chore(release): v0.8.0-preview.0

fix: skip non-existent file imports instead of warning (ENOENT)

docs/developers/development/npm.md

@@ -202,7 +202,7 @@ This is the most critical stage where files are moved and transformed into their
       - Copies README.md and LICENSE to dist/
       - Copies locales folder for internationalization
       - Creates a clean package.json for distribution with only necessary dependencies
-      - Includes runtime dependencies like tiktoken
+      - Keeps distribution dependencies minimal (no bundled runtime deps)
       - Maintains optional dependencies for node-pty
 
 2.  The JavaScript Bundle is Created:

esbuild.config.js

@@ -33,7 +33,6 @@ const external = [
   '@lydell/node-pty-linux-x64',
   '@lydell/node-pty-win32-arm64',
   '@lydell/node-pty-win32-x64',
-  'tiktoken',
 ];
 
 esbuild

package-lock.json

@@ -1,12 +1,12 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "lockfileVersion": 3,
   "requires": true,
   "packages": {
     "": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.7.1",
+      "version": "0.8.0-preview.0",
       "workspaces": [
         "packages/*"
       ],
@@ -15682,12 +15682,6 @@
         "tslib": "^2"
       }
     },
-    "node_modules/tiktoken": {
-      "version": "1.0.22",
-      "resolved": "https://registry.npmjs.org/tiktoken/-/tiktoken-1.0.22.tgz",
-      "integrity": "sha512-PKvy1rVF1RibfF3JlXBSP0Jrcw2uq3yXdgcEXtKTYn3QJ/cBRBHDnrJ5jHky+MENZ6DIPwNUGWpkVx+7joCpNA==",
-      "license": "MIT"
-    },
     "node_modules/tinybench": {
       "version": "2.9.0",
       "resolved": "https://registry.npmjs.org/tinybench/-/tinybench-2.9.0.tgz",
@@ -17310,7 +17304,7 @@
     },
     "packages/cli": {
       "name": "@qwen-code/qwen-code",
-      "version": "0.7.1",
+      "version": "0.8.0-preview.0",
       "dependencies": {
         "@google/genai": "1.30.0",
         "@iarna/toml": "^2.2.5",
@@ -17947,7 +17941,7 @@
     },
     "packages/core": {
       "name": "@qwen-code/qwen-code-core",
-      "version": "0.7.1",
+      "version": "0.8.0-preview.0",
       "hasInstallScript": true,
       "dependencies": {
         "@anthropic-ai/sdk": "^0.36.1",
@@ -17990,7 +17984,6 @@
         "shell-quote": "^1.8.3",
         "simple-git": "^3.28.0",
         "strip-ansi": "^7.1.0",
-        "tiktoken": "^1.0.21",
         "undici": "^6.22.0",
         "uuid": "^9.0.1",
         "ws": "^8.18.0"
@@ -18592,7 +18585,6 @@
       "license": "Apache-2.0",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.25.1",
-        "tiktoken": "^1.0.21",
         "zod": "^3.25.0"
       },
       "devDependencies": {
@@ -21408,7 +21400,7 @@
     },
     "packages/test-utils": {
       "name": "@qwen-code/qwen-code-test-utils",
-      "version": "0.7.1",
+      "version": "0.8.0-preview.0",
       "dev": true,
       "license": "Apache-2.0",
       "devDependencies": {
@@ -21420,7 +21412,7 @@
     },
     "packages/vscode-ide-companion": {
       "name": "qwen-code-vscode-ide-companion",
-      "version": "0.7.1",
+      "version": "0.8.0-preview.0",
       "license": "LICENSE",
       "dependencies": {
         "@modelcontextprotocol/sdk": "^1.25.1",

package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "engines": {
     "node": ">=20.0.0"
   },
@@ -13,7 +13,7 @@
     "url": "git+https://github.com/QwenLM/qwen-code.git"
   },
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.1"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.8.0-preview.0"
   },
   "scripts": {
     "start": "cross-env node scripts/start.js",

packages/cli/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "description": "Qwen Code",
   "repository": {
     "type": "git",
@@ -33,19 +33,20 @@
     "dist"
   ],
   "config": {
-    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.7.1"
+    "sandboxImageUri": "ghcr.io/qwenlm/qwen-code:0.8.0-preview.0"
   },
   "dependencies": {
     "@google/genai": "1.30.0",
     "@iarna/toml": "^2.2.5",
-    "@qwen-code/qwen-code-core": "file:../core",
     "@modelcontextprotocol/sdk": "^1.25.1",
+    "@qwen-code/qwen-code-core": "file:../core",
     "@types/update-notifier": "^6.0.8",
     "ansi-regex": "^6.2.2",
     "command-exists": "^1.2.9",
     "comment-json": "^4.2.5",
     "diff": "^7.0.0",
     "dotenv": "^17.1.0",
+    "extract-zip": "^2.0.1",
     "fzf": "^0.5.2",
     "glob": "^10.5.0",
     "highlight.js": "^11.11.1",
@@ -65,7 +66,6 @@
     "strip-json-comments": "^3.1.1",
     "tar": "^7.5.2",
     "undici": "^6.22.0",
-    "extract-zip": "^2.0.1",
     "update-notifier": "^7.3.1",
     "wrap-ansi": "9.0.2",
     "yargs": "^17.7.2",
@@ -74,6 +74,7 @@
   "devDependencies": {
     "@babel/runtime": "^7.27.6",
     "@google/gemini-cli-test-utils": "file:../test-utils",
+    "@qwen-code/qwen-code-test-utils": "file:../test-utils",
     "@testing-library/react": "^16.3.0",
     "@types/archiver": "^6.0.3",
     "@types/command-exists": "^1.2.3",
@@ -92,8 +93,7 @@
     "pretty-format": "^30.0.2",
     "react-dom": "^19.1.0",
     "typescript": "^5.3.3",
-    "vitest": "^3.1.1",
-    "@qwen-code/qwen-code-test-utils": "file:../test-utils"
+    "vitest": "^3.1.1"
   },
   "engines": {
     "node": ">=20"

packages/cli/src/acp-integration/acp.ts

@@ -8,6 +8,7 @@
 
 import { z } from 'zod';
 import * as schema from './schema.js';
+import { ACP_ERROR_CODES } from './errorCodes.js';
 export * from './schema.js';
 
 import type { WritableStream, ReadableStream } from 'node:stream/web';
@@ -349,27 +350,51 @@ export class RequestError extends Error {
   }
 
   static parseError(details?: string): RequestError {
-    return new RequestError(-32700, 'Parse error', details);
+    return new RequestError(
+      ACP_ERROR_CODES.PARSE_ERROR,
+      'Parse error',
+      details,
+    );
   }
 
   static invalidRequest(details?: string): RequestError {
-    return new RequestError(-32600, 'Invalid request', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INVALID_REQUEST,
+      'Invalid request',
+      details,
+    );
   }
 
   static methodNotFound(details?: string): RequestError {
-    return new RequestError(-32601, 'Method not found', details);
+    return new RequestError(
+      ACP_ERROR_CODES.METHOD_NOT_FOUND,
+      'Method not found',
+      details,
+    );
   }
 
   static invalidParams(details?: string): RequestError {
-    return new RequestError(-32602, 'Invalid params', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INVALID_PARAMS,
+      'Invalid params',
+      details,
+    );
   }
 
   static internalError(details?: string): RequestError {
-    return new RequestError(-32603, 'Internal error', details);
+    return new RequestError(
+      ACP_ERROR_CODES.INTERNAL_ERROR,
+      'Internal error',
+      details,
+    );
   }
 
   static authRequired(details?: string): RequestError {
-    return new RequestError(-32000, 'Authentication required', details);
+    return new RequestError(
+      ACP_ERROR_CODES.AUTH_REQUIRED,
+      'Authentication required',
+      details,
+    );
   }
 
   toResult<T>(): Result<T> {

packages/cli/src/acp-integration/errorCodes.ts

@@ -0,0 +1,25 @@
+/**
+ * @license
+ * Copyright 2025 Google LLC
+ * SPDX-License-Identifier: Apache-2.0
+ */
+
+export const ACP_ERROR_CODES = {
+  // Parse error: invalid JSON received by server.
+  PARSE_ERROR: -32700,
+  // Invalid request: JSON is not a valid Request object.
+  INVALID_REQUEST: -32600,
+  // Method not found: method does not exist or is unavailable.
+  METHOD_NOT_FOUND: -32601,
+  // Invalid params: invalid method parameter(s).
+  INVALID_PARAMS: -32602,
+  // Internal error: implementation-defined server error.
+  INTERNAL_ERROR: -32603,
+  // Authentication required: must authenticate before operation.
+  AUTH_REQUIRED: -32000,
+  // Resource not found: e.g. missing file.
+  RESOURCE_NOT_FOUND: -32002,
+} as const;
+
+export type AcpErrorCode =
+  (typeof ACP_ERROR_CODES)[keyof typeof ACP_ERROR_CODES];

packages/cli/src/acp-integration/service/filesystem.test.ts

@@ -7,6 +7,7 @@
 import { describe, expect, it, vi } from 'vitest';
 import type { FileSystemService } from '@qwen-code/qwen-code-core';
 import { AcpFileSystemService } from './filesystem.js';
+import { ACP_ERROR_CODES } from '../errorCodes.js';
 
 const createFallback = (): FileSystemService => ({
   readTextFile: vi.fn(),
@@ -16,11 +17,13 @@ const createFallback = (): FileSystemService => ({
 
 describe('AcpFileSystemService', () => {
   describe('readTextFile ENOENT handling', () => {
-    it('parses path from ACP ENOENT message (quoted)', async () => {
+    it('converts RESOURCE_NOT_FOUND error to ENOENT', async () => {
+      const resourceNotFoundError = {
+        code: ACP_ERROR_CODES.RESOURCE_NOT_FOUND,
+        message: 'File not found',
+      };
       const client = {
-        readTextFile: vi
-          .fn()
-          .mockResolvedValue({ content: 'ERROR: ENOENT: "/remote/file.txt"' }),
+        readTextFile: vi.fn().mockRejectedValue(resourceNotFoundError),
       } as unknown as import('../acp.js').Client;
 
       const svc = new AcpFileSystemService(
@@ -30,15 +33,20 @@ describe('AcpFileSystemService', () => {
         createFallback(),
       );
 
-      await expect(svc.readTextFile('/local/file.txt')).rejects.toMatchObject({
+      await expect(svc.readTextFile('/some/file.txt')).rejects.toMatchObject({
         code: 'ENOENT',
-        path: '/remote/file.txt',
+        errno: -2,
+        path: '/some/file.txt',
       });
     });
 
-    it('falls back to requested path when none provided', async () => {
+    it('re-throws other errors unchanged', async () => {
+      const otherError = {
+        code: ACP_ERROR_CODES.INTERNAL_ERROR,
+        message: 'Internal error',
+      };
       const client = {
-        readTextFile: vi.fn().mockResolvedValue({ content: 'ERROR: ENOENT:' }),
+        readTextFile: vi.fn().mockRejectedValue(otherError),
       } as unknown as import('../acp.js').Client;
 
       const svc = new AcpFileSystemService(
@@ -48,12 +56,34 @@ describe('AcpFileSystemService', () => {
         createFallback(),
       );
 
-      await expect(
-        svc.readTextFile('/fallback/path.txt'),
-      ).rejects.toMatchObject({
-        code: 'ENOENT',
-        path: '/fallback/path.txt',
+      await expect(svc.readTextFile('/some/file.txt')).rejects.toMatchObject({
+        code: ACP_ERROR_CODES.INTERNAL_ERROR,
+        message: 'Internal error',
       });
     });
+
+    it('uses fallback when readTextFile capability is disabled', async () => {
+      const client = {
+        readTextFile: vi.fn(),
+      } as unknown as import('../acp.js').Client;
+
+      const fallback = createFallback();
+      (fallback.readTextFile as ReturnType<typeof vi.fn>).mockResolvedValue(
+        'fallback content',
+      );
+
+      const svc = new AcpFileSystemService(
+        client,
+        'session-3',
+        { readTextFile: false, writeTextFile: true },
+        fallback,
+      );
+
+      const result = await svc.readTextFile('/some/file.txt');
+
+      expect(result).toBe('fallback content');
+      expect(fallback.readTextFile).toHaveBeenCalledWith('/some/file.txt');
+      expect(client.readTextFile).not.toHaveBeenCalled();
+    });
   });
 });

packages/cli/src/acp-integration/service/filesystem.ts

@@ -6,6 +6,7 @@
 
 import type { FileSystemService } from '@qwen-code/qwen-code-core';
 import type * as acp from '../acp.js';
+import { ACP_ERROR_CODES } from '../errorCodes.js';
 
 /**
  * ACP client-based implementation of FileSystemService
@@ -23,25 +24,31 @@ export class AcpFileSystemService implements FileSystemService {
       return this.fallback.readTextFile(filePath);
     }
 
-    const response = await this.client.readTextFile({
-      path: filePath,
-      sessionId: this.sessionId,
-      line: null,
-      limit: null,
-    });
+    let response: { content: string };
+    try {
+      response = await this.client.readTextFile({
+        path: filePath,
+        sessionId: this.sessionId,
+        line: null,
+        limit: null,
+      });
+    } catch (error) {
+      const errorCode =
+        typeof error === 'object' && error !== null && 'code' in error
+          ? (error as { code?: unknown }).code
+          : undefined;
 
-    if (response.content.startsWith('ERROR: ENOENT:')) {
-      // Treat ACP error strings as structured ENOENT errors without
-      // assuming a specific platform format.
-      const match = /^ERROR:\s*ENOENT:\s*(?<path>.*)$/i.exec(response.content);
-      const err = new Error(response.content) as NodeJS.ErrnoException;
-      err.code = 'ENOENT';
-      err.errno = -2;
-      const rawPath = match?.groups?.['path']?.trim();
-      err['path'] = rawPath
-        ? rawPath.replace(/^['"]|['"]$/g, '') || filePath
-        : filePath;
-      throw err;
+      if (errorCode === ACP_ERROR_CODES.RESOURCE_NOT_FOUND) {
+        const err = new Error(
+          `File not found: ${filePath}`,
+        ) as NodeJS.ErrnoException;
+        err.code = 'ENOENT';
+        err.errno = -2;
+        err.path = filePath;
+        throw err;
+      }
+
+      throw error;
     }
 
     return response.content;

packages/cli/src/nonInteractiveCliCommands.ts

@@ -38,6 +38,7 @@ export const ALLOWED_BUILTIN_COMMANDS_NON_INTERACTIVE = [
   'init',
   'summary',
   'compress',
+  'bug',
 ] as const;
 
