scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-17 04:34:25 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 265

test(translation): share rich fixtures across Claude, GPT and Gemini providers (#46585)

Browse source 
* test(integration): add rich anthropic claude haiku 5.5, opus 5.5 and fable 5.1 translation cases

Capture-backed basic cases on /v1/chat/completions, /v1/messages and /v1/responses for claude-haiku-5-5, claude-opus-5-5 and claude-fable-5-1, reusing the shared client templates and ANTHROPIC_MESSAGES_REQUEST/RESPONSE with model-specific id, content and usage overrides. The minimal Opus 5.5 hello cases are replaced by the rich conversation. Sonnet 5.5 and legacy models are unchanged

* test(translation): rich OpenAI captures for gpt-6.1-sol, gpt-6-luna, gpt-6-astra and gpt-5.6-terra

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(translation): rich Azure gpt-6.1-sol, gpt-6-luna, gpt-6-astra and gpt-5.6-terra cases

* test(translation): rich azure_ai Claude cases for haiku-5-5 and fable-5-1

Bind the shared chat_completions, messages and responses client templates and the anthropic provider templates to azure_ai/claude-haiku-5-5 and azure_ai/claude-fable-5-1 from real Azure AI Foundry captures, keeping the Azure dialect exact (/anthropic/v1/messages, x-api-key plus api-key on chat_completions and responses, system as a text block list on /v1/messages). Add prompt_cache_hit variants for both models from the second call inside the cache window. The two deployments need rows in tests/integration/proxy_config.yaml

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(translation): rich Gemini bases for gemini-3.8-flash, gemini-3.1-pro-preview and gemini-4-argon

Add the shared generateContent provider templates in templates/gemini.py from
real captures and bind the three target models on chat completions, messages
and responses with explicit per-model response overrides. gemini-4-argon is
registered in the three basic lists. gemini-3.5-flash is unchanged

* test(translation): enrich vertex_ai claude and gemini cases from live captures

Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>

* test(integration): rich Bedrock converse, invoke and mantle translation cases from real captures

* test(integration): register the rich translation deployments and follow the rich Gemini 3.8 Flash cases

Add the synthetic deployments the rich provider cases bind (anthropic, openai, azure, azure_ai, gemini, vertex_ai, bedrock converse, invoke and mantle) to tests/integration/proxy_config.yaml, all pointed at the fake provider on 127.0.0.1:8191 with synthetic keys. The Gemini omitted-temperature contract now takes its expected generationConfig and reply text from the rich GEMINI_3_8_FLASH_TEST_CASE literals instead of the retired minimal hello cases

* test(translation): reuse bridged and native response templates

---------

Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Co-authored-by: kerry <kerry@berri.ai>
This commit is contained in:
Kerry Lu 2026-10-14 19:53:09 -07:00 • committed by GitHub
parent e889d9d653
commit 7b7604f0ed
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
72 changed files with 15953 additions and 7134 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

17
tests/integration/providers/test_gemini_omitted_temperature.py
View file

@ -20,9 +20,9 @@ from pydantic import JsonValue
GENERATE_TARGET: Final = "/models/gemini-3.8-flash:generateContent"
STREAM_TARGET: Final = "/models/gemini-3.8-flash:streamGenerateContent?alt=sse"
EXPECTED_GENERATION_CONFIG: Final = {"max_output_tokens": 1024}
ENDPOINT_CASES: Final = (CHAT_COMPLETIONS_TEST_CASE, MESSAGES_TEST_CASE, RESPONSES_TEST_CASE)
BURST: Final = ENDPOINT_CASES * 4
BURST_ANSWER: Final = "I need to inspect `shop/validation.py` next."
STREAM_USAGE: Final = {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
@ -54,6 +54,12 @@ def _generation_config(request: Request) -> dict[str, JsonValue]:
return object_value(JSON_OBJECT.validate_json(request.body)["generationConfig"])
def _expected_generation_config(case: TranslationTestCase) -> dict[str, JsonValue]:
expected: Final = object_value(case.expected_provider_request["generationConfig"])
assert "temperature" not in expected, expected
return expected
@pytest.mark.parametrize("case", ENDPOINT_CASES, ids=lambda case: case.litellm_endpoint)
def test_streamed_request_without_temperature_forwards_none(
case: TranslationTestCase, gateway: Gateway, provider: SharedProvider
@ -64,7 +70,7 @@ def test_streamed_request_without_temperature_forwards_none(
assert "Hello." in response.text, response.text
received: Final = provider.received()
assert [(request.method, request.target) for request in received] == [("POST", STREAM_TARGET)]
assert _generation_config(received[0]) == EXPECTED_GENERATION_CONFIG
assert _generation_config(received[0]) == _expected_generation_config(case)
def test_concurrent_mixed_endpoint_burst_without_temperature_forwards_none(
@ -77,7 +83,10 @@ def test_concurrent_mixed_endpoint_burst_without_temperature_forwards_none(
pool.map(lambda case: gateway.request("POST", case.litellm_endpoint, case.litellm_request), BURST)
)
assert [response.status_code for response in responses] == [200] * len(BURST), [r.text for r in responses]
assert all("Hello." in response.text for response in responses), [r.text for r in responses]
assert all(BURST_ANSWER in response.text for response in responses), [r.text for r in responses]
received: Final = provider.received()
assert [(request.method, request.target) for request in received] == [("POST", GENERATE_TARGET)] * len(BURST)
assert [_generation_config(request) for request in received] == [EXPECTED_GENERATION_CONFIG] * len(BURST)
expected_configs: Final = [_expected_generation_config(CHAT_COMPLETIONS_TEST_CASE)] * len(BURST)
assert sorted(map(json.dumps, (_generation_config(r) for r in received))) == sorted(
map(json.dumps, expected_configs)
)

43
tests/integration/proxy_config.yaml
View file

@ -54,6 +54,11 @@ model_list:
model: gemini/gemini-3.1-pro-preview
api_base: http://127.0.0.1:8191
api_key: synthetic-gemini-key
- model_name: gemini/gemini-4-argon
litellm_params:
model: gemini/gemini-4-argon
api_base: http://127.0.0.1:8191
api_key: synthetic-gemini-key
- model_name: azure_ai/claude-haiku-4-5
litellm_params:
model: azure_ai/claude-haiku-4-5
@ -174,14 +179,19 @@ model_list:
model: openai/gpt-6-luna
api_base: http://127.0.0.1:8191
api_key: synthetic-openai-key
- model_name: openai/gpt-6.1-sol
litellm_params:
model: openai/gpt-6.1-sol
api_base: http://127.0.0.1:8191
api_key: synthetic-openai-key
- model_name: openai/gpt-6-astra
litellm_params:
model: openai/gpt-6-astra
api_base: http://127.0.0.1:8191
api_key: synthetic-openai-key
- model_name: openai/gpt-6.1-sol
- model_name: openai/gpt-5.6-terra
litellm_params:
model: openai/gpt-6.1-sol
model: openai/gpt-5.6-terra
api_base: http://127.0.0.1:8191
api_key: synthetic-openai-key
- model_name: openai/responses/gpt-5.6-sol
@ -218,15 +228,21 @@ model_list:
api_base: http://127.0.0.1:8191
api_key: synthetic-azure-key
api_version: "2025-04-01-preview"
- model_name: azure/gpt-6.1-sol
litellm_params:
model: azure/gpt-6.1-sol
api_base: http://127.0.0.1:8191
api_key: synthetic-azure-key
api_version: "2025-04-01-preview"
- model_name: azure/gpt-6-astra
litellm_params:
model: azure/gpt-6-astra
api_base: http://127.0.0.1:8191
api_key: synthetic-azure-key
api_version: "2025-04-01-preview"
- model_name: azure/gpt-6.1-sol
- model_name: azure/gpt-5.6-terra
litellm_params:
model: azure/gpt-6.1-sol
model: azure/gpt-5.6-terra
api_base: http://127.0.0.1:8191
api_key: synthetic-azure-key
api_version: "2025-04-01-preview"
@ -348,6 +364,13 @@ model_list:
vertex_project: synthetic-vertex-project
vertex_location: global
vertex_credentials: '{"type": "external_account", "audience": "synthetic-vertex-audience", "subject_token_type": "urn:ietf:params:oauth:token-type:jwt", "token_url": "http://127.0.0.1:8190/_oauth/token", "credential_source": {"url": "http://127.0.0.1:8190/health"}}'
- model_name: vertex_ai/gemini-4-argon
litellm_params:
model: vertex_ai/gemini-4-argon
api_base: http://127.0.0.1:8191
vertex_project: synthetic-vertex-project
vertex_location: global
vertex_credentials: '{"type": "external_account", "audience": "synthetic-vertex-audience", "subject_token_type": "urn:ietf:params:oauth:token-type:jwt", "token_url": "http://127.0.0.1:8190/_oauth/token", "credential_source": {"url": "http://127.0.0.1:8190/health"}}'
- model_name: bedrock_mantle/anthropic.claude-haiku-4-5
litellm_params:
model: bedrock_mantle/anthropic.claude-haiku-4-5
@ -396,6 +419,18 @@ model_list:
api_base: http://127.0.0.1:8191
api_key: synthetic-bedrock-mantle-key
aws_region_name: us-east-1
- model_name: bedrock_mantle/openai.gpt-6-astra
litellm_params:
model: bedrock_mantle/openai.gpt-6-astra
api_base: http://127.0.0.1:8191
api_key: synthetic-bedrock-mantle-key
aws_region_name: us-east-1
- model_name: bedrock_mantle/openai.gpt-5.6-terra
litellm_params:
model: bedrock_mantle/openai.gpt-5.6-terra
api_base: http://127.0.0.1:8191
api_key: synthetic-bedrock-mantle-key
aws_region_name: us-east-1
- model_name: perplexity/pplx-decider-v1-27b
litellm_params:
model: perplexity/pplx-decider-v1-27b

465
tests/integration/translation/chat_completions/bases/anthropic.py
View file

@ -86,89 +86,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "anthropic/claude-haiku-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "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-5-5",
"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-5-5",
"id": "msg_011CfoboJTmCCdzhHCYYzodZ",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "anthropic/claude-haiku-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",
},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
@ -429,81 +346,144 @@ CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
expected_litellm_response={**CHAT_COMPLETIONS_RESPONSE, "model": "anthropic/claude-sonnet-5-5"},
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSoggKEAgSGAI4AUIIdGhpbmtpbmcSDHAtt0k5pW+O+4p0yhoMaSOEZS5bpcu05veLIjDPL1g9WsQtCQvCTT+d7CtZXdj8Ky/U+qJXk5YK"
"V+PIuWEZQeNKcaPTleGe9utaR6QqvwdoSvSgT9fVmK4SrR/XSTbPcPpCcRV84Y8g7ZDohrCzpb826nqiRF1A9tQ1K9OrlqiBEmG9ODXI3oy2"
"ag915CwW8oJBjCWAmjmRvkQf64/0IOhqWEunbBPwdfCqqiRtbv1qnqaT2v+WfJeVd7Q72GMGVPjDpI8sZw+k5BoaczYZtJ+T0PbMMNXEwDG8"
"q780JLCmcw5fByE+mX3cUX7SSoAehpwvvmd1/BkzZ7EQaWic7G759KgxzYRtBOiF8Mg9N/holW5GfDF3eBEhAH7JgnV1t+yY+oPy1LpzYGJb"
"GP8gJryTIDRfJmEIX9LwrGjcO30rfGemRv/kzKy1PAY1oLB1jHY6jbO/uGYxZRJy51Sm2Byqj4BHUhZKEEV2GmKwxvr4CBYObD3dBF32FlxD"
"pF4Xz6KuGGUx88ftC51Azp6ySLT/kOsVfqHcXYpH/RbO3BozdCg1AK3pceCljkGmlvZDEVgXZh66O41ZGi7Ku+KbvHADhfJ1dBYodZzNJg8F"
"+MVcQLy4ZhAyfcxp91g6l46vjyEhLEoRNKwrg/dh3cavCsu0EBFQtUgd61U6Eovzyh1JOWDd5mnRE/rN4ISXWcOMKd8o05LZpzmoLkbnub8R"
"DPV0LnPzMd+HHrDpMGoO79qDJU1MdiKhPKGacRP2GnA9Bv5T74r3Y6Zz3KO1tj9TtQ93aPQuiU5Te45T1aIzkNAemkDwuDN/8h/hd0CRCklk"
"2XLb+7ZhQAINBc+yrwoDMq4+vB6y5qjsBBeOMGgWzyPvimWOt4VZczacLJRTKSocioZSYD+tJycCVbaeny41gTGPKicjI4CAji6MEcloNIVt"
"G0bcQwPamtpDokxo/XKQL6W7sL37DQRU5UD+mNG9ntVMgQPb6EmC4boMq/EoEAEqbok0WwUwWhxPfN0EE87gtYUxavNx2/VQJuAVyM8tdKeK"
"hvO8fy0G9d28tRO6yCFvbpKBYDuscZexVT8y5PLJOqVyqIdTYOG6pDDp8MyQ95mDtPHOpTLHo8XAsYtQlHi7qLKmkFx6BjuHu/r97FH2pdgt"
"F2KT5CQmELeTJ1uXD/PsGN60qwONfsWD3fhrrP+rXo32utPzSNM6ndXNfSHHWwKUQ2YyJ3Z/aZCcDFW3e2FkjtcXuhzVL19h3tONpUDyXYOt"
"BGecFGhVULxeQLMjhdK+6gibmoyjgQk/B/F7SO6SJjdvrtgwuKbOEYjSYJUC/49n4CE1gzNdtKdeI2qvYMyADizfeL15vU8mhdoFlOdlPCKd"
"KY+uwXEHfI4/mRgB"
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "anthropic/claude-opus-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_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={
"model": "claude-opus-5-5",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
expected_provider_request={**ANTHROPIC_MESSAGES_REQUEST, "model": "claude-haiku-5-5"},
mock_provider_response={
"model": "claude-opus-5-5",
"id": "msg_011CfgDzp3URQ38dAAc8F3RP",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-haiku-5-5",
"id": "msg_011Cg36zdxXCpWpnwgbTX1Ss",
"content": [
{
"type": "thinking",
"thinking": "There's a mention of a chat_completions client I don't actually have access to, "
"so I'll ignore that and stick to my available tools. I'll proceed by reading "
"validation.py, keeping in mind edge cases like zero, negative, and non-integer "
"values before deciding what to examine next.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` to see how `validate_quantity` treats zero, "
"negative, and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_015ndrvU4VqqoMBzK35jt4TX",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 288,
"output_tokens_details": {"thinking_tokens": 149},
"service_tier": "standard",
"inference_geo": "global",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "anthropic/claude-opus-5-5",
"object": "chat.completion",
**CHAT_COMPLETIONS_RESPONSE,
"model": "anthropic/claude-haiku-5-5",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello.",
"content": "I'll read `shop/validation.py` to see how `validate_quantity` treats zero, "
"negative, and non-integer values.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"tool_calls": [
{
"index": 2,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "toolu_015ndrvU4VqqoMBzK35jt4TX",
"type": "function",
},
],
"reasoning_content": "There's a mention of a chat_completions client I don't actually have access "
"to, so I'll ignore that and stick to my available tools. I'll proceed by "
"reading validation.py, keeping in mind edge cases like zero, negative, and "
"non-integer values before deciding what to examine next.\n"
"\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "There's a mention of a chat_completions client I don't actually have "
"access to, so I'll ignore that and stick to my available tools. I'll "
"proceed by reading validation.py, keeping in mind edge cases like "
"zero, negative, and non-integer values before deciding what to "
"examine next.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "There's a mention of a chat_completions client I don't actually "
"have access to, so I'll ignore that and stick to my available "
"tools. I'll proceed by reading validation.py, keeping in mind "
"edge cases like zero, negative, and non-integer values before "
"deciding what to examine next.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 288,
"prompt_tokens": 880,
"total_tokens": 1168,
"completion_tokens_details": {"reasoning_tokens": 149, "text_tokens": 139},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",
@ -511,82 +491,219 @@ CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSqAYKEAgSGAI4AUIIdGhpbmtpbmcSDBSDqizSHGEEWmpWOxoM4DGvp9vRY4pul7dSIjB07rrpoEV7n5wqYphj7CiaeVIq2s4AlZ2SwEWL"
"xmrdDsZmUBGnz3qCIj9GC21mC5QqxQWhWTlPxM+tJt925MxVve4HmM6e+Gydxpty4kFx7Pk8nqlfDTooB3vyVOyto6ACj/sooxJ1BgEGJgOX"
"z1cH1Y9TG8Y1ca6DiiVm5Gw+6W5/U2FSWZyejNWbykYLxCdMLiLgH3MlCi5SvfIiQR0wgyT/0/1JpM6nrSmPp+zODEqWpbwrCTcwW3g9jSbe"
"Jvzfhr9pi6RZQj37dXkWzBDstK1La/HQoUSn/Zp8EMa8fjQOclN/VzQbAtbcfnhO+jJpQfmfWWC3UVoXFfSw86v+sX4/yBdZ+r7eXLB+dF8B"
"2mEcsWQuCtWa/EBgFR+1Xwyfaqno9/LpFfmiN58IwiAvTwYVkiwhpoJBY6035QDcXQGZURB2eNEMzg4Ay3lY/bp/ElMQPvjKy58ZihDXGysB"
"PPOinfZYNEeCyctJ9VC2957KTV2GlgNVxJ0No9KnZumvvbad4BdU9Bt9z2VsNahvwPVO+sHb2tNLJUsHpznIIoUfrdaEfdPI7r/UoCRt2KRA"
"OO+ejBYkS/D7otJHkjt/1/wOhEFuSNGLZ9yIsSPtI/qFvklkpptEbVQWd8Hs3cwyhZXBoXkFLr7Lku86jFMj8JuErAerc0zgMPLVsUC1s48L"
"mB5lt2xHuYhoqSYbAtRhLBS47t1YMpPf11bUFjRX72wS4jOb0ZMzXHw2G+yQfFhb+xHkUO4OKrDB3+x3GIbjOraTpmeYN6e9MydUuHJiZFzp"
"wTmrNzfYqHN6nNugAjMBJiPDHOmHn4AzeMJEoNu+PU5B73q5Xi22x0AqOF/D0xFIeDQHhDwnqBfvrVIq+Z0JVuoAwVroAx8y9MiIz5YUPlnn"
"N2njDJs7VfN6JIh/J7Ak+mfOgYt92Ofi7HcKAyg4INNwAp3a9lts21O6sBDugOfVr9VFWmASX/TQ/IelHuHHxNtDIgtOFRVLj1QY1iFAyXfT"
"dzYcGAE="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_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"},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-opus-5-5",
"id": "msg_011Cg371jh5oo3SEfLpT5Eep",
"content": [
{
"type": "thinking",
"thinking": "I'll focus on reading the validation file first, around line 18, since that's "
"what was specifically requested before looking at the tests.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "Next I'll open `shop/validation.py` around `validate_quantity` (line 18) to see "
"how it handles zero, negative and non-integer quantities.",
},
{
"type": "tool_use",
"id": "toolu_01Ew2u9E9j2mkT6RbwSw13uR",
"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": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 215,
"output_tokens_details": {"thinking_tokens": 66},
"service_tier": "standard",
"inference_geo": "global",
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "anthropic/claude-opus-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Next I'll open `shop/validation.py` around `validate_quantity` (line 18) to "
"see how it handles zero, negative and non-integer quantities.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"name": "read_file",
},
"id": "toolu_01Ew2u9E9j2mkT6RbwSw13uR",
"type": "function",
},
],
"reasoning_content": "I'll focus on reading the validation file first, around line 18, since that's "
"what was specifically requested before looking at the tests.\n"
"\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll focus on reading the validation file first, around line 18, "
"since that's what was specifically requested before looking at the "
"tests.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll focus on reading the validation file first, around line 18, "
"since that's what was specifically requested before looking at "
"the tests.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
},
},
},
],
"usage": {
"completion_tokens": 215,
"prompt_tokens": 880,
"total_tokens": 1095,
"completion_tokens_details": {"reasoning_tokens": 66, "text_tokens": 149},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",
},
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "anthropic/claude-fable-5-1",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_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={
"model": "claude-fable-5-1",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
expected_provider_request={**ANTHROPIC_MESSAGES_REQUEST, "model": "claude-fable-5-1"},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_011Cg33fMNz7YZzvSR7Ycg5X",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_011Cg372bGMBoXaSKUXjtQcr",
"content": [
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, "
"negative, and non-integer quantities are handled.",
},
{
"type": "tool_use",
"id": "toolu_01XMSjzRvHCE753Wx4dU2Vxo",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 143,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "global",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "anthropic/claude-fable-5-1",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello!",
"content": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, "
"negative, and non-integer quantities are handled.",
"role": "assistant",
"tool_calls": [
{
"index": 1,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"name": "read_file",
},
"id": "toolu_01XMSjzRvHCE753Wx4dU2Vxo",
"type": "function",
},
],
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 143,
"prompt_tokens": 880,
"total_tokens": 1023,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 143},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",

