Commit Graph

166 Commits

Author SHA1 Message Date
Matt Rubens
d1c39c17e9 Add tests 2025-01-08 17:59:22 -05:00
Matt Rubens
7137f8c528 Spacing adjustments 2025-01-08 17:28:32 -05:00
RaySinner
d5fd2bbb82 merge: resolve conflicts after upstream merge 2025-01-08 23:47:26 +03:00
sam hoang
352f34d8ce feat: config manager using secret store 2025-01-07 20:09:55 -05:00
Matt Rubens
0aa5f1fb85 Add the o1 model 2025-01-07 13:33:47 -05:00
Matt Rubens
c9de9cda66 Revert some whitespace changes 2025-01-07 10:31:42 -05:00
RaySinner
fe22d1ff2d feat: add retry request control with delay settings
- Add requestDelaySeconds setting for configuring delay between retry attempts
- Add alwaysApproveResubmit option for automatic retry approval
- Add api_req_retry_delayed message type for delayed retries
- Update UI components to support new retry control settings
2025-01-07 10:21:51 -05:00
RaySinner
98b9007c36 merge(upstream): merge upstream changes keeping VSCode LM provider and adding Glama support 2025-01-07 01:54:46 +03:00
RaySinner
9d62a7bb77 feat(vscode-lm): implement VS Code Language Models provider 2025-01-07 01:23:22 +03:00
Matt Rubens
7e9ea7ac28 Add a Git section to the context mentions 2025-01-06 12:17:26 -05:00
Matt Rubens
7383a0514a Merge pull request #282 from RooVetGit/open_ai_streaming_toggle
Streaming checkbox for OpenAI-compatible providers
2025-01-05 22:46:50 -05:00
Matt Rubens
2cdfff02c0 Streaming checkbox for OpenAI-compatible providers 2025-01-05 20:34:54 -05:00
Frank
8b0e9bbf32 fix: remove unnecessary comment 2025-01-05 19:25:35 -05:00
Frank
e5e700ffcb feat: add Glama gateway 2025-01-04 22:50:12 -05:00
Daniel Riccio
ed358b4e07 Add toggle to enable or disable MCP servers on the system prompt 2025-01-02 21:02:59 -08:00
Matt Rubens
c8b8eff147 Setting for number of terminal lines to return from commands 2024-12-30 23:15:01 -08:00
Matt Rubens
90ed3a4582 Add a button to delete user messages 2024-12-30 17:54:37 -08:00
Matt Rubens
ff062c6e2e Allow selection of multiple browser viewport sizes and adjusting screenshot quality 2024-12-29 16:26:18 -08:00
Matt Rubens
6290f90fa5 Refactor 2024-12-29 12:20:35 -08:00
Matt Rubens
eb8c4cc50f Add DeepSeek to the list of providers 2024-12-29 11:27:31 -08:00
sam hoang
7021b71776 fix(openai-compatible) fix load model when change baseUrl 2024-12-30 02:20:20 +07:00
Matt Rubens
111abdbb2c Enhance prompt button for openrouter 2024-12-28 15:44:14 -08:00
Matt Rubens
1581ed135b Merge pull request #207 from samhvw8/feat/openai-list-models
feat list model for open ai compatible
2024-12-27 22:44:27 -08:00
Matt Rubens
03707d5dcc Add configurable delay after auto-writes to allow diagnostics to catch up 2024-12-26 09:59:01 -08:00
sam hoang
198e1965e9 feat openai-list-models 2024-12-25 01:02:33 +07:00
Matt Rubens
8b4c52fb51 Add a preferred language dropdown 2024-12-21 10:23:01 -05:00
student
ffd51479c1 Fix gemini-2.0-flash-thinking-exp-1219 contewWindow 2024-12-20 00:32:40 +01:00
Matt Rubens
38138164e5 Add gemini-2.0-flash-thinking-exp-1219 2024-12-19 15:32:30 -05:00
Matt Rubens
3aca5e813e Make fuzzy diff matching configurable (and default to off) 2024-12-18 15:26:44 -05:00
Matt Rubens
6a6084b7ca Toggle to switch browser size to 1280x800 2024-12-18 00:33:46 -05:00
Mike C
1be51a46b1 Merge pull request #60 from Premshay/main
feat(api): unify Bedrock provider using Runtime API
2024-12-17 09:29:43 -06:00
Premshay
e93f59085f Merge branch 'RooVetGit:main' into main 2024-12-17 12:40:53 +02:00
Matt Rubens
06202be46f Remove debug checkbox 2024-12-16 22:58:04 -05:00
Justin Quan
bb5fababae Merge branch 'main' into jq/sound-setting-improvements 2024-12-16 11:00:17 -08:00
Matt Rubens
c2b4b05459 Diff debugging 2024-12-16 12:19:44 -05:00
Justin Quan
1adc36a292 add volume setting 2024-12-15 23:22:44 -08:00
Premshay
acf472aae0 Update api.ts 2024-12-15 11:28:54 +02:00
Premshay
8460a796e9 Merge branch 'main' into main 2024-12-15 11:15:43 +02:00
Matt Rubens
3d7ff32406 Allow enabling/disabling of MCP servers 2024-12-14 01:39:25 -05:00
Matt Rubens
23efdeaf35 More safety around always allowing MCP 2024-12-13 17:32:26 -05:00
Matt Rubens
1346f1280c MCP checkbox for always allow 2024-12-13 16:14:13 -05:00
Matt Rubens
6ee118e0a2 Merge pull request #86 from RooVetGit/fix-openai-compatible-streaming
Add 'Include stream options' checkbox for OpenAI-compatible providers
2024-12-13 01:41:15 -05:00
Matt Rubens
be3d8a6166 Incorporate MCP changes (#93)
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
2024-12-12 23:16:39 -05:00
Matt Rubens
2cfd76c305 Add 'Include stream options' checkbox for OpenAI-compatible providers 2024-12-12 09:20:58 -05:00
Matt Rubens
156cab8cbc Fix: Add checkbox for stream_options in OpenAI-compatible providers 2024-12-12 08:58:38 -05:00
Cline
51a57d5bbf fix(bedrock): improve stream handling and type safety
- Fix TypeScript error in ConverseStreamCommand payload
- Add proper JSON parsing for test stream events
- Improve error handling with proper Error objects
- Add test-specific model info with required fields
- Fix cross-region inference and prompt cache config
2024-12-11 22:47:59 +02:00
Cline
140318cecd feat(api): unify Bedrock provider using Runtime API
Problem:
The current Bedrock implementation uses the Bedrock SDK, which requires separate handling for different model types and doesn't provide a unified streaming interface.

