Просмотр исходного кода

fix(pwsh): stamp the calling session's sandbox policy onto pwsh tool calls

Huanqi Cao 1 месяц назад
Родитель
Сommit
43d53d339d

+ 5 - 2
docs/module-graph.md

@@ -445,6 +445,7 @@ flowchart TD
   pkg_sandbox_local --> pkg_invariants
   pkg_sandbox_local --> pkg_llm
   pkg_sandbox_local --> pkg_sandbox
+  pkg_sandbox_local --> pkg_session
   pkg_session_projection --> pkg_invariants
   pkg_session_projection --> pkg_session
   pkg_llm_retry --> pkg_agent
@@ -868,6 +869,8 @@ flowchart TD
   pkg_tool_pwsh --> pkg_bash_env
   pkg_tool_pwsh --> pkg_invariants
   pkg_tool_pwsh --> pkg_llm
+  pkg_tool_pwsh --> pkg_sandbox
+  pkg_tool_pwsh --> pkg_sandbox_policy
   pkg_tool_pwsh --> pkg_system_prompt
   pkg_tool_pwsh --> pkg_tasks
   pkg_tool_pwsh --> pkg_tools
@@ -1232,7 +1235,7 @@ flowchart TD
 | [`app-boot`](../packages/ui/app-boot) | `ui` | [`environment`](../packages/util/environment), [`invariants`](../packages/support/invariants), [`paths`](../packages/util/paths), [`system-prompt`](../packages/core/system-prompt) |
 | [`code-runtime-worker`](../packages/code-runtime/code-runtime-worker) | `code-runtime` | [`code-runtime`](../packages/code-runtime/code-runtime), [`invariants`](../packages/support/invariants), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
 | [`lsp-local`](../packages/lsp/lsp-local) | `lsp` | [`brand`](../packages/util/brand), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`lsp`](../packages/lsp/lsp), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
-| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox) |
+| [`sandbox-local`](../packages/sandbox/sandbox-local) | `sandbox` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`session`](../packages/core/session) |
 | [`session-projection`](../packages/session-projection/session-projection) | `session-projection` | [`invariants`](../packages/support/invariants), [`session`](../packages/core/session) |
 | [`llm-retry`](../packages/llm/llm-retry) | `llm` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`timeout`](../packages/util/timeout) |
 | [`token-meter`](../packages/llm/token-meter) | `llm` | [`compact`](../packages/compact/compact), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`session-projection`](../packages/session-projection/session-projection) |
@@ -1313,7 +1316,7 @@ flowchart TD
 | [`session-telemetry-otel`](../packages/telemetry/session-telemetry-otel) | `telemetry` | [`brand`](../packages/util/brand), [`command-feedback`](../packages/feedback/command-feedback), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`paths`](../packages/util/paths), [`session`](../packages/core/session), [`session-telemetry`](../packages/telemetry/session-telemetry) |
 | [`tool-workflow`](../packages/workflow/tool-workflow) | `workflow` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`workflow`](../packages/workflow/workflow) |
 | [`tool-bash`](../packages/bash/tool-bash) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |
-| [`tool-pwsh`](../packages/bash/tool-pwsh) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
+| [`tool-pwsh`](../packages/bash/tool-pwsh) | `bash` | [`agent`](../packages/core/agent), [`bash`](../packages/bash/bash), [`bash-env`](../packages/bash/bash-env), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox`](../packages/sandbox/sandbox), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`system-prompt`](../packages/core/system-prompt), [`tasks`](../packages/tasks/tasks), [`tools`](../packages/core/tools) |
 | [`subagent-acp`](../packages/subagent/subagent-acp) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
 | [`subagent-claude-code`](../packages/subagent/subagent-claude-code) | `subagent` | [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`subprocess`](../packages/subprocess/subprocess), [`timeout`](../packages/util/timeout) |
 | [`subagent-inprocess`](../packages/subagent/subagent-inprocess) | `subagent` | [`agent`](../packages/core/agent), [`invariants`](../packages/support/invariants), [`llm`](../packages/llm/llm), [`sandbox-policy`](../packages/sandbox/sandbox-policy), [`session`](../packages/core/session), [`subagent`](../packages/subagent/subagent), [`system-prompt`](../packages/core/system-prompt), [`tools`](../packages/core/tools), [`user-approval`](../packages/ui/user-approval) |

