Migrates LLM model metadata and cost configuration from static code to a dynamic database-driven registry. Adds new backend modules for LLM registry and model types, updates block and cost configuration logic to fetch model info and costs from the database, and ensures block schemas and UI options reflect enabled/disabled models. This enables dynamic management of LLM models and costs via the admin UI and database migrations.
## Changes 🏗️
Update the new library agent page, empty view to look like:
<img width="900" height="1060" alt="Screenshot 2025-12-01 at 14 12 10"
src="https://github.com/user-attachments/assets/e6a22a4f-35f4-434e-bbb1-593390034b9a"
/>
Now we display an **About this agent** card on the left when the agent
is published on the marketplace. I expanded the:
```
/api/library/agents/{id}
```
endpoint to return as well the following:
```js
{
// ...
created_at: "timestamp",
marketplace_listing: {
creator: { name: "string", "slug": string, id: "string" },
name: "string",
slug: "string",
id: "string"
}
}
```
To be able to display this extra information on the card and link to the
creator and marketplace pages.
Also:
- design system updates regarding navbar and colors
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run locally and see the new page for an agent with no runs
We want to allow external tools to explore the marketplace and use the
chat agent tools
### Changes 🏗️
- add store api routes
- add tool api routes
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] tested all endpoints work
---------
Co-authored-by: Copilot Autofix powered by AI <62310815+github-advanced-security[bot]@users.noreply.github.com>
## Changes 🏗️
Update tokens of the design system with new values 🖌️🎨
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Storybook build passes, no type errors
This PR improves the user experience by defaulting the node output
accordion to an expanded state. Previously, users had to manually expand
the accordion to view execution results, which added an unnecessary
click to the workflow. With this change, output data is immediately
visible when available, allowing users to quickly see the results of
their node executions. The ability to collapse the accordion is
preserved for users who prefer a more compact interface.
### Changes 🏗️
- **Changed default state of node output accordion**: The node output
section now defaults to expanded (`isExpanded = true`) instead of
collapsed
- **Improved user experience**: Users can now immediately see node
execution results without needing to manually expand the accordion
- **Maintains collapse functionality**: Users can still manually
collapse the accordion if they prefer a more compact view
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Execute a node and verify the output accordion is expanded by
default
- [x] Verify output data is immediately visible after node execution
- [x] Test that the accordion can still be manually collapsed
- [x] Confirm the accordion state resets to expanded when switching
between nodes
- [x] Test with different types of output data (simple values, objects,
arrays)
This PR implements a minimum movement threshold of 50 pixels for node
position changes before they are logged to the history system. This
prevents the undo/redo history from being cluttered with minor,
unintentional movements that occur when users interact with block inputs
or accidentally nudge nodes.
### Changes 🏗️
- **Added movement threshold for history tracking**: Implemented a 50px
minimum movement requirement before logging node position changes to
history
- **Prevents history spam**: Stops small, unintentional movements (like
clicking on inputs inside blocks) from cluttering the undo/redo history
- **Tracks drag start positions**: Maintains initial positions when
dragging begins to accurately calculate total movement distance
- **Improved history management**: Only significant node movements are
now recorded, matching the behavior of the old builder
- **Memory efficient**: Cleans up tracked positions after drag
operations complete
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Drag a node less than 50px and verify no history entry is created
- [x] Drag a node more than 50px and verify history entry is created
- [x] Click on inputs inside blocks and verify no history entries are
created
- [x] Test undo/redo functionality works correctly with the threshold
- [x] Verify adding/removing nodes still creates history entries
- [x] Test multiple nodes being dragged simultaneously
This PR addresses the need for better user awareness when building
trigger-based agents. When a user adds webhook/trigger nodes to their
flow, a prominent banner now appears at the bottom of the builder
informing them they're creating a "Trigger Agent" and providing a direct
link to monitor its activity in the Agent Library.
### Changes 🏗️
- **Added TriggerAgentBanner component**: New banner that displays at
the bottom of the builder when the flow contains webhook/trigger nodes
- **Implemented webhook node detection**: Added `hasWebhookNodes` method
to nodeStore that checks if any nodes are of type WEBHOOK or
WEBHOOK_MANUAL
- **Conditional banner display**: Builder now shows TriggerAgentBanner
instead of BuilderActions when webhook nodes are present
- **Dynamic library link**: Banner includes a link to the specific agent
in the library (if found) or defaults to the general library page
- **Integrated with existing flow context**: Uses the current flowID to
fetch the corresponding library agent for proper linking
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Add a webhook node to a flow and verify the banner appears
- [x] Remove all webhook nodes and verify the banner disappears
- [x] Test with both WEBHOOK and WEBHOOK_MANUAL node types
- [x] Click the library link and verify it navigates to the correct
agent page
- [x] Test library link fallback when agent is not found in library
- [x] Verify banner styling and positioning at bottom center of builder
This PR fixes issue where edges were not being copied when selecting
multiple nodes with Shift+Select.
