早记录未加载且 viewport 包含已加载时间域起点时，中性的省略号控件会标识被省略的前缀，并可加载一页更早历史，而不会为未知部分虚构耗时。助手时间条会区分记录到的 TTFT 与解码时间，悬停 500 ms 后可查看精确时刻和耗时详情。拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整的已加载记录表。滚轮手势用于缩放时间域。右键单击会清除所选区间；在已放大的 viewport 上按住右键拖动则只会平移视图，不会改变该区间。初始视图和流式更新都会停留在尾部；向上滚动会暂停跟随，因此新记录不会打断对旧记录的检查。仅含内容更新的流式帧会保持虚拟行的键和高度不变、复用测量结果，并且不会重复写入末尾滚动位置。已完成的回复会在 Trajectory target State 中保留组装后的 blocks、计时与用量，共享 Session 窗口则保留原始 Event。Trajectory 要求会话壳将 composer 作为浮层置于全高记录表上方；其响应式纵向滚动容器会预留 composer 的实时高度，确保仍可滚动到最后几行。Trajectory 自有的 Definition 从共享 Session 窗口组装业务记录，其中包括因取消而冻结的助手和工具记录，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包不提供 service，也不声明 Context 合并；它会注册 target 专属 Event Definition、Trajectory view builder，以及会话 `'conversation.view'` slot 环中的一个视图标签页。约定：api-contracts v3 §8。
Trajectory 渲染按轮次组织的事件记录表，其中可选择用户、助手、工具和嵌套子工具记录。较粗的分割线标示轮次边界，紧凑的行内标记标识步骤，主记录表仅保留索引、事件和内容；选择记录则会打开局部检查器，查看 token 用量、耗时、输入、输出和计时。可滚动的概述区域默认保持滚动条滑块透明，直到鼠标悬停该区域或其中包含键盘焦点时才显示，同时不改变滚动条预留的几何空间。独立运行的压缩（compaction）请求会按时间顺序显示在自己的 `Between turns` 区段中，而带编号的压缩仍位于其所属轮次内。长记录表打开时定位于当前尾部，用户到达已加载范围顶部时加载一页更早的历史，并且只挂载可见行窗口和少量额外缓冲行；仅含请求的分隔行并入下一个具备可测高度的虚拟项，语义行键和 ARIA 索引在向前补页后保持不变。选择、时间线导航、折叠、搜索和请求汇总只覆盖当前已加载的窗口。初始尾部完成定位前以及更早页面仍在等待时，记录表会用明确的加载行遮住真实记录。固定在记录表上方的 Overview 区域从左到右投影记录的真实开始时间与耗时；仍有更早记录未加载且 viewport 包含已加载时间域起点时，中性的省略号控件会标识被省略的前缀，并可加载一页更早历史，而不会为未知部分虚构耗时。助手时间条会区分记录到的 TTFT 与解码时间，悬停 500 ms 后可查看精确时刻和耗时详情。拖选一个区间会将记录表聚焦到活动区间与该闭区间有重叠的所有记录，清除选择则恢复完整的已加载记录表。滚轮手势用于缩放时间域。右键单击会清除所选区间；在已放大的 viewport 上按住右键拖动则只会平移视图，不会改变该区间。初始视图和流式更新都会停留在尾部；向上滚动会暂停跟随，因此新记录不会打断对旧记录的检查。仅含内容更新的流式帧会保持虚拟行的键和高度不变、复用测量结果，并且不会重复写入末尾滚动位置。工具栏的 “Export” 按钮会将会话日志——根会话及其全部子代理——下载为宿主流式返回的 ZIP（`GET /api/session.export`）：每个文件都是会话存储工件的逐字原文（根为 `session.jsonl`，子代理为 `subagents/<id>/session.jsonl`；无清单，与后端持久化工件逐字节一致），每个被包含日志引用的图片则放在 `media/<attachmentId>.<ext>` 下。fixture 模式（无宿主）对导出应答 404。已完成的回复会在 Trajectory target State 中保留组装后的 blocks、计时与用量，共享 Session 窗口则保留原始 Event。Trajectory 要求会话壳将 composer 作为浮层置于全高记录表上方；其响应式纵向滚动容器会预留 composer 的实时高度，确保仍可滚动到最后几行。Trajectory 自有的 Definition 从共享 Session 窗口组装业务记录，其中包括因取消而冻结的助手和工具记录，因此 Trajectory 既不读取也不改变 Chat 会话快照。该包不提供 service，也不声明 Context 合并；它会注册 target 专属 Event Definition、Trajectory view builder，以及会话 `'conversation.view'` slot 环中的一个视图标签页。约定：api-contracts v3 §8。
## 模型体验

3
packages/client/ui-trajectory/package.json
View File

@@ -32,6 +32,7 @@
"dsh": {
"client": {
"inject": [
"@deepseek-ai/dsh-client-locale",
"@deepseek-ai/dsh-client-runtime",
"@deepseek-ai/dsh-client-ui-conversation"
],
@@ -49,6 +50,7 @@
},
"peerDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-client-locale": "workspace:^",
"@deepseek-ai/dsh-client-runtime": "workspace:^",
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
@@ -60,6 +62,7 @@
},
"devDependencies": {
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-client-locale": "workspace:^",
"@deepseek-ai/dsh-client-runtime": "workspace:^",
"@deepseek-ai/dsh-client-ui-primitives": "workspace:^",
"@deepseek-ai/dsh-client-ui-conversation": "workspace:^",

30
packages/client/ui-trajectory/src/client/TrajectoryTable.tsx
View File

@@ -156,8 +156,8 @@ type DetailTab =
| 'tools'
| 'overview'
| 'rendered'
| 'raw'
| 'source'
| 'origin'
| 'input'
| 'output'
| 'schema'
@@ -800,7 +800,7 @@ function RequestOptions({
)
}
function messageOriginLabel(source: unknown): string {
function messageSourceLabel(source: unknown): string {
if (typeof source !== 'object' || source === null || Array.isArray(source)) {
return 'Unknown'
}
@@ -823,16 +823,16 @@ function messageOriginLabel(source: unknown): string {
return `${kind[0]?.toUpperCase() ?? ''}${kind.slice(1)}`
}
function MessageOrigin({ record }: { record: TableRecord }) {
function MessageSource({ record }: { record: TableRecord }) {
const source = record.cell.messageSource
if (source === undefined) return <p className={css.noPayload}>Origin not recorded</p>
if (source === undefined) return <p className={css.noPayload}>Source not recorded</p>
const data = typeof source === 'object' && source !== null
? source
: { value: source }
return (
<JsonTree
data={data}
label="Message origin JSON"
label="Message source JSON"
className={css.jsonPayload}
/>
)
@@ -897,17 +897,17 @@ function detailTabs(record: TableRecord): readonly DetailTabItem[] {
if (record.cell.kind === 'compacted') {
return [
{ id: 'overview', label: 'Summary' },
{ id: 'source', label: 'Raw Output' },
{ id: 'raw', label: 'Raw Output' },
]
}
if (isMarkdownRecord(record)) {
return [
{ id: 'overview', label: 'Summary' },
{ id: 'rendered', label: 'Preview' },
{ id: 'source', label: 'Source' },
{ id: 'raw', label: 'Raw' },
...(record.cell.messageSource === undefined
? []
: [{ id: 'origin', label: 'Origin' } as const]),
: [{ id: 'source', label: 'Source' } as const]),
]
}
return [
@@ -2855,14 +2855,14 @@ export function TrajectoryTable({
>
{selected.cell.messageSource !== undefined && (
<div>
<dt>Origin</dt>
<dt>Source</dt>
<dd className={css.overviewParentLinks}>
<button
type="button"
className={css.overviewHierarchyNavLink}
onClick={() => { activateTab('origin') }}
onClick={() => { activateTab('source') }}
>
<span>{messageOriginLabel(selected.cell.messageSource)}</span>
<span>{messageSourceLabel(selected.cell.messageSource)}</span>
<IconChevronRightOutline14
className={css.overviewHierarchyJumpIconTight}
size={11}
@@ -2875,7 +2875,7 @@ export function TrajectoryTable({
<div>
<dt>
{selectedAssistantRequestTarget !== undefined
? 'Origin'
? 'Source'
: 'Hierarchy'}
</dt>
<dd className={css.overviewParentLinks}>
@@ -2999,7 +2999,7 @@ export function TrajectoryTable({
onOpenCall={openCallSummary}
/>
)}
{!promptSelected && selected !== undefined && activeTab === 'source' && (
{!promptSelected && selected !== undefined && activeTab === 'raw' && (
<MarkdownRecordContent
record={selected}
rendered={false}
@@ -3008,8 +3008,8 @@ export function TrajectoryTable({
onOpenCall={openCallSummary}
/>
)}
{!promptSelected && selected !== undefined && activeTab === 'origin' && (
<MessageOrigin record={selected} />
{!promptSelected && selected !== undefined && activeTab === 'source' && (
<MessageSource record={selected} />
)}
{!promptSelected && selected !== undefined && activeTab === 'input' && (
<RecordPayload record={selected} direction="input" />

40
packages/client/ui-trajectory/src/client/TrajectoryToolbar.module.css
View File

@@ -164,6 +164,46 @@
font: 14px/14px var(--ds-font-family-code);
}
.export {
display: inline-flex;
flex: none;
align-items: center;
height: 20px;
padding: 0 7px;
gap: 4px;
border: 0;
border-radius: 3px;
color: var(--dsw-alias-label-tertiary);
background: transparent;
cursor: pointer;
font: var(--dsw-font-xxs-12);
}
.export:hover:not(:disabled) {
color: var(--dsw-alias-label-primary);
background: var(--dsw-alias-interactive-bg-hover);
}
.export:focus-visible {
outline: 1px solid var(--dsw-alias-state-business-primary);
outline-offset: 1px;
}
.export:disabled {
color: var(--dsw-alias-label-dimmed);
cursor: wait;
}
.exportIcon {
flex: none;
width: 12px;
height: 12px;
stroke: currentColor;
stroke-width: 1.25;
stroke-linecap: round;
stroke-linejoin: round;
}
.search {
display: flex;
flex: 0 1 164px;

54
packages/client/ui-trajectory/src/client/TrajectoryToolbar.tsx
View File

@@ -1,6 +1,8 @@
/** Trajectory toolbar: timeline and ledger fold controls. */
import type { TranslateNS } from '@deepseek-ai/dsh-client-ui-slots'
import { IconSearchOutline16 } from '@deepseek-ai/dsh-client-ui-primitives'
import type { NS } from './locales.ts'
import css from './TrajectoryToolbar.module.css'
export interface TrajectoryToolbarProps {
@@ -24,6 +26,14 @@ export interface TrajectoryToolbarProps {
searchQuery: string
/** Update the live ledger search query. */
onSearchQueryChange: (query: string) => void
/** Whether the session-log export is in flight. */
exporting: boolean
/** Trigger the session-log export download. */
onExport: () => void
/** Export failure message, shown while set; null while idle or successful. */
exportError: string | null
/** Translate a toolbar dictionary key. */
t: TranslateNS<typeof NS>
}
/**
@@ -42,17 +52,21 @@ export function TrajectoryToolbar({
onToggleAllAssistants,
searchQuery,
onSearchQueryChange,
exporting,
onExport,
exportError,
t,
}: TrajectoryToolbarProps) {
return (
<div className={css.root} role="toolbar" aria-label="Trajectory toolbar">
<div className={css.root} role="toolbar" aria-label={t('toolbar.aria')}>
<div className={css.inner}>
<div className={css.actions}>
<button
type="button"
className={css.toggle}
aria-label="Use actual duration"
aria-label={t('toolbar.useActualDuration')}
aria-pressed={actualDuration}
title={actualDuration ? 'Use equal-width operations' : 'Use actual duration'}
title={actualDuration ? t('toolbar.useEqualWidth') : t('toolbar.useActualDuration')}
onClick={() => { onActualDurationChange(!actualDuration) }}
>
<svg
@@ -64,7 +78,7 @@ export function TrajectoryToolbar({
<circle cx="8" cy="8" r="5.25" />
<path d="M8 4.75V8l2.25 1.5" />
</svg>
Duration
{t('toolbar.duration')}
</button>
<button
type="button"
@@ -74,7 +88,7 @@ export function TrajectoryToolbar({
hidden
onClick={() => { onActualTimeChange(!actualTime) }}
>
<span>Actual time</span>
<span>{t('toolbar.actualTime')}</span>
<span className={css.controlTrack} data-on={actualTime || undefined} aria-hidden="true">
<span className={css.controlThumb} />
</span>
@@ -82,28 +96,42 @@ export function TrajectoryToolbar({
<button
type="button"
className={css.action}
aria-label={allTurnsCollapsed ? 'Expand turns' : 'Collapse turns'}
aria-label={allTurnsCollapsed ? t('toolbar.expandTurns') : t('toolbar.collapseTurns')}
aria-pressed={allTurnsCollapsed}
title={allTurnsCollapsed ? 'Expand turns' : 'Collapse turns'}
title={allTurnsCollapsed ? t('toolbar.expandTurns') : t('toolbar.collapseTurns')}
onClick={onToggleAllTurns}
>
<span className={css.actionIcon} aria-hidden="true">
{allTurnsCollapsed ? '⊞' : '⊟'}
</span>
Turns
{t('toolbar.turns')}
</button>
<button
type="button"
className={css.action}
aria-label={allAssistantsCollapsed ? 'Expand calls' : 'Collapse calls'}
aria-label={allAssistantsCollapsed ? t('toolbar.expandCalls') : t('toolbar.collapseCalls')}
aria-pressed={allAssistantsCollapsed}
title={allAssistantsCollapsed ? 'Expand calls' : 'Collapse calls'}
title={allAssistantsCollapsed ? t('toolbar.expandCalls') : t('toolbar.collapseCalls')}
onClick={onToggleAllAssistants}
>
<span className={css.actionIcon} aria-hidden="true">
{allAssistantsCollapsed ? '⊞' : '⊟'}
</span>
Calls
{t('toolbar.calls')}
</button>
<button
type="button"
className={css.export}
aria-label={t('toolbar.exportAria')}
title={exportError ?? (exporting ? t('toolbar.exporting') : t('toolbar.exportTitle'))}
disabled={exporting}
onClick={onExport}
>
<svg className={css.exportIcon} viewBox="0 0 16 16" fill="none" aria-hidden="true">
<path d="M8 3v7m0 0 3-3m-3 3L5 7" />
<path d="M3 11.5V13a1 1 0 0 0 1 1h8a1 1 0 0 0 1-1v-1.5" />
</svg>
{t('toolbar.export')}
</button>
</div>
<div className={css.search}>
@@ -111,8 +139,8 @@ export function TrajectoryToolbar({
<input
type="search"
className={css.searchInput}
aria-label="Search trajectory"
placeholder="Search"
aria-label={t('toolbar.search')}
placeholder={t('toolbar.searchPlaceholder')}
value={searchQuery}
onChange={(event) => { onSearchQueryChange(event.currentTarget.value) }}
/>

34
packages/client/ui-trajectory/src/client/TrajectoryView.tsx
View File

@@ -2,7 +2,7 @@
import { useCallback, useEffect, useMemo, useRef, useState } from 'react'
import type { ConvViewProps } from '@deepseek-ai/dsh-client-ui-conversation/client'
import type { InjectFace } from '@deepseek-ai/dsh-client-ui-slots'
import type { InjectFace, PropsLocale } from '@deepseek-ai/dsh-client-ui-slots'
import type {
AssistantBlock, AssistantMessageNode, ConversationSnapshot,
SnapshotStore,
@@ -71,6 +71,8 @@ export interface TrajectoryViewInjected {
}
loadOlder: () => Promise<boolean>
setActualDuration: (actualDuration: boolean) => void
/** Download the session log (including subagent logs) as a ZIP archive; rejects on failure. */
exportLog: () => Promise<void>
}
interface UsageLike {
@@ -118,9 +120,9 @@ function addUsage(
}
export function TrajectoryView({
useSession, useDuration, loadOlder, setActualDuration,
inspect, onInspectDone,
}: ConvViewProps & InjectFace<TrajectoryViewInjected>) {
useSession, useDuration, loadOlder, setActualDuration, exportLog,
inspect, onInspectDone, t,
}: ConvViewProps & InjectFace<TrajectoryViewInjected> & PropsLocale<'trajectory'>) {
const [collapsedTurns, setCollapsedTurns] = useState<ReadonlySet<number>>(EMPTY_TURN_IDS)
const [collapsedAssistants, setCollapsedAssistants] =
useState<ReadonlySet<string>>(EMPTY_RECORD_IDS)
@@ -128,6 +130,8 @@ export function TrajectoryView({
const actualDuration = useDuration(value => value)
const [actualTime, setActualTime] = useState(false)
const [searchQuery, setSearchQuery] = useState('')
const [exporting, setExporting] = useState(false)
const [exportError, setExportError] = useState<string | null>(null)
const [searchIndex] = useState(() => new TrajectorySearchIndex())
const [searchIndexRevision, setSearchIndexRevision] = useState(0)
const searchIndexTimer = useRef<ReturnType<typeof setTimeout> | null>(null)
@@ -443,6 +447,19 @@ export function TrajectoryView({
return loadOlder()
}, [loadOlder])
const onExport = useCallback(() => {
if (exporting) return
setExporting(true)
setExportError(null)
void exportLog().then(
() => { setExporting(false) },
(error: unknown) => {
setExportError(error instanceof Error ? error.message : String(error))
setExporting(false)
},
)
}, [exportLog, exporting])
return (
<div className={css.root} data-conversation-composer-overlay="">
<TrajectoryToolbar
@@ -462,7 +479,16 @@ export function TrajectoryView({
onToggleAllAssistants={toggleAllAssistants}
searchQuery={searchQuery}
onSearchQueryChange={setSearchQuery}
exporting={exporting}
onExport={onExport}
exportError={exportError}
t={t}
/>
{exportError !== null && (
<div className={css.exportError} role="alert">
{exportError}
</div>
)}
<TrajectoryTimeline
turns={timelineTurns}
mode={timelineMode}

42
packages/client/ui-trajectory/src/client/export-log.ts Normal file
View File

@@ -0,0 +1,42 @@
/**
* Session log export: browser download of the host-streamed ZIP. The archive
* itself is produced and streamed by the host (GET /api/session.export); this
* module only derives the download filename and triggers the browser save.
* @module
*/
/**
* Collapse an untrusted session id into one safe path/filename segment.
* Distinct ids may collapse onto one segment (impossible for the host-minted
* UUIDs, so no uniqueness suffix is kept).
* @param id - the raw session id.
* @returns a filesystem-safe single segment.
*/
function safeSessionIdSegment(id: string): string {
return id.replace(/[^A-Za-z0-9_-]/g, '_')
}
/**
* The export archive filename for one session (same convention the host's
* Content-Disposition uses).
* @param sessionId - the root session id.
* @returns the download filename.
*/
export function sessionLogZipFilename(sessionId: string): string {
return `dsh-session-${safeSessionIdSegment(sessionId)}.zip`
}
/**
* Trigger a browser download of a blob response.
* @param blob - the response body to save (passed straight through, no copy).
* @param filename - the download filename.
*/
export function downloadBlob(blob: Blob, filename: string): void {
const url = URL.createObjectURL(blob)
const anchor = document.createElement('a')
anchor.href = url
anchor.download = filename
anchor.click()
// Revoke one tick later: some browsers read the blob URL after click().
setTimeout(() => { URL.revokeObjectURL(url) }, 0)
}

35
packages/client/ui-trajectory/src/client/index.ts
View File

@@ -4,20 +4,24 @@
*/
import type { Context } from '@deepseek-ai/cordis'
import type { SessionId } from '@deepseek-ai/dsh-client-runtime/client'
// Type-only: pulls the locale plugin's Context merge (ctx.locale).
import type {} from '@deepseek-ai/dsh-client-locale/client'
// Type-only: the 'conversation.view' SlotMap row (declared by the slot's
// owning package) must be in the program for the register calls to type.
import type {} from '@deepseek-ai/dsh-client-ui-conversation/client'
import { createTrajectoryDurationStore } from './duration-store.ts'
import { TrajectoryView, type TrajectoryViewInjected } from './TrajectoryView.tsx'
import { downloadBlob, sessionLogZipFilename } from './export-log.ts'
import { en, NS, zh } from './locales.ts'
import { registerTrajectoryAssistantDefinition } from './trajectory-assistant-definition.ts'
import { registerTrajectoryCompactionDefinitions } from './trajectory-compaction-definition.ts'
import { registerTrajectoryMessageDefinitions } from './trajectory-message-definitions.ts'
import { registerTrajectoryRequestHeaderDefinition } from './trajectory-request-header-definition.ts'
import { registerTrajectoryConversationView } from './trajectory-snapshot-builder.ts'
import { registerTrajectoryToolDefinition } from './trajectory-tool-definition.ts'
import { TrajectoryView, type TrajectoryViewInjected } from './TrajectoryView.tsx'
/** Required services: the conversation slot, registries, and ordinary Session paging. */
export const inject = ['slots', 'conversationEvents', 'conversationViews', 'sessions']
/** Required services: the conversation slot, registries, ordinary Session paging, and the locale service. */
export const inject = ['slots', 'conversationEvents', 'conversationViews', 'sessions', 'locale']
/**
* Client plugin body: register the trajectory view tab. The registration
@@ -25,6 +29,11 @@ export const inject = ['slots', 'conversationEvents', 'conversationViews', 'sess
* @param ctx - client root context.
*/
export function apply(ctx: Context): void {
ctx.effect(() => ctx.locale.register(NS, { zh, en }), 'ui-trajectory: dictionaries')
// Registration-time text (the view tab label) reads through the bound
// translate as a thunk, so it follows the active locale without
// re-registration.
const t = ctx.locale.bind(NS)
const duration = createTrajectoryDurationStore()
registerTrajectoryMessageDefinitions(ctx)
registerTrajectoryRequestHeaderDefinition(ctx)
@@ -36,7 +45,8 @@ export function apply(ctx: Context): void {
name: 'conversation.view',
id: 'trajectory',
order: 10,
label: 'Trajectory',
locale: NS,
label: () => t('view.trajectory'),
inject: (sessionId: SessionId): TrajectoryViewInjected => {
const session = ctx.sessions.binding(sessionId)?.session
if (session === undefined) {
@@ -50,6 +60,23 @@ export function apply(ctx: Context): void {
return session.getSnapshot().views.get('trajectory') !== before
},
setActualDuration: (value) => { duration.set(value) },
exportLog: async () => {
// The host streams the ZIP (root + descendant artifacts verbatim)
// from GET /api/session.export; the browser downloads the response.
// A null origin (no-location Node contexts) falls back like the
// carrier's resolveBase so the URL stays valid.
const loc = (globalThis as { location?: { origin?: string } }).location
const origin = loc?.origin !== undefined && loc.origin !== 'null' ? loc.origin : 'http://dsh.internal'
const url = new URL('/api/session.export', origin)
url.searchParams.set('sessionId', sessionId)
url.searchParams.set('includeDescendants', 'true')
const response = await fetch(url)
if (!response.ok) {
const detail = await response.text().catch(() => '')
throw new Error(`Export failed: HTTP ${response.status}${detail === '' ? '' : ` ${detail}`}`)
}
downloadBlob(await response.blob(), sessionLogZipFilename(sessionId))
},
}
},
}, TrajectoryView))

76
packages/client/ui-trajectory/src/client/locales.ts Normal file
View File

@@ -0,0 +1,76 @@
/** `trajectory` namespace dictionaries (view tab label + toolbar strings). */
/** Dictionary namespace owned by this plugin. */
export const NS = 'trajectory'
/** The trajectory dictionary key set (the source of truth for both locales). */
export type TrajectoryKey =
| 'view.trajectory'
| 'toolbar.aria'
| 'toolbar.duration'
| 'toolbar.useActualDuration'
| 'toolbar.useEqualWidth'
| 'toolbar.actualTime'
| 'toolbar.turns'
| 'toolbar.expandTurns'
| 'toolbar.collapseTurns'
| 'toolbar.calls'
| 'toolbar.expandCalls'
| 'toolbar.collapseCalls'
| 'toolbar.export'
| 'toolbar.exportAria'
| 'toolbar.exporting'
| 'toolbar.exportTitle'
| 'toolbar.search'
| 'toolbar.searchPlaceholder'
declare module '@deepseek-ai/dsh-client-ui-slots' {
interface LocaleNamespaceMap {
/** The trajectory view tab label and toolbar strings. */
'trajectory': TrajectoryKey
}
}
/** Simplified Chinese dictionary (the key-set source of truth). */
export const zh: Record<TrajectoryKey, string> = {
'view.trajectory': '轨迹',
'toolbar.aria': '轨迹工具栏',
'toolbar.duration': 'Duration',
'toolbar.useActualDuration': 'Use actual duration',
'toolbar.useEqualWidth': 'Use equal-width operations',
'toolbar.actualTime': '实际时间',
'toolbar.turns': 'Turns',
'toolbar.expandTurns': 'Expand turns',
'toolbar.collapseTurns': 'Collapse turns',
'toolbar.calls': 'Calls',
'toolbar.expandCalls': 'Expand calls',
'toolbar.collapseCalls': 'Collapse calls',
'toolbar.export': 'Export',
'toolbar.exportAria': 'Export session log',
'toolbar.exporting': 'Exporting…',
'toolbar.exportTitle': 'Export session log (ZIP, includes subagents)',
'toolbar.search': '搜索轨迹',
'toolbar.searchPlaceholder': '搜索',
}
/** English dictionary. */
export const en: Record<TrajectoryKey, string> = {
'view.trajectory': 'Trajectory',
'toolbar.aria': 'Trajectory toolbar',
'toolbar.duration': 'Duration',
'toolbar.useActualDuration': 'Use actual duration',
'toolbar.useEqualWidth': 'Use equal-width operations',
'toolbar.actualTime': 'Actual time',
'toolbar.turns': 'Turns',
'toolbar.expandTurns': 'Expand turns',
'toolbar.collapseTurns': 'Collapse turns',
'toolbar.calls': 'Calls',
'toolbar.expandCalls': 'Expand calls',
'toolbar.collapseCalls': 'Collapse calls',
'toolbar.export': 'Export',
'toolbar.exportAria': 'Export session log',
'toolbar.exporting': 'Exporting…',
'toolbar.exportTitle': 'Export session log (ZIP, includes subagents)',
'toolbar.search': 'Search trajectory',
'toolbar.searchPlaceholder': 'Search',
}

12
packages/client/ui-trajectory/src/client/views.module.css
View File

@@ -13,6 +13,18 @@
background: var(--dsw-alias-bg-layer-1);
}
.exportError {
box-sizing: border-box;
flex: none;
width: 100%;
padding: 4px 10px;
border-bottom: 1px solid var(--dsw-alias-border-l2);
color: var(--dsw-alias-label-danger, var(--dsw-alias-label-primary));
background: var(--dsw-alias-bg-layer-2);
font: var(--dsw-font-xxs-12);
overflow-wrap: anywhere;
}
.ledger {
position: relative;
z-index: 0;

9
packages/client/ui-trajectory/tests/client-bundle.spec.ts
View File

@@ -64,7 +64,7 @@ describe('tsdown client artifact', () => {
expect(handoff.id).toBe(PLUGIN_ID)
expect(surface.apply).toBeTypeOf('function')
expect(surface.inject).toEqual([
'slots', 'conversationEvents', 'conversationViews', 'sessions',
'slots', 'conversationEvents', 'conversationViews', 'sessions', 'locale',
])
})
@@ -80,8 +80,13 @@ describe('tsdown client artifact', () => {
children: { 'conversation.view': { kind: 'list', scope: 'session' } },
}, (_p: { renderSlot?: unknown }) => null)
// Paging is session-owned; this registration-only probe never renders the
// entry, so the binding stays deliberately empty.
// entry, so the binding stays deliberately empty. The locale plugin backs
// the locale-aware view tab label (its settings scope needs a connection
// handle).
ctx.provide('sessions', { binding: () => undefined })
ctx.provide('connection', { api: { settings: {} }, isLoopback: false } as never)
const locale = await import('@deepseek-ai/dsh-client-locale/client')
ctx.plugin({ inject: [...locale.inject], apply: locale.apply })
const fiber = ctx.plugin(surface as { apply: (ctx: Context) => void })
await fiber.await()
const events = ctx.get('conversationEvents') as ConversationEventRegistry

24
packages/client/ui-trajectory/tests/export-log.spec.ts Normal file
View File

@@ -0,0 +1,24 @@
// @vitest-environment node
/**
* Session-log export filename derivation. The archive itself is produced and
* streamed by the host (GET /api/session.export); this package only derives
* the download filename and triggers the browser save.
*/
import { describe, expect, it } from 'vitest'
import { sessionLogZipFilename } from '../src/client/export-log.ts'
describe('sessionLogZipFilename', () => {
it('keeps safe session ids verbatim', () => {
expect(sessionLogZipFilename('session-abc_1-2')).toBe('dsh-session-session-abc_1-2.zip')
})
it('neutralizes unsafe id characters that could shape the filename', () => {
expect(sessionLogZipFilename('../evil')).toBe('dsh-session-___evil.zip')
expect(sessionLogZipFilename('a/b')).toBe('dsh-session-a_b.zip')
})
it('strips dots so a dot-only id cannot shape a dot segment', () => {
expect(sessionLogZipFilename('..')).toBe('dsh-session-__.zip')
})
})

61
packages/client/ui-trajectory/tests/toolbar.spec.tsx Normal file
View File

@@ -0,0 +1,61 @@
// @vitest-environment jsdom
/** Trajectory toolbar export button: click dispatch, in-flight disable, and error surfacing. */
import { afterEach, describe, expect, it, vi } from 'vitest'
import { cleanup, fireEvent, render, screen } from '@testing-library/react'
import type { LocaleKeysOf } from '@deepseek-ai/dsh-client-ui-slots'
import { TrajectoryToolbar, type TrajectoryToolbarProps } from '../src/client/TrajectoryToolbar.tsx'
import { zh, type TrajectoryKey } from '../src/client/locales.ts'
/** Test translator pinned to the Simplified Chinese dictionary. */
const zhT = (key: LocaleKeysOf<'trajectory'>): string => zh[key as TrajectoryKey] ?? key
afterEach(() => {
cleanup()
vi.restoreAllMocks()
})
function baseProps(overrides: Partial<TrajectoryToolbarProps> = {}): TrajectoryToolbarProps {
return {
actualDuration: false,
onActualDurationChange: vi.fn(),
actualTime: false,
onActualTimeChange: vi.fn(),
allTurnsCollapsed: false,
onToggleAllTurns: vi.fn(),
allAssistantsCollapsed: false,
onToggleAllAssistants: vi.fn(),
searchQuery: '',
onSearchQueryChange: vi.fn(),
exporting: false,
onExport: vi.fn(),
exportError: null,
t: zhT,
...overrides,
}
}
describe('TrajectoryToolbar export', () => {
it('renders the export button and dispatches the export callback on click', () => {
const onExport = vi.fn()
render(<TrajectoryToolbar {...baseProps({ onExport })} />)
const button = screen.getByRole('button', { name: 'Export session log' })
fireEvent.click(button)
expect(onExport).toHaveBeenCalledTimes(1)
})
it('disables the button while an export is in flight and blocks dispatch', () => {
const onExport = vi.fn()
render(<TrajectoryToolbar {...baseProps({ exporting: true, onExport })} />)
const button = screen.getByRole('button', { name: 'Export session log' }) as HTMLButtonElement
expect(button.disabled).toBe(true)
fireEvent.click(button)
expect(onExport).not.toHaveBeenCalled()
})
it('surfaces an export failure as the button title', () => {
render(<TrajectoryToolbar {...baseProps({ exportError: 'Export failed: internal boom' })} />)
const button = screen.getByRole('button', { name: 'Export session log' })
expect(button.title).toBe('Export failed: internal boom')
})
})

94
packages/client/ui-trajectory/tests/views.spec.tsx
View File

@@ -29,6 +29,9 @@ import {
} from '@deepseek-ai/dsh-client-ui-conversation/src/client/skeleton/ConversationSession.tsx'
import { createChatStore } from '@deepseek-ai/dsh-client-ui-conversation/src/client/stores.ts'
import { zh as conversationZh } from '@deepseek-ai/dsh-client-ui-conversation/src/client/locales.ts'
import { apply as localeApply, inject as localeInject } from '@deepseek-ai/dsh-client-locale/client'
import type { LocaleKeysOf } from '@deepseek-ai/dsh-client-ui-slots'
import { zh, type TrajectoryKey } from '../src/client/locales.ts'
import { apply, inject } from '@deepseek-ai/dsh-client-ui-trajectory/client'
import { apply as nodeApply } from '@deepseek-ai/dsh-client-ui-trajectory'
import type { TrajectoryTurnModel } from '../src/client/layout.ts'
@@ -132,6 +135,12 @@ function standaloneDuration(): Pick<
}
}
function standaloneExport(
onExport: () => Promise<void> = vi.fn(() => Promise.resolve()),
): Pick<ComponentProps<typeof TrajectoryView>, 'exportLog'> {
return { exportLog: onExport }
}
function fakeSession(nodes: ConversationSnapshot['nodes']) {
const store = createSnapshotStore(historySnapshot(nodes))
return { store, useSession: bindSnapshotSelector(store) }
@@ -153,14 +162,18 @@ function emptyWorkspaces() {
}
/** Standalone view props: the session-scope standard kit the outlet would bake. */
function standaloneProps(nodes: ConversationSnapshot['nodes']): ConvViewProps {
function standaloneProps(
nodes: ConversationSnapshot['nodes'],
): ConvViewProps & { t: (key: LocaleKeysOf<'trajectory'>) => string } {
return {
sessionId: SID,
useSession: fakeSession(nodes).useSession,
useSessions: emptySessions(),
useWorkspaces: emptyWorkspaces(),
useProjection: (() => undefined) as never,
} as unknown as ConvViewProps
// The locale seat the outlet would inject for the declared namespace.
t: (key: LocaleKeysOf<'trajectory'>) => zh[key as TrajectoryKey] ?? key,
} as unknown as ConvViewProps & { t: (key: LocaleKeysOf<'trajectory'>) => string }
}
/** Real-stack bench: root Context + real SlotsService ring + the plugin fiber. */
@@ -188,6 +201,10 @@ async function bench(snapshot = historySnapshot(NODES)) {
const chatBody = vi.fn(() => <div data-testid="chat-body" />)
slots.register(
{ name: 'conversation.view', id: 'chat', order: 0, label: 'Chat' } as never, chatBody as never)
// The locale plugin backs the locale-aware view tab label ('locale' in
// inject); its settings scope needs a connection handle.
ctx.provide('connection', { api: { settings: {} }, isLoopback: false } as never)
ctx.plugin({ inject: [...localeInject], apply: localeApply })
const fiber = ctx.plugin({ inject: [...inject], apply })
await fiber.await()
return { ctx, slots, fiber, loadOlder, sessionStore }
@@ -232,7 +249,9 @@ function mount(slots: SlotsService, nodes: ConversationSnapshot['nodes'] = NODES
return {
loadOlder: trajectory.loadOlder,
setActualDuration: trajectory.setActualDuration,
exportLog: trajectory.exportLog,
useDuration: bindSnapshotSelector(trajectory.hooks.duration),
t: (key: TrajectoryKey) => zh[key],
}
})()
: injected
@@ -352,7 +371,7 @@ describe('tab switching in ConversationRoot', () => {
expect(screen.queryByText(/turns ·/)).toBeNull()
expect(view.container.querySelectorAll('tr[data-turn-start="true"]')).toHaveLength(2)
expect(screen.queryByRole('columnheader')).toBeNull()
expect(screen.getByRole('toolbar', { name: 'Trajectory toolbar' })).toBeTruthy()
expect(screen.getByRole('toolbar', { name: '轨迹工具栏' })).toBeTruthy()
expect(screen.getByRole('region', { name: 'Trajectory timeline' })).toBeTruthy()
expect(view.container.querySelector('[data-conversation-composer-overlay]')).toBeTruthy()
fireEvent.click(screen.getByRole('button', { name: 'Collapse turns' }))
@@ -365,6 +384,17 @@ describe('tab switching in ConversationRoot', () => {
expect(b.loadOlder).not.toHaveBeenCalled()
})
it('labels the trajectory tab in the active locale', async () => {
const b = await bench()
const labelOf = () => tabsOf(b.slots).find(tab => tab.id === 'trajectory')?.label
expect(labelOf()).toBe('Trajectory')
const locale = b.ctx.get('locale') as { setLocale(id: string): void }
locale.setLocale('zh')
expect(labelOf()).toBe('轨迹')
locale.setLocale('en')
expect(labelOf()).toBe('Trajectory')
})
it('opens a local record inspector and switches payload tabs without opening chat details', async () => {
const b = await bench()
mount(b.slots)
@@ -553,7 +583,7 @@ describe('tab switching in ConversationRoot', () => {
const b = await bench(historySnapshot([]))
mount(b.slots)
fireEvent.click(screen.getByRole('tab', { name: 'Trajectory' }))
expect(screen.getByRole('toolbar', { name: 'Trajectory toolbar' })).toBeTruthy()
expect(screen.getByRole('toolbar', { name: '轨迹工具栏' })).toBeTruthy()
expect(screen.getByText('No timing data')).toBeTruthy()
expect(screen.getByRole<HTMLButtonElement>('button', {
name: 'Collapse turns',
@@ -1100,13 +1130,62 @@ describe('timeline projection', () => {
...standaloneProps([]),
...standaloneHistory(historySnapshot([])),
...standaloneDuration(),
...standaloneExport(),
},
))
expect(screen.getByRole('toolbar', { name: 'Trajectory toolbar' })).toBeTruthy()
expect(screen.getByRole('toolbar', { name: '轨迹工具栏' })).toBeTruthy()
expect(screen.queryByRole('row')).toBeNull()
})
})
describe('session log export', () => {
afterEach(() => {
vi.unstubAllGlobals()
Reflect.deleteProperty(URL, 'createObjectURL')
Reflect.deleteProperty(HTMLAnchorElement.prototype, 'click')
})
it('downloads the host-streamed ZIP with descendants on click', async () => {
// exportLog always fetches a URL instance, so the mock's shape stays narrow.
const fetchMock = vi.fn(async (input: URL) => {
expect(input.pathname).toBe('/api/session.export')
expect(input.searchParams.get('sessionId')).toBe(SID)
expect(input.searchParams.get('includeDescendants')).toBe('true')
return new Response('zip-bytes')
})
vi.stubGlobal('fetch', fetchMock)
const createObjectURL = vi.fn(() => 'blob:export')
URL.createObjectURL = createObjectURL
const clickAnchor = vi.fn()
HTMLAnchorElement.prototype.click = clickAnchor
const b = await bench(historySnapshot(NODES))
mount(b.slots)
fireEvent.click(screen.getByRole('tab', { name: 'Trajectory' }))
fireEvent.click(screen.getByRole('button', { name: 'Export session log' }))
await vi.waitFor(() => {
expect(fetchMock).toHaveBeenCalledOnce()
})
// The blob download lands a few microtasks after the fetch settles.
await vi.waitFor(() => {
expect(createObjectURL).toHaveBeenCalled()
})
expect(clickAnchor).toHaveBeenCalled()
})
it('surfaces the download failure in the visible alert bar', async () => {
vi.stubGlobal('fetch', vi.fn(async () => new Response('boom', { status: 404 })))
const b = await bench(historySnapshot(NODES))
mount(b.slots)
fireEvent.click(screen.getByRole('tab', { name: 'Trajectory' }))
fireEvent.click(screen.getByRole('button', { name: 'Export session log' }))
await vi.waitFor(() => {
const alert = screen.queryByRole('alert')
expect(alert).not.toBeNull()
expect(alert!.textContent).toContain('HTTP 404')
})
})
})
describe('TrajectoryView state', () => {
it('persists the duration preference through the runtime snapshot-store seam', () => {
const firstDuration = createTrajectoryDurationStore()
@@ -1117,6 +1196,7 @@ describe('TrajectoryView state', () => {
const first = render(
<TrajectoryView
{...commonProps}
{...standaloneExport()}
useDuration={bindSnapshotSelector(firstDuration)}
setActualDuration={(value) => { firstDuration.set(value) }}
/>,
@@ -1132,6 +1212,7 @@ describe('TrajectoryView state', () => {
render(
<TrajectoryView
{...commonProps}
{...standaloneExport()}
useDuration={bindSnapshotSelector(restoredDuration)}
setActualDuration={(value) => { restoredDuration.set(value) }}
/>,
@@ -1140,6 +1221,8 @@ describe('TrajectoryView state', () => {
.toBe('true')
})
it('keeps ledger and timeline selection on the same event after prepend', () => {
const older = {
kind: 'user', seq: 1, time: 1_000,
@@ -1154,6 +1237,7 @@ describe('TrajectoryView state', () => {
<TrajectoryView
{...standaloneProps([])}
{...standaloneDuration()}
{...standaloneExport()}
useSession={bindSnapshotSelector(store)}
loadOlder={vi.fn(() => Promise.resolve(false))}
/>,

