Matt Rubens
fe3e9325a5
Include inference-profile in Bedrock arnRegex ( #2156 )
2025-03-31 13:52:57 -04:00
Chris Estreich
3322e08cb7
Relax provider profiles schema and log parse error to PostHog ( #2139 )
...
* Relax provider profiles schema and log parse error to PostHog
* Create wise-moose-shop.md
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-03-30 23:07:34 -07:00
Duong M. CUONG
af6753608f
Remove hard-coded o3-mini model when streaming is enabled, allowing custom o3-mini-<reasoning> model ( #2134 )
...
Remove hard-coded o3-mini model when streaming is enabled
2025-03-30 23:12:18 -04:00
Taiki Maekawa
2985172c61
feat: add bedrock application inference profile ( #1938 )
2025-03-24 10:17:47 -04:00
teddyOOXX
cc2420ea1a
fix qwq model in openai provider ( #1940 )
...
* feat: Add the openAiR1FormatEnabled field to enable this switch in OpenAI compatible mode to support the current QWQ and future additional classes of R1 models.
* feat: Add the openAiR1FormatEnabled field to enable this switch in OpenAI compatible mode to support the current QWQ and future additional classes of R1 models.
* fix: add miss i18n
* fix: add miss i18n
* fix: remove the redundant call
---------
Co-authored-by: xiong <yueminxiong.xym@alibaba-inc.com>
2025-03-24 10:14:44 -04:00
Matt Rubens
e810a886d2
Welcome page OAuth ( #1913 )
...
* Add Requesty OAuth flow
* New 1-click onboarding flow
* Requesty: Use correct default model info
* When called from the onboard flow, created the default profile
Glama OAuth handler changed for consistency.
* Add router images
* Shuffle the routers
* Translate
* Appease knip
---------
Co-authored-by: Daniel Trugman <dtrugman@gmail.com>
2025-03-23 10:08:16 -04:00
pugazhendhi-m
003388a5c4
Fix maxTokens to 8192 only for compatible Anthropic models ( #1862 )
...
Fix maxTokens to 8096 only for compatible Anthropic models
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
2025-03-23 02:23:29 -04:00
Jason Owens
87b9b72b32
Corrected bug in openrouter.ts and pre-commit and pre-push husky scripts ( #1853 )
...
- Corrected error causing free models listed under openrouter to show pricing information
- Updated pre-push and pre-commit scripts to work in Windows environments when pushing to branch (windows requires npm/npx to include the ".cmd" extension to recognize and compile.
2025-03-23 02:12:53 -04:00
Matt Rubens
2597347e91
Use openrouter stream_options include_usage ( #1905 )
2025-03-23 01:52:43 -04:00
Matt Rubens
95ba760daf
Non-thinking sonnet has 8192 max tokens ( #1860 )
2025-03-21 00:24:57 -04:00
Yukky
b033082523
Reflect Cross-region inference option in ap-xx region ( #1842 )
...
* Fix: Enable cross-region inference for 'ap-xx' region in AwsBedrockHandler.completePrompt
* Fix: Enable cross-region inference for 'ap-xx' region in AwsBedrockHandler.createMessage
* Create itchy-waves-move.md
---------
Co-authored-by: Matt Rubens <mrubens@users.noreply.github.com>
2025-03-20 16:03:51 -04:00
pugazhendhi-m
e4c398d888
Discards temperature setting on o3-mini for Unbound ( #1836 )
...
* Discards temperature setting on o3-mini for Unbound
* Adds changeset
---------
Co-authored-by: Pugazhendhi <pugazhendhi@unboundsecurity.ai>
2025-03-20 09:11:22 -04:00
Wojciech Kordalski
499b8e4665
Fake AI provider ( #1769 )
...
* Fake AI
* Do not show Fake AI in Roo-Code settings
* Rename providers/fake-provider.ts to providers/fake-ai.ts
2025-03-19 19:07:59 -07:00
Chris Estreich
eb74f02094
Choose specific provider when using OpenRouter ( #1753 )
...
* Choose specific provider when using OpenRouter
* Add translations
2025-03-17 15:40:27 -07:00
cte
f108dfaeb8
Evals
2025-03-17 10:09:19 -07:00
Matt Rubens
4ada518e58
Merge branch 'main' into jbbrown/bedrock_cost_intelligent_prompt_routing
2025-03-13 17:17:44 -04:00
Smartsheet-JB-Brown
6c74e9ba7b
PR review cleanup
2025-03-13 13:04:16 -07:00
Smartsheet-JB-Brown
8d30b6f44a
Update src/api/providers/bedrock.ts
...
agree, sorry old Javascript habits
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-03-13 09:56:07 -07:00
Smartsheet-JB-Brown
f7675244bd
Update src/api/providers/bedrock.ts
...
