Spaces:
Running
Running
File size: 35,711 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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 | """Public commit-boundary behavior for canonical execution failures."""
import asyncio
import json
from collections.abc import AsyncIterator, Mapping
from typing import Any, cast
from unittest.mock import MagicMock, patch
import httpx2
import pytest
from fastapi.testclient import TestClient
from openai import AsyncOpenAI
from free_claude_code.application.model_metadata import ProviderModelInfo
from free_claude_code.config.loader import compose_settings_snapshot
from free_claude_code.config.settings import Settings
from free_claude_code.core.anthropic import ReasoningReplayMode
from free_claude_code.core.anthropic.stream_contracts import parse_sse_text
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,
openai_error_from_failure,
)
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 free_claude_code.providers.openai_chat import (
NO_REASONING,
OpenAIChatProfile,
OpenAIChatProvider,
OpenAIChatRequestPolicy,
)
from tests.api.support import create_test_app
from tests.api.test_delivered_stream_recovery import text_events
from tests.providers.support import immediate_admission, make_provider_config
_PARTIAL_CONTENT = "PARTIAL_ASSISTANT_CONTENT"
class CanonicalFailureProvider:
"""Provider double that raises one request-correlated canonical failure."""
def __init__(
self,
chunks: list[str],
*,
kind: FailureKind,
status_code: int,
message: str,
retryable: bool,
grouped: bool = False,
) -> None:
self._chunks = chunks
self._kind = kind
self._status_code = status_code
self._message = message
self._retryable = retryable
self._grouped = grouped
self.stream_kwargs: list[dict[str, Any]] = []
async def stream_messages(
self,
_request: object,
**kwargs: Any,
) -> AsyncIterator[StreamOutput]:
self.stream_kwargs.append(kwargs)
for chunk in self._chunks:
yield StreamOutput((chunk,))
failure = self._failure(str(kwargs["request_id"]))
if self._grouped:
raise self._grouped_failure(failure)
raise failure
async def stream_responses(
self,
_request: OpenAIResponsesRequest,
**kwargs: Any,
) -> AsyncIterator[StreamOutput]:
self.stream_kwargs.append(kwargs)
failure = self._failure(str(kwargs["request_id"]))
if not self._chunks:
if self._grouped:
raise self._grouped_failure(failure)
raise failure
for chunk in _partial_responses_stream(failure):
yield StreamOutput((chunk,))
def _failure(self, request_id: str) -> ExecutionFailure:
return ExecutionFailure(
kind=self._kind,
status_code=self._status_code,
message=f"{self._message}\n\nRequest ID: {request_id}",
retryable=self._retryable,
)
@staticmethod
def _grouped_failure(failure: ExecutionFailure) -> ExceptionGroup:
return ExceptionGroup(
"provider stream and cleanup failed",
[
RuntimeError("cleanup failed"),
ExceptionGroup("provider request failed", [failure]),
],
)
class ResponsesFailureProvider:
"""Provider double that raises after committing a Responses lifecycle."""
def __init__(self, *, responses_chunks: tuple[str, ...] = ()) -> None:
self._responses_chunks = responses_chunks
self.close_calls = 0
async def stream_responses(
self,
_request: OpenAIResponsesRequest,
*,
input_tokens: int,
request_id: str,
response_model: str,
reasoning: ReasoningPolicy,
request_headers: Mapping[str, str] | None = None,
model_info: ProviderModelInfo | None = None,
continuation: ContinuationSeed | None = None,
) -> AsyncIterator[StreamOutput]:
del input_tokens, response_model, reasoning
try:
for chunk in self._responses_chunks:
yield StreamOutput((chunk,))
raise ExecutionFailure(
FailureKind.TIMEOUT,
504,
f"Provider read timed out.\n\nRequest ID: {request_id}",
False,
)
finally:
self.close_calls += 1
def _messages_payload(*, stream: bool) -> dict[str, object]:
return {
"model": "nvidia_nim/test-model",
"messages": [{"role": "user", "content": "Hello"}],
"max_tokens": 32,
"stream": stream,
}
def _responses_payload() -> dict[str, object]:
return {
"model": "nvidia_nim/test-model",
"input": "Hello",
"max_output_tokens": 32,
}
def _partial_anthropic_stream(*, close_block: bool) -> list[str]:
chunks = [
format_sse_event("message_start", {"type": "message_start", "message": {}}),
