This is page 87 of 114. Use http://codebase.md/microsoft/semanticworkbench?lines=false&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
--------------------------------------------------------------------------------
/ai_context/generated/CONFIGURATION.md:
--------------------------------------------------------------------------------
```markdown
# *.md | *.toml | Makefile | *.json | *.yml | *.yaml
[collect-files]
**Search:** ['*.md', '*.toml', 'Makefile', '*.json', '*.yml', '*.yaml']
**Exclude:** ['.venv', 'node_modules', '*.lock', '.git', '__pycache__', '*.pyc', '*.ruff_cache', 'logs', 'output', 'workbench-app', 'workbench-service', 'assistants', 'libraries', 'mcp-servers', 'examples', 'tools']
**Include:** []
**Date:** 5/31/2025, 12:06:20 PM
**Files:** 10
=== File: CLAUDE.md ===
# Semantic Workbench Developer Guidelines
## AI Context System
**Generate comprehensive codebase context for development:**
* `make ai-context-files` - Generate AI context files for all components
* Files created in `ai_context/generated/` organized by logical boundaries:
- **Python Libraries** (by functional group):
- `PYTHON_LIBRARIES_CORE.md` - Core API model, assistant framework, events
- `PYTHON_LIBRARIES_AI_CLIENTS.md` - Anthropic, OpenAI, LLM clients
- `PYTHON_LIBRARIES_EXTENSIONS.md` - Assistant/MCP extensions, content safety
- `PYTHON_LIBRARIES_SPECIALIZED.md` - Guided conversation, assistant drive
- `PYTHON_LIBRARIES_SKILLS.md` - Skills library with patterns and routines
- **Assistants** (by individual implementation):
- `ASSISTANTS_OVERVIEW.md` - Common patterns and all assistant summaries
- `ASSISTANT_PROJECT.md` - Project assistant (most complex)
- `ASSISTANT_DOCUMENT.md` - Document processing assistant
- `ASSISTANT_CODESPACE.md` - Development environment assistant
- `ASSISTANT_NAVIGATOR.md` - Workbench navigation assistant
- `ASSISTANT_PROSPECTOR.md` - Advanced agent with artifact creation
- `ASSISTANTS_OTHER.md` - Explorer, guided conversation, skill assistants
- **Platform Components**:
- `WORKBENCH_FRONTEND.md` - React app components and UI patterns
- `WORKBENCH_SERVICE.md` - Backend API, database, and service logic
- `MCP_SERVERS.md` - Model Context Protocol server implementations
- `DOTNET_LIBRARIES.md` - .NET libraries and connectors
- **Supporting Files**:
- `EXAMPLES.md` - Sample code and getting-started templates
- `TOOLS.md` - Build scripts and development utilities
- `CONFIGURATION.md` - Root-level configs and project setup
- `ASPIRE_ORCHESTRATOR.md` - Container orchestration setup
**Using AI Context for Development:**
* **New developers**: Read `CONFIGURATION.md` + `PYTHON_LIBRARIES_CORE.md` for project overview
* **Building assistants**:
- Start with `ASSISTANTS_OVERVIEW.md` for common patterns
- Use specific assistant files (e.g., `ASSISTANT_PROJECT.md`) as implementation templates
* **Working on specific assistants**: Load the relevant `ASSISTANT_*.md` file for focused context
* **Library development**: Choose appropriate `PYTHON_LIBRARIES_*.md` file by functional area
* **Frontend work**: Study component patterns in `WORKBENCH_FRONTEND.md`
* **API development**: Follow service patterns from `WORKBENCH_SERVICE.md`
* **MCP servers**: Use existing servers in `MCP_SERVERS.md` as templates
* **AI tools**: Provide relevant context files for better code generation and debugging
* **Code reviews**: Reference context files to understand cross-component impacts
## Common Commands
* Build/Install: `make install` (recursive for all subdirectories)
* Format: `make format` (runs ruff formatter)
* Lint: `make lint` (runs ruff linter)
* Type-check: `make type-check` (runs pyright)
* Test: `make test` (runs pytest)
* Single test: `uv run pytest tests/test_file.py::test_function -v`
* Frontend: `cd workbench-app && pnpm dev` (starts dev server)
* Workbench service: `cd workbench-service && python -m semantic_workbench_service.start`
## Code Style
### Python
* Indentation: 4 spaces
* Line length: 120 characters
* Imports: stdlib → third-party → local, alphabetized within groups
* Naming: `snake_case` for functions/variables, `CamelCase` for classes, `UPPER_SNAKE_CASE` for constants
* Types: Use type annotations consistently; prefer Union syntax (`str | None`) for Python 3.10+
* Documentation: Triple-quote docstrings with param/return descriptions
### C# (.NET)
* Naming: `PascalCase` for classes/methods/properties, `camelCase` for parameters/local variables, `_camelCase` for private fields
* Error handling: Use try/catch with specific exceptions, `ConfigureAwait(false)` with async
* Documentation: XML comments for public APIs
* Async: Use async/await consistently with cancellation tokens
### TypeScript/React (Frontend)
* Component files: Use PascalCase for component names and files (e.g., `MessageHeader.tsx`)
* Hooks: Prefix with 'use' (e.g., `useConversationEvents.ts`)
* CSS: Use Fluent UI styling with mergeStyle and useClasses pattern
* State management: Redux with Redux Toolkit and RTK Query
* Models: Define strong TypeScript interfaces/types
## Tools
* Python: Uses uv for environment/dependency management
* Linting/Formatting: Ruff (Python), ESLint (TypeScript)
* Type checking: Pyright (Python), TypeScript compiler
* Testing: pytest (Python), React Testing Library (Frontend)
* Frontend: React, Fluent UI v9, Fluent Copilot components
* Package management: uv (Python), pnpm (Frontend)
=== File: CODE_OF_CONDUCT.md ===
# Microsoft Open Source Code of Conduct
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
Resources:
- [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/)
- [Microsoft Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/)
- Contact [[email protected]](mailto:[email protected]) with questions or concerns
=== File: CONTRIBUTING.md ===
# Contributing to Semantic Workbench
You can contribute to the Semantic Workbench with issues and pull requests (PRs). Simply
filing issues for problems you encounter is a great way to contribute. Contributing
code is greatly appreciated.
## Reporting Issues
We always welcome bug reports, API proposals and overall feedback. Here are a few
tips on how you can make reporting your issue as effective as possible.
### Where to Report
New issues can be reported in our [list of issues](https://github.com/microsoft/semanticworkbench/issues).
Before filing a new issue, please search the list of issues to make sure it does
not already exist.
If you do find an existing issue for what you wanted to report, please include
your own feedback in the discussion. Do consider up-voting (👍 reaction) the original
post, as this helps us prioritize popular issues in our backlog.
### Writing a Good Bug Report
Good bug reports make it easier for maintainers to verify and root cause the
underlying problem.
The better a bug report, the faster the problem will be resolved. Ideally, a bug
report should contain the following information:
- A high-level description of the problem.
- A _minimal reproduction_, i.e. the smallest size of code/configuration required
to reproduce the wrong behavior.
- A description of the _expected behavior_, contrasted with the _actual behavior_ observed.
- Information on the environment: OS/distribution, CPU architecture, SDK version, etc.
- Additional information, e.g. Is it a regression from previous versions? Are there
any known workarounds?
## Contributing Changes
Project maintainers will merge accepted code changes from contributors.
### DOs and DON'Ts
DO's:
- **DO** clearly state on an issue that you are going to take on implementing it.
- **DO** follow the standard coding conventions
- [Python](https://pypi.org/project/black/)
- [Typescript](https://typescript-eslint.io/rules/)/[React](https://github.com/jsx-eslint/eslint-plugin-react/tree/master/docs/rules)
- [.NET](https://learn.microsoft.com/dotnet/csharp/fundamentals/coding-style/coding-conventions)
- **DO** give priority to the current style of the project or file you're changing
if it diverges from the general guidelines.