+ 4 - 0
packages/bash/tool-pwsh/package.json

@@ -30,6 +30,8 @@
     "@deepseek-ai/dsh-bash-env": "^0.0.1",
     "@deepseek-ai/dsh-invariants": "^0.0.1",
     "@deepseek-ai/dsh-llm": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox": "^0.0.1",
+    "@deepseek-ai/dsh-sandbox-policy": "^0.0.1",
     "@deepseek-ai/dsh-system-prompt": "^0.0.1",
     "@deepseek-ai/dsh-tasks": "^0.0.1",
     "@deepseek-ai/dsh-tools": "^0.0.1",
@@ -46,6 +48,8 @@
     "@deepseek-ai/dsh-llm": "workspace:^",
     "@deepseek-ai/dsh-loader-smoke": "workspace:^",
     "@deepseek-ai/dsh-pwsh-local": "workspace:^",
+    "@deepseek-ai/dsh-sandbox": "workspace:^",
+    "@deepseek-ai/dsh-sandbox-policy": "workspace:^",
     "@deepseek-ai/dsh-subprocess-local": "workspace:^",
     "@deepseek-ai/dsh-system-prompt": "workspace:^",
     "@deepseek-ai/dsh-tasks": "workspace:^",

+ 21 - 6
packages/bash/tool-pwsh/src/index.ts

@@ -4,11 +4,13 @@
  * `@deepseek-ai/dsh-pwsh-local`) backs `ctx.bash`; the tool contract is
  * PowerShell-dialect: native `C:\...` paths and `$env:NAME` variables.
  *
- * Behavior mirrors `dsh-tool-bash` call-for-call minus the sandbox surface:
- * foreground and `run_in_background` execution (background handles register
- * with the generic `ctx.tasks` runtime), the managed `DSH_*` environment
- * through the shared `bash-env` registry, and the bash marker/truncation
- * rendering story. UI presentation mirrors the bash tool's too: a completed
+ * Behavior mirrors `dsh-tool-bash` call-for-call minus the escalation
+ * surface: foreground and `run_in_background` execution (background handles
+ * register with the generic `ctx.tasks` runtime), the managed `DSH_*`
+ * environment through the shared `bash-env` registry, the per-call sandbox
+ * policy resolution (the calling session's mode and cwd travel to the
+ * confining executor), and the bash marker/truncation rendering story. UI
+ * presentation mirrors the bash tool's too: a completed
  * foreground call is a terminal card with the parsed exit-status pill, using
  * the shared exit-status parse from `@deepseek-ai/dsh-bash`.
  *
@@ -19,12 +21,14 @@ import { isAbsolute, resolve as resolvePath } from 'node:path'
 import type { Context } from 'cordis'
 import z from 'schemastery'
 import { defineTool, TOOL_ABORTED } from '@deepseek-ai/dsh-tools'
-import type { GenericCallView, TerminalCallView, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
+import type { GenericCallView, TerminalCallView, ToolExecution, ToolResult, ToolResultView } from '@deepseek-ai/dsh-tools'
 import { HarnessError } from '@deepseek-ai/dsh-llm'
 import type { Agent } from '@deepseek-ai/dsh-agent'
 import type {} from '@deepseek-ai/dsh-system-prompt'
 import type {} from '@deepseek-ai/dsh-tasks'
 import type {} from '@deepseek-ai/dsh-bash-env'
+import type { SandboxExecutionPolicy } from '@deepseek-ai/dsh-sandbox'
+import type { SandboxPolicyService } from '@deepseek-ai/dsh-sandbox-policy'
 import type { BashRunResult } from '@deepseek-ai/dsh-bash'
 import { parseExitStatus } from '@deepseek-ai/dsh-bash'
 import { processOutcome } from './background.ts'
@@ -141,6 +145,14 @@ const BACKGROUND_OUTPUT_PROPERTIES = {
 
 export function apply(ctx: Context, config: Config = {}): void {
   const backgroundEnabled = config.enableRunInBackground ?? true
+  const defaultMode = ctx.bash.sandboxMode
+  const sandboxPolicy: SandboxPolicyService | undefined = defaultMode === undefined ? undefined : ctx.get('sandboxPolicy')
+  if (defaultMode !== undefined && sandboxPolicy === undefined) {
+    throw new Error('tool-pwsh: the mounted bash executor confines but ctx.sandboxPolicy is missing')
+  }
+  /** Resolve the complete standing policy for this call when a confining executor is mounted. */
+  const resolveSandboxPolicy = (exec: ToolExecution): SandboxExecutionPolicy | undefined =>
+    sandboxPolicy?.resolve(exec.agent === undefined ? {} : { session: exec.agent.session })
 
