fix: Add IDE-style panel scrolling

fix: Add reranking to prioritize source code over text files

fix: Require explicit code citations in RAG responses

fix: Improve UI layout - VS Code style file tree, better buttons

feat: Implement 3-panel file explorer UI

feat: Update chat UI to showcase RAG capabilities

fix: Add strict anti-hallucination rules to prompts

fix: Wire up 'Try asking' suggestion buttons to chat

fix: Switch to FAISS as default and use /tmp for persist directory

fix: Add faiss-cpu and langchain-chroma to requirements

fix: Configure Streamlit for Hugging Face file uploads

fix: Add detailed logging and error handling for source ingestion

feat: Add HTTP ZIP download fallback for GitHub repos

fix: Update Dockerfile for Hugging Face /tmp directories and env vars

fix: Use /tmp directory for Hugging Face compatibility

feat: Add Groq-optimized prompts, vector DB fallback, improved ignore patterns

feat: Add runtime Gemini model switching on rate limits - automatically tries next model

feat: Add Gemini 3 preview models to fallback list

feat: Add Gemini model fallback logic - tries multiple models in sequence

fix: Add ChromaDB auto-recovery from corruption

fix: Use gemini-2.5-flash as default (confirmed working)

fix: Add models/ prefix to Gemini model names

fix: Update Gemini model list to available models

fix: Add langchain-huggingface to requirements.txt

Remove binary assets for HF Spaces

Add Dockerfile for HF Spaces

Deploy to Hugging Face Spaces

feat: Add local embeddings to bypass API rate limits

fix: Simplify __init__.py to fix import error

feat: Add Next.js frontend with Framer Motion animations

docs: Organize project with clear README and clean exports

chore: Remove unused files (rate_limit_config, setup.py, ingestor, cli)

chore: Remove unnecessary helper scripts

feat: Add MCP + CrewAI integration with multi-mode interface

Refactor: Removed all Sage branding and assets

Refactor: Upgraded to Agentic Chatbot with AST & Call Graph support

Use storia-sage as pypi package name.

Apply formatting

Update "Processing chunks" into "Processing files"

Revert default index name back to sage; pinecone doesn't allow underscores

Bump pypi version, restrict Python version

Adapt to Anthropic's new count_tokens API

Apply formatting

Closes [FEATURE REQUEST] Expand to other vector stores beyond Pinecone (#102)

Added the progress bar (#104)

Fix formatting in test_vector_store.py

Fix formatting

Adding tests for vector_store.py (#98)

Update reranker.py (#99)

Implemented Reciprocal Rank Fusion (#87)