* Update 'Require Approval' button description to clarify dependency on MemoryAgent
* Refine RequiredApproval message description
* Fix message description by removing unscaped character ('\')
* Break line
* docs: clarify and enhance the "Require Approval" description for Agent node
* chore: slight update of the description
* feat: Add option to disable conversation history
- Add new `disableConversationHistory` boolean parameter in LLMNodes.ts and Agent.ts to optionally skip including conversation history in prompts
- Fix potential error in Agent.ts when messages array is empty by adding null safety checks
- Improve memory efficiency by allowing stateless interactions when history isn't needed
* feat: add conversation history filtering options
Replace the disable conversation history feature with a more flexible filtering system that allows selecting:
- User question only
- Last message only
- All messages (default)
- No messages
This provides more granular control over conversation context management.
* chore: break lines
* chore: removed ending semi columns
* chore: fix eslint errors
* fix(sequentialagents): improve conversation history filtering logic
- Remove unnecessary state.messages check for user_question case
- Add proper null handling for last_message and all_messages cases
- Remove @ts-ignore comments with proper typing
* Update LLMNode.ts
* Update Agent.ts
---------
Co-authored-by: Henry Heng <henryheng@flowiseai.com>
* add functionality for full file uploads, add remove messages from view dialog and API
* add attachments swagger
* update question to include uploadedFilesContent
* make config dialog modal lg size
* Base changes for ServerSide Events (instead of socket.io)
* lint fixes
* adding of interface and separate methods for streaming events
* lint
* first draft, handles both internal and external prediction end points.
* lint fixes
* additional internal end point for streaming and associated changes
* return streamresponse as true to build agent flow
* 1) JSON formatting for internal events
2) other fixes
* 1) convert internal event to metadata to maintain consistency with external response
* fix action and metadata streaming
* fix for error when agent flow is aborted
* prevent subflows from streaming and other code cleanup
* prevent streaming from enclosed tools
* add fix for preventing chaintool streaming
* update lock file
* add open when hidden to sse
* Streaming errors
* Streaming errors
* add fix for showing error message
* add code interpreter
* add artifacts to view message dialog
* Update pnpm-lock.yaml
---------
Co-authored-by: Vinod Paidimarry <vinodkiran@outlook.in>
Henry Heng
Ahmed Rowaihi
Jean Ibarz