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": _PARTIAL_CONTENT},
},
),
]
if close_block:
chunks.append(
format_sse_event(
"content_block_stop",
{"type": "content_block_stop", "index": 0},
)
)
return chunks
def _partial_responses_stream(failure: ExecutionFailure) -> list[str]:
response_id = "resp_failure_contract"
message: JsonObject = {
"id": "msg_failure_contract",
"type": "message",
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": _PARTIAL_CONTENT,
"annotations": [],
"logprobs": [],
}
],
}
created = _responses_event(
"response.created",
{
"type": "response.created",
"sequence_number": 0,
"response": _responses_wire_payload(
response_id=response_id,
status="in_progress",
),
},
)
item_done = _responses_event(
"response.output_item.done",
{
"type": "response.output_item.done",
"sequence_number": 1,
"output_index": 0,
"item": message,
},
)
failed = _responses_event(
"response.failed",
{
"type": "response.failed",
"sequence_number": 2,
"response": _responses_wire_payload(
response_id=response_id,
status="failed",
output=[message],
error=cast(JsonObject, openai_error_from_failure(failure)),
),
},
)
return [created, item_done, failed]
def _responses_event(event_type: str, payload: JsonObject) -> str:
return f"event: {event_type}\ndata: {json.dumps(payload)}\n\n"
def _responses_wire_payload(
*,
response_id: str,
status: str,
output: list[JsonObject] | None = None,
error: JsonObject | None = None,
) -> JsonObject:
return {
"id": response_id,
"object": "response",
"model": "nvidia_nim/test-model",
"status": status,
"output": output or [],
"error": error,
"usage": None,
}
def _client_for(
provider: CanonicalFailureProvider | ResponsesFailureProvider | OpenAIChatProvider,
*,
settings: Settings | None = None,
):
app = create_test_app(settings)
return (
patch("free_claude_code.api.routes.resolve_provider", return_value=provider),
TestClient(app),
)
@pytest.mark.parametrize("path", ["/v1/messages", "/v1/responses"])
@pytest.mark.parametrize("partial", [False, True])
def test_retired_progress_value_does_not_interrupt_slow_response(
path, partial, monkeypatch
):
closed = []
class SlowStream(httpx2.AsyncByteStream):
async def __aiter__(self):
chunks = [
("data: " + json.dumps(event) + "\n\n").encode()
for event in text_events("chat", "Hello")
]
if partial:
yield chunks.pop(0)
release = asyncio.Event()
timer = asyncio.get_running_loop().call_later(0.05, release.set)
try:
await release.wait()
finally:
timer.cancel()
for chunk in chunks:
yield chunk
yield b"data: [DONE]\n\n"
async def aclose(self):
closed.append(True)
sdk = AsyncOpenAI(
api_key="test",
base_url="https://provider.invalid/v1",
max_retries=0,
http_client=httpx2.AsyncClient(
transport=httpx2.MockTransport(
lambda _: httpx2.Response(
200,
headers={"content-type": "text/event-stream"},
stream=SlowStream(),
)
)
),
)
provider = OpenAIChatProvider(
make_provider_config(api_key="test", base_url="https://provider.invalid/v1"),
profile=OpenAIChatProfile(
OpenAIChatRequestPolicy("TEST", ReasoningReplayMode.REASONING_CONTENT),
NO_REASONING,
),
admission=immediate_admission(),
client=sdk,
)
settings = compose_settings_snapshot(
{}, {"PROVIDER_PROGRESS_TIMEOUT": "0.01"}
).settings
resolver_patch, client = _client_for(provider, settings=settings)
try:
with resolver_patch, client:
response = client.post(
path,
json=_messages_payload(stream=True)
if path == "/v1/messages"
else _responses_payload(),
)
finally:
asyncio.run(sdk.close())
assert response.status_code == 200, response.text
events = parse_sse_text(response.text)
assert events[-1].event == (
"message_stop" if path == "/v1/messages" else "response.completed"
)
assert "Hello" in response.text
assert closed == [True]
@pytest.mark.parametrize("partial", [False, True])
def test_sdk_stream_invalid_request_preserves_public_error_semantics(
partial, monkeypatch
) -> None:
calls = 0
def reply(request: httpx2.Request) -> httpx2.Response:
nonlocal calls
calls += 1
events = []
if partial:
events.append(
{
"id": "chat_invalid",
"object": "chat.completion.chunk",
"created": 0,
"model": "test-model",
"choices": [
{
"index": 0,
"delta": {"content": _PARTIAL_CONTENT},
"finish_reason": None,
}
],
}
)
