Merge branch 'dev' into abhi/integration-test-setup

- Deleted AGENTS.md, which contained frontend testing rules and guidelines, as it is no longer relevant to the current testing framework and practices.

autogpt_platform/backend/backend/api/features/executions/review/model.py

@@ -179,14 +179,6 @@ class ReviewRequest(BaseModel):
     reviews: List[ReviewItem] = Field(
         description="All reviews with their approval status, data, and messages"
     )
-    auto_approve_future_actions: bool = Field(
-        default=False,
-        description=(
-            "If true, future reviews from the same blocks (nodes) being approved "
-            "will be automatically approved for the remainder of this execution. "
-            "This only affects the current execution run."
-        ),
-    )
 
     @model_validator(mode="after")
     def validate_review_completeness(self):

autogpt_platform/backend/backend/api/features/executions/review/review_routes_test.py

@@ -490,321 +490,3 @@ def test_process_review_action_invalid_node_exec_id(
     # Should be a 400 Bad Request, not 500 Internal Server Error
     assert response.status_code == 400
     assert "Invalid node execution ID format" in response.json()["detail"]
-
-
-def test_process_review_action_auto_approve_creates_auto_approval_records(
-    mocker: pytest_mock.MockerFixture,
-    sample_pending_review: PendingHumanReviewModel,
-    test_user_id: str,
-) -> None:
-    """Test that auto_approve_future_actions flag creates auto-approval records"""
-    from backend.data.execution import ExecutionContext, NodeExecutionResult
-    from backend.data.graph import GraphSettings
-
-    # Mock process_all_reviews
-    mock_process_all_reviews = mocker.patch(
-        "backend.api.features.executions.review.routes.process_all_reviews_for_execution"
-    )
-    approved_review = PendingHumanReviewModel(
-        node_exec_id="test_node_123",
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        payload={"data": "test payload"},
-        instructions="Please review",
-        editable=True,
-        status=ReviewStatus.APPROVED,
-        review_message="Approved",
-        was_edited=False,
-        processed=False,
-        created_at=FIXED_NOW,
-        updated_at=FIXED_NOW,
-        reviewed_at=FIXED_NOW,
-    )
-    mock_process_all_reviews.return_value = {"test_node_123": approved_review}
-
-    # Mock get_node_execution to return node_id
-    mock_get_node_execution = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_execution"
-    )
-    mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
-    mock_node_exec.node_id = "test_node_def_456"
-    mock_get_node_execution.return_value = mock_node_exec
-
-    # Mock create_auto_approval_record
-    mock_create_auto_approval = mocker.patch(
-        "backend.api.features.executions.review.routes.create_auto_approval_record"
-    )
-
-    # Mock has_pending_reviews_for_graph_exec
-    mock_has_pending = mocker.patch(
-        "backend.api.features.executions.review.routes.has_pending_reviews_for_graph_exec"
-    )
-    mock_has_pending.return_value = False
-
-    # Mock get_graph_settings to return custom settings
-    mock_get_settings = mocker.patch(
-        "backend.api.features.executions.review.routes.get_graph_settings"
-    )
-    mock_get_settings.return_value = GraphSettings(
-        human_in_the_loop_safe_mode=True,
-        sensitive_action_safe_mode=True,
-    )
-
-    # Mock add_graph_execution
-    mock_add_execution = mocker.patch(
-        "backend.api.features.executions.review.routes.add_graph_execution"
-    )
-
-    request_data = {
-        "reviews": [
-            {
-                "node_exec_id": "test_node_123",
-                "approved": True,
-                "message": "Approved",
-            }
-        ],
-        "auto_approve_future_actions": True,
-    }
-
-    response = client.post("/api/review/action", json=request_data)
-
-    assert response.status_code == 200
-
-    # Verify process_all_reviews_for_execution was called (without auto_approve param)
-    mock_process_all_reviews.assert_called_once()
-
-    # Verify create_auto_approval_record was called for the approved review
-    mock_create_auto_approval.assert_called_once_with(
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        node_id="test_node_def_456",
-        payload={"data": "test payload"},
-    )
-
-    # Verify get_graph_settings was called with correct parameters
-    mock_get_settings.assert_called_once_with(
-        user_id=test_user_id, graph_id="test_graph_789"
-    )
-
-    # Verify add_graph_execution was called with proper ExecutionContext
-    mock_add_execution.assert_called_once()
-    call_kwargs = mock_add_execution.call_args.kwargs
-    execution_context = call_kwargs["execution_context"]
-
-    assert isinstance(execution_context, ExecutionContext)
-    assert execution_context.human_in_the_loop_safe_mode is True
-    assert execution_context.sensitive_action_safe_mode is True
-
-
-def test_process_review_action_without_auto_approve_still_loads_settings(
-    mocker: pytest_mock.MockerFixture,
-    sample_pending_review: PendingHumanReviewModel,
-    test_user_id: str,
-) -> None:
-    """Test that execution context is created with settings even without auto-approve"""
-    from backend.data.execution import ExecutionContext
-    from backend.data.graph import GraphSettings
-
-    # Mock process_all_reviews
-    mock_process_all_reviews = mocker.patch(
-        "backend.api.features.executions.review.routes.process_all_reviews_for_execution"
-    )
-    approved_review = PendingHumanReviewModel(
-        node_exec_id="test_node_123",
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        payload={"data": "test payload"},
-        instructions="Please review",
-        editable=True,
-        status=ReviewStatus.APPROVED,
-        review_message="Approved",
-        was_edited=False,
-        processed=False,
-        created_at=FIXED_NOW,
-        updated_at=FIXED_NOW,
-        reviewed_at=FIXED_NOW,
-    )
-    mock_process_all_reviews.return_value = {"test_node_123": approved_review}
-
-    # Mock create_auto_approval_record - should NOT be called when auto_approve is False
-    mock_create_auto_approval = mocker.patch(
-        "backend.api.features.executions.review.routes.create_auto_approval_record"
-    )
-
-    # Mock has_pending_reviews_for_graph_exec
-    mock_has_pending = mocker.patch(
-        "backend.api.features.executions.review.routes.has_pending_reviews_for_graph_exec"
-    )
-    mock_has_pending.return_value = False
-
-    # Mock get_graph_settings with sensitive_action_safe_mode enabled
-    mock_get_settings = mocker.patch(
-        "backend.api.features.executions.review.routes.get_graph_settings"
-    )
-    mock_get_settings.return_value = GraphSettings(
-        human_in_the_loop_safe_mode=False,
-        sensitive_action_safe_mode=True,
-    )
-
-    # Mock add_graph_execution
-    mock_add_execution = mocker.patch(
-        "backend.api.features.executions.review.routes.add_graph_execution"
-    )
-
-    # Request WITHOUT auto_approve_future_actions
-    request_data = {
-        "reviews": [
-            {
-                "node_exec_id": "test_node_123",
-                "approved": True,
-                "message": "Approved",
-            }
-        ],
-        "auto_approve_future_actions": False,
-    }
-
-    response = client.post("/api/review/action", json=request_data)
-
-    assert response.status_code == 200
-
-    # Verify process_all_reviews_for_execution was called
-    mock_process_all_reviews.assert_called_once()
-
-    # Verify create_auto_approval_record was NOT called (auto_approve_future_actions=False)
-    mock_create_auto_approval.assert_not_called()
-
-    # Verify settings were loaded
-    mock_get_settings.assert_called_once()
-
-    # Verify ExecutionContext has proper settings
-    mock_add_execution.assert_called_once()
-    call_kwargs = mock_add_execution.call_args.kwargs
-    execution_context = call_kwargs["execution_context"]
-
-    assert isinstance(execution_context, ExecutionContext)
-    assert execution_context.human_in_the_loop_safe_mode is False
-    assert execution_context.sensitive_action_safe_mode is True
-
-
-def test_process_review_action_auto_approve_only_applies_to_approved_reviews(
-    mocker: pytest_mock.MockerFixture,
-    test_user_id: str,
-) -> None:
-    """Test that auto_approve record is created only for approved reviews"""
-    from backend.data.execution import ExecutionContext, NodeExecutionResult
-    from backend.data.graph import GraphSettings
-
-    # Create two reviews - one approved, one rejected
-    approved_review = PendingHumanReviewModel(
-        node_exec_id="node_exec_approved",
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        payload={"data": "approved"},
-        instructions="Review",
-        editable=True,
-        status=ReviewStatus.APPROVED,
-        review_message=None,
-        was_edited=False,
-        processed=False,
-        created_at=FIXED_NOW,
-        updated_at=FIXED_NOW,
-        reviewed_at=FIXED_NOW,
-    )
-    rejected_review = PendingHumanReviewModel(
-        node_exec_id="node_exec_rejected",
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        payload={"data": "rejected"},
-        instructions="Review",
-        editable=True,
-        status=ReviewStatus.REJECTED,
-        review_message="Rejected",
-        was_edited=False,
-        processed=False,
-        created_at=FIXED_NOW,
-        updated_at=FIXED_NOW,
-        reviewed_at=FIXED_NOW,
-    )
-
-    # Mock process_all_reviews
-    mock_process_all_reviews = mocker.patch(
-        "backend.api.features.executions.review.routes.process_all_reviews_for_execution"
-    )
-    mock_process_all_reviews.return_value = {
-        "node_exec_approved": approved_review,
-        "node_exec_rejected": rejected_review,
-    }
-
-    # Mock get_node_execution to return node_id (only called for approved review)
-    mock_get_node_execution = mocker.patch(
-        "backend.api.features.executions.review.routes.get_node_execution"
-    )
-    mock_node_exec = mocker.Mock(spec=NodeExecutionResult)
-    mock_node_exec.node_id = "test_node_def_approved"
-    mock_get_node_execution.return_value = mock_node_exec
-
-    # Mock create_auto_approval_record
-    mock_create_auto_approval = mocker.patch(
-        "backend.api.features.executions.review.routes.create_auto_approval_record"
-    )
-
-    # Mock has_pending_reviews_for_graph_exec
-    mock_has_pending = mocker.patch(
-        "backend.api.features.executions.review.routes.has_pending_reviews_for_graph_exec"
-    )
-    mock_has_pending.return_value = False
-
-    # Mock get_graph_settings
-    mock_get_settings = mocker.patch(
-        "backend.api.features.executions.review.routes.get_graph_settings"
-    )
-    mock_get_settings.return_value = GraphSettings()
-
-    # Mock add_graph_execution
-    mock_add_execution = mocker.patch(
-        "backend.api.features.executions.review.routes.add_graph_execution"
-    )
-
-    request_data = {
-        "reviews": [
-            {"node_exec_id": "node_exec_approved", "approved": True},
-            {"node_exec_id": "node_exec_rejected", "approved": False},
-        ],
-        "auto_approve_future_actions": True,
-    }
-
-    response = client.post("/api/review/action", json=request_data)
-
-    assert response.status_code == 200
-
-    # Verify process_all_reviews_for_execution was called
-    mock_process_all_reviews.assert_called_once()
-
-    # Verify create_auto_approval_record was called ONLY for the approved review
-    # (not for the rejected one)
-    mock_create_auto_approval.assert_called_once_with(
-        user_id=test_user_id,
-        graph_exec_id="test_graph_exec_456",
-        graph_id="test_graph_789",
-        graph_version=1,
-        node_id="test_node_def_approved",
-        payload={"data": "approved"},
-    )
-
-    # Verify get_node_execution was called only for approved review
-    mock_get_node_execution.assert_called_once_with("node_exec_approved")
-
-    # Verify ExecutionContext was created (auto-approval is now DB-based)
-    call_kwargs = mock_add_execution.call_args.kwargs
-    execution_context = call_kwargs["execution_context"]
-    assert isinstance(execution_context, ExecutionContext)

