scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-11-11 08:38:24 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 359
litellm/tests/integration/translation/responses/bases/anthropic.py
devin-ai-integration[bot] b578dcf278
test(translation): recapture anthropic claude bases after usage speed field (#47116) 
Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
2026-10-17 09:29:56 -07:00

903 lines
36 KiB
Python
Raw Permalink Blame History

import json
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import (
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
RESPONSES_REQUEST,
RESPONSES_RESPONSE,
)
from integration.translation.templates.anthropic import ANTHROPIC_MESSAGES_REQUEST, ANTHROPIC_MESSAGES_RESPONSE
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "anthropic/claude-haiku-4-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-haiku-4-5",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
mock_provider_response={
"model": "claude-haiku-4-5-20251001",
"id": "msg_011Cg7v1CTrRytLeZfaZojBR",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 17,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 5,
"service_tier": "standard",
"inference_geo": "not_available",
"speed": "standard",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "anthropic/claude-haiku-4-5",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"phase": None,
}
],
"parallel_tool_calls": False,
"temperature": None,
"tool_choice": "auto",
"tools": [],
"top_p": None,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 17,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 17,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 5,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 5},
"total_tokens": 22,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "anthropic/claude-sonnet-4-6",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-sonnet-4-6",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
mock_provider_response={
"model": "claude-sonnet-4-6",
"id": "msg_011Cg7v1kr1sYXyQA143nsda",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello! How can I help you?"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 18,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 11,
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "anthropic/claude-sonnet-4-6",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello! How can I help you?", "annotations": []}],
"phase": None,
}
],
"parallel_tool_calls": False,
"temperature": None,
"tool_choice": "auto",
"tools": [],
"top_p": None,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 18,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 18,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 11,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 11},
"total_tokens": 29,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
CLAUDE_SONNET_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "anthropic/claude-sonnet-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-sonnet-5",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
mock_provider_response={
"model": "claude-sonnet-5",
"id": "msg_011Cg7v215mkRTDBRoPcerLf",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 21,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "anthropic/claude-sonnet-5",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"phase": None,
}
],
"parallel_tool_calls": False,
"temperature": None,
"tool_choice": "auto",
"tools": [],
"top_p": None,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 21,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 21,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 27,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "anthropic/claude-opus-4-8",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-opus-4-8",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
mock_provider_response={
"model": "claude-opus-4-8",
"id": "msg_011Cg7v1PgnYbGrw8eGpka6f",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 21,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "anthropic/claude-opus-4-8",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"phase": None,
}
],
"parallel_tool_calls": False,
"temperature": None,
