This is page 4 of 145. Use http://codebase.md/microsoft/semanticworkbench?lines=true&page={x} to view the full context.
# Directory Structure
```
├── .devcontainer
│ ├── .vscode
│ │ └── settings.json
│ ├── devcontainer.json
│ ├── OPTIMIZING_FOR_CODESPACES.md
│ ├── POST_SETUP_README.md
│ └── README.md
├── .dockerignore
├── .gitattributes
├── .github
│ ├── policheck.yml
│ └── workflows
│ ├── assistants-codespace-assistant.yml
│ ├── assistants-document-assistant.yml
│ ├── assistants-explorer-assistant.yml
│ ├── assistants-guided-conversation-assistant.yml
│ ├── assistants-knowledge-transfer-assistant.yml
│ ├── assistants-navigator-assistant.yml
│ ├── assistants-project-assistant.yml
│ ├── assistants-prospector-assistant.yml
│ ├── assistants-skill-assistant.yml
│ ├── libraries.yml
│ ├── mcp-server-giphy.yml
│ ├── mcp-server-memory-filesystem-edit.yml
│ ├── mcp-server-memory-user-bio.yml
│ ├── mcp-server-memory-whiteboard.yml
│ ├── mcp-server-open-deep-research-clone.yml
│ ├── mcp-server-web-research.yml
│ ├── workbench-app.yml
│ └── workbench-service.yml
├── .gitignore
├── .multi-root-tools
│ ├── Makefile
│ └── README.md
├── .vscode
│ ├── extensions.json
│ ├── launch.json
│ └── settings.json
├── ai_context
│ └── generated
│ ├── ASPIRE_ORCHESTRATOR.md
│ ├── ASSISTANT_CODESPACE.md
│ ├── ASSISTANT_DOCUMENT.md
│ ├── ASSISTANT_NAVIGATOR.md
│ ├── ASSISTANT_PROJECT.md
│ ├── ASSISTANT_PROSPECTOR.md
│ ├── ASSISTANTS_OTHER.md
│ ├── ASSISTANTS_OVERVIEW.md
│ ├── CONFIGURATION.md
│ ├── DOTNET_LIBRARIES.md
│ ├── EXAMPLES.md
│ ├── MCP_SERVERS.md
│ ├── PYTHON_LIBRARIES_AI_CLIENTS.md
│ ├── PYTHON_LIBRARIES_CORE.md
│ ├── PYTHON_LIBRARIES_EXTENSIONS.md
│ ├── PYTHON_LIBRARIES_SKILLS.md
│ ├── PYTHON_LIBRARIES_SPECIALIZED.md
│ ├── TOOLS.md
│ ├── WORKBENCH_FRONTEND.md
│ └── WORKBENCH_SERVICE.md
├── aspire-orchestrator
│ ├── .editorconfig
│ ├── Aspire.AppHost
│ │ ├── .gitignore
│ │ ├── appsettings.json
│ │ ├── Aspire.AppHost.csproj
│ │ ├── Program.cs
│ │ └── Properties
│ │ └── launchSettings.json
│ ├── Aspire.Extensions
│ │ ├── Aspire.Extensions.csproj
│ │ ├── Dashboard.cs
│ │ ├── DockerFileExtensions.cs
│ │ ├── PathNormalizer.cs
│ │ ├── UvAppHostingExtensions.cs
│ │ ├── UvAppResource.cs
│ │ ├── VirtualEnvironment.cs
│ │ └── WorkbenchServiceHostingExtensions.cs
│ ├── Aspire.ServiceDefaults
│ │ ├── Aspire.ServiceDefaults.csproj
│ │ └── Extensions.cs
│ ├── README.md
│ ├── run.sh
│ ├── SemanticWorkbench.Aspire.sln
│ └── SemanticWorkbench.Aspire.sln.DotSettings
├── assistants
│ ├── codespace-assistant
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ ├── icon_context_transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── models.py
│ │ │ │ ├── request_builder.py
│ │ │ │ ├── response.py
│ │ │ │ ├── step_handler.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── abbreviations.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ └── openai_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── card_content_context_transfer.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── codespace_assistant_info.md
│ │ │ │ ├── context_transfer_assistant_info.md
│ │ │ │ ├── guardrails_prompt.txt
│ │ │ │ ├── guidance_prompt_context_transfer.txt
│ │ │ │ ├── guidance_prompt.txt
│ │ │ │ ├── instruction_prompt_context_transfer.txt
│ │ │ │ └── instruction_prompt.txt
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── document-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── context_management
│ │ │ │ ├── __init__.py
│ │ │ │ └── inspector.py
│ │ │ ├── filesystem
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _convert.py
│ │ │ │ ├── _file_sources.py
│ │ │ │ ├── _filesystem.py
│ │ │ │ ├── _inspector.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _prompts.py
│ │ │ │ └── _tasks.py
│ │ │ ├── guidance
│ │ │ │ ├── __init__.py
│ │ │ │ ├── dynamic_ui_inspector.py
│ │ │ │ ├── guidance_config.py
│ │ │ │ ├── guidance_prompts.py
│ │ │ │ └── README.md
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── models.py
│ │ │ │ ├── prompts.py
│ │ │ │ ├── responder.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ ├── openai_utils.py
│ │ │ │ ├── tokens_tiktoken.py
│ │ │ │ └── workbench_messages.py
│ │ │ ├── text_includes
│ │ │ │ └── document_assistant_info.md
│ │ │ ├── types.py
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── assistant.code-workspace
│ │ ├── CLAUDE.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_convert.py
│ │ │ └── test_data
│ │ │ ├── blank_image.png
│ │ │ ├── Formatting Test.docx
│ │ │ ├── sample_data.csv
│ │ │ ├── sample_data.xlsx
│ │ │ ├── sample_page.html
│ │ │ ├── sample_presentation.pptx
│ │ │ └── simple_pdf.pdf
│ │ └── uv.lock
│ ├── explorer-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── model.py
│ │ │ │ ├── response_anthropic.py
│ │ │ │ ├── response_openai.py
│ │ │ │ └── response.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── guided-conversation-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agents
│ │ │ │ ├── guided_conversation
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── definition.py
│ │ │ │ │ └── definitions
│ │ │ │ │ ├── er_triage.py
│ │ │ │ │ ├── interview.py
│ │ │ │ │ ├── patient_intake.py
│ │ │ │ │ └── poem_feedback.py
│ │ │ │ └── guided_conversation_agent.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── knowledge-transfer-assistant
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agentic
│ │ │ │ ├── __init__.py
│ │ │ │ ├── analysis.py
│ │ │ │ ├── coordinator_support.py
│ │ │ │ └── team_welcome.py
│ │ │ ├── assets
│ │ │ │ ├── icon-knowledge-transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── assistant.py
│ │ │ ├── common.py
│ │ │ ├── config.py
│ │ │ ├── conversation_clients.py
│ │ │ ├── conversation_share_link.py
│ │ │ ├── data.py
│ │ │ ├── domain
│ │ │ │ ├── __init__.py
│ │ │ │ ├── audience_manager.py
│ │ │ │ ├── information_request_manager.py
│ │ │ │ ├── knowledge_brief_manager.py
│ │ │ │ ├── knowledge_digest_manager.py
│ │ │ │ ├── learning_objectives_manager.py
│ │ │ │ └── share_manager.py
│ │ │ ├── files.py
│ │ │ ├── logging.py
│ │ │ ├── notifications.py
│ │ │ ├── respond.py
│ │ │ ├── storage_models.py
│ │ │ ├── storage.py
│ │ │ ├── string_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── assistant_info.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── coordinator_instructions.txt
│ │ │ │ ├── coordinator_role.txt
│ │ │ │ ├── knowledge_digest_instructions.txt
│ │ │ │ ├── knowledge_digest_prompt.txt
│ │ │ │ ├── share_information_request_detection.txt
│ │ │ │ ├── team_instructions.txt
│ │ │ │ ├── team_role.txt
│ │ │ │ └── welcome_message_generation.txt
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base.py
│ │ │ │ ├── information_requests.py
│ │ │ │ ├── learning_objectives.py
│ │ │ │ ├── learning_outcomes.py
│ │ │ │ ├── progress_tracking.py
│ │ │ │ └── share_setup.py
│ │ │ ├── ui_tabs
│ │ │ │ ├── __init__.py
│ │ │ │ ├── brief.py
│ │ │ │ ├── common.py
│ │ │ │ ├── debug.py
│ │ │ │ ├── learning.py
│ │ │ │ └── sharing.py
│ │ │ └── utils.py
│ │ ├── CLAUDE.md
│ │ ├── docs
│ │ │ ├── design
│ │ │ │ ├── actions.md
│ │ │ │ └── inference.md
│ │ │ ├── DEV_GUIDE.md
│ │ │ ├── how-kta-works.md
│ │ │ ├── JTBD.md
│ │ │ ├── knowledge-transfer-goals.md
│ │ │ ├── learning_assistance.md
│ │ │ ├── notable_claude_conversations
│ │ │ │ ├── clarifying_quad_modal_design.md
│ │ │ │ ├── CLAUDE_PROMPTS.md
│ │ │ │ ├── transfer_state.md
│ │ │ │ └── trying_the_context_agent.md
│ │ │ └── opportunities-of-knowledge-transfer.md
│ │ ├── knowledge-transfer-assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_artifact_loading.py
│ │ │ ├── test_inspector.py
│ │ │ ├── test_share_manager.py
│ │ │ ├── test_share_storage.py
│ │ │ ├── test_share_tools.py
│ │ │ └── test_team_mode.py
│ │ └── uv.lock
│ ├── Makefile
│ ├── navigator-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── assets
│ │ │ │ ├── card_content.md
│ │ │ │ └── icon.svg
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── helpers.py
│ │ │ ├── response
│ │ │ │ ├── __init__.py
│ │ │ │ ├── completion_handler.py
│ │ │ │ ├── completion_requestor.py
│ │ │ │ ├── local_tool
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── add_assistant_to_conversation.py
│ │ │ │ │ ├── list_assistant_services.py
│ │ │ │ │ └── model.py
│ │ │ │ ├── models.py
│ │ │ │ ├── prompt.py
│ │ │ │ ├── request_builder.py
│ │ │ │ ├── response.py
│ │ │ │ ├── step_handler.py
│ │ │ │ └── utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── formatting_utils.py
│ │ │ │ ├── message_utils.py
│ │ │ │ ├── openai_utils.py
│ │ │ │ └── tools.py
│ │ │ ├── text_includes
│ │ │ │ ├── guardrails_prompt.md
│ │ │ │ ├── guidance_prompt.md
│ │ │ │ ├── instruction_prompt.md
│ │ │ │ ├── navigator_assistant_info.md
│ │ │ │ └── semantic_workbench_features.md
│ │ │ └── whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── _inspector.py
│ │ │ └── _whiteboard.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── project-assistant
│ │ ├── .cspell
│ │ │ └── custom-dictionary-workspace.txt
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agentic
│ │ │ │ ├── __init__.py
│ │ │ │ ├── act.py
│ │ │ │ ├── coordinator_next_action.py
│ │ │ │ ├── create_invitation.py
│ │ │ │ ├── detect_audience_and_takeaways.py
│ │ │ │ ├── detect_coordinator_actions.py
│ │ │ │ ├── detect_information_request_needs.py
│ │ │ │ ├── detect_knowledge_package_gaps.py
│ │ │ │ ├── focus.py
│ │ │ │ ├── respond.py
│ │ │ │ ├── team_welcome.py
│ │ │ │ └── update_digest.py
│ │ │ ├── assets
│ │ │ │ ├── icon-knowledge-transfer.svg
│ │ │ │ └── icon.svg
│ │ │ ├── assistant.py
│ │ │ ├── common.py
│ │ │ ├── config.py
│ │ │ ├── conversation_clients.py
│ │ │ ├── data.py
│ │ │ ├── domain
│ │ │ │ ├── __init__.py
│ │ │ │ ├── audience_manager.py
│ │ │ │ ├── conversation_preferences_manager.py
│ │ │ │ ├── information_request_manager.py
│ │ │ │ ├── knowledge_brief_manager.py
│ │ │ │ ├── knowledge_digest_manager.py
│ │ │ │ ├── learning_objectives_manager.py
│ │ │ │ ├── share_manager.py
│ │ │ │ ├── tasks_manager.py
│ │ │ │ └── transfer_manager.py
│ │ │ ├── errors.py
│ │ │ ├── files.py
│ │ │ ├── logging.py
│ │ │ ├── notifications.py
│ │ │ ├── prompt_utils.py
│ │ │ ├── storage.py
│ │ │ ├── string_utils.py
│ │ │ ├── text_includes
│ │ │ │ ├── actor_instructions.md
│ │ │ │ ├── assistant_info.md
│ │ │ │ ├── card_content.md
│ │ │ │ ├── coordinator_instructions copy.md
│ │ │ │ ├── coordinator_instructions.md
│ │ │ │ ├── create_invitation.md
│ │ │ │ ├── detect_audience.md
│ │ │ │ ├── detect_coordinator_actions.md
│ │ │ │ ├── detect_information_request_needs.md
│ │ │ │ ├── detect_knowledge_package_gaps.md
│ │ │ │ ├── focus.md
│ │ │ │ ├── knowledge_digest_instructions.txt
│ │ │ │ ├── team_instructions.txt
│ │ │ │ ├── to_do.md
│ │ │ │ ├── update_knowledge_brief.md
│ │ │ │ ├── update_knowledge_digest.md
│ │ │ │ └── welcome_message_generation.txt
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── base.py
│ │ │ │ ├── conversation_preferences.py
│ │ │ │ ├── information_requests.py
│ │ │ │ ├── learning_objectives.py
│ │ │ │ ├── learning_outcomes.py
│ │ │ │ ├── progress_tracking.py
│ │ │ │ ├── share_setup.py
│ │ │ │ ├── system_reminders.py
│ │ │ │ ├── tasks.py
│ │ │ │ └── todo.py
│ │ │ ├── ui_tabs
│ │ │ │ ├── __init__.py
│ │ │ │ ├── brief.py
│ │ │ │ ├── common.py
│ │ │ │ ├── debug.py
│ │ │ │ ├── learning.py
│ │ │ │ └── sharing.py
│ │ │ └── utils.py
│ │ ├── CLAUDE.md
│ │ ├── docs
│ │ │ ├── design
│ │ │ │ ├── actions.md
│ │ │ │ ├── control_options.md
│ │ │ │ ├── design.md
│ │ │ │ ├── inference.md
│ │ │ │ └── PXL_20250814_190140267.jpg
│ │ │ ├── DEV_GUIDE.md
│ │ │ ├── how-kta-works.md
│ │ │ ├── JTBD.md
│ │ │ ├── knowledge-transfer-goals.md
│ │ │ ├── learning_assistance.md
│ │ │ ├── notable_claude_conversations
│ │ │ │ ├── clarifying_quad_modal_design.md
│ │ │ │ ├── CLAUDE_PROMPTS.md
│ │ │ │ ├── transfer_state.md
│ │ │ │ └── trying_the_context_agent.md
│ │ │ └── opportunities-of-knowledge-transfer.md
│ │ ├── knowledge-transfer-assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── __init__.py
│ │ │ ├── test_artifact_loading.py
│ │ │ ├── test_inspector.py
│ │ │ ├── test_share_manager.py
│ │ │ ├── test_share_storage.py
│ │ │ └── test_team_mode.py
│ │ └── uv.lock
│ ├── prospector-assistant
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── agents
│ │ │ │ ├── artifact_agent.py
│ │ │ │ ├── document
│ │ │ │ │ ├── config.py
│ │ │ │ │ ├── gc_draft_content_feedback_config.py
│ │ │ │ │ ├── gc_draft_outline_feedback_config.py
│ │ │ │ │ ├── guided_conversation.py
│ │ │ │ │ └── state.py
│ │ │ │ └── document_agent.py
│ │ │ ├── artifact_creation_extension
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _llm.py
│ │ │ │ ├── config.py
│ │ │ │ ├── document.py
│ │ │ │ ├── extension.py
│ │ │ │ ├── store.py
│ │ │ │ ├── test
│ │ │ │ │ ├── conftest.py
│ │ │ │ │ ├── evaluation.py
│ │ │ │ │ ├── test_completion_with_tools.py
│ │ │ │ │ └── test_extension.py
│ │ │ │ └── tools.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ ├── form_fill_extension
│ │ │ │ ├── __init__.py
│ │ │ │ ├── config.py
│ │ │ │ ├── extension.py
│ │ │ │ ├── inspector.py
│ │ │ │ ├── state.py
│ │ │ │ └── steps
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _guided_conversation.py
│ │ │ │ ├── _llm.py
│ │ │ │ ├── acquire_form_step.py
│ │ │ │ ├── extract_form_fields_step.py
│ │ │ │ ├── fill_form_step.py
│ │ │ │ └── types.py
│ │ │ ├── helpers.py
│ │ │ ├── legacy.py
│ │ │ └── text_includes
│ │ │ ├── artifact_agent_enabled.md
│ │ │ ├── guardrails_prompt.txt
│ │ │ ├── guided_conversation_agent_enabled.md
│ │ │ └── skills_agent_enabled.md
│ │ ├── assistant.code-workspace
│ │ ├── gc_learnings
│ │ │ ├── gc_learnings.md
│ │ │ └── images
│ │ │ ├── gc_conversation_plan_fcn.png
│ │ │ ├── gc_conversation_plan_template.png
│ │ │ ├── gc_execute_plan_callstack.png
│ │ │ ├── gc_functions.png
│ │ │ ├── gc_generate_plan_callstack.png
│ │ │ ├── gc_get_resource_instructions.png
│ │ │ ├── gc_get_termination_instructions.png
│ │ │ ├── gc_kernel_arguments.png
│ │ │ ├── gc_plan_calls.png
│ │ │ ├── gc_termination_instructions.png
│ │ │ ├── sk_get_chat_message_contents.png
│ │ │ ├── sk_inner_get_chat_message_contents.png
│ │ │ ├── sk_send_request_prep.png
│ │ │ └── sk_send_request.png
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ └── skill-assistant
│ ├── .env.example
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── assistant
│ │ ├── __init__.py
│ │ ├── config.py
│ │ ├── logging.py
│ │ ├── skill_assistant.py
│ │ ├── skill_engine_registry.py
│ │ ├── skill_event_mapper.py
│ │ ├── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ └── workbench_helpers.py
│ ├── assistant.code-workspace
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ ├── tests
│ │ └── test_setup.py
│ └── uv.lock
├── CLAUDE.md
├── CODE_OF_CONDUCT.md
├── CONTRIBUTING.md
├── docs
│ ├── .vscode
│ │ └── settings.json
│ ├── ASSISTANT_CONFIG.md
│ ├── ASSISTANT_DEVELOPMENT_GUIDE.md
│ ├── CUSTOM_APP_REGISTRATION.md
