> For the complete documentation index, see [llms.txt](https://modelmesh.gitbook.io/cline-zhong-wen-ban-docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://modelmesh.gitbook.io/cline-zhong-wen-ban-docs/getting-started/context-management.md).
# Context Management
Context is key to getting the most out of Cline
> 💡 **Quick Reference**
>
> * Context = The information Cline knows about your project
> * Context Window = How much information Cline can hold at once
> * Use context files to maintain project knowledge
> * Reset when the context window gets full
### Understanding Context & Context Windows
In a world of infinite context, the context window is what Cline currently has available
Think of working with Cline like collaborating with a thorough, proactive teammate:
#### How Context is Built
Cline actively builds context in two ways:
1. **Automatic Context Gathering (i.e. Cline-driven)**
* Proactively reads related files
* Explores project structure
* Analyzes patterns and relationships
* Maps dependencies and imports
* Asks clarifying questions
2. **User-Guided Context**
* Share specific files
* Provide documentation
* Answer Cline's questions
* Guide focus areas
* Share design thoughts and requirements
💡 **Key Point**: Cline isn't passive - it actively seeks to understand your project. You can either let it explore or guide its focus, especially in [Plan](https://docs.cline.bot/exploring-clines-tools/plan-and-act-modes-a-guide-to-effective-ai-development) mode.
#### Context & Context Windows
Think of context like a whiteboard you and Cline share:
* **Context** is all the information available:
* What Cline has discovered
* What you've shared
* Your conversation history
* Project requirements
* Previous decisions
* **Context Window** is the size of the whiteboard itself:
* Measured in tokens (1 token ≈ 3/4 of an English word)
* Each model has a fixed size:
* Claude 3.5 Sonnet: 200,000 tokens
* DeepSeek: 64,000 tokens
* When the whiteboard is full, you need to erase (clear context) to write more
* [How Cline manages context under the hood](https://cline.bot/blog/understanding-the-new-context-window-progress-bar-in-cline)
⚠️ **Important**: Having a large context window (like Claude's 200k tokens) doesn't mean you should fill it completely. Just like a cluttered whiteboard, too much information can make it harder to focus on what's important.
### Understanding the Context Window Progress Bar
Cline provides a visual way to monitor your context window usage through a progress bar:
#### Reading the Bar
* ↑ shows input tokens (what you've sent to the LLM)
* ↓ shows output tokens (what the LLM has generated)
* The progress bar visualizes how much of your context window you've used
* The total shows your model's maximum capacity (e.g., 200k for Claude 3.5-Sonnet)
#### When to Watch the Bar
* During long coding sessions
* When working with multiple files
* Before starting complex tasks
* When Cline seems to lose context
💡 **Tip**: Consider starting a fresh session when usage reaches 70-80% to maintain optimal performance.
### Working with Context Files
Context files help maintain understanding across sessions. They serve as documentation specifically designed to help AI assistants understand your project.
**Approaches to Context Files**
1. **Evergreen Project Context (i.e.** [**Memory Bank**](https://docs.cline.bot/improving-your-prompting-skills/custom-instructions-library/cline-memory-bank)**)**
* Living documentation that evolves with your project
* Updated as architecture and patterns emerge
* Example: The Memory Bank pattern maintains files like `techContext.md` and `systemPatterns.md`
* Useful for long-running projects and teams
2. **Task-Specific Context (i.e.** [**Structured Approach**](https://cline.bot/blog/building-advanced-software-with-cline-a-structured-approach)**)**
* Created for specific implementation tasks
* Document requirements, constraints, and decisions
* Example:
Copy
```
# auth-system-implementation.md
## Requirements
- OAuth2 implementation
- Support for Google and GitHub
- Rate limiting on auth endpoints
## Technical Decisions
- Using Passport.js for provider integration
- JWT for session management
- Redis for rate limiting
```
3. **Knowledge Transfer Docs**
* Switch to plan mode and ask Cline to document everything you've accomplished so far, along with the remaining steps, in a markdown file.
* Copy the contents of the markdown file.
* Start a new task using that content as context.
**Using Context Files Effectively**
1. **Structure and Format**
* Use clear, consistent organization
* Include relevant examples
* Link related concepts
* Keep information focused
2. **Maintenance**
* Update after significant changes
* Version control your context files
* Remove outdated information
* Document key decisions
### Practical Tips
1. **Starting New Projects**
* Let Cline explore the codebase
* Answer its questions about structure and patterns
* Consider setting up basic context files
* Document key design decisions
2. **Ongoing Development**
* Update context files with significant changes
* Share relevant documentation
* Use Plan mode for complex discussions
* Start fresh sessions when needed
3. **Team Projects**
* Share common context files (consider using [.clinerules](https://docs.cline.bot/improving-your-prompting-skills/prompting) files in project roots)
* Document architectural decisions
* Maintain consistent patterns
* Keep documentation current
Remember: The goal is to help Cline maintain consistent understanding of your project across sessions.