fix(ripgrep): use @vscode/ripgrep package as the builtin source (#911 )

The vendored-binary lookup at vendor/ripgrep/<arch>-<platform>/rg never resolved in this fork — that directory does not ship — so users without a system rg had no working fallback. Switch to the @vscode/ripgrep package so Microsoft maintains the platform/arch matrix and the binary is delivered via npm. - src/utils/ripgrep.ts: replace hand-rolled vendor-path resolution with rgPath from @vscode/ripgrep. Lazy require so a missing package falls through to the system rg branch instead of throwing at import. Drop builtinExists from the config args; builtinCommand is now a string-or-null. The system override (USE_BUILTIN_RIPGREP=0), the Bun-compiled standalone embedded mode, the macOS codesign hook, and all retry/timeout/error logic are preserved untouched. - scripts/build.ts: mark @vscode/ripgrep as external. The package resolves rgPath via __dirname at runtime, so bundling would freeze the build host's absolute path into dist/cli.mjs. - src/utils/ripgrep.test.ts: update for the new config shape and add tests covering USE_BUILTIN_RIPGREP=0, embedded mode, last-resort fallback, and null builtin path. Tested locally on Linux (Bun 1.3.13). macOS (codesign hook) and Windows (rg.exe extension) need contributor verification.
2026-04-28 09:21:07 +05:30
5 changed files with 106 additions and 29 deletions
--- a/bun.lock
+++ b/bun.lock
@@ -28,6 +28,7 @@
        "@opentelemetry/sdk-trace-base": "2.6.1",
        "@opentelemetry/sdk-trace-node": "2.6.1",
        "@opentelemetry/semantic-conventions": "1.40.0",
+        "@vscode/ripgrep": "^1.17.1",
        "ajv": "8.18.0",
        "auto-bind": "5.0.1",
        "axios": "1.15.0",
@@ -461,6 +462,8 @@

    "@types/react": ["@types/react@19.2.14", "", { "dependencies": { "csstype": "^3.2.2" } }, "sha512-ilcTH/UniCkMdtexkoCN0bI7pMcJDvmQFPvuPvmEaYA/NSfFTAgdUSLAoVjaRJm7+6PvcM+q1zYOwS4wTYMF9w=="],

+    "@vscode/ripgrep": ["@vscode/ripgrep@1.17.1", "", { "dependencies": { "https-proxy-agent": "^7.0.2", "proxy-from-env": "^1.1.0", "yauzl": "^2.9.2" } }, "sha512-xTs7DGyAO3IsJYOCTBP8LnTvPiYVKEuyv8s0xyJDBXfs8rhBfqnZPvb6xDT+RnwWzcXqW27xLS/aGrkjX7lNWw=="],
+
    "accepts": ["accepts@2.0.0", "", { "dependencies": { "mime-types": "^3.0.0", "negotiator": "^1.0.0" } }, "sha512-5cvg6CtKwfgdmVqY1WIiXKc3Q1bkRqGLi+2W/6ao+6Y7gu/RCwRuAhGEzh5B4KlszSuTLgZYuqFqo5bImjNKng=="],

    "agent-base": ["agent-base@7.1.4", "", {}, "sha512-MnA+YT8fwfJPgBx3m60MNqakm30XOkyIoH1y6huTQvC0PwZG7ki8NacLBcrPbNoo8vEZy7Jpuk7+jMO+CUovTQ=="],
@@ -491,6 +494,8 @@

    "bowser": ["bowser@2.14.1", "", {}, "sha512-tzPjzCxygAKWFOJP011oxFHs57HzIhOEracIgAePE4pqB3LikALKnSzUyU4MGs9/iCEUuHlAJTjTc5M+u7YEGg=="],

