Skip to content

Conversation

@ashu8912
Copy link
Member

@ashu8912 ashu8912 commented Sep 8, 2025

No description provided.

@ashu8912 ashu8912 marked this pull request as draft September 8, 2025 17:33
@ashu8912 ashu8912 force-pushed the add-mcp-server branch 2 times, most recently from aa9aa8e to 3bd4cbb Compare September 10, 2025 04:21
@ashu8912 ashu8912 force-pushed the add-mcp-server branch 3 times, most recently from 10b04e6 to 1b93e58 Compare September 21, 2025 11:11
@ashu8912 ashu8912 marked this pull request as ready for review September 29, 2025 13:29
@ashu8912 ashu8912 force-pushed the add-mcp-server branch 2 times, most recently from 2620b42 to fe38c68 Compare September 29, 2025 14:12
@illume illume added ai-assistant enhancement New feature or request labels Oct 8, 2025
@ashu8912 ashu8912 force-pushed the add-mcp-server branch 2 times, most recently from c81b4a7 to 628ad14 Compare October 9, 2025 11:54
@ashu8912 ashu8912 force-pushed the add-mcp-server branch 3 times, most recently from a2c1b1f to de28bed Compare October 27, 2025 19:17
Signed-off-by: Ashu Ghildiyal <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Ashu Ghildiyal <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Ashu Ghildiyal <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Ashu Ghildiyal <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Ashu Ghildiyal <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
- Add MCPOutputFormatter for AI-powered formatting of MCP tool outputs
- Add MCPOutputDisplay component for rendering formatted MCP results
- Add MCPFormattedMessage component for displaying MCP messages in chat
- Support multiple output types: table, metrics, list, graph, text, error
- Include insights, warnings, and actionable items in formatted output
- Add comprehensive argument processing and validation

Signed-off-by: ashu8912 <[email protected]>
- Add PromptWidthContext to eliminate prop drilling for width state
- Add PromptWidthProvider wrapper in AIPanelComponent
- Enable components to access prompt width through usePromptWidth hook
- Improve state management across the component hierarchy

Signed-off-by: ashu8912 <[email protected]>
- Add InlineToolConfirmation component for embedded tool approval UI
- Add InlineToolApprovalManager for managing tool confirmation state
- Extend ToolApprovalDialog with inline approval capabilities
- Add support for tool confirmation in Prompt interface
- Enable seamless tool approval workflow within chat interface

Signed-off-by: ashu8912 <[email protected]>
- Add ToolsDialog component for displaying and managing AI tools
- Provide interface for viewing tool configurations and capabilities
- Export ToolsDialog in assistant components index

Signed-off-by: ashu8912 <[email protected]>
…gration

- Add originalArgs storage in tool response metadata for retry capability
- Integrate MCPOutputFormatter for AI-powered output formatting
- Improve MCP tool argument mapping and validation
- Add comprehensive error handling and formatting for tool failures
- Include originalArgs in all formatted outputs (success, error, fallback)
- Enable tool retry functionality through stored execution arguments

Signed-off-by: ashu8912 <[email protected]>
- Add MCPFormattedMessage integration to ContentRenderer
- Add onRetryTool prop propagation through component hierarchy
- Integrate prompt width context usage in components
- Add MCP tool retry functionality to chat interface
- Update TextStreamContainer and AIChatContent with retry support

Signed-off-by: ashu8912 <[email protected]>
- Add handleRetryTool function for re-executing failed tools
- Integrate inline tool approval manager for seamless confirmations
- Add comprehensive tool response processing and error handling
- Implement suggestion parsing and display from AI responses
- Add retry capability propagation to chat components
- Improve user experience with better tool interaction workflow

Signed-off-by: ashu8912 <[email protected]>
- Add comprehensive tool response processing and validation
- Implement intelligent message preparation for tool contexts
- Add specialized system prompts for tool response handling
- Improve tool call alignment validation and error handling
- Add content size management to prevent memory issues
- Enhance user context building with conversation history and tool results
- Support multiple provider compatibility (Azure, Anthropic, etc.)

Signed-off-by: ashu8912 <[email protected]>
- Add MCPConfigEditorDialog with Monaco Editor integration
- Provide syntax highlighting and auto-formatting for JSON configurations
- Include tabbed interface with Configuration Editor and Schema Documentation
- Add real-time validation with clear error messages
- Support for environment variables in server configuration
- Include comprehensive schema documentation with field descriptions
- Add Load Example and Reset functionality for easy configuration management

Signed-off-by: ashu8912 <[email protected]>
ashu8912 and others added 21 commits October 29, 2025 13:27
The "white-space: pre-wrap" left lots of spacing around the text.

Signed-off-by: Joaquim Rocha <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
So we don't show very long descriptions in the tools dialog.

Signed-off-by: Joaquim Rocha <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Joaquim Rocha <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: Joaquim Rocha <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Signed-off-by: ashu8912 <[email protected]>
Instead of just relying on editing JSON.
@illume illume requested a review from Copilot November 3, 2025 10:10
@illume illume changed the title Add ability to run mcp server from ai-assistant plugin ai-assistant: Add ability to run mcp server from ai-assistant plugin Nov 3, 2025
Copy link
Contributor

@illume illume left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

It's important to do these standard things for PRs to speed reviews along:

  • PR description
  • screenshots or video
  • steps to test each fix or piece of functionality
  • link to the related issue
  • If there are no tests at all, please justify this. Note that it will slow reviews down, and slow down future changes
  • Document fields and functions. This speeds up the review, and helps speed up further changes.
  • git commit messages with context of the modules changed in subject, AND a "why" in the git commit body unless it's covered in the git message subject.
ai-assistant: MCPSettings: Add MCP settings UI and Electron config API

- Add components/settings/MCPSettings.tsx: UI for configuring MCP servers (add/remove/toggle/edit),
  uses window.desktopApi.mcp.getConfig/updateConfig when running in Electron, falls back to pluginStore.
- Extend ElectronMCPApi typings with getConfig and updateConfig for config persistence.
- Provide default server when enabling MCP with no servers, and a "Test MCP Connection" action.

