Commit Graph

172 Commits

Author SHA1 Message Date
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
yetone
8cca147b94 fix: the editing issue on claude (#1828) 2025-04-08 11:26:49 +08:00
PSeitz
1e2e233ff5 fix max_tokens for reasoning models (#1819) 2025-04-07 13:55:40 +08:00
yetone
cd13eeb7d9 fix: revert max_completion_tokens to max_tokens (#1741) 2025-03-27 16:53:55 +08:00
yetone
b41556ee21 feat: extract text editor tools (#1726) 2025-03-26 17:59:59 +08:00
yetone
a2aec079c9 feat: extract str_replace tool (#1710) 2025-03-25 18:43:57 +08:00
yetone
25e9b1c111 fix: copilot's openai tool description cannot use long text (#1700) 2025-03-24 19:54:06 +08:00
yetone
49ae3c84fd feat: add view_range parameter and remove read_file llm tool (#1690) 2025-03-24 15:07:14 +08:00
yetone
4749e4ea1a fix: filter out create_file tool in claude provider (#1677) 2025-03-22 22:24:29 +08:00
kyrisu
20fea1e717 refactor: rename is_o_series_model to is_reasoning_model (#1632) 2025-03-19 01:45:28 +08:00
kernitus
7d137d32cb fix: do not allow max_tokens & max_completion_tokens at the same time (#1633)
* fix: do not allow max_tokens & max_completion_tokens at the same time

* chore: fix formatting
2025-03-19 01:44:41 +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
Florian Engelhardt
3b86549485 Add extra headers for OpenAI (#1615) 2025-03-17 17:51:08 +08:00
brook hong
e204ca1cf3 feat: support tools in bedrock (#1598) 2025-03-17 13:42:18 +08:00
yetone
3504e64407 fix: empty message content (#1611) 2025-03-17 05:15:57 +08:00
yetone
eb5a2f6cca fix: missing tool use (#1610) 2025-03-17 05:00:03 +08:00
yetone
dfdab1d41f fix: openai tool histories (#1606) 2025-03-17 03:06:26 +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
e332d74c06 fix: anthropic rate limit (#1583) 2025-03-14 14:13:47 +08:00
yetone
f9f92dc9d4 Revert "fix: Always handle the extra response outside of stream, such as the exceptions from bedrock (#1526)" (#1569)
This reverts commit f9ab6934d2.
2025-03-12 19:10:05 +08:00
miguelosana
fee1aacdfc feat: Add claude tools to vertex claude provider (#1559)
* feat: Add claude tools to vertex claude provider

* fix: export transform_tool from claude.lua

* Include type for transfor_tool

---------

Co-authored-by: Miguelo Sana <miguelo@incubeta.com>
2025-03-12 18:43:44 +08:00
brook hong
f9ab6934d2 fix: Always handle the extra response outside of stream, such as the exceptions from bedrock (#1526) 2025-03-12 16:29:32 +08:00
kernitus
9552a960ef fix(azure): attempt to call is_o_series_model (#1560) 2025-03-12 02:53:59 +08:00
yetone
7c3460628b fix: cannot serialise userdata (#1551) 2025-03-11 00:55:05 +08:00
yetone
aa2c2b0054 fix: stricter static typing (#1550) 2025-03-11 00:41:21 +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
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
adasauce
02fb470140 feat: support cmd: loading api keys for google search APIs (#1532)
refactor environment loading logic into Utils and use it for existing
provider loading, and web search where appropriate.
2025-03-09 15:01:49 +08:00
yetone
868c136574 refactor: remove use_xml_format (#1535) 2025-03-09 14:58:30 +08:00
yetone
d75094b815 fix: bedrock (#1524)
* fix: bedrock

* fix: bad variable name

* fix: missing metatable
2025-03-08 02:17:28 +08:00
yetone
4d983532a1 fix: more readable value name (#1521) 2025-03-07 20:27:11 +08:00
Umut Önder
dbe31a866a Fix attempt to call field 'is_o_series_model' in Copilot provider (#1514) 2025-03-07 11:14:36 +08:00
yetone
11305eaacd fix: bedrock (#1516) 2025-03-07 11:12:59 +08:00
yetone
25dee44de9 fix: bedrock (#1511) 2025-03-07 00:30:30 +08:00
yetone
8620ea3e12 refactor: summarize memory (#1508) 2025-03-07 00:12:57 +08:00
yetone
5aa55689ff fix: bedrock claude do not support prompt caching (#1507) 2025-03-06 18:31:56 +08:00
yetone
662b6a547b fix: cache prompt count (#1499) 2025-03-06 00:08:59 +08:00
yetone
93c2e1fd83 feat: cache tool use (#1496) 2025-03-05 19:43:18 +08:00
yetone
cc078a5337 feat: support redacted thinking (#1492) 2025-03-05 18:53:24 +08:00
brook hong
e1d2d825e2 fix: handle bedrock exceptions (#1483) 2025-03-04 23:47:28 +08:00
brook hong
6bd966e8e2 fix: pass context to provider for stream data parsing (#1475)
* fix: pass context to provider for stream data parsing

* fix: luatype

---------

Co-authored-by: yetone <yetoneful@gmail.com>
2025-03-04 00:20:27 +08:00
yetone
0d592f440c Revert "refactor: message content (#1424)" (#1442)
This reverts commit ae8497faf1.
2025-03-01 13:25:51 +08:00
yetone
ae8497faf1 refactor: message content (#1424) 2025-02-28 14:43:39 +08:00
yetone
ebadba7420 fix: claude extended thinking (#1419) 2025-02-27 15:21:00 +08:00
yetone
5abe579019 fix: retry when rate limited (#1417) 2025-02-27 12:52:58 +08:00
Matthew Brookhart
e69e7eceeb feat: support Microsoft Entra ID authentication (#1274)
Co-authored-by: Matthew Brookhart <Matthew Brookhart>
2025-02-27 12:00:36 +08:00
Xiaochao Dong
81067b31aa fix(copilot): fail to decode the empty token file (#1414) 2025-02-27 11:44:24 +08:00
yetone
e7ffb76499 fix: reuse parse_messages and remove parse_response_data and have a good function name for check env exists (#1386) 2025-02-25 13:52:13 +08:00
Peter Cardenas
afa674c6fd chore: prefer not to use function assignment (#1381) 2025-02-25 12:08:03 +08:00