Merge remote-tracking branch 'origin/feat/ripgrep-packaged-binary' into feat/pwsh-tool

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

@@ -354,6 +354,9 @@ const BACKGROUND_OUTPUT_PROPERTIES = {
 } as const
 
 export function apply(ctx: Context, config: Config = {}): void {
+  // FIXME(bash-env-ownership): Move ctx.bashEnv to a tool-independent shell
+  // environment plugin; replacing this tool with persistent Bash must not
+  // remove the managed DSH_* contributor seam.
   const bashEnv = new BashEnvRegistry(ctx, config)
   bashEnv.register({
     name: 'session-persistence',

packages/fs/tool-fs-search/src/index.ts

@@ -55,6 +55,7 @@ export {
   SEARCH_TIMEOUT_MS,
   SearchError,
   previewLine,
+  resolveRgPath,
   runRipgrep,
   toWorkdirRelative,
   trySaveFormattedResult,
@@ -83,7 +84,7 @@ export interface Config {
   rawOutputMaxBytes?: number
   /** Terminate-escalation grace period (ms) for one search process, handed to the subprocess seam. */
   graceMs?: number
-  /** Max bytes retained for one search's stderr diagnostic tail (never surfaced to the model). */
+  /** Max bytes retained for one search's stderr tail; the excerpt is embedded in `SEARCH_*` error messages, never shown on success. */
   stderrMaxBytes?: number
   /** Cooperative tool-call timeout budget (ms) on both tools, enforced by `@deepseek-ai/dsh-timeout-policy` through `exec.signal`. */
   timeoutMs?: number

packages/fs/tool-fs-search/src/search-core.ts

@@ -21,11 +21,10 @@
 
 import { isAbsolute, relative, sep } from 'node:path'
 import type { Context } from 'cordis'
-import { rgPath } from '@vscode/ripgrep'
 import { HarnessError } from '@deepseek-ai/dsh-llm'
 import { ItemRetainer, TextRetainer } from '@deepseek-ai/dsh-retention'
 import type { RetainedItems } from '@deepseek-ai/dsh-retention'
-import type { SubprocessCollect, SubprocessOutcome, SubprocessOutputRead, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'
+import type { SubprocessHandle, SubprocessOutcome, SubprocessOutputRead, SubprocessSpawnSpec } from '@deepseek-ai/dsh-subprocess'
 import type { SaveTextSpill, SpillRef } from '@deepseek-ai/dsh-spill'
 import type { ToolExecution } from '@deepseek-ai/dsh-tools'
 
