|
1 | 1 | # Changelog |
2 | 2 |
|
| 3 | +### 0.18.0 |
| 4 | + |
| 5 | +#### New Features |
| 6 | +- **Model Picker Badges**: Model picker now shows cost tier indicators and server-controlled badges (e.g. "Free", "New") |
| 7 | +- **Ask Mode Enhancements**: Slash commands (`/`) and external editor (`Ctrl+O`) now work in Ask mode |
| 8 | +- **Single-Click Login**: Streamlined browser-based authentication flow |
| 9 | +- **/context**: `/context` to see context window usage |
| 10 | + |
| 11 | +#### Improvements |
| 12 | +- **Sub-agents Credit Usage**: Add support for subagents credit usage via non interactive mode for enterprise customers and /stats for all users |
| 13 | +- **Faster Tool Execution**: Reduced tool execution delays in large workspaces by caching enumeration state and parallelizing rule file reads |
| 14 | +- **Incremental Session Saving**: Agent progress is now saved after each LLM exchange, preventing loss of work if the process crashes mid-turn |
| 15 | +- **Message Queue Persistence**: Queued messages are now saved to the session file, so they survive CLI restarts |
| 16 | +- **Smarter Input Modes**: Pasting or recalling history entries with a prefix (`/`, `!`, `#`) now automatically enters the corresponding input mode |
| 17 | +- **Slash Command Ordering**: Exact alias matches (e.g. `/q` → `queue`) are now prioritized over fuzzy matches |
| 18 | +- **Stash/Recall Hints**: Added Ctrl+S (stash) and Ctrl+T (recall) to help screens for easier discovery |
| 19 | +- **Task Tool Performance**: Parallelized task tool operations to prevent occasional hanging |
| 20 | +- **Chat History Truncation**: Improved content-aware truncation measurement with a higher default limit, preventing premature history loss in long sessions |
| 21 | +- **Network Resilience**: Improved error messages and circuit breakers for unstable network connections |
| 22 | + |
| 23 | +### 0.17.0 |
| 24 | + |
| 25 | +#### New Features |
| 26 | +- Ask mode improvements: Slash commands and Ctrl+O (external editor) now work in ask mode |
| 27 | +- Ctrl+R history search: Persistent reverse history search across sessions |
| 28 | +- Selective session deletion: Delete individual sessions from the session picker |
| 29 | +- Message queue editing: Up arrow key opens the queue popover, with a hint shown in the message placeholder |
| 30 | +- Custom slash commands in --queue: Queued messages now resolve custom slash commands (e.g., `--queue "/my-command"`) |
| 31 | +- --queue support in non-interactive mode: Queue multiple prompts in `--print` mode for chained workflows |
| 32 | + |
| 33 | +#### Improvements |
| 34 | +- Indexing denylist: Permanently decline indexing for specific workspaces with a "Never index this workspace" option |
| 35 | +- Incremental session saving: Agent progress is now saved after each LLM exchange, preventing work loss on crashes |
| 36 | +- Task management: Task system now auto-recovers if the task list is missing, and task names are shown in update displays |
| 37 | +- Sub-agents now have access to MCP tools from their parent agent |
| 38 | +- Session auto-rename now triggers correctly for messages with tool calls |
| 39 | +- Config wizard: All options now visible without scrolling |
| 40 | +- Session list ordering: Newest sessions appear first |
| 41 | +- User message display: Improved formatting with full row highlight and brighter text |
| 42 | +- Improved summarization with incremental updates and backend-driven token counting |
| 43 | +- Remote history sync: Better conflict resolution for synced sessions |
| 44 | +- Memory improvement during git indexing |
| 45 | +- MCP OAuth: Better handling of non-conformant server responses for dynamic client registration |
| 46 | +- TUI rendering flickering improvements |
| 47 | + |
3 | 48 | ### 0.16.0 |
4 | 49 |
|
5 | 50 | #### New Features |
|
0 commit comments