## Changes 🏗️
### Design updates
Design updates on the new Library page. New empty views with
illustration and overall changes on the sidebar and selected run
sections...
<img width="800" height="871" alt="Screenshot 2025-12-03 at 14 03 45"
src="https://github.com/user-attachments/assets/6970af99-dda8-4cd8-a9b5-97fe5ee2032e"
/>
<img width="800" height="844" alt="Screenshot 2025-12-03 at 14 03 52"
src="https://github.com/user-attachments/assets/92e6af79-db9f-4098-961f-9ae3b3300ffa"
/>
<img width="800" height="816" alt="Screenshot 2025-12-03 at 14 03 57"
src="https://github.com/user-attachments/assets/7e23e612-b446-4c53-8ea2-f0e2b1574ec3"
/>
<img width="800" height="862" alt="Screenshot 2025-12-03 at 14 04 07"
src="https://github.com/user-attachments/assets/e3398232-e74b-4a06-8702-30a96862dc00"
/>
### Architecture
- Make selected tabs/items synced with the URL via `?activeTab=` and
`?activeItem=`, so it is easy and predictable to change their state...
- Some minor updates on the design system I missed on previous PRs ...
## 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 locally and check the new page ( still wip )
- [OPEN-2871: TypeError: URL constructor: www.agpt.co is not a valid
URL.](https://linear.app/autogpt/issue/OPEN-2871/typeerror-url-constructor-wwwagptco-is-not-a-valid-url)
- [Sentry Issue BUILDER-56D: TypeError: URL constructor: www.agpt.co is
not a valid
URL.](https://significant-gravitas.sentry.io/issues/7081476631/)
### Changes 🏗️
- Amend URL handling in `CreatorLinks` to correctly handle URLs with
implicit schema
### 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:
- Trivial change, CI is sufficient
### Changes 🏗️
- Modify the HTTP block to handle HTTP errors (4xx, 5xx) by returning
response objects instead of raising exceptions.
- This allows proper handling of client_error and server_error outputs.
Fixes
[AUTOGPT-SERVER-6VP](https://sentry.io/organizations/significant-gravitas/issues/7023985892/).
The issue was that: HTTP errors are raised as exceptions by `Requests`
default behavior, bypassing the block's intended error output handling,
resulting in `BlockUnknownError`.
This fix was generated by Seer in Sentry, triggered by Nicholas Tindle.
👁️ Run ID: 4902617
Not quite right? [Click here to continue debugging with
Seer.](https://sentry.io/organizations/significant-gravitas/issues/7023985892/?seerDrawer=true)
### 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 with a service that will return 4XX and 5XX errors to make
sure the correct paths are followed
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> HTTP block now returns 4xx/5xx responses instead of raising, and
Requests gains retry_max_attempts with last-result handling.
>
> - **Backend**
> - **HTTP block (`backend/blocks/http.py`)**:
> - Use `Requests(raise_for_status=False, retry_max_attempts=1)` so
4xx/5xx return response objects and route to
`client_error`/`server_error` outputs.
> - **HTTP client util (`backend/util/request.py`)**:
> - Add `retry_max_attempts` option with `stop_after_attempt` and
`_return_last_result` to return the final response when retries stop.
> - Build `tenacity` retry config dynamically in `Requests.request()`;
validate `retry_max_attempts >= 1` when provided.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
fccae61c26. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: seer-by-sentry[bot] <157164994+seer-by-sentry[bot]@users.noreply.github.com>
Co-authored-by: Cursor Agent <cursoragent@cursor.com>
Co-authored-by: nicholas.tindle <nicholas.tindle@agpt.co>
Allow the external api to manage credentials
### Changes 🏗️
- add ability to external api to manage credentials
### 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 it works
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Introduces external API endpoints to manage integrations (OAuth
initiation/completion and credential CRUD), adds external OAuth state
fields, and new API key permissions/config.