+    "buffer-crc32": ["buffer-crc32@0.2.13", "", {}, "sha512-VO9Ht/+p3SN7SKWqcrgEzjGbRSJYTx+Q1pTQC0wrWqHx0vpJraQ6GtHx8tvcg1rlK1byhU5gccxgOgj7B0TDkQ=="],
+
    "buffer-equal-constant-time": ["buffer-equal-constant-time@1.0.1", "", {}, "sha512-zRpUiDwd/xk6ADqPMATG8vc9VPrkck7T07OIx0gnjmJAnHnTVXNQG3vfvWNuiZIkwu9KrKdA1iJKfsfTVxE6NA=="],

    "bun-types": ["bun-types@1.3.11", "", { "dependencies": { "@types/node": "*" } }, "sha512-1KGPpoxQWl9f6wcZh57LvrPIInQMn2TQ7jsgxqpRzg+l0QPOFvJVH7HmvHo/AiPgwXy+/Thf6Ov3EdVn1vOabg=="],
@@ -609,6 +614,8 @@

    "fast-xml-parser": ["fast-xml-parser@5.5.8", "", { "dependencies": { "fast-xml-builder": "^1.1.4", "path-expression-matcher": "^1.2.0", "strnum": "^2.2.0" }, "bin": { "fxparser": "src/cli/cli.js" } }, "sha512-Z7Fh2nVQSb2d+poDViM063ix2ZGt9jmY1nWhPfHBOK2Hgnb/OW3P4Et3P/81SEej0J7QbWtJqxO05h8QYfK7LQ=="],

+    "fd-slicer": ["fd-slicer@1.1.0", "", { "dependencies": { "pend": "~1.2.0" } }, "sha512-cE1qsB/VwyQozZ+q1dGxR8LBYNZeofhEdUNGSMbQD3Gw2lAzX9Zb3uIU6Ebc/Fmyjo9AWWfnn0AUCHqtevs/8g=="],
+
    "fflate": ["fflate@0.8.2", "", {}, "sha512-cPJU47OaAoCbg0pBvzsgpTPhmhqI5eJjh/JIu8tPj5q+T7iLvW/JAYUqmE7KOB4R1ZyEhzBaIQpQpardBF5z8A=="],

    "figures": ["figures@6.1.0", "", { "dependencies": { "is-unicode-supported": "^2.0.0" } }, "sha512-d+l3qxjSesT4V7v2fh+QnmFnUWv9lSpjarhShNTgBOfA0ttejbQUAlHLitbjkoRiDulW0OPoQPYIGhIC8ohejg=="],
@@ -787,6 +794,8 @@

    "path-to-regexp": ["path-to-regexp@8.4.1", "", {}, "sha512-fvU78fIjZ+SBM9YwCknCvKOUKkLVqtWDVctl0s7xIqfmfb38t2TT4ZU2gHm+Z8xGwgW+QWEU3oQSAzIbo89Ggw=="],

+    "pend": ["pend@1.2.0", "", {}, "sha512-F3asv42UuXchdzt+xXqfW1OGlVBe+mxa2mqI0pg5yAHZPvFmY3Y6drSf/GQ1A86WgWEN9Kzh/WrgKa6iGcHXLg=="],
+
    "picomatch": ["picomatch@4.0.4", "", {}, "sha512-QP88BAKvMam/3NxH6vj2o21R6MjxZUAd6nlwAS/pnGvN9IVLocLHxGYIzFhg6fUQ+5th6P4dv4eW9jX3DSIj7A=="],

    "pkce-challenge": ["pkce-challenge@5.0.1", "", {}, "sha512-wQ0b/W4Fr01qtpHlqSqspcj3EhBvimsdh0KlHhH8HRZnMsEa0ea2fTULOXOS9ccQr3om+GcGRk4e+isrZWV8qQ=="],
@@ -801,7 +810,7 @@

    "proxy-addr": ["proxy-addr@2.0.7", "", { "dependencies": { "forwarded": "0.2.0", "ipaddr.js": "1.9.1" } }, "sha512-llQsMLSUDUPT44jdrU/O37qlnifitDP+ZwrmmZcoSKyLKvtZxpyV0n2/bD/N4tBAAZ/gJEdZU7KMraoK1+XYAg=="],