│ ├── HOSTED_ASSISTANT_WITH_LOCAL_MCP_SERVERS.md
│ ├── images
│ │ ├── architecture-animation.gif
│ │ ├── configure_assistant.png
│ │ ├── conversation_canvas_open.png
│ │ ├── conversation_duplicate.png
│ │ ├── conversation_export.png
│ │ ├── conversation_share_dialog.png
│ │ ├── conversation_share_link.png
│ │ ├── dashboard_configured_view.png
│ │ ├── dashboard_view.png
│ │ ├── license_agreement.png
│ │ ├── message_bar.png
│ │ ├── message_inspection.png
│ │ ├── message_link.png
│ │ ├── new_prospector_assistant_dialog.png
│ │ ├── open_conversation_canvas.png
│ │ ├── prospector_example.png
│ │ ├── readme1.png
│ │ ├── readme2.png
│ │ ├── readme3.png
│ │ ├── rewind.png
│ │ ├── signin_page.png
│ │ └── splash_screen.png
│ ├── LOCAL_ASSISTANT_WITH_REMOTE_WORKBENCH.md
│ ├── SETUP_DEV_ENVIRONMENT.md
│ └── WORKBENCH_APP.md
├── examples
│ ├── dotnet
│ │ ├── .editorconfig
│ │ ├── dotnet-01-echo-bot
│ │ │ ├── appsettings.json
│ │ │ ├── dotnet-01-echo-bot.csproj
│ │ │ ├── MyAgent.cs
│ │ │ ├── MyAgentConfig.cs
│ │ │ ├── MyWorkbenchConnector.cs
│ │ │ ├── Program.cs
│ │ │ └── README.md
│ │ ├── dotnet-02-message-types-demo
│ │ │ ├── appsettings.json
│ │ │ ├── ConnectorExtensions.cs
│ │ │ ├── docs
│ │ │ │ ├── abc.png
│ │ │ │ ├── code.png
│ │ │ │ ├── config.png
│ │ │ │ ├── echo.png
│ │ │ │ ├── markdown.png
│ │ │ │ ├── mermaid.png
│ │ │ │ ├── reverse.png
│ │ │ │ └── safety-check.png
│ │ │ ├── dotnet-02-message-types-demo.csproj
│ │ │ ├── MyAgent.cs
│ │ │ ├── MyAgentConfig.cs
│ │ │ ├── MyWorkbenchConnector.cs
│ │ │ ├── Program.cs
│ │ │ └── README.md
│ │ └── dotnet-03-simple-chatbot
│ │ ├── appsettings.json
│ │ ├── ConnectorExtensions.cs
│ │ ├── dotnet-03-simple-chatbot.csproj
│ │ ├── MyAgent.cs
│ │ ├── MyAgentConfig.cs
│ │ ├── MyWorkbenchConnector.cs
│ │ ├── Program.cs
│ │ └── README.md
│ ├── Makefile
│ └── python
│ ├── python-01-echo-bot
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ └── config.py
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── python-02-simple-chatbot
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant
│ │ │ ├── __init__.py
│ │ │ ├── chat.py
│ │ │ ├── config.py
│ │ │ └── text_includes
│ │ │ └── guardrails_prompt.txt
│ │ ├── assistant.code-workspace
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ └── python-03-multimodel-chatbot
│ ├── .env.example
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── assistant
│ │ ├── __init__.py
│ │ ├── chat.py
│ │ ├── config.py
│ │ ├── model_adapters.py
│ │ └── text_includes
│ │ └── guardrails_prompt.txt
│ ├── assistant.code-workspace
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ └── uv.lock
├── KNOWN_ISSUES.md
├── libraries
│ ├── dotnet
│ │ ├── .editorconfig
│ │ ├── pack.sh
│ │ ├── README.md
│ │ ├── SemanticWorkbench.sln
│ │ ├── SemanticWorkbench.sln.DotSettings
│ │ └── WorkbenchConnector
│ │ ├── AgentBase.cs
│ │ ├── AgentConfig
│ │ │ ├── AgentConfigBase.cs
│ │ │ ├── AgentConfigPropertyAttribute.cs
│ │ │ └── ConfigUtils.cs
│ │ ├── Constants.cs
│ │ ├── IAgentBase.cs
│ │ ├── icon.png
│ │ ├── Models
│ │ │ ├── Command.cs
│ │ │ ├── Conversation.cs
│ │ │ ├── ConversationEvent.cs
│ │ │ ├── DebugInfo.cs
│ │ │ ├── Insight.cs
│ │ │ ├── Message.cs
│ │ │ ├── MessageMetadata.cs
│ │ │ ├── Participant.cs
│ │ │ ├── Sender.cs
│ │ │ └── ServiceInfo.cs
│ │ ├── Storage
│ │ │ ├── AgentInfo.cs
│ │ │ ├── AgentServiceStorage.cs
│ │ │ └── IAgentServiceStorage.cs
│ │ ├── StringLoggingExtensions.cs
│ │ ├── Webservice.cs
│ │ ├── WorkbenchConfig.cs
│ │ ├── WorkbenchConnector.cs
│ │ └── WorkbenchConnector.csproj
│ ├── Makefile
│ └── python
│ ├── anthropic-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── anthropic_client
│ │ │ ├── __init__.py
│ │ │ ├── client.py
│ │ │ ├── config.py
│ │ │ └── messages.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── assistant-data-gen
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── assistant_data_gen
│ │ │ ├── __init__.py
│ │ │ ├── assistant_api.py
│ │ │ ├── config.py
│ │ │ ├── gce
│ │ │ │ ├── __init__.py
│ │ │ │ ├── gce_agent.py
│ │ │ │ └── prompts.py
│ │ │ └── pydantic_ai_utils.py
│ │ ├── configs
│ │ │ └── document_assistant_example_config.yaml
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── scripts
│ │ │ ├── gce_simulation.py
│ │ │ └── generate_scenario.py
│ │ └── uv.lock
│ ├── assistant-drive
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ └── settings.json
│ │ ├── assistant_drive
│ │ │ ├── __init__.py
│ │ │ ├── drive.py
│ │ │ └── tests
│ │ │ └── test_basic.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── pytest.ini
│ │ ├── README.md
│ │ ├── usage.ipynb
│ │ └── uv.lock
│ ├── assistant-extensions
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── assistant_extensions
│ │ │ ├── __init__.py
│ │ │ ├── ai_clients
│ │ │ │ └── config.py
│ │ │ ├── artifacts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _artifacts.py
│ │ │ │ ├── _inspector.py
│ │ │ │ └── _model.py
│ │ │ ├── attachments
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _attachments.py
│ │ │ │ ├── _convert.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _shared.py
│ │ │ │ └── _summarizer.py
│ │ │ ├── chat_context_toolkit
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _config.py
│ │ │ │ ├── archive
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── _archive.py
│ │ │ │ │ └── _summarizer.py
│ │ │ │ ├── message_history
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── _history.py
│ │ │ │ │ └── _message.py
│ │ │ │ └── virtual_filesystem
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _archive_file_source.py
│ │ │ │ └── _attachments_file_source.py
│ │ │ ├── dashboard_card
│ │ │ │ ├── __init__.py
│ │ │ │ └── _dashboard_card.py
│ │ │ ├── document_editor
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _extension.py
│ │ │ │ ├── _inspector.py
│ │ │ │ └── _model.py
│ │ │ ├── mcp
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _assistant_file_resource_handler.py
│ │ │ │ ├── _client_utils.py
│ │ │ │ ├── _devtunnel.py
│ │ │ │ ├── _model.py
│ │ │ │ ├── _openai_utils.py
│ │ │ │ ├── _sampling_handler.py
│ │ │ │ ├── _tool_utils.py
│ │ │ │ └── _workbench_file_resource_handler.py
│ │ │ ├── navigator
│ │ │ │ ├── __init__.py
│ │ │ │ └── _navigator.py
│ │ │ └── workflows
│ │ │ ├── __init__.py
│ │ │ ├── _model.py
│ │ │ ├── _workflows.py
│ │ │ └── runners
│ │ │ └── _user_proxy.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ └── attachments
│ │ │ └── test_attachments.py
│ │ └── uv.lock
│ ├── chat-context-toolkit
│ │ ├── .claude
│ │ │ └── settings.local.json
│ │ ├── .env.sample
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── assets
│ │ │ ├── archive_v1.png
│ │ │ ├── history_v1.png
│ │ │ └── vfs_v1.png
│ │ ├── chat_context_toolkit
│ │ │ ├── __init__.py
│ │ │ ├── archive
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _archive_reader.py
│ │ │ │ ├── _archive_task_queue.py
│ │ │ │ ├── _state.py
│ │ │ │ ├── _types.py
│ │ │ │ └── summarization
│ │ │ │ ├── __init__.py
│ │ │ │ └── _summarizer.py
│ │ │ ├── history
│ │ │ │ ├── __init__.py
│ │ │ │ ├── _budget.py
│ │ │ │ ├── _decorators.py
│ │ │ │ ├── _history.py
│ │ │ │ ├── _prioritize.py
│ │ │ │ ├── _types.py
│ │ │ │ └── tool_abbreviations
│ │ │ │ ├── __init__.py
│ │ │ │ └── _tool_abbreviations.py
│ │ │ └── virtual_filesystem
│ │ │ ├── __init__.py
│ │ │ ├── _types.py
│ │ │ ├── _virtual_filesystem.py
│ │ │ ├── README.md
│ │ │ └── tools
│ │ │ ├── __init__.py
│ │ │ ├── _ls_tool.py
│ │ │ ├── _tools.py
│ │ │ └── _view_tool.py
│ │ ├── CLAUDE.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ ├── archive
│ │ │ │ └── test_archive_reader.py
│ │ │ ├── history
│ │ │ │ ├── test_abbreviate_messages.py
│ │ │ │ ├── test_history.py
│ │ │ │ ├── test_pair_and_order_tool_messages.py
│ │ │ │ ├── test_prioritize.py
│ │ │ │ └── test_truncate_messages.py
│ │ │ └── virtual_filesystem
│ │ │ ├── test_virtual_filesystem.py
│ │ │ └── tools
│ │ │ ├── test_ls_tool.py
│ │ │ ├── test_tools.py
│ │ │ └── test_view_tool.py
│ │ └── uv.lock
│ ├── content-safety
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── content_safety
│ │ │ ├── __init__.py
│ │ │ ├── evaluators
│ │ │ │ ├── __init__.py
│ │ │ │ ├── azure_content_safety
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── config.py
│ │ │ │ │ └── evaluator.py
│ │ │ │ ├── config.py
│ │ │ │ ├── evaluator.py
│ │ │ │ └── openai_moderations
│ │ │ │ ├── __init__.py
│ │ │ │ ├── config.py
│ │ │ │ └── evaluator.py
│ │ │ └── README.md
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── events
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── events
│ │ │ ├── __init__.py
│ │ │ └── events.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── guided-conversation
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── guided_conversation
│ │ │ ├── __init__.py
│ │ │ ├── functions
│ │ │ │ ├── __init__.py
│ │ │ │ ├── conversation_plan.py
│ │ │ │ ├── execution.py
│ │ │ │ └── final_update_plan.py
│ │ │ ├── guided_conversation_agent.py
│ │ │ ├── plugins
│ │ │ │ ├── __init__.py
│ │ │ │ ├── agenda.py
│ │ │ │ └── artifact.py
│ │ │ └── utils
│ │ │ ├── __init__.py
│ │ │ ├── base_model_llm.py
│ │ │ ├── conversation_helpers.py
│ │ │ ├── openai_tool_calling.py
│ │ │ ├── plugin_helpers.py
│ │ │ └── resources.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── llm-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── llm_client
│ │ │ ├── __init__.py
│ │ │ └── model.py
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── Makefile
│ ├── mcp-extensions
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_extensions
│ │ │ ├── __init__.py
│ │ │ ├── _client_session.py
│ │ │ ├── _model.py
│ │ │ ├── _sampling.py
│ │ │ ├── _server_extensions.py
│ │ │ ├── _tool_utils.py
│ │ │ ├── llm
│ │ │ │ ├── __init__.py
│ │ │ │ ├── chat_completion.py
│ │ │ │ ├── helpers.py
│ │ │ │ ├── llm_types.py
│ │ │ │ ├── mcp_chat_completion.py
│ │ │ │ └── openai_chat_completion.py
│ │ │ └── server
│ │ │ ├── __init__.py
│ │ │ └── storage.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_tool_utils.py
│ │ └── uv.lock
│ ├── mcp-tunnel
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_tunnel
│ │ │ ├── __init__.py
│ │ │ ├── _devtunnel.py
│ │ │ ├── _dir.py
│ │ │ └── _main.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── openai-client
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── openai_client
│ │ │ ├── __init__.py
│ │ │ ├── chat_driver
│ │ │ │ ├── __init__.py
│ │ │ │ ├── chat_driver.ipynb
│ │ │ │ ├── chat_driver.py
│ │ │ │ ├── message_history_providers
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── in_memory_message_history_provider.py
│ │ │ │ │ ├── local_message_history_provider.py
│ │ │ │ │ ├── message_history_provider.py
│ │ │ │ │ └── tests
│ │ │ │ │ └── formatted_instructions_test.py
│ │ │ │ └── README.md
│ │ │ ├── client.py
│ │ │ ├── completion.py
│ │ │ ├── config.py
│ │ │ ├── errors.py
│ │ │ ├── logging.py
│ │ │ ├── messages.py
│ │ │ ├── tokens.py
│ │ │ └── tools.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── test_command_parsing.py
│ │ │ ├── test_formatted_messages.py
│ │ │ ├── test_messages.py
│ │ │ └── test_tokens.py
│ │ └── uv.lock
│ ├── semantic-workbench-api-model
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── semantic_workbench_api_model
│ │ │ ├── __init__.py
│ │ │ ├── assistant_model.py
│ │ │ ├── assistant_service_client.py
│ │ │ ├── workbench_model.py
│ │ │ └── workbench_service_client.py
│ │ └── uv.lock
│ ├── semantic-workbench-assistant
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── semantic_workbench_assistant
│ │ │ ├── __init__.py
│ │ │ ├── assistant_app
│ │ │ │ ├── __init__.py
│ │ │ │ ├── assistant.py
│ │ │ │ ├── config.py
│ │ │ │ ├── content_safety.py
│ │ │ │ ├── context.py
│ │ │ │ ├── error.py
│ │ │ │ ├── export_import.py
│ │ │ │ ├── protocol.py
│ │ │ │ └── service.py
│ │ │ ├── assistant_service.py
│ │ │ ├── auth.py
│ │ │ ├── canonical.py
│ │ │ ├── command.py
│ │ │ ├── config.py
│ │ │ ├── logging_config.py
│ │ │ ├── settings.py
│ │ │ ├── start.py
│ │ │ └── storage.py
│ │ ├── tests
│ │ │ ├── conftest.py
│ │ │ ├── test_assistant_app.py
│ │ │ ├── test_canonical.py
│ │ │ ├── test_config.py
│ │ │ └── test_storage.py
│ │ └── uv.lock
│ └── skills
│ ├── .vscode
│ │ └── settings.json
│ ├── Makefile
│ ├── README.md
│ └── skill-library
│ ├── .vscode
│ │ └── settings.json
│ ├── docs
│ │ └── vs-recipe-tool.md
│ ├── Makefile
│ ├── pyproject.toml
│ ├── README.md
│ ├── skill_library
│ │ ├── __init__.py
│ │ ├── chat_driver_helpers.py
│ │ ├── cli
│ │ │ ├── azure_openai.py
│ │ │ ├── conversation_history.py
│ │ │ ├── README.md
│ │ │ ├── run_routine.py
│ │ │ ├── settings.py
│ │ │ └── skill_logger.py
│ │ ├── engine.py
│ │ ├── llm_info.txt
│ │ ├── logging.py
│ │ ├── README.md
│ │ ├── routine_stack.py
│ │ ├── skill.py
│ │ ├── skills
│ │ │ ├── common
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── bing_search.py
│ │ │ │ ├── consolidate.py
│ │ │ │ ├── echo.py
│ │ │ │ ├── gather_context.py
│ │ │ │ ├── get_content_from_url.py
│ │ │ │ ├── gpt_complete.py
│ │ │ │ ├── select_user_intent.py
│ │ │ │ └── summarize.py
│ │ │ ├── eval
│ │ │ │ ├── __init__.py
│ │ │ │ ├── eval_skill.py
│ │ │ │ └── routines
│ │ │ │ └── eval.py
│ │ │ ├── fabric
│ │ │ │ ├── __init__.py
│ │ │ │ ├── fabric_skill.py
│ │ │ │ ├── patterns
│ │ │ │ │ ├── agility_story
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── ai
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_answers
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_candidates
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_cfp_submission
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_claims
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_comments
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_debate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_email_headers
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_incident
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_interviewer_techniques
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_logs
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_malware
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_military_strategy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_mistakes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_paper
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_patent
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_personality
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_presentation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_product_feedback
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_proposition
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose_json
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_prose_pinker
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_risk
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_sales_call
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_spiritual_text
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_tech_impact