@@ -154,6 +153,26 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu
   )
 }
 
+let rgPathPromise: Promise<string> | undefined
+
+/**
+ * The packaged ripgrep binary path, resolved lazily once per process.
+ *
+ * `@vscode/ripgrep` resolves its platform package (`@vscode/ripgrep-<platform>
+ * -<arch>`) at module evaluation, so a static import would turn a missing or
+ * corrupt platform package (`pnpm install --omit=optional`, partial install)
+ * into a failure of the whole Loader composition. Resolving at the call
+ * boundary keeps that failure at the first search call as `SEARCH_FAILED` —
+ * the package's documented no-load-time-probe contract.
+ *
+ * @returns the packaged binary's absolute path; the memoized promise rejects
+ *   when the platform package cannot be resolved.
+ */
+export function resolveRgPath(): Promise<string> {
+  rgPathPromise ??= import('@vscode/ripgrep').then(module => module.rgPath)
+  return rgPathPromise
+}
+
 /**
  * Run the packaged ripgrep binary with a plain argv vector and return its
  * complete raw stdout. The working directory is the calling agent's session
@@ -173,9 +192,12 @@ function completeStdout(toolName: string, stdout: SubprocessOutputRead, rawOutpu
  * success with zero results (`noMatches`), anything else throws a
  * {@link SearchError} (abort/timeout → `SEARCH_ABORTED`, invalid pattern →
  * `SEARCH_INVALID_PATTERN`, the rest → `SEARCH_FAILED` /
- * `SEARCH_RAW_OUTPUT_OVERFLOW`). A spawn REJECTION — the seam's
- * infrastructure failures — is translated into `SEARCH_FAILED` with the
- * original as `cause`; a pre-aborted signal becomes `SEARCH_ABORTED`.
+ * `SEARCH_RAW_OUTPUT_OVERFLOW`). Both launch-time failure domains are
+ * classified: a synchronous throw at spawn CREATION (a NUL in argv, an abort
+ * racing the pre-check, a rejected `@vscode/ripgrep` resolution) and a
+ * rejection of `handle.done` (the seam's infrastructure failures) both become
+ * `SEARCH_FAILED` with the original as `cause` — an abort already observed by
+ * creation time becomes `SEARCH_ABORTED` instead.
  *
  * @param ctx - the plugin context; execution uses its `subprocess` service.
  * @param exec - the tool-execution context; supplies the session cwd and the abort signal.
@@ -200,19 +222,31 @@ export async function runRipgrep(
   }
   const cwd = exec.agent?.session.header.cwd
   const workdir = cwd ?? process.cwd()
-  const collect = (maxBytes: number): SubprocessCollect =>
-    ({ maxBytes })
-  const handle = ctx.subprocess.spawn({
-    argv: [rgPath, '--no-config', ...argv],
-    cwd: workdir,
-    stdio: {
-      stdin: 'ignore',
-      stdout: collect(rawOutputMaxBytes),
-      stderr: collect(stderrMaxBytes),
-    },
-    graceMs,
-    signal: exec.signal,
-  } satisfies SubprocessSpawnSpec)
+  let handle: SubprocessHandle
+  try {
+    handle = ctx.subprocess.spawn({
+      argv: [await resolveRgPath(), '--no-config', ...argv],
+      cwd: workdir,
+      stdio: {
+        stdin: 'ignore',
+        stdout: { maxBytes: rawOutputMaxBytes },
+        stderr: { maxBytes: stderrMaxBytes },
+      },
+      graceMs,
+      signal: exec.signal,
+    } satisfies SubprocessSpawnSpec)
+  } catch (error: unknown) {
+    // Node's spawn() throws synchronously for a NUL in argv, and the local
+    // impl can throw synchronously when the signal aborts between the check
+    // above and this call (or when the platform-package resolution rejects).
+    // The static narrowing that proves this re-check "always false" cannot
+    // see AbortSignal state changes.
+    // oxlint-disable-next-line typescript/no-unnecessary-condition
+    if (exec.signal.aborted) {
+      throw new SearchError(`${toolName} was aborted before completion (tool timeout or caller cancellation)`, 'SEARCH_ABORTED')
+    }
+    throw new SearchError(`${toolName} could not start its search command (ripgrep launch failed)`, 'SEARCH_FAILED', { cause: error })
+  }
   let outcome: SubprocessOutcome
   try {
     outcome = await handle.done

packages/fs/tool-fs-search/tests/rg-path.spec.ts

@@ -0,0 +1,37 @@
+/**
+ * Failure-path tests for the lazy packaged-ripgrep resolution. The success
+ * path (the real `@vscode/ripgrep` module) is exercised throughout
+ * tools.spec.ts; here the module is mocked to throw at evaluation, proving a
+ * missing or corrupt platform package (`--omit=optional`, partial install)
+ * surfaces as a per-call `SEARCH_FAILED` — not a composition-load failure.
+ */
+
+import { describe, expect, it, vi } from 'vitest'
+import { Context } from 'cordis'
+import { CallId } from '@deepseek-ai/dsh-llm'
+import type { ToolExecution } from '@deepseek-ai/dsh-tools'
+import { resolveRgPath, runRipgrep } from '@deepseek-ai/dsh-tool-fs-search'
+
+// Any access to the mocked module's surface throws — the shape a missing
+// platform package produces at module evaluation.
+vi.mock('@vscode/ripgrep', () => new Proxy({}, {
+  get() {
+    throw new Error('platform package @vscode/ripgrep-win32-x64 is not installed')
+  },
+}))
+
+describe('lazy packaged-ripgrep resolution', () => {
+  it('fails the first search call with SEARCH_FAILED instead of failing module load', async () => {
+    // The resolution rejects before any spawn, so no subprocess service is needed.
+    const controller = new AbortController()
+    const exec = { signal: controller.signal, name: 'glob', callId: CallId('missing-platform-package') } as unknown as ToolExecution
+
+    await expect(runRipgrep(new Context(), exec, 'glob', ['--files'], 1_000_000, 3_000, 64 * 1024))
+      .rejects.toMatchObject({ name: 'SearchError', code: 'SEARCH_FAILED' })
+  })
+
+  it('keeps failing every subsequent call (the resolution is memoized)', async () => {
+    await expect(resolveRgPath()).rejects.toThrow(/platform package/)
+    await expect(resolveRgPath()).rejects.toThrow(/platform package/)
+  })
+})

