Add Requesty as an OpenAI-compatible LLM backend - #125
Open
Thibaultjaigu wants to merge 1 commit into
Open
Conversation
Mirror the existing OpenRouter integration to support Requesty (https://router.requesty.ai/v1). Adds a requesty backend branch and _send_requesty() in llm_backend.py, the requesty option in config/manager.yaml and the --backend argparse choices, and documents it in INTERACTIVE_MODE_GUIDE.md. Auth via REQUESTY_API_KEY.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Add Requesty as an LLM backend
Adds Requesty as a manager LLM backend, mirroring the
existing OpenRouter integration. Requesty is an OpenAI-compatible router that uses the
same
provider/modelnaming scheme as OpenRouter (e.g.anthropic/claude-sonnet-4,openai/gpt-4o-mini).Changes
src/interactive/llm_backend.pyrequestybranch inLLMBackend.send()dispatch._send_requesty()method, a 1:1 mirror of_send_openrouter()that POSTs tohttps://router.requesty.ai/v1/chat/completionswithAuthorization: Bearer $REQUESTY_API_KEY. Same OpenAI-compatible request/response and tool-call parsing.__init__docstrings to mention the new backend.config/manager.yaml— addsrequestyto thellm_backendoptions and a model example.src/interactive/manager.py— addsrequestyto the--backendargparse choices.INTERACTIVE_MODE_GUIDE.md— documentsrequestyin the--backendoption table.Notes
REQUESTY_API_KEYenvironment variable (parallelsOPENROUTER_API_KEY).httpxpath.Testing
python -m py_compileon both edited Python modules — passes.POST https://router.requesty.ai/v1/chat/completionswithmodel=openai/gpt-4o-minireturned HTTP 200 and a valid OpenAI-compatible completion.
I work at Requesty. This mirrors the existing OpenRouter wiring. Happy to adjust or close it if it's not a fit.