"tool_choice": "auto",
"tools": [],
"top_p": None,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 21,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 21,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 27,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-sonnet-5-5"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-sonnet-5-5",
"system": [
{
"type": "text",
"text": "You help maintain a synthetic Python project. Read the relevant files before "
"suggesting a fix. Explain which file you need next, then call a read-only tool. "
"Never change files. Use the responses client for this project review. Consider "
"zero, negative and non-integer quantities before choosing the next file to "
"inspect.",
}
],
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-sonnet-5-5",
"id": "msg_011Cg32qrmyWNAPnHJhxBL3M",
"content": [
{
"type": "thinking",
"thinking": "The user wants the validation file read first, but since the test reads are "
"independent, I can just include both in the same batch since it's "
"effectively still prioritizing validation.\n"
"\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll check `shop/validation.py` to see how `validate_quantity` handles "
"zero, negative, and non-integer values, and read `tests/test_validation.py` "
"alongside it to confirm the expected behavior.\n"
"\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_01GYseiK8hh9QxfWJ6HbiAt3",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"caller": {"type": "direct"},
},
{
"type": "tool_use",
"id": "toolu_01U3TuUTifkSBLVzyTFnbMN1",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 509,
"output_tokens_details": {"thinking_tokens": 313},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
},
expected_litellm_response={**RESPONSES_RESPONSE, "model": "anthropic/claude-sonnet-5-5"},
)
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSkgYKEAgSGAI4AUIIdGhpbmtpbmcSDDNkbcUmfOcV76xw1BoM1d74UojfhlwUKXJRIjDruKpmF7Xkn4wU+s/jLhdQL1oTKBrwFivaGL2z"
"2qnyjXgtCgYeYxa4syAiIlaJMkwqrwXgBL0q4FtZvicmkVAfs3GMC/MvUk3zJ5psHQWMfE+EYU436rT6+Xcoj47t9XgRI+Qs5vio51d6AvNR"
"snONcWIVexutCBNKfDOcnBZwzcgr6xlR8+bvZI0a4kgGEkJzqUm5nkST8scZwMkJPsgk0Zrr8aDDcGGmtc161vfYqDIMq6+IpnOlib1Q/FA0"
"gO2Trdo93xLjKvHUXbmSzXokO5x7s60ymFjVd6RzmoLStGgBwiMXElWT40WPh/T2tx2GtuYJ6EPuMOpIqzmI3pLbYplVdVBGdEhUL+wPD8gT"
"mHbBq1Oz8cwSdUyRWBTMCgyZdMkuIw6lPFRAec/19JbDZQWQbnKCOmZK9YwicptzrbllIKqNjJTX4sww8MvMp69lMRxeFqM9tBnC7oIYevEg"
"witiRyKsVfbQTfmexva4g1WenMsqKDub77WJPsbhN0ihuQvlLssmGtRLKh/C4waaaCTzqsj4mDO1UEnflUczRoQHF2fxlsQBVjMc0QcuICYL"
"nwcc2ZL8zvL14sELhiSx2PvxjOIwNuEezF3w3uhS8o/9CSbfJnJL6lQ3lldTA8+WL+cvzN+73+9rTN89GRCJPGni52cMkuGV5ObB2dAyNsBi"
"/WsPwiUetMhWeds/kP+Ct1cqagNuCTenGF+oKf0qNsvIPnWoc8a8YW9bxlEgQ9qBF0NXT26RkEE90Qsp4aseb/qmEDKxE2DMcdMwOru3CEvD"
"xQNy07Dak3+tiSS63kRZwsRFbMTb42W98NrDXqq+sfyvMQarPJj/OmWExt9rna3Y+BlWNq0j82gUyCY4gzv4VHM/OyuhNcmNKDdDsgvSwub9"
"wRSKmuC4LDAhrRMuTQ/cMZq1+ZyQHiuFvnsArZxCusQ5QxDjxRGsI+uMeWmkPY3TN1ofMSIbeWpyiwnsR8EYAQ=="
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-haiku-5-5"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-haiku-5-5",
"system": [
{
"type": "text",
"text": "You help maintain a synthetic Python project. Read the relevant files before "
"suggesting a fix. Explain which file you need next, then call a read-only tool. "
"Never change files. Use the responses client for this project review. Consider "
"zero, negative and non-integer quantities before choosing the next file to "
"inspect.",
}
],
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-haiku-5-5",
"id": "msg_011Cg3716ZuhZgb2YrqgDQVR",
"content": [
{
"type": "thinking",
"thinking": "I'll just read the validation.py file directly, starting with a reasonable range "
"near the top of the file since no specific lines were requested.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_01H53znxFvBbuHPXNePjEhW5",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 167,
"output_tokens_details": {"thinking_tokens": 67},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
},
expected_litellm_response={
**RESPONSES_RESPONSE,
"model": "anthropic/claude-haiku-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll just read the validation.py file directly, starting with a "
