Skip to content

feat: add Tensorix as an LLM provider#11184

Open
shanemort1982 wants to merge 2 commits intocontinuedev:mainfrom
shanemort1982:add-tensorix-provider
Open

feat: add Tensorix as an LLM provider#11184
shanemort1982 wants to merge 2 commits intocontinuedev:mainfrom
shanemort1982:add-tensorix-provider

Conversation

@shanemort1982
Copy link

@shanemort1982 shanemort1982 commented Mar 8, 2026

Hey 👋

I've added Tensorix as a new provider option. It's an OpenAI-compatible API gateway — one key gets you DeepSeek V3/R1, Llama 4, Qwen 3, GLM-4, MiniMax, and a bunch of other models. Pay-as-you-go, no subscription.

What's in the PR

Pretty lightweight since it just extends the OpenAI class:

  • core/llm/llms/Tensorix.ts — new provider class (14 lines, extends OpenAI)
  • core/llm/llms/index.ts — registration
  • core/control-plane/schema.ts — schema validation
  • extensions/vscode/config_schema.json — VS Code config support
  • gui/src/pages/AddNewModel/configs/providers.ts — GUI model picker with AUTODETECT

Usage

{
  "models": [{
    "provider": "tensorix",
    "model": "deepseek/deepseek-chat-v3.1",
    "apiKey": "YOUR_KEY"
  }]
}

Users can also pick Tensorix from the Add Model UI and it'll auto-detect available models.

Why add this

Continue already has great provider coverage and Tensorix fills a gap for users who want a single gateway to multiple model families (DeepSeek, Meta, Qwen, etc.) without managing separate API keys. We've already got a Continue integration guide on our docs and would be happy to cross-link — more visibility for both projects.

Followed the same patterns as SiliconFlow/Novita. Let me know if you'd like any changes!


Summary by cubic

Add tensorix as an OpenAI-compatible LLM provider, giving users access to DeepSeek, Llama, Qwen, GLM, and more through a single API key. Provider is available in config, VS Code, and the Add Model UI with auto-detect.

  • New Features

    • New Tensorix class extending OpenAI with default apiBase https://api.tensorix.ai/v1/ and model deepseek/deepseek-chat-v3.1.
    • Registered tensorix in LLMClasses and control-plane schemas for models and embeddings.
    • VS Code config_schema.json updated to support tensorix with provider help text.
    • GUI model picker adds tensorix with API key input and AUTODETECT.
  • Bug Fixes

    • Fixed missing commas in VS Code config_schema.json for tensorix entries.

Written for commit 4c71836. Summary will update on new commits.

Adds Tensorix (https://tensorix.ai) as a new OpenAI-compatible
provider, giving users access to DeepSeek, Llama 4, Qwen, GLM,
and other models through a single API key.

Changes:
- New LLM class (core/llm/llms/Tensorix.ts)
- Registered in LLM index and config schema
- Added to VS Code extension config schema
- Added to GUI provider selection with AUTODETECT
@shanemort1982 shanemort1982 requested a review from a team as a code owner March 8, 2026 10:53
@shanemort1982 shanemort1982 requested review from RomneyDa and removed request for a team March 8, 2026 10:53
@dosubot dosubot bot added the size:M This PR changes 30-99 lines, ignoring generated files. label Mar 8, 2026
@github-actions
Copy link
Contributor

github-actions bot commented Mar 8, 2026

All contributors have signed the CLA ✍️ ✅
Posted by the CLA Assistant Lite bot.

Copy link
Contributor

@cubic-dev-ai cubic-dev-ai bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

1 issue found across 5 files

Prompt for AI agents (unresolved issues)

Check if these issues are valid — if so, understand the root cause of each and fix them. If appropriate, use sub-agents to investigate and fix each issue separately.


<file name="extensions/vscode/config_schema.json">

<violation number="1" location="extensions/vscode/config_schema.json:230">
P1: Missing comma after newly added `"tensorix"` makes `config_schema.json` invalid JSON and breaks schema parsing.</violation>
</file>

Since this is your first cubic review, here's how it works:

  • cubic automatically reviews your code and comments on bugs and improvements
  • Teach cubic by replying to its comments. cubic learns from your replies and gets better over time
  • Add one-off context when rerunning by tagging @cubic-dev-ai with guidance or docs links (including llms.txt)
  • Ask questions if you need clarification on any suggestion

Reply with feedback, questions, or to request a fix. Tag @cubic-dev-ai to re-run a review.

@shanemort1982
Copy link
Author

I have read the CLA Document and I hereby sign the CLA

Co-authored-by: openhands <openhands@all-hands.dev>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

size:M This PR changes 30-99 lines, ignoring generated files.

Projects

Status: Todo

Development

Successfully merging this pull request may close these issues.

1 participant