instrument sandbox docker runtime

adapter/sandbox/reconciliation.py

@@ -3,7 +3,7 @@ from typing import Protocol
 from uuid import UUID
 
 from domain.sandbox import SandboxSession
-from usecase.interface import Logger
+from usecase.interface import Logger, Metrics, Tracer
 
 
 class SandboxSessionStateSource(Protocol):
@@ -13,27 +13,45 @@ class SandboxSessionStateSource(Protocol):
 class SandboxSessionRegistry(Protocol):
     def replace_all(self, sessions: list[SandboxSession]) -> None: ...
 
+    def count_active(self) -> int: ...
+
 
 @dataclass(frozen=True, slots=True)
 class SandboxSessionReconciler:
     state_source: SandboxSessionStateSource
     registry: SandboxSessionRegistry
     logger: Logger
+    metrics: Metrics
+    tracer: Tracer
 
     def execute(self) -> list[SandboxSession]:
-        sessions_by_chat_id: dict[UUID, SandboxSession] = {}
-        for session in sorted(
-            self.state_source.list_active_sessions(),
-            key=lambda item: item.created_at,
-        ):
-            sessions_by_chat_id[session.chat_id] = session
+        with self.tracer.start_span(
+            'adapter.sandbox.reconcile_sessions',
+        ) as span:
+            try:
+                sessions_by_chat_id: dict[UUID, SandboxSession] = {}
+                discovered_sessions = self.state_source.list_active_sessions()
+                span.set_attribute('sandbox.discovered_count', len(discovered_sessions))
+                for session in sorted(
+                    discovered_sessions,
+                    key=lambda item: item.created_at,
+                ):
+                    sessions_by_chat_id[session.chat_id] = session
 
-        sessions = list(sessions_by_chat_id.values())
-        self.registry.replace_all(sessions)
-        self.logger.info(
-            'sandbox_reconciled',
-            attrs={
-                'session_count': len(sessions),
-            },
-        )
-        return sessions
+                sessions = list(sessions_by_chat_id.values())
+                self.registry.replace_all(sessions)
+                active_count = self.registry.count_active()
+                self.metrics.set('sandbox.active.count', active_count)
+                span.set_attribute('sandbox.active_count', active_count)
+                span.set_attribute('sandbox.result', 'reconciled')
+                self.logger.info(
+                    'sandbox_reconciled',
+                    attrs={
+                        'session_count': active_count,
+                    },
+                )
+                return sessions
+            except Exception as exc:
+                span.set_attribute('sandbox.result', 'error')
+                span.record_error(exc)
+                raise