abbyswag/qwen-code
1
0
Fork 0
mirror of https://github.com/QwenLM/qwen-code.git synced 2025-12-19 09:33:53 +00:00
Code Issues Packages Projects Releases Wiki Activity

feat: update docs

Browse Source
This commit is contained in:
pomelo-nwu
2025-12-12 19:37:36 +08:00
parent f417ace1b0
commit 57df439f43
5 changed files with 25 additions and 144 deletions
Download Patch File Download Diff File Expand all files Collapse all files

3
docs-site/package.json
View File

@@ -8,7 +8,8 @@
"main": "index.js",
"scripts": {
"link": "ln -s ../docs content",
"dev": "next --turbopack",
"clean": "rm -rf .next",
"dev": "npm run clean && next --turbopack",
"test": "echo \"Error: no test specified\" && exit 1"
},
"dependencies": {

1
docs-site/src/app/layout.jsx
View File

@@ -41,6 +41,7 @@ export default async function RootLayout({ children }) {
pageMap={await getPageMap()}
docsRepositoryBase="https://github.com/QwenLM/qwen-code/docs"
footer={footer}
search={false}
// ... Your additional layout options
>
{children}

3
docs/users/features/_meta.ts
View File

@@ -4,9 +4,6 @@ export default {
display: 'hidden',
},
headless: 'Headless Mode',
'welcome-back': {
display: 'hidden',
},
'approval-mode': 'Approval Mode',
'token-caching': 'Token Caching',
mcp: 'MCP',

29
docs/users/features/token-caching.md
View File

@@ -1,14 +1,29 @@
# Token Caching and Cost Optimization
Qwen Code automatically optimizes API costs through token caching when using API key [authentication](/users/configuration/settings#environment-variables-for-api-access) (e.g., OpenAI-compatible providers). This feature reuses previous system instructions and context to reduce the number of tokens processed in subsequent requests.
Qwen Code automatically optimizes API costs through token caching when using API key authentication. This feature stores frequently used content like system instructions and conversation history to reduce the number of tokens processed in subsequent requests.
**Token caching is available for:**
## How It Benefits You
- API key users (Qwen API key)
- Vertex AI users (with project and location setup)
- **Cost reduction**: Less tokens mean lower API costs
- **Faster responses**: Cached content is retrieved more quickly
- **Automatic optimization**: No configuration needed - it works behind the scenes
**Token caching is not available for:**
## Token caching is available for
- OAuth users (Google Personal/Enterprise accounts) - the Code Assist API does not support cached content creation at this time
- API key users (Qwen API key, OpenAI-compatible providers)
You can view your token usage and cached token savings using the `/stats` command. When cached tokens are available, they will be displayed in the stats output.
## Monitoring Your Savings
Use the `/stats` command to see your cached token savings:
- When active, the stats display shows how many tokens were served from cache
- You'll see both the absolute number and percentage of cached tokens
- Example: "10,500 (90.4%) of input tokens were served from the cache, reducing costs."
This information is only displayed when cached tokens are being used, which occurs with API key authentication but not with OAuth authentication.
## Example Stats Display
![Qwen Code Stats Display](https://img.alicdn.com/imgextra/i3/O1CN01F1yzRs1juyZu63jdS_!!6000000004609-2-tps-1038-738.png)
The above image shows an example of the `/stats` command output, highlighting the cached token savings information.

133
docs/users/features/welcome-back.md
View File

@@ -1,133 +0,0 @@
# Welcome Back Feature
The Welcome Back feature helps you seamlessly resume your work by automatically detecting when you return to a project with existing conversation history and offering to continue from where you left off.
## Overview
When you start Qwen Code in a project directory that contains a previously generated project summary (`.qwen/PROJECT_SUMMARY.md`), the Welcome Back dialog will automatically appear, giving you the option to either start fresh or continue your previous conversation.
## How It Works
### Automatic Detection
The Welcome Back feature automatically detects:
- **Project Summary File:** Looks for `.qwen/PROJECT_SUMMARY.md` in your current project directory
- **Conversation History:** Checks if there's meaningful conversation history to resume
- **Settings:** Respects your `enableWelcomeBack` setting (enabled by default)
### Welcome Back Dialog
When a project summary is found, you'll see a dialog with:
- **Last Updated Time:** Shows when the summary was last generated
- **Overall Goal:** Displays the main objective from your previous session
- **Current Plan:** Shows task progress with status indicators:
- `[DONE]` - Completed tasks
- `[IN PROGRESS]` - Currently working on
- `[TODO]` - Planned tasks
- **Task Statistics:** Summary of total tasks, completed, in progress, and pending
### Options
You have two choices when the Welcome Back dialog appears:
1. **Start new chat session**
- Closes the dialog and begins a fresh conversation
- No previous context is loaded
2. **Continue previous conversation**
- Automatically fills the input with: `@.qwen/PROJECT_SUMMARY.md, Based on our previous conversation, Let's continue?`
- Loads the project summary as context for the AI
- Allows you to seamlessly pick up where you left off
## Configuration
### Enable/Disable Welcome Back
You can control the Welcome Back feature through settings:
**Via Settings Dialog:**
1. Run `/settings` in Qwen Code
2. Find "Enable Welcome Back" in the UI category
3. Toggle the setting on/off
**Via Settings File:**
Add to your `.qwen/settings.json`:
```json
{
"enableWelcomeBack": true
}
```
**Settings Locations:**
- **User settings:** `~/.qwen/settings.json` (affects all projects)
- **Project settings:** `.qwen/settings.json` (project-specific)
### Keyboard Shortcuts
- **Escape:** Close the Welcome Back dialog (defaults to "Start new chat session")
## Integration with Other Features
### Project Summary Generation
The Welcome Back feature works seamlessly with the `/summary` command:
1. **Generate Summary:** Use `/summary` to create a project summary
2. **Automatic Detection:** Next time you start Qwen Code in this project, Welcome Back will detect the summary
3. **Resume Work:** Choose to continue and the summary will be loaded as context
### Quit Confirmation
When exiting with `/quit-confirm` and choosing "Generate summary and quit":
1. A project summary is automatically created
2. Next session will trigger the Welcome Back dialog
3. You can seamlessly continue your work
## File Structure
The Welcome Back feature creates and uses:
```
your-project/
├── .qwen/
│ └── PROJECT_SUMMARY.md # Generated project summary
```
### PROJECT_SUMMARY.md Format
The generated summary follows this structure:
```markdown
# Project Summary
## Overall Goal
<!-- Single, concise sentence describing the high-level objective -->
## Key Knowledge
<!-- Crucial facts, conventions, and constraints -->
<!-- Includes: technology choices, architecture decisions, user preferences -->
## Recent Actions
<!-- Summary of significant recent work and outcomes -->
<!-- Includes: accomplishments, discoveries, recent changes -->
## Current Plan
<!-- The current development roadmap and next steps -->
<!-- Uses status markers: [DONE], [IN PROGRESS], [TODO] -->
---
## Summary Metadata
**Update time**: 2025-01-10T15:30:00.000Z
```