autogpt_platform/backend/backend/api/features/executions/review/routes.py

@@ -5,14 +5,8 @@ import autogpt_libs.auth as autogpt_auth_lib
 from fastapi import APIRouter, HTTPException, Query, Security, status
 from prisma.enums import ReviewStatus
 
-from backend.data.execution import (
-    ExecutionContext,
-    get_graph_execution_meta,
-    get_node_execution,
-)
-from backend.data.graph import get_graph_settings
+from backend.data.execution import get_graph_execution_meta
 from backend.data.human_review import (
-    create_auto_approval_record,
     get_pending_reviews_for_execution,
     get_pending_reviews_for_user,
     has_pending_reviews_for_graph_exec,
@@ -134,20 +128,14 @@ async def process_review_action(
         )
 
     # Build review decisions map
-    # When auto_approve_future_actions is true, ignore any edited data
-    # (auto-approved reviews should use original data for consistency)
     review_decisions = {}
     for review in request.reviews:
         review_status = (
             ReviewStatus.APPROVED if review.approved else ReviewStatus.REJECTED
         )
-        # If auto-approving future actions, don't allow data modifications
-        reviewed_data = (
-            None if request.auto_approve_future_actions else review.reviewed_data
-        )
         review_decisions[review.node_exec_id] = (
             review_status,
-            reviewed_data,
+            review.reviewed_data,
             review.message,
         )
 
@@ -157,22 +145,6 @@ async def process_review_action(
         review_decisions=review_decisions,
     )
 
-    # Create auto-approval records for approved reviews if requested
-    if request.auto_approve_future_actions:
-        for node_exec_id, review in updated_reviews.items():
-            if review.status == ReviewStatus.APPROVED:
-                # Look up the node_id from the node execution
-                node_exec = await get_node_execution(node_exec_id)
-                if node_exec:
-                    await create_auto_approval_record(
-                        user_id=user_id,
-                        graph_exec_id=review.graph_exec_id,
-                        graph_id=review.graph_id,
-                        graph_version=review.graph_version,
-                        node_id=node_exec.node_id,
-                        payload=review.payload,
-                    )
-
     # Count results
     approved_count = sum(
         1
@@ -197,24 +169,10 @@ async def process_review_action(
         if not still_has_pending:
             # Resume execution
             try:
-                # Load graph settings to create proper execution context
-                settings = await get_graph_settings(
-                    user_id=user_id, graph_id=first_review.graph_id
-                )
-
-                # Create execution context with settings
-                # Note: auto-approval is now handled via database lookup in
-                # check_auto_approval(), no need to pass auto_approved_node_ids
-                execution_context = ExecutionContext(
-                    human_in_the_loop_safe_mode=settings.human_in_the_loop_safe_mode,
-                    sensitive_action_safe_mode=settings.sensitive_action_safe_mode,
-                )
-
                 await add_graph_execution(
                     graph_id=first_review.graph_id,
                     user_id=user_id,
                     graph_exec_id=graph_exec_id,
-                    execution_context=execution_context,
                 )
                 logger.info(f"Resumed execution {graph_exec_id}")
             except Exception as e:

autogpt_platform/backend/backend/blocks/basic.py

@@ -116,7 +116,6 @@ class PrintToConsoleBlock(Block):
             input_schema=PrintToConsoleBlock.Input,
             output_schema=PrintToConsoleBlock.Output,
             test_input={"text": "Hello, World!"},
-            is_sensitive_action=True,
             test_output=[
                 ("output", "Hello, World!"),
                 ("status", "printed"),

autogpt_platform/backend/backend/blocks/helpers/review.py

@@ -10,7 +10,7 @@ from prisma.enums import ReviewStatus
 from pydantic import BaseModel
 
 from backend.data.execution import ExecutionContext, ExecutionStatus
-from backend.data.human_review import ReviewResult, check_auto_approval
+from backend.data.human_review import ReviewResult
 from backend.executor.manager import async_update_node_execution_status
 from backend.util.clients import get_database_manager_async_client
 
