File size: 22,172 Bytes
a9e27c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
844b7df
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
a9e27c0
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
from unittest.mock import MagicMock, patch

import pytest
from fastapi.testclient import TestClient

from free_claude_code.config.constants import DEFAULT_MODEL
from free_claude_code.config.settings import Settings
from free_claude_code.core.anthropic import ReasoningReplayMode
from free_claude_code.core.failures import ExecutionFailure, FailureKind
from free_claude_code.core.reasoning import ReasoningPolicy
from free_claude_code.core.stream_output import StreamOutput
from free_claude_code.providers.nvidia_nim import NvidiaNimProvider
from free_claude_code.providers.openai_chat import (
    NO_REASONING,
    OpenAIChatProfile,
    OpenAIChatProvider,
    OpenAIChatRequestPolicy,
)
from tests.api.support import create_test_app
from tests.providers.support import immediate_admission, make_provider_config


@pytest.mark.parametrize("stream", [False, True])
@pytest.mark.parametrize("prefix", ["", "anthropic/", "claude-3-freecc-no-thinking/"])
@pytest.mark.parametrize(
    "ref,upstream",
    [
        ("github_models/vendor/opus", DEFAULT_MODEL.split("/", 1)[1]),
        (
            "nvidia_nim/nvidia/nemotron-3-super-120b-a12b",
            "nvidia/nemotron-3-ultra-550b-a55b",
        ),
    ],
)
def test_retired_model_ingress_calls_replacement(client, stream, prefix, ref, upstream):
    original = f"{prefix}{ref}"
    _stream_messages_calls.clear()
    response = client.post(
        "/v1/messages",
        json={
            "model": original,
            "max_tokens": 32,
            "messages": [{"role": "user", "content": "hello"}],
            "stream": stream,
        },
    )
    assert response.status_code == 200
    assert len(_stream_messages_calls) == 1
    args, kwargs = _stream_messages_calls[0]
    assert args[0].model == upstream
    assert kwargs["response_model"] == original
    if prefix == "claude-3-freecc-no-thinking/":
        assert kwargs["reasoning"] == ReasoningPolicy.off()


@pytest.fixture
def app():
    return create_test_app(Settings())


# Mock provider
mock_provider = MagicMock(spec=NvidiaNimProvider)

# Track stream_messages calls for test_model_mapping
_stream_messages_calls: list = []


async def _mock_stream_messages(*args, **kwargs):
    """Minimal async generator for streaming tests."""
    _stream_messages_calls.append((args, kwargs))
    yield StreamOutput(
        (
            'event: message_start\ndata: {"type":"message_start","message":{"type":"message","id":"m","role":"assistant","content":[],"model":"test"}}\n\n',
        )
    )
    yield StreamOutput(
        (
            'event: message_delta\ndata: {"type":"message_delta","delta":{"stop_reason":"end_turn"}}\n\nevent: message_stop\ndata: {"type":"message_stop"}\n\n',
        )
    )


async def _mock_pre_start_rate_limit(*args, **kwargs):
    """Provider stream that fails before any downstream-visible SSE chunk."""
    _stream_messages_calls.append((args, kwargs))
    raise ExecutionFailure(
        kind=FailureKind.RATE_LIMIT,
        status_code=429,
        message="upstream is busy",
        retryable=True,
    )
    yield StreamOutput(("unreachable",))


async def _mock_empty_stream(*args, **kwargs):
    """Provider stream that completes without a protocol frame."""
    _stream_messages_calls.append((args, kwargs))
    if False:
        yield StreamOutput(("unreachable",))


def _invalid_request_error(response):
    assert response.status_code == 400
    payload = response.json()
    assert payload["type"] == "error"
    assert payload["request_id"] == response.headers["request-id"]
    assert payload["error"]["type"] == "invalid_request_error"
    return payload["error"]


def _terminal_json_error(response, *, status_code: int):
    assert response.status_code == status_code
    assert response.headers["content-type"].startswith("application/json")
    assert response.headers["x-should-retry"] == "false"
    request_id = response.headers["request-id"]
    payload = response.json()
    assert payload["request_id"] == request_id
    return payload["error"]


