Commit graph

8 commits

Author SHA1 Message Date
Salman Paracha
5108013df4
fixing a bug where by we were writing the cluster_name for an upstream LLM more than once (#607)
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
2025-10-27 17:01:59 -07:00
Salman Paracha
566e7b9c09
fixed bug in Bedrock translation code and dramatically improved tracing for outbound LLM traffic (#601)
* dramatically improve LLM traces and fixed bug with Bedrock translation from claude code

* addressing comments

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
2025-10-24 14:07:05 -07:00
Salman Paracha
9407ae6af7
Add support for Amazon Bedrock Converse and ConverseStream (#588)
* first commit to get Bedrock Converse API working. Next commit support for streaming and binary frames

* adding translation from BedrockBinaryFrameDecoder to AnthropicMessagesEvent

* Claude Code works with Amazon Bedrock

* added tests for openai streaming from bedrock

* PR comments fixed

* adding support for bedrock in docs as supported provider

* cargo fmt

* revertted to chatgpt models for claude code routing

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
Co-authored-by: Adil Hafeez <adil.hafeez@gmail.com>
2025-10-22 11:31:21 -07:00
Salman Paracha
f00870dccb
adding support for claude code routing (#575)
* fixed for claude code routing. first commit

* removing redundant enum tags for cache_control

* making sure that claude code can run via the archgw cli

* fixing broken config

* adding a README.md and updated the cli to use more of our defined patterns for params

* fixed config.yaml

* minor fixes to make sure PR is clean. Ready to ship

* adding claude-sonnet-4-5 to the config

* fixes based on PR

* fixed alias for README

* fixed 400 error handling tests, now that we write temperature to 1.0 for GPT-5

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local>
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-288.local>
2025-09-29 19:23:08 -07:00
Salman Paracha
03c2cf6f0d
fixed changes related to max_tokens and processing http error codes like 400 properly (#574)
Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-257.local>
2025-09-25 17:00:37 -07:00
Salman Paracha
fbe82351c0
Salmanap/fix docs new providers model alias (#571)
* fixed docs and added ollama as a first-class LLM provider

* matching the LLM routing section on the README.md to the docs

* updated the section on preference-based routing

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-167.local>
2025-09-19 10:19:57 -07:00
Salman Paracha
8d0b468345
draft commit to add support for xAI, TogehterAI, AzureOpenAI (#570)
* draft commit to add support for xAI, LambdaAI, TogehterAI, AzureOpenAI

* fixing failing tests and updating rederend config file

* Update arch_config_with_aliases.yaml

* adding the AZURE_API_KEY to the GH workflow for e2e

* fixing GH secerts

* adding valdiating for azure_openai

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-167.local>
2025-09-18 18:36:30 -07:00
Salman Paracha
4eb2b410c5
adding support for model aliases in archgw (#566)
* adding support for model aliases in archgw

* fixed PR based on feedback

* removing README. Not relevant for PR

---------

Co-authored-by: Salman Paracha <salmanparacha@MacBook-Pro-136.local>
2025-09-16 11:12:08 -07:00