This is page 88 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
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-office/data/word/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!
----------------------------------
```
--------------------------------------------------------------------------------
/mcp-servers/mcp-server-open-deep-research/mcp_server/libs/open_deep_research/mdconvert.py:
--------------------------------------------------------------------------------
```python
# This is copied from Magentic-one's great repo: https://github.com/microsoft/autogen/blob/v0.4.4/python/packages/autogen-magentic-one/src/autogen_magentic_one/markdown_browser/mdconvert.py
# Thanks to Microsoft researchers for open-sourcing this!
# type: ignore
import base64
import copy
import html
import json
import mimetypes
import os
import re
import shutil
import subprocess
import sys
import tempfile
import traceback
import zipfile
from typing import Any, Dict, List, Optional, Union
from urllib.parse import parse_qs, quote, unquote, urlparse, urlunparse
import mammoth
import markdownify
import pandas as pd
import pdfminer
import pdfminer.high_level
import pptx
# File-format detection
import puremagic
import pydub
import requests
import speech_recognition as sr
from bs4 import BeautifulSoup
from youtube_transcript_api import YouTubeTranscriptApi
from youtube_transcript_api.formatters import SRTFormatter
# FIXME: Pass the extract_dir into the MarkdownConverter instead of importing the settings
from ... import settings
class _CustomMarkdownify(markdownify.MarkdownConverter):
"""
A custom version of markdownify's MarkdownConverter. Changes include:
- Altering the default heading style to use '#', '##', etc.
- Removing javascript hyperlinks.
- Truncating images with large data:uri sources.
- Ensuring URIs are properly escaped, and do not conflict with Markdown syntax
"""
def __init__(self, **options: Any):
options["heading_style"] = options.get("heading_style", markdownify.ATX)
# Explicitly cast options to the expected type if necessary
super().__init__(**options)
def convert_hn(self, n: int, el: Any, text: str, convert_as_inline: bool) -> str:
"""Same as usual, but be sure to start with a new line"""
if not convert_as_inline:
if not re.search(r"^\n", text):
return "\n" + super().convert_hn(n, el, text, convert_as_inline) # type: ignore
return super().convert_hn(n, el, text, convert_as_inline) # type: ignore
def convert_a(self, el: Any, text: str, convert_as_inline: bool):
"""Same as usual converter, but removes Javascript links and escapes URIs."""
prefix, suffix, text = markdownify.chomp(text) # type: ignore
if not text:
return ""
href = el.get("href")
title = el.get("title")
# Escape URIs and skip non-http or file schemes
if href:
try:
parsed_url = urlparse(href) # type: ignore
if parsed_url.scheme and parsed_url.scheme.lower() not in ["http", "https", "file"]: # type: ignore
return "%s%s%s" % (prefix, text, suffix)
href = urlunparse(parsed_url._replace(path=quote(unquote(parsed_url.path)))) # type: ignore
except ValueError: # It's not clear if this ever gets thrown
return "%s%s%s" % (prefix, text, suffix)
# For the replacement see #29: text nodes underscores are escaped
if (
self.options["autolinks"]
and text.replace(r"\_", "_") == href
and not title
and not self.options["default_title"]
):
# Shortcut syntax
return "<%s>" % href
if self.options["default_title"] and not title:
title = href
title_part = ' "%s"' % title.replace('"', r"\"") if title else ""
return "%s[%s](%s%s)%s" % (prefix, text, href, title_part, suffix) if href else text
def convert_img(self, el: Any, text: str, convert_as_inline: bool) -> str:
"""Same as usual converter, but removes data URIs"""
alt = el.attrs.get("alt", None) or ""
src = el.attrs.get("src", None) or ""
title = el.attrs.get("title", None) or ""
title_part = ' "%s"' % title.replace('"', r"\"") if title else ""
if convert_as_inline and el.parent.name not in self.options["keep_inline_images_in"]:
return alt
# Remove dataURIs
if src.startswith("data:"):
src = src.split(",")[0] + "..."
return "" % (alt, src, title_part)
def convert_soup(self, soup: Any) -> str:
return super().convert_soup(soup) # type: ignore
class DocumentConverterResult:
"""The result of converting a document to text."""
def __init__(self, title: Union[str, None] = None, text_content: str = ""):
self.title: Union[str, None] = title
self.text_content: str = text_content
class DocumentConverter:
"""Abstract superclass of all DocumentConverters."""
