Snapshots for AI

Generates markdown-formatted snapshots of user-selected code files through a VS Code UI dialog, applying configurable glob-pattern filtering to exclude directories like node_modules and .git. The extension reads file contents from the workspace, applies syntax highlighting via markdown code fence language tags, and structures output as a single markdown document suitable for pasting into external AI assistants. File selection is user-controlled via checkbox UI with select/deselect-all functionality.

Optionally includes a full project directory tree visualization in the markdown snapshot when the `default_include_entire_project_structure` configuration flag is enabled. The extension traverses the workspace directory hierarchy, respects exclusion patterns (node_modules, .git, etc.), and formats the tree as markdown text (likely using indentation or tree-drawing characters). This provides AI assistants with a high-level overview of project organization without including file contents.

Applies glob-pattern-based filtering to exclude files and directories from snapshots via a `.snapshots/config.json` configuration file with `excluded_patterns` and `included_patterns` arrays. The extension evaluates file paths against these patterns during snapshot generation, allowing developers to persistently exclude common non-essential directories (node_modules, .git, build artifacts) without manual selection each time. Inclusion patterns can override exclusion rules for selective re-inclusion of files.

Allows developers to define a `default_prompt` string in `.snapshots/config.json` that is automatically prepended to every generated snapshot as markdown text. This prompt can provide instructions, context, or questions for the AI assistant that will receive the snapshot. The prompt is included before the code content, enabling developers to frame the snapshot with specific requests or background information without manual editing.

Formats exported code files as markdown code blocks with language-specific syntax highlighting tags (e.g., python, javascript). The extension infers the language from file extensions and applies the appropriate markdown language identifier, enabling AI assistants and markdown renderers to apply syntax highlighting when displaying the snapshot. This improves readability and helps AI models understand code structure through visual formatting.

Provides a camera icon button in the VS Code editor title bar that triggers snapshot generation with a single click. Clicking the icon opens a file selection dialog where users can check/uncheck individual files and use select/deselect-all buttons to control which files are included. The UI is modal and blocking, requiring the user to complete file selection before the snapshot is generated. This integration makes snapshot creation a native VS Code workflow without requiring command-line invocation or menu navigation.

Automatically discovers and lists all text-based files in the VS Code workspace, excluding binary files and respecting the configured exclusion patterns. The extension scans the workspace directory structure, filters out non-text files (images, executables, compiled artifacts), and presents the remaining files in the selection dialog. This enables developers to see all available code files without manually navigating the file system, while automatically hiding irrelevant binary content.

Provides a configuration flag `default_include_all_files` that, when enabled, automatically includes all discovered files in the snapshot without requiring user file selection. This bypasses the modal file selection dialog and generates the snapshot with all non-excluded files in a single operation. This mode is useful for generating comprehensive project snapshots without manual interaction, though it may produce very large markdown documents.

Generates the snapshot as a markdown document and exports it to the system clipboard, enabling developers to immediately paste the content into external AI assistants (ChatGPT, Claude, etc.) without saving to disk or using file operations. The markdown is formatted with code blocks, optional project structure, and prepended prompts, all ready for consumption by AI chat interfaces. This streamlines the workflow of preparing code context and sharing it with external AI tools.