3
packages/client/ui-trajectory/tsconfig.json
View File

@@ -11,6 +11,9 @@
{
"path": "../../../vendor/cordis"
},
{
"path": "../locale"
},
{
"path": "../ui-conversation"
},

10
packages/core/agent-tool-mode/src/index.ts
View File

@@ -5,8 +5,10 @@
* The tool registry itself stays on the host plane — the agent loop's
* scheduler, the API proxy's presenters, and every tool plugin are all its
* consumers, so it cannot move into a preset. What a preset CAN own is the
* presentation: `ctx.tools.presentAs()` declares it for the mounting agent
* alone, so a Code Mode agent runs beside native ones in one process.
* presentation: `ctx.tools.presentAs()` declares it for the mounting SCOPE,
* which is the preset's standing mount, so the declaration covers every agent
* joined to that preset and a Code Mode preset runs beside native ones in one
* process. One row per composition, not one per session.
*
* A code mode needs a TypeScript code runtime, which is a host-plane service
* ([`dsh-code-runtime-worker`](../../code-runtime/code-runtime-worker/README.md)).
@@ -50,8 +52,8 @@ export const Config: z<Config> = z.object({
})
/**
* Declare this agent's tool presentation.
* @param ctx - the mounting agent's scope context.
* Declare the tool presentation for every agent this composition covers.
* @param ctx - the mounting composition's scope context (a preset's standing scope).
* @param config - the selected presentation.
*/
export function apply(ctx: Context, config: Config): void {

4
packages/core/agent/README.i18n.yaml
View File

@@ -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/core/agent/README.md
README.md: 0fb65b94a3b311aa9f0df09d39dd937cba4cc7b4
README.zh.md: 44f67483343a98c280317793ece544bd0b984596
README.md: 61294df5cca1b03f9f158678f2992a6e4fbaaffd
README.zh.md: 5576a07330926cfd8fd5bd42c8a0351a375f035c

2
packages/core/agent/README.md
View File

@@ -58,6 +58,8 @@ Inbox live notifications are deliberately per-message and minimal: `agent/inbox/
Turn and step boundaries and the model token stream are durable `session/event` facts rather than mirrored `agent/*` notifications. Consumers read `turn/*`, `step/*`, and `assistant/chunk` from the session feed; tool policy and outcome observation belong to the complete pipeline documented by [`dsh-tools`](../tools/README.md).
`foldConsumedWork(events)` reads that feed back for the one question the turn sequence cannot answer alone: what became of the work a log consumed. It returns the latest `turn/end` that accounts for consumed work — a turn that entered a model step, or one that claimed inbox input and then failed, was stopped, or was rejected before reaching one — plus whether accepted work was later cancelled out of the inbox unrun. Both facts come from the log, so a cancellation reads the same whichever owner issued it. A no-step turn that took nothing, or emptied its claim and completed, describes no work and is skipped; a `blocked` end over claimed input is an account, because rejection discarded that input.
### Agent interface (`types.ts`)
The handle every plugin programs against:

2
packages/core/agent/README.zh.md
View File

@@ -58,6 +58,8 @@ inbox 的实时通知刻意采用逐消息的最小载荷：`agent/inbox/inserte
轮次和步骤边界以及模型 token 流是持久 `session/event` 事实，而不是镜像的 `agent/*` 通知。消费方从会话事件流读取 `turn/*`、`step/*` 和 `assistant/chunk`；工具策略与结果观测属于 [`dsh-tools`](../tools/README.md) 记录的完整流水线。
`foldConsumedWork(events)` 把这条事件流读回来，回答仅凭轮次序列无法回答的那个问题：一份日志消费掉的工作最终怎样了。它返回能够为已消费工作作出交代的最新 `turn/end`——即进入过模型 step 的轮次，或者认领了 inbox 输入、但在进入 step 之前失败、被停下或被拒绝的轮次——并额外给出「已接受的工作此后是否被从 inbox 中取消且从未运行」。两项事实都来自日志，因此无论由哪个所有者发起取消，读出来都一样。没有取走任何输入、或认领批次被改写清空后正常结束的无 step 轮次不描述工作，会被跳过；认领过输入、以 `blocked` 结束的轮次则是一份交代，因为拒绝把这些输入一并丢弃了。
### Agent 接口（`types.ts`）
每个插件面向的 handle：

108
packages/core/agent/src/consumed-work.ts Normal file
View File

@@ -0,0 +1,108 @@
/**
* How one agent log accounts for the work it consumed.
*
* The turn and step vocabulary alone cannot answer this. A turn that stops
* before its first step leaves a `turn/end` shaped exactly like the balanced
* no-op turns a rejection or an empty claim produces, so reading turns in
* isolation either credits cut-short work as finished or convicts every no-op.
* The missing fact is the inbox's own record: {@link Inbox} logs each mutation
* with `removedCount` and marks a cancellation `outcome: 'canceled'`, which
* separates a turn claiming its input from work being dropped unrun.
*
* @module @deepseek-ai/dsh-agent/consumed-work
*/
import type { SessionEvent, TurnEndReason } from '@deepseek-ai/dsh-session'
/** How one agent log accounts for the work it consumed. */
export interface ConsumedWork {
/**
* The latest closed turn that accounts for consumed work: one that entered a
* model step, or one that claimed inbox input and then failed, was stopped,
* or was rejected. Absent when no turn closed over any work.
*/
readonly end?: SessionEvent<'turn/end'>
/**
* Whether accepted work was cancelled out of the inbox, unrun, after that
* turn. This is the only account of input a cancellation took before any turn
* could open over it — no `turn/end` describes it.
*/
readonly droppedUnrun: boolean
}
/**
* Whether a turn that consumed input but never reached a step ends in a way
* that accounts for that input. Only a `completed` end does not: it had
* nothing left to run once its claim was rewritten away. A `blocked` end is
* that input's ending too — the pre-step rejection that produced it discarded
* the claimed messages, so the work it took will never run.
* @param reason - the turn's recorded ending.
* @returns whether the ending accounts for the input the turn took.
*/
function accountsForClaim(reason: TurnEndReason): boolean {
switch (reason.kind) {
case 'completed':
return false
case 'blocked':
case 'aborted':
case 'interrupted':
case 'error':
return true
/* v8 ignore next 4 -- unreachable: the one unnamed built-in, `max-tokens`, requires a step,
* so its turn short-circuits as stepped before this call, and `TurnEndReasonMap` is
* merge-extensible, so a backend-added variant cannot be listed; an unnameable ending over
* consumed input must not read as success. */
default:
return true
}
}
/**
* Fold one agent log, or an owned suffix of one, into its account of consumed
* work. Single pass, and every input is the log itself: no caller has to sample
* live state before cancelling, so a cancellation issued by anyone — the owner's
* teardown, an ancestor's interrupt, an unloading plugin — reads the same.
* @param events - the log, or an owned suffix, to fold.
* @returns the accounting turn when one closed, and whether work was dropped unrun after it.
*/
export function foldConsumedWork(events: readonly SessionEvent[]): ConsumedWork {
const stepped = new Set<number>()
const claimed = new Set<number>()
let open: number | undefined
let end: SessionEvent<'turn/end'> | undefined
let droppedUnrun = false
for (const event of events) {
switch (event.type) {
case 'turn/start':
open = event.data.turn
break
case 'step/start':
stepped.add(event.data.turn)
break
case 'agent/inbox/spliced': {
const { removedCount, outcome, inserted } = event.data
if (removedCount === undefined) break
// A replacement keeps the work pending under a new identity, so only a
// cancellation that leaves nothing behind drops it.
if (outcome === 'canceled') droppedUnrun ||= inserted.length === 0
// Claims are the loop's own step-boundary reads, always inside a turn.
else if (open !== undefined) claimed.add(open)
break
}
case 'turn/end': {
const { turn, reason } = event.data
open = undefined
if (stepped.delete(turn) || (claimed.delete(turn) && accountsForClaim(reason))) {
end = event
// Anything dropped before this turn closed is what its own ending
// reports; only a later drop is still unaccounted for.
droppedUnrun = false
}
break
}
default:
break
}
}
return { ...end === undefined ? {} : { end }, droppedUnrun }
}

1
packages/core/agent/src/index.ts
View File

@@ -18,6 +18,7 @@ import type { Agent, AgentOptions } from './runtime-types.ts'
export * from './runtime-types.ts'
export * from './types.ts'
export * from './inbox.ts'
export * from './consumed-work.ts'
export * from './model-selection.ts'
export { agentCarrier, agentEvents, assembleContextFor, emitAgentEvent } from './dispatch.ts'
export type { AgentEventDispatch, AgentSubjectEvent } from './dispatch.ts'

160
packages/core/agent/tests/consumed-work.spec.ts Normal file
View File

@@ -0,0 +1,160 @@
import { describe, expect, it } from 'vitest'
import { createUserMessage } from '@deepseek-ai/dsh-llm'
import { Session, SessionId } from '@deepseek-ai/dsh-session'
import type { TurnEndReason } from '@deepseek-ai/dsh-session'
import { foldConsumedWork } from '@deepseek-ai/dsh-agent'
/** One pending message, as the inbox records it. */
function message(text: string) {
return createUserMessage({ content: [{ type: 'text', text }], source: { kind: 'user' } })
}
/** Log an accepted message the way `Inbox.append()` does. */
function accept(session: Session, text: string): void {
session.append('agent/inbox/spliced', { target: 'next-turn', start: 0, inserted: [message(text)] })
}
/** Log the step-boundary read of one pending message, as `Inbox.claim()` does. */
function claim(session: Session): void {
session.append('agent/inbox/spliced', { target: 'next-turn', start: 0, removedCount: 1, inserted: [] })
}
/** Log a cancellation of one pending message, as `Inbox.clear()` does. */
function cancelPending(session: Session): void {
session.append('agent/inbox/spliced', {
target: 'next-turn', start: 0, removedCount: 1, inserted: [], outcome: 'canceled',
})
}
/** Run one whole turn that reached a model step. */
function steppedTurn(session: Session, turn: number, reason: TurnEndReason): void {
session.append('turn/start', { turn })
claim(session)
session.append('step/start', { turn, step: 1 })
session.append('step/end', { turn, step: 1 })
session.append('turn/end', { turn, reason })
}
describe('foldConsumedWork', () => {
it('reports nothing for a log that consumed no work', () => {
const session = Session.create(SessionId('empty'))
accept(session, 'queued')
expect(foldConsumedWork(session.events)).toEqual({ droppedUnrun: false })
})
it('reports the latest turn that entered a model step', () => {
const session = Session.create(SessionId('stepped'))
steppedTurn(session, 1, { kind: 'completed' })
steppedTurn(session, 2, { kind: 'max-tokens' })
expect(foldConsumedWork(session.events).end?.data)
.toEqual({ turn: 2, reason: { kind: 'max-tokens' } })
})
it('reports a turn that claimed its input and then failed before any step', () => {
const session = Session.create(SessionId('failed-claim'))
steppedTurn(session, 1, { kind: 'completed' })
// The step boundary runs the durability checkpoint and prompt assembly, so a
// turn can take its input and then fail without entering a step.
session.append('turn/start', { turn: 2 })
claim(session)
session.append('turn/end', { turn: 2, reason: { kind: 'error', error: { message: 'ENOSPC', code: 'UNKNOWN' } } })
expect(foldConsumedWork(session.events).end?.data.turn).toBe(2)
})
it('reports a turn that claimed its input and was then stopped before any step', () => {
const session = Session.create(SessionId('stopped-claim'))
steppedTurn(session, 1, { kind: 'completed' })
session.append('turn/start', { turn: 2 })
claim(session)
session.append('turn/end', { turn: 2, reason: { kind: 'aborted', reason: { kind: 'user' } } })
expect(foldConsumedWork(session.events).end?.data.turn).toBe(2)
})
it('ignores a turn stopped, failed, or rejected without taking any input', () => {
const session = Session.create(SessionId('no-claim'))
steppedTurn(session, 1, { kind: 'completed' })
session.append('turn/start', { turn: 2 })
session.append('turn/end', { turn: 2, reason: { kind: 'aborted', reason: { kind: 'parent' } } })
session.append('turn/start', { turn: 3 })
session.append('turn/end', { turn: 3, reason: { kind: 'error', error: { message: 'x', code: 'UNKNOWN' } } })
session.append('turn/start', { turn: 4 })
session.append('turn/end', { turn: 4, reason: { kind: 'blocked' } })
// None of these turns describes work: they opened, found nothing of their own, and closed.
expect(foldConsumedWork(session.events).end?.data.turn).toBe(1)
})
it('reports a turn whose claimed input a pre-step rejection discarded', () => {
const session = Session.create(SessionId('rejected-claim'))
steppedTurn(session, 1, { kind: 'completed' })
session.append('turn/start', { turn: 2 })
claim(session)
session.append('turn/end', { turn: 2, reason: { kind: 'blocked' } })
// Rejection does not retain the claimed messages, so the `blocked` end is
// the only account of input that will never run.
expect(foldConsumedWork(session.events).end?.data.turn).toBe(2)
})
it('ignores a claim its own turn emptied', () => {
const session = Session.create(SessionId('emptied-claim'))
steppedTurn(session, 1, { kind: 'completed' })
session.append('turn/start', { turn: 2 })
claim(session)
session.append('turn/end', { turn: 2, reason: { kind: 'completed' } })
// An emptied claim ran nothing and dropped nothing: a listener rewrote the
// batch away, which is not this log's account of the work.
expect(foldConsumedWork(session.events).end?.data.turn).toBe(1)
})
it('credits a claim with no open turn to no turn at all', () => {
const session = Session.create(SessionId('mid-turn-suffix'))
steppedTurn(session, 1, { kind: 'completed' })
// An owned suffix can begin inside a turn whose start it does not contain,
// so a claim may appear with no turn to attribute it to.
claim(session)
session.append('turn/end', { turn: 2, reason: { kind: 'aborted', reason: { kind: 'user' } } })
expect(foldConsumedWork(session.events).end?.data.turn).toBe(1)
})
it('reports work cancelled out of the inbox after the last accounting turn', () => {
const session = Session.create(SessionId('dropped'))
steppedTurn(session, 1, { kind: 'completed' })
accept(session, 'never runs')
cancelPending(session)
// No turn opened over it, so only the cancellation says the work was cut short.
expect(foldConsumedWork(session.events)).toEqual({
end: session.events.find(event => event.type === 'turn/end'),
droppedUnrun: true,
})
})
it('keeps a replacement pending rather than counting it as dropped', () => {
const session = Session.create(SessionId('replaced'))
steppedTurn(session, 1, { kind: 'completed' })
session.append('agent/inbox/spliced', {
target: 'next-turn', start: 0, removedCount: 1, inserted: [message('rewritten')], outcome: 'canceled',
})
expect(foldConsumedWork(session.events).droppedUnrun).toBe(false)
})
it('lets a later accounting turn absorb an earlier drop', () => {
const session = Session.create(SessionId('absorbed'))
steppedTurn(session, 1, { kind: 'completed' })
cancelPending(session)
steppedTurn(session, 2, { kind: 'completed' })
expect(foldConsumedWork(session.events)).toEqual({
end: session.events.findLast(event => event.type === 'turn/end'),
droppedUnrun: false,
})
})
})

21
packages/core/session/src/index.ts
View File

@@ -34,27 +34,6 @@ export { deriveEventMessage, foldSurface, isAppendSurfaceEvent, isReplacementSur
export { canonicalHeader, foldRequestHeader, headerEquals } from './request-header.ts'
export { KNOWN_SESSION_EVENT_TYPES } from './known-event-types.ts'
/**
* Find the latest closed turn that entered at least one model step, ignoring
* balanced no-step turns produced by rejection, empty input, or cancellation.
* @param events - session events, or an owned suffix, to inspect.
* @returns the latest matching turn end, or `undefined`.
*/
export function findLastMessageTurnEnd(
events: readonly SessionEvent[],
): SessionEvent<'turn/end'> | undefined {
const steppedTurns = new Set<number>()
let latest: SessionEvent<'turn/end'> | undefined
for (const event of events) {
if (event.type === 'step/start') {
steppedTurns.add(event.data.turn)
continue
}
if (event.type === 'turn/end' && steppedTurns.delete(event.data.turn)) latest = event
}
return latest
}
declare module '@deepseek-ai/cordis' {
interface Context {
sessions: SessionStore

17
packages/core/session/tests/session.spec.ts
View File

@@ -7,28 +7,11 @@ import SessionStore, {
Session,
SessionEvent,
SessionId,
findLastMessageTurnEnd,
snapshotSessionEvent,
} from '@deepseek-ai/dsh-session'
import type { CreateSessionOptions, SessionEventType, SessionHeader, SessionSurface, TodoItem } from '@deepseek-ai/dsh-session'
describe('Session', () => {
it('finds the latest closed turn that entered a model step', () => {
const session = Session.create(SessionId('last-message-turn'))
session.append('turn/start', { turn: 1 })
session.append('turn/end', { turn: 1, reason: { kind: 'blocked' } })
expect(findLastMessageTurnEnd(session.events)).toBeUndefined()
session.append('turn/start', { turn: 2 })
session.append('step/start', { turn: 2, step: 1 })
session.append('step/end', { turn: 2, step: 1 })
session.append('turn/end', { turn: 2, reason: { kind: 'max-tokens' } })
expect(findLastMessageTurnEnd(session.events)?.data)
.toEqual({ turn: 2, reason: { kind: 'max-tokens' } })
})
it('exposes one stable readonly surface view', () => {
const session = Session.create(SessionId('surface-view'))
const surface = session.surface

18
packages/core/tools/src/index.ts
View File

@@ -786,7 +786,7 @@ export class ToolRegistry extends Service {
scope => new ToolLayer(scope),
() => { this.ctx.emit('tools/change') },
)
/** Presentation for agents that declare none; {@link presentAs} shadows it per agent. */
/** Presentation for scopes that declare none; {@link presentAs} shadows it per scope. */
private readonly defaultMode: ToolPresentationMode
private readonly maxParallelSubCalls: number
/**
@@ -811,7 +811,7 @@ export class ToolRegistry extends Service {
/**
* The generated-SDK prompt section, registered globally by a code-mode
* deployment and per agent by {@link presentAs}.
* deployment and per scope by {@link presentAs}.
*
* The body regenerates from the CALLING scope, and renders empty for an
* agent presenting natively — an agent that opted out under a code-mode
@@ -880,12 +880,14 @@ export class ToolRegistry extends Service {
}
/**
* Present this agent's tools in `mode` instead of the deployment default.
* Present the calling scope's tools in `mode` instead of the deployment
* default. Nearest scope on the chain wins, so a preset's standing
* declaration covers every agent joined under it.
*
* Scoped only, and one declaration per agent: this is how an agent preset
* composes a Code Mode agent beside native ones in the same process, and a
* Scoped only, and one declaration per scope: this is how an agent preset
* composes Code Mode agents beside native ones in the same process, and a
* process-global override would be the `mode` config field instead.
* @param mode - the presentation this agent's model sees.
* @param mode - the presentation the covered agents' models see.
* @returns the exact disposer that restores the deployment default.
*/
presentAs(mode: ToolPresentationMode): () => void {
@@ -898,14 +900,14 @@ export class ToolRegistry extends Service {
ctx,
(layer) => {
if (layer.mode !== undefined) {
throw new Error(`tools.presentAs("${mode}") conflicts with "${layer.mode}" already declared for this agent; one composition selects one presentation`)
throw new Error(`tools.presentAs("${mode}") conflicts with "${layer.mode}" already declared for this scope; one composition selects one presentation`)
}
layer.mode = mode
return () => { layer.mode = undefined }
},
{ label: 'tools.presentAs()' },
)
// The SDK section is per agent for the same reason the mode is. Under a
// The SDK section is per scope for the same reason the mode is. Under a
// deployment that already defaults to a code mode this shadows the
// global registration with an identical body, which costs nothing and
// keeps one rule instead of a case analysis.

4
packages/host/apiproxy/README.i18n.yaml
View File

@@ -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/host/apiproxy/README.md
README.md: 2a27ab9f2cfcd4f12c32b815583b13f439b3eaac
README.zh.md: ba49ccff82bab1e677bad1495e48b8503564ae1d
README.md: 5fe19af8069766c56f8926ccef88dc1d9fb3c950
README.zh.md: bdb26a63832c1461b4e56798e64c1253a916118d

2
packages/host/apiproxy/README.md
View File

@@ -28,6 +28,8 @@ Question responses are validated against their pending request before the first
`session.history`'s tail page (`beforeSeq` absent) additionally carries an optional `projections` block — the watermark snapshot of every unit registered on `ctx.sessionProjections` (`@deepseek-ai/dsh-session-projection`), with `asOfSeq` = the last event seq the values reflect (`-1` on an empty log). The gateway also subscribes to the registry's change feed and mints a `session/projection` mux frame per changed unit (`{sessionId, key, value, seq}` — live push state, never logged; clients hold one generic per-session value store under higher-seq-wins). The carrier holds zero domain knowledge (each value passed its unit's own schema inside the registry; the wire schemas keep `values`/`value` wide); loadOlder pages never carry the block, and a composition without the registry serves histories without either surface.
Session-log export is a host-only download surface, not an RPC: `GET /api/session.export?sessionId=…&includeDescendants=true` streams a ZIP whose files are each session's stored artifact text verbatim (the persistence backend's `readRaw` — exact durable bytes decoded from the physical encoding, never a reconstruction from parsed events), root under its original base name plus each subagent descendant under `subagents/<id>/`, and every image any included log references under `media/<attachmentId>.<ext>` (read and verified from the attachment store; a shared image appears once). Compression runs on the host with fflate's streaming Zip API, so the response is chunked as it is produced and the host never holds the whole archive in one buffer, and production yields whenever the response queue fills, so a slow consumer bounds the accumulation (fflate's callback is synchronous — the drain point is the only backpressure). It requires the persistence, session-query, and attachment services: a deployment without any answers 500, a missing root session 404, and a descendant without a stored artifact or a referenced image that cannot be read fails the stream (fail-loud, never silent under-export). The carrier mounts the endpoint; `ApiProxy.downloads.sessionLog` implements it.
Session titles ride the generic projection pair like every other domain — the history-tail `projections` block plus `session/projection` frames under the `title` key. Titles do not join `session.list`; cold sessions remain metadata-only there until opening or resuming attaches their logs. `session.rename` accepts an explicit user title (resuming a cold session first), delegating to `ctx.sessionTitle.rename` — the accepted `session/title` event pins the title against automatic regeneration — and returns the normalized title plus its event seq so a client settles its `title` projection cell ahead of the push frame; a title that normalizes to empty returns `title-invalid`.
`session.fork` maps an optional event anchor to the first `turn/end` at or after it, letting a message action include that message's whole turn. An omitted or past-end anchor selects the last completed turn; an in-log anchor whose turn remains open returns `fork-unavailable` rather than clipping backward. The published child inherits the source's seeded history, cwd, latest logged `ModelSelection`, and lineage before joining the source Workspace. If Workspace attachment fails, `workspace-attach-failed` carries the already-published child id so clients can reconcile it. The [SessionStore fork decision](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md) records why the anchor maps to that `turn/end`.

2
packages/host/apiproxy/README.zh.md
View File

@@ -28,6 +28,8 @@ Settings 分节中的 `reasoningEffort` 在 agent-default-model 插件配置中
`session.history` 的尾页（不带 `beforeSeq`）额外携带一个可选的 `projections` 块——`ctx.sessionProjections`（`@deepseek-ai/dsh-session-projection`）上每个已注册单元的水位线快照，`asOfSeq` = 这些值共同反映到的最后一个事件 seq（空日志为 `-1`）。网关还订阅注册表的变更流，为每个状态发生变化的单元生成一个 `session/projection` mux 帧（`{sessionId, key, value, seq}`——实时推送状态，绝不入日志；客户端按 seq 高者胜维护一个按会话的通用值仓）。载体不持有任何领域知识（每个值在注册表内部已过其单元自己的 schema；协议 schema 对 `values`/`value` 保持宽松）；loadOlder 页永不携带该块，未装注册表的组合则两个面都不提供。
会话日志导出是宿主侧的下载面，不是 RPC：`GET /api/session.export?sessionId=…&includeDescendants=true` 流式返回一个 ZIP，其中每个文件都是会话存储工件的逐字原文（持久化后端的 `readRaw`——按物理编码解码的确切持久化字节，绝非从解析后事件重建），根会话放在其原始基础文件名下，每个子代理后代放在 `subagents/<id>/` 下，每个被任何包含的日志引用的图片放在 `media/<attachmentId>.<ext>` 下（从附件存储读取并校验；共享图片只出现一次）。压缩在宿主侧用 fflate 的流式 Zip API 完成，响应边生成边分块写出，宿主从不把整个归档放进单个缓冲区，且每当响应队列填满时生产会让出，慢消费者因此只产生有界的积压（fflate 的回调是同步的——让出点是唯一的背压手段）。它要求同时挂载持久化、session-query 与附件服务：任一缺失应答 500，根会话缺失应答 404，后代缺少存储工件或引用的图片无法读取则整个流失败（fail-loud，绝不静默少导出）。端点由传输层挂载，`ApiProxy.downloads.sessionLog` 实现它。
会话标题与其他所有领域一样搭乘这对通用投影机制——历史尾页的 `projections` 块外加 `title` 键下的 `session/projection` 帧。标题不会加入 `session.list`；冷会话在其中仍只有元数据，直到打开或恢复操作附加其日志。`session.rename` 接受用户显式标题（冷会话先恢复），委托给 `ctx.sessionTitle.rename`——被接受的 `session/title` 事件将标题钉住、不再被自动生成覆盖——并返回规范化后的标题及其事件 seq，让 client 在推送帧到达前就结算自己的 `title` 投影格；规范化后为空的标题返回 `title-invalid`。
`session.fork` 将可选事件锚点映射到该锚点处或其后的首个 `turn/end`，使消息操作可包含该消息所在的完整轮次。锚点省略或超过末尾时，选择最后一个已完成轮次；若锚点已在日志中，而其所在轮次仍开放，则返回 `fork-unavailable`，不会向较早位置裁剪。发布后的子会话会先继承源会话的种子历史、cwd、日志中最新的 `ModelSelection` 及谱系，再加入源 Workspace。如果附加到 Workspace 失败，`workspace-attach-failed` 会携带已发布的子会话 id，供客户端对账。[SessionStore fork 决策](../../../.agents/notes/implemented/feature/2026-06-30-session-store-fork-api.md)记录了为何锚点要映射到该 `turn/end`。

1
packages/host/apiproxy/package.json
View File

@@ -71,6 +71,7 @@
"@deepseek-ai/dsh-user-interaction": "workspace:^",
"@deepseek-ai/dsh-workspace": "workspace:^",
"@deepseek-ai/schemastery": "workspace:^",
"fflate": "^0.8.2",
"zod": "^4.4.3"
},
"peerDependencies": {

141
packages/host/apiproxy/src/api-proxy.ts
View File

@@ -42,6 +42,13 @@ import type {
QueuedInboxItem, SessionSummary, SettingsNamespaceView, SubagentAddress, TaskView, ToolEventView,
WorkspaceId, WorkspaceView,
} from './api/index.ts'
import {
sessionLogExportDeps,
sessionLogZipFilename,
streamSessionLogZip,
type SessionLogExportReady,
} from './session-export.ts'
import type { SessionRawArtifact } from '@deepseek-ai/dsh-session-persistence'
import {
SESSION_SEARCH_RESULT_LIMIT,
SESSION_SEARCH_SNIPPET_MAX_CODE_POINTS,
@@ -705,6 +712,16 @@ function historyPage(
* registry). An absent registry means the deployment has no projection seam:
* the whole block is absent and clients treat every key as capability-absent.
*/
/**
* Which session a transcript read is served from. An attached session is the
* live object and keeps appending, so its events and projection baseline are
* read together in one synchronous step; a detached one is already a frozen
* inspection.
*/
type HistorySource =
| { readonly kind: 'attached'; readonly session: Session }
| { readonly kind: 'detached'; readonly header: SessionHeader; readonly events: SessionEvent[] }
function projectionsFor(ctx: Context, session: Session): SessionProjectionsBlock | undefined {
const registry = ctx.get('sessionProjections')
if (registry === undefined) return undefined
@@ -1348,24 +1365,55 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
return undefined
}
/** Read one transcript cut and optional projection baseline without acquiring an Agent owner. */
async function historyStateFor(
sessionId: SessionId,
includeProjections: boolean,
): Promise<{ header: SessionHeader; events: SessionEvent[]; projections?: SessionProjectionsBlock }> {
/**
* Resolve which session one transcript read is served from, without
* acquiring an Agent owner. This is the read's only asynchronous step
* besides ensuring the composition; {@link historyCutOf} takes the cut.
* @param sessionId - the transcript being read.
* @returns the attached session, or the inspected detached header and events.
* @throws {@link ApiRemoteSessionNotFound} when no project-backed session has that identity.
*/
async function historySourceFor(sessionId: SessionId): Promise<HistorySource> {
const attached = ctx.sessions.get(sessionId)
if (attached !== undefined) {
const events = [...attached.events]
const projections = includeProjections ? projectionsFor(ctx, attached) : undefined
return { header: attached.header, events, ...projections === undefined ? {} : { projections } }
}
if (attached !== undefined) return { kind: 'attached', session: attached }
const inspected = await inspectServable(sessionId)
const projections = includeProjections ? detachedProjectionsFor(ctx, inspected.events) : undefined
return {
header: inspected.meta,
events: inspected.events,
...projections === undefined ? {} : { projections },
return { kind: 'detached', header: inspected.meta, events: inspected.events }
}
/**
* The header and events {@link presenterScopeFor} reads to decide which
* composition a transcript ran under.
* @param source - the live or detached session this read is served from.
* @returns that session's creation header and its events.
*/
function sourceSession(source: HistorySource): PresetBearingSession {
if (source.kind === 'detached') return { header: source.header, events: source.events }
return { header: source.session.header, events: source.session.events }
}
/**
* One transcript cut: the events and the projection baseline that describe
* the SAME log position.
*
* Synchronous, and the two reads sit next to each other, because an attached
* session keeps appending: an `await` between them would serve events cut at
* N beside a baseline folded to N+1, which is one response describing two
* moments. The caller does its awaiting before this call.
* @param source - the live or detached session this read is served from.
* @param includeProjections - whether the caller asked for the baseline (a tail page does).
* @returns the events and, when asked, the baseline for that same position.
*/
function historyCutOf(
source: HistorySource,
includeProjections: boolean,
): { events: SessionEvent[]; projections?: SessionProjectionsBlock } {
if (source.kind === 'detached') {
const projections = includeProjections ? detachedProjectionsFor(ctx, source.events) : undefined
return { events: source.events, ...projections === undefined ? {} : { projections } }
}
const events = [...source.session.events]
const projections = includeProjections ? projectionsFor(ctx, source.session) : undefined
return { events, ...projections === undefined ? {} : { projections } }
}
/**
@@ -2025,9 +2073,22 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
async history(request) {
const { sessionId, beforeSeq, maxMessages } = request.payload
let state: { header: SessionHeader; events: SessionEvent[]; projections?: SessionProjectionsBlock }
try {
state = await historyStateFor(sessionId, beforeSeq === undefined)
const source = await historySourceFor(sessionId)
// Both awaits happen BEFORE the cut. Ensuring the recorded
// composition's standing mount is what registers its projection
// units, so a first cold read would otherwise serve a baseline
// missing every preset-owned key; and an attached session keeps
// appending, so awaiting between the two reads would pair events cut
// at N with a baseline folded to N+1.
const scope = await presenterScopeFor(sessionId, sourceSession(source))
const cut = historyCutOf(source, beforeSeq === undefined)
const page = historyPage(ctx, cut.events, beforeSeq, maxMessages, scope)
return ok(request, {
events: page.events,
hasMore: page.hasMore,
...cut.projections === undefined ? {} : { projections: cut.projections },
})
} catch (error: unknown) {
if (error instanceof SessionNotFound) {
return err(request, { code: 'session-not-found', message: error.message, details: { sessionId } })
@@ -2038,12 +2099,6 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
details: {},
})
}
const page = historyPage(ctx, state.events, beforeSeq, maxMessages, await presenterScopeFor(sessionId, state))
return ok(request, {
events: page.events,
hasMore: page.hasMore,
...state.projections === undefined ? {} : { projections: state.projections },
})
},
async models(request) {
@@ -3422,6 +3477,46 @@ export function createApiProxy(ctx: Context, defaults: ApiProxyDefaults): ApiPro
},
},
downloads: {
async sessionLog(request, signal) {
// Clean error path first: missing services answer 500 and a missing
// root artifact 404 before any zip byte is produced. The root content
// read here is reused as the first zip entry, so nothing is read twice.
const deps = sessionLogExportDeps(ctx)
if (deps.sessionQuery === undefined || deps.sessionPersistence === undefined || deps.attachments === undefined) {
return new Response(
'session log export is unavailable: missing session-query, session-persistence, or attachments service',
{ status: 500 },
)
}
const ready: SessionLogExportReady = {
sessionQuery: deps.sessionQuery,
sessionPersistence: deps.sessionPersistence,
attachments: deps.attachments,
}
let root: SessionRawArtifact | undefined
try {
root = await deps.sessionPersistence.readRaw(request.sessionId, signal)
} catch {
// Backend read failure: answer 500 without echoing the error, which
// may carry absolute host paths into the browser error bar.
return new Response('session log export failed to read the stored artifact', { status: 500 })
}
if (root === undefined) {
return new Response('session not found', { status: 404 })
}
return new Response(
streamSessionLogZip(ready, root, request.sessionId, request.includeDescendants === true, signal),
{
headers: {
'content-type': 'application/zip',
'content-disposition': `attachment; filename="${sessionLogZipFilename(request.sessionId)}"`,
},
},
)
},
},
respond(message: ClientResponse): Promise<RpcReceipt> {
// Route by the echoed rpcId (the wire correlation): approvals first,
// then questions — the two registries share one id space of UUIDs.