909
tests/integration/translation/chat_completions/bases/azure.py
View file

@ -1,6 +1,9 @@
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.azure import AZURE_RESPONSES_BRIDGE_REQUEST, AZURE_RESPONSES_RESPONSE
from pydantic import JsonValue
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -459,464 +462,584 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 489, "check_offset": 0},
},
]
GPT_6_LUNA_ENCRYPTED_REASONING: Final = (
"gAAAAABq0CO5Co3fPBWyqHQfJ1ms2Y-BIc2sUtT_XTbjdSYTT6QTAaPmp8ylGto8Y3Of8ATTnesNsPFU"
"7kLy9CJ_Lb2Pl5F7ln4lykRgrtPV-7f-B3FU_zaPLktc2eYem0KqseLyq3kBK90cXXTU0eEKJk458iGU"
"fjCFXwxXSB2q_f6rHwxaw5XjQ6IJO_-weFQqarHq3kH7oxqfiWR2udVzYFvkmJ3ezaEQBAJFGREpqHVq"
"NguzyFGuJLNK4urfedbSgOBmOMWZ8jxlPVCpe0FBu4fqvHhKKrBUxBdgvFS9UvhCCAeULfLQrxFBdQk_"
"ncDkur6n1iT9UuFTkSDEX36MdI9i-Wfx7VGbgmc6sZHJMoHEA5Ut11GmiFdQEgYG5R29Nl1iqAjjBm2g"
"3ZN2QNYQ7Ez_FLbOgE4dfF5uw5R239QLURkuEYdPAkfHVfewFiNyHstpoRkQ7qBcSfuvJZTbxPQPHpBd"
"h6tELbKDrZy0upGR-InCK8MGrl9jpSnAtGT5jhS97Je8kay4zEjcFWW7-Km0IchvPLWU__ftBh38tqmn"
"vprkmBsQpcNDhtx5MLZHEixrcbb-48y92c3_voScqLPDT7vM4sXDh3_8Op6ECc-BBh66af2PKef5wBD2"
"eAiD9G2dl5UAsQalER0rf5s_Us0CzDfZIc1P4I6WrGK9odBayY1WYpVU57ng5ZeTfnoSYzQt1iaiiEEB"
"PdVfQHc1Yc44D-Fk1Ipin7dThHshMn4oiYiCQI1ckRcpeLvPCycASykjaPLJyImrGP7CLgKWJPj1wr5R"
"4XWkGwI5MOI83Y-Zdq3eVUQErpJShokpqITgWVJO-zrClUkwsVbely-9CKjlorLDLTYsAbLNIoJp6xxN"
"AF2qt3QObhtKr7mxyq2idnVgdsk4Xj02P6XI-NERyqEdWOnUf7hDG8ZB75thRXDfKPiGkRFyCikPCV7Y"
"4mpeUIE5pytFjYLLOYEq36_GlEcGFosWPyi1Z_V_suyzC0Wy7KGIRMoGdVyyBZrIpCQvVConXD0AFGsY"
"Mvg4pxnwXK8gk_5N7ALIaGj9KM2X1i8ywKepmDw6Y1OVyfGCPhXyfuQd43ul1XIFczTemXw15PC9q2YX"
"d3FuAXQQbKYycaPm7beOLi1gGehWqlcbYx0ZbJV4bk4VrxD94TGoii8T-hbckP2qeJInXCGRsT-vXw3P"
"mGM_IkXTEJvZD_XmfinP7KPyjHyg-Lnx990ODgAOX0UhPCl58lsRlRq0XWldC8soDN-TKQh1E2j3vEGq"
"YC8goY-zCX-5prx9F__fFBYFMQlRPFtDa3JzBEV2cJ8wavsIZ1r9vow6I4QSguIsp5tToakfVaoou4ct"
"p94gqzyuymCtslLZ1Ndau4npTMUT1TzhVbQ-KJPRuuXht03dghpmmSe4sBnmpsLJHigktIL7ozhj3hue"
"Gp6s3t5L8_Cx2vtXKxsOmWsDLM7VxA5Lz_lUGIjgWGyA6LFbssAVkjXLz_okVdFMvDUu2ZkYUnfvwXv1"
"A1sUGJ_259aAEeIu0jlpMhCS6X54"
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "azure/gpt-6-luna",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6-luna/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6-luna",
"max_completion_tokens": 64,
"stream": False,
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure/gpt-6-luna"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={**AZURE_RESPONSES_BRIDGE_REQUEST, "model": "gpt-6-luna", "stream": False},
mock_provider_response={
"choices": [
**AZURE_RESPONSES_RESPONSE,
"id": "resp_0257792c0e8dcbb3006ad023b8112081958c7c4379959d4c6b",
"created_at": 1792025528,
"completed_at": 1792025529,
"content_filters": GPT_6_LUNA_CONTENT_FILTERS,
"model": "gpt-6-luna",
"output": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1791231849,
"id": "chatcmpl-EVjWDVYMA8Y26Lw8Jk3617Q3kWSUS",
"model": "gpt-6-luna-2026-09-22",
"object": "chat.completion",
"prompt_filter_results": [
"id": "rs_0257792c0e8dcbb3006ad023b8e27481959ae045c67273b7d7",
"type": "reasoning",
"content": [],
"encrypted_content": GPT_6_LUNA_ENCRYPTED_REASONING,
"summary": [],
},
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
"id": "msg_0257792c0e8dcbb3006ad023b939b88195b37db135f24d9db5",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I need `shop/validation.py` next to see the quantity checks, especially how zero "
"and negative values are handled."
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0257792c0e8dcbb3006ad023b97338819589076c2f853d85bb",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":160}',
"call_id": "call_nF1gXonXpNHBt14U2XkvfYZ8",
"name": "read_file",
},
],
"routing": {"serving_pipereplica": "d20260930053954-f91e8c7b-prefill-r7-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 2,
"engine_ttft_ms": 65,
"engine_ttlt_ms": 80,
"pre_inference_ms": 83,
"service_tbt_ms": 5,
"service_ttft_ms": 282,
"service_ttlt_ms": 306,
"user_visible_ttft_ms": 199,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 129,
"output_tokens_details": {"reasoning_tokens": 65},
"total_tokens": 441,
},
},
expected_litellm_response={
"id": "chatcmpl-EVjWDVYMA8Y26Lw8Jk3617Q3kWSUS",
"created": 1791231849,
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_0257792c0e8dcbb3006ad023b8112081958c7c4379959d4c6b",
"model": "azure/gpt-6-luna",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {"content": "Hello!", "role": "assistant", "annotations": [], "refusal": None},
"provider_specific_fields": {
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
}
"message": {
"content": (
"I need `shop/validation.py` next to see the quantity checks, especially how zero "
"and negative values are handled."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": ('{"path":"shop/validation.py","start_line":1,"end_line":160}'),
"name": "read_file",
},
"id": "call_nF1gXonXpNHBt14U2XkvfYZ8",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0257792c0e8dcbb3006ad023b8e27481959ae045c67273b7d7",
"encrypted_content": GPT_6_LUNA_ENCRYPTED_REASONING,
"summary": [],
}
],
},
"logprobs": None,
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 2,
"engine_ttft_ms": 65,
"engine_ttlt_ms": 80,
"pre_inference_ms": 83,
"service_tbt_ms": 5,
"service_ttft_ms": 282,
"service_ttlt_ms": 306,
"user_visible_ttft_ms": 199,
},
"completion_tokens": 129,
"prompt_tokens": 312,
"total_tokens": 441,
"completion_tokens_details": {"reasoning_tokens": 65},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"content_filters": GPT_6_LUNA_CONTENT_FILTERS,
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"prompt_filter_results": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
],
"routing": {"serving_pipereplica": "d20260930053954-f91e8c7b-prefill-r7-dp0-prefill"},
"system_fingerprint": None,
"tool_usage": AZURE_RESPONSES_RESPONSE["tool_usage"],
},
)
GPT_6_1_SOL_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 578, "check_offset": 0},
},
]
GPT_6_1_SOL_ENCRYPTED_REASONING: Final = (
"gAAAAABq0COvgomuqwo0Z3KFAStLOih2JmYOubPtUjtpD1zCRSCXdDnHGkj8asyVemaCsQr8szo_esDZ"
"PIT2Y9ghPTx1d5moHnS_lyX4nn3Almf4SYZ1pm8maTgEdntGFzcNtPRwW70-CgpeKe5z8zTwxsxyyKDb"
"OYTjt4hjUbAa4pM0K9JR9u5Q_P-LKgfcv3SNCeNSMs5lSV1aBMpuWEGJrlYF020C4wtmru3lH9VjQlOn"
"nW8uD1SCcPm7Sp1_Mm16PJBX4j2grbcIOJZDqj7OcjzRMAb2Gw96QfIg1_efR4BDVHzACkDClzPaiWuI"
"rAmGMA8bJDtQBPijZN3Hahu8eMoMd-XZDVQPx_7XM3F5OWUiuos_kEZNAhIIQHcLrXvyyf7slWvbT4Af"
"c8bvO45t1wOu5E_ALLhWcUCvbfPKBmHrlsRtBEVd_5n0q8jRwR1e5nyjPhMo3YsHvPmwHUJ5Gi1DZycD"
"-FDj6NpwlLcV3eeKaD8c-wNnHuXwfzi_KzIwU1phF_QxJ3ofegtM-3HwCqgaxxVFEhtIh3yezUKeqC7R"
"fSSHpmI-Q59TRf6-R7h6NFJKMG4Hg6C5twvVloHV2YMUHfBrgWr44X9FTzEwxJ89niDRtaB9Xvo2Qzme"
"9LUF-CWuGYTKj5QyRUQFOtclmBL335YTvTDWT8V-eN6KTE33XQNDEPSKuecES6fGHVCuIOeyQkWkvrW8"
"O2OrPJAmoW5g9AFWSWbeLWmDTTav6vbTyu0Ef9cvaRHRTOMq6q8VlEQoTQkJNUM8OKguY7Ad-1VSoIFW"
"D4_LvhuRsDsQiBu1diEq3hRNhXssBUd5wkFLOXw7UITRHONHhk7TDmVh0yjOwBr_e323vmL2e4BouKoX"
"x_0Umeb1jkjFlGgmpW59LmqXd91aXxjioYLxVMOMC7ib7O01_dD-OvWavSxAy9GLnex06mgThS2T5_u4"
"MRmpXIVVqdniqvoxx6YwX5F3TwRoIVc511oXyOG0QkKVLD1k0pI9OdFjiWNVH6XuhWPpVnAhqR6KYejn"
"hQQwuHA4KV4Nd6wOMFbhPjKPCuRcaN1vbgTbRJlwD8O2OV537hjDq6TQaezFJMk3HPK5bB_-J3kmUCul"
"YOXw0jgw-Ze8EmKLDZoCz3jq4NjNA9s0sLGd_Xg0kR6GeOmpLMWtT024yQ7gowGendkcHjIw3S-fIfiI"
"zJtZ-Hk9_iMBk8FE5Syb-j0kmzGF2gFj7ywTTdGoMsM3aTOvusVL14D1N_IfMryUdeoNJ41G8SvqGjtH"
"gyqCER9grGItYgKueDjt6IC5I086__HogkmrpzLZxSIpFCXX6rArVDsIYdS9XFgLW1oBKsVUs5DLnIYe"
"Ncv_cC-oTvEDBaYdhDPYbn_5N6q0q7dtbvohO-XJxOfLh0jC3TelEn7m5EXMPpAygQP2sPtI4_SmhA1C"
"Tji-B-6J60kBUiKmp65ZVxx8BDMI9dv3PLxsw4R0zh6fP_Fsok0UKJOQlfC6k47yhDuTcdN_vq7sAc3q"
"6P9b7Ud7Bz3JtY8Lg516vLK2vti4iwu7dcHlNiIoNZTGMANKYccO-XSRuJbX09bypgJB9sSR56_-Cb1i"
"b1C5RtkTv3ueRvq58Hw1RIINmiTTJn2MiYi_P-yXAirR39YTxcyRNUk4UDgK1lK73lrnpiBELJe-CPQg"
"wgLlalzjk8j0CnIMUA=="
)
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "azure/gpt-6.1-sol",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6.1-sol/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6.1-sol",
"max_completion_tokens": 64,
"stream": False,
},
mock_provider_response={
"choices": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1791231851,
"id": "chatcmpl-EVjWFBfdrUdRu3rbi6eAXbuO4zfNm",
"model": "gpt-6.1-sol-2026-09-29",
"object": "chat.completion",
"prompt_filter_results": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
],
"routing": {"serving_pipereplica": "d20260929014647-f3a90410-prefill-r11-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 8,
"engine_ttft_ms": 440,
"engine_ttlt_ms": 491,
"pre_inference_ms": 70,
"service_tbt_ms": 9,
"service_ttft_ms": 773,
"service_ttlt_ms": 819,
"user_visible_ttft_ms": 703,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure/gpt-6.1-sol"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={**AZURE_RESPONSES_BRIDGE_REQUEST, "model": "gpt-6.1-sol", "stream": False},
mock_provider_response={**AZURE_RESPONSES_RESPONSE},
expected_litellm_response={
"id": "chatcmpl-EVjWFBfdrUdRu3rbi6eAXbuO4zfNm",
"created": 1791231851,
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_03952e888f4f1827006ad023aa00108190b24e51d376e9a373",
"model": "azure/gpt-6.1-sol",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {"content": "Hello!", "role": "assistant", "annotations": [], "refusal": None},
"provider_specific_fields": {
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
}
"message": {
"content": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n"
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": ('{"path":"shop/validation.py","start_line":1,"end_line":200}'),
"name": "read_file",
},
"id": "call_mWfqifVeCXVWLiiNM1Ac2MjL",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_03952e888f4f1827006ad023ae0c048190acdee29b5d20c5b3",
"encrypted_content": GPT_6_1_SOL_ENCRYPTED_REASONING,
"summary": [],
}
],
},
"logprobs": None,
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 8,
"engine_ttft_ms": 440,
"engine_ttlt_ms": 491,
"pre_inference_ms": 70,
"service_tbt_ms": 9,
"service_ttft_ms": 773,
"service_ttlt_ms": 819,
"user_visible_ttft_ms": 703,
},
"completion_tokens": 154,
"prompt_tokens": 312,
