Skip to content

Commit 9d4233b

Browse files
committed
add changelog
1 parent e862bf4 commit 9d4233b

File tree

1 file changed

+111
-0
lines changed

1 file changed

+111
-0
lines changed

CHANGELOG.md

Lines changed: 111 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,111 @@
1+
# Changelog
2+
3+
### 0.5.5
4+
5+
- Ask Mode: a streamlined prompt-first interaction mode with improved transcript rendering.
6+
- New session commands: `auggie session list` and `auggie session resume` to manage and continue sessions.
7+
- MCP quality-of-life: simpler `mcp add` syntax, automatic migration of legacy settings, and a `/status` check.
8+
- Add Ask Mode for CLI/TUI, with formatting and input history improvements.
9+
- Add `auggie session list` and `auggie session resume` commands.
10+
- Add `--permission` flag to configure tool permissions at runtime.
11+
- Support compressed syntax for `mcp add` and auto-migrate legacy MCP settings.json format.
12+
- Add `/status` command to check MCP and rules status.
13+
- Add `--max-turns` to cap agent iterations in print mode.
14+
- Add basic JSON output mode.
15+
- Improve keyboard handling: Ctrl+C to clear input, Ctrl+D forward delete; fix Delete key acting as Backspace.
16+
- Improve non-interactive error messages when auth is missing.
17+
- Fix crash when denying indexing by properly initializing status messaging.
18+
- Fix markdown list indentation in TUI output.
19+
- Fixed issue where rules were dropped when combined content was too long.
20+
- MCP settings now use a record-based schema; legacy formats auto-migrate on run.
21+
22+
### 0.5.4
23+
24+
- Manage Model Context Protocol (MCP) servers with `auggie mcp add|list|remove`
25+
- Configure MCP servers in your settings file (`~/.augment/settings.json`) or via a config file passed with `--mcp-config`
26+
- Skip waiting for indexing to complete before codebase retrieval executes in TUI mode
27+
- If API requests are retried, the CLI shows a clear message so you know what's happening
28+
- Interrupting an operation now cleans up any partial output to keep the screen tidy
29+
- Custom slash command help text now shows the selected model; logging and parsing are consistent in both interactive and non‑interactive modes
30+
- Session tracking is more reliable between the CLI and the API
31+
- Authentication works correctly when you provide both an API token and an API URL
32+
- On Windows, home‑directory detection across different drives has been fixed to avoid incorrect indexing
33+
34+
### 0.5.3
35+
36+
- Non-interactive slash command syntax: Run custom commands directly from the shell with `auggie /<command> ...` (e.g., `auggie "/joke robot" -p`)
37+
- Indexing is now enabled by default in print mode, with a safety guard that disables indexing when running from your home directory to avoid accidentally uploading your entire home folder
38+
39+
### 0.5.2
40+
41+
- Custom commands can now specify which AI model to use in their frontmatter configuration
42+
- Slash commands can be run directly from the command line (e.g., `auggie /help`)
43+
- Improved paste functionality on Windows and support for Chinese character input
44+
- Enhanced feedback submission with proper handling of bracketed paste
45+
- Quiet mode (`--quiet`) now automatically defaults to text output mode
46+
- Empty agent responses are no longer displayed in the CLI interface
47+
- CLI continues gracefully when settings fail to load instead of crashing
48+
- Invalid MCP configuration no longer causes crashes
49+
- Added workspace size limits to prevent indexing excessively large directories
50+
- Fixed typo: "enchance" → "enhance" in prompt enhancer
51+
52+
### 0.5.1
53+
54+
- Added ability to edit existing tool permission rules without recreating them (press 'e' to edit)
55+
- Improved tool permissions UI with better visual hierarchy and clearer permission types display
56+
- Simplified permissions management
57+
- Added long help text that can be toggled with '?' in Normal mode
58+
- Fixed Ctrl+C and double escape shortcuts to work properly in vim mode
59+
- Automatically enter INSERT mode when typing `/vim` command
60+
- Cleaned up vim mode help text for better clarity
61+
- Added slash commands to the history manager for easier command recall
62+
- Fixed command exit behavior - commands like `model list`, `tokens print`, and `session delete` now properly exit after completion
63+
- Prevented indexing when running CLI from home directory to avoid performance issues
64+
- Fixed git worktree detection
65+
- Limited @ file cache size to prevent performance degradation when opened in large directories
66+
- Display default model in brackets when no model is explicitly selected
67+
- Updated onboarding messages and tips for better user experience
68+
69+
### 0.5.0
70+
71+
- Added `/editor` command to compose prompts in your preferred external editor (VS Code, vim, nano, etc.)
72+
- Added `Ctrl+O` keyboard shortcut for quick access to external editor
73+
- Added current AI model name display in the status line footer
74+
- Added `j/k` keyboard navigation support for all menus (Task List, Model Picker, GitHub workflow)
75+
- Improved popover heights for better visibility on smaller screens
76+
- Fixed footer wrapping issues on narrow terminal widths
77+
- Added `/verbose` command to toggle between compact and detailed transcript views
78+
- Fixed verbose command toggle to properly apply changes in the current session
79+
- Improved help text with dynamic command listing and better keyboard shortcut documentation
80+
- Enhanced onboarding experience with clearer feature descriptions
81+
- Implemented comprehensive theme-based system across markdown, tool formatters, and status indicators
82+
- Reduced flicker in iTerm when opening/closing popovers
83+
- Added smart git update events with file tracking for better performance
84+
- Improved error handling in str-replace-editor tool to detect when old and new strings are the same
85+
- Enhanced settings management with structured return types and better error handling
86+
- Fixed double @ appearing in file picker mode
87+
- Fixed indexing confirmation to wait before initializing runtime
88+
- Fixed tool permission type display for "ask-user" permissions
89+
- Corrected typos and improved help text clarity
90+
- Fixed clipboard functionality with proper feedback and error handling
91+
- Enhanced scrollable list components for better handling of long item lists
92+
93+
### 0.4.0
94+
95+
- Added support for custom slash commands (`/<command>`) in interactive mode and `--command` flag in non-interactive mode
96+
- Support for nested custom commands using colon separator (e.g., `nested:command`)
97+
- Custom commands can be defined in `.augment/commands` or `~/.augment/commands` directories
98+
- Added tab completion for slash commands in interactive mode
99+
- Custom commands from Claude Code are now automatically detected and imported
100+
- Added detailed help section for `--command` flag with `auggie --command --help`
101+
- Added shorthand flags for common options: `-i` (input), `-if` (input-file), `-p` (prompt), `-q` (query), `-lm` (list-models), `-m` (model), `-cm` (command)
102+
- Added user settings support via `~/.augment/settings.json` for persistent model preferences
103+
- Support for CLAUDE.md and AGENTS.md configuration files in addition to .augment/guidelines.md
104+
- Settings are validated with schema and gracefully handle malformed JSON
105+
- Added prompt enhancement via Ctrl+P in interactive mode to improve prompts using AI
106+
- Improved navigation in input box with Option+Left/Right for word navigation
107+
- Enhanced multi-line prompt navigation with up/down arrows
108+
- Added repository and branch information badges to agent cards
109+
- Improved select menu system with better modularity and pagination support
110+
- Fixed regression in input history and cursor movement in interactive mode
111+
- Fixed extraneous border display on successful side effects with green border

0 commit comments

Comments
 (0)