feat(platform): Add execution analytics admin endpoint with feature flag bypass (#11327)

This PR adds a comprehensive execution analytics admin endpoint that
generates AI-powered activity summaries and correctness scores for graph
executions, with proper feature flag bypass for admin use.

### Changes 🏗️

**Backend Changes:**
- Added admin endpoint: `/api/executions/admin/execution_analytics`
- Implemented feature flag bypass with `skip_feature_flag=True`
parameter for admin operations
- Fixed async database client usage (`get_db_async_client`) to resolve
async/await errors
- Added batch processing with configurable size limits to handle large
datasets
- Comprehensive error handling and logging for troubleshooting
- Renamed entire feature from "Activity Backfill" to "Execution
Analytics" for clarity

**Frontend Changes:**
- Created clean admin UI for execution analytics generation at
`/admin/execution-analytics`
- Built form with graph ID input, model selection dropdown, and optional
filters
- Implemented results table with status badges and detailed execution
information
- Added CSV export functionality for analytics results
- Integrated with generated TypeScript API client for proper
authentication
- Added proper error handling with toast notifications and loading
states

**Database & API:**
- Fixed critical async/await issue by switching from sync to async
database client
- Updated router configuration and endpoint naming for consistency
- Generated proper TypeScript types and API client integration
- Applied feature flag filtering at API level while bypassing for admin
operations

### 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:

**Test Plan:**
- [x] Admin can access execution analytics page at
`/admin/execution-analytics`
- [x] Form validation works correctly (requires graph ID, validates
inputs)
- [x] API endpoint `/api/executions/admin/execution_analytics` responds
correctly
- [x] Authentication works properly through generated API client
- [x] Analytics generation works with different LLM models (gpt-4o-mini,
gpt-4o, etc.)
- [x] Results display correctly with appropriate status badges
(success/failed/skipped)
- [x] CSV export functionality downloads correct data
- [x] Error handling displays appropriate toast messages
- [x] Feature flag bypass works for admin users (generates analytics
regardless of user flags)
- [x] Batch processing handles multiple executions correctly
- [x] Loading states show proper feedback during processing

#### For configuration changes:
- [x] `.env.default` is updated or already compatible with my changes
- [x] `docker-compose.yml` is updated or already compatible with my
changes
- [x] No configuration changes required for this feature

**Related to:** PR #11325 (base correctness score functionality)

🤖 Generated with [Claude Code](https://claude.ai/code)

---------

Co-authored-by: Claude <[email protected]>
Co-authored-by: claude[bot] <41898282+claude[bot]@users.noreply.github.com>
Co-authored-by: Zamil Majdy <[email protected]>

Author: 3 people

autogpt_platform/backend/backend/data/execution.py

@@ -194,6 +194,12 @@ def to_db(self) -> GraphExecutionStats:
                 correctness_score=self.correctness_score,
             )
 
+        def without_activity_features(self) -> "GraphExecutionMeta.Stats":
+            """Return a copy of stats with activity features (activity_status, correctness_score) set to None."""
+            return self.model_copy(
+                update={"activity_status": None, "correctness_score": None}
+            )
+
     stats: Stats | None
 
     @staticmethod

autogpt_platform/backend/backend/executor/activity_status_generator.py

@@ -91,6 +91,8 @@ async def generate_activity_status_for_execution(
     db_client: "DatabaseManagerAsyncClient",
     user_id: str,
     execution_status: ExecutionStatus | None = None,
+    model_name: str = "gpt-4o-mini",
+    skip_feature_flag: bool = False,
 ) -> ActivityStatusResponse | None:
     """
     Generate an AI-based activity status summary and correctness assessment for a graph execution.
@@ -112,7 +114,9 @@ async def generate_activity_status_for_execution(
         or None if feature is disabled
     """
     # Check LaunchDarkly feature flag for AI activity status generation with full context support
-    if not await is_feature_enabled(Flag.AI_ACTIVITY_STATUS, user_id):
+    if not skip_feature_flag and not await is_feature_enabled(
+        Flag.AI_ACTIVITY_STATUS, user_id
+    ):
         logger.debug("AI activity status generation is disabled via LaunchDarkly")
         return None
 