@@ -55,7 +55,6 @@ class HITLReviewHelper:
     async def _handle_review_request(
         input_data: Any,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -70,7 +69,6 @@ class HITLReviewHelper:
         Args:
             input_data: The input data to be reviewed
             user_id: ID of the user requesting the review
-            node_id: ID of the node in the graph definition
             node_exec_id: ID of the node execution
             graph_exec_id: ID of the graph execution
             graph_id: ID of the graph
@@ -85,27 +83,15 @@ class HITLReviewHelper:
         Raises:
             Exception: If review creation or status update fails
         """
-        # Note: Safe mode checks (human_in_the_loop_safe_mode, sensitive_action_safe_mode)
-        # are handled by the caller:
-        # - HITL blocks check human_in_the_loop_safe_mode in their run() method
-        # - Sensitive action blocks check sensitive_action_safe_mode in is_block_exec_need_review()
-        # This function only handles auto-approval for specific nodes.
-
-        # Check if this node has been auto-approved in a previous review
-        auto_approval = await check_auto_approval(
-            graph_exec_id=graph_exec_id,
-            node_id=node_id,
-        )
-        if auto_approval:
+        # Skip review if safe mode is disabled - return auto-approved result
+        if not execution_context.human_in_the_loop_safe_mode:
             logger.info(
-                f"Block {block_name} skipping review for node {node_exec_id} - "
-                f"node {node_id} has auto-approval from previous review"
+                f"Block {block_name} skipping review for node {node_exec_id} - safe mode disabled"
             )
-            # Return a new ReviewResult with the current node_exec_id but approved status
             return ReviewResult(
                 data=input_data,
                 status=ReviewStatus.APPROVED,
-                message="Auto-approved (user approved all future actions for this block)",
+                message="Auto-approved (safe mode disabled)",
                 processed=True,
                 node_exec_id=node_exec_id,
             )
@@ -143,7 +129,6 @@ class HITLReviewHelper:
     async def handle_review_decision(
         input_data: Any,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -158,7 +143,6 @@ class HITLReviewHelper:
         Args:
             input_data: The input data to be reviewed
             user_id: ID of the user requesting the review
-            node_id: ID of the node in the graph definition
             node_exec_id: ID of the node execution
             graph_exec_id: ID of the graph execution
             graph_id: ID of the graph
@@ -174,7 +158,6 @@ class HITLReviewHelper:
         review_result = await HITLReviewHelper._handle_review_request(
             input_data=input_data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,

autogpt_platform/backend/backend/blocks/human_in_the_loop.py

@@ -97,7 +97,6 @@ class HumanInTheLoopBlock(Block):
         input_data: Input,
         *,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -116,7 +115,6 @@ class HumanInTheLoopBlock(Block):
         decision = await self.handle_review_decision(
             input_data=input_data.data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,

autogpt_platform/backend/backend/data/block.py

@@ -441,7 +441,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         static_output: bool = False,
         block_type: BlockType = BlockType.STANDARD,
         webhook_config: Optional[BlockWebhookConfig | BlockManualWebhookConfig] = None,
-        is_sensitive_action: bool = False,
     ):
         """
         Initialize the block with the given schema.
@@ -474,8 +473,8 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         self.static_output = static_output
         self.block_type = block_type
         self.webhook_config = webhook_config
-        self.is_sensitive_action = is_sensitive_action
         self.execution_stats: NodeExecutionStats = NodeExecutionStats()
+        self.is_sensitive_action: bool = False
 
         if self.webhook_config:
             if isinstance(self.webhook_config, BlockWebhookConfig):
@@ -623,7 +622,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         input_data: BlockInput,
         *,
         user_id: str,
-        node_id: str,
         node_exec_id: str,
         graph_exec_id: str,
         graph_id: str,
@@ -650,7 +648,6 @@ class Block(ABC, Generic[BlockSchemaInputType, BlockSchemaOutputType]):
         decision = await HITLReviewHelper.handle_review_decision(
             input_data=input_data,
             user_id=user_id,
-            node_id=node_id,
             node_exec_id=node_exec_id,
             graph_exec_id=graph_exec_id,
             graph_id=graph_id,

autogpt_platform/backend/backend/data/human_review.py

@@ -32,87 +32,6 @@ class ReviewResult(BaseModel):
     node_exec_id: str
 
 
-def get_auto_approve_key(graph_exec_id: str, node_id: str) -> str:
-    """Generate the special nodeExecId key for auto-approval records."""
-    return f"auto_approve_{graph_exec_id}_{node_id}"
-
-
-async def check_auto_approval(
-    graph_exec_id: str,
-    node_id: str,
-) -> Optional[ReviewResult]:
-    """
-    Check if there's an existing auto-approval record for this node in this execution.
-
-    Auto-approval records are stored as PendingHumanReview entries with a special
-    nodeExecId pattern: "auto_approve_{graph_exec_id}_{node_id}"
-
-    Args:
-        graph_exec_id: ID of the graph execution
-        node_id: ID of the node definition (not execution)
-
-    Returns:
-        ReviewResult if auto-approval found, None otherwise
-    """
-    auto_approve_key = get_auto_approve_key(graph_exec_id, node_id)
-
-    # Look for the auto-approval record by its special key
-    auto_approved_review = await PendingHumanReview.prisma().find_unique(
-        where={"nodeExecId": auto_approve_key},
-    )
-
-    if auto_approved_review and auto_approved_review.status == ReviewStatus.APPROVED:
-        logger.info(
-            f"Found auto-approval for node {node_id} in execution {graph_exec_id}"
-        )
-        return ReviewResult(
-            data=auto_approved_review.payload,
-            status=ReviewStatus.APPROVED,
-            message="Auto-approved (user approved all future actions for this block)",
-            processed=True,
-            node_exec_id=auto_approve_key,
-        )
-
-    return None
-
-
-async def create_auto_approval_record(
-    user_id: str,
-    graph_exec_id: str,
-    graph_id: str,
-    graph_version: int,
-    node_id: str,
-    payload: SafeJsonData,
-) -> None:
-    """
-    Create an auto-approval record for a node in this execution.
-
-    This is stored as a PendingHumanReview with a special nodeExecId pattern
-    and status=APPROVED, so future executions of the same node can skip review.
-    """
-    auto_approve_key = get_auto_approve_key(graph_exec_id, node_id)
-
-    await PendingHumanReview.prisma().upsert(
-        where={"nodeExecId": auto_approve_key},
-        data={
-            "create": {
-                "nodeExecId": auto_approve_key,
-                "userId": user_id,
-                "graphExecId": graph_exec_id,
-                "graphId": graph_id,
-                "graphVersion": graph_version,
-                "payload": SafeJson(payload),
-                "instructions": "Auto-approval record",
-                "editable": False,
-                "status": ReviewStatus.APPROVED,
-                "processed": True,
-                "reviewedAt": datetime.now(timezone.utc),
-            },
-            "update": {},  # Already exists, no update needed
-        },
-    )
-
-
 async def get_or_create_human_review(
     user_id: str,
     node_exec_id: str,

autogpt_platform/backend/backend/data/human_review_test.py

@@ -46,8 +46,8 @@ async def test_get_or_create_human_review_new(
     sample_db_review.status = ReviewStatus.WAITING
     sample_db_review.processed = False
 
-    mock_prisma = mocker.patch("backend.data.human_review.PendingHumanReview.prisma")
-    mock_prisma.return_value.upsert = AsyncMock(return_value=sample_db_review)
+    mock_upsert = mocker.patch("backend.data.human_review.PendingHumanReview.prisma")
+    mock_upsert.return_value.upsert = AsyncMock(return_value=sample_db_review)
 
     result = await get_or_create_human_review(
         user_id="test-user-123",
@@ -75,8 +75,8 @@ async def test_get_or_create_human_review_approved(
     sample_db_review.processed = False
     sample_db_review.reviewMessage = "Looks good"
 
-    mock_prisma = mocker.patch("backend.data.human_review.PendingHumanReview.prisma")
-    mock_prisma.return_value.upsert = AsyncMock(return_value=sample_db_review)
+    mock_upsert = mocker.patch("backend.data.human_review.PendingHumanReview.prisma")
+    mock_upsert.return_value.upsert = AsyncMock(return_value=sample_db_review)
 
     result = await get_or_create_human_review(
         user_id="test-user-123",

autogpt_platform/backend/migrations/20260121200000_remove_node_execution_fk_from_pending_human_review/migration.sql

@@ -1,7 +0,0 @@
--- Remove NodeExecution foreign key from PendingHumanReview
--- The nodeExecId column remains as the primary key, but we remove the FK constraint
--- to AgentNodeExecution since PendingHumanReview records can persist after node
--- execution records are deleted.
-
--- Drop foreign key constraint that linked PendingHumanReview.nodeExecId to AgentNodeExecution.id
-ALTER TABLE "platform"."PendingHumanReview" DROP CONSTRAINT IF EXISTS "PendingHumanReview_nodeExecId_fkey";

autogpt_platform/backend/schema.prisma

@@ -517,6 +517,8 @@ model AgentNodeExecution {
 
   stats Json?
 
+  PendingHumanReview PendingHumanReview?
+
   @@index([agentGraphExecutionId, agentNodeId, executionStatus])
   @@index([agentNodeId, executionStatus])
   @@index([addedTime, queuedTime])
@@ -565,7 +567,6 @@ enum ReviewStatus {
 }
 
 // Pending human reviews for Human-in-the-loop blocks
-// Also stores auto-approval records with special nodeExecId patterns (e.g., "auto_approve_{graph_exec_id}_{node_id}")
 model PendingHumanReview {
   nodeExecId    String       @id
   userId        String
@@ -584,6 +585,7 @@ model PendingHumanReview {
   reviewedAt    DateTime?
 
