Prompt flow for VS Code

Enables users to create and edit prompt flow definitions using a directed acyclic graph (DAG) model persisted as flow.dag.yaml files. The extension provides both a visual editor (triggered via Ctrl+K,V or code lens) and YAML text editing with inline code lens actions, allowing developers to define multi-step LLM workflows by composing nodes (prompts, tools, Python functions) and connecting them via data dependencies. The visual editor abstracts YAML complexity while maintaining full fidelity with the underlying DAG structure.

Provides a debugging interface (triggered via F5 keybinding) that executes a prompt flow step-by-step with breakpoint support, allowing developers to inspect intermediate outputs, variable states, and node execution results. The debugger integrates with VS Code's standard debug protocol, displaying execution traces and enabling pause/resume/step-through workflows. This capability surfaces runtime behavior of LLM calls and tool invocations, helping developers identify logic errors, unexpected model outputs, or data transformation issues within their flows.

Collects usage data about extension interactions (flow creation, debugging, testing, connection management) and sends telemetry to Microsoft for product improvement and analytics. The telemetry system tracks feature adoption, error rates, and user workflows to inform development priorities. While telemetry is enabled by default, users can disable it via VS Code settings, providing opt-out capability. This capability enables Microsoft to understand how developers use prompt flows and identify areas for improvement.

Restricts flow execution to local development machines, with explicit non-support for remote execution environments (SSH, containers, WSL, web-based VS Code). Flows execute within the selected local Python interpreter, limiting deployment to development and testing scenarios. This design choice prioritizes simplicity and local debugging experience over production deployment capabilities, positioning the extension as a development tool rather than a production orchestration platform.

Enables running test suites against prompt flows via Shift+F5 keybinding, executing flows against predefined test datasets and comparing outputs against expected results. The testing framework supports batch execution of flows with multiple input variations, collecting metrics (latency, token usage, success/failure rates) and surfacing test results in VS Code's test explorer. This capability allows developers to validate flow behavior across diverse inputs and detect regressions when modifying prompts or node logic.

Provides a connection management system (accessible via sidebar 'Connections' section) that abstracts credentials and API endpoints for external services (e.g., Azure OpenAI, custom APIs). Developers define connections via YAML templates (create/update_{ConnectionType}_connection.yaml) with code lens guidance, and flows reference connections by name rather than embedding credentials. The extension handles credential storage and injection at runtime, supporting multiple connection types through a generic connection framework. This decouples flow definitions from environment-specific secrets and enables reuse across development, staging, and production environments.

Allows developers to add nodes to flows (via Ctrl+Cmd+N keybinding or visual editor) and define data dependencies between them, creating a directed acyclic graph of operations. Nodes represent discrete units of work: LLM prompts, tool invocations, Python functions, or data transformations. The extension manages node inputs/outputs, type checking, and data flow routing, ensuring outputs from upstream nodes correctly feed into downstream node inputs. This capability abstracts the complexity of orchestrating multiple LLM calls and tool invocations into a declarative dependency graph.

Integrates with VS Code's Python extension to detect and manage the active Python interpreter, enabling flows to execute within a specific Python environment with isolated dependencies. The extension provides an 'Install dependencies' action in the sidebar that installs promptflow and promptflow-tools packages into the selected environment. This capability ensures flows run with correct package versions and allows developers to manage environment-specific dependencies (e.g., custom tool packages) without affecting system Python or other projects.

Provides a dedicated sidebar panel (labeled 'Prompt flow') with quick access to common flow operations: creating new flows, installing dependencies, managing connections, and accessing flow documentation. The sidebar organizes operations into subsections (Quick access, Connections, Dependencies) with one-click actions, reducing the need to navigate command palette or context menus. This capability centralizes flow-related operations in a discoverable UI location, improving accessibility for developers new to prompt flows.

Enables right-click context menu actions on directories and files to create new flows directly in the selected location. The 'New flow in this directory' action creates a flow.dag.yaml template in the chosen directory, initializing the flow structure with default nodes and connections. This capability reduces friction for creating new flows by eliminating the need to manually create directories or YAML files, and provides a familiar file-system-based workflow for developers.

Displays inline code lens actions above flow.dag.yaml files and connection configuration files, providing quick access to operations like 'Open visual editor', 'Run debug', 'Run test', and 'Create/update connection'. Code lens actions reduce context switching by allowing developers to trigger operations directly from the YAML editor without opening sidebars or command palettes. This capability integrates flow operations into the natural code editing workflow, improving efficiency for developers who prefer text-based editing.

Provides keyboard shortcuts for common flow operations: F5 for debug execution, Shift+F5 for test execution, Ctrl+Cmd+N for adding nodes, and Ctrl+Cmd+K,V for opening visual editor. These keybindings enable rapid iteration on flows without mouse interaction or menu navigation, supporting keyboard-driven workflows. The keybindings follow VS Code conventions (F5 for debug, Shift+F5 for test) making them discoverable for developers familiar with VS Code's debugging paradigm.