26
packages/host/apiproxy/src/api/downloads.schema.ts Normal file
View File

@@ -0,0 +1,26 @@
/**
* downloads domain zod schemas. The GET download surface has no wire
* envelope: the request arrives as query parameters (all strings), so its
* request schema parses the raw query-parameter object into the method's
* exact request shape. SessionId brand cast point: sessionIdSchema, and only
* there (hosted in sessions.schema like every other cast).
*/
import { z } from 'zod'
import type { DownloadsApi } from './downloads.ts'
import { sessionIdSchema } from './sessions.schema.ts'
/**
* session.export query params → the sessionLog request. `includeDescendants`
* accepts exactly `true`/`false`/absent; any other value is rejected (400) so
* a misspelled flag cannot silently under-export.
*/
export const sessionLogQuerySchema = z
.object({
sessionId: sessionIdSchema,
includeDescendants: z.union([z.literal('true'), z.literal('false')]).optional(),
})
.transform(query => ({
sessionId: query.sessionId,
...(query.includeDescendants === 'true' ? { includeDescendants: true } : {}),
})) satisfies z.ZodType<Parameters<DownloadsApi['sessionLog']>[0]>

25
packages/host/apiproxy/src/api/downloads.ts Normal file
View File

@@ -0,0 +1,25 @@
/**
* downloads domain contract: host-only download surfaces — the GET-download
* channel family, the mirror of the SSE-stream `events` domain. No wire
* envelope: the carrier's GET routes answer these directly, and the browser
* `IApiClient` never exposes them.
*/
import type { SessionId } from '@deepseek-ai/dsh-session/types'
/** Host-only download surfaces (no wire envelope; absent from IApiClient). */
export interface DownloadsApi {
/**
* Stream one session-log ZIP — the root artifact verbatim plus each subagent
* descendant's — as an attachment response. The carrier's GET route answers
* this directly; the browser never calls it.
* @param request - the root session id and whether to include descendants.
* @param signal - cancellation for the underlying reads.
* @returns the ZIP attachment response; missing services answer 500 and a
* missing root session 404 before any byte is produced.
*/
sessionLog(
request: { sessionId: SessionId; includeDescendants?: boolean },
signal: AbortSignal,
): Promise<Response>
}

9
packages/host/apiproxy/src/api/index.ts
View File

@@ -16,6 +16,7 @@ import type { GoalsApi } from './goals.ts'
import type { SettingsApi } from './settings.ts'
import type { CredentialsApi } from './credentials.ts'
import type { LlmApi } from './llm.ts'
import type { DownloadsApi } from './downloads.ts'
import type { ClientResponse, RpcReceipt } from './rpc.ts'
/** Root interface of the unified API surface. New client-request domain = one new file pair + one field here + one map row. */
@@ -32,6 +33,8 @@ export interface ApiProxy {
settings: SettingsApi
credentials: CredentialsApi
llm: LlmApi
/** Host-only download surfaces (GET, no wire envelope); absent from IApiClient. */
downloads: DownloadsApi
/** Response entry for server-requests (client-response, echoing their rpcId); not a domain method (four-quadrant model). */
respond(message: ClientResponse): Promise<RpcReceipt>
}
@@ -39,9 +42,8 @@ export interface ApiProxy {
// ---- Domain interfaces and payload entities ----
export type {
HistoryEntry, ModelCatalogFailure, ModelCatalogModel, ModelProviderGroup, ModelReasoning,
ModelReasoningEffort, ModelSelection, PromptContentPart, QueueAction, SessionModels, SessionProjectionsBlock,
SessionSearchItem,
SessionsApi, SessionSummary,
ModelReasoningEffort, ModelSelection, PromptContentPart, QueueAction, SessionModels,
SessionProjectionsBlock, SessionSearchItem, SessionsApi, SessionSummary,
} from './sessions.ts'
export type { DirectoryEntry, DirectoryListing, HostApi } from './host.ts'
export type {
@@ -58,6 +60,7 @@ export type { GoalsApi, GoalId, GoalRef } from './goals.ts'
export type { SettingsApi, SettingsNamespaceView, SettingsPathOpView, SettingsSecretView } from './settings.ts'
export type { CredentialsApi, CredentialView } from './credentials.ts'
export type { ConfigurableProviderView, DiscoveredModelView, LlmApi } from './llm.ts'
export type { DownloadsApi } from './downloads.ts'
export type { ApprovalResponsePayload } from './approvals.ts'
export type { QuestionResponsePayload } from './questions.ts'

12
packages/host/apiproxy/src/fetch/handler.ts
View File

@@ -9,6 +9,7 @@
import { randomUUID } from 'node:crypto'
import type { z } from 'zod'
import type { ApiProxy, MuxFrame, HostFrame } from '../api/index.ts'
import { sessionLogQuerySchema } from '../api/downloads.schema.ts'
import type { RequestPayload, ResponseValue, RpcMethodMap } from '../api/rpc-map.ts'
import type { ClientRequest, RpcError, RpcRequest, RpcResponse, ServerRequest, ServerResponse } from '../api/rpc.ts'
import { RpcId } from '../api/rpc.ts'
@@ -249,12 +250,23 @@ export function toFetchHandler(api: ApiProxy): { fetch: typeof fetch } {
const url = new URL(req.url)
const path = url.pathname
// No-envelope GET channel surface (SSE streams + host-only download):
// physical routes that answer directly, without a wire envelope.
if (path === '/api/events.mux' && req.method === 'GET') {
return sseResponse(api.events.mux({ rpcId: RpcId(randomUUID()), payload: {} }, req.signal))
}
if (path === '/api/events.host' && req.method === 'GET') {
return sseResponse(api.events.host({ rpcId: RpcId(randomUUID()), payload: {} }, req.signal))
}
if (path === '/api/session.export' && req.method === 'GET') {
// Query params are a different boundary from the POST envelope, but
// the request still casts its brands only through the domain schema.
const parsed = sessionLogQuerySchema.safeParse(Object.fromEntries(url.searchParams))
if (!parsed.success) {
return new Response('missing or invalid sessionId query parameter', { status: 400 })
}
return api.downloads.sessionLog(parsed.data, req.signal)
}
if (req.method !== 'POST' || !path.startsWith('/api/')) {
return new Response('not found', { status: 404 })

2
packages/host/apiproxy/src/index.ts
View File

@@ -72,6 +72,7 @@ export class ApiProxyService extends Service implements ApiProxy {
readonly credentials: ApiProxy['credentials']
readonly llm: ApiProxy['llm']
readonly events: ApiProxy['events']
readonly downloads: ApiProxy['downloads']
readonly respond: ApiProxy['respond']
constructor(ctx: Context, config: Config) {
@@ -94,6 +95,7 @@ export class ApiProxyService extends Service implements ApiProxy {
this.credentials = api.credentials
this.llm = api.llm
this.events = api.events
this.downloads = api.downloads
// createApiProxy returns closures (no `this` capture), so the bind is
// behavior-neutral.
this.respond = api.respond.bind(api)

357
packages/host/apiproxy/src/session-export.ts Normal file
View File

@@ -0,0 +1,357 @@
/**
* Host-side session-log download: streams one ZIP archive whose files are the
* sessions' stored artifact text verbatim plus every referenced media object.
* The root artifact sits under its original base name (`session.jsonl`); each
* subagent descendant under `subagents/<id>/<filename>`; each image referenced
* by any included log under `media/<attachmentId>.<ext>` (content-addressed,
* so one archive never duplicates a shared image). No manifest is written —
* every file is byte-identical to the backend's durable artifact or attachment
* store and self-describing through its own header line or media type.
* Compression runs on the host with fflate's streaming Zip API, so the archive
* bytes are produced incrementally and the host never holds the whole archive
* in one buffer; production yields to the consumer whenever the response queue
* fills past its high-water mark, so a slow consumer bounds the accumulation
* instead of piling up the whole archive (fflate's callback is synchronous —
* this drain point is the only backpressure available).
* @module
*/
import { Zip, ZipDeflate } from 'fflate'
import type { Context } from '@deepseek-ai/cordis'
import type { AttachmentStore, ImageAttachmentRef } from '@deepseek-ai/dsh-attachment'
import type { SessionLineageNode, SessionQueryService } from '@deepseek-ai/dsh-session-query'
import type { SessionId } from '@deepseek-ai/dsh-session'
import type { SessionPersistence, SessionRawArtifact } from '@deepseek-ai/dsh-session-persistence'
/** The services a session-log export needs (absent → the export is unavailable). */
export interface SessionLogExportDeps {
readonly sessionQuery: SessionQueryService | undefined
readonly sessionPersistence: SessionPersistence | undefined
readonly attachments: AttachmentStore | undefined
}
/** The export services narrowed to the mounted ones streaming actually reads. */
export interface SessionLogExportReady {
readonly sessionQuery: SessionQueryService
readonly sessionPersistence: SessionPersistence
readonly attachments: AttachmentStore
}
/**
* Resolve the persistence, session-query, and attachment services a log export needs.
* @param ctx - the composed host context.
* @returns the export services (absent when the deployment does not mount them).
*/
export function sessionLogExportDeps(ctx: Context): SessionLogExportDeps {
return {
sessionQuery: ctx.get('sessionQuery'),
sessionPersistence: ctx.get('sessionPersistence'),
attachments: ctx.get('attachments'),
}
}
/** One exported file: a stored artifact text or one referenced media object. */
export type SessionLogZipEntry =
| { readonly path: string; readonly content: string }
| { readonly path: string; readonly data: Uint8Array }
/** Zip extension for each accepted raster media type. */
const MEDIA_TYPE_EXTENSIONS: Record<ImageAttachmentRef['mediaType'], string> = {
'image/png': 'png',
'image/jpeg': 'jpg',
'image/webp': 'webp',
'image/gif': 'gif',
}
/**
* The zip path for one media object: content-addressed by the opaque
* attachment id so shared images land once and the id in the log maps back to
* the archive entry without a manifest.
* @param ref - the durable reference from a session log.
* @returns the archive path.
*/
function mediaEntryPath(ref: ImageAttachmentRef): string {
return `media/${String(ref.attachmentId)}.${MEDIA_TYPE_EXTENSIONS[ref.mediaType]}`
}
/**
* Collect every image reference inside one content array, descending into
* nested tool results the way the live attachment route does.
* @param content - an event content array (or nested tool-result content).
* @param refs - the dedupe map being filled (keyed by attachment id).
*/
function collectImageRefs(content: unknown, refs: Map<string, ImageAttachmentRef>): void {
if (!Array.isArray(content)) return
const pending: unknown[] = []
for (const item of content) pending.push(item)
while (pending.length > 0) {
const value = pending.pop()
if (typeof value !== 'object' || value === null || Array.isArray(value)) continue
const block = value as { type?: unknown; attachment?: unknown; content?: unknown }
if (block.type === 'image' && typeof block.attachment === 'object' && block.attachment !== null) {
const ref = block.attachment as ImageAttachmentRef
refs.set(String(ref.attachmentId), ref)
}
if (Array.isArray(block.content)) {
for (const item of block.content) pending.push(item)
}
}
}
/**
* Collect every image reference one session event carries, across the same
* carriers the live attachment route scans (direct content, message content,
* inserted messages, and completed assistant chunk blocks).
* @param event - one parsed JSONL event object.
* @param refs - the dedupe map being filled (keyed by attachment id).
*/
function collectEventImageRefs(event: unknown, refs: Map<string, ImageAttachmentRef>): void {
const data = (event as { data?: unknown }).data
if (typeof data !== 'object' || data === null) return
const carrier = data as {
content?: unknown
message?: { content?: unknown }
inserted?: Array<{ content?: unknown }>
chunk?: { type?: unknown; block?: unknown }
}
collectImageRefs(carrier.content, refs)
if (carrier.message !== undefined) collectImageRefs(carrier.message.content, refs)
if (carrier.inserted !== undefined) {
for (const message of carrier.inserted) collectImageRefs(message.content, refs)
}
if (carrier.chunk?.type === 'block-end') collectImageRefs([carrier.chunk.block], refs)
}
/**
* Collect the distinct media references one stored artifact text names.
* Lines that fail to parse cannot reference media and are skipped (the
* artifact text itself is exported verbatim regardless).
* @param content - the stored artifact text.
* @returns the dedupe map keyed by attachment id.
*/
function imageRefsInArtifact(content: string): Map<string, ImageAttachmentRef> {
const refs = new Map<string, ImageAttachmentRef>()
for (const line of content.split('\n')) {
if (line === '') continue
let event: unknown
try {
event = JSON.parse(line)
} catch {
continue
}
collectEventImageRefs(event, refs)
}
return refs
}
/**
* One safe zip path segment from an untrusted session id. Session ids are
* host-controlled, but the brand allows any non-empty string, so `../`, dot
* segments, and separator characters are neutralized before they can shape
* archive entries. Distinct ids may collapse onto one segment (id collision
* is impossible for the host-minted UUIDs, so no uniqueness suffix is kept).
* @param id - the raw session id.
* @returns a filesystem-safe single path segment.
*/
function safeSessionIdSegment(id: string): string {
return id.replace(/[^A-Za-z0-9_-]/g, '_')
}
/**
* The export archive filename for one root session.
* @param sessionId - the root session id (sanitized to one safe path segment).
* @returns the attachment filename for the session's export archive.
*/
export function sessionLogZipFilename(sessionId: string): string {
return `dsh-session-${safeSessionIdSegment(sessionId)}.zip`
}
/**
* Yield the export entries in zip order: the preloaded root artifact first,
* then every subagent descendant in lineage order (each read from the
* persistence backend right before it is yielded and dropped after the
* consumer moves on), then every distinct media object referenced by any of
* the included logs (read and verified from the attachment store, one archive
* entry per attachment id). The host holds at most one descendant's artifact
* text and one media object at a time beyond the root.
* @param deps - the mounted export services (the caller answered 500 before this runs).
* @param root - the already-read root artifact (read by the caller so the
* missing-session path can answer cleanly before streaming starts).
* @param sessionId - the root session id.
* @param includeDescendants - whether to include every subagent descendant.
* @param signal - optional cancellation for read work.
* @returns the export entries in zip order.
*/
export async function* sessionLogZipEntries(
deps: SessionLogExportReady,
root: SessionRawArtifact,
sessionId: SessionId,
includeDescendants: boolean,
signal?: AbortSignal,
): AsyncGenerator<SessionLogZipEntry> {
const media = new Map<string, ImageAttachmentRef>()
const rememberMedia = (content: string): void => {
for (const [id, ref] of imageRefsInArtifact(content)) media.set(id, ref)
}
rememberMedia(root.content)
yield { path: root.filename, content: root.content }
if (includeDescendants) {
const seen = new Set<SessionId>([sessionId])
const collect = async function* (
nodes: readonly SessionLineageNode[],
): AsyncGenerator<SessionLogZipEntry> {
for (const node of nodes) {
signal?.throwIfAborted()
const id = node.session.header.id
if (seen.has(id)) continue
seen.add(id)
const raw = await deps.sessionPersistence.readRaw(id)
if (raw === undefined) {
throw new Error(`subagent "${id}" has no stored log artifact`)
}
rememberMedia(raw.content)
yield {
path: `subagents/${safeSessionIdSegment(id)}/${raw.filename}`,
content: raw.content,
}
yield* collect(node.descendants)
}
}
const lineage = await deps.sessionQuery.traceSession(sessionId)
yield* collect(lineage.descendants)
}
for (const ref of media.values()) {
signal?.throwIfAborted()
const stored = await deps.attachments.readImage(ref)
yield { path: mediaEntryPath(ref), data: stored.data }
}
}
/** How many code units of artifact text one zip push carries (bounded encode memory). */
const PUSH_CHUNK_CODE_UNITS = 1 << 16
/** How many bytes of media one zip push carries (bounded memory; images are already size-capped). */
const PUSH_CHUNK_BYTES = 1 << 16
/**
* Push one media object's bytes into a deflate stream in bounded chunks,
* yielding to a slow consumer between chunks like the artifact path does.
* @param deflate - the zip entry's deflate stream.
* @param data - the stored image bytes.
* @param signal - optional cancellation; throws when aborted.
*/
async function pushBinaryChunks(
deflate: ZipDeflate,
data: Uint8Array,
controller: ReadableStreamDefaultController<Uint8Array>,
signal?: AbortSignal,
): Promise<void> {
let offset = 0
do {
signal?.throwIfAborted()
const end = Math.min(offset + PUSH_CHUNK_BYTES, data.byteLength)
const finalChunk = end >= data.byteLength
deflate.push(data.subarray(offset, end), finalChunk)
offset = end
/* v8 ignore next 2 -- only fires when a slow consumer leaves the queue over-full */
if (controller.desiredSize !== null && controller.desiredSize < 0) {
await new Promise(resolve => setTimeout(resolve, 0))
}
} while (offset < data.byteLength)
}
/**
* Push one artifact's text into a deflate stream in bounded chunks, never
* splitting a surrogate pair across a chunk boundary (a lone high surrogate
* re-encodes as U+FFFD and would silently corrupt the exported artifact).
* @param deflate - the zip entry's deflate stream.
* @param content - the artifact text verbatim.
* @param signal - optional cancellation; throws when aborted.
*/
async function pushArtifactChunks(
deflate: ZipDeflate,
content: string,
controller: ReadableStreamDefaultController<Uint8Array>,
signal?: AbortSignal,
): Promise<void> {
const encoder = new TextEncoder()
let offset = 0
let finalChunk: boolean
do {
signal?.throwIfAborted()
let end = Math.min(offset + PUSH_CHUNK_CODE_UNITS, content.length)
if (end < content.length && end - offset > 1) {
// Back off one code unit when the boundary lands inside a surrogate
// pair: the pair then starts the next chunk whole.
const last = content.charCodeAt(end - 1)
if (last >= 0xd800 && last <= 0xdbff) end -= 1
}
finalChunk = end >= content.length
deflate.push(encoder.encode(content.slice(offset, end)), finalChunk)
offset = end
/* v8 ignore next 2 -- only fires when a slow consumer leaves the queue over-full */
if (controller.desiredSize !== null && controller.desiredSize < 0) {
await new Promise(resolve => setTimeout(resolve, 0))
}
} while (!finalChunk)
}
/**
* Stream one session-log ZIP as a WHATWG ReadableStream. The root artifact is
* read and validated by the caller before this is called (missing root or
* missing services answer cleanly before any byte is produced); each entry is
* then encoded and deflated in bounded chunks as it is produced, so the
* archive bytes arrive incrementally. A descendant that fails to read errors
* the stream (fail-loud, never silent under-export).
* @param deps - the mounted export services (the caller answered 500 before this runs).
* @param root - the already-read root artifact (first zip entry).
* @param sessionId - the root session id.
* @param includeDescendants - whether to include every subagent descendant.
* @param signal - optional cancellation for read work.
* @returns the zip byte stream.
*/
export function streamSessionLogZip(
deps: SessionLogExportReady,
root: SessionRawArtifact,
sessionId: SessionId,
includeDescendants: boolean,
signal?: AbortSignal,
): ReadableStream<Uint8Array> {
return new ReadableStream<Uint8Array>({
start(controller) {
// fflate invokes the callback synchronously per compressed chunk, so a
// single push can enqueue ahead of a slow consumer; pushArtifactChunks
// yields between chunks once the queue is over-full, bounding the
// accumulation to the queue high-water mark plus one push.
const zip = new Zip((error, data, final) => {
/* v8 ignore next 3 -- fflate reports only internal zip failures, unreachable for valid inputs */
if (error) {
controller.error(error)
return
}
/* v8 ignore next -- fflate may emit empty chunks; not controllable from tests */
if (data.byteLength > 0) controller.enqueue(data)
if (final) controller.close()
})
void (async () => {
try {
for await (const entry of sessionLogZipEntries(deps, root, sessionId, includeDescendants, signal)) {
const deflate = new ZipDeflate(entry.path, { level: 6 })
zip.add(deflate)
if ('content' in entry) {
await pushArtifactChunks(deflate, entry.content, controller, signal)
} else {
await pushBinaryChunks(deflate, entry.data, controller, signal)
}
}
zip.end()
} catch (error) {
// A mid-stream failure (missing descendant, cancellation, read
// error) must fail the download rather than ship a truncated archive.
/* v8 ignore next -- typed backends reject with Error, and DOMException is one in Node */
controller.error(error instanceof Error ? error : new Error(String(error)))
}
})()
},
})
}

1
packages/host/apiproxy/tests/client-handler.spec.ts
View File

@@ -133,6 +133,7 @@ function scriptedApi(overrides: {
},
events: { mux: () => empty<MuxFrame>(), host: () => empty<HostFrame>(), ...overrides.events },
respond: overrides.respond ?? (() => Promise.resolve({ accepted: false as const, reason: 'not-pending' as const })),
downloads: { sessionLog: async () => new Response('stub', { status: 404 }) },
}
}

5
packages/host/apiproxy/tests/fetch-carrier.spec.ts
View File

@@ -300,6 +300,11 @@ function fakeApi(overrides: Partial<{ muxFrames: MuxFrame[]; hostFrames: HostFra
async respond(message: ClientResponse): Promise<RpcReceipt> {
return message.rpcId === 'known' ? { accepted: true } : { accepted: false, reason: 'not-pending' }
},
downloads: {
async sessionLog() {
return new Response('stub', { status: 404 })
},
},
}
}

377
packages/host/apiproxy/tests/session-export.spec.ts Normal file
View File

@@ -0,0 +1,377 @@
/**
* session.export host path: the GET download endpoint streams a ZIP whose
* files are the stored artifacts verbatim (root + optional descendants), and
* the degenerate compositions fail loudly (missing services → 500, missing
* root → 404, missing descendant → errored stream).
*/
import { describe, expect, it } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import { unzipSync, strFromU8 } from 'fflate'
import type { ImageAttachmentRef } from '@deepseek-ai/dsh-attachment'
import UserInteractionService from '@deepseek-ai/dsh-user-interaction'
import type { SessionHeader, SessionId } from '@deepseek-ai/dsh-session'
import type { SessionLineageNode } from '@deepseek-ai/dsh-session-query'
import type { SessionRawArtifact } from '@deepseek-ai/dsh-session-persistence'
import { toFetchHandler } from '@deepseek-ai/dsh-host-apiproxy'
import { createApiProxy } from '@deepseek-ai/dsh-host-apiproxy'
const sid = (id: string): SessionId => id as SessionId
function header(id: string, parentSession?: SessionId): SessionHeader {
return {
version: 0,
id: sid(id),
createdAt: 1000,
cwd: '/proj',
...parentSession === undefined ? {} : { parentSession },
delegationDepth: parentSession === undefined ? 0 : 1,
}
}
function artifact(id: string, parentSession?: SessionId, content?: string): SessionRawArtifact {
return {
meta: header(id, parentSession),
filename: 'session.jsonl',
content: content ?? `{"type":"session","version":0,"id":"${id}","createdAt":1000}\n{"type":"turn/start","seq":0,"time":2000,"data":{"turn":1}}\n`,
}
}
function node(id: string, ...descendants: SessionLineageNode[]): SessionLineageNode {
return { session: { header: header(id, sid('session-root')), live: false, persisted: true }, descendants }
}
/** One durable image object served by the fake attachment store. */
function storedImage(id: string, mediaType: ImageAttachmentRef['mediaType'] = 'image/png') {
return {
ref: { attachmentId: sid(id), mediaType, bytes: 4, width: 2, height: 2 } as unknown as ImageAttachmentRef,
data: new Uint8Array([1, 2, 3, 4]),
}
}
/** A user/message event line carrying one image reference. */
function imageEventLine(id: string, mediaType: ImageAttachmentRef['mediaType'] = 'image/png'): string {
return `{"type":"user/message","seq":1,"time":1000,"data":{"content":[{"type":"image","attachment":{"attachmentId":"${id}","mediaType":"${mediaType}","bytes":4,"width":2,"height":2}}]}}`
}
async function buildApi(
artifacts: Record<string, SessionRawArtifact>,
descendants: SessionLineageNode[] = [],
services: {
query?: boolean
persistence?: boolean | 'throw'
attachments?: boolean | ((ref: ImageAttachmentRef) => Promise<ReturnType<typeof storedImage>>)
} = {},
) {
const ctx = new Context()
await ctx.plugin(UserInteractionService)
const query = services.query ?? true
const persistence = services.persistence ?? true
if (query) {
ctx.provide('sessionQuery', {
traceSession: async () => ({
target: { header: header('session-root'), live: false, persisted: true },
ancestors: [],
complete: true,
root: { header: header('session-root'), live: false, persisted: true },
descendants,
}),
} as never)
}
if (persistence) {
ctx.provide('sessionPersistence', {
readRaw: async (id: SessionId) => {
if (persistence === 'throw') throw new Error('/host/private/session.jsonl')
return artifacts[id]
},
} as never)
}
if (services.attachments !== false) {
const readImage = typeof services.attachments === 'function'
? services.attachments
: async (ref: ImageAttachmentRef) => storedImage(String(ref.attachmentId), ref.mediaType)
ctx.provide('attachments', {
imageLimits: {} as never,
validateImage: async () => {},
saveImage: async () => { throw new Error('export never saves images') },
readImage,
} as never)
}
return createApiProxy(ctx, {
defaultModelSelection: () => ({ provider: 'p', model: 'm' }),
cwd: '/tmp',
})
}
async function responseBytes(response: Response): Promise<Uint8Array> {
return new Uint8Array(await response.arrayBuffer())
}
describe('session.export download endpoint', () => {
it('streams a ZIP with the root artifact verbatim under its original filename', async () => {
const api = await buildApi({ 'session-root': artifact('session-root') })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(200)
expect(response.headers.get('content-type')).toBe('application/zip')
expect(response.headers.get('content-disposition')).toContain('dsh-session-session-root.zip')
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files)).toEqual(['session.jsonl'])
expect(strFromU8(files['session.jsonl'] as Uint8Array)).toBe(artifact('session-root').content)
})
it('includes descendant artifacts under subagents/<id>/ when requested', async () => {
const api = await buildApi({
'session-root': artifact('session-root'),
'child-a': artifact('child-a', sid('session-root')),
'grandchild-a': artifact('grandchild-a', sid('child-a')),
}, [
node('child-a', node('grandchild-a')),
])
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=true'),
)
expect(response.status).toBe(200)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files).sort()).toEqual([
'session.jsonl',
'subagents/child-a/session.jsonl',
'subagents/grandchild-a/session.jsonl',
])
expect(strFromU8(files['subagents/child-a/session.jsonl'] as Uint8Array))
.toBe(artifact('child-a').content)
})
it('answers 404 for a missing root session', async () => {
const api = await buildApi({})
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(404)
})
it('answers 400 when the sessionId query parameter is absent', async () => {
const api = await buildApi({ 'session-root': artifact('session-root') })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?includeDescendants=true'),
)
expect(response.status).toBe(400)
})
it('answers 400 for an includeDescendants value other than true or false', async () => {
const api = await buildApi({ 'session-root': artifact('session-root') })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=1'),
)
expect(response.status).toBe(400)
})
it('answers 500 when the deployment mounts no persistence or session-query service', async () => {
const api = await buildApi({}, [], { query: false, persistence: false })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(500)
expect(await response.text()).toContain('session-query')
})
it('fails the whole export when a descendant has no stored artifact', async () => {
const api = await buildApi({
'session-root': artifact('session-root'),
}, [node('child-missing')])
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=true'),
)
expect(response.status).toBe(200)
// The stream errors before completing, so the body read rejects rather
// than returning a truncated-but-valid archive.
await expect(response.arrayBuffer()).rejects.toThrow()
})
it('keeps an astral character whole when its surrogate pair straddles a push boundary', async () => {
// The push loop slices by 2^16 code units and must back off one unit when
// the boundary lands inside a surrogate pair; otherwise the pair re-encodes
// as U+FFFD and the exported artifact is silently corrupted.
const root = { ...artifact('session-root'), content: `${'a'.repeat((1 << 16) - 1)}😀tail` }
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
const files = unzipSync(await responseBytes(response))
expect(strFromU8(files['session.jsonl'] as Uint8Array)).toBe(root.content)
})
it('splits a long artifact on a plain code-unit boundary without backoff', async () => {
// A boundary that lands on a BMP character needs no surrogate backoff; the
// round trip must still be byte-identical across the multi-chunk push.
const root = { ...artifact('session-root'), content: 'z'.repeat((1 << 16) + 4096) }
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
const files = unzipSync(await responseBytes(response))
expect(strFromU8(files['session.jsonl'] as Uint8Array)).toBe(root.content)
})
it('exports an empty artifact as an empty zip entry', async () => {
const root = { ...artifact('session-root'), content: '' }
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files)).toEqual(['session.jsonl'])
expect(strFromU8(files['session.jsonl'] as Uint8Array)).toBe('')
})
it('exports a shared lineage node once (seen-set dedup)', async () => {
const api = await buildApi({
'session-root': artifact('session-root'),
'child-a': artifact('child-a', sid('session-root')),
'child-b': artifact('child-b', sid('session-root')),
shared: artifact('shared', sid('child-a')),
}, [
node('child-a', node('shared')),
node('child-b', node('shared')),
])
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=true'),
)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files).sort()).toEqual([
'session.jsonl',
'subagents/child-a/session.jsonl',
'subagents/child-b/session.jsonl',
'subagents/shared/session.jsonl',
])
})
it('answers 500 without leaking the backend error when the root artifact read fails', async () => {
const api = await buildApi({}, [], { query: true, persistence: 'throw' })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(500)
const body = await response.text()
expect(body).toBe('session log export failed to read the stored artifact')
expect(body).not.toContain('/host/private/')
})
it('includes media objects referenced by the root log under media/<id>.<ext>', async () => {
const root = artifact('session-root', undefined, [
'{"type":"session","version":0,"id":"session-root","createdAt":1000}',
imageEventLine('img-1'),
].join('\n') + '\n')
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(200)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files).sort()).toEqual(['media/img-1.png', 'session.jsonl'])
expect(files['media/img-1.png']).toEqual(storedImage('img-1').data)
})
it('collects media referenced from nested tool results', async () => {
const nested = '{"type":"assistant/message","seq":2,"time":2000,"data":{"content":[{"type":"tool-result","content":[{"type":"image","attachment":{"attachmentId":"nested-1","mediaType":"image/webp","bytes":4,"width":2,"height":2}}]}]}}'
const root = artifact('session-root', undefined, [
'{"type":"session","version":0,"id":"session-root","createdAt":1000}',
nested,
].join('\n') + '\n')
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files).sort()).toEqual(['media/nested-1.webp', 'session.jsonl'])
})
it('scans the wrapped, inserted, and chunk carriers plus non-object content items', async () => {
const block = (id: string, mediaType: string) =>
`{"type":"image","attachment":{"attachmentId":"${id}","mediaType":"${mediaType}","bytes":4,"width":2,"height":2}}`
const wrapped = `{"type":"assistant/message","seq":2,"time":2000,"data":{"message":{"role":"assistant","content":["noise",${block('wrapped-1', 'image/jpeg')}]}}}`
const inserted = `{"type":"context/inserted","seq":3,"time":3000,"data":{"inserted":[{"content":[${block('inserted-1', 'image/gif')}]}]}}`
const chunk = `{"type":"assistant/chunk","seq":4,"time":4000,"data":{"chunk":{"type":"block-end","block":${block('chunk-1', 'image/png')}}}}`
const root = artifact('session-root', undefined, [
'{"type":"session","version":0,"id":"session-root","createdAt":1000}',
wrapped,
inserted,
chunk,
].join('\n') + '\n')
const api = await buildApi({ 'session-root': root })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
const files = unzipSync(await responseBytes(response))
expect(Object.keys(files).sort()).toEqual([
'media/chunk-1.png',
'media/inserted-1.gif',
'media/wrapped-1.jpg',
'session.jsonl',
])
})
it('deduplicates one media object referenced by several included logs', async () => {
const line = imageEventLine('shared-img')
const root = artifact('session-root', undefined, [
'{"type":"session","version":0,"id":"session-root","createdAt":1000}',
line,
].join('\n') + '\n')
const child = artifact('child-a', sid('session-root'), [
'{"type":"session","version":0,"id":"child-a","createdAt":1000}',
line,
].join('\n') + '\n')
const api = await buildApi({ 'session-root': root, 'child-a': child }, [node('child-a')])
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=true'),
)
const files = unzipSync(await responseBytes(response))
expect(files['media/shared-img.png']).toEqual(storedImage('shared-img').data)
expect(Object.keys(files).filter(name => name.startsWith('media/'))).toEqual(['media/shared-img.png'])
})
it('includes descendant media only when descendants are requested', async () => {
const child = artifact('child-a', sid('session-root'), [
'{"type":"session","version":0,"id":"child-a","createdAt":1000}',
imageEventLine('child-img'),
].join('\n') + '\n')
const api = await buildApi({ 'session-root': artifact('session-root'), 'child-a': child }, [node('child-a')])
const without = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(Object.keys(unzipSync(await responseBytes(without)))).toEqual(['session.jsonl'])
const withDescendants = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root&includeDescendants=true'),
)
expect(Object.keys(unzipSync(await responseBytes(withDescendants))).sort()).toEqual([
'media/child-img.png',
'session.jsonl',
'subagents/child-a/session.jsonl',
])
})
it('fails the whole export when a referenced image cannot be read', async () => {
const root = artifact('session-root', undefined, [
'{"type":"session","version":0,"id":"session-root","createdAt":1000}',
imageEventLine('gone-img'),
].join('\n') + '\n')
const api = await buildApi({ 'session-root': root }, [], {
attachments: async () => { throw new Error('attachment bytes missing') },
})
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(200)
await expect(response.arrayBuffer()).rejects.toThrow('attachment bytes missing')
})
it('answers 500 when the deployment mounts no attachments service', async () => {
const api = await buildApi({ 'session-root': artifact('session-root') }, [], { attachments: false })
const response = await toFetchHandler(api).fetch(
new Request('http://host/api/session.export?sessionId=session-root'),
)
expect(response.status).toBe(500)
expect(await response.text()).toContain('attachments')
})
})

4
packages/preset/agent-presets/README.i18n.yaml
View File

@@ -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/preset/agent-presets/README.md
README.md: e31dc8e666096baf6fd6b2cf9407110c7678c6e1
README.zh.md: cf7e24bb0f256623beec1b86c70473a70be03cb5
README.md: 98891c8710adc7d72dee20a8466742ee6f649956
README.zh.md: 0fcc5fa4d697affc2185b9251c6a60dee6510042

3
packages/preset/agent-presets/README.md
View File

@@ -133,7 +133,8 @@ Prefix-stable for the life of an agent: a composition is installed once, before
## Known Limitations and Deferred Work
- **A preset cannot be changed once a session has produced anything** — `recompose` re-links a BLANK session's parent scope to another standing mount, and only a blank one: switching a composition that already ran would strand tools the model has called. Changing the default affects only sessions created afterwards.
- **A generation is keyed on the composition file alone** — the stamp check notices `agent.cordis.yml` changing, not an edit to a skill file or asset beside it; those reach new sessions only once the composition file itself moves or the process restarts. Sessions already joined keep their generation, and nothing reclaims a superseded one while the process lives (bounded by how often compositions are edited, not by sessions).
- **A generation is keyed on the composition file alone** — the stamp check notices `agent.cordis.yml` changing, not an edit to a skill file or asset beside it; those reach new sessions only once the composition file itself moves or the process restarts.
- **A superseded generation is never reclaimed** — sessions already joined keep the generation they run on, and the roster holds no join count that could tell when the last one left, so the whole subtree stays mounted until the process ends. The cost is per generation rather than per session, but it is not free: `dsh-skill-local` watches its roots by default, so each edit-then-create cycle adds a live watcher set. Bounded by how often compositions are edited — which the settings-page authoring flow makes a per-save event rather than a per-deploy one. Reclaiming one needs a joined-agent count on the standing mount; see the `TODO` at `ensureStanding`.
- **A copy is never mounted to validate** — it is byte-identical to its source, so a source broken on disk yields a copy exactly as broken as the source; discovery's health check marks both rows on the next roster read rather than deferring the failure to a session start.
- **Health is a shape check, not a mount** — discovery proves the composition parses in the loader dialect and holds named rows, not that every row's module resolves or activates; a row naming an absent package still fails at the first session, which rolls the creation back.
- **A copy is a snapshot that drifts** — upgrading the deployment does not update copies of shipped presets, and there is no patch semantics at this layer to express "standard plus one change" (that is the bundle layer's `cordis.patch.yml`); the shipped set itself accepts the same cost — `cordis` and `code` are full copies of `standard` — so the whole assembly stays readable in one file.

3
packages/preset/agent-presets/README.zh.md
View File

@@ -133,7 +133,8 @@ Indirectly, through the plugins a standing composition registers, which own ever
## Known Limitations and Deferred Work
- **会话一旦产出内容便无法更换 preset** —— `recompose` 把**空白**会话的父作用域重链到另一个常驻挂载，且仅限空白会话：切换已运行过的组装会抽走模型已调用的工具。更改默认值只影响此后创建的会话。
- **代际只以组装文件为键** —— stamp 检查只察觉 `agent.cordis.yml` 的变化，察觉不到旁边 skill 文件或资产的编辑；那些编辑要等组装文件本身变动或进程重启才达到新会话。已加入的会话保持其代际，进程存活期间不回收被替代的代际（上限取决于组装被编辑的频率，而非会话数）。
- **代际只以组装文件为键** —— stamp 检查只察觉 `agent.cordis.yml` 的变化，察觉不到旁边 skill 文件或资产的编辑；那些编辑要等组装文件本身变动或进程重启才达到新会话。
- **被替代的代际永不回收** —— 已加入的会话保持其运行所在的代际，而名单没有加入计数可以判断最后一个何时离开，因此整棵子树一直挂到进程结束。代价按代际计而非按会话计，但并非为零：`dsh-skill-local` 默认监听自己的根目录，因此每一轮「编辑后建会话」都会新增一套活的 watcher。上限取决于组装被编辑的频率——而设置页的编写流程把这件事从「每次部署」变成了「每次保存」。要回收就需要给常驻挂载加上已加入 agent 的计数；见 `ensureStanding` 处的 `TODO`。
- **副本从不被实际挂载以校验** —— 它与来源逐字节相同，因此磁盘上已坏的来源会产出与来源同样损坏的副本；发现过程的健康检查会在下一次读取名单时把两行都标出来，而不是把失败推迟到会话启动。
- **健康是形状检查，不是挂载** —— 发现过程只证明组装能以加载器方言解析、由具名行组成，不证明每一行的模块都能解析并激活；引用不存在的包的行仍在第一个会话处失败，并回滚该会话的创建。
- **副本是会漂移的快照** —— 升级部署不会更新随附 preset 的副本，本层也没有表达「standard 加一处改动」的 patch 语义（那是 bundle 层 `cordis.patch.yml` 的能力）；随附集合自己也接受同样的代价——`cordis` 与 `code` 就是 `standard` 的完整副本——换来整份组装在一个文件里可读。

2
packages/preset/agent-presets/package.json
View File

@@ -34,12 +34,14 @@
"peerDependencies": {
"@deepseek-ai/cordis-plugin-include": "workspace:^",
"@deepseek-ai/cordis-plugin-loader": "workspace:^",
"@deepseek-ai/dsh-agent": "workspace:^",
"@deepseek-ai/dsh-atomic-write": "workspace:^",
"@deepseek-ai/dsh-invariants": "workspace:^",
"@deepseek-ai/dsh-paths": "workspace:^",
"@deepseek-ai/dsh-scope": "workspace:^",
"@deepseek-ai/dsh-session": "workspace:^",
"@deepseek-ai/dsh-settings": "workspace:^",
"@deepseek-ai/dsh-system-prompt": "workspace:^",
"@deepseek-ai/cordis": "workspace:^"
},
"dependencies": {

30
packages/preset/agent-presets/src/index.ts
View File

@@ -25,6 +25,8 @@ import { stat } from 'node:fs/promises'
import { Context, Service } from '@deepseek-ai/cordis'
import z from '@deepseek-ai/schemastery'
import { bindScopeParent, createScope, scopeOf, type Scope, type ScopeKey, type ScopeParentBinding } from '@deepseek-ai/dsh-scope'
// Type-only: resolves the `agent/created` lifecycle event this service watches.
import type {} from '@deepseek-ai/dsh-agent'
import { settingsNamespace, type SettingsScope, type default as SettingsService } from '@deepseek-ai/dsh-settings'
import { discoverPresets } from './discovery.ts'
import { copyComposition, deleteComposition, readComposition } from './authoring.ts'
@@ -130,6 +132,28 @@ export class AgentPresets extends Service {
this.settingsService = undefined
}, 'agentPresets.settings()')
})
// Advisory, not fatal: a synchronous `agent/created` listener that throws
// VETOES publication, and this service must not, because composing an agent
// outside the roster is legal — `recompose` binds exactly such a bare agent
// below, and the ACP, SDK-server, and headless entry points all create one.
// The invariant companion is the check that fails loud, at assembly. Why an
// unjoined agent matters at all has one home: the [Agent
// Note](../../../../.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md).
//
// Known false positive: a session created bare and bound later by
// `recompose` is warned about once, before its first bind. No shipped flow
// does that today — the Web surface mounts in `setup` and children join
// through `composeFrom` before publication.
ctx.on('agent/created', ({ agent }) => {
if (this.config.roots.length === 0) return
if (this.composedPreset(agent.ctx) !== undefined) return
ctx.logger.warn(
`agent "${agent.id}" was published without joining an agent preset; `
+ 'its tools, prompt sections, and skill catalog resolve against the empty global layer '
+ '(join through AgentPresets.mount() or composeFrom() in the agent factory setup)',
)
})
}
/**
@@ -440,6 +464,12 @@ export class AgentPresets extends Service {
// disappearing, and failing the session over a stat would not.
const current = await compositionStamp(preset.path)
if (current === undefined || sameStamp(mounted.stamp, current)) return mounted
// TODO: reclaim the superseded generation once the last agent joined to
// it is gone. The subtree is not inert — `dsh-skill-local` watches its
// roots — and the settings-page authoring flow turns "a composition
// changed" into a per-save event. This needs a joined-agent count on
// StandingMount, incremented in `mount`/`composeFrom`/`recompose` and
// decremented when the agent's scope key dies.
// Guarded delete: a caller that raced this one may have already started
// the next generation, and dropping THAT pointer would fork a third.
if (this.standing.get(preset.id) === pending) this.standing.delete(preset.id)

36
packages/preset/agent-presets/src/invariant.ts
View File

@@ -5,6 +5,10 @@
import type { Context } from '@deepseek-ai/cordis'
import type { InvariantInstaller } from '@deepseek-ai/dsh-invariants'
// Type-only: resolves the `system-prompt/assemble` waterfall this companion
// joins, and the `agent` field `dsh-agent` merges into its context.
import type {} from '@deepseek-ai/dsh-system-prompt'
import type {} from '@deepseek-ai/dsh-agent'
// Imported through the package name, not `./mount.ts`: a module shared between
// the two build entry points becomes a third chunk that the published `files`
// list does not carry, which `verify-built-package-invariants` rejects.
@@ -18,9 +22,10 @@ export const name = 'agent-presets-invariant'
export const inject = ['invariants']
/**
* Assert that no installed preset composition reaches the root service realm.
* Assert that no installed preset composition reaches the root service realm,
* and that a deployment configuring a roster composes every agent from it.
*
* `mountPreset` proves this once, when the subtree settles. A row that
* `mountPreset` proves the first once, when the subtree settles. A row that
* publishes later — from a timer, or an asynchronous continuation after its
* plugin returned — would escape that one-shot audit, so re-check every live
* mount whenever a service registration changes.
@@ -37,6 +42,33 @@ const install: InvariantInstaller = (ctx, fail) => {
)
}
}, { global: true })
// An agent that joined no preset resolves `tools`, `system-prompt`, and
// `skill` against the empty global layer, so the model receives nothing.
// `composedPreset()` is the roster's own answer to "did this agent join",
// read from the live scope chain — see the [Agent
// Note](../../../../.agents/notes/implemented/architecture/2026-08-10-host-plane-ownership-after-presets.md)
// for why the warning beside it is advisory while this one fails.
//
// Two conditions, each load-bearing. `context.agent` is what makes this an
// AGENT assembly: a scope-only assembly — a cold read resolving presenters
// in a standing key, a diagnostic — is not an agent and must not be judged
// on whether it joined anything. And assembly rather than publication is the
// moment that matters, because an unjoined agent is legal until it addresses
// a model: `recompose` binds a bare agent as its first link, and that agent
// is unjoined for its whole life up to the switch.
ctx.on('system-prompt/assemble', (_assembly, context, next) => {
const presets = ctx.get('agentPresets')
const agent = context.agent
if (presets !== undefined && presets.config.roots.length > 0
&& agent !== undefined && presets.composedPreset(agent.ctx) === undefined) {
fail(
`agent "${agent.id}" addressed a model without joining any agent preset while a roster is `
+ 'composed; its tools, prompt sections, and skill catalog resolve against the empty global layer',
)
}
return next()
})
}
/**