>
> - **External API – Integrations**:
> - Add router `backend/server/external/routes/integrations.py` with
endpoints to:
> - `GET /v1/integrations/providers` list providers (incl. default
scopes)
> - `POST /v1/integrations/{provider}/oauth/initiate` and `POST
/oauth/complete` for external OAuth (custom callback, state)
> - `GET /v1/integrations/credentials` and `GET /{provider}/credentials`
to list credentials
> - `POST /{provider}/credentials` to create `api_key`, `user_password`,
`host_scoped` creds; `DELETE /{provider}/credentials/{cred_id}` to
delete
> - Wire router in `backend/server/external/api.py`.
> - **Auth/Permissions**:
> - Add `APIKeyPermission` values: `MANAGE_INTEGRATIONS`,
`READ_INTEGRATIONS`, `DELETE_INTEGRATIONS` (schema + migration +
OpenAPI).
> - **Data model / Store**:
> - Extend `OAuthState` with external-flow fields: `callback_url`,
`state_metadata`, `api_key_id`, `is_external`.
> - Update `IntegrationCredentialsStore.store_state_token(...)` to
accept/store external OAuth metadata.
> - **OAuth providers**:
> - Set GitHub handler `DEFAULT_SCOPES = ["repo"]` in
`integrations/oauth/github.py`.
> - **Config**:
> - Add `config.external_oauth_callback_origins` in
`backend/util/settings.py` to validate allowed OAuth callback origins.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
249bba9e59. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Co-authored-by: Reinier van der Leer <pwuts@agpt.co>
## Summary
- Clamp `start_time` to at least 10 seconds before request time (Twitter
API requirement)
- Update input description to document this automatic adjustment
- Fix `serialize_list` to handle `None` data gracefully (exposed by the
fix)
## Background
Twitter API returns `400 Bad Request` when `start_time` is less than 10
seconds before the request time. Users providing current/future times
would hit this error.
**Sentry Issue:**
[BUILDER-3PG](https://significant-gravitas.sentry.io/issues/6919685270/)
## Affected Blocks
- `TwitterSearchRecentTweetsBlock`
- `TwitterGetUserMentionsBlock`
- `TwitterGetHomeTimelineBlock`
- `TwitterGetUserTweetsBlock`
## Test plan
- [x] Tested `TwitterSearchRecentTweetsBlock` with current time as
`start_time`
- [x] Verified clamping works and API call succeeds
- [x] Verified "No tweets found" is returned correctly when search
window has no results
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
## Summary
Fix broken `update_agent_version_in_library` functionality by eagerly
loading `AgentGraph` while loading the library, also consolidating
duplicate code that updates agent version in library and configures HITL
safe mode settings.
## Problem
The `update_agent_version_in_library` is currently failed with this
error:
```
File "/Users/abhi/Documents/AutoGPT/autogpt_platform/backend/backend/server/v2/library/model.py", line 110, in from_db
raise ValueError("Associated Agent record is required.")
ValueError: Associated Agent record is required.
```
also logic was duplicated across two router endpoints with identical
implementations, creating maintenance burden and potential for
inconsistencies.
## Changes Made
### Created Helper Method
- Add `_update_library_agent_version_and_settings()` helper function
- Fixes broken `update_agent_version_in_library` by centralizing the
logic
- Uses proper error handling and settings merging with `model_copy()`
### Replaced Duplicate Code
- **In `update_graph` function** (v1.py:863) - replaced 13 lines with
single helper call
- **In `set_graph_active_version` function** (v1.py:920) - replaced 13
lines with single helper call
### Benefits
- **Fixes broken functionality**: Centralizes
`update_agent_version_in_library` logic
- **DRY Principle**: Eliminates code duplication across two router
endpoints
- **Maintainability**: Single place to modify the library agent update
logic
- **Consistency**: Ensures both endpoints use identical logic for HITL
safe mode configuration
- **Readability**: Cleaner, more focused endpoint implementations
## Technical Details
The helper method fixes broken `update_agent_version_in_library` by
handling:
1. Updating agent version in library via
`update_agent_version_in_library()`
2. Conditionally setting `human_in_the_loop_safe_mode: true` if graph
has HITL blocks and setting is not already configured
3. Proper settings merging to preserve existing configuration
## Testing
- [x] Code compiles and passes type checking
- [x] Pre-commit hooks pass (linting, formatting, type checking)
- [x] Both affected endpoints maintain same functionality with cleaner
implementation
Fixes broken duplicate code identified in v1.py router endpoints for
`update_agent_version_in_library`.