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
raise NotImplementedError()
class PlainTextConverter(DocumentConverter):
"""Anything with content type text/plain"""
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
# Guess the content type from any file extension that might be around
content_type, _ = mimetypes.guess_type("__placeholder" + kwargs.get("file_extension", ""))
# Only accept text files
if content_type is None:
return None
# elif "text/" not in content_type.lower():
# return None
text_content = ""
with open(local_path, "rt", encoding="utf-8") as fh:
text_content = fh.read()
return DocumentConverterResult(
title=None,
text_content=text_content,
)
class HtmlConverter(DocumentConverter):
"""Anything with content type text/html"""
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
# Bail if not html
extension = kwargs.get("file_extension", "")
if extension.lower() not in [".html", ".htm"]:
return None
result = None
with open(local_path, "rt", encoding="utf-8") as fh:
result = self._convert(fh.read())
return result
def _convert(self, html_content: str) -> Union[None, DocumentConverterResult]:
"""Helper function that converts and HTML string."""
# Parse the string
soup = BeautifulSoup(html_content, "html.parser")
# Remove javascript and style blocks
for script in soup(["script", "style"]):
script.extract()
# Print only the main content
body_elm = soup.find("body")
webpage_text = ""
if body_elm:
webpage_text = _CustomMarkdownify().convert_soup(body_elm)
else:
webpage_text = _CustomMarkdownify().convert_soup(soup)
assert isinstance(webpage_text, str)
return DocumentConverterResult(
title=None if soup.title is None else soup.title.string, text_content=webpage_text
)
class WikipediaConverter(DocumentConverter):
"""Handle Wikipedia pages separately, focusing only on the main document content."""
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
# Bail if not Wikipedia
extension = kwargs.get("file_extension", "")
if extension.lower() not in [".html", ".htm"]:
return None
url = kwargs.get("url", "")
if not re.search(r"^https?:\/\/[a-zA-Z]{2,3}\.wikipedia.org\/", url):
return None
# Parse the file
soup = None
with open(local_path, "rt", encoding="utf-8") as fh:
soup = BeautifulSoup(fh.read(), "html.parser")
# Remove javascript and style blocks
for script in soup(["script", "style"]):
script.extract()
# Print only the main content
body_elm = soup.find("div", {"id": "mw-content-text"})
title_elm = soup.find("span", {"class": "mw-page-title-main"})
webpage_text = ""
main_title = None if soup.title is None else soup.title.string
if body_elm:
# What's the title
if title_elm and len(title_elm) > 0:
main_title = title_elm.string # type: ignore
assert isinstance(main_title, str)
# Convert the page
webpage_text = f"# {main_title}\n\n" + _CustomMarkdownify().convert_soup(body_elm)
else:
webpage_text = _CustomMarkdownify().convert_soup(soup)
return DocumentConverterResult(
title=main_title,
text_content=webpage_text,
)
class YouTubeConverter(DocumentConverter):
"""Handle YouTube specially, focusing on the video title, description, and transcript."""