mock_provider.stream_messages = _mock_stream_messages


@pytest.fixture
def client(app):
    """HTTP client with provider resolution stubbed; patch only for this file."""
    with (
        patch(
            "free_claude_code.api.routes.resolve_provider",
            return_value=mock_provider,
        ),
        TestClient(app) as test_client,
    ):
        yield test_client


def test_root(client: TestClient):
    response = client.get("/")
    assert response.status_code == 200
    assert response.json()["status"] == "ok"
    assert response.headers["request-id"].startswith("req_")


def test_health(client: TestClient):
    response = client.get("/health")
    assert response.status_code == 200
    assert response.json()["status"] == "healthy"
    assert response.headers["request-id"].startswith("req_")


def test_models_list(client: TestClient):
    response = client.get("/v1/models")
    assert response.status_code == 200
    data = response.json()
    assert data["has_more"] is False
    ids = [item["id"] for item in data["data"]]
    assert "claude-sonnet-5-5" in ids
    assert data["first_id"] == ids[0]
    assert data["last_id"] == ids[-1]
    assert response.headers["x-request-id"] == response.headers["request-id"]


def test_probe_endpoints_return_204_with_allow_headers(client: TestClient):
    responses = [
        client.head("/"),
        client.options("/"),
        client.head("/health"),
        client.options("/health"),
        client.head("/v1/messages"),
        client.options("/v1/messages"),
        client.head("/v1/messages/count_tokens"),
        client.options("/v1/messages/count_tokens"),
    ]

    for response in responses:
        assert response.status_code == 204
        assert "Allow" in response.headers


def test_create_message_stream(client: TestClient):
    """Create message returns streaming response."""
    _stream_messages_calls.clear()
    payload = {
        "model": "claude-3-sonnet",
        "messages": [{"role": "user", "content": "Hi"}],
        "max_tokens": 100,
        "stream": True,
    }
    response = client.post("/v1/messages", json=payload)
    assert response.status_code == 200
    assert "text/event-stream" in response.headers.get("content-type", "")
    content = b"".join(response.iter_bytes())
    assert b"message_start" in content or b"event:" in content
    assert _stream_messages_calls[0][1]["request_id"] == response.headers["request-id"]


def test_auto_mode_classifier_without_stream_returns_json(client: TestClient):
    """Claude side queries omit stream and require one complete Message object."""
    _stream_messages_calls.clear()
    payload = {
        "model": "claude-opus-4-8",
        "max_tokens": 64,
        "system": (
            "You are a security monitor. Respond with <block>yes</block> "
            "or <block>no</block>."
        ),
        "messages": [
            {
                "role": "user",
                "content": "<transcript>\nBash curl example.com\n</transcript>",
            }
        ],
    }

    response = client.post("/v1/messages?beta=true", json=payload)

    assert response.status_code == 200
    assert response.headers["content-type"].startswith("application/json")
    body = response.json()
    assert body["type"] == "message"
    assert body["usage"] == {"input_tokens": 0, "output_tokens": 0}
    routed_request = _stream_messages_calls[0][0][0]
    assert routed_request.stream is False
    assert _stream_messages_calls[0][1]["reasoning"] == ReasoningPolicy.prefer_off()


def test_create_message_ingress_error_has_request_id_without_terminal_header(
    client: TestClient,
):
    response = client.post(
        "/v1/messages",
        json={"model": "test", "messages": [], "max_tokens": 10, "stream": True},
    )

    assert response.status_code == 400
    assert "x-should-retry" not in response.headers
    assert response.json()["request_id"] == response.headers["request-id"]


