mirror of
https://github.com/Palm1r/QodeAssist.git
synced 2025-12-11 20:02:50 -05:00
feat: Update built in roles and docs
This commit is contained in:
Petr Mironychev
@ -159,6 +159,7 @@ For optimal coding assistance, we recommend using these top-tier models:
|
||||
### Additional Configuration
|
||||
|
||||
- **[Agent Roles](docs/agent-roles.md)** - Create AI personas with specialized system prompts
|
||||
- **[Chat Summarization](docs/chat-summarization.md)** - Compress conversations to save context tokens
|
||||
- **[Project Rules](docs/project-rules.md)** - Customize AI behavior for your project
|
||||
- **[Ignoring Files](docs/ignoring-files.md)** - Exclude files from context using `.qodeassistignore`
|
||||
|
||||
@ -196,6 +197,7 @@ Configure in: `Tools → Options → QodeAssist → Code Completion → General
|
||||
- Chat history with auto-save and restore
|
||||
- Token usage monitoring
|
||||
- **[Agent Roles](docs/agent-roles.md)** - Switch between AI personas (Developer, Reviewer, custom roles)
|
||||
- **[Chat Summarization](docs/chat-summarization.md)** - Compress long conversations into AI-generated summaries
|
||||
- **[File Context](docs/file-context.md)** - Attach or link files for better context
|
||||
- Automatic syncing with open editor files (optional)
|
||||
- Extended thinking mode (Claude, other providers in plan) - Enable deeper reasoning for complex tasks
|
||||
|
||||
@ -15,13 +15,16 @@ Agent Roles are reusable system prompt configurations that modify how the AI ass
|
||||
|
||||
## Default Roles
|
||||
|
||||
QodeAssist comes with two built-in roles:
|
||||
QodeAssist comes with three built-in roles:
|
||||
|
||||
### Developer
|
||||
General coding assistance focused on writing clean, maintainable code following industry standards. Best for implementation tasks, debugging, and code explanations.
|
||||
Experienced Qt/C++ developer with a structured workflow: analyze the problem, propose a solution, wait for approval, then implement. Best for implementation tasks where you want thoughtful, minimal code changes.
|
||||
|
||||
### Code Reviewer
|
||||
Expert code review persona that identifies bugs, performance issues, and adherence to best practices. Provides constructive feedback with specific suggestions for improvement.
|
||||
Expert C++/QML code reviewer specializing in C++20 and Qt6. Checks for bugs, memory leaks, thread safety, Qt patterns, and production readiness. Provides direct, specific feedback with code examples.
|
||||
|
||||
### Researcher
|
||||
Research-oriented developer who investigates problems and explores solutions. Analyzes problems, presents multiple approaches with trade-offs, and recommends the best option. Does not write implementation code — focuses on helping you make informed decisions.
|
||||
|
||||
## Using Agent Roles
|
||||
|
||||
|
||||
115
docs/chat-summarization.md
Normal file
115
docs/chat-summarization.md
Normal file
@ -0,0 +1,115 @@
|
||||
# Chat Summarization
|
||||
|
||||
Chat Summarization allows you to compress long conversations into concise AI-generated summaries. This helps save context tokens and makes it easier to continue work on complex topics without losing important information.
|
||||
|
||||
## Overview
|
||||
|
||||
When conversations grow long, they consume more context tokens with each message. Chat Summarization uses your configured Chat Assistant provider to create an intelligent summary that preserves:
|
||||
|
||||
- Key decisions and conclusions
|
||||
- Technical details and code references
|
||||
- Important context for continuing the conversation
|
||||
|
||||
**Key Features:**
|
||||
- **One-click compression**: Summarize directly from the chat toolbar
|
||||
- **Preserves original**: Creates a new chat file, keeping the original intact
|
||||
- **Smart summaries**: AI extracts the most relevant information
|
||||
- **Markdown formatted**: Summaries are well-structured and readable
|
||||
|
||||
## Using Chat Summarization
|
||||
|
||||
### Compressing a Chat
|
||||
|
||||
1. Open any chat with conversation history
|
||||
2. Click the **Compress** button (📦) in the chat top bar
|
||||
3. Wait for the AI to generate the summary
|
||||
4. A new chat opens with the compressed summary
|
||||
|
||||
### What Gets Preserved
|
||||
|
||||
The summarization process:
|
||||
- Maintains chronological flow of the discussion
|
||||
- Keeps technical details, code snippets, and file references
|
||||
- Preserves key decisions and conclusions
|
||||
- Aims for 30-40% of the original conversation length
|
||||
|
||||
### What Gets Filtered
|
||||
|
||||
The following message types are excluded from summarization:
|
||||
- Tool call results (file reads, searches)
|
||||
- File edit blocks
|
||||
- Thinking/reasoning blocks
|
||||
|
||||
## How It Works
|
||||
|
||||
```
|
||||
┌─────────────────────────────────────────────────────────────┐
|
||||
│ CHAT SUMMARIZATION │
|
||||
├─────────────────────────────────────────────────────────────┤
|
||||
│ 1. Original chat messages are collected │
|
||||
│ 2. Tool/thinking messages are filtered out │
|
||||
│ 3. AI generates a structured summary │
|
||||
│ 4. New chat file is created with summary as first message │
|
||||
│ 5. Original chat remains unchanged │
|
||||
└─────────────────────────────────────────────────────────────┘
|
||||
```
|
||||
|
||||
### File Naming
|
||||
|
||||
Compressed chats are saved with a unique suffix:
|
||||
```
|
||||
original_chat.json → original_chat_a1b2c.json
|
||||
```
|
||||
|
||||
Both files appear in your chat history, allowing you to switch between the full conversation and the summary.