### Changes 🏗️
- **Fixed edge copying logic**: Removed the requirement for edges to be
explicitly selected - now automatically includes all edges between
selected nodes when copying
- **Migrated to custom stores**: Refactored copy-paste functionality to
use `useNodeStore` and `useEdgeStore` instead of ReactFlow's built-in
state management
- **Improved type safety**: Replaced generic `Node` and `Edge` types
with `CustomNode` and `CustomEdge` for better type checking
- **Enhanced paste behavior**:
- Deselects existing nodes before pasting to ensure only pasted nodes
are selected
- Uses store methods for adding nodes and edges, ensuring proper state
management
- **Simplified node data handling**: Removed manual clearing of
backend_id, status, and nodeExecutionResult - now handled by the store's
addNode method
- **Added debugging support**: Added console logging for copied data to
aid in troubleshooting
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Select multiple nodes using Shift+Select and copy with Ctrl/Cmd+C
- [x] Verify edges between selected nodes are included in the copy
- [x] Paste with Ctrl/Cmd+V and confirm both nodes and edges appear
- [x] Verify pasted elements maintain correct connections
- [x] Confirm only pasted nodes are selected after paste
- [x] Test that pasted nodes have unique IDs
- [x] Verify pasted nodes appear centered in the current viewport
This PR fixes an issue where undefined `customized_name` values were
being included in node metadata, which could cause issues with data
persistence and agent exports. The fix ensures that the
`customized_name` property is only included when it has been explicitly
set by the user.
### Changes 🏗️
- **Fixed metadata serialization**: Modified `getNodeAsGraphNode` to
only include `customized_name` in the metadata when it has been
explicitly set (not undefined)
- **Improved data structure**: Uses object spread syntax to
conditionally include the `customized_name` property, preventing
undefined values from being stored
- **Cleaned up code**: Removed unnecessary TODO comment and improved
code readability
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create a new agent and verify metadata doesn't include undefined
customized_name
- [x] Customize a block name and verify it's properly saved in metadata
- [x] Export an agent and verify the JSON doesn't contain undefined
customized_name fields
- [x] Import an agent with customized names and verify they are
preserved
- [x] Save and reload an agent to ensure metadata persistence works
correctly
This PR enables users to add agents directly to the builder from search
results and marketplace views. Previously, users had to navigate to
different sections to add agents - now they can do it with a single
click from wherever they find the agent. The change includes proper
loading states, error handling, and success notifications to provide a
smooth user experience.
### Changes 🏗️
- **Added direct agent-to-builder functionality**: Users can now add
agents directly to the builder from search results and marketplace views
- **Created reusable hook `useAddAgentToBuilder`**: Centralized logic
for adding both library and marketplace agents to the builder
- **Enhanced search results interaction**: Added click handlers and
loading states to agent cards in search results
- **Improved marketplace agent addition**: Marketplace agents are now
added to both library and builder with proper feedback
- **Added loading states**: Visual feedback when agents are being added
(loading spinners on cards)
- **Improved error handling**: Added toast notifications for success and
failure cases with descriptive error messages
- **Added Sentry error tracking**: Captures exceptions for better
debugging in production
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Search for agents and add them to builder from search results
- [x] Add marketplace agents which should appear in both library and
builder
- [x] Verify loading states appear during agent addition
- [x] Test error scenarios (network failure, invalid agent)
- [x] Confirm toast notifications appear for both success and error
cases
- [x] Verify builder viewport centers on newly added agent
## Changes 🏗️
Re-arrange the folder structure of the new Library page sub-components
so they are grouped by location:
### Before
<img width="238" height="506" alt="Screenshot 2025-11-27 at 23 45 27"
src="https://github.com/user-attachments/assets/429fda6e-bf74-4d80-9306-028365789ca1"
/>
All components where on a single level, which works fine for simpler
pages without that many sub-components, but on this one which has so
much functionality it ends up messier...
### After
<img width="226" height="517" alt="Screenshot 2025-11-27 at 23 45 46"
src="https://github.com/user-attachments/assets/99c098ea-ff11-4779-bad8-7d524bf91605"
/>
### Imports order
I edited some files, and the linter/formatter automatically sorted
import order as per the lint plugin.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run the new library agent page locally and click around
## Summary
This PR implements a comprehensive Human In The Loop (HITL) block that
allows agents to pause execution and wait for human
approval/modification of data before continuing.
https://github.com/user-attachments/assets/c027d731-17d3-494c-85ca-97c3bf33329c
## Key Features
- Added WAITING_FOR_REVIEW status to AgentExecutionStatus enum
- Created PendingHumanReview database table for storing review requests
- Implemented HumanInTheLoopBlock that extracts input data and creates
review entries
- Added API endpoints at /api/executions/review for fetching and
reviewing pending data
- Updated execution manager to properly handle waiting status and resume
after approval
## Frontend Components
- PendingReviewCard for individual review handling
- PendingReviewsList for multiple reviews
- FloatingReviewsPanel for graph builder integration
- Integrated review UI into 3 locations: legacy library, new library,
and graph builder
## Technical Implementation
- Added proper type safety throughout with SafeJson handling
- Optimized database queries using count functions instead of full data
fetching
- Fixed imports to be top-level instead of local
- All formatters and linters pass
## Test plan
- [ ] Test Human In The Loop block creation in graph builder
- [ ] Test block execution pauses and creates pending review
- [ ] Test review UI appears in all 3 locations
- [ ] Test data modification and approval workflow
- [ ] Test rejection workflow
- [ ] Test execution resumes after approval
🤖 Generated with [Claude Code](https://claude.ai/code)
<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->
## Summary by CodeRabbit
* **New Features**
* Added Human-In-The-Loop review workflows to pause executions for human
validation.
* Users can approve or reject pending tasks, optionally editing
submitted data and adding a message.
* New "Waiting for Review" execution status with UI indicators across
run lists, badges, and activity views.
* Review management UI: pending review cards, list view, and a floating
reviews panel for quick access.
<!-- end of auto-generated comment: release notes by coderabbit.ai -->
---------
Co-authored-by: Claude <noreply@anthropic.com>
### 🏗️ Changes
This PR adds a Google Drive Picker field type to enhance the user
experience of existing Google blocks, replacing manual file ID entry
with a visual file picker.