"reasonable range near the top of the file since no specific lines were "
"requested.\n"
"\n",
"annotations": [],
}
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I'll just read the validation.py file directly, starting with a "
"reasonable range near the top of the file since no specific lines were "
"requested.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
}
],
separators=(",", ":"),
),
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "toolu_01H53znxFvBbuHPXNePjEhW5",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01H53znxFvBbuHPXNePjEhW5",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 873,
},
"output_tokens": 167,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 67, "text_tokens": 100},
"total_tokens": 1044,
"cost": None,
},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll just read the validation.py file directly, starting with a reasonable "
"range near the top of the file since no specific lines were requested.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
}
],
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSmwYKEAgSGAI4AUIIdGhpbmtpbmcSDAp614h0T9spOzVRohoMRXG5Q7QnUaybHmMQIjDVSvcKksTqmvoyviUgrnx25thBdpJEPfO61S1d"
"hV+zrTe/1FP4+d14zYjlYEZ8Id0quAW5bhrtPXA2ESV73lWwlm/w+SYE+QsiZA9rbSOkSdKLTg37S3i/w+ad4VIFTr1iNoV8RfYZog2D3q69"
"miBOF29U8ILsi+tUM66QNtGdGWDahlsimm+d/IMs+Ie4uP8OHr5X/bJ7NS2MJ407WhS1E+rYrmOce5lHOmhVPGzcL2EM+ToptZ84DR8N7iIq"
"k9pP8CoQL7Z10aCTkG4r2tbdIup7RE3WXrsBHNbs+RAqF5LXbEpsQZaXLx71U1DpDffx6OZ3OSCw1tEcA4o2FDVFNv8CQO3wBnWqkZyjehqb"
"sMarphzyvDxDO7T//sTTVM1593gEbLoRNeUne3bwtgdwoDPMXminh541bLo8vjo25kERKJedEUG/CDZqT16YziXqlSvzV/TgQeddzb2TLnJT"
"LoYoXsmn8789+6nBPdIe3SQu1nhVP5XUgC0+dI/iKqbiuswuslOSx3ZuIEan3i/HZ+XflqXy4ewB0+5sLHbiwzmGEbrZcWl0wbebc2Da0LnY"
"rgAQHqKH0vl4o3fGmaPMxcPml9RP4zG0KblC24o6acb0DYAFTSfblE3dKoMgZwPfiMijqiXriZQSuF5Y3VGY6CcWGQDi5kLzbFe5D2HA/nM4"
"66bjH9VKvVsVglODnnDPQD84e9YM86EelbaxCQcNo9MrCpp7g0tWRvMEiAlfKo0W4hvsYaa2op3XMbHVlJeWJcoU/WPodcEnSEPl6/pz522X"
"I/ItEKXeKIqs0VG9giw0pxuHB8+ig+8bn74Lezmw4LLHk67D2/PCVKLSqrIkHfE41ASdJSFAopc7YY8iovyAVdvUfm+7Vefmmphkx7C162Ze"
"gVLS7mSAxuQCWsIlFyui50D75X8xEa2CdijsbrTvCqKIQHcywq8oLLGmDilMRs1DlnQiAWETjHvpzp3WEs9eZBi4tHPz5CMYAQ=="
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1: Final = (
"CAQS0QYKEQgSGAI4AUIJbmFycmF0aW9uEgwL0nQCUkLBdQqyQ48aDBNdOXSFQIfQqDyzeyIwgBeYVWjfsySdPznFBTS6nfeLZiDt+L2EHka6"
"Wp6pH2lO/ZVHd45V/Yy8qr0uX3xrKu0F3QlrjBy505vPXf94O0o7bPvrihxLhHnG9Wf14JgZfAXTqiM7kZxqRCJF2DlP2S4BzspQGIILMu+e"
"gnizwTdKpM7I2XgSqV4ZnQRhjPgRVgQkQrbRfSRtfFWDTcJtz/Lp/2KQw6ijdj1tWc66QB8uNSkTStOlz1sseMaBWNOps0WK+vkJw6J+ZbZK"
"dFdZSgNQ2Iwxl3Pys57YHUrqHaVi3NJVFK760EZeavxciDafSs+ZlTuzeghIy/iLQdSSeUhCl0pZE6SCkEWca+A02GewaHguZ9eRoGnCVsSw"
"soQT3aeK7sUbas1sFDyWSvieJ0naBRUN6ae1QSBAWqYnsvEEx11wWcN/DB3SzjM5j48po9ov+wbeoBl2nex/iUVSfBBixe36nZ8Vt37dC6f+"
"0wgw5DHVtiqFKYSH/b3owUf2RJuYUut7LPkT5qFm0mPlkCqSfZqpRwijVAmV0obs61IgrTVlmFq2igWs0rt9v5iuM7+zjI/DtLL6NgGaFgXW"
"Oc8VjDsrHnUMCK0/QtHuC51aE8mqzw47i4wTQ3O5+/8F8ZJn0PkmxB2lZixCSZ42XhU5pqPiTAWjuXciwXzkCcJKz+CR2cl2gFWw3oQR1N6B"
"f9Wlk3f6DrtPywDFDlY7piBz25k958iZDRvTYkleo8daA+DAWMXS+3k0doIpNBSQMoE67GCgqk3A22huvgYdCqlD142RbrdB7xlUviysajfB"
"lbOFXNjs5Lp+v7UVPiNCDJwha/ZIZfmgp86OSKryKTRrBiMNZRv7v9xF5NyQhB+MzGG3pDzzhqYUlzpIE2vmAd4Hk3/T4X5WvIGW+Juv2U+r"
"pHW59B5K/+2tF3VczG//CpHoB6R+8fNWTDp4Bx+l7v+Pep1lBvVG+XAZZHwaPxeXgaOZcUYs/SMdxYDBflXfvxusttZoXNiXJROZle/lIIeo"
"fDbMvuc14FSkdLJ+N41d4et8zwXI5BcOxPIB7ryDVejwgF/F5kAMtnVdzQEYAQ=="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-opus-5-5"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-opus-5-5",
"system": [
{
"type": "text",
"text": "You help maintain a synthetic Python project. Read the relevant files before "
"suggesting a fix. Explain which file you need next, then call a read-only tool. "
"Never change files. Use the responses client for this project review. Consider "
"zero, negative and non-integer quantities before choosing the next file to "
"inspect.",
}
],
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-opus-5-5",
"id": "msg_011Cg372KDhhjt1fiWYa1qCb",
"content": [
{
"type": "thinking",
"thinking": "Since the user asked for the validation file first, I'll start by reading "