 /**

packages/cli/src/ui/colors.ts

@@ -38,6 +38,12 @@ export const Colors: ColorsTheme = {
   get AccentRed() {
     return themeManager.getActiveTheme().colors.AccentRed;
   },
+  get AccentYellowDim() {
+    return themeManager.getActiveTheme().colors.AccentYellowDim;
+  },
+  get AccentRedDim() {
+    return themeManager.getActiveTheme().colors.AccentRedDim;
+  },
   get DiffAdded() {
     return themeManager.getActiveTheme().colors.DiffAdded;
   },

packages/cli/src/ui/components/InputPrompt.tsx

@@ -749,10 +749,10 @@ export const InputPrompt: React.FC<InputPromptProps> = ({
     statusColor = theme.ui.symbol;
     statusText = t('Shell mode');
   } else if (showYoloStyling) {
-    statusColor = theme.status.error;
+    statusColor = theme.status.errorDim;
     statusText = t('YOLO mode');
   } else if (showAutoAcceptStyling) {
-    statusColor = theme.status.warning;
+    statusColor = theme.status.warningDim;
     statusText = t('Accepting edits');
   }
 

packages/cli/src/ui/themes/ansi-light.ts

@@ -18,6 +18,8 @@ const ansiLightColors: ColorsTheme = {
   AccentGreen: 'green',
   AccentYellow: 'orange',
   AccentRed: 'red',
+  AccentYellowDim: 'orange',
+  AccentRedDim: 'red',
   DiffAdded: '#E5F2E5',
   DiffRemoved: '#FFE5E5',
   Comment: 'gray',

packages/cli/src/ui/themes/ansi.ts

@@ -18,6 +18,8 @@ const ansiColors: ColorsTheme = {
   AccentGreen: 'green',
   AccentYellow: 'yellow',
   AccentRed: 'red',
+  AccentYellowDim: 'yellow',
+  AccentRedDim: 'red',
   DiffAdded: '#003300',
   DiffRemoved: '#4D0000',
   Comment: 'gray',

packages/cli/src/ui/themes/atom-one-dark.ts

@@ -17,6 +17,8 @@ const atomOneDarkColors: ColorsTheme = {
   AccentGreen: '#98c379',
   AccentYellow: '#e6c07b',
   AccentRed: '#e06c75',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#39544E',
   DiffRemoved: '#562B2F',
   Comment: '#5c6370',

packages/cli/src/ui/themes/ayu-light.ts

@@ -17,6 +17,8 @@ const ayuLightColors: ColorsTheme = {
   AccentGreen: '#86b300',
   AccentYellow: '#f2ae49',
   AccentRed: '#f07171',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#C6EAD8',
   DiffRemoved: '#FFCCCC',
   Comment: '#ABADB1',

packages/cli/src/ui/themes/ayu.ts

@@ -17,6 +17,8 @@ const ayuDarkColors: ColorsTheme = {
   AccentGreen: '#AAD94C',
   AccentYellow: '#FFB454',
   AccentRed: '#F26D78',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#293022',
   DiffRemoved: '#3D1215',
   Comment: '#646A71',

packages/cli/src/ui/themes/dracula.ts

@@ -17,6 +17,8 @@ const draculaColors: ColorsTheme = {
   AccentGreen: '#50fa7b',
   AccentYellow: '#fff783',
   AccentRed: '#ff5555',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#11431d',
   DiffRemoved: '#6e1818',
   Comment: '#6272a4',

packages/cli/src/ui/themes/github-dark.ts

@@ -17,6 +17,8 @@ const githubDarkColors: ColorsTheme = {
   AccentGreen: '#85E89D',
   AccentYellow: '#FFAB70',
   AccentRed: '#F97583',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#3C4636',
   DiffRemoved: '#502125',
   Comment: '#6A737D',

packages/cli/src/ui/themes/github-light.ts

@@ -17,6 +17,8 @@ const githubLightColors: ColorsTheme = {
   AccentGreen: '#008080',
   AccentYellow: '#990073',
   AccentRed: '#d14',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#C6EAD8',
   DiffRemoved: '#FFCCCC',
   Comment: '#998',

packages/cli/src/ui/themes/googlecode.ts

@@ -17,6 +17,8 @@ const googleCodeColors: ColorsTheme = {
   AccentGreen: '#080',
   AccentYellow: '#660',
   AccentRed: '#800',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#C6EAD8',
   DiffRemoved: '#FEDEDE',
   Comment: '#5f6368',

packages/cli/src/ui/themes/no-color.ts

@@ -19,6 +19,8 @@ const noColorColorsTheme: ColorsTheme = {
   AccentGreen: '',
   AccentYellow: '',
   AccentRed: '',
+  AccentYellowDim: '',
+  AccentRedDim: '',
   DiffAdded: '',
   DiffRemoved: '',
   Comment: '',
@@ -52,6 +54,8 @@ const noColorSemanticColors: SemanticColors = {
     error: '',
     success: '',
     warning: '',
+    errorDim: '',
+    warningDim: '',
   },
 };
 

packages/cli/src/ui/themes/qwen-dark.ts

@@ -18,6 +18,8 @@ const qwenDarkColors: ColorsTheme = {
   AccentGreen: '#AAD94C',
   AccentYellow: '#FFD700',
   AccentRed: '#F26D78',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#AAD94C',
   DiffRemoved: '#F26D78',
   Comment: '#646A71',

packages/cli/src/ui/themes/qwen-light.ts

@@ -18,6 +18,8 @@ const qwenLightColors: ColorsTheme = {
   AccentGreen: '#86b300',
   AccentYellow: '#f2ae49',
   AccentRed: '#f07171',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#86b300',
   DiffRemoved: '#f07171',
   Comment: '#ABADB1',

packages/cli/src/ui/themes/semantic-tokens.ts

@@ -33,6 +33,9 @@ export interface SemanticColors {
     error: string;
     success: string;
     warning: string;
+    // Dim variants for less intense UI elements
+    errorDim: string;
+    warningDim: string;
   };
 }
 
@@ -63,6 +66,8 @@ export const lightSemanticColors: SemanticColors = {
     error: lightTheme.AccentRed,
     success: lightTheme.AccentGreen,
     warning: lightTheme.AccentYellow,
+    errorDim: lightTheme.AccentRedDim,
+    warningDim: lightTheme.AccentYellowDim,
   },
 };
 
@@ -93,6 +98,8 @@ export const darkSemanticColors: SemanticColors = {
     error: darkTheme.AccentRed,
     success: darkTheme.AccentGreen,
     warning: darkTheme.AccentYellow,
+    errorDim: darkTheme.AccentRedDim,
+    warningDim: darkTheme.AccentYellowDim,
   },
 };
 
@@ -123,5 +130,7 @@ export const ansiSemanticColors: SemanticColors = {
     error: ansiTheme.AccentRed,
     success: ansiTheme.AccentGreen,
     warning: ansiTheme.AccentYellow,
+    errorDim: ansiTheme.AccentRedDim,
+    warningDim: ansiTheme.AccentYellowDim,
   },
 };

packages/cli/src/ui/themes/shades-of-purple.ts

@@ -22,6 +22,8 @@ const shadesOfPurpleColors: ColorsTheme = {
   AccentGreen: '#A5FF90', // Strings and many others
   AccentYellow: '#fad000', // Title, main yellow
   AccentRed: '#ff628c', // Error/deletion accent
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#383E45',
   DiffRemoved: '#572244',
   Comment: '#B362FF', // Comment color (same as AccentPurple)

packages/cli/src/ui/themes/theme.ts

@@ -21,6 +21,9 @@ export interface ColorsTheme {
   AccentGreen: string;
   AccentYellow: string;
   AccentRed: string;
+  // Dim variants for less intense UI elements
+  AccentYellowDim: string;
+  AccentRedDim: string;
   DiffAdded: string;
   DiffRemoved: string;
   Comment: string;
@@ -58,6 +61,8 @@ export interface CustomTheme {
     error?: string;
     success?: string;
     warning?: string;
+    errorDim?: string;
+    warningDim?: string;
   };
 
   // Legacy properties (all optional)
@@ -70,6 +75,8 @@ export interface CustomTheme {
   AccentGreen?: string;
   AccentYellow?: string;
   AccentRed?: string;
+  AccentYellowDim?: string;
+  AccentRedDim?: string;
   DiffAdded?: string;
   DiffRemoved?: string;
   Comment?: string;
@@ -88,6 +95,8 @@ export const lightTheme: ColorsTheme = {
   AccentGreen: '#3CA84B',
   AccentYellow: '#D5A40A',
   AccentRed: '#DD4C4C',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#C6EAD8',
   DiffRemoved: '#FFCCCC',
   Comment: '#008000',
@@ -106,6 +115,8 @@ export const darkTheme: ColorsTheme = {
   AccentGreen: '#A6E3A1',
   AccentYellow: '#F9E2AF',
   AccentRed: '#F38BA8',
+  AccentYellowDim: '#8B7530',
+  AccentRedDim: '#8B3A4A',
   DiffAdded: '#28350B',
   DiffRemoved: '#430000',
   Comment: '#6C7086',
@@ -124,6 +135,8 @@ export const ansiTheme: ColorsTheme = {
   AccentGreen: 'green',
   AccentYellow: 'yellow',
   AccentRed: 'red',
+  AccentYellowDim: 'yellow',
+  AccentRedDim: 'red',
   DiffAdded: 'green',
   DiffRemoved: 'red',
   Comment: 'gray',
@@ -182,6 +195,8 @@ export class Theme {
         error: this.colors.AccentRed,
         success: this.colors.AccentGreen,
         warning: this.colors.AccentYellow,
+        errorDim: this.colors.AccentRedDim,
+        warningDim: this.colors.AccentYellowDim,
       },
     };
     this._colorMap = Object.freeze(this._buildColorMap(rawMappings)); // Build and freeze the map
@@ -261,6 +276,10 @@ export function createCustomTheme(customTheme: CustomTheme): Theme {
     AccentGreen: customTheme.status?.success ?? customTheme.AccentGreen ?? '',
     AccentYellow: customTheme.status?.warning ?? customTheme.AccentYellow ?? '',
     AccentRed: customTheme.status?.error ?? customTheme.AccentRed ?? '',
+    AccentYellowDim:
+      customTheme.status?.warningDim ?? customTheme.AccentYellowDim ?? '',
+    AccentRedDim:
+      customTheme.status?.errorDim ?? customTheme.AccentRedDim ?? '',
     DiffAdded:
       customTheme.background?.diff?.added ?? customTheme.DiffAdded ?? '',
     DiffRemoved:
@@ -435,6 +454,8 @@ export function createCustomTheme(customTheme: CustomTheme): Theme {
       error: customTheme.status?.error ?? colors.AccentRed,
       success: customTheme.status?.success ?? colors.AccentGreen,
       warning: customTheme.status?.warning ?? colors.AccentYellow,
+      errorDim: customTheme.status?.errorDim ?? colors.AccentRedDim,
+      warningDim: customTheme.status?.warningDim ?? colors.AccentYellowDim,
     },
   };
 

packages/cli/src/ui/themes/xcode.ts

@@ -17,6 +17,8 @@ const xcodeColors: ColorsTheme = {
   AccentGreen: '#007400',
   AccentYellow: '#836C28',
   AccentRed: '#c41a16',
+  AccentYellowDim: '#8B7000',
+  AccentRedDim: '#993333',
   DiffAdded: '#C6EAD8',
   DiffRemoved: '#FEDEDE',
   Comment: '#007400',

packages/cli/src/utils/handleAutoUpdate.test.ts

@@ -241,9 +241,12 @@ describe('handleAutoUpdate', () => {
     handleAutoUpdate(mockUpdateInfo, mockSettings, '/root', mockSpawn);
 
     expect(mockSpawn).toHaveBeenCalledWith(
-      'npm i -g @qwen-code/qwen-code@nightly',
+      expect.stringMatching(/^(bash|cmd\.exe)$/),
+      expect.arrayContaining([
+        expect.stringMatching(/^(-c|\/c)$/),
+        'npm i -g @qwen-code/qwen-code@nightly',
+      ]),
       {
-        shell: true,
         stdio: 'pipe',
       },
     );

packages/cli/src/utils/handleAutoUpdate.ts

@@ -12,6 +12,7 @@ import type { HistoryItem } from '../ui/types.js';
 import { MessageType } from '../ui/types.js';
 import { spawnWrapper } from './spawnWrapper.js';
 import type { spawn } from 'node:child_process';
+import os from 'node:os';
 
 export function handleAutoUpdate(
   info: UpdateObject | null,
@@ -53,7 +54,10 @@ export function handleAutoUpdate(
     '@latest',
     isNightly ? '@nightly' : `@${info.update.latest}`,
   );
-  const updateProcess = spawnFn(updateCommand, { stdio: 'pipe', shell: true });
+  const isWindows = os.platform() === 'win32';
+  const shell = isWindows ? 'cmd.exe' : 'bash';
+  const shellArgs = isWindows ? ['/c', updateCommand] : ['-c', updateCommand];
+  const updateProcess = spawnFn(shell, shellArgs, { stdio: 'pipe' });
   let errorOutput = '';
   updateProcess.stderr.on('data', (data) => {
     errorOutput += data.toString();

packages/cli/src/utils/sandbox.ts

@@ -291,9 +291,10 @@ export async function start_sandbox(
           sandboxEnv['NO_PROXY'] = noProxy;
           sandboxEnv['no_proxy'] = noProxy;
         }
-        proxyProcess = spawn(proxyCommand, {
+        // Note: CodeQL flags this as js/shell-command-injection-from-environment.
+        // This is intentional - CLI tool executes user-provided proxy commands.
+        proxyProcess = spawn('bash', ['-c', proxyCommand], {
           stdio: ['ignore', 'pipe', 'pipe'],
-          shell: true,
           detached: true,
         });
         // install handlers to stop proxy on exit/signal
@@ -781,9 +782,15 @@ export async function start_sandbox(
     if (proxyCommand) {
       // run proxyCommand in its own container
       const proxyContainerCommand = `${config.command} run --rm --init ${userFlag} --name ${SANDBOX_PROXY_NAME} --network ${SANDBOX_PROXY_NAME} -p 8877:8877 -v ${process.cwd()}:${workdir} --workdir ${workdir} ${image} ${proxyCommand}`;
-      proxyProcess = spawn(proxyContainerCommand, {
+      const isWindows = os.platform() === 'win32';
+      const proxyShell = isWindows ? 'cmd.exe' : 'bash';
+      const proxyShellArgs = isWindows
+        ? ['/c', proxyContainerCommand]
+        : ['-c', proxyContainerCommand];
+      // Note: CodeQL flags this as js/shell-command-injection-from-environment.
+      // This is intentional - CLI tool executes user-provided proxy commands in container.
+      proxyProcess = spawn(proxyShell, proxyShellArgs, {
         stdio: ['ignore', 'pipe', 'pipe'],
-        shell: true,
         detached: true,
       });
       // install handlers to stop proxy on exit/signal

packages/core/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code-core",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "description": "Qwen Code Core",
   "repository": {
     "type": "git",
@@ -63,7 +63,6 @@
     "shell-quote": "^1.8.3",
     "simple-git": "^3.28.0",
     "strip-ansi": "^7.1.0",
-    "tiktoken": "^1.0.21",
     "undici": "^6.22.0",
     "uuid": "^9.0.1",
     "ws": "^8.18.0"

packages/core/src/core/anthropicContentGenerator/anthropicContentGenerator.test.ts

