Kedro

Enables Go-to-Definition and Find-Reference navigation within Kedro projects by parsing pipeline.py files and resolving references to configuration files (catalog.yml, parameters.yml) using static AST analysis. Implements bidirectional linking: from pipeline definitions to YAML configs and vice versa, without executing code or requiring runtime introspection. Uses VSCode's built-in language server protocol (LSP) to register custom definition and reference providers scoped to Kedro project structure.

Provides context-aware autocomplete suggestions when typing dataset or parameter names in pipeline.py files by matching against the Kedro data catalog and parameters schema. Triggered by typing a double-quote character within a pipeline definition, the extension queries the project's catalog.yml and parameters.yml to suggest valid identifiers. Uses VSCode's CompletionItemProvider API to register custom completion handlers that validate suggestions against Kedro's schema, preventing typos and invalid references.

Displays contextual metadata when hovering over pipeline elements (dataset names, parameter keys, node definitions) by extracting information from Kedro configuration files and pipeline definitions. Implements VSCode's HoverProvider API to parse YAML catalog entries and parameter definitions, then renders formatted tooltips showing dataset type, location, description, and parameter values. Performs static metadata extraction without executing code or querying runtime state.

Validates catalog.yml and parameters.yml files against Kedro's schema in real-time as the developer edits, providing inline error markers and diagnostic messages for invalid configurations. Implements VSCode's DiagnosticsCollection API to register a custom validator that parses YAML files and checks them against Kedro's schema definition, reporting missing required fields, invalid data types, and malformed entries. Validation runs on file save and during editing, with errors displayed in the Problems panel and inline in the editor.

Renders an interactive flowchart visualization of the Kedro pipeline DAG in a VSCode sidebar panel using Kedro-Viz, displaying nodes, datasets, and dependencies as a directed acyclic graph. Implements hyperlink navigation from flowchart nodes to their corresponding Python function definitions and from data nodes to their catalog entries. The visualization updates when pipeline definitions change, with an optional auto-reload feature that refreshes the graph without manual server restart. Uses Kedro-Viz as an embedded visualization engine, rendering the DAG in a webview panel within VSCode.

Provides a VSCode Command Palette command (`kedro: Run Kedro Viz`) that launches the Kedro-Viz visualization server and renders the pipeline flowchart in the sidebar panel. Implements VSCode's Command API to register custom commands that invoke Kedro CLI operations (e.g., `kedro viz`) through the selected Python interpreter. The command integrates with VSCode's task system to run Kedro commands in the background, displaying output in the integrated terminal and handling errors gracefully.

Integrates with VSCode's Python extension to allow selection of the Python interpreter used for Kedro operations (pipeline execution, server initialization, code analysis). Provides a command (`> Python: select interpreter`) that delegates to the Python extension's interpreter picker, allowing developers to switch between virtual environments, conda environments, or system Python installations. The selected interpreter is used for all Kedro CLI operations and code analysis within the extension.

Provides a command to select and configure the active Kedro project when multiple projects exist in the workspace or when the extension needs to be pointed to a non-root project directory. Implements VSCode's QuickPick API to present available Kedro projects and allows configuration of the project path. The selected project becomes the context for all subsequent code navigation, visualization, and command execution. Configuration mechanism is undocumented but likely stored in VSCode workspace settings.

Manages the lifecycle of the Kedro language server (`vscode-kedro` server) that powers code analysis, navigation, and validation features. Provides a command (`kedro: restart server`) to manually restart the language server when it becomes unresponsive or when project configuration changes require reinitialization. The language server is implemented as a separate process that communicates with VSCode via the Language Server Protocol (LSP), handling all static analysis and schema validation operations.

Provides a command (`kedro: Select Pipeline View`) to filter the Kedro-Viz visualization to display only specific pipelines when a project contains multiple pipelines. Implements VSCode's QuickPick API to present available pipelines and allows selection of which pipeline(s) to visualize. The visualization updates to show only the selected pipeline's nodes and dependencies, enabling focused exploration of large multi-pipeline projects. Filtering is applied to the Kedro-Viz rendering without modifying the underlying project configuration.