   ctx.systemPrompt.section({
     name: 'tool:pwsh',
@@ -224,12 +236,15 @@ export function apply(ctx: Context, config: Config = {}): void {
     /* jscpd:ignore-start -- the execute path mirrors dsh-tool-bash's by design (see the pwsh-tool-and-executor Agent Note). */
     async execute(args: PwshToolArgs, exec) {
       validatePwshArgs(args)
+      // Description is display metadata; workdir defaults to the caller's session.
+      const standingPolicy = resolveSandboxPolicy(exec)
       const workdir = resolveWorkdir(args.workdir, exec)
       const request = {
         command: args.command,
         ...workdir !== undefined ? { workdir } : {},
         ...args.timeoutMs !== undefined ? { timeoutMs: args.timeoutMs } : {},
         dshEnv: ctx.bashEnv.collect(exec),
+        ...standingPolicy !== undefined ? { sandboxPolicy: standingPolicy } : {},
       }
       if (args.run_in_background === true) {
         // Undeclared keys are allowed, so schema omission also needs enforcement.

+ 99 - 2
packages/bash/tool-pwsh/tests/tools.spec.ts

@@ -11,7 +11,7 @@
 
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import { mkdtempSync } from 'node:fs'
+import { mkdtempSync, realpathSync } from 'node:fs'
 import { tmpdir } from 'node:os'
 import { join, resolve as resolvePath } from 'node:path'
 import { CallId } from '@deepseek-ai/dsh-llm'
@@ -24,6 +24,7 @@ import type { Agent } from '@deepseek-ai/dsh-agent'
 import { SessionId } from '@deepseek-ai/dsh-session'
 import { BashExecutor } from '@deepseek-ai/dsh-bash'
 import type { BashExecRequest, BashExecSpec, BashProcess, BashRunResult } from '@deepseek-ai/dsh-bash'
+import SandboxPolicyService from '@deepseek-ai/dsh-sandbox-policy'
 import * as ToolPwsh from '@deepseek-ai/dsh-tool-pwsh'
 import * as BashEnvPlugin from '@deepseek-ai/dsh-bash-env'
 import type { BashProcessRead } from '@deepseek-ai/dsh-bash'
@@ -150,9 +151,59 @@ async function setupWithTasks(toolConfig: Partial<ToolPwsh.Config> = {}, dshHome
   return { ctx, bash }
 }
 
+/**
+ * A CONFINING fake executor (`sandboxMode` advertised): the tool must resolve
+ * the calling session's standing policy and stamp it on the request, exactly
+ * like the bash tool — the per-session sandbox-policy regression surface.
+ */
+class ConfiningFakeBash extends BashExecutor {
+  requests: BashExecRequest[] = []
+
+  override get sandboxMode() {
+    return 'read-only' as const
+  }
+
+  override resolve(request: BashExecRequest): BashExecSpec {
+    this.requests.push(request)
+    return {
+      command: request.command,
+      workdir: request.workdir ?? process.cwd(),
+      timeoutMs: request.timeoutMs ?? 60_000,
+      stdoutMaxBytes: request.stdoutMaxBytes ?? 64_000,
+      ...request.signal ? { signal: request.signal } : {},
+      ...request.dshEnv !== undefined ? { dshEnv: request.dshEnv } : {},
+      sandboxPolicy: request.sandboxPolicy,
+    }
+  }
+
+  override async run(_spec: BashExecSpec): Promise<BashRunResult> {
+    return runResult('ok\n')
+  }
+
+  override start(_spec: BashExecSpec): BashProcess {
+    return fakeProcess()
+  }
+}
+
+/** Sandboxed composition: the shared policy service + a confining executor + the pwsh tool. */
+async function setupSandboxed(toolConfig: Partial<ToolPwsh.Config> = {}) {
+  const ctx = new Context()
+  await ctx.plugin(SystemPrompt)
+  await ctx.plugin(ToolRegistry)
+  await ctx.plugin(AgentRegistry)
+  await ctx.plugin(BashEnvPlugin)
+  await ctx.plugin(SandboxPolicyService, {})
+  await ctx.plugin(ConfiningFakeBash)
+  await ctx.plugin(ToolPwsh, toolConfig)
+  const bash = ctx.bash as ConfiningFakeBash
+  return { ctx, bash }
+}
+
 /**
  * Build a fake {@link Agent} with the shared agent/session identity, give it a
  * dedicated lifecycle fiber for `Agent.ctx`, and register it in `ctx.agents`.
+ * The fake session carries an empty event log (the sandbox-policy resolver
+ * folds the log for mode overrides, mirroring a real session).
  */
 function registerFakeAgent(ctx: Context, sessionId: string): Agent {
   const scopeFiber = ctx.plugin(() => {})
@@ -160,7 +211,7 @@ function registerFakeAgent(ctx: Context, sessionId: string): Agent {
   const agent = {
     id,
     ctx: scopeFiber.ctx,
-    session: { id, header: { version: 0, id, createdAt: 0 } },
+    session: { id, header: { version: 0, id, createdAt: 0 }, events: [] },
   } as unknown as Agent
   ctx.agents.register(agent)
   return agent
@@ -397,6 +448,52 @@ describe('execution through the bash seam', () => {
   })
 })
 
