| Commit message (Collapse) | Author | Files | ||
|---|---|---|---|---|
| 2024-12-10 | allow passing single line range | Martin Bielik | 1 | |
| 2024-12-08 | don't include not selected line, refactor ranges, fixes #112 | Martin Bielik | 1 | |
| 2024-12-07 | improved initial message config | Martin Bielik | 1 | |
| 2024-12-06 | allow override global token config | Martin Bielik | 1 | |
| 2024-12-05 | moving from legacy completions api | Martin Bielik | 1 | |
| 2024-12-03 | docu new options | Martin Bielik | 1 | |
| 2024-12-03 | o1 support - max_completion_tokens | Martin Bielik | 1 | |
| 2024-07-29 | remove useless buffer in keep open mode | Martin Bielik | 1 | |
| 2024-07-25 | private MakeScratchWindow function | Martin Bielik | 1 | |
| 2024-07-24 | switch to last created buffer in keep open mode | Martin Bielik | 1 | |
| 2024-07-23 | allow multiple chats in keep open mode | Martin Bielik | 2 | |
| 2024-06-09 | added abort flag to the plugin functions | Martin Bielik | 1 | |
| 2024-06-09 | handle paste mode in finally block | Martin Bielik | 1 | |
| 2024-05-31 | gpt-4o as default chat model | Martin Bielik | 1 | |
| 2024-05-31 | define required max_tokens for turbo-instruct model | Martin Bielik | 1 | |
| 2024-04-14 | increase token limit | Enno | 1 | |
| 2024-03-24 | refactoring: extracted to helper function, using guards | Martin Bielik | 1 | |
| 2024-03-24 | retab | Martin Bielik | 1 | |
| 2024-03-24 | consistent execution delimiter | Martin Bielik | 1 | |
| 2024-03-14 | automatically unset &paste also after failed command | Konfekt | 1 | |
| 2024-03-11 | Implement smarter AI chat window detection to reuse existing AI chat windows. | Konfekt | 1 | |
| First search for AI chat windows within the same tab and then within other tabs if none are found in the current tab. It now prioritizes the reusing of an existing chat window that matches the '.aichat' filetype before considering opening a new one. If there are no existing AI chat windows, the plugin will open a new chat window as a last resort. diff --git a/autoload/vim_ai.vim b/autoload/vim_ai.vim: - " reuse chat in active window or tab + " TODO: look for first active chat buffer. If .aichat file is used, + " then reuse chat in active window - " allow .aichat files windows to be switched to, preferably on same tab - let buffer_list_tab = tabpagebuflist(tabpagenr()) - let buffer_list_tab = filter(buffer_list_tab, 'getbufvar(v:val, "&filetype") ==# "aichat"') - - let buffer_list = [] - for i in range(tabpagenr('$')) - call extend(buffer_list, tabpagebuflist(i + 1)) - endfor - let buffer_list = filter(buffer_list, 'getbufvar(v:val, "&filetype") ==# "aichat"') - - if len(buffer_list_tab) > 0 - call win_gotoid(win_findbuf(buffer_list_tab[0])[0]) - elseif len(buffer_list) > 0 - call win_gotoid(win_findbuf(buffer_list[0])[0]) - else - " open new chat window - let l:open_conf = l:config['ui']['open_chat_command'] - call s:OpenChatWindow(l:open_conf) - endif + " open new chat window + let l:open_conf = l:config['ui']['open_chat_command'] + call s:OpenChatWindow(l:open_conf) | ||||
| 2024-03-10 | detect chat window in other tabs as well | Konfekt | 1 | |
| diff --git a/autoload/vim_ai.vim b/autoload/vim_ai.vim: - - let l:chat_win_ids = win_findbuf(bufnr(s:scratch_buffer_name)) - if !empty(l:chat_win_ids) - " TODO: look for first active chat buffer. If .aichat file is used, - " then reuse chat in active window - call win_gotoid(l:chat_win_ids[0]) + let l:chat_win_id = bufwinid(s:scratch_buffer_name) + if l:chat_win_id != -1 + " TODO: look for first active chat buffer, in case .aichat file is used + " reuse chat in active window + call win_gotoid(l:chat_win_id) | ||||
| 2024-03-09 | removed unused log | Martin Bielik | 1 | |
| 2024-03-09 | roles example file | Martin Bielik | 2 | |
| 2024-03-09 | roles completion | Martin Bielik | 1 | |
| 2024-03-09 | removed unused variable | Martin Bielik | 1 | |
| 2024-03-09 | remove garbled text | Konfekt | 1 | |
| 2024-03-09 | fix typo | Konfekt | 1 | |
| 2024-03-08 | allow overriding range if called on visual selection | Konfekt | 1 | |
| Check if the start and end line of range equals that of visual selection. If so, take the visual selection; otherwise the supplied range | ||||
| 2024-03-08 | feat: add an option to customize api key file location | jiangyinzuo | 1 | |
| 2024-02-26 | removed debug log | Martin Bielik | 1 | |
| 2024-02-26 | apply suggestions of review at PR #77 | Konfekt | 1 | |
| 2024-02-26 | drop superfluous selection argument and fix instruction argument | Konfekt | 1 | |
| 2024-02-26 | align AIRedo with AI/AIEdit/Chat | Konfekt | 1 | |
| These changes were necessary to fix a bug where commands were not being executed correctly in non-visual modes, and to make the code cleaner and more efficient. By explicitly handling the visual selection state, it ensures that the plugin functions correctly regardless of how the user invokes the AI features. | ||||
| 2024-02-26 | fix selection handling in vim_ai functions | Konfekt | 1 | |
| addresses https://github.com/madox2/vim-ai/issues/76 | ||||
| 2023-12-02 | added explaining comment | Martin Bielik | 1 | |
| 2023-12-02 | fix selection include extra content when the user is in visual mode | cposture | 1 | |
| 2023-10-21 | endpoint_url config | Martin Bielik | 1 | |
| 2023-10-21 | option to disable authorization | Martin Bielik | 1 | |
| 2023-10-21 | base_url extracted to config, docu | Martin Bielik | 1 | |
| 2023-09-26 | use gpt-3.5-turbo-instruct by default, closes #48 | Martin Bielik | 1 | |
| 2023-05-07 | Allow modification of vim_ai_open_chat_presets | BonaBeavis | 1 | |
| 2023-05-02 | configurable paste mode | Martin Bielik | 2 | |
| 2023-05-02 | using value from extended config | Martin Bielik | 1 | |
| 2023-04-22 | added AINewChat command | Martin Bielik | 1 | |
| 2023-04-22 | open_chat_command presets | Martin Bielik | 2 | |
| 2023-04-22 | custom commands documentation | Martin Bielik | 1 | |
| 2023-04-22 | pass config as a parameter | Martin Bielik | 2 | |
| 2023-04-22 | fixed redo in chat | Martin Bielik | 1 | |
| 2023-04-22 | fixed redo in chat | Martin Bielik | 1 | |