Co-authored-by: Claude <noreply@anthropic.com>
This PR addresses two issues:
1. **Empty values being sent to backend**: Node inputs were including
empty strings, null, and undefined values when converting to backend
format, causing unnecessary data to be sent.
2. **Incorrect connection detection in ObjectEditor**: The component was
checking if the parent field was connected instead of checking
individual key-value pairs, causing incorrect UI state for dynamic
properties.
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
- **nodeStore.ts**: Added `pruneEmptyValues` utility to remove
empty/null/undefined values from `hardcodedValues` before converting
nodes to backend format. This ensures only meaningful input values are
sent to the backend API.
- **ObjectEditorWidget.tsx**:
- Removed unused `fieldKey` prop from component interface
- Fixed connection detection logic to check individual key-value handle
IDs instead of the parent field key, ensuring correct connection state
for each dynamic property in object editors
### 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 node with object input fields and verify empty values are
not sent to backend
- [x] Add multiple key-value pairs to an object editor widget
- [x] Connect individual key-value pairs via handles and verify
connection state is correctly displayed
- [x] Disconnect a key-value pair and verify the input field becomes
editable
- [x] Save and reload an agent with object inputs to verify empty values
are pruned correctly
- [x] Verify that non-empty values are still correctly preserved and
sent to backend
This PR fixes an issue where the `isGraphRunning` state wasn't being
updated when users manually executed graphs. This caused the UI to not
show proper feedback that a graph was running, such as the running
background animation. The fix adds a `setIsGraphRunning` method to the
graph store and ensures it's called both when starting execution (for
immediate UI feedback) and when errors occur (to reset the state).
### Changes 🏗️
- **Added `setIsGraphRunning` method to graphStore**: Provides a way to
manually control the graph running state
- **Set running state on manual execution**: Updates `isGraphRunning` to
`true` immediately when users click the Run button, providing instant UI
feedback
- **Reset state on execution errors**: Ensures `isGraphRunning` is set
back to `false` if the graph execution fails, preventing the UI from
showing incorrect running state
- **Improved UI responsiveness**: Users now see immediate visual
feedback (like the running background) when they start a graph execution
- **Cleaned up unused import**: Removed unnecessary `flowID` from
useQueryStates in Flow component
- I’ve also changed the colour of the running background to a lighter
shade of purple.
### 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] Click Run button and verify the running background appears
immediately
- [x] Test with graphs that require input values via the input dialog
- [x] Verify running state is cleared when execution completes
- [x] Test error scenarios and confirm running state is reset on failure
- [x] Confirm all UI elements that depend on `isGraphRunning` update
correctly
- [x] Test multiple consecutive runs to ensure state management is
consistent
## Summary
Fix critical validation errors in GraphExecutionEntry and
NodeExecutionEntry models that were preventing HITL block execution, and
re-enable HITL test suite.
## Root Cause
After introducing ExecutionContext as a mandatory field, existing
messages in the execution queue lacked this field, causing validation
failures:
```
[GraphExecutor] [ExecutionManager] Could not parse run message: 1 validation error for GraphExecutionEntry
execution_context
Field required [type=missing, input_value={'user_id': '26db15cb-a29...