"total_tokens": 466,
"completion_tokens_details": {"reasoning_tokens": 89},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"content_filters": GPT_6_1_SOL_CONTENT_FILTERS,
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"prompt_filter_results": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
],
"routing": {"serving_pipereplica": "d20260929014647-f3a90410-prefill-r11-dp0-prefill"},
"system_fingerprint": None,
"tool_usage": AZURE_RESPONSES_RESPONSE["tool_usage"],
},
)
GPT_6_ASTRA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_text": {"detected": False, "filtered": False},
"protected_material_code": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 459, "check_offset": 0},
}
]
GPT_6_ASTRA_ENCRYPTED_REASONING: Final = (
"gAAAAABq0CPDbn4g-dCLkDZ90pK6ePzjtg1TpduhwuSh1HFNOWpCL6JcLlasgA7lAnoba8Zm8LZe5T23"
"BMKHJVWyNRygNF8WDBBQvKvUhX2BOjPSf9wUbkXuctD_VtgwabIhmtwFhS6LH3iYbXzztiGqB898M7sF"
"QPlW8yqde_2hojqasenBXwkhsmeVHZZRxq0TXjc8eZeJ4WEdZOck0TB1eV0xb3UArpyy3amtuONzYCy2"
"wDVDAAlBVPTCcOC67biyQaEL7lipOMukY-yoGoQ-_SnRfLiVQDtl6U2mRA6svav-EEYm8igRyau6CSbp"
"CKYAHflNODMH4y27mX2iCRBeFkZ-nDAzEDdxd7UPFFrp-lKbCueG7JYIyBfkQlJMB_YyY2rcF6AWuLMt"
"K8RauqiMH-lgPZS1p4KhAauH1jSb47s3ZTgF4rowkMLdgAwdxIZD-3aoGXN9l4XOHumUfQNpJMNZbg9c"
"RayPzWlUEOXWEZ7WBchPzl_yIvZCvtTk3ljpUDmJuEb0Ox_TiWqFEr2__UgFccG49x5Sv9pSXqxrsjMw"
"y6ysHzZLbveONQ-gGcraErJcnnwSFSq_gsGiDPV-AJAMo-qY9vf5y6wJOSwIgQHpBx2e3WQAlp2R7vLr"
"QN_-cXtKgTcuVVGGjVLJIazz5Br4Yke70ms5nqPVOQYVfnXTAOzfbOrFfO_U5DoIW6xorPtPd_WFkw7Q"
"jK-gpm7AfkZL2RTICcwZDXuR6RCnSZMbOkBLCFlvZ3WyliM7j3fcvhxhfhA2Svp5kOxVjzZwY0NNMNA9"
"9x5td-Ht8ZgFX-UxIxo8H3sxy5cu-1JKd2eQb4QYoMyVXqk8ZOS28HPGgsx_B4pPTl2KOQ8b0KtNoiB1"
"58YDy9e74nb5u4U9I7Xkf8rS5EGmX1aGFAgW89XEymYCLfBfhtDjZQZAVyPSPxEdQd6CPnoVBy1MGrMK"
"zbyt8X4xEIJJupb8SLuLmfkxKskE4QHfoX5h9As_Ak9WGEn5TIFtJJWmBk6cwZOoswtBSDbgLf-Xid3n"
"2qfPX0UwdUnQzMNdc9eG9CU5vtvs-lRCMJbH3qHlK19vF82EoZT_z4lrHNXSyLOZad1kGaCRDFLakFCW"
"KF7Qil-U69jZCpyaghA1Ebts_es48dSwTLm9Kh323P_y5_o2baqKxT9FUKh5kVztjdiBSLx1LA5mzMUj"
"wdEWQpKh-RfKRnb9YoRGvCYrfvGtF_TcuYEg1DXQkOGejpaeXd-21Vaq44w1XJ72Kyun9KCJvoZu9O01"
"vo8uhUnhNksGqx26p8M6bxIePVhfA-_RVbg_meJov3jgH3OHphRLAO6jIECT-GauSo7p3fjmSviQlkZB"
"520Y5e6n3LPNZ8zpVYvtKooOj1VC0r6F_8vOdN8G5NvjELx2gptVXspfBoM3Ku1q7pFFUKqTG091ZKsS"
"tiFlIphwqI9D4d5aRaerUp2mN_X_aPJoj02O6svBMsbUHAns0PqVoCDg1HogteEQPSiHJTT_D033QDG6"
"ybr4oLs="
)
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "azure/gpt-6-astra",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6-astra/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6-astra",
"max_completion_tokens": 64,
"stream": False,
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure/gpt-6-astra"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={**AZURE_RESPONSES_BRIDGE_REQUEST, "model": "gpt-6-astra", "stream": False},
mock_provider_response={
"choices": [
**AZURE_RESPONSES_RESPONSE,
"id": "resp_03d9860d694cf03b006ad023bfd5f881979bc737bdacd3fdec",
"created_at": 1792025535,
"completed_at": 1792025539,
"content_filters": GPT_6_ASTRA_CONTENT_FILTERS,
"model": "gpt-6-astra",
"output": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1792022229,
"id": "chatcmpl-EZ38HKM9wxIe1d1BEJdXW3rW8ceOB",
"model": "gpt-6-astra-2026-09-03",
"object": "chat.completion",
"prompt_filter_results": [
"id": "rs_03d9860d694cf03b006ad023c113c0819784747d4f0860d98a",
"type": "reasoning",
"content": [],
"encrypted_content": GPT_6_ASTRA_ENCRYPTED_REASONING,
"summary": [],
},
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
"id": "msg_03d9860d694cf03b006ad023c246808197b42e6d5551340e2b",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I’ll read `shop/validation.py` first to see how it handles zero, negative, and "
"non-integer quantities.\n"
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_03d9860d694cf03b006ad023c2b42081978ef9bf4a11041d28",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_2kSDJH2w71KGgAbbYNfoELU7",
"name": "read_file",
},
],
"routing": {"serving_pipereplica": "d20260921004409-52a9ff06-prefill-r12-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 12,
"engine_ttft_ms": 311,
"engine_ttlt_ms": 384,
"pre_inference_ms": 149,
"service_tbt_ms": 6,
"service_ttft_ms": 948,
"service_ttlt_ms": 977,
"user_visible_ttft_ms": 799,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 135,
"output_tokens_details": {"reasoning_tokens": 70},
"total_tokens": 447,
},
},
expected_litellm_response={
"id": "chatcmpl-EZ38HKM9wxIe1d1BEJdXW3rW8ceOB",
"created": 1792022229,
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_03d9860d694cf03b006ad023bfd5f881979bc737bdacd3fdec",
"model": "azure/gpt-6-astra",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {"content": "Hello!", "role": "assistant", "annotations": [], "refusal": None},
"provider_specific_fields": {
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
}
"message": {
"content": (
"I’ll read `shop/validation.py` first to see how it handles zero, negative, and "
"non-integer quantities.\n"
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": ('{"path":"shop/validation.py","start_line":1,"end_line":200}'),
"name": "read_file",
},
"id": "call_2kSDJH2w71KGgAbbYNfoELU7",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_03d9860d694cf03b006ad023c113c0819784747d4f0860d98a",
"encrypted_content": GPT_6_ASTRA_ENCRYPTED_REASONING,
"summary": [],
}
],
},
"logprobs": None,
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 12,
"engine_ttft_ms": 311,
"engine_ttlt_ms": 384,
"pre_inference_ms": 149,
"service_tbt_ms": 6,
"service_ttft_ms": 948,
"service_ttlt_ms": 977,
"user_visible_ttft_ms": 799,
},
"completion_tokens": 135,
"prompt_tokens": 312,
"total_tokens": 447,
"completion_tokens_details": {"reasoning_tokens": 70},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"content_filters": GPT_6_ASTRA_CONTENT_FILTERS,
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"prompt_filter_results": [
"tool_usage": AZURE_RESPONSES_RESPONSE["tool_usage"],
},
)
GPT_5_6_TERRA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 388, "check_offset": 0},
},
]
GPT_5_6_TERRA_ENCRYPTED_REASONING: Final = (
"gAAAAABq0CPOOqy44P30Q1NqlPLLgAVH4x-Gd5CYim_MQz5OgD7eB1qP82U2pKslsZhD5378bFPvj194"
"3FU_ZJKBe0K8qBQ7WC0llLY7GBHxkqG1pk1QoaRjPi5Ns_gwkF3hFSCnGXgjN_6WZVc8mraXVm6kVVCp"
"YVctOcGPC0FEwPkvFk-UKGyVyEn8--LESX2S0O_3ObP1S4beDMv4L8kAF3LOAlGBKujFdfqk1ch1-yZa"
"CTA0ePCYXz35wUGwmjpO2NIo-nMPuDUeP-1Y7jzG8gJBdkP9o7-7pR9aCWcurj8wn-ae3Sgtx9WE7I42"
"eiDBp0CAV0uet_SDAZ5csE0v6Q_amiKBh7TEabBnPMp4CYZxjhVRDAiU3oDciHzq8odZB1Ftwr3_YmEX"
"YKtuet_lg2wE6s1yEX4itWaYkT6sfh9lR-DafSdF1o9-2jUbgP4FwYrl3LBSadUYlP-mDlsAwrm3caif"
"GQFATcpLE229i8Yw9aiMmrgWXpJ-vP-f-gM_8EWPZ_HXXTJIrCqYcnD4LjxmLHXesuTdt_QsdeUxSFqX"
"SzH_Ywl0fNqlH_LUtG1PfO8CEG_TF9QNFsDBY9qOE9NO0LHoTbUsjTCcdglewNQUh_s8W2L_PBMqYpxE"
"v8xWdvKTsnO1D0aMsE5ovo_T8ROJR46NrrcdAsFPFEceL5G_yjGwLUnB7TRFRvkSm8BSjnaCKqbv9TPy"
"Uzs3CjMsGmz3_8mHRMJTP8hO0kp97a8oZMKeokVrdSYk4pGv9Oyy9GW1BaUVvCEgUV7Dmrk-mt9znTCf"
"GlbBkiF6x_LqdQahGjVdSJQk2NpVZQktzKNyQhzHS-ATargehB4TAANyvyRUL4-zyK_QLVCaN2AlIMPx"
"_6frDw-vmb6bNHXmpc5fyU66Z0JaL_kTpHVTDBdxD5NprC8DEBaaxbnb283hP15dRxLHAb6fOprCkbLd"
"oJfXyyRmoCD2kkdIBhrzOxFr7h9Ipfvf-Qy-gjRpZVbfOzkUTfqxqe5vI5uAGk8uxz5EQFgdH_NgNaZ7"
"76ji97ewVoX-RWgnAra0kzzU_ECDOE52lztUcz6yKLwH9Rw2FqxZJucA0Bh6_6lQbsZAlWz9CuYTcCtu"
"6lnJVfmsVMOJRvnykjYGzaX5tpShxmsu1YiCRmOzXTxB2wdATSHr90OWH3_8w-OkVDBBUO9ByDxlepid"
"zcX043O9BJhdkXFWBUrwjzBO_NWyKKLm7yRu6Evgg34EvlFhFc1F2p6qqTsml_yNsZyw6I3NErTkw4KH"
"aYVQH-DCiM7QoqJK6eJxaEk8QBF6Macs8aXVCYC1xXqvApLQELhvuIDLcGDQSQYLeJKdbq6UksNnp-LE"
"1bt7HPvcSL3heudkey4BtoE5OqnyDV2msEzLtkw="
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure/gpt-5.6-terra"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={**AZURE_RESPONSES_BRIDGE_REQUEST, "model": "gpt-5.6-terra", "stream": False},
mock_provider_response={
**AZURE_RESPONSES_RESPONSE,
"id": "resp_0146fd70db485046006ad023cbf5b48197a496e74bfbe99f66",
"created_at": 1792025548,
"completed_at": 1792025550,
"content_filters": GPT_5_6_TERRA_CONTENT_FILTERS,
"model": "gpt-5.6-terra",
"output": [
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"id": "rs_0146fd70db485046006ad023cd55848197b06f3cbd7f6046e5",
"type": "reasoning",
"content": [],
"encrypted_content": GPT_5_6_TERRA_ENCRYPTED_REASONING,
"summary": [],
},
{
"id": "msg_0146fd70db485046006ad023cddf1c8197bfc55155a0310a0b",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"Next I need `shop/validation.py` to inspect the validation branches for zero, "
"negative, and non-integer quantities before reviewing the tests."
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0146fd70db485046006ad023ce20d481979de3a49e428ae4e8",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_TZsfYd2RtwusZpfe2wrbwnRf",
"name": "read_file",
},
],
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 110,
"output_tokens_details": {"reasoning_tokens": 41},
"total_tokens": 422,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_0146fd70db485046006ad023cbf5b48197a496e74bfbe99f66",
"model": "azure/gpt-5.6-terra",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": (
"Next I need `shop/validation.py` to inspect the validation branches for zero, "
"negative, and non-integer quantities before reviewing the tests."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": ('{"path":"shop/validation.py","start_line":1,"end_line":200}'),
"name": "read_file",
},
"id": "call_TZsfYd2RtwusZpfe2wrbwnRf",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0146fd70db485046006ad023cd55848197b06f3cbd7f6046e5",
"encrypted_content": GPT_5_6_TERRA_ENCRYPTED_REASONING,
"summary": [],
}
],
},
}
],
"routing": {"serving_pipereplica": "d20260921004409-52a9ff06-prefill-r12-dp0-prefill"},
"system_fingerprint": None,
"usage": {
"completion_tokens": 110,
"prompt_tokens": 312,
"total_tokens": 422,
"completion_tokens_details": {"reasoning_tokens": 41},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"content_filters": GPT_5_6_TERRA_CONTENT_FILTERS,
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"tool_usage": AZURE_RESPONSES_RESPONSE["tool_usage"],
},
)

