- Introduce check for .md extension and use technical writer system prompt.
- Adjust response cleaning: trim for markdown, use CleanCodeResponse for code.
- Remove nolint comment and unnecessary line skipping in removeLastModifiedComments.
- Add PowerShell quick install snippet to release notes body
- Update MIME type detection to include .ps1 files as text/plain
- Remove unnecessary comments from workflow script
- Introduced grokkit-install.ps1 for Windows, mirroring bash installer with auto-detection, checksum verification, and safe installation
- Updated README with one-line and download-first install methods for Bash and PowerShell
- Added Windows-specific notes, improved formatting, tables, and examples in README
- Ensured cross-platform consistency in installation instructions
- Strip leading 'v' from VERSION for flexible invocation
- Add robust checksum download and verification using sha256sum or shasum
- Handle missing checksum tools or entries gracefully with warnings
- Update asset naming to include 'v' prefix consistently
- Improve platform detection formatting and add trap for temp dir cleanup
- Minor echo message updates for better user feedback
- Added debug echoes, changelog entries for v0.3.1
- Changed asset filename, binary handling, commented out checksum and cleanup
- Fixed quoting in case statements and echoes
- Adjust asset filename to include 'v' prefix for version
- Comment out checksum download and verification
- Fix quoting in case statements and echo commands
- Update binary naming and extraction handling
- Comment out temp dir cleanup trap
- Add debug echo statements for download and extraction
- Change default output to .grokkit/analysis.md for project-local storage
- Add directory creation for .grokkit to ensure it exists before writing
- Refine project analysis.md with more accurate tech stack, function refs, and learning path details
Move the project analysis from `analyze.md` to `.grokkit/analysis.md` for better organization under a dedicated directory. Update content with more accurate inferences on tech stack, directory structure, function references, and learning paths based on deeper code review. This improves maintainability and provides a more comprehensive overview for contributors.
Update CHANGELOG.md with added features like analyze command, Go-specific prompts, and language detection; changes to prompts, detection logic, and command handling; fixes for config, imports, and safety checks.
Add a "none" linter configuration for the Rexx language to provide structure,
while noting that no traditional linter is used and it's primarily for grokkit analyze.
- Remove `rootCmd.AddCommand(analyzeCmd)` from `cmd/analyze.go` init func
- Add empty `Linters` array for Rexx in `internal/linter/linter.go` with comment for analyze support
- Change default output filename in analyze command from analyze.md to analysis.md
- Add Rexx language detection with extensions .rx, .rex, .rexlib, .rexx, .cls
Update DetectPrimaryLanguage to normalize "C/C++" and "C++" to "c" for consistent counting.
Revise function comment and internal comments for clarity.
Remove redundant comment on finding most common language.
- Introduce analyze.md with comprehensive breakdown of Grokkit project, including tech stack, structure, APIs, data flow, and learning path.
- Update cmd/analyze.go to include detected language in user prompt for more targeted AI analysis.
Introduced a new documentation page `analyze.md` detailing the `analyze` command, including usage, options, prompt discovery, language support, safety features, best practices, and an example workflow. Updated `index.md` to include a link to the new guide.
- Modify Go prompt to include instruction for inferring project name from directory or go.mod.
- Update analyze command to infer project name from directory base and replace placeholder in prompt content.
- Enhance prompt formatting with bold text and rephrased sections for clarity.
- Enhance discoverSourceFiles to skip additional noise directories like "build" and "dist" while descending into source directories.
- Update safety check to use package-level logger without .Get().
- Refine buildProjectContext with better labeling and consistent git remote handling.
- Minor comment and string adjustments for clarity.
- Fix config.GetModel to use command name and flag
- Switch to package-level logger functions
- Update git.IsRepo to take no arguments
- Simplify linter language detection comments
- Adjust Grok client creation to NewClient().StreamSilent
- Add error handling for confirmation input
- Remove unnecessary imports and refine comments in linter
- Updated Go analysis prompt for clarity, structure, and educational focus.
- Improved buildProjectContext to include shallow key files and cleaner Git remote handling.
- Implemented DetectPrimaryLanguage with counting logic and Go bias; added SupportedLanguages.
- Enhanced LoadAnalysisPrompt with better language handling, fallbacks, and error clarity.
- Add Go-specific analysis prompt in .grokkit/prompts/go.md
- Expand cmd/analyze.go to discover files, detect language, load prompts, build context, generate report via Grok, and handle output with preview/confirmation
- Integrate analyzeCmd into root command
- Introduce internal/linter/language.go for primary language detection
- Add internal/prompts/analyze.go for loading analysis prompts from project or global locations
Introduces a new Cobra command `analyze` that performs deep project analysis,
discovers files, builds context, streams to Grok for report generation, and
handles output with confirmation.
