Skip to content

Conversation

@SL-Mar
Copy link
Owner

@SL-Mar SL-Mar commented Jan 26, 2026

No description provided.

claude and others added 4 commits January 26, 2026 00:24
- Add OllamaProvider class for local model inference without API costs
- Support popular models: llama3.2, codellama, qwen2.5-coder, mistral
- Update LLMFactory with Ollama registration and base_url parameter
- Add ollama_base_url and ollama_model config options
- Fix typo: "Mistral Provider" -> "MistralProvider"
- Add missing CodeValidator class to processor.py that was referenced
  by tests but didn't exist, causing import failures
- Implement QuantConnectMCPServer.start() method with proper tool
  registration instead of placeholder pass statement
- Implement get_api_docs() with topic mapping to QuantConnect docs
  instead of returning placeholder string
- Add comprehensive unit tests for all previously untested modules:
  - test_config.py: Config, ModelConfig, UIConfig, ToolsConfig tests
  - test_agents.py: BaseAgent, AlphaAgent, UniverseAgent, RiskAgent,
    StrategyAgent tests
  - test_tools.py: Tool base class, ReadFileTool, WriteFileTool,
    SearchArticlesTool, ValidateCodeTool, BacktestTool tests
  - test_llm_providers.py: LLMFactory, AnthropicProvider, MistralProvider,
    DeepSeekProvider, OpenAIProvider, OllamaProvider tests
  - test_mcp.py: QuantConnectMCPClient, QuantConnectMCPServer tests
  - test_autonomous.py: LearningDatabase, CompilationError,
    PerformancePattern, GeneratedStrategy tests
  - test_evolver.py: EvolutionConfig, Variant, ElitePool, EvolutionState tests
  - test_library.py: CoverageTracker, CategoryProgress, StrategyTaxonomy tests
@SL-Mar SL-Mar merged commit a3a1dd6 into gamma Jan 26, 2026
4 of 14 checks passed
@SL-Mar SL-Mar deleted the claude/merge-tests-to-gamma-Yvvvl branch January 26, 2026 00:57
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.

2 participants