-    "proxy-from-env": ["proxy-from-env@2.1.0", "", {}, "sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA=="],
+    "proxy-from-env": ["proxy-from-env@1.1.0", "", {}, "sha512-D+zkORCbA9f1tdWRK0RaCR3GPv50cMxcrz4X8k5LTSUD1Dkw47mKJEZQNunItRTkWwgtaUSo1RVFRIG9ZXiFYg=="],

    "qrcode": ["qrcode@1.5.4", "", { "dependencies": { "dijkstrajs": "^1.0.1", "pngjs": "^5.0.0", "yargs": "^15.3.1" }, "bin": { "qrcode": "bin/qrcode" } }, "sha512-1ca71Zgiu6ORjHqFBDpnSMTR2ReToX4l1Au1VFLyVeBTFavzQnv5JxMFr3ukHVKpSrSA2MCk0lNJSykjUfz7Zg=="],

@@ -953,6 +962,8 @@

    "yargs-parser": ["yargs-parser@21.1.1", "", {}, "sha512-tVpsJW7DdjecAiFpbIB1e3qxIQsE6NoPc5/eTdrbbIC4h0LVsWhnoa3g+m2HclBIujHzsxZ4VJVA+GUuc2/LBw=="],

+    "yauzl": ["yauzl@2.10.0", "", { "dependencies": { "buffer-crc32": "~0.2.3", "fd-slicer": "~1.1.0" } }, "sha512-p4a9I6X6nu6IhoGmBqAcbJy1mlC4j27vEPZX9F4L4/vZT3Lyq1VkFHw/V/PUcB9Buo+DG3iHkT0x3Qya58zc3g=="],
+
    "yoctocolors": ["yoctocolors@2.1.2", "", {}, "sha512-CzhO+pFNo8ajLM2d2IW/R93ipy99LWjtwblvC1RsoSUMZgyLbYFr221TnSNT7GjGdYui6P459mw9JH/g/zW2ug=="],

    "zod": ["zod@3.25.76", "", {}, "sha512-gzUt/qt81nXsFGKIFcC3YnfEAx5NkunCfnDlvuBSSFS02bcXu4Lmea0AFIUwbLWxWPx3d9p8S5QoaujKcNQxcQ=="],
@@ -1369,6 +1380,8 @@

    "@smithy/uuid/tslib": ["tslib@2.8.1", "", {}, "sha512-oJFu94HQb+KVduSUQL7wnpmqnfmLsOA/nAh6b6EH0wCEoK0/mPeXU6c3wKDV83MkOuHPRHtSXKKU99IBazS/2w=="],

+    "axios/proxy-from-env": ["proxy-from-env@2.1.0", "", {}, "sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA=="],
+
    "cli-highlight/chalk": ["chalk@4.1.2", "", { "dependencies": { "ansi-styles": "^4.1.0", "supports-color": "^7.1.0" } }, "sha512-oKnbhFyRIXpUuez8iBMmyEa4nbj4IOQyuhc/wy9kY7/WVPcwIO9VA668Pu8RkO7+0G76SLROeyw9CpQ061i4mA=="],

    "cli-highlight/yargs": ["yargs@16.2.0", "", { "dependencies": { "cliui": "^7.0.2", "escalade": "^3.1.1", "get-caller-file": "^2.0.5", "require-directory": "^2.1.1", "string-width": "^4.2.0", "y18n": "^5.0.5", "yargs-parser": "^20.2.2" } }, "sha512-D1mvvtDG0L5ft/jGWkLpG1+m0eQxOfaBvTNELraWj22wSVUMWxZUvYgJYcKh6jGGIkJFhH4IZPQhR4TKpc8mBw=="],
@@ -1429,6 +1442,8 @@

    "@aws-sdk/nested-clients/@smithy/util-base64/@smithy/util-buffer-from": ["@smithy/util-buffer-from@4.2.2", "", { "dependencies": { "@smithy/is-array-buffer": "^4.2.2", "tslib": "^2.6.2" } }, "sha512-FDXD7cvUoFWwN6vtQfEta540Y/YBe5JneK3SoZg9bThSoOAC/eGeYEua6RkBgKjGa/sz6Y+DuBZj3+YEY21y4Q=="],