@@ -19,9 +19,7 @@ const mockTokenizer = {
 };
 
 vi.mock('../../utils/request-tokenizer/index.js', () => ({
-  getDefaultTokenizer: vi.fn(() => mockTokenizer),
-  DefaultRequestTokenizer: vi.fn(() => mockTokenizer),
-  disposeDefaultTokenizer: vi.fn(),
+  RequestTokenEstimator: vi.fn(() => mockTokenizer),
 }));
 
 type AnthropicCreateArgs = [unknown, { signal?: AbortSignal }?];
@@ -352,9 +350,7 @@ describe('AnthropicContentGenerator', () => {
       };
 
       const result = await generator.countTokens(request);
-      expect(mockTokenizer.calculateTokens).toHaveBeenCalledWith(request, {
-        textEncoding: 'cl100k_base',
-      });
+      expect(mockTokenizer.calculateTokens).toHaveBeenCalledWith(request);
       expect(result.totalTokens).toBe(50);
     });
 

packages/core/src/core/anthropicContentGenerator/anthropicContentGenerator.ts

@@ -25,7 +25,7 @@ type MessageCreateParamsNonStreaming =
   Anthropic.MessageCreateParamsNonStreaming;
 type MessageCreateParamsStreaming = Anthropic.MessageCreateParamsStreaming;
 type RawMessageStreamEvent = Anthropic.RawMessageStreamEvent;
-import { getDefaultTokenizer } from '../../utils/request-tokenizer/index.js';
+import { RequestTokenEstimator } from '../../utils/request-tokenizer/index.js';
 import { safeJsonParse } from '../../utils/safeJsonParse.js';
 import { AnthropicContentConverter } from './converter.js';
 
@@ -105,10 +105,8 @@ export class AnthropicContentGenerator implements ContentGenerator {
     request: CountTokensParameters,
   ): Promise<CountTokensResponse> {
     try {
-      const tokenizer = getDefaultTokenizer();
-      const result = await tokenizer.calculateTokens(request, {
-        textEncoding: 'cl100k_base',
-      });
+      const estimator = new RequestTokenEstimator();
+      const result = await estimator.calculateTokens(request);
 
       return {
         totalTokens: result.totalTokens,

packages/core/src/core/client.test.ts

@@ -153,6 +153,26 @@ vi.mock('../telemetry/loggers.js', () => ({
   logNextSpeakerCheck: vi.fn(),
 }));
 
+// Mock RequestTokenizer to use simple character-based estimation
+vi.mock('../utils/request-tokenizer/requestTokenizer.js', () => ({
+  RequestTokenizer: class {
+    async calculateTokens(request: { contents: unknown }) {
+      // Simple estimation: count characters in JSON and divide by 4
+      const totalChars = JSON.stringify(request.contents).length;
+      return {
+        totalTokens: Math.floor(totalChars / 4),
+        breakdown: {
+          textTokens: Math.floor(totalChars / 4),
+          imageTokens: 0,
+          audioTokens: 0,
+          otherTokens: 0,
+        },
+        processingTime: 0,
+      };
+    }
+  },
+}));
+
 /**
  * Array.fromAsync ponyfill, which will be available in es 2024.
  *
@@ -417,6 +437,12 @@ describe('Gemini Client (client.ts)', () => {
       ] as Content[],
       originalTokenCount = 1000,
       summaryText = 'This is a summary.',
+      // Token counts returned in usageMetadata to simulate what the API would return
+      // Default values ensure successful compression:
+      // newTokenCount = originalTokenCount - (compressionInputTokenCount - 1000) + compressionOutputTokenCount
+      // = 1000 - (1600 - 1000) + 50 = 1000 - 600 + 50 = 450 (< 1000, success)
+      compressionInputTokenCount = 1600,
+      compressionOutputTokenCount = 50,
     } = {}) {
       const mockOriginalChat: Partial<GeminiChat> = {
         getHistory: vi.fn((_curated?: boolean) => chatHistory),
@@ -438,6 +464,12 @@ describe('Gemini Client (client.ts)', () => {
             },
           },
         ],
+        usageMetadata: {
+          promptTokenCount: compressionInputTokenCount,
+          candidatesTokenCount: compressionOutputTokenCount,
+          totalTokenCount:
+            compressionInputTokenCount + compressionOutputTokenCount,
+        },
       } as unknown as GenerateContentResponse);
 
       // Calculate what the new history will be
@@ -477,11 +509,13 @@ describe('Gemini Client (client.ts)', () => {
         .fn()
         .mockResolvedValue(mockNewChat as GeminiChat);
 
-      const totalChars = newCompressedHistory.reduce(
-        (total, content) => total + JSON.stringify(content).length,
+      // New token count formula: originalTokenCount - (compressionInputTokenCount - 1000) + compressionOutputTokenCount
+      const estimatedNewTokenCount = Math.max(
         0,
+        originalTokenCount -
+          (compressionInputTokenCount - 1000) +
+          compressionOutputTokenCount,
       );
-      const estimatedNewTokenCount = Math.floor(totalChars / 4);
 
       return {
         client,
@@ -493,49 +527,58 @@ describe('Gemini Client (client.ts)', () => {
 
     describe('when compression inflates the token count', () => {
       it('allows compression to be forced/manual after a failure', async () => {
-        // Call 1 (Fails): Setup with a long summary to inflate tokens
+        // Call 1 (Fails): Setup with token counts that will inflate
+        // newTokenCount = originalTokenCount - (compressionInputTokenCount - 1000) + compressionOutputTokenCount
+        // = 100 - (1010 - 1000) + 200 = 100 - 10 + 200 = 290 > 100 (inflation)
         const longSummary = 'long summary '.repeat(100);
         const { client, estimatedNewTokenCount: inflatedTokenCount } = setup({
           originalTokenCount: 100,
           summaryText: longSummary,
+          compressionInputTokenCount: 1010,
+          compressionOutputTokenCount: 200,
         });
         expect(inflatedTokenCount).toBeGreaterThan(100); // Ensure setup is correct
 
         await client.tryCompressChat('prompt-id-4', false); // Fails
 
-        // Call 2 (Forced): Re-setup with a short summary
+        // Call 2 (Forced): Re-setup with token counts that will compress
+        // newTokenCount = 100 - (1100 - 1000) + 50 = 100 - 100 + 50 = 50 <= 100 (compression)
         const shortSummary = 'short';
         const { estimatedNewTokenCount: compressedTokenCount } = setup({
           originalTokenCount: 100,
           summaryText: shortSummary,
+          compressionInputTokenCount: 1100,
+          compressionOutputTokenCount: 50,
         });
         expect(compressedTokenCount).toBeLessThanOrEqual(100); // Ensure setup is correct
 
         const result = await client.tryCompressChat('prompt-id-4', true); // Forced
 
-        expect(result).toEqual({
-          compressionStatus: CompressionStatus.COMPRESSED,
-          newTokenCount: compressedTokenCount,
-          originalTokenCount: 100,
-        });
+        expect(result.compressionStatus).toBe(CompressionStatus.COMPRESSED);
+        expect(result.originalTokenCount).toBe(100);
+        // newTokenCount might be clamped to originalTokenCount due to tolerance logic
+        expect(result.newTokenCount).toBeLessThanOrEqual(100);
       });
 
       it('yields the result even if the compression inflated the tokens', async () => {
+        // newTokenCount = 100 - (1010 - 1000) + 200 = 100 - 10 + 200 = 290 > 100 (inflation)
         const longSummary = 'long summary '.repeat(100);
         const { client, estimatedNewTokenCount } = setup({
           originalTokenCount: 100,
           summaryText: longSummary,
+          compressionInputTokenCount: 1010,
+          compressionOutputTokenCount: 200,
         });
         expect(estimatedNewTokenCount).toBeGreaterThan(100); // Ensure setup is correct
 
         const result = await client.tryCompressChat('prompt-id-4', false);
 
-        expect(result).toEqual({
-          compressionStatus:
-            CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
-          newTokenCount: estimatedNewTokenCount,
-          originalTokenCount: 100,
-        });
+        expect(result.compressionStatus).toBe(
+          CompressionStatus.COMPRESSION_FAILED_INFLATED_TOKEN_COUNT,
+        );
+        expect(result.originalTokenCount).toBe(100);
+        // The newTokenCount should be higher than original since compression failed due to inflation
+        expect(result.newTokenCount).toBeGreaterThan(100);
         // IMPORTANT: The change in client.ts means setLastPromptTokenCount is NOT called on failure
         expect(
           uiTelemetryService.setLastPromptTokenCount,
@@ -543,10 +586,13 @@ describe('Gemini Client (client.ts)', () => {
       });
 
       it('does not manipulate the source chat', async () => {
+        // newTokenCount = 100 - (1010 - 1000) + 200 = 100 - 10 + 200 = 290 > 100 (inflation)
         const longSummary = 'long summary '.repeat(100);
         const { client, mockOriginalChat, estimatedNewTokenCount } = setup({
           originalTokenCount: 100,
           summaryText: longSummary,
+          compressionInputTokenCount: 1010,
+          compressionOutputTokenCount: 200,
         });
         expect(estimatedNewTokenCount).toBeGreaterThan(100); // Ensure setup is correct
 
@@ -557,10 +603,13 @@ describe('Gemini Client (client.ts)', () => {
       });
 
       it('will not attempt to compress context after a failure', async () => {
+        // newTokenCount = 100 - (1010 - 1000) + 200 = 100 - 10 + 200 = 290 > 100 (inflation)
         const longSummary = 'long summary '.repeat(100);
         const { client, estimatedNewTokenCount } = setup({
           originalTokenCount: 100,
           summaryText: longSummary,
+          compressionInputTokenCount: 1010,
+          compressionOutputTokenCount: 200,
         });
         expect(estimatedNewTokenCount).toBeGreaterThan(100); // Ensure setup is correct
 
@@ -631,6 +680,7 @@ describe('Gemini Client (client.ts)', () => {
       );
 
       // Mock the summary response from the chat
+      // newTokenCount = 501 - (1400 - 1000) + 50 = 501 - 400 + 50 = 151 <= 501 (success)
       const summaryText = 'This is a summary.';
       mockGenerateContentFn.mockResolvedValue({
         candidates: [
@@ -641,6 +691,11 @@ describe('Gemini Client (client.ts)', () => {
             },
           },
         ],
+        usageMetadata: {
+          promptTokenCount: 1400,
+          candidatesTokenCount: 50,
+          totalTokenCount: 1450,
+        },
       } as unknown as GenerateContentResponse);
 
       // Mock startChat to complete the compression flow
@@ -719,13 +774,8 @@ describe('Gemini Client (client.ts)', () => {
         .fn()
         .mockResolvedValue(mockNewChat as GeminiChat);
 
-      const totalChars = newCompressedHistory.reduce(
-        (total, content) => total + JSON.stringify(content).length,
-        0,
-      );
-      const newTokenCount = Math.floor(totalChars / 4);
-
       // Mock the summary response from the chat
+      // newTokenCount = 501 - (1400 - 1000) + 50 = 501 - 400 + 50 = 151 <= 501 (success)
       mockGenerateContentFn.mockResolvedValue({
         candidates: [
           {
@@ -735,6 +785,11 @@ describe('Gemini Client (client.ts)', () => {
             },
           },
         ],
+        usageMetadata: {
+          promptTokenCount: 1400,
+          candidatesTokenCount: 50,
+          totalTokenCount: 1450,
+        },
       } as unknown as GenerateContentResponse);
 
       const initialChat = client.getChat();
@@ -744,12 +799,11 @@ describe('Gemini Client (client.ts)', () => {
       expect(tokenLimit).toHaveBeenCalled();
       expect(mockGenerateContentFn).toHaveBeenCalled();
 
-      // Assert that summarization happened and returned the correct stats
-      expect(result).toEqual({
-        compressionStatus: CompressionStatus.COMPRESSED,
-        originalTokenCount,
-        newTokenCount,
-      });
+      // Assert that summarization happened
+      expect(result.compressionStatus).toBe(CompressionStatus.COMPRESSED);
+      expect(result.originalTokenCount).toBe(originalTokenCount);
+      // newTokenCount might be clamped to originalTokenCount due to tolerance logic
+      expect(result.newTokenCount).toBeLessThanOrEqual(originalTokenCount);
 
       // Assert that the chat was reset
       expect(newChat).not.toBe(initialChat);
@@ -809,13 +863,8 @@ describe('Gemini Client (client.ts)', () => {
         .fn()
         .mockResolvedValue(mockNewChat as GeminiChat);
 
-      const totalChars = newCompressedHistory.reduce(
-        (total, content) => total + JSON.stringify(content).length,
-        0,
-      );
-      const newTokenCount = Math.floor(totalChars / 4);
-
       // Mock the summary response from the chat
+      // newTokenCount = 700 - (1500 - 1000) + 50 = 700 - 500 + 50 = 250 <= 700 (success)
       mockGenerateContentFn.mockResolvedValue({
         candidates: [
           {
@@ -825,6 +874,11 @@ describe('Gemini Client (client.ts)', () => {
             },
           },
         ],
+        usageMetadata: {
+          promptTokenCount: 1500,
+          candidatesTokenCount: 50,
+          totalTokenCount: 1550,
+        },
       } as unknown as GenerateContentResponse);
 
       const initialChat = client.getChat();
@@ -834,12 +888,11 @@ describe('Gemini Client (client.ts)', () => {
       expect(tokenLimit).toHaveBeenCalled();
       expect(mockGenerateContentFn).toHaveBeenCalled();
 
