feat(providers): add SambaNova as an OpenAI-compatible provider - #2
Open
snova-kwasia wants to merge 2 commits into
Open
feat(providers): add SambaNova as an OpenAI-compatible provider#2snova-kwasia wants to merge 2 commits into
snova-kwasia wants to merge 2 commits into
Conversation
- Add SambanovaProvider via _compat() helper with OpenAI-compatible endpoint - Add 4 curated model entries (Llama 3.3 70B, Qwen 2.5 Coder, Llama 3.2 Vision, DeepSeek V3) - Update capabilities heuristics to handle Llama-prefixed model names - Add Sambanova logo SVG and wire up in GUI provider gallery - Add API key help link in ProviderSetup.tsx
snova-kwasia
marked this pull request as ready for review
August 4, 2026 05:45
Models verified via GET /models endpoint: - DeepSeek-V3.1 (131072 ctx) - DeepSeek-V3.2 (32768 ctx) - Meta-Llama-3.3-70B-Instruct (131072 ctx) - MiniMax-M2.7 (196608 ctx) - gemma-4-31B-it (131072 ctx) - gpt-oss-120b (131072 ctx)
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Why
OpenWorker should support SambaNova as a first-class model provider, enabling users to leverage SambaNova's fast inference for open-weight models like Llama 3.3 70B, Qwen Coder, and DeepSeek V3.
Root cause
SambaNova was not in the provider registry. Users wanting to use SambaNova models had no way to configure them through the UI.
Fix
Added SambaNova as an OpenAI-compatible provider by:
ProviderDescriptorvia the existing_compat()helper with the SambaNova API endpoint (https://api.sambanova.ai/v1) andSAMBANOVA_API_KEYenv var supportvision=True)cloud.sambanova.aiTests
get_descriptor('sambanova')returns name, title, andneeds_key=Truetsc --noEmitwith no errors)Confidence
High. The implementation follows the exact same pattern as all other OpenAI-compatible vendors (Together, Fireworks, OpenRouter, DeepSeek, etc.) using the
_compat()helper. The changes are isolated to provider files and the GUI component wiring.