+    "@mendable/firecrawl-js/axios/proxy-from-env": ["proxy-from-env@2.1.0", "", {}, "sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA=="],
+
    "@opentelemetry/exporter-trace-otlp-grpc/@opentelemetry/core/@opentelemetry/semantic-conventions": ["@opentelemetry/semantic-conventions@1.28.0", "", {}, "sha512-lp4qAiMTD4sNWW4DbKLBkfiMZ4jbAboJIGOQr5DvciMRI494OapieI9qiODpOt0XBr1LjIDy1xAGAnVs5supTA=="],

    "@opentelemetry/exporter-trace-otlp-grpc/@opentelemetry/otlp-transformer/@opentelemetry/api-logs": ["@opentelemetry/api-logs@0.57.2", "", { "dependencies": { "@opentelemetry/api": "^1.3.0" } }, "sha512-uIX52NnTM0iBh84MShlpouI7UKqkZ7MrUszTmaypHBu4r7NofznSnQRfJ+uUeDtQDj6w8eFGg5KBLDAwAPz1+A=="],
@@ -1509,6 +1524,8 @@

    "cliui/wrap-ansi/ansi-styles": ["ansi-styles@4.3.0", "", { "dependencies": { "color-convert": "^2.0.1" } }, "sha512-zbB9rCJAT1rbjiVDb2hqKFHNYLxgtk8NURxZ3IZwD3F6NtxbXZQCnnSi1Lkx+IDohdPlFp222wVALIheZJQSEg=="],

+    "firecrawl/axios/proxy-from-env": ["proxy-from-env@2.1.0", "", {}, "sha512-cJ+oHTW1VAEa8cJslgmUZrc+sjRKgAKl3Zyse6+PV38hZe/V6Z14TbCuXcan9F9ghlz4QrFr2c92TNF82UkYHA=="],
+
    "form-data/mime-types/mime-db": ["mime-db@1.52.0", "", {}, "sha512-sPU4uV7dYlvtWJxwwxHD0PuihVNiE7TyAbQ5SWxDCB9mUYvOgroQOwYQQOKPJ8CIbE+1ETVlOoK1UC2nU3gYvg=="],

    "qrcode/yargs/cliui": ["cliui@6.0.0", "", { "dependencies": { "string-width": "^4.2.0", "strip-ansi": "^6.0.0", "wrap-ansi": "^6.2.0" } }, "sha512-t6wbgtoCXvAzst7QgXxJYqPt0usEfbgQdftEPbLL/cvv6HPE5VgvqCuAIDR0NgU52ds6rFwqrgakNLrHEjCbrQ=="],
--- a/package.json
+++ b/package.json
@@ -74,6 +74,7 @@
    "@opentelemetry/sdk-trace-base": "2.6.1",
    "@opentelemetry/sdk-trace-node": "2.6.1",
    "@opentelemetry/semantic-conventions": "1.40.0",
+    "@vscode/ripgrep": "^1.17.1",
    "ajv": "8.18.0",
    "auto-bind": "5.0.1",
    "axios": "1.15.0",
--- a/scripts/build.ts
+++ b/scripts/build.ts
@@ -472,6 +472,11 @@ ${exports}
    '@aws-sdk/credential-providers',
    '@azure/identity',
    'google-auth-library',
+    // @vscode/ripgrep ships a platform-specific binary alongside its
+    // index.js and resolves the path via __dirname at runtime. Bundling
+    // would freeze the build host's absolute path into dist/cli.mjs, so we
+    // keep it external and rely on the npm package being installed.
+    '@vscode/ripgrep',
  ],
 })

