Add sources parameter to completion requests and update documentation: Enhance the CompletionRequest model to include an optional sources field for document filtering. Update related API examples and documentation to reflect this change, ensuring clarity on usage and implications for project document retrieval.

Update dependencies and enhance agent functionality: upgrade LangChain to v1.2.x, adjust retrieval tools for improved pagination and filtering, and implement new project ID checks. Modify settings for RAG top-k and add support for custom state management in agents. Enhance documentation for streaming SSE client and tools policy, ensuring clarity on usage and constraints.

Enable V2 again

Update default agent identifier from 'V2' to 'V1' across multiple services for consistency in agent orchestration and handling.

Refactoring gestion Agent

refactor transcription: replace Supabase quota checker with a noop implementation, update transcription models to include server-measured audio duration, and enhance job response structure for improved reliability and consistency.

refactor transcription: update meeting transcription model to 'gpt-4o-mini-transcribe', enhance TranscriptionResponse and JobStatusResponse models with metadata fields, and implement usage normalization utilities for improved tracking and reporting.

feat transcription: introduce asynchronous transcription job endpoints for audio and meeting files, allowing users to upload files and poll for job status. Update models and services to handle job creation, status tracking, and response formatting. Enhance documentation with examples and details on supported audio formats and job management.

feat documents: add document deletion functionality and enhance upload process with UUID validation. Implement checks for duplicate documents during upload and update models to support delete responses. Refactor ingestion service to include document ID in processing pipelines.

feat voice: integrate WebRTC ICE server configuration, enhance voice pipeline with new modes, and improve VAD settings for better audio processing

Implement Voice Activity Detection (VAD) configuration: Add VAD parameters to settings, create VADConfigDTO for validation, and integrate VAD handling in the voice bot. Update frontend to allow dynamic VAD parameter adjustments during sessions.

feat voice: enhance voice pipeline with mode selection and transcript retrieval functionality

Enhance conversation management: Add conversation_id to CompletionRequest, CompletionResponse, and StreamChunk models. Update agent service methods to utilize conversation_id for server-side memory management. Ensure conversation_id is included in responses and streaming chunks for consistent context handling.

Include project knowledge in Workflow

Injestion project documents

Update default model in CompletionRequest from GPT-5 to Mistral Large for improved performance.

Remove OpenAI models & add Magistral model

Enhance conversation workflows by introducing summarization and classification agents. Implement retrieval nodes for document fetching, and update settings for Supabase integration. Add Markdown to PDF conversion utilities and improve agent service to handle document metadata. Refactor agent registry to support orchestrated workflows.

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.

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

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.

FIrst Commit