# Actual error shape captured from hosted NIM, inside HTTP 200 SSE.
events.append(
{
"error": {
"message": "ValueError: Received multimodal data but multimodal processing is not enabled. Use --enable-multimodal flag to enable multimodal processing.",
"type": "invalid_request_error",
"code": 400,
}
}
)
return httpx2.Response(
200,
headers={"content-type": "text/event-stream"},
text="".join(f"data: {json.dumps(event)}\n\n" for event in events)
+ "data: [DONE]\n\n",
)
sdk = AsyncOpenAI(
api_key="test",
base_url="https://provider.invalid/v1",
max_retries=0,
http_client=httpx2.AsyncClient(transport=httpx2.MockTransport(reply)),
)
provider = OpenAIChatProvider(
make_provider_config(api_key="test", base_url="https://provider.invalid/v1"),
profile=OpenAIChatProfile(
OpenAIChatRequestPolicy("TEST", ReasoningReplayMode.REASONING_CONTENT),
NO_REASONING,
),
admission=immediate_admission(max_attempts=3),
client=sdk,
)
resolver_patch, client = _client_for(provider)
try:
with resolver_patch, client:
response = client.post("/v1/messages", json=_messages_payload(stream=True))
finally:
asyncio.run(sdk.close())
assert calls == 1
request_id = response.headers["request-id"]
if partial:
assert response.status_code == 200
events = parse_sse_text(response.text)
assert _PARTIAL_CONTENT in response.text
assert events[-1].event == "error"
assert not any(event.event == "message_stop" for event in events)
error = events[-1].data["error"]
else:
assert response.status_code == 400
assert response.headers["x-should-retry"] == "false"
assert response.json()["request_id"] == request_id
error = response.json()["error"]
assert error["type"] == "invalid_request_error"
assert "multimodal processing is not enabled" in error["message"]
assert request_id in error["message"]
def _terminal_trace(trace_mock: MagicMock) -> dict[str, Any]:
return dict(
next(
call.kwargs
for call in trace_mock.call_args_list
if call.kwargs.get("event")
== "free_claude_code.api.response.terminal_execution_error"
)
)
def _grouped_rate_limit_provider(chunks: list[str]) -> CanonicalFailureProvider:
return CanonicalFailureProvider(
chunks,
kind=FailureKind.RATE_LIMIT,
status_code=429,
message="upstream is busy",
retryable=True,
grouped=True,
)
def _timeout_provider(chunks: list[str]) -> CanonicalFailureProvider:
return CanonicalFailureProvider(
chunks,
kind=FailureKind.TIMEOUT,
status_code=504,
message="Provider read timed out.",
retryable=False,
)
@pytest.mark.parametrize(
("path", "payload", "expected_type"),
[
("/v1/messages", _messages_payload(stream=True), "rate_limit_error"),
("/v1/responses", _responses_payload(), "rate_limit_error"),
],
)
def test_grouped_pre_start_execution_failure_keeps_canonical_wire_error(
path: str,
payload: dict[str, object],
expected_type: str,
) -> None:
provider = _grouped_rate_limit_provider([])
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
assert response.status_code == 429
assert response.headers["x-should-retry"] == "false"
error = response.json()["error"]
assert error["type"] == expected_type
assert error["message"] == f"upstream is busy\n\nRequest ID: {request_id}"
trace = _terminal_trace(trace_mock)
assert trace["status_code"] == 429
assert trace["error_type"] == "rate_limit_error"
assert trace["exc_type"] == "ExecutionFailure"
assert trace["failure_kind"] == "rate_limit"
@pytest.mark.parametrize("path", ["/v1/messages", "/v1/responses"])
def test_grouped_post_start_execution_failure_keeps_canonical_terminal_event(
path: str,
) -> None:
provider = _grouped_rate_limit_provider(_partial_anthropic_stream(close_block=True))
payload = (
_messages_payload(stream=True)
if path == "/v1/messages"
else _responses_payload()
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
events = parse_sse_text(response.text)
if path == "/v1/messages":
assert events[-1].event == "error"
error = events[-1].data["error"]
else:
assert events[-1].event == "response.failed"
error = events[-1].data["response"]["error"]
assert response.status_code == 200
assert error["type"] == "rate_limit_error"
assert error["message"] == f"upstream is busy\n\nRequest ID: {request_id}"
if path == "/v1/messages":
assert _terminal_trace(trace_mock)["failure_kind"] == "rate_limit"
else:
trace_mock.assert_not_called()
def test_grouped_stream_false_execution_failure_discards_partial_content() -> None:
provider = _grouped_rate_limit_provider(
_partial_anthropic_stream(close_block=False)
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post("/v1/messages", json=_messages_payload(stream=False))
request_id = response.headers["request-id"]
assert response.status_code == 429
assert response.headers["x-should-retry"] == "false"
