feat: multi agent sept 2025 #376
Draft
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
docs: process of choosing between sandbox and production configurations when deploying Azure infrastructure using the `azd up` command
feat: Update deployment configurations to set WAF architecture parameters
fix: Updated Planner prompt to remove EXCEPTION wording and align with LLM behavior
fix: p2/p3 Bug fixes
fix: enable the appinsights telemetry logs code
Added Reusing an Existing Log Analytics Workspace section
fix: added fix for not creating task for input like "x" or "abcd" or meani…
feat: Merging the changes from dev to main
fix: Bug fixes of #19515,#19330,#19278
Renamed and relocated data files and scripts from src/data/ to data/ for improved project organization. Also removed the obsolete .env.sample file from the old directory.
Renamed 'my_mcp_server.py' to 'mcp_server.py' and replaced 'my_mcp_test_client.py' with 'mcp_test_client.py' to standardize file naming. Updated the test client to reference the new server filename.
Reorganized the MCP server into a modular structure with separate directories for core logic, services, utilities, and configuration. Introduced service classes for HR, tech support, and general tools, and implemented a factory pattern for tool registration. Added FastAPI-based HTTP API with authentication, Docker support, environment-based configuration, and comprehensive test scaffolding. Removed legacy test client and updated main server entry point for dual HTTP/MCP protocol support.
Rewrote and streamlined the MCP server to use FastMCP as the core, removed legacy FastAPI/HTTP API code, and improved argument parsing for transport selection. Updated and condensed README.md, and added a new, comprehensive README_NEW.md with clear instructions, architecture, and usage examples for FastMCP transports and CLI. The server now focuses on FastMCP transports (stdio, http, streamable-http, sse) and provides improved logging and configuration.
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
| static async createPlan( | ||
| description: string | ||
| ): Promise<{ plan_id: string; status: string; session_id: string }> { | ||
| const sessionId = this.generateSessionId(); |
Check failure
Code scanning / CodeQL
Insecure randomness High
Show autofix suggestion
Hide autofix suggestion
Copilot Autofix
AI about 22 hours ago
To fix the problem, replace the use of Math.random() in the generateSessionId method with a cryptographically secure random number generator. In the browser, the recommended approach is to use window.crypto.getRandomValues to generate random values. Specifically, generate a random 32-bit unsigned integer using window.crypto.getRandomValues(new Uint32Array(1))[0] and use that as the random component of the session ID. This change should be made in the generateSessionId method in src/frontend/src/services/TaskService.tsx, replacing line 104. No additional imports are needed, as window.crypto is available in modern browsers.
Suggested changeset
1
src/frontend/src/services/TaskService.tsx
| @@ -101,7 +101,8 @@ | ||
| */ | ||
| static generateSessionId(): string { | ||
| const timestamp = new Date().getTime(); | ||
| const random = Math.floor(Math.random() * 10000); | ||
| // Use cryptographically secure random number | ||
| const random = window.crypto.getRandomValues(new Uint32Array(1))[0]; | ||
| return `sid_${timestamp}_${random}`; | ||
| } | ||
| /** |
Copilot is powered by AI and may make mistakes. Always verify output.
Unable to commit as this autofix suggestion is now outdated
Refactored AzureConfig and MCPConfig classes for improved readability and removed hardcoded Azure credentials from settings.py. Updated fastmcp version from 0.4.0 to 2.2.4 in requirements.txt.
Introduces a comprehensive guide for testing the MACAE MCP Server in a Docker container. The documentation covers prerequisites, build and run instructions, endpoint testing, troubleshooting, performance and integration testing, environment configurations, Docker Compose usage, and success criteria.
…e AI Foundry - Add POST /api/upload_team_config endpoint for team configuration management - Implement FoundryAgentService for bulk agent creation with error handling - Add comprehensive RAI validation for all uploaded content - Add team selection UI with search, delete, and validation features - Add model deployment and search index validation services
Introduces DataToolService to provide access to specific CSV datasets via new tools: data_provider and show_tables. Updates the factory and service registration to include the new service and adds the DATA domain to the Domain enum. This enables controlled access to allowed data files for the MCP server.
Moved data files to new locations, added new backend app.py, and introduced v3 MCP server modules with supporting services, configuration, and orchestration. Updated documentation for Docker MCP server testing and Azure AI Foundry project reuse. Improved deployment guides and infrastructure outputs for better environment configuration.
feat: Json upload setting page
Deleted multiple CSV and JSON files containing various datasets such as competitor pricing, customer churn, marketing engagement, loyalty program, subscription benefits, access attempts, incident reports, feedback surveys, customer profiles, service interactions, delivery metrics, product returns, product table, purchase history, sentiment analysis, store visits, and website activity logs. This change may be part of a data cleanup or migration process.
Introduced multiple new datasets covering customer profiles, purchase history, churn analysis, feedback, service interactions, loyalty program, marketing engagement, competitor pricing, product returns, delivery metrics, social media sentiment, store visits, unauthorized access attempts, warehouse incidents, and website activity logs. These datasets support comprehensive analysis for customer behavior, operational performance, and competitive benchmarking.
Renamed test_fastmcp_run.py from src/backend/v3/mcp_server/ to src/tests/mcp_server/ to improve test organization and maintain consistency in the project structure.
Moved model and search validation logic from app_kernel.py into JsonService, consolidating related methods and removing redundant service classes. Updated endpoints to use JsonService for model and search validation, and improved configuration handling. Added DATASET_PATH to .env.example.
Deleted imports for OnboardingOrchestrationManager and MagenticScenarios from app_kernel.py as they are not used in the file.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Purpose
Does this introduce a breaking change?
How to Test
What to Check
Verify that the following are valid
Other Information