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
# Bail if not YouTube
extension = kwargs.get("file_extension", "")
if extension.lower() not in [".html", ".htm"]:
return None
url = kwargs.get("url", "")
if not url.startswith("https://www.youtube.com/watch?"):
return None
# Parse the file
soup = None
with open(local_path, "rt", encoding="utf-8") as fh:
soup = BeautifulSoup(fh.read(), "html.parser")
# Read the meta tags
assert soup.title is not None and soup.title.string is not None
metadata: Dict[str, str] = {"title": soup.title.string}
for meta in soup(["meta"]):
for a in meta.attrs:
if a in ["itemprop", "property", "name"]:
metadata[meta[a]] = meta.get("content", "")
break
# We can also try to read the full description. This is more prone to breaking, since it reaches into the page implementation
try:
for script in soup(["script"]):
content = script.text
if "ytInitialData" in content:
lines = re.split(r"\r?\n", content)
obj_start = lines[0].find("{")
obj_end = lines[0].rfind("}")
if obj_start >= 0 and obj_end >= 0:
data = json.loads(lines[0][obj_start : obj_end + 1])
attrdesc = self._findKey(data, "attributedDescriptionBodyText") # type: ignore
if attrdesc:
metadata["description"] = str(attrdesc["content"])
break
except Exception:
pass
# Start preparing the page
webpage_text = "# YouTube\n"
title = self._get(metadata, ["title", "og:title", "name"]) # type: ignore
assert isinstance(title, str)
if title:
webpage_text += f"\n## {title}\n"
stats = ""
views = self._get(metadata, ["interactionCount"]) # type: ignore
if views:
stats += f"- **Views:** {views}\n"
keywords = self._get(metadata, ["keywords"]) # type: ignore
if keywords:
stats += f"- **Keywords:** {keywords}\n"
runtime = self._get(metadata, ["duration"]) # type: ignore
if runtime:
stats += f"- **Runtime:** {runtime}\n"
if len(stats) > 0:
webpage_text += f"\n### Video Metadata\n{stats}\n"
description = self._get(metadata, ["description", "og:description"]) # type: ignore
if description:
webpage_text += f"\n### Description\n{description}\n"
transcript_text = ""
parsed_url = urlparse(url) # type: ignore
params = parse_qs(parsed_url.query) # type: ignore
if "v" in params:
assert isinstance(params["v"][0], str)
video_id = str(params["v"][0])
try:
# Must be a single transcript.
transcript = YouTubeTranscriptApi.get_transcript(video_id) # type: ignore
# transcript_text = " ".join([part["text"] for part in transcript]) # type: ignore
# Alternative formatting:
transcript_text = SRTFormatter().format_transcript(transcript)
except Exception:
pass
if transcript_text:
webpage_text += f"\n### Transcript\n{transcript_text}\n"
title = title if title else soup.title.string
assert isinstance(title, str)
return DocumentConverterResult(
title=title,
text_content=webpage_text,
)
def _get(self, metadata: Dict[str, str], keys: List[str], default: Union[str, None] = None) -> Union[str, None]:
for k in keys:
if k in metadata:
return metadata[k]
return default
def _findKey(self, json: Any, key: str) -> Union[str, None]: # TODO: Fix json type
if isinstance(json, list):
for elm in json:
ret = self._findKey(elm, key)
if ret is not None:
return ret
elif isinstance(json, dict):
for k in json:
if k == key:
return json[k]
else:
ret = self._findKey(json[k], key)
if ret is not None:
return ret
return None
class PdfConverter(DocumentConverter):
"""
Converts PDFs to Markdown. Most style information is ignored, so the results are essentially plain-text.
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a PDF
extension = kwargs.get("file_extension", "")
if extension.lower() != ".pdf":
return None
return DocumentConverterResult(
title=None,
text_content=pdfminer.high_level.extract_text(local_path),
)
class DocxConverter(HtmlConverter):
"""
Converts DOCX files to Markdown. Style information (e.g.m headings) and tables are preserved where possible.
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a DOCX
extension = kwargs.get("file_extension", "")
if extension.lower() != ".docx":
return None
result = None
with open(local_path, "rb") as docx_file:
result = mammoth.convert_to_html(docx_file)
html_content = result.value
result = self._convert(html_content)
return result
class XlsxConverter(HtmlConverter):
"""
Converts XLSX files to Markdown, with each sheet presented as a separate Markdown table.
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a XLSX
extension = kwargs.get("file_extension", "")
if extension.lower() not in [".xlsx", ".xls"]:
return None
sheets = pd.read_excel(local_path, sheet_name=None)
md_content = ""
for s in sheets:
md_content += f"## {s}\n"
html_content = sheets[s].to_html(index=False)
md_content += self._convert(html_content).text_content.strip() + "\n\n"
return DocumentConverterResult(
title=None,
text_content=md_content.strip(),
)
class PptxConverter(HtmlConverter):
"""
Converts PPTX files to Markdown. Supports heading, tables and images with alt text.