Notes:
- Argument parsing is space-based (no quote handling).
- Ensure native side exposes getTools (used by the test action) and that updateConfig triggers any required client restart.

Copy link

Copilot AI left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Pull Request Overview

This PR adds comprehensive MCP (Model Context Protocol) integration to the AI assistant, enabling connection to external tools and services. It introduces tool approval workflows, intelligent argument processing, and enhanced tool management capabilities.

  • Added MCP server configuration and management in Electron environments
  • Implemented tool approval dialogs with inline confirmation UI
  • Created intelligent argument processing using AI for MCP tools
  • Added tool orchestration for multi-tool execution

Reviewed Changes

Copilot reviewed 40 out of 42 changed files in this pull request and generated 13 comments.

Show a summary per file
File Description
ai-assistant/src/utils/ToolConfigManager.ts Added source tracking ('built-in' vs 'mcp'), MCP tool integration functions, and tool state initialization
ai-assistant/src/utils/ToolApprovalManager.ts New approval manager for tool execution with session-based auto-approval
ai-assistant/src/utils/InlineToolApprovalManager.ts Inline tool approval with user context extraction for intelligent argument processing
ai-assistant/src/langchain/tools/ToolManager.ts Enhanced with MCP tool support, argument mapping, and formatter integration
ai-assistant/src/langchain/tools/ToolOrchestrator.ts New orchestrator for analyzing and coordinating multi-tool execution
ai-assistant/src/langchain/formatters/MCPOutputFormatter.ts AI-powered formatter for MCP tool output with markdown support
ai-assistant/src/langchain/LangChainManager.ts Major updates for tool orchestration, inline approval, and argument enhancement
ai-assistant/src/components/mcpOutput/MCPOutputDisplay.tsx Rich UI component for displaying formatted MCP tool results
ai-assistant/src/components/mcpOutput/MCPArgumentProcessor.ts Intelligent argument processing with schema validation
ai-assistant/src/components/settings/MCPSettings.tsx MCP server configuration UI with enable/disable controls
ai-assistant/src/components/common/InlineToolConfirmation.tsx Inline tool confirmation component (exported via index)
ai-assistant/src/types/electron.d.ts TypeScript definitions for Electron MCP API
ai-assistant/src/hooks/useClusterChangeNotifier.ts Hook for monitoring cluster changes and notifying MCP servers
Files not reviewed (1)
  • ai-assistant/package-lock.json: Language not supported
Comments suppressed due to low confidence (2)

ai-assistant/src/langchain/tools/ToolManager.ts:226

  • This statement is unreachable.
    ai-assistant/src/langchain/tools/ToolManager.ts:258
  • This statement is unreachable.

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

Comment on lines +225 to +226
return this.filterMCPArguments(inputValue, inputSchema);
return this.filterMCPArguments(inputValue, inputSchema);
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Duplicate return statement on lines 225-226. The second return is unreachable and should be removed.

Copilot uses AI. Check for mistakes.
Comment on lines +257 to +258
return inputValue;
return inputValue;
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Duplicate return statement on lines 257-258. The second return is unreachable and should be removed.

Copilot uses AI. Check for mistakes.
Comment on lines +3 to +16
import {
Alert,
Box,
Button,
DialogActions,
DialogContent,
DialogTitle,
FormControlLabel,
IconButton,
Paper,
Switch,
TextField,
Typography,
} from '@mui/material';
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unused import Paper.

Copilot uses AI. Check for mistakes.
Comment on lines +3 to +24
import {
Alert,
Box,
Button,
Chip,
DialogActions,
DialogContent,
DialogTitle,
FormControlLabel,
IconButton,
Paper,
Switch,
Table,
TableBody,
TableCell,
TableContainer,
TableHead,
TableRow,
TextField,
Tooltip,
Typography,
} from '@mui/material';
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unused import Chip.

Copilot uses AI. Check for mistakes.
): FormattedMCPOutput {
// Try to detect if it's JSON
let data: any;
let type: FormattedMCPOutput['type'] = 'text';
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The initial value of type is unused, since it is always overwritten.

Suggested change
let type: FormattedMCPOutput['type'] = 'text';
let type: FormattedMCPOutput['type'];

Copilot uses AI. Check for mistakes.
cursor: isActionInProgress ? 'not-allowed' : 'pointer',
}}
>
{isDenying ? 'Denying...' : 'Deny'}
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This use of variable 'isDenying' always evaluates to false.

Copilot uses AI. Check for mistakes.
size="small"
onClick={handleApprove}
startIcon={
isApproving ? (
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This use of variable 'isApproving' always evaluates to false.

Copilot uses AI. Check for mistakes.
}
color="primary"
sx={{
opacity: isApproving ? 0.7 : 1,
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This use of variable 'isApproving' always evaluates to false.

Copilot uses AI. Check for mistakes.
cursor: isActionInProgress ? 'not-allowed' : 'pointer',
}}
>
{isApproving
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This use of variable 'isApproving' always evaluates to false.

Copilot uses AI. Check for mistakes.
}

// First, check if args is properly structured for the schema
if (args && typeof args === 'object') {
Copy link

Copilot AI Nov 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

This use of variable 'args' always evaluates to true.

Copilot uses AI. Check for mistakes.
@illume illume marked this pull request as draft November 3, 2025 19:45
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

ai-assistant enhancement New feature or request

Projects

None yet

Development

Successfully merging this pull request may close these issues.

4 participants