   User           User                @relation(fields: [userId], references: [id], onDelete: Cascade)
+  NodeExecution  AgentNodeExecution  @relation(fields: [nodeExecId], references: [id], onDelete: Cascade)
   GraphExecution AgentGraphExecution @relation(fields: [graphExecId], references: [id], onDelete: Cascade)
 
   @@unique([nodeExecId]) // One pending review per node execution

autogpt_platform/frontend/.env.default

@@ -29,4 +29,4 @@ NEXT_PUBLIC_CLOUDFLARE_TURNSTILE_SITE_KEY=
 NEXT_PUBLIC_TURNSTILE=disabled
 
 # PR previews
-NEXT_PUBLIC_PREVIEW_STEALING_DEV=
+NEXT_PUBLIC_PREVIEW_STEALING_DEV=

autogpt_platform/frontend/orval.config.ts

@@ -16,6 +16,12 @@ export default defineConfig({
       client: "react-query",
       httpClient: "fetch",
       indexFiles: false,
+      mock: {
+        type: "msw",
+        baseUrl: "http://localhost:3000/api/proxy",
+        generateEachHttpStatus: true,
+        delay: 0,
+      },
       override: {
         mutator: {
           path: "./mutators/custom-mutator.ts",

autogpt_platform/frontend/package.json

@@ -15,6 +15,8 @@
     "types": "tsc --noEmit",
     "test": "NEXT_PUBLIC_PW_TEST=true next build --turbo && playwright test",
     "test-ui": "NEXT_PUBLIC_PW_TEST=true next build --turbo && playwright test --ui",
+    "test:unit": "vitest run",
+    "test:unit:watch": "vitest",
     "test:no-build": "playwright test",
     "gentests": "playwright codegen http://localhost:3000",
     "storybook": "storybook dev -p 6006",
@@ -118,6 +120,7 @@
   },
   "devDependencies": {
     "@chromatic-com/storybook": "4.1.2",
+    "happy-dom": "20.3.4",
     "@opentelemetry/instrumentation": "0.209.0",
     "@playwright/test": "1.56.1",
     "@storybook/addon-a11y": "9.1.5",
@@ -127,6 +130,8 @@
     "@storybook/nextjs": "9.1.5",
     "@tanstack/eslint-plugin-query": "5.91.2",
     "@tanstack/react-query-devtools": "5.90.2",
+    "@testing-library/dom": "10.4.1",
+    "@testing-library/react": "16.3.2",
     "@types/canvas-confetti": "1.9.0",
     "@types/lodash": "4.17.20",
     "@types/negotiator": "0.6.4",
@@ -135,6 +140,7 @@
     "@types/react-dom": "18.3.5",
     "@types/react-modal": "3.16.3",
     "@types/react-window": "1.8.8",
+    "@vitejs/plugin-react": "5.1.2",
     "axe-playwright": "2.2.2",
     "chromatic": "13.3.3",
     "concurrently": "9.2.1",
@@ -153,7 +159,9 @@
     "require-in-the-middle": "8.0.1",
     "storybook": "9.1.5",
     "tailwindcss": "3.4.17",
-    "typescript": "5.9.3"
+    "typescript": "5.9.3",
+    "vite-tsconfig-paths": "6.0.4",
+    "vitest": "4.0.17"
   },
   "msw": {
     "workerDirectory": [

autogpt_platform/frontend/src/app/(platform)/build/components/FloatingSafeModeToogle.tsx

@@ -86,6 +86,7 @@ export function FloatingSafeModeToggle({
   const {
     currentHITLSafeMode,
     showHITLToggle,
+    isHITLStateUndetermined,
     handleHITLToggle,
     currentSensitiveActionSafeMode,
     showSensitiveActionToggle,
@@ -98,9 +99,16 @@ export function FloatingSafeModeToggle({
     return null;
   }
 
+  const showHITL = showHITLToggle && !isHITLStateUndetermined;
+  const showSensitive = showSensitiveActionToggle;
+
+  if (!showHITL && !showSensitive) {
+    return null;
+  }
+
   return (
     <div className={cn("fixed z-50 flex flex-col gap-2", className)}>
-      {showHITLToggle && (
+      {showHITL && (
         <SafeModeButton
           isEnabled={currentHITLSafeMode}
           label="Human in the loop block approval"
@@ -111,7 +119,7 @@ export function FloatingSafeModeToggle({
           fullWidth={fullWidth}
         />
       )}
-      {showSensitiveActionToggle && (
+      {showSensitive && (
         <SafeModeButton
           isEnabled={currentSensitiveActionSafeMode}
           label="Sensitive actions blocks approval"

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/RunAgentModal.tsx

@@ -14,10 +14,6 @@ import {
 import { Dialog } from "@/components/molecules/Dialog/Dialog";
 import { useEffect, useRef, useState } from "react";
 import { ScheduleAgentModal } from "../ScheduleAgentModal/ScheduleAgentModal";
-import {
-  AIAgentSafetyPopup,
-  useAIAgentSafetyPopup,
-} from "./components/AIAgentSafetyPopup/AIAgentSafetyPopup";
 import { ModalHeader } from "./components/ModalHeader/ModalHeader";
 import { ModalRunSection } from "./components/ModalRunSection/ModalRunSection";
 import { RunActions } from "./components/RunActions/RunActions";
@@ -87,17 +83,8 @@ export function RunAgentModal({
 
   const [isScheduleModalOpen, setIsScheduleModalOpen] = useState(false);
   const [hasOverflow, setHasOverflow] = useState(false);
-  const [isSafetyPopupOpen, setIsSafetyPopupOpen] = useState(false);
-  const [pendingRunAction, setPendingRunAction] = useState<(() => void) | null>(
-    null,
-  );
   const contentRef = useRef<HTMLDivElement>(null);
 
-  const { shouldShowPopup, dismissPopup } = useAIAgentSafetyPopup(
-    agent.has_sensitive_action,
-    agent.has_human_in_the_loop,
-  );
-
   const hasAnySetupFields =
     Object.keys(agentInputFields || {}).length > 0 ||
     Object.keys(agentCredentialsInputFields || {}).length > 0;
@@ -178,24 +165,6 @@ export function RunAgentModal({
     onScheduleCreated?.(schedule);
   }
 
-  function handleRunWithSafetyCheck() {
-    if (shouldShowPopup) {
-      setPendingRunAction(() => handleRun);
-      setIsSafetyPopupOpen(true);
-    } else {
-      handleRun();
-    }
-  }
-
-  function handleSafetyPopupAcknowledge() {
-    setIsSafetyPopupOpen(false);
-    dismissPopup();
-    if (pendingRunAction) {
-      pendingRunAction();
-      setPendingRunAction(null);
-    }
-  }
-
   return (
     <>
       <Dialog
@@ -279,7 +248,7 @@ export function RunAgentModal({
                 )}
                 <RunActions
                   defaultRunType={defaultRunType}
-                  onRun={handleRunWithSafetyCheck}
+                  onRun={handleRun}
                   isExecuting={isExecuting}
                   isSettingUpTrigger={isSettingUpTrigger}
                   isRunReady={allRequiredInputsAreSet}
@@ -297,11 +266,6 @@ export function RunAgentModal({
           </div>
         </Dialog.Content>
       </Dialog>
-
-      <AIAgentSafetyPopup
-        isOpen={isSafetyPopupOpen}
-        onAcknowledge={handleSafetyPopupAcknowledge}
-      />
     </>
   );
 }

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/modals/RunAgentModal/components/AIAgentSafetyPopup/AIAgentSafetyPopup.tsx