#### Backend Changes
- **Added and types** in :
- Configurable picker field with OAuth scope management
- Support for multiselect, folder selection, and MIME type filtering
- Proper access token handling for file downloads
- **Enhanced Gmail blocks**: Updated attachment fields to use Google
Drive Picker for better UX
- **Enhanced Google Sheets blocks**: Updated spreadsheet selection to
use picker instead of manual ID entry
- **Added utility**: Async file download with virus scanning and 100MB
size limit
#### Frontend Changes
- **Enhanced GoogleDrivePicker component**: Improved UI with folder icon
and multiselect messaging
- **Integrated picker in form renderers**: Auto-renders for fields with
format
- **Added shared GoogleDrivePickerInput component**: Eliminates code
duplication between NodeInputs and RunAgentInputs
- **Added type definitions**: Complete TypeScript support for picker
schemas and responses
#### Key Features
- 🎯 **Visual file selection**: Replace manual Google Drive file ID entry
with intuitive picker
- 📁 **Flexible configuration**: Support for documents, spreadsheets,
folders, and custom MIME types
- 🔒 **Minimal OAuth scopes**: Uses scope for security (only access to
user-selected files)
- ⚡ **Enhanced UX**: Seamless integration in both block configuration
and agent run modals
- 🛡️ **Security**: Virus scanning and file size limits for downloaded
attachments
#### Migration Impact
- **Backward compatible**: Existing blocks continue to work with manual
ID entry
- **Progressive enhancement**: New picker fields provide better UX for
the same functionality
- **No breaking changes**: all existing blocks should be unaffected
This enhancement improves the user experience of Google blocks without
introducing new systems or breaking existing functionality.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x]Test multiple of the new blocks [of note is that the create
spreadsheet block should be not used for now as it uses api not drive
picker]
- [x] chain the blocks together and pass values between them
---------
Co-authored-by: Lluis Agusti <hi@llu.lu>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
Co-authored-by: Claude <noreply@anthropic.com>
## Changes 🏗️
Addresses this code scanning alert
[security/code-scanning/156](https://github.com/Significant-Gravitas/AutoGPT/security/code-scanning/156)
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] No prototype pollution
## Changes 🏗️
Show spinners on the login/logout buttons while they are being
processed.
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Login with password: there is a spinner on the button while
logging in
- [x] Logout: there is a spinner on the button while logging out
### Changes 🏗️
<img width="1490" height="432" alt="Screenshot 2025-11-24 at 23 26 12"
src="https://github.com/user-attachments/assets/e5a149f2-7751-4276-9b76-707db7afdd46"
/>
The agent output buttons on the new run page weren't always clickable
due to a missing `z-index`.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Login
- [x] Open run in new runs page
- [x] Ouput buttons are clickable without issues
## Changes 🏗️
Change the favicon colour in the tab depending on the environment, so
when you have multiple tabs open (production, staging, local... ) it is
clear which map to what.
### Local ( orange )
<img width="257" height="40" alt="Screenshot 2025-11-24 at 22 38 27"
src="https://github.com/user-attachments/assets/705ddf6b-cc4a-498a-ad15-ed2c60f6b397"
/>
### Dev ( green )
<img width="263" height="40" alt="Screenshot 2025-11-24 at 22 45 20"
src="https://github.com/user-attachments/assets/eda3ba16-8646-4032-ad3c-7a8fc4db778c"
/>
### Example
<img width="513" height="41" alt="Screenshot 2025-11-24 at 22 45 09"
src="https://github.com/user-attachments/assets/1a43f860-536a-465e-9c10-a68c5218a58c"
/>
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Load the app and the favicon colour matches the env
## Changes 🏗️
Add some missing page titles, most importantly the missing one the new
runs page.
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run the app
- [x] Page titles are there
## Changes 🏗️
When the user is logged in and tries to navigate to `/login` or
`/signup` manually, redirect them away to `/marketplace`.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Login
- [x] Go to `/login` or `/signup`
- [x] You are redirected back into `/marketplace`
This PR introduces several improvements to the new builder experience:
**1. Agent Outputs Feature** ✨
- Implemented a new `AgentOutputs` component that displays execution
outputs from OUTPUT blocks
- Added a slide-out sheet UI to view agent outputs with proper
formatting
- Integrated with existing output renderers from the library view
- Shows output block names, descriptions, and rendered values
- Added beta badge to indicate feature is still experimental
**2. UI/UX Improvements** 🎨
- Fixed graph loading spinner color from violet to neutral zinc for
better consistency
- Adjusted node shadow styling for better visual hierarchy (reduced
shadow when not selected)
- Fixed credential field button spacing to prevent layout overflow
- Improved array editor widget delete button positioning
- Added proper link handling for integration redirects (opens in new
tab)
- Fixed object editor to handle null values gracefully
**3. Performance & State Management** 🚀
- Fixed race condition in run input dialog by awaiting execution before
closing
- Added proper history initialization after graph loads
- Added `outputSchema` to graph store for tracking output blocks
- Fixed search bar to maintain query state properly
- Added automatic fit view on graph load for better initial viewport
**4. Build Actions Bar** 🔧
- Reduced padding for more compact appearance
- Enabled/disabled Agent Outputs button based on presence of output
blocks
- Removed loading icon from manual run button when not executing
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Created and executed an agent with OUTPUT blocks to verify outputs
display correctly
- [x] Tested output viewer with different data types (text, JSON,
images, etc.)