330
tests/integration/translation/chat_completions/bases/azure_ai.py
View file

@ -2,6 +2,8 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.anthropic import ANTHROPIC_MESSAGES_REQUEST, ANTHROPIC_MESSAGES_RESPONSE
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -85,90 +87,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "azure_ai/claude-haiku-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"api-key": "synthetic-azure-ai-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-haiku-5-5",
"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-5-5",
"id": "msg_011CfoboMutM3uKRT9qW3upD",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "azure_ai/claude-haiku-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",
},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
@ -583,19 +501,27 @@ CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSwwgKEAgSGAI4AUIIdGhpbmtpbmcSDKfqwDliolwjkEk4/xoMbtopFWwu6m8MsKPLIjBYY7k/jbVLmSR7KHeAvyUV9jUyWBV6qdv+M9Uq"
"JG7K7iHhxyzCRoLI+DsRvaqtq3gq4AdEnhxf+3y6bp2Gfgm19WyxAVxsc3BDwyrIOL2frop5j8DtwrGL7KwweKZcQ9Zm6R/VtGDH2r88PsxM"
"g2oSgmYTBR0jEyaOxl4EwRllE3RfE8vkQP66TAx4RyCpbIGVB1lBXxdxVnFgzS8JQMaJnQ4jdXUdR8sH57heOUMuE2trGBVaKoDSWli2FtTw"
"kDNHd99zv/b2cSZtIN7W/d/FuxRVzxlvuuFQO27y7pmaczsSldqKmCRtcGOb21RFF9u3I9eznIN8394JyQWIXEdWmnXuQL/7BKai2nD+R7No"
"5gLT9gY5y1stqQZ8FPkbHxKnt9/WciUc5lyGz7uGJbUiEUYAFR0j41l8+3VXWpF4OV1aEQa2eHNATLpYJ8I3Wctlu2mcOm+096aak+BW1XXt"
"vnkMSvBbM3JUElx5k5chZmfMUHFA32KuAj3VZ58lfnOBxGDE7gMNMVvxdAC/h7nRSrO6ICgMYYXy4kFkpVLZz6kH6K32cEAwl1pCPjxYIZVL"
"OwrPXzjsQUqRpjekBFr1lx23oxR2fUId0EsFpPbJSZHjaN/amBsMY/g3iGFiPU3uQW7+Llvhb/OGpNwI3YtWxi3cTZkNdLaItCnl0QsJ6aFS"
"D0oq0HcrKsIvcbMp05kz/rNFAGRBd5QrUthuh/CvYJUHosauz5OYrvRlzzKlsEVomzIkwVQw0ZrYhq0xZvwIRa7JbRoDadHL6uTNybKFCISX"
"33IimEMVpkaMBEvygWya25H7pSK9OREbzV17rpS5cGBebOLKYjgZms7WhAERsyNm+gYIDcr+X5AGrOrz3qM/diknhnC5rNgbaO8w+JQl1i+D"
"wrNXsCW61u+/KRI2Qf3ekaHG4fcETWz+Y1+JisK7WskmyihKAkexlLaxqyn5RisYGj9tKs4OpjCd1w4lhS6346ypK0ufsfyHjqfn7TVjIsVt"
"posdTv+Wc3fTr7WDcmiJ+hBD/YxouCYYxS+hssBS/ut0QFfWH2dh0/2qGeNd70QqXEt+tbsopsrqpV2OZy9YE8VvLqZicNJHqbZTivXKsEFX"
"YN4pnKv4X7ykWtCILbpbTZNg1iBa4z+T2fSFdAUJVgRFherqjCcD209AA4wj3UJewZX8nwX2Js1W/MRFrAIWzwwBI3x6eCq6OaaeXzSwUS9M"
"I24Sk4o5rm9/czgj2Ottsq0Rmvsng/r3ZOpu8uKfjhxKmCSSQEE4ZZ7NBwLTOUVOcmBoeRfQbyjDKr7NYiaVuN7NlJw2NQbsyhAgqlD8IBpz"
"Z0XczPP0u+uEKTIsVXcjAtHIjyx361hlCa1waGh5DqmWg7zhv2QenFwjBBgB"
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "azure_ai/claude-fable-5-1",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure_ai/claude-haiku-5-5"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
@ -603,63 +529,209 @@ CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-fable-5-1",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
},
expected_provider_request={**ANTHROPIC_MESSAGES_REQUEST, "model": "claude-haiku-5-5"},
mock_provider_response={
"model": "claude-fable-5-1",
"id": "msg_011Cg33iornZJuXHAdrimopu",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-haiku-5-5",
"id": "msg_011Cg37MxTLdwH6PHKZXCEey",
"content": [
{
"type": "thinking",
"thinking": "I need to read shop/validation.py next, keeping in mind edge cases like zero, "
"negative, or non-integer quantities since the validation logic likely handles those. "
"I'll look at the function starting around line 18 to understand its scope.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` first. The search hit `validate_quantity` at line 18, "
"so I'll start there and check how it treats zero, negative, and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_01M68cqREYA4WqXBUK8rqcEq",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 324,
"output_tokens_details": {"thinking_tokens": 167},
"service_tier": "standard",
"inference_geo": "global",
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "azure_ai/claude-haiku-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read `shop/validation.py` first. The search hit `validate_quantity` at line 18, "
"so I'll start there and check how it treats zero, negative, and non-integer values.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "toolu_01M68cqREYA4WqXBUK8rqcEq",
"type": "function",
},
],
"reasoning_content": "I need to read shop/validation.py next, keeping in mind edge cases like zero, "
"negative, or non-integer quantities since the validation logic likely handles those. "
"I'll look at the function starting around line 18 to understand its scope.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to read shop/validation.py next, keeping in mind edge cases like zero, "
"negative, or non-integer quantities since the validation logic likely handles those. "
"I'll look at the function starting around line 18 to understand its scope.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to read shop/validation.py next, keeping in mind edge cases like zero, "
"negative, or non-integer quantities since the validation logic likely handles those. "
"I'll look at the function starting around line 18 to understand its scope.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
},
},
},
],
"usage": {
"completion_tokens": 324,
"prompt_tokens": 880,
"total_tokens": 1204,
"completion_tokens_details": {"reasoning_tokens": 167, "text_tokens": 157},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"inference_geo": "global",
"service_tier": "standard",
},
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "azure_ai/claude-fable-5-1"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"api-key": "synthetic-azure-ai-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={**ANTHROPIC_MESSAGES_REQUEST, "model": "claude-fable-5-1"},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_011Cg37NcfzdXibtC3dWhVWi",
"content": [
{
"type": "text",
"text": "I'll read the validation code and the test together since they are independent.",
},
{
"type": "tool_use",
"id": "toolu_01LxkeKf9WX9BVpiWrvfKUyc",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
{
"type": "tool_use",
"id": "toolu_0139NDXUipoVov5pyoTErFZZ",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 30},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 216,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "azure_ai/claude-fable-5-1",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello!",
"content": "I'll read the validation code and the test together since they are independent.",
"role": "assistant",
"tool_calls": [
{
"index": 1,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"name": "read_file",
},
"id": "toolu_01LxkeKf9WX9BVpiWrvfKUyc",
"type": "function",
},
{
"index": 2,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "tests/test_validation.py", "start_line": 1, "end_line": 30}',
"name": "read_file",
},
"id": "toolu_0139NDXUipoVov5pyoTErFZZ",
"type": "function",
},
],
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 216,
"prompt_tokens": 880,
"total_tokens": 1096,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 216},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"inference_geo": "not_available",
"service_tier": "standard",

636
tests/integration/translation/chat_completions/bases/bedrock_converse.py
View file