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_threat_report
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── analyze_threat_report_cmds
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── analyze_threat_report_trends
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── answer_interview_question
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── ask_secure_by_design_questions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── ask_uncle_duke
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── capture_thinkers_work
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── check_agreement
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── clean_text
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── coding_master
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── compare_and_contrast
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── convert_to_markdown
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_5_sentence_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_academic_paper
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ai_jobs_analysis
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_aphorisms
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_art_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_better_frame
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_coding_project
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_command
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_cyber_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_design_document
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_diy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_formal_email
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_git_diff_commit
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_graph_from_input
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_hormozi_offer
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_idea_compass
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_investigation_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_keynote
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_logo
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_markmap_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_mermaid_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_mermaid_visualization_for_github
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_micro_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_network_threat_landscape
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_newsletter_entry
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_npc
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_pattern
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_prd
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_prediction_block
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_quiz
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_reading_plan
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_recursive_outline
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_report_finding
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_rpg_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_security_update
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_show_intro
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_sigma_rules
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_story_explanation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_stride_threat_model
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_summary
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_tags
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_threat_scenarios
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ttrc_graph
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_ttrc_narrative
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_upgrade_pack
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_user_story
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── create_video_chapters
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── create_visualization
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── dialog_with_socrates
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── enrich_blog_post
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_code
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── explain_docs
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── explain_math
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_project
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── explain_terms
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── export_data_as_csv
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_algorithm_update_recommendations
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_article_wisdom
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_book_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_book_recommendations
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_business_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_controversial_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_core_message
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_ctf_writeup
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_domains
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_extraordinary_claims
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_ideas
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_insights
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_insights_dm
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_instructions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_jokes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_latest_video
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_main_idea
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_most_redeeming_thing
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_patterns
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_poc
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_predictions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_primary_problem
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_primary_solution
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_product_features
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_questions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_recipe
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_recommendations
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_references
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_skills
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_song_meaning
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_sponsors
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_videoid
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── extract_wisdom
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── extract_wisdom-1.0.0
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_agents
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_dm
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── extract_wisdom_nometa
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── find_hidden_message
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── find_logical_fallacies
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── get_wow_per_minute
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── get_youtube_rss
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── humanize
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_distinctions
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_perspectives
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_relationships
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_dsrp_systems
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── identify_job_stories
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── improve_academic_writing
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── improve_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── improve_report_finding
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── improve_writing
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── judge_output
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── label_and_rate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── loaded
│ │ │ │ │ ├── md_callout
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── official_pattern_template
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── pattern_explanations.md
│ │ │ │ │ ├── prepare_7s_strategy
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── provide_guidance
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_ai_response
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_ai_result
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── rate_content
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── rate_value
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── raw_query
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── raycast
│ │ │ │ │ │ ├── capture_thinkers_work
│ │ │ │ │ │ ├── create_story_explanation
│ │ │ │ │ │ ├── extract_primary_problem
│ │ │ │ │ │ ├── extract_wisdom
│ │ │ │ │ │ └── yt
│ │ │ │ │ ├── recommend_artists
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── recommend_pipeline_upgrades
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── recommend_talkpanel_topics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── refine_design_document
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── review_design
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── sanitize_broken_html_to_markdown
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── show_fabric_options_markmap
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── solve_with_cot
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── stringify
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── suggest_pattern
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize
│ │ │ │ │ │ ├── dmiessler
│ │ │ │ │ │ │ └── summarize
│ │ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ │ └── user.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_debate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_git_changes
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_git_diff
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_lecture
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_legislation
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_meeting
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_micro
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_newsletter
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_paper
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_prompt
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── summarize_pull-requests
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── summarize_rpg_session
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_analyze_challenge_handling
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_check_metrics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_create_h3_career
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_create_opening_sentences
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_describe_life_outlook
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_extract_intro_sentences
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_extract_panel_topics
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_blindspots
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_negative_thinking
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_find_neglected_goals
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_give_encouragement
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_red_team_thinking
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_threat_model_plans
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_visualize_mission_goals_projects
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── t_year_in_review
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── to_flashcards
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── transcribe_minutes
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── translate
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── tweet
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_essay
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_hackerone_report
│ │ │ │ │ │ ├── README.md
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_latex
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_micro_essay
│ │ │ │ │ │ └── system.md
│ │ │ │ │ ├── write_nuclei_template_rule
│ │ │ │ │ │ ├── system.md
│ │ │ │ │ │ └── user.md
│ │ │ │ │ ├── write_pull-request
│ │ │ │ │ │ └── system.md
│ │ │ │ │ └── write_semgrep_rule
│ │ │ │ │ ├── system.md
│ │ │ │ │ └── user.md
│ │ │ │ └── routines
│ │ │ │ ├── list.py
│ │ │ │ ├── run.py
│ │ │ │ └── show.py
│ │ │ ├── guided_conversation
│ │ │ │ ├── __init__.py
│ │ │ │ ├── agenda.py
│ │ │ │ ├── artifact_helpers.py
│ │ │ │ ├── chat_completions
│ │ │ │ │ ├── fix_agenda_error.py
│ │ │ │ │ ├── fix_artifact_error.py
│ │ │ │ │ ├── generate_agenda.py
│ │ │ │ │ ├── generate_artifact_updates.py
│ │ │ │ │ ├── generate_final_artifact.py
│ │ │ │ │ └── generate_message.py
│ │ │ │ ├── conversation_guides
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── acrostic_poem.py
│ │ │ │ │ ├── er_triage.py
│ │ │ │ │ ├── interview.py
│ │ │ │ │ └── patient_intake.py
│ │ │ │ ├── guide.py
│ │ │ │ ├── guided_conversation_skill.py
│ │ │ │ ├── logging.py
│ │ │ │ ├── message.py
│ │ │ │ ├── resources.py
│ │ │ │ ├── routines
│ │ │ │ │ └── guided_conversation.py
│ │ │ │ └── tests
│ │ │ │ ├── conftest.py
│ │ │ │ ├── test_artifact_helpers.py
│ │ │ │ ├── test_generate_agenda.py
│ │ │ │ ├── test_generate_artifact_updates.py
│ │ │ │ ├── test_generate_final_artifact.py
│ │ │ │ └── test_resource.py
│ │ │ ├── meta
│ │ │ │ ├── __init__.py
│ │ │ │ ├── meta_skill.py
│ │ │ │ ├── README.md
│ │ │ │ └── routines
│ │ │ │ └── generate_routine.py
│ │ │ ├── posix
│ │ │ │ ├── __init__.py
│ │ │ │ ├── posix_skill.py
│ │ │ │ ├── routines
│ │ │ │ │ ├── append_file.py
│ │ │ │ │ ├── cd.py
│ │ │ │ │ ├── ls.py
│ │ │ │ │ ├── make_home_dir.py
│ │ │ │ │ ├── mkdir.py
│ │ │ │ │ ├── mv.py
│ │ │ │ │ ├── pwd.py
│ │ │ │ │ ├── read_file.py
│ │ │ │ │ ├── rm.py
│ │ │ │ │ ├── touch.py
│ │ │ │ │ └── write_file.py
│ │ │ │ └── sandbox_shell.py
│ │ │ ├── README.md
│ │ │ ├── research
│ │ │ │ ├── __init__.py
│ │ │ │ ├── README.md
│ │ │ │ ├── research_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── answer_question_about_content.py
│ │ │ │ ├── evaluate_answer.py
│ │ │ │ ├── generate_research_plan.py
│ │ │ │ ├── generate_search_query.py
│ │ │ │ ├── update_research_plan.py
│ │ │ │ ├── web_research.py
│ │ │ │ └── web_search.py
│ │ │ ├── research2