@@ -273,7 +277,7 @@ async def generate_activity_status_for_execution(
             prompt=prompt[1]["content"],  # User prompt content
             sys_prompt=prompt[0]["content"],  # System prompt content
             expected_format=expected_format,
-            model=LlmModel.GPT4O_MINI,
+            model=LlmModel(model_name),
             credentials=credentials_input,  # type: ignore
             max_tokens=150,
             retry=3,
@@ -306,7 +310,7 @@ async def generate_activity_status_for_execution(
         return activity_response
 
     except Exception as e:
-        logger.error(
+        logger.exception(
             f"Failed to generate activity status for execution {graph_exec_id}: {str(e)}"
         )
         return None

autogpt_platform/backend/backend/server/rest_api.py

@@ -24,6 +24,7 @@
 import backend.server.routers.postmark.postmark
 import backend.server.routers.v1
 import backend.server.v2.admin.credit_admin_routes
+import backend.server.v2.admin.execution_analytics_routes
 import backend.server.v2.admin.store_admin_routes
 import backend.server.v2.builder
 import backend.server.v2.builder.routes
@@ -269,6 +270,11 @@ async def validation_error_handler(
     tags=["v2", "admin"],
     prefix="/api/credits",
 )
+app.include_router(
+    backend.server.v2.admin.execution_analytics_routes.router,
+    tags=["v2", "admin"],
+    prefix="/api/executions",
+)
 app.include_router(
     backend.server.v2.library.routes.router, tags=["v2"], prefix="/api/library"
 )

autogpt_platform/backend/backend/server/routers/v1.py

@@ -89,6 +89,7 @@
 from backend.util.clients import get_scheduler_client
 from backend.util.cloud_storage import get_cloud_storage_handler
 from backend.util.exceptions import GraphValidationError, NotFoundError
+from backend.util.feature_flag import Flag, is_feature_enabled
 from backend.util.json import dumps
 from backend.util.settings import Settings
 from backend.util.timezone_utils import (
@@ -109,6 +110,39 @@ def _create_file_size_error(size_bytes: int, max_size_mb: int) -> HTTPException:
 settings = Settings()
 logger = logging.getLogger(__name__)
 
+
+async def hide_activity_summaries_if_disabled(
+    executions: list[execution_db.GraphExecutionMeta], user_id: str
+) -> list[execution_db.GraphExecutionMeta]:
+    """Hide activity summaries and scores if AI_ACTIVITY_STATUS feature is disabled."""
+    if await is_feature_enabled(Flag.AI_ACTIVITY_STATUS, user_id):
+        return executions  # Return as-is if feature is enabled
+
+    # Filter out activity features if disabled
+    filtered_executions = []
+    for execution in executions:
+        if execution.stats:
+            filtered_stats = execution.stats.without_activity_features()
+            execution = execution.model_copy(update={"stats": filtered_stats})
+        filtered_executions.append(execution)
+    return filtered_executions
+
+
+async def hide_activity_summary_if_disabled(
+    execution: execution_db.GraphExecution | execution_db.GraphExecutionWithNodes,
+    user_id: str,
+) -> execution_db.GraphExecution | execution_db.GraphExecutionWithNodes:
+    """Hide activity summary and score for a single execution if AI_ACTIVITY_STATUS feature is disabled."""
+    if await is_feature_enabled(Flag.AI_ACTIVITY_STATUS, user_id):
+        return execution  # Return as-is if feature is enabled
+
+    # Filter out activity features if disabled
+    if execution.stats:
+        filtered_stats = execution.stats.without_activity_features()
+        return execution.model_copy(update={"stats": filtered_stats})
+    return execution
+
+
 # Define the API routes
 v1_router = APIRouter()
 
@@ -986,7 +1020,12 @@ async def list_graphs_executions(
         page=1,
         page_size=250,
     )
-    return paginated_result.executions
+
+    # Apply feature flags to filter out disabled features
+    filtered_executions = await hide_activity_summaries_if_disabled(
+        paginated_result.executions, user_id
+    )
+    return filtered_executions
 
 
 @v1_router.get(
@@ -1003,13 +1042,21 @@ async def list_graph_executions(
         25, ge=1, le=100, description="Number of executions per page"
     ),
 ) -> execution_db.GraphExecutionsPaginated:
-    return await execution_db.get_graph_executions_paginated(
+    paginated_result = await execution_db.get_graph_executions_paginated(
         graph_id=graph_id,
         user_id=user_id,
         page=page,
         page_size=page_size,
     )
 
+    # Apply feature flags to filter out disabled features
+    filtered_executions = await hide_activity_summaries_if_disabled(
+        paginated_result.executions, user_id
+    )
+    return execution_db.GraphExecutionsPaginated(
+        executions=filtered_executions, pagination=paginated_result.pagination
+    )
+
 
 @v1_router.get(
     path="/graphs/{graph_id}/executions/{graph_exec_id}",
@@ -1038,6 +1085,9 @@ async def get_graph_execution(
             status_code=404, detail=f"Graph execution #{graph_exec_id} not found."
         )
 
+    # Apply feature flags to filter out disabled features
+    result = await hide_activity_summary_if_disabled(result, user_id)
+
     return result