llmposter 0.4.8

Drop-in mock server for OpenAI, Anthropic & Gemini APIs — library or standalone CLI. SSE streaming, tool calling, OAuth2, failure injection, streaming chaos, stateful scenarios, request capture, hot-reload, response templating. Test LLM apps without burning tokens.
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
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
#[cfg(feature = "oauth")]
use llmposter::server::OAuthConfig;
use llmposter::{Fixture, ServerBuilder};

#[tokio::test]
async fn should_pass_without_auth_enabled() {
    let server = ServerBuilder::new()
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 200);
}

#[tokio::test]
async fn should_reject_missing_token_when_auth_enabled() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid-token")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 401);
    // 401 responses must still carry x-request-id
    assert!(resp.headers().get("x-request-id").is_some());
}

#[tokio::test]
async fn should_accept_valid_token() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid-token")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", "Bearer valid-token")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 200);
}

#[tokio::test]
async fn should_accept_case_insensitive_bearer_scheme() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid-token")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    // RFC 7235: auth-scheme is case-insensitive
    for scheme in ["bearer", "BEARER", "Bearer", "bEaReR"] {
        let resp = client
            .post(format!("{}/v1/chat/completions", server.url()))
            .header("Authorization", format!("{} valid-token", scheme))
            .json(&serde_json::json!({
                "model": "gpt-4",
                "messages": [{"role": "user", "content": "hi"}]
            }))
            .send()
            .await
            .unwrap();
        assert_eq!(resp.status(), 200, "Failed for scheme: {}", scheme);
    }
}

#[tokio::test]
async fn should_reject_wrong_token() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid-token")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", "Bearer wrong-token")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 401);
}

#[tokio::test]
async fn should_expire_token_after_n_uses() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token_uses("short-lived", 2)
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    for i in 0..2 {
        let resp = client
            .post(format!("{}/v1/chat/completions", server.url()))
            .header("Authorization", "Bearer short-lived")
            .json(&serde_json::json!({
                "model": "gpt-4",
                "messages": [{"role": "user", "content": "hi"}]
            }))
            .send()
            .await
            .unwrap();
        assert_eq!(resp.status(), 200, "use {} should succeed", i + 1);
    }

    // Third use should be rejected — token expired
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", "Bearer short-lived")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 401);
}

#[tokio::test]
async fn should_return_anthropic_401_for_messages_endpoint() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/messages", server.url()))
        .header("Authorization", "Bearer wrong")
        .json(&serde_json::json!({
            "model": "claude",
            "max_tokens": 100,
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 401);
    let body: serde_json::Value = resp.json().await.unwrap();
    assert_eq!(body["type"], "error");
    assert_eq!(body["error"]["type"], "authentication_error");
}

#[tokio::test]
async fn should_return_gemini_401_for_generate_content() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("valid")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!(
            "{}/v1beta/models/gemini-pro:generateContent",
            server.url()
        ))
        .header("Authorization", "Bearer wrong")
        .json(&serde_json::json!({
            "contents": [{"role": "user", "parts": [{"text": "hi"}]}]
        }))
        .send()
        .await
        .unwrap();

    assert_eq!(resp.status(), 401);
    let body: serde_json::Value = resp.json().await.unwrap();
    assert_eq!(body["error"]["code"], 401);
    assert_eq!(body["error"]["status"], "UNAUTHENTICATED");
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_accept_oauth_issued_token_on_llm_endpoint() {
    let server = ServerBuilder::new()
        .with_oauth_defaults()
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let oauth_url = server.oauth_url().expect("OAuth URL should be set");
    let (client_id, client_secret) = server
        .oauth_client_credentials()
        .await
        .expect("should have credentials");

    // Get token via client_credentials grant
    let token_resp = client
        .post(format!("{}/token", oauth_url))
        .form(&[
            ("grant_type", "client_credentials"),
            ("client_id", client_id.as_str()),
            ("client_secret", client_secret.as_str()),
        ])
        .send()
        .await
        .unwrap();
    assert_eq!(token_resp.status(), 200);
    let token_body: serde_json::Value = token_resp.json().await.unwrap();
    let access_token = token_body["access_token"]
        .as_str()
        .expect("must have access_token");

    // Use the OAuth-issued token on an LLM endpoint
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", format!("Bearer {}", access_token))
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 200);
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_reject_revoked_oauth_token() {
    let server = ServerBuilder::new()
        .with_oauth_defaults()
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let oauth_url = server.oauth_url().unwrap();
    let (client_id, client_secret) = server.oauth_client_credentials().await.unwrap();

    // Get token via client_credentials grant
    let token_resp = client
        .post(format!("{}/token", oauth_url))
        .form(&[
            ("grant_type", "client_credentials"),
            ("client_id", client_id.as_str()),
            ("client_secret", client_secret.as_str()),
        ])
        .send()
        .await
        .unwrap();
    let token_body: serde_json::Value = token_resp.json().await.unwrap();
    let access_token = token_body["access_token"].as_str().unwrap();

    // Revoke the token via oauth-mock (requires Basic auth)
    let revoke_resp = client
        .post(format!("{}/revoke", oauth_url))
        .basic_auth(&client_id, Some(&client_secret))
        .form(&[("token", access_token)])
        .send()
        .await
        .unwrap();
    assert_eq!(revoke_resp.status(), 200);

    // Token should now be rejected on the LLM endpoint
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", format!("Bearer {}", access_token))
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 401);
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_accept_oauth_with_custom_client_config() {
    let server = ServerBuilder::new()
        .with_oauth(OAuthConfig {
            client_id: "my-app".to_string(),
            client_secret: "s3cret".to_string(),
            ..OAuthConfig::default()
        })
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let oauth_url = server.oauth_url().expect("OAuth URL should be set");