-      // Assert that summarization happened and returned the correct stats
-      expect(result).toEqual({
-        compressionStatus: CompressionStatus.COMPRESSED,
-        originalTokenCount,
-        newTokenCount,
-      });
+      // Assert that summarization happened
+      expect(result.compressionStatus).toBe(CompressionStatus.COMPRESSED);
+      expect(result.originalTokenCount).toBe(originalTokenCount);
+      // newTokenCount might be clamped to originalTokenCount due to tolerance logic
+      expect(result.newTokenCount).toBeLessThanOrEqual(originalTokenCount);
       // Assert that the chat was reset
       expect(newChat).not.toBe(initialChat);
 
@@ -887,13 +940,8 @@ describe('Gemini Client (client.ts)', () => {
         .fn()
         .mockResolvedValue(mockNewChat as GeminiChat);
 
-      const totalChars = newCompressedHistory.reduce(
-        (total, content) => total + JSON.stringify(content).length,
-        0,
-      );
-      const newTokenCount = Math.floor(totalChars / 4);
-
       // Mock the summary response from the chat
+      // newTokenCount = 100 - (1060 - 1000) + 20 = 100 - 60 + 20 = 60 <= 100 (success)
       mockGenerateContentFn.mockResolvedValue({
         candidates: [
           {
@@ -903,6 +951,11 @@ describe('Gemini Client (client.ts)', () => {
             },
           },
         ],
+        usageMetadata: {
+          promptTokenCount: 1060,
+          candidatesTokenCount: 20,
+          totalTokenCount: 1080,
+        },
       } as unknown as GenerateContentResponse);
 
       const initialChat = client.getChat();
@@ -911,11 +964,10 @@ describe('Gemini Client (client.ts)', () => {
 
       expect(mockGenerateContentFn).toHaveBeenCalled();
 
-      expect(result).toEqual({
-        compressionStatus: CompressionStatus.COMPRESSED,
-        originalTokenCount,
-        newTokenCount,
-      });
+      expect(result.compressionStatus).toBe(CompressionStatus.COMPRESSED);
+      expect(result.originalTokenCount).toBe(originalTokenCount);
+      // newTokenCount might be clamped to originalTokenCount due to tolerance logic
+      expect(result.newTokenCount).toBeLessThanOrEqual(originalTokenCount);
 
       // Assert that the chat was reset
       expect(newChat).not.toBe(initialChat);

packages/core/src/core/client.ts

@@ -441,47 +441,19 @@ export class GeminiClient {
       yield { type: GeminiEventType.ChatCompressed, value: compressed };
     }
 
-    // Check session token limit after compression using accurate token counting
+    // Check session token limit after compression.
+    // `lastPromptTokenCount` is treated as authoritative for the (possibly compressed) history;
     const sessionTokenLimit = this.config.getSessionTokenLimit();
     if (sessionTokenLimit > 0) {
-      // Get all the content that would be sent in an API call
-      const currentHistory = this.getChat().getHistory(true);
-      const userMemory = this.config.getUserMemory();
-      const systemPrompt = getCoreSystemPrompt(
-        userMemory,
-        this.config.getModel(),
-      );
-      const initialHistory = await getInitialChatHistory(this.config);
-
-      // Create a mock request content to count total tokens
-      const mockRequestContent = [
-        {
-          role: 'system' as const,
-          parts: [{ text: systemPrompt }],
-        },
-        ...initialHistory,
-        ...currentHistory,
-      ];
-
-      // Use the improved countTokens method for accurate counting
-      const { totalTokens: totalRequestTokens } = await this.config
-        .getContentGenerator()
-        .countTokens({
-          model: this.config.getModel(),
-          contents: mockRequestContent,
-        });
-
-      if (
-        totalRequestTokens !== undefined &&
-        totalRequestTokens > sessionTokenLimit
-      ) {
+      const lastPromptTokenCount = uiTelemetryService.getLastPromptTokenCount();
+      if (lastPromptTokenCount > sessionTokenLimit) {
         yield {
           type: GeminiEventType.SessionTokenLimitExceeded,
           value: {
-            currentTokens: totalRequestTokens,
+            currentTokens: lastPromptTokenCount,
             limit: sessionTokenLimit,
             message:
-              `Session token limit exceeded: ${totalRequestTokens} tokens > ${sessionTokenLimit} limit. ` +
+              `Session token limit exceeded: ${lastPromptTokenCount} tokens > ${sessionTokenLimit} limit. ` +
               'Please start a new session or increase the sessionTokenLimit in your settings.json.',
           },
         };

packages/core/src/core/geminiChat.test.ts

@@ -708,7 +708,7 @@ describe('GeminiChat', () => {
 
       // Verify that token counting is called when usageMetadata is present
       expect(uiTelemetryService.setLastPromptTokenCount).toHaveBeenCalledWith(
-        42,
+        57,
       );
       expect(uiTelemetryService.setLastPromptTokenCount).toHaveBeenCalledTimes(
         1,

packages/core/src/core/geminiChat.ts

@@ -529,10 +529,10 @@ export class GeminiChat {
       // Collect token usage for consolidated recording
       if (chunk.usageMetadata) {
         usageMetadata = chunk.usageMetadata;
-        if (chunk.usageMetadata.promptTokenCount !== undefined) {
-          uiTelemetryService.setLastPromptTokenCount(
-            chunk.usageMetadata.promptTokenCount,
-          );
+        const lastPromptTokenCount =
+          usageMetadata.totalTokenCount ?? usageMetadata.promptTokenCount;
+        if (lastPromptTokenCount) {
+          uiTelemetryService.setLastPromptTokenCount(lastPromptTokenCount);
         }
       }
 

packages/core/src/core/openaiContentGenerator/openaiContentGenerator.test.ts

@@ -22,17 +22,7 @@ const mockTokenizer = {
 };
 
 vi.mock('../../../utils/request-tokenizer/index.js', () => ({
-  getDefaultTokenizer: vi.fn(() => mockTokenizer),
-  DefaultRequestTokenizer: vi.fn(() => mockTokenizer),
-  disposeDefaultTokenizer: vi.fn(),
-}));
-
-// Mock tiktoken as well for completeness
-vi.mock('tiktoken', () => ({
-  get_encoding: vi.fn(() => ({
-    encode: vi.fn(() => new Array(50)), // Mock 50 tokens
-    free: vi.fn(),
-  })),
+  RequestTokenEstimator: vi.fn(() => mockTokenizer),
 }));
 
 // Now import the modules that depend on the mocked modules
@@ -134,7 +124,7 @@ describe('OpenAIContentGenerator (Refactored)', () => {
   });
 
   describe('countTokens', () => {
-    it('should count tokens using tiktoken', async () => {
+    it('should count tokens using character-based estimation', async () => {
       const request: CountTokensParameters = {
         contents: [{ role: 'user', parts: [{ text: 'Hello world' }] }],
         model: 'gpt-4',
@@ -142,26 +132,27 @@ describe('OpenAIContentGenerator (Refactored)', () => {
 
       const result = await generator.countTokens(request);
 
-      expect(result.totalTokens).toBe(50); // Mocked value
+      // 'Hello world' = 11 ASCII chars
+      // 11 / 4 = 2.75 -> ceil = 3 tokens
+      expect(result.totalTokens).toBe(3);
     });
 
-    it('should fall back to character approximation if tiktoken fails', async () => {
-      // Mock tiktoken to throw error
-      vi.doMock('tiktoken', () => ({
-        get_encoding: vi.fn().mockImplementation(() => {
-          throw new Error('Tiktoken failed');
-        }),
-      }));
-
+    it('should handle multimodal content', async () => {
       const request: CountTokensParameters = {
-        contents: [{ role: 'user', parts: [{ text: 'Hello world' }] }],
+        contents: [
+          {
+            role: 'user',
+            parts: [{ text: 'Hello' }, { text: ' world' }],
+          },
+        ],
         model: 'gpt-4',
       };
 
       const result = await generator.countTokens(request);
 
-      // Should use character approximation (content length / 4)
-      expect(result.totalTokens).toBeGreaterThan(0);
+      // Parts are combined for estimation:
+      // 'Hello world' = 11 ASCII chars -> 11/4 = 2.75 -> ceil = 3 tokens
+      expect(result.totalTokens).toBe(3);
     });
   });
 

packages/core/src/core/openaiContentGenerator/openaiContentGenerator.ts

@@ -12,7 +12,7 @@ import type {
 import type { PipelineConfig } from './pipeline.js';
 import { ContentGenerationPipeline } from './pipeline.js';
 import { EnhancedErrorHandler } from './errorHandler.js';
-import { getDefaultTokenizer } from '../../utils/request-tokenizer/index.js';
+import { RequestTokenEstimator } from '../../utils/request-tokenizer/index.js';
 import type { ContentGeneratorConfig } from '../contentGenerator.js';
 import { isAbortError } from '../../utils/errors.js';
 
@@ -80,11 +80,9 @@ export class OpenAIContentGenerator implements ContentGenerator {
     request: CountTokensParameters,
   ): Promise<CountTokensResponse> {
     try {
-      // Use the new high-performance request tokenizer
-      const tokenizer = getDefaultTokenizer();
-      const result = await tokenizer.calculateTokens(request, {
-        textEncoding: 'cl100k_base', // Use GPT-4 encoding for consistency
-      });
+      // Use the request token estimator (character-based).
+      const estimator = new RequestTokenEstimator();
+      const result = await estimator.calculateTokens(request);
 
       return {
         totalTokens: result.totalTokens,

packages/core/src/models/constants.ts

@@ -102,16 +102,14 @@ export const QWEN_OAUTH_ALLOWED_MODELS = [
 export const QWEN_OAUTH_MODELS: ModelConfig[] = [
   {
     id: 'coder-model',
-    name: 'Qwen Coder',
-    description:
-      'The latest Qwen Coder model from Alibaba Cloud ModelStudio (version: qwen3-coder-plus-2025-09-23)',
+    name: 'coder-model',
+    description: 'The latest Qwen Coder model from Alibaba Cloud ModelStudio',
     capabilities: { vision: false },
   },
   {
     id: 'vision-model',
-    name: 'Qwen Vision',
-    description:
-      'The latest Qwen Vision model from Alibaba Cloud ModelStudio (version: qwen3-vl-plus-2025-09-23)',
+    name: 'vision-model',
+    description: 'The latest Qwen Vision model from Alibaba Cloud ModelStudio',
     capabilities: { vision: true },
   },
 ];

packages/core/src/services/chatCompressionService.test.ts

@@ -15,13 +15,11 @@ import { uiTelemetryService } from '../telemetry/uiTelemetry.js';
 import { tokenLimit } from '../core/tokenLimits.js';
 import type { GeminiChat } from '../core/geminiChat.js';
 import type { Config } from '../config/config.js';
-import { getInitialChatHistory } from '../utils/environmentContext.js';
 import type { ContentGenerator } from '../core/contentGenerator.js';
 
 vi.mock('../telemetry/uiTelemetry.js');
 vi.mock('../core/tokenLimits.js');
 vi.mock('../telemetry/loggers.js');
-vi.mock('../utils/environmentContext.js');
 
 describe('findCompressSplitPoint', () => {
   it('should throw an error for non-positive numbers', () => {
@@ -122,9 +120,6 @@ describe('ChatCompressionService', () => {
 
     vi.mocked(tokenLimit).mockReturnValue(1000);
     vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(500);
-    vi.mocked(getInitialChatHistory).mockImplementation(
-      async (_config, extraHistory) => extraHistory || [],
-    );
   });
 
   afterEach(() => {
@@ -241,6 +236,7 @@ describe('ChatCompressionService', () => {
     vi.mocked(mockChat.getHistory).mockReturnValue(history);
     vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(800);
     vi.mocked(tokenLimit).mockReturnValue(1000);
+    // newTokenCount = 800 - (1600 - 1000) + 50 = 800 - 600 + 50 = 250 <= 800 (success)
     const mockGenerateContent = vi.fn().mockResolvedValue({
       candidates: [
         {
@@ -249,6 +245,11 @@ describe('ChatCompressionService', () => {
           },
         },
       ],
+      usageMetadata: {
+        promptTokenCount: 1600,
+        candidatesTokenCount: 50,
+        totalTokenCount: 1650,
+      },
     } as unknown as GenerateContentResponse);
     vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
       generateContent: mockGenerateContent,
@@ -264,6 +265,7 @@ describe('ChatCompressionService', () => {
     );
 
     expect(result.info.compressionStatus).toBe(CompressionStatus.COMPRESSED);
+    expect(result.info.newTokenCount).toBe(250); // 800 - (1600 - 1000) + 50
     expect(result.newHistory).not.toBeNull();
     expect(result.newHistory![0].parts![0].text).toBe('Summary');
     expect(mockGenerateContent).toHaveBeenCalled();
@@ -280,6 +282,7 @@ describe('ChatCompressionService', () => {
     vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(100);
     vi.mocked(tokenLimit).mockReturnValue(1000);
 
+    // newTokenCount = 100 - (1100 - 1000) + 50 = 100 - 100 + 50 = 50 <= 100 (success)
     const mockGenerateContent = vi.fn().mockResolvedValue({
       candidates: [
         {
@@ -288,6 +291,11 @@ describe('ChatCompressionService', () => {
           },
         },
       ],
+      usageMetadata: {
+        promptTokenCount: 1100,
+        candidatesTokenCount: 50,
+        totalTokenCount: 1150,
+      },
     } as unknown as GenerateContentResponse);
     vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
       generateContent: mockGenerateContent,
@@ -315,15 +323,19 @@ describe('ChatCompressionService', () => {
     vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(10);
     vi.mocked(tokenLimit).mockReturnValue(1000);
 