def test_create_message_rejects_unportable_image_as_invalid_request() -> None:
    with patch(
        "free_claude_code.providers.openai_chat.client.AsyncOpenAI",
        return_value=MagicMock(),
    ):
        provider = OpenAIChatProvider(
            make_provider_config(
                api_key="test-key",
                base_url="https://provider.invalid/v1",
            ),
            profile=OpenAIChatProfile(
                OpenAIChatRequestPolicy(
                    provider_name="TEST_CHAT",
                    reasoning_replay=ReasoningReplayMode.REASONING_CONTENT,
                ),
                NO_REASONING,
            ),
            admission=immediate_admission(provider_name="TEST_CHAT"),
        )
    test_app = create_test_app()
    with (
        patch("free_claude_code.api.routes.resolve_provider", return_value=provider),
        TestClient(test_app) as test_client,
    ):
        response = test_client.post(
            "/v1/messages",
            json={
                "model": "nvidia_nim/test-model",
                "max_tokens": 32,
                "messages": [
                    {
                        "role": "user",
                        "content": [
                            {
                                "type": "image",
                                "source": {"type": "file", "file_id": "file_1"},
                            }
                        ],
                    }
                ],
            },
        )

    assert response.status_code == 400
    assert response.json()["error"]["type"] == "invalid_request_error"
    assert "file" in response.json()["error"]["message"]


def test_create_message_schema_validation_has_request_id_without_terminal_header(
    client: TestClient,
):
    response = client.post(
        "/v1/messages",
        json={"model": "test", "messages": "not-a-list"},
    )

    assert response.status_code == 422
    assert response.headers["request-id"].startswith("req_")
    assert "x-should-retry" not in response.headers


def test_create_message_pre_start_provider_error_returns_terminal_json(
    client: TestClient,
):
    """Pre-start provider failures keep status without enabling client retries."""
    mock_provider.stream_messages = _mock_pre_start_rate_limit
    _stream_messages_calls.clear()
    payload = {
        "model": "claude-3-sonnet",
        "messages": [{"role": "user", "content": "Hi"}],
        "max_tokens": 100,
        "stream": True,
    }

    with (
        patch("free_claude_code.api.response_streams.trace_event") as trace,
        patch("free_claude_code.application.execution.trace_event") as execution_trace,
    ):
        response = client.post("/v1/messages", json=payload)

    error = _terminal_json_error(response, status_code=429)
    assert error == {"type": "rate_limit_error", "message": "upstream is busy"}
    request_id = response.headers["request-id"]
    assert _stream_messages_calls[0][1]["request_id"] == request_id
    route_trace = next(
        call.kwargs
        for call in execution_trace.call_args_list
        if call.kwargs.get("event") == "free_claude_code.api.route.resolved"
    )
    assert route_trace["request_id"] == request_id
    terminal_trace = next(
        call.kwargs
        for call in trace.call_args_list
        if call.kwargs.get("event")
        == "free_claude_code.api.response.terminal_execution_error"
    )
    assert terminal_trace == {
        "stage": "egress",
        "event": "free_claude_code.api.response.terminal_execution_error",
        "source": "api",
        "wire_api": "messages",
        "request_id": request_id,
        "status_code": 429,
        "error_type": "rate_limit_error",
        "client_should_retry": False,
        "exc_type": "ExecutionFailure",
        "failure_kind": "rate_limit",
        "provider_retryable": True,
    }
    mock_provider.stream_messages = _mock_stream_messages


@pytest.mark.parametrize(
    "system_turn",
    [
        {"role": "system", "content": "system prompt"},
        {
            "role": "system",
            "content": [{"type": "text", "text": "reminder"}],
            "clear_at": "next_user_message",
        },
    ],
    ids=["text", "clear-at"],
)
@pytest.mark.parametrize("leading", [True, False], ids=["leading", "mid"])
def test_system_role_messages_are_rejected(client: TestClient, system_turn, leading):
    """System prompts belong in ``system``; Claude Code retries without the turn."""
    _stream_messages_calls.clear()
    messages = [{"role": "user", "content": "Hi"}]
    messages.insert(0 if leading else 1, system_turn)
    if not leading:
        messages.append({"role": "user", "content": "again"})

    response = client.post(
        "/v1/messages",
        json={
            "model": "claude-3-sonnet",
            "messages": messages,
            "max_tokens": 100,
            "stream": True,
        },
    )

    error = _invalid_request_error(response)
    assert "top-level `system` field" in error["message"]
    assert "run `claude update`" in error["message"]
    assert error["details"] == {"error_code": "mid_conversation_system_not_supported"}
    assert _stream_messages_calls == []