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a PPTX
extension = kwargs.get("file_extension", "")
if extension.lower() != ".pptx":
return None
md_content = ""
presentation = pptx.Presentation(local_path)
slide_num = 0
for slide in presentation.slides:
slide_num += 1
md_content += f"\n\n<!-- Slide number: {slide_num} -->\n"
title = slide.shapes.title
for shape in slide.shapes:
# Pictures
if self._is_picture(shape):
# https://github.com/scanny/python-pptx/pull/512#issuecomment-1713100069
alt_text = ""
try:
alt_text = shape._element._nvXxPr.cNvPr.attrib.get("descr", "")
except Exception:
pass
# A placeholder name
filename = re.sub(r"\W", "", shape.name) + ".jpg"
md_content += "\n![" + (alt_text if alt_text else shape.name) + "](" + filename + ")\n"
# Tables
if self._is_table(shape):
html_table = "<html><body><table>"
first_row = True
for row in shape.table.rows:
html_table += "<tr>"
for cell in row.cells:
if first_row:
html_table += "<th>" + html.escape(cell.text) + "</th>"
else:
html_table += "<td>" + html.escape(cell.text) + "</td>"
html_table += "</tr>"
first_row = False
html_table += "</table></body></html>"
md_content += "\n" + self._convert(html_table).text_content.strip() + "\n"
# Text areas
elif shape.has_text_frame:
if shape == title:
md_content += "# " + shape.text.lstrip() + "\n"
else:
md_content += shape.text + "\n"
md_content = md_content.strip()
if slide.has_notes_slide:
md_content += "\n\n### Notes:\n"
notes_frame = slide.notes_slide.notes_text_frame
if notes_frame is not None:
md_content += notes_frame.text
md_content = md_content.strip()
return DocumentConverterResult(
title=None,
text_content=md_content.strip(),
)
def _is_picture(self, shape):
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.PICTURE:
return True
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.PLACEHOLDER:
if hasattr(shape, "image"):
return True
return False
def _is_table(self, shape):
if shape.shape_type == pptx.enum.shapes.MSO_SHAPE_TYPE.TABLE:
return True
return False
class MediaConverter(DocumentConverter):
"""
Abstract class for multi-modal media (e.g., images and audio)
"""
def _get_metadata(self, local_path):
exiftool = shutil.which("exiftool")
if not exiftool:
return None
else:
try:
result = subprocess.run([exiftool, "-json", local_path], capture_output=True, text=True).stdout
return json.loads(result)[0]
except Exception:
return None
class WavConverter(MediaConverter):
"""
Converts WAV files to markdown via extraction of metadata (if `exiftool` is installed), and speech transcription (if `speech_recognition` is installed).
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a XLSX
extension = kwargs.get("file_extension", "")
if extension.lower() != ".wav":
return None
md_content = ""
# Add metadata
metadata = self._get_metadata(local_path)
if metadata:
for f in [
"Title",
"Artist",
"Author",
"Band",
"Album",
"Genre",
"Track",
"DateTimeOriginal",
"CreateDate",
"Duration",
]:
if f in metadata:
md_content += f"{f}: {metadata[f]}\n"
# Transcribe
try:
transcript = self._transcribe_audio(local_path)
md_content += "\n\n### Audio Transcript:\n" + ("[No speech detected]" if transcript == "" else transcript)
except Exception:
md_content += "\n\n### Audio Transcript:\nError. Could not transcribe this audio."
return DocumentConverterResult(
title=None,
text_content=md_content.strip(),
)
def _transcribe_audio(self, local_path) -> str:
recognizer = sr.Recognizer()
with sr.AudioFile(local_path) as source:
audio = recognizer.record(source)
return recognizer.recognize_google(audio).strip()
class Mp3Converter(WavConverter):
"""
Converts MP3 files to markdown via extraction of metadata (if `exiftool` is installed), and speech transcription (if `speech_recognition` AND `pydub` are installed).