│ │ │ │ ├── __init__.py
│ │ │ │ ├── README.md
│ │ │ │ ├── research_skill.py
│ │ │ │ └── routines
│ │ │ │ ├── facts.py
│ │ │ │ ├── make_final_report.py
│ │ │ │ ├── research.py
│ │ │ │ ├── search_plan.py
│ │ │ │ ├── search.py
│ │ │ │ └── visit_pages.py
│ │ │ └── web_research
│ │ │ ├── __init__.py
│ │ │ ├── README.md
│ │ │ ├── research_skill.py
│ │ │ └── routines
│ │ │ ├── facts.py
│ │ │ ├── make_final_report.py
│ │ │ ├── research.py
│ │ │ ├── search_plan.py
│ │ │ ├── search.py
│ │ │ └── visit_pages.py
│ │ ├── tests
│ │ │ ├── test_common_skill.py
│ │ │ ├── test_integration.py
│ │ │ ├── test_routine_stack.py
│ │ │ ├── tst_skill
│ │ │ │ ├── __init__.py
│ │ │ │ └── routines
│ │ │ │ ├── __init__.py
│ │ │ │ └── a_routine.py
│ │ │ └── utilities
│ │ │ ├── test_find_template_vars.py
│ │ │ ├── test_make_arg_set.py
│ │ │ ├── test_paramspec.py
│ │ │ ├── test_parse_command_string.py
│ │ │ └── test_to_string.py
│ │ ├── types.py
│ │ ├── usage.py
│ │ └── utilities.py
│ └── uv.lock
├── LICENSE
├── Makefile
├── mcp-servers
│ ├── ai-assist-content
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── mcp-example-brave-search.md
│ │ ├── mcp-fastmcp-typescript-README.md
│ │ ├── mcp-llms-full.txt
│ │ ├── mcp-metadata-tips.md
│ │ ├── mcp-python-sdk-README.md
│ │ ├── mcp-typescript-sdk-README.md
│ │ ├── pydanticai-documentation.md
│ │ ├── pydanticai-example-question-graph.md
│ │ ├── pydanticai-example-weather.md
│ │ ├── pydanticai-tutorial.md
│ │ └── README.md
│ ├── Makefile
│ ├── mcp-server-bing-search
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_bing_search
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── clean_website.py
│ │ │ │ └── filter_links.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── tools.py
│ │ │ ├── types.py
│ │ │ ├── utils.py
│ │ │ └── web
│ │ │ ├── __init__.py
│ │ │ ├── get_content.py
│ │ │ ├── llm_processing.py
│ │ │ ├── process_website.py
│ │ │ └── search_bing.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_tools.py
│ │ └── uv.lock
│ ├── mcp-server-bundle
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_bundle
│ │ │ ├── __init__.py
│ │ │ └── main.py
│ │ ├── pyinstaller.spec
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-filesystem
│ │ ├── .env.example
│ │ ├── .github
│ │ │ └── workflows
│ │ │ └── ci.yml
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_filesystem
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_filesystem.py
│ │ └── uv.lock
│ ├── mcp-server-filesystem-edit
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── data
│ │ │ ├── attachments
│ │ │ │ ├── Daily Game Ideas.txt
│ │ │ │ ├── Frontend Framework Proposal.txt
│ │ │ │ ├── ReDoodle.txt
│ │ │ │ └── Research Template.tex
│ │ │ ├── test_cases.yaml
│ │ │ └── transcripts
│ │ │ ├── transcript_research_simple.md
│ │ │ ├── transcript_Startup_Idea_1_202503031513.md
│ │ │ ├── transcript_Startup_Idea_2_202503031659.md
│ │ │ └── transcript_Web_Frontends_202502281551.md
│ │ ├── Makefile
│ │ ├── mcp_server_filesystem_edit
│ │ │ ├── __init__.py
│ │ │ ├── app_handling
│ │ │ │ ├── __init__.py
│ │ │ │ ├── excel.py
│ │ │ │ ├── miktex.py
│ │ │ │ ├── office_common.py
│ │ │ │ ├── powerpoint.py
│ │ │ │ └── word.py
│ │ │ ├── config.py
│ │ │ ├── evals
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common.py
│ │ │ │ ├── run_comments.py
│ │ │ │ ├── run_edit.py
│ │ │ │ └── run_ppt_edit.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── add_comments.py
│ │ │ │ ├── analyze_comments.py
│ │ │ │ ├── latex_edit.py
│ │ │ │ ├── markdown_draft.py
│ │ │ │ ├── markdown_edit.py
│ │ │ │ └── powerpoint_edit.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── add_comments.py
│ │ │ │ ├── edit_adapters
│ │ │ │ │ ├── __init__.py
│ │ │ │ │ ├── common.py
│ │ │ │ │ ├── latex.py
│ │ │ │ │ └── markdown.py
│ │ │ │ ├── edit.py
│ │ │ │ └── helpers.py
│ │ │ └── types.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ ├── app_handling
│ │ │ │ ├── test_excel.py
│ │ │ │ ├── test_miktext.py
│ │ │ │ ├── test_office_common.py
│ │ │ │ ├── test_powerpoint.py
│ │ │ │ └── test_word.py
│ │ │ ├── conftest.py
│ │ │ └── tools
│ │ │ └── edit_adapters
│ │ │ ├── test_latex.py
│ │ │ └── test_markdown.py
│ │ └── uv.lock
│ ├── mcp-server-fusion
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── AddInIcon.svg
│ │ ├── config.py
│ │ ├── FusionMCPServerAddIn.manifest
│ │ ├── FusionMCPServerAddIn.py
│ │ ├── mcp_server_fusion
│ │ │ ├── __init__.py
│ │ │ ├── fusion_mcp_server.py
│ │ │ ├── fusion_utils
│ │ │ │ ├── __init__.py
│ │ │ │ ├── event_utils.py
│ │ │ │ ├── general_utils.py
│ │ │ │ └── tool_utils.py
│ │ │ ├── mcp_tools
│ │ │ │ ├── __init__.py
│ │ │ │ ├── fusion_3d_operation.py
│ │ │ │ ├── fusion_geometry.py
│ │ │ │ ├── fusion_pattern.py
│ │ │ │ └── fusion_sketch.py
│ │ │ └── vendor
│ │ │ └── README.md
│ │ ├── README.md
│ │ └── requirements.txt
│ ├── mcp-server-giphy
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── giphy_search.py
│ │ │ ├── sampling.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ └── utils.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-memory-user-bio
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_memory_user_bio
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-memory-whiteboard
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_memory_whiteboard
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-office
│ │ ├── .env.example
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── build.sh
│ │ ├── data
│ │ │ ├── attachments
│ │ │ │ ├── Daily Game Ideas.txt
│ │ │ │ ├── Frontend Framework Proposal.txt
│ │ │ │ └── ReDoodle.txt
│ │ │ └── word
│ │ │ ├── test_cases.yaml
│ │ │ └── transcripts
│ │ │ ├── transcript_Startup_Idea_1_202503031513.md
│ │ │ ├── transcript_Startup_Idea_2_202503031659.md
│ │ │ └── transcript_Web_Frontends_202502281551.md
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── app_interaction
│ │ │ │ ├── __init__.py
│ │ │ │ ├── excel_editor.py
│ │ │ │ ├── powerpoint_editor.py
│ │ │ │ └── word_editor.py
│ │ │ ├── config.py
│ │ │ ├── constants.py
│ │ │ ├── evals
│ │ │ │ ├── __init__.py
│ │ │ │ ├── common.py
│ │ │ │ ├── run_comment_analysis.py
│ │ │ │ ├── run_feedback.py
│ │ │ │ └── run_markdown_edit.py
│ │ │ ├── helpers.py
│ │ │ ├── markdown_edit
│ │ │ │ ├── __init__.py
│ │ │ │ ├── comment_analysis.py
│ │ │ │ ├── feedback_step.py
│ │ │ │ ├── markdown_edit.py
│ │ │ │ └── utils.py
│ │ │ ├── prompts
│ │ │ │ ├── __init__.py
│ │ │ │ ├── comment_analysis.py
│ │ │ │ ├── feedback.py
│ │ │ │ ├── markdown_draft.py
│ │ │ │ └── markdown_edit.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ └── types.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── tests
│ │ │ └── test_word_editor.py
│ │ └── uv.lock
│ ├── mcp-server-open-deep-research
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server
│ │ │ ├── __init__.py
│ │ │ ├── config.py
│ │ │ ├── libs
│ │ │ │ └── open_deep_research
│ │ │ │ ├── cookies.py
│ │ │ │ ├── mdconvert.py
│ │ │ │ ├── run_agents.py
│ │ │ │ ├── text_inspector_tool.py
│ │ │ │ ├── text_web_browser.py
│ │ │ │ └── visual_qa.py
│ │ │ ├── open_deep_research.py
│ │ │ ├── server.py
│ │ │ └── start.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ └── uv.lock
│ ├── mcp-server-open-deep-research-clone
│ │ ├── .env.example
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json
│ │ │ └── settings.json
│ │ ├── Makefile
│ │ ├── mcp_server_open_deep_research_clone
│ │ │ ├── __init__.py
│ │ │ ├── azure_openai.py
│ │ │ ├── config.py
│ │ │ ├── logging.py
│ │ │ ├── sampling.py
│ │ │ ├── server.py
│ │ │ ├── start.py
│ │ │ ├── utils.py
│ │ │ └── web_research.py
│ │ ├── pyproject.toml
│ │ ├── README.md
│ │ ├── test
│ │ │ └── test_open_deep_research_clone.py
│ │ └── uv.lock
│ ├── mcp-server-template
│ │ ├── .taplo.toml
│ │ ├── .vscode
│ │ │ └── settings.json
│ │ ├── copier.yml
│ │ ├── README.md
│ │ └── template
│ │ └── {{ project_slug }}
│ │ ├── .env.example.jinja
│ │ ├── .gitignore
│ │ ├── .vscode
│ │ │ ├── launch.json.jinja
│ │ │ └── settings.json
│ │ ├── {{ module_name }}
│ │ │ ├── __init__.py
│ │ │ ├── config.py.jinja
│ │ │ ├── server.py.jinja
│ │ │ └── start.py.jinja
│ │ ├── Makefile.jinja
│ │ ├── pyproject.toml.jinja
│ │ └── README.md.jinja
│ ├── mcp-server-vscode
│ │ ├── .eslintrc.cjs
│ │ ├── .gitignore
│ │ ├── .npmrc
│ │ ├── .vscode
│ │ │ ├── extensions.json
│ │ │ ├── launch.json
│ │ │ ├── settings.json
│ │ │ └── tasks.json
│ │ ├── .vscode-test.mjs
│ │ ├── .vscodeignore
│ │ ├── ASSISTANT_BOOTSTRAP.md
│ │ ├── eslint.config.mjs
│ │ ├── images
│ │ │ └── icon.png
│ │ ├── LICENSE
│ │ ├── Makefile
│ │ ├── out
│ │ │ ├── extension.d.ts
│ │ │ ├── extension.js
│ │ │ ├── test
│ │ │ │ ├── extension.test.d.ts
│ │ │ │ └── extension.test.js
│ │ │ ├── tools
│ │ │ │ ├── code_checker.d.ts
│ │ │ │ ├── code_checker.js
│ │ │ │ ├── debug_tools.d.ts
│ │ │ │ ├── debug_tools.js
│ │ │ │ ├── focus_editor.d.ts
│ │ │ │ ├── focus_editor.js
│ │ │ │ ├── search_symbol.d.ts
│ │ │ │ └── search_symbol.js
│ │ │ └── utils
│ │ │ ├── port.d.ts
│ │ │ └── port.js
│ │ ├── package.json
│ │ ├── pnpm-lock.yaml
│ │ ├── prettier.config.cjs
│ │ ├── README.md
│ │ ├── src
│ │ │ ├── extension.d.ts
│ │ │ ├── extension.ts
│ │ │ ├── test
│ │ │ │ ├── extension.test.d.ts
│ │ │ │ └── extension.test.ts
│ │ │ ├── tools
│ │ │ │ ├── code_checker.d.ts
│ │ │ │ ├── code_checker.ts
│ │ │ │ ├── debug_tools.d.ts
│ │ │ │ ├── debug_tools.ts
│ │ │ │ ├── focus_editor.d.ts
│ │ │ │ ├── focus_editor.ts
│ │ │ │ ├── search_symbol.d.ts
│ │ │ │ └── search_symbol.ts
│ │ │ └── utils
│ │ │ ├── port.d.ts
│ │ │ └── port.ts
│ │ ├── tsconfig.json
│ │ ├── tsconfig.tsbuildinfo
│ │ ├── vsc-extension-quickstart.md
│ │ └── webpack.config.js
│ └── mcp-server-web-research
│ ├── .env.example
│ ├── .gitignore
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── Makefile
│ ├── mcp_server_web_research
│ │ ├── __init__.py
│ │ ├── azure_openai.py
│ │ ├── config.py
│ │ ├── logging.py
│ │ ├── sampling.py
│ │ ├── server.py
│ │ ├── start.py
│ │ ├── utils.py
│ │ └── web_research.py
│ ├── pyproject.toml
│ ├── README.md
│ ├── test
│ │ └── test_web_research.py
│ └── uv.lock
├── README.md
├── RESPONSIBLE_AI_FAQ.md
├── ruff.toml
├── SECURITY.md
├── semantic-workbench.code-workspace
├── SUPPORT.md
├── tools
│ ├── build_ai_context_files.py
│ ├── collect_files.py
│ ├── docker
│ │ ├── azure_website_sshd.conf
│ │ ├── docker-entrypoint.sh
│ │ ├── Dockerfile.assistant
│ │ └── Dockerfile.mcp-server
│ ├── makefiles
│ │ ├── docker-assistant.mk
│ │ ├── docker-mcp-server.mk
│ │ ├── docker.mk
│ │ ├── python.mk
│ │ ├── recursive.mk
│ │ └── shell.mk
│ ├── reset-service-data.ps1
│ ├── reset-service-data.sh
│ ├── run-app.ps1
│ ├── run-app.sh
│ ├── run-canonical-agent.ps1
│ ├── run-canonical-agent.sh
│ ├── run-dotnet-examples-with-aspire.sh
│ ├── run-python-example1.sh
│ ├── run-python-example2.ps1
│ ├── run-python-example2.sh
│ ├── run-service.ps1
│ ├── run-service.sh
│ ├── run-workbench-chatbot.ps1
│ └── run-workbench-chatbot.sh
├── workbench-app
│ ├── .dockerignore
│ ├── .env.example
│ ├── .eslintrc.cjs
│ ├── .gitignore
│ ├── .vscode
│ │ ├── launch.json
│ │ └── settings.json
│ ├── docker-entrypoint.sh
│ ├── Dockerfile
│ ├── docs
│ │ ├── APP_DEV_GUIDE.md
│ │ ├── MESSAGE_METADATA.md
│ │ ├── MESSAGE_TYPES.md
│ │ ├── README.md
│ │ └── STATE_INSPECTORS.md
│ ├── index.html
│ ├── Makefile
│ ├── nginx.conf
│ ├── package.json
│ ├── pnpm-lock.yaml
│ ├── prettier.config.cjs
│ ├── public
│ │ └── assets
│ │ ├── background-1-upscaled.jpg
│ │ ├── background-1-upscaled.png
│ │ ├── background-1.jpg
│ │ ├── background-1.png
│ │ ├── background-2.jpg
│ │ ├── background-2.png
│ │ ├── experimental-feature.jpg
│ │ ├── favicon.svg
│ │ ├── workflow-designer-1.jpg
│ │ ├── workflow-designer-outlets.jpg
│ │ ├── workflow-designer-states.jpg
│ │ └── workflow-designer-transitions.jpg
│ ├── README.md
│ ├── run.sh
│ ├── src
│ │ ├── components
│ │ │ ├── App
│ │ │ │ ├── AppFooter.tsx
│ │ │ │ ├── AppHeader.tsx
│ │ │ │ ├── AppMenu.tsx
│ │ │ │ ├── AppView.tsx
│ │ │ │ ├── CodeLabel.tsx
│ │ │ │ ├── CommandButton.tsx
│ │ │ │ ├── ConfirmLeave.tsx
│ │ │ │ ├── ContentExport.tsx
│ │ │ │ ├── ContentImport.tsx
│ │ │ │ ├── CopyButton.tsx
│ │ │ │ ├── DialogControl.tsx
│ │ │ │ ├── DynamicIframe.tsx
│ │ │ │ ├── ErrorListFromAppState.tsx
│ │ │ │ ├── ErrorMessageBar.tsx
│ │ │ │ ├── ExperimentalNotice.tsx
│ │ │ │ ├── FormWidgets
│ │ │ │ │ ├── BaseModelEditorWidget.tsx
│ │ │ │ │ ├── CustomizedArrayFieldTemplate.tsx
│ │ │ │ │ ├── CustomizedFieldTemplate.tsx
│ │ │ │ │ ├── CustomizedObjectFieldTemplate.tsx
│ │ │ │ │ └── InspectableWidget.tsx
│ │ │ │ ├── LabelWithDescription.tsx
│ │ │ │ ├── Loading.tsx
│ │ │ │ ├── MenuItemControl.tsx
│ │ │ │ ├── MiniControl.tsx
│ │ │ │ ├── MyAssistantServiceRegistrations.tsx
│ │ │ │ ├── MyItemsManager.tsx
│ │ │ │ ├── OverflowMenu.tsx
│ │ │ │ ├── PresenceMotionList.tsx
│ │ │ │ ├── ProfileSettings.tsx
│ │ │ │ └── TooltipWrapper.tsx
│ │ │ ├── Assistants
│ │ │ │ ├── ApplyConfigButton.tsx
│ │ │ │ ├── AssistantAdd.tsx
│ │ │ │ ├── AssistantConfigExportButton.tsx
│ │ │ │ ├── AssistantConfigImportButton.tsx
│ │ │ │ ├── AssistantConfiguration.tsx
│ │ │ │ ├── AssistantConfigure.tsx
│ │ │ │ ├── AssistantCreate.tsx
│ │ │ │ ├── AssistantDelete.tsx
│ │ │ │ ├── AssistantDuplicate.tsx
│ │ │ │ ├── AssistantExport.tsx
│ │ │ │ ├── AssistantImport.tsx
│ │ │ │ ├── AssistantRemove.tsx
│ │ │ │ ├── AssistantRename.tsx
│ │ │ │ ├── AssistantServiceInfo.tsx
│ │ │ │ ├── AssistantServiceMetadata.tsx
│ │ │ │ └── MyAssistants.tsx
│ │ │ ├── AssistantServiceRegistrations
│ │ │ │ ├── AssistantServiceRegistrationApiKey.tsx
│ │ │ │ ├── AssistantServiceRegistrationApiKeyReset.tsx
│ │ │ │ ├── AssistantServiceRegistrationCreate.tsx
│ │ │ │ └── AssistantServiceRegistrationRemove.tsx
│ │ │ ├── Conversations
│ │ │ │ ├── Canvas
│ │ │ │ │ ├── AssistantCanvas.tsx
│ │ │ │ │ ├── AssistantCanvasList.tsx
│ │ │ │ │ ├── AssistantInspector.tsx
│ │ │ │ │ ├── AssistantInspectorList.tsx
│ │ │ │ │ └── ConversationCanvas.tsx
│ │ │ │ ├── ChatInputPlugins
│ │ │ │ │ ├── ClearEditorPlugin.tsx
│ │ │ │ │ ├── LexicalMenu.ts
│ │ │ │ │ ├── ParticipantMentionsPlugin.tsx
│ │ │ │ │ ├── TypeaheadMenuPlugin.css
│ │ │ │ │ └── TypeaheadMenuPlugin.tsx
│ │ │ │ ├── ContentRenderers
│ │ │ │ │ ├── CodeContentRenderer.tsx
│ │ │ │ │ ├── ContentListRenderer.tsx
│ │ │ │ │ ├── ContentRenderer.tsx
│ │ │ │ │ ├── DiffRenderer.tsx
│ │ │ │ │ ├── HtmlContentRenderer.tsx
│ │ │ │ │ ├── JsonSchemaContentRenderer.tsx
│ │ │ │ │ ├── MarkdownContentRenderer.tsx
│ │ │ │ │ ├── MarkdownEditorRenderer.tsx
│ │ │ │ │ ├── MermaidContentRenderer.tsx
│ │ │ │ │ ├── MusicABCContentRenderer.css
│ │ │ │ │ └── MusicABCContentRenderer.tsx
│ │ │ │ ├── ContextWindow.tsx
│ │ │ │ ├── ConversationCreate.tsx
│ │ │ │ ├── ConversationDuplicate.tsx
│ │ │ │ ├── ConversationExport.tsx
│ │ │ │ ├── ConversationFileIcon.tsx
│ │ │ │ ├── ConversationRemove.tsx
│ │ │ │ ├── ConversationRename.tsx
│ │ │ │ ├── ConversationShare.tsx
│ │ │ │ ├── ConversationShareCreate.tsx