"shop/validation.py around line 18 before looking at anything else.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll check validate_quantity in shop/validation.py to see how it handles zero, "
"negative, and non-integer inputs before moving to the test file.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_0186wos82AWCLwkPWVeVegg8",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 228,
"output_tokens_details": {"thinking_tokens": 130},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
},
expected_litellm_response={
**RESPONSES_RESPONSE,
"model": "anthropic/claude-opus-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Since the user asked for the validation file first, I'll start by reading "
"shop/validation.py around line 18 before looking at anything else.\n"
"\n"
"I'll check validate_quantity in shop/validation.py to see how it handles "
"zero, negative, and non-integer inputs before moving to the test file.\n"
"\n",
"annotations": [],
}
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "Since the user asked for the validation file first, I'll start by reading "
"shop/validation.py around line 18 before looking at anything else.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll check validate_quantity in shop/validation.py to see how it handles "
"zero, negative, and non-integer inputs before moving to the test file.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
],
separators=(",", ":"),
),
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"call_id": "toolu_0186wos82AWCLwkPWVeVegg8",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_0186wos82AWCLwkPWVeVegg8",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 873,
},
"output_tokens": 228,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 130, "text_tokens": 98},
"total_tokens": 1105,
"cost": None,
},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "Since the user asked for the validation file first, I'll start by reading "
"shop/validation.py around line 18 before looking at anything else.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll check validate_quantity in shop/validation.py to see how it handles "
"zero, negative, and non-integer inputs before moving to the test file.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
],
},
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-fable-5-1"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-fable-5-1",
"system": [
{
"type": "text",
"text": "You help maintain a synthetic Python project. Read the relevant files before "
"suggesting a fix. Explain which file you need next, then call a read-only tool. "
"Never change files. Use the responses client for this project review. Consider "
"zero, negative and non-integer quantities before choosing the next file to "
"inspect.",
}
],
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_011Cg3734Dqb6rpmJnPKii79",
"content": [
{
"type": "text",
"text": "Reading `shop/validation.py` first to see the rule behind the zero rejection, "
"then I'll read the test file in a separate step since there's nothing to derive "
"from it for the read.",
},
{
"type": "tool_use",
"id": "toolu_01QKMW1txMKCm8oSZyEwo7wX",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 155,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "global",
"speed": "standard",
},
},
expected_litellm_response={
**RESPONSES_RESPONSE,
"model": "anthropic/claude-fable-5-1",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "Reading `shop/validation.py` first to see the rule behind the zero "
"rejection, then I'll read the test file in a separate step since there's "
"nothing to derive from it for the read.",
"annotations": [],
}
],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"call_id": "toolu_01QKMW1txMKCm8oSZyEwo7wX",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01QKMW1txMKCm8oSZyEwo7wX",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 873,
},
"output_tokens": 155,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 155},
"total_tokens": 1032,
"cost": None,
},
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
Reference in a new issue View git blame Copy permalink