```
## Changes Made
### 🔧 Execution Model Fixes (`backend/data/execution.py`)
- **Add backward compatibility**: `execution_context: ExecutionContext =
Field(default_factory=ExecutionContext)`
- **Prevent shared mutable defaults**: Use `default_factory` instead of
direct instantiation to avoid mutation issues
- **Ignore unknown fields**: Add `model_config = {"extra": "ignore"}`
for future compatibility
- **Applied to both models**: GraphExecutionEntry and NodeExecutionEntry
### 🧪 Re-enable HITL Test Suite
- **Remove test skips**: Remove `pytestmark = pytest.mark.skip()` from
`human_review_test.py`
- **Remove test skips**: Remove `pytestmark = pytest.mark.skip()` from
`review_routes_test.py`
- **Restore test coverage**: HITL functionality now properly tested in
CI
## Default ExecutionContext Behavior
When execution_context is missing from old messages, provides safe
defaults:
- `safe_mode: bool = True` (HITL blocks require approval by default)
- `user_timezone: str = "UTC"` (safe timezone default)
- `root_execution_id: Optional[str] = None`
- `parent_execution_id: Optional[str] = None`
## Impact
- ✅ **Fixes deployment validation errors** in dev environment
- ✅ **Maintains backward compatibility** with existing queue messages
- ✅ **Restores proper HITL test coverage** in CI
- ✅ **Ensures isolation**: Each execution gets its own ExecutionContext
instance
- ✅ **Future-proofs**: Protects against message format changes
## Testing
- [x] HITL test suite re-enabled and should pass in CI
- [x] Existing executions continue to work with sensible defaults
- [x] New executions receive proper ExecutionContext from caller
- [x] Verified `default_factory` prevents shared mutable instances
## Files Changed
- `backend/data/execution.py` - Add backward-compatible ExecutionContext
defaults
- `backend/data/human_review_test.py` - Re-enable test suite
- `backend/server/v2/executions/review/review_routes_test.py` -
Re-enable test suite
Resolves the "Field required" validation error preventing HITL block
execution in dev environment.
🤖 Generated with [Claude Code](https://claude.ai/code)
Co-Authored-By: Claude <noreply@anthropic.com>
Co-authored-by: Claude <noreply@anthropic.com>
## Summary
- Add `jlumbroso/free-disk-space@v1.3.1` action to claude.yml workflow
- Frees up disk space on Ubuntu runner before heavy Docker and
dependency setup
- Skips `large-packages` (slow) and `docker-images` (needed for
workflow)
## Test plan
- [x] Verify claude.yml workflow runs successfully without disk space
errors
🤖 Generated with [Claude Code](https://claude.com/claude-code)
Co-authored-by: Claude <noreply@anthropic.com>
Adds a new Discord block that allows users to create threads in Discord
channels. This addresses issue OPEN-2666 which requested the ability to
create Discord threads from workflows.
## Solution
Implemented `CreateDiscordThreadBlock` in
`autogpt_platform/backend/backend/blocks/discord/bot_blocks.py` with the
following features:
- Create public or private threads in Discord channels via bot token
- Support for both channel ID and channel name lookup (with optional
server name)
- Configurable thread type (public/private toggle)
- Configurable auto-archive duration (60, 1440, 4320, or 10080 minutes)
- Optional initial message to send in the newly created thread
- Outputs: status, thread_id, and thread_name for workflow chaining
The block follows the existing Discord block patterns and includes
proper error handling for permissions, channel not found, and login
failures.
#### 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] Verify block appears in the workflow builder UI
- [x] Test creating a public thread with valid bot token and channel ID
- [x] Test creating a private thread with valid bot token and channel
name
- [x] Test with invalid channel ID/name to verify error handling
- [x] Test with bot lacking thread creation permissions
- [x] Verify thread_id output can be chained to subsequent blocks
- [x] Test auto-archive duration options (60, 1440, 4320, 10080 minutes)
- [x] Test sending initial message in newly created thread
Video to show the blocks working!
https://github.com/user-attachments/assets/f248f315-05b3-47e2-bd6b-4c64d53c35fc
Simplifying the chat tool system to use only 2 tools
### Changes 🏗️
- remove old tools
- expand run_agent tool to include all stages
### 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 adding credentials work
- [x] tested running an agent works
- [x] tested scheduling an agent works
Sometime block errors are raised with message set as None, we now handle
this case
### Changes 🏗️
- handle case of None message
- Add tests
### 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] write unit tests
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Ensure `BlockExecutionError` and `BlockUnknownError` provide default
messages when given None/empty input, with new unit tests covering
formatting and inheritance.