- **DO** include tests when adding new features. When fixing bugs, start with
adding a test that highlights how the current behavior is broken.
- **DO** keep the discussions focused. When a new or related topic comes up
it's often better to create new issue than to side track the discussion.
- **DO** blog and tweet (or whatever) about your contributions, frequently!
DON'Ts:
- **DON'T** surprise us with big pull requests. Instead, file an issue and start
a discussion so we can agree on a direction before you invest a large amount of time.
- **DON'T** commit code that you didn't write. If you find code that you think is a good
fit to add to Semantic Workbench, file an issue and start a discussion before proceeding.
- **DON'T** submit PRs that alter licensing related files or headers. If you believe
there's a problem with them, file an issue and we'll be happy to discuss it.
- **DON'T** make new features, APIs, or services without filing an issue and discussing with us first.
### Breaking Changes
Contributions must maintain API signature and behavioral compatibility. Contributions
that include breaking changes will be rejected. Please file an issue to discuss
your idea or change if you believe that a breaking change is warranted.
### Suggested Workflow
We use and recommend the following workflow:
1. Create an issue for your work.
- You can skip this step for trivial changes.
- Reuse an existing issue on the topic, if there is one.
- Get agreement from the team and the community that your proposed change is
a good one.
- Clearly state that you are going to take on implementing it, if that's the case.
You can request that the issue be assigned to you. Note: The issue filer and
the implementer don't have to be the same person.
2. Create a personal fork of the repository on GitHub (if you don't already have one).
3. In your fork, create a branch off of main (`git checkout -b my_branch`).
- Name the branch so that it clearly communicates your intentions, such as
"issue-123" or "github_handle-issue".
4. Make and commit your changes to your branch.
5. Add new tests corresponding to your change, if applicable.
6. Run the build and tests as described in the readme for the part(s) of the Semantic Workbench your changes impact to ensure that your build is clean and all tests are passing.
7. Create a PR against the repository's **main** branch.
- State in the description what issue or improvement your change is addressing.
- Verify that all the Continuous Integration checks are passing.
8. Wait for feedback or approval of your changes from the code maintainers.
9. When area owners have signed off, and all checks are green, your PR will be merged.
For a detailed walkthrough of this workflow, including how to set up forks and manage your Git workflow, refer to the [Detailed Workflow Walkthrough](#detailed-workflow-walkthrough) section.
### Adding Assistants
We appreciate your interest in extending Semantic Workbench's functionality through
providing assistants in the main repo. However, we want to clarify our approach to
our GitHub repository. To maintain a clean and manageable codebase we will not be
hosting assistants directly in the Semantic Workbench GitHub repository.
Instead, we encourage contributors to host their assistants in separate
repositories under their own GitHub accounts or organization. You can then
provide a link to your assistant repository in the relevant discussions, issues,
or documentation within the Semantic Workbench repository. This approach ensures
that each assistant can be maintained independently and allows for easier tracking
of updates and issues specific to each assistant. We will only provide a few assistants for demonstrating how to build your own in this repository.
### PR - CI Process
The continuous integration (CI) system will automatically perform the required
builds and run tests (including the ones you are expected to run) for PRs. Builds
and test runs must be clean.
If the CI build fails for any reason, the PR issue will be updated with a link
that can be used to determine the cause of the failure.
### Detailed Workflow Walkthrough
This detailed guide walks you through the process of contributing to our repository via forking, cloning, and managing your Git workflow.
Start by forking the repository on GitHub. This creates a copy of the repository under your GitHub account.
Clone your forked repository to your local machine:
```bash
git clone https://github.com/YOUR_USERNAME/semanticworkbench.git
cd semanticworkbench
```
Add the original repository as an upstream remote:
```bash
git remote add upstream https://github.com/microsoft/semanticworkbench.git
```
Check your remotes to ensure you have both `origin` and `upstream`:
```bash
git remote -v
```
You should see something like this:
```
origin https://github.com/YOUR_USERNAME/semanticworkbench.git (fetch)
origin https://github.com/YOUR_USERNAME/semanticworkbench.git (push)
upstream https://github.com/microsoft/semanticworkbench.git (fetch)
upstream https://github.com/microsoft/semanticworkbench.git (push)
```
To keep your fork updated with the latest changes from upstream, configure your local `main` branch to track the upstream `main` branch:
```bash
git branch -u upstream/main main
```
Alternatively, you can edit your `.git/config` file:
```ini
[branch "main"]
remote = upstream
merge = refs/heads/main
```
Before starting a new feature or bug fix, ensure that your fork is up-to-date with the latest changes from upstream:
```bash
git checkout main
git pull upstream main
```
Create a new branch for your feature or bug fix:
```bash
git checkout -b feature-name
```
Make your changes in the codebase. Once you are satisfied, add and commit your changes:
```bash
git add .
git commit -m "Description of your changes"
```
Push your changes to your fork:
```bash
git push origin feature-name
```
Go to your fork on GitHub, and you should see a `Compare & pull request` button. Click it and submit your pull request (PR) against the original repository’s `main` branch.
If there are changes in the main repository after you created your branch, sync them to your branch:
```bash
git checkout main
git pull upstream main
git checkout feature-name
git rebase main
```
Once your PR is merged, you can delete your branch both locally and from GitHub.
**Locally:**
```bash
git branch -d feature-name
```
**On GitHub:**
Go to your fork and delete the branch from the `Branches` section.
=== File: KNOWN_ISSUES.md ===
# Semantic Workbench Known Issues
You may encounter the following known issues, which may include workarounds, mitigation's, or expected resolution time-frames.
## Semantic Workbench App
### Error loading conversations: {"name":"BrowserAuthError","message":"hash_empty_error: Hash value cannot be processed because it is empty. Please verify that your redirectUri is not clearing the hash..."}
This error may appear when the access token for your login has expired and is not refreshing properly. More exploration is needed for the actual fix.
**Workaround**
1. If you encounter this error when using the Semantic Workbench app, please log out of the web app (upper right corner) and log back in.
=== File: Makefile ===
this_dir = $(patsubst %/,%,$(dir $(realpath $(lastword $(MAKEFILE_LIST)))))
include $(this_dir)/tools/makefiles/recursive.mk
# AI Context Files Generation - runs at repo root only
.PHONY: ai-context-files
ai-context-files:
@echo "Building AI context files..."
@python tools/build_ai_context_files.py
@echo "AI context files generated in ai_context/generated/"
=== File: README.md ===
# Semantic Workbench
Semantic Workbench is a versatile tool designed to help prototype intelligent assistants quickly.
It supports the creation of new assistants or the integration of existing ones, all within a
cohesive interface. The workbench provides a user-friendly UI for creating conversations with one
or more assistants, configuring settings, and exposing various behaviors.
The Semantic Workbench is composed of three main components:
- [Workbench Service](workbench-service/README.md) (Python): The backend service that
handles core functionalities.
- [Workbench App](workbench-app/README.md) (React/Typescript): The frontend web user
interface for interacting with workbench and assistants.
- [Assistant Services](examples) (Python, C#, etc.): any number of assistant services that implement the service protocols/APIs,
developed using any framework and programming language of your choice.
Designed to be agnostic of any agent framework, language, or platform, the Semantic Workbench
facilitates experimentation, development, testing, and measurement of agent behaviors and workflows.
Assistants integrate with the workbench via a RESTful API, allowing for flexibility and broad applicability in various development environments.