assert response.json()["error"] == {
"type": "rate_limit_error",
"message": f"upstream is busy\n\nRequest ID: {request_id}",
}
assert _PARTIAL_CONTENT not in response.text
trace = _terminal_trace(trace_mock)
assert trace["status_code"] == 429
assert trace["error_type"] == "rate_limit_error"
assert trace["exc_type"] == "ExecutionFailure"
assert trace["failure_kind"] == "rate_limit"
def test_messages_pre_start_execution_failure_is_correlated_terminal_json() -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.RATE_LIMIT,
status_code=429,
message="upstream is busy",
retryable=True,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/messages", json=_messages_payload(stream=True))
request_id = response.headers["request-id"]
assert response.status_code == 429
assert response.headers["content-type"].startswith("application/json")
assert response.headers["x-should-retry"] == "false"
assert "x-request-id" not in response.headers
assert response.json() == {
"type": "error",
"error": {
"type": "rate_limit_error",
"message": f"upstream is busy\n\nRequest ID: {request_id}",
},
"request_id": request_id,
}
assert provider.stream_kwargs[0]["request_id"] == request_id
@pytest.mark.parametrize(
("path", "payload"),
[
("/v1/messages", _messages_payload(stream=True)),
("/v1/responses", _responses_payload()),
],
)
def test_pre_start_permission_failure_preserves_403_without_client_retry(
path: str,
payload: dict[str, object],
) -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.PERMISSION,
status_code=403,
message="Provider denied access.",
retryable=False,
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
error = response.json()["error"]
assert response.status_code == 403
assert response.headers["x-should-retry"] == "false"
assert error["type"] == "permission_error"
assert error["message"] == f"Provider denied access.\n\nRequest ID: {request_id}"
if path == "/v1/messages":
assert response.json()["request_id"] == request_id
assert "x-request-id" not in response.headers
else:
assert response.headers["x-request-id"] == request_id
trace = _terminal_trace(trace_mock)
assert trace["failure_kind"] == "permission"
assert trace["status_code"] == 403
assert trace["error_type"] == "permission_error"
assert trace["provider_retryable"] is False
@pytest.mark.parametrize(
("path", "payload"),
[
("/v1/messages", _messages_payload(stream=True)),
("/v1/responses", _responses_payload()),
],
)
def test_pre_start_request_too_large_failure_preserves_413(
path: str,
payload: dict[str, object],
) -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.INVALID_REQUEST,
status_code=413,
message="Provider rejected the request as too large.",
retryable=False,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
body = response.json()
assert response.status_code == 413
assert response.headers["x-should-retry"] == "false"
assert body["error"]["type"] == "request_too_large"
assert body["error"]["message"] == (
f"Provider rejected the request as too large.\n\nRequest ID: {request_id}"
)
if path == "/v1/messages":
assert body["request_id"] == request_id
else:
assert response.headers["x-request-id"] == request_id
def test_messages_context_window_failure_triggers_client_compaction() -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.CONTEXT_WINDOW_EXCEEDED,
status_code=400,
message="Provider input exceeds the model context window.",
retryable=False,
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post("/v1/messages", json=_messages_payload(stream=True))
request_id = response.headers["request-id"]
assert response.status_code == 400
assert response.headers["x-should-retry"] == "false"
assert response.json() == {
"type": "error",
"error": {
"type": "invalid_request_error",
"message": (
"prompt is too long\n\n"
"Provider input exceeds the model context window.\n\n"
f"Request ID: {request_id}"
),
},
"request_id": request_id,
}
trace = _terminal_trace(trace_mock)
assert trace["failure_kind"] == "context_window_exceeded"
assert trace["status_code"] == 400
assert trace["error_type"] == "invalid_request_error"
assert trace["provider_retryable"] is False
def test_responses_context_window_failure_triggers_client_compaction() -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.CONTEXT_WINDOW_EXCEEDED,
status_code=400,
message="Provider input exceeds the model context window.",
retryable=False,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/responses", json=_responses_payload())
request_id = response.headers["request-id"]
assert response.status_code == 400
assert response.headers["x-should-retry"] == "false"
assert response.json()["error"] == {
