Skip to content

feat: add Venice AI provider#12117

Draft
roomote-v0[bot] wants to merge 1 commit intomainfrom
feature/add-venice-ai-provider
Draft

feat: add Venice AI provider#12117
roomote-v0[bot] wants to merge 1 commit intomainfrom
feature/add-venice-ai-provider

Conversation

@roomote-v0
Copy link
Copy Markdown
Contributor

@roomote-v0 roomote-v0 bot commented Apr 14, 2026

Related GitHub Issue

Closes: #12106

Description

This PR attempts to address Issue #12106 by adding Venice AI as a new provider to Roo Code. Venice AI offers an OpenAI-compatible API at https://api.venice.ai/api/v1 for private inference.

Implementation details:

  • Type definitions (packages/types/src/providers/venice.ts): Defines VeniceModelId, veniceDefaultModelId, and veniceModels with modern models (glm-4-32b as default, trinity-v1, deepseek-r1-671b, deepseek-v3-0324, qwen-2.5-coder-32b, llama-3.3-70b) per issue feedback from @joshua-mo-143
  • API handler (src/api/providers/venice.ts): Extends BaseOpenAiCompatibleProvider pointed at the Venice API endpoint
  • Provider settings: Added veniceApiKey to schemas, secret keys, provider names, and model ID mappings
  • UI component (webview-ui/src/components/settings/providers/Venice.tsx): API key input with link to Venice settings page
  • Wired into: buildApiHandler, ProfileValidator, ApiOptions, useSelectedModel, constants, and i18n strings

Follows the same pattern as SambaNova and other OpenAI-compatible providers.

Feedback and guidance are welcome.

Test Procedure

  • Added unit tests in src/api/providers/__tests__/venice.spec.ts (9 tests covering base URL, API key, default model, specified model, completePrompt, error handling, streaming text, streaming usage, and API parameters)
  • All Venice tests pass: cd src && npx vitest run api/providers/__tests__/venice.spec.ts
  • Existing ProfileValidator tests pass (28/28)
  • Existing types package tests pass (180/180)
  • Full lint and type-check pass across the monorepo

Pre-Submission Checklist

  • Issue Linked: This PR is linked to an approved GitHub Issue (see "Related GitHub Issue" above).
  • Scope: My changes are focused on the linked issue (one major feature/fix per PR).
  • Self-Review: I have performed a thorough self-review of my code.
  • Testing: New and/or updated tests have been added to cover my changes (if applicable).
  • Documentation Impact: No documentation updates needed for this provider addition.
  • Contribution Guidelines: I have read and agree to the Contributor Guidelines.

Documentation Updates

No documentation updates are required. The provider will appear automatically in the provider dropdown in settings.

Interactively review PR in Roo Code Cloud

Adds Venice AI (https://venice.ai) as a new OpenAI-compatible provider
for private inference. Includes modern models like glm-4-32b, trinity-v1,
deepseek-r1-671b, deepseek-v3-0324, qwen-2.5-coder-32b, and llama-3.3-70b.

Closes #12106
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[ENHANCEMENT] add Venice AI provider

1 participant