# Workbench interface examples
# Quick start (Recommended) - GitHub Codespaces for turn-key development environment
GitHub Codespaces 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 your local machine. It works with any system with a web
browser and internet connection, including Windows, MacOS, Linux, Chromebooks, tablets, and mobile devices.
See the [GitHub Codespaces / devcontainer README](.devcontainer/README.md) for more information on how to set up and use GitHub Codespaces
with Semantic Workbench.
## Local development environment
See the [setup guide](docs/SETUP_DEV_ENVIRONMENT.md) on how to configure your dev environment. Or if you have Docker installed you can use dev containers with VS Code which will function similarly to Codespaces.
## Using VS Code
Codespaces will is configured to use `semantic-workbench.code-workspace`, if you are working locally that is recommended over opening the repo root. This ensures that all project configurations, such as tools, formatters, and linters, are correctly applied in VS Code. This avoids issues like incorrect error reporting and non-functional tools.
Workspace files allow us to manage multiple projects within a monorepo more effectively. Each project can use its own virtual environment (venv), maintaining isolation and avoiding dependency conflicts. Multi-root workspaces (\*.code-workspace files) can point to multiple projects, each configured with its own Python interpreter, ensuring seamless functionality of Python tools and extensions.
### Start the app and service
- Use VS Code > `Run and Debug` (Ctrl/Cmd+Shift+D) > `semantic-workbench` to start the project
- Open your browser and navigate to `https://127.0.0.1:4000`
- You may receive a warning about the app not being secure; click `Advanced` and `Proceed to localhost` to continue
- You can now interact with the app and service in the browser
### Start an assistant service:
- Launch an example an [example](examples/) assistant service:
- No llm api keys needed
- Use VS Code > `Run and Debug` (Ctrl/Cmd+Shift+D) > `examples: python-01-echo-bot` to start the example assistant that echos your messages. This is a good base to understand the basics of building your own assistant.
- Bring your own llm api keys
- Use VS Code > `Run and Debug` (Ctrl/Cmd+Shift+D) > `examples: python-02-simple-chatbot` to start the example chatbot assistant. Either set your keys in your .env file or after creating the assistant as described below, select it and provide the keys in the configuration page.
## Open the Workbench and create an Assistant
Open the app in your browser at [`https://localhost:4000`](https://localhost:4000). When you first log into the Semantic Workbench, follow these steps to get started:
1. **Create an Assistant**: On the dashboard, click the `New Assistant` button. Select a template from the available assistant services, provide a name, and click `Save`.
2. **Start a Conversation**: On the dashboard, click the `New Conversation` button. Provide a title for the conversation and click `Save`.
3. **Add the Assistant**: In the conversation window, click the conversation canvas icon and add your assistant to the conversation from the conversation canvas. Now you can converse with your assistant using the message box at the bottom of the conversation window.
Expected: You get a response from your assistant!
Note that the workbench provides capabilities that not all examples use, for example providing attachments. See the [Semantic Workbench](docs/WORKBENCH_APP.md) for more details.
# Developing your own assistants
To develop new assistants and connect existing ones, see the [Assistant Development Guide](docs/ASSISTANT_DEVELOPMENT_GUIDE.md) or any check out one of the [examples](examples).
- [Python example 1](examples/python/python-01-echo-bot/README.md): a simple assistant echoing text back.
- [Python example 2](examples/python/python-02-simple-chatbot/README.md): a simple chatbot implementing metaprompt guardrails and content moderation.
- [Python example 3](examples/python/python-03-multimodel-chatbot/README.md): an extension of the simple chatbot that supports configuration against additional llms.
- [.NET example 1](examples/dotnet/dotnet-01-echo-bot/README.md): a simple agent with echo and support for a basic `/say` command.
- [.NET example 2](examples/dotnet/dotnet-02-message-types-demo/README.md): a simple assistants showcasing Azure AI Content Safety integration and some workbench features like Mermaid graphs.
- [.NET example 3](examples/dotnet/dotnet-03-simple-chatbot/README.md): a functional chatbot implementing metaprompt guardrails and content moderation.
## Starting the workbench from the command line
- Run the script `tools\run-workbench-chatbot.sh` or `tools\run-workbench-chatbot.ps` which does the following:
- Starts the backend service, see [here for instructions](workbench-service/README.md).
- Starts the frontend app, see [here for instructions](workbench-app/README.md).
- Starts the [Python chatbot example](examples/python/python-02-simple-chatbot/README.md)
## Refreshing Dev Environment
- Use the `tools\reset-service-data.sh` or `tools\reset-service-data.sh` script to reset all service data. You can also delete `~/workbench-service/.data` or specific files if you know which one(s).
- From repo root, run `make clean install`.
- This will perform a `git clean` and run installs in all sub-directories
- Or a faster option if you just want to install semantic workbench related stuff:
- From repo root, run `make clean`
- From `~/workbench-app`, run `make install`
- From `~/workbench-service`, run `make install`
# Contributing
This project welcomes contributions and suggestions. Most contributions require you to agree to a
Contributor License Agreement (CLA) declaring that you have the right to, and actually do, grant us
the rights to use your contribution. For details, visit <https://cla.opensource.microsoft.com>.
When you submit a pull request, a CLA bot will automatically determine whether you need to provide
a CLA and decorate the PR appropriately (e.g., status check, comment). Simply follow the instructions
provided by the bot. You will only need to do this once across all repos using our CLA.
Please see the detailed [contributing guide](CONTRIBUTING.md) for more information on how you can get involved.
This project has adopted the [Microsoft Open Source Code of Conduct](https://opensource.microsoft.com/codeofconduct/).
For more information see the [Code of Conduct FAQ](https://opensource.microsoft.com/codeofconduct/faq/) or
contact [[email protected]](mailto:[email protected]) with any additional questions or comments.
# Trademarks
This project may contain trademarks or logos for projects, products, or services. Authorized use of Microsoft
trademarks or logos is subject to and must follow
[Microsoft's Trademark & Brand Guidelines](https://www.microsoft.com/en-us/legal/intellectualproperty/trademarks/usage/general).
Use of Microsoft trademarks or logos in modified versions of this project must not cause confusion or imply Microsoft sponsorship.
Any use of third-party trademarks or logos are subject to those third-party's policies.
=== File: RESPONSIBLE_AI_FAQ.md ===
# Semantic Workbench's Responsible AI FAQ
## What is Semantic Workbench?
- Semantic Workbench is a web application intended to help prototyping assistants during the development phase.
- Semantic Workbench provides a user interface for creating conversations with one or more assistants, including a configuration user interface, and a service to connect custom assistants.
## What is/are Semantic Workbench’s intended use(s)?
- Semantic Workbench is designed for prototyping assistants, running conversations and testing assistants behavior in a test environment.
- Semantic Workbench is not intended to be run in a production environment. AI assistants and agents developed with the help of Semantic Workbench, should be deployed separately from the workbench environment, in dedicated environments with proper monitoring and safety protections.
## How was Semantic Workbench evaluated? What metrics are used to measure performance?
Semantic Workbench has been built from the ground up specifically for the experimentation use-case. Other user interfaces and tools have been evaluated, but none allowed to prototype assistants decoupled from a specific underlying technology stack such as AI models or frameworks.
Semantic Workbench does not mandate any specific technology or framework.
Developers can use any of preferred technology and connect their bots to Semantic Workbench to benefit from its user interface, including configuration, debugging and visualization tools.
## What are the limitations of Semantic Workbench? How can users minimize the impact of Semantic Workbench’s limitations when using the system?
- Semantic Workbench is not an assistant in itself, it only allows to connect and test existing assistants.
- Semantic Workbench is not a container for Production assistants. Assistants and Agents are executed in the workbench environment only during development and test phases.
- Semantic Workbench does not monitor assistants behavior, it's only designed to make it easier for developers to observe the behavior. Developers are responsible for designing assistants and understanding if these are working properly.