@@ -1,95 +0,0 @@
-"use client";
-
-import { Button } from "@/components/atoms/Button/Button";
-import { Text } from "@/components/atoms/Text/Text";
-import { Dialog } from "@/components/molecules/Dialog/Dialog";
-import { Key, storage } from "@/services/storage/local-storage";
-import { ShieldCheckIcon } from "@phosphor-icons/react";
-import { useCallback, useEffect, useState } from "react";
-
-interface Props {
-  onAcknowledge: () => void;
-  isOpen: boolean;
-}
-
-export function AIAgentSafetyPopup({ onAcknowledge, isOpen }: Props) {
-  function handleAcknowledge() {
-    // Mark popup as shown so it won't appear again
-    storage.set(Key.AI_AGENT_SAFETY_POPUP_SHOWN, "true");
-    onAcknowledge();
-  }
-
-  if (!isOpen) return null;
-
-  return (
-    <Dialog
-      controlled={{ isOpen, set: () => {} }}
-      styling={{ maxWidth: "480px" }}
-    >
-      <Dialog.Content>
-        <div className="flex flex-col items-center p-6 text-center">
-          <div className="mb-6 flex h-16 w-16 items-center justify-center rounded-full bg-blue-50">
-            <ShieldCheckIcon
-              weight="fill"
-              size={32}
-              className="text-blue-600"
-            />
-          </div>
-
-          <Text variant="h3" className="mb-4">
-            Safety Checks Enabled
-          </Text>
-
-          <Text variant="body" className="mb-2 text-zinc-700">
-            AI-generated agents may take actions that affect your data or
-            external systems.
-          </Text>
-
-          <Text variant="body" className="mb-8 text-zinc-700">
-            AutoGPT includes safety checks so you&apos;ll always have the
-            opportunity to review and approve sensitive actions before they
-            happen.
-          </Text>
-
-          <Button
-            variant="primary"
-            size="large"
-            className="w-full"
-            onClick={handleAcknowledge}
-          >
-            Got it
-          </Button>
-        </div>
-      </Dialog.Content>
-    </Dialog>
-  );
-}
-
-export function useAIAgentSafetyPopup(
-  hasSensitiveAction: boolean,
-  hasHumanInTheLoop: boolean,
-) {
-  const [shouldShowPopup, setShouldShowPopup] = useState(false);
-  const [hasChecked, setHasChecked] = useState(false);
-
-  useEffect(() => {
-    // Only check once after mount (to avoid SSR issues)
-    if (hasChecked) return;
-
-    const hasSeenPopup =
-      storage.get(Key.AI_AGENT_SAFETY_POPUP_SHOWN) === "true";
-    const isRelevantAgent = hasSensitiveAction || hasHumanInTheLoop;
-
-    setShouldShowPopup(!hasSeenPopup && isRelevantAgent);
-    setHasChecked(true);
-  }, [hasSensitiveAction, hasHumanInTheLoop, hasChecked]);
-
-  const dismissPopup = useCallback(() => {
-    setShouldShowPopup(false);
-  }, []);
-
-  return {
-    shouldShowPopup,
-    dismissPopup,
-  };
-}

autogpt_platform/frontend/src/app/(platform)/library/agents/[id]/components/NewAgentLibraryView/components/selected-views/SelectedRunView/components/SafeModeToggle.tsx

@@ -69,6 +69,7 @@ export function SafeModeToggle({ graph, className }: Props) {
   const {
     currentHITLSafeMode,
     showHITLToggle,
+    isHITLStateUndetermined,
     handleHITLToggle,
     currentSensitiveActionSafeMode,
     showSensitiveActionToggle,
@@ -77,13 +78,20 @@ export function SafeModeToggle({ graph, className }: Props) {
     shouldShowToggle,
   } = useAgentSafeMode(graph);
 
-  if (!shouldShowToggle) {
+  if (!shouldShowToggle || isHITLStateUndetermined) {
+    return null;
+  }
+
+  const showHITL = showHITLToggle && !isHITLStateUndetermined;
+  const showSensitive = showSensitiveActionToggle;
+
+  if (!showHITL && !showSensitive) {
     return null;
   }
 
   return (
     <div className={cn("flex gap-1", className)}>
-      {showHITLToggle && (
+      {showHITL && (
         <SafeModeIconButton
           isEnabled={currentHITLSafeMode}
           label="Human-in-the-loop"
@@ -93,7 +101,7 @@ export function SafeModeToggle({ graph, className }: Props) {
           isPending={isPending}
         />
       )}
-      {showSensitiveActionToggle && (
+      {showSensitive && (
         <SafeModeIconButton
           isEnabled={currentSensitiveActionSafeMode}
           label="Sensitive actions"

autogpt_platform/frontend/src/app/api/openapi.json

@@ -9425,12 +9425,6 @@
             "type": "array",
             "title": "Reviews",
             "description": "All reviews with their approval status, data, and messages"
-          },
-          "auto_approve_future_actions": {
-            "type": "boolean",
-            "title": "Auto Approve Future Actions",
-            "description": "If true, future reviews from the same blocks (nodes) being approved will be automatically approved for the remainder of this execution. This only affects the current execution run.",
-            "default": false
           }
         },
         "type": "object",

autogpt_platform/frontend/src/components/atoms/Badge/Badge.test.tsx

@@ -1,81 +0,0 @@
-// import { render, screen } from "@testing-library/react";
-// import { describe, expect, it } from "vitest";
-// import { Badge } from "./Badge";
-
-// describe("Badge Component", () => {
-//   it("renders badge with content", () => {
-//     render(<Badge variant="success">Success</Badge>);
-
-//     expect(screen.getByText("Success")).toBeInTheDocument();
-//   });
-
-//   it("applies correct variant styles", () => {
-//     const { rerender } = render(<Badge variant="success">Success</Badge>);
-//     let badge = screen.getByText("Success");
-//     expect(badge).toHaveClass("bg-green-100", "text-green-800");
-
-//     rerender(<Badge variant="error">Error</Badge>);
-//     badge = screen.getByText("Error");
-//     expect(badge).toHaveClass("bg-red-100", "text-red-800");
-
-//     rerender(<Badge variant="info">Info</Badge>);
-//     badge = screen.getByText("Info");
-//     expect(badge).toHaveClass("bg-slate-100", "text-slate-800");
-//   });
-
-//   it("applies custom className", () => {
-//     render(
-//       <Badge variant="success" className="custom-class">
-//         Success
-//       </Badge>,
-//     );
-
-//     const badge = screen.getByText("Success");
-//     expect(badge).toHaveClass("custom-class");
-//   });
-
-//   it("renders as span element", () => {
-//     render(<Badge variant="success">Success</Badge>);
-
-//     const badge = screen.getByText("Success");
-//     expect(badge.tagName).toBe("SPAN");
-//   });
-
-//   it("renders children correctly", () => {
-//     render(
-//       <Badge variant="success">
-//         <span>Custom</span> Content
-//       </Badge>,
-//     );
-
-//     expect(screen.getByText("Custom")).toBeInTheDocument();
-//     expect(screen.getByText("Content")).toBeInTheDocument();
-//   });
-
-//   it("supports all badge variants", () => {
-//     const variants = ["success", "error", "info"] as const;
-
-//     variants.forEach((variant) => {
-//       const { unmount } = render(
-//         <Badge variant={variant} data-testid={`badge-${variant}`}>
-//           {variant}
-//         </Badge>,
-//       );
-
-//       expect(screen.getByTestId(`badge-${variant}`)).toBeInTheDocument();
-//       unmount();
-//     });
-//   });
-
-//   it("handles long text content", () => {
-//     render(
-//       <Badge variant="info">
-//         Very long text that should be handled properly by the component
-//       </Badge>,
-//     );
-
-//     const badge = screen.getByText(/Very long text/);
-//     expect(badge).toBeInTheDocument();
-//     expect(badge).toHaveClass("overflow-hidden", "text-ellipsis");
-//   });
-// });

autogpt_platform/frontend/src/components/organisms/FloatingReviewsPanel/FloatingReviewsPanel.tsx

@@ -31,29 +31,6 @@ export function FloatingReviewsPanel({
       query: {
         enabled: !!(graphId && executionId),
         select: okData,
-        // Poll while execution is in progress to detect status changes
-        refetchInterval: (q) => {
-          // Note: refetchInterval callback receives raw data before select transform
-          const rawData = q.state.data as
-            | { status: number; data?: { status?: string } }
-            | undefined;
-          if (rawData?.status !== 200) return false;
-
-          const status = rawData?.data?.status;
-          if (!status) return false;
-
-          // Poll every 2 seconds while running or in review
-          if (
-            status === AgentExecutionStatus.RUNNING ||
-            status === AgentExecutionStatus.QUEUED ||
-            status === AgentExecutionStatus.INCOMPLETE ||
-            status === AgentExecutionStatus.REVIEW
-          ) {
-            return 2000;
-          }
-          return false;
-        },
-        refetchIntervalInBackground: true,
       },
     },
   );
@@ -63,27 +40,23 @@ export function FloatingReviewsPanel({
     useShallow((state) => state.graphExecutionStatus),
   );
 