-    const longSummary = 'a'.repeat(1000); // Long summary to inflate token count
     const mockGenerateContent = vi.fn().mockResolvedValue({
       candidates: [
         {
           content: {
-            parts: [{ text: longSummary }],
+            parts: [{ text: 'Summary' }],
           },
         },
       ],
+      usageMetadata: {
+        promptTokenCount: 1,
+        candidatesTokenCount: 20,
+        totalTokenCount: 21,
+      },
     } as unknown as GenerateContentResponse);
     vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
       generateContent: mockGenerateContent,
@@ -344,6 +356,48 @@ describe('ChatCompressionService', () => {
     expect(result.newHistory).toBeNull();
   });
 
+  it('should return FAILED if usage metadata is missing', async () => {
+    const history: Content[] = [
+      { role: 'user', parts: [{ text: 'msg1' }] },
+      { role: 'model', parts: [{ text: 'msg2' }] },
+      { role: 'user', parts: [{ text: 'msg3' }] },
+      { role: 'model', parts: [{ text: 'msg4' }] },
+    ];
+    vi.mocked(mockChat.getHistory).mockReturnValue(history);
+    vi.mocked(uiTelemetryService.getLastPromptTokenCount).mockReturnValue(800);
+    vi.mocked(tokenLimit).mockReturnValue(1000);
+
+    const mockGenerateContent = vi.fn().mockResolvedValue({
+      candidates: [
+        {
+          content: {
+            parts: [{ text: 'Summary' }],
+          },
+        },
+      ],
+      // No usageMetadata -> keep original token count
+    } as unknown as GenerateContentResponse);
+    vi.mocked(mockConfig.getContentGenerator).mockReturnValue({
+      generateContent: mockGenerateContent,
+    } as unknown as ContentGenerator);
+
+    const result = await service.compress(
+      mockChat,
+      mockPromptId,
+      false,
+      mockModel,
+      mockConfig,
+      false,
+    );
+
+    expect(result.info.compressionStatus).toBe(
+      CompressionStatus.COMPRESSION_FAILED_TOKEN_COUNT_ERROR,
+    );
+    expect(result.info.originalTokenCount).toBe(800);
+    expect(result.info.newTokenCount).toBe(800);
+    expect(result.newHistory).toBeNull();
+  });
+
   it('should return FAILED if summary is empty string', async () => {
     const history: Content[] = [
       { role: 'user', parts: [{ text: 'msg1' }] },

packages/core/src/services/chatCompressionService.ts

@@ -14,7 +14,6 @@ import { getCompressionPrompt } from '../core/prompts.js';
 import { getResponseText } from '../utils/partUtils.js';
 import { logChatCompression } from '../telemetry/loggers.js';
 import { makeChatCompressionEvent } from '../telemetry/types.js';
-import { getInitialChatHistory } from '../utils/environmentContext.js';
 
 /**
  * Threshold for compression token count as a fraction of the model's token limit.
@@ -163,9 +162,25 @@ export class ChatCompressionService {
     );
     const summary = getResponseText(summaryResponse) ?? '';
     const isSummaryEmpty = !summary || summary.trim().length === 0;
+    const compressionUsageMetadata = summaryResponse.usageMetadata;
+    const compressionInputTokenCount =
+      compressionUsageMetadata?.promptTokenCount;
+    let compressionOutputTokenCount =
+      compressionUsageMetadata?.candidatesTokenCount;
+    if (
+      compressionOutputTokenCount === undefined &&
+      typeof compressionUsageMetadata?.totalTokenCount === 'number' &&
+      typeof compressionInputTokenCount === 'number'
+    ) {
+      compressionOutputTokenCount = Math.max(
+        0,
+        compressionUsageMetadata.totalTokenCount - compressionInputTokenCount,
+      );
+    }
 
     let newTokenCount = originalTokenCount;
     let extraHistory: Content[] = [];
+    let canCalculateNewTokenCount = false;
 
     if (!isSummaryEmpty) {
       extraHistory = [
@@ -180,16 +195,26 @@ export class ChatCompressionService {
         ...historyToKeep,
       ];
 
-      // Use a shared utility to construct the initial history for an accurate token count.
-      const fullNewHistory = await getInitialChatHistory(config, extraHistory);
-
-      // Estimate token count 1 token ≈ 4 characters
-      newTokenCount = Math.floor(
-        fullNewHistory.reduce(
-          (total, content) => total + JSON.stringify(content).length,
+      // Best-effort token math using *only* model-reported token counts.
+      //
+      // Note: compressionInputTokenCount includes the compression prompt and
+      // the extra "reason in your scratchpad" instruction(approx. 1000 tokens), and
+      // compressionOutputTokenCount may include non-persisted tokens (thoughts).
+      // We accept these inaccuracies to avoid local token estimation.
+      if (
+        typeof compressionInputTokenCount === 'number' &&
+        compressionInputTokenCount > 0 &&
+        typeof compressionOutputTokenCount === 'number' &&
+        compressionOutputTokenCount > 0
+      ) {
+        canCalculateNewTokenCount = true;
+        newTokenCount = Math.max(
           0,
-        ) / 4,
-      );
+          originalTokenCount -
+            (compressionInputTokenCount - 1000) +
+            compressionOutputTokenCount,
+        );
+      }
     }
 
     logChatCompression(
@@ -197,6 +222,8 @@ export class ChatCompressionService {
       makeChatCompressionEvent({
         tokens_before: originalTokenCount,
         tokens_after: newTokenCount,
+        compression_input_token_count: compressionInputTokenCount,
+        compression_output_token_count: compressionOutputTokenCount,
       }),
     );
 
@@ -209,6 +236,16 @@ export class ChatCompressionService {
           compressionStatus: CompressionStatus.COMPRESSION_FAILED_EMPTY_SUMMARY,
         },
       };
+    } else if (!canCalculateNewTokenCount) {
+      return {
+        newHistory: null,
+        info: {
+          originalTokenCount,
+          newTokenCount: originalTokenCount,
+          compressionStatus:
+            CompressionStatus.COMPRESSION_FAILED_TOKEN_COUNT_ERROR,
+        },
+      };
     } else if (newTokenCount > originalTokenCount) {
       return {
         newHistory: null,

packages/core/src/services/shellExecutionService.test.ts

@@ -580,9 +580,11 @@ describe('ShellExecutionService child_process fallback', () => {
       });
 
       expect(mockCpSpawn).toHaveBeenCalledWith(
-        'ls -l',
-        [],
-        expect.objectContaining({ shell: 'bash' }),
+        'bash',
+        ['-c', 'ls -l'],
+        expect.objectContaining({
+          detached: true,
+        }),
       );
       expect(result.exitCode).toBe(0);
       expect(result.signal).toBeNull();
@@ -825,10 +827,9 @@ describe('ShellExecutionService child_process fallback', () => {
       );
 
       expect(mockCpSpawn).toHaveBeenCalledWith(
-        'dir "foo bar"',
-        [],
+        'cmd.exe',
+        ['/c', 'dir "foo bar"'],
         expect.objectContaining({
-          shell: true,
           detached: false,
           windowsHide: true,
         }),
@@ -840,10 +841,9 @@ describe('ShellExecutionService child_process fallback', () => {
       await simulateExecution('ls "foo bar"', (cp) => cp.emit('exit', 0, null));
 
       expect(mockCpSpawn).toHaveBeenCalledWith(
-        'ls "foo bar"',
-        [],
+        'bash',
+        ['-c', 'ls "foo bar"'],
         expect.objectContaining({
-          shell: 'bash',
           detached: true,
         }),
       );

packages/core/src/services/shellExecutionService.ts

@@ -223,12 +223,17 @@ export class ShellExecutionService {
   ): ShellExecutionHandle {
     try {
       const isWindows = os.platform() === 'win32';
+      const shell = isWindows ? 'cmd.exe' : 'bash';
+      const shellArgs = isWindows
+        ? ['/c', commandToExecute]
+        : ['-c', commandToExecute];
 
-      const child = cpSpawn(commandToExecute, [], {
+      // Note: CodeQL flags this as js/shell-command-injection-from-environment.
+      // This is intentional - CLI tool executes user-provided shell commands.
+      const child = cpSpawn(shell, shellArgs, {
         cwd,
         stdio: ['ignore', 'pipe', 'pipe'],
-        windowsVerbatimArguments: true,
-        shell: isWindows ? true : 'bash',
+        windowsVerbatimArguments: isWindows,
         detached: !isWindows,
         windowsHide: isWindows,
         env: {

packages/core/src/telemetry/types.ts

@@ -439,17 +439,27 @@ export interface ChatCompressionEvent extends BaseTelemetryEvent {
   'event.timestamp': string;
   tokens_before: number;
   tokens_after: number;
+  compression_input_token_count?: number;
+  compression_output_token_count?: number;
 }
 
 export function makeChatCompressionEvent({
   tokens_before,
   tokens_after,
+  compression_input_token_count,
+  compression_output_token_count,
 }: Omit<ChatCompressionEvent, CommonFields>): ChatCompressionEvent {
   return {
     'event.name': 'chat_compression',
     'event.timestamp': new Date().toISOString(),
     tokens_before,
     tokens_after,
+    ...(compression_input_token_count !== undefined
+      ? { compression_input_token_count }
+      : {}),
+    ...(compression_output_token_count !== undefined
+      ? { compression_output_token_count }
+      : {}),
   };
 }
 

packages/core/src/utils/memoryImportProcessor.test.ts

@@ -92,11 +92,15 @@ const findCodeBlocks = (
 
 describe('memoryImportProcessor', () => {
   beforeEach(() => {
-    vi.clearAllMocks();
+    vi.resetAllMocks(); // Use resetAllMocks to clear mock implementations
     // Mock console methods
     console.warn = vi.fn();
     console.error = vi.fn();
     console.debug = vi.fn();
+    // Default mock for lstat (used by findProjectRoot)
+    mockedFs.lstat.mockRejectedValue(
+      Object.assign(new Error('ENOENT'), { code: 'ENOENT' }),
+    );
   });
 
   afterEach(() => {
@@ -204,20 +208,43 @@ describe('memoryImportProcessor', () => {
       );
     });
 
-    it('should handle file not found errors', async () => {
+    it('should silently preserve content when file not found (ENOENT)', async () => {
       const content = 'Content @./nonexistent.md more content';
       const basePath = testPath('test', 'path');
 
-      mockedFs.access.mockRejectedValue(new Error('File not found'));
+      // Mock ENOENT error (file not found)
+      mockedFs.access.mockRejectedValue(
+        Object.assign(new Error('ENOENT: no such file or directory'), {
+          code: 'ENOENT',
+        }),
+      );
 
       const result = await processImports(content, basePath, true);
 
+      // Content should be preserved as-is when file doesn't exist
+      expect(result.content).toBe(content);
+      // No error should be logged for ENOENT
+      expect(console.error).not.toHaveBeenCalled();
+    });
+
+    it('should log error for non-ENOENT file access errors', async () => {
+      const content = 'Content @./permission-denied.md more content';
+      const basePath = testPath('test', 'path');
+
+      // Mock a permission denied error (not ENOENT)
+      mockedFs.access.mockRejectedValue(
+        Object.assign(new Error('Permission denied'), { code: 'EACCES' }),
+      );
+
+      const result = await processImports(content, basePath, true);
+
+      // Should show error comment for non-ENOENT errors
       expect(result.content).toContain(
-        '<!-- Import failed: ./nonexistent.md - File not found -->',
+        '<!-- Import failed: ./permission-denied.md - Permission denied -->',
       );
       expect(console.error).toHaveBeenCalledWith(
         '[ERROR] [ImportProcessor]',
-        'Failed to import ./nonexistent.md: File not found',
+        'Failed to import ./permission-denied.md: Permission denied',
       );
     });
 
@@ -448,6 +475,50 @@ describe('memoryImportProcessor', () => {
       expect(result.importTree.imports).toBeUndefined();
     });
 
+    it('should still import valid paths while ignoring non-existent paths', async () => {
+      const content = '使用 @./valid.md 文件和 @中文路径 注解';
+      const basePath = testPath('test', 'path');
+      const importedContent = 'Valid imported content';
+
+      // Mock: valid.md exists, 中文路径 doesn't exist
+      mockedFs.access
+        .mockResolvedValueOnce(undefined) // ./valid.md exists
+        .mockRejectedValueOnce(
+          Object.assign(new Error('ENOENT'), { code: 'ENOENT' }),
+        ); // 中文路径 doesn't exist
+      mockedFs.readFile.mockResolvedValue(importedContent);
+
+      const result = await processImports(content, basePath, true);
+
+      // Should import valid.md
+      expect(result.content).toContain(importedContent);
+      expect(result.content).toContain('<!-- Imported from: ./valid.md -->');
+      // The non-existent path should remain as-is
+      expect(result.content).toContain('@中文路径');
+    });
+
+    it('should import Chinese file names if they exist', async () => {
+      const content = '导入 @./中文文档.md 文件';
+      const projectRoot = testPath('test', 'project');
+      const basePath = testPath(projectRoot, 'src');
+      const importedContent = '这是中文文档的内容';
+
+      mockedFs.access.mockResolvedValue(undefined);
+      mockedFs.readFile.mockResolvedValue(importedContent);
+
+      const result = await processImports(
+        content,
+        basePath,
+        true,
+        undefined,
+        projectRoot,
+      );
+
+      // Should successfully import the Chinese-named file
+      expect(result.content).toContain(importedContent);
+      expect(result.content).toContain('<!-- Imported from: ./中文文档.md -->');
+    });
+
     it('should allow imports from parent and subdirectories within project root', async () => {
       const content =
         'Parent import: @../parent.md Subdir import: @./components/sub.md';

packages/core/src/utils/memoryImportProcessor.ts

@@ -150,6 +150,18 @@ function isLetter(char: string): boolean {
   ); // a-z
 }
 
+/**
+ * Checks if an error is a "file not found" error (ENOENT)
+ */
+function isFileNotFoundError(err: unknown): boolean {
+  return (
+    typeof err === 'object' &&
+    err !== null &&
+    'code' in err &&
+    (err as { code: unknown }).code === 'ENOENT'
+  );
+}
+
 function findCodeRegions(content: string): Array<[number, number]> {
   const regions: Array<[number, number]> = [];
   const tokens = marked.lexer(content);
@@ -292,7 +304,9 @@ export async function processImports(
             depth + 1,
           );
         } catch (error) {
-          if (debugMode) {
+          // If file doesn't exist, silently skip this import (it's not a real import)
+          // Only log warnings for other types of errors
+          if (!isFileNotFoundError(error) && debugMode) {
             logger.warn(
               `Failed to import ${fullPath}: ${hasMessage(error) ? error.message : 'Unknown error'}`,
             );
@@ -371,6 +385,12 @@ export async function processImports(
       result += `<!-- Imported from: ${importPath} -->\n${imported.content}\n<!-- End of import from: ${importPath} -->`;
       imports.push(imported.importTree);
     } catch (err: unknown) {
+      // If file doesn't exist, preserve the original @path text (it's not a real import)
+      if (isFileNotFoundError(err)) {
+        result += `@${importPath}`;
+        continue;
+      }
+      // For other errors, log and add error comment
       let message = 'Unknown error';
       if (hasMessage(err)) {
         message = err.message;

packages/core/src/utils/request-tokenizer/index.ts

@@ -4,37 +4,8 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-export { DefaultRequestTokenizer } from './requestTokenizer.js';
-import { DefaultRequestTokenizer } from './requestTokenizer.js';
+export { RequestTokenizer as RequestTokenEstimator } from './requestTokenizer.js';
 export { TextTokenizer } from './textTokenizer.js';
 export { ImageTokenizer } from './imageTokenizer.js';
 