32
packages/preset/agent-presets/tests/invariant.spec.ts
View File

@@ -7,7 +7,7 @@ import LlmService from '@deepseek-ai/dsh-llm'
import SessionStore, { SessionId } from '@deepseek-ai/dsh-session'
import SystemPrompt from '@deepseek-ai/dsh-system-prompt'
import ToolRegistry from '@deepseek-ai/dsh-tools'
import AgentRegistry from '@deepseek-ai/dsh-agent'
import AgentRegistry, { assembleContextFor } from '@deepseek-ai/dsh-agent'
import AgentLoop from '@deepseek-ai/dsh-agent-loop'
import InvariantService from '@deepseek-ai/dsh-invariants'
import { describe, expect, it } from 'vitest'
@@ -84,4 +84,34 @@ describe('agent-presets invariants', () => {
setup: async (agentCtx: Context) => void await ctx.agentPresets.mount(agentCtx, 'isolated'),
})).resolves.toBeDefined()
})
it('rejects an agent that addresses a model without joining any preset', async () => {
const ctx = await harness()
// The delegation shape: an agent composed outside the roster joined no
// standing mount, so every registry view it reads is the empty global
// layer. Publication alone stays legal — `recompose` binds exactly such an
// agent — so nothing fires until that empty world reaches a prompt.
const handle = await ctx.agents.create({ sessionId: SessionId('inv-unjoined') })
await expect(ctx.systemPrompt.assemble(assembleContextFor(handle.agent)))
.rejects.toThrow(/without joining any agent preset/)
})
it('admits a joined agent, a scopeless read, and a standing-key read', async () => {
const ctx = await harness()
const handle = await ctx.agents.create({
sessionId: SessionId('inv-joined'),
setup: async (agentCtx: Context) => void await ctx.agentPresets.mount(agentCtx, 'standard'),
})
await expect(ctx.systemPrompt.assemble(assembleContextFor(handle.agent))).resolves.toBeDefined()
// A scopeless assembly belongs to no agent, so it cannot be an unjoined one.
await expect(ctx.systemPrompt.assemble({})).resolves.toBeDefined()
// Neither can a scope that is not an agent at all: a standing preset key
// has no parent of its own, so a chain-length rule would reject the cold
// read that resolves presenters in it. `context.agent` is what keeps this
// check to agent assemblies.
const standing = await ctx.agentPresets.standingKeyFor('standard')
await expect(ctx.systemPrompt.assemble({ scope: standing })).resolves.toBeDefined()
})
})

29
packages/preset/agent-presets/tests/mount.spec.ts
View File

@@ -499,6 +499,35 @@ describe('replacing a composition', () => {
expect(toolNames(ctx, handle.agent)).toEqual(['alpha'])
})
it('names an agent that was published without joining any preset', async () => {
const ctx = await harness()
const warnings: string[] = []
ctx.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof ctx.logger.warn
await ctx.agents.create({ sessionId: SessionId('sess-unjoined-warn') })
// Advisory, not fatal: a synchronous `agent/created` throw would veto
// publication, and creating an agent outside the roster stays legal.
expect(warnings.filter(line => line.includes('sess-unjoined-warn'))).toHaveLength(1)
expect(warnings.at(-1)).toMatch(/without joining an agent preset/)
warnings.length = 0
await agentOn(ctx, 'sess-joined-quiet', 'minimal')
expect(warnings).toEqual([])
})
it('says nothing when the deployment configures no roster at all', async () => {
// Presets are optional: every surface except the Web bundle keeps its
// model-facing rows in the host plane, so an agent with a chain of one is
// exactly right there and the diagnostic must stay silent.
const rosterless = await harness({ default: 'standard', roots: [] })
const warnings: string[] = []
rosterless.logger.warn = ((message: unknown) => { warnings.push(String(message)) }) as typeof rosterless.logger.warn
await rosterless.agents.create({ sessionId: SessionId('sess-no-roster') })
expect(warnings).toEqual([])
})
it('composes an agent that had nothing installed', async () => {
// An agent created without a preset has no binding to re-link, so the
// switch is its first bind — exactly a mount — and once bound only the

6
packages/preset/agent-presets/tsconfig.json
View File

@@ -18,12 +18,18 @@
{
"path": "../../../vendor/include"
},
{
"path": "../../core/agent"
},
{
"path": "../../core/scope"
},
{
"path": "../../core/session"
},
{
"path": "../../core/system-prompt"
},
{
"path": "../../settings/settings"
},

4
packages/sandbox/sandbox-local/README.i18n.yaml
View File

@@ -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/sandbox/sandbox-local/README.md
README.md: 4d9e8275ba3fe0c1f49555b61e319f52194244bc
README.zh.md: 8a755e6c5b0c266538277bbbcd118fd24ab164f3
README.md: e43133c7c5b64d7779162b790ee6cab7806fd100
README.zh.md: 32743d1b0aba5bed41ee53d90c4ed44dc936161c

6
packages/sandbox/sandbox-local/README.md
View File

@@ -2,7 +2,7 @@
English | [中文](README.zh.md)
Local implementation of the [`dsh-sandbox`](../sandbox/) seam. It selects and caches one platform runner: Linux prefers a working `bwrap` then Landlock; macOS uses Seatbelt. Multiple candidates are probed in order, while a sole candidate is selected directly.
Local implementation of the [`dsh-sandbox`](../sandbox/) seam. It selects and caches one platform runner: Linux prefers a working `bwrap` then Landlock; macOS uses Seatbelt; Windows uses the ACL restricted-token runner. Multiple candidates are probed in order, while a sole candidate is selected directly.
The package root exports the default and named `LocalSandboxProvider` plugin and `Config`; platform profile builders stay internal.
@@ -12,6 +12,8 @@ Policy is per call; the provider stores only the mechanism and cached runner ver
The Seatbelt profile is allow-default with `(deny file-write*)` plus write allow-lists, so exactly the mode's promised file effects are governed: `read-only` grants the `/dev/null` literal alone; `workspace-write` adds the workspace root, `/tmp`, and the per-user darwin temp dir (`os.tmpdir()` — the platform's real temp area for mkstemp-family tools), every root canonicalized because Seatbelt matches resolved paths (`/tmp` IS `/private/tmp`). Apple marks the `sandbox-exec` CLI deprecated but ships it on every macOS; the functional probe is what fails closed if that ever changes.
The Windows rung keeps one deterministic write SID and standing ACE per workspace, but gives every live session/workspace pair a random private temp directory with a distinct SID and revocable ACE. Sessions sharing a workspace therefore share its intended write authority without inheriting one another's temp authority. A fresh provider always chooses a new temp path and SID, so crash residue cannot block or authorize a resumed session; agentless calls receive the same per-invocation isolation from the runner. A workspace equal to or containing the platform temp root fails before any ACL mutation because its inheritable workspace ACE would otherwise reach every private temp child.
[`@deepseek-ai/node-addon-landlock-run`](https://www.npmjs.com/package/@deepseek-ai/node-addon-landlock-run) supplies the platform launcher, functional probe, and CLI argument vocabulary. This provider owns only mode-to-grant mapping and runner selection. Keeping path resolution and probe parsing with the versioned binary prevents contract drift.
```yaml
@@ -31,7 +33,7 @@ No direct invalidation; the named consumer owns any request-prefix changes.
## Known Limitations and Deferred Work
- **Windows has no runner** — `win32` fails closed with `SANDBOX_UNAVAILABLE`; an AppContainer-family backend is deferred.
- **Windows ACL enforcement is partial** — the restricted token must retain Everyone for process initialization, so external objects granting Everyone write access remain writable; NTFS hard links also alias one file object across workspace and external paths. The provider reports `enforcement: 'partial'` rather than overstating that boundary as full.
- **Landlock may be partial** — older supported kernel ABIs confine only the access classes they expose, reported as `enforcement: 'partial'` rather than overstated as full.
- **Seatbelt depends on deprecated `sandbox-exec`** — macOS still ships it, but this provider cannot replace or probe that private policy engine if Apple removes it.
- **Runner selection is cached for the provider lifetime** — installing, removing, or repairing a runner requires reloading the plugin before selection changes.

6
packages/sandbox/sandbox-local/README.zh.md
View File

@@ -2,7 +2,7 @@
[English](README.md) | 中文
[`dsh-sandbox`](../sandbox/) seam 的本地实现。它选择并缓存一个平台 runner：Linux 优先选择可工作的 `bwrap`，否则选择 Landlock；macOS 使用 Seatbelt。多个候选项会按顺序探测，只有一个候选项时则直接选择。
[`dsh-sandbox`](../sandbox/) seam 的本地实现。它选择并缓存一个平台 runner：Linux 优先选择可工作的 `bwrap`，否则选择 Landlock；macOS 使用 Seatbelt；Windows 使用 ACL 受限令牌 runner。多个候选项会按顺序探测，只有一个候选项时则直接选择。
包根目录导出默认及命名的 `LocalSandboxProvider` 插件和 `Config`；平台 profile builder 仍为内部实现。
@@ -12,6 +12,8 @@
Seatbelt profile 默认允许，但带 `(deny file-write*)` 和写入 allow-list，因此恰好约束相应模式承诺的文件操作：`read-only` 只授予 `/dev/null` 字面路径；`workspace-write` 另加工作区根目录、`/tmp` 和逐用户 darwin 临时目录（`os.tmpdir()`，即平台供 mkstemp 家族工具使用的真实临时区域）。每个根目录都经过规范化，因为 Seatbelt 匹配解析后的路径（`/tmp` 就是 `/private/tmp`）。Apple 将 `sandbox-exec` CLI（命令行界面）标为 deprecated，但所有 macOS 系统仍会提供它；若情况发生变化，功能探测会使执行被拒绝。
Windows 档为每个工作区保留一个确定性写入 SID 和常驻 ACE，但为每个活跃的会话/工作区对分配一个随机私有临时目录，以及不同的 SID 和可回收 ACE。因此，共享工作区的会话会共享预期的写权限，却不会继承彼此的临时目录权限。新的提供方总会选择新的临时路径和 SID，因此崩溃残留既无法阻止恢复的会话，也无法向其授权；runner 会为无 agent（智能体）的调用提供同样的逐调用隔离。如果工作区等于或包含平台临时根目录，调用会在任何 ACL 改动发生前失败，因为否则其可继承的工作区 ACE 会延伸到每个私有临时子目录。
[`@deepseek-ai/node-addon-landlock-run`](https://www.npmjs.com/package/@deepseek-ai/node-addon-landlock-run)提供平台 launcher、功能探测和 CLI 参数词汇。该提供方只负责模式到授权的映射与 runner 选择。把路径解析和探测解析保留在带版本的 binary 中，可防止约定漂移。
```yaml
@@ -31,7 +33,7 @@ Seatbelt profile 默认允许，但带 `(deny file-write*)` 和写入 allow-list
## 已知限制与暂缓事项
- **Windows 没有 runner**：`win32` 以 `SANDBOX_UNAVAILABLE` 拒绝执行；AppContainer 家族后端暂缓实现。
- **Windows ACL 只能实现部分强制执行**：受限令牌必须保留 Everyone 以完成进程初始化，因此授予 Everyone 写访问的外部对象仍可写；NTFS 硬链接也会使工作区路径与外部路径指向同一个文件对象。提供方报告 `enforcement: 'partial'`，而不会把该边界夸大为完整强制执行。
- **Landlock 可能只实现部分强制执行**：较旧且受支持的内核 ABI 只能限制自身公开的访问类别，因此报告 `enforcement: 'partial'`，不会夸大为完整强制执行。
- **Seatbelt 依赖已弃用的 `sandbox-exec`**：macOS 仍会提供它，但若 Apple 移除该私有策略引擎，该提供方无法替换或探测。
- **runner 选择在提供方生命周期内缓存**：安装、移除或修复 runner 后，必须重载插件才能改变选择。

193
packages/sandbox/sandbox-local/src/index.ts
View File

@@ -7,20 +7,21 @@
*
* The windows-acl rung additionally owns the write grants: the write SID is
* the per-WORKSPACE identity derived from the canonical workspace path
* (`workspaceWriteSid`), and the private temp subdirectory is DERIVED per
* session (session id + workspace — nothing stored). The
* (`workspaceWriteSid`), while every live session receives a RANDOM private
* temp directory and its own derived capability (`tempWriteSid`). The
* workspace-root ACE materializes once per workspace per server lifetime
* and STANDS (the cross-session reuse cache — the exact-ACE skip makes
* every later provision O(1) instead of re-propagating the tree per
* session); the private-temp ACEs are revoked on dispose. The runner
* receives `--write-sid` (the derived identity; its presence marks the
* seam-managed contract) and stops managing DACLs itself.
* receives both SIDs (their presence marks the seam-managed contract) and
* stops managing DACLs itself. The rung reports partial enforcement because
* WRITE_RESTRICTED must retain Everyone in its
* restricting list and NTFS hard links alias one file object across paths.
* @module @deepseek-ai/dsh-sandbox-local
*/
import { spawnSync } from 'node:child_process'
import { createHash } from 'node:crypto'
import { existsSync, mkdirSync, rmSync } from 'node:fs'
import { existsSync, mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
@@ -36,7 +37,7 @@ import { assertNever } from '@deepseek-ai/dsh-llm'
import { SandboxProvider, SandboxUnavailableError } from '@deepseek-ai/dsh-sandbox'
import type { ConfinedArgv, ConfinedSandboxMode, RunnerFailureRule, SandboxEnforcement, SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
import type { SessionId } from '@deepseek-ai/dsh-session'
import { AclWriteGrant, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
import { AclWriteGrant, assertTempRootOutsideWorkspace, tempWriteSid, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
import { bwrapProfileArgs, landlockProfileArgs, seatbeltProfileArgs } from './profiles.ts'
/** Plugin config. All optional — `static Config` supplies the defaults. */
@@ -110,25 +111,6 @@ function defaultProbeWindowsAcl(runnerInvocation: string[], timeoutMs: number):
return probe.status === 0
}
/**
* The session's private temp subdirectory: `<tmpdir>\dsh-<16 hex>`, derived
* from the session id and its workspace instead of stored. The same session
* and workspace always name the same directory — a resumed session
* re-grants it (the exact-ACE skip keeps that O(1)) — while a fork's
* different session id names a fresh one. The name is predictable to anyone
* who knows the session id (the confined command sees it as
* `DSH_SESSION_ID`), so the provider creates the directory EXCLUSIVELY and
* rejects reparse points: a pre-placed entry fails the first confined run
* loudly, and cannot redirect the grant onto a foreign object.
* @param sessionId - the policy's calling-session identity.
* @param workspaceRoot - the resolved policy root.
* @returns the session's private temp subdirectory path.
*/
export function sessionTempDir(sessionId: SessionId, workspaceRoot: string): string {
const digest = createHash('sha256').update(String(sessionId)).update('\0').update(workspaceRoot).digest('hex')
return join(tmpdir(), `dsh-${digest.slice(0, 16)}`)
}
/** Test hook: inject probe verdicts / a fake launcher / a platform without real runners. */
export interface SandboxInternals {
/** Replaces `process.platform` for chain selection (exercise any platform's chain from any host). */
@@ -158,6 +140,13 @@ export interface SandboxInternals {
/** The chain's verdict: which runner confines, and how completely it enforces. */
type SelectedRunner = { runner: 'bwrap' | 'landlock' | 'seatbelt' | 'windows-acl'; enforcement: SandboxEnforcement }
/** One live session/workspace pair's private temp directory and capability. */
interface AclTempCapability {
dir: string
writeSid: string
grant: AclWriteGrant
}
/**
* The runner chain per platform — selection is BY PLATFORM first, probes
* second: a platform's chain is probed in preference order only when it has
@@ -189,13 +178,12 @@ const STATIC_ENFORCEMENT: Record<SelectedRunner['runner'], SandboxEnforcement> =
bwrap: 'full',
landlock: 'full',
seatbelt: 'full',
// 'full' is the SUPPORTED-SURFACE promise: on NTFS both restricting lists
// close every ambient write (INTERACTIVE/LOCAL and Authenticated Users are
// absent from both — pinned by the runner's Public-probe and CIM-denial
// regressions). FAT-class (non-ACL) targets are declared unsupported
// (warn-only) in the backend README — outside the promise, not an
// exception to it.
'windows-acl': 'full',
// WRITE_RESTRICTED needs Everyone in both restricting lists for process
// initialization. An external object that grants Everyone write access
// therefore remains writable, and NTFS hard links can alias a granted
// workspace file to a path outside it. The backend enforces the remaining
// ACL-addressable surface but must not advertise the absolute promise.
'windows-acl': 'partial',
}
/**
@@ -255,8 +243,9 @@ const RUNNER_FAILURE_RULES = {
* Local process-sandbox provider. Registers as `ctx.sandbox`. Caches the
* chain verdict and, on the windows-acl rung, the write grants
* ({@link AclWriteGrant}: the standing workspace-root grant per workspace
* and the revocable private-temp grant per session, the latter revoked on
* provider dispose); the one-time probes spawn nothing else.
* and the revocable private-temp grant per live session/workspace pair, the
* latter revoked on provider dispose); the one-time probes spawn nothing
* else.
*/
export class LocalSandboxProvider extends SandboxProvider {
// Inline schema call: the config catalog walks `static Config` statically.
@@ -278,12 +267,11 @@ export class LocalSandboxProvider extends SandboxProvider {
* Server-lifetime write grants (windows-acl rung): the STANDING
* workspace-root grant per workspace (its ACE is the cross-session reuse
* cache and outlives the provider — never revoked) and the REVOCABLE
* private-temp grant per session (revoked on provider dispose).
* private-temp grant per live session/workspace pair (revoked on provider
* dispose).
*/
private readonly workspaceGrants = new Map<string, AclWriteGrant>()
private readonly tempGrants = new Map<string, AclWriteGrant>()
/** Session id → the private temp directory this provider created (removed on dispose). */
private readonly tempDirs = new Map<string, string>()
private readonly tempCapabilities = new Map<string, AclTempCapability>()
constructor(ctx: Context, config: Config) {
super(ctx)
@@ -357,20 +345,19 @@ export class LocalSandboxProvider extends SandboxProvider {
/**
* The windows-acl runner argv for one policy. With a calling session (the
* policy's `sessionId`), the write grants are materialized once per server
* lifetime — the standing workspace-root grant per workspace and the
* revocable private-temp grant per session — and the runner receives
* `--write-sid` (the workspace-derived identity; its presence marks the
* seam-managed DACL contract) plus, under workspace-write, the session's
* PRIVATE temp subdirectory (derived from session id + workspace) — it
* grants nothing and revokes nothing. Agentless calls pass the ambient
* temp root and no `--write-sid`: the runner self-manages its DACLs.
* policy's `sessionId`) under workspace-write, the grants are materialized
* once per provider lifetime — the standing workspace-root grant per
* workspace and a revocable, RANDOM private-temp capability per live
* session/workspace pair. The runner receives `--write-sid` plus
* `--temp-write-sid` and grants nothing itself. Agentless workspace-write
* calls pass the ambient temp ROOT and no SID flags: the runner creates and
* removes a random private child directory for that one invocation.
* @param policy - the resolved per-call policy.
* @returns the runner invocation.
*/
private windowsAclRunnerArgv(policy: SandboxPolicy): string[] {
const sessionId = policy.sessionId
if (sessionId === undefined) {
if (sessionId === undefined || policy.mode === 'read-only') {
return [
...this.windowsAclRunnerInvocation(),
'--workspace', policy.workspaceRoot,
@@ -378,45 +365,33 @@ export class LocalSandboxProvider extends SandboxProvider {
'--mode', policy.mode,
]
}
this.materializeAclGrant(sessionId, policy.workspaceRoot, policy.mode)
const temp = this.materializeAclGrant(sessionId, policy.workspaceRoot)
return [
...this.windowsAclRunnerInvocation(),
'--workspace', policy.workspaceRoot,
// Workspace-write sessions confine their temp writes to the PRIVATE
// per-session subdirectory (bwrap --tmpfs /tmp semantics); read-only
// runs pass the ambient temp root — the runner validates it exists
// but grants nothing. The derived write SID is the per-workspace
// identity; the flag's presence marks the seam-managed DACL contract.
'--temp', policy.mode === 'workspace-write' ? sessionTempDir(sessionId, policy.workspaceRoot) : tmpdir(),
'--temp', temp.dir,
'--mode', policy.mode,
'--write-sid', workspaceWriteSid(policy.workspaceRoot),
'--temp-write-sid', temp.writeSid,
]
}
/**
* Materialize the session's ACEs once per server lifetime: lazily at its
* first confined execution, reused for every later call (the map hits are
* the whole call). The write SID is the per-workspace identity derived
* from the workspace. Workspace-write grants the workspace root STANDING
* (the ACE outlives every session — the reuse cache) and the session's
* private temp subdirectory REVOCABLY — the directory is derived from
* session id + workspace, created here EXCLUSIVELY (a pre-existing entry
* or a reparse point fails the first confined run loudly, so the grant
* never lands on a foreign object); read-only materializes NOTHING — its
* token alone restricts every write, and the standing grant from an
* earlier workspace-write period is KEPT through a downgrade (never
* revoked): the read-only restricted token carries no write SID (the
* read-only list), so the ACE is inert there, while the map hit keeps the
* re-upgrade free of re-propagation. Fail-closed: a half-materialized
* temp grant is revoked before the error propagates.
* Materialize one workspace-write policy's ACEs once per provider
* lifetime. The workspace SID and standing root grant are shared by the
* workspace. The temp directory is random and carries a distinct SID, so
* another session on the same workspace cannot use the shared workspace
* SID to enter it. A fresh provider always chooses a new path; crash
* residue therefore cannot collide with or authorize a resumed session.
* Fail-closed: a half-materialized temp grant is revoked and its directory
* removed before the error propagates.
* @param sessionId - the policy's calling-session identity.
* @param workspaceRoot - the resolved policy root.
* @param mode - the policy mode (grants exist only under workspace-write).
* @returns the pair's private temp directory and write capability.
*/
private materializeAclGrant(sessionId: SessionId, workspaceRoot: string, mode: ConfinedSandboxMode): void {
if (mode === 'read-only') return
private materializeAclGrant(sessionId: SessionId, workspaceRoot: string): AclTempCapability {
assertTempRootOutsideWorkspace(workspaceRoot, tmpdir())
const writeSid = workspaceWriteSid(workspaceRoot)
const tempDir = sessionTempDir(sessionId, workspaceRoot)
if (!this.workspaceGrants.has(workspaceRoot)) {
const grant = AclWriteGrant.create(writeSid)
try {
@@ -434,32 +409,37 @@ export class LocalSandboxProvider extends SandboxProvider {
}
this.workspaceGrants.set(workspaceRoot, grant)
}
if (this.tempGrants.has(sessionId)) return
const grant = AclWriteGrant.create(writeSid)
// The directory is removed again in the catch only when THIS confine
// created it — a pre-existing entry (EEXIST) is a foreign object and is
// never deleted.
let created = false
const key = JSON.stringify([String(sessionId), workspaceRoot])
const existing = this.tempCapabilities.get(key)
if (existing !== undefined) return existing
const tempDir = mkdtempSync(join(tmpdir(), 'dsh-'))
const tempSid = tempWriteSid(tempDir)
let grant: AclWriteGrant | undefined
try {
// Exclusive creation (no `recursive`): a pre-existing entry OR a
// reparse point both fail EEXIST — the grant never lands on a foreign
// object.
mkdirSync(tempDir)
created = true
grant = AclWriteGrant.create(tempSid)
grant.add(tempDir)
} catch (error) {
if (created) rmSync(tempDir, { recursive: true, force: true })
// Revoke whatever stands and free the SID — never leave a half-grant
// behind a failed confine (the runner never runs).
const cleanupFailures: unknown[] = []
if (grant !== undefined) {
try {
grant.dispose()
} catch (cleanupError) {
cleanupFailures.push(cleanupError)
}
}
try {
grant.dispose()
this.removeTempDir(tempDir)
} catch (cleanupError) {
throw new AggregateError([error, cleanupError], 'sandbox-local windows-acl temp grant materialization failed and its cleanup also failed')
cleanupFailures.push(cleanupError)
}
if (cleanupFailures.length > 0) {
throw new AggregateError([error, ...cleanupFailures], 'sandbox-local windows-acl temp grant materialization failed and its cleanup also failed')
}
throw error
}
this.tempGrants.set(sessionId, grant)
this.tempDirs.set(sessionId, tempDir)
const capability = { dir: tempDir, writeSid: tempSid, grant }
this.tempCapabilities.set(key, capability)
return capability
}
/**
@@ -468,36 +448,40 @@ export class LocalSandboxProvider extends SandboxProvider {
* removed, and every SID allocation is freed; the standing workspace ACEs
* stay (the reuse cache). Cleanup failures are reported, not thrown:
* cordis teardown must not be aborted by grant cleanup. A crash skips all
* of it — the next resume then fails loudly at the exclusive creation and
* OS temp hygiene (or manual removal) recovers.
* of it, but a new provider never reuses the residue's random path or SID;
* OS temp hygiene (or manual removal) eventually reclaims it.
*/
private revokeAclGrants(): void {
if (this.workspaceGrants.size === 0 && this.tempGrants.size === 0) return
if (this.workspaceGrants.size === 0 && this.tempCapabilities.size === 0) return
const failures: unknown[] = []
for (const grant of [...this.workspaceGrants.values(), ...this.tempGrants.values()]) {
for (const grant of [...this.workspaceGrants.values(), ...[...this.tempCapabilities.values()].map(capability => capability.grant)]) {
try {
grant.dispose()
} catch (error) {
failures.push(error)
}
}
const rmTempDir = this.internals.rmTempDir ?? ((dir: string) => { rmSync(dir, { recursive: true, force: true }) })
for (const dir of this.tempDirs.values()) {
for (const { dir } of this.tempCapabilities.values()) {
try {
rmTempDir(dir)
this.removeTempDir(dir)
} catch (error) {
failures.push(error)
}
}
this.workspaceGrants.clear()
this.tempGrants.clear()
this.tempDirs.clear()
this.tempCapabilities.clear()
if (failures.length > 0) {
this.ctx.logger.warn(`sandbox-local: windows-acl grant cleanup completed with ${failures.length} failure(s)`)
for (const error of failures) this.ctx.logger.warn(error)
}
}
/** Remove one provider-owned private temp directory (injectable for cleanup tests). */
private removeTempDir(dir: string): void {
const remove = this.internals.rmTempDir ?? ((path: string) => { rmSync(path, { recursive: true, force: true }) })
remove(dir)
}
/**
* Resolve which runner confines commands, once, for the provider's
* lifetime: this platform's chain ({@link PLATFORM_CHAINS}), its sole
@@ -529,8 +513,9 @@ export class LocalSandboxProvider extends SandboxProvider {
private probeRunner(runner: SelectedRunner['runner']): SandboxEnforcement | 'unusable' {
// bwrap's mount profile and Seatbelt's deny-file-write* profile govern
// every promised file effect by construction, so their passing probes
// are always full enforcement; only the Landlock launcher's probe report
// distinguishes full from per-ABI-partial.
// are always full enforcement; the Landlock launcher's probe report
// distinguishes full from per-ABI-partial, while windows-acl is always
// partial for its documented Everyone and hard-link boundaries.
switch (runner) {
case 'bwrap': {
const probe = this.internals.probeBwrap ?? (() => defaultProbeBwrap(this.probeTimeoutMs))
@@ -547,7 +532,7 @@ export class LocalSandboxProvider extends SandboxProvider {
case 'windows-acl': {
const probe = this.internals.probeWindowsAcl
?? (() => defaultProbeWindowsAcl(this.windowsAclRunnerInvocation(), this.probeTimeoutMs))
return probe() ? 'full' : 'unusable'
return probe() ? 'partial' : 'unusable'
}
default: return assertNever(runner)
}