-  // Determine if we should poll for pending reviews
-  const isInReviewStatus =
-    executionDetails?.status === AgentExecutionStatus.REVIEW ||
-    graphExecutionStatus === AgentExecutionStatus.REVIEW;
-
   const { pendingReviews, isLoading, refetch } = usePendingReviewsForExecution(
     executionId || "",
-    {
-      enabled: !!executionId,
-      // Poll every 2 seconds when in REVIEW status to catch new reviews
-      refetchInterval: isInReviewStatus ? 2000 : false,
-    },
   );
 
-  // Refetch pending reviews when execution status changes
   useEffect(() => {
-    if (executionId && executionDetails?.status) {
+    if (executionId) {
       refetch();
     }
   }, [executionDetails?.status, executionId, refetch]);
 
+  // Refetch when graph execution status changes to REVIEW
+  useEffect(() => {
+    if (graphExecutionStatus === AgentExecutionStatus.REVIEW && executionId) {
+      refetch();
+    }
+  }, [graphExecutionStatus, executionId, refetch]);
+
   if (
     !executionId ||
     (!isLoading &&

autogpt_platform/frontend/src/components/organisms/PendingReviewsList/PendingReviewsList.tsx

@@ -1,9 +1,8 @@
-import { useState, useCallback } from "react";
+import { useState } from "react";
 import { PendingHumanReviewModel } from "@/app/api/__generated__/models/pendingHumanReviewModel";
 import { PendingReviewCard } from "@/components/organisms/PendingReviewCard/PendingReviewCard";
 import { Text } from "@/components/atoms/Text/Text";
 import { Button } from "@/components/atoms/Button/Button";
-import { Switch } from "@/components/atoms/Switch/Switch";
 import { useToast } from "@/components/molecules/Toast/use-toast";
 import { ClockIcon, WarningIcon } from "@phosphor-icons/react";
 import { usePostV2ProcessReviewAction } from "@/app/api/__generated__/endpoints/executions/executions";
@@ -41,8 +40,6 @@ export function PendingReviewsList({
     "approve" | "reject" | null
   >(null);
 
-  const [autoApproveFuture, setAutoApproveFuture] = useState(false);
-
   const { toast } = useToast();
 
   const reviewActionMutation = usePostV2ProcessReviewAction({
@@ -95,26 +92,6 @@ export function PendingReviewsList({
     setReviewMessageMap((prev) => ({ ...prev, [nodeExecId]: message }));
   }
 
-  // Reset data to original values when toggling auto-approve
-  const handleAutoApproveFutureToggle = useCallback(
-    (enabled: boolean) => {
-      setAutoApproveFuture(enabled);
-      if (enabled) {
-        // Reset all data to original values
-        const originalData: Record<string, string> = {};
-        reviews.forEach((review) => {
-          originalData[review.node_exec_id] = JSON.stringify(
-            review.payload,
-            null,
-            2,
-          );
-        });
-        setReviewDataMap(originalData);
-      }
-    },
-    [reviews],
-  );
-
   function processReviews(approved: boolean) {
     if (reviews.length === 0) {
       toast({
@@ -132,31 +109,22 @@ export function PendingReviewsList({
       const reviewData = reviewDataMap[review.node_exec_id];
       const reviewMessage = reviewMessageMap[review.node_exec_id];
 
-      // When auto-approving future actions, send undefined (use original data)
-      // Otherwise, parse and send the edited data if available
-      let parsedData: any = undefined;
+      let parsedData: any = review.payload; // Default to original payload
 
-      if (!autoApproveFuture) {
-        // For regular approve/reject, use edited data if available
-        if (review.editable && reviewData) {
-          try {
-            parsedData = JSON.parse(reviewData);
-          } catch (error) {
-            toast({
-              title: "Invalid JSON",
-              description: `Please fix the JSON format in review for node ${review.node_exec_id}: ${error instanceof Error ? error.message : "Invalid syntax"}`,
-              variant: "destructive",
-            });
-            setPendingAction(null);
-            return;
-          }
-        } else {
-          // No edits, use original payload
-          parsedData = review.payload;
+      // Parse edited data if available and editable
+      if (review.editable && reviewData) {
+        try {
+          parsedData = JSON.parse(reviewData);
+        } catch (error) {
+          toast({
+            title: "Invalid JSON",
+            description: `Please fix the JSON format in review for node ${review.node_exec_id}: ${error instanceof Error ? error.message : "Invalid syntax"}`,
+            variant: "destructive",
+          });
+          setPendingAction(null);
+          return;
         }
       }
-      // When autoApproveFuture is true, parsedData stays undefined
-      // Backend will use the original payload stored in the database
 
       reviewItems.push({
         node_exec_id: review.node_exec_id,
@@ -169,7 +137,6 @@ export function PendingReviewsList({
     reviewActionMutation.mutate({
       data: {
         reviews: reviewItems,
-        auto_approve_future_actions: autoApproveFuture && approved,
       },
     });
   }
@@ -215,37 +182,21 @@ export function PendingReviewsList({
       <div className="space-y-7">
         {reviews.map((review) => (
           <PendingReviewCard
-            key={`${review.node_exec_id}-${autoApproveFuture}`}
+            key={review.node_exec_id}
             review={review}
             onReviewDataChange={handleReviewDataChange}
             onReviewMessageChange={handleReviewMessageChange}
             reviewMessage={reviewMessageMap[review.node_exec_id] || ""}
-            isDisabled={autoApproveFuture}
           />
         ))}
       </div>
 
-      <div className="space-y-4">
-        {/* Auto-approve toggle */}
-        <div className="flex items-center gap-3">
-          <Switch
-            checked={autoApproveFuture}
-            onCheckedChange={handleAutoApproveFutureToggle}
-            disabled={reviewActionMutation.isPending}
-          />
-          <Text variant="body" className="text-textBlack">
-            Auto-approve all future actions from these blocks
-          </Text>
-        </div>
+      <div className="space-y-7">
+        <Text variant="body" className="text-textGrey">
+          Note: Changes you make here apply only to this task
+        </Text>
 
-        {autoApproveFuture && (
-          <Text variant="small" className="text-amber-600">
-            Editing is disabled. Original data will be used for this and all
-            future reviews from these blocks.
-          </Text>
-        )}
-
-        <div className="flex flex-wrap gap-2">
+        <div className="flex gap-2">
           <Button
             onClick={() => processReviews(true)}
             disabled={reviewActionMutation.isPending || reviews.length === 0}
@@ -269,11 +220,6 @@ export function PendingReviewsList({
             Reject
           </Button>
         </div>
-
-        <Text variant="small" className="text-textGrey">
-          You can turn auto-approval on or off anytime in this agent&apos;s
-          settings.
-        </Text>
       </div>
     </div>
   );

autogpt_platform/frontend/src/hooks/usePendingReviews.ts

@@ -15,22 +15,8 @@ export function usePendingReviews() {
   };
 }
 
-interface UsePendingReviewsForExecutionOptions {
-  enabled?: boolean;
-  refetchInterval?: number | false;
-}
-
-export function usePendingReviewsForExecution(
-  graphExecId: string,
-  options?: UsePendingReviewsForExecutionOptions,
-) {
-  const query = useGetV2GetPendingReviewsForExecution(graphExecId, {
-    query: {
-      enabled: options?.enabled ?? !!graphExecId,
-      refetchInterval: options?.refetchInterval,
-      refetchIntervalInBackground: !!options?.refetchInterval,
-    },
-  });
+export function usePendingReviewsForExecution(graphExecId: string) {
+  const query = useGetV2GetPendingReviewsForExecution(graphExecId);
 
   return {
     pendingReviews: okData(query.data) || [],

autogpt_platform/frontend/src/mocks/index.ts

@@ -0,0 +1,13 @@
+// We are not using this for tests because Vitest runs our tests in a Node.js environment.
+// However, we can use it for development purposes to test our UI in the browser with fake data.
+export async function initMocks() {
+  if (typeof window === "undefined") {
+    const { server } = await import("./mock-server");
+    server.listen({ onUnhandledRequest: "bypass" });
+    console.log("[MSW] Server mock initialized");
+  } else {
+    const { worker } = await import("./mock-browser");
+    await worker.start({ onUnhandledRequest: "bypass" });
+    console.log("[MSW] Browser mock initialized");
+  }
+}

