feat: add Synthorai LLM requester - #2474
Conversation
|
All contributors have signed the CLA. ✅ 所有贡献者均已签署 CLA。 |
|
I have read the CLA Document and I hereby sign the CLA |
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
|
Correcting the precedent I cited, because I cited the wrong one and it happens to be the worst possible wrong one. The description said this follows "the same manifest-only pattern as the OrcaRouter integration (#2411)". #2411 was closed without merging on 2026-08-13 — so I was holding up a rejected PR as evidence that this kind of contribution gets accepted. I didn't check its state before citing it. The correct precedent is #2326 ( Also restating the disclosure where a reviewer will actually see it: I'm affiliated with Synthorai, so this is a vendor adding its own requester rather than a user request, and I'm not claiming demand for it. CLA is signed. Happy to change anything about the manifest if the shape isn't what you want. |
Adds Synthorai (https://synthorai.io) as a supported LLM requester, following the same manifest-only pattern as the TokenLab requester (#2326), merged 2026-07-15 — same two files, an
.svgand a<name>chatcmpl.yaml.Synthorai is an OpenAI/Anthropic-compatible LLM gateway routing to 113 models across 11 upstream providers (Claude, GPT, Gemini, GLM, Kimi, DeepSeek, Qwen, etc.) at direct upstream pricing, no markup. Docs: https://synthorai.io/docs
Changes
src/langbot/pkg/provider/modelmgr/requesters/synthoraichatcmpl.yamlsrc/langbot/pkg/provider/modelmgr/requesters/synthorai.svgPoints
execution.pythonat the existing generic./chatcmpl.py/OpenAIChatCompletions(same executor the base OpenAI entry uses) rather than a new per-provider .py file, since this is a plain OpenAI-compatible passthrough with no custom request/response shaping needed.