│ │ │ │ ├── ConversationShareList.tsx
│ │ │ │ ├── ConversationShareView.tsx
│ │ │ │ ├── ConversationsImport.tsx
│ │ │ │ ├── ConversationTranscript.tsx
│ │ │ │ ├── DebugInspector.tsx
│ │ │ │ ├── FileItem.tsx
│ │ │ │ ├── FileList.tsx
│ │ │ │ ├── InputAttachmentList.tsx
│ │ │ │ ├── InputOptionsControl.tsx
│ │ │ │ ├── InteractHistory.tsx
│ │ │ │ ├── InteractInput.tsx
│ │ │ │ ├── Message
│ │ │ │ │ ├── AttachmentSection.tsx
│ │ │ │ │ ├── ContentRenderer.tsx
│ │ │ │ │ ├── ContentSafetyNotice.tsx
│ │ │ │ │ ├── InteractMessage.tsx
│ │ │ │ │ ├── MessageActions.tsx
│ │ │ │ │ ├── MessageBase.tsx
│ │ │ │ │ ├── MessageBody.tsx
│ │ │ │ │ ├── MessageContent.tsx
│ │ │ │ │ ├── MessageFooter.tsx
│ │ │ │ │ ├── MessageHeader.tsx
│ │ │ │ │ ├── NotificationAccordion.tsx
│ │ │ │ │ └── ToolResultMessage.tsx
│ │ │ │ ├── MessageDelete.tsx
│ │ │ │ ├── MessageLink.tsx
│ │ │ │ ├── MyConversations.tsx
│ │ │ │ ├── MyShares.tsx
│ │ │ │ ├── ParticipantAvatar.tsx
│ │ │ │ ├── ParticipantAvatarGroup.tsx
│ │ │ │ ├── ParticipantItem.tsx
│ │ │ │ ├── ParticipantList.tsx
│ │ │ │ ├── ParticipantStatus.tsx
│ │ │ │ ├── RewindConversation.tsx
│ │ │ │ ├── ShareRemove.tsx
│ │ │ │ ├── SpeechButton.tsx
│ │ │ │ └── ToolCalls.tsx
│ │ │ └── FrontDoor
│ │ │ ├── Chat
│ │ │ │ ├── AssistantDrawer.tsx
│ │ │ │ ├── CanvasDrawer.tsx
│ │ │ │ ├── Chat.tsx
│ │ │ │ ├── ChatCanvas.tsx
│ │ │ │ ├── ChatControls.tsx
│ │ │ │ └── ConversationDrawer.tsx
│ │ │ ├── Controls
│ │ │ │ ├── AssistantCard.tsx
│ │ │ │ ├── AssistantSelector.tsx
│ │ │ │ ├── AssistantServiceSelector.tsx
│ │ │ │ ├── ConversationItem.tsx
│ │ │ │ ├── ConversationList.tsx
│ │ │ │ ├── ConversationListOptions.tsx
│ │ │ │ ├── NewConversationButton.tsx
│ │ │ │ ├── NewConversationForm.tsx
│ │ │ │ └── SiteMenuButton.tsx
│ │ │ ├── GlobalContent.tsx
│ │ │ └── MainContent.tsx
│ │ ├── Constants.ts
│ │ ├── global.d.ts
│ │ ├── index.css
│ │ ├── libs
│ │ │ ├── AppStorage.ts
│ │ │ ├── AuthHelper.ts
│ │ │ ├── EventSubscriptionManager.ts
│ │ │ ├── Theme.ts
│ │ │ ├── useAssistantCapabilities.ts
│ │ │ ├── useChatCanvasController.ts
│ │ │ ├── useConversationEvents.ts
│ │ │ ├── useConversationUtility.ts
│ │ │ ├── useCreateConversation.ts
│ │ │ ├── useDebugComponentLifecycle.ts
│ │ │ ├── useDragAndDrop.ts
│ │ │ ├── useEnvironment.ts
│ │ │ ├── useExportUtility.ts
│ │ │ ├── useHistoryUtility.ts
│ │ │ ├── useKeySequence.ts
│ │ │ ├── useMediaQuery.ts
│ │ │ ├── useMicrosoftGraph.ts
│ │ │ ├── useNotify.tsx
│ │ │ ├── useParticipantUtility.tsx
│ │ │ ├── useSiteUtility.ts
│ │ │ ├── useWorkbenchEventSource.ts
│ │ │ ├── useWorkbenchService.ts
│ │ │ └── Utility.ts
│ │ ├── main.tsx
│ │ ├── models
│ │ │ ├── Assistant.ts
│ │ │ ├── AssistantCapability.ts
│ │ │ ├── AssistantServiceInfo.ts
│ │ │ ├── AssistantServiceRegistration.ts
│ │ │ ├── Config.ts
│ │ │ ├── Conversation.ts
│ │ │ ├── ConversationFile.ts
│ │ │ ├── ConversationMessage.ts
│ │ │ ├── ConversationMessageDebug.ts
│ │ │ ├── ConversationParticipant.ts
│ │ │ ├── ConversationShare.ts
│ │ │ ├── ConversationShareRedemption.ts
│ │ │ ├── ConversationState.ts
│ │ │ ├── ConversationStateDescription.ts
│ │ │ ├── ServiceEnvironment.ts
│ │ │ └── User.ts
│ │ ├── redux
│ │ │ ├── app
│ │ │ │ ├── hooks.ts
│ │ │ │ ├── rtkQueryErrorLogger.ts
│ │ │ │ └── store.ts
│ │ │ └── features
│ │ │ ├── app
│ │ │ │ ├── appSlice.ts
│ │ │ │ └── AppState.ts
│ │ │ ├── chatCanvas
│ │ │ │ ├── chatCanvasSlice.ts
│ │ │ │ └── ChatCanvasState.ts
│ │ │ ├── localUser
│ │ │ │ ├── localUserSlice.ts
│ │ │ │ └── LocalUserState.ts
│ │ │ └── settings
│ │ │ ├── settingsSlice.ts
│ │ │ └── SettingsState.ts
│ │ ├── Root.tsx
│ │ ├── routes
│ │ │ ├── AcceptTerms.tsx
│ │ │ ├── AssistantEditor.tsx
│ │ │ ├── AssistantServiceRegistrationEditor.tsx
│ │ │ ├── Dashboard.tsx
│ │ │ ├── ErrorPage.tsx
│ │ │ ├── FrontDoor.tsx
│ │ │ ├── Login.tsx
│ │ │ ├── Settings.tsx
│ │ │ ├── ShareRedeem.tsx
│ │ │ └── Shares.tsx
│ │ ├── services
│ │ │ └── workbench
│ │ │ ├── assistant.ts
│ │ │ ├── assistantService.ts
│ │ │ ├── conversation.ts
│ │ │ ├── file.ts
│ │ │ ├── index.ts
│ │ │ ├── participant.ts
│ │ │ ├── share.ts
│ │ │ ├── state.ts
│ │ │ └── workbench.ts
│ │ └── vite-env.d.ts
│ ├── tools
│ │ └── filtered-ts-prune.cjs
│ ├── tsconfig.json
│ └── vite.config.ts
└── workbench-service
├── .env.example
├── .vscode
│ ├── extensions.json
│ ├── launch.json
│ └── settings.json
├── alembic.ini
├── devdb
│ ├── docker-compose.yaml
│ └── postgresql-init.sh
├── Dockerfile
├── Makefile
├── migrations
│ ├── env.py
│ ├── README
│ ├── script.py.mako
│ └── versions
│ ├── 2024_09_19_000000_69dcda481c14_init.py
│ ├── 2024_09_19_190029_dffb1d7e219a_file_version_filename.py
│ ├── 2024_09_20_204130_b29524775484_share.py
│ ├── 2024_10_30_231536_039bec8edc33_index_message_type.py
│ ├── 2024_11_04_204029_5149c7fb5a32_conversationmessagedebug.py
│ ├── 2024_11_05_015124_245baf258e11_double_check_debugs.py
│ ├── 2024_11_25_191056_a106de176394_drop_workflow.py
│ ├── 2025_03_19_140136_aaaf792d4d72_set_user_title_set.py
│ ├── 2025_03_21_153250_3763629295ad_add_assistant_template_id.py
│ ├── 2025_05_19_163613_b2f86e981885_delete_context_transfer_assistants.py
│ └── 2025_06_18_174328_503c739152f3_delete_knowlege_transfer_assistants.py
├── pyproject.toml
├── README.md
├── semantic_workbench_service
│ ├── __init__.py
│ ├── api.py
│ ├── assistant_api_key.py
│ ├── auth.py
│ ├── azure_speech.py
│ ├── config.py
│ ├── controller
│ │ ├── __init__.py
│ │ ├── assistant_service_client_pool.py
│ │ ├── assistant_service_registration.py
│ │ ├── assistant.py
│ │ ├── conversation_share.py
│ │ ├── conversation.py
│ │ ├── convert.py
│ │ ├── exceptions.py
│ │ ├── export_import.py
│ │ ├── file.py
│ │ ├── participant.py
│ │ └── user.py
│ ├── db.py
│ ├── event.py
│ ├── files.py
│ ├── logging_config.py
│ ├── middleware.py
│ ├── query.py
│ ├── service_user_principals.py
│ ├── service.py
│ └── start.py
├── tests
│ ├── __init__.py
│ ├── conftest.py
│ ├── docker-compose.yaml
│ ├── test_assistant_api_key.py
│ ├── test_files.py
│ ├── test_integration.py
│ ├── test_middleware.py
│ ├── test_migrations.py
│ ├── test_workbench_service.py
│ └── types.py
└── uv.lock
```
# Files
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-fusion/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Fusion MCP Server
2 |
3 | Fusion MCP Server for help creating 3D models
4 |
5 | This is a [Model Context Protocol](https://github.com/modelcontextprotocol) (MCP) server project.
6 |
7 | ## Setup and Installation
8 |
9 | Simply run:
10 |
11 | ```bash
12 | pip install -r requirements.txt --target ./mcp_server_fusion/vendor
13 | ```
14 |
15 | To create the virtual environment and install dependencies.
16 |
17 | ### Running the Server
18 |
19 | - Open Autodesk Fusion
20 | - Utilities > Add-Ins > Scripts and Add-Ins...
21 | - Select the Add-Ins tab
22 | - Click the My AddIns "+" icon to add a new Add-In
23 | - Choose the _main project directory_
24 | - This is the folder that contains [FusionMCPServerAddIn.py](./FusionMCPServerAddIn.py)
25 | - After added, select `FusionMCPServerAddIn` and click `Run`
26 | - Select `Run on Startup` to have the server start automatically when Fusion starts
27 | - The server will start silently, you can test it from your terminal via:
28 |
29 | ```bash
30 | curl -N http://127.0.0.1:6050/sse
31 | ```
32 |
33 | Which should return something similar to:
34 |
35 | ```
36 | C:\>curl -N http://127.0.0.1:6010/sse
37 | event: endpoint
38 | data: /messages?sessionId=947e3ec6-7d10-442f-af8e-e8fe9779f285
39 | ```
40 |
41 | Use `Ctrl+C` to disconnect the curl command.
42 |
43 | ### Debugging the Server
44 |
45 | To run the server in debug mode, open the Scripts and Add-Ins dialog, select the `FusionMCPServerAddIn` and click `Debug`.
46 | This will launch VS Code with the project open. Use the `F5` or `Run & Debug` button and select the `mcp-servers:mcp-server-fusion (attach)` configuration and click `Start Debugging`. This will attach to the running Fusion instance and allow you to debug the server. Wait until you see that the server is listening before attempting to connect.
47 |
48 | ```
49 | c:\Users\<your_user>\AppData\Roaming\Autodesk\Autodesk Fusion 360\API\AddIns\mcp-server-fusion
50 | Starting MCP Server add-in
51 | Starting MCP server thread
52 | MCP Server add-in started successfully
53 | INFO: Started server process [43816]
54 | INFO: Waiting for application startup.
55 | INFO: Application startup complete.
56 | INFO: Uvicorn running on http://0.0.0.0:6050 (Press CTRL+C to quit)
57 | ```
58 |
59 | ## Client Configuration
60 |
61 | To use this MCP server in your setup, consider the following configuration:
62 |
63 | ### SSE
64 |
65 | The SSE URL is:
66 |
67 | ```bash
68 | http://127.0.0.1:6050/sse
69 | ```
70 |
71 | ```json
72 | {
73 | "mcpServers": {
74 | "mcp-server-fusion": {
75 | "command": "http://127.0.0.1:6050/sse",
76 | "args": []
77 | }
78 | }
79 | }
80 | ```
81 |
82 | Here are some extra instructions to consider adding to your assistant configuration, but feel free to experiment further:
83 |
84 | ```
85 | When creating models, remember the following:
86 | - Z is vertical, X is horizontal, and Y is depth
87 | - The top plane for an entity is an XY plane, at the Z coordinate of the top of the entity
88 | - The bottom plane for an entity is an XY plane, at the Z coordinate of the bottom of the entity
89 | - The front plane for an entity is an XZ plane, at the Y coordinate of the front of the entity
90 | - The back plane for an entity is an XZ plane, at the Y coordinate of the back of the entity
91 | - The left plane for an entity is a YZ plane, at the X coordinate of the left of the entity
92 | - The right plane for an entity is a YZ plane, at the X coordinate of the right of the entity
93 | - Remember to always use the correct plane and consider the amount of adjustment on the 3rd plane necessary
94 | ```
95 |
```
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-filesystem/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # filesystem MCP Server
2 |
3 | Cross platform file system server
4 |
5 | This is a [Model Context Protocol](https://github.com/modelcontextprotocol) (MCP) server project.
6 |
7 | ## Setup and Installation
8 |
9 | Simply run:
10 |
11 | ```bash
12 | make
13 | ```
14 |
15 | To create the virtual environment and install dependencies.
16 |
17 | ### Running the Server
18 |
19 | Use the VSCode launch configuration, or run manually:
20 |
21 | The server requires specifying at least one allowed directory (for security reasons).
22 |
23 | For stdio transport, specify directories using the --allowed_directories argument:
24 |
25 | ```bash
26 | uv run -m mcp_server_filesystem.start --allowed_directories /path1 /path2 /path3
27 | ```
28 |
29 | For SSE transport, you can start the server without specifying directories:
30 |
31 | ```bash
32 | uv run -m mcp_server_filesystem.start --transport sse --port 6060
33 | ```
34 |
35 | ### Setting Allowed Directories
36 |
37 | The server uses "allowed directories" for security purposes. There are two ways to configure them:
38 |
39 | 1. **Command line arguments**: Using `--allowed_directories` parameter (required for stdio transport)
40 | 2. **Root configuration**: For SSE transport, the server can use the roots defined by the client
41 |
42 | When using the root configuration approach, the MCP client sets the accessible directories through the session's `list_roots()` mechanism so each allowed directory must be set in the client's root configuration.
43 |
44 | ## Tools Available
45 |
46 | ### `read_file`
47 | Reads the contents of a specific file.
48 |
49 | ### `write_file`
50 | Writes content to a specified file path. Creates the file if it does not exist.
51 |
52 | ### `list_directory`
53 | Lists all files and subdirectories within a specified directory.
54 |
55 | ### `create_directory`
56 | Creates a new directory or ensures an existing one remains accessible.
57 |
58 | ### `edit_file`
59 | Edits the contents of a text file with specified replacements. Supports a dry run mode to preview changes without applying them.
60 |
61 | ### `search_files`
62 | Recursively searches for files matching a pattern across subdirectories.
63 |
64 | ### `get_file_info`
65 | Retrieves and displays detailed metadata about a specified file or directory.
66 |
67 | ### `read_multiple_files`
68 | Reads the content of multiple files simultaneously and returns their contents in a dictionary. Files not accessible are marked with error messages.
69 |
70 | ### `move_file`
71 | Moves or renames a file or directory from a source path to a target destination.
72 |
73 | ### `list_allowed_directories`
74 | Returns a list of directories that the server is permitted to access.
75 |
76 |
77 | ## Client Configuration
78 |
79 | To use this MCP server in your setup, consider the following configuration:
80 |
81 | ### Stdio
82 |
83 | ```json
84 | {
85 | "mcpServers": {
86 | "mcp-server-filesystem": {
87 | "command": "uv",
88 | "args": ["run", "-m", "mcp_server_filesystem.start", "--allowed_directories", "/path1", "/path2"]
89 | }
90 | }
91 | }
92 | ```
93 |
94 | ### SSE
95 |
96 | ```json
97 | {
98 | "mcpServers": {
99 | "mcp-server-filesystem": {
100 | "command": "http://127.0.0.1:6060/sse",
101 | "args": ["/path1", "/path2"]
102 | }
103 | }
104 | }
105 | ```
106 |
107 | The args will be automatically joined with commas and added as a query parameter named 'args'.
108 |
109 | ### Direct URL Configuration
110 |
111 | If you prefer, you can also configure the URL directly with the args parameter already included:
112 |
113 | ```json
114 | {
115 | "mcpServers": {
116 | "mcp-server-filesystem": {
117 | "command": "http://127.0.0.1:6060/sse?args=/path1,/path2,/path3",
118 | "args": []
119 | }
120 | }
121 | }
122 | ```
123 |
124 | This approach is more verbose but might be preferable in some configurations.
125 |
```
--------------------------------------------------------------------------------
/.devcontainer/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using GitHub Codespaces with devcontainers for development
2 |
3 | This folder contains the configuration files for using GitHub Codespaces with devcontainers for development.
4 |
5 | GitHub Codespaces is a feature of GitHub that provides a cloud-based development environment for your repository. It allows you to develop, build, and test your code in a consistent environment, without needing to install dependencies or configure a local development environment. You just need to run a local VS Code instance to connect to the Codespace.
6 |
7 | ## Why
8 |
9 | - **Consistent environment**: All developers use the same environment, regardless of their local setup.
10 | - **Platform agnostic**: Works on any system that can run VS Code.
11 | - **Isolated environment**: The devcontainer is isolated from the host machine, so you can install dependencies without affecting your local setup.