@ -2,6 +2,12 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.bedrock_converse import (
BEDROCK_CONVERSE_REQUEST,
BEDROCK_CONVERSE_RESPONSE,
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
)
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -60,64 +66,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
},
mock_provider_response={
"metrics": {"latencyMs": 954},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
"usage": {
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"serverToolUsage": {},
"totalTokens": 29,
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello.", "role": "assistant"}}],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
@ -289,173 +237,525 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/converse/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
},
mock_provider_response={
"metrics": {"latencyMs": 892},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
"usage": {
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"serverToolUsage": {},
"totalTokens": 29,
},
},
expected_provider_request={**BEDROCK_CONVERSE_REQUEST},
mock_provider_response={**BEDROCK_CONVERSE_RESPONSE},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello.", "role": "assistant"}}],
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read `shop/validation.py` next, starting with the `validate_quantity` function "
"found at line 18.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "tooluse_qWzJMc6h58NlspiEa01FUC",
"type": "function",
},
],
"reasoning_content": "I need to figure out which file to read for validation, then use a read-only tool to "
"look at it—I'll check the first 60 lines or so since I don't know its exact "
"length.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to figure out which file to read for validation, then use a read-only "
"tool to look at it—I'll check the first 60 lines or so since I don't know "
"its exact length.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"reasoningContentBlocks": [
{
"reasoningText": {
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
"text": "I need to figure out which file to read for validation, then use a "
"read-only tool to look at it—I'll check the first 60 lines or so "
"since I don't know its exact length.\n\n",
},
},
],
},
},
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 230,
"prompt_tokens": 860,
"total_tokens": 1090,
"completion_tokens_details": {"reasoning_tokens": 96, "text_tokens": 134},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 856,
"cache_creation_tokens": 856,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 856, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 856,
"cache_read_input_tokens": 0,
},
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS9QUKEggSEAEYAjgBQgh0aGlua2luZxIMHeQumEXUSngowYp2Ggw6RETkY6n11eC2W98iMLxQa5+C/eZvHir2PVIhfArk/wZFsCSOH7e3"
"dqBUFaBA8tvcE0LO+g3l1B51aj/2bCqQBbsVVKGduphL2uGxAmAfucVEigmAzobLXjnxMizAS4+QFSE4iS/vbgj9oH/JgaZu1izkc77Y8vtC"
"IzTWqlSeyu8ThzVgljSrPMO76qbBKJPM3N/3VYKrV2iK1OljKXeJMZXuEFTtUJm562vm1sihud8t1EnG+Q849jjXts3Y4sB5tfDewbFG5LsY"
"tclTSq468Kv0fw7vTEGQ1silrl1hMvMc65ZD1o7YAwYurdDaTc1JJbEYLVNtHgwFK4G1G4vdWIHuk9DKNvCeOxFoGhfyYwGbDMX9SqYaHQh3"
"rcX5I/b5JHf2bE2l/5pyiBirAXjlG9EhBOYCdypDGXzlDqr4Oc4xaRWYjv8ixXhov9FHEUj0sdB3YTMxnEaUn4KgvdBSTS+O89wOMcoZBz8T"
"1mR3ig3IxUV27YS6ZSYImaoie9VzuWLNovu1x3rFyrM2cP222Z9NahtcOIXysUVSoe1nYYAYa4K5A7+BXf2xWhUZjfyzG/mGP/LsQCZeXxwY"
"1e0m3ivyUanPUxVrnK1nvpB9FcY7T8UPw2LH2W8VWDXG1MPdjPwZcQJsdc/LxwSmWUv4jwa/jEBOvyKC9GTJRn2TDiUNhzFoLn/wSzdfk5aV"
"rwJd0z5ALiaR9yXm5qgGmK0v1slPo8VmgzoFzLGmkU4UE0uT3etr9IfiR9wAyctSMuKuZ+ApETINbZWOybLaJynLYdaoGYrCwTDB2p3JTQV5"
"HP8aQm6l11YgxxymNnSMHEXmYibBp2B1YH/2TkysI01LMnxBGo79aa1KnzYHSZQpbmqSDmjn6SR3KhjwYxDz7drr8S49a5QPxsYoaffWTrwj"
"0BbxGgQuwjB0pbIQFWiK+eOA+lShN3Sm+8WrdtcwPUbmGAE="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/converse/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={**BEDROCK_CONVERSE_REQUEST},
mock_provider_response={
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 86}}},
"metrics": {"latencyMs": 3449},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
"text": "The user asked me to read the validation file first, so I'll do that "
"before looking at the tests, even though reading both in parallel would be "
"fine too. I'll pull in the full validation file since it's short, roughly "
"18 lines.\n\n",
},
},
},
{
"text": "I'll read `shop/validation.py` first. `validate_quantity` is defined at line 18, "
"so I'm reading the top of the file through the function and what follows it.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_rN6y4cQORe8ESxDQcIl9SR",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 856, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 856,
"cacheWriteInputTokens": 856,
"inputTokens": 4,
"outputTokens": 237,
"serverToolUsage": {},
"totalTokens": 1097,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read `shop/validation.py` first. `validate_quantity` is defined at line 18, so "
"I'm reading the top of the file through the function and what follows it.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "tooluse_rN6y4cQORe8ESxDQcIl9SR",
"type": "function",
},
],
"reasoning_content": "The user asked me to read the validation file first, so I'll do that before looking at "
"the tests, even though reading both in parallel would be fine too. I'll pull in the "
"full validation file since it's short, roughly 18 lines.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "The user asked me to read the validation file first, so I'll do that before "
"looking at the tests, even though reading both in parallel would be fine too. "
"I'll pull in the full validation file since it's short, roughly 18 lines.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"reasoningContentBlocks": [
{
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
"text": "The user asked me to read the validation file first, so I'll do that "
"before looking at the tests, even though reading both in parallel "
"would be fine too. I'll pull in the full validation file since it's "
"short, roughly 18 lines.\n\n",
},
},
],
},
},
},
],
"usage": {
"completion_tokens": 237,
"prompt_tokens": 860,
"total_tokens": 1097,
"completion_tokens_details": {"reasoning_tokens": 86, "text_tokens": 151},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 856,
"cache_creation_tokens": 856,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 856, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 856,
"cache_read_input_tokens": 0,
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSwwUKEggSEAEYAjgBQgh0aGlua2luZxIMeqMdLtmn33y9cIexGgym8fsZQt5P/lSqgpQiMAC92xJoxWLNXHHgGhS+0mdadsD4aDidh2B3"
"XDq8VlyD6g3Heynf1faRQ72efXv4zCreBGbwmU6DTP7IlfHZXPnTXAo979PeGnhoChdOtJ6GKSs/w9rjsAee+Eys02cjJerLDxhf44lHr2iW"
"bxhJQNft2DnosDk3OCMtWx77ksDERl4mcnJplzLJSMTCPO9HSbTkJzWJ5Jj7x0DjznblKBes8q1NPFVV7pqXMB7yo2mPlledoEzt+rYXXiFa"
"NBpuSQ8wvflyON6rwl0UoToTGpUb8rjvjqVkInhX82Y3hIbYgixYzhA9OCh+xMuDQzldRLdM5NgT+9dxHrklL1ZaHuWrpBP12q7qo0j3A7dT"
"/2/JAvGiJqfCcGptfc2RPDK/NgnTxBAbqvUW0VUm8zhg7SDHMC+hunwy4phUc8yBpaJFI5vmthSU++vvyVwNYChs6i0DVdMe6c7Lxzzk3W0Z"
"iAMrgsalHyjK6IzsnwMusiMW64foeMN0OKx3lYSZT9oqp6nDVecBwgH4npD2Pq4PPe7C5S5KVCzvq4guVTCcQM7XUXdck6QzgZrDm/kFp3lz"
"splN7GdOh+PUYAvGvmhnBvPkWKFRPSEcX6vPlbNfhC+ADY8C/oVjjVFjvyBv/aF4BDlY8s4ZV76kmiiyfXQ8P+BpO2QtId1GvlmOq8SmwcAe"
"cMgtz4o0nWWNAaTV8CH+YjswCSe6lscs5bTZzf8724OKBx0lOs+Axn0Lwo5gHekzCimCUpA8leG0dIg6t6FOVRmjcmIoTlh39Xu2LmjrTjNG"
"A8BBS3u+O+R2158XIfII393jsgpVwg8Dn5WIAK8U1LzQDAj7IrhSuN1q2UJG8ZEsi6JmFmWdGXdCi1FVWNkyDBgB"
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/converse/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
},
expected_provider_request={**BEDROCK_CONVERSE_REQUEST},
mock_provider_response={
"metrics": {"latencyMs": 10460},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 65}}},
"metrics": {"latencyMs": 3552},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
"text": "Since the user asked to look at the validation file first, I'll focus on "
"that around line 18 before touching the tests, which can wait since "
"they're independent anyway.\n\n",
},
},
},
{
"text": "Next I'll open `shop/validation.py` around `validate_quantity` (line 18). That "
"should show how zero, negative and non-integer values are handled. After that I'll "
"read the tests.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
"name": "read_file",
"toolUseId": "tooluse_zGYCbMhgYTTAQl5dBHNkKs",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 856, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 856,
"cacheWriteInputTokens": 856,
"inputTokens": 4,
"outputTokens": 223,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1083,
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello.", "role": "assistant"}}],
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Next I'll open `shop/validation.py` around `validate_quantity` (line 18). That should "
"show how zero, negative and non-integer values are handled. After that I'll read the "
"tests.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"name": "read_file",
},
"id": "tooluse_zGYCbMhgYTTAQl5dBHNkKs",
"type": "function",
},
],
"reasoning_content": "Since the user asked to look at the validation file first, I'll focus on that around "
"line 18 before touching the tests, which can wait since they're independent anyway.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "Since the user asked to look at the validation file first, I'll focus on that "
"around line 18 before touching the tests, which can wait since they're "
"independent anyway.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"reasoningContentBlocks": [
{
"reasoningText": {
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
"text": "Since the user asked to look at the validation file first, I'll focus "
"on that around line 18 before touching the tests, which can wait since "
"they're independent anyway.\n\n",
},
},
],
},
},
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 223,
"prompt_tokens": 860,
"total_tokens": 1083,
"completion_tokens_details": {"reasoning_tokens": 65, "text_tokens": 158},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 856,
"cache_creation_tokens": 856,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 856, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 856,
"cache_read_input_tokens": 0,
},
},
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0: Final = (
"CAQSrwUKEwgSEAEYAjgBQgluYXJyYXRpb24SDNCGJ8kKyGwJSh36gxoM2/14CeUIPZHnkx/iIjAYx/Gy8bDJhXdDJVKLzNi0l/VKFEq/9uTz"
"mI1Vx1GUXRI6Yj7imDIn3cnUzf5dj6AqyQQhWjFSAqAjMK8gOQ2PqoyPonbTrxwsld+dZM44c+ffNp2YgBSEQyNUlXF+nCYX6kAGwmzSZkKq"
"W8CGWrIH2dB+TzWfz3fsx/GglprifZ0YFvyoMq+Ri6LQnS/GFuqtaJrYhwngV34u1M1jFJv3qw+HvTGmiums0KACTSP8F+vI3OfedHfhaiyz"
"pQnbFie2gqVJOvRNst521omILp8ds5QrBoq2VYnwt7TZEO1IfNfan8OAcetSMUvAYCrW2I3IiZ7lTpMTV2K2Dzyw5NLY7LNrwA/bJuKNbyWI"
"JvFi8zrgIxLAsLNXV0gCLib7qdywHg8k/otUlOSOfHzLaDuwO0BR8OpSjJcm38lUpCg+6twP49FC943vhOJ3t9qR3PSeCEkLdzFEZGUak1Xr"
"sqwK/dfU8R22lGelQK7xwVNGKB6JOQ5pbIA8gUviT8DDQ9nQAaj+HKSYiN3ss3+qD3qPMuBK/XYojp5rbIrpqfoyWogvX9hwWCBFAYC9OUHR"
"199q8fAFQxSRVUKSjCPopCQC9AKouLmeeotr0AI6KKB0deg1MudLkgy6KcKvEgptDqOqJJMpyO+3WxJ5serIbwNgIAbs3Kl9rLsJrmZ3qzfW"
"qw0/yxJGjwLFRLAy2o6Q+6y5kAQA0CsURIjbdvIF7hpHkvlAYdzfX+ApwQY115nAUTkYyliu8myjDBCRXb2mEnAKk7+rQ/tr67/szVV/8B8S"
"3CmxaoFlhHHbwCAHpGZNWPFAOa8hvOPxsewJ+Hr5z34kC4g2QdDdiyPRANAYAQ=="
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/converse/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"toolConfig": {
"tools": [
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
"name": "search_files",
"description": "Search source and test files for a literal term.",
},
},
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
"name": "read_file",
"description": "Read a range of lines from a project file.",
},
},
],
},
},
mock_provider_response={
"metrics": {"latencyMs": 4060},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 0}}},
"metrics": {"latencyMs": 5476},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
"text": "Checking `shop/validation.py` to see how `validate_quantity` handles zero, "
"negative, and non-integer inputs, and pulling in the test file at the same "
"time.\n\n",
},
},
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_u1AisurVMo0RZh6mAjHMl2",
"type": "tool_use",
},
},
{
"toolUse": {
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 40},
"name": "read_file",
"toolUseId": "tooluse_M4eCGwAM39nEOXlNrXyTx5",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 876, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 876,
"cacheWriteInputTokens": 876,
"inputTokens": 4,
"outputTokens": 267,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1147,
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello.", "role": "assistant"}}],
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "",
"role": "assistant",
"tool_calls": [
{
"index": 1,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "tooluse_u1AisurVMo0RZh6mAjHMl2",
"type": "function",
},
{
"index": 2,
"function": {
"arguments": '{"path": "tests/test_validation.py", "start_line": 1, "end_line": 40}',
"name": "read_file",
},
"id": "tooluse_M4eCGwAM39nEOXlNrXyTx5",
"type": "function",
},
],
"reasoning_content": "Checking `shop/validation.py` to see how `validate_quantity` handles zero, negative, "
"and non-integer inputs, and pulling in the test file at the same time.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "Checking `shop/validation.py` to see how `validate_quantity` handles zero, "
"negative, and non-integer inputs, and pulling in the test file at the same "
"time.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"reasoningContentBlocks": [
{
"reasoningText": {
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
"text": "Checking `shop/validation.py` to see how `validate_quantity` handles "
"zero, negative, and non-integer inputs, and pulling in the test file "
"at the same time.\n\n",
},
},
],
},
},
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 267,
"prompt_tokens": 880,
"total_tokens": 1147,
"completion_tokens_details": {},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
},
},

555
tests/integration/translation/chat_completions/bases/bedrock_invoke.py
View file