- [x] Verified credential field layouts don't overflow in constrained
spaces
- [x] Tested array editor delete functionality and button positioning
- [x] Confirmed graph loads with proper fit view and history
initialization
- [x] Tested run input dialog closes only after execution starts
- [x] Verified integration links open in new tabs
- [x] Tested object editor with null values
## Changes 🏗️
<img width="900" height="757" alt="Screenshot 2025-11-19 at 12 18 38"
src="https://github.com/user-attachments/assets/e2c2a4cf-a05e-431e-853d-fb0a68729e54"
/>
When the dev environment is used for a PR preview, show a banner at the
top of the page to indicate this.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create a PR preview against Dev
- [x] Check it shows the banner once this is merged
- [x] Or try locally with the env var set
### For configuration changes:
`NEXT_PUBLIC_PREVIEW_STEALING_DEV` is set programmatically via our Infra
CI.
This PR introduces several performance and user experience improvements
to the new builder, focusing on node positioning, state management
optimizations, and visual enhancements.
The new builder had several issues that impacted developer experience
and runtime performance:
- Inefficient store subscriptions causing unnecessary re-renders
- No intelligent node positioning when adding blocks via clicking
- useEffect dependencies causing potential stale closures
- Width constraints missing on form fields affecting layout consistency
### Changes 🏗️
#### Performance Optimizations
- **Store subscription optimization**: Added `useShallow` from zustand
to prevent unnecessary re-renders in
[NodeContainer](file:///app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/NodeContainer.tsx)
and
[NodeExecutionBadge](file:///app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/NodeExecutionBadge.tsx)
- **useEffect cleanup**: Split combined useEffects in
[useFlow](file:///app/(platform)/build/hooks/useFlow.ts) for clearer
dependencies and better performance
- **Memoization**: Added `memo` to
[NewControlPanel](file:///app/(platform)/build/components/NewControlPanel/NewControlPanel.tsx)
to prevent unnecessary re-renders
- **Callback optimization**: Wrapped `onDrop` handler in `useCallback`
to prevent recreation on every render
#### UX Improvements
- **Smart node positioning**: Implemented `findFreePosition` algorithm
in [helper.ts](file:///app/(platform)/build/components/helper.ts) that:
- Automatically finds non-overlapping positions for new nodes
- Tries right, left, then below existing nodes
- Falls back to far-right position if no space available
- **Click-to-add blocks**: Added click handlers to blocks that:
- Add the block at an intelligent position
- Automatically pan viewport to center the new node with smooth
animation
- **Visual feedback**: Added loading state with spinner icon for agent
blocks during fetch
- **Form field width**: Added `max-w-[340px]` constraint to prevent
overflow in
[FieldTemplate](file:///components/renderers/input-renderer/templates/FieldTemplate.tsx)
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create from scratch and execute an agent with at least 3 blocks
- [x] Test adding blocks via drag-and-drop ensures no overlapping
- [x] Test adding blocks via click positions them intelligently
- [x] Test viewport animation when adding blocks via click
- [x] Import an agent from file upload, and confirm it executes
correctly
- [x] Test loading spinner appears when adding agents from "My Agents"
- [x] Verify performance improvements by checking React DevTools for
reduced re-renders
## Summary
Implement comprehensive parameterization of the activity status
generation system to enable custom prompts for admin analytics
dashboard.
## Changes Made
### Core Function Enhancement (`activity_status_generator.py`)
- **Extract hardcoded prompts to constants**: `DEFAULT_SYSTEM_PROMPT`
and `DEFAULT_USER_PROMPT`
- **Add prompt parameters**: `system_prompt`, `user_prompt` with
defaults to maintain backward compatibility
- **Template substitution system**: User prompt supports
`{{GRAPH_NAME}}` and `{{EXECUTION_DATA}}` placeholders
- **Skip existing flag**: `skip_existing` parameter allows admin to
force regeneration of existing data
- **Maintain manager compatibility**: All existing calls continue to
work with default parameters
### Admin API Enhancement (`execution_analytics_routes.py`)
- **Custom prompt fields**: `system_prompt` and `user_prompt` optional
fields in `ExecutionAnalyticsRequest`
- **Skip existing control**: `skip_existing` boolean flag for admin
regeneration option
- **Template documentation**: Clear documentation of placeholder system
in field descriptions
- **Backward compatibility**: All existing API calls work unchanged
### Template System Design
- **Simple placeholder replacement**: `{{GRAPH_NAME}}` → actual graph
name, `{{EXECUTION_DATA}}` → JSON execution data
- **No dependencies**: Uses simple `string.replace()` for maximum
compatibility
- **JSON safety**: Execution data properly serialized as indented JSON
- **Validation tested**: Template substitution verified to work
correctly
## Key Features
### For Regular Users (Manager Integration)
- **No changes required**: Existing manager.py calls work unchanged
- **Default behavior preserved**: Same prompts and logic as before
- **Feature flag compatibility**: LaunchDarkly integration unchanged
### For Admin Analytics Dashboard
- **Custom system prompts**: Admins can override the AI evaluation
criteria
- **Custom user prompts**: Admins can modify the analysis instructions
with execution data templates
- **Force regeneration**: `skip_existing=False` allows reprocessing
existing executions with new prompts
- **Complete model list**: Access to all LLM models from `llm.py` (70+
models including GPT, Claude, Gemini, etc.)