12 | - **Quick setup**: You can start developing in a few minutes, without needing to install dependencies or configure your environment.
13 |
14 | ## Setup
15 |
16 | While you can use GitHub Codespaces directly from the GitHub website, it is recommended to use a local installation of VS Code to connect to the Codespace. There is currently an issue with the Codespaces browser-based editor that prevents the app from being able to connect to the service (see [this discussion comment](https://github.com/orgs/community/discussions/15351#discussioncomment-4112535)).
17 |
18 | For more details on using GitHub Codespaces in VS Code, see the [documentation](https://docs.github.com/en/codespaces/developing-in-a-codespace/using-github-codespaces-in-visual-studio-code).
19 |
20 | ### Pre-requisites
21 |
22 | - Install [Visual Studio Code](https://code.visualstudio.com/)
23 |
24 | ### Create a new GitHub Codespace via VS Code
25 |
26 | - Launch VS Code and open the command palette with the `F1` key or `Ctrl/Cmd+Shift+P`
27 | - Type `Codespaces: Create New Codespace...` and select it
28 | - Type in the name of the repository you want to use, or select a repository from the list
29 | - Click the branch you want to develop on
30 | - Select the machine type you want to use
31 | - The Codespace will be created and you will be connected to it
32 | - Allow the Codespace to build, which may take a few minutes
33 |
34 | ## How to use
35 |
36 | IMPORTANT: Make sure to open the main workspace file: `semantic-workbench.code-workspace` and not just open the root folder in VSCode:
37 |
38 | `File` -> `Open Workspace from File...` -> Choose the `semantic-workbench.code-workspace` file from the list.
39 |
40 |
41 | ### Connecting to the Codespace in the future
42 |
43 | - Launch VS Code and open the command palette with the `F1` key or `Ctrl/Cmd+Shift+P`
44 | - Type `Codespaces: Connect to Codespace...` and select it
45 |
46 | ### Optimizing your Codespaces experience
47 |
48 | See [OPTIMIZING_FOR_CODESPACES.md](./OPTIMIZING_FOR_CODESPACES.md) for tips on optimizing your Codespaces experience.
49 |
50 | ### Next steps
51 |
52 | Once you have connected to the Codespace, it should automatically open the workspace file for the Semantic Workbench project. If it does not, you can open the workspace file manually:
53 |
54 | - Use the command palette: `Ctrl/Cmd+P` and type `semantic-workbench.code-workspace` to open the workspace file
55 | - Click `Open Workspace` button in lower right corner to launch the workspace
56 |
57 | From here, you can start the app and service, and interact with the Semantic Workbench app in your browser.
58 |
59 | See [POST_SETUP_README.md](./POST_SETUP_README.md) for the steps to get started with the Semantic Workbench app and service and assistants.
60 |
```
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-filesystem-edit/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Filesystem Edit MCP Server
2 |
3 | Allows for robust editing of Markdown, Office, and LaTeX files.
4 | Your system and configuration will determine which are supported. By default working with Markdown (`.md`) files is always enabled
5 |
6 | This is a [Model Context Protocol](https://github.com/modelcontextprotocol) (MCP) server project.
7 |
8 | ## Setup and Installation
9 |
10 | Simply run:
11 |
12 | ```bash
13 | make
14 | ```
15 |
16 | To create the virtual environment and install dependencies.
17 |
18 | ### Running the Server
19 |
20 | Use the VSCode launch configuration, or run manually:
21 |
22 | Defaults to stdio transport:
23 |
24 | ```bash
25 | uv run mcp-server-filesystem-edit
26 | ```
27 |
28 | For SSE transport:
29 |
30 | ```bash
31 | uv run mcp-server-filesystem-edit --transport sse --port 25567
32 | ```
33 |
34 | The SSE URL is:
35 |
36 | ```bash
37 | http://127.0.0.1:25567/sse
38 | ```
39 |
40 |
41 | ### Optional Features
42 | - If you have pdflatex installed on your system and you would like `edit_file` to automatically compile LaTeX files for you,
43 | can provide the argument `--enable-pdflatex` when starting the server.
44 | - If the system is Windows, it will automatically you have Office apps installed and will use them to edit `.docx` files and also view `.xlsx` files.
45 |
46 |
47 | ### Setting Working Directory
48 | The server uses a single working directory for security purposes. There are two ways to configure them:
49 |
50 | 1. **Command line arguments**: Using `--allowed_directories` parameter (required for stdio transport) which will use the first directory.
51 | 2. **Root configuration**: For SSE transport, the server can use the roots defined by the client and it will use the first valid dir as the working directory. When using this approach, the MCP client makes the working available through the session's `list_roots()` mechanism.
52 |
53 |
54 | ## Tools
55 | ### `list_working_directory()`
56 | - Lists the files in the working directory relative to it.
57 | - All other tools will need to provide paths relative to this directory.
58 |
59 | ### `view_file(path)`
60 | - Reads the content of the file at the given path.
61 | - NOTE: Currently only certain common file types are supported.
62 | - For viewing:
63 | - Directly can view: `.md`, `.csv`, `.tex`
64 | - Can be viewed through an office app, only on Windows: `.docx`, `.xlsx` (first worksheet)
65 | - These file extensions can be edited:
66 | - Directly on the filesystem: `.md`, `.tex`
67 | - Through an office app, only on Windows: `.docx`
68 | - If you have `pdflatex` installed and provide the `--enable-pdflatex` argument, you can also automatically compile LaTeX files.
69 |
70 | ### `edit_file(path, task: str)`
71 | - Edits the file at the given path with the provided content according to the task.
72 | - Uses sampling to understand things like conversation history and attachments from the client.
73 | - All other file types will return an error.
74 | - If `enable-pdflatex` is set, it will compile the LaTeX file using pdflatex and return the output.
75 |
76 | ### `add_comments(path, only_analyze: bool)`
77 | - Reads the file at the given path, adds comments to the content, and returns suggestions on what to do next.
78 | - If only_analyze is set to true, it will only analyze the comments in the current file and return hints on what to do next without modifying the file.
79 |
80 |
81 | ## Client Configuration
82 |
83 | To use this MCP server in your setup, consider the following configuration:
84 |
85 | ### Stdio
86 |
87 | ```json
88 | {
89 | "mcpServers": {
90 | "mcp-server-filesystem-edit": {
91 | "command": "uv",
92 | "args": ["run", "-m", "mcp_server_filesystem_edit.start"]
93 | }
94 | }
95 | }
96 | ```
97 |
98 | ### SSE
99 |
100 | ```json
101 | {
102 | "mcpServers": {
103 | "mcp-server-filesystem-edit": {
104 | "command": "http://127.0.0.1:25567/sse",
105 | "args": []
106 | }
107 | }
108 | }
109 | ```
110 |
```
--------------------------------------------------------------------------------
/examples/dotnet/dotnet-03-simple-chatbot/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using Semantic Workbench with .NET Agents
2 |
3 | This project provides a functional chatbot example, leveraging OpenAI or Azure OpenAI (or any OpenAI compatible service),
4 | allowing to use **Semantic Workbench** to test it.
5 |
6 | ## Responsible AI
7 |
8 | The chatbot includes some important best practices for AI development, such as:
9 |
10 | - **System prompt safety**, ie a set of LLM guardrails to protect users. As a developer you should understand how these
11 | guardrails work in your scenarios, and how to change them if needed. The system prompt and the prompt safety
12 | guardrails are split in two to help with testing. When talking to LLM models, prompt safety is injected before the
13 | system prompt.
14 | - See https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message for more details
15 | about protecting application and users in different scenarios.
16 | - **Content moderation**, via [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety).
17 |
18 | ## Running the example
19 |
20 | 1. Configure the agent, creating an `appsettings.development.json` to override values in `appsettings.json`:
21 | - Content Safety:
22 | - `AzureContentSafety.Endpoint`: endpoint of your [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety) service
23 | - `AzureContentSafety.AuthType`: change it to `AzureIdentity` if you're using managed identities or similar.
24 | - `AzureContentSafety.ApiKey`: your service API key (when not using managed identities)
25 | - AI services:
26 | - `AzureOpenAI.Endpoint`: endpoint of your Azure OpenAI service (if you are using Azure OpenAI)
27 | - `AzureOpenAI.AuthType`: change it to `AzureIdentity` if you're using managed identities or similar.
28 | - `AzureOpenAI.ApiKey`: your service API key (when not using managed identities)
29 | - `OpenAI.Endpoint`: change the value if you're using OpenAI compatible services like LM Studio
30 | - `OpenAI.ApiKey`: the service credentials
31 | 2. Start the agent, e.g. from this folder run `dotnet run`
32 | 3. Start the workbench backend, e.g. from root of the repo: `./tools/run-service.sh`. More info in the [README](../../../README.md).
33 | 4. Start the workbench frontend, e.g. from root of the repo: `./tools/run-app.sh`. More info in
34 | the [README](../../../README.md).
35 |
36 | ## Project Overview
37 |
38 | The sample project utilizes the `WorkbenchConnector` library and the `AgentBase` class to connect the agent to Semantic Workbench.
39 |
40 | The `MyAgentConfig` class defines some settings you can customize while developing your agent. For instance you can
41 | change the system prompt, test different safety rules, connect to OpenAI, Azure OpenAI or compatible services like
42 | LM Studio, change LLM temperature and nucleus sampling, etc.
43 |
44 | The `appsettings.json` file contains workbench settings, credentials and few other details.
45 |
46 | ## From Development to Production
47 |
48 | It's important to highlight how Semantic Workbench is a development tool, and it's not designed to host agents in
49 | a production environment.
50 | The workbench helps with testing and debugging, in a development and isolated environment, usually your localhost.
51 |
52 | The core of your agent/AI application, e.g. how it reacts to users, how it invokes tools, how it stores data, can be
53 | developed with any framework, such as Semantic Kernel, Langchain, OpenAI assistants, etc. That is typically the code
54 | you will add to `MyAgent.cs`.
55 |
56 | **Semantic Workbench is not a framework**. Settings like `MyAgentConfig.cs` and dependencies on `WorkbenchConnector`
57 | library are used only to test and debug your code in Semantic Workbench. **When an agent is fully developed and ready
58 | for production, configurable settings should be hard coded, dependencies on `WorkbenchConnector` and `AgentBase` should
59 | be removed**.
60 |
```
--------------------------------------------------------------------------------
/libraries/python/content-safety/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Content Safety for Semantic Workbench
2 |
3 | This library provides content safety evaluators to screen and filter potentially harmful content in Semantic Workbench assistants. It helps ensure that user-generated, model-generated, and assistant-generated content is appropriate and safe.
4 |
5 | ## Key Features
6 |
7 | - **Multiple Providers**: Support for both Azure Content Safety and OpenAI Moderations API
8 | - **Unified Interface**: Common API regardless of the underlying provider
9 | - **Configuration UI**: Integration with Semantic Workbench's configuration system
10 | - **Flexible Integration**: Easy to integrate with any assistant implementation
11 |
12 | ## Available Evaluators
13 |
14 | ### Combined Content Safety Evaluator
15 |
16 | The `CombinedContentSafetyEvaluator` provides a unified interface for using various content safety services:
17 |
18 | ```python
19 | from content_safety.evaluators import CombinedContentSafetyEvaluator, CombinedContentSafetyEvaluatorConfig
20 | from content_safety.evaluators.azure_content_safety.config import AzureContentSafetyEvaluatorConfig
21 |
22 | # Configure with Azure Content Safety
23 | config = CombinedContentSafetyEvaluatorConfig(
24 | service_config=AzureContentSafetyEvaluatorConfig(
25 | endpoint="https://your-resource.cognitiveservices.azure.com/",
26 | api_key="your-api-key",
27 | threshold=0.5, # Flag content with harm probability above 50%
28 | )
29 | )
30 |
31 | # Create evaluator
32 | evaluator = CombinedContentSafetyEvaluator(config)
33 |
34 | # Evaluate content
35 | result = await evaluator.evaluate("Some content to evaluate")
36 | ```
37 |
38 | ### Azure Content Safety Evaluator
39 |
40 | Evaluates content using Azure's Content Safety service:
41 |
42 | ```python
43 | from content_safety.evaluators.azure_content_safety import AzureContentSafetyEvaluator, AzureContentSafetyEvaluatorConfig
44 |
45 | config = AzureContentSafetyEvaluatorConfig(
46 | endpoint="https://your-resource.cognitiveservices.azure.com/",
47 | api_key="your-api-key",
48 | threshold=0.5
49 | )
50 |
51 | evaluator = AzureContentSafetyEvaluator(config)
52 | result = await evaluator.evaluate("Content to check")
53 | ```
54 |
55 | ### OpenAI Moderations Evaluator
56 |
57 | Evaluates content using OpenAI's Moderations API:
58 |
59 | ```python
60 | from content_safety.evaluators.openai_moderations import OpenAIContentSafetyEvaluator, OpenAIContentSafetyEvaluatorConfig
61 |
62 | config = OpenAIContentSafetyEvaluatorConfig(
63 | api_key="your-openai-api-key",
64 | threshold=0.8, # Higher threshold (80%)
65 | max_item_size=4000 # Automatic chunking for longer content
66 | )
67 |
68 | evaluator = OpenAIContentSafetyEvaluator(config)
69 | result = await evaluator.evaluate("Content to check")
70 | ```
71 |
72 | ## Integration with Assistants
73 |
74 | To integrate with a Semantic Workbench assistant:
75 |
76 | ```python
77 | from content_safety.evaluators import CombinedContentSafetyEvaluator
78 | from semantic_workbench_assistant.assistant_app import ContentSafety
79 |
80 | # Define evaluator factory
81 | async def content_evaluator_factory(context):
82 | config = await assistant_config.get(context.assistant)
83 | return CombinedContentSafetyEvaluator(config.content_safety_config)
84 |
85 | # Create content safety component
86 | content_safety = ContentSafety(content_evaluator_factory)
87 |
88 | # Add to assistant
89 | assistant = AssistantApp(
90 | assistant_service_id="your-assistant",
91 | assistant_service_name="Your Assistant",
92 | content_interceptor=content_safety
93 | )
94 | ```
95 |
96 | ## Configuration UI
97 |
98 | The library includes Pydantic models with UI annotations for easy integration with Semantic Workbench's configuration interface. These models generate appropriate form controls in the assistant configuration UI.
99 |
100 | ## Evaluation Results
101 |
102 | Evaluation results include:
103 | - Whether content was flagged as unsafe
104 | - Detailed categorization (violence, sexual, hate speech, etc.)
105 | - Confidence scores for different harm categories
106 | - Original response from the provider for debugging
107 |
108 | ## Learn More
109 |
110 | See the [Responsible AI FAQ](../../../RESPONSIBLE_AI_FAQ.md) for more information about content safety in the Semantic Workbench ecosystem.
```
--------------------------------------------------------------------------------
/libraries/python/skills/skill-library/skill_library/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Skill Library
2 |
3 | ## Concepts
4 |
5 | ### Skills
6 |
7 | Think of a skill as a package of assistant capabilities. A skill contains
8 | "[routines](#routines)" that are entire procedures an assistant can run.
9 |
10 | Using an everyday example in our own lives, you can imagine hiring a chef to
11 | cook you a meal. The chef would be skilled at doing things in the kitchen (like
12 | chopping or mixing or frying) and would also be able to execute full recipes,
13 | allowing them to make particular dishes according to your preferences. All of
14 | these actions can be encoded in a skill with routines.
15 |
16 | A [Posix skill](./skills/posix/) (file system
17 | interaction) is provided. Various routines are provided in the skill that
18 | provide posix-like ability to manage a file system (creating directories and
19 | files, listing files, reading files, etc.). In addition, though, a "compound"
20 | routine (one that runs other routines) is provided that can create a user
21 | directory with all of its associated sub directories.
22 |
23 | We ship this and some other skill packages with the library
24 | [here](./skills/), but you can import skill packages from
25 | anywhere.
26 |
27 | When a skill engine is registered to an assistant, a user will be able to see the
28 | skill's routines by running the message command `/list_routines`.
29 |
30 | See: [skill.py](./skill.py)
31 |
32 | #### Routines
33 |
34 | Routines are instructions that guide an agent to perform a program in a
35 | prescribed manner, oftentimes in collaboration with users over many
36 | interactions.
37 |
38 | Implementation-wise, a routine is simply a Python module with a `main` function
39 | that follows a particular signature. You put all the routines inside a `routine`
40 | directory inside a skill package.
41 |
42 | ### Skill Engine
43 |
44 | The `Engine` is the object that gets instantiated with all the running skills.
