Refactor system message handling in create_simple_graph_with_history to utilize a template for dynamic content generation, improving clarity and maintainability. Update SYSTEM_PROMPT to SYSTEM_PROMPT_TEMPLATE for consistency in prompt management.

Refactor create_simple_graph_with_history to conditionally add SystemMessage only if not already present in conversation history, improving message management. Update agent_service.py to handle system messages in the message list.

Update base_graph.py to format document output with XML-like tags and adjust retriever calls to specify a limit of 8 results for both formation and prestation types, improving document retrieval efficiency.

Implement streaming support validation in completion endpoint and enhance error handling for unsupported models. Update LLMService to include streaming capability check for models, specifically marking 'gpt-5' as non-streaming. Adjust API documentation for clarity on error responses.

Fix streaming mode with old messages

Update model references in enums and models to replace GPT-5 Mini with GPT-5 Chat, reflecting the latest model naming conventions and ensuring consistency across the LLMService.

Remove large PDF files and add .gitignore to respect HuggingFace Spaces 10MB limit

Refactor base_graph.py to support dual document types for retrieval and context formatting, enhancing the agent's ability to handle formation and prestation contexts separately.

Refactor LLMService to handle model-specific parameters for OpenAI's `gpt-5`, using `max_completion_tokens` instead of `max_tokens` and ensuring temperature is set to 1.0 when required.

Enhance LLMService to coerce temperature to 1.0 for OpenAI models that do not support custom values, specifically for `gpt-5` models, to prevent API errors.

Add first retriever

Enhance base_graph.py to include SystemMessage and integrate system prompt in LLM call for improved conversation context

Add MistralService module for file upload, OCR, and chat completion functionality

Update requirements.txt to upgrade pydantic-settings, add langchain-community, and include new dependencies for Supabase and vecs

Add dotenv support to load environment variables in app.py

Update model references from GPT-5 Pro to GPT-5 across enums, models, and service files, and adjust agent registry to use the history-enabled graph creation function.

fix streaming mode

Update LLMService to correct model descriptions for GPT-5 Pro and GPT-4

Update requirements.txt to upgrade dependencies and add new packages

Update requirements.txt to comment out real-time dependencies for future implementation

Update README.md to include project metadata and configuration reference

FIrst Commit

initial commit