-export type {
-  RequestTokenizer,
-  TokenizerConfig,
-  TokenCalculationResult,
-  ImageMetadata,
-} from './types.js';
-
-// Singleton instance for convenient usage
-let defaultTokenizer: DefaultRequestTokenizer | null = null;
-
-/**
- * Get the default request tokenizer instance
- */
-export function getDefaultTokenizer(): DefaultRequestTokenizer {
-  if (!defaultTokenizer) {
-    defaultTokenizer = new DefaultRequestTokenizer();
-  }
-  return defaultTokenizer;
-}
-
-/**
- * Dispose of the default tokenizer instance
- */
-export async function disposeDefaultTokenizer(): Promise<void> {
-  if (defaultTokenizer) {
-    await defaultTokenizer.dispose();
-    defaultTokenizer = null;
-  }
-}
+export type { TokenCalculationResult, ImageMetadata } from './types.js';

packages/core/src/utils/request-tokenizer/requestTokenizer.test.ts

@@ -4,19 +4,15 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { describe, it, expect, beforeEach, afterEach } from 'vitest';
-import { DefaultRequestTokenizer } from './requestTokenizer.js';
+import { describe, it, expect, beforeEach } from 'vitest';
+import { RequestTokenizer } from './requestTokenizer.js';
 import type { CountTokensParameters } from '@google/genai';
 
-describe('DefaultRequestTokenizer', () => {
-  let tokenizer: DefaultRequestTokenizer;
+describe('RequestTokenEstimator', () => {
+  let tokenizer: RequestTokenizer;
 
   beforeEach(() => {
-    tokenizer = new DefaultRequestTokenizer();
-  });
-
-  afterEach(async () => {
-    await tokenizer.dispose();
+    tokenizer = new RequestTokenizer();
   });
 
   describe('text token calculation', () => {
@@ -221,25 +217,7 @@ describe('DefaultRequestTokenizer', () => {
     });
   });
 
-  describe('configuration', () => {
-    it('should use custom text encoding', async () => {
-      const request: CountTokensParameters = {
-        model: 'test-model',
-        contents: [
-          {
-            role: 'user',
-            parts: [{ text: 'Test text for encoding' }],
-          },
-        ],
-      };
-
-      const result = await tokenizer.calculateTokens(request, {
-        textEncoding: 'cl100k_base',
-      });
-
-      expect(result.totalTokens).toBeGreaterThan(0);
-    });
-
+  describe('images', () => {
     it('should process multiple images serially', async () => {
       const pngBase64 =
         'iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAYAAAAfFcSJAAAADUlEQVR42mNkYPhfDwAChAI9jU77yQAAAABJRU5ErkJggg==';

packages/core/src/utils/request-tokenizer/requestTokenizer.ts

@@ -10,18 +10,14 @@ import type {
   Part,
   PartUnion,
 } from '@google/genai';
-import type {
-  RequestTokenizer,
-  TokenizerConfig,
-  TokenCalculationResult,
-} from './types.js';
+import type { TokenCalculationResult } from './types.js';
 import { TextTokenizer } from './textTokenizer.js';
 import { ImageTokenizer } from './imageTokenizer.js';
 
 /**
- * Simple request tokenizer that handles text and image content serially
+ * Simple request token estimator that handles text and image content serially
  */
-export class DefaultRequestTokenizer implements RequestTokenizer {
+export class RequestTokenizer {
   private textTokenizer: TextTokenizer;
   private imageTokenizer: ImageTokenizer;
 
@@ -35,15 +31,9 @@ export class DefaultRequestTokenizer implements RequestTokenizer {
    */
   async calculateTokens(
     request: CountTokensParameters,
-    config: TokenizerConfig = {},
   ): Promise<TokenCalculationResult> {
     const startTime = performance.now();
 
-    // Apply configuration
-    if (config.textEncoding) {
-      this.textTokenizer = new TextTokenizer(config.textEncoding);
-    }
-
     try {
       // Process request content and group by type
       const { textContents, imageContents, audioContents, otherContents } =
@@ -112,9 +102,8 @@ export class DefaultRequestTokenizer implements RequestTokenizer {
     if (textContents.length === 0) return 0;
 
     try {
-      const tokenCounts =
-        await this.textTokenizer.calculateTokensBatch(textContents);
-      return tokenCounts.reduce((sum, count) => sum + count, 0);
+      // Avoid per-part rounding inflation by estimating once on the combined text.
+      return await this.textTokenizer.calculateTokens(textContents.join(''));
     } catch (error) {
       console.warn('Error calculating text tokens:', error);
       // Fallback: character-based estimation
@@ -177,10 +166,8 @@ export class DefaultRequestTokenizer implements RequestTokenizer {
     if (otherContents.length === 0) return 0;
 
     try {
-      // Treat other content as text for token calculation
-      const tokenCounts =
-        await this.textTokenizer.calculateTokensBatch(otherContents);
-      return tokenCounts.reduce((sum, count) => sum + count, 0);
+      // Treat other content as text, and avoid per-item rounding inflation.
+      return await this.textTokenizer.calculateTokens(otherContents.join(''));
     } catch (error) {
       console.warn('Error calculating other content tokens:', error);
       // Fallback: character-based estimation
@@ -264,7 +251,18 @@ export class DefaultRequestTokenizer implements RequestTokenizer {
           otherContents,
         );
       }
+      return;
     }
+
+    // Some request shapes (e.g. CountTokensParameters) allow passing parts directly
+    // instead of wrapping them in a { parts: [...] } Content object.
+    this.processPart(
+      content as Part | string,
+      textContents,
+      imageContents,
+      audioContents,
+      otherContents,
+    );
   }
 
   /**
@@ -326,16 +324,4 @@ export class DefaultRequestTokenizer implements RequestTokenizer {
       console.warn('Failed to serialize unknown part type:', error);
     }
   }
-
-  /**
-   * Dispose of resources
-   */
-  async dispose(): Promise<void> {
-    try {
-      // Dispose of tokenizers
-      this.textTokenizer.dispose();
-    } catch (error) {
-      console.warn('Error disposing request tokenizer:', error);
-    }
-  }
 }

packages/core/src/utils/request-tokenizer/textTokenizer.test.ts

@@ -4,36 +4,14 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import { describe, it, expect, vi, beforeEach, afterEach } from 'vitest';
+import { describe, it, expect, beforeEach } from 'vitest';
 import { TextTokenizer } from './textTokenizer.js';
 
-// Mock tiktoken at the top level with hoisted functions
-const mockEncode = vi.hoisted(() => vi.fn());
-const mockFree = vi.hoisted(() => vi.fn());
-const mockGetEncoding = vi.hoisted(() => vi.fn());
-
-vi.mock('tiktoken', () => ({
-  get_encoding: mockGetEncoding,
-}));
-
 describe('TextTokenizer', () => {
   let tokenizer: TextTokenizer;
-  let consoleWarnSpy: ReturnType<typeof vi.spyOn>;
 
   beforeEach(() => {
-    vi.resetAllMocks();
-    consoleWarnSpy = vi.spyOn(console, 'warn').mockImplementation(() => {});
-
-    // Default mock implementation
-    mockGetEncoding.mockReturnValue({
-      encode: mockEncode,
-      free: mockFree,
-    });
-  });
-
-  afterEach(() => {
-    vi.restoreAllMocks();
-    tokenizer?.dispose();
+    tokenizer = new TextTokenizer();
   });
 
   describe('constructor', () => {
@@ -42,17 +20,14 @@ describe('TextTokenizer', () => {
       expect(tokenizer).toBeInstanceOf(TextTokenizer);
     });
 
-    it('should create tokenizer with custom encoding', () => {
-      tokenizer = new TextTokenizer('gpt2');
+    it('should create tokenizer with custom encoding (for backward compatibility)', () => {
+      tokenizer = new TextTokenizer();
       expect(tokenizer).toBeInstanceOf(TextTokenizer);
+      // Note: encoding name is accepted but not used
     });
   });
 
   describe('calculateTokens', () => {
-    beforeEach(() => {
-      tokenizer = new TextTokenizer();
-    });
-
     it('should return 0 for empty text', async () => {
       const result = await tokenizer.calculateTokens('');
       expect(result).toBe(0);
@@ -69,99 +44,77 @@ describe('TextTokenizer', () => {
       expect(result2).toBe(0);
     });
 
-    it('should calculate tokens using tiktoken when available', async () => {
-      const testText = 'Hello, world!';
-      const mockTokens = [1, 2, 3, 4, 5]; // 5 tokens
-      mockEncode.mockReturnValue(mockTokens);
-
+    it('should calculate tokens using character-based estimation for ASCII text', async () => {
+      const testText = 'Hello, world!'; // 13 ASCII chars
       const result = await tokenizer.calculateTokens(testText);
+      // 13 / 4 = 3.25 -> ceil = 4
+      expect(result).toBe(4);
+    });
 
-      expect(mockGetEncoding).toHaveBeenCalledWith('cl100k_base');
-      expect(mockEncode).toHaveBeenCalledWith(testText);
+    it('should calculate tokens for code (ASCII)', async () => {
+      const code = 'function test() { return 42; }'; // 30 ASCII chars
+      const result = await tokenizer.calculateTokens(code);
+      // 30 / 4 = 7.5 -> ceil = 8
+      expect(result).toBe(8);
+    });
+
+    it('should calculate tokens for non-ASCII text (CJK)', async () => {
+      const unicodeText = '你好世界'; // 4 non-ASCII chars
+      const result = await tokenizer.calculateTokens(unicodeText);
+      // 4 * 1.1 = 4.4 -> ceil = 5
       expect(result).toBe(5);
     });
 
-    it('should use fallback calculation when tiktoken fails to load', async () => {
-      mockGetEncoding.mockImplementation(() => {
-        throw new Error('Failed to load tiktoken');
-      });
-
-      const testText = 'Hello, world!'; // 13 characters
-      const result = await tokenizer.calculateTokens(testText);
-
-      expect(consoleWarnSpy).toHaveBeenCalledWith(
-        'Failed to load tiktoken with encoding cl100k_base:',
-        expect.any(Error),
-      );
-      // Fallback: Math.ceil(13 / 4) = 4
+    it('should calculate tokens for mixed ASCII and non-ASCII text', async () => {
+      const mixedText = 'Hello 世界'; // 6 ASCII + 2 non-ASCII
+      const result = await tokenizer.calculateTokens(mixedText);
+      // (6 / 4) + (2 * 1.1) = 1.5 + 2.2 = 3.7 -> ceil = 4
       expect(result).toBe(4);
     });
 
-    it('should use fallback calculation when encoding fails', async () => {
-      mockEncode.mockImplementation(() => {
-        throw new Error('Encoding failed');
-      });
-
-      const testText = 'Hello, world!'; // 13 characters
-      const result = await tokenizer.calculateTokens(testText);
-
-      expect(consoleWarnSpy).toHaveBeenCalledWith(
-        'Error encoding text with tiktoken:',
-        expect.any(Error),
-      );
-      // Fallback: Math.ceil(13 / 4) = 4
-      expect(result).toBe(4);
+    it('should calculate tokens for emoji', async () => {
+      const emojiText = '🌍'; // 2 UTF-16 code units (non-ASCII)
+      const result = await tokenizer.calculateTokens(emojiText);
+      // 2 * 1.1 = 2.2 -> ceil = 3
+      expect(result).toBe(3);
     });
 
     it('should handle very long text', async () => {
-      const longText = 'a'.repeat(10000);
-      const mockTokens = new Array(2500); // 2500 tokens
-      mockEncode.mockReturnValue(mockTokens);
-
+      const longText = 'a'.repeat(10000); // 10000 ASCII chars
       const result = await tokenizer.calculateTokens(longText);
-
+      // 10000 / 4 = 2500 -> ceil = 2500
       expect(result).toBe(2500);
     });
 
-    it('should handle unicode characters', async () => {
-      const unicodeText = '你好世界 🌍';
-      const mockTokens = [1, 2, 3, 4, 5, 6];
-      mockEncode.mockReturnValue(mockTokens);
-
-      const result = await tokenizer.calculateTokens(unicodeText);
-
-      expect(result).toBe(6);
+    it('should handle text with only whitespace', async () => {
+      const whitespaceText = '   \n\t  '; // 7 ASCII chars
+      const result = await tokenizer.calculateTokens(whitespaceText);
+      // 7 / 4 = 1.75 -> ceil = 2
+      expect(result).toBe(2);
     });
 
-    it('should use custom encoding when specified', async () => {
-      tokenizer = new TextTokenizer('gpt2');
-      const testText = 'Hello, world!';
-      const mockTokens = [1, 2, 3];
-      mockEncode.mockReturnValue(mockTokens);
+    it('should handle special characters and symbols', async () => {
+      const specialText = '!@#$%^&*()_+-=[]{}|;:,.<>?'; // 26 ASCII chars
+      const result = await tokenizer.calculateTokens(specialText);
+      // 26 / 4 = 6.5 -> ceil = 7
+      expect(result).toBe(7);
+    });
 