45 | The engine can be asked to list or run any routine it has been configured with
46 | and will do so in a managed "run context". The engine contains an "assistant
47 | drive" that can be scoped to a specific persistence location to keep all the
48 | state of the engine in one spot. The engine also handles the event handling for
49 | all registered skills. Once an engine is started you can call (or subscribe to)
50 | its `events` endpoint to get a list of generated events.
51 |
52 | See: [engine.py](./engine.py), [Assistant Drive](../../../assistant-drive/README.md)
53 |
54 | ## State
55 |
56 | The skill library provides multiple ways to manage state in an assistant.
57 |
58 | ### Drives
59 |
60 | We use the [Assistant Drive](../../../assistant-drive/README.md) package to provide
61 | simple disk storage to components in the skill library. Each engine is given
62 | a drive (the "assistant drive") that should be "sub-drived" by all skills to use
63 | as storage. This keeps all of the data together in one spot, making it easier to
64 | copy/backup/clone/fork assistants.
65 |
66 | ### Routine Stack state
67 |
68 | Even breaking drives down to the skill levels, trying to manage all state in
69 | drives is somewhat like trying to store information in "global state" and has
70 | similar problems... it introduces coupling between skills and routines in that
71 | one routine needs to know where another routine stored specific information. As
72 | complexity of the routines increases, this can result in an explosion of
73 | complexity of routine configuration. To avoid this, we created the idea of a
74 | "routine stack" which is managed by the skill registry's routine runner. Each
75 | time a routine is run, an object to store state for that routine is created and
76 | put on a stack for that routine run. If the routine calls a subroutine, another
77 | frame is added to the stack for the new routine. Once the routine is completed,
78 | the state object is removed from the run stack automatically. This allows each
79 | routine to have its own state to be used for persistence of all variables
80 | between runs (e.g. interactions with the user or switching focus to other
81 | routines). Of course, a routine can still choose to save data in a drive or
82 | another location, but putting it on the stack is a simple way to avoid more
83 | complex configuration.
84 |
85 | See: [routine_stack.py](./routine_stack.py)
86 |
```
--------------------------------------------------------------------------------
/libraries/python/mcp-tunnel/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # MCP Tunnel
2 |
3 | A command-line tool for managing secure tunnels to local Model Context Protocol (MCP) servers.
4 |
5 | ## Overview
6 |
7 | MCP Tunnel simplifies the process of exposing locally running MCP servers to the internet through secure tunnels. This enables AI assistants like Codespace assistant to connect to your local MCP servers, allowing them to access local resources, files, and functionality.
8 |
9 | The tool uses Microsoft's DevTunnel service to create secure tunnels from the internet to your local machine. It can manage multiple tunnels simultaneously and generates the necessary configuration files for connecting your Codespace assistant to these tunnels.
10 |
11 | ## Prerequisites
12 |
13 | - uv
14 | - [Microsoft DevTunnel CLI](https://learn.microsoft.com/en-us/azure/developer/dev-tunnels/get-started) installed and available in your PATH
15 | - A Microsoft account (to log in to DevTunnel)
16 |
17 | ## Quickstart - Run from this repo
18 |
19 | Run the mcp-tunnel script directly from this repository using `uvx`:
20 |
21 | ```bash
22 | uvx --from git+https://github.com/microsoft/semanticworkbench#subdirectory=libraries/python/mcp-tunnel mcp-tunnel --help
23 | ```
24 |
25 | ## Installation for development on a repo clone
26 |
27 | After cloning the repo, install MCP Tunnel using make from the `mcp-tunnel` directory:
28 |
29 | ```bash
30 | make install
31 | ```
32 |
33 | ## Usage
34 |
35 | ### Basic Usage
36 |
37 | Start tunnels for default MCP servers (vscode on port 6010 and office on port 25566):
38 |
39 | ```bash
40 | uvx --from git+https://github.com/microsoft/semanticworkbench#subdirectory=libraries/python/mcp-tunnel mcp-tunnel
41 | ```
42 |
43 | or on a cloned repo
44 |
45 | ```bash
46 | uv run mcp-tunnel
47 | ```
48 |
49 | ### Custom Servers
50 |
51 | Specify custom server names and ports:
52 |
53 | ```bash
54 | uvx --from git+https://github.com/microsoft/semanticworkbench#subdirectory=libraries/python/mcp-tunnel mcp-tunnel --servers "myserver:8080,anotherserver:9000"
55 | ```
56 |
57 | or on a cloned repo
58 |
59 | ```bash
60 | uv run mcp-tunnel --servers "myserver:8080,anotherserver:9000"
61 | ```
62 |
63 | ### Output
64 |
65 | When you run MCP Tunnel, it will:
66 |
67 | 1. Check if DevTunnel CLI is installed
68 | 2. Check if you are logged in to DevTunnel CLI, and if not, initiate a login
69 | 3. Create tunnels for each specified server
70 | 4. Start tunnel processes and display their output with color-coding
71 | 5. Generate an assistant configuration file at `~/.mcp-tunnel/assistant-config.yaml`, for use with the Codespace assistant
72 | 6. Generate an MCP client configuration file at `~/.mcp-tunnel/mcp-client.json`, for use with MCP clients such as Claude desktop
73 | 7. Keep tunnels running until you press Ctrl+C
74 |
75 | ## Assistant Configuration
76 |
77 | MCP Tunnel generates a configuration file at `~/.mcp-tunnel/assistant-config.yaml` that can be used to connect your AI assistant to the tunnels.
78 |
79 | You can use this configuration with the Codespace assistant by importing it from the Assistant Configuration screen.
80 |
81 | ## MCP Client Configuration
82 |
83 | MCP Tunnel generates a configuration file at `~/.mcp-tunnel/mcp-client.json` that can be used to connect your MCP clients to the tunnels.
84 |
85 | Read the documentation for your specific MCP client to learn how to apply this configuration.
86 |
87 | ### Setting Up Your MCP Client Machine
88 |
89 | After running `mcp-tunnel`, you'll need to set up your MCP client machine to connect to the tunnels:
90 |
91 | 1. **Install DevTunnel**: Follow the [installation instructions](https://learn.microsoft.com/en-us/azure/developer/dev-tunnels/get-started?#install)
92 |
93 | 2. **Log in with your Microsoft account**:
94 |
95 | ```bash
96 | devtunnel user login
97 | ```
98 |
99 | 3. **Start port forwarding** (use the tunnel ID from your `mcp-client.json` output):
100 |
101 | ```bash
102 | devtunnel connect <TUNNEL_ID>
103 | ```
104 |
105 | 4. **Install MCP Proxy**: Follow the [installation instructions](https://github.com/sparfenyuk/mcp-proxy?tab=readme-ov-file#installation)
106 |
107 | 5. **Update your MCP client configuration** according to the instructions for your specific MCP client
108 |
109 | 6. **Restart your MCP client** to apply the changes
110 |
111 | ## Troubleshooting
112 |
113 | ### DevTunnel CLI Not Found
114 |
115 | If you see an error about the DevTunnel CLI not being found:
116 |
117 | 1. Install the DevTunnel CLI by following the [official instructions](https://learn.microsoft.com/en-us/azure/developer/dev-tunnels/get-started)
118 | 2. Make sure it's in your PATH
119 | 3. Test that it works by running `devtunnel --version`
120 |
```
--------------------------------------------------------------------------------
/libraries/python/mcp-extensions/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # MCP Extensions Library
2 |
3 | The `mcp-extensions` library is a supplemental toolkit designed to enhance the functionality and usability of the Model Context Protocol (MCP) framework. MCP provides a standardized interface for bridging AI models with external resources, tools, and prompts. This library builds on that foundation by offering utility methods, helper functions, and extended models to improve workflow efficiency and enable advanced integration features.
4 |
5 | ## What is MCP?
6 |
7 | MCP (Model Context Protocol) allows applications to provide structured data sources, executable tools, and reusable prompts to Large Language Models (LLMs) in a standardized way. Using MCP, you can:
8 |
9 | - Build MCP clients to communicate with MCP servers.
10 | - Create MCP servers that expose resources, tools, and prompts for model interaction.
11 | - Leverage seamless integrations between your services and LLM applications.
12 |
13 | The `mcp-extensions` library supplements this ecosystem to bridge specific gaps in workflows or extend capabilities.
14 |
15 | ## Features
16 |
17 | ### 1. Tool Execution Enhancements
18 |
19 | - **Notification-based Lifecycles:** Implement `execute_tool_with_notifications` to handle tool calls with real-time notifications to the server. This is particularly valuable for:
20 | - Progress tracking.
21 | - Handling asynchronous tool execution.
22 |
23 | ```python
24 | await execute_tool_with_notifications(
25 | session=session,
26 | tool_call_function=my_tool_call,
27 | notification_handler=handle_server_notifications
28 | )
29 | ```
30 |
31 | ### 2. Conversion Utilities
32 |
33 | - **Convert MCP Tools:** Leverages `convert_tools_to_openai_tools` to transform MCP tools into OpenAI-compatible function definitions. Useful for interoperating with ecosystems that leverage OpenAI's function call syntax.
34 |
35 | ```python
36 | converted_tools = convert_tools_to_openai_tools(mcp_tools, extra_properties={'user_context': 'optional'})
37 | ```
38 |
39 | ### 3. Progress Notifications
40 |
41 | - **Report Progress to MCP Clients:**
42 | Provide fine-grained updates about ongoing tasks using `send_tool_call_progress`. Ideal for applications where the client requires detailed visibility into long-running tasks.
43 |
44 | ```python
45 | await send_tool_call_progress(context, "50% task completed", data={"step": 3})
46 | ```
47 |
48 | ### 4. Extended Data Models
49 |
50 | - **Custom Server Notification Handlers:** Includes extended models like `ToolCallFunction`, `ServerNotificationHandler`, and `ToolCallProgressMessage` for greater flexibility when handling server events and workflow lifecycles.
51 |
52 | ```python
53 | from mcp_extensions._model import ServerNotificationHandler, ToolCallProgressMessage
54 | ```
55 |
56 | ## Use Cases
57 |
58 | ### A. Enhanced Tool Lifecycle Management
59 |
60 | The library helps in managing tool lifecycles—for asynchronous executions, task progress reporting, and server-side notification handling.
61 |
62 | ### B. Cross-Ecosystem Interoperability
63 |
64 | By transforming MCP tool definitions to OpenAI's tool schema, the library facilitates hybrid use cases where functionality needs to work seamlessly across frameworks.
65 |
66 | ### C. Real-Time Execution Feedback
67 |
68 | Applications requiring frequent updates about task statuses benefit from the notification-based features built into the library.
69 |
70 | ## Installation
71 |
72 | To install the `mcp-extensions` library, run:
73 |
74 | ```bash
75 | pip install mcp-extensions
76 | ```
77 |
78 | Ensure that you are using Python 3.11 or later to leverage the library's features.
79 |
80 | ## Supported Dependencies
81 |
82 | The library depends on:
83 |
84 | - `deepmerge`: For combining tool properties with additional metadata.
85 | - `mcp`: Required for core protocol interactions.
86 |
87 | Optional:
88 |
89 | - `openai`: If integrating with OpenAI's APIs.
90 |
91 | ## Getting Started
92 |
93 | Here is a minimal example to use the library’s tool execution utilities:
94 |
95 | ```python
96 | from mcp_extensions import execute_tool_with_notifications
97 |
98 | async def my_tool_call():
99 | # Perform tool-specific task
100 | return {"result": "completed"}
101 |
102 | async def handle_server_notifications(notification):
103 | print(f"Received server notification: {notification}")
104 |
105 | await execute_tool_with_notifications(
106 | session=session,
107 | tool_call_function=my_tool_call,
108 | notification_handler=handle_server_notifications
109 | )
110 | ```
111 |
112 | ---
113 |
114 | For more information on the Model Context Protocol, visit the [official documentation](https://modelcontextprotocol.io).
115 |
```
--------------------------------------------------------------------------------
/assistants/prospector-assistant/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using Semantic Workbench with python assistants
2 |
3 | This project provides an assistant to help mine artifacts for ideas, leveraging OpenAI or Azure OpenAI (or any OpenAI compatible service), allowing to use **Semantic Workbench** to test it.
4 |
5 | ## Responsible AI
6 |
7 | The chatbot includes some important best practices for AI development, such as:
8 |
9 | - **System prompt safety**, ie a set of LLM guardrails to protect users. As a developer you should understand how these
10 | guardrails work in your scenarios, and how to change them if needed. The system prompt and the prompt safety
11 | guardrails are split in two to help with testing. When talking to LLM models, prompt safety is injected before the
12 | system prompt.
13 | - See https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message for more details
14 | about protecting application and users in different scenarios.
15 | - **Content moderation**, via [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety)
16 | or [OpenAI Content Moderation](https://platform.openai.com/docs/guides/moderation).
17 |
18 | See the [Responsible AI FAQ](../../RESPONSIBLE_AI_FAQ.md) for more information.
19 |
20 | # Suggested Development Environment
21 |
22 | - Use GitHub Codespaces for a quick, turn-key dev environment: [/.devcontainer/README.md](../../.devcontainer/README.md)
23 | - VS Code is recommended for development
24 |
25 | ## Pre-requisites
26 |
27 | - Set up your dev environment
28 | - SUGGESTED: Use GitHub Codespaces for a quick, easy, and consistent dev
29 | environment: [/.devcontainer/README.md](../../.devcontainer/README.md)
30 | - ALTERNATIVE: Local setup following the [main README](../../README.md#local-development-environment)
31 | - Set up and verify that the workbench app and service are running using the [semantic-workbench.code-workspace](../../semantic-workbench.code-workspace)
32 | - If using Azure OpenAI, set up an Azure account and create a Content Safety resource
33 | - See [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety) for more information
34 | - Copy the `.env.example` to `.env` and update the `ASSISTANT__AZURE_CONTENT_SAFETY_ENDPOINT` value with the endpoint of your Azure Content Safety resource
35 | - From VS Code > `Terminal`, run `az login` to authenticate with Azure prior to starting the assistant
36 |
37 | ## Steps
38 |
39 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `semantic-workbench` to start the app and service from this workspace
40 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `launch assistant` to start the assistant.
41 | - If running in a devcontainer, follow the instructions in [.devcontainer/POST_SETUP_README.md](../../.devcontainer/POST_SETUP_README.md#start-the-app-and-service) for any additional steps.
42 | - Return to the workbench app to interact with the assistant
43 | - Add a new assistant from the main menu of the app, choose the assistant name as defined by the `service_name` in [chat.py](./assistant/chat.py)
44 | - Click the newly created assistant to configure and interact with it
45 |
46 | ## Starting the example from CLI
47 |
48 | If you're not using VS Code and/or Codespaces, you can also work from the
49 | command line, using `uv`:
50 |
51 | ```
52 | cd <PATH TO THIS FOLDER>
53 |
54 | uv run start-assistant
55 | ```
56 |
57 | ## Create your own assistant
58 |
59 | Copy the contents of this folder to your project.
60 |
61 | - The paths are already set if you put in the same repo root and relative path of `/<your_projects>/<your_assistant_name>`
62 | - If placed in a different location, update the references in the `pyproject.toml` to point to the appropriate locations for the `semantic-workbench-*` packages
63 |
64 | ## From Development to Production
65 |
66 | It's important to highlight how Semantic Workbench is a development tool, and it's not designed to host agents in
67 | a production environment. The workbench helps with testing and debugging, in a development and isolated environment, usually your localhost.
68 |
69 | The core of your assistant/AI application, e.g. how it reacts to users, how it invokes tools, how it stores data, can be
70 | developed with any framework, such as Semantic Kernel, Langchain, OpenAI assistants, etc. That is typically the code
71 | you will add to `chat.py`.
72 |
73 | **Semantic Workbench is not a framework**. Dependencies on `semantic-workbench-assistant` package are used only to test and debug your code in Semantic Workbench. **When an assistant is fully developed and ready for production, configurable settings should be hard coded, dependencies on `semantic-workbench-assistant` and similar should be removed**.
74 |
```
--------------------------------------------------------------------------------
/examples/python/python-02-simple-chatbot/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using Semantic Workbench with python assistants
2 |
3 | This project provides a functional chatbot example, leveraging OpenAI or Azure OpenAI (or any OpenAI compatible service),
4 | allowing to use **Semantic Workbench** to test it.
5 |
6 | ## Responsible AI
7 |
8 | The chatbot includes some important best practices for AI development, such as:
9 |
10 | - **System prompt safety**, ie a set of LLM guardrails to protect users. As a developer you should understand how these
11 | guardrails work in your scenarios, and how to change them if needed. The system prompt and the prompt safety
12 | guardrails are split in two to help with testing. When talking to LLM models, prompt safety is injected before the
13 | system prompt.
