Skip to content

Analyze project status and identify improvements#44

Merged
markl-a merged 5 commits intomainfrom
claude/analyze-project-status-M0agB
Jan 17, 2026
Merged

Analyze project status and identify improvements#44
markl-a merged 5 commits intomainfrom
claude/analyze-project-status-M0agB

Conversation

@markl-a
Copy link
Owner

@markl-a markl-a commented Jan 17, 2026

No description provided.

- Add GeminiClient with full chat, async chat, and streaming support
- Support for Gemini 1.5 Pro, Flash, and other models
- Automatic retry with exponential backoff
- Safety settings and generation config customization
- Token counting support
- Register gemini provider in LLMClientFactory
- Add google-generativeai dependency to requirements.txt
- Add AdvancedRetriever with HyDE (Hypothetical Document Embeddings)
- Add MultiQuery retrieval for better query coverage
- Add CrossEncoderReranker for improved precision
- Add CohereReranker for API-based reranking
- Implement Reciprocal Rank Fusion for result combination
- Add convenience classes: HyDERetriever, MultiQueryRetriever, RerankedRetriever
- Support async retrieval methods
- Add BaseMemoryStore abstract class for storage backends
- Add SQLiteMemoryStore for local file-based persistence
- Add RedisMemoryStore for distributed in-memory storage
- Add JSONFileMemoryStore for simple file-based storage
- Add MemoryStoreFactory for easy store creation
- Add PersistentAgent with automatic memory save/load
- Add ConversationManager for multi-conversation handling
- Support conversation switching, export/import, and metadata
- Add TokenBudgetManager for tracking and limiting token usage
- Support hourly, daily, weekly, and monthly budget limits
- Add per-model budget allocation
- Add SQLiteUsageStore and InMemoryUsageStore backends
- Include cost calculation for OpenAI, Anthropic, and Google models
- Add alert thresholds and callbacks for budget warnings
- Implement BudgetExceededError for enforcing limits
- Add usage statistics and cost summary reports
- Update README to reflect new LLM providers, RAG, and agent features
- Update Roadmap to mark completed items
- Add comprehensive CHANGELOG entries for all new features
- Document Google Gemini, Advanced RAG, Memory Persistence, Token Budget
@markl-a markl-a merged commit ee14f55 into main Jan 17, 2026
0 of 6 checks passed
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