autogpt_platform/frontend/src/mocks/mock-browser.ts

@@ -0,0 +1,4 @@
+import { setupWorker } from "msw/browser";
+import { mockHandlers } from "./mock-handlers";
+
+export const worker = setupWorker(...mockHandlers);

autogpt_platform/frontend/src/mocks/mock-handlers.ts

@@ -0,0 +1,48 @@
+import { getAdminMock } from "@/app/api/__generated__/endpoints/admin/admin.msw";
+import { getAnalyticsMock } from "@/app/api/__generated__/endpoints/analytics/analytics.msw";
+import { getApiKeysMock } from "@/app/api/__generated__/endpoints/api-keys/api-keys.msw";
+import { getAuthMock } from "@/app/api/__generated__/endpoints/auth/auth.msw";
+import { getBlocksMock } from "@/app/api/__generated__/endpoints/blocks/blocks.msw";
+import { getChatMock } from "@/app/api/__generated__/endpoints/chat/chat.msw";
+import { getCreditsMock } from "@/app/api/__generated__/endpoints/credits/credits.msw";
+import { getDefaultMock } from "@/app/api/__generated__/endpoints/default/default.msw";
+import { getEmailMock } from "@/app/api/__generated__/endpoints/email/email.msw";
+import { getExecutionsMock } from "@/app/api/__generated__/endpoints/executions/executions.msw";
+import { getFilesMock } from "@/app/api/__generated__/endpoints/files/files.msw";
+import { getGraphsMock } from "@/app/api/__generated__/endpoints/graphs/graphs.msw";
+import { getHealthMock } from "@/app/api/__generated__/endpoints/health/health.msw";
+import { getIntegrationsMock } from "@/app/api/__generated__/endpoints/integrations/integrations.msw";
+import { getLibraryMock } from "@/app/api/__generated__/endpoints/library/library.msw";
+import { getMetricsMock } from "@/app/api/__generated__/endpoints/metrics/metrics.msw";
+import { getOauthMock } from "@/app/api/__generated__/endpoints/oauth/oauth.msw";
+import { getOnboardingMock } from "@/app/api/__generated__/endpoints/onboarding/onboarding.msw";
+import { getOttoMock } from "@/app/api/__generated__/endpoints/otto/otto.msw";
+import { getPresetsMock } from "@/app/api/__generated__/endpoints/presets/presets.msw";
+import { getSchedulesMock } from "@/app/api/__generated__/endpoints/schedules/schedules.msw";
+import { getStoreMock } from "@/app/api/__generated__/endpoints/store/store.msw";
+
+// Pass hard-coded data to individual handler functions to override faker-generated data.
+export const mockHandlers = [
+  ...getAdminMock(),
+  ...getAnalyticsMock(),
+  ...getApiKeysMock(),
+  ...getAuthMock(),
+  ...getBlocksMock(),
+  ...getChatMock(),
+  ...getCreditsMock(),
+  ...getDefaultMock(),
+  ...getEmailMock(),
+  ...getExecutionsMock(),
+  ...getFilesMock(),
+  ...getGraphsMock(),
+  ...getHealthMock(),
+  ...getIntegrationsMock(),
+  ...getLibraryMock(),
+  ...getMetricsMock(),
+  ...getOauthMock(),
+  ...getOnboardingMock(),
+  ...getOttoMock(),
+  ...getPresetsMock(),
+  ...getSchedulesMock(),
+  ...getStoreMock(),
+];

autogpt_platform/frontend/src/mocks/mock-server.ts

@@ -0,0 +1,4 @@
+import { setupServer } from "msw/node";
+import { mockHandlers } from "./mock-handlers";
+
+export const server = setupServer(...mockHandlers);

autogpt_platform/frontend/src/services/storage/local-storage.ts

@@ -10,7 +10,6 @@ export enum Key {
   LIBRARY_AGENTS_CACHE = "library-agents-cache",
   CHAT_SESSION_ID = "chat_session_id",
   COOKIE_CONSENT = "autogpt_cookie_consent",
-  AI_AGENT_SAFETY_POPUP_SHOWN = "ai-agent-safety-popup-shown",
 }
 
 function get(key: Key) {

autogpt_platform/frontend/src/tests/CLAUDE.md

@@ -0,0 +1,220 @@
+# Frontend Testing Rules 🧪
+
+## Testing Types Overview
+
+| Type            | Tool                  | Speed           | Purpose                          |
+| --------------- | --------------------- | --------------- | -------------------------------- |
+| **E2E**         | Playwright            | Slow (~5s/test) | Real browser, full user journeys |
+| **Integration** | Vitest + RTL          | Fast (~100ms)   | Component + mocked API           |
+| **Unit**        | Vitest + RTL          | Fastest (~10ms) | Individual functions/components  |
+| **Visual**      | Storybook + Chromatic | N/A             | UI appearance, design system     |
+
+---
+
+## When to Use Each
+
+### ✅ E2E Tests (Playwright)
+
+**Use for:** Critical user journeys that MUST work in a real browser.
+
+- Authentication flows (login, signup, logout)
+- Payment or sensitive transactions
+- Flows requiring real browser APIs (clipboard, downloads)
+- Cross-page navigation that must work end-to-end
+
+**Location:** `src/tests/*.spec.ts` (centralized, as there will be fewer of them)
+
+### ✅ Integration Tests (Vitest + RTL)
+
+**Use for:** Testing components with their dependencies (API calls, state).
+
+- Page-level behavior with mocked API responses
+- Components that fetch data
+- User interactions that trigger API calls
+- Feature flows within a single page
+
+**Location:** Place tests in a `__tests__` folder next to the component:
+
+```
+ComponentName/
+  __tests__/
+    main.test.tsx
+    some-flow.test.tsx
+  ComponentName.tsx
+  useComponentName.ts
+```
+
+**Start at page level:** Initially write integration tests at the "page" level. No need to write them for every small component.
+
+```
+/library/
+  __tests__/
+    main.test.tsx
+    searching-agents.test.tsx
+    agents-pagination.test.tsx
+  page.tsx
+  useLibraryPage.ts
+```
+
+Start with a `main.test.tsx` file and split into smaller files as it grows.
+
+**What integration tests should do:**
+
+1. Render a page or complex modal (e.g., `AgentPublishModal`)
+2. Mock API requests via MSW
+3. Assert UI scenarios via Testing Library
+
+```tsx
+// Example: Test page renders data from API
+import { server } from "@/mocks/mock-server";
+import { getDeleteV2DeleteStoreSubmissionMockHandler422 } from "@/app/api/__generated__/endpoints/store/store.msw";
+
+test("shows error when submission fails", async () => {
+  // Override default handler to return error status
+  server.use(getDeleteV2DeleteStoreSubmissionMockHandler422());
+
+  render(<MarketplacePage />);
+  await screen.findByText("Featured Agents");
+  // ... assert error UI
+});
+```
+
+**Tip:** Use `findBy...` methods most of the time—they wait for elements to appear, so async code won't cause flaky tests. The regular `getBy...` methods don't wait and error immediately.
+
+### ✅ Unit Tests (Vitest + RTL)
+
+**Use for:** Testing isolated components and utility functions.
+
+- Pure utility functions (`lib/utils.ts`)
+- Component rendering with various props
+- Component state changes
+- Custom hooks
+
+**Location:** Co-located with the file: `Component.test.tsx` next to `Component.tsx`
+
+```tsx
+// Example: Test component renders correctly
+render(<AgentCard title="My Agent" />);
+expect(screen.getByText("My Agent")).toBeInTheDocument();
+```
+
+### ✅ Storybook Tests (Visual)
+
+**Use for:** Design system, visual appearance, component documentation.
+
+- Atoms (Button, Input, Badge)
+- Molecules (Dialog, Card)
+- Visual states (hover, disabled, loading)
+- Responsive layouts
+
+**Location:** Co-located: `Component.stories.tsx` next to `Component.tsx`
+
+---
+
+## Decision Flowchart
+
+```
+Does it need a REAL browser/backend?
+├─ YES → E2E (Playwright)
+└─ NO
+   └─ Does it involve API calls or complex state?
+      ├─ YES → Integration (Vitest + RTL)
+      └─ NO
+         └─ Is it about visual appearance?
+            ├─ YES → Storybook
+            └─ NO → Unit (Vitest + RTL)
+```
+
+---
+
+## What NOT to Test
+
+❌ Third-party library internals (Radix UI, React Query)  
+❌ CSS styling details (use Storybook)  
+❌ Simple prop-passing components with no logic  
+❌ TypeScript types
+
+---
+
+## File Organization
+
+```
+src/
+├── components/
+│   └── atoms/
+│       └── Button/
+│           ├── Button.tsx
+│           ├── Button.test.tsx      # Unit test
+│           └── Button.stories.tsx   # Visual test
+├── app/
+│   └── (platform)/
+│       └── marketplace/
+│           └── components/
+│               └── MainMarketplacePage/
+│                   ├── __tests__/
+│                   │   ├── main.test.tsx           # Integration test
+│                   │   └── search-agents.test.tsx  # Integration test
+│                   ├── MainMarketplacePage.tsx
+│                   └── useMainMarketplacePage.ts
+├── lib/
+│   ├── utils.ts
+│   └── utils.test.ts                # Unit test
+├── mocks/
+│   ├── mock-handlers.ts             # MSW handlers (auto-generated via Orval)
+│   └── mock-server.ts               # MSW server setup
+└── tests/
+    ├── integrations/
+    │   ├── test-utils.tsx           # Testing utilities
+    │   └── vitest.setup.tsx         # Integration test setup
+    └── *.spec.ts                    # E2E tests (Playwright) - centralized
+```
+
+---
+
+## Priority Matrix
+
+| Component Type      | Test Priority | Recommended Test |
+| ------------------- | ------------- | ---------------- |
+| Pages/Features      | **Highest**   | Integration      |
+| Custom Hooks        | High          | Unit             |
+| Utility Functions   | High          | Unit             |
+| Organisms (complex) | High          | Integration      |
+| Molecules           | Medium        | Unit + Storybook |
+| Atoms               | Medium        | Storybook only\* |
+
+\*Atoms are typically simple enough that Storybook visual tests suffice.
+
+---
+
+## MSW Mocking
+
+API mocking is handled via MSW (Mock Service Worker). Handlers are auto-generated by Orval from the OpenAPI schema.
+
+**Default behavior:** All client-side requests are intercepted and return 200 status with faker-generated data.
+
+**Override for specific tests:** Use generated error handlers to test non-OK status scenarios:
+
+```tsx
+import { server } from "@/mocks/mock-server";
+import { getDeleteV2DeleteStoreSubmissionMockHandler422 } from "@/app/api/__generated__/endpoints/store/store.msw";
+
+test("shows error when deletion fails", async () => {
+  server.use(getDeleteV2DeleteStoreSubmissionMockHandler422());
+
+  render(<MyComponent />);
+  // ... assert error UI
+});
+```
+
+**Generated handlers location:** `src/app/api/__generated__/endpoints/*/` - each endpoint has handlers for different status codes.
+
+---
+
+## Golden Rules
+
+1. **Test behavior, not implementation** - Query by role/text, not class names
+2. **One assertion per concept** - Tests should be focused
+3. **Mock at boundaries** - Mock API calls, not internal functions
+4. **Co-locate integration tests** - Keep `__tests__/` folder next to the component
+5. **E2E is expensive** - Only for critical happy paths; prefer integration tests
+6. **AI agents are good at writing integration tests** - Start with these when adding test coverage