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a MP3
extension = kwargs.get("file_extension", "")
if extension.lower() != ".mp3":
return None
md_content = ""
# Add metadata
metadata = self._get_metadata(local_path)
if metadata:
for f in [
"Title",
"Artist",
"Author",
"Band",
"Album",
"Genre",
"Track",
"DateTimeOriginal",
"CreateDate",
"Duration",
]:
if f in metadata:
md_content += f"{f}: {metadata[f]}\n"
# Transcribe
handle, temp_path = tempfile.mkstemp(suffix=".wav")
os.close(handle)
try:
sound = pydub.AudioSegment.from_mp3(local_path)
sound.export(temp_path, format="wav")
_args = dict()
_args.update(kwargs)
_args["file_extension"] = ".wav"
try:
transcript = super()._transcribe_audio(temp_path).strip()
md_content += "\n\n### Audio Transcript:\n" + (
"[No speech detected]" if transcript == "" else transcript
)
except Exception:
md_content += "\n\n### Audio Transcript:\nError. Could not transcribe this audio."
finally:
os.unlink(temp_path)
# Return the result
return DocumentConverterResult(
title=None,
text_content=md_content.strip(),
)
class ZipConverter(DocumentConverter):
"""
Extracts ZIP files to a permanent local directory and returns a listing of extracted files.
"""
def __init__(self, extract_dir: str = "downloads"):
"""
Initialize with path to extraction directory.
Args:
extract_dir: The directory where files will be extracted. Defaults to "downloads"
"""
self.extract_dir = extract_dir
# Create the extraction directory if it doesn't exist
os.makedirs(self.extract_dir, exist_ok=True)
def convert(self, local_path: str, **kwargs: Any) -> Union[None, DocumentConverterResult]:
# Bail if not a ZIP file
extension = kwargs.get("file_extension", "")
if extension.lower() != ".zip":
return None
# Verify it's actually a ZIP file
if not zipfile.is_zipfile(local_path):
return None
# Extract all files and build list
extracted_files = []
with zipfile.ZipFile(local_path, "r") as zip_ref:
# Extract all files
zip_ref.extractall(self.extract_dir)
# Get list of all files
for file_path in zip_ref.namelist():
# Skip directories
if not file_path.endswith("/"):
extracted_files.append(self.extract_dir + "/" + file_path)
# Sort files for consistent output
extracted_files.sort()
# Build the markdown content
md_content = "Downloaded the following files:\n"
for file in extracted_files:
md_content += f"* {file}\n"
return DocumentConverterResult(title="Extracted Files", text_content=md_content.strip())
class ImageConverter(MediaConverter):
"""
Converts images to markdown via extraction of metadata (if `exiftool` is installed), OCR (if `easyocr` is installed), and description via a multimodal LLM (if an mlm_client is configured).
"""
def convert(self, local_path, **kwargs) -> Union[None, DocumentConverterResult]:
# Bail if not a XLSX
extension = kwargs.get("file_extension", "")
if extension.lower() not in [".jpg", ".jpeg", ".png"]:
return None
md_content = ""
# Add metadata
metadata = self._get_metadata(local_path)
if metadata:
for f in [
"ImageSize",
"Title",
"Caption",
"Description",
"Keywords",
"Artist",
"Author",
"DateTimeOriginal",
"CreateDate",
"GPSPosition",
]:
if f in metadata:
md_content += f"{f}: {metadata[f]}\n"
# Try describing the image with GPTV
mlm_client = kwargs.get("mlm_client")
mlm_model = kwargs.get("mlm_model")
if mlm_client is not None and mlm_model is not None:
md_content += (
"\n# Description:\n"
+ self._get_mlm_description(
local_path, extension, mlm_client, mlm_model, prompt=kwargs.get("mlm_prompt")
).strip()
+ "\n"
)
return DocumentConverterResult(
title=None,
text_content=md_content,
)
def _get_mlm_description(self, local_path, extension, client, model, prompt=None):
if prompt is None or prompt.strip() == "":
prompt = "Write a detailed caption for this image."
sys.stderr.write(f"MLM Prompt:\n{prompt}\n")
data_uri = ""
with open(local_path, "rb") as image_file:
content_type, encoding = mimetypes.guess_type("_dummy" + extension)
if content_type is None:
content_type = "image/jpeg"
image_base64 = base64.b64encode(image_file.read()).decode("utf-8")
data_uri = f"data:{content_type};base64,{image_base64}"
messages = [
{
"role": "user",
"content": [
{"type": "text", "text": prompt},
{
"type": "image_url",
"image_url": {
"url": data_uri,
},
},
],
}
]
response = client.chat.completions.create(model=model, messages=messages)
return response.choices[0].message.content
class FileConversionException(Exception):
pass
class UnsupportedFormatException(Exception):
pass
class MarkdownConverter:
"""(In preview) An extremely simple text-based document reader, suitable for LLM use.
