Commit Graph

210 Commits

Author SHA1 Message Date
msvechla
2f806ca342 Resolve AWS credentials using default credentials provider chain for Bedrock (#1752) 2025-05-16 11:13:40 +08:00
aniaan
113913355a feat(sidebar): Add option and keymap to start a new chat directly (#2004) 2025-05-07 15:27:50 +08:00
yetone
60897ee9a6 fix: o1 model (#1992) 2025-05-06 19:32:55 +08:00
yetone
a67f3071e4 chores: update default copilot model (#1988) 2025-05-05 17:14:50 +08:00
yetone
32ca1ed38e fix: set default auto suggestions provider to nil (#1951) 2025-05-01 02:50:01 +08:00
doodleEsc
cee31ebb7f feat: allow excluding filetypes from selector autolaunch. (#1937)
Co-authored-by: doodleEsc <cokie@foxmail.com>
Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
2025-04-30 03:12:45 +08:00
yetone
f10b8383e3 refactor: history messages (#1934) 2025-04-30 03:07:18 +08:00
Ricardo Maraschini
cff8cbf9c5 feat: add config for ollama keep alive (#1858) 2025-04-17 10:47:51 +08:00
yetone
2f2aaee3b4 fix: only use q to close sidebar (#1884) 2025-04-16 23:43:55 +08:00
Shiwei Ge
4f717e0699 feat: add Bedrock Claude 3.7 Sonnet model configuration (#1860)
Co-authored-by: Shiwei Ge <geshiwei@amazon.com>
2025-04-16 14:38:34 +08:00
yetone
756d1f1e24 feat: universal selector (#1877) 2025-04-15 16:40:47 +08:00
zenk
e295fe82f0 feat(windows): add fillchars option for the windows (#1854)
Co-authored-by: zhangkai.zju <zhangkai.zju@bytedance.com>
2025-04-11 12:28:38 +08:00
yetone
51bad68087 fix: window switch (#1856) 2025-04-11 11:42:55 +08:00
yetone
04336913b3 Revert "fix max_tokens for reasoning models (#1819)" (#1839)
* Revert "fix max_tokens for reasoning models (#1819)"

This reverts commit 1e2e233ff5.

* Revert "fix: revert max_completion_tokens to max_tokens (#1741)"

This reverts commit cd13eeb7d9.

* fix: nvim_version
2025-04-09 16:58:54 +08:00
Jorge Valdez
1fc57ab1ae feat: add support for searxng (#1814)
* Add support for searxng

* body.results not body.web

* type annotation

* update docs
2025-04-09 14:35:42 +08:00
yetone
d5210f4afb fix: ask floating window border (#1837) 2025-04-09 14:30:57 +08:00
Mike Wu
c0d3afe0a4 feat: allow overriding img_paste options (#1827) 2025-04-08 10:46:20 +08:00
yetone
d76a158b61 feat: custom slash commands (#1826) 2025-04-07 22:19:59 +08:00
doodleEsc
1c36cfc812 fix: enhance web search functionality with proxy support (#1823)
* fix: enhance web search functionality with proxy support

- Remove unnecessary blank line in README.md
- Add missing closing details tag in both README.md and README_zh.md
- Add proxy support to the web search engine configuration in config.lua
- Ensure the web search function uses the proxy setting when available in init.lua
- Fix a potential nil access in the response body format check in config.lua

Signed-off-by: 范立洲 <fanlizhou@yunqilaohe.com>

* [pre-commit.ci lite] apply automatic fixes

---------

Signed-off-by: 范立洲 <fanlizhou@yunqilaohe.com>
Co-authored-by: 范立洲 <fanlizhou@yunqilaohe.com>
Co-authored-by: pre-commit-ci-lite[bot] <117423508+pre-commit-ci-lite[bot]@users.noreply.github.com>
2025-04-07 15:05:22 +08:00
yetone
89a86f0fc1 fix: search engine did not return correctly (#1801) 2025-04-02 20:32:58 +08:00
yetone
0828d32346 fix: AvanteEdit command (#1799) 2025-04-02 16:27:10 +08:00
yetone
46073c0efd feat: aihubmix (#1780)
* feat: aihubmix

* feat: add chinese readme
2025-03-31 18:58:41 +08:00
adasauce
484e473a5a fix: update gemini max_tokens and use 2.0 model (#1767)
docs ref for max output tokens:
https://ai.google.dev/gemini-api/docs/models#gemini-2.0-flash

Token limits[*]

