Skip to content

refactor: generalize inference layer to multiple providers - #62

Merged
Anton-Horn merged 1 commit into
mainfrom
refactor/multi-provider-inference
Jul 5, 2026
Merged

refactor: generalize inference layer to multiple providers#62
Anton-Horn merged 1 commit into
mainfrom
refactor/multi-provider-inference

Conversation

@Anton-Horn

Copy link
Copy Markdown
Contributor

Replace the OpenRouter-only integration with a provider-agnostic inference layer supporting Anthropic, Google, OpenAI, and OpenAI-compatible backends.

  • Add server/lib/inference/{text,image,embed}.ts as the shared entry point
  • Add provider backends under server/lib/providers/ (anthropic, google, openai, openai-compatible) alongside the existing openrouter one
  • Remove server/lib/openrouter/* and server/lib/ai/provider.ts
  • Add /providers route and web providers API; update setup/admin UI
  • Update CLI handlers, search, media, and chat providers to the new layer

🤖 Generated with Claude Code

Replace the OpenRouter-only integration with a provider-agnostic
inference layer supporting Anthropic, Google, OpenAI, and
OpenAI-compatible backends.

- Add server/lib/inference/{text,image,embed}.ts as the shared entry point
- Add provider backends under server/lib/providers/ (anthropic, google,
  openai, openai-compatible) alongside the existing openrouter one
- Remove server/lib/openrouter/* and server/lib/ai/provider.ts
- Add /providers route and web providers API; update setup/admin UI
- Update CLI handlers, search, media, and chat providers to the new layer
@Anton-Horn
Anton-Horn merged commit ee06864 into main Jul 5, 2026
1 check passed
@Anton-Horn
Anton-Horn deleted the refactor/multi-provider-inference branch July 5, 2026 14:11
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.

1 participant