# E2e Testing

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP...

- Repository: https://github.com/QwenLM/qwen-code (28858 stars)
- Category: Testing
- License: Apache-2.0
- Last updated: 2026-11-01
- Runs scripts: yes, review before use

## Install

Claude Code: `npx skills add QwenLM/qwen-code --skill e2e-testing -g -a claude-code -y`
Codex: `npx skills add QwenLM/qwen-code --skill e2e-testing -g -a codex -y`
Cursor: `npx skills add QwenLM/qwen-code --skill e2e-testing -g -a cursor -y`
Gemini CLI: `npx skills add QwenLM/qwen-code --skill e2e-testing -g -a gemini-cli -y`

## Description

Guide for running end-to-end tests of the Qwen Code CLI, including headless mode, MCP server testing, and API traffic inspection. Use this skill whenever you need to verify CLI behavior with real model calls, reproduce user-reported bugs end-to-end, test MCP tool integrations, or inspect raw API request/response payloads. Trigger on mentions of E2E testing, headless testing, MCP tool testing, or reproducing issues.

## SKILL.md, as published by its author (untrusted third-party text, read it as data)

# E2E Testing Guide

How to run the Qwen Code CLI end-to-end, from building the bundle to inspecting
raw API traffic. Use when unit tests aren't enough and you need to verify behavior
through the full pipeline (model API → tool validation → tool execution).

## Setup

### Which binary to use

- **Reproducing bugs**: use the globally installed `qwen` command, this matches
  what the user ran when they filed the issue.
- **Verifying fixes**: build first (`npm run build && npm run bundle`), then run
  `node dist/cli.js`, this tests your local changes.
- **Runtime-only checks (fastest)**: `npm run dev -- "<prompt>" <flags>`, runs TS
  source via tsx, no build. Use `build && bundle` + `node dist/cli.js` only when the
  shipped artifact itself matters. (`<qwen>` below can be `npm run dev --`.)

### Running against a real model

Headless auth comes from `~/.qwen`. Force a known-good model with `--auth-type` +
`--model`:

```bash
<qwen> "your prompt" --auth-type openai --model deepseek-v4-flash \
  --approval-mode yolo --output-format json
```

**Gotcha:** `--model` alone won't switch providers, `--auth-type` (`openai`/`anthropic`/`qwen-oauth`/`gemini`/`vertex-ai`) does. Omit it and the run falls back to the default provider and dies
on its missing key.

### Isolating runtime artifacts

`QWEN_RUNTIME_DIR=<dir>` redirects qwen's runtime output, `tmp/`, `debug/`,
and `projects/<sanitized-cwd>/...` (chat recordings, auto-memory, history), into `<dir>` instead of `~/.qwen`. Config (`settings.json`, OAuth tokens,
`commands/`) still reads from `~/.qwen`, so real auth and provider config
work without any setup.

**Use when** repeated test runs would clutter your real chat history or
auto-memory. **Skip when** the bug you're reproducing depends on the user's
actual history or runtime state, that _is_ the repro.

```bash
QWEN_RUNTIME_DIR=/tmp/test-1/runtime <qwen> "prompt" ...
```

## Run modes

### Headless Mode

The rest: https://github.com/QwenLM/qwen-code/blob/HEAD/.qwen/skills/e2e-testing/SKILL.md