- Intelligent assistants must be developed with usual IDEs and development tools like Semantic Kernel, Langchain, Autogen, following the best practices there recommended, for instance [Responsible AI and Semantic Kernel](https://learn.microsoft.com/semantic-kernel/when-to-use-ai/responsible-ai) and [LangSmith](https://www.langchain.com/langsmith).
- The workbench is unable to automatically discover agents: once the code for an agent is ready, some extra code needs to be added in order to connect the assistant to Semantic Workbench.
- Developers making use of the provided sample agents or connecting their own agents to Semantic Workbench are responsible for implementing security and safety into their agents, using, for example, [Azure AI Content Safety](https://azure.microsoft.com/eproducts/ai-services/ai-content-safety) and [Microsoft Purview](https://www.microsoft.com/security/business/microsoft-purview), and leveraging tools like [Responsible AI Toolbox](https://github.com/microsoft/responsible-ai-toolbox).
- When using Semantic Workbench to test an assistant, developers should carefully observe the bot’s behavior and use the debugging tools to investigate any unexpected outcomes. Although Semantic Workbench does not automatically detect harmful, inaccurate, or biased content, it enables developers to run and debug conversations, which helps identify and fix issues, improve the bot’s behavior, and edit prompts and code as necessary.
- Developers using Semantic Workbench can adopt a user-centric approach in designing applications, ensuring that users are well-informed and have the ability to approve any actions taken by the AI. Semantic Workbench exposes all the information provided by the connected assistants, so it's important that developers code these assistants to expose their rationale, prompts, and state.
- Additionally, intelligent assistants developers should implement mechanisms to monitor and filter any automatically generated information, if deemed necessary. Some of these mechanisms include:
- moderating users' input and AI's output, for instance using [Azure AI Content Safety](https://azure.microsoft.com/products/ai-services/ai-content-safety).
- including metaprompt guardrails, instructing LLMs how to protect users and business logic. For instance see [this page](https://learn.microsoft.com/azure/ai-services/openai/concepts/system-message) for information and examples.
- By addressing responsible AI issues in this manner, developers can create assistants that are not only efficient and useful but also adhere to ethical guidelines and prioritize user trust and safety.
## What operational factors and settings allow for effective and responsible use of Semantic Workbench?
- First and foremost, use Semantic Workbench to access your assistants only in private development environments, such as your localhost.
- Developers using Semantic Workbench can precisely define user interactions and how user data is managed in the source code of their intelligent assistants.
- If a prototype assistant runs a sequence of components, additional risks/failures may arise when using non-deterministic behavior. To mitigate this, developers can:
- Implement safety measures and bounds on each component to prevent undesired outcomes.
- Add output to the user to maintain control and awareness of the system's state.
- In multi-agent scenarios, build in places that prompt the user for a response, ensuring user involvement and reducing the likelihood of undesired results due to multi-agent looping.
- When working with AI, the developer can enable content moderation in the AI platforms used, and has complete control on the prompts being used, including the ability to define responsible boundaries and guidelines. For instance:
- When using Azure OpenAI, by default the service includes a content filtering system that works alongside core models. This system works by running both the prompt and completion through an ensemble of classification models aimed at detecting and preventing the output of harmful content. In addition to the content filtering system, the Azure OpenAI Service performs monitoring to detect content and/or behaviors that suggest use of the service in a manner that might violate applicable product terms. The filter configuration can be adjusted, for example to block also "low severity level" content. See [here](https://learn.microsoft.com/azure/ai-services/openai/concepts/content-filter) for more information.
- The developer can integrate Azure AI Content Safety to detect harmful user-generated and AI-generated content, including text and images. The service includes an interactive Studio online tool with templates and customized workflows. See [here](https://learn.microsoft.com/azure/ai-services/content-safety) for more information.
- When using OpenAI the developer can integrate OpenAI Moderation to identify problematic content and take action, for instance by filtering it. See [here](https://platform.openai.com/docs/guides/moderation) for more information.
- Other AI providers provide content moderation and moderation APIs, which developers can integrate with Node Engine.
=== File: SECURITY.md ===
## Security
Microsoft takes the security of our software products and services seriously, which includes all source code repositories managed through our GitHub organizations, which include [Microsoft](https://github.com/Microsoft), [Azure](https://github.com/Azure), [DotNet](https://github.com/dotnet), [AspNet](https://github.com/aspnet) and [Xamarin](https://github.com/xamarin).
If you believe you have found a security vulnerability in any Microsoft-owned repository that meets [Microsoft's definition of a security vulnerability](https://aka.ms/security.md/definition), please report it to us as described below.
## Reporting Security Issues
**Please do not report security vulnerabilities through public GitHub issues.**
Instead, please report them to the Microsoft Security Response Center (MSRC) at [https://msrc.microsoft.com/create-report](https://aka.ms/security.md/msrc/create-report).
If you prefer to submit without logging in, send email to [[email protected]](mailto:[email protected]). If possible, encrypt your message with our PGP key; please download it from the [Microsoft Security Response Center PGP Key page](https://aka.ms/security.md/msrc/pgp).
You should receive a response within 24 hours. If for some reason you do not, please follow up via email to ensure we received your original message. Additional information can be found at [microsoft.com/msrc](https://www.microsoft.com/msrc).
Please include the requested information listed below (as much as you can provide) to help us better understand the nature and scope of the possible issue:
* Type of issue (e.g. buffer overflow, SQL injection, cross-site scripting, etc.)
* Full paths of source file(s) related to the manifestation of the issue
* The location of the affected source code (tag/branch/commit or direct URL)
* Any special configuration required to reproduce the issue
* Step-by-step instructions to reproduce the issue
* Proof-of-concept or exploit code (if possible)
* Impact of the issue, including how an attacker might exploit the issue
This information will help us triage your report more quickly.
If you are reporting for a bug bounty, more complete reports can contribute to a higher bounty award. Please visit our [Microsoft Bug Bounty Program](https://aka.ms/security.md/msrc/bounty) page for more details about our active programs.
## Preferred Languages
We prefer all communications to be in English.
## Policy
Microsoft follows the principle of [Coordinated Vulnerability Disclosure](https://aka.ms/security.md/cvd).
=== File: SUPPORT.md ===
# Support
## How to file issues and get help
This project uses GitHub Issues to track bugs and feature requests. Please search the existing
issues before filing new issues to avoid duplicates. For new issues, file your bug or
feature request as a new Issue.
For help and questions about using this project, please create a new GitHub Issue with your request.
## Microsoft Support Policy
Support for this project is limited to the resources listed above.
=== File: ruff.toml ===
line-length = 120
target-version = "py311"
[format]
docstring-code-format = true
line-ending = "lf"
preview = true
```
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-filesystem-edit/data/transcripts/transcript_Startup_Idea_2_202503031659.md:
--------------------------------------------------------------------------------
```markdown
### [Monday, March 3 3:01 PM] User:
notice: User created the conversation
----------------------------------
### [Monday, March 3 3:01 PM] User:
notice: Codespace Assistant 2-26 added to conversation
----------------------------------
### [Monday, March 3 3:01 PM] Codespace Assistant 2-26:
Hello! I am an assistant that can help you with coding projects within the context of the Semantic Workbench.Let's get started by having a conversation about your project. You can ask me questions, request code snippets, or ask for help with debugging. I can also help you with markdown, code snippets, and other types of content. You can also attach .docx, text, and image files to your chat messages to help me better understand the context of our conversation. Where would you like to start?
----------------------------------
### [Monday, March 3 3:05 PM] User:
Hello! I am trying to come up with a startup idea. I want it to be around "daily challenge games" kind of like a crossword or suduko, but the trick is that they are AI powered. What do you think about this?