Solution:
Integrate the Bedrock Runtime API to provide a single, unified interface for all Bedrock models (Claude and Nova) using the ConverseStream API. This eliminates the need for separate handlers while maintaining all existing functionality.

Key Changes:
- Refactored AwsBedrockHandler to use @aws-sdk/client-bedrock-runtime
- Enhanced bedrock-converse-format.ts to handle all content types and properly transform between Anthropic and Bedrock formats
- Maintained cross-region inference support with proper region prefixing
- Added support for prompt caching configuration
- Improved AWS credentials handling to better support default providers
- Added proper error handling and token tracking for all response types

Dependencies:
- Added @aws-sdk/client-bedrock-runtime for unified API access
- Removed @anthropic-ai/bedrock-sdk dependency

Testing:
- Verified message format conversion for all content types
- Tested cross-region inference functionality
- Validated streaming responses for both Claude and Nova models

This change simplifies the codebase by providing a single, consistent interface for all Bedrock models while maintaining full compatibility with existing features.
2024-12-11 22:47:56 +02:00
Cline
dffc040e7c feat(bedrock): Add Meta Llama 3, 3.1, and 3.2 models with detailed pricing and context windows 2024-12-11 22:31:32 +02:00
Matt Rubens
0e0c848a96 Fix Gemini 2.0 context window 2024-12-11 14:02:54 -05:00
Matt Rubens
65bbefed55 Add Gemini 2.0 2024-12-11 13:36:46 -05:00