--- a/src/utils/ripgrep.test.ts
+++ b/src/utils/ripgrep.test.ts
@@ -5,16 +5,15 @@ import { resolveRipgrepConfig, wrapRipgrepUnavailableError } from './ripgrep.js'

 const MOCK_BUILTIN_PATH = path.normalize(
  process.platform === 'win32'
-    ? `vendor/ripgrep/${process.arch}-win32/rg.exe`
-    : `vendor/ripgrep/${process.arch}-${process.platform}/rg`,
+    ? `node_modules/@vscode/ripgrep/bin/rg.exe`
+    : `node_modules/@vscode/ripgrep/bin/rg`,
 )

-test('ripgrepCommand falls back to system rg when builtin binary is missing', () => {
+test('falls back to system rg when @vscode/ripgrep cannot be resolved', () => {
  const config = resolveRipgrepConfig({
    userWantsSystemRipgrep: false,
    bundledMode: false,
-    builtinCommand: MOCK_BUILTIN_PATH,
-    builtinExists: false,
+    builtinCommand: null,
    systemExecutablePath: '/usr/bin/rg',
    processExecPath: '/fake/bun',
  })
@@ -26,12 +25,11 @@ test('ripgrepCommand falls back to system rg when builtin binary is missing', ()
  })
 })

-test('ripgrepCommand keeps builtin mode when bundled binary exists', () => {
+test('uses builtin @vscode/ripgrep path when the package resolves', () => {
  const config = resolveRipgrepConfig({
    userWantsSystemRipgrep: false,
    bundledMode: false,
    builtinCommand: MOCK_BUILTIN_PATH,
-    builtinExists: true,
    systemExecutablePath: '/usr/bin/rg',
    processExecPath: '/fake/bun',
  })
@@ -43,10 +41,59 @@ test('ripgrepCommand keeps builtin mode when bundled binary exists', () => {
  })
 })

+test('honors USE_BUILTIN_RIPGREP=0 by selecting system rg even when builtin is available', () => {
+  const config = resolveRipgrepConfig({
+    userWantsSystemRipgrep: true,
+    bundledMode: false,
+    builtinCommand: MOCK_BUILTIN_PATH,
+    systemExecutablePath: '/usr/bin/rg',
+    processExecPath: '/fake/bun',
+  })
+
+  expect(config).toMatchObject({
+    mode: 'system',
+    command: 'rg',
+    args: [],
+  })
+})
+
+test('keeps embedded mode for Bun-compiled standalone executables', () => {
+  const config = resolveRipgrepConfig({
+    userWantsSystemRipgrep: false,
+    bundledMode: true,
+    builtinCommand: null,
+    systemExecutablePath: '/usr/bin/rg',
+    processExecPath: '/opt/openclaude/bin/openclaude',
+  })
+
+  expect(config).toMatchObject({
+    mode: 'embedded',
+    command: '/opt/openclaude/bin/openclaude',
+    args: ['--no-config'],
+    argv0: 'rg',
+  })
+})
+
+test('falls through to system rg as a last resort even when not on PATH', () => {
+  const config = resolveRipgrepConfig({
+    userWantsSystemRipgrep: false,
+    bundledMode: false,
+    builtinCommand: null,
+    systemExecutablePath: 'rg',
+    processExecPath: '/fake/bun',
+  })
+
+  expect(config).toMatchObject({
+    mode: 'system',
+    command: 'rg',
+    args: [],
+  })
+})
+
 test('wrapRipgrepUnavailableError explains missing packaged fallback', () => {
  const error = wrapRipgrepUnavailableError(
    { code: 'ENOENT', message: 'spawn rg ENOENT' },
-    { mode: 'builtin', command: 'C:\\fake\\vendor\\ripgrep\\rg.exe', args: [] },
+    { mode: 'builtin', command: 'C:\\fake\\node_modules\\@vscode\\ripgrep\\bin\\rg.exe', args: [] },
    'win32',
  )

