Commit graph

837 commits

Author SHA1 Message Date
James Barker
b85960ba2a
updated to fix no break condition on loop and to use the same number of retries and delay as the glama provider (for consistency)
Signed-off-by: James Barker <james@jcbdevelopment.co.uk>
2025-02-10 14:58:44 +00:00
sam hoang
41fcf85c48 refactor(api): improve OpenAI handler inheritance
- Add OpenAiHandlerOptions interface for configuration
- Extract processUsageMetrics to base class for reuse
- Update RequestyHandler to extend OpenAiHandler
- Add proper type safety for metrics handling
- Clean up code duplication across handlers
2025-02-10 20:14:23 +07:00
sam hoang
91fe764cb8 feat: add Requesty API provider support
- Add RequestyHandler implementation for API integration
- Add RequestyModelPicker component for model selection
- Update shared types and messages for Requesty support
- Update API options to include Requesty provider
2025-02-10 20:13:43 +07:00
James Barker
9c480aaac2
add retries to openrouter generation endpoint to prevent failures on slow usage stat updates server side
Signed-off-by: James Barker <james@jcbdevelopment.co.uk>
2025-02-10 09:13:55 +00:00
Matt Rubens
2ccab1444b Merge remote-tracking branch 'origin/main' into temperature_control 2025-02-09 22:53:44 -05:00
Roo Code
2ddf54de5d Support the Ark provider when used through OpenAI compatible 2025-02-08 23:53:19 -05:00
Vignesh Subbiah
70ed217149
Merge branch 'main' into pm/unbound-fetch-models 2025-02-08 17:46:35 +05:30
Joe Manley
71d344d0a8 Fix tests 2025-02-07 23:17:02 -08:00
Joe Manley
88fb6ec15a Remove magic numbers 2025-02-07 23:09:06 -08:00
Joe Manley
adedc1c2c6 Remove magic numbers 2025-02-07 23:08:26 -08:00
Joe Manley
ce858aa34e
Update src/api/providers/ollama.ts
Suggestion from Matt

Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-02-07 21:22:18 -08:00
Roo Code
bc9773ff9a Configure per-configuration temperature 2025-02-08 00:21:13 -05:00
Pugazhendhi
64a579e965 Fixes default model in test file 2025-02-07 19:31:36 +05:30
Roo Code
4b3ea07033 Prevent provider client instantiations from throwing 2025-02-07 03:06:01 -08:00
Pugazhendhi
01be0389ee Fixed indentation 2025-02-07 14:06:57 +05:30
Pugazhendhi
e0417e99f8 Fixed indentation 2025-02-07 14:05:56 +05:30
Pugazhendhi
5955c01ce8 Removed AutoApproveMenu.test.tsx 2025-02-07 14:05:08 +05:30
pugazhendhi-m
26baaf89a3
Merge branch 'main' into WEB-1756 2025-02-07 13:02:46 +05:30
Matt Rubens
8f410b7bbf
Merge pull request #812 from RooVetGit/cte/catch-openai-handler-exception
Don't throw when `openAiBaseUrl` is not a valid URL
2025-02-06 07:42:38 -05:00
cte
e0336b5ad8 Don't throw when openAiBaseUrl is not a valid URL 2025-02-06 01:25:08 -08:00
Pugazhendhi
18f15559e3 Fixes test file 2025-02-06 13:03:03 +05:30
Pugazhendhi
32f91b6291 Merged with main branch 2025-02-06 12:44:22 +05:30
Sam
f2c96b89c0 fix(r1): ensure r1 works with ollama 2025-02-06 14:21:29 +11:00
Matt Rubens
49c21b6c69 Add new gemini models 2025-02-05 12:04:36 -05:00
Pugazhendhi
ea3d384e48 Fetches all models from gateway during init 2025-02-03 12:18:15 +05:30
Matt Rubens
27976b791c Merge remote-tracking branch 'origin/main' into fix-o3-formatting 2025-02-02 00:53:15 -05:00
Nissa Seru
df932935cf Refactor openai-native, prepend string to developer instructions so that o1/o3 will use md 2025-02-01 22:53:54 -05:00
Matt Rubens
d047c8beae Add o3-mini-high and o3-mini-low 2025-02-01 00:52:41 -05:00
Matt Rubens
0cd1642612 PR feedback 2025-01-31 23:19:50 -05:00
Matt Rubens
0050daf746 Make o3-mini work in glama 2025-01-31 22:54:35 -05:00
Matt Rubens
7d28ff516c Streaming version of o3-mini 2025-01-31 17:51:03 -05:00
Matt Rubens
af9231d22d Make o3-mini work 2025-01-31 16:35:32 -05:00
Anton Shpigunov
7329e945b4 Add expectation to match actual API response in tests 2025-01-31 23:19:17 +02:00
Anton Shpigunov
58fdb6f9ef support o3-mini 2025-01-31 23:09:05 +02:00
Piotr Rogowski
161a6a5d9e Relax deepseek-r1 detection so it also includes distilled models 2025-01-30 23:43:15 +01:00
Piotr Rogowski
60cb550db7 Fix crash when delta in openai api handling could be empty in some cases.
Fixes #641
2025-01-29 19:43:10 +01:00
Vignesh Subbiah
d6433591b2 Add typing for usageData and adds some unit tests 2025-01-29 22:53:43 +05:30
Vignesh Subbiah
6ccb061d33 Refactors the cached token code for all models 2025-01-29 22:25:01 +05:30
kinandan
26369ca48b Fixing anthropic model caching in roo-code 2025-01-29 21:44:47 +05:30
Piotr Rogowski
1534a9c047 Add support for perplexity/sonar-reasoning 2025-01-29 09:54:19 +01:00
Matt Rubens
76278ed99e
Merge pull request #616 from websentry-ai/vs/support-unbound
Supports unbound API provider
2025-01-29 00:10:21 -05:00
Piotr Rogowski
9710fd1110 handle other deepseek-r1 variants on openrouter 2025-01-28 20:53:07 +01:00
pugazhendhi-m
ea30563cca
Merge branch 'main' into vs/support-unbound 2025-01-28 21:58:23 +05:30
Vignesh Subbiah
5329c712de Yields the usage tokens 2025-01-28 21:11:16 +05:30
Vignesh Subbiah
4008a1a53e Modifying the usage of unbound.ts in compliance with all providers 2025-01-28 19:43:52 +05:30
Matt Rubens
18c7f57afb Add test 2025-01-28 00:15:14 -05:00
Piotr Rogowski
cb23be6346 Extend deepseek-r1 support 2025-01-27 21:27:24 +01:00
Pugazhendhi
31ec687768 Adds provider names to dropdown 2025-01-27 19:48:43 +05:30
Pugazhendhi
aed51a2bc5 Updates error reading 2025-01-27 19:48:31 +05:30
Pugazhendhi
336f76baa9 Changes production url 2025-01-27 19:48:17 +05:30