-      const result = await tokenizer.calculateTokens(testText);
-
-      expect(mockGetEncoding).toHaveBeenCalledWith('gpt2');
-      expect(result).toBe(3);
+    it('should handle very short text', async () => {
+      const result = await tokenizer.calculateTokens('a');
+      // 1 / 4 = 0.25 -> ceil = 1
+      expect(result).toBe(1);
     });
   });
 
   describe('calculateTokensBatch', () => {
-    beforeEach(() => {
-      tokenizer = new TextTokenizer();
-    });
-
     it('should process multiple texts and return token counts', async () => {
       const texts = ['Hello', 'world', 'test'];
-      mockEncode
-        .mockReturnValueOnce([1, 2]) // 2 tokens for 'Hello'
-        .mockReturnValueOnce([3, 4, 5]) // 3 tokens for 'world'
-        .mockReturnValueOnce([6]); // 1 token for 'test'
-
       const result = await tokenizer.calculateTokensBatch(texts);
-
-      expect(result).toEqual([2, 3, 1]);
-      expect(mockEncode).toHaveBeenCalledTimes(3);
+      // 'Hello' = 5 / 4 = 1.25 -> ceil = 2
+      // 'world' = 5 / 4 = 1.25 -> ceil = 2
+      // 'test' = 4 / 4 = 1 -> ceil = 1
+      expect(result).toEqual([2, 2, 1]);
     });
 
     it('should handle empty array', async () => {
@@ -171,177 +124,156 @@ describe('TextTokenizer', () => {
 
     it('should handle array with empty strings', async () => {
       const texts = ['', 'hello', ''];
-      mockEncode.mockReturnValue([1, 2, 3]); // Only called for 'hello'
-
       const result = await tokenizer.calculateTokensBatch(texts);
-
-      expect(result).toEqual([0, 3, 0]);
-      expect(mockEncode).toHaveBeenCalledTimes(1);
-      expect(mockEncode).toHaveBeenCalledWith('hello');
+      // '' = 0
+      // 'hello' = 5 / 4 = 1.25 -> ceil = 2
+      // '' = 0
+      expect(result).toEqual([0, 2, 0]);
     });
 
-    it('should use fallback calculation when tiktoken fails to load', async () => {
-      mockGetEncoding.mockImplementation(() => {
-        throw new Error('Failed to load tiktoken');
-      });
-
-      const texts = ['Hello', 'world']; // 5 and 5 characters
+    it('should handle mixed ASCII and non-ASCII texts', async () => {
+      const texts = ['Hello', '世界', 'Hello 世界'];
       const result = await tokenizer.calculateTokensBatch(texts);
-
-      expect(consoleWarnSpy).toHaveBeenCalledWith(
-        'Failed to load tiktoken with encoding cl100k_base:',
-        expect.any(Error),
-      );
-      // Fallback: Math.ceil(5/4) = 2 for both
-      expect(result).toEqual([2, 2]);
-    });
-
-    it('should use fallback calculation when encoding fails during batch processing', async () => {
-      mockEncode.mockImplementation(() => {
-        throw new Error('Encoding failed');
-      });
-
-      const texts = ['Hello', 'world']; // 5 and 5 characters
-      const result = await tokenizer.calculateTokensBatch(texts);
-
-      expect(consoleWarnSpy).toHaveBeenCalledWith(
-        'Error encoding texts with tiktoken:',
-        expect.any(Error),
-      );
-      // Fallback: Math.ceil(5/4) = 2 for both
-      expect(result).toEqual([2, 2]);
+      // 'Hello' = 5 / 4 = 1.25 -> ceil = 2
+      // '世界' = 2 * 1.1 = 2.2 -> ceil = 3
+      // 'Hello 世界' = (6/4) + (2*1.1) = 1.5 + 2.2 = 3.7 -> ceil = 4
+      expect(result).toEqual([2, 3, 4]);
     });
 
     it('should handle null and undefined values in batch', async () => {
       const texts = [null, 'hello', undefined, 'world'] as unknown as string[];
-      mockEncode
-        .mockReturnValueOnce([1, 2, 3]) // 3 tokens for 'hello'
-        .mockReturnValueOnce([4, 5]); // 2 tokens for 'world'
-
       const result = await tokenizer.calculateTokensBatch(texts);
+      // null = 0
+      // 'hello' = 5 / 4 = 1.25 -> ceil = 2
+      // undefined = 0
+      // 'world' = 5 / 4 = 1.25 -> ceil = 2
+      expect(result).toEqual([0, 2, 0, 2]);
+    });
 
-      expect(result).toEqual([0, 3, 0, 2]);
+    it('should process large batches efficiently', async () => {
+      const texts = Array.from({ length: 1000 }, (_, i) => `text${i}`);
+      const result = await tokenizer.calculateTokensBatch(texts);
+      expect(result).toHaveLength(1000);
+      // Verify results are reasonable
+      result.forEach((count) => {
+        expect(count).toBeGreaterThan(0);
+        expect(count).toBeLessThan(10); // 'textNNN' should be less than 10 tokens
+      });
     });
   });
 
-  describe('dispose', () => {
-    beforeEach(() => {
-      tokenizer = new TextTokenizer();
+  describe('backward compatibility', () => {
+    it('should accept encoding parameter in constructor', () => {
+      const tokenizer1 = new TextTokenizer();
+      const tokenizer2 = new TextTokenizer();
+      const tokenizer3 = new TextTokenizer();
+
+      expect(tokenizer1).toBeInstanceOf(TextTokenizer);
+      expect(tokenizer2).toBeInstanceOf(TextTokenizer);
+      expect(tokenizer3).toBeInstanceOf(TextTokenizer);
     });
 
-    it('should free tiktoken encoding when disposing', async () => {
-      // Initialize the encoding by calling calculateTokens
-      await tokenizer.calculateTokens('test');
+    it('should produce same results regardless of encoding parameter', async () => {
+      const text = 'Hello, world!';
+      const tokenizer1 = new TextTokenizer();
+      const tokenizer2 = new TextTokenizer();
+      const tokenizer3 = new TextTokenizer();
 
-      tokenizer.dispose();
+      const result1 = await tokenizer1.calculateTokens(text);
+      const result2 = await tokenizer2.calculateTokens(text);
+      const result3 = await tokenizer3.calculateTokens(text);
 
-      expect(mockFree).toHaveBeenCalled();
+      // All should use character-based estimation, ignoring encoding parameter
+      expect(result1).toBe(result2);
+      expect(result2).toBe(result3);
+      expect(result1).toBe(4); // 13 / 4 = 3.25 -> ceil = 4
     });
 
-    it('should handle disposal when encoding is not initialized', () => {
-      expect(() => tokenizer.dispose()).not.toThrow();
-      expect(mockFree).not.toHaveBeenCalled();
+    it('should maintain async interface for calculateTokens', async () => {
+      const result = tokenizer.calculateTokens('test');
+      expect(result).toBeInstanceOf(Promise);
+      await expect(result).resolves.toBe(1);
     });
 
-    it('should handle disposal when encoding is null', async () => {
-      // Force encoding to be null by making tiktoken fail
-      mockGetEncoding.mockImplementation(() => {
-        throw new Error('Failed to load');
-      });
-
-      await tokenizer.calculateTokens('test');
-
-      expect(() => tokenizer.dispose()).not.toThrow();
-      expect(mockFree).not.toHaveBeenCalled();
-    });
-
-    it('should handle errors during disposal gracefully', async () => {
-      await tokenizer.calculateTokens('test');
-
-      mockFree.mockImplementation(() => {
-        throw new Error('Free failed');
-      });
-
-      tokenizer.dispose();
-
-      expect(consoleWarnSpy).toHaveBeenCalledWith(
-        'Error freeing tiktoken encoding:',
-        expect.any(Error),
-      );
-    });
-
-    it('should allow multiple calls to dispose', async () => {
-      await tokenizer.calculateTokens('test');
-
-      tokenizer.dispose();
-      tokenizer.dispose(); // Second call should not throw
-
-      expect(mockFree).toHaveBeenCalledTimes(1);
-    });
-  });
-
-  describe('lazy initialization', () => {
-    beforeEach(() => {
-      tokenizer = new TextTokenizer();
-    });
-
-    it('should not initialize tiktoken until first use', () => {
-      expect(mockGetEncoding).not.toHaveBeenCalled();
-    });
-
-    it('should initialize tiktoken on first calculateTokens call', async () => {
-      await tokenizer.calculateTokens('test');
-      expect(mockGetEncoding).toHaveBeenCalledTimes(1);
-    });
-
-    it('should not reinitialize tiktoken on subsequent calls', async () => {
-      await tokenizer.calculateTokens('test1');
-      await tokenizer.calculateTokens('test2');
-
-      expect(mockGetEncoding).toHaveBeenCalledTimes(1);
-    });
-
-    it('should initialize tiktoken on first calculateTokensBatch call', async () => {
-      await tokenizer.calculateTokensBatch(['test']);
-      expect(mockGetEncoding).toHaveBeenCalledTimes(1);
+    it('should maintain async interface for calculateTokensBatch', async () => {
+      const result = tokenizer.calculateTokensBatch(['test']);
+      expect(result).toBeInstanceOf(Promise);
+      await expect(result).resolves.toEqual([1]);
     });
   });
 
   describe('edge cases', () => {
-    beforeEach(() => {
-      tokenizer = new TextTokenizer();
-    });
-
-    it('should handle very short text', async () => {
-      const result = await tokenizer.calculateTokens('a');
-
-      if (mockGetEncoding.mock.calls.length > 0) {
-        // If tiktoken was called, use its result
-        expect(mockEncode).toHaveBeenCalledWith('a');
-      } else {
-        // If tiktoken failed, should use fallback: Math.ceil(1/4) = 1
-        expect(result).toBe(1);
-      }
-    });
-
-    it('should handle text with only whitespace', async () => {
-      const whitespaceText = '   \n\t  ';
-      const mockTokens = [1];
-      mockEncode.mockReturnValue(mockTokens);
-
-      const result = await tokenizer.calculateTokens(whitespaceText);
-
+    it('should handle text with only newlines', async () => {
+      const text = '\n\n\n'; // 3 ASCII chars
+      const result = await tokenizer.calculateTokens(text);
+      // 3 / 4 = 0.75 -> ceil = 1
       expect(result).toBe(1);
     });
 
-    it('should handle special characters and symbols', async () => {
-      const specialText = '!@#$%^&*()_+-=[]{}|;:,.<>?';
-      const mockTokens = new Array(10);
-      mockEncode.mockReturnValue(mockTokens);
+    it('should handle text with tabs', async () => {
+      const text = '\t\t\t\t'; // 4 ASCII chars
+      const result = await tokenizer.calculateTokens(text);
+      // 4 / 4 = 1 -> ceil = 1
+      expect(result).toBe(1);
+    });
 
-      const result = await tokenizer.calculateTokens(specialText);
+    it('should handle surrogate pairs correctly', async () => {
+      // Character outside BMP (Basic Multilingual Plane)
+      const text = '𝕳𝖊𝖑𝖑𝖔'; // Mathematical bold letters (2 UTF-16 units each)
+      const result = await tokenizer.calculateTokens(text);
+      // Each character is 2 UTF-16 units, all non-ASCII
+      // Total: 10 non-ASCII units
+      // 10 * 1.1 = 11 -> ceil = 11
+      expect(result).toBe(11);
+    });
 
-      expect(result).toBe(10);
+    it('should handle combining characters', async () => {
+      // e + combining acute accent
+      const text = 'e\u0301'; // 2 chars: 'e' (ASCII) + combining acute (non-ASCII)
+      const result = await tokenizer.calculateTokens(text);
+      // ASCII: 1 / 4 = 0.25
+      // Non-ASCII: 1 * 1.1 = 1.1
+      // Total: 0.25 + 1.1 = 1.35 -> ceil = 2
+      expect(result).toBe(2);
+    });
+
+    it('should handle accented characters', async () => {
+      const text = 'café'; // 'caf' = 3 ASCII, 'é' = 1 non-ASCII
+      const result = await tokenizer.calculateTokens(text);
+      // ASCII: 3 / 4 = 0.75
+      // Non-ASCII: 1 * 1.1 = 1.1
+      // Total: 0.75 + 1.1 = 1.85 -> ceil = 2
+      expect(result).toBe(2);
+    });
+
+    it('should handle various unicode scripts', async () => {
+      const cyrillic = 'Привет'; // 6 non-ASCII chars
+      const arabic = 'مرحبا'; // 5 non-ASCII chars
+      const japanese = 'こんにちは'; // 5 non-ASCII chars
+
+      const result1 = await tokenizer.calculateTokens(cyrillic);
+      const result2 = await tokenizer.calculateTokens(arabic);
+      const result3 = await tokenizer.calculateTokens(japanese);
+
+      // All should use 1.1 tokens per char
+      expect(result1).toBe(7); // 6 * 1.1 = 6.6 -> ceil = 7
+      expect(result2).toBe(6); // 5 * 1.1 = 5.5 -> ceil = 6
+      expect(result3).toBe(6); // 5 * 1.1 = 5.5 -> ceil = 6
+    });
+  });
+
+  describe('large inputs', () => {
+    it('should handle very long text', async () => {
+      const longText = 'a'.repeat(200000); // 200k characters
+      const result = await tokenizer.calculateTokens(longText);
+      expect(result).toBe(50000); // 200000 / 4
+    });
+
+    it('should handle large batches', async () => {
+      const texts = Array.from({ length: 5000 }, () => 'Hello, world!');
+      const result = await tokenizer.calculateTokensBatch(texts);
+      expect(result).toHaveLength(5000);
+      expect(result[0]).toBe(4);
     });
   });
 });

packages/core/src/utils/request-tokenizer/textTokenizer.ts

@@ -4,94 +4,55 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import type { TiktokenEncoding, Tiktoken } from 'tiktoken';
-import { get_encoding } from 'tiktoken';
-
 /**
- * Text tokenizer for calculating text tokens using tiktoken
+ * Text tokenizer for calculating text tokens using character-based estimation.
+ *
+ * Uses a lightweight character-based approach that is "good enough" for
+ * guardrail features like sessionTokenLimit.
+ *
+ * Algorithm:
+ * - ASCII characters: 0.25 tokens per char (4 chars = 1 token)
+ * - Non-ASCII characters: 1.1 tokens per char (conservative for CJK, emoji, etc.)
  */
 export class TextTokenizer {
-  private encoding: Tiktoken | null = null;
-  private encodingName: string;
-
-  constructor(encodingName: string = 'cl100k_base') {
-    this.encodingName = encodingName;
-  }
-
-  /**
-   * Initialize the tokenizer (lazy loading)
-   */
-  private async ensureEncoding(): Promise<void> {
-    if (this.encoding) return;
-
-    try {
-      // Use type assertion since we know the encoding name is valid
-      this.encoding = get_encoding(this.encodingName as TiktokenEncoding);
-    } catch (error) {
-      console.warn(
-        `Failed to load tiktoken with encoding ${this.encodingName}:`,
-        error,
-      );
-      this.encoding = null;
-    }
-  }
-
   /**
    * Calculate tokens for text content
+   *
+   * @param text - The text to estimate tokens for
+   * @returns The estimated token count
    */
   async calculateTokens(text: string): Promise<number> {
-    if (!text) return 0;
-
-    await this.ensureEncoding();
-
-    if (this.encoding) {
-      try {
-        return this.encoding.encode(text).length;
-      } catch (error) {
-        console.warn('Error encoding text with tiktoken:', error);
-      }
-    }
-
-    // Fallback: rough approximation using character count
-    // This is a conservative estimate: 1 token ≈ 4 characters for most languages
-    return Math.ceil(text.length / 4);
+    return this.calculateTokensSync(text);
   }
 