"message": (
"Provider input exceeds the model context window.\n\n"
f"Request ID: {request_id}"
),
"type": "invalid_request_error",
"param": None,
"code": "context_length_exceeded",
}
def test_responses_pre_start_execution_failure_is_correlated_terminal_json() -> None:
provider = CanonicalFailureProvider(
[],
kind=FailureKind.OVERLOADED,
status_code=529,
message="provider overloaded",
retryable=True,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/responses", json=_responses_payload())
request_id = response.headers["request-id"]
assert response.status_code == 529
assert response.headers["content-type"].startswith("application/json")
assert response.headers["x-should-retry"] == "false"
assert response.headers["x-request-id"] == request_id
assert response.json() == {
"error": {
"message": f"provider overloaded\n\nRequest ID: {request_id}",
"type": "overloaded_error",
"param": None,
"code": None,
}
}
assert provider.stream_kwargs[0]["request_id"] == request_id
def test_messages_post_start_execution_failure_follows_closed_block() -> None:
provider = CanonicalFailureProvider(
_partial_anthropic_stream(close_block=True),
kind=FailureKind.OVERLOADED,
status_code=529,
message="provider overloaded",
retryable=True,
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post("/v1/messages", json=_messages_payload(stream=True))
request_id = response.headers["request-id"]
events = parse_sse_text(response.text)
assert response.status_code == 200
assert "x-should-retry" not in response.headers
assert [event.event for event in events] == [
"message_start",
"content_block_start",
"content_block_delta",
"content_block_stop",
"error",
]
assert events[-1].data["error"] == {
"type": "overloaded_error",
"message": f"provider overloaded\n\nRequest ID: {request_id}",
}
assert "message_stop" not in response.text
assert _terminal_trace(trace_mock) == {
"stage": "egress",
"event": "free_claude_code.api.response.terminal_execution_error",
"source": "api",
"wire_api": "messages",
"request_id": request_id,
"status_code": 529,
"error_type": "overloaded_error",
"client_should_retry": False,
"exc_type": "ExecutionFailure",
"failure_kind": "overloaded",
"provider_retryable": True,
}
def test_responses_post_start_execution_failure_retains_id_after_block_close() -> None:
provider = CanonicalFailureProvider(
_partial_anthropic_stream(close_block=True),
kind=FailureKind.RATE_LIMIT,
status_code=429,
message="upstream is busy",
retryable=True,
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post("/v1/responses", json=_responses_payload())
request_id = response.headers["request-id"]
events = parse_sse_text(response.text)
event_names = [event.event for event in events]
created = events[0].data["response"]
failed = events[-1].data["response"]
assert response.status_code == 200
assert response.headers["x-request-id"] == request_id
assert "x-should-retry" not in response.headers
assert event_names[0] == "response.created"
assert "response.output_item.done" in event_names
assert event_names.index("response.output_item.done") < event_names.index(
"response.failed"
)
assert event_names[-1] == "response.failed"
assert failed["id"] == created["id"]
assert failed["status"] == "failed"
assert failed["error"] == {
"message": f"upstream is busy\n\nRequest ID: {request_id}",
"type": "rate_limit_error",
"param": None,
"code": None,
}
trace_mock.assert_not_called()
def test_responses_post_start_context_failure_retains_compaction_code() -> None:
provider = CanonicalFailureProvider(
_partial_anthropic_stream(close_block=True),
kind=FailureKind.CONTEXT_WINDOW_EXCEEDED,
status_code=400,
message="Provider input exceeds the model context window.",
retryable=False,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/responses", json=_responses_payload())
events = parse_sse_text(response.text)
assert events[-1].event == "response.failed"
assert events[-1].data["response"]["error"]["code"] == ("context_length_exceeded")
def test_messages_stream_false_discards_partial_content_on_execution_failure() -> None:
provider = CanonicalFailureProvider(
_partial_anthropic_stream(close_block=False),
kind=FailureKind.RATE_LIMIT,
status_code=429,
message="upstream is busy",
retryable=True,
)
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/messages", json=_messages_payload(stream=False))
request_id = response.headers["request-id"]
assert response.status_code == 429
assert response.headers["content-type"].startswith("application/json")
assert response.headers["x-should-retry"] == "false"
assert response.json()["request_id"] == request_id
assert response.json()["error"] == {
"type": "rate_limit_error",