|
||||
|
||||
## Best Practices
|
||||
|
||||
1. **Summarize at natural breakpoints**: Compress after completing a major task or topic
|
||||
2. **Review the summary**: Ensure important details were captured before continuing
|
||||
3. **Keep originals**: Don't delete original chats until you've verified the summary is sufficient
|
||||
4. **Use for long sessions**: Most beneficial for conversations with 20+ messages
|
||||
|
||||
## When to Use
|
||||
|
||||
**Good candidates for summarization:**
|
||||
- Long debugging sessions with resolved issues
|
||||
- Feature implementation discussions with final decisions
|
||||
- Research conversations where conclusions were reached
|
||||
- Any chat approaching context limits
|
||||
|
||||
**Consider keeping full history for:**
|
||||
- Ongoing work that may need exact message references
|
||||
- Conversations with important code snippets you'll copy
|
||||
- Discussions where the reasoning process matters
|
||||
|
||||
## Configuration
|
||||
|
||||
Chat Summarization uses your current Chat Assistant settings:
|
||||
- **Provider**: Same as Chat Assistant (Settings → QodeAssist → General)
|
||||
- **Model**: Same as Chat Assistant
|
||||
- **Template**: Same as Chat Assistant
|
||||
|
||||
No additional configuration is required.
|
||||
|
||||
## Troubleshooting
|
||||
|
||||
### Compression Button Not Visible
|
||||
- Ensure you have an active chat with messages
|
||||
- Check that the chat top bar is visible
|
||||
|
||||
### Compression Fails
|
||||
- Verify your Chat Assistant provider is configured correctly
|
||||
- Check network connectivity
|
||||
- Ensure the model supports chat completions
|
||||
|
||||
### Summary Missing Details
|
||||
- The AI aims for 30-40% compression; some details may be condensed
|
||||
- For critical information, keep the original chat
|
||||
- Consider summarizing smaller conversation segments
|
||||
|
||||
## Related Documentation
|
||||
|
||||
- [Agent Roles](agent-roles.md) - Switch between AI personas
|
||||
- [File Context](file-context.md) - Attach files to chat
|
||||
- [Project Rules](project-rules.md) - Customize AI behavior
|
||||
@ -124,6 +124,9 @@ void AgentRolesManager::ensureDefaultRoles()
|
||||
|
||||
if (!dir.exists("reviewer.json"))
|
||||
saveRole(getDefaultReviewerRole());
|
||||
|
||||
if (!dir.exists("researcher.json"))
|
||||
saveRole(getDefaultResearcherRole());
|
||||
}
|
||||
|
||||
AgentRole AgentRolesManager::getDefaultDeveloperRole()
|
||||
@ -131,12 +134,34 @@ AgentRole AgentRolesManager::getDefaultDeveloperRole()
|
||||
return AgentRole{
|
||||
"developer",
|
||||
"Developer",
|
||||
"General coding assistance and implementation",
|
||||
"You are an advanced AI assistant specializing in C++, Qt, and QML development. "
|
||||
"Your role is to provide helpful, accurate, and detailed responses to questions "
|
||||
"about coding, debugging, and best practices in these technologies. "
|
||||
"Focus on writing clean, maintainable code following industry standards.",
|
||||
false};
|
||||
"Experienced Qt/C++ developer for implementation tasks",
|
||||
"You are an experienced Qt/C++ developer working on a Qt Creator plugin.\n\n"
|
||||
"Your workflow:\n"
|
||||
"1. **Analyze** - understand the problem and what needs to be done\n"
|
||||
"2. **Propose solution** - explain your approach in 2-3 sentences\n"
|
||||
"3. **Wait for approval** - don't write code until the solution is confirmed\n"
|
||||
"4. **Implement** - write clean, minimal code that solves the task\n\n"
|
||||
"When analyzing:\n"
|
||||
"- Ask clarifying questions if requirements are unclear\n"
|
||||
"- Check existing code for similar patterns\n"
|
||||
"- Consider edge cases and potential issues\n\n"
|
||||
"When proposing:\n"
|
||||
"- Explain what you'll change and why\n"
|
||||
"- Mention files you'll modify\n"
|
||||
"- Note any architectural implications\n\n"
|
||||
"When implementing:\n"
|
||||
"- Use C++20, Qt6, follow existing codebase style\n"
|
||||
"- Write only what's needed (MVP approach)\n"
|
||||
"- Include file paths and necessary changes\n"
|
||||
"- Handle errors properly\n"
|
||||
"- Make sure it compiles\n\n"
|
||||