## Technical Validation
- ✅ Template substitution tested and working
- ✅ Default behavior preserved for existing code
- ✅ Admin API parameter validation working
- ✅ All imports and function signatures correct
- ✅ Backward compatibility maintained
## Use Cases Enabled
- **A/B testing**: Compare different prompt strategies on same execution
data
- **Custom evaluation**: Tailor success criteria for specific graph
types
- **Prompt optimization**: Iterate on prompt design based on admin
feedback
- **Bulk reprocessing**: Regenerate activity status with improved
prompts
## Testing
- Template substitution functionality verified
- Function signatures and imports validated
- Code formatting and linting passed
- Backward compatibility confirmed
## Breaking Changes
None - all existing functionality preserved with default parameters.
## Related Issues
Resolves the requirement to expose prompt customization on the frontend
execution analytics dashboard.
---------
Co-authored-by: Claude <noreply@anthropic.com>
The rfjs library was throwing validation errors for our custom format
types `short-text` and `long-text` because these are not standard JSON
Schema formats. This was causing form validation to fail even though
these formats are valid in our application context.
<img width="792" height="85" alt="Screenshot 2025-11-18 at 9 39 08 AM"
src="https://github.com/user-attachments/assets/c75c584f-b991-483c-8779-fc93877028e0"
/>
### Changes 🏗️
- Created a custom validator using `@rjsf/validator-ajv8`'s
`customizeValidator` function
- Added support for `short-text` and `long-text` custom formats that
accept any string value
- Replaced the default validator with our custom validator in the
FormRenderer component
- Disabled strict mode and format validation in AJV options to prevent
validation errors for non-standard formats
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create an agent with input blocks that use short-text format
- [x] Create an agent with input blocks that use long-text format
- [x] Execute the agent and verify no validation errors appear
- [x] Verify that form submission works correctly with both formats
- [x] Test that other standard formats (email, URL, etc.) still work as
expected
- depends on https://github.com/Significant-Gravitas/AutoGPT/pull/11368
This PR adds the ability to rename nodes directly in the flow editor by
double-clicking on their titles.
https://github.com/user-attachments/assets/1de3fc5c-f859-425e-b4cf-dfb21c3efe3d
### Changes 🏗️
- **Added inline node title editing functionality:**
- Users can now double-click on any node title to enter edit mode
- Custom titles are saved on Enter key or blur, canceled on Escape key
- Custom node names are persisted in the node's metadata as
`customized_name`
- Added tooltip to display full title when text is truncated
- **Modified node data handling:**
- Updated `nodeStore` to include `customized_name` in metadata when
converting nodes
- Modified `helper.ts` to pass metadata (including custom titles) to
custom nodes
- Added metadata property to `CustomNodeData` type
- **UI improvements:**
- Added hover cursor indication for editable titles
- Implemented proper focus management during editing
- Maintained consistent styling between display and edit modes
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Double-click on various node types to enter edit mode
- [x] Type new names and press Enter to save
- [x] Press Escape to cancel editing and revert to original name
- [x] Click outside the input field to save changes
- [x] Verify custom names persist after page refresh
- [x] Test with long node names to ensure tooltip appears
- [x] Verify custom names are saved with the graph
- [x] Test editing on all node types (standard, input, output, webhook,
etc.)
- Resolves#11390
This unbreaks the last step of the Builder tutorial :)
### Changes 🏗️
- Give `isSaving` time to propagate before calling dependent callback
`saveAndRun`
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run through Builder tutorial; Run (with implicit save) should work
at once
## Changes 🏗️
Fixed the logout errors by removing duplicate redirects. `serverLogout`
was calling `redirect("/login")` (which throws `NEXT_REDIRECT`), and
then `useSupabaseStore` was also calling `router.refresh()`, causing
conflicts.
Updated `serverLogout` to return a result object instead of redirecting,
and moved the redirect to the client using `router.push("/login")` after
logout completes. This removes the `NEXT_REDIRECT` error and ensures a
single redirect.
<img width="800" height="706" alt="Screenshot 2025-11-18 at 16 14 54"
src="https://github.com/user-attachments/assets/38e0e55c-f48d-4b25-a07b-d4729e229c70"
/>
Also addressed 401 errors during logout. Hooks like `useCredits` were
still making API calls after logout, causing "Authorization header is
missing" errors. Added a check in `_makeClientRequest` to detect
logout-in-progress and suppress authentication errors during that
window. This prevents console noise and avoids unnecessary error
handling.
<img width="800" height="742" alt="Screenshot 2025-11-18 at 16 14 45"
src="https://github.com/user-attachments/assets/6fb2270a-97a0-4411-9e5a-9b4b52117af3"
/>
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Log out of your account
- [x] There are no errors showing up on the browser devtools
This refactor improves developer experience (DX) by creating a more
maintainable and extensible architecture.
The previous `CustomNode` implementation had several issues:
- Code was duplicated across different node types (StandardNodeBlock,
OutputBlock, etc.)
