add sandbox observability failure tests

test/test_docker_runtime.py

@@ -43,6 +43,27 @@ class FakeListedContainer(FakeContainer):
         self.attrs = {'Created': created_at}
 
 
+class FailingStopContainer(FakeListedContainer):
+    def __init__(
+        self,
+        container_id: str,
+        *,
+        labels: dict[str, str],
+        created_at: str,
+        error: Exception,
+    ) -> None:
+        super().__init__(
+            container_id,
+            labels=labels,
+            created_at=created_at,
+        )
+        self._error = error
+
+    def stop(self) -> None:
+        self.stop_calls += 1
+        raise self._error
+
+
 class RunKwargs(TypedDict):
     detach: bool
     labels: dict[str, str]
@@ -435,23 +456,143 @@ def test_runtime_stop_ignores_missing_container(tmp_path: Path) -> None:
     config = build_config(tmp_path)
     containers = FakeContainers()
     containers.get_result = NotFound('missing')
-    runtime = build_runtime(config, containers)
+    metrics = RecordingMetrics()
+    tracer = RecordingTracer()
+    runtime = DockerSandboxRuntime(
+        config,
+        FakeDockerClient(containers),
+        metrics,
+        tracer,
+    )
 
     runtime.stop('container-123')
 
     assert containers.get_calls == ['container-123']
+    duration_call = _find_record_call(
+        metrics,
+        'sandbox.runtime.stop.duration_ms',
+        attrs={'operation': 'stop', 'result': 'not_found'},
+    )
+    assert duration_call[1] >= 0
+    span = _find_span(
+        tracer,
+        'adapter.docker.stop_sandbox',
+        {'container.id': 'container-123'},
+        {'sandbox.result': 'not_found'},
+    )
+    assert not span.errors
+    stop_error_calls = [
+        call
+        for call in metrics.increment_calls
+        if call[0] == 'sandbox.runtime.error.total'
+        and call[2] is not None
+        and call[2].get('operation') == 'stop'
+    ]
+    assert stop_error_calls == []
 
 
 def test_runtime_stop_wraps_docker_errors(tmp_path: Path) -> None:
     config = build_config(tmp_path)
     containers = FakeContainers()
-    containers.get_result = DockerException('boom')
-    runtime = build_runtime(config, containers)
+    containers.get_result = FailingStopContainer(
+        'container-123',
+        labels={
+            'session_id': str(SESSION_ID),
+            'chat_id': str(CHAT_ID),
+            'expires_at': '2026-04-02T12:05:00+00:00',
+        },
+        created_at='2026-04-02T12:00:00Z',
+        error=DockerException('boom'),
+    )
+    metrics = RecordingMetrics()
+    tracer = RecordingTracer()
+    runtime = DockerSandboxRuntime(
+        config,
+        FakeDockerClient(containers),
+        metrics,
+        tracer,
+    )
 
     with pytest.raises(SandboxError) as excinfo:
         runtime.stop('container-123')
 
     assert str(excinfo.value) == 'sandbox_stop_failed'
+    _find_increment_call(
+        metrics,
+        'sandbox.runtime.error.total',
+        attrs={'operation': 'stop', 'error.type': 'DockerException'},
+    )
+    duration_call = _find_record_call(
+        metrics,
+        'sandbox.runtime.stop.duration_ms',
+        attrs={'operation': 'stop', 'result': 'error'},
+    )
+    assert duration_call[1] >= 0
+    span = _find_span(
+        tracer,
+        'adapter.docker.stop_sandbox',
+        {'container.id': 'container-123'},
+        {
+            'session.id': str(SESSION_ID),
+            'chat.id': str(CHAT_ID),
+            'sandbox.result': 'error',
+        },
+    )
+    cause = excinfo.value.__cause__
+    assert isinstance(cause, DockerException)
+    assert cause in span.errors
+
+
+def test_runtime_stop_records_observability_on_success(tmp_path: Path) -> None:
+    config = build_config(tmp_path)
+    containers = FakeContainers()
+    container = FakeListedContainer(
+        'container-123',
+        labels={
+            'session_id': str(SESSION_ID),
+            'chat_id': str(CHAT_ID),
+            'expires_at': '2026-04-02T12:05:00+00:00',
+        },
+        created_at='2026-04-02T12:00:00Z',
+    )
+    containers.get_result = container
+    metrics = RecordingMetrics()
+    tracer = RecordingTracer()
+    runtime = DockerSandboxRuntime(
+        config,
+        FakeDockerClient(containers),
+        metrics,
+        tracer,
+    )
+
+    runtime.stop('container-123')
+
+    assert container.stop_calls == 1
+    duration_call = _find_record_call(
+        metrics,
+        'sandbox.runtime.stop.duration_ms',
+        attrs={'operation': 'stop', 'result': 'stopped'},
+    )
+    assert duration_call[1] >= 0
+    span = _find_span(
+        tracer,
+        'adapter.docker.stop_sandbox',
+        {'container.id': 'container-123'},
+        {
+            'session.id': str(SESSION_ID),
+            'chat.id': str(CHAT_ID),
+            'sandbox.result': 'stopped',
+        },
+    )
+    assert not span.errors
+    stop_error_calls = [
+        call
+        for call in metrics.increment_calls
+        if call[0] == 'sandbox.runtime.error.total'
+        and call[2] is not None
+        and call[2].get('operation') == 'stop'
+    ]
+    assert stop_error_calls == []
 
 
 def test_runtime_list_active_sessions_reads_valid_labeled_containers(