----------------------------------
### [Monday, March 3 3:06 PM] Codespace Assistant 2-26:
David, I think this is an excellent idea! AI-powered daily challenge games could take traditional formats like crosswords or Sudoku to the next level by introducing adaptability, personalization, and dynamic content that grows with the user. Here are some directions to flesh out your idea further:
### 1. **Core Concept: AI-Powered Challenge Games**
- Each day, users receive unique challenges created by AI, ensuring that every experience is fresh and tailored.
- The AI learns and adjusts the difficulty level based on user performance and preferences.
- Themes could range from traditional puzzles (e.g., word games, math challenges) to more novel concepts (e.g., logic-based storytelling puzzles, pattern recognition).
---
### 2. **Unique Selling Points**
- **Personalization:** Tailored puzzles based on user skills and progress. Are they better at number games or solving riddles? The AI adapts!
- **Endless Creativity:** AI can generate puzzles outside the realm of what's feasible manually, including hybrid formats.
- **Social Play:** Introduce multiplayer or collaborative challenges combining AI-generated puzzles with competitive or cooperative dynamics.
- **Niche Focus**: Cater to specific interests (e.g., coding challenges for developers, trivia-based games for bookworms, or even fitness-inspired mental puzzles).
---
### 3. **Game Ideas in Detail**
Here are some innovative concepts:
#### AI-Enhanced Crosswords
- Dynamic themes for every day, like pop culture, science, or a user's favorite TV series.
- Generated clues that match user preferences (e.g., easy/hard styles or witty vs. straightforward).
#### Visual Puzzle Challenges
- AI-generated image or video riddles (e.g., "Spot the pattern," design-based challenges).
- Picture-based Sudoku-style layouts with dynamically changing rules.
#### Logic Coding Puzzles
- AI generates small coding challenges where players write snippets of code to "unlock" levels.
- These could scale from basic logic to actions requiring complex algorithms (think Python, JavaScript).
#### Language Learning Games
- “Translate this phrase” or “Fix grammar errors” to improve or learn foreign languages.
- AI-enhanced phonetic puzzles (e.g., “Find the matching sound for this word”).
#### Social Deduction/Team Challenges
- Cooperative games where AI generates clues that individuals must share and interpret together.
- Time-based race modes (e.g., solve X puzzles within 15 minutes collaboratively).
---
### 4. **Business and Monetization Plan**
Given the potential popularity of personalized gaming apps, here are a few ways to monetize:
- **Freemium Model:** Free gameplay with premium features (ad-free, advanced AI features, unique themes).
- **Subscriptions:** Offer a daily dose of premium puzzles for a monthly fee.
- **Sponsorships and Licensing:** Collaborate with brands or media franchises to create customized puzzle sets.
- **Merchandising:** Sell “pro-player perks,” hint systems, or even physical versions of the puzzles for offline play.
---
### 5. **Strengths of AI Here**
AI can:
- Ensure every challenge stays fresh, erasing the problem of repetition common in puzzles.
- Support language-based, math-based, or even multimedia puzzles in ways that scale globally.
- Automatically assess user engagement and tweak challenges to keep them hooked.
---
### 6. **MVP (Minimum Viable Product) Idea**
To start small and validate your concept:
- Create a web/mobile game focused on one type of AI challenge (e.g., an AI-generated crossword or Sudoku).
- Use GPT-based language models or generative image technology to create dynamic puzzles.
- Track user engagement and refine features based on initial traction.
---
How do you feel about these directions for your startup idea? Would you like me to work on a strategy document, some sample designs, or an app pitch? Let me know how you’d like to proceed!
----------------------------------
### [Monday, March 3 3:09 PM] User:
Let's focus more on the game ideas. I've actually created one. I'm attaching some info about it
attachment: ReDoodle.txt
----------------------------------
### [Monday, March 3 3:10 PM] Codespace Assistant 2-26:
David, your creation of **ReDoodle** as a daily web puzzle game is fantastic! The concept of transforming a starting image into a goal image through a series of prompts is both creative and offers lots of potential for engagement. Here's how we could expand on your ideas or generate complementary games in the same space of daily challenges:
---
### 1. **Building on ReDoodle**
Since ReDoodle transforms images based on prompts, here are a few ways to deepen or extend the current concept:
- **Timed Challenges:** Introduce a countdown timer to solve the puzzle for an extra layer of excitement.
- **Daily Leaderboards:** Track how many transformations it takes for users to get to the target image and rank them globally.
- **Creative Bonus Rounds:** Reward users for doing something creative (e.g., a funniest transformation wins).
- **Themed Weeks:** Each week could focus on a particular thematic goal (e.g., reimagining famous paintings or movie stills).
- **AI Feedback System:** After they finish a puzzle, the AI could analyze their approach and provide humorous commentary or improvement suggestions.
---
### 2. **New "Re"-Based Game Ideas**
Inspired by ReDoodle's transformative gameplay, here are other AI-powered "re-" games:
- **ReSketch:** Players refine or replicate rough AI-generated drawings into high-quality illustrations by giving drawing-style prompts.
- **ReCompose:** Transform or rearrange music notes until the output matches a target piece of music, combining GPT with audio tech.
- **ReMeme:** Given a target meme format and theme, players must construct a viral-worthy meme using AI-generated content.
---
### 3. **AI Image Creativity Games**
Taking inspiration from ReDoodle, here are more visual game types that could differentiate your offering:
- **Pixel Chaser:** Start with a pixelated version of the target image, and with each accurate guess about its composition, the image becomes clearer.
- **Style Hunt:** Transform an ordinary image into one that matches a famous artistic style or painter by using descriptive prompts (e.g., "Make this in the style of Van Gogh").
- **Story in Frames:** Players are given a randomized sequence of images and must rearrange them or generate additional scenes to create a coherent story.
---
### 4. **Text-Based Challenge Games**
For users who enjoy daily prompts but prefer word-based interactivity, text-based challenges include:
- **WordSculpt:** Players are given a messy, abstract AI-generated paragraph and must reword prompts to transform it into coherent or specific text.
- **ConvoJourney:** Start with a snippet of an AI-driven conversation and craft prompts or responses to lead toward a fixed, humorous, or dramatic sentence.
---
### 5. **Logic-Based Games**
For fans of puzzles that require thinking and strategy:
- **MathMaze:** Start with a numerical outcome, and players must use AI-suggested inputs to break it down into component equations (bonus for the most creative solutions).
- **Logic Grid Story:** Generate a story where users need to deduce hidden elements based on provided clues (classic logic puzzle style).
---
### 6. **Dynamic Team Games**
Incorporate multiplayer elements and team-based challenges:
- **Shared Doodles:** Team up to collaboratively solve a transformation challenge, with different players working on parts of the puzzle sequentially.
- **Prompt Roulette:** Each player adds unique descriptive prompts alternately to complete transformations, creating unpredictable yet fun outcomes.
---
### 7. **Experimental Challenge Ideas**
Try more avant-garde gameplay:
- **Dream Debugger:** Start with a surreal AI-generated dreamscape image, and players must submit prompts to "fix glitches" or uncover coherent story elements.
- **Virtual Escape Room:** Create and solve a series of AI-generated virtual "rooms" by interpreting images/story elements to find clues.
---
Would you like me to expand in detail on any of these, maybe mock up a design for another game, or suggest how you could tie several of these into a unified platform? ReDoodle could become the flagship of an exciting, broader daily AI puzzle brand!
----------------------------------
### [Monday, March 3 3:11 PM] User:
Ok. Let's first start a document on game ideas - I think this is the biggest hurdle. Proving that we have enough novel and interesting games that leverage AI.