- Poor separation of concerns with all logic in a single component
- Limited flexibility for handling different block types
- Inconsistent handle display logic across different node types
<img width="2133" height="831" alt="Screenshot 2025-11-12 at 9 25 10 PM"
src="https://github.com/user-attachments/assets/02864bba-9ffe-4629-98ab-1c43fa644844"
/>
## Changes 🏗️
- **Refactored CustomNode structure**:
- Extracted reusable components:
[`NodeContainer`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/NodeContainer.tsx),
[`NodeHeader`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/NodeHeader.tsx),
[`NodeAdvancedToggle`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/NodeAdvancedToggle.tsx),
[`WebhookDisclaimer`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/WebhookDisclaimer.tsx)
- Removed `StandardNodeBlock.tsx` and consolidated logic into
[`CustomNode.tsx`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/CustomNode.tsx)
- Moved
[`StickyNoteBlock`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/FlowEditor/nodes/CustomNode/components/StickyNoteBlock.tsx)
to components folder for better organization
- **Added BlockUIType-specific logic**:
- Implemented conditional handle display based on block type (INPUT,
WEBHOOK, WEBHOOK_MANUAL blocks don't show handles)
- Added special handling for AGENT blocks with dynamic input/output
schemas
- Added webhook-specific disclaimer component with library agent
integration
- Fixed OUTPUT block's name field to not show input handle
- **Enhanced FormCreator**:
- Added `showHandles` prop for granular control
- Added `className` prop for styling flexibility (used for webhook
opacity)
- **Improved nodeStore**:
- Added `getNodeBlockUIType` method for retrieving node UI types
- **UI/UX improvements**:
- Fixed duplicate gap classes in
[`BuilderActions`](file:///Users/abhi/Documents/AutoGPT/autogpt_platform/frontend/src/app/(platform)/build/components/BuilderActions/BuilderActions.tsx)
- Added proper styling for webhook blocks (disabled state with reduced
opacity)
- Improved field template spacing for specific block types
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create and test a standard node block with input/output handles
- [x] Create and test INPUT block (verify no input handles)
- [x] Create and test OUTPUT block (verify name field has no handle)
- [x] Create and test WEBHOOK block (verify disclaimer appears and form
is disabled)
- [x] Create and test AGENT block with custom schemas
- [x] Create and test sticky note block
- [x] Verify advanced toggle works for all node types
- [x] Test node execution badges display correctly
- [x] Verify node selection highlighting works
Currently when an agent fails validation during a scheduled run, we
raise an error then try again, regardless of why.
This change removed the agent schedule and notifies the user
### Changes 🏗️
- add schedule_id to the GraphExecutionJobArgs
- add agent_name to the GraphExecutionJobArgs
- Delete schedule on GraphValidationError
- Notify the user with a message that include the agent name
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] I have ensured the scheduler tests work with these changes
This PR removes turnstile from the platform.
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Test to make sure that turnstile is gone, it will be.
- [x] Test logging in with out turnstile to make sure it still works
- [x] Test registering a new account with out turnstile and it works
## Summary
- Replaced the question mark icon with explicit "Give Feedback" text in
the feedback button
- Applied consistent styling to match the "Tutorial" button
- Removed QuestionMarkCircledIcon dependency from TallyPopup component
## Motivation
Users reported not knowing what the question mark icon was for, which
prevented them from discovering the feedback feature. Making the button
text-based and explicit removes this confusion.
## Changes
- Removed `QuestionMarkCircledIcon` import and icon element
- Changed button to display only "Give Feedback" text
- Added consistent styling (height, rounded corners, background color)
to match Tutorial button
- Button text can wrap to two lines if needed for better readability
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Check the UI to see that the question mark on the tally button has
been replaced with "Give Feedback"
Before
<img width="618" height="198" alt="image"
src="https://github.com/user-attachments/assets/0d4803eb-9a05-4a43-aaff-cc43b6d0cda4"
/>
After
<img width="298" height="126" alt="image"
src="https://github.com/user-attachments/assets/c1e1c3b5-94b4-4ad9-87e9-a0feca1143e3"
/>
---------
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
## Summary
Adds a non-blocking warning banner to Login and Sign Up pages that
alerts mobile users about potential limitations in the mobile
experience.
## Changes
- Created `MobileWarningBanner` component in `src/components/auth/`
- Integrated banner into Login page (`/login`)
- Integrated banner into Sign Up page (`/signup`)
- Banner displays only on mobile devices (viewports < 768px)
- Uses existing `useBreakpoint` hook for responsive detection
## Design Details
- **Position**: Appears below the login/signup card (after the bottom
"Sign up"/"Log in" links)
- **Style**: Amber-themed warning banner with DeviceMobile icon
- **Message**:
- Title: "Heads up: AutoGPT works best on desktop"
- Description: "Some features may be limited on mobile. For the best
experience, consider switching to a desktop."
- **Behavior**: Non-blocking, no user interaction required
<img width="342" height="81" alt="image"
src="https://github.com/user-attachments/assets/b6584299-b388-4d8d-b951-02bd95915566"
/>
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Verified banner appears on mobile viewports (< 768px)
- [x] Verified banner is hidden on desktop viewports (≥ 768px)
- [x] Tested on Login page
- [x] Tested on Sign Up page
<img width="342" height="758" alt="image"
src="https://github.com/user-attachments/assets/077b3e0a-ab9c-41c7-83b7-7ee80a3396fd"
/>
<img width="342" height="759" alt="image"
src="https://github.com/user-attachments/assets/77a64b28-748b-4d97-bd7c-67c55e5e9f22"
/>
---------
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
## Changes 🏗️
### Issue 1: login/signup redirect conflict
There are 2 hooks, both on the login and signup pages, that attempt to
call `router.push` once a user logs in or is created.
The main offender seems to be this hook:
```tsx
useEffect(() => {
if (user) router.push("/");
}, [user]);
```
Which is in place on both pages to prevent logged-in users from
accessing `/login` or `/signup`. What happens is when a user signs up or
logs in, if they need onboarding, there is a `router.push` down the line
to redirect them there, which conflicts with the one done in this hook.
**Solution**
I moved the logic from that hook to the `middleware.ts`, which is a
better place for it... It won't conflict anymore with onboarding
redirects done in those pages
### Issue 2: onboarding server redirects
Potential race condition: both the server component and the client
`<OnboardingProvider />` perform redirects. The server component
redirects happen first, but if onboarding state changes after mount, the
provider can redirect again, causing rapid mount/unmount cycles.