@ -2,6 +2,12 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.bedrock_invoke import (
BEDROCK_INVOKE_REQUEST,
BEDROCK_INVOKE_RESPONSE,
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
)
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -77,82 +83,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
mock_provider_response={
"model": "claude-haiku-5-5",
"id": "msg_bdrk_prp4tfjg2ibow6km7wkqw5euejxxssl2ngm6wbgjxyg7xd32tkja",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
@ -377,226 +307,435 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={**BEDROCK_INVOKE_REQUEST},
mock_provider_response={**BEDROCK_INVOKE_RESPONSE},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read `shop/validation.py` around the `validate_quantity` definition at line 18. "
"I'm checking how it treats zero, negative, and non-integer values.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "toolu_bdrk_01Hfy4YfUU7hZUxEmpp4oDYV",
"type": "function",
},
],
"reasoning_content": "I should look at shop/validation.py, focusing on how it handles zero, negative, and "
"non-integer inputs before deciding what to read next. I'll check the first 60 lines or "
"so since I don't know the file's full length yet.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I should look at shop/validation.py, focusing on how it handles zero, "
"negative, and non-integer inputs before deciding what to read next. I'll check "
"the first 60 lines or so since I don't know the file's full length yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I should look at shop/validation.py, focusing on how it handles zero, "
"negative, and non-integer inputs before deciding what to read next. I'll "
"check the first 60 lines or so since I don't know the file's full length "
"yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
},
},
},
],
"usage": {
"completion_tokens": 295,
"prompt_tokens": 880,
"total_tokens": 1175,
"completion_tokens_details": {"reasoning_tokens": 143, "text_tokens": 152},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSwgUKEggSEAEYAjgBQgh0aGlua2luZxIMwv5o3sIXxVdkUO0MGgxObtbvqBQXfANsnrwiMMS0BVrFyZB1bCUZfx4cUYR/+/9/NfiPwTEU"
"jsGSOJFjxW95CdHDmohqchGNWlIBUirdBEZuOEcmqJBmrwvvX5mho5M6DJskEztgdUjCFIzTM5CXU24my+0yxBnIrFUrgzqaihEmKWmwxSEN"
"rGOtF41225PHpYTpfWHKxn6tay7STRpm8K6x6AXYtYJSWMAa0pvCBrsc8U4jvbuAHhLUqxliQG0WwkbX4UK2/6uGMSwYDMHsh+kvDLa17WhU"
"vjZsKg0ocntDgcMBG4WVxhaCMurK2lhDP14G5q3CdViTQd8TiM/ooU2cx7NrlqHWtB0tr4QuZaXZlTZjLz+wpIPzvLSQvyybecc/LrD+4EGV"
"CbVHTucTj8qEBWNoT7JPnwHIH3nWyspyauyD37m3nE2GcTtyIaNFnyXwFMgPZb8CNphtgc0QIYu6/egzk0msGdhyxWo48D/PMs5uL9FjFIrK"
"xiFgG+nE3ck4ipexy/W69W/G2fzL756UZc3dUpYMj21MbAgMyxqiIemKKaw8w8UTaEDJUw7IxXFXklqjOehMaGJT+YDR6G88bPgfG5FTjegK"
"UBVhR472cBMPIauHwaGz5I6ZuetVBuaNuS1DhFnMkRvj+Z/GdtJANK4EySK28w/n9TTqrkFqwO0LBV9lGUgoubOOUfYM/AE55WD6OEX7HbKi"
"t22c/5TTmH8UuSXG5YbMZ3LP5rnB52zvi/wi53E0jVEQraX4Yf2ueoOrunlngmR/xW9Sq7+CK/9mcO6RuMn9yD8LJxf7/bg+yNij8kFGTOvu"
"B06RdfOrbD2MNAWkvtpdfvKcSzVElSQkltI7zoqnKJ23x8CF66vwj3ThszmGexzvdt4CZtrjw4ZcP6YwGUnOGAE="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
expected_provider_request={**BEDROCK_INVOKE_REQUEST},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-sonnet-5-5",
"id": "msg_bdrk_tozg7mwrkjb7fisuua7q5ylekeypufs6he64a2tlncr4bvdg4dha",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_a7sjc6m6nfuwupssre5yi22kzpdwizomnscfdrysperwjop7fe5a",
"content": [
{
"type": "thinking",
"thinking": "Since the user explicitly asked for the validation file first, I'll prioritize reading "
"that before the tests, focusing on the area around line 18.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I need `shop/validation.py` next. It defines `validate_quantity`, which should show how "
"zero, negative and non-integer values are handled. I'll read the area around line 18.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01LNktDaewoxFywoyzT1eMrE",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 224,
"output_tokens_details": {"thinking_tokens": 69},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello.",
"content": "I need `shop/validation.py` next. It defines `validate_quantity`, which should show "
"how zero, negative and non-integer values are handled. I'll read the area around line "
"18.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "toolu_bdrk_01LNktDaewoxFywoyzT1eMrE",
"type": "function",
},
],
"reasoning_content": "Since the user explicitly asked for the validation file first, I'll prioritize reading "
"that before the tests, focusing on the area around line 18.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "Since the user explicitly asked for the validation file first, I'll prioritize "
"reading that before the tests, focusing on the area around line 18.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "Since the user explicitly asked for the validation file first, I'll "
"prioritize reading that before the tests, focusing on the area around line "
"18.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
],
},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 224,
"prompt_tokens": 880,
"total_tokens": 1104,
"completion_tokens_details": {"reasoning_tokens": 69, "text_tokens": 155},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSigQKEggSEAEYAjgBQgh0aGlua2luZxIMq3frSfibHHldP8/aGgxVeuAxm7EIGP7vV10iMCQSYTMAj3EpHNaNy9ic8GJApnD9KmWXPGJ6"
"BqKYlRYlNcvpHFdOGC3d8HHYlYWetCqlA/lyfcAC8HgdVosWlvsFkLvgcAmmV8VUSSJCD7VHV1sC8YjChiQ0bO/DWbfCeK3FUNbDwhAJEstb"
"q3Pj4THSbsDtJHlIcukGM/xOqXvfjcisMMPjpF8xuK5ai1cnFehLGWHpdj99zC1nK1E/k4OqHYOhzWfHLMQdbeTgR5FP9cVexDyKI/5mlZw9"
"YxIbOxEjSYAwsR5Q6cIDWjl2ao1M4OhorS/UR1FYp99jwQE5a/zRGOPsFpfPLXR4KCqDKCezAH31LLUkc9iHHgblh5N118kZtGCPRZA8EMmj"
"HsKZEJ8NdZZfok3Jlrlx0F2773aBBdOsX9MyzopsW4Ap/izR7swjR3hfZy6j/7CnvyghiT7N/4rpIDXiz/2XjVdumk3Rddta3PijbpUpDsMJ"
"63IJrMcFYLbDypGIdbdHjNyriHlOiwDUy3t4Yh/CwOgw9gkPLKoAVHStFt7YiNnoNCzCGCcbCav7zTCCBZDLdhvbV3QNDHc+b6KkSLsvN+md"
"u1+4Y6IkqLrhjV7TMledvs22t7vrI5w9M39WGwLztkxmCZbPzfyCWEMYAQ=="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
expected_provider_request={**BEDROCK_INVOKE_REQUEST},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-opus-5-5",
"id": "msg_bdrk_mxljoibckai4wqyt4wd7cmslqjtlkals5cbwms2hackerasjglha",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_qyqgstng2m3crzmaqzbueka3ep22c7lsslqm5vqoatdm7pi37crq",
"content": [
{
"type": "thinking",
"thinking": "I need to check the validation file, particularly around line 18 where the user wants me "
"to look.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how zero, "
"negative and non-integer values are checked.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_016r8yEaJbeHsNj69b8tCYY5",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 45},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 163,
"output_tokens_details": {"thinking_tokens": 18},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello.",
"content": "I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how zero, "
"negative and non-integer values are checked.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 45}',
"name": "read_file",
},
"id": "toolu_bdrk_016r8yEaJbeHsNj69b8tCYY5",
"type": "function",
},
],
"reasoning_content": "I need to check the validation file, particularly around line 18 where the user wants "
"me to look.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to check the validation file, particularly around line 18 where the "
"user wants me to look.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to check the validation file, particularly around line 18 where the "
"user wants me to look.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 163,
"prompt_tokens": 880,
"total_tokens": 1043,
"completion_tokens_details": {"reasoning_tokens": 18, "text_tokens": 145},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},
},
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0: Final = (
"CAQS5AcKEggSEAEYAjgBQgh0aGlua2luZxIMZ3CC5ydK6won2yd9GgxE4gMZ+E/WBfdMZvAiMEVQQ4qw23oAzYzAw0ZKeKq2slCfdKWoUJRd"
"3yCnR0UZgiVPAHOYvnJkBTUpMEzpOSr/BuPzDT9Eso9jzyJX/huQF3Pd7Hwlj+PQFM9uKARSgoG2Dsr1igyT1mEfbp/ePlaLZdxWFpHnHjDk"
"IiVcVqpUTsJ9XSCQyYAOENmalP+NP+DJ2JkQyaZNf3DIIdDNpOWT1hhq2CdYoHu0yuyUTbeihla45+rF68EY3TplHFoDAatrii0itWJ+cA5b"
"OHdolQY1UUyVFkhWyxmiOlh0Zt2Tc/ITerLKB0fySyHWmBzwdU27u5Q1kCeOFB/Qx0FMz8X/tWz034Lh17vJsrxud7PNvREUuYfpDRFrr9+l"
"HEXP2H/BqVEsN55egf1Nc8vu5E5EmBAxU3B7gkJes+PiD/yj/LkwUPDlUZGJnKJB7Vt1ylYcxHaMAfavUHrBLsTbvx6lwyor66phw6v6lQNR"
"TDsMY6qibpE+H5bY5bpGtdH772Z9LWyHRXG94qNHg6YjH46m/NlocjSk5C4U9i6YqYAPYZrHFO4ELzwuqaNmWXUuf4FoL70DAUeUNPn4dsJl"
"lKWyrqs/LmrGolJsde8GpwpTlNNRMkm1hhBMpCnjSrzCS9GElJ0FjF4zrzKpcFmVqGYJ7jf1mWA0lnGmUJQK8FPTAIhtQDgSWmh6sDos4A1T"
"ox12fHGTxflSqi3CIF57+NFmLefxTJLgOEmY8i8yDssZrnDsJC2/1RoKxgEfUJ7a1S6Tx9LWLVwDJJU81FJkCk3R8ZIc3boT7wzlm5Nmxb02"
"r/NubRSPOdsL5tL4UltVQJv2KMGK2/gIgF5vFB5LM5LtBNtdfLolEd6Nar0Loz8aI11mZ0toCIlo8m9nLdut9wx1cjB4ZqmQQLgaZIiM8ZuD"
"I07fPCnfgsnSWAdJ2TrPioGSv1Z0wz+vMZMYzB1ebNpl66WlpWJPTVwbjc7YZH7gNKxduopuh6ZGikhtXuCsv7Xm3K4jb8mRW0esr43IjGO7"
"u4U6bcDAOUwqBa4vR3czuHPSHn2EI69WlPEP1G4Im+DS1G25SJ6VVj4WkYmmid+OEuamPWNYgQ/RUL2nOBSzLFhfBl/R8Dk3ozTOIcooqAB6"
"9e1vCyVh27iTrRahadf0Zx9EqYjc6anG/lIerWRiFvMhZBjvdSbU6H7Ft54ACQUq4ZVGJt747CgmtS2gmokM8klKqkeXZPxlIcPd6yJvxGa4"
"MCh929kyGTs1EkoAt8Qu4OR924AtF3KkBQinwisYAQ=="
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
expected_provider_request={**BEDROCK_INVOKE_REQUEST},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_bdrk_g7xqazu6324fsulzlcgyoh4ixc2pytulkxmgzcjh6bvesncpiweq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_ygn75gjwiywsmw52hhhtugcac2xa3b6qjaoygnm3ihch23zsv4ba",
"content": [
{
"type": "thinking",
"thinking": "The user explicitly said to read the validation file first, so I'll respect that "
"sequencing rather than reading both files in parallel. I'll read the validation file now.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero and negative "
"values are checked.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01MGYCujwiQim9cJXKY33qzc",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 276,
"output_tokens_details": {"thinking_tokens": 141},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello.",
"content": "I'll read `shop/validation.py` around `validate_quantity` to see how zero and negative "
"values are checked.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"name": "read_file",
},
"id": "toolu_bdrk_01MGYCujwiQim9cJXKY33qzc",
"type": "function",
},
],
"reasoning_content": "The user explicitly said to read the validation file first, so I'll respect that "
"sequencing rather than reading both files in parallel. I'll read the validation file "
"now.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "The user explicitly said to read the validation file first, so I'll respect "
"that sequencing rather than reading both files in parallel. I'll read the "
"validation file now.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "The user explicitly said to read the validation file first, so I'll "
"respect that sequencing rather than reading both files in parallel. I'll "
"read the validation file now.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
},
},
}
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"completion_tokens": 276,
"prompt_tokens": 880,
"total_tokens": 1156,
"completion_tokens_details": {"reasoning_tokens": 141, "text_tokens": 135},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"text_tokens": 4,
"cache_write_tokens": 876,
"cache_creation_tokens": 876,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},

678
tests/integration/translation/chat_completions/bases/bedrock_mantle.py
View file

@ -2,7 +2,14 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.bedrock_mantle import (
BEDROCK_MANTLE_ANTHROPIC_MESSAGES_REQUEST,
BEDROCK_MANTLE_ANTHROPIC_MESSAGES_RESPONSE,
BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
)
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -163,86 +170,6 @@ CLAUDE_SONNET_5_TEST_CASE: Final = TranslationTestCase(
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock_mantle/anthropic.claude-opus-5-5",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-bedrock-mantle-key",
},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
"model": "anthropic.claude-opus-5-5",
},
mock_provider_response={
"model": "claude-opus-5-5",
"id": "msg_bdrk_ynrmln5e2d6gulngkuay6eypqvjtghpnmtiioovu57numo6rag2q",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
},
expected_litellm_response={
"id": ANY,
"created": ANY,
"model": "bedrock_mantle/anthropic.claude-opus-5-5",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
}
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 23,
"total_tokens": 29,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 6},
"prompt_tokens_details": {
"cached_tokens": 0,
"text_tokens": 23,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"service_tier": "standard",
},
},
)
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
@ -533,100 +460,76 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock_mantle/openai.gpt-6-luna",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/v1/responses",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock_mantle/anthropic.claude-opus-5-5"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
"authorization": "Bearer synthetic-bedrock-mantle-key",
},
expected_provider_request={
"model": "openai.gpt-6-luna",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"stream": False,
},
mock_provider_response={
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791240609,
"created_at": 1791240609,
"error": None,
"frequency_penalty": 0.0,
"id": "resp_y6jkekxfsn43teacrqd745fnw5m6l3q6sczasxu6y4nxmaoittxq",
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
"metadata": {},
"model": "openai.gpt-6-luna",
"object": "response",
"output": [
{
"content": [{"annotations": [], "logprobs": [], "text": "Hello!", "type": "output_text"}],
"id": "msg_fb51254d3c005892a700f8dc8c55b04d",
"phase": "final_answer",
"role": "assistant",
"status": "completed",
"type": "message",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "in_memory",
"reasoning": {"summary": None, "effort": "medium", "context": "all_turns"},
"safety_identifier": None,
"service_tier": "default",
"status": "completed",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
},
"user": None,
"moderation": None,
},
expected_provider_request={**BEDROCK_MANTLE_ANTHROPIC_MESSAGES_REQUEST},
mock_provider_response={**BEDROCK_MANTLE_ANTHROPIC_MESSAGES_RESPONSE},
expected_litellm_response={
"id": "resp_y6jkekxfsn43teacrqd745fnw5m6l3q6sczasxu6y4nxmaoittxq",
"created": ANY,
"model": "bedrock_mantle/openai.gpt-6-luna",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello!", "role": "assistant"}}],
**CHAT_COMPLETIONS_RESPONSE,
"model": "bedrock_mantle/anthropic.claude-opus-5-5",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Next I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how it "
"handles zero, negative and non-integer values.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"name": "read_file",
},
"id": "toolu_bdrk_018J8SJwAgjhRkkmtm3xdJx2",
"type": "function",
},
],
"reasoning_content": "I should check the validation file first, starting around line 18.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I should check the validation file first, starting around line 18.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I should check the validation file first, starting around line 18.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
},
},
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 19,
"total_tokens": 25,
"completion_tokens_details": {"reasoning_tokens": 0},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
"completion_tokens": 166,
"prompt_tokens": 880,
"total_tokens": 1046,
"completion_tokens_details": {"reasoning_tokens": 19, "text_tokens": 147},
"prompt_tokens_details": {
"cached_tokens": 876,
"text_tokens": 4,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 876,
"service_tier": "standard",
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
},
)
@ -634,90 +537,385 @@ GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "bedrock_mantle/openai.gpt-6.1-sol",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock_mantle/openai.gpt-6.1-sol"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
"model": "openai.gpt-6.1-sol",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"stream": False,
},
mock_provider_response={
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791240612,
"created_at": 1791240612,
"error": None,
"frequency_penalty": 0.0,
"id": "resp_rjew7tdxw2lzv5egpmamwt2g5aifjxopahkpmzawjlcyucblokyq",
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
"metadata": {},
"model": "openai.gpt-6.1-sol",
"object": "response",
"output": [
{
"content": [{"annotations": [], "logprobs": [], "text": "Hello!", "type": "output_text"}],
"id": "msg_6f7c19b0241956fda392424fc5aa3db9",
"phase": "final_answer",
"role": "assistant",
"status": "completed",
"type": "message",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "in_memory",
"reasoning": {"summary": None, "effort": "medium", "context": "all_turns"},
"safety_identifier": None,
"service_tier": "default",
"status": "completed",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
},
"user": None,
"moderation": None,
},
mock_provider_response={**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE},
expected_litellm_response={
"id": "resp_rjew7tdxw2lzv5egpmamwt2g5aifjxopahkpmzawjlcyucblokyq",
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_izakuft4jrxwmodefqee2jjt6gkmayywwuuc242pduoydywb3v4a",
"model": "bedrock_mantle/openai.gpt-6.1-sol",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello!", "role": "assistant"}}],
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I’ll read `shop/validation.py` first to see how it handles zero, negative, and "
"non-integer quantities before inspecting the tests.",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_399ba0e7ac865a798b46a6cabe6b6bde",
"type": "function",
},
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_7a90cfc98ff653aeb165c2b845bc1e4b",
"encrypted_content": "rsn_rru6BQHgUc/VWS5vRIAlHwIFeJ7rFK0vbfOLCW3lZUKZX7nZu5wsyKm4u2DeoLRbILW0AF8AAQAVYXdzLWNyeXB0by1wdWJsaWMta2V5AERBN1N2LzZrWDd1QWV1WkpjQ1dEOFQvSDR2Y0ZaY2ZWemtpR2ZWNGRncEgwZmJqMVBNd3FIV2NnbFlTcHVOcVMyZWc9PQABABFhd3Mta21zLWhpZXJhcmNoeQAKYmVybS1zdG9yZQBcmpoCBv5IPHctwun5UTXrXrEmFVDe7MUULd6PZATyexPQO0PepR8jRQ3zVYSjkLkI8eYSjtPsT9kCKrIpsJlAuid+IimJvnTBHGplsaTC/53IpOSzB87nJlx+m4kCAAAQANtzzELZF5mKNBTvW/ca/WZ6iJI42OwsDigg6J5ZOIdJaC35TDfpQsssoDFQIHtI/v////8AAAABAAAAAAAAAAAAAAABAAABSyq/hcdJ8rImbQvE2c8qmEFM3skJI4sMoBBIdIZm8ljKX6zuu9kBGRln5StGWzlUOVYemoWeHBoDDuZkGDWAeTcQYdNeiCuTOQBg1kfIvhSGpGZHyKIfg+XnWIjrExKbZhmAC/GMebMNNuJ1/ZUFnq0UtD8X1r2xEkIWCUsQHysv9E6D6AstjrAgpo5arvZG0Gi5gryi/eE9Q7IGwilIvzeslUlM7sVcmD5RWe83nMeXmCUR41N50TK11F1j/H314CtKbJbMQWNWGLUUSRiKjqDFiC+o4bioQCRzvka6NUkIBitgjjkJ+etpL5ibB065xADWxaRc6WoUe1VkNVKXlYq4kOBNhnkJSHuasIJiD8/suYWXshD9XMF+SffKyKk3zscZwAuZ7N/ZOayYqGrhOMryCFYXvSo7v8PJ1hvg64z1MknImFG/6rSEVox9yeyfSEQmeDX/ABwO8PAsAGcwZQIwIpngWR/1wARV01RTUI+B4dV7XaR1AC0aOv5KfuQw5UJOnfGVp8E7MS379SPiA+SEAjEA0TMJ1LJ3cXitGqWvPATglnscU7UW9Mhny4elQ+cw7pFm5kRlYA/lkAyDdNyjZFVU",
"summary": [],
},
],
},
},
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 19,
"total_tokens": 25,
"completion_tokens_details": {"reasoning_tokens": 0},
"completion_tokens": 108,
"prompt_tokens": 312,
"total_tokens": 420,
"completion_tokens_details": {"reasoning_tokens": 39},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock_mantle/openai.gpt-6-luna"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-6-luna",
"stream": False,
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027279,
"created_at": 1792027278,
"id": "resp_pbro2cu7wxoshets5f2v3mmv22dzjjepi3ztmm6qceyuuveilumq",
"model": "openai.gpt-6-luna",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_41fd1f946fd95402ac51feb270547528",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I need `shop/validation.py` next; it contains the quantity validator, so it will "
"show how zero, negative, and non-integer values are handled.",
"type": "output_text",
},
],
"id": "msg_bd4b22ee05d75ecc863a79cadb0abc97",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":100}',
"call_id": "call_2bb9788b89cf56e595d03edd897cf96d",
"id": "fc_6cec15107b1055dd90bdbf343add57e6",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 115,
"output_tokens_details": {"reasoning_tokens": 42},
"total_tokens": 427,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_pbro2cu7wxoshets5f2v3mmv22dzjjepi3ztmm6qceyuuveilumq",
"model": "bedrock_mantle/openai.gpt-6-luna",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I need `shop/validation.py` next; it contains the quantity validator, so it will show "
"how zero, negative, and non-integer values are handled.",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":100}',
"name": "read_file",
},
"id": "call_2bb9788b89cf56e595d03edd897cf96d",
"type": "function",
},
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_41fd1f946fd95402ac51feb270547528",
"encrypted_content": "rsn_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",
"summary": [],
},
],
},
},
],
"usage": {
"completion_tokens": 115,
"prompt_tokens": 312,
"total_tokens": 427,
"completion_tokens_details": {"reasoning_tokens": 42},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
},
)
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock_mantle/openai.gpt-6-astra"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-6-astra",
"stream": False,
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027285,
"created_at": 1792027282,
"id": "resp_jpvjizqjx4f4u6nyz7deamnfdzbqxgxqm7nirzdlaxm2mbp5r7yq",
"model": "openai.gpt-6-astra",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_5ddaaaa907d7599da226348b310ffaa1",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, negative, "
"and non-integer quantities.\n",
"type": "output_text",
},
],
"id": "msg_7ee57d84b2515199bcfd28428434f307",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_48b391faab505f0e90dfc7c451b87c2b",
"id": "fc_c8b90cef33d256a986e7a9229db5017a",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 148,
"output_tokens_details": {"reasoning_tokens": 83},
"total_tokens": 460,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_jpvjizqjx4f4u6nyz7deamnfdzbqxgxqm7nirzdlaxm2mbp5r7yq",
"model": "bedrock_mantle/openai.gpt-6-astra",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_48b391faab505f0e90dfc7c451b87c2b",
"type": "function",
},
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_5ddaaaa907d7599da226348b310ffaa1",
"encrypted_content": "rsn_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",
"summary": [],
},
],
},
},
],
"usage": {
"completion_tokens": 148,
"prompt_tokens": 312,
"total_tokens": 460,
"completion_tokens_details": {"reasoning_tokens": 83},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
},
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "bedrock_mantle/openai.gpt-5.6-terra"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-5.6-terra",
"stream": False,
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027294,
"created_at": 1792027292,
"id": "resp_rzoladobotq7d5aitvspg3wwysoow5b436v6zaymozikilgh4uwa",
"model": "openai.gpt-5.6-terra",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_2985de4698f95e958cd7c7cd377a76a2",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "Next I need `shop/validation.py`, which contains `validate_quantity`; I’ll "
"inspect it to verify the handling of zero, negative, and non-integer inputs before "
"reviewing the tests.",
"type": "output_text",
},
],
"id": "msg_afefa5c808a159a1965dc7c7986d0693",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_fc5f6bc78e0b5332b7866a98d5470b46",
"id": "fc_1e6d0bcf394d5b64badb08659c4c6028",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 114,
"output_tokens_details": {"reasoning_tokens": 36},
"total_tokens": 426,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"id": "resp_rzoladobotq7d5aitvspg3wwysoow5b436v6zaymozikilgh4uwa",
"model": "bedrock_mantle/openai.gpt-5.6-terra",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Next I need `shop/validation.py`, which contains `validate_quantity`; I’ll "
"inspect it to verify the handling of zero, negative, and non-integer inputs before "
"reviewing the tests.",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_fc5f6bc78e0b5332b7866a98d5470b46",
"type": "function",
},
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_2985de4698f95e958cd7c7cd377a76a2",
"encrypted_content": "rsn_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",
"summary": [],
},
],
},
},
],
"usage": {
"completion_tokens": 114,
"prompt_tokens": 312,
"total_tokens": 426,
"completion_tokens_details": {"reasoning_tokens": 36},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},