   /**
-   * Calculate tokens for multiple text strings in parallel
+   * Calculate tokens for multiple text strings
+   *
+   * @param texts - Array of text strings to estimate tokens for
+   * @returns Array of token counts corresponding to each input text
    */
   async calculateTokensBatch(texts: string[]): Promise<number[]> {
-    await this.ensureEncoding();
-
-    if (this.encoding) {
-      try {
-        return texts.map((text) => {
-          if (!text) return 0;
-          // this.encoding may be null, add a null check to satisfy lint
-          return this.encoding ? this.encoding.encode(text).length : 0;
-        });
-      } catch (error) {
-        console.warn('Error encoding texts with tiktoken:', error);
-        // In case of error, return fallback estimation for all texts
-        return texts.map((text) => Math.ceil((text || '').length / 4));
-      }
-    }
-
-    // Fallback for batch processing
-    return texts.map((text) => Math.ceil((text || '').length / 4));
+    return texts.map((text) => this.calculateTokensSync(text));
   }
 
-  /**
-   * Dispose of resources
-   */
-  dispose(): void {
-    if (this.encoding) {
-      try {
-        this.encoding.free();
-      } catch (error) {
-        console.warn('Error freeing tiktoken encoding:', error);
-      }
-      this.encoding = null;
+  private calculateTokensSync(text: string): number {
+    if (!text || text.length === 0) {
+      return 0;
     }
+
+    let asciiChars = 0;
+    let nonAsciiChars = 0;
+
+    for (let i = 0; i < text.length; i++) {
+      const charCode = text.charCodeAt(i);
+      if (charCode < 128) {
+        asciiChars++;
+      } else {
+        nonAsciiChars++;
+      }
+    }
+
+    const tokens = asciiChars / 4 + nonAsciiChars * 1.1;
+    return Math.ceil(tokens);
   }
 }

packages/core/src/utils/request-tokenizer/types.ts

@@ -4,8 +4,6 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
-import type { CountTokensParameters } from '@google/genai';
-
 /**
  * Token calculation result for different content types
  */
@@ -23,14 +21,6 @@ export interface TokenCalculationResult {
   processingTime: number;
 }
 
-/**
- * Configuration for token calculation
- */
-export interface TokenizerConfig {
-  /** Custom text tokenizer encoding (defaults to cl100k_base) */
-  textEncoding?: string;
-}
-
 /**
  * Image metadata extracted from base64 data
  */
@@ -44,21 +34,3 @@ export interface ImageMetadata {
   /** Size of the base64 data in bytes */
   dataSize: number;
 }
-
-/**
- * Request tokenizer interface
- */
-export interface RequestTokenizer {
-  /**
-   * Calculate tokens for a request
-   */
-  calculateTokens(
-    request: CountTokensParameters,
-    config?: TokenizerConfig,
-  ): Promise<TokenCalculationResult>;
-
-  /**
-   * Dispose of resources (worker threads, etc.)
-   */
-  dispose(): Promise<void>;
-}

packages/sdk-typescript/package.json

@@ -46,8 +46,7 @@
   },
   "dependencies": {
     "@modelcontextprotocol/sdk": "^1.25.1",
-    "zod": "^3.25.0",
-    "tiktoken": "^1.0.21"
+    "zod": "^3.25.0"
   },
   "devDependencies": {
     "@types/node": "^20.14.0",

packages/test-utils/package.json

@@ -1,6 +1,6 @@
 {
   "name": "@qwen-code/qwen-code-test-utils",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "private": true,
   "main": "src/index.ts",
   "license": "Apache-2.0",

packages/vscode-ide-companion/package.json

@@ -2,7 +2,7 @@
   "name": "qwen-code-vscode-ide-companion",
   "displayName": "Qwen Code Companion",
   "description": "Enable Qwen Code with direct access to your VS Code workspace.",
-  "version": "0.7.1",
+  "version": "0.8.0-preview.0",
   "publisher": "qwenlm",
   "icon": "assets/icon.png",
   "repository": {

packages/vscode-ide-companion/src/constants/acpSchema.ts

@@ -23,3 +23,23 @@ export const CLIENT_METHODS = {
   session_request_permission: 'session/request_permission',
   session_update: 'session/update',
 } as const;
+
+export const ACP_ERROR_CODES = {
+  // Parse error: invalid JSON received by server.
+  PARSE_ERROR: -32700,
+  // Invalid request: JSON is not a valid Request object.
+  INVALID_REQUEST: -32600,
+  // Method not found: method does not exist or is unavailable.
+  METHOD_NOT_FOUND: -32601,
+  // Invalid params: invalid method parameter(s).
+  INVALID_PARAMS: -32602,
+  // Internal error: implementation-defined server error.
+  INTERNAL_ERROR: -32603,
+  // Authentication required: must authenticate before operation.
+  AUTH_REQUIRED: -32000,
+  // Resource not found: e.g. missing file.
+  RESOURCE_NOT_FOUND: -32002,
+} as const;
+
+export type AcpErrorCode =
+  (typeof ACP_ERROR_CODES)[keyof typeof ACP_ERROR_CODES];

packages/vscode-ide-companion/src/ide-server.ts

@@ -28,6 +28,7 @@ import * as os from 'node:os';
 import type { z } from 'zod';
 import type { DiffManager } from './diff-manager.js';
 import { OpenFilesManager } from './open-files-manager.js';
+import { ACP_ERROR_CODES } from './constants/acpSchema.js';
 
 class CORSError extends Error {
   constructor(message: string) {
@@ -264,7 +265,7 @@ export class IDEServer {
           res.status(400).json({
             jsonrpc: '2.0',
             error: {
-              code: -32000,
+              code: ACP_ERROR_CODES.AUTH_REQUIRED,
               message:
                 'Bad Request: No valid session ID provided for non-initialize request.',
             },
@@ -283,7 +284,7 @@ export class IDEServer {
             res.status(500).json({
               jsonrpc: '2.0' as const,
               error: {
-                code: -32603,
+                code: ACP_ERROR_CODES.INTERNAL_ERROR,
                 message: 'Internal server error',
               },
               id: null,

packages/vscode-ide-companion/src/services/acpConnection.ts

@@ -5,6 +5,7 @@
  */
 
 import { JSONRPC_VERSION } from '../types/acpTypes.js';
+import { ACP_ERROR_CODES } from '../constants/acpSchema.js';
 import type {
   AcpMessage,
   AcpPermissionRequest,
@@ -232,12 +233,34 @@ export class AcpConnection {
         })
         .catch((error) => {
           if ('id' in message && typeof message.id === 'number') {
+            const errorMessage =
+              error instanceof Error
+                ? error.message
+                : typeof error === 'object' &&
+                    error !== null &&
+                    'message' in error &&
+                    typeof (error as { message: unknown }).message === 'string'
+                  ? (error as { message: string }).message
+                  : String(error);
+
+            let errorCode: number = ACP_ERROR_CODES.INTERNAL_ERROR;
+            const errorCodeValue =
+              typeof error === 'object' && error !== null && 'code' in error
+                ? (error as { code?: unknown }).code
+                : undefined;
+
+            if (typeof errorCodeValue === 'number') {
+              errorCode = errorCodeValue;
+            } else if (errorCodeValue === 'ENOENT') {
+              errorCode = ACP_ERROR_CODES.RESOURCE_NOT_FOUND;
+            }
+
             this.messageHandler.sendResponseMessage(this.child, {
               jsonrpc: JSONRPC_VERSION,
               id: message.id,
               error: {
-                code: -32603,
-                message: error instanceof Error ? error.message : String(error),
+                code: errorCode,
+                message: errorMessage,
               },
             });
           }

packages/vscode-ide-companion/src/services/acpFileHandler.ts

@@ -66,6 +66,11 @@ export class AcpFileHandler {
       const errorMsg = error instanceof Error ? error.message : String(error);
       console.error(`[ACP] Failed to read file ${params.path}:`, errorMsg);
 
+      const nodeError = error as NodeJS.ErrnoException;
+      if (nodeError?.code === 'ENOENT') {
+        throw error;
+      }
+
       throw new Error(`Failed to read file '${params.path}': ${errorMsg}`);
     }
   }

packages/vscode-ide-companion/src/utils/authErrors.ts

@@ -4,9 +4,11 @@
  * SPDX-License-Identifier: Apache-2.0
  */
 
+import { ACP_ERROR_CODES } from '../constants/acpSchema.js';
+
 const AUTH_ERROR_PATTERNS = [
   'Authentication required', // Standard authentication request message
-  '(code: -32000)', // RPC error code -32000 indicates authentication failure
+  `(code: ${ACP_ERROR_CODES.AUTH_REQUIRED})`, // RPC error code indicates auth failure
   'Unauthorized', // HTTP unauthorized error
   'Invalid token', // Invalid token
   'Session expired', // Session expired

packages/vscode-ide-companion/src/webview/handlers/SessionMessageHandler.ts

@@ -8,6 +8,9 @@ import * as vscode from 'vscode';
 import { BaseMessageHandler } from './BaseMessageHandler.js';
 import type { ChatMessage } from '../../services/qwenAgentManager.js';
 import type { ApprovalModeValue } from '../../types/approvalModeValueTypes.js';
+import { ACP_ERROR_CODES } from '../../constants/acpSchema.js';
+
+const AUTH_REQUIRED_CODE_PATTERN = `(code: ${ACP_ERROR_CODES.AUTH_REQUIRED})`;
 
 /**
  * Session message handler
@@ -355,7 +358,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
           createErr instanceof Error ? createErr.message : String(createErr);
         if (
           errorMsg.includes('Authentication required') ||
-          errorMsg.includes('(code: -32000)')
+          errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN)
         ) {
           await this.promptLogin(
             'Your login session has expired or is invalid. Please login again to continue using Qwen Code.',
@@ -421,7 +424,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
         errorMsg.includes('Session not found') ||
         errorMsg.includes('No active ACP session') ||
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token')
       ) {
@@ -512,7 +515,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
       // Check for authentication/session expiration errors
       if (
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token') ||
         errorMsg.includes('No active ACP session')
@@ -622,7 +625,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
         // Check for authentication/session expiration errors
         if (
           errorMsg.includes('Authentication required') ||
-          errorMsg.includes('(code: -32000)') ||
+          errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
           errorMsg.includes('Unauthorized') ||
           errorMsg.includes('Invalid token') ||
           errorMsg.includes('No active ACP session')
@@ -682,7 +685,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
             // Check for authentication/session expiration errors in session creation
             if (
               createErrorMsg.includes('Authentication required') ||
-              createErrorMsg.includes('(code: -32000)') ||
+              createErrorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
               createErrorMsg.includes('Unauthorized') ||
               createErrorMsg.includes('Invalid token') ||
               createErrorMsg.includes('No active ACP session')
@@ -722,7 +725,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
       // Check for authentication/session expiration errors
       if (
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token') ||
         errorMsg.includes('No active ACP session')
@@ -777,7 +780,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
       // Check for authentication/session expiration errors
       if (
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token') ||
         errorMsg.includes('No active ACP session')
@@ -827,7 +830,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
         // Check for authentication/session expiration errors
         if (
           errorMsg.includes('Authentication required') ||
-          errorMsg.includes('(code: -32000)') ||
+          errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
           errorMsg.includes('Unauthorized') ||
           errorMsg.includes('Invalid token') ||
           errorMsg.includes('No active ACP session')
@@ -855,7 +858,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
       // Check for authentication/session expiration errors
       if (
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token') ||
         errorMsg.includes('No active ACP session')
@@ -961,7 +964,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
         // Check for authentication/session expiration errors
         if (
           errorMsg.includes('Authentication required') ||
-          errorMsg.includes('(code: -32000)') ||
+          errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
           errorMsg.includes('Unauthorized') ||
           errorMsg.includes('Invalid token') ||
           errorMsg.includes('No active ACP session')
@@ -989,7 +992,7 @@ export class SessionMessageHandler extends BaseMessageHandler {
       // Check for authentication/session expiration errors
       if (
         errorMsg.includes('Authentication required') ||
-        errorMsg.includes('(code: -32000)') ||
+        errorMsg.includes(AUTH_REQUIRED_CODE_PATTERN) ||
         errorMsg.includes('Unauthorized') ||
         errorMsg.includes('Invalid token') ||
         errorMsg.includes('No active ACP session')

scripts/prepare-package.js

@@ -98,17 +98,6 @@ console.log('Creating package.json for distribution...');
 const rootPackageJson = JSON.parse(
   fs.readFileSync(path.join(rootDir, 'package.json'), 'utf-8'),
 );
-const corePackageJson = JSON.parse(
-  fs.readFileSync(
-    path.join(rootDir, 'packages', 'core', 'package.json'),
-    'utf-8',
-  ),
-);
-
-const runtimeDependencies = {};
-if (corePackageJson.dependencies?.tiktoken) {
-  runtimeDependencies.tiktoken = corePackageJson.dependencies.tiktoken;
-}
 
 // Create a clean package.json for the published package
 const distPackageJson = {
@@ -124,7 +113,7 @@ const distPackageJson = {
   },
   files: ['cli.js', 'vendor', '*.sb', 'README.md', 'LICENSE', 'locales'],
   config: rootPackageJson.config,
-  dependencies: runtimeDependencies,
+  dependencies: {},
   optionalDependencies: {
     '@lydell/node-pty': '1.1.0',
     '@lydell/node-pty-darwin-arm64': '1.1.0',