----------------------------------
### [Monday, March 3 3:11 PM] Codespace Assistant 2-26:
Excellent decision! Compiling a structured document with game ideas will help you demonstrate the breadth of possibilities and convince stakeholders or collaborators of the platform's potential. I’ll get started on drafting a document that outlines a variety of novel AI-driven game concepts, organized by categories and potential features.
Let me create a Word document containing these ideas. Starting with the foundation you've already developed, I will add sections for further brainstorming and expansion.
Let me handle the initial draft for you.
----------------------------------
### [Monday, March 3 3:13 PM] Codespace Assistant 2-26:
note: [Document Editor]: The document has been created from scratch, detailing ideas for "AI-Powered Daily Challenge Games." It includes an overview of the concept, emphasizing the integration of AI for generating unique, tailored experiences. Several themed categories of games were introduced:
1. **Building on ReDoodle:** Suggestions for enhancing existing games with elements like daily leaderboards, creative bonus rounds, and themed weeks.
2. **New 'Re'-Based Game Ideas:** Innovative games like ReSketch to enhance AI drawings and ReCompose to modify music arrangements.
3. **AI Image Creativity Games:** Concepts such as Pixel Chaser and Story in Frames, focusing on visual transformation and narrative building.
4. **Text-Based Challenge Games:** Examples include WordSculpt for refining generated text and ConvoJourney for interactive storytelling.
5. **Logic-Based Games:** Introduced MathMaze and Logic Grid Story for puzzle-solving enthusiasts.
6. **Dynamic Team Games:** Suggestions for coll... <truncated>
----------------------------------
### [Monday, March 3 3:13 PM] Codespace Assistant 2-26:
I've drafted a Word document detailing a range of AI-powered daily challenge game concepts. The focus is on creating unique, engaging, and varied experiences that leverage AI technology. It covers categories like building on ReDoodle, introducing playful "Re-" themes, creative image-based games, text and logic challenges, dynamic team-based play, and experimental concepts.
Let me know if you'd like me to refine or expand on specific sections, or if you’d like to explore additional themes or directions!
----------------------------------
### [Monday, March 3 3:45 PM] User:
Can you reorganize the document to be the top 5 most unique and novel games ideas?
----------------------------------
### [Monday, March 3 3:46 PM] Codespace Assistant 2-26:
Reorganizing the document to prioritize the top 5 most unique and novel game ideas, rearranging the sections to reflect this focus while keeping the rest of the content intact.
----------------------------------
### [Monday, March 3 3:46 PM] Codespace Assistant 2-26:
note: [Document Editor]: The sections "Enhancements on ReDoodle," "Text-Based Challenge Games," and "Dynamic Team Games" were removed entirely from the document. Sections "New 'Re'-Based Game Ideas," "AI Image Creativity Games," "Logic-Based Games," and "Experimental Challenge Ideas" remain unchanged. Overall, this streamlining reduced the document's content to focus on fewer categories, removing specific proposals for enhancements and text- or team-based challenges.
----------------------------------
### [Monday, March 3 3:46 PM] Codespace Assistant 2-26:
I've reorganized the document to focus on the top 5 most unique and novel game ideas. Let me know if you'd like me to refine this list further, explore additional ideas to include, or create a summary to make the document presentation-ready!
----------------------------------
### [Monday, March 3 3:55 PM] User:
Ok, can you now expand on each of the game ideas?
----------------------------------
### [Monday, March 3 3:55 PM] Codespace Assistant 2-26:
Great idea! Expanding on each of the five most novel game ideas will help flesh out their potential and make the document more comprehensive. I'll elaborate on the mechanics, unique features, AI integration, and possible user engagement strategies for each game concept. Let me handle this expansion process.
----------------------------------
### [Monday, March 3 4:02 PM] Codespace Assistant 2-26:
note: [Document Editor]: The updated document expanded upon each game concept, providing detailed descriptions and additional features for each idea:
1. **Dream Debugger** was elaborated into a surreal, choice-based puzzle game where players fix glitches or shape an AI-generated dream using descriptive prompts, leading to branching scenarios and multiple endings.
2. **ReMeme** now includes a scoring system based on humor and theme alignment, introduces a leaderboard mechanic, and supports social sharing of memes.
3. **Pixel Chaser** added gameplay details, such as earning hints through mini-challenges, progressively increasing pixelation in advanced levels, and featuring bonus levels with famous artworks or landscapes.
4. **Logic Grid Story** introduces more sophisticated logic puzzles, interconnected mysteries, and a scoring system for efficiency and accuracy to enhance replayability.
5. **Virtual Escape Room** expanded to highlight dynamically AI-generated room elements, cooperative gamep... <truncated>
----------------------------------
### [Monday, March 3 4:02 PM] Codespace Assistant 2-26:
I expanded on the top 5 game ideas in the document, adding detailed mechanics, unique AI features, player engagement strategies, and ideas for enriching the gameplay experience. Let me know if you’d like me to tweak further, or focus on any specific aspects like visuals or implementation!
----------------------------------
### [Monday, March 3 4:04 PM] User:
Great, now can you add a section for each game about how it leverages AI, in particular LLMs, image generation (or similar tech), voice, etc
----------------------------------
### [Monday, March 3 4:04 PM] Codespace Assistant 2-26:
Adding a section for each game to explain how it directly leverages AI, specifying technologies like large language models (LLMs), image generation, and voice processing. This will articulate the innovative use of technologies for each concept. Let me add this to the document.
----------------------------------
### [Monday, March 3 4:07 PM] Codespace Assistant 2-26:
note: [Document Editor]: The document was updated to include sections explaining how AI is leveraged within each proposed game concept. These additions describe the use of technologies like large language models (LLMs), image generation models, natural language processing, and procedural algorithms to enhance game dynamics. Each game now has a dedicated "How It Leverages AI" subsection detailing its specific implementation of AI technologies, such as dynamic narrative generation in "Dream Debugger," meme scoring in "ReMeme," image refinement in "Pixel Chaser," logic grid management in "Logic Grid Story," and procedural room design in "Virtual Escape Room." These changes add depth and specificity to how AI underpins the gameplay and innovation in these concepts.
----------------------------------
### [Monday, March 3 4:07 PM] Codespace Assistant 2-26:
I’ve included clear sections for each game on how they leverage AI technologies like LLMs, image generation, procedural algorithms, and more. These sections detail the technical aspects enhancing the game's innovation. Let me know if you’d like any additional refinement or examples!
----------------------------------
### [Monday, March 3 4:09 PM] User:
Ok for those idea, can you add a technical implementation section? I want to get a sense of how much effort they would be implement
----------------------------------
### [Monday, March 3 4:09 PM] Codespace Assistant 2-26:
I'll add a "Technical Implementation" section for each game, outlining the core technologies, development timeframes, and complexity to help evaluate the effort involved in bringing these concepts to life. Let me handle that for you.
----------------------------------
### [Monday, March 3 4:10 PM] Codespace Assistant 2-26:
note: [Document Editor]: The primary updates to the document involve the addition of "Technical Implementation" subsections for each of the described game concepts—"Dream Debugger," "ReMeme," and "Pixel Chaser." These new sections provide detailed explanations of how each game could be technically realized using specific AI technologies and tools. For example:
- **Dream Debugger**: Suggestions include using large language models (LLMs) like GPT for narrative responses, image generation models like Stable Diffusion for visuals, and state management systems for branching scenarios.
- **ReMeme**: The section outlines utilizing LLMs fine-tuned for meme generation, implementing image processing AI for formatting, scoring algorithms for evaluating captions, and social media API integration.
