File size: 10,481 Bytes
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
"""Controlled provider boundary for model-fallback API and product tests."""

import json
from collections.abc import AsyncIterator, Generator, Mapping
from contextlib import contextmanager
from unittest.mock import patch

from fastapi.testclient import TestClient

from free_claude_code.application.errors import InvalidRequestError
from free_claude_code.application.model_metadata import ProviderModelInfo
from free_claude_code.config.model_refs import ModelFallback
from free_claude_code.config.settings import Settings
from free_claude_code.core.anthropic import MessagesRequest
from free_claude_code.core.anthropic.streaming import format_sse_event
from free_claude_code.core.failures import ExecutionFailure, FailureKind
from free_claude_code.core.json_types import JsonObject
from free_claude_code.core.openai_responses import OpenAIResponsesRequest
from free_claude_code.core.reasoning import ReasoningPolicy
from free_claude_code.core.stream_output import StreamOutput
from free_claude_code.core.stream_recovery import ContinuationSeed
from tests.api.support import create_test_app


def execution_failure(message: str, *, retryable: bool = True) -> ExecutionFailure:
    return ExecutionFailure(
        kind=FailureKind.OVERLOADED,
        status_code=529,
        message=message,
        retryable=retryable,
    )


def text_stream(text: str, *, model: str) -> list[str]:
    return [
        format_sse_event(
            "message_start",
            {
                "type": "message_start",
                "message": {
                    "id": "msg_fallback",
                    "type": "message",
                    "role": "assistant",
                    "model": model,
                    "content": [],
                    "stop_reason": None,
                    "stop_sequence": None,
                    "usage": {"input_tokens": 3, "output_tokens": 0},
                },
            },
        ),
        format_sse_event(
            "content_block_start",
            {
                "type": "content_block_start",
                "index": 0,
                "content_block": {"type": "text", "text": ""},
            },
        ),
        format_sse_event(
            "content_block_delta",
            {
                "type": "content_block_delta",
                "index": 0,
                "delta": {"type": "text_delta", "text": text},
            },
        ),
        format_sse_event(
            "content_block_stop",
            {"type": "content_block_stop", "index": 0},
        ),
        format_sse_event(
            "message_delta",
            {
                "type": "message_delta",
                "delta": {"stop_reason": "end_turn", "stop_sequence": None},
                "usage": {"input_tokens": 3, "output_tokens": 4},
            },
        ),
        format_sse_event("message_stop", {"type": "message_stop"}),
    ]


def responses_created_event(*, model: str) -> str:
    return _responses_event(
        "response.created",
        {
            "type": "response.created",
            "sequence_number": 0,
            "response": _responses_payload(
                model=model,
                status="in_progress",
            ),
        },
    )


def responses_text_stream(text: str, *, model: str) -> list[str]:
    output: JsonObject = {
        "id": "msg_fallback",
        "type": "message",
        "status": "completed",
        "role": "assistant",
        "content": [
            {
                "type": "output_text",
                "text": text,
                "annotations": [],
                "logprobs": [],
            }
        ],
    }
    return [
        responses_created_event(model=model),
        _responses_event(
            "response.output_text.delta",
            {
                "type": "response.output_text.delta",
                "sequence_number": 1,
                "item_id": "msg_fallback",
                "output_index": 0,
                "content_index": 0,
                "delta": text,
                "logprobs": [],
            },
        ),
        _responses_event(
            "response.completed",
            {
                "type": "response.completed",
                "sequence_number": 2,
                "response": _responses_payload(
                    model=model,
                    status="completed",
                    output=[output],
                ),
            },
        ),
    ]


def responses_failure_event(
    failure: ExecutionFailure,
    *,
    model: str,
) -> str:
    return _responses_event(
        "response.failed",
        {
            "type": "response.failed",
            "sequence_number": 1,
            "response": _responses_payload(
                model=model,
                status="failed",
                error={
                    "message": failure.message,
                    "type": "api_error",
                    "param": None,
                    "code": None,
                },
            ),
        },
    )


def _responses_event(event_type: str, payload: JsonObject) -> str:
    return f"event: {event_type}\ndata: {json.dumps(payload)}\n\n"


def _responses_payload(
    *,
    model: str,
    status: str,
    output: list[JsonObject] | None = None,
    error: JsonObject | None = None,
) -> JsonObject:
    return {
        "id": "resp_fallback",
        "object": "response",
        "model": model,
        "status": status,
        "output": output or [],
        "error": error,
        "usage": None,
    }