369
packages/sandbox/sandbox-local/tests/acl-grants.spec.ts
View File

@@ -1,27 +1,26 @@
/**
* windows-acl write grants: the SERVER-LIFETIME ACE materialization
* (standing workspace grant per workspace, revocable private-temp grant per
* session) plus the derived private-temp identity, through the REAL
* LocalSandboxProvider.confine(). Win32 surface mocked at the package
* boundary (the workspace-derived SID mocked to a constant); the real-FFI
* grant behavior lives in sandbox-windows-acl's win32 tests.
* windows-acl grant ownership through the real LocalSandboxProvider: one
* standing capability per workspace plus one random, distinct, revocable
* temp capability per live session/workspace pair. The Win32 grant surface
* is mocked; native access checks live in sandbox-windows-acl's runner suite.
*/
import { existsSync, mkdirSync, mkdtempSync, rmSync, symlinkSync } from 'node:fs'
import { existsSync, mkdtempSync, realpathSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { basename, join } from 'node:path'
import { beforeEach, describe, expect, it, vi } from 'vitest'
import { Context } from '@deepseek-ai/cordis'
import type { SandboxPolicy } from '@deepseek-ai/dsh-sandbox'
import { SessionId } from '@deepseek-ai/dsh-session'
import { LocalSandboxProvider, sessionTempDir } from '@deepseek-ai/dsh-sandbox-local'
import { LocalSandboxProvider } from '@deepseek-ai/dsh-sandbox-local'
/** Cross-file state shared with the vi.mock factory (hoisting contract). */
const mockState = vi.hoisted(() => ({
grants: [] as Array<{ writeSid: string; added: Array<{ path: string; standing: boolean }>; disposed: boolean }>,
addFailure: undefined as Error | undefined,
/** Restricts {@link addFailure} to this path (undefined = every add throws). */
addFailurePath: undefined as string | undefined,
/** Restrict an add failure to standing (workspace) or revocable (temp). */
addFailureStanding: undefined as boolean | undefined,
createTempFailure: undefined as Error | undefined,
disposeFailure: undefined as Error | undefined,
}))
@@ -35,24 +34,36 @@ vi.mock('@deepseek-ai/dsh-sandbox-windows-acl', () => {
mockState.grants.push(this)
}
static create(writeSid: string): MockAclWriteGrant {
if (writeSid.startsWith('TEMP:') && mockState.createTempFailure !== undefined) throw mockState.createTempFailure
return new MockAclWriteGrant(writeSid)
}
add(path: string, standing = false): void {
if (mockState.addFailure !== undefined && (mockState.addFailurePath === undefined || mockState.addFailurePath === path)) {
this.added.push({ path, standing })
if (mockState.addFailure !== undefined
&& (mockState.addFailureStanding === undefined || mockState.addFailureStanding === standing)) {
throw mockState.addFailure
}
this.added.push({ path, standing })
}
dispose(): void {
if (mockState.disposeFailure !== undefined) throw mockState.disposeFailure
this.disposed = true
}
}
return { AclWriteGrant: MockAclWriteGrant, workspaceWriteSid: () => 'S-1-4-42-42' }
return {
AclWriteGrant: MockAclWriteGrant,
assertTempRootOutsideWorkspace: (workspaceRoot: string, tempRoot: string) => {
const workspace = realpathSync.native(workspaceRoot)
const temp = realpathSync.native(tempRoot)
if (temp === workspace || temp.startsWith(`${workspace}${process.platform === 'win32' ? '\\' : '/'}`)) {
throw new Error(`Windows ACL temp root must be outside the workspace: workspace=${workspaceRoot}; temp=${tempRoot}`)
}
},
workspaceWriteSid: () => 'S-1-4-42-42',
tempWriteSid: (path: string) => `TEMP:${path}`,
}
})
/** The workspace-derived write SID the mock pins for every workspace. */
const DERIVED_SID = 'S-1-4-42-42'
const WORKSPACE_SID = 'S-1-4-42-42'
async function setup() {
const ctx = new Context()
@@ -62,279 +73,232 @@ async function setup() {
return { ctx, sandbox, fiber }
}
/** A workspace root the policy carries. */
function workspaceRoot(): string {
return mkdtempSync(join(tmpdir(), 'dsh-acl-grants-ws-'))
}
function flag(argv: readonly string[], name: string): string | undefined {
const index = argv.indexOf(name)
return index < 0 ? undefined : argv[index + 1]
}
describe('windows-acl write grants (LocalSandboxProvider)', () => {
const scratch: string[] = []
beforeEach(() => {
mockState.grants = []
mockState.addFailure = undefined
mockState.addFailurePath = undefined
mockState.addFailureStanding = undefined
mockState.createTempFailure = undefined
mockState.disposeFailure = undefined
})
const cleanup = () => {
for (const grant of mockState.grants) {
for (const added of grant.added) {
if (!added.standing) rmSync(added.path, { recursive: true, force: true })
}
}
for (const dir of scratch.splice(0)) rmSync(dir, { recursive: true, force: true })
}
it('workspace-write: first confine materializes ONCE (standing workspace + revocable private temp), the derived temp dir rides the argv', async () => {
it('workspace-write materializes one standing workspace grant and one private temp capability, then reuses both', async () => {
try {
const { sandbox, fiber } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
const tempDir = sessionTempDir(SessionId('sess-1'), ws)
scratch.push(tempDir)
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-1') }
const confined = sandbox.confine(['pwsh', '/Command', 'x'], policy)
const tempDir = flag(confined.argv, '--temp')
const tempSid = flag(confined.argv, '--temp-write-sid')
expect(tempDir).toBeDefined()
expect(basename(tempDir ?? '')).toMatch(/^dsh-[A-Za-z0-9_-]{6}$/u)
expect(tempSid).toBe(`TEMP:${tempDir}`)
expect(tempSid).not.toBe(WORKSPACE_SID)
expect(confined.argv).toEqual([
'node', 'windows-acl-runner.js',
'--workspace', ws,
'--temp', tempDir,
'--mode', 'workspace-write',
'--write-sid', DERIVED_SID,
'--write-sid', WORKSPACE_SID,
'--temp-write-sid', tempSid,
'--',
'pwsh', '/Command', 'x',
])
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[0]).toMatchObject({
writeSid: DERIVED_SID,
added: [{ path: ws, standing: true }], // standing: the reuse cache, never revoked
disposed: false,
})
expect(mockState.grants[1]).toMatchObject({
writeSid: DERIVED_SID,
added: [{ path: tempDir, standing: false }],
disposed: false,
})
expect(existsSync(tempDir)).toBe(true) // created exclusively
expect(mockState.grants).toEqual([
expect.objectContaining({ writeSid: WORKSPACE_SID, added: [{ path: ws, standing: true }], disposed: false }),
expect.objectContaining({ writeSid: tempSid, added: [{ path: tempDir, standing: false }], disposed: false }),
])
expect(existsSync(tempDir ?? '')).toBe(true)
// Reuse: the second confine is the map hits.
sandbox.confine(['pwsh', '/Command', 'x'], policy)
expect(sandbox.confine(['pwsh', '/Command', 'x'], policy).argv).toEqual(confined.argv)
expect(mockState.grants).toHaveLength(2)
await fiber.dispose()
// dispose() runs on BOTH grants: the standing workspace ACE is left in
// place (the mock marks it disposed only as instance teardown).
expect(mockState.grants[0]!.disposed).toBe(true)
expect(mockState.grants[1]!.disposed).toBe(true)
expect(mockState.grants.every(grant => grant.disposed)).toBe(true)
expect(existsSync(tempDir ?? '')).toBe(false)
} finally {
cleanup()
}
})
it('mode switch: read-only materializes nothing, the upgrade materializes ONCE with the derived SID, the downgrade keeps the standing grant', async () => {
it('read-only materializes no capability; upgrade creates them and downgrade leaves them reusable', async () => {
try {
const { sandbox } = await setup()
const { sandbox, fiber } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
const tempDir = sessionTempDir(SessionId('sess-switch'), ws)
scratch.push(tempDir)
const readOnly: SandboxPolicy = { mode: 'read-only', workspaceRoot: ws, sessionId: SessionId('sess-switch') }
const workspaceWrite: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-switch') }
const readOnly: SandboxPolicy = { mode: 'read-only', workspaceRoot: ws, sessionId: SessionId('switch') }
const workspaceWrite: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('switch') }
// read-only first: nothing materialized, ambient temp.
const confinedRo = sandbox.confine(['true'], readOnly)
expect(confinedRo.argv).toEqual([
expect(sandbox.confine(['true'], readOnly).argv).toEqual([
'node', 'windows-acl-runner.js',
'--workspace', ws,
'--temp', tmpdir(), // NOT the private subdir: read-only grants nothing
'--temp', tmpdir(),
'--mode', 'read-only',
'--write-sid', DERIVED_SID,
'--',
'true',
])
expect(mockState.grants).toHaveLength(0)
expect(existsSync(tempDir)).toBe(false)
// Upgrade: first workspace-write materializes with the derived SID.
const upgraded = sandbox.confine(['true'], workspaceWrite)
expect(upgraded.argv).toEqual([
'node', 'windows-acl-runner.js',
'--workspace', ws,
'--temp', tempDir,
'--mode', 'workspace-write',
'--write-sid', DERIVED_SID,
'--',
'true',
])
expect(flag(upgraded.argv, '--temp-write-sid')).not.toBe(WORKSPACE_SID)
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[0]).toMatchObject({ writeSid: DERIVED_SID, added: [{ path: ws, standing: true }], disposed: false })
expect(mockState.grants[1]).toMatchObject({
writeSid: DERIVED_SID,
added: [{ path: tempDir, standing: false }],
disposed: false,
})
expect(existsSync(tempDir)).toBe(true)
// Reuse: map hits.
sandbox.confine(['true'], workspaceWrite)
expect(mockState.grants).toHaveLength(2)
// Downgrade: standing grant KEPT (inert under read-only, free re-upgrade).
sandbox.confine(['true'], readOnly)
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[0]!.disposed).toBe(false)
expect(mockState.grants.every(grant => !grant.disposed)).toBe(true)
expect(sandbox.confine(['true'], workspaceWrite).argv).toEqual(upgraded.argv)
await fiber.dispose()
} finally {
cleanup()
}
})
it('resume: a fresh provider derives the SAME temp dir for the same session and workspace and re-grants it', async () => {
it('a fresh provider gives a resumed session a new temp path and SID, so crash residue cannot collide', async () => {
try {
const ws = workspaceRoot()
scratch.push(ws)
const first = await setup()
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('resumed') }
const first = await setup()
const firstConfined = first.sandbox.confine(['true'], policy)
expect(mockState.grants).toHaveLength(2)
const firstTemp = flag(firstConfined.argv, '--temp') ?? ''
// Clean restart: dispose revokes the temp ACE and removes the private
// temp directory, so the fresh provider's exclusive creation succeeds.
await first.fiber.dispose()
mockState.grants = []
// The first provider remains live: model an unclean prior process whose
// temp directory and ACE survived. A new provider must still proceed.
const second = await setup()
const secondConfined = second.sandbox.confine(['true'], policy)
expect(secondConfined.argv).toEqual(firstConfined.argv)
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[1]).toMatchObject({
writeSid: DERIVED_SID,
added: [{ path: sessionTempDir(SessionId('resumed'), ws), standing: false }],
})
const secondTemp = flag(secondConfined.argv, '--temp') ?? ''
expect(secondTemp).not.toBe(firstTemp)
expect(flag(secondConfined.argv, '--temp-write-sid')).not.toBe(flag(firstConfined.argv, '--temp-write-sid'))
expect(existsSync(firstTemp)).toBe(true)
expect(existsSync(secondTemp)).toBe(true)
await second.fiber.dispose()
await first.fiber.dispose()
} finally {
cleanup()
}
})
it('fork: a different session id derives a DIFFERENT private temp identity over the same workspace', async () => {
it('forks and workspace changes receive distinct temp capabilities while each workspace grant is reused', async () => {
try {
const { sandbox } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
const parentPolicy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('parent') }
const childPolicy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('child') }
const { sandbox, fiber } = await setup()
const wsA = workspaceRoot()
const wsB = workspaceRoot()
scratch.push(wsA, wsB)
const parent = sandbox.confine(['true'], { mode: 'workspace-write', workspaceRoot: wsA, sessionId: SessionId('parent') })
const child = sandbox.confine(['true'], { mode: 'workspace-write', workspaceRoot: wsA, sessionId: SessionId('child') })
const moved = sandbox.confine(['true'], { mode: 'workspace-write', workspaceRoot: wsB, sessionId: SessionId('parent') })
sandbox.confine(['true'], parentPolicy)
const parentTemp = sessionTempDir(SessionId('parent'), ws)
scratch.push(parentTemp)
sandbox.confine(['true'], childPolicy)
const childTemp = sessionTempDir(SessionId('child'), ws)
scratch.push(childTemp)
expect(flag(child.argv, '--temp')).not.toBe(flag(parent.argv, '--temp'))
expect(flag(child.argv, '--temp-write-sid')).not.toBe(flag(parent.argv, '--temp-write-sid'))
expect(flag(moved.argv, '--temp')).not.toBe(flag(parent.argv, '--temp'))
expect(mockState.grants).toHaveLength(5) // workspace A + two temps + workspace B + one temp
// Fresh temp identity, NOT the parent's (the workspace SID is shared by
// derivation — the workspace is the same, so the standing grant is the
// map hit and only the child's temp grant joins).
expect(childTemp).not.toBe(parentTemp)
expect(mockState.grants).toHaveLength(3)
expect(mockState.grants[2]).toMatchObject({ added: [{ path: childTemp, standing: false }] })
await fiber.dispose()
} finally {
cleanup()
}
})
it('creates the private temp dir EXCLUSIVELY: a pre-existing entry or a reparse point fails EEXIST, never receiving the temp grant', async () => {
it('workspace grant failure disposes its SID, aggregates cleanup failure, and never creates a temp directory', async () => {
try {
const { sandbox } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
// Pre-existing entry: exclusive mkdir throws EEXIST instead of adopting it.
const preexisting = sessionTempDir(SessionId('preexisting'), ws)
mkdirSync(preexisting)
scratch.push(preexisting)
const prePolicy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('preexisting') }
expect(() => sandbox.confine(['true'], prePolicy)).toThrow(/EEXIST/)
// The standing workspace grant is the intended end state and stays; the
// failed temp grant self-disposes.
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[0]!.disposed).toBe(false)
expect(mockState.grants[1]!.disposed).toBe(true) // self-revoked
// Reparse point: same EEXIST (exclusive mkdir never follows links).
const target = mkdtempSync(join(tmpdir(), 'dsh-acl-junction-target-'))
scratch.push(target)
const linkPath = sessionTempDir(SessionId('reparse'), ws)
symlinkSync(target, linkPath)
scratch.push(linkPath)
const linkPolicy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('reparse') }
expect(() => sandbox.confine(['true'], linkPolicy)).toThrow(/EEXIST/)
// Same workspace as the preexisting case: the standing workspace grant
// is the map hit (not recreated) — only the failed temp grant joins.
expect(mockState.grants).toHaveLength(3)
expect(mockState.grants[2]!.disposed).toBe(true)
// Temp-side cleanup failure: the standing workspace grant stays (map
// hit), the exclusive mkdir fails, AND the temp grant's dispose also
// fails — the temp cleanup AggregateError propagates.
mockState.grants = []
mockState.disposeFailure = new Error('temp cleanup exploded')
const dupTemp = sessionTempDir(SessionId('temp-cleanup-fail'), ws)
mkdirSync(dupTemp)
scratch.push(dupTemp)
const dupPolicy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('temp-cleanup-fail') }
expect(() => sandbox.confine(['true'], dupPolicy)).toThrow(/temp grant materialization failed and its cleanup also failed/)
expect(mockState.grants).toHaveLength(1) // only the failed temp grant (the workspace grant was the map hit)
} finally {
cleanup()
}
})
it('a grant failure mid-materialization disposes the failed grant and rethrows (AggregateError when the cleanup also fails)', async () => {
try {
const { sandbox } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
scratch.push(sessionTempDir(SessionId('sess-add-fail'), ws))
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-add-fail') }
// add() throws on the FIRST (workspace) grant: cleanup dispose() runs, original error propagates.
mockState.addFailure = new Error('grant exploded')
expect(() => sandbox.confine(['true'], policy)).toThrow('grant exploded')
mockState.addFailureStanding = true
mockState.addFailure = new Error('workspace grant exploded')
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('workspace-fail'),
})).toThrow('workspace grant exploded')
expect(mockState.grants).toHaveLength(1)
expect(mockState.grants[0]!.disposed).toBe(true)
// add() AND dispose() both throw: AggregateError.
mockState.grants = []
mockState.addFailure = new Error('grant exploded again')
mockState.disposeFailure = new Error('cleanup exploded')
expect(() => sandbox.confine(['true'], policy)).toThrow(AggregateError)
mockState.disposeFailure = new Error('workspace cleanup exploded')
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('workspace-cleanup-fail'),
})).toThrow(/workspace grant failed and its cleanup also failed/u)
expect(mockState.grants).toHaveLength(2)
} finally {
cleanup()
}
})
it('a temp add failure after the exclusive mkdir removed the half-created directory again', async () => {
it('rejects a workspace containing the ambient temp root before any ACL mutation', async () => {
const { sandbox } = await setup()
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: realpathSync.native(tmpdir()), sessionId: SessionId('overlap'),
})).toThrow(/temp root must be outside the workspace/u)
expect(mockState.grants).toHaveLength(0)
})
it('temp grant creation/add failures remove the random directory; cleanup failures aggregate', async () => {
try {
const { sandbox } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
const tempDir = sessionTempDir(SessionId('sess-temp-add-fail'), ws)
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-temp-add-fail') }
// The workspace grant succeeds; only the TEMP grant's add throws (the
// path-targeted failure keeps the workspace branch intact).
mockState.addFailurePath = tempDir
mockState.createTempFailure = new Error('temp SID creation exploded')
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('create-fail'),
})).toThrow('temp SID creation exploded')
expect(mockState.grants).toHaveLength(1) // workspace only; random temp was removed
mockState.createTempFailure = undefined
mockState.addFailureStanding = false
mockState.addFailure = new Error('temp add exploded')
expect(() => sandbox.confine(['true'], policy)).toThrow('temp add exploded')
expect(existsSync(tempDir)).toBe(false) // the half-created directory is removed again
expect(mockState.grants).toHaveLength(2)
expect(mockState.grants[0]!.disposed).toBe(false) // the standing workspace grant stays
expect(mockState.grants[1]!.disposed).toBe(true) // the failed temp grant self-disposes
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('add-fail'),
})).toThrow('temp add exploded')
const failedTempGrant = mockState.grants.at(-1)
expect(failedTempGrant?.disposed).toBe(true)
expect(failedTempGrant?.added).toHaveLength(1)
expect(existsSync(failedTempGrant?.added[0]?.path ?? '')).toBe(false)
mockState.addFailureStanding = false
mockState.addFailure = new Error('temp add exploded')
sandbox.internals.rmTempDir = () => { throw new Error('temp rm exploded') }
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('rm-fail'),
})).toThrow(/temp grant materialization failed and its cleanup also failed/u)
delete sandbox.internals.rmTempDir
mockState.addFailureStanding = false
mockState.addFailure = new Error('temp add exploded')
mockState.disposeFailure = new Error('temp cleanup exploded')
expect(() => sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('aggregate-fail'),
})).toThrow(/temp grant materialization failed and its cleanup also failed/u)
} finally {
cleanup()
}
})
it('agentless calls stay self-managed: no --write-sid, the ambient temp root, no grants', async () => {
it('agentless calls pass a temp root and no capabilities; the runner owns the private child lifecycle', async () => {
try {
const { sandbox, fiber } = await setup()
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: '/ws' }
const confined = sandbox.confine(['pwsh', '/Command', 'x'], policy)
const confined = sandbox.confine(['pwsh', '/Command', 'x'], { mode: 'workspace-write', workspaceRoot: '/ws' })
expect(confined.argv).toEqual([
'node', 'windows-acl-runner.js',
'--workspace', '/ws',
@@ -350,55 +314,26 @@ describe('windows-acl write grants (LocalSandboxProvider)', () => {
}
})
it('a failing dispose at provider teardown is reported via ctx.logger.warn and never thrown into teardown', async () => {
it('provider teardown reports grant and directory cleanup failures without aborting teardown', async () => {
try {
const { ctx, sandbox, fiber } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
scratch.push(sessionTempDir(SessionId('sess-dispose'), ws))
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-dispose') }
sandbox.confine(['true'], policy)
expect(mockState.grants).toHaveLength(2)
const confined = sandbox.confine(['true'], {
mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('dispose'),
})
const tempDir = flag(confined.argv, '--temp') ?? ''
mockState.disposeFailure = new Error('revoke exploded')
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
await fiber.dispose()
// BOTH grants (standing workspace + revocable temp) fail their dispose.
expect(warn).toHaveBeenCalledWith(expect.stringContaining('cleanup completed with 2 failure(s)'))
expect(warn).toHaveBeenCalledWith(expect.objectContaining({ message: 'revoke exploded' }))
} finally {
cleanup()
}
})
it('a failing private-temp removal at provider teardown is reported via ctx.logger.warn and never thrown into teardown', async () => {
try {
const { ctx, sandbox, fiber } = await setup()
const ws = workspaceRoot()
scratch.push(ws)
scratch.push(sessionTempDir(SessionId('sess-rm-fail'), ws))
const policy: SandboxPolicy = { mode: 'workspace-write', workspaceRoot: ws, sessionId: SessionId('sess-rm-fail') }
sandbox.confine(['true'], policy)
expect(mockState.grants).toHaveLength(2)
sandbox.internals.rmTempDir = () => { throw new Error('rm exploded') }
const warn = vi.spyOn(ctx.logger, 'warn').mockImplementation(() => undefined)
await fiber.dispose()
// Both grants dispose cleanly; only the directory removal fails.
expect(warn).toHaveBeenCalledWith(expect.stringContaining('cleanup completed with 1 failure(s)'))
expect(warn).toHaveBeenCalledWith(expect.stringContaining('cleanup completed with 3 failure(s)'))
expect(warn).toHaveBeenCalledWith(expect.objectContaining({ message: 'revoke exploded' }))
expect(warn).toHaveBeenCalledWith(expect.objectContaining({ message: 'rm exploded' }))
expect(existsSync(tempDir)).toBe(true) // injected removal failed; test cleanup reclaims it
} finally {
cleanup()
}
})
it('sessionTempDir derives the same well-shaped name for the same session and workspace, distinct otherwise', () => {
const base = sessionTempDir(SessionId('sess-a'), '/ws/a')
expect(basename(base)).toMatch(/^dsh-[0-9a-f]{16}$/)
expect(sessionTempDir(SessionId('sess-a'), '/ws/a')).toBe(base)
expect(sessionTempDir(SessionId('sess-b'), '/ws/a')).not.toBe(base) // different session
expect(sessionTempDir(SessionId('sess-a'), '/ws/b')).not.toBe(base) // different workspace
// The separator prevents id/workspace collisions from merging inputs.
expect(sessionTempDir(SessionId('ab'), '/ws/c')).not.toBe(sessionTempDir(SessionId('a'), '/ws/bc'))
})
})

2
packages/sandbox/sandbox-local/tests/local.spec.ts
View File

@@ -381,7 +381,7 @@ describe('the windows-acl probe (runner invocation contract)', () => {
const confined = sandbox.confine(['true'], RO)
expect(probeWindowsAcl).toHaveBeenCalledTimes(1)
expect(confined.argv.slice(-4)).toEqual(['--mode', 'read-only', '--', 'true'])
expect(confined.enforcement).toBe('full')
expect(confined.enforcement).toBe('partial')
expect(confined.denialSignatures).toEqual(['access is denied', 'access to the path', 'permission denied'])
expect(confined.runnerFailureRules).toEqual([{ allowedExitCodes: [127], fatalSignatures: ['windows-acl-run: '] }])
})

4
packages/sandbox/sandbox-windows-acl/README.i18n.yaml
View File

@@ -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/sandbox/sandbox-windows-acl/README.md
README.md: b13160f7490878143c719ca617936b74ffd298af
README.zh.md: 9895449f6f416ad971bbbfff700c9fd62ad99c44
README.md: 280dc2b38844feff87eb792223b87ead251f3e16
README.zh.md: 06121c3142bd788d0e1fe8cfa38fa8a668bb270a

52
packages/sandbox/sandbox-windows-acl/README.md
View File

@@ -2,52 +2,63 @@
English | [中文](README.zh.md)
Windows write-restriction sandbox backend for the [harness sandbox seam](../sandbox/): a Node.js/[koffi](https://koffi.dev/) port of the mechanism in [huoyaoyuan/windows-acl-restrict-poc](https://github.com/huoyaoyuan/windows-acl-restrict-poc) (`10e4dfb`, the fixed revision), mounted as the win32 rung of the [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) chain (`workspace-write` / `read-only` modes); the same package carries the Linux/macOS backends.
Windows write-restriction sandbox backend for the [harness sandbox seam](../sandbox/): a Node.js/[koffi](https://koffi.dev/) port of the mechanism in [huoyaoyuan/windows-acl-restrict-poc](https://github.com/huoyaoyuan/windows-acl-restrict-poc) (`10e4dfb`, the fixed revision), mounted as the `enforcement: 'partial'` win32 rung of the [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) chain (`workspace-write` / `read-only` modes); the same package carries the Linux/macOS backends.
Mechanism in one line: the caller's token is duplicated into a `WRITE_RESTRICTED` token whose restricting SIDs include a write SID (`S-1-4-x-y`) whose Write ACEs exist only on the workspace and the session's private temp directory. The write SID is the per-WORKSPACE identity, derived deterministically from the canonical workspace path (`workspaceWriteSid`), so the workspace-root ACE materializes once per workspace per machine — every later session, call, or restart hits the exact-ACE skip — instead of once per session (see [The confinement runner](#the-confinement-runner)). Windows then grants a write only where BOTH the caller's normal access AND the restricting-SID intersection allow it — the write SID is the write allowlist, and it grants nothing anywhere else on the system; the token's write check also inherits the ambient write ACEs of the OTHER restricting SIDs (the keep-alive group logon SID + Everyone — the Modes section below is the complete boundary).
Mechanism in one line: the caller's token is duplicated into a `WRITE_RESTRICTED` token whose restricting SIDs carry separate workspace and private-temp capabilities. The workspace SID is derived deterministically from the canonical workspace path (`workspaceWriteSid`), so the workspace-root ACE materializes once per workspace per machine and every later session, call, or restart hits the exact-ACE skip. Each live session/workspace pair instead receives a random temp directory and a SID derived from that path (`tempWriteSid`), so sessions share the intended workspace authority without inheriting one another's temp authority. Windows grants a write only where BOTH the caller's normal access AND the restricting-SID intersection allow it. These SIDs are the primary allowlists and grant nothing elsewhere, but the check also inherits ambient write ACEs of the OTHER restricting SIDs (the keep-alive group logon SID + Everyone), and NTFS ACLs belong to file objects rather than paths; the Everyone and hard-link boundaries are why the rung reports partial rather than full enforcement.
Building directly on the raw ACL mechanism is the recorded design choice: it implements both confinement modes without the problems the rejected container options carry — see the [design note](../../../.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md) ([mxc](https://github.com/microsoft/mxc/blob/main/docs/process-container/os-version-support.md) needs an OS floor of Windows 11 24H2 and wholesale host DACL writes for arbitrary-path reads; AppContainer cannot do arbitrary-path reads at all).
## Usage
```ts
import { AclSandbox, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
import { mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { AclSandbox, tempWriteSid, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
const workspaceRoot = process.cwd()
const tempDir = mkdtempSync(join(tmpdir(), 'dsh-'))
// mode selects the token's restricting-SID list (see Modes below) and must
// match the grant shape: read-only pairs with zero grants. workspace-write
// REQUIRES the workspace's write SID — the per-workspace identity.
const sandbox = new AclSandbox({ writableDirs: [workspaceRoot], writeSid: workspaceWriteSid(workspaceRoot), mode: 'workspace-write' })
// match the grant shape. workspace-write requires distinct workspace and
// private-temp identities; pass tempDir: null to disable temp writes.
const sandbox = new AclSandbox({
writableDirs: [workspaceRoot],
tempDir,
writeSid: workspaceWriteSid(workspaceRoot),
tempWriteSid: tempWriteSid(tempDir),
mode: 'workspace-write',
})
await sandbox.init() // throws on ANY Win32 failure — never spawns unrestricted
const child = sandbox.spawn({ command: 'pwsh', args: ['-NoProfile', '-Command', '...'], cwd: workspaceRoot })
const { stdout, stderr, exitCode } = await child.wait()
sandbox.dispose() // revokes the revocable (temp) grant, keeps the standing workspace ACE; reports every cleanup failure
rmSync(tempDir, { recursive: true, force: true })
```
A direct `AclSandbox` grants the workspace ACEs STANDING (dispose() leaves them — they are the cross-instance reuse cache) and the temp ACE revocably (dispose() revokes it, so an inheritable ACE never outlives the instance on the ambient temp root). The server-side reuse is the `AclWriteGrant` class: `add(path, standing)` per directory, `dispose()` revokes the revocable paths and frees the SID — see the runner contract below. Every Win32 API call in this package is checked; failures throw `Win32Error` carrying the API name, the exact Win32 code, the `FormatMessageW` system text, and the failing path/context. This is deliberate: the POC ignored every return value and, when `CreateRestrictedToken` failed, silently ran the child with the FULL unrestricted token (fail-open). This port fails closed by construction.
A direct `AclSandbox` requires an explicit private temp directory (or `tempDir: null`; the ambient temp root is never an implicit grant), grants the workspace ACEs STANDING (dispose() leaves them — they are the cross-instance reuse cache), and grants the distinct temp SID revocably. The server-side reuse is the `AclWriteGrant` class: `add(path, standing)` per directory, `dispose()` revokes the revocable paths and frees the SID — see the runner contract below. Every Win32 API call in this package is checked; failures throw `Win32Error` carrying the API name, the exact Win32 code, the `FormatMessageW` system text, and the failing path/context. This is deliberate: the POC ignored every return value and, when `CreateRestrictedToken` failed, silently ran the child with the FULL unrestricted token (fail-open). This port fails closed by construction.
## The confinement runner
The seam-facing shape is the **runner entry** (`./runner`), the argv-prefix wrapper `@deepseek-ai/dsh-sandbox-local` spawns in place of the caller's command — the same architecture as bwrap/landlock-run/sandbox-exec, so the sandbox seam's `confine()` contract needs no change. Stable argv contract:
```sh
node runner.js --workspace <dir> --temp <dir> --mode <read-only|workspace-write> [--write-sid <S-1-4-…>] -- <argv...>
node runner.js --workspace <dir> --temp <dir> --mode <read-only|workspace-write> [--write-sid <S-1-4-…> --temp-write-sid <S-1-4-…>] -- <argv...>
```
The runner creates the restricted token, spawns the wrapped argv under it with the caller's stdio passed straight through (the caller's pipes, made inheritable around the spawn — Node clears stdio inheritability at startup, which raw spawns must compensate for), wraps the child in a `KILL_ON_JOB_CLOSE` job (a dead runner kills the child), ignores its own console Ctrl+C so the child handles its own, mirrors the child's exit code, and revokes its temp grant on exit (workspace ACEs stand). Every runner-side failure prints `windows-acl-run: <detail>` to stderr and exits 127 — the seam's `RUNNER_FAILURE_RULES` match that signature, so a runner refusal is never mistaken for a denial.
The runner creates the restricted token, spawns the wrapped argv under it with the caller's stdio passed straight through (the caller's pipes, made inheritable around the spawn — Node clears stdio inheritability at startup, which raw spawns must compensate for), wraps the child in a `KILL_ON_JOB_CLOSE` job (a dead runner kills the child), ignores its own console Ctrl+C so the child handles its own, mirrors the child's exit code, and revokes its self-managed temp grant on exit (workspace ACEs stand). Every runner-side failure prints `windows-acl-run: <detail>` to stderr and exits 127 — the seam's `RUNNER_FAILURE_RULES` match that signature, so a runner refusal is never mistaken for a denial.
**Workspace grant reuse** (`--write-sid`): the write SID is DERIVED from the workspace path — no SID or temp-dir state is stored anywhere (the previous per-session random SID and its tamper surface are gone). The seam materializes the workspace ACE STANDING (once per workspace per server lifetime, never revoked — it is the reuse cache) and the temp ACE revocably (revoked on provider dispose), both lazily at the session's first confined execution. The session's private temp subdirectory is DERIVED from the session id + workspace (sha256, 16 hex) instead of stored: a resumed session derives the same directory and re-grants it (the exact-ACE skip keeps that O(1)), while a fork's different session id derives a fresh one. The directory is created EXCLUSIVELY — a pre-existing entry or a reparse point fails the first confined run loudly, so the grant never lands on a foreign object — and removed again on provider dispose. Under `--write-sid` the runner neither grants nor revokes (`manageDacls: false`) — the flag's presence marks the seam-managed contract, its value is the derived SID; without it (standalone use) the runner self-manages with the SAME derived SID (workspace ACEs standing, temp ACE revocable per call). Re-granting after a restart is idempotent: `grantWrite` reads the current DACL and SKIPS the `SetNamedSecurityInfoW` apply when the exact ACE already stands (that apply eagerly re-propagates the identical ACE across the whole tree — minutes on large workspaces). Standing ACEs from an unclean shutdown need no garbage collection — they ARE the cache; the same derived SID re-hits them forever. Known cost: materializing the grant on a big workspace tree blocks for the full eager propagation once per workspace per machine (the first confined write ever on this host).
**Workspace reuse and temp isolation**: the seam materializes the deterministic workspace SID's ACE STANDING (once per workspace per server lifetime, never revoked — it is the reuse cache), then creates a random private temp directory and distinct revocable SID for each live session/workspace pair. It passes both identities as the required `--write-sid`/`--temp-write-sid` pair; the runner verifies each against its owning path and neither grants nor revokes (`manageDacls: false`). A fork receives a different temp capability, and a fresh provider gives even the same resumed session a new path and SID, so crash residue is inert litter rather than a collision or inherited capability. Without the pair, `--temp` names a root: an agentless/standalone workspace-write runner creates a random private child, self-manages its temp SID, rewrites TMP/TEMP, and removes the child on exit. A workspace equal to or containing that root is rejected before any grant because its inheritable workspace ACE would otherwise authorize every private child; the direct API likewise rejects overlap between any writable root and the actual private temp directory. Re-granting the standing workspace ACE after a restart is idempotent: `grantWrite` reads the current DACL and skips `SetNamedSecurityInfoW` when the exact ACE already stands (that apply eagerly re-propagates the identical ACE across the whole tree — minutes on large workspaces). Known cost: the first grant on a big workspace tree blocks for that eager propagation once per workspace per machine.
Modes (the token's restricting-SID list follows the mode; the keep-alive group is logon SID + Everyone in BOTH modes — early DLL init dies with `0xC0000142` and CNG crashes pwsh with `0xE0434352` without them):
- `workspace-write` (logon SID, Everyone, write SID): the workspace and the session's PRIVATE temp subdirectory carry the write-SID Write grant; every other write is denied by the token intersection.
- `read-only` (logon SID, Everyone — NO write SID): STRICT zero grants — nothing is writable. The write SID stays OUT of the list on purpose: the standing workspace grant ACE from an earlier workspace-write period (a `/permission` downgrade, or a crash-resumed session) remains INERT under read-only because the write-restricted pass-2 check grants only what the restricting list carries — while the standing ACE keeps the re-upgrade free of re-propagation. NUL writes are AMBIENT, not granted: the device DACL grants Everyone read+write+execute (`0x1201BF`), so openers whose mask fits it (cmd `> NUL`, node `\\.\NUL`) can write it in BOTH modes — the sandbox cannot zero-grant the NUL device while Everyone stays in the keep-alive group. `Set-Content NUL` fails in both modes (a PowerShell/.NET-layer effect, pinned by the read-only suite — the device DACL is not the denying party); PowerShell's `> $null` redirection keeps working (it discards without opening NUL).
- `workspace-write` (logon SID, Everyone, workspace SID, temp SID): the workspace and the session's PRIVATE temp subdirectory carry separate Write grants; other ACL-addressable writes are denied except for the documented Everyone and hard-link boundaries.
- `read-only` (logon SID, Everyone — NO write SID): no explicit write-SID grants. The write SID stays OUT of the list on purpose: the standing workspace grant ACE from an earlier workspace-write period (a `/permission` downgrade, or a crash-resumed session) remains INERT under read-only because the write-restricted pass-2 check grants only what the restricting list carries — while the standing ACE keeps the re-upgrade free of re-propagation. Everyone's ambient rights remain the documented partial boundary. NUL writes are AMBIENT, not granted: the device DACL grants Everyone read+write+execute (`0x1201BF`), so openers whose mask fits it (cmd `> NUL`, node `\\.\NUL`) can write it in BOTH modes — the sandbox cannot zero-grant the NUL device while Everyone stays in the keep-alive group. `Set-Content NUL` fails in both modes (a PowerShell/.NET-layer effect, pinned by the read-only suite — the device DACL is not the denying party); PowerShell's `> $null` redirection keeps working (it discards without opening NUL).
Authenticated Users is absent from BOTH lists — the WMI namespace security check fails (`0x80041003`), so CIM cmdlets and `Get-ComputerInfo` (which silently returns incomplete results rather than an error) are unavailable in EVERY confined mode, and the C:\-root tree-creation escape (standing `AU:(AD)` + `AU:(OI)(CI)(IO)(M)` ACEs) is closed in both — the model-facing surface documents that contract, not a prompt promise. INTERACTIVE/LOCAL are absent from BOTH lists too: the host's Public tree grants write to INTERACTIVE, so Public writes are denied — pinned by the runner's ambient-writable Public-probe regression (see the design note).
The `AclSandbox` class (`tempDir: null` disables the temp grant) remains the programmatic API for direct spawns; `AclWriteGrant` is the server-side materialization half of the grant lifecycle.
The `AclSandbox` class (explicit private `tempDir` + `tempWriteSid`, or `tempDir: null` to disable temp writes) remains the programmatic API for direct spawns; `AclWriteGrant` is the server-side materialization half of the grant lifecycle.
## Header verification
@@ -61,17 +72,19 @@ The koffi struct definitions assert their sizes against the probe at module load
## Verified boundaries (inherent to restricted tokens, not this port)
- **Everyone grants remain ambient write authority.** Everyone must stay in both restricting lists: removing it breaks early DLL initialization and CNG. An external NTFS object whose normal DACL grants Everyone a requested write right therefore clears both access checks and stays writable under both modes. The real runner suite provisions an external `Everyone:Modify` directory and pins that behavior; the provider reports `enforcement: 'partial'` so callers can reject or surface the weaker boundary.
- **Hard links are file-object aliases, not path aliases.** An inheritable workspace ACE propagated onto an existing NTFS hard link changes the one underlying file security descriptor, so the same object is writable through an external alias. Rejecting every multiply-linked workspace file is not viable for ordinary pnpm installations, which use hard links into their content-addressable store; the native runner suite pins the gap and the provider's partial report names its consequence.
- **Writes are restricted; reads, network, and process visibility are not.** `WRITE_RESTRICTED` intersects write accesses only, so a confined child can read any caller-readable file and open sockets. `read-only` mode therefore cannot be expressed by this mechanism alone; pair it with a read-side policy or an AppContainer/`S-1-15-2` capability token for stronger confinement.
- **Console isolation is unavailable.** Under the restricted token, children created with `CREATE_NO_WINDOW` / `CREATE_NEW_CONSOLE` die during DLL initialization with `STATUS_DLL_INIT_FAILED` (`0xC0000142`). The POC tried to fix this by adding the console logon SID (`S-1-2-1`) to the restricting list; on Windows 11 26200 `CreateWellKnownSid(WinLocalLogonSid)` fails with `ERROR_INVALID_PARAMETER` (87), the correct `WinConsoleLogonSid` yields a valid `S-1-2-1` but the child still dies, and the POC's final revision removed both the SID and console isolation. Children therefore share the host console; stdio redirection is pipe-based and unaffected.
- **ACL grants are standing directory mutations.** They persist if the process dies mid-run; workspace ACEs are standing BY DESIGN (never revoked — the reuse cache), temp ACEs are revoked by `dispose()` (`init()` also revokes an already-applied temp grant when a later step fails). The POC's documented manual cleanup (`icacls <dir> /remove '*S-1-4-…'`) fails on this platform with `ERROR_NONE_MAPPED` (1332) — revoke through this module instead. An unclean shutdown needs no self-healing for the workspace ACE: the derived SID re-hits the standing ACE on the next provision (skipping the apply); the write-SID ACE never accumulates a second identity per restart because the identity IS the workspace.
- **Granted directories must be caller-owned.** The owner's implicit `WRITE_DAC` is what lets the sandbox edit the DACL without elevation.
- **The temp grant follows `GetTempPathW`** — pass `tempDir` explicitly whenever possible. `GetTempPathW` reads the NATIVE environment block, which host runtimes that manage `process.env` through worker pools may not keep in sync (verified with vitest: a worker-side `process.env.TMP` change never reached the native block). The seam passes the session's PRIVATE subdirectory (`<temp>\dsh-<16 hex>` derived from the session id + workspace, created exclusively — a pre-existing entry or reparse point fails loudly); a defaulted grant landing on the real temp dir inherits `(OI)(CI)` over every subdirectory of temp, silently widening the allowlist — point it at a per-sandbox directory instead.
- **The confined child's temp root is private per session** (workspace-write + `--write-sid`): the runner rewrites TMP/TEMP via `SetEnvironmentVariableW` to the session's private subdirectory before the spawn and the child inherits the rewritten block (bwrap `--tmpfs /tmp` semantics). Read-only leaves the ambient temp entries untouched — writes there are denied anyway. The subdirectory is removed on provider dispose; after a crash it may survive as plain `%TEMP%` litter until OS temp hygiene (or manual removal) reclaims it — a later resume then fails loudly at the exclusive creation.
- **The ambient temp root is never granted implicitly.** A direct `AclSandbox` workspace-write caller must supply an existing private `tempDir` plus its distinct `tempWriteSid`, or explicitly disable temp writes with `tempDir: null`. The actual temp directory must be disjoint from every writable root. The seam creates a random private directory; agentless runner calls treat `--temp` as the parent root and create their own random child, but reject a workspace equal to or containing that parent before any ACL mutation.
- **The confined child's temp capability is private per live session/workspace pair.** The runner rewrites TMP/TEMP via `SetEnvironmentVariableW` to that private directory before the spawn and the child inherits the rewritten block (bwrap `--tmpfs /tmp` semantics). The temp ACE and directory are removed on provider disposal, or after each agentless invocation. A crash can leave inert `%TEMP%` litter, but a resumed provider chooses a new random path and SID instead of colliding with or reauthorizing the residue. The native runner suite proves that two tokens sharing the same workspace SID cannot write one another's temp directories.
- **`whoami` and token-inspection cmdlets fail under the restricted token.** `GetTokenInformation` on the duplicate is partially unavailable to the child, so `whoami /all` reports errors — diagnostic noise of the restriction scheme, not an operational failure; the denial surfaces that matter (file writes) are unaffected.
## Model Experience
Indirectly, through [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md), [`dsh-pwsh-sandbox`](../../bash/pwsh-sandbox/README.md), and their tools, which render this backend's enforcement and denial facts (the confined stderr the tool layer classifies through `denialSignatures`) while the [`dsh-sandbox`](../sandbox/README.md) seam owns the `SANDBOX_UNAVAILABLE` text and runner selection.
Indirectly, through [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md), [`dsh-pwsh-sandbox`](../../bash/pwsh-sandbox/README.md), and their tools, which render this backend's partial-enforcement and denial facts (the confined stderr the tool layer classifies through `denialSignatures`) while the [`dsh-sandbox`](../sandbox/README.md) seam owns the `SANDBOX_UNAVAILABLE` text and runner selection.
#### KV Cache effect
@@ -80,12 +93,11 @@ None directly; the denial surface belongs to the tool layer.
## Known Limitations and Deferred Work
- **One write allowlist per workspace** — the write SID is the unit of the allowlist and IS the workspace identity; reusing one sandbox instance across two workspaces widens both grants to both roots (the same SID would then name two roots). Create one instance per workspace root — the seam does exactly this, keyed by the workspace path.
- **Cleanup is best-effort by design** — `dispose()` attempts every temp revocation and aggregates failures into an `AggregateError`; a cleanup failure leaves a standing (but write-SID-only) temp ACE that this process's next `init()`/`dispose()` cycle or `icacls` (via the ACE, not the trustee name) can still remove.
- **Cleanup is best-effort by design** — `dispose()` attempts every temp revocation and aggregates failures into an `AggregateError`; a cleanup failure can leave the random directory and its temp-SID-only ACE behind. Once the process exits no future token carries that SID, so the residue is inert until OS temp hygiene or manual directory removal reclaims it.
- **Standing workspace ACEs are invisible residue.** Renaming a workspace derives a new SID; the old ACEs on the old path stay (inert, write-SID-only). A future cleanup command may reap them; nothing re-propagates because of them.
- **NULL-DACL directories are not identity-preserving under grant+revoke.** A directory with a NULL DACL (rare — Windows-created directories carry real DACLs) means "everyone full control"; `grantWrite` builds the new ACL from that null, and the revoke round-trip leaves an EMPTY (deny-all) DACL rather than the original NULL DACL. The POC shares the behavior; real workspace and temp directories carry real DACLs, so this stays a documented edge rather than a guarded path.
- **Piped stdio capture is impossible for confined grandchildren (the named-pipe default SD template).** libuv's pipe stdio uses NAMED pipes; `CreateNamedPipeW` without security attributes installs the Win32 layer's user-mode default SD template (built by KernelBase — owner/SYSTEM/Admins full, Everyone/ANONYMOUS read-only, the fixed template [MS documents](https://learn.microsoft.com/en-us/windows/win32/ipc/named-pipe-security-and-access-rights)) — NOT the token default DACL, which is what the kernel applies to a raw SD-null create — so the client-end open requests write access no restricting SID is granted: `spawn(..., { stdio: 'pipe' })` inside a confined process fails with EPERM, the POC-documented "no output redirection" boundary of WRITE_RESTRICTED tokens. Inherited (`inherit`/fd) and ignored (`ignore`) stdio spawns work, and anonymous pipes (CreatePipe — a token-default-DACL consumer, e.g. PowerShell pipelines) work because the restricted token's default DACL carries a full-access restricting-SID ACE (set at init). A confined process therefore cannot capture a grandchild's output through a pipe; tools that must capture output cannot run confined.
- **Grant materialization is an eager full-tree propagation.** `SetNamedSecurityInfoW` on a directory with inheritable ACEs walks every descendant immediately (NOT lazily per access — measured at tens of seconds on large workspace trees plus the real temp root). The per-workspace identity pays it once per workspace per machine (lazily at the first confined execution ever, skipped entirely on every later provision when the exact ACE stands). If a workspace is huge, the first confined write on this host is correspondingly slow.
- **Resuming one session concurrently in two server processes fails the second at its first confined write.** Both processes derive the same private temp directory; the second one's exclusive creation hits the first one's directory and fails loudly. Single-writer session usage (the normal deployment) never sees this.
- **Grant materialization is an eager full-tree propagation.** `SetNamedSecurityInfoW` on a directory with inheritable ACEs walks every descendant immediately (NOT lazily per access — measured at tens of seconds on large workspace trees). The per-workspace identity pays it once per workspace per machine (lazily at the first confined execution ever, skipped entirely on every later provision when the exact ACE stands). Private temp directories start empty, so their distinct grant is cheap. If a workspace is huge, the first confined write on this host is correspondingly slow.
- **Read-side confinement and network policy are out of scope** — `WRITE_RESTRICTED` intersects write accesses only; pair this backend with a read-side policy for stronger confinement.
- **Wide-directory and FAT-volume warnings are deferred; FAT-class targets stay writable.** The UI-side warnings for granting unusually wide directories or FAT-class (non-ACL) volumes are not yet implemented, and a FAT volume as a grant ROOT simply fails the grant loudly (no ACL support). A FAT-class target OUTSIDE the granted roots is different: it has no security descriptors, so the restricted token's write check passes (Everyone sits in both lists) and such targets are writable under BOTH confined modes. FAT is treated as a legacy residue — unsupported and not engineered around; this warn-only posture is documented here rather than mitigated.
- **Both confined modes run `pwsh` in ConstrainedLanguage.** The restricted token trips PowerShell's lockdown detection, so under `read-only` AND `workspace-write` the language mode is ConstrainedLanguage: `Add-Type` (C# compile, P/Invoke), non-core .NET static calls (`[System.IO.*]::`, `[math]::`, `[Environment]::`), COM objects, and reflection fail with `Cannot create type` / `Cannot invoke method` ("only core types") errors, and `$ExecutionContext.SessionState.LanguageMode = 'FullLanguage'` is refused. Core cmdlets, core types (`[string]`, `[datetime]`, `[regex]`, `[guid]`), `-f` formatting, and property access keep working. The `pwsh` tool description teaches this contract to the model; `danger-full-access` calls run unconfined at FullLanguage.
- **PowerShell language mode differs by confined mode.** Under `read-only`, PowerShell cannot create its AppLocker probe files in temp and conservatively starts in ConstrainedLanguage: `Add-Type` (C# compile, P/Invoke), non-core .NET static calls (`[System.IO.*]::`, `[math]::`, `[Environment]::`), COM objects, and reflection fail with `Cannot create type` / `Cannot invoke method` ("only core types") errors, and `$ExecutionContext.SessionState.LanguageMode = 'FullLanguage'` is refused. Under the shipped `workspace-write` path, the private-temp capability lets that probe complete, so pwsh stays in FullLanguage unless host-wide WDAC/AppLocker policy says otherwise; a direct `AclSandbox` configured with `tempDir: null` has no such guarantee and can fail the probe closed like read-only. This split is PowerShell startup behavior, not part of the ACL write boundary. The `pwsh` tool description teaches the shipped modes to the model; `danger-full-access` calls run unconfined at FullLanguage.