def test_system_role_rejection_names_the_claude_code_version(client: TestClient):
    _stream_messages_calls.clear()
    response = client.post(
        "/v1/messages",
        headers={"User-Agent": "claude-cli/2.1.288 (external, cli)"},
        json={
            "model": "claude-3-sonnet",
            "messages": [
                {"role": "user", "content": "Hi"},
                {"role": "system", "content": "reminder"},
            ],
            "max_tokens": 100,
        },
    )

    error = _invalid_request_error(response)
    assert error["message"] == (
        "Claude Code 2.1.288 sent a system message inside `messages`, which "
        "Free Claude Code can't accept. Run `claude update`, then restart "
        "Claude Code."
    )
    assert error["details"] == {"error_code": "mid_conversation_system_not_supported"}
    assert _stream_messages_calls == []


def test_new_claude_code_normalizes_inline_system_turns(client: TestClient):
    _stream_messages_calls.clear()
    response = client.post(
        "/v1/messages",
        headers={"User-Agent": "claude-cli/2.1.317 (external, cli)"},
        json={
            "model": "claude-3-sonnet",
            "messages": [
                {"role": "user", "content": "Hi"},
                {"role": "system", "content": "reminder"},
                {"role": "user", "content": "again"},
            ],
            "max_tokens": 100,
            "stream": True,
        },
    )

    assert response.status_code == 200
    assert len(_stream_messages_calls) == 1
    request = _stream_messages_calls[0][0][0]
    assert request.system == [{"type": "text", "text": "reminder"}]
    assert [message.role for message in request.messages] == ["user", "user"]


def test_count_tokens_rejects_system_role_messages_with_update_hint(
    client: TestClient,
):
    response = client.post(
        "/v1/messages/count_tokens",
        headers={"User-Agent": "claude-cli/2.1.288 (external, cli)"},
        json={
            "model": "test",
            "messages": [
                {"role": "system", "content": "reminder"},
                {"role": "user", "content": "Hello"},
            ],
        },
    )

    error = _invalid_request_error(response)
    assert "Claude Code 2.1.288" in error["message"]
    assert "Run `claude update`" in error["message"]
    assert error["details"] == {"error_code": "mid_conversation_system_not_supported"}


def test_model_mapping(client: TestClient):
    # Test Haiku mapping
    _stream_messages_calls.clear()
    payload_haiku = {
        "model": "claude-3-haiku-20240307",
        "messages": [{"role": "user", "content": "Hi"}],
        "max_tokens": 100,
        "stream": True,
    }
    client.post("/v1/messages", json=payload_haiku)
    assert len(_stream_messages_calls) == 1
    args = _stream_messages_calls[0][0]
    kwargs = _stream_messages_calls[0][1]
    assert args[0].model != "claude-3-haiku-20240307"
    assert kwargs["reasoning"] == ReasoningPolicy.provider_default()


@pytest.mark.parametrize(
    ("failure", "expected_type"),
    [
        (
            ExecutionFailure(
                FailureKind.AUTHENTICATION, 401, "Invalid Key", retryable=False
            ),
            "authentication_error",
        ),
        (
            ExecutionFailure(
                FailureKind.INVALID_REQUEST,
                400,
                "Invalid request api_key=SECRET useful detail",
                retryable=False,
            ),
            "invalid_request_error",
        ),
        (
            ExecutionFailure(
                FailureKind.RATE_LIMIT, 429, "Too Many Requests", retryable=True
            ),
            "rate_limit_error",
        ),
        (
            ExecutionFailure(
                FailureKind.OVERLOADED, 529, "Server Overloaded", retryable=True
            ),
            "overloaded_error",
        ),
        (
            ExecutionFailure(
                FailureKind.UPSTREAM, 503, "Upstream failed", retryable=True
            ),
            "api_error",
        ),
    ],
)
def test_provider_execution_errors_preserve_status_and_type(
    client: TestClient,
    failure: ExecutionFailure,
    expected_type: str,
):
    base_payload = {
        "model": "test",
        "messages": [{"role": "user", "content": "Hi"}],
        "max_tokens": 10,
        "stream": True,
    }