**Solution**
Make all onboarding redirects central in `/onboarding` which is now a
client component do in client redirects only and displaying a spinner
while it does so.
## Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Tested locally login/logout/signup and trying to access `/login`
and `/signup` being logged in
<!-- Clearly explain the need for these changes: -->
This PR enhances the visual feedback in the flow editor by adding
animated "beads" that travel along edges during execution. This provides
users with clear, real-time visualization of data flow and execution
progress through the graph, making it easier to understand which
connections are active and track execution state.
https://github.com/user-attachments/assets/df4a4650-8192-403f-a200-15f6af95e384
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
- **Added new edge data types and structure:**
- Added `CustomEdgeData` type with `isStatic`, `beadUp`, `beadDown`, and
`beadData` properties
- Created `CustomEdge` type extending XYEdge with custom data
- **Implemented bead animation components:**
- Added `JSBeads.tsx` - JavaScript-based animation component with
real-time updates
- Added `SVGBeads.tsx` - SVG-based animation component (for future
consideration)
- Added helper functions for path calculations and bead positioning
- **Updated edge rendering:**
- Modified `CustomEdge` component to display beads during execution
- Added static edge styling with dashed lines (`stroke-dasharray: 6`)
- Improved visual hierarchy with different stroke styles for
selected/unselected states
- **Refactored edge management:**
- Converted `edgeStore` from using `Connection` type to `CustomEdge`
type
- Added `updateEdgeBeads` and `resetEdgeBeads` methods for bead state
management
- Updated `copyPasteStore` to work with new edge structure
- **Added support for static outputs:**
- Added `staticOutput` property to `CustomNodeData`
- Static edges show continuous bead animation while regular edges show
one-time animation
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Create a flow with multiple blocks and verify beads animate along
edges during execution
- [x] Test that beads increment when execution starts (`beadUp`) and
decrement when completed (`beadDown`)
- [x] Verify static edges display with dashed lines and continuous
animation
- [x] Confirm copy/paste operations preserve edge data and bead states
- [x] Test edge animations performance with complex graphs (10+ nodes)
- [x] Verify bead animations complete properly before disappearing
- [x] Test that multiple beads can animate on the same edge for
concurrent executions
- [x] Verify edge selection/deletion still works with new visualization
- [x] Test that bead state resets properly when starting new executions
## Changes 🏗️
- Clear backend_id when pasting blocks to prevent duplicate ID errors
- Add copy/paste functionality to new FlowEditor
- Ensure pasted blocks use newly generated UUIDs when saving
Fixes issue where copying and pasting blocks would fail with 'Unique
constraint failed' error because the old backend_id was being reused
instead of the new node ID.
## Checklist 📋
### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Add any block to the builder, save and run the graph and wait for
it to finish, then copy and paste the first block and paste it, try to
use it and it should now work and not have any issues/errors
https://github.com/user-attachments/assets/c24f9a9a-8e4f-4988-8731-cddc34a0da13
---------
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
Use WebSocket notifications from the backend to display confetti.
### Changes 🏗️
- Send WebSocket notifications to the browser when new onboarding steps
are completed
- Handle WebSocket notifications events in the Wallet and use them
instead of frontend-based logic to play confetti (fixes confetti
appearing on every refresh)
- Scroll to newly completed tasks when wallet opens just before confetti
plays
- Fix: make `Run again` button complete `RE_RUN_AGENT` task
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Confetti are displayed when previously uncompleted tasks are
completed
- [x] Confetti do not appear on page refresh
- [x] Wallet scrolls on open before confetti is displayed
- [x] `Run again` button completes `RE_RUN_AGENT` task
This PR fixes a flaky test issue in the signup flow where Playwright's
strict mode was failing due to duplicate heading elements on the
marketplace page.
### Problem
The test was failing intermittently with the following error:
```
Error: strict mode violation: getByText('Bringing you AI agents designed by thinkers from around the world') resolved to 2 elements
```
This occurred because the marketplace page contains two identical `<h3>`
elements with the same text, causing Playwright's strict mode to throw
an error when trying to select a single element.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Run E2E tests locally multiple times to ensure no flakiness
- [x] Check CI pipeline runs successfully
Fixes two related bugs in the agent scheduling UI that caused confusion
for users setting up recurring schedules:
1. **"on day nan of every month" display bug**: When scheduling an agent
to repeat every N days (e.g., "every 2 days"), the schedule info panel
incorrectly displayed "on day nan of every month" instead of the correct
"Every N days at HH:MM" format.
2. **Confusing time picker for hourly intervals**: When setting up a
schedule with "every N hours", the UI displayed a time picker labeled
"at 9 o'clock" which was confusing because the time setting is ignored
for hourly intervals. Users were unclear about what this setting meant
or if it had any effect.