"Keep it practical:\n"
|
||||
"- Short explanations, let code speak\n"
|
||||
"- No over-engineering or unnecessary refactoring\n"
|
||||
"- No TODOs, debug code, or unfinished work\n"
|
||||
"- Point out non-obvious things\n\n"
|
||||
"You're a pragmatic team member who thinks before coding.",
|
||||
true};
|
||||
}
|
||||
|
||||
AgentRole AgentRolesManager::getDefaultReviewerRole()
|
||||
@ -144,16 +169,58 @@ AgentRole AgentRolesManager::getDefaultReviewerRole()
|
||||
return AgentRole{
|
||||
"reviewer",
|
||||
"Code Reviewer",
|
||||
"Code review, quality assurance, and best practices",
|
||||
"You are an expert code reviewer specializing in C++, Qt, and QML. "
|
||||
"Your role is to:\n"
|
||||
"- Identify potential bugs, memory leaks, and performance issues\n"
|
||||
"- Check adherence to coding standards and best practices\n"
|
||||
"- Suggest improvements for readability and maintainability\n"
|
||||
"- Verify proper error handling and edge cases\n"
|
||||
"- Ensure thread safety and proper Qt object lifetime management\n"
|
||||
"Provide constructive, specific feedback with examples.",
|
||||
false};
|
||||
"Expert C++/QML code reviewer for quality assurance",
|
||||
"You are an expert C++/QML code reviewer specializing in C++20 and Qt6.\n\n"
|
||||
"What you check:\n"
|
||||
"- Bugs, memory leaks, undefined behavior\n"
|
||||
"- C++20 compliance and Qt6 patterns\n"
|
||||
"- RAII, move semantics, smart pointers\n"
|
||||
"- Qt parent-child ownership and signal/slot correctness\n"
|
||||
"- Thread safety and Qt concurrent usage\n"
|
||||
"- const-correctness and Qt container usage\n"
|
||||
"- Performance bottlenecks\n"
|
||||
"- Production readiness: error handling, no debug leftovers\n\n"
|
||||
"What you do:\n"
|
||||
"- Point out problems with clear explanations\n"
|
||||
"- Suggest specific fixes with code examples\n"
|
||||
"- Remove unnecessary comments, keep essential docs only\n"
|
||||
"- Flag anything that's not production-ready\n"
|
||||
"- Recommend optimizations when you spot them\n\n"
|
||||
"Focus on: correctness, performance, maintainability, Qt idioms.\n\n"
|
||||
"Be direct and specific. Show, don't just tell.",
|
||||
true};
|
||||
}
|
||||
|
||||
AgentRole AgentRolesManager::getDefaultResearcherRole()
|
||||
{
|
||||
return AgentRole{
|
||||
"researcher",
|
||||
"Researcher",
|
||||
"Research-oriented developer for exploring solutions",
|
||||
"You are a research-oriented Qt/C++ developer who investigates problems and explores "
|
||||
"solutions.\n\n"
|
||||
"Your job is to think, not to code:\n"
|
||||
"- Deep dive into the problem before suggesting anything\n"
|
||||
"- Research Qt docs, patterns, and best practices\n"
|
||||
"- Find multiple ways to solve it\n"
|
||||
"- Compare trade-offs: performance, complexity, maintainability\n"
|
||||
"- Look for relevant Qt APIs and modules\n"
|
||||
"- Think about architectural consequences\n\n"
|
||||
"How you work:\n"
|
||||
"1. **Problem Analysis** - what exactly needs solving\n"
|
||||
"2. **Research Findings** - what you learned about this problem space\n"
|
||||
"3. **Solution Options** - present 2-3 approaches with honest pros/cons\n"
|
||||
"4. **Recommendation** - which one fits best and why\n"
|
||||
"5. **Next Steps** - what to consider before implementing\n\n"
|
||||
"What you provide:\n"
|
||||
"- Clear comparison of different approaches\n"
|
||||
"- Code snippets as examples (not ready-to-use patches)\n"
|
||||
"- Links to docs, examples, similar implementations\n"
|
||||
"- Questions to clarify requirements\n"
|
||||
"- Warning about potential problems\n\n"
|
||||
"You DO NOT write implementation code. You explore options and let the developer choose.\n\n"
|
||||
"Think like a consultant: research thoroughly, present clearly, stay objective.",
|
||||
true};
|
||||
}
|
||||
|
||||
} // namespace QodeAssist::Settings
|
||||
|
||||
@ -76,6 +76,7 @@ public:
|
||||
private:
|
||||
static AgentRole getDefaultDeveloperRole();
|
||||
static AgentRole getDefaultReviewerRole();
|
||||
static AgentRole getDefaultResearcherRole();
|
||||
};
|
||||
|
||||
} // namespace QodeAssist::Settings
|
||||
|
||||
Reference in New Issue
Block a user