Spaces:
Runtime error
Runtime error
Commit History
-
Fix CrewAI compatibility and agent input parameter extraction
7ea9284 -
solved chatllm problems
2610f53
-
final commits
ff40840 -
Added fixed agent to agent communication
6df13ef
-
Fix: Update last_activity only for user messages
- Remove automatic last_activity updates from get_session() - Add update_activity parameter to update_session() - Only update last_activity when user messages are added - Viewing sessions/history no longer updates last_activity - Ensures session list shows true last interaction time6cb5907 -
Fix: Add missing generate_message_id function to schemas.py
b1206db
-
Refactor: Use MongoDB _id for messages, pipeline_id_index for components, standardize outputs to result:{text:{}} format
d6a6b32
-
feat: API response corrections - add message_id, component tracking, and error handling
- Added ID generation utilities (message_id, component_id, output_id) - Enhanced ComponentMetadata with component_output, hasError, and structured errors - Renamed result_preview to result in pipeline responses - Added hasError flag to ChatResponse model - Removed internal fields (current_file, pipeline_s3_key) from API responses - Updated session_manager to use generate_message_id() - Enhanced pipeline_manager with component tracking and error handling - Updated API routes to expose new response structures All changes are backward compatible. No database migration required.7c2e633
-
Update services/pipeline_executor.py
e6e087d
-
Update services/pipeline_executor.py
db5afca
-
feat: Implement V3 S3 Architecture - Complete Refactor
- S3 as single source of truth for conversations and pipelines - MongoDB stores metadata only (IDs, status, timestamps, S3 references) - Added conversation integrity validation (_validate_conversation_integrity) - Added pipeline integrity validation (_validate_pipeline_integrity) - Implemented pipeline lifecycle enforcement (ID creation before execution) - Added model attribution tracking (Bedrock/Mistral) - Implemented DELETE /sessions/{session_id} endpoint - Deleted 10 redundant/duplicate endpoints - Removed 900+ lines of legacy code - All changes comply with MasterLLM V3 Architecture Rules0f8c838
-
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
aaaba76
-
feat: Add V3 API endpoints with file metadata - sessions list, history, and pipeline executions
c4a01de -
fix: Chat name generation now only happens once per session
- Added check before calling chat name generation - Prevents multiple Bedrock API calls for same session - Fixes 'Failed to generate chat name' spam in logs - Chat name generates only after first user message if not already set2534de8 -
fix: Gracefully handle missing pipeline records in executor
- Check if pipeline record exists before creating S3 final output - Fall back to basic response if no pipeline record found - This allows executor to work with or without pipeline manager - Fixes 'Pipeline not found' error during execution40d8682 -
feat: Implement V3 Architecture - S3 + Normalized MongoDB
Major architectural refactor implementing V3 design: New Features: - S3 Manager: Upload/download with presigned URLs (7-day max expiry) - MongoDB Schemas: Pydantic models for 5 normalized collections - Pipeline Manager: Component tracking, S3 output storage - Workflow Manager: Save workflows without deduplication - Session Manager: Complete refactor with normalized schema + S3 Infrastructure: - services/s3_manager.py (411 lines) - services/schemas.py (321 lines) - services/pipeline_manager.py (412 lines) - services/workflow_manager.py (189 lines) Core Updates: - Refactored session_manager.py for normalized MongoDB + S3 - Integrated pipeline_executor.py with pipeline_manager - Updated api_routes_v2.py response models (removed history) New API Endpoints: - PUT /sessions/{id}/rename - POST /workflows/save - GET /workflows - GET /workflows/{id} - GET /files/{id}/url Bug Fixes: - Fixed max iteration error (better formula) - Prevented unwanted components in pipeline execution Breaking …f0db057
-
Update services/session_manager.py
2fc4e76
-
Update services/pipeline_executor.py
3cd5b75 -
making sure end page always greater than start page and in the same seeing getting the same value output even if the pipeline generated is different
5cf6369 -
Update services/pipeline_executor.py
fc6e06b -
Update services/pipeline_executor.py
4ee1ff0 -
Update services/pipeline_generator.py
310e8f9 -
Update services/intent_classifier.py
e3fee32 -
Create intent_classifier.py
d36787a
-
Update services/pipeline_executor.py
7482bb6 -
Update services/pipeline_executor.py
6427bef -
Update services/pipeline_executor.py
f1e4b62 -
langchain sends the reques in specific format and bedrock doesnt allow it, so the request doesnt reaches mistral and now manual calling
199576c -
Update services/pipeline_executor.py
c895fea -
Update services/pipeline_executor.py
d79e2c1 -
Update services/pipeline_executor.py
145565b -
Update services/pipeline_executor.py
f950b83 -
Update services/pipeline_executor.py
b19aecc -
Update services/pipeline_generator.py
79998e9 -
Update services/agent_langchain.py
a140d98 -
Update services/pipeline_executor.py
4294b7a -
Update services/pipeline_executor.py
5ce9404 -
Update services/pipeline_executor.py
7b081f4 -
Update services/pipeline_executor.py
d67e022 -
Update services/pipeline_executor.py
e56aeb3 -
Update services/session_manager.py
4a61db5 -
Update services/agent_langchain.py
6960794 -
Update services/master_tools.py
a3b18ea -
Update services/masterllm.py
22d9309 -
Update services/mcp_server.py
5f78432 -
Update services/pipeline_executor.py
4555a81 -
Update services/pipeline_generator.py
a955a4b
-
Update services/agent_crewai.py
dc7a501 -
Update services/agent_crewai.py
f55317e -
Update services/agent_crewai.py
dd0b012