autogpt_platform/frontend/src/tests/integrations/mock-supabase-request.tsx

@@ -0,0 +1,25 @@
+import { vi } from "vitest";
+
+const mockSupabaseClient = {
+  auth: {
+    getUser: vi.fn().mockResolvedValue({
+      data: { user: null },
+      error: null,
+    }),
+    getSession: vi.fn().mockResolvedValue({
+      data: { session: null },
+      error: null,
+    }),
+    signOut: vi.fn().mockResolvedValue({ error: null }),
+    refreshSession: vi.fn().mockResolvedValue({
+      data: { session: null, user: null },
+      error: null,
+    }),
+  },
+};
+
+export const mockSupabaseRequest = () => {
+  vi.mock("@/lib/supabase/server/getServerSupabase", () => ({
+    getServerSupabase: vi.fn().mockResolvedValue(mockSupabaseClient),
+  }));
+};

autogpt_platform/frontend/src/tests/integrations/setup-nextjs-mocks.tsx

@@ -0,0 +1,63 @@
+import { vi } from "vitest";
+
+export const mockNextjsModules = () => {
+  vi.mock("next/image", () => ({
+    __esModule: true,
+    default: ({
+      fill: _fill,
+      priority: _priority,
+      quality: _quality,
+      placeholder: _placeholder,
+      blurDataURL: _blurDataURL,
+      loader: _loader,
+      ...props
+    }: any) => {
+      // eslint-disable-next-line jsx-a11y/alt-text, @next/next/no-img-element
+      return <img {...props} />;
+    },
+  }));
+
+  vi.mock("next/headers", () => ({
+    cookies: vi.fn(() => ({
+      get: vi.fn(() => undefined),
+      getAll: vi.fn(() => []),
+      set: vi.fn(),
+      delete: vi.fn(),
+      has: vi.fn(() => false),
+    })),
+    headers: vi.fn(() => new Headers()),
+  }));
+
+  vi.mock("next/dist/server/request/cookies", () => ({
+    cookies: vi.fn(() => ({
+      get: vi.fn(() => undefined),
+      getAll: vi.fn(() => []),
+      set: vi.fn(),
+      delete: vi.fn(),
+      has: vi.fn(() => false),
+    })),
+  }));
+
+  vi.mock("next/navigation", () => ({
+    useRouter: () => ({
+      push: vi.fn(),
+      replace: vi.fn(),
+      prefetch: vi.fn(),
+      back: vi.fn(),
+      forward: vi.fn(),
+      refresh: vi.fn(),
+    }),
+    usePathname: () => "/marketplace",
+    useSearchParams: () => new URLSearchParams(),
+    useParams: () => ({}),
+  }));
+
+  vi.mock("next/link", () => ({
+    __esModule: true,
+    default: ({ children, href, ...props }: any) => (
+      <a href={href} {...props}>
+        {children}
+      </a>
+    ),
+  }));
+};

autogpt_platform/frontend/src/tests/integrations/test-utils.tsx

@@ -0,0 +1,36 @@
+import { BackendAPIProvider } from "@/lib/autogpt-server-api/context";
+import OnboardingProvider from "@/providers/onboarding/onboarding-provider";
+import { QueryClient, QueryClientProvider } from "@tanstack/react-query";
+import { render, RenderOptions } from "@testing-library/react";
+import { ReactElement, ReactNode } from "react";
+
+function createTestQueryClient() {
+  return new QueryClient({
+    defaultOptions: {
+      queries: {
+        retry: false,
+      },
+    },
+  });
+}
+
+function TestProviders({ children }: { children: ReactNode }) {
+  const queryClient = createTestQueryClient();
+  return (
+    <QueryClientProvider client={queryClient}>
+      <BackendAPIProvider>
+        <OnboardingProvider>{children}</OnboardingProvider>
+      </BackendAPIProvider>
+    </QueryClientProvider>
+  );
+}
+
+function customRender(
+  ui: ReactElement,
+  options?: Omit<RenderOptions, "wrapper">,
+) {
+  return render(ui, { wrapper: TestProviders, ...options });
+}
+
+export * from "@testing-library/react";
+export { customRender as render };

autogpt_platform/frontend/src/tests/integrations/vitest.setup.tsx

@@ -0,0 +1,12 @@
+import { beforeAll, afterAll, afterEach } from "vitest";
+import { server } from "@/mocks/mock-server";
+import { mockNextjsModules } from "./setup-nextjs-mocks";
+import { mockSupabaseRequest } from "./mock-supabase-request";
+
+beforeAll(() => {
+  mockNextjsModules();
+  mockSupabaseRequest(); // If you need user's data - please mock supabase actions in your specific test - it sends null user [It's only to avoid cookies() call]
+  return server.listen({ onUnhandledRequest: "error" });
+});
+afterEach(() => server.resetHandlers());
+afterAll(() => server.close());

autogpt_platform/frontend/vitest.config.mts

@@ -0,0 +1,12 @@
+import { defineConfig } from "vitest/config";
+import react from "@vitejs/plugin-react";
+import tsconfigPaths from "vite-tsconfig-paths";
+
+export default defineConfig({
+  plugins: [tsconfigPaths(), react()],
+  test: {
+    environment: "happy-dom",
+    include: ["src/**/*.test.tsx"],
+    setupFiles: ["./src/tests/integrations/vitest.setup.tsx"],
+  },
+});