feat(backend): Add Sentry user and tag tracking to node execution (#11170)

Integrates Sentry SDK to set user and contextual tags during node
execution for improved error tracking and user count analytics. Ensures
Sentry context is properly set and restored, and exceptions are captured
with relevant context before scope restoration.

<!-- Clearly explain the need for these changes: -->

### Changes 🏗️
Adds sentry tracking to block failures
<!-- 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] Test to make sure the userid and block details show up in Sentry
  - [x] make sure other errors aren't contaminated 


<!-- This is an auto-generated comment: release notes by coderabbit.ai
-->

## Summary by CodeRabbit

- New Features
- Added conditional support for feature flags when configured, enabling
targeted rollouts and experiments without impacting unconfigured
environments.

- Chores
- Enhanced error monitoring with richer contextual data during node
execution to improve stability and diagnostics.
- Updated metrics initialization to dynamically include feature flag
integrations when available, without altering behavior for unconfigured
setups.

<!-- end of auto-generated comment: release notes by coderabbit.ai -->

autogpt_platform/backend/backend/executor/manager.py

@@ -10,6 +10,7 @@ from contextlib import asynccontextmanager
 from datetime import datetime, timedelta, timezone
 from typing import TYPE_CHECKING, Any, Optional, TypeVar, cast
 
+import sentry_sdk
 from pika.adapters.blocking_connection import BlockingChannel
 from pika.spec import Basic, BasicProperties
 from prometheus_client import Gauge, start_http_server
@@ -224,6 +225,23 @@ async def execute_node(
         extra_exec_kwargs[field_name] = credentials
 
     output_size = 0
+
+    # sentry tracking nonsense to get user counts for blocks because isolation scopes don't work :(
+    scope = sentry_sdk.get_current_scope()
+
+    # save the tags
+    original_user = scope._user
+    original_tags = dict(scope._tags) if scope._tags else {}
+    # Set user ID for error tracking
+    scope.set_user({"id": user_id})
+
+    scope.set_tag("graph_id", graph_id)
+    scope.set_tag("node_id", node_id)
+    scope.set_tag("block_name", node_block.name)
+    scope.set_tag("block_id", node_block.id)
+    for k, v in (data.user_context or UserContext(timezone="UTC")).model_dump().items():
+        scope.set_tag(f"user_context.{k}", v)
+
     try:
         async for output_name, output_data in node_block.execute(
             input_data, **extra_exec_kwargs
@@ -232,6 +250,12 @@ async def execute_node(
             output_size += len(json.dumps(output_data))
             log_metadata.debug("Node produced output", **{output_name: output_data})
             yield output_name, output_data
+    except Exception:
+        # Capture exception WITH context still set before restoring scope
+        sentry_sdk.capture_exception(scope=scope)
+        sentry_sdk.flush()  # Ensure it's sent before we restore scope
+        # Re-raise to maintain normal error flow
+        raise
     finally:
         # Ensure credentials are released even if execution fails
         if creds_lock and (await creds_lock.locked()) and (await creds_lock.owned()):
@@ -246,6 +270,10 @@ async def execute_node(
             execution_stats.input_size = input_size
             execution_stats.output_size = output_size
 
+        # Restore scope AFTER error has been captured
+        scope._user = original_user
+        scope._tags = original_tags
+
 
 async def _enqueue_next_nodes(
     db_client: "DatabaseManagerAsyncClient",
@@ -570,7 +598,6 @@ class ExecutionProcessor:
                 await persist_output(
                     "error", str(stats.error) or type(stats.error).__name__
                 )
-
         return status
 
     @func_retry

autogpt_platform/backend/backend/util/feature_flag.py

@@ -37,6 +37,11 @@ class Flag(str, Enum):
     AGENT_ACTIVITY = "agent-activity"
 
 
+def is_configured() -> bool:
+    """Check if LaunchDarkly is configured with an SDK key."""
+    return bool(settings.secrets.launch_darkly_sdk_key)
+
+
 def get_client() -> LDClient:
     """Get the LaunchDarkly client singleton."""
     if not _is_initialized:

autogpt_platform/backend/backend/util/metrics.py

@@ -5,8 +5,10 @@ import sentry_sdk
 from pydantic import SecretStr
 from sentry_sdk.integrations.anthropic import AnthropicIntegration
 from sentry_sdk.integrations.asyncio import AsyncioIntegration
+from sentry_sdk.integrations.launchdarkly import LaunchDarklyIntegration
 from sentry_sdk.integrations.logging import LoggingIntegration
 
+from backend.util.feature_flag import get_client, is_configured
 from backend.util.settings import Settings
 
 settings = Settings()
@@ -19,6 +21,9 @@ class DiscordChannel(str, Enum):
 
 def sentry_init():
     sentry_dsn = settings.secrets.sentry_dsn
+    integrations = []
+    if is_configured():
+        integrations.append(LaunchDarklyIntegration(get_client()))
     sentry_sdk.init(
         dsn=sentry_dsn,
         traces_sample_rate=1.0,
@@ -31,7 +36,8 @@ def sentry_init():
             AnthropicIntegration(
                 include_prompts=False,
             ),
-        ],
+        ]
+        + integrations,
     )