This reader will convert common file-types or webpages to Markdown."""
def __init__(
self,
requests_session: Optional[requests.Session] = None,
mlm_client: Optional[Any] = None,
mlm_model: Optional[Any] = None,
):
if requests_session is None:
self._requests_session = requests.Session()
else:
self._requests_session = requests_session
self._mlm_client = mlm_client
self._mlm_model = mlm_model
self._page_converters: List[DocumentConverter] = []
# Register converters for successful browsing operations
# Later registrations are tried first / take higher priority than earlier registrations
# To this end, the most specific converters should appear below the most generic converters
self.register_page_converter(PlainTextConverter())
self.register_page_converter(HtmlConverter())
self.register_page_converter(WikipediaConverter())
self.register_page_converter(YouTubeConverter())
self.register_page_converter(DocxConverter())
self.register_page_converter(XlsxConverter())
self.register_page_converter(PptxConverter())
self.register_page_converter(WavConverter())
self.register_page_converter(Mp3Converter())
self.register_page_converter(ImageConverter())
# self.register_page_converter(ZipConverter())
# FIXME: Pass the extract_dir into the MarkdownConverter instead of importing the settings
self.register_page_converter(ZipConverter(extract_dir=f"{settings.data_folder}/extract_dir"))
self.register_page_converter(PdfConverter())
def convert(
self, source: Union[str, requests.Response], **kwargs: Any
) -> DocumentConverterResult: # TODO: deal with kwargs
"""
Args:
- source: can be a string representing a path or url, or a requests.response object
- extension: specifies the file extension to use when interpreting the file. If None, infer from source (path, uri, content-type, etc.)
"""
# Local path or url
if isinstance(source, str):
if source.startswith("http://") or source.startswith("https://") or source.startswith("file://"):
return self.convert_url(source, **kwargs)
else:
return self.convert_local(source, **kwargs)
# Request response
elif isinstance(source, requests.Response):
return self.convert_response(source, **kwargs)
def convert_local(self, path: str, **kwargs: Any) -> DocumentConverterResult: # TODO: deal with kwargs
# Prepare a list of extensions to try (in order of priority)
ext = kwargs.get("file_extension")
extensions = [ext] if ext is not None else []
# Get extension alternatives from the path and puremagic
base, ext = os.path.splitext(path)
self._append_ext(extensions, ext)
self._append_ext(extensions, self._guess_ext_magic(path))
# Convert
return self._convert(path, extensions, **kwargs)