541
tests/integration/translation/chat_completions/bases/gemini.py
View file

@ -1,7 +1,396 @@
from collections.abc import Mapping
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.gemini import (
GEMINI_3_8_FLASH_THOUGHT,
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
GEMINI_GENERATE_CONTENT_REQUEST,
GEMINI_GENERATE_CONTENT_RESPONSE,
)
from pydantic import JsonValue
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "gemini/gemini-3.8-flash"},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request=GEMINI_GENERATE_CONTENT_REQUEST,
mock_provider_response=GEMINI_GENERATE_CONTENT_RESPONSE,
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "gemini/gemini-3.8-flash",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": (
"To check how zero, negative, and non-integer quantities (such as floats, non-numeric values, or "
"values less than or equal to zero) are validated, I need to inspect `shop/validation.py` next."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"provider_specific_fields": {
"thought_signature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
"function": {
"arguments": '{"path": "shop/validation.py", "end_line": 50, "start_line": 1}',
"name": "read_file",
},
"id": "call_7668__thought__" + GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
"type": "function",
},
],
"images": [],
"reasoning_content": GEMINI_3_8_FLASH_THOUGHT,
"thinking_blocks": [
{
"type": "thinking",
"thinking": GEMINI_3_8_FLASH_THOUGHT,
},
],
"provider_specific_fields": {
"thought_signatures": [
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
],
},
},
"provider_specific_fields": {
"native_finish_reason": "STOP",
},
},
],
"usage": {
"completion_tokens": 655,
"prompt_tokens": 358,
"total_tokens": 1013,
"completion_tokens_details": {
"reasoning_tokens": 575,
"text_tokens": 80,
},
"prompt_tokens_details": {
"text_tokens": 358,
},
},
"vertex_ai_citation_metadata": [],
"vertex_ai_grounding_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_url_context_metadata": [],
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT: Final = (
"**Analyzing Quantity Validation in shop/validation.py**\n\n"
"Okay, so the goal here is pretty clear: the user wants to understand how the system validates th"
"e `quantity` field, specifically how zero and negative quantities are handled. My job is to fin"
"d the relevant code and explain what's happening.\n\n"
"The search results pointed to `shop/validation.py`, and specifically to a `validate_quantity` fu"
"nction on line 18. Excellent! That's a direct lead.\n\n"
"Now, I need to get a look at that code. To do that, I'm going to leverage the `read_file` tool. "
"I'm thinking I'll read a block of code around that line – let's say from line 10 to 30 – to give"
" us some context around the function itself. That should give me enough to validate our underst"
"anding of the user request.\n\nIn summary, I'm going to read the `shop/validation.py` file to exam"
"ine the `validate_quantity` function, then I will call the tool.\n\n\n"
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = (
"ErAFCq0FAWkUfRNlFv/lCrWnTeRSJUQxveeFy7unSAIXuMtxRKgoOGMtvJFe+qjPDFHdUuZP3JdL5ppGcmh8B8rxQ2ixle8Z"
"4kyuY1ZCCxoXUYj4al2xk6tKOKmB9Nwcyk8EMfl34HkY4wwzPdnHd5LiHDpdOG+LRDtvCTn0sIZ5vp7xEba4z/3OoSJkNZ5Y"
"dhprkDwNqSEJrCujrSwejQlRBarfIBzKmIMsOuOVuX+jTOZjLjuY2BQ+WaFBze/Nkl3lqBEs1ItCelts/L+6SAFvuzeCdcrt"
"ahBH6+t8M9ZPOCkWcvrCiuwi8xF3AzAhTdTfEcECHFB4HpiJbuPRGNWVNO+c0Xj1tti+oOM6hamlxxiNiE6qEu6fVGI/f14u"
"9fPL5XpGla06CtB5YIo94WifNUdpaF1ydl1VNs7N/qJwH0glZmTqiNGuP3SyURtRg/S7TTIHp2dMyTYWc/baAl0p6g5vJuHd"
"6vN3yBOa8jnUS7di1WKamCFnqKck8vmfXHGwiWsUVHn2SKrI/PKoWOTTw3uc3+Z37pRl/+L9SpNdbfecvOqTrqw12iVi38QY"
"HEukvJu6FqlRQOvOt3wPbb/RAVStD0fpRTQnTkYrS/lI2inNGrDWWpPpi/0u7dWrzJFOGO/7jV+63BggBPplEVcEkCmZrrZC"
"2XAsnjzTzAhPzgZ8kR0m0pvjq2lbJgREIeai4ygQ6q0OQkclZmQChISjtw1K/lSuuNlJCrwZFn9Xsp6JaJ6GrGkaJsbgCOOH"
"bsDyGOba58qNXvvHq33A0km8GthfqiEoEwxLcHwyH3jDDnuYf+/XdqdckdXcMf1T9HcMF1xMhYdkjlYSgVP5iRMIJ/2R1WgK"
"gXoTgXjLCfHUnUUjFFjpgJwEzqfd8M+7cJfS9tcK07Pu4FSmuZcbCuDX9w=="
)
GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"thought": True,
},
{
"text": (
"I will now read the `shop/validation.py` file to see the implementation of the `validate_quantit"
"y` function."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"start_line": 10,
"end_line": 30,
},
"id": "call_1654638",
},
"thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 358,
"candidatesTokenCount": 60,
"totalTokenCount": 568,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 358,
},
],
"thoughtsTokenCount": 150,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "2ybQaqy6Gd2i6dkPm82G2AU",
}
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "gemini/gemini-3.1-pro-preview"},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request=GEMINI_GENERATE_CONTENT_REQUEST,
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "gemini/gemini-3.1-pro-preview",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": (
"I will now read the `shop/validation.py` file to see the implementation of the `validate_quantit"
"y` function."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"provider_specific_fields": {
"thought_signature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 10, "end_line": 30}',
"name": "read_file",
},
"id": "call_1654638__thought__" + GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
"type": "function",
},
],
"images": [],
"reasoning_content": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"thinking_blocks": [
{
"type": "thinking",
"thinking": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
},
],
"provider_specific_fields": {
"thought_signatures": [
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
],
},
},
"provider_specific_fields": {
"native_finish_reason": "STOP",
},
},
],
"usage": {
"completion_tokens": 210,
"prompt_tokens": 358,
"total_tokens": 568,
"completion_tokens_details": {
"reasoning_tokens": 150,
"text_tokens": 60,
},
"prompt_tokens_details": {
"text_tokens": 358,
},
},
"vertex_ai_citation_metadata": [],
"vertex_ai_grounding_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_url_context_metadata": [],
},
)
GEMINI_4_ARGON_THOUGHT: Final = (
"**My Analysis of Quantity Validation**\n\n"
"Okay, so the user wants me to start by looking at `shop/validation.py`. Right, that makes perfec"
"t sense given the instructions and the task. I need to understand how the system handles quantit"
"ies, especially zero, negative, and potentially non-integer values. It's crucial for me to have "
"that foundational knowledge before I even *think* about suggesting a fix, and the system wants m"
"e to ensure this is understood and considered.\n\n"
"Therefore, I'll state explicitly that I need to examine the `validate_quantity` function within "
"`shop/validation.py`. This will allow me to properly evaluate how quantities are being handled i"
"n detail.\n\nNow, I will use the `read_file` tool on `shop/validation.py`.\n\n\n"
)
GEMINI_4_ARGON_THOUGHT_SIGNATURE: Final = (
"Er0FCroFAWkUfRNrM27jPbX+vFoKJwoTVY0Na19E0vke/4MAfKRQYmXkW61lN+IKyH0lUQrByoh3xOQWzUqZrNCCJXa492UF"
"RkKVWhi+PVV+fwUBYsmlj7U9Yn379+WUNYt8rkl04KN7jmZJqzrP7T0A58rciLtp4t8vw1I+yi0+OZRBrvg9iU0gyCeWldbp"
"icQEAiwJBKYIJ9iiy5nFwhwbjANtiqo3WflAuBar1rWfnOq7aU3OOu6x5ZWKVABmTylKPBVCZeVn5ey5t/XJWxPPCF6ObIiF"
"V99T6S3OI+5wcC1HmHcl3LTCUHsSleVynLZ6Xpg1kpPmCEsFneXBEDqTgTjtYVSyuO/3dqnIM6Z/0OiPp+yoh1cjQguM72xB"
"2cqE+/OISSZTn85bhcXKXAQYHD4K0rOC7SL2bJVFtMOIrwby5CL4bFWiwFV8TLQzgHzE0Yhs2/tfGezXrofVaI0HApsUEKDz"
"F4zitTKD5pzw6k0JHOlZ9iETqCnPcQwhw5H2w+QYqn6M7D7HUQvYUF5ZhVWToq55xi/x261Q0K/a3LHUZuBZrYHpYP8NoV29"
"3v9Vibad/rPZK80wLDSgl+U/HAPuy/nBSoYM4IzQun5AkN6XTCHEM6cKUHLY6GzFTMWiWhBH9EBAUTP34OF4ztaNLxuZvjUn"
"X/iSiKRZj4cFHN74cfDJBj/SdRo/hlWVXl7D3TXAF9UOsjj3Hq5vjoSyIMJjLAoEU0ZxfrqkHGXE0kKHLqiuZaC9lzK0UvrV"
"V0MoQ+vf2NkzuN92hjMoFL9yi6DZgogR3B8XCUpghB4Jjx4CPX212Q4kPBxPYAuq7c2+VAm3yX3IDVmDnzENBNBKlqmXkjf6"
"LMdS+HZdhDwno+M5sq17u75h+FPfOQM8JXh0T5B8zAuQM6jtaKwqANJJYK9/wJM7zBQ5W1PnvaE="
)
GEMINI_4_ARGON_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_4_ARGON_THOUGHT,
"thought": True,
},
{
"text": (
"I will read `shop/validation.py` next to see how `validate_quantity` handles zero, negative, and"
" non-integer quantities."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"start_line": 1,
"end_line": 50,
},
"id": "call_1426689",
},
"thoughtSignature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 414,
"candidatesTokenCount": 69,
"totalTokenCount": 628,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 414,
},
],
"candidatesTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 69,
},
],
"thoughtsTokenCount": 145,
},
"modelVersion": "gemini-4-argon",
"responseId": "4CbQarGpL8SGz7IPxf-zyQ0",
}
GEMINI_4_ARGON_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "gemini/gemini-4-argon"},
expected_provider_endpoint="/models/gemini-4-argon:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request=GEMINI_GENERATE_CONTENT_REQUEST,
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_4_ARGON_RESPONSE_FIELDS},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "gemini/gemini-4-argon",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": (
"I will read `shop/validation.py` next to see how `validate_quantity` handles zero, negative, and"
" non-integer quantities."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"provider_specific_fields": {
"thought_signature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"name": "read_file",
},
"id": "call_1426689__thought__" + GEMINI_4_ARGON_THOUGHT_SIGNATURE,
"type": "function",
},
],
"images": [],
"reasoning_content": GEMINI_4_ARGON_THOUGHT,
"thinking_blocks": [
{
"type": "thinking",
"thinking": GEMINI_4_ARGON_THOUGHT,
},
],
"provider_specific_fields": {
"thought_signatures": [
GEMINI_4_ARGON_THOUGHT_SIGNATURE,
],
},
},
"provider_specific_fields": {
"native_finish_reason": "STOP",
},
},
],
"usage": {
"completion_tokens": 214,
"prompt_tokens": 414,
"total_tokens": 628,
"completion_tokens_details": {
"reasoning_tokens": 145,
"text_tokens": 69,
},
"prompt_tokens_details": {
"text_tokens": 414,
},
},
"vertex_ai_citation_metadata": [],
"vertex_ai_grounding_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_url_context_metadata": [],
},
)
GEMINI_3_5_FLASH_THOUGHT_SIGNATURE: Final = "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"
@ -78,155 +467,3 @@ GEMINI_3_5_FLASH_TEST_CASE: Final = TranslationTestCase(
"vertex_ai_citation_metadata": [],
},
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = "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"
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "gemini/gemini-3.8-flash",
"max_tokens": 1024,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 120,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 108,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "5BjEaunaCtadz7IP-8WKsAk",
},
expected_litellm_response={
"id": "5BjEaunaCtadz7IP-8WKsAk",
"created": ANY,
"model": "gemini/gemini-3.8-flash",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"images": [],
"thinking_blocks": [],
"provider_specific_fields": {"thought_signatures": [GEMINI_3_8_FLASH_THOUGHT_SIGNATURE]},
},
"provider_specific_fields": {"native_finish_reason": "STOP"},
}
],
"usage": {
"completion_tokens": 110,
"prompt_tokens": 10,
"total_tokens": 120,
"completion_tokens_details": {"reasoning_tokens": 108, "text_tokens": 2},
"prompt_tokens_details": {"text_tokens": 10},
},
"vertex_ai_grounding_metadata": [],
"vertex_ai_url_context_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_citation_metadata": [],
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = "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"
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "gemini/gemini-3.1-pro-preview",
"max_tokens": 1024,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 115,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 103,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "5RjEaqfwC7XYqtsPp6TuoAY",
},
expected_litellm_response={
"id": "5RjEaqfwC7XYqtsPp6TuoAY",
"created": ANY,
"model": "gemini/gemini-3.1-pro-preview",
"object": "chat.completion",
"choices": [
{
"finish_reason": "stop",
"index": 0,
"message": {
"content": "Hello.",
"role": "assistant",
"images": [],
"thinking_blocks": [],
"provider_specific_fields": {"thought_signatures": [GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE]},
},
"provider_specific_fields": {"native_finish_reason": "STOP"},
}
],
"usage": {
"completion_tokens": 105,
"prompt_tokens": 10,
"total_tokens": 115,
"completion_tokens_details": {"reasoning_tokens": 103, "text_tokens": 2},
"prompt_tokens_details": {"text_tokens": 10},
},
"vertex_ai_grounding_metadata": [],
"vertex_ai_url_context_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_citation_metadata": [],
},
)