>
> - **Backend**:
> - `backend/util/exceptions.py`:
> - `BlockExecutionError`: default `None` message to `"Output error was
None"`.
> - `BlockUnknownError`: default empty/`None` message to `"Unknown error
occurred"`.
> - **Tests**:
> - `backend/util/exceptions_test.py`: add tests for message formatting,
`None`/empty handling, and exception inheritance.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
6e9b31ae47. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Youtube can blocks cloud ips causing the youtube transcribe blocks to
not work. This PR adds webshare proxy to get around this issue
### Changes 🏗️
- add webshare proxy to youtube transcribe block
### 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 tested this works locally using the proxy
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Routes YouTube transcript fetching through Webshare proxy using
user/password credentials, wiring in provider enum, settings, default
credentials, and updated tests.
>
> - **Blocks** (`backend/blocks/youtube.py`):
> - Use `WebshareProxyConfig` with `YouTubeTranscriptApi` to fetch
transcripts via proxy.
> - Add `credentials` input (`user_password` for `webshare_proxy`);
include test credentials and mocks.
> - Update method signatures: `get_transcript(video_id, credentials)`
and `run(..., *, credentials, ...)`.
> - Change description to indicate proxy usage; add logging.
> - **Integrations**:
> - Providers (`backend/integrations/providers.py`): add
`ProviderName.WEBSHARE_PROXY`.
> - Credentials store (`backend/integrations/credentials_store.py`): add
`webshare_proxy` `UserPasswordCredentials`; include in
`DEFAULT_CREDENTIALS` and conditionally in `get_all_creds`.
> - **Settings** (`backend/util/settings.py`): add secrets
`webshare_proxy_username` and `webshare_proxy_password`.
> - **Tests** (`test/blocks/test_youtube.py`): update to pass
credentials and assert proxy config; add custom-credentials test; adjust
fallback/priority tests.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
d060898488. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
Eliminates explicit Google Sheets API scopes from credentials fields in
all Google Sheets-related blocks. This change may be intended to
centralize or dynamically manage API scopes elsewhere, simplifying block
configuration.
<!-- Clearly explain the need for these changes: -->
### Changes 🏗️
- removes the scopes we aren't approved to use
<!-- Concisely describe all of the changes made in this pull request:
-->
### 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] Bently tested it on his fresh account and it worked!
## 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>
## Summary
Complete migration of all non-test `query_raw` calls to use
`query_raw_with_schema` for proper PostgreSQL schema context handling.
This resolves the marketplace API failures where queries were looking
for unqualified table names.
## Root Cause
Prisma's `query_raw()` doesn't respect the `schema` parameter in
`DATABASE_URL` (`?schema=platform`) for raw SQL queries, causing queries
to fail when looking for unqualified table names in multi-schema
environments.
## Changes Made
### Files Updated
- ✅ **backend/server/v2/store/db.py**: Already updated in previous
commit
- ✅ **backend/server/v2/builder/db.py**: Updated `get_suggested_blocks`
query at line 343
- ✅ **backend/check_store_data.py**: Updated all 4 `query_raw` calls to
use schema-aware queries
- ✅ **backend/check_db.py**: Updated all `query_raw` calls (import
already existed)
### Technical Implementation
- Add import: `from backend.data.db import query_raw_with_schema`
- Replace `prisma.get_client().query_raw()` with
`query_raw_with_schema()`
- Add `{schema_prefix}` placeholder to table references in SQL queries
- Fix f-string template conflicts by using double braces
`{{schema_prefix}}`
### Query Examples
**Before:**
```sql
FROM "StoreAgent"
FROM "AgentNodeExecution" execution
```
**After:**
```sql
FROM {schema_prefix}"StoreAgent"
FROM {schema_prefix}"AgentNodeExecution" execution
```
## Impact
- ✅ All raw SQL queries now properly respect platform schema context
- ✅ Fixes "relation does not exist" errors in multi-schema environments
- ✅ Maintains backward compatibility with public schema deployments
- ✅ Code formatting passes with `poetry run format`
## Testing
- All `query_raw` usages in non-test code successfully migrated
- `query_raw_with_schema` automatically handles schema prefix injection
- Existing query logic unchanged, only schema awareness added
## Before/After
**Before:** GET /api/store/agents → "relation 'StoreAgent' does not
exist"
**After:** GET /api/store/agents → ✅ Returns store agents correctly
Resolves the marketplace API failures and ensures consistent schema
handling across all raw SQL operations.