# TODO what should stream's type be?
def convert_stream(self, stream: Any, **kwargs: Any) -> DocumentConverterResult: # TODO: deal with kwargs
# Prepare a list of extensions to try (in order of priority)
ext = kwargs.get("file_extension")
extensions = [ext] if ext is not None else []
# Save the file locally to a temporary file. It will be deleted before this method exits
handle, temp_path = tempfile.mkstemp()
fh = os.fdopen(handle, "wb")
result = None
try:
# Write to the temporary file
content = stream.read()
if isinstance(content, str):
fh.write(content.encode("utf-8"))
else:
fh.write(content)
fh.close()
# Use puremagic to check for more extension options
self._append_ext(extensions, self._guess_ext_magic(temp_path))
# Convert
result = self._convert(temp_path, extensions, **kwargs)
# Clean up
finally:
try:
fh.close()
except Exception:
pass
os.unlink(temp_path)
return result
def convert_url(self, url: str, **kwargs: Any) -> DocumentConverterResult: # TODO: fix kwargs type
# Send a HTTP request to the URL
user_agent = "Mozilla/5.0 (Windows NT 10.0; Win64; x64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/119.0.0.0 Safari/537.36 Edg/119.0.0.0"
response = self._requests_session.get(url, stream=True, headers={"User-Agent": user_agent})
response.raise_for_status()
return self.convert_response(response, **kwargs)
def convert_response(
self, response: requests.Response, **kwargs: Any
) -> DocumentConverterResult: # TODO fix kwargs type
# Prepare a list of extensions to try (in order of priority)
ext = kwargs.get("file_extension")
extensions = [ext] if ext is not None else []
# Guess from the mimetype
content_type = response.headers.get("content-type", "").split(";")[0]
self._append_ext(extensions, mimetypes.guess_extension(content_type))
# Read the content disposition if there is one
content_disposition = response.headers.get("content-disposition", "")
m = re.search(r"filename=([^;]+)", content_disposition)
if m:
base, ext = os.path.splitext(m.group(1).strip("\"'"))
self._append_ext(extensions, ext)
# Read from the extension from the path
base, ext = os.path.splitext(urlparse(response.url).path)
self._append_ext(extensions, ext)
# Save the file locally to a temporary file. It will be deleted before this method exits
handle, temp_path = tempfile.mkstemp()
fh = os.fdopen(handle, "wb")
result = None
try:
# Download the file
for chunk in response.iter_content(chunk_size=512):
fh.write(chunk)
fh.close()
# Use puremagic to check for more extension options
self._append_ext(extensions, self._guess_ext_magic(temp_path))
# Convert
result = self._convert(temp_path, extensions, url=response.url)
except Exception as e:
print(f"Error in converting: {e}")
# Clean up
finally:
try:
fh.close()
except Exception:
pass
os.unlink(temp_path)
return result
def _convert(self, local_path: str, extensions: List[Union[str, None]], **kwargs) -> DocumentConverterResult:
error_trace = ""
for ext in extensions + [None]: # Try last with no extension
for converter in self._page_converters:
_kwargs = copy.deepcopy(kwargs)
# Overwrite file_extension appropriately
if ext is None:
if "file_extension" in _kwargs:
del _kwargs["file_extension"]
else:
_kwargs.update({"file_extension": ext})
# Copy any additional global options
if "mlm_client" not in _kwargs and self._mlm_client is not None:
_kwargs["mlm_client"] = self._mlm_client
if "mlm_model" not in _kwargs and self._mlm_model is not None:
_kwargs["mlm_model"] = self._mlm_model
# If we hit an error log it and keep trying
try:
res = converter.convert(local_path, **_kwargs)
except Exception:
error_trace = ("\n\n" + traceback.format_exc()).strip()
if res is not None:
# Normalize the content
res.text_content = "\n".join([line.rstrip() for line in re.split(r"\r?\n", res.text_content)])
res.text_content = re.sub(r"\n{3,}", "\n\n", res.text_content)
# Todo
return res
# If we got this far without success, report any exceptions
if len(error_trace) > 0:
raise FileConversionException(
f"Could not convert '{local_path}' to Markdown. File type was recognized as {extensions}. While converting the file, the following error was encountered:\n\n{error_trace}"
)
# Nothing can handle it!
raise UnsupportedFormatException(
f"Could not convert '{local_path}' to Markdown. The formats {extensions} are not supported."
)
def _append_ext(self, extensions, ext):
"""Append a unique non-None, non-empty extension to a list of extensions."""
if ext is None:
return
ext = ext.strip()
if ext == "":
return
# if ext not in extensions:
if True:
extensions.append(ext)
def _guess_ext_magic(self, path):
"""Use puremagic (a Python implementation of libmagic) to guess a file's extension based on the first few bytes."""
# Use puremagic to guess
try:
guesses = puremagic.magic_file(path)
if len(guesses) > 0:
ext = guesses[0].extension.strip()
if len(ext) > 0:
return ext
except FileNotFoundError:
pass
except IsADirectoryError:
pass
except PermissionError:
pass
return None
def register_page_converter(self, converter: DocumentConverter) -> None:
"""Register a page text converter."""
self._page_converters.insert(0, converter)
```