mirror of
https://github.com/QwenLM/qwen-code.git
synced 2025-12-19 09:33:53 +00:00
feat: update docs
This commit is contained in:
pomelo-nwu
@@ -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',
|
||||
|
||||
@@ -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
|
||||
|
||||
|
||||
|
||||
The above image shows an example of the `/stats` command output, highlighting the cached token savings information.
|
||||
|
||||
@@ -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
|
||||
```
|
||||
Reference in New Issue
Block a user