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
d8df9a5e2c
Cost display updating for Bedrock custom ARNs that are prompt routers
2025-03-11 21:58:07 -07:00
dongqing
9d0b824b90
fix test error for wrong arguments after additional base url added
2025-03-11 17:37:07 +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
Daniel Trugman
c51f59e50b
Requesty: Correctly calculate request costs
2025-03-07 16:41:09 +00:00
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
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
Olwer Altuve
2e78662e9e
fix(deepseek): update base URL to remove /v1 endpoint
2025-03-05 16:57:44 -04:00
Pugazhendhi
4073bdcb20
Fixes tests
2025-03-05 16:53:26 +05:30
refactorthis
589387ba65
feat: add x-title and http-referer header to all openai providers
...
- Provides the ability for Open AI compatible gateways, such as LiteLLM, Open Router, Requesty to determine originating app.
- Uses standard set by Open Router.
2025-03-05 19:16:23 +11:00
Matt Rubens
63cecf8b22
Support 128k max tokens for openrouter thinking
2025-03-03 09:37:55 -05:00
cte
62385ba4c7
Custom max tokens fix for non-thinking models
2025-03-01 21:05:03 -08:00
ashktn
4caa49228f
feat: Add support for Gemini models on Vertex AI
2025-02-28 18:59:26 -05:00
cte
8cbce2ded0
Add provider-agnostic modelMaxThinkingTokens setting
2025-02-27 16:06:47 -08:00
Chris Estreich
54c687485b
Merge pull request #1254 from lupuletic/added-new-thinking-support
...
Added support for Claude Sonnet 3.7 thinking via Vertex AI
2025-02-27 15:51:58 -08:00
Catalin Lupuleti
5eba1d53fb
Added tests for Claude Sonnet Thinking
2025-02-27 22:15:17 +00:00
Matt Rubens
e7769cea57
Add gpt-4.5-preview
2025-02-27 15:30:04 -05:00
Chris Estreich
02c955e1e6
Merge pull request #961 from aitoroses/feat/vertex-prompt-caching
...
Add Vertex AI prompt caching support for Claude models
2025-02-27 12:03:20 -08:00
cte
d66b5d2db6
Fix tests
2025-02-27 02:40:39 -08:00
Aitor Oses
9b267e9afc
Add Vertex AI prompt caching support and enhance streaming handling
...
- Implemented comprehensive prompt caching strategy for Vertex AI models
- Added support for caching system prompts and user message text blocks
- Enhanced stream processing to handle cache-related usage metrics
- Updated model configurations to enable prompt caching
- Improved type definitions for Vertex AI message handling
2025-02-25 15:30:10 +01:00
cte
543b68f785
Fix tests
2025-02-24 16:09:31 -08:00
cte
a130e656f1
Fix tests
2025-02-24 13:07:00 -08:00
Matt Rubens
5ffb145c13
Enable streaming for o1
2025-02-14 20:58:18 -05:00
d.o.it
8a5563b520
Add MistralHandler constructor validation and unit tests
2025-02-12 15:47:14 +01:00
Matt Rubens
2449c49358
Merge remote-tracking branch 'origin/main' into feat/roo-code-requesty-provider
2025-02-10 10:53:51 -05:00
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
Matt Rubens
2ccab1444b
Merge remote-tracking branch 'origin/main' into temperature_control
2025-02-09 22:53:44 -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
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-m
26baaf89a3
Merge branch 'main' into WEB-1756
2025-02-07 13:02:46 +05:30
Pugazhendhi
18f15559e3
Fixes test file
2025-02-06 13:03:03 +05:30
Matt Rubens
49c21b6c69
Add new gemini models
2025-02-05 12:04:36 -05:00
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
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
Vignesh Subbiah
d6433591b2
Add typing for usageData and adds some unit tests
2025-01-29 22:53:43 +05:30
Vignesh Subbiah
4008a1a53e
Modifying the usage of unbound.ts in compliance with all providers
2025-01-28 19:43:52 +05:30
Pugazhendhi
270105bac8
Adds test file
2025-01-27 19:48:04 +05:30
Matt Rubens
0cfc095544
Merge remote-tracking branch 'origin/main' into aws-profile-support
2025-01-24 09:10:11 -05:00
Matt Rubens
82a6d13c20
Change default
2025-01-22 08:18:29 -08:00
Matt Rubens
2a11bcabfd
Update openrouter.test.ts
2025-01-21 19:32:59 -05:00