Update the feature description to include educational report details and prompt discovery mechanism.
Add automatic prompt loading from project or global config paths, with error handling for missing prompts.
Revise acceptance criteria, implementation plan, and add proposed CLI usage and flags.
Include default prompt for Go and user-guide updates for custom prompts.
Queues a new Markdown spec in todo/queued for the `grokkit analyze` command, including description, acceptance criteria, implementation plan, and priority. This feature enables deep project analysis and generates educational Markdown reports on tech stack, functions, and more.
Summarize changes including new features like recipe support, safe shell commands, and refactoring improvements; updates to configurations and security; fixes for various bugs and handling.
- Introduce new test suite in internal/recipe/recipe_test.go covering recipe loading, parameter overrides, safety checks, work dir resolution, file discovery, and unified patch creation.
- Remove t.Parallel() from tests in cmd/changelog_test.go, cmd/root_test.go, and cmd/scaffold_test.go that modify global state (e.g., os.Args, HOME, or use os.Chdir()) to avoid race conditions and ensure test isolation.
- Simplified README.md by moving detailed command docs, workflows, and development info to dedicated user-guide/ and developer-guide/ directories.
- Created index.md files for both guides to improve navigation.
- Extracted individual command guides (e.g., chat.md, edit.md) into user-guide/ for focused, maintainable documentation.
- Moved architecture, configuration, and troubleshooting to developer-guide/.
- Updated README links to point to the new docs structure.
- Reorganize commit commands into commit-msg and commit
- Add sections for scaffold, recipe, and testgen
- Update PR description base branch example
- Add new features to quality section: AI unit test generation, file scaffolding, transactional recipes
- Update directory structure with .grokkit/recipes and internal/recipe
- Introduce global safeCommands() map for command whitelisting.
- Implement case-insensitive prefix checking for allowed commands.
- Simplify argument handling by removing redundant int conversions.
- Update error messages and comments for clarity on security policies.
- Remove outdated comments and adjust prompt text for consistency.
Update the command matching logic to require an exact match or the command followed by a space and arguments. Also normalize case and trim whitespace for safe commands to prevent loose prefix matches that could allow unintended commands.
Update the executeReadOnlyShell function to handle numbers in command arguments,
such as 'tree -L 3', by changing Args to []interface{} and converting them to strings
before execution. Add strconv import for formatting.
- Tighten trigger conditions for read-only shell steps to specific phrases
- Add robust JSON extraction with escaped quote handling
- Reorder user confirmation before whitelist check in execution flow
- Relocate FileChange struct and clean up comments
- Update recipe markdown for step title consistency
- Introduce new Step 1 in result-refactor.md for exploring project structure using safe read-only shell commands (e.g., tree, cat).
- Rename subsequent steps accordingly.
- Add handler in runner.go for read-only shell steps triggered by keywords like "explore" or "inspect".
Implement executeReadOnlyShell method to safely run whitelisted read-only commands,
prompting for user approval and integrating AI-suggested commands for filesystem context.
- Replace hardcoded safeCommands map with sync.OnceValue loading from ~/.config/grokkit/safe_shell_commands.yaml
- Provide fallback built-in safe list if config load fails
- Add safe_shell_commands.yaml.example for user reference
- Update safety check to use loaded map and prefix matching
- Renamed safeReadOnlyCommands to safeCommands for clarity.
- Added support for additional safe commands including GNU utilities (find, grep, which),
Git commands (diff, branch), and various test runners (go test, make test/lint, pytest, etc.).
- Updated safety check to allow commands prefixed with any safe command for flexibility.
- Improved error message for unsafe commands.
Update the error message for unsafe shell commands to be more concise and user-friendly, removing redundant "ERROR:" prefix and "try again" instruction.
- Consolidate resolveWorkDir and remove resolvePackagePath for cleaner path handling.
- Eliminate executeShellCommands and related logic to disable shell execution in recipes.
- Simplify error messaging in loader for unsafe commands.
Implement a read-only command whitelist in the recipe loader to reject
potentially dangerous shell commands, ensuring only safe operations like
ls, pwd, cat, etc., are permitted. This enhances security by preventing
execution of unauthorized commands in recipes.
- Rename and expand resolvePackagePath to resolveWorkDir, which now appends project_name if provided
- Update discoverFiles to use workDir and add default search pattern if none specified
- Modify executeShellCommands prompt to include workDir and enforce relative paths only
- Add safety checks to reject shell commands with ".." or absolute paths to prevent directory escapes
- Minor prompt and formatting adjustments for clarity and consistency
- Introduce resolvePackagePath to handle ~ expansion, relative paths, and absolutization at the start.
- Update discoverFiles and executeShellCommands to use the resolved workDir.
- Remove redundant path logic from discoverFiles and shell execution for better maintainability.
