Fix CrewAI compatibility and agent input parameter extraction

Remove secrets and ignore .env

solved chatllm problems

final commits

Added fixed agent to agent communication

adding pipeline status into the message response

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Enforced chat_name along with chat_id (#1)

Update: last_activity updates for all message interactions

Fix: Update last_activity only for user messages

Fix: Properly detect and report pipeline failures

Implement Gemini-based automatic chat name generation

Fix: Add missing generate_message_id function to schemas.py

Refactor: Use MongoDB _id for messages, pipeline_id_index for components, standardize outputs to result:{text:{}} format

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

feat: Complete API response corrections - add pipelines endpoint and enhanced error handling

feat: API response corrections - add message_id, component tracking, and error handling

Update api_routes_v2.py

Update services/pipeline_executor.py

Update api_routes_v2.py

Update api_routes_v2.py

Update api_routes_v2.py

Update services/pipeline_executor.py

feat: Add pipeline components metadata and fix sort orders

fix: CRITICAL - Replace S3 URIs with presigned URLs in all API responses

fix: Add file metadata to messages in conversation history

fix: Remove JSON result from assistant_response in /chat/unified - cleaner UI response

fix: CRITICAL - Store pipelines in BOTH session.pipelines_history AND pipelines collection

fix: Critical pipeline ID sequencing bug

fix: Replace _mark_latest_pipeline_history_status with V3 functions

fix: Add missing uuid import

fix: Replace remaining _push_pipeline_history calls with _create_pipeline_record

fix: V3 migration issues - Auto-migrate old sessions and use Mistral for chat names

feat: Implement V3 S3 Architecture - Complete Refactor

Convert all POST API endpoints to use Form data for Swagger UI testing

feat: Unified pipeline lifecycle - single S3 file per pipeline - Pipeline now stored in S3 with pipeline_id at creation - Proposals stored in S3, only reference in MongoDB - Results appended to same S3 file on completion - Workflow save uses pipeline_id, works at any stage - pipelines_history now in session API response

feat: Display final_output_url in pipeline completion message - shows presigned S3 URL where all component outputs are stored with expiry time

feat: Add V3 API endpoints with file metadata - sessions list, history, and pipeline executions

fix: Add missing execution_id initialization

feat: Complete file upload V3 integration

feat: Implement remaining V3 architecture fixes

fix: Chat name generation now only happens once per session