class ControlledFallbackProvider:
    def __init__(
        self,
        *,
        failure: ExecutionFailure | None = None,
        chunks_before_failure: tuple[str, ...] = (),
        responses_chunks_before_failure: tuple[str, ...] = (),
        text: str | None = None,
        validation_error: InvalidRequestError | None = None,
    ) -> None:
        self._failure = failure
        self._chunks_before_failure = chunks_before_failure
        self._responses_chunks_before_failure = responses_chunks_before_failure
        self._text = text
        self._validation_error = validation_error
        self.stream_models: list[str] = []
        self.response_models: list[str] = []
        self.requests: list[MessagesRequest | OpenAIResponsesRequest] = []
        self.reasoning_policies: list[ReasoningPolicy] = []
        self.close_calls = 0

    async def stream_messages(
        self,
        request: MessagesRequest,
        input_tokens: int = 0,
        *,
        request_id: str | None = None,
        response_model: str | None = None,
        reasoning: ReasoningPolicy,
        request_headers: Mapping[str, str] | None = None,
        model_info: ProviderModelInfo | None = None,
        continuation: ContinuationSeed | None = None,
    ) -> AsyncIterator[StreamOutput]:
        del input_tokens, request_id
        if self._validation_error is not None:
            raise self._validation_error
        self.stream_models.append(request.model)
        self.requests.append(request.model_copy(deep=True))
        self.reasoning_policies.append(reasoning)
        public_model = response_model or request.model
        self.response_models.append(public_model)
        try:
            for chunk in self._chunks_before_failure:
                yield StreamOutput((chunk,))
            if self._failure is not None:
                raise self._failure
            assert self._text is not None
            for chunk in text_stream(self._text, model=public_model):
                yield StreamOutput((chunk,))
        finally:
            self.close_calls += 1

    async def stream_responses(
        self,
        request: OpenAIResponsesRequest,
        input_tokens: int = 0,
        *,
        request_id: str | None = None,
        response_model: str | None = None,
        reasoning: ReasoningPolicy,
        request_headers: Mapping[str, str] | None = None,
        model_info: ProviderModelInfo | None = None,
        continuation: ContinuationSeed | None = None,
    ) -> AsyncIterator[StreamOutput]:
        del input_tokens, request_id
        if self._validation_error is not None:
            raise self._validation_error
        self.stream_models.append(request.model)
        self.requests.append(request.model_copy(deep=True))
        self.reasoning_policies.append(reasoning)
        public_model = response_model or request.model
        self.response_models.append(public_model)
        try:
            for chunk in self._responses_chunks_before_failure:
                yield StreamOutput((chunk,))
            if self._failure is not None:
                if self._responses_chunks_before_failure:
                    yield StreamOutput(
                        (responses_failure_event(self._failure, model=public_model),)
                    )
                    return
                raise self._failure
            assert self._text is not None
            for chunk in responses_text_stream(self._text, model=public_model):
                yield StreamOutput((chunk,))
        finally:
            self.close_calls += 1


@contextmanager
def fallback_client(
    primary: ControlledFallbackProvider,
    fallback: ControlledFallbackProvider,
    *,
    settings: Settings | None = None,
    extra_providers: Mapping[str, ControlledFallbackProvider] | None = None,
) -> Generator[TestClient]:
    app = create_test_app(
        settings
        or Settings(
            model="nvidia_nim/primary-model",
            model_fallbacks=(ModelFallback(model="groq/fallback-model"),),
        )
    )

    def resolve(
        provider_id: str,
        _api_key_number: int,
        *,
        lease: object,
    ) -> ControlledFallbackProvider:
        del lease
        return {"nvidia_nim": primary, "groq": fallback, **(extra_providers or {})}[
            provider_id
        ]

    with (
        patch(
            "free_claude_code.api.routes.resolve_provider",
            side_effect=resolve,
        ),
        TestClient(app) as client,
    ):
        yield client


def messages_payload(*, stream: bool) -> dict[str, object]:
    return {
        "model": "nvidia_nim/primary-model",
        "messages": [{"role": "user", "content": "Hello"}],
        "max_tokens": 32,
        "stream": stream,
    }


def responses_payload() -> dict[str, object]:
    return {
        "model": "nvidia_nim/primary-model",
        "input": "Hello",
        "max_output_tokens": 32,
        "stream": True,
    }