14 | - See https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message for more details
15 | about protecting application and users in different scenarios.
16 | - **Content moderation**, via [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety)
17 | or [OpenAI Content Moderation](https://platform.openai.com/docs/guides/moderation).
18 |
19 | See the [Responsible AI FAQ](../../../RESPONSIBLE_AI_FAQ.md) for more information.
20 |
21 | ## Suggested Development Environment
22 |
23 | - Use GitHub Codespaces for a quick, turn-key dev environment: [.devcontainer/README.md](../../../.devcontainer/README.md)
24 | - VS Code is recommended for development
25 |
26 | ## Pre-requisites
27 |
28 | - Set up your dev environment
29 | - SUGGESTED: Use GitHub Codespaces for a quick, easy, and consistent dev
30 | environment: [.devcontainer/README.md](../../../.devcontainer/README.md)
31 | - ALTERNATIVE: Local setup following the [main README](../../../README.md#local-development-environment)
32 | - Set up and verify that the workbench app and service are running using the [semantic-workbench.code-workspace](../../../semantic-workbench.code-workspace)
33 | - If using Azure OpenAI, set up an Azure account and create a Content Safety resource
34 | - See [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety) for more information
35 | - Copy the `.env.example` to `.env` and update the `ASSISTANT__AZURE_CONTENT_SAFETY_ENDPOINT` value with the endpoint of your Azure Content Safety resource
36 | - From VS Code > `Terminal`, run `az login` to authenticate with Azure prior to starting the assistant
37 |
38 | ## Steps
39 |
40 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `semantic-workbench` to start the app and service from this workspace
41 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `launch assistant` to start the assistant.
42 | - If running in a devcontainer, follow the instructions in [.devcontainer/POST_SETUP_README.md](../../../.devcontainer/POST_SETUP_README.md#start-the-app-and-service) for any additional steps.
43 | - Return to the workbench app to interact with the assistant
44 | - Add a new assistant from the main menu of the app, choose the assistant name as defined by the `service_name` in [chat.py](./assistant/chat.py)
45 | - Click the newly created assistant to configure and interact with it
46 |
47 | ## Starting the example from CLI
48 |
49 | If you're not using VS Code and/or Codespaces, you can also work from the
50 | command line, using `uv`:
51 |
52 | ```
53 | cd <PATH TO THIS FOLDER>
54 |
55 | uv run start-assistant
56 | ```
57 |
58 | ## Create your own assistant
59 |
60 | Copy the contents of this folder to your project.
61 |
62 | - The paths are already set if you put in the same repo root and relative path of `/<your_projects>/<your_assistant_name>`
63 | - If placed in a different location, update the references in the `pyproject.toml` to point to the appropriate locations for the `semantic-workbench-*` packages
64 |
65 | ## From Development to Production
66 |
67 | It's important to highlight how Semantic Workbench is a development tool, and it's not designed to host agents in
68 | a production environment. The workbench helps with testing and debugging, in a development and isolated environment, usually your localhost.
69 |
70 | The core of your assistant/AI application, e.g. how it reacts to users, how it invokes tools, how it stores data, can be
71 | developed with any framework, such as Semantic Kernel, Langchain, OpenAI assistants, etc. That is typically the code
72 | you will add to `chat.py`.
73 |
74 | **Semantic Workbench is not a framework**. Dependencies on `semantic-workbench-assistant` package are used only to test and debug your code in Semantic Workbench. **When an assistant is fully developed and ready for production, configurable settings should be hard coded, dependencies on `semantic-workbench-assistant` and similar should be removed**.
75 |
```
--------------------------------------------------------------------------------
/assistants/explorer-assistant/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using Semantic Workbench with python assistants
2 |
3 | This project provides an assistant to help explore assistant ideas and capabilities, leveraging OpenAI or Azure OpenAI (or any OpenAI compatible service), allowing to use **Semantic Workbench** to test it.
4 |
5 | ## Responsible AI
6 |
7 | The chatbot includes some important best practices for AI development, such as:
8 |
9 | - **System prompt safety**, ie a set of LLM guardrails to protect users. As a developer you should understand how these
10 | guardrails work in your scenarios, and how to change them if needed. The system prompt and the prompt safety
11 | guardrails are split in two to help with testing. When talking to LLM models, prompt safety is injected before the
12 | system prompt.
13 | - See https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message for more details
14 | about protecting application and users in different scenarios.
15 | - **Content moderation**, via [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety)
16 | or [OpenAI Content Moderation](https://platform.openai.com/docs/guides/moderation).
17 |
18 | See the [Responsible AI FAQ](../../RESPONSIBLE_AI_FAQ.md) for more information.
19 |
20 | # Suggested Development Environment
21 |
22 | - Use GitHub Codespaces for a quick, turn-key dev environment: [/.devcontainer/README.md](../../.devcontainer/README.md)
23 | - VS Code is recommended for development
24 |
25 | ## Pre-requisites
26 |
27 | - Set up your dev environment
28 | - SUGGESTED: Use GitHub Codespaces for a quick, easy, and consistent dev
29 | environment: [/.devcontainer/README.md](../../.devcontainer/README.md)
30 | - ALTERNATIVE: Local setup following the [main README](../../README.md#local-development-environment)
31 | - Set up and verify that the workbench app and service are running using the [semantic-workbench.code-workspace](../../semantic-workbench.code-workspace)
32 | - If using Azure OpenAI, set up an Azure account and create a Content Safety resource
33 | - See [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety) for more information
34 | - Copy the `.env.example` to `.env` and update the `ASSISTANT__AZURE_CONTENT_SAFETY_ENDPOINT` value with the endpoint of your Azure Content Safety resource
35 | - From VS Code > `Terminal`, run `az login` to authenticate with Azure prior to starting the assistant
36 |
37 | ## Steps
38 |
39 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `semantic-workbench` to start the app and service from this workspace
40 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `launch assistant` to start the assistant.
41 | - If running in a devcontainer, follow the instructions in [.devcontainer/POST_SETUP_README.md](../../.devcontainer/POST_SETUP_README.md#start-the-app-and-service) for any additional steps.
42 | - Return to the workbench app to interact with the assistant
43 | - Add a new assistant from the main menu of the app, choose the assistant name as defined by the `service_name` in [chat.py](./explorer_assistant/chat.py)
44 | - Click the newly created assistant to configure and interact with it
45 |
46 | ## Starting the example from CLI
47 |
48 | If you're not using VS Code and/or Codespaces, you can also work from the
49 | command line, using `uv`:
50 |
51 | ```
52 | cd <PATH TO THIS FOLDER>
53 |
54 | uv run start-assistant
55 | ```
56 |
57 | ## Create your own assistant
58 |
59 | Copy the contents of this folder to your project.
60 |
61 | - The paths are already set if you put in the same repo root and relative path of `/<your_projects>/<your_assistant_name>`
62 | - If placed in a different location, update the references in the `pyproject.toml` to point to the appropriate locations for the `semantic-workbench-*` packages
63 |
64 | ## From Development to Production
65 |
66 | It's important to highlight how Semantic Workbench is a development tool, and it's not designed to host agents in
67 | a production environment. The workbench helps with testing and debugging, in a development and isolated environment, usually your localhost.
68 |
69 | The core of your assistant/AI application, e.g. how it reacts to users, how it invokes tools, how it stores data, can be
70 | developed with any framework, such as Semantic Kernel, Langchain, OpenAI assistants, etc. That is typically the code
71 | you will add to `chat.py`.
72 |
73 | **Semantic Workbench is not a framework**. Dependencies on `semantic-workbench-assistant` package are used only to test and debug your code in Semantic Workbench. **When an assistant is fully developed and ready for production, configurable settings should be hard coded, dependencies on `semantic-workbench-assistant` and similar should be removed**.
74 |
```
--------------------------------------------------------------------------------
/libraries/python/skills/skill-library/skill_library/skills/fabric/patterns/summarize_paper/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Generate summary of an academic paper
2 |
3 | This pattern generates a summary of an academic paper based on the provided text. The input should be the complete text of the paper. The output is a summary including the following sections:
4 |
5 | **Title and authors of the Paper**
6 |
7 | **Main Goal and Fundamental Concept**
8 |
9 | **Technical Approach**
10 |
11 | **Distinctive Features**
12 |
13 | **Experimental Setup and Results**
14 |
15 | **Advantages and Limitations**
16 |
17 | **Conclusion**
18 |
19 |
20 | # Example run in MacOS/Linux:
21 |
22 | Copy the paper text to the clipboard and execute the following command:
23 |
24 | ```bash
25 | pbpaste | fabric --pattern summarize_paper
26 | ```
27 |
28 | or
29 |
30 | ```bash
31 | pbpaste | summarize_paper
32 | ```
33 |
34 | # Example output:
35 |
36 | ```markdown
37 | ### Title and authors of the Paper:
38 | **Internet of Paint (IoP): Channel Modeling and Capacity Analysis for Terahertz Electromagnetic Nanonetworks Embedded in Paint**
39 | Authors: Lasantha Thakshila Wedage, Mehmet C. Vuran, Bernard Butler, Yevgeni Koucheryavy, Sasitharan Balasubramaniam
40 |
41 | ### Main Goal and Fundamental Concept
42 |
43 | The primary objective of this research is to introduce and analyze the concept of the Internet of Paint (IoP), a novel idea that integrates nano-network devices within paint to enable communication through painted surfaces using terahertz (THz) frequencies. The core hypothesis is that by embedding nano-scale radios in paint, it's possible to create a new medium for electromagnetic communication, leveraging the unique properties of THz waves for short-range, high-capacity data transmission.
44 |
45 | ### Technical Approach
46 |
47 | The study employs a comprehensive channel model to assess the communication capabilities of nano-devices embedded in paint. This model considers multipath communication strategies, including direct wave propagation, reflections from interfaces (Air-Paint and Paint-Plaster), and lateral wave propagation along these interfaces. The research evaluates the performance across three different paint types, analyzing path losses, received powers, and channel capacities to understand how THz waves interact with painted surfaces.
48 |
49 | ### Distinctive Features
50 |
51 | This research is pioneering in its exploration of paint as a medium for THz communication, marking a significant departure from traditional communication environments. The innovative aspects include:
52 | - The concept of integrating nano-network devices within paint (IoP).
53 | - A detailed channel model that accounts for the unique interaction of THz waves with painted surfaces and interfaces.
54 | - The examination of lateral wave propagation as a key mechanism for communication in this novel medium.
55 |
56 | ### Experimental Setup and Results
57 |
58 | The experimental analysis is based on simulations that explore the impact of frequency, line of sight (LoS) distance, and burial depth of transceivers within the paint on path loss and channel capacity. The study finds that path loss slightly increases with frequency and LoS distance, with higher refractive index paints experiencing higher path losses. Lateral waves show promising performance for communication at increased LoS distances, especially when transceivers are near the Air-Paint interface. The results also indicate a substantial reduction in channel capacity with increased LoS distance and burial depth, highlighting the need for transceivers to be closely positioned and near the Air-Paint interface for effective communication.
59 |
60 | ### Advantages and Limitations
61 |
62 | The proposed IoP approach offers several advantages, including the potential for seamless integration of communication networks into building structures without affecting aesthetics, and the ability to support novel applications like gas sensing and posture recognition. However, the study also identifies limitations, such as the reduced channel capacity compared to air-based communication channels and the challenges associated with controlling the placement and orientation of nano-devices within the paint.
63 |
64 | ### Conclusion
65 |
66 | The Internet of Paint represents a groundbreaking step towards integrating communication capabilities directly into building materials, opening up new possibilities for smart environments. Despite its limitations, such as lower channel capacity compared to traditional air-based channels, IoP offers a unique blend of aesthetics, functionality, and innovation in communication technology. This study lays the foundation for further exploration and development in this emerging field.
67 | ```
68 |
69 | ## Meta
70 |
71 | - **Author**: Song Luo (https://www.linkedin.com/in/song-luo-bb17315/)
72 | - **Published**: May 11, 2024
```
--------------------------------------------------------------------------------
/examples/python/python-03-multimodel-chatbot/README.md:
--------------------------------------------------------------------------------
```markdown
1 | # Using Semantic Workbench with different AI models
2 |
3 | This project provides a functional chatbot example that can be configured to use models from OpenAI, Anthropic, or Google Gemini that can be used in the **Semantic Workbench**. This example provides a general message model that adapts to the configured model at runtime. Each model is called using their own native Python SDK.
4 |
5 | ## Responsible AI
6 |
7 | The chatbot includes some important best practices for AI development, such as:
8 |
9 | - **System prompt safety**, ie a set of LLM guardrails to protect users. As a developer you should understand how these
10 | guardrails work in your scenarios, and how to change them if needed. The system prompt and the prompt safety
11 | guardrails are split in two to help with testing. When talking to LLM models, prompt safety is injected before the
12 | system prompt.
13 | - See https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message for more details
14 | about protecting application and users in different scenarios.
15 | - **Content moderation**, via [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety)
16 | or [OpenAI Content Moderation](https://platform.openai.com/docs/guides/moderation).
17 |
18 | See the [Responsible AI FAQ](../../../RESPONSIBLE_AI_FAQ.md) for more information.
19 |
20 | ## Suggested Development Environment
21 |
22 | - Use GitHub Codespaces for a quick, turn-key dev environment: [/.devcontainer/README.md](../../../.devcontainer/README.md)
23 | - VS Code is recommended for development
24 |
25 | ## Pre-requisites
26 |
27 | - Set up your dev environment
28 | - SUGGESTED: Use GitHub Codespaces for a quick, easy, and consistent dev
29 | environment: [/.devcontainer/README.md](../../../.devcontainer/README.md)
30 | - ALTERNATIVE: Local setup following the [main README](../../../README.md#local-development-environment)
31 | - Set up and verify that the workbench app and service are running using the [semantic-workbench.code-workspace](../../../semantic-workbench.code-workspace)
32 | - If using Azure OpenAI, set up an Azure account and create a Content Safety resource
33 | - See [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety) for more information
34 | - Copy the `.env.example` to `.env` and update the `ASSISTANT__AZURE_CONTENT_SAFETY_ENDPOINT` value with the endpoint of your Azure Content Safety resource
35 | - From VS Code > `Terminal`, run `az login` to authenticate with Azure prior to starting the assistant
36 |
37 | ## Steps
38 |
39 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `semantic-workbench` to start the app and service from this workspace
40 | - Use VS Code > `Run and Debug` (ctrl/cmd+shift+d) > `launch assistant` to start the assistant.
41 | - If running in a devcontainer, follow the instructions in [.devcontainer/POST_SETUP_README.md](../../../.devcontainer/POST_SETUP_README.md#start-the-app-and-service) for any additional steps.
42 | - Return to the workbench app to interact with the assistant
43 | - Add a new assistant from the main menu of the app, choose the assistant name as defined by the `service_name` in [chat.py](./assistant/chat.py)
44 | - Click the newly created assistant to configure and interact with it
45 |
46 | ## Starting the example from CLI
47 |
48 | If you're not using VS Code and/or Codespaces, you can also work from the
49 | command line, using `uv`:
50 |
51 | ```
52 | cd <PATH TO THIS FOLDER>
53 |
54 | uv run start-assistant
55 | ```
56 |
57 | ## Create your own assistant
58 |
59 | Copy the contents of this folder to your project.
60 |
61 | - The paths are already set if you put in the same repo root and relative path of `/<your_projects>/<your_assistant_name>`
62 | - If placed in a different location, update the references in the `pyproject.toml` to point to the appropriate locations for the `semantic-workbench-*` packages
63 |
64 | ## From Development to Production
65 |
66 | It's important to highlight how Semantic Workbench is a development tool, and it's not designed to host agents in
67 | a production environment. The workbench helps with testing and debugging, in a development and isolated environment, usually your localhost.
68 |
69 | The core of your assistant/AI application, e.g. how it reacts to users, how it invokes tools, how it stores data, can be
70 | developed with any framework, such as Semantic Kernel, Langchain, OpenAI assistants, etc. That is typically the code
71 | you will add to `chat.py`.
72 |
73 | **Semantic Workbench is not a framework**. Dependencies on `semantic-workbench-assistant` package are used only to test and debug your code in Semantic Workbench. **When an assistant is fully developed and ready for production, configurable settings should be hard coded, dependencies on `semantic-workbench-assistant` and similar should be removed**.
74 |
```