    // Get token with custom credentials
    let token_resp = client
        .post(format!("{}/token", oauth_url))
        .form(&[
            ("grant_type", "client_credentials"),
            ("client_id", "my-app"),
            ("client_secret", "s3cret"),
        ])
        .send()
        .await
        .unwrap();
    assert_eq!(token_resp.status(), 200);
    let token_body: serde_json::Value = token_resp.json().await.unwrap();
    let access_token = token_body["access_token"]
        .as_str()
        .expect("must have access_token");

    // Use the token on an LLM endpoint
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", format!("Bearer {}", access_token))
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 200);
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_still_accept_hardcoded_bearer_token_when_oauth_enabled() {
    let server = ServerBuilder::new()
        .with_oauth_defaults()
        .with_bearer_token("static-key")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();

    // Hardcoded token should work
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", "Bearer static-key")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 200);
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_reject_random_token_when_oauth_enabled() {
    let server = ServerBuilder::new()
        .with_oauth_defaults()
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();

    // Random token not issued by oauth-mock should be rejected
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("Authorization", "Bearer not-a-real-token")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 401);
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_support_with_oauth_custom_config() {
    let server = ServerBuilder::new()
        .with_oauth(OAuthConfig {
            client_id: "custom-id".to_string(),
            client_secret: "custom-secret".to_string(),
            ..OAuthConfig::default()
        })
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();
    assert!(server.oauth_url().is_some());
    // Debug output should work
    let debug = format!("{:?}", server);
    assert!(debug.contains("MockServer"));
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_return_none_for_approve_device_code_without_oauth() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("tok")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();
    // No OAuth configured, so oauth_url returns None
    assert!(server.oauth_url().is_none());
}

#[tokio::test]
async fn should_restore_access_when_re_added_after_exhaustion() {
    use llmposter::auth::TokenStatus;
    let auth = llmposter::AuthState::new();
    auth.add_token("tok", Some(1));
    assert_eq!(auth.check_and_use("tok"), TokenStatus::Valid); // use 1, exhausted
    assert_eq!(auth.check_and_use("tok"), TokenStatus::Exhausted);
    // Re-adding the same token clears the deny-list
    auth.add_token("tok", None);
    assert_eq!(auth.check_and_use("tok"), TokenStatus::Valid); // restored
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_return_none_credentials_without_oauth() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("tok")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();
    assert!(server.oauth_client_credentials().await.is_none());
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_error_approve_device_code_without_oauth() {
    let server = ServerBuilder::new()
        .with_auth(true)
        .with_bearer_token("tok")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();
    assert!(server.approve_device_code("fake").await.is_err());
}

#[cfg(feature = "oauth")]
#[tokio::test]
async fn should_approve_device_code_with_oauth_enabled() {
    let server = ServerBuilder::new()
        .with_oauth_defaults()
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    // approve_device_code with a non-existent user_code should return an error
    // from the OAuth server (not from the "OAuth not configured" branch).
    let result = server.approve_device_code("nonexistent").await;
    assert!(result.is_err());
    // The error should come from oauth-mock, NOT "OAuth not configured"
    let err_msg = result.unwrap_err().to_string();
    assert!(
        !err_msg.contains("OAuth not configured"),
        "Expected oauth-mock error, got: {}",
        err_msg
    );
}

#[tokio::test]
async fn should_allow_code_route_without_auth_token() {
    // GET /code/200 (and any /code/{N}) is a public utility route — auth should not block it.
    let server = ServerBuilder::new()
        .with_bearer_token("secret-token")
        .fixture(Fixture::new().respond_with_content("hello"))
        .build()
        .await
        .unwrap();

    // No Authorization header — /code/200 must still return 200.
    let resp = reqwest::get(format!("{}/code/200", server.url()))
        .await
        .unwrap();
    assert_eq!(resp.status(), 200);
}

#[tokio::test]
async fn should_reject_exhausted_token_with_401() {
    let server = ServerBuilder::new()
        .with_bearer_token_uses("one-shot", 1)
        .fixture(Fixture::new().respond_with_content("ok"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();

    // First request succeeds
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("authorization", "Bearer one-shot")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 200);

    // Second request — token exhausted
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("authorization", "Bearer one-shot")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 401);
}

#[tokio::test]
async fn should_reject_non_bearer_authorization_header() {
    let server = ServerBuilder::new()
        .with_bearer_token("valid-token")
        .fixture(Fixture::new().respond_with_content("ok"))
        .build()
        .await
        .unwrap();

    let client = reqwest::Client::new();
    let resp = client
        .post(format!("{}/v1/chat/completions", server.url()))
        .header("authorization", "Basic dXNlcjpwYXNz")
        .json(&serde_json::json!({
            "model": "gpt-4",
            "messages": [{"role": "user", "content": "hi"}]
        }))
        .send()
        .await
        .unwrap();
    assert_eq!(resp.status(), 401);
}

#[tokio::test]
async fn should_not_require_auth_for_unknown_routes() {
    let server = ServerBuilder::new()
        .with_bearer_token("secret")
        .fixture(Fixture::new().respond_with_content("ok"))
        .build()
        .await
        .unwrap();

    // Unknown route should return 404, not 401 — auth only applies to /v1/ and /v1beta/
    let resp = reqwest::get(format!("{}/nonexistent", server.url()))
        .await
        .unwrap();
    assert_eq!(
        resp.status(),
        404,
        "non-LLM route should return 404, not 401"
    );
}