scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-08-28 05:27:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 1
1551 commits 2166 branches 585 tags 928 MiB
Commit graph

114 commits

Author SHA1 Message Date
Saoud Rizwan
1127e2a33c Add Claude 3.7 Sonnet 2025-02-24 11:07:23 -08:00
Quentin Machu
82f1f79b3e fix: make AWS Bedrock authentication predictable 
Anthropic's Bedrock SDK creates an AWS credential provider chain [1]
for each request it needs to sign. By doing so right before actually
having to sign the request, it can utilize any session created after
VSCode launched (i.e. outside of the process), and it can renew the
sessions every time necessary transparently for the user.

Cline, on the other hand, by transforming the provided AWS_PROFILE into
a key / secret / session, as part of client initialization, completely
short-circuits this, making it very difficult for users in companies where
sessions are short-lived. Furthermore, Cline would silently ignore the
provided AWS_PROFILE if there isn't a current/non-expired session at the time
of initialization, pass null keys to the Bedrock SDK, which would then
make use the default profile, which may not be configured or authorized
to use AWS Bedrock (as most AWS SSO hub accounts would). From the
perspective of the user, this would manifest itself as an "supported
country" error or unhelpful errors that are basically impossible to
debug without attaching a debugger to Cline.. and such developers may
end up reaching out to their DevOps/IT teams for help, which also could
turn into a waste of time.

This PR addresses the aforementioned issues by resolving the credentials on
every invocation.

1: 61b55599d5/packages/bedrock-sdk/src/auth.ts (L19)
 2025-02-20 22:41:29 +08:00
Saoud Rizwan
e40e6ddbcd Refactor 2025-02-18 10:49:37 -08:00
Daniel Trugman
cc166f4144
Requesty provider improvements (#1829) 
* Requesty: Add cline headers to requests

* Requesty: Add support for cache read/write tokens

* Requesty: Remove deepseek reasoner conversions that are handled in-flight by Requesty

* Requesty: Read o3-mini reasoning effort from Cline settings

* Requesty: Add total cost per interaction

* Add changeset
 2025-02-17 10:37:23 -08:00
Saoud Rizwan
5dea79c65f Fix Mistral provider server URL 2025-02-17 10:35:21 -08:00
Shawn Smith
a99648884a
Fix: Bedrock Profiles (#1751) 
* fix-bedrock-profiles

* fix-bedrock-profiles

* resolve linting issue

* fixes

* resolve using var

* add changeset

* update changeset
 2025-02-12 17:56:20 -08:00
brownrw8
0434b5c772
Advanced configuration for OpenAI Compatible Providers (#1737) 
* feat: advanced configuration for OpenAI Compatible Providers

* Update .changeset/thirty-eyes-appear.md

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* Update webview-ui/src/components/settings/ApiOptions.tsx

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>

* dropdown menu

* Show pricing if user entered model info

---------

Co-authored-by: ellipsis-dev[bot] <65095814+ellipsis-dev[bot]@users.noreply.github.com>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-12 14:09:55 -08:00
Sanjaykumar S
e534c3dbc7
Add api key for litellm api provider #1766 (#1767) 
* Add api key for litellm api provider

* Added Changeset

* Update litellm.ts

* Update ApiOptions.tsx

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-12 10:56:13 -08:00
Waylon
e8a2e88fa0
feat: qwen platform adds deepseek-r1/v3 support (#1729) 
Co-authored-by: fine <fine_951111@163.com>
 2025-02-10 20:04:16 -08:00
Saoud Rizwan
fbd249d387 Adjust generation retry params 2025-02-09 02:14:34 -08:00
Saoud Rizwan
43200007cf Retry openrouter generation endpoint to fix context limit errors 2025-02-08 20:15:38 -08:00
Saoud Rizwan
fa05f94dfa Fixes 2025-02-07 21:34:47 -08:00
Evan
4449b51e2c
Let's reason together (#1597) 
* let's reason together

* typo

* changeset

* Fix type error

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-07 14:32:14 -08:00
brownrw8
84f017c98e
feat:Add Together API Provider (#1698) 2025-02-07 13:55:48 -08:00
Daniel Steigman
076b1e39e6
Nighttrek/bedrock credential manager (#1667) 
* added initial AWS bedrock support

* fixed formatting

* updated to fix persistence

* added changeset
 2025-02-06 23:36:38 -08:00
brownrw8
3cacd57949
Add dedicated Requesty provider (#1677) 
* feat: Add dedicated Requesty provider

* Update ExtensionStateContext.tsx

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-06 20:45:52 -08:00
aicc
548338d39e
Add alibaba qwen models plus/max/coder-plus/turbo both stable and latest to use. (#1648) 
* add alibaba qwen-max qwen-plus qwen-turbo qwen-coder-plus  stable/latest models

* add alibaba qwen-max qwen-plus qwen-turbo qwen-coder-plus  stable/latest models

* Provide the api line choice for international user

* Remove redundant code

* Copy fixes

* Create dry-socks-talk.md

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-05 23:23:33 -08:00
Michael
bd5eb8fcae
feat: add retry decorator with rate limit handling (#1605) 
* fix: improve retry decorator with smart rate limit handling

- Add handling of rate limit (429) errors
- Implement retry timing based on response headers
- Add exponential backoff when no headers present
- Add a few unit tests