+describe('per-call sandbox policy resolution', () => {
+  it('stamps the CALLING SESSION\'s resolved policy onto the request (session cwd, not the server launch dir)', async () => {
+    const { ctx, bash } = await setupSandboxed()
+    const sessionCwd = mkdtempSync(join(tmpdir(), 'dsh-tool-pwsh-policy-'))
+    const agent = registerFakeAgent(ctx, 'policy-session')
+    Object.assign(agent.session.header, { cwd: sessionCwd })
+    const result = await call(ctx, 'pwsh', { command: 'Write-Output hi', description: 'say hi' }, agent)
+    expect(result.isError).toBe(false)
+    // The policy's workspace root is the session cwd canonicalized by the
+    // policy service (realpath + resolve), NEVER the web server's launch dir;
+    // the calling session's identity rides along for backend per-session state.
+    expect(bash.requests[0]?.sandboxPolicy).toEqual({
+      mode: 'read-only',
+      workspaceRoot: resolvePath(realpathSync.native(sessionCwd)),
+      sessionId: 'policy-session',
+    })
+  })
+
+  it('falls back to the deployment policy without an agent, and omits the field entirely without a confining executor', async () => {
+    const { ctx, bash } = await setupSandboxed()
+    await call(ctx, 'pwsh', { command: 'Write-Output hi', description: 'say hi' })
+    expect(bash.requests[0]?.sandboxPolicy).toEqual({
+      mode: 'read-only',
+      workspaceRoot: resolvePath(realpathSync.native(process.cwd())),
+    })
+
+    // The base FakeBash advertises no sandboxMode, so the tool must not stamp
+    // any policy (the executor defaulting stays the executor's own).
+    const plain = await setup()
+    await call(plain.ctx, 'pwsh', { command: 'Write-Output hi', description: 'say hi' })
+    expect(plain.bash.requests[0]).not.toHaveProperty('sandboxPolicy')
+  })
+
+  it('fails load when a confining executor has no shared sandbox-policy resolver', async () => {
+    const ctx = new Context()
+    await ctx.plugin(SystemPrompt)
+    await ctx.plugin(ToolRegistry)
+    await ctx.plugin(AgentRegistry)
+    await ctx.plugin(BashEnvPlugin)
+    await ctx.plugin(ConfiningFakeBash)
+    await expect(ctx.plugin(ToolPwsh)).rejects.toThrow(
+      'tool-pwsh: the mounted bash executor confines but ctx.sandboxPolicy is missing',
+    )
+  })
+})
+
 describe('background execution through the task runtime', () => {
   it('run_in_background acks with the task id, readable through the REAL task_output tool', async () => {
     const { ctx } = await setupWithTasks()

+ 6 - 0
packages/bash/tool-pwsh/tsconfig.json

@@ -38,6 +38,12 @@
     {
       "path": "../../core/system-prompt"
     },
+    {
+      "path": "../../sandbox/sandbox"
+    },
+    {
+      "path": "../../sandbox/sandbox-policy"
+    },
     {
       "path": "../../support/invariants"
     }