- **Pixel Chaser**: Suggestions include using image recognition models like Vision Transformer for matching guesses, an image generation engine for creating and pixelating images, and backend systems to dynami... <truncated>
----------------------------------
### [Monday, March 3 4:10 PM] Codespace Assistant 2-26:
I’ve added "Technical Implementation" sections for each game, outlining the tools, frameworks, and processes required for development. These include leveraging large language models, image generation AI, scoring algorithms, and integration techniques to evaluate the feasibility and effort for each idea. Let me know if you'd like further details or refinement!
----------------------------------
### [Monday, March 3 4:13 PM] User:
I had another idea that I want to work with you on. It is a vector math based idea. Something like we are given "apple" + "royalty" = <user has to guess>
----------------------------------
### [Monday, March 3 4:13 PM] Codespace Assistant 2-26:
That’s a very intriguing concept! This idea could be based on vector arithmetic using text embeddings like those generated by large language models (e.g., GPT models or other word embedding algorithms). The gameplay revolves around leveraging word associations and relationships encoded in the embeddings.
To flesh this out quickly:
### Initial Concept:
- **Core Gameplay:**
- Players are given two or more words (e.g., "apple" + "royalty"), and the AI computes the sum/difference in their vector embeddings. The player then guesses the resulting word based on the contextual "math."
- Possible answers for "apple + royalty" might include "crown," "pie," etc.
- **AI Integration Idea:** Leverage AI text embedding models like OpenAI's word embeddings or cosine similarity engines to match user input to the expected answer.
---
Would you like me to create a detailed description of the game and how it could work, or should we immediately begin incorporating it into the document alongside the others?
----------------------------------
### [Monday, March 3 4:14 PM] User:
Lets expand on the idea some more. How would the score be computed? Would it be too hard to have the user guess the exact closest word?
----------------------------------
### [Monday, March 3 4:14 PM] Codespace Assistant 2-26:
These are excellent considerations! Let’s explore scoring systems and gameplay mechanics to ensure the game is both fun and accessible. Here's a breakdown:
---
### 1. **Scoring System**
A flexible scoring system will make the game engaging while rewarding users for getting close to the "perfect" answer. Here’s how it could work:
- **Cosine Similarity Scoring:**
- The system computes the cosine similarity between the user’s guess and the true vector result. The score could range from 0 (completely unrelated) to 1 (exact match).
- Scores can be bucketed into ranges for simplicity:
- **0.90–1.00:** Perfect match (e.g., "crown").
- **0.75–0.89:** Close match (e.g., "throne").
- **0.50–0.74:** Somewhat related (e.g., "castle").
- Below **0.50:** Too far off (e.g., "fruit").
- **Partial Credit for Creativity:** Players might get bonus points for submitting guesses that are imaginative but not directly correct, encouraging lateral thinking.
---
### 2. **Flexible Answer Matching**
Requiring an exact match may indeed frustrate players. To avoid this:
- Use multiple "valid answers" for a single vector calculation. For example, "apple + royalty" might allow "crown," "golden," or "throne."
- Introduce hints for tougher questions (e.g., display synonyms related to the expected answer).
---
### 3. **Challenge Ideas**
- **Difficulty Levels:**
- **Easy:** Closer vector pairings (e.g., "cat + small" = "kitten").
- **Medium:** More abstract relationships (e.g., "summer - hot").
- **Hard:** Multi-word operations (e.g., "Rome + fight - empire").
- **Timed Challenges:** Adding a timer per guess keeps players on their toes.
- **Combo Scoring:** Chain multiple correct guesses to earn bonus multipliers.
---
### 4. **AI Model Adjustments**
To reduce difficulty:
1. Use **fine-tuned embeddings** for domain-specific challenges (e.g., pop culture terms).
2. Allow **leniency thresholds**—accept words within 10% similarity of the intended answer.
---
### 5. **Fun Themes for Word Sets**
- Literary: "Shakespeare + Love = Romeo."
- Food-Based: "Pizza + Happiness = Party."
- Geography or History: "Greece + War = Sparta."
---
Would you like me to start creating an official description for this game or work on some example rounds to illustrate how this scoring might look to players?
----------------------------------
### [Monday, March 3 4:15 PM] User:
Can you add this to my document as the first idea?
----------------------------------
### [Monday, March 3 4:15 PM] Codespace Assistant 2-26:
[no response from openai]
----------------------------------
### [Monday, March 3 4:16 PM] Codespace Assistant 2-26:
note: [Document Editor]: A new game concept, **Vector Math Challenge**, was added to the document. This game involves word association and mathematical operations on word embeddings, challenging players to predict the resulting word based on AI-computed vector math. Details about how it leverages AI through word embeddings, cosine similarity for scoring, and AI-generated hints were outlined. The technical implementation for this concept was also explained, including the use of pre-trained word embedding models and backend systems for gameplay.
The rest of the document remains unchanged, retaining the original descriptions of the existing games: Dream Debugger, ReMeme, and Pixel Chaser.
----------------------------------
### [Monday, March 3 4:16 PM] Codespace Assistant 2-26:
I’ve added the **Vector Math Challenge** as the first concept in your document. It includes gameplay mechanics, how it leverages AI (e.g., cosine similarity and word embeddings), and a technical implementation plan. Let me know if you’d like any modifications or further details!
----------------------------------
### [Monday, March 3 4:16 PM] User:
Can you think of a better name?
----------------------------------
### [Monday, March 3 4:17 PM] Codespace Assistant 2-26:
Sure! Here are some alternative name ideas for your game:
1. **Word Alchemy** – Transforming words through creative combinations.
2. **Vector Vibes** – Playing with vector relationships in a fun way.
3. **Semantic Shuffle** – Highlighting the reshuffling of meanings through word math.
4. **Mind Matrix** – Emphasizing the logical and intuitive thinking required.
5. **Word Fusion** – Combining words to create something new.
6. **Idea Equation** – Representing thought-provoking word equations.
7. **Concept Crunch** – Crunching words into meaningful results.
8. **LexiMath** – A blend of "lexicon" and "math."
Let me know if any of these resonate or you'd like further brainstorming!
----------------------------------
### [Monday, March 3 4:17 PM] User:
I like semantic shuffle. Update to that in my doc
----------------------------------
### [Monday, March 3 4:17 PM] Codespace Assistant 2-26:
[no response from openai]
----------------------------------
### [Monday, March 3 4:18 PM] Codespace Assistant 2-26:
note: [Document Editor]: The primary change made to the document was renaming the "Vector Math Challenge" game to "Semantic Shuffle." All references to the previous title were updated accordingly, but the game concept, its AI utilization details, and technical implementation remained unchanged. No other sections or content were modified in the document.
----------------------------------
### [Monday, March 3 4:18 PM] Codespace Assistant 2-26:
I've updated the title of the game concept to **Semantic Shuffle** throughout the document. Let me know if there’s anything else you’d like to adjust or refine!
----------------------------------
### [Monday, March 3 4:19 PM] User:
Under each game, can you add one sentence or less catch phrase?
----------------------------------
### [Monday, March 3 4:19 PM] Codespace Assistant 2-26:
Adding a catchy one-liner summarizing each game concept to make them more engaging and memorable. Let me take care of that in your document.
----------------------------------
### [Monday, March 3 4:20 PM] Codespace Assistant 2-26:
note: [Document Editor]: The edits to the document enhanced its appeal by adding engaging tagline-like sentences for each game concept, aiming to capture the reader’s interest and succinctly summarize the unique essence of each game. For *Semantic Shuffle*, a phrase highlighting creativity and semantics was included. Similarly, for *Dream Debugger*, a tagline emphasizing the surreal and choice-driven narrative was added. *ReMeme* gained a sentence that underscores humor and viral potential, while *Pixel Chaser* was complemented with a line about mystery and visual reveals. No structural or content-based changes were made to the detailed descriptions or technical implementations.
