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
566fa0f154
Merge branch 'fix-deepseek-cache-official-api' of https://github.com/olweraltuve/Roo-Code into fix-deepseek-cache-official-api
2025-03-06 11:31:04 -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
Olwer Altuve
1711d6c04d
feat(deepseek): enhance model support with prompt caching and detailed usage metrics
...
- Add support for prompt caching in DeepSeek models
- Update model configurations to reflect caching capabilities
- Implement detailed usage metrics tracking cache write and read tokens
- Extend test coverage for new usage metrics and model parameters
- Update pricing information for DeepSeek models to include cache-related costs
2025-03-06 08:26:03 -04:00
eong
e3ffd1337a
Merge branch 'main' into feature/vertex-credentials-auth
2025-03-06 15:17:49 +13:00
Matt Rubens
73ac64924e
Merge remote-tracking branch 'origin/main' into human-relay
2025-03-05 10:34:03 -05:00
eong
01f83b4d17
Add credentials auth for Google vertex
2025-03-06 00:51:38 +13:00
sam hoang
9bbd902d5d
update new way to manage state
2025-03-05 00:06:30 +07:00
sam hoang
0a0634488a
update api config key list to match with api key and global state key
2025-03-04 22:34:13 +07:00
sam hoang
b4094a6281
refactor by pr comment
2025-03-04 21:56:22 +07:00
Adam Larson
1c8f9ed683
first pass on speculative decoding with LMStudio
2025-03-04 01:48:40 -05:00
Felix NyxJae
40dd7ac532
Merge branch 'main' of github.com:NyxJae/Roo-Code into human-relay
2025-03-04 11:23:04 +08:00
Matt Rubens
af06af136c
Set Vertex maxTokens to 64000
2025-03-03 16:03:22 -05:00
Matt Rubens
2b7df5e106
Update max tokens for vertex too
2025-03-03 09:44:02 -05:00
Tom X Nguyen
ef93f5d422
refactor: always enable 128k for simplification
2025-03-03 11:17:01 +07:00
Felix NyxJae
626827ab3f
Merge branch 'RooVetGit:main' into human-relay
2025-03-03 10:19:02 +08:00
Tom X Nguyen
aec03d71c3
feat: add virtual id for extended output capabilities
2025-03-03 07:47:12 +07:00
ashktn
4caa49228f
feat: Add support for Gemini models on Vertex AI
2025-02-28 18:59:26 -05:00
Felix NyxJae
8a5f16cbf2
Merge branch 'RooVetGit:main' into human-relay
2025-02-28 17:41:05 +08:00
Chris Estreich
31d2d17847
Fix maxTokens defaults for Claude 3.7 Sonnet models
2025-02-28 01:15:44 -08:00
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
3514f6506b
Added support for Claude Sonnet 3.7 thinking via Vertex AI
2025-02-27 21:56:56 +00:00
Matt Rubens
e7769cea57
Add gpt-4.5-preview
2025-02-27 15:30:04 -05:00
Chris Estreich
22ec3b21fe
Merge pull request #1244 from lupuletic/add-cache-costs-vertex-ai
...
Added cache costs for Claude Sonnet 3.7 via Vertex AI
2025-02-27 12:03:55 -08:00
Catalin Lupuleti
eec1769b6b
Added cache costs for Claude Sonnet 3.7 via Vertex AI
2025-02-27 18:56:28 +00:00
Felix NyxJae
3bb1d78c17
feat: Added human relay function and related message processing initial version
2025-02-27 18:08:05 +08:00
Aitor Oses
ea38d9ebba
Enable prompt caching for Claude Sonnet 3.7 Vertex AI model
2025-02-27 09:04:54 +01:00
Aitor Oses
4d22ae53fb
Merge remote-tracking branch 'upstream/main' into feat/vertex-prompt-caching
2025-02-27 08:55:06 +01:00
Chris Estreich
5e53d00ebc
Allow control over maxTokens for thinking models
2025-02-26 14:23:11 -08:00
cte
e56908f6c1
Thinking settings tweaks
2025-02-25 15:48:20 -08:00
Chris Estreich
7f1c6d7079
Merge branch 'cte/move-model-fetchers' into cte/openrouter-claude-thinking
2025-02-25 13:21:08 -08:00
Chris Estreich
392a237985
Support Claude 3.7 Sonnet "Thinking" in OpenRouter
2025-02-25 12:58:03 -08:00
Matt Rubens
91ef9fbdb3
Clean up maxTokens logic
2025-02-25 15:29:57 -05:00
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
b2b135c05c
[WIP] Claude 3.7 Sonnet (Thinking)
2025-02-24 15:45:26 -08:00
Matt Rubens
2f877c5ffe
Merge pull request #1156 from RooVetGit/add_claude_3_7_to_bedrock
...
Add Claude 3.7 to Bedrock
2025-02-24 15:51:10 -06:00
cte
b24a335503
Set maxTokens to 64K for Anthropic / 3.7 Sonnet
2025-02-24 13:48:47 -08:00
Matt Rubens
92131adc6d
Add Claude 3.7 to Bedrock
2025-02-24 15:35:00 -06:00
cte
d94067aba8
Revert maxTokens change for now
2025-02-24 12:54:05 -08:00
cte
0e644f102f
Default to Claude 3.7 where appropriate
2025-02-24 12:48:55 -08:00
Chris Estreich
645d069c08
Merge pull request #1149 from RooVetGit/cte/claude-3.7
...
Add Claude 3.7
2025-02-24 11:35:00 -08:00
cte
c677a450d1
Fix maxTokens
2025-02-24 11:30:15 -08:00
cte
92ac610366
Add Claude 3.7
2025-02-24 11:14:08 -08:00
Catalin Lupuleti
39715f13e1
Added support for Claude sonnet 3.7 via VertexAI
2025-02-24 19:05:05 +00:00
Marvin Thobejane
a7c842fd9d
gpt 4o price update
2025-02-21 00:11:18 +02:00
d.o.it
95078a6bc9
add mistral latest api models
2025-02-12 15:04:02 +01:00
d.o.it
4497e42206
Add Mistral API configuration and models
2025-02-12 14:22:40 +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
d6e55afb51
using ModelPicker for Requesty Model Picker
2025-02-10 20:14:50 +07:00