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>
- Added `store_media_file` utility to convert local file paths to Data
URIs for image processing.
- Updated `AIImageCustomizerBlock` to utilize processed images in model
execution, improving compatibility with Replicate API.
- Added optional Aspect ratio input to AIImageCustomizerBlock
This change enhances the image handling capabilities of the AI image
customizer, ensuring that images are properly formatted for external
processing.
<!-- Clearly explain the need for these changes: -->
### Changes 🏗️
<!-- Concisely describe all of the changes made in this pull request:
-->
### 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] Created agent using AI Image Customizer block attached to agent
file input
- [x] Run agent, confirmed block is working
- [x] Confirm block is still working in original direct file upload
setup.
### Testing Results
#### Before (dev cloud):
<img width="836" height="592" alt="image"
src="https://github.com/user-attachments/assets/88c75668-c5c9-44bb-bec5-6554088a0cb7"
/>
#### After (local):
<img width="827" height="587" alt="image"
src="https://github.com/user-attachments/assets/04fea431-70a5-4173-bc84-d354c03d7174"
/>
<!-- CURSOR_SUMMARY -->
---
> [!NOTE]
> Preprocesses input images to data URIs and adds an `aspect_ratio`
option, wiring both through to Replicate in `AIImageCustomizerBlock`.
>
> - **Backend**
> - **`backend/blocks/ai_image_customizer.py`**:
> - Preprocesses input images via `store_media_file(...,
return_content=True)` to Data URIs before invoking Replicate.
> - Adds `AspectRatio` enum and `aspect_ratio` input; passed through
`run_model` and included in Replicate input.
> - Updates block test input accordingly.
>
> <sup>Written by [Cursor
Bugbot](https://cursor.com/dashboard?tab=bugbot) for commit
4116cf80d7. This will update automatically
on new commits. Configure
[here](https://cursor.com/dashboard?tab=bugbot).</sup>
<!-- /CURSOR_SUMMARY -->
---------
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
Co-authored-by: Claude <noreply@anthropic.com>
Co-authored-by: Nicholas Tindle <nicholas.tindle@agpt.co>
## 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
This unbreaks the Claude Code and Copilot workflows in our repo.
- Follow-up to #11288
### Changes 🏗️
- Update `node-version` on `actions/setup-node@v4` from v21 to v22
Bumps [cross-env](https://github.com/kentcdodds/cross-env) from 7.0.3 to
10.1.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/kentcdodds/cross-env/releases">cross-env's
releases</a>.</em></p>
<blockquote>
<h2>v10.1.0</h2>
<h1><a
href="https://github.com/kentcdodds/cross-env/compare/v10.0.0...v10.1.0">10.1.0</a>
(2025-09-29)</h1>
<h3>Features</h3>
<ul>
<li>add support for default value syntax (<a
href="152ae6a85b">152ae6a</a>)</li>
</ul>
<p>For example:</p>
<pre lang="json"><code>"dev:server": "cross-env wrangler
dev --port ${PORT:-8787}",
</code></pre>
<p>If <code>PORT</code> is already set, use that value, otherwise
fallback to <code>8787</code>.</p>
<p>Learn more about <a
href="https://www.gnu.org/software/bash/manual/html_node/Shell-Parameter-Expansion.html">Shell
Parameter Expansion</a></p>
<h2>v10.0.0</h2>
<h1><a
href="https://github.com/kentcdodds/cross-env/compare/v9.0.0...v10.0.0">10.0.0</a>
(2025-07-25)</h1>
<p>TL;DR: You should probably not have to change anything if:</p>
<ul>
<li>You're using a modern maintained version of Node.js (v20+ is
tested)</li>
<li>You're only using the CLI (most of you are as that's the intended
purpose)</li>
</ul>
<p>In this release (which should have been v8 except I had some issues
with automated releases 🙈), I've updated all the things and modernized
the package. This happened in <a
href="https://redirect.github.com/kentcdodds/cross-env/issues/261">#261</a></p>