### Changes 🏗️
**Fixed `humanizeCronExpression` function**
(`autogpt_platform/frontend/src/lib/cron-expression-utils.ts`):
- Reordered cron expression parsing logic to handle day intervals
(`*/N`) before monthly checks
- Added `!dayOfMonth.startsWith("*/")` guard to monthly and yearly
checks to prevent misinterpreting day intervals as monthly day lists
- This ensures expressions like `0 9 */2 * *` (every 2 days at 9:00) are
correctly displayed as "Every 2 days at 09:00" instead of "on day nan of
every month"
**Updated `CronScheduler` component**
(`autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/AgentRunsView/components/ScheduleAgentModal/components/CronScheduler/CronScheduler.tsx`):
- Hide `TimeAt` component for custom intervals with unit "hours" (time
is ignored for hourly intervals)
- Pass context-aware label to `TimeAt`: "Starting at" for custom day
intervals, "At" for other frequencies
- This clarifies that the time setting is the starting time for day
intervals and removes confusion for hourly intervals
**Enhanced `TimeAt` component**
(`autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/AgentRunsView/components/ScheduleAgentModal/components/CronScheduler/TimeAt.tsx`):
- Added optional `label` prop (defaults to "At") to allow context-aware
labeling
- Component now displays "Starting at" when used with custom day
intervals for better clarity
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
<!-- Put your test plan here: -->
- [x] Schedule an agent with "Custom" frequency, "Every 2 days" interval
- verify it displays as "Every 2 days at HH:MM" in the schedule info
panel (not "on day nan of every month")
- [x] Schedule an agent with "Monthly" frequency - verify it displays
correctly (e.g., "On day 1, 15 of every month at HH:MM")
<img width="845" height="388" alt="image"
src="https://github.com/user-attachments/assets/02ed0b73-bf5e-48fd-a7b0-6f4d4687eb13"
/>
<img width="839" height="374" alt="image"
src="https://github.com/user-attachments/assets/be62eee2-3fdd-4b20-aecf-669c3c6c6fb2"
/>
- Resolves#11345
### Changes 🏗️
- Move tool use routing logic from frontend to backend: routing info was
being baked into graph links by the frontend, inconsistently, causing
issues
- Rework tool use routing to use target node ID instead of target block
name
- Add a bit of magic to `NodeOutputs` component to show tool node title
instead of ID
DX:
- Removed `build` from `.prettierignore` -> re-enable formatting for
builder components
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Use SDM block in a graph; verify it works
- [x] Use SDM block with agent executor block as tool; verify it works
- Tests for `parse_execution_output` pass (checked by CI)
## Summary
This PR fixes an issue where multiple keyboard save event listeners were
being registered when the same save hook was used in multiple
components, causing the graph to be saved multiple times (3x) when using
Ctrl/Cmd+S.
## Changes
- **Created a centralized `useSaveGraph` hook** in
`/hooks/useSaveGraph.ts` that encapsulates all graph saving logic
- **Refactored `useNewSaveControl`** to use the new centralized hook
instead of duplicating save logic
- **Updated `useRunGraph` and `useScheduleGraph`** to use the
centralized `useSaveGraph` hook directly
- **Simplified the save control component** by removing redundant logic
and using cleaner naming conventions
## Problem
The previous implementation had the save logic duplicated in
`useNewSaveControl`, and when this hook was used in multiple places
(NewSaveControl component, RunGraph, ScheduleGraph), each instance would
register its own keyboard event listener for Ctrl/Cmd+S. This caused:
- Multiple save requests being sent simultaneously
- "Unique constraint failed on the fields: ('id', 'version')" errors
from the backend
- Poor performance due to unnecessary re-renders
## Solution
By centralizing the save logic in a dedicated `useSaveGraph` hook:
- Save logic is now in one place, making it easier to maintain
- Components can use the save functionality without registering
duplicate event listeners
- The keyboard shortcut listener is only registered once in the
`useNewSaveControl` hook
- Other components (RunGraph, ScheduleGraph) can call `saveGraph`
directly without side effects
## Testing
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] Verified Ctrl/Cmd+S saves the graph only once
- [x] Tested save functionality from Save Control popup
- [x] Confirmed Run Graph and Schedule Graph still save before execution
- [x] Verified no duplicate save requests in network tab
- [x] Checked that save toast notifications appear correctly
In this PR, I’ve added drag-and-drop functionality to the new builder
using built-in HTML drag-and-drop.
https://github.com/user-attachments/assets/b27c281e-6216-4131-9a89-e10b0dd56a8f
### Changes
- Added ReactFlowProvider to manage flow state in BuilderPage and Flow
components.
- Implemented drag-and-drop support for blocks in the NewControlPanel,
allowing users to drag blocks from the menu and drop them onto the
canvas.
- Enhanced the Block component to handle drag events and provide visual
feedback during dragging.
- Updated useFlow hook to include onDragOver and onDrop handlers for
managing block placement.
- Adjusted nodeStore to accept position parameters for added blocks,
improving placement accuracy.
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] I’ve tried dragging and dropping multiple blocks, and it works
perfectly as shown in the video.
- depends one https://github.com/Significant-Gravitas/AutoGPT/pull/11339
In this PR, I’ve added a dropdown menu to the custom node. This allows
you to delete a node, copy a node, and if the node is an agent node, you
can also navigate to that specific agent.
<img width="633" height="403" alt="Screenshot 2025-11-08 at 7 24 38 PM"
src="https://github.com/user-attachments/assets/89dd2906-95f5-40a5-82d1-de05075e4f30"
/>
###Changes
- Added context menu to custom nodes with copy, delete, and open agent
options
- Added performance optimization with memo for custom edge
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] All three buttons are working perfectly.
- [x] The “Go to graph” option is only visible in the sub-graph node.
In the new builder, I’ve added a copy-paste functionality using the
keyboard.
https://github.com/user-attachments/assets/3106ae86-3f47-4807-a598-9c0b166eaae9
### Changes 🏗️
- Added useCopyPasteKeyboard hook for handling keyboard shortcuts
- Created new copyPasteStore for state management
- Implemented performance optimizations (memo on CustomEdge)
- Updated nodeStore and edgeStore to support the functionality
### Checklist 📋
#### For code changes:
- [x] I have clearly listed my changes in the PR description
- [x] I have made a test plan
- [x] I have tested my changes according to the test plan:
- [x] The copy-paste functionality is working correctly as you can see
in the video.
