anthropic-async 0.5.2

Anthropic API client for Rust with prompt caching support
Documentation 
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149

use anthropic_async::AnthropicConfig;
use anthropic_async::Client;
use anthropic_async::types::content::*;
use anthropic_async::types::messages::*;
use std::sync::Arc;
use std::sync::atomic::AtomicUsize;
use std::sync::atomic::Ordering;
use wiremock::Mock;
use wiremock::MockServer;
use wiremock::ResponseTemplate;
use wiremock::matchers::method;
use wiremock::matchers::path;

#[tokio::test]
async fn test_retry_on_429_then_success() {
    let server = MockServer::start().await;
    let count = Arc::new(AtomicUsize::new(0));

    let count_clone = Arc::clone(&count);
    Mock::given(method("POST"))
        .and(path("/v1/messages"))
        .respond_with(move |_req: &wiremock::Request| {
            let i = count_clone.fetch_add(1, Ordering::SeqCst);
            if i == 0 {
                ResponseTemplate::new(429)
                    .insert_header("retry-after-ms", "100")
                    .set_body_json(serde_json::json!({
                        "error": {
                            "message": "Rate limit exceeded",
                            "type": "rate_limit_error"
                        }
                    }))
            } else {
                ResponseTemplate::new(200).set_body_json(serde_json::json!({
                    "id": "msg",
                    "type": "message",
                    "role": "assistant",
                    "content": [{"type": "text", "text": "Success"}],
                    "model": "claude"
                }))
            }
        })
        .mount(&server)
        .await;

    let cfg = AnthropicConfig::new()
        .with_api_base(server.uri())
        .with_api_key("test");
    let client = Client::with_config(cfg);

    let request = MessagesCreateRequest {
        model: "claude".into(),
        max_tokens: 10,
        messages: vec![MessageParam {
            role: MessageRole::User,
            content: "test".into(),
        }],
        ..Default::default()
    };

    let response = client.messages().create(request).await.unwrap();
    assert_eq!(response.kind, "message");
    assert!(count.load(Ordering::SeqCst) >= 2);
}

#[tokio::test]
async fn test_529_overloaded_retry() {
    let server = MockServer::start().await;
    let count = Arc::new(AtomicUsize::new(0));

    let count_clone = Arc::clone(&count);
    Mock::given(method("POST"))
        .and(path("/v1/messages"))
        .respond_with(move |_req: &wiremock::Request| {
            let i = count_clone.fetch_add(1, Ordering::SeqCst);
            if i == 0 {
                ResponseTemplate::new(529).set_body_json(serde_json::json!({
                    "error": {
                        "message": "Overloaded",
                        "type": "overloaded_error"
                    }
                }))
            } else {
                ResponseTemplate::new(200).set_body_json(serde_json::json!({
                    "id": "msg",
                    "type": "message",
                    "role": "assistant",
                    "content": [{"type": "text", "text": "Success"}],
                    "model": "claude"
                }))
            }
        })
        .mount(&server)
        .await;

    let cfg = AnthropicConfig::new()
        .with_api_base(server.uri())
        .with_api_key("test");
    let client = Client::with_config(cfg);

    let request = MessagesCreateRequest {
        model: "claude".into(),
        max_tokens: 10,
        messages: vec![MessageParam {
            role: MessageRole::User,
            content: "test".into(),
        }],
        ..Default::default()
    };

    let response = client.messages().create(request).await.unwrap();
    assert_eq!(response.kind, "message");
}

#[tokio::test]
async fn test_non_retryable_400() {
    let server = MockServer::start().await;

    Mock::given(method("POST"))
        .and(path("/v1/messages"))
        .respond_with(ResponseTemplate::new(400).set_body_json(serde_json::json!({
            "error": {
                "message": "Invalid request",
                "type": "invalid_request_error"
            }
        })))
        .mount(&server)
        .await;

    let cfg = AnthropicConfig::new()
        .with_api_base(server.uri())
        .with_api_key("test");
    let client = Client::with_config(cfg);

    let request = MessagesCreateRequest {
        model: "invalid-model".into(),
        max_tokens: 10,
        messages: vec![],
        ..Default::default()
    };

    let err = client.messages().create(request).await.unwrap_err();
    match err {
        anthropic_async::AnthropicError::Api(obj) => {
            assert_eq!(obj.message, "Invalid request");
        }
        _ => panic!("Expected Api error"),
    }
}