Input token limit
1,048,576

Output token limit
8,192
2025-03-30 12:53:41 +08:00
kronion
edf02a7d1f fix: correct max_tokens for Claude 3.5 Haiku (#1761)
Co-authored-by: Collin Stedman <2781682+kronion@users.noreply.github.com>
2025-03-29 18:44:35 +08:00
kyrisu
78d6c389b4 feat: add command to include all buffer files in file selector (#1748) 2025-03-28 10:24:49 +08:00
yetone
cd13eeb7d9 fix: revert max_completion_tokens to max_tokens (#1741) 2025-03-27 16:53:55 +08:00
guanghechen
0b4a493d60 improve: support to customize the keymaps for cancelling the editing (#1730)
* improve: support to customize the keymaps for cancelling the editing

* docs: update README
2025-03-26 21:58:03 +08:00
yetone
39787969c7 fix: memory (#1718) 2025-03-26 00:45:54 +08:00
yetone
a2aec079c9 feat: extract str_replace tool (#1710) 2025-03-25 18:43:57 +08:00
yetone
8c4244b940 fix: decrease history max tokens (#1709) 2025-03-25 16:07:45 +08:00
Omar Crespo
bae5275705 feat: add stop sequence (#1652) 2025-03-21 19:34:33 +08:00
yetone
1c8cac1958 feat: history manager (#1644) 2025-03-19 17:28:05 +08:00
yetone
191d7b8783 feat: claude text editor tool (#1631) 2025-03-19 00:09:49 +08:00
kernitus
10ce065d9e feat: update openai/azure params (#1604)
* feat(openai): use max_completion_tokens & reasoning_effort params

* feat(openai): use developer prompt for reasoning models

* docs: update openai config in readme

* refactor: follow lua style quotes

* fix(azure): rename max_tokens to max_completion_tokens

* refactor(azure): remove duplicate field

* refactor: update types

* refactor(azure): update type
2025-03-18 19:40:20 +08:00
Ellis Rahhal
51eb8fc2d9 feat: added optional docker args for rag service (#1589) 2025-03-18 12:06:37 +08:00
Florian Engelhardt
3b86549485 Add extra headers for OpenAI (#1615) 2025-03-17 17:51:08 +08:00
yetone
63605a55a3 fix: increase history max_tokens (#1609) 2025-03-17 04:38:08 +08:00
yetone
79bf76ed72 fix: increase max_tokens (#1607) 2025-03-17 03:29:44 +08:00
yetone
6e77da83c1 fix: better sidebar (#1603)
* fix: better sidebar

* feat: better msg history

* fix: tests
2025-03-17 01:40:05 +08:00
yetone
d307467771 feat: hide in model selector (#1574) 2025-03-13 01:39:59 +08:00
yetone
8b37cfc306 feat: system_prompt can be a function (#1571) 2025-03-12 19:57:17 +08:00
yetone
9e3e8d06a2 feat: get custom tools from a function (#1567) 2025-03-12 17:57:09 +08:00
miguelosana
3eaaaa8f5f feat: add vertex claude provider (#1549)
* feat: Add vertex claude provider

* remove debug logging

---------

Co-authored-by: Miguelo Sana <miguelo@incubeta.com>
2025-03-10 22:43:10 +08:00
yetone
558a7bbd38 fix: close_from_input keybinding types (#1546) 2025-03-10 15:54:01 +08:00
Jae-Won Chung
9fa2d9e51d fix: remove sidebar.close_from_input default keybinding (#1536)
* Remove <c-d> from default insert mode keybinding

* Check `close_from_input ~= nil` before keymap

* Default `close_from_input` to `nil`

* Update README.md keybinding defaults

* Try to pass type check
2025-03-10 15:31:13 +08:00
yetone
750ee80971 feat: add ollama as supported provider (#1543)
* feat: add ollama as supported provider

*This implementation is only working with `stream = true`*
- Uses the actual ollama api and allows for passing additional options
- Properly passes the system prompt to api

Use ollama as provider in opts like this:
opts = {
        debug = true,
        provider = "ollama",
        ollama = {
                api_key_name = "",
                endpoint = "http://127.0.0.1:11434",
                model = "qwen2.5-coder:latest",
                options = {
                        num_ctx = 32768,
                        temperature = 0,
                },
                stream = true,
        },

* fix: ollama types

---------

Co-authored-by: jtabke <25010496+jtabke@users.noreply.github.com>
2025-03-10 02:23:56 +08:00
yetone
868c136574 refactor: remove use_xml_format (#1535) 2025-03-09 14:58:30 +08:00
brook hong
4766e76a31 feat: add key mappings to close sidebar in input_container (#1494)
* add key mappings to close sidebar in input_container
* add autocmd to enter normal mode on leaving input_container
* add autocmd to enter insert mode on entering input_container
2025-03-08 12:55:13 +08:00
yetone
8344d3ee3d feat: support customizing system_prompt in the configuration (#1527) 2025-03-08 12:51:49 +08:00
yetone
d75094b815 fix: bedrock (#1524)
* fix: bedrock

* fix: bad variable name

* fix: missing metatable
2025-03-08 02:17:28 +08:00