fix(pwsh-local): pin UTF-8 I/O so the Windows PowerShell 5.1 fallback cannot garble output

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

@@ -34,6 +34,17 @@ export const ENV_OVERRIDES = {
   GIT_PAGER: 'cat',
 } as const
 
+/**
+ * UTF-8 I/O pinning prepended to every command. The subprocess collector
+ * decodes output bytes as UTF-8, but Windows PowerShell 5.1 (the last-resort
+ * executable fallback) writes the console/OEM code page by default, which
+ * garbles non-ASCII output; pwsh 7 defaults to UTF-8 and is unaffected. The
+ * statements ride on line 1 after `; ` separators so PowerShell error line
+ * numbers stay accurate.
+ */
+export const ENCODING_PREAMBLE =
+  '[Console]::OutputEncoding = [System.Text.UTF8Encoding]::new($false); $OutputEncoding = [System.Text.UTF8Encoding]::new($false); '
+
 /** Default SIGTERM→SIGKILL grace period (the `graceMs` config). */
 const DEFAULT_GRACE_MS = 3_000
 
@@ -197,7 +208,7 @@ export class PwshLocalExecutor extends BashExecutor {
     const collect = (maxBytes: number): SubprocessCollect =>
       ({ maxBytes, spill: { maxBytes: this.config.maxSpillBytes } })
     return {
-      argv: [this.pwshPath, '-NoLogo', '-NoProfile', '-NonInteractive', '-Command', spec.command],
+      argv: [this.pwshPath, '-NoLogo', '-NoProfile', '-NonInteractive', '-Command', `${ENCODING_PREAMBLE}${spec.command}`],
       cwd: spec.workdir,
       stdio: {
         stdin: spec.stdin !== undefined ? { data: spec.stdin } : 'ignore',
@@ -307,7 +318,10 @@ export class PwshLocalExecutor extends BashExecutor {
 
   /**
    * Settlement hook for subclasses that attach execution facts to a process.
-   * The base implementation is intentionally empty.
+   * The base implementation is intentionally empty. Mirrored from
+   * `dsh-bash-local` (whose sandboxing subclass consumes the same hook); it is
+   * the declared seam for a future pwsh-confining subclass and has no consumer
+   * in this package yet.
    * @param _proc - the settled process handle.
    * @param _stderr - the process's retained stderr tail used by subclasses for settlement classification.
    */

packages/bash/pwsh-local/tests/executor.spec.ts

@@ -15,13 +15,17 @@ import { join } from 'node:path'
 import { spawnSync } from 'node:child_process'
 import { describe, expect, it } from 'vitest'
 import { Context } from 'cordis'
-import { PwshLocalExecutor, candidatePwshPaths, resolvePwshPath } from '@deepseek-ai/dsh-pwsh-local'
+import { PwshLocalExecutor, ENCODING_PREAMBLE, candidatePwshPaths, resolvePwshPath } from '@deepseek-ai/dsh-pwsh-local'
 import LocalSubprocessService from '@deepseek-ai/dsh-subprocess-local'
+import SubprocessService from '@deepseek-ai/dsh-subprocess'
+import type { SubprocessHandle, SubprocessOutputReader, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'
 import type { BashProcess } from '@deepseek-ai/dsh-bash'
 
 const spillDir = mkdtempSync(join(tmpdir(), 'dsh-pwsh-exec-spec-'))
 
-const hasPwsh = spawnSync('pwsh', ['-NoLogo', '-NoProfile', '-NonInteractive', '-Command', '$true'], { encoding: 'utf8' }).status === 0
+// The probe follows the executor's own resolution (Program Files installs on
+// Windows are found even when bare `pwsh` is not on PATH).
+const hasPwsh = spawnSync(resolvePwshPath(), ['-NoLogo', '-NoProfile', '-NonInteractive', '-Command', '$true'], { encoding: 'utf8' }).status === 0
 
 /** Normalize PowerShell's platform line endings (CRLF on Windows, LF elsewhere). */
 const lf = (text: string): string => text.replace(/\r\n/g, '\n')
@@ -110,6 +114,42 @@ describe('resolvePwshPath and candidatePwshPaths (pure, every platform)', () =>
   })
 })
 
+describe('spawn construction (pure, every platform)', () => {
+  /** A subprocess service that records spawn specs and settles instantly. */
+  class CapturingSubprocessService extends SubprocessService {
+    specs: SubprocessSpawnSpec[] = []
+    private readonly reader: SubprocessOutputReader = {
+      readFrom: () => ({ text: '', lossy: false, nextOffset: 0 }),
+    }
+    override spawn(spec: SubprocessSpawnSpec): SubprocessHandle {
+      this.specs.push(spec)
+      return {
+        pid: -1,
+        stdin: undefined,
+        stdout: undefined,
+        stderr: undefined,
+        collected: { stdout: this.reader, stderr: this.reader },
+        done: Promise.resolve({ exitCode: 0, signal: null }),
+        terminate: () => {},
+        waitForExit: async () => true,
+      }
+    }
+  }
+
+  it('runs every command as ONE argv element under the UTF-8 encoding preamble', async () => {
+    const ctx = new Context()
+    const subprocess = new CapturingSubprocessService(ctx)
+    await ctx.plugin(PwshLocalExecutor)
+    await ctx.bash.run(ctx.bash.resolve({ command: 'Write-Output 你好' }))
+    expect(subprocess.specs).toHaveLength(1)
+    const { argv } = subprocess.specs[0]!
+    expect(argv.slice(0, 5)).toEqual([expect.any(String), '-NoLogo', '-NoProfile', '-NonInteractive', '-Command'])
+    expect(argv[5]).toBe(`${ENCODING_PREAMBLE}Write-Output 你好`)
+    expect(ENCODING_PREAMBLE).toContain('[Console]::OutputEncoding')
+    expect(ENCODING_PREAMBLE).toContain('$OutputEncoding')
+  })
+})
+
 describe.skipIf(!hasPwsh)('PwshLocalExecutor.run', () => {
   it('resolves with output and the effective timeout', async () => {
     const { bash } = await setup({ timeoutMs: 5_000 })