<p>Was this needed? Not really, but I just thought it'd be fun to
modernize this package.</p>
<p>Here's the highlights of what was done.</p>
<ul>
<li>Replace Jest with Vitest for testing</li>
<li>Convert all source files from .js to .ts with proper TypeScript
types</li>
<li>Use zshy for ESM-only builds (removes CJS support)</li>
<li>Adopt <code>@epic-web/config</code> for TypeScript, ESLint, and
Prettier</li>
<li>Update to Node.js >=20 requirement</li>
<li>Remove kcd-scripts dependency</li>
<li>Add comprehensive e2e tests with GitHub Actions matrix testing</li>
<li>Update GitHub workflow with caching and cross-platform testing</li>
<li>Modernize documentation and remove outdated sections</li>
<li>Update all dependencies to latest versions</li>
<li>Add proper TypeScript declarations and exports</li>
</ul>
<p>The tool maintains its original functionality while being completely
modernized with the latest tooling and best practices</p>
<h3>BREAKING CHANGES</h3>
<ul>
<li>This is a major rewrite that changes the module format from CommonJS
to ESM-only. The package now requires Node.js >=20 and only exports
ESM modules (not relevant in most cases).</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="152ae6a85b"><code>152ae6a</code></a>
feat: add support ofr default value syntax</li>
<li><a
href="bd70d1ab25"><code>bd70d1a</code></a>
chore: upgrade zshy</li>
<li><a
href="8e0b190df9"><code>8e0b190</code></a>
chore(ci): get coverage</li>
<li><a
href="8635e80e81"><code>8635e80</code></a>
fix(release): manually release a major version</li>
<li><a
href="3a58f22360"><code>3a58f22</code></a>
chore: fix npmrc registry</li>
<li><a
href="b70bfff5ec"><code>b70bfff</code></a>
chore(ci): add names to steps and workflows</li>
<li><a
href="cc5759dc36"><code>cc5759d</code></a>
fix(release): manually release a major version</li>
<li><a
href="080a859190"><code>080a859</code></a>
chore: remove publish script</li>
<li><a
href="31e5bc70e7"><code>31e5bc7</code></a>
chore(ci): restore built files</li>
<li><a
href="81e9c34f55"><code>81e9c34</code></a>
chore(ci): add back semantic-release</li>
<li>Additional commits viewable in <a
href="https://github.com/kentcdodds/cross-env/compare/v7.0.3...v10.1.0">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores)
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com>
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Co-authored-by: Zamil Majdy <zamil.majdy@agpt.co>
## 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
This PR adds the latest [claude opus
4.5](https://www.anthropic.com/news/claude-opus-4-5) model to the
platform
### 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] Test and use the llm to make sure it works
## 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 adds some of the latest grok models to the platform
``x-ai/grok-4-fast``, ``x-ai/grok-4.1-fast`` and ``ai/grok-code-fast-1``
#### 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 all of the latest grok models to make sure they work and they
do!
<img width="1089" height="714" alt="image"
src="https://github.com/user-attachments/assets/0d1e3984-69e8-432b-982a-b04c16bc4f41"
/>
This PR adds the latest google banana pro image generator and editor to
the platform and fixes up some of the prices for the image generation
models
I asked for ``Generate a image of a dog on a skateboard`` and this is
what i got:
<img width="2048" height="2048" alt="image"
src="https://github.com/user-attachments/assets/9b6c16d8-df8f-4fb6-a009-d6d342f9beb7"
/>
### 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 the image generator and image editor block using the latest
google banana pro model and it works
---------
Co-authored-by: Abhimanyu Yadav <122007096+Abhi1992002@users.noreply.github.com>