52
packages/sandbox/sandbox-windows-acl/README.zh.md
View File

@@ -2,32 +2,43 @@
[English](README.md) | 中文
面向 [harness 沙盒 seam](../sandbox/) 的 Windows 写入限制沙盒后端：一个 Node.js/[koffi](https://koffi.dev/) 实现的、对 [huoyaoyuan/windows-acl-restrict-poc](https://github.com/huoyaoyuan/windows-acl-restrict-poc)（`10e4dfb`，修复后的修订）机制的移植，挂载为 [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) 链的 win32 一级（`workspace-write` / `read-only` 两种模式）；Linux/macOS 后端在同一包中。
面向 [harness 沙盒 seam](../sandbox/) 的 Windows 写入限制沙盒后端：一个 Node.js/[koffi](https://koffi.dev/) 实现的、对 [huoyaoyuan/windows-acl-restrict-poc](https://github.com/huoyaoyuan/windows-acl-restrict-poc)（`10e4dfb`，修复后的修订）机制的移植，挂载为 [`@deepseek-ai/dsh-sandbox-local`](../sandbox-local/) 链中报告 `enforcement: 'partial'` 的 win32 一级（`workspace-write` / `read-only` 两种模式）；Linux/macOS 后端在同一包中。
一句话机制：把调用者令牌复制为 `WRITE_RESTRICTED` 受限令牌，其 restricting SIDs 中加入一个写入 SID（`S-1-4-x-y`），该 SID 的 Write ACE 只存在于工作区与会话的私有临时目录上。写入 SID 是**按工作区**的身份，由规范工作区路径确定性派生（`workspaceWriteSid`），因此工作区根目录 ACE 每台机器每个工作区只物化一次——之后每次会话、调用、重启都命中精确 ACE 跳过——而不是每会话一次（见[隔离 runner](#the-confinement-runner)）。此后 Windows 只在「调用者正常权限」与「restricting SID 交集」同时允许时才放行写入——写入 SID 就是写入白名单，而它在系统其余位置不授予任何权限；令牌的写检查还会继承**其他** restricting SID 的环境写 ACE（保活组登录 SID + Everyone——下文「模式」段是完整边界）。
一句话机制：把调用者令牌复制为 `WRITE_RESTRICTED` 受限令牌，其 restricting SIDs 携带彼此独立的工作区能力与私有临时目录能力。工作区 SID 由规范工作区路径确定性派生（`workspaceWriteSid`），因此工作区根目录 ACE 每台机器每个工作区只物化一次，之后每次会话、调用或重启都命中精确 ACE 跳过。每个活跃的会话/工作区对则获得一个随机临时目录，以及一个从该路径派生的 SID（`tempWriteSid`），因此各会话共享预期的工作区权限，却不会继承彼此的临时目录权限。此后 Windows 只在「调用者正常权限」与「restricting SID 交集」同时允许时才放行写入。这些 SID 是主要白名单，在系统其余位置不授予任何权限；但该检查还会继承**其他** restricting SID 的环境写 ACE（保活组登录 SID + Everyone），而 NTFS ACL 属于文件对象而非路径。Everyone 与硬链接边界正是该档报告部分而非完整强制执行的原因。
直接构建在原生 ACL 机制上是记录在案的设计选择：它实现两种隔离模式，且不背负被否决的容器方案的问题——见[设计笔记](../../../.agents/notes/implemented/feature/2026-08-08-windows-acl-restricted-token-sandbox.md)（[mxc](https://github.com/microsoft/mxc/blob/main/docs/process-container/os-version-support.md) 要求 Windows 11 24H2 的 OS 下限，且任意路径读取需要整体改写宿主 DACL；AppContainer 根本无法任意路径读取）。
## 用法
```ts
import { AclSandbox, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
import { mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { AclSandbox, tempWriteSid, workspaceWriteSid } from '@deepseek-ai/dsh-sandbox-windows-acl'
const workspaceRoot = process.cwd()
const tempDir = mkdtempSync(join(tmpdir(), 'dsh-'))
// mode selects the token's restricting-SID list (see Modes below) and must
// match the grant shape: read-only pairs with zero grants. workspace-write
// REQUIRES the workspace's write SID — the per-workspace identity.
const sandbox = new AclSandbox({ writableDirs: [workspaceRoot], writeSid: workspaceWriteSid(workspaceRoot), mode: 'workspace-write' })
// match the grant shape. workspace-write requires distinct workspace and
// private-temp identities; pass tempDir: null to disable temp writes.
const sandbox = new AclSandbox({
writableDirs: [workspaceRoot],
tempDir,
writeSid: workspaceWriteSid(workspaceRoot),
tempWriteSid: tempWriteSid(tempDir),
mode: 'workspace-write',
})
await sandbox.init() // throws on ANY Win32 failure — never spawns unrestricted
const child = sandbox.spawn({ command: 'pwsh', args: ['-NoProfile', '-Command', '...'], cwd: workspaceRoot })
const { stdout, stderr, exitCode } = await child.wait()
sandbox.dispose() // revokes the revocable (temp) grant, keeps the standing workspace ACE; reports every cleanup failure
rmSync(tempDir, { recursive: true, force: true })
```
直接使用 `AclSandbox` 时，工作区 ACE 以**常驻**方式授予（`dispose()` 保留它们——它们是跨实例的复用缓存），临时 ACE 以**可回收**方式授予（`dispose()` 撤销它，这样可继承 ACE 不会在环境临时根目录上比实例活得更久）。服务端复用则是 `AclWriteGrant` 类：每个目录一次 `add(path, standing)`，`dispose()` 撤销可回收路径并释放 SID——见下方 runner 契约。本包中的每个 Win32 API 调用都有检查；失败抛出 `Win32Error`，携带 API 名、精确 Win32 错误码、`FormatMessageW` 系统文本和失败的路径/上下文。这是刻意的：POC 忽略每个返回值，当 `CreateRestrictedToken` 失败时用完整无限制令牌静默运行子进程（fail-open）。本移植从构造上 fail-closed。
直接使用 `AclSandbox` 时，必须显式提供私有临时目录（或通过 `tempDir: null` 禁用临时写入；环境临时根目录绝不会被隐式授权），工作区 ACE 以**常驻**方式授予（`dispose()` 保留它们——它们是跨实例的复用缓存），不同的临时 SID 则以**可回收**方式授予。服务端复用则是 `AclWriteGrant` 类：每个目录一次 `add(path, standing)`，`dispose()` 撤销可回收路径并释放 SID——见下方 runner 契约。本包中的每个 Win32 API 调用都有检查；失败抛出 `Win32Error`，携带 API 名、精确 Win32 错误码、`FormatMessageW` 系统文本和失败的路径/上下文。这是刻意的：POC 忽略每个返回值，当 `CreateRestrictedToken` 失败时用完整无限制令牌静默运行子进程（fail-open）。本移植从构造上 fail-closed。
<a id="the-confinement-runner"></a>
@@ -36,20 +47,20 @@ sandbox.dispose() // revokes the revocable (temp) grant, keeps the standing work
面向 seam 的形态是 **runner 入口**（`./runner`）：`@deepseek-ai/dsh-sandbox-local` 在调用者命令的位置 spawn 的 argv 前缀包装——与 bwrap/landlock-run/sandbox-exec 同一架构，因此沙盒 seam 的 `confine()` 契约无需改动。稳定的 argv 契约：
```sh
node runner.js --workspace <dir> --temp <dir> --mode <read-only|workspace-write> [--write-sid <S-1-4-…>] -- <argv...>
node runner.js --workspace <dir> --temp <dir> --mode <read-only|workspace-write> [--write-sid <S-1-4-…> --temp-write-sid <S-1-4-…>] -- <argv...>
```
runner 创建受限令牌，在它之下 spawn 包装后的 argv，调用者的 stdio 直接透传（调用者的管道在 spawn 前后被设为可继承——Node 在启动时清除 stdio 可继承性，裸 spawn 必须补偿这一点），把子进程包进 `KILL_ON_JOB_CLOSE` job（runner 死亡则子进程死亡），忽略自身的控制台 Ctrl+C 让子进程自行处理，镜像子进程的退出码，并在退出时撤销其临时授权（工作区 ACE 常驻）。每个 runner 侧失败都会向 stderr 打印 `windows-acl-run: <detail>` 并以 127 退出——seam 的 `RUNNER_FAILURE_RULES` 匹配该签名，因此 runner 拒绝永远不会被误判为拒绝授权。
runner 创建受限令牌，在它之下 spawn 包装后的 argv，调用者的 stdio 直接透传（调用者的管道在 spawn 前后被设为可继承——Node 在启动时清除 stdio 可继承性，裸 spawn 必须补偿这一点），把子进程包进 `KILL_ON_JOB_CLOSE` job（runner 死亡则子进程死亡），忽略自身的控制台 Ctrl+C 让子进程自行处理，镜像子进程的退出码，并在退出时撤销其自行管理的临时授权（工作区 ACE 常驻）。每个 runner 侧失败都会向 stderr 打印 `windows-acl-run: <detail>` 并以 127 退出——seam 的 `RUNNER_FAILURE_RULES` 匹配该签名，因此 runner 拒绝永远不会被误判为拒绝授权。
**按工作区授权复用**（`--write-sid`）：写入 SID 从工作区路径**派生**——任何地方都不存储 SID 或临时目录状态（先前每会话随机 SID 及其篡改面已移除）。seam 把工作区 ACE **常驻**物化（每个工作区每服务器生命周期一次，绝不撤销——它就是复用缓存），把临时 ACE **可回收**物化（提供方 dispose 时撤销），两者都在会话首次受限执行时惰性进行。会话的私有临时子目录由会话 id + 工作区**派生**（sha256、16 位 hex）而非存储：恢复的会话派生同一个目录并重新授权（精确 ACE 跳过使这一步保持 O(1)），而 fork 的不同会话 id 会派生出一个全新的目录。该目录以**独占**方式创建——已存在条目或重解析点会让首次受限运行大声失败，因此授权永远不会落到外部对象上——并在提供方 dispose 时再次移除。传入 `--write-sid` 时 runner 既不授权也不回收（`manageDacls: false`）——该标志的存在标记 seam 管理的契约，其值即派生 SID；不传它（独立使用）时 runner 用**同一个**派生 SID 自行管理（工作区 ACE 常驻，临时 ACE 每次调用可回收）。重启后重新授权是幂等的：`grantWrite` 读取当前 DACL，当完全相同的 ACE 已存在时跳过 `SetNamedSecurityInfoW` 的应用（该应用会把相同的 ACE 急切地重新传播到整棵树——大型工作区上以分钟计）。异常关闭遗留的 ACE 无需垃圾回收——它们**就是**缓存；同一个派生 SID 永远重新命中它们。已知代价：在大型工作区树上物化授权会阻塞整次急切传播，每台机器每个工作区一次（该主机上的第一次受限写入）。
**工作区复用与临时隔离**：seam 先把确定性工作区 SID 的 ACE **常驻**物化（每个工作区每服务器生命周期一次，绝不撤销——它就是复用缓存），再为每个活跃的会话/工作区对创建随机私有临时目录和不同的可回收 SID。它把两种身份作为必须成对出现的 `--write-sid`/`--temp-write-sid` 传入；runner 对照各自所属路径验证二者，既不授权也不撤销（`manageDacls: false`）。fork 获得不同的临时能力；即使恢复的是同一会话，新的提供方也会给出新的路径和 SID，因此崩溃残留只是失效垃圾，而非冲突或继承的能力。如果不带这一对标志，`--temp` 指定的是根目录：无 agent（智能体）/独立的 workspace-write runner 会创建随机私有子目录，自行管理其临时 SID，重写 TMP/TEMP，并在退出时移除该子目录。工作区若等于或包含该根目录，会在任何授权前被拒绝，因为否则其可继承的工作区 ACE 会向每个私有子目录授权；直接 API 同样拒绝任何可写根目录与实际私有临时目录重叠。重启后重新授权常驻工作区 ACE 是幂等的：`grantWrite` 读取当前 DACL，当完全相同的 ACE 已存在时跳过 `SetNamedSecurityInfoW`（应用该 ACE 会把相同的 ACE 急切地重新传播到整棵树——大型工作区上以分钟计）。已知代价：大型工作区树的首次授权会阻塞整次急切传播，每台机器每个工作区一次。
模式（令牌的 restricting-SID 列表随模式而变；保活组登录 SID + Everyone 在**两种**模式下都存在——没有它们早期 DLL 初始化会以 `0xC0000142` 死亡、CNG 会让 pwsh 以 `0xE0434352` 崩溃）：
- `workspace-write`（登录 SID、Everyone、写入 SID）：工作区与会话的**私有**临时子目录携带写入 SID 的 Write 授权；其余写全部被令牌交集拒绝。
- `read-only`（登录 SID、Everyone——**不含**写入 SID）：**严格零授权**——没有任何可写位置。写入 SID 有意留在列表**之外**：先前 workspace-write 时期留下的常驻授权 ACE（`/permission` 降级，或崩溃后恢复的会话）在 read-only 下保持**失效**，因为 write-restricted 的 pass-2 检查只授予 restricting 列表所携带的内容——而常驻 ACE 让重新升级免于重新传播。NUL 写入是**环境性**的、不是被授权的：设备 DACL 授予 Everyone 读+写+执行（`0x1201BF`），因此访问掩码落在其内的打开者（cmd 的 `> NUL`、node 的 `\\.\NUL`）在**两种**模式下都能写——只要 Everyone 还在保活组里，沙盒就无法把 NUL 设备归零。`Set-Content NUL` 在两种模式下都失败（PowerShell/.NET 层效应，由 read-only 套件钉住——拒绝方不是设备 DACL）；PowerShell 的 `> $null` 重定向不受影响（它直接丢弃、不打开 NUL）。
- `workspace-write`（登录 SID、Everyone、工作区 SID、临时 SID）：工作区与会话的**私有**临时子目录分别携带 Write 授权；受 ACL 管辖的其他写入都会被拒绝，已记录的 Everyone 与硬链接边界除外。
- `read-only`（登录 SID、Everyone——**不含**写入 SID）：不存在显式的写入 SID 授权。写入 SID 有意留在列表**之外**：先前 workspace-write 时期留下的常驻授权 ACE（`/permission` 降级，或崩溃后恢复的会话）在 read-only 下保持**失效**，因为 write-restricted 的 pass-2 检查只授予 restricting 列表所携带的内容——而常驻 ACE 让重新升级免于重新传播。Everyone 的环境权限仍构成已记录的部分强制执行边界。NUL 写入是**环境性**的、不是被授权的：设备 DACL 授予 Everyone 读+写+执行（`0x1201BF`），因此访问掩码落在其内的打开者（cmd 的 `> NUL`、node 的 `\\.\NUL`）在**两种**模式下都能写——只要 Everyone 还在保活组里，沙盒就无法把 NUL 设备归零。`Set-Content NUL` 在两种模式下都失败（PowerShell/.NET 层效应，由 read-only 套件钉住——拒绝方不是设备 DACL）；PowerShell 的 `> $null` 重定向不受影响（它直接丢弃、不打开 NUL）。
Authenticated Users 在**两种**列表中都不存在——WMI 命名空间安全检查失败（`0x80041003`），因此 CIM cmdlet 与 `Get-ComputerInfo`（它静默返回不完整结果而非报错）在**所有**受限模式下都不可用，且 C:\-root 树创建逃逸（常驻的 `AU:(AD)` + `AU:(OI)(CI)(IO)(M)` ACE）在两种模式下都被关闭——面向模型的表面记录的是该契约，而不是提示词承诺。INTERACTIVE/LOCAL 在两种列表中同样不存在：宿主的 Public 树向 INTERACTIVE 授予写权限，因此 Public 写入被拒绝——由 runner 的环境可写 Public 探针回归测试钉住（见设计笔记）。
`AclSandbox` 类（`tempDir: null` 禁用临时授权）仍是直接 spawn 的编程 API；`AclWriteGrant` 是授权生命周期的服务端物化一半。
`AclSandbox` 类（显式私有 `tempDir` + `tempWriteSid`，或用 `tempDir: null` 禁用临时写入）仍是直接 spawn 的编程 API；`AclWriteGrant` 是授权生命周期的服务端物化一半。
## 头部验证
@@ -63,17 +74,19 @@ koffi 结构体定义在模块加载时对照探针断言其大小，因此头
## 已验证边界（受限令牌固有，非本移植引入）
- **Everyone 授权仍是环境中的写权限来源。** Everyone 必须保留在两种 restricting 列表中：移除它会破坏早期 DLL 初始化与 CNG。因此，如果外部 NTFS 对象的正常 DACL 向 Everyone 授予所请求的写权限，它就会同时通过两次访问检查，并在两种模式下保持可写。真实 runner 套件配置一个外部 `Everyone:Modify` 目录并钉住该行为；提供方报告 `enforcement: 'partial'`，使调用方能够拒绝或向上暴露这项较弱的边界。
- **硬链接是文件对象别名，而非路径别名。** 传播到已有 NTFS 硬链接上的可继承工作区 ACE 会修改底层同一文件的安全描述符，因此同一对象也可通过外部别名写入。拒绝工作区中的所有多链接文件不具可行性，因为普通 pnpm 安装会使用硬链接指向其内容寻址存储；原生 runner 套件钉住该缺口，提供方的部分强制执行报告则点明其后果。
- **写入受限；读取、网络与进程可见性不受限。** `WRITE_RESTRICTED` 只交叉检查写访问，因此受限子进程可以读取调用者可读的任何文件并打开套接字。`read-only` 模式因而不能仅靠该机制表达；将其与读侧策略或 AppContainer/`S-1-15-2` capability 令牌配对以获得更强隔离。
- **控制台隔离不可用。** 在受限令牌下，以 `CREATE_NO_WINDOW` / `CREATE_NEW_CONSOLE` 创建的子进程在 DLL 初始化期间以 `STATUS_DLL_INIT_FAILED`（`0xC0000142`）死亡。POC 尝试把控制台登录 SID（`S-1-2-1`）加入 restricting 列表来修复；在 Windows 11 26200 上 `CreateWellKnownSid(WinLocalLogonSid)` 以 `ERROR_INVALID_PARAMETER`（87）失败，正确的 `WinConsoleLogonSid` 能产出合法 `S-1-2-1` 但子进程仍然死亡，POC 的最终修订同时移除了该 SID 与控制台隔离。子进程因此共享宿主控制台；stdio 重定向走管道，不受影响。
- **ACL 授权是对真实目录的驻留改动。** 进程中途死亡会留下授权；工作区 ACE **按设计**常驻（绝不撤销——复用缓存），临时 ACE 由 `dispose()` 撤销（后续步骤失败时 `init()` 也会撤销已应用的临时授权）。POC 注释里的手工清理命令（`icacls <dir> /remove '*S-1-4-…'`）在本平台实测失败（`ERROR_NONE_MAPPED` 1332）——请通过本模块回收。工作区 ACE 在异常关闭后无需自愈：派生 SID 在下一次供给时重新命中常驻 ACE（跳过应用）；写入 SID ACE 不会因每次重启而累积第二个身份，因为身份**就是**工作区。
- **被授权目录必须由调用者拥有。** 所有者的隐式 `WRITE_DAC` 是沙盒无需提权即可编辑 DACL 的原因。
- **临时授权跟随 `GetTempPathW`**——尽可能显式传 `tempDir`。`GetTempPathW` 读取**原生**环境块，而通过 worker 池管理 `process.env` 的宿主运行时可能没有与之保持同步（vitest 实测：worker 侧的 `process.env.TMP` 变更从未到达原生块）。seam 传入会话的**私有**子目录（`<temp>\dsh-<16 hex>`，由会话 id + 工作区派生、独占创建——已存在条目或重解析点会大声失败）；默认授权落在真实临时目录上会让 `(OI)(CI)` 继承到临时目录的每个子目录，静默扩大白名单——请改指向每个沙盒的目录。
- **受限子进程的临时根目录按会话私有**（workspace-write + `--write-sid`）：runner 在 spawn 之前用 `SetEnvironmentVariableW` 把 TMP/TEMP 改写为会话的私有子目录，子进程继承改写后的环境块（bwrap `--tmpfs /tmp` 的语义）。read-only 保持环境中的临时目录条目不动——那里的写入反正会被拒绝。子目录在提供方 dispose 时移除；崩溃后它可能作为普通 `%TEMP%` 垃圾存活，直到 OS 的临时目录卫生（或手动删除）将其回收——之后的恢复会在独占创建处大声失败。
- **环境临时根目录绝不会被隐式授权。** 直接使用 `AclSandbox` 的 workspace-write 调用方必须提供一个已存在的私有 `tempDir` 及其不同的 `tempWriteSid`，或通过 `tempDir: null` 显式禁用临时写入。实际临时目录不得与任何可写根目录重叠。seam 会创建随机私有目录；无 agent runner 调用把 `--temp` 视为父根目录并自行创建随机子目录，但如果工作区等于或包含该父根目录，就会在任何 ACL 改动前拒绝调用。
- **受限子进程的临时能力按每个活跃的会话/工作区对私有。** runner 在 spawn 之前用 `SetEnvironmentVariableW` 把 TMP/TEMP 改写为该私有目录，子进程继承改写后的环境块（bwrap `--tmpfs /tmp` 的语义）。临时 ACE 与目录会在提供方 dispose 时移除，或在每次无 agent 调用后移除。崩溃可能留下失效的 `%TEMP%` 垃圾，但恢复后的提供方会选择新的随机路径和 SID，而不会与残留发生冲突或重新向其授权。原生 runner 套件证明，共享同一工作区 SID 的两个令牌无法写入彼此的临时目录。
- **受限令牌下 `whoami` 与令牌检查 cmdlet 会失败。** 子进程对复制令牌的 `GetTokenInformation` 部分不可用，因此 `whoami /all` 报错——这是限制方案的诊断噪音，不是运行故障；真正重要的拒绝面（文件写入）不受影响。
## Model Experience
间接地通过 [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md)、[`dsh-pwsh-sandbox`](../../bash/pwsh-sandbox/README.md) 及其工具呈现：它们渲染此后端的强制与拒绝事实（工具层通过 `denialSignatures` 分类的受限 stderr），而 [`dsh-sandbox`](../sandbox/README.md) seam 拥有 `SANDBOX_UNAVAILABLE` 文本与 runner 选择。
间接地通过 [`dsh-bash-sandbox`](../../bash/bash-sandbox/README.md)、[`dsh-pwsh-sandbox`](../../bash/pwsh-sandbox/README.md) 及其工具呈现：它们渲染此后端的部分强制执行与拒绝事实（工具层通过 `denialSignatures` 分类的受限 stderr），而 [`dsh-sandbox`](../sandbox/README.md) seam 拥有 `SANDBOX_UNAVAILABLE` 文本与 runner 选择。
#### KV Cache 影响
@@ -82,12 +95,11 @@ koffi 结构体定义在模块加载时对照探针断言其大小，因此头
## Known Limitations and Deferred Work
- **每个工作区一个写入白名单** —— 写入 SID 是白名单的基本单位，且**就是**工作区身份；同一沙盒实例跨两个工作区复用时，两个根目录会互相扩大授权面（同一个 SID 将命名两个根）。请按工作区根目录各建一个实例——seam 正是这样做的，以工作区路径为键。
- **清理尽力而为** —— `dispose()` 会尝试全部临时撤销并把失败聚合为 `AggregateError`；清理失败只会留下仅含写入 SID 的临时 ACE，本进程下次 `init()`/`dispose()` 循环或 `icacls`（按 ACE 而非受托者名）仍可清除。
- **清理按设计尽力而为** —— `dispose()` 会尝试全部临时撤销并把失败聚合为 `AggregateError`；清理失败可能留下随机目录及其仅含临时 SID 的 ACE。进程退出后，不会再有令牌携带该 SID，因此残留保持失效，直到 OS 临时目录卫生或手动移除目录将其回收。
- **常驻工作区 ACE 是不可见残留。** 工作区改名会派生新的 SID；旧路径上的旧 ACE 留在原地（失效、仅含写入 SID）。未来的清理命令可以回收它们；它们不会引起任何重新传播。
- **NULL-DACL 目录在 grant+revoke 往返下不保持身份。** 带 NULL DACL 的目录（罕见——Windows 创建的目录都带真实 DACL）意味着「所有人完全控制」；`grantWrite` 从该 null 构建新 ACL，撤销往返后留下的是 EMPTY（全部拒绝）DACL 而非原始 NULL DACL。POC 行为相同；真实工作区与临时目录都带真实 DACL，因此这仍是记录在案的边界情形而非守护路径。
- **受限孙进程的管道 stdio 捕获不可用（named pipe 的默认 SD 模板）。** libuv 的管道 stdio 用的是 NAMED pipe；不带安全属性调用 `CreateNamedPipeW` 时，其默认安全描述符不是内核的模板，而是 Win32 层在用户态安装的默认 SD 模板（由 KernelBase 构建——owner/SYSTEM/Admins 全权，Everyone/ANONYMOUS 只读，即 [MS 文档](https://learn.microsoft.com/en-us/windows/win32/ipc/named-pipe-security-and-access-rights)记载的固定模板）——**不是**令牌默认 DACL（后者才是内核在原始 SD-null 创建时应用的）——因此 client 端打开所请求的写访问没有任何 restricting SID 被授予：受限进程内 `spawn(..., { stdio: 'pipe' })` 以 EPERM 失败，这是 POC 记载的 WRITE_RESTRICTED「无法重定向输出」边界。继承（`inherit`/fd）与忽略（`ignore`）stdio 的 spawn 可用；匿名管道（CreatePipe——令牌默认 DACL 的消费者，例如 PowerShell 的管道）因受限令牌默认 DACL 携带 restricting SID 全权 ACE（init 时写入）而可用。受限进程因此无法用管道捕获孙进程输出；必须捕获输出的工具无法在受限下运行。
- **授权物化是急切的全树传播。** 在带可继承 ACE 的目录上调用 `SetNamedSecurityInfoW` 会立即遍历每个后代（**不是**按访问惰性进行——大型工作区树上实测数十秒，加上真实临时根目录）。按工作区身份每台机器每个工作区只付一次（在首次受限执行时惰性进行，之后每次供给在精确 ACE 常驻时完全跳过）。如果工作区巨大，该主机上的第一次受限写入相应变慢。
- **两个服务器进程并发恢复同一会话时，第二个会在其首次受限写入处失败。** 两个进程派生同一个私有临时目录；第二个的独占创建撞上第一个的目录并大声失败。单写者会话用法（常规部署）永远不会遇到。
- **授权物化是急切的全树传播。** 在带可继承 ACE 的目录上调用 `SetNamedSecurityInfoW` 会立即遍历每个后代（**不是**按访问惰性进行——大型工作区树上实测数十秒）。按工作区身份每台机器每个工作区只付一次（在首次受限执行时惰性进行，之后每次供给在精确 ACE 常驻时完全跳过）。私有临时目录创建时为空，因此其独立授权开销很小。如果工作区巨大，该主机上的第一次受限写入相应变慢。
- **读侧隔离与网络策略不在范围内** —— `WRITE_RESTRICTED` 只交叉检查写访问；将此后端与读侧策略配对以获得更强隔离。
- **宽目录与 FAT 卷警告已推迟；FAT 类目标保持可写。** 对异常宽的目录或 FAT 类（非 ACL）卷的 UI 侧警告尚未实现，且 FAT 卷作为授权**根**只会大声失败（无 ACL 支持）。授权根**之外**的 FAT 类目标则不同：它没有安全描述符，因此受限令牌的写检查通过（Everyone 在两种列表中都在）——此类目标在**两种**受限模式下都可写。FAT 被视为遗留残留——不受支持、不围绕它设计；此处记录的是这种仅警告的立场，而非缓解措施。
- **两种受限模式都运行 ConstrainedLanguage 的 `pwsh`。** 受限令牌会触发 PowerShell 的锁定检测，因此在 `read-only` **和** `workspace-write` 下语言模式都是 ConstrainedLanguage：`Add-Type`（C# 编译、P/Invoke）、非核心 .NET 静态调用（`[System.IO.*]::`、`[math]::`、`[Environment]::`）、COM 对象与反射以 `Cannot create type` / `Cannot invoke method`（「only core types」）错误失败，且 `$ExecutionContext.SessionState.LanguageMode = 'FullLanguage'` 被拒绝。核心 cmdlet、核心类型（`[string]`、`[datetime]`、`[regex]`、`[guid]`）、`-f` 格式化与属性访问保持可用。`pwsh` 工具描述向模型传授该契约；`danger-full-access` 调用不受限地在 FullLanguage 下运行。
- **PowerShell 语言模式因受限模式而异。** 在 `read-only` 下，PowerShell 无法在临时目录中创建 AppLocker 探针文件，因此会保守地以 ConstrainedLanguage 启动：`Add-Type`（C# 编译、P/Invoke）、非核心 .NET 静态调用（`[System.IO.*]::`、`[math]::`、`[Environment]::`）、COM 对象与反射以 `Cannot create type` / `Cannot invoke method`（「only core types」）错误失败，且 `$ExecutionContext.SessionState.LanguageMode = 'FullLanguage'` 被拒绝。交付的 `workspace-write` 路径拥有私有临时目录能力，可使该探针完成，因此除非主机范围的 WDAC/AppLocker 策略另有规定，否则 pwsh 保持 FullLanguage；直接使用 `AclSandbox` 并配置 `tempDir: null` 时则没有这一保证，探针可能像 read-only 一样失败并按 fail-closed 处理。这一区别属于 PowerShell 启动行为，不是 ACL 写入边界的一部分。`pwsh` 工具描述向模型传授这些交付模式；`danger-full-access` 调用不受限地在 FullLanguage 下运行。

2
packages/sandbox/sandbox-windows-acl/package.json
View File

@@ -1,6 +1,6 @@
{
"name": "@deepseek-ai/dsh-sandbox-windows-acl",
"description": "Windows ACL write-restriction sandbox backend (restricted-token spawn with orphan-SID write allowlist) for the DeepSeek Harness sandbox seam",
"description": "Windows ACL write-restriction sandbox backend (restricted-token spawn with capability-SID write allowlist) for the DeepSeek Harness sandbox seam",
"version": "0.0.1-rc.1",
"publishConfig": {
"access": "restricted"

20
packages/sandbox/sandbox-windows-acl/src/acl.ts
View File

@@ -1,5 +1,5 @@
/**
* ACL editing helpers: grant/revoke the orphan write SID on a directory via
* ACL editing helpers: grant/revoke a capability SID on a directory via
* SetEntriesInAclW + SetNamedSecurityInfoW (the same calls the POC uses, with
* the failure handling the POC lacks). Every API call is checked and every
* failure is reported with the API name, the exact Win32 code, the formatted
@@ -39,7 +39,7 @@ export function buildExplicitAccess(sidPtr: NativePtr, mode: number, permissions
entry.writeUInt32LE(abi.NO_MULTIPLE_TRUSTEE, 24) // Trustee.MultipleTrusteeOperation
entry.writeUInt32LE(abi.TRUSTEE_IS_SID, 28) // Trustee.TrusteeForm
entry.writeUInt32LE(abi.TRUSTEE_IS_UNKNOWN, 32) // Trustee.TrusteeType
entry.writeBigUInt64LE(ptrAddress(sidPtr), 40) // Trustee.ptstrName = the orphan SID
entry.writeBigUInt64LE(ptrAddress(sidPtr), 40) // Trustee.ptstrName = the capability SID
return entry
}
@@ -181,16 +181,16 @@ function mergeAndApply(
/**
* True when the explicit DACL already carries the EXACT write grant this
* module would add (Allow ACE, OI|CI inheritance, {@link abi.GRANT_MASK}, the
* orphan SID). Every field is read through koffi.decode at pointer offsets —
* capability SID). Every field is read through koffi.decode at pointer offsets —
* no memcpy, no pointer arithmetic. The ACE's SID is INLINE (embedded in the
* ACE after the 4-byte mask — there is no pointer to read; reading one
* yields garbage addresses and crashed EqualSid, verified by gdb), so it is
* compared field-by-field against the orphan SID through bounded offset
* compared field-by-field against the capability SID through bounded offset
* reads ({@link sameSidAt}). A malformed header reads as "no exact grant"
* so the caller falls back to the merge-apply path, which owns the robust
* failure handling.
* @param oldAcl - the current explicit DACL pointer (from {@link readCurrentDacl}).
* @param sidPtr - the orphan write SID to match.
* @param sidPtr - the capability SID to match.
* @returns whether the exact grant ACE is already present.
*/
function hasExactGrant(oldAcl: NativePtr, sidPtr: NativePtr): boolean {
@@ -213,7 +213,7 @@ function hasExactGrant(oldAcl: NativePtr, sidPtr: NativePtr): boolean {
}
/**
* Grant `GRANT_MASK` (Write+Delete, displays as "Modify") to the orphan SID
* Grant `GRANT_MASK` (Write+Delete, displays as "Modify") to the capability SID
* on `path`, inheriting to subcontainers and objects. Idempotent: when the
* directory's current explicit DACL already carries the exact ACE (the
* per-session grant surviving from a previous server lifetime), the
@@ -226,7 +226,7 @@ function hasExactGrant(oldAcl: NativePtr, sidPtr: NativePtr): boolean {
* precondition as the POC.
* @param api - the binding table.
* @param path - the directory whose DACL gains the grant (the workspace or temp root).
* @param sidPtr - the orphan write SID the ACE names.
* @param sidPtr - the capability SID the ACE names.
*/
export function grantWrite(api: Win32Bindings, path: string, sidPtr: NativePtr): void {
withPathLock(api, path, () => {
@@ -244,15 +244,15 @@ export function grantWrite(api: Win32Bindings, path: string, sidPtr: NativePtr):
}
/**
* Remove every ACE for the orphan SID from the directory DACL (REVOKE_ACCESS
* Remove every ACE for the capability SID from the directory DACL (REVOKE_ACCESS
* merge — other entries are preserved). Returns whether an ACE removal was
* attempted (false when the directory carries no DACL at all).
*
* Runs under the per-path lock (the whole get-merge-set sequence); the
* descriptor/ACL allocation contract lives on {@link readCurrentDacl}.
* @param api - the binding table.
* @param path - the directory whose DACL loses the orphan-SID ACEs.
* @param sidPtr - the orphan write SID whose ACEs are removed.
* @param path - the directory whose DACL loses the capability-SID ACEs.
* @param sidPtr - the capability SID whose ACEs are removed.
* @returns whether an ACE removal was attempted (false when the directory carries no DACL at all).
*/
export function revokeWrite(api: Win32Bindings, path: string, sidPtr: NativePtr): boolean {

17
packages/sandbox/sandbox-windows-acl/src/grant.ts
View File

@@ -1,12 +1,9 @@
/**
* Server-side per-session write grant: the ACE materialization half of the
* sandbox seam's per-session grant reuse. The seam (sandbox-local) holds ONE
* {@link AclWriteGrant} per session for the server process's lifetime —
* created lazily at the session's first confined execution, reused (never
* re-applied) for every later call, revoked on provider dispose. The durable
* half (the session's SID and paths surviving a restart) lives in the
* session log, owned by the seam; this module owns only the native half: the
* parsed SID pointer and the standing ACEs.
* Server-side write-grant materialization. The sandbox seam holds one
* standing workspace grant per workspace and one revocable temp grant per
* live session/workspace pair. Workspace identities survive by deterministic
* derivation and their standing ACE; temp identities derive from random
* private paths and are deliberately new after a restart.
*
* Fail-closed: `add` throws on any grant failure and the caller disposes the
* instance (revoking every path granted so far); `dispose` revokes every
@@ -19,7 +16,7 @@ import { allocPtrSlot, decodePtr, isNullPtr, throwLastError, win32Sync } from '.
import type { NativePtr, Win32Bindings } from './ffi.ts'
/**
* One write SID's server-lifetime grant materialization: the parsed SID
* One write SID's provider-lifetime grant materialization: the parsed SID
* pointer plus every directory whose DACL currently carries its ACE.
* Workspace paths are added STANDING (their ACEs are the cross-session reuse
* cache and outlive the grant — dispose() skips revoking them, or the next
@@ -45,7 +42,7 @@ export class AclWriteGrant {
/**
* Parse the SID string and open the binding table (lazily, once per
* server). Fail-closed: any failure throws — nothing is granted yet.
* @param writeSid - the orphan write SID string (`S-1-4-x-y`).
* @param writeSid - the workspace (`S-1-4-x-y`) or temp (`S-1-4-x-y-1`) capability SID string.
* @param api - optional already-resolved bindings (tests).
* @returns the ready grant (no ACEs yet).
*/