----------------------------------
### [Monday, March 3 4:20 PM] Codespace Assistant 2-26:
I’ve added a catchy one-liner under each game to summarize their unique essence and make them more engaging. Let me know if you want to refine any of the taglines or add additional flair!
----------------------------------
### [Monday, March 3 4:21 PM] User:
Can we flesh out Dream Debugger some more? I'm not really getting how to implement that one.
----------------------------------
### [Monday, March 3 4:22 PM] Codespace Assistant 2-26:
Absolutely! Dream Debugger has a lot of potential, but implementing a surreal, choice-driven puzzle game requires more detail to clarify its mechanics and technical foundation. Let me expand its section in the document with specifics on:
1. **Gameplay Mechanics:** How players interact with the game world, solve puzzles, and influence the narrative.
2. **AI Utilization:** How we employ models for generating dream scenarios, managing branching choices, and creating visuals.
3. **Technical Implementation Plan:** Defining systems for procedural generation, player state management, and puzzle design.
Let me revise the document to flesh this out.
----------------------------------
### [Monday, March 3 4:23 PM] Codespace Assistant 2-26:
note: [Document Editor]: The primary changes made to the document are as follows:
1. **Expanded Description for "Dream Debugger"**:
- Shifted from a broad overview of gameplay to a more detailed narrative-focused premise. It now highlights players' roles as dream detectives solving mysteries within dreamscapes. Specific gameplay elements, such as repairing objects or choosing between confronting or avoiding characters, were added to illustrate how choices shape outcomes and encourage replayability.
- Additional details were introduced on the use of AI for procedurally generated environments, contextual narrative adjustments, and ensuring visual coherence in dream elements.
2. **Updated Technical Implementation for "Dream Debugger"**:
- Broader explanation of tools and techniques, including the use of libraries like Ink or Twine for narrative generation, procedural art rendering with Unity or Unreal Engine, and dynamic dialogue using AI models like GPT.
- Mentioned the use of Ho... <truncated>
----------------------------------
### [Monday, March 3 4:23 PM] Codespace Assistant 2-26:
I’ve fleshed out the *Dream Debugger* section significantly, providing more detailed gameplay mechanics and a clear technical implementation plan. This includes procedural generation for visuals, narrative tools for branching storylines, and AI for dynamic interactions. Let me know if this adds clarity or if any parts need further refinement!
----------------------------------
### [Monday, March 3 4:24 PM] User:
I think Dream Debugger is too much like a "real" game. Let's replace it with something more that could be played quickly or on mobile. What ideas do you have?
----------------------------------
### [Monday, March 3 4:24 PM] Codespace Assistant 2-26:
I understand your concern—mobile-friendly, quick-to-play games typically focus on short sessions, easy interactions, and replayability. Here are some alternative ideas that can replace **Dream Debugger** and align with that approach:
---
### 1. **AI Word Collapse**
- **Concept:** Players are given a grid of words and must find pairs of words that "collapse" into a similar concept (e.g., “apple” + “tree” = “orchard”).
- **Gameplay:** Players clear the grid by making associations, and the faster they finish, the higher their score.
- **AI Use:** An AI determines valid associations using embeddings and similarity scores.
---
### 2. **Rapid Remix**
- **Concept:** Players remix AI-generated music or art in under 60 seconds to fit a given theme (e.g., turn a cheerful tune into a spooky one).
- **Gameplay:** Drag-and-drop sliders or quick prompts adjust the tone, color, or tempo.
- **AI Use:** Embedding models or fine-tuned generative AI refine the user’s remix in real time.
---
### 3. **Emoji Alchemy**
- **Concept:** Combine emojis like ingredients in a potion to generate unexpected results (e.g., “🌊 + 🧊 = 🧊 Ocean Ice Shelf”).
- **Gameplay:** Players gain points for creative combinations that align with AI-calculated similarities.
- **AI Use:** Generative tools create descriptions for rare combinations and reward originality.
---
### 4. **Chain Reaction**
- **Concept:** Build word or image chains linking concepts together (e.g., "cat" -> "dog" -> "wolf"), striving for either creativity or accuracy.
- **Gameplay:** Set time limits for creating the chain to add pressure.
- **AI Use:** NLP models evaluate chain plausibility and creativity simultaneously.
---
### 5. **Prompt Master**
- **Concept:** Players are presented with a goal or scenario (e.g., "Describe a blue-skinned alien"), and they must craft the shortest possible prompt to achieve the result.
- **Gameplay:** A timer adds urgency, and scoring depends on matching precision at minimal length.
- **AI Use:** Leverages a fine-tuned AI generator to visually or textually create the result based on prompts.
---
### Mobile and Quick-Play Principles:
- **Game Length:** Sessions last about 2–3 minutes with instant score feedback.
- **Interaction Style:** Tap-based, drag-and-drop, or quick prompts make for intuitive gameplay.
- **Replayability:** Procedurally generated content makes every game unique.
---
Would you like me to add one of these to the document and expand on it? If so, let me know which one resonates most!
----------------------------------
### [Monday, March 3 4:26 PM] User:
Oh I like emoji alchemy! Can you add that as another related option under Semantic shuffle.
----------------------------------
### [Monday, March 3 4:26 PM] Codespace Assistant 2-26:
Adding **Emoji Alchemy** as a related option under **Semantic Shuffle** to expand the variety of gameplay concepts associated with this theme. Let me update the document with this addition.
----------------------------------
### [Monday, March 3 4:27 PM] Codespace Assistant 2-26:
note: [Document Editor]: A new game concept, **Emoji Alchemy**, was added to the document. This game is a creative and fast-paced experience where players mix emojis to produce surprising and imaginative outcomes, such as combining "🌊" (ocean) and "🌞" (sun) to yield "tropical beach." The game uses AI to analyze emoji relationships, generate combinations, and score originality and alignment with themes. The description includes the game concept, its use of AI, and a brief discussion on how it would be technically implemented. No other sections were changed or modified.
----------------------------------
### [Monday, March 3 4:27 PM] Codespace Assistant 2-26:
I’ve added **Emoji Alchemy** as a related option under **Semantic Shuffle** in the document. This includes its concept, how it uses AI for analyzing emoji relationships, and a brief technical implementation overview. Let me know how else I can refine or expand the document!
----------------------------------
### [Monday, March 3 4:28 PM] User:
I also like the concept of Rapid remix and how it uses audio/music gen. That is another area to help bolster the amount of options we have. Let's expand on that and add to the page.
----------------------------------
### [Monday, March 3 4:28 PM] Codespace Assistant 2-26:
Great choice! I'll expand on **Rapid Remix**, exploring its mechanics, AI-driven music or art generation, and quick replayable gameplay tailored for mobile or daily challenges. I'll add it to your document with enough detail to demonstrate its feasibility and appeal. Let me take care of that.
----------------------------------
### [Monday, March 3 4:30 PM] Codespace Assistant 2-26:
note: [Document Editor]: A new game concept, **Rapid Remix**, was added to the document. This game focuses on challenging players to quickly remix AI-generated music and visuals to match a target theme, such as altering the mood of a tune or the tone of an image. Detailed explanations were added for how the game leverages AI, including the use of generative audio and image models for real-time transformations, and a scoring system that rewards creativity, precision, and speed. Additionally, technical implementation details were outlined, including the use of tools like generative audio and image models, user-friendly interfaces, and scoring algorithms. No other substantial changes were made to the existing content.
----------------------------------
### [Monday, March 3 4:30 PM] Codespace Assistant 2-26:
I’ve added **Rapid Remix** to the document, detailing its concept of using AI to remix music or visuals on the fly, tied to quick and engaging challenges. The description includes gameplay mechanics, AI-driven elements, and a technical implementation outline. Let me know if you’d like to adjust or refine any part of it!
----------------------------------
```