yes, unneeded remnant
Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
2025-03-13 08:09:21 -07:00
Matt Rubens
774248be1e
Fix more hard-coded openrouter urls
2025-03-12 14:08:17 -04:00
Matt Rubens
93611ea6b5
Merge remote-tracking branch 'origin/main' into support-custom-baseUrl-for-google-ai-studio-gemini
2025-03-12 11:55:14 -04:00
Matt Rubens
c8b3095d93
Merge pull request #1566 from lightrabbit/feature/openai-compatible-deepseek-reasoning-support
...
feat: openai-compatible deepseek/qwq reasoning support
2025-03-12 11:39:49 -04:00
Matt Rubens
9b5ee27320
Merge pull request #1587 from dleen/cache
...
feat: Add prompt caching to OpenAI-compatible custom models
2025-03-12 11:35:42 -04:00
David Leen
10c1e7df2f
Add cache control key to messages in OpenAI compatible provider
2025-03-11 22:43:33 -07:00
Smartsheet-JB-Brown
d8df9a5e2c
Cost display updating for Bedrock custom ARNs that are prompt routers
2025-03-11 21:58:07 -07:00
cte
4b6def5f31
ContextProxy fix - constructor should not be async
2025-03-11 14:24:21 -07:00
Matt Rubens
76f91819c1
Use baseURL in OpenRouter generation check
2025-03-11 09:41:57 -04:00
dongqing
9d0b824b90
fix test error for wrong arguments after additional base url added
2025-03-11 17:37:07 +08:00
dongqing
a3a5592654
add config for gemini custom base url
2025-03-11 16:46:40 +08:00
dqroid
8b0956666c
Merge branch 'main' into support-custom-baseUrl-for-google-ai-studio-gemini
2025-03-11 16:15:52 +08:00
lightrabbit
7114cef03e
feat: openai-compatible deepseek/qwq reasoning support
2025-03-11 14:13:17 +08:00
Matt Rubens
f306461276
Fix usage tracking for SiliconFlow etc
2025-03-10 22:59:08 -04:00
Matt Rubens
77186e8ee0
Cleanup
2025-03-10 22:15:52 -04:00
Smartsheet-JB-Brown
171037a938
Add enhanced error handling and logging for AWS Bedrock custom ARNs
2025-03-10 14:25:52 -07:00
Matt Rubens
6644202b55
Merge pull request #1451 from dtrugman/feat/add-openai-style-cost-calculation
...
Add openai style cost calculation
2025-03-10 10:11:30 -04:00
dongqing
85b54b33ba
support custom base url for gemini in google AI studio
2025-03-10 19:06:58 +08:00
yt3trees
9246cf8f6d
Add o3-mini support to openai compatible
2025-03-08 20:23:53 +09:00
Matt Rubens
2a65db61cf
Merge pull request #1444 from moqimoqidea/patch-1
...
fix claude 3.7 think enhance prompt problem.
2025-03-07 21:39:56 -05:00
Daniel Trugman
c51f59e50b
Requesty: Correctly calculate request costs
2025-03-07 16:41:09 +00:00
Daniel Trugman
e14b1b2dab
Add OpenAI-style cost calculation
2025-03-07 13:53:32 +00:00
Daniel Trugman
129f15884f
Requesty: Correctly set image and computer use support
2025-03-07 13:00:37 +00:00
moqimoqidea
aa70d755f8
fix claude 3.7 think enhance prompt problem.
2025-03-07 16:28:44 +08:00
Matt Rubens
70a88aee4d
Merge pull request #1392 from eonghk/feature/vertex-credentials-auth
...
Add credentials auth for Google vertex
2025-03-06 16:45:45 -05:00
Olwer Altuve
21101e25bf
refactor(deepseek): update test expectations
...
- Update test case to reflect current object reference behavior for model info
2025-03-06 12:29:13 -04:00
Olwer Altuve
e75fdc1ef6
only info
2025-03-06 11:51:11 -04:00
Olwer Altuve
89cf2c4c58
feat(api): Add DeepSeek provider support for prompt caching and detailed usage metrics
...
- Update DeepSeekHandler to support prompt caching
- Add cache token tracking in usage metrics
- Update DeepSeek model configurations with cache-related pricing
- Enhance test coverage for cache and usage metric handling
2025-03-06 11:26:15 -04:00
Chris Estreich
c9e21eb091
Merge pull request #1414 from websentry-ai/pm/add-unbound-metadata
...
Adds Unbound metadata for non-streaming requests
2025-03-05 21:07:27 -08:00
eong
e3ffd1337a
Merge branch 'main' into feature/vertex-credentials-auth
2025-03-06 15:17:49 +13:00
Olwer Altuve
2e78662e9e
fix(deepseek): update base URL to remove /v1 endpoint
2025-03-05 16:57:44 -04:00
Matt Rubens
e4fb0081b1
Update commands to roo-cline to be consistent with others
2025-03-05 10:39:36 -05:00