226
packages/sandbox/sandbox-windows-acl/src/index.ts
View File

@@ -2,10 +2,10 @@
* Windows ACL write-restriction sandbox backend for the DeepSeek Harness
* sandbox seam. Mirrors the mechanism of github.com/huoyaoyuan/
* windows-acl-restrict-poc @ 10e4dfb (the fixed revision): a WRITE_RESTRICTED
* token whose restricting SIDs include a write SID (`S-1-4-x-y`) that only
* this sandbox adds to the target directories' DACLs — the intersection
* check then allows writes exactly where that SID has a Write ACE, and
* nowhere else the write SID is concerned (the token's write check ALSO
* token whose restricting SIDs include distinct workspace and temp write
* SIDs that this sandbox adds to their owning directories' DACLs — the
* intersection check then allows writes exactly where either capability has
* a Write ACE, and nowhere else those SIDs are concerned (the check ALSO
* inherits the ambient write ACEs of the other restricting SIDs — the
* keep-alive group logon SID + Everyone; Authenticated Users, INTERACTIVE,
* and LOCAL are absent from both lists — see the seam's dual-list contract
@@ -15,7 +15,9 @@
* path, so the workspace-root ACE materializes once per workspace per
* machine and every later provision hits the exact-ACE skip — the
* grant-reuse story the per-session random SID paid a full tree propagation
* per session for. Unlike the POC, every API failure throws with the API
* per session for. Each private temp directory instead receives its own SID,
* so sibling sessions sharing a workspace cannot enter one another's temp
* trees. Unlike the POC, every API failure throws with the API
* name and exact Win32 code; a child is NEVER spawned unrestricted.
*
* Known boundaries (inherent to restricted tokens, not this port):
@@ -24,15 +26,14 @@
* - console isolation is unavailable — children share the host console
* (CREATE_NO_WINDOW / CREATE_NEW_CONSOLE children die with
* STATUS_DLL_INIT_FAILED under the restriction);
* - the temp directory and every writable directory must be owned by the
* - the private temp directory and every writable directory must be owned by the
* caller (owner-implicit WRITE_DAC);
* - grants are standing ACE mutations on real directories. WORKSPACE grants
* are deliberately never revoked — the ACE is the cross-session reuse
* cache (revoking would force the next session to re-propagate the whole
* tree). TEMP grants are revocable: dispose() removes them so a standing
* inheritable ACE never outlives its session's temp directory (an
* inheritable ACE on the ambient temp root would otherwise widen the
* SID's write reach to every future temp file). With `manageDacls: false`
* inheritable ACE never outlives its session's temp directory. The
* ambient temp root is never granted implicitly. With `manageDacls: false`
* the CALLER owns the DACLs (the sandbox seam's grant reuse):
* init()/dispose() skip grant/revoke entirely and the caller must not
* revoke under live children.
@@ -44,26 +45,27 @@ import { resolve } from 'node:path'
import { grantWrite, revokeWrite } from './acl.ts'
import { Win32Error } from './errors.ts'
import { allocPtrSlot, decodePtr, getTempPath, isNullPtr, throwLastError, win32 } from './ffi.ts'
import { allocPtrSlot, decodePtr, isNullPtr, throwLastError, win32 } from './ffi.ts'
import type { NativePtr, Win32Bindings } from './ffi.ts'
import { assertPrivateTempDisjoint } from './path-boundary.ts'
import { drainPipe, spawnSandboxed, spawnSandboxedInherited, waitForExit } from './spawn.ts'
import { createRestrictedToken, findLogonSid, makeWellKnownSid, openCurrentProcessToken, setTokenDefaultDaclGrant } from './token.ts'
import * as abi from './win32-abi.ts'
export { quoteArg } from './spawn.ts'
export { AclWriteGrant } from './grant.ts'
export { workspaceWriteSid } from './workspace-sid.ts'
export { assertTempRootOutsideWorkspace } from './path-boundary.ts'
export { tempWriteSid, workspaceWriteSid } from './workspace-sid.ts'
export { Win32Error } from './errors.ts'
/** Construction options: the write allowlist, the optional temp grant, and the orphan SID identity. */
/** Construction options: the workspace/temp allowlists and their distinct SID identities. */
export interface AclSandboxOptions {
/** Directories the confined child may write into (must exist and be caller-owned). */
writableDirs: readonly string[]
/**
* Temp directory to also grant; defaults to GetTempPathW() at init time.
* Pass null for read-only confinement: NO temp grant (strict zero grant on
* the filesystem; the NUL device stays ambient-writable via Everyone — see
* README).
* Existing private temp directory to grant. Workspace-write callers must
* pass it explicitly or pass null to disable temp writes; the ambient temp
* root is never an implicit grant. Read-only accepts only null/undefined.
*/
tempDir?: string | null
/**
@@ -74,6 +76,13 @@ export interface AclSandboxOptions {
* outlives every instance and later provisions hit the exact-ACE skip.
*/
writeSid?: string
/**
* The private temp directory's write SID. Required whenever
* workspace-write grants a temp directory, absent otherwise. It must be
* distinct from {@link writeSid}, so sibling sessions sharing a workspace
* cannot use the standing workspace capability in one another's temp tree.
*/
tempWriteSid?: string
/**
* The file-effect mode this instance confines under — selects the
* restricted token's restricting-SID list (I for read-only, J for
@@ -85,7 +94,7 @@ export interface AclSandboxOptions {
/**
* Whether this instance owns its DACL grants (default true). False means
* the CALLER has already materialized the ACEs (the sandbox seam's
* per-session grant reuse): init()/dispose() skip grant/revoke entirely —
* workspace/temp capability lifecycle): init()/dispose() skip grant/revoke entirely —
* the caller holds the grants for its own lifetime and revokes them.
*/
manageDacls?: boolean
@@ -123,6 +132,22 @@ export interface AclSandboxChild {
wait(): Promise<AclSandboxChildResult>
}
/** Free one optional SID while retaining a failure for best-effort sibling cleanup. */
function freeSidBestEffort(
api: Win32Bindings,
sidPtr: NativePtr | undefined,
label: string,
failures: unknown[],
): void {
if (sidPtr === undefined) return
try {
const freed = api.localFree(sidPtr)
if (!isNullPtr(freed)) throwLastError(api, 'LocalFree', label)
} catch (error) {
failures.push(error)
}
}
/**
* One write-restricted sandbox instance: token + write-SID grants + spawn.
* `init()` is fail-closed — any Win32 failure revokes the revocable (temp)
@@ -135,8 +160,10 @@ export interface AclSandboxChild {
export class AclSandbox {
/** Absolute writable directories (constructor-validated). */
readonly writableDirs: string[]
/** The write SID string whose ACEs form the write allowlist (workspace-write only). */
/** The workspace SID string whose ACEs form the workspace allowlist. */
readonly writeSid: string | undefined
/** The private temp directory's write SID (workspace-write with temp only). */
readonly tempWriteSid: string | undefined
/** The file-effect mode — the restricted token's restricting-SID list selection. */
readonly mode: 'read-only' | 'workspace-write'
private readonly tempDirOption: string | null | undefined
@@ -145,9 +172,10 @@ export class AclSandbox {
private api: Win32Bindings | undefined
private token: NativePtr | undefined
private writeSidPtr: NativePtr | undefined
/** The well-known/logon SID allocations init() makes; freed by dispose() alongside the write SID. */
private tempWriteSidPtr: NativePtr | undefined
/** The well-known/logon SID allocations init() makes; freed by dispose() alongside the write SIDs. */
private sidAllocations: NativePtr[] = []
private grantedPaths: string[] = []
private grantedPaths: Array<{ path: string; sidPtr: NativePtr }> = []
constructor(options: AclSandboxOptions) {
this.mode = options.mode
@@ -161,9 +189,28 @@ export class AclSandbox {
})
this.tempDirOption = options.tempDir
this.writeSid = options.writeSid
this.tempWriteSid = options.tempWriteSid
if (this.mode === 'workspace-write' && this.writeSid === undefined) {
throw new Error('AclSandbox workspace-write requires a write SID — derive it from the workspace via workspaceWriteSid()')
}
if (this.mode === 'workspace-write' && this.tempDirOption === undefined) {
throw new Error('AclSandbox workspace-write requires an explicit private temp directory or null')
}
if (this.mode === 'read-only' && this.tempDirOption !== undefined && this.tempDirOption !== null) {
throw new Error('AclSandbox read-only does not accept a temp directory')
}
if (this.mode === 'read-only' && (this.writeSid !== undefined || this.tempWriteSid !== undefined)) {
throw new Error('AclSandbox read-only does not accept write SIDs')
}
if (this.mode === 'workspace-write' && this.tempDirOption !== null && this.tempWriteSid === undefined) {
throw new Error('AclSandbox workspace-write with temp requires a temp write SID — derive it via tempWriteSid()')
}
if (this.tempDirOption === null && this.tempWriteSid !== undefined) {
throw new Error('AclSandbox temp write SID requires a temp directory')
}
if (this.writeSid !== undefined && this.tempWriteSid === this.writeSid) {
throw new Error('AclSandbox workspace and temp write SIDs must be distinct')
}
}
/** Resolved temp directory (available after init; null when temp grants are disabled). */
@@ -171,56 +218,56 @@ export class AclSandbox {
return this.tempDirResolved
}
/** Create the restricted token and apply the orphan-SID grants. Idempotent-unsafe: once per instance. */
/** Create the restricted token and apply the capability-SID grants. Idempotent-unsafe: once per instance. */
async init(): Promise<void> {
if (this.api !== undefined) throw new Error('AclSandbox is already initialized')
const api = await win32()
const currentToken = openCurrentProcessToken(api)
let currentTokenOpen = true
let restrictedToken: NativePtr | undefined
try {
// Read-only runs carry no write SID (its restricting list has no
// orphan): nothing to parse, nothing to grant.
let writeSidPtr: NativePtr | undefined
if (this.writeSid !== undefined) {
const parseSid = (sid: string): NativePtr => {
const sidSlot = allocPtrSlot()
if (api.convertStringSidToSidW(this.writeSid, sidSlot) === 0) {
throwLastError(api, 'ConvertStringSidToSidW', this.writeSid)
if (api.convertStringSidToSidW(sid, sidSlot) === 0) {
throwLastError(api, 'ConvertStringSidToSidW', sid)
}
const parsedSid = decodePtr(sidSlot)
if (parsedSid === null) throw new Win32Error('ConvertStringSidToSidW', api.getLastError(), this.writeSid)
this.writeSidPtr = parsedSid
writeSidPtr = parsedSid
if (parsedSid === null) throw new Win32Error('ConvertStringSidToSidW', api.getLastError(), sid)
return parsedSid
}
this.writeSidPtr = this.writeSid === undefined ? undefined : parseSid(this.writeSid)
this.tempWriteSidPtr = this.tempWriteSid === undefined ? undefined : parseSid(this.tempWriteSid)
const tempDir = this.tempDirOption === null
? null
: this.tempDirOption !== undefined ? this.tempDirOption : getTempPath(api)
const tempDir = this.mode === 'read-only' || this.tempDirOption === null ? null : this.tempDirOption
/* v8 ignore next -- constructor validation requires workspace-write to supply
an explicit temp directory or null; the other branches normalize to null. */
if (tempDir === undefined) throw new Error('AclSandbox workspace-write temp directory was not resolved')
if (tempDir !== null) {
if (!existsSync(tempDir) || !statSync(tempDir).isDirectory()) {
throw new Error(`AclSandbox temp dir does not exist or is not a directory: ${tempDir}`)
}
this.tempDirResolved = tempDir
assertPrivateTempDisjoint(this.writableDirs, tempDir)
}
this.tempDirResolved = tempDir
// manageDacls: false — the caller (the sandbox seam's grant) already
// materialized the ACEs; this instance must neither add nor remove any.
// When this instance owns the DACLs, writableDir ACEs are STANDING (the
// per-workspace reuse cache — dispose() never revokes them, or the next
// provision would re-propagate the whole tree) and the temp ACE is
// REVOCABLE (dispose() removes it — an inheritable ACE on the ambient
// temp root must not outlive the instance, or it would widen the SID's
// write reach to every future temp file).
// REVOCABLE (dispose() removes it before the private directory is
// deleted; the ambient temp root is never granted).
if (this.manageDacls) {
if (writeSidPtr !== undefined) {
if (this.writeSidPtr !== undefined) {
for (const path of this.writableDirs) {
grantWrite(api, path, writeSidPtr)
grantWrite(api, path, this.writeSidPtr)
}
if (tempDir !== null) {
if (tempDir !== null && this.tempWriteSidPtr !== undefined) {
// Record BEFORE granting: grantWrite can throw after a successful
// apply (a LocalFree failure), and the fail-closed catch must still
// revoke that path (revoking an ungranted path is a no-op merge).
this.grantedPaths.push(tempDir)
grantWrite(api, tempDir, writeSidPtr)
this.grantedPaths.push({ path: tempDir, sidPtr: this.tempWriteSidPtr })
grantWrite(api, tempDir, this.tempWriteSidPtr)
}
}
}
@@ -228,58 +275,63 @@ export class AclSandbox {
this.sidAllocations.push(logonSid)
const worldSid = makeWellKnownSid(api, abi.WinWorldSid)
this.sidAllocations.push(worldSid)
const restricted = createRestrictedToken(
api, currentToken, logonSid, writeSidPtr,
const writeSids = [this.writeSidPtr, this.tempWriteSidPtr].filter((sid): sid is NativePtr => sid !== undefined)
restrictedToken = createRestrictedToken(
api, currentToken, logonSid, writeSids,
{ world: worldSid },
this.mode,
)
this.token = restrictedToken
// The restricted token's default DACL still names only the user's
// ambient SIDs — none of the restricting SIDs. Every NEW object the
// confined process creates (anonymous stdio pipes, sync objects) takes
// its DACL from that default, so the write pass-2 check would deny
// pipe creation (ERROR_ACCESS_DENIED; Node EPERM) and break every
// piped-stdio grandchild spawn. Merge a full-access ACE for a
// restricting SID (the write SID under workspace-write, Everyone under
// read-only): new-object creation stays gated by the parent object's
// DACL, while the new object's own DACL passes pass-2.
setTokenDefaultDaclGrant(api, restricted, writeSidPtr ?? worldSid)
this.token = restricted
// restricting SID (the PRIVATE temp SID when present, otherwise the
// workspace SID, or Everyone under read-only): new-object creation
// stays gated by the parent object's DACL, while the new object's own
// DACL passes pass-2. Choosing the temp SID prevents default-DACL
// objects in one session's temp tree from acquiring the shared
// workspace capability.
setTokenDefaultDaclGrant(api, restrictedToken, this.tempWriteSidPtr ?? this.writeSidPtr ?? worldSid)
if (api.closeHandle(currentToken) === 0) throwLastError(api, 'CloseHandle', 'current process token')
currentTokenOpen = false
this.api = api
} catch (error) {
// Best-effort close on the failure path (last error already captured in `error`).
api.closeHandle(currentToken)
// FIXME(windows-acl): a failure after createRestrictedToken leaks the restricted
// token handle and the parsed write SID — this.api stays undefined, so dispose()
// early-returns and cannot clean them up. Close the token and free the write SID
// here (the hardening-followup rework already does both).
// Fail-closed cleanup: revoke the revocable (temp) grants and free the init SID
// allocations a failed init left behind. Standing workspace ACEs are NOT
// Fail-closed cleanup: never leave a revocable (temp) grant or SID
// allocation behind a failed init. Standing workspace ACEs are NOT
// revoked — they are the intended end state (the reuse cache), not an
// error artifact.
const cleanupFailures: unknown[] = []
const writeSidPtr = this.writeSidPtr
if (writeSidPtr !== undefined) {
for (const path of this.grantedPaths) {
try {
revokeWrite(api, path, writeSidPtr)
} catch (cleanupError) {
cleanupFailures.push(cleanupError)
}
}
if (currentTokenOpen && api.closeHandle(currentToken) === 0) {
cleanupFailures.push(new Win32Error('CloseHandle', api.getLastError(), 'current process token after init failure'))
}
for (const sidPtr of this.sidAllocations.splice(0)) {
if (restrictedToken !== undefined && api.closeHandle(restrictedToken) === 0) {
cleanupFailures.push(new Win32Error('CloseHandle', api.getLastError(), 'restricted token after init failure'))
}
for (const grant of this.grantedPaths) {
try {
const freed = api.localFree(sidPtr)
if (!isNullPtr(freed)) throwLastError(api, 'LocalFree', 'init SID allocation')
revokeWrite(api, grant.path, grant.sidPtr)
} catch (cleanupError) {
cleanupFailures.push(cleanupError)
}
}
for (const [label, sidPtr] of [['workspace write SID', this.writeSidPtr], ['temp write SID', this.tempWriteSidPtr]] as const) {
freeSidBestEffort(api, sidPtr, label, cleanupFailures)
}
for (const sidPtr of this.sidAllocations.splice(0)) {
freeSidBestEffort(api, sidPtr, 'init SID allocation', cleanupFailures)
}
this.token = undefined
this.writeSidPtr = undefined
this.tempWriteSidPtr = undefined
this.tempDirResolved = undefined
this.grantedPaths = []
if (cleanupFailures.length > 0) {
throw new AggregateError(
[error, ...cleanupFailures],
`AclSandbox init failed and ${cleanupFailures.length} grant revocation(s) also failed`,
`AclSandbox init failed and ${cleanupFailures.length} cleanup operation(s) also failed`,
)
}
throw error
@@ -345,23 +397,17 @@ export class AclSandbox {
const api = this.api
if (api === undefined) return
const failures: unknown[] = []
const writeSidPtr = this.writeSidPtr
if (writeSidPtr !== undefined) {
if (this.manageDacls) {
for (const path of this.grantedPaths) {
try {
revokeWrite(api, path, writeSidPtr)
} catch (error) {
failures.push(error)
}
if (this.manageDacls) {
for (const grant of this.grantedPaths) {
try {
revokeWrite(api, grant.path, grant.sidPtr)
} catch (error) {
failures.push(error)
}
}
try {
const freed = api.localFree(writeSidPtr)
if (!isNullPtr(freed)) throwLastError(api, 'LocalFree', 'write SID')
} catch (error) {
failures.push(error)
}
}
for (const [label, sidPtr] of [['workspace write SID', this.writeSidPtr], ['temp write SID', this.tempWriteSidPtr]] as const) {
freeSidBestEffort(api, sidPtr, label, failures)
}
const token = this.token
/* v8 ignore next -- init assigns this.api only after this.token, so an initialized instance always
@@ -374,16 +420,12 @@ export class AclSandbox {
}
}
for (const sidPtr of this.sidAllocations.splice(0)) {
try {
const freed = api.localFree(sidPtr)
if (!isNullPtr(freed)) throwLastError(api, 'LocalFree', 'init SID allocation')
} catch (error) {
failures.push(error)
}
freeSidBestEffort(api, sidPtr, 'init SID allocation', failures)
}
this.api = undefined
this.token = undefined
this.writeSidPtr = undefined
this.tempWriteSidPtr = undefined
this.grantedPaths = []
if (failures.length > 0) {
throw new AggregateError(failures, `AclSandbox dispose completed with ${failures.length} cleanup failure(s)`)

40
packages/sandbox/sandbox-windows-acl/src/path-boundary.ts Normal file
View File

@@ -0,0 +1,40 @@
/**
* Canonical directory-boundary checks for the Windows ACL workspace and
* private-temp capabilities.
* @module @deepseek-ai/dsh-sandbox-windows-acl/path-boundary
*/
import { realpathSync } from 'node:fs'
import { isAbsolute, relative, sep } from 'node:path'
/** Whether `root` is the same canonical directory as `candidate` or contains it. */
function containsDirectory(root: string, candidate: string): boolean {
const relation = relative(realpathSync.native(root), realpathSync.native(candidate))
return relation === '' || (!isAbsolute(relation) && relation !== '..' && !relation.startsWith(`..${sep}`))
}
/**
* Reject a temp parent that is inside the workspace: every child created
* below it would inherit the standing workspace capability.
* @param workspaceRoot - the canonical workspace root that receives the standing ACE.
* @param tempRoot - the existing parent beneath which a private temp child would be created.
*/
export function assertTempRootOutsideWorkspace(workspaceRoot: string, tempRoot: string): void {
if (containsDirectory(workspaceRoot, tempRoot)) {
throw new Error(`Windows ACL temp root must be outside the workspace: workspace=${workspaceRoot}; temp=${tempRoot}`)
}
}
/**
* Reject overlap between an actual private temp directory and any writable
* directory: either inheritance direction would merge the two capabilities.
* @param writableDirs - directories carrying the standing workspace capability.
* @param tempDir - the existing directory carrying the revocable temp capability.
*/
export function assertPrivateTempDisjoint(writableDirs: readonly string[], tempDir: string): void {
for (const writableDir of writableDirs) {
if (containsDirectory(writableDir, tempDir) || containsDirectory(tempDir, writableDir)) {
throw new Error(`AclSandbox private temp directory must be disjoint from writable directories: writable=${writableDir}; temp=${tempDir}`)
}
}
}

146
packages/sandbox/sandbox-windows-acl/src/runner.ts
View File

@@ -10,33 +10,29 @@
* keep the same contract):
* [node, runner.js, '--workspace', <dir>, '--temp', <dir>,
* '--mode', <read-only|workspace-write>,
* ['--write-sid', <S-1-4-…>], '--', <argv...>]
* ['--write-sid', <S-1-4-…>,
* '--temp-write-sid', <S-1-4-…>], '--', <argv...>]
*
* Modes:
* - workspace-write: the workspace and temp directories carry the orphan-SID
* Write grant; every other write is denied by the token intersection.
* - read-only: STRICT zero grants — no directory is writable, not even the
* NUL device (`> $null` fails with access denied); the restricting list
* carries no orphan SID, so a standing grant ACE from an earlier
* - workspace-write: the workspace and temp directories carry distinct
* capability-SID Write grants; other ACL-addressable writes are denied
* except for the documented Everyone and hard-link boundaries.
* - read-only: no capability-SID grants; the restricting list carries no
* capability SID, so a standing grant ACE from an earlier
* workspace-write period stays inert. BOTH modes drop Authenticated Users
* (CIM unavailable — documented in README) and INTERACTIVE/LOCAL (the
* Public tree writes are denied); the two lists share the keep-alive group
* (logon SID, EVERYONE) and differ only by the orphan.
* (logon SID, EVERYONE) and differ only by the capabilities.
*
* `--write-sid`: the seam's grant contract — the CALLER has already
* materialized the write-SID ACEs (the seam's workspace + private-temp
* grants, server lifetime) and owns their revocation, so the runner neither
* grants nor revokes (manageDacls: false). The carried SID is the
* per-workspace identity ({@link workspaceWriteSid}) — the seam derives it
* from the policy root; the flag's PRESENCE is the seam-managed marker (its
* value must equal the workspace-derived SID). Absent `--write-sid`
* (standalone/test use) the runner self-manages grants per invocation with
* the same workspace-derived SID (its workspace ACEs are standing — the
* reuse cache — and its temp ACE is revoked on exit). With `--write-sid` in
* workspace-write mode, the runner rewrites the TMP/TEMP entries of its OWN
* environment (SetEnvironmentVariableW) to the `--temp` directory — a
* PRIVATE per-session temp subdirectory the seam provisions (bwrap `--tmpfs
* /tmp` semantics) — and the child inherits the rewritten block (lpEnvironment
* `--write-sid` + `--temp-write-sid`: the seam's grant contract — the
* CALLER has already materialized distinct workspace and private-temp ACEs
* and owns their revocation, so the runner neither grants nor revokes
* (`manageDacls: false`). Both values are checked against their owning paths.
* Without the pair (standalone/agentless use), workspace-write treats
* `--temp` as a ROOT, creates a random private child directory, derives its
* own temp SID, and removes that directory after the child exits. In both
* flows the runner rewrites TMP/TEMP in its OWN environment to the private
* directory before spawning; the child inherits that block (`lpEnvironment`
* NULL; an explicit block through koffi trips ERROR_INVALID_PARAMETER in
* CreateProcessAsUserW, verified empirically). Read-only leaves the ambient
* temp entries untouched (writes there are denied anyway).
@@ -48,11 +44,12 @@
* @module @deepseek-ai/dsh-sandbox-windows-acl/runner
*/
import { existsSync, statSync } from 'node:fs'
import { existsSync, mkdtempSync, rmSync, statSync } from 'node:fs'
import { join } from 'node:path'
import { win32 } from './ffi.ts'
import { AclSandbox } from './index.ts'
import { workspaceWriteSid } from './workspace-sid.ts'
import { AclSandbox, assertTempRootOutsideWorkspace } from './index.ts'
import { tempWriteSid, workspaceWriteSid } from './workspace-sid.ts'
const RUNNER_SIGNATURE = 'windows-acl-run'
const RUNNER_FAILURE_EXIT = 127
@@ -70,6 +67,7 @@ interface ParsedArgs {
temp: string
mode: 'read-only' | 'workspace-write'
writeSid: string | undefined
tempWriteSid: string | undefined
command: string
args: string[]
}
@@ -79,6 +77,7 @@ function parseArgs(raw: string[]): ParsedArgs {
let temp: string | undefined
let mode: string | undefined
let writeSid: string | undefined
let parsedTempWriteSid: string | undefined
let index = 0
for (; index < raw.length; index++) {
const token = raw[index]
@@ -94,6 +93,7 @@ function parseArgs(raw: string[]): ParsedArgs {
case '--temp': temp = value; break
case '--mode': mode = value; break
case '--write-sid': writeSid = value; break
case '--temp-write-sid': parsedTempWriteSid = value; break
default: fail(`unknown argument: ${token}`)
}
}
@@ -103,7 +103,7 @@ function parseArgs(raw: string[]): ParsedArgs {
const argv = raw.slice(index)
const command = argv[0]
if (command === undefined) fail('missing command after --')
return { workspace, temp, mode, writeSid, command, args: argv.slice(1) }
return { workspace, temp, mode, writeSid, tempWriteSid: parsedTempWriteSid, command, args: argv.slice(1) }
}
function requireDirectory(label: string, path: string): void {
@@ -119,6 +119,17 @@ async function main(): Promise<number> {
requireDirectory('--workspace', parsed.workspace)
requireDirectory('--temp', parsed.temp)
const seamManaged = parsed.writeSid !== undefined || parsed.tempWriteSid !== undefined
if (parsed.mode === 'read-only' && seamManaged) {
fail('read-only does not accept --write-sid or --temp-write-sid')
}
if (parsed.mode === 'workspace-write' && (parsed.writeSid === undefined) !== (parsed.tempWriteSid === undefined)) {
fail('workspace-write requires --write-sid and --temp-write-sid together')
}
if (parsed.mode === 'workspace-write') {
assertTempRootOutsideWorkspace(parsed.workspace, parsed.temp)
}
const api = await win32()
// Ignore this process's own CTRL+C: the confined child (same console) keeps
// handling its own; the runner must survive to revoke grants and mirror the
@@ -127,36 +138,46 @@ async function main(): Promise<number> {
fail(`SetConsoleCtrlHandler failed (Win32 ${api.getLastError()})`)
}
// The write SID is the per-workspace identity in BOTH flows; the flag's
// presence (seam-derived, or the self-managed derivation) selects who
// owns the DACLs below.
const writeSid = parsed.mode === 'workspace-write' ? parsed.writeSid ?? workspaceWriteSid(parsed.workspace) : undefined
const sandbox = new AclSandbox({
writableDirs: parsed.mode === 'workspace-write' ? [parsed.workspace] : [],
tempDir: parsed.mode === 'workspace-write' ? parsed.temp : null,
mode: parsed.mode,
...writeSid === undefined ? {} : { writeSid },
// With --write-sid the seam owns the DACLs (workspace + private-temp
// grants): this invocation must neither add nor revoke ACEs.
manageDacls: parsed.writeSid === undefined,
})
await sandbox.init()
// The seam's per-session temp contract: under --write-sid, workspace-write
// children see the PRIVATE per-session temp subdirectory through TMP/TEMP
// (bwrap --tmpfs /tmp semantics). The runner rewrites its OWN environment
// (SetEnvironmentVariableW) and the child inherits the block; self-managed
// and read-only runs keep the ambient entries.
if (parsed.mode === 'workspace-write' && parsed.writeSid !== undefined) {
if (api.setEnvironmentVariableW('TMP', parsed.temp) === 0) {
fail(`SetEnvironmentVariableW TMP failed (Win32 ${api.getLastError()})`)
}
if (api.setEnvironmentVariableW('TEMP', parsed.temp) === 0) {
fail(`SetEnvironmentVariableW TEMP failed (Win32 ${api.getLastError()})`)
}
}
let ownedTempDir: string | undefined
let sandbox: AclSandbox | undefined
let initialized = false
try {
let privateTempDir: string | null = null
let writeSid: string | undefined
let privateTempSid: string | undefined
if (parsed.mode === 'workspace-write') {
writeSid = workspaceWriteSid(parsed.workspace)
if (seamManaged) {
if (parsed.writeSid !== writeSid) fail('--write-sid does not match --workspace')
privateTempDir = parsed.temp
privateTempSid = tempWriteSid(privateTempDir)
if (parsed.tempWriteSid !== privateTempSid) fail('--temp-write-sid does not match --temp')
} else {
ownedTempDir = mkdtempSync(join(parsed.temp, 'dsh-'))
privateTempDir = ownedTempDir
privateTempSid = tempWriteSid(privateTempDir)
}
}
sandbox = new AclSandbox({
writableDirs: parsed.mode === 'workspace-write' ? [parsed.workspace] : [],
tempDir: privateTempDir,
mode: parsed.mode,
...writeSid === undefined ? {} : { writeSid },
...privateTempSid === undefined ? {} : { tempWriteSid: privateTempSid },
manageDacls: !seamManaged,
})
await sandbox.init()
initialized = true
if (privateTempDir !== null) {
if (api.setEnvironmentVariableW('TMP', privateTempDir) === 0) {
fail(`SetEnvironmentVariableW TMP failed (Win32 ${api.getLastError()})`)
}
if (api.setEnvironmentVariableW('TEMP', privateTempDir) === 0) {
fail(`SetEnvironmentVariableW TEMP failed (Win32 ${api.getLastError()})`)
}
}
const child = sandbox.spawn({
command: parsed.command,
args: parsed.args,
@@ -166,10 +187,19 @@ async function main(): Promise<number> {
return result.exitCode
} finally {
// Cleanup failures must not mask the child's exit code: report and keep going.
try {
sandbox.dispose()
} catch (error) {
process.stderr.write(`${RUNNER_SIGNATURE}: cleanup: ${error instanceof Error ? error.message : String(error)}\n`)
if (initialized) {
try {
sandbox?.dispose()
} catch (error) {
process.stderr.write(`${RUNNER_SIGNATURE}: cleanup: ${error instanceof Error ? error.message : String(error)}\n`)
}
}
if (ownedTempDir !== undefined) {
try {
rmSync(ownedTempDir, { recursive: true, force: true })
} catch (error) {
process.stderr.write(`${RUNNER_SIGNATURE}: cleanup: ${error instanceof Error ? error.message : String(error)}\n`)
}
}
}
}

26
packages/sandbox/sandbox-windows-acl/src/token.ts
View File

@@ -162,18 +162,19 @@ export interface RestrictingSidSet {
* Create the write-restricted token with the mode-selected restricting list
* (verified on Win11 26200, see the POC-worktree restrict-variant harness):
* - read-only: [logon SID, EVERYONE]
* - workspace-write: [logon SID, EVERYONE, orphan]
* - workspace-write: [logon SID, EVERYONE, workspace SID, optional temp SID]
*
* The logon SID + EVERYONE keep-alive group is shared by both modes: early
* DLL init dies with 0xC0000142 and CNG (`\Device\CNG` write trustee —
* pwsh crashes 0xE0434352) fails without them. The write SID joins ONLY
* pwsh crashes 0xE0434352) fails without them. The write SIDs join ONLY
* workspace-write — read-only carries no write SID, so a standing grant ACE
* from an earlier workspace-write period (a `/permission` mode downgrade, or
* a crash-resumed session) stays INERT under read-only: the WRITE_RESTRICTED
* pass-2 check grants only what the restricting list carries, keeping
* read-only strictly zero-grant even with stale ACEs standing, while the
* unrevoked ACE keeps the re-upgrade free (the grant's exact-ACE skip — no
* re-propagation). Authenticated Users is absent from BOTH lists: the WMI
* pass-2 check grants only what the restricting list carries, keeping that
* workspace grant inert under read-only while the unrevoked ACE keeps the
* re-upgrade free (the grant's exact-ACE skip — no re-propagation).
* Everyone's own ambient grants remain the documented partial boundary.
* Authenticated Users is absent from BOTH lists: the WMI
* namespace security check fails (0x80041003), so CIM is unavailable in
* every confined mode, and the C:\-root tree-creation escape (standing
* `AU:(AD)` + `AU:(OI)(CI)(IO)(M)` ACEs) is closed in both — documented in
@@ -185,24 +186,25 @@ export interface RestrictingSidSet {
* @param api - the binding table.
* @param currentToken - the process token to restrict.
* @param logonSid - the copied logon session SID.
* @param writeSid - the write SID forming the write allowlist (workspace-write only; absent under read-only).
* @param writeSids - the distinct write SIDs forming the workspace and
* optional temp allowlists (workspace-write only; empty under read-only).
* @param known - the well-known SIDs entering the restricting list.
* @param mode - selects the restricting list (workspace-write adds the write SID).
* @param mode - selects the restricting list (workspace-write adds the capability SIDs).
* @returns the restricted token handle.
*/
export function createRestrictedToken(
api: Win32Bindings,
currentToken: NativePtr,
logonSid: NativePtr,
writeSid: NativePtr | undefined,
writeSids: readonly NativePtr[],
known: RestrictingSidSet,
mode: 'read-only' | 'workspace-write',
): NativePtr {
const restrictingSids = buildRestrictingSids(mode === 'read-only'
? [logonSid, known.world]
: writeSid === undefined
? (() => { throw new Error('createRestrictedToken: workspace-write restricting list requires the write SID') })()
: [logonSid, known.world, writeSid])
: writeSids.length === 0
? (() => { throw new Error('createRestrictedToken: workspace-write restricting list requires at least one write SID') })()
: [logonSid, known.world, ...writeSids])
const tokenSlot = allocPtrSlot()
const created = api.createRestrictedToken(
currentToken,

2
packages/sandbox/sandbox-windows-acl/src/win32-abi.ts
View File

@@ -63,7 +63,7 @@ export const FILE_DELETE_CHILD = 0x0040
// security boundary).
/**
* GRANT_MASK: FILE_GENERIC_WRITE minus READ_CONTROL plus DELETE and
* FILE_DELETE_CHILD — the write+delete access mask the orphan-SID ACEs grant
* FILE_DELETE_CHILD — the write+delete access mask the capability-SID ACEs grant
* (displays as "Modify" in Explorer/icacls). WRITE_DAC/WRITE_OWNER are
* deliberately excluded: they would let the confined child take ownership or
* rewrite DACLs.

22
packages/sandbox/sandbox-windows-acl/src/workspace-sid.ts
View File

@@ -8,8 +8,10 @@
* once per session. The SID's power is defined solely by the ACEs that name
* it (which exist only on the workspace tree and the session's private temp
* directory), and only tokens minted for that workspace carry it — the SID
* string itself is not a secret (the previous per-session SID was likewise
* logged in the plain).
* string itself is not a secret. Temporary directories use a separate,
* per-directory identity from {@link tempWriteSid}; sharing the workspace
* identity with temp would let sibling sessions write one another's temp
* trees.
*
* The input MUST be the canonical workspace path (`realpathSync.native` on
* Windows — the sandbox-policy `resolveWorkspaceRoot` already applies it):
@@ -26,7 +28,7 @@ import { createHash } from 'node:crypto'
/**
* Derive the workspace's write SID (`S-1-4-x-y`; subauthorities 30-bit,
* matching the orphan shape the token and ACE layers already carry).
* matching the workspace-capability shape the token and ACE layers carry).
* @param workspaceRoot - the canonical workspace path.
* @returns the SDDL string form.
*/
@@ -36,3 +38,17 @@ export function workspaceWriteSid(workspaceRoot: string): string {
const second = (digest.readUInt32LE(4) % (2 ** 30 - 1)) + 1
return `S-1-4-${first}-${second}`
}
/**
* Derive one private temp directory's write SID. The random directory path
* is the capability identity; a fixed third subauthority domain-separates
* the result from every two-subauthority workspace SID.
* @param tempDir - the private temp directory's absolute path.
* @returns the SDDL string form.
*/
export function tempWriteSid(tempDir: string): string {
const digest = createHash('sha256').update('temp\0', 'utf8').update(tempDir, 'utf8').digest()
const first = (digest.readUInt32LE(0) % (2 ** 30 - 1)) + 1
const second = (digest.readUInt32LE(4) % (2 ** 30 - 1)) + 1
return `S-1-4-${first}-${second}-1`
}

65
packages/sandbox/sandbox-windows-acl/tests/acl.spec.ts
View File

@@ -9,7 +9,7 @@
* whose per-test lock file is removed in cleanup.
*/
import { mkdtempSync, rmSync } from 'node:fs'
import { mkdirSync, mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it, vi } from 'vitest'
@@ -120,7 +120,7 @@ describe.skipIf(!isWin32)('ACL editing', () => {
const api = await win32()
const dir = scratch()
const usersSid = sidFromString(api, 'S-1-5-32-545')
const orphanSid = sidFromString(api, 'S-1-4-4242-1')
const capabilitySid = sidFromString(api, 'S-1-4-4242-1')
try {
// Install one explicit ACE (Users + benign read mask) with the
// package's own bindings, exactly like a pre-existing explicit DACL
@@ -137,37 +137,37 @@ describe.skipIf(!isWin32)('ACL editing', () => {
expect(applyResult, `SetNamedSecurityInfoW setup (${applyResult})`).toBe(abi.ERROR_SUCCESS)
expect(isNullPtr(freed)).toBe(true)
grantWrite(api, dir, orphanSid)
revokeWrite(api, dir, orphanSid)
grantWrite(api, dir, capabilitySid)
revokeWrite(api, dir, capabilitySid)
const aces = readDirectAces(api, dir)
expect(aces.some(ace => ace.sid === 'S-1-5-32-545')).toBe(true) // explicit ACE preserved
expect(aces.some(ace => ace.sid === 'S-1-4-4242-1')).toBe(false) // orphan grant fully removed
} finally {
if (!isNullPtr(usersSid)) api.localFree(usersSid)
if (!isNullPtr(orphanSid)) api.localFree(orphanSid)
if (!isNullPtr(capabilitySid)) api.localFree(capabilitySid)
}
})
it('grantWrite is idempotent: a second grant over the standing exact ACE skips the SetNamedSecurityInfoW apply (no eager full-tree re-propagation)', async () => {
const api = await win32()
const dir = scratch()
const orphanSid = sidFromString(api, 'S-1-4-4242-2')
const capabilitySid = sidFromString(api, 'S-1-4-4242-2')
const apply = vi.spyOn(api, 'setNamedSecurityInfoW')
try {
grantWrite(api, dir, orphanSid)
grantWrite(api, dir, capabilitySid)
expect(apply).toHaveBeenCalledTimes(1)
// The exact ACE now stands (the per-session grant surviving from a
// previous server lifetime): the second grant is a DACL read only.
grantWrite(api, dir, orphanSid)
grantWrite(api, dir, capabilitySid)
expect(apply).toHaveBeenCalledTimes(1)
const aces = readDirectAces(api, dir)
expect(aces.filter(ace => ace.sid === 'S-1-4-4242-2')).toHaveLength(1)
revokeWrite(api, dir, orphanSid)
revokeWrite(api, dir, capabilitySid)
expect(readDirectAces(api, dir).some(ace => ace.sid === 'S-1-4-4242-2')).toBe(false)
} finally {
apply.mockRestore()
if (!isNullPtr(orphanSid)) api.localFree(orphanSid)
if (!isNullPtr(capabilitySid)) api.localFree(capabilitySid)
}
})
@@ -192,21 +192,58 @@ describe.skipIf(!isWin32)('ACL editing', () => {
const api = await win32()
const workspaceDir = scratch()
const tempDir = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspaceDir], tempDir, writeSid: 'S-1-4-9000-3', mode: 'workspace-write' })
const sandbox = new AclSandbox({
writableDirs: [workspaceDir],
tempDir,
writeSid: 'S-1-4-9000-3',
tempWriteSid: 'S-1-4-9000-3-1',
mode: 'workspace-write',
})
await sandbox.init()
sandbox.dispose()
const workspaceAces = readDirectAces(api, workspaceDir)
expect(workspaceAces.some(ace => ace.sid === 'S-1-4-9000-3')).toBe(true)
const tempAces = readDirectAces(api, tempDir)
expect(tempAces.some(ace => ace.sid === 'S-1-4-9000-3')).toBe(false)
expect(tempAces.some(ace => ace.sid === 'S-1-4-9000-3-1')).toBe(false)
})
it('rejects an overlapping private temp directory before applying either capability', async () => {
const workspaceDir = scratch()
const nestedTemp = join(workspaceDir, 'temp')
const writeSid = 'S-1-4-9000-30'
const privateTempSid = 'S-1-4-9000-30-1'
mkdirSync(nestedTemp)
const sandbox = new AclSandbox({
writableDirs: [workspaceDir],
tempDir: nestedTemp,
writeSid,
tempWriteSid: privateTempSid,
mode: 'workspace-write',
})
await expect(sandbox.init()).rejects.toThrow(/private temp directory must be disjoint/u)
const api = await win32()
expect(readDirectAces(api, workspaceDir).some(ace => ace.sid === writeSid)).toBe(false)
expect(readDirectAces(api, nestedTemp).some(ace => ace.sid === privateTempSid)).toBe(false)
})
it('workspace-write without a write SID fails at construction; the token layer guards the same contract', () => {
const dir = scratch()
expect(() => new AclSandbox({ writableDirs: [dir], tempDir: null, mode: 'workspace-write' }))
.toThrow(/requires a write SID/)
expect(() => createRestrictedToken({} as never, 0n as never, 0n as never, undefined, { world: 0n as never }, 'workspace-write'))
.toThrow(/requires the write SID/)
expect(() => new AclSandbox({ writableDirs: [dir], writeSid: 'S-1-4-1-1', mode: 'workspace-write' }))
.toThrow(/requires an explicit private temp directory or null/)
expect(() => new AclSandbox({ writableDirs: [dir], tempDir: dir, writeSid: 'S-1-4-1-1', mode: 'workspace-write' }))
.toThrow(/requires a temp write SID/)
expect(() => new AclSandbox({
writableDirs: [dir],
tempDir: dir,
writeSid: 'S-1-4-1-1',
tempWriteSid: 'S-1-4-1-1',
mode: 'workspace-write',
})).toThrow(/must be distinct/)
expect(() => createRestrictedToken({} as never, 0n as never, 0n as never, [], { world: 0n as never }, 'workspace-write'))
.toThrow(/requires at least one write SID/)
})
it('the per-path lock is exclusive: a second immediate lock attempt fails with ERROR_LOCK_VIOLATION until release', async () => {