Fixes #713

* Create modern-knives-tan.md

* Improve readability in retry.ts

---------

Co-authored-by: Michael Overhorst <m.overhorst@spotonmedics.nl>
Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2025-02-05 23:11:01 -08:00
Daniel Steigman
905327db4e
Merge pull request #1610 from ViezeVingertjes/feat/1609-add-mistral-models 
feat: Add support for all available Mistral API models
 2025-02-04 23:52:10 -08:00
Michael Overhorst
fd676ef047 Removed /v1 from the url and tested several models. 2025-02-05 06:51:02 +01:00
Michael Overhorst
2cc0fa906c Updated the mistral url. 2025-02-05 06:41:00 +01:00
Hiroki Nakashima
180fbd5995
feat: add LiteLLM API provider support (#1618) 2025-02-04 14:46:13 -08:00
Daniel Trugman
a087f5e583
Fix reasoning_content check for openai & deepseek streams (#1594) 2025-02-01 16:15:57 -08:00
Saoud Rizwan
5eb8086b42 Add o3-mini support to OpenAI 2025-01-31 15:21:42 -08:00
Saoud Rizwan
6500b7c210 Fixes 2025-01-31 02:38:27 -08:00
Saoud Rizwan
68ac266463 Add better support for r1 + show reasoning tokens 2025-01-31 02:35:06 -08:00
Saoud Rizwan
d9af2acf5b Fix deepseek 2025-01-21 13:40:40 -08:00
Slava Kurilyak
f4df887fcd
feat: Add DeepSeek-R1 (deepseek-reasoner) support (#1355) 
* feat: Add DeepSeek-R1 (deepseek-reasoner) support

- Add new deepseek-reasoner model with proper pricing info
- Fix temperature parameter being sent to unsupported deepseek-reasoner model
- Improve model selection logic in DeepSeekHandler
- Update CHANGELOG with new features and fixes
- Bump version to 3.1.11

* style: apply prettier formatting to deepseek provider and api definitions
 2025-01-21 13:37:34 -08:00
Saoud Rizwan
6ceda01b24 Remove consult advisor tool 2025-01-20 16:12:12 -08:00
Saoud Rizwan
39b0389b9d Add vscode LM API types 2025-01-20 16:12:11 -08:00
Saoud Rizwan
8ec0b2cf08 Add VS Code LM API 2025-01-20 16:12:10 -08:00
Saoud Rizwan
771332ca3e Add respond_to_inquiry 2025-01-20 16:12:10 -08:00
Saoud Rizwan
7aeab15ecf Add advisor model to anthropic 2025-01-20 16:12:10 -08:00
Saoud Rizwan
f4ae4c66df Add advisor model to openrouter 2025-01-20 16:12:09 -08:00
Saoud Rizwan
2b1e3f553b Add Mistral API provider 2025-01-16 19:40:27 -08:00
Matt Rubens
a025b5cfd3
Add the o1 model (#1246) 2025-01-14 12:20:26 -08:00
Saoud Rizwan
25cd7cc8e2 chore: Prettier fix formatting 2025-01-06 12:41:33 -08:00
Saoud Rizwan
9de7253998 refactor: code cleanup, formatting updates, improved workspace handling, checkpoints feature 
Add instructions

Fix completion

Refactor

Rename reset to restore

add haschanges flag

Remove log

Better error handling

Better error handling

Fix wording

Fix

Fix

Fix

Comment

Add hash for only latest tool

Prepare for release

Fix

Fix delete

Format fix
 2025-01-06 12:40:30 -08:00
Saoud Rizwan
781434dd97 Fix DeepSeek cost reporting 2024-12-31 17:49:18 -08:00
Saoud Rizwan
505e7ea481 Fix deepseek price reporting 2024-12-31 13:10:17 -08:00
Saoud Rizwan
9ab24806f9 Fix context window error with deepseek 2024-12-31 12:26:47 -08:00
Saoud Rizwan
576de4df1a Add DeepSeek provider 2024-12-31 11:47:44 -08:00
Saoud Rizwan
7386e3db2b Add OpenRouter middle out transform to avoid context limit errors 2024-12-26 13:22:13 -08:00
Mark Percival
93e70c62f1
Chore: Prettier for consistant formatting (#794) 
* Chore: Pretier for consistant formatting

- TODO: This PR needs to be updated by Saoud after he runs `npm install` & `npm format:fix` and commits the results of the prettier changes.

* Revert prettier config

* Run npm install

* Fix prettier config and ignore package lock

* Run format

---------

Co-authored-by: Saoud Rizwan <7799382+saoudrizwan@users.noreply.github.com>
 2024-11-21 13:13:54 -08:00
Saoud Rizwan
39bc35eec1 Add LM Studio provider 2024-11-12 22:02:42 -05:00
Saoud Rizwan
bac0b1a0cb Add prompt caching for new model ids on openrouter 2024-11-12 18:35:51 -05:00
Saoud Rizwan
ad29ff2a03 Add AWS cross-region inference toggle 2024-11-07 13:51:13 -05:00
Saoud Rizwan
48cdfa9874 Add Haiku 3.5 to Anthropic, Bedrock, Vertex 2024-11-04 14:08:25 -05:00
Saoud Rizwan
62688c261a Prepare for release 2024-10-22 16:22:37 -04:00
Saoud Rizwan
165272ab47 Update Anthropic model IDs 2024-10-22 16:21:17 -04:00