refactor: consolidate LLM clients and extract BaseReviewer #178
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
Addresses critical and high-priority code duplication: 1. **OllamaClient consolidation** (Critical) - Extract duplicated OllamaClient from 6 locations into `src/kit/ollama_client.py` - Single implementation with context manager support and session injection - Eliminates ~150 lines of duplicate code 2. **LLM client factory** (High) - New `src/kit/llm_client_factory.py` with centralized factory functions - `create_openai_client`, `create_anthropic_client`, `create_google_client`, `create_ollama_client` - `create_client_from_config` for summaries module - `create_client_from_review_config` for PR review modules - Eliminates duplicated initialization logic across 6 files 3. **BaseReviewer extraction** (High) - New `src/kit/pr_review/base_reviewer.py` with shared functionality - PRReviewer and AgenticPRReviewer now inherit from BaseReviewer - Shared methods: `parse_pr_url`, `get_pr_details`, `get_pr_files`, `get_pr_diff`, `get_repo_for_analysis` - Eliminates ~200 lines of duplicate code between reviewers All external APIs remain unchanged. Total reduction: ~450 lines of duplicate code. Tests: 37 new unit tests added across 3 new test files.
- Remove model validation checks from commit, review, and summarize commands (models change frequently, let the API return errors for invalid ones) - Fix provider switch: update llm.provider and llm_provider when switching - Fix model override: update llm_model convenience accessor
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Summary
src/kit/ollama_client.pywith context manager support and session injectionsrc/kit/llm_client_factory.pywith centralized factory functions for all LLM providers (OpenAI, Anthropic, Google, Ollama)src/kit/pr_review/base_reviewer.pybase class with shared GitHub API and caching functionality; PRReviewer and AgenticPRReviewer now inherit from itTotal reduction: ~450 lines of duplicate code. All external APIs remain unchanged.
Changes
src/kit/ollama_client.pysrc/kit/llm_client_factory.pysrc/kit/pr_review/base_reviewer.pysrc/kit/pr_review/reviewer.pysrc/kit/pr_review/agentic_reviewer.pysrc/kit/pr_review/local_reviewer.pysrc/kit/pr_review/summarizer.pysrc/kit/pr_review/commit_generator.pysrc/kit/summaries.pytests/test_ollama_client.pytests/test_llm_client_factory.pytests/test_base_reviewer.pyTest plan
kit review --help, etc.)