refactor: API provider #183
Merged
Conversation
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
…vider interfaces - Extracted message normalization, SSE handling, and response utilities into `src/api/utils.ts`. - Created `BaseOpenAIProvider.ts` with `LLMProvider`, `ModelProvider`, and `ChatCompletionProvider` implementations. - Added `types/provider.ts` to expose provider interfaces and updated `types/index.ts`. - Updated `src/context/chat.tsx` and `src/api/inference.ts` to use the new utilities. - Added `filterThoughtFromMsgs` helper to `src/utils/index.ts`. - Updated imports across the codebase and removed legacy functions.
…pport - Move BaseOpenAIProvider into `src/api/providers` and update imports - Introduce `LlamaCppProvider` with its own `jsonToModels` implementation - Create provider index to expose `getInferenceProvider` - Make `BaseOpenAIProvider` constructor accept optional `baseUrl` and throw error when omitted
- Replace legacy InferenceApi with BaseOpenAIProvider and LlamaCppProvider - Introduce provider caching, dynamic model retrieval, and cache expiration logic - Update InferenceContext to expose `provider` and `selectedModel` instead of `api` and `serverProps` - Add Modality type and extend InferenceApiModel with modalities and output_modalities - Add parseLlamaCppModelName helper and serverProps interface updates - Update hooks and components to use new provider API and configToCustomOptions
- Introduce OpenRouterProvider extending BaseOpenAIProvider - Implement 15‑minute cache expiration check - Convert OpenRouter model data to InferenceApiModel - Update BaseOpenAIProvider lastUpdated to protected for subclass use - Register open-router in getInferenceProvider
- Introduced `updateSelectedModel` callback to set the selected model when config changes - Invoked it in `syncServer` and the initialization effect to replace duplicated logic - Updated dependency arrays to include `updateSelectedModel` for correct memoization
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.
No description provided.