--- a/src/utils/ripgrep.ts
+++ b/src/utils/ripgrep.ts
@@ -5,7 +5,6 @@ import memoize from 'lodash-es/memoize.js'
 import { homedir } from 'os'
 import * as path from 'path'
 import { logEvent } from 'src/services/analytics/index.js'
-import { fileURLToPath } from 'url'
 import { isInBundledMode } from './bundledMode.js'
 import { logForDebugging } from './debug.js'
 import { isEnvDefinedFalsy } from './envUtils.js'
@@ -15,13 +14,6 @@ import { logError } from './log.js'
 import { getPlatform } from './platform.js'
 import { countCharInString } from './stringUtils.js'

-const __filename = fileURLToPath(import.meta.url)
-// we use node:path.join instead of node:url.resolve because the former doesn't encode spaces
-const __dirname = path.join(
-  __filename,
-  process.env.NODE_ENV === 'test' ? '../../../' : '../',
-)
-
 type RipgrepConfig = {
  mode: 'system' | 'builtin' | 'embedded'
  command: string
@@ -35,11 +27,31 @@ function isErrnoException(error: unknown): error is NodeJS.ErrnoException {
  return error instanceof Error
 }

+/**
+ * Returns the ripgrep binary path provided by the @vscode/ripgrep package.
+ * The package downloads a platform/arch-specific binary at npm install time
+ * (cached under the package's bin/ directory). Returns null when the package
+ * cannot be resolved — for example when running as a Bun-compiled standalone
+ * executable that doesn't ship node_modules.
+ */
+function resolveBuiltinRgPath(): string | null {
+  try {
+    // Lazy require so the resolution failure path stays graceful at import
+    // time. The package only exports `rgPath`, so we do not need the rest.
+    const mod = require('@vscode/ripgrep') as { rgPath?: string }
+    if (mod.rgPath && existsSync(mod.rgPath)) {
+      return mod.rgPath
+    }
+  } catch {
+    // Falls through to null — caller decides the fallback.
+  }
+  return null
+}
+
 type ResolveRipgrepConfigArgs = {
  userWantsSystemRipgrep: boolean
  bundledMode: boolean
-  builtinCommand: string
-  builtinExists: boolean
+  builtinCommand: string | null
  systemExecutablePath: string
  processExecPath?: string
 }
@@ -48,7 +60,6 @@ export function resolveRipgrepConfig({
  userWantsSystemRipgrep,
  bundledMode,
  builtinCommand,
-  builtinExists,
  systemExecutablePath,
  processExecPath = process.execPath,
 }: ResolveRipgrepConfigArgs): RipgrepConfig {
@@ -66,7 +77,7 @@ export function resolveRipgrepConfig({
    }
  }

-  if (builtinExists) {
+  if (builtinCommand) {
    return { mode: 'builtin', command: builtinCommand, args: [] }
  }

@@ -74,7 +85,9 @@ export function resolveRipgrepConfig({
    return { mode: 'system', command: 'rg', args: [] }
  }

-  return { mode: 'builtin', command: builtinCommand, args: [] }
+  // Last resort — leaves error reporting to the executor when no binary
+  // can be located. wrapRipgrepUnavailableError() surfaces an install hint.
+  return { mode: 'system', command: 'rg', args: [] }
 }

 const getRipgrepConfig = memoize((): RipgrepConfig => {
@@ -82,19 +95,13 @@ const getRipgrepConfig = memoize((): RipgrepConfig => {
    process.env.USE_BUILTIN_RIPGREP,
  )
  const bundledMode = isInBundledMode()
-  const rgRoot = path.resolve(__dirname, 'vendor', 'ripgrep')
-  const builtinCommand =
-    process.platform === 'win32'
-      ? path.resolve(rgRoot, `${process.arch}-win32`, 'rg.exe')
-      : path.resolve(rgRoot, `${process.arch}-${process.platform}`, 'rg')
-  const builtinExists = existsSync(builtinCommand)
+  const builtinCommand = resolveBuiltinRgPath()
  const { cmd: systemExecutablePath } = findExecutable('rg', [])

  return resolveRipgrepConfig({
    userWantsSystemRipgrep,
    bundledMode,
    builtinCommand,
-    builtinExists,
    systemExecutablePath,
  })
 })