    def _raise_provider_error(*args, **kwargs):
        raise failure

    try:
        mock_provider.stream_messages = _raise_provider_error
        response = client.post("/v1/messages", json=base_payload)
        error = _terminal_json_error(response, status_code=failure.status_code)
        assert error["type"] == expected_type
        assert "SECRET" not in error["message"]
        if expected_type == "invalid_request_error":
            assert "useful detail" in error["message"]
    finally:
        mock_provider.stream_messages = _mock_stream_messages


def test_empty_provider_stream_returns_terminal_json(client: TestClient):
    mock_provider.stream_messages = _mock_empty_stream
    try:
        response = client.post(
            "/v1/messages",
            json={
                "model": "test",
                "messages": [{"role": "user", "content": "Hi"}],
                "max_tokens": 10,
                "stream": True,
            },
        )
        error = _terminal_json_error(response, status_code=500)
        assert error["type"] == "api_error"
        assert error["message"] == "Stream ended before emitting a response."
    finally:
        mock_provider.stream_messages = _mock_stream_messages


def test_generic_stream_exception_returns_terminal_json(client: TestClient):
    """Unexpected provider execution failures return detailed terminal JSON."""

    def _raise_runtime(*args, **kwargs):
        raise RuntimeError("unexpected crash")

    mock_provider.stream_messages = _raise_runtime
    response = client.post(
        "/v1/messages",
        json={
            "model": "test",
            "messages": [{"role": "user", "content": "Hi"}],
            "max_tokens": 10,
            "stream": True,
        },
    )
    error = _terminal_json_error(response, status_code=500)
    assert error["type"] == "api_error"
    assert error["message"] == "unexpected crash"
    mock_provider.stream_messages = _mock_stream_messages


def test_generic_stream_exception_with_status_code_returns_terminal_json(
    client: TestClient,
):
    """Ad-hoc status_code attrs do not become retryable HTTP responses."""

    class ExceptionWithStatus(RuntimeError):
        def __init__(self, msg: str, status_code: int = 500):
            super().__init__(msg)
            self.status_code = status_code

    def _raise_with_status(*args, **kwargs):
        raise ExceptionWithStatus("bad gateway", 502)

    mock_provider.stream_messages = _raise_with_status
    response = client.post(
        "/v1/messages",
        json={
            "model": "test",
            "messages": [{"role": "user", "content": "Hi"}],
            "max_tokens": 10,
            "stream": True,
        },
    )
    error = _terminal_json_error(response, status_code=500)
    assert error["type"] == "api_error"
    assert error["message"] == "bad gateway"
    mock_provider.stream_messages = _mock_stream_messages


def test_generic_stream_exception_empty_message_returns_non_empty_error(
    client: TestClient,
):
    """Exceptions with empty __str__ still return a readable HTTP detail."""

    class SilentError(RuntimeError):
        def __str__(self):
            return ""

    def _raise_silent(*args, **kwargs):
        raise SilentError()

    mock_provider.stream_messages = _raise_silent
    response = client.post(
        "/v1/messages",
        json={
            "model": "test",
            "messages": [{"role": "user", "content": "Hi"}],
            "max_tokens": 10,
            "stream": True,
        },
    )
    error = _terminal_json_error(response, status_code=500)
    assert error["type"] == "api_error"
    assert error["message"] != ""
    mock_provider.stream_messages = _mock_stream_messages


def test_count_tokens_endpoint(client: TestClient):
    """count_tokens endpoint returns token count."""
    response = client.post(
        "/v1/messages/count_tokens",
        json={"model": "test", "messages": [{"role": "user", "content": "Hello"}]},
    )
    assert response.status_code == 200
    assert "input_tokens" in response.json()
    assert response.headers["request-id"].startswith("req_")


def test_stop_endpoint_no_workflow_no_cli_503(app, client: TestClient):
    """POST /stop without messaging workflow or cli_manager returns 503."""
    # Ensure no messaging workflow or cli_manager on app state
    if hasattr(app.state, "messaging_workflow"):
        delattr(app.state, "messaging_workflow")
    if hasattr(app.state, "cli_manager"):
        delattr(app.state, "cli_manager")
    response = client.post("/stop")
    assert response.status_code == 503