packages/fs/tool-fs-search/tests/tools.spec.ts

@@ -32,6 +32,7 @@ import {
   presentGrepCall,
   presentGrepResult,
   previewLine,
+  resolveRgPath,
   runRipgrep,
   sampleAcrossTopLevel,
   toWorkdirRelative,
@@ -468,6 +469,48 @@ describe('workdir derivation and signal forwarding', () => {
     expect(text(result)).toContain('could not start')
   })
 
+  it('classifies a synchronous spawn-creation throw as SEARCH_FAILED', async () => {
+    // Node's spawn() throws synchronously for a NUL in argv, and the local
+    // impl can throw synchronously for other invalid specs. Creation-time
+    // failures must join the error vocabulary instead of escaping raw.
+    const { ctx, subprocess } = await setup()
+    subprocess.handler = () => { throw new Error('spawn ERR_INVALID_ARG_VALUE') }
+
+    const result = await call(ctx, 'grep', { pattern: 'x' })
+
+    expect(result.isError).toBe(true)
+    expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_FAILED' } })
+    expect(text(result)).toContain('could not start')
+  })
+
+  it('classifies a synchronous spawn-creation throw after an abort as SEARCH_ABORTED', async () => {
+    // The local impl can throw synchronously when the signal aborts between
+    // the pre-spawn check and the spawn call; no process was launched, so the
+    // abort is the reportable cause.
+    const { ctx, subprocess } = await setup()
+    const controller = new AbortController()
+    subprocess.handler = () => {
+      controller.abort('timeout')
+      throw new Error('aborted during spawn')
+    }
+
+    const result = await call(ctx, 'glob', { pattern: '*' }, { signal: controller.signal })
+
+    expect(result.isError).toBe(true)
+    expect(result.error).toMatchObject({ info: { name: 'SearchError', code: 'SEARCH_ABORTED' } })
+    expect(text(result)).toContain('aborted before completion')
+  })
+
+  it('resolves the packaged ripgrep path lazily, once per process', async () => {
+    // The module must not touch @vscode/ripgrep at load (a missing platform
+    // package would otherwise fail the whole composition), and repeated
+    // resolution reuses the first result. The resolution-failure path is
+    // pinned separately in rg-path.spec.ts.
+    await setup()
+    expect(await resolveRgPath()).toBe(rgPath)
+    expect(resolveRgPath()).toBe(resolveRgPath())
+  })
+
   it('rejects when the subprocess implementation drops a requested collect stream', async () => {
     const { ctx, subprocess } = await setup()
     subprocess.dropReaders = true

packages/host/webserver/tests/webserver.spec.ts

@@ -111,6 +111,8 @@ describe('real Loader composition', () => {
     // Static fallback semantics: real asset served, traversal 403, non-GET/
     // HEAD without a matching route 405.
     expect(await request(port, '/app.js')).toMatchObject({ status: 200, body: 'export {}' })
+    await writeFile(join(root!, 'dist', 'app.js'), 'export const rebuilt = true')
+    expect(await request(port, '/app.js')).toMatchObject({ status: 200, body: 'export const rebuilt = true' })
     expect((await request(port, '/..%2f..%2fetc%2fpasswd')).status).toBe(403)
     expect((await request(port, '/nowhere', { method: 'POST' })).status).toBe(405)