feat: introduce the LLM-based workflow copilot #4020
Merged
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
github-actions
bot
added
feature
dependencies
Contributor
Xiao-zhen-Liu
left a comment
Xiao-zhen-Liu
left a comment
There was a problem hiding this comment.
Left a few comments. Before I continue reviewing all the changes, I wonder if it is possible to make this into smaller PRs, e.g., you could introduce action plan in a separate PR.
frontend/src/app/workspace/service/workflow-graph/model/workflow-action.service.ts
Outdated
Show resolved
Hide resolved
Contributor
|
This PR is too big! Let's discuss whether we can decompose it and how. |
Contributor
|
@bobbai00 Please summarize the plan per our discussion. In the new PRs, include a architecture diagram and related screenshots. |
Contributor
Author
Xiao-zhen-Liu
requested changes
Nov 10, 2025
Contributor
Xiao-zhen-Liu
left a comment
Xiao-zhen-Liu
left a comment
There was a problem hiding this comment.
Tested and works well. Left some comments mainly for improving clarity.
I also think we should have a configuration flag for this feature. It would be even better if admins can turn it on / off dynamically.
...pp/workspace/component/workflow-editor/context-menu/context-menu/context-menu.component.html
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.ts
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-panel.component.ts
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-panel.component.ts
Show resolved
Hide resolved
...d/src/app/workspace/component/agent-panel/agent-registration/agent-registration.component.ts
Outdated
Show resolved
Hide resolved
Xiao-zhen-Liu
approved these changes
Nov 17, 2025
Contributor
Xiao-zhen-Liu
left a comment
Xiao-zhen-Liu
left a comment
There was a problem hiding this comment.
LGTM in general. Please fix the remaining minor issues, and add a flag to turn this feature on/off.
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.ts
Outdated
Show resolved
Hide resolved
...pp/workspace/component/workflow-editor/context-menu/context-menu/context-menu.component.html
Outdated
Show resolved
Hide resolved
aglinxinyuan
approved these changes
Nov 18, 2025
Contributor
aglinxinyuan
left a comment
aglinxinyuan
left a comment
There was a problem hiding this comment.
Left mirror comments. There is quite a bit of room to improve code quality, but it doesn’t affect functionality.
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.scss
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.scss
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.scss
Outdated
Show resolved
Hide resolved
frontend/src/app/workspace/component/agent-panel/agent-chat/agent-chat.component.scss
Show resolved
Hide resolved
- Remove unused isStopping() method from agent-chat.component.ts - Revert accidental formatting changes in context-menu.component.html
Reverts the global user-select style from 'text' back to 'none' to restore proper drag-and-drop functionality for operators in the operator menu. The 'user-select: text' change was making operators selectable, which interfered with the drag-and-drop interaction.
Adds a new 'copilotEnabled' configuration flag that allows administrators to enable/disable the AI copilot feature. The feature is disabled by default and can be controlled via the GUI_WORKFLOW_WORKSPACE_COPILOT_ENABLED environment variable. Changes: - Add copilot-enabled flag to gui.conf (default: false) - Add parsing logic in GuiConfig.scala - Add flag to ConfigResource API response - Add copilotEnabled to frontend GuiConfig type - Add default value in mock config service - Conditionally render agent-panel based on flag in workspace This addresses the PR feedback requesting a configuration flag that admins can use to turn the feature on/off dynamically.
bobbai00
changed the title
bobbai00
changed the title
bobbai00
changed the title
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
5 participants
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Please see this wiki page to learn how to enable this feature
What changes were proposed in this PR?
This PR introduces the LLM agent management & chat panel on the workflow workspace to help users with their workflows.
Demo
Manage agent using the panel
Ask agent questions regarding available Texera operators
Ask agent about users' current workflow
Architecture Diagram
See #4034
Major Changes
Frontend: introduce the agent management & chat panel
Backend:
litellmis introduced: which is a open source service that manages the communication between app and LLM APIsAccessControlServiceis modified: adding the logic for routinglitellmrelated requestsAny related issues, documentation, discussions?
Related to #4034
Current PR limitation and future PR plans
In current PR, the agent is only able to act in a "read-only" way, meaning it can only answer questions regarding operators, but couldn't change user's workflow.
In future PRs,
How was this PR tested?
Frontend unit test cases are added.
To test the PR e2e:
bin/litellm-config.yamlAccessControlServiceWas this PR authored or co-authored using generative AI tooling?
The code content is co-authored with Claude code. This PR is not generated by generative AI.