"message": f"upstream is busy\n\nRequest ID: {request_id}",
}
assert _PARTIAL_CONTENT not in response.text
@pytest.mark.parametrize(
("path", "payload"),
[
("/v1/messages", _messages_payload(stream=True)),
("/v1/responses", _responses_payload()),
],
)
def test_pre_start_provider_timeout_is_terminal_504(
path: str,
payload: dict[str, object],
) -> None:
provider = _timeout_provider([])
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
assert response.status_code == 504
assert response.headers["content-type"].startswith("application/json")
assert response.headers["x-should-retry"] == "false"
assert response.json()["error"] == {
"type": "timeout_error",
"message": (f"Provider read timed out.\n\nRequest ID: {request_id}"),
**({} if path == "/v1/messages" else {"param": None, "code": None}),
}
if path == "/v1/messages":
assert response.json()["request_id"] == request_id
assert "x-request-id" not in response.headers
else:
assert response.headers["x-request-id"] == request_id
trace = _terminal_trace(trace_mock)
assert trace["status_code"] == 504
assert trace["error_type"] == "timeout_error"
assert trace["failure_kind"] == "timeout"
assert trace["provider_retryable"] is False
assert trace["client_should_retry"] is False
@pytest.mark.parametrize("path", ["/v1/messages", "/v1/responses"])
def test_post_start_provider_timeout_is_terminal_protocol_event(path: str) -> None:
provider = _timeout_provider(_partial_anthropic_stream(close_block=True))
payload = (
_messages_payload(stream=True)
if path == "/v1/messages"
else _responses_payload()
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post(path, json=payload)
request_id = response.headers["request-id"]
events = parse_sse_text(response.text)
assert response.status_code == 200
assert "x-should-retry" not in response.headers
if path == "/v1/messages":
assert events[-1].event == "error"
error = events[-1].data["error"]
assert "message_stop" not in response.text
else:
assert events[0].event == "response.created"
assert events[-1].event == "response.failed"
assert events[-1].data["response"]["id"] == events[0].data["response"]["id"]
error = events[-1].data["response"]["error"]
assert error["type"] == "timeout_error"
assert error["message"] == (f"Provider read timed out.\n\nRequest ID: {request_id}")
if path == "/v1/messages":
trace = _terminal_trace(trace_mock)
assert trace["failure_kind"] == "timeout"
assert trace["provider_retryable"] is False
assert trace["client_should_retry"] is False
else:
trace_mock.assert_not_called()
def test_responses_provider_timeout_closes_committed_lifecycle() -> None:
response_id = "resp_provider_timeout"
provider = ResponsesFailureProvider(
responses_chunks=(
_responses_event(
"response.created",
{
"type": "response.created",
"sequence_number": 0,
"response": _responses_wire_payload(
response_id=response_id,
status="in_progress",
),
},
),
)
)
resolver_patch, client = _client_for(provider)
with (
resolver_patch,
patch("free_claude_code.api.response_streams.trace_event") as trace_mock,
client,
):
response = client.post("/v1/responses", json=_responses_payload())
request_id = response.headers["request-id"]
events = parse_sse_text(response.text)
assert response.status_code == 200
assert [event.event for event in events] == [
"response.created",
"response.failed",
]
assert events[-1].data["sequence_number"] == 1
failed = events[-1].data["response"]
assert failed["id"] == response_id
assert failed["status"] == "failed"
assert failed["error"] == {
"message": (f"Provider read timed out.\n\nRequest ID: {request_id}"),
"type": "timeout_error",
"param": None,
"code": None,
}
assert provider.close_calls == 1
assert _terminal_trace(trace_mock) == {
"stage": "egress",
"event": "free_claude_code.api.response.terminal_execution_error",
"source": "api",
"wire_api": "responses",
"request_id": request_id,
"status_code": 504,
"error_type": "timeout_error",
"client_should_retry": False,
"exc_type": "ExecutionFailure",
"failure_kind": "timeout",
"provider_retryable": False,
}
def test_stream_false_provider_timeout_discards_partial_content() -> None:
provider = _timeout_provider(_partial_anthropic_stream(close_block=False))
resolver_patch, client = _client_for(provider)
with resolver_patch, client:
response = client.post("/v1/messages", json=_messages_payload(stream=False))
request_id = response.headers["request-id"]
assert response.status_code == 504
assert response.headers["x-should-retry"] == "false"
assert response.json()["error"] == {
"type": "timeout_error",
"message": (f"Provider read timed out.\n\nRequest ID: {request_id}"),
}
assert _PARTIAL_CONTENT not in response.text
|