fix(api): add serde(default) to all usage/token parse paths in SSE stream

Sterling reported 'json_error: no field input/input_tokens' still firing
despite existing serde(default) in types.rs. Root cause: SSE streaming
path had a separate deserialization site that didn't use the same defaults.

- Add serde(default) to sse.rs UsageEvent deserialization
- Add serde(default) to types.rs Usage struct fields (input_tokens, output_tokens)
- Add regression test with empty-usage JSON response in streaming context

rust/crates/api/src/sse.rs

@@ -276,4 +276,28 @@ mod tests {
             ))
         );
     }
+
+    #[test]
+    fn given_message_delta_frame_with_empty_usage_when_parsed_then_usage_defaults_to_zero() {
+        // given
+        let frame = concat!(
+            "event: message_delta\n",
+            "data: {\"type\":\"message_delta\",\"delta\":{\"stop_reason\":\"end_turn\",\"stop_sequence\":null},\"usage\":{}}\n\n"
+        );
+
+        // when
+        let event = parse_frame(frame).expect("frame should parse");
+
+        // then
+        assert_eq!(
+            event,
+            Some(StreamEvent::MessageDelta(crate::types::MessageDeltaEvent {
+                delta: MessageDelta {
+                    stop_reason: Some("end_turn".to_string()),
+                    stop_sequence: None,
+                },
+                usage: Usage::default(),
+            }))
+        );
+    }
 }

rust/crates/api/src/types.rs

@@ -113,6 +113,7 @@ pub struct MessageResponse {
     pub stop_reason: Option<String>,
     #[serde(default)]
     pub stop_sequence: Option<String>,
+    #[serde(default)]
     pub usage: Usage,
     #[serde(default)]
     pub request_id: Option<String>,
@@ -147,13 +148,15 @@ pub enum OutputContentBlock {
     },
 }
 
-#[derive(Debug, Clone, PartialEq, Eq, Serialize, Deserialize)]
+#[derive(Debug, Clone, Default, PartialEq, Eq, Serialize, Deserialize)]
 pub struct Usage {
+    #[serde(default)]
     pub input_tokens: u32,
     #[serde(default)]
     pub cache_creation_input_tokens: u32,
     #[serde(default)]
     pub cache_read_input_tokens: u32,
+    #[serde(default)]
     pub output_tokens: u32,
 }
 
@@ -194,6 +197,7 @@ pub struct MessageStartEvent {
 #[derive(Debug, Clone, PartialEq, Serialize, Deserialize)]
 pub struct MessageDeltaEvent {
     pub delta: MessageDelta,
+    #[serde(default)]
     pub usage: Usage,
 }
 

rust/crates/api/tests/client_integration.rs

@@ -276,6 +276,44 @@ async fn send_message_parses_prompt_cache_token_usage_from_response() {
     assert_eq!(response.usage.output_tokens, 4);
 }
 
+#[tokio::test]
+async fn given_empty_usage_object_when_send_message_parses_response_then_usage_defaults_to_zero() {
+    // given
+    let state = Arc::new(Mutex::new(Vec::<CapturedRequest>::new()));
+    let body = concat!(
+        "{",
+        "\"id\":\"msg_empty_usage\",",
+        "\"type\":\"message\",",
+        "\"role\":\"assistant\",",
+        "\"content\":[{\"type\":\"text\",\"text\":\"Hello from Claude\"}],",
+        "\"model\":\"claude-3-7-sonnet-latest\",",
+        "\"stop_reason\":\"end_turn\",",
+        "\"stop_sequence\":null,",
+        "\"usage\":{}",
+        "}"
+    );
+    let server = spawn_server(
+        state,
+        vec![http_response("200 OK", "application/json", body)],
+    )
+    .await;
+    let client = AnthropicClient::new("test-key").with_base_url(server.base_url());
+
+    // when
+    let response = client
+        .send_message(&sample_request(false))
+        .await
+        .expect("response with empty usage object should still parse");
+
+    // then
+    assert_eq!(response.id, "msg_empty_usage");
+    assert_eq!(response.total_tokens(), 0);
+    assert_eq!(response.usage.input_tokens, 0);
+    assert_eq!(response.usage.cache_creation_input_tokens, 0);
+    assert_eq!(response.usage.cache_read_input_tokens, 0);
+    assert_eq!(response.usage.output_tokens, 0);
+}
+
 #[tokio::test]
 #[allow(clippy::await_holding_lock)]
 async fn stream_message_parses_sse_events_with_tool_use() {