95
packages/sandbox/sandbox-windows-acl/tests/index-failure-paths.spec.ts
View File

@@ -59,8 +59,8 @@ function scratch(): string {
}
/**
* The stub the whole happy pipeline needs: token opening, write-SID parse,
* workspace+temp grants, logon-SID scan, well-known SID, restricted token,
* The stub the whole happy pipeline needs: token opening, capability-SID
* parsing, workspace+temp grants, logon-SID scan, well-known SID, restricted token,
* default-DACL merge, piped/inherited spawns, drains, and exit waits all
* succeed. Every test flips one call per branch.
*/
@@ -186,6 +186,28 @@ describe('AclSandbox constructor validation', () => {
expect(sandbox.mode).toBe('read-only')
expect(sandbox.tempDir).toBeUndefined()
})
it('rejects temp authority under read-only', () => {
const workspace = scratch()
const temp = scratch()
expect(() => new AclSandbox({ writableDirs: [workspace], tempDir: temp, mode: 'read-only' }))
.toThrow(/read-only does not accept a temp directory/u)
expect(() => new AclSandbox({ writableDirs: [workspace], tempDir: null, writeSid: 'S-1-4-9000-1', mode: 'read-only' }))
.toThrow(/read-only does not accept write SIDs/u)
expect(() => new AclSandbox({ writableDirs: [workspace], tempDir: null, tempWriteSid: 'S-1-4-9000-1-1', mode: 'read-only' }))
.toThrow(/read-only does not accept write SIDs/u)
})
it('rejects a temp SID when temp writes are disabled', () => {
const workspace = scratch()
expect(() => new AclSandbox({
writableDirs: [workspace],
tempDir: null,
writeSid: 'S-1-4-9000-2',
tempWriteSid: 'S-1-4-9000-2-1',
mode: 'workspace-write',
})).toThrow(/temp write SID requires a temp directory/u)
})
})
describe('AclSandbox init', () => {
@@ -193,17 +215,22 @@ describe('AclSandbox init', () => {
const { setNamedSecurityInfoW } = state.stubs as HappyStubs
const workspace = scratch()
const temp = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspace], tempDir: temp, writeSid: 'S-1-4-9000-1', mode: 'workspace-write' })
const sandbox = new AclSandbox({
writableDirs: [workspace],
tempDir: temp,
writeSid: 'S-1-4-9000-1',
tempWriteSid: 'S-1-4-9000-1-1',
mode: 'workspace-write',
})
await sandbox.init()
expect(sandbox.tempDir).toBe(resolve(temp))
expect(setNamedSecurityInfoW).toHaveBeenCalledTimes(2)
})
it('defaults the temp dir to GetTempPathW when no tempDir option is given', async () => {
it('requires an explicit private temp directory or null under workspace-write', () => {
const workspace = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspace], writeSid: 'S-1-4-9000-2', mode: 'workspace-write' })
await sandbox.init()
expect(sandbox.tempDir).toBe(tmpdir().replace(/[\\/]$/u, ''))
expect(() => new AclSandbox({ writableDirs: [workspace], writeSid: 'S-1-4-9000-2', mode: 'workspace-write' }))
.toThrow(/requires an explicit private temp directory or null/u)
})
it('applies no grants when the temp dir option is null', async () => {
@@ -216,7 +243,13 @@ describe('AclSandbox init', () => {
it('rejects a temp dir that does not exist', async () => {
const workspace = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspace], tempDir: join(scratch(), 'missing'), writeSid: 'S-1-4-9000-4', mode: 'workspace-write' })
const sandbox = new AclSandbox({
writableDirs: [workspace],
tempDir: join(scratch(), 'missing'),
writeSid: 'S-1-4-9000-4',
tempWriteSid: 'S-1-4-9000-4-1',
mode: 'workspace-write',
})
await expect(sandbox.init()).rejects.toThrow(/temp dir does not exist/u)
})
@@ -263,18 +296,31 @@ describe('AclSandbox init', () => {
await expect(sandbox.init()).rejects.toBeInstanceOf(Win32Error)
})
it('reports a failed close of the current process token', async () => {
const { closeHandle } = state.stubs as HappyStubs
it('aggregates failed current and restricted token closes after init', async () => {
const { closeHandle, createRestrictedToken } = state.stubs as HappyStubs
const workspace = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspace], tempDir: null, writeSid: 'S-1-4-9000-9', mode: 'workspace-write' })
const restrictedToken = 99n
createRestrictedToken.mockImplementation((
_existing: unknown, _flags: unknown, _dc: unknown, _ds: unknown, _pc: unknown, _pd: unknown,
_rc: unknown, _rs: unknown, slot: NativePtr,
) => {
koffi.encode(slot, PVOID, restrictedToken)
return 1
})
// fresh() hands out 1n to OpenProcess and 2n to OpenProcessToken; the
// token-layer close of 1n succeeds and init's close of 2n fails.
closeHandle.mockImplementation((handle: NativePtr) => (handle === 2n ? 0 : 1))
closeHandle.mockImplementation((handle: NativePtr) => (handle === 2n || handle === restrictedToken ? 0 : 1))
// The failure lands after this.token is stored but before this.api is
// assigned; the catch drains the SID allocations and rethrows the
// original error. (The stored restricted token and parsed write SID leak
// until process exit — see the FIXME in init's catch.)
await expect(sandbox.init()).rejects.toMatchObject({ api: 'CloseHandle' })
// assigned. Cleanup retries the still-open handle and reports both close
// failures plus the restricted-token close after releasing parsed SIDs.
await expect(sandbox.init()).rejects.toMatchObject({
errors: [
{ api: 'CloseHandle' },
{ api: 'CloseHandle' },
{ api: 'CloseHandle' },
],
})
})
it('revokes the revocable grants and aggregates cleanup failures when the token pipeline fails', async () => {
@@ -296,8 +342,15 @@ describe('AclSandbox init', () => {
koffi.encode(descriptor, PVOID, 0n)
return 0
})
const sandbox = new AclSandbox({ writableDirs: [workspace], tempDir: temp, writeSid: 'S-1-4-9000-10', mode: 'workspace-write' })
await expect(sandbox.init()).rejects.toThrow(/3 grant revocation\(s\) also failed/u)
const sandbox = new AclSandbox({
writableDirs: [workspace],
tempDir: temp,
writeSid: 'S-1-4-9000-10',
tempWriteSid: 'S-1-4-9000-10-1',
mode: 'workspace-write',
})
await expect(sandbox.init()).rejects.toThrow(/5 cleanup operation\(s\) also failed/u)
expect(sandbox.tempDir).toBeUndefined()
})
})
@@ -354,7 +407,13 @@ describe('AclSandbox dispose', () => {
const { getNamedSecurityInfoW } = state.stubs as HappyStubs
const workspace = scratch()
const temp = scratch()
const sandbox = new AclSandbox({ writableDirs: [workspace], tempDir: temp, writeSid: 'S-1-4-9000-16', mode: 'workspace-write' })
const sandbox = new AclSandbox({
writableDirs: [workspace],
tempDir: temp,
writeSid: 'S-1-4-9000-16',
tempWriteSid: 'S-1-4-9000-16-1',
mode: 'workspace-write',
})
await sandbox.init()
getNamedSecurityInfoW.mockReturnValue(2)
expect(() => { sandbox.dispose() }).toThrow(/1 cleanup failure/u)

65
packages/sandbox/sandbox-windows-acl/tests/path-boundary.spec.ts Normal file
View File

@@ -0,0 +1,65 @@
/** Canonical path-overlap checks that keep workspace and temp capabilities separate. */
import { mkdirSync, mkdtempSync, rmSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { afterEach, describe, expect, it } from 'vitest'
import { assertPrivateTempDisjoint, assertTempRootOutsideWorkspace } from '../src/path-boundary.ts'
describe('Windows ACL temp path boundary', () => {
const scratchDirs: string[] = []
afterEach(() => {
for (const dir of scratchDirs.splice(0)) rmSync(dir, { recursive: true, force: true })
})
function scratch(): string {
const dir = mkdtempSync(join(tmpdir(), 'dsh-acl-boundary-'))
scratchDirs.push(dir)
return dir
}
it('rejects a temp root equal to or below the workspace', () => {
const workspace = scratch()
const nested = join(workspace, 'temp')
mkdirSync(nested)
expect(() => {
assertTempRootOutsideWorkspace(workspace, workspace)
}).toThrow(/temp root must be outside the workspace/u)
expect(() => {
assertTempRootOutsideWorkspace(workspace, nested)
}).toThrow(/temp root must be outside the workspace/u)
})
it('accepts a temp parent above the workspace because a fresh child is a sibling', () => {
const tempRoot = scratch()
const workspace = join(tempRoot, 'workspace')
mkdirSync(workspace)
expect(() => {
assertTempRootOutsideWorkspace(workspace, tempRoot)
}).not.toThrow()
})
it('requires an actual private temp directory to be disjoint in either direction', () => {
const root = scratch()
const workspace = join(root, 'workspace')
const nestedTemp = join(workspace, 'temp')
const siblingTemp = join(root, 'sibling-temp')
mkdirSync(workspace)
mkdirSync(nestedTemp)
mkdirSync(siblingTemp)
expect(() => {
assertPrivateTempDisjoint([workspace], nestedTemp)
}).toThrow(/must be disjoint/u)
expect(() => {
assertPrivateTempDisjoint([nestedTemp], workspace)
}).toThrow(/must be disjoint/u)
expect(() => {
assertPrivateTempDisjoint([workspace], siblingTemp)
}).not.toThrow()
})
})

33
packages/sandbox/sandbox-windows-acl/tests/probe.spec.ts
View File

@@ -6,10 +6,10 @@
* WRITE_RESTRICTED token intersects write accesses only.
*
* The escape target sits in its own scratch dir under the system temp
* directory, OUTSIDE both granted trees: tempDir is passed EXPLICITLY (never
* defaulted through GetTempPathW, whose grant would inherit (OI)(CI) over the
* whole real temp tree) and the writable dir is a separate mkdtemp directory
* that contains neither sibling. Nothing under the user profile is touched.
* directory, OUTSIDE both granted trees: tempDir is an explicit private
* mkdtemp directory (the API never grants the ambient temp root implicitly),
* and the writable dir is a separate mkdtemp directory that contains neither
* sibling. Nothing under the user profile is touched.
*/
import { execFileSync } from 'node:child_process'
@@ -47,11 +47,15 @@ describe.skipIf(!isWin32 || !pwshAvailable())('AclSandbox write restriction', ()
secretFile = join(scratchRoot, 'secret.txt')
writeFileSync(secretFile, 'top secret - must stay readable to prove the read boundary')
escapeFile = join(scratchRoot, 'escaped.txt')
// tempDir is passed explicitly: GetTempPathW reads the native environment
// block, which host runtimes (vitest worker pools) may not keep in sync
// with process.env — and a real-temp grant would inherit over every
// temp subdirectory, including this test's scratch dir.
sandbox = new AclSandbox({ writableDirs: [writableDir], tempDir: isolatedTemp, writeSid: 'S-1-4-9000-4', mode: 'workspace-write' })
// The direct API requires this explicit private temp directory and its
// own SID; it never widens the grant over the ambient temp root.
sandbox = new AclSandbox({
writableDirs: [writableDir],
tempDir: isolatedTemp,
writeSid: 'S-1-4-9000-4',
tempWriteSid: 'S-1-4-9000-4-1',
mode: 'workspace-write',
})
await sandbox.init()
})
@@ -91,7 +95,16 @@ describe.skipIf(!isWin32 || !pwshAvailable())('AclSandbox write restriction', ()
it('fails closed when the write SID cannot be parsed (no unrestricted fallback)', async () => {
// A malformed SID makes ConvertStringSidToSidW fail; init must throw
// before any grant is applied and never spawn unrestricted.
const broken = new AclSandbox({ writableDirs: [writableDir], writeSid: 'S-1-4-abc-1', mode: 'workspace-write' })
const broken = new AclSandbox({ writableDirs: [writableDir], tempDir: null, writeSid: 'S-1-4-abc-1', mode: 'workspace-write' })
await expect(broken.init()).rejects.toThrow(/ConvertStringSidToSidW/u)
}, 15_000)
it('failed init clears provisional temp state before a retry', async () => {
const broken = new AclSandbox({ writableDirs: [writableDir], tempDir: null, writeSid: 'S-1-4-abc-1', mode: 'workspace-write' })
const provisionalState = broken as unknown as { tempDirResolved: string | undefined }
provisionalState.tempDirResolved = isolatedTemp
await expect(broken.init()).rejects.toThrow(/ConvertStringSidToSidW/u)
expect(broken.tempDir).toBeUndefined()
}, 15_000)
})

6
packages/sandbox/sandbox-windows-acl/tests/provider-chain.spec.ts
View File

@@ -25,7 +25,7 @@ async function setup(internals: LocalSandboxProvider['internals']) {
}
describe('windows-acl win32 chain (LocalSandboxProvider)', () => {
it('workspace-write: runner argv prefix, explicit temp, mode flag, full enforcement, ACL denial dialect', async () => {
it('agentless workspace-write: runner argv prefix, temp root, mode flag, partial enforcement, ACL denial dialect', async () => {
const probeWindowsAcl = vi.fn(() => true)
const sandbox = await setup({
platform: 'win32',
@@ -41,7 +41,7 @@ describe('windows-acl win32 chain (LocalSandboxProvider)', () => {
'--',
'pwsh', '/Command', 'x',
])
expect(confined.enforcement).toBe('full')
expect(confined.enforcement).toBe('partial')
expect(confined.denialSignatures).toEqual(['access is denied', 'access to the path', 'permission denied'])
expect(confined.runnerFailureRules).toEqual([{ allowedExitCodes: [127], fatalSignatures: ['windows-acl-run: '] }])
// A sole candidate is selected unprobed.
@@ -52,7 +52,7 @@ describe('windows-acl win32 chain (LocalSandboxProvider)', () => {
const sandbox = await setup({ platform: 'win32', windowsAclRunnerArgs: ['node', 'windows-acl-runner.js'] })
const confined = sandbox.confine(['true'], RO)
expect(confined.argv.slice(-4)).toEqual(['--mode', 'read-only', '--', 'true'])
expect(confined.enforcement).toBe('full')
expect(confined.enforcement).toBe('partial')
expect(confined.runnerFailureRules).toEqual([{ allowedExitCodes: [127], fatalSignatures: ['windows-acl-run: '] }])
})
})

207
packages/sandbox/sandbox-windows-acl/tests/runner.spec.ts
View File

@@ -6,14 +6,14 @@
*/
import { spawnSync } from 'node:child_process'
import { existsSync, mkdirSync, mkdtempSync, rmSync, writeFileSync } from 'node:fs'
import { existsSync, linkSync, mkdirSync, mkdtempSync, readFileSync, rmSync, writeFileSync } from 'node:fs'
import { tmpdir } from 'node:os'
import { join } from 'node:path'
import { fileURLToPath } from 'node:url'
import { afterAll, beforeAll, describe, expect, it } from 'vitest'
import { resolvePwshPath } from '@deepseek-ai/dsh-pwsh-local'
import { AclWriteGrant } from '../src/index.ts'
import { AclWriteGrant, tempWriteSid, workspaceWriteSid } from '../src/index.ts'
const isWin32 = process.platform === 'win32'
const runnerEntry = fileURLToPath(new URL('../src/runner.ts', import.meta.url))
@@ -38,6 +38,7 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
let isolatedTemp!: string
let secretFile!: string
let escapeFile!: string
let worldWritableDir!: string
// The ambient-writable probe target: a subdirectory of C:\Users\Public.
// INTERACTIVE/LOCAL are absent from BOTH restricting lists, so the Public
// tree's INTERACTIVE grant must NOT satisfy the write check — the ambient
@@ -54,6 +55,12 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
secretFile = join(scratchRoot, 'secret.txt')
writeFileSync(secretFile, 'top secret - must stay readable to prove the read boundary')
escapeFile = join(scratchRoot, 'escaped.txt')
worldWritableDir = join(scratchRoot, 'world-writable')
mkdirSync(worldWritableDir)
const worldGrant = spawnSync('icacls', [worldWritableDir, '/grant', '*S-1-1-0:(OI)(CI)(M)'], { encoding: 'utf8' })
if (worldGrant.status !== 0) {
throw new Error(`icacls Everyone grant failed: ${worldGrant.stdout}\n${worldGrant.stderr}`)
}
try {
publicProbeDir = mkdtempSync(join(process.env.PUBLIC ?? 'C:\\Users\\Public', 'dsh-acl-public-'))
} catch {
@@ -70,12 +77,13 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
it('workspace-write: the confined child writes granted directories only', () => {
const probe = [
"$ErrorActionPreference='SilentlyContinue';",
// The restricted token puts pwsh into ConstrainedLanguage in BOTH modes
// (documented Known Limitation) — pinned here so a token change that
// silently restores FullLanguage is caught.
// The private-temp capability lets PowerShell complete its startup
// AppLocker probe, so without a host policy workspace-write stays in
// FullLanguage. Read-only cannot create those scratch files and fails
// that probe closed to ConstrainedLanguage (pinned below).
'\'LANGMODE: \' + $ExecutionContext.SessionState.LanguageMode;',
`try{Set-Content -Path '${writableDir}\\child-wrote.txt' -Value ok -ErrorAction Stop;'TARGET-WRITE: OK'}catch{'TARGET-WRITE: DENIED'};`,
`try{Set-Content -Path '${isolatedTemp}\\child-wrote.txt' -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};`,
"try{Set-Content -Path (Join-Path $env:TEMP 'child-wrote.txt') -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};",
`try{Set-Content -Path '${escapeFile}' -Value ok -ErrorAction Stop;'ESCAPE-WRITE: OK (ESCAPE!)'}catch{'ESCAPE-WRITE: DENIED'};`,
`try{Get-Content '${secretFile}' -ErrorAction Stop | Out-Null;'SECRET-READ: OK'}catch{'SECRET-READ: DENIED'};`,
// Authenticated Users is absent from BOTH lists: the WMI namespace
@@ -89,7 +97,7 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
'--', 'pwsh', '/NoLogo', '/NonInteractive', '/NoProfile', '/Command', probe,
])
expect(result.status, `stderr: ${result.stderr}`).toBe(0)
expect(result.stdout).toContain('LANGMODE: ConstrainedLanguage')
expect(result.stdout).toContain('LANGMODE: FullLanguage')
expect(result.stdout).toContain('TARGET-WRITE: OK')
expect(result.stdout).toContain('TEMP-WRITE: OK')
expect(result.stdout).toContain('ESCAPE-WRITE: DENIED')
@@ -99,13 +107,14 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
expect(existsSync(join(writableDir, 'child-wrote.txt'))).toBe(true)
}, 30_000)
it('read-only: strict zero grants — no writes anywhere (not even NUL), reads and $null redirection fine, CIM unavailable', () => {
it('read-only: no write-SID grants — workspace/temp writes denied, reads and $null redirection fine, CIM unavailable', () => {
const probe = [
"$ErrorActionPreference='SilentlyContinue';",
'\'LANGMODE: \' + $ExecutionContext.SessionState.LanguageMode;',
`try{Set-Content -Path '${writableDir}\\readonly-child-wrote.txt' -Value ok -ErrorAction Stop;'TARGET-WRITE: OK'}catch{'TARGET-WRITE: DENIED'};`,
`try{Set-Content -Path '${isolatedTemp}\\readonly-child-wrote.txt' -Value ok -ErrorAction Stop;'TEMP-WRITE: OK'}catch{'TEMP-WRITE: DENIED'};`,
// The NUL device is a securable object: strict zero grants deny it too.
// Set-Content NUL fails at the PowerShell/.NET layer even though the
// device DACL's Everyone rights remain an ambient backend boundary.
'try{Set-Content -Path \'NUL\' -Value ok -ErrorAction Stop;\'NUL-WRITE: OK\'}catch{\'NUL-WRITE: DENIED\'};',
// PowerShell's $null redirection discards without opening NUL — must keep working.
'echo hi > $null;\'DOLLAR-NULL: OK\';',
@@ -155,33 +164,37 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
expect(existsSync(renamedDir)).toBe(true)
}, 30_000)
it('--write-sid: the runner trusts the caller-owned grants — private temp subdir via the TMP/TEMP env rewrite, no grants of its own', () => {
const writeSid = 'S-1-4-9000-99'
it('paired SIDs: the runner trusts caller-owned private-temp grants and materializes nothing itself', () => {
const seamWorkspace = join(scratchRoot, 'seam-workspace')
mkdirSync(seamWorkspace)
const writeSid = workspaceWriteSid(seamWorkspace)
const privateTemp = join(isolatedTemp, 'private-subdir')
mkdirSync(privateTemp)
const grant = AclWriteGrant.create(writeSid)
const privateTempSid = tempWriteSid(privateTemp)
const grant = AclWriteGrant.create(privateTempSid)
grant.add(privateTemp)
try {
const probe = [
"$ErrorActionPreference='SilentlyContinue';",
`try{Set-Content -Path '${writableDir}\\server-granted.txt' -Value ok -ErrorAction Stop;'WORKSPACE-WRITE: OK'}catch{'WORKSPACE-WRITE: DENIED'};`,
`try{Set-Content -Path '${seamWorkspace}\\server-granted.txt' -Value ok -ErrorAction Stop;'WORKSPACE-WRITE: OK'}catch{'WORKSPACE-WRITE: DENIED'};`,
`try{Set-Content -Path '${privateTemp}\\server-granted.txt' -Value ok -ErrorAction Stop;'PRIVATE-TEMP-WRITE: OK'}catch{'PRIVATE-TEMP-WRITE: DENIED'};`,
"'TEMP-ENV: ' + $env:TEMP;",
"'TMP-ENV: ' + $env:TMP",
].join('')
const result = runRunner([
'--workspace', writableDir, '--temp', privateTemp, '--mode', 'workspace-write', '--write-sid', writeSid,
'--workspace', seamWorkspace, '--temp', privateTemp, '--mode', 'workspace-write', '--write-sid', writeSid,
'--temp-write-sid', privateTempSid,
'--', 'pwsh', '/NoLogo', '/NonInteractive', '/NoProfile', '/Command', probe,
])
expect(result.status, `stderr: ${result.stderr}`).toBe(0)
// The runner granted nothing (only the caller's private-temp grant
// The runner granted nothing (only the caller's temp-SID grant
// stands): the workspace write is denied, the private temp write lands,
// and the child's TMP/TEMP point at the private subdirectory.
expect(result.stdout).toContain('WORKSPACE-WRITE: DENIED')
expect(result.stdout).toContain('PRIVATE-TEMP-WRITE: OK')
expect(result.stdout).toContain(`TEMP-ENV: ${privateTemp}`)
expect(result.stdout).toContain(`TMP-ENV: ${privateTemp}`)
expect(existsSync(join(writableDir, 'server-granted.txt'))).toBe(false)
expect(existsSync(join(seamWorkspace, 'server-granted.txt'))).toBe(false)
expect(existsSync(join(privateTemp, 'server-granted.txt'))).toBe(true)
} finally {
grant.dispose()
@@ -189,6 +202,97 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
}
}, 30_000)
it('temp capabilities isolate sibling sessions that share one workspace SID', () => {
const writeSid = workspaceWriteSid(writableDir)
const tempA = join(isolatedTemp, 'session-a')
const tempB = join(isolatedTemp, 'session-b')
mkdirSync(tempA)
mkdirSync(tempB)
const sidA = tempWriteSid(tempA)
const sidB = tempWriteSid(tempB)
const workspaceGrant = AclWriteGrant.create(writeSid)
const grantA = AclWriteGrant.create(sidA)
const grantB = AclWriteGrant.create(sidB)
workspaceGrant.add(writableDir)
grantA.add(tempA)
grantB.add(tempB)
const sharedWorkspaceFile = join(writableDir, 'shared-between-sessions.txt')
const probe = [
"const fs = require('node:fs');",
"const targets = [['OWN', process.argv[1]], ['SIBLING', process.argv[2]], ['WORKSPACE', process.argv[3]]];",
"if (process.argv[4]) targets.push(['SIBLING-EXISTING', process.argv[4]]);",
'for (const [name, target] of targets) {',
"try { fs.writeFileSync(target, name); console.log(name + ': OK'); } catch { console.log(name + ': DENIED'); }",
'}',
].join('')
try {
const resultA = runRunner([
'--workspace', writableDir, '--temp', tempA, '--mode', 'workspace-write',
'--write-sid', writeSid, '--temp-write-sid', sidA,
'--', process.execPath, '-e', probe, join(tempA, 'a.txt'), join(tempB, 'a-escaped.txt'), sharedWorkspaceFile,
])
expect(resultA.status, `stderr: ${resultA.stderr}`).toBe(0)
expect(resultA.stdout).toContain('OWN: OK')
expect(resultA.stdout).toContain('SIBLING: DENIED')
expect(resultA.stdout).toContain('WORKSPACE: OK')
const resultB = runRunner([
'--workspace', writableDir, '--temp', tempB, '--mode', 'workspace-write',
'--write-sid', writeSid, '--temp-write-sid', sidB,
'--', process.execPath, '-e', probe, join(tempB, 'b.txt'), join(tempA, 'b-escaped.txt'), sharedWorkspaceFile, join(tempA, 'a.txt'),
])
expect(resultB.status, `stderr: ${resultB.stderr}`).toBe(0)
expect(resultB.stdout).toContain('OWN: OK')
expect(resultB.stdout).toContain('SIBLING: DENIED')
expect(resultB.stdout).toContain('SIBLING-EXISTING: DENIED')
expect(resultB.stdout).toContain('WORKSPACE: OK')
expect(existsSync(join(tempB, 'a-escaped.txt'))).toBe(false)
expect(existsSync(join(tempA, 'b-escaped.txt'))).toBe(false)
expect(readFileSync(join(tempA, 'a.txt'), 'utf8')).toBe('OWN')
} finally {
workspaceGrant.dispose()
grantA.dispose()
grantB.dispose()
rmSync(tempA, { recursive: true, force: true })
rmSync(tempB, { recursive: true, force: true })
}
}, 30_000)
it('agentless workspace-write creates a fresh private temp per call and removes it on exit', () => {
const captureA = join(writableDir, 'agentless-temp-a.txt')
const captureB = join(writableDir, 'agentless-temp-b.txt')
for (const capture of [captureA, captureB]) {
const result = runRunner([
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'workspace-write',
'--', process.execPath, '-e', "require('node:fs').writeFileSync(process.argv[1], process.env.TEMP)", capture,
])
expect(result.status, `stderr: ${result.stderr}`).toBe(0)
}
const tempA = readFileSync(captureA, 'utf8')
const tempB = readFileSync(captureB, 'utf8')
expect(tempA).not.toBe(tempB)
expect(tempA.startsWith(isolatedTemp)).toBe(true)
expect(tempB.startsWith(isolatedTemp)).toBe(true)
expect(existsSync(tempA)).toBe(false)
expect(existsSync(tempB)).toBe(false)
}, 30_000)
it('agentless workspace-write rejects a temp root inside the workspace before spawning', () => {
const overlapWorkspace = join(scratchRoot, 'overlap-workspace')
const nestedTempRoot = join(overlapWorkspace, 'temp')
const marker = join(overlapWorkspace, 'command-ran.txt')
mkdirSync(overlapWorkspace)
mkdirSync(nestedTempRoot)
const result = runRunner([
'--workspace', overlapWorkspace, '--temp', nestedTempRoot, '--mode', 'workspace-write',
'--', process.execPath, '-e', "require('node:fs').writeFileSync(process.argv[1], 'ran')", marker,
])
expect(result.status, `stderr: ${result.stderr}`).toBe(127)
expect(result.stderr).toContain('windows-acl-run: Windows ACL temp root must be outside the workspace')
expect(existsSync(marker)).toBe(false)
}, 15_000)
it('confined children spawn grandchildren with inherited stdio; piped capture stays denied (named-pipe default SD template)', () => {
// Two-layer pin of the grandchild-spawn boundary:
// - the token default DACL carries a restricting-SID ACE (set in init),
@@ -226,11 +330,14 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
// The reported defect: a session that materialized its grant in
// workspace-write keeps the ACE standing for the server lifetime. After
// switching to read-only, the restricted token's read-only list must carry NO
// orphan SID — the standing ACE stays but the pass-2 check cannot use
// capability SID — the standing ACE stays but the pass-2 check cannot use
// it, so the workspace write is denied (previously it LEAKED). The
// switch back reuses the SAME standing ACE: the re-upgrade write lands
// without any re-grant.
const writeSid = 'S-1-4-9001-7'
const writeSid = workspaceWriteSid(writableDir)
const privateTemp = join(isolatedTemp, 'mode-switch-temp')
mkdirSync(privateTemp)
const privateTempSid = tempWriteSid(privateTemp)
const grant = AclWriteGrant.create(writeSid)
grant.add(writableDir)
try {
@@ -239,7 +346,7 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
`try{Set-Content -Path '${writableDir}\\downgraded.txt' -Value ok -ErrorAction Stop;'DOWNGRADE-WRITE: OK (LEAK!)'}catch{'DOWNGRADE-WRITE: DENIED'}`,
].join('')
const downgraded = runRunner([
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'read-only', '--write-sid', writeSid,
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'read-only',
'--', 'pwsh', '/NoLogo', '/NonInteractive', '/NoProfile', '/Command', downgradeProbe,
])
expect(downgraded.status, `stderr: ${downgraded.stderr}`).toBe(0)
@@ -251,7 +358,8 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
`try{Set-Content -Path '${writableDir}\\reupgraded.txt' -Value ok -ErrorAction Stop;'REUPGRADE-WRITE: OK'}catch{'REUPGRADE-WRITE: DENIED'}`,
].join('')
const reupgraded = runRunner([
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'workspace-write', '--write-sid', writeSid,
'--workspace', writableDir, '--temp', privateTemp, '--mode', 'workspace-write', '--write-sid', writeSid,
'--temp-write-sid', privateTempSid,
'--', 'pwsh', '/NoLogo', '/NonInteractive', '/NoProfile', '/Command', reupgradeProbe,
])
expect(reupgraded.status, `stderr: ${reupgraded.stderr}`).toBe(0)
@@ -259,6 +367,7 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
expect(existsSync(join(writableDir, 'reupgraded.txt'))).toBe(true)
} finally {
grant.dispose()
rmSync(privateTemp, { recursive: true, force: true })
}
}, 30_000)
@@ -286,9 +395,67 @@ describe.skipIf(!isWin32 || !pwshAvailable())('windows-acl runner', () => {
}
}, 30_000)
it('partial boundary: an external Everyone-Modify directory stays writable under BOTH modes', () => {
// Everyone is a required keep-alive restricting SID: without it early DLL
// initialization and CNG fail. A normal DACL that grants Everyone Modify
// therefore also clears the WRITE_RESTRICTED pass-2 check. Pin this
// unavoidable gap beside the provider's `partial` enforcement report.
for (const mode of ['read-only', 'workspace-write'] as const) {
const target = join(worldWritableDir, `${mode}.txt`)
const result = runRunner([
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', mode,
'--', process.execPath, '-e', "require('node:fs').writeFileSync(process.argv[1], 'written')", target,
])
expect(result.status, `mode: ${mode}\nstderr: ${result.stderr}`).toBe(0)
expect(existsSync(target), `mode: ${mode}`).toBe(true)
}
}, 30_000)
it('partial boundary: a workspace hard link lets the grant reach an external file object', () => {
// NTFS ACLs belong to the file object, not one pathname. Propagating the
// workspace write-SID ACE through an existing hard-link alias therefore
// grants the external alias too. pnpm workspaces commonly contain hard
// links, so rejecting every multiply-linked file is not a viable profile.
const hardlinkWorkspace = join(scratchRoot, 'hardlink-workspace')
const hardlinkTemp = join(scratchRoot, 'hardlink-temp')
const externalFile = join(scratchRoot, 'hardlink-target.txt')
const workspaceLink = join(hardlinkWorkspace, 'hardlink-alias.txt')
mkdirSync(hardlinkWorkspace)
mkdirSync(hardlinkTemp)
writeFileSync(externalFile, 'original')
linkSync(externalFile, workspaceLink)
const result = runRunner([
// This workspace has not been granted before the alias exists: the first
// recursive materialization reaches the shared file security descriptor.
'--workspace', hardlinkWorkspace, '--temp', hardlinkTemp, '--mode', 'workspace-write',
'--', process.execPath, '-e', "require('node:fs').writeFileSync(process.argv[1], 'mutated')", workspaceLink,
])
expect(result.status, `stderr: ${result.stderr}`).toBe(0)
expect(readFileSync(externalFile, 'utf8')).toBe('mutated')
}, 30_000)
it('runner-side failure: signature on stderr and exit 127, the command never runs', () => {
const result = runRunner(['--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'workspace-write'])
expect(result.status).toBe(127)
expect(result.stderr).toContain('windows-acl-run: ')
}, 15_000)
it('runner-side failure: seam-managed SID flags must be paired and match their owning paths', () => {
const writeSid = workspaceWriteSid(writableDir)
const tempSid = tempWriteSid(isolatedTemp)
const cases = [
['--write-sid', writeSid],
['--write-sid', 'S-1-4-1-2', '--temp-write-sid', tempSid],
['--write-sid', writeSid, '--temp-write-sid', 'S-1-4-1-2-1'],
]
for (const args of cases) {
const result = runRunner([
'--workspace', writableDir, '--temp', isolatedTemp, '--mode', 'workspace-write',
...args,
'--', process.execPath, '-e', 'process.exit(99)',
])
expect(result.status, `args: ${args.join(' ')}\nstderr: ${result.stderr}`).toBe(127)
expect(result.stderr).toContain('windows-acl-run: ')
}
}, 15_000)
})

8
packages/sandbox/sandbox-windows-acl/tests/token-failure-paths.spec.ts
View File

@@ -383,7 +383,7 @@ describe('createRestrictedToken failure paths', () => {
})
const api = { createRestrictedToken: create } as unknown as Win32Bindings
const logon = allocBytes(12)
expect(createRestrictedToken(api, 1n as NativePtr, logon, undefined, { world: 2n as NativePtr }, 'read-only')).toBe(9n)
expect(createRestrictedToken(api, 1n as NativePtr, logon, [], { world: 2n as NativePtr }, 'read-only')).toBe(9n)
})
it('builds the workspace-write restricting list with the write SID', () => {
@@ -397,7 +397,7 @@ describe('createRestrictedToken failure paths', () => {
})
const api = { createRestrictedToken: create } as unknown as Win32Bindings
const logon = allocBytes(12)
expect(createRestrictedToken(api, 1n as NativePtr, logon, 3n as NativePtr, { world: 2n as NativePtr }, 'workspace-write')).toBe(9n)
expect(createRestrictedToken(api, 1n as NativePtr, logon, [3n as NativePtr], { world: 2n as NativePtr }, 'workspace-write')).toBe(9n)
})
it('reports when CreateRestrictedToken fails', () => {
@@ -409,7 +409,7 @@ describe('createRestrictedToken failure paths', () => {
const logon = allocBytes(12)
let caught: unknown
try {
createRestrictedToken(api, 1n as NativePtr, logon, undefined, { world: 2n as NativePtr }, 'read-only')
createRestrictedToken(api, 1n as NativePtr, logon, [], { world: 2n as NativePtr }, 'read-only')
} catch (error) {
caught = error
}
@@ -426,7 +426,7 @@ describe('createRestrictedToken failure paths', () => {
const logon = allocBytes(12)
let caught: unknown
try {
createRestrictedToken(api, 1n as NativePtr, logon, undefined, { world: 2n as NativePtr }, 'read-only')
createRestrictedToken(api, 1n as NativePtr, logon, [], { world: 2n as NativePtr }, 'read-only')
} catch (error) {
caught = error
}

19
packages/sandbox/sandbox-windows-acl/tests/workspace-sid.spec.ts
View File

@@ -1,7 +1,7 @@
/**
* workspaceWriteSid tests: the per-workspace write identity is deterministic
* (the same canonical path always derives the same SID — the property the
* cross-session grant reuse rests on), orphan-shaped, distinct across
* cross-session grant reuse rests on), capability-shaped, distinct across
* workspaces, and byte-sensitive (the canonical path is the caller's
* contract; an alias spelling derives a second identity, self-healing at
* the cost of one extra tree propagation).
@@ -9,10 +9,10 @@
import { describe, expect, it } from 'vitest'
import { workspaceWriteSid } from '../src/index.ts'
import { tempWriteSid, workspaceWriteSid } from '../src/index.ts'
describe('workspaceWriteSid', () => {
it('derives a stable orphan-shaped SID per workspace path', () => {
it('derives a stable capability-shaped SID per workspace path', () => {
const first = workspaceWriteSid('C:\\Users\\agent\\repo')
const second = workspaceWriteSid('C:\\Users\\agent\\repo')
expect(first).toBe(second)
@@ -28,3 +28,16 @@ describe('workspaceWriteSid', () => {
expect(workspaceWriteSid('C:\\Repo\\')).not.toBe(workspaceWriteSid('C:\\Repo'))
})
})
describe('tempWriteSid', () => {
it('derives a stable domain-separated SID per private temp path', () => {
const temp = tempWriteSid('C:\\Users\\agent\\AppData\\Local\\Temp\\dsh-abc123')
expect(temp).toBe(tempWriteSid('C:\\Users\\agent\\AppData\\Local\\Temp\\dsh-abc123'))
expect(temp).toMatch(/^S-1-4-\d+-\d+-1$/u)
expect(temp).not.toBe(workspaceWriteSid('C:\\Users\\agent\\AppData\\Local\\Temp\\dsh-abc123'))
})
it('derives distinct capabilities for distinct private temp paths', () => {
expect(tempWriteSid('C:\\Temp\\dsh-a')).not.toBe(tempWriteSid('C:\\Temp\\dsh-b'))
})
})

10
packages/sandbox/sandbox/src/index.ts
View File

@@ -43,10 +43,10 @@ export interface SandboxExecutionPolicy {
workspaceRoot: string
/**
* Opaque identity of the calling session (the branded `dsh-session`
* SessionId). Backends key per-session state off it (e.g. the windows-acl
* per-session private temp subdirectory — the write grant itself is
* per-workspace, derived from the workspace root); absent for agentless
* calls, which fall back to per-call backend state.
* SessionId). Backends key per-session state off it (e.g. windows-acl gives
* each live session/workspace pair a random private temp directory and SID,
* while the workspace SID and standing grant remain per-workspace); absent
* for agentless calls, which fall back to per-call backend state.
*/
sessionId?: SessionId
}
@@ -156,7 +156,7 @@ declare module '@deepseek-ai/cordis' {
* skipped for a sole candidate, whose own refusal remains the fail-closed end.
*/
export abstract class SandboxProvider extends Service {
/* v8 ignore next -- Windows has no sandbox backend to instantiate this service. */
/* v8 ignore next -- abstract service construction is covered through concrete provider packages. */
constructor(ctx: Context) {
super(ctx, 'sandbox')
}

Some files were not shown because too many files have changed in this diff Show More