734
tests/integration/translation/chat_completions/bases/openai.py
View file

@ -1,7 +1,11 @@
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.openai import (
OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS,
OPENAI_RESPONSES_RESPONSE,
)
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -276,280 +280,632 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "openai/gpt-6-luna",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "openai/gpt-6-luna"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6-luna",
"max_completion_tokens": 64,
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS, "model": "gpt-6-luna"},
mock_provider_response={
"id": "chatcmpl-EVhxzlhJ6vfxv0dDB3QzTZvHJWTno",
"object": "chat.completion",
"created": 1791225883,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-luna",
"choices": [
"id": "resp_0a2459714d575226006ad02398406087d0a2501571a0097cce",
"created_at": 1792025496,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025499,
"instructions": (
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect."
),
"output": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!", "refusal": None, "annotations": []},
"finish_reason": "stop",
}
"id": "rs_0a2459714d575226006ad0239a42d087d08ab86bc19873f8f8",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0CObTtOHdIl0AomNdpnN-jGzO6wbopH5o7XAO-1__huttxkYQhzVBAV_TQ_Y-LHedrilDsn2OYqDrSZke4WPG2uMFL0z1kvWcj1zShAuI3bzLB4637l7tqQeM41ncLLPD2gfy4gS1G4oX-vWl-cJK5apCct8b6VXdWClY9H7OmLyrtYeyeTcvacBq3cJf6OJg6zI2f4O-rPsifmcGdXwojO8JWhliGBJX_98gjGwKEdBAVJHFXP57xEZbCd9b2ISUofeSbdVfvzCnwsRs5Bx40pQf_abIM99JdNNictIr0Zim2jiIEh5hfOJhlu6vRmaLT3eJ9fRE_ao_wkSaCllTwzH7z-QUBSSXmj8SqQCp0m-WExL4SPKrTLhQteqTRDx4F833tJNJbdAe65PyO_2cChbvqmIU9BMB0dftkbfWdt3JwP8be7_aSG-c250rTCB373oI8Xf5vBQcqVhJ3hfu-1ddFjWgFdk7b7V1nlBKsKK3_EzCNCMmcoGwKFShIZRL9RxyBYiStLjUT3PA9DtBay6wKyW62mG2JJPQxknrOE0BBmcD3Kg4EbH9jgThKxv4zQkFTSl_-gsoSFFnUbhRDCcSQpirefKYf_xBWpBU55_jjHWfkhZXfOuU4eArnD6g4Lt7T3wd9SQyRh3I5xdtzNUxd4fswu99REgL_S3tfUmPohLrFGBywb4SSFbqaz7HwR8y3NN9Aet7XVdTskdfv0g3_sBKQyCf1o3-hc4lNBFxXFaEEFXMQTPZKOjfPJNP7ZKxfueiwadGg0aVV-dPCAMnMuSncc5RC17f9ohZyGncTQHT1lLJJPOiAcQPThZABVu4Ptnuhn2oXs0HGk_q6y3cWDXOZOojrFncvDGHC8dUx2KNhNKsDGVGteHay8UDQBmEnSMez2mfHdCRRcuO6R9ZBWV-7TMAMxYgJ_nnGk-n2WAEmIrnWtSQkvInKtYf3A8bB9nyJ6Beu8IL20baT1SD3mtnm4y-ozQ8uuVsuVRNAatotjX23kjzx0kXpiS9xNeD5nYmxIDpO9TAb3nx2F5KPbEYbOB-7B_yvjteQFk6EfApTmwH9xX2nOGfN42ttX063EtBK4IvSbbGWLbjmfbgHB_hdn6Iev7zJxZ53M_WyPAMWcbvx7OZijvfAznAwGyRDDFla-CZmQhiFDPq5GwVsLwSHK-XIi-nPMJfBaBBXdP03KqG6whBNA2q6ZvyAvdr5hyFab6atRocfK6eSGbhpmrY5VTDEW7P1jqmG2myIFEMtgNCw7HA9DC11RD0cRk6e2Fwl_xrmHm9G7NL06RQT5NaGJIBRRHRt9fqAj4JlWFbXzj866Ob21ApfBHvP7GLrTWQeNJf5IcJYrZbgTK0JOn0twLTf0ekZoDzrw7qu1a9OnC3rsDQsMYRNtaOkAyHOfQhcQwZmg264AIhqmy_69fUZxBuLq-aLIVSDiJUujKRqiTtjAlvdqXObg-1lnDf9IhSB4qXn0Vcraows4g9b2-gc2t6GoGwqf3Cv7fXFK4jWajNsNenMgEjHyXVTGRY5fIBLBhoRzOcuy8FuIXN6WeYj6JAbnGfnB4Z4yssWJrSiqcH4X5YUHSZDYkB3w9dsZpTDCr8kNoW6oJrnrX6tegNQJUIi6iaQHR2vxptmnvueTKbC3sj2J0ICPWhLKbjOHMOHgGoLaT_s-SiH4CjrvoZALYOWMKyP0EMghJl9mNFLt-mnexO6Egm6J9xAuglMUxFm1txFuDBAp7jq1TR6z1mLm4-ZorpVIvbJv85FS4qQmpGpY_nU1IFTwcKET4skSsJk9utzfW5nfG6A9kejsG-eJNg9yatnenrglGNDs5RmfBKvbvr_yGK1agM3n47n9So8r7G46CviCHDoyx0nvQwog83YYAQOxEd8mlziu0ZmBrEwWxSMeGyYIPVGOWr3FrutMX7ySxxN9uk7oNzZFl9O4PoZwaCCipA0KDAVXiJ0A36Zp2sqnIeecXkWJEZHxynZ6Y8mOFn4SM-JrZ_PJBvWPpPEYTTKSCUrBh1ytBzXN2zU435TJ8I1hGBiG6atVCJ3DK4UtBhzYMwkG6Yj6jhXGBsNBUBaN8-vmCcda620JebM1U4dCtLhwsW_4J2B-S9gaYIXWtV10kIO-yKW_L8QCZQAtB44pOfKwPjy_n4PHoMV4IibbNDCDclVl8cAnO7-RJH5sewDmU1M_u5llf1x6wd8nWBKh1_kBlc6jPIZ8hkVTxy6QvthAYPV5_BPGtOEhbxj8po60tBU5d-kZMEkLBFQdKjiwTOMTBBe5SsdC32vnqL7ZZEj5ZK6xiCY4jYA8ykTyE9jTtx_rdnSpPMLviBw2gbOmlOVGoUw_AX71pojMTYDuVT_mnXrid5Dd7vVaBe8-3a9p0dnxX29k5JEo48yT9DY5JqXo2Dvg5YAadq4uueww8VGOrM25V",
"summary": [],
},
{
"id": "msg_0a2459714d575226006ad0239af77c87d09bf21be68f806551",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to see how it handles zero, negative, "
"and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0a2459714d575226006ad0239b46bc87d0ad9e2b753765029b",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_zySVmQauaNPsuWHCle7BA4CX",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 5,
"total_tokens": 24,
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0,
},
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 141,
"output_tokens_details": {"reasoning_tokens": 76},
"total_tokens": 453,
},
"service_tier": "default",
"system_fingerprint": None,
},
expected_litellm_response={
"id": "chatcmpl-EVhxzlhJ6vfxv0dDB3QzTZvHJWTno",
"created": 1791225883,
**CHAT_COMPLETIONS_RESPONSE,
"model": "openai/gpt-6-luna",
"object": "chat.completion",
"id": "resp_0a2459714d575226006ad02398406087d0a2501571a0097cce",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello!",
"content": "I’ll read `shop/validation.py` first to see how it handles zero, "
"negative, and non-integer quantities.",
"role": "assistant",
"refusal": None,
"annotations": [],
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_zySVmQauaNPsuWHCle7BA4CX",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0a2459714d575226006ad0239a42d087d08ab86bc19873f8f8",
"encrypted_content": "gAAAAABq0CObTtOHdIl0AomNdpnN-jGzO6wbopH5o7XAO-1__huttxkYQhzVBAV_TQ_Y-LHedrilDsn2OYqDrSZke4WPG2uMFL0z1kvWcj1zShAuI3bzLB4637l7tqQeM41ncLLPD2gfy4gS1G4oX-vWl-cJK5apCct8b6VXdWClY9H7OmLyrtYeyeTcvacBq3cJf6OJg6zI2f4O-rPsifmcGdXwojO8JWhliGBJX_98gjGwKEdBAVJHFXP57xEZbCd9b2ISUofeSbdVfvzCnwsRs5Bx40pQf_abIM99JdNNictIr0Zim2jiIEh5hfOJhlu6vRmaLT3eJ9fRE_ao_wkSaCllTwzH7z-QUBSSXmj8SqQCp0m-WExL4SPKrTLhQteqTRDx4F833tJNJbdAe65PyO_2cChbvqmIU9BMB0dftkbfWdt3JwP8be7_aSG-c250rTCB373oI8Xf5vBQcqVhJ3hfu-1ddFjWgFdk7b7V1nlBKsKK3_EzCNCMmcoGwKFShIZRL9RxyBYiStLjUT3PA9DtBay6wKyW62mG2JJPQxknrOE0BBmcD3Kg4EbH9jgThKxv4zQkFTSl_-gsoSFFnUbhRDCcSQpirefKYf_xBWpBU55_jjHWfkhZXfOuU4eArnD6g4Lt7T3wd9SQyRh3I5xdtzNUxd4fswu99REgL_S3tfUmPohLrFGBywb4SSFbqaz7HwR8y3NN9Aet7XVdTskdfv0g3_sBKQyCf1o3-hc4lNBFxXFaEEFXMQTPZKOjfPJNP7ZKxfueiwadGg0aVV-dPCAMnMuSncc5RC17f9ohZyGncTQHT1lLJJPOiAcQPThZABVu4Ptnuhn2oXs0HGk_q6y3cWDXOZOojrFncvDGHC8dUx2KNhNKsDGVGteHay8UDQBmEnSMez2mfHdCRRcuO6R9ZBWV-7TMAMxYgJ_nnGk-n2WAEmIrnWtSQkvInKtYf3A8bB9nyJ6Beu8IL20baT1SD3mtnm4y-ozQ8uuVsuVRNAatotjX23kjzx0kXpiS9xNeD5nYmxIDpO9TAb3nx2F5KPbEYbOB-7B_yvjteQFk6EfApTmwH9xX2nOGfN42ttX063EtBK4IvSbbGWLbjmfbgHB_hdn6Iev7zJxZ53M_WyPAMWcbvx7OZijvfAznAwGyRDDFla-CZmQhiFDPq5GwVsLwSHK-XIi-nPMJfBaBBXdP03KqG6whBNA2q6ZvyAvdr5hyFab6atRocfK6eSGbhpmrY5VTDEW7P1jqmG2myIFEMtgNCw7HA9DC11RD0cRk6e2Fwl_xrmHm9G7NL06RQT5NaGJIBRRHRt9fqAj4JlWFbXzj866Ob21ApfBHvP7GLrTWQeNJf5IcJYrZbgTK0JOn0twLTf0ekZoDzrw7qu1a9OnC3rsDQsMYRNtaOkAyHOfQhcQwZmg264AIhqmy_69fUZxBuLq-aLIVSDiJUujKRqiTtjAlvdqXObg-1lnDf9IhSB4qXn0Vcraows4g9b2-gc2t6GoGwqf3Cv7fXFK4jWajNsNenMgEjHyXVTGRY5fIBLBhoRzOcuy8FuIXN6WeYj6JAbnGfnB4Z4yssWJrSiqcH4X5YUHSZDYkB3w9dsZpTDCr8kNoW6oJrnrX6tegNQJUIi6iaQHR2vxptmnvueTKbC3sj2J0ICPWhLKbjOHMOHgGoLaT_s-SiH4CjrvoZALYOWMKyP0EMghJl9mNFLt-mnexO6Egm6J9xAuglMUxFm1txFuDBAp7jq1TR6z1mLm4-ZorpVIvbJv85FS4qQmpGpY_nU1IFTwcKET4skSsJk9utzfW5nfG6A9kejsG-eJNg9yatnenrglGNDs5RmfBKvbvr_yGK1agM3n47n9So8r7G46CviCHDoyx0nvQwog83YYAQOxEd8mlziu0ZmBrEwWxSMeGyYIPVGOWr3FrutMX7ySxxN9uk7oNzZFl9O4PoZwaCCipA0KDAVXiJ0A36Zp2sqnIeecXkWJEZHxynZ6Y8mOFn4SM-JrZ_PJBvWPpPEYTTKSCUrBh1ytBzXN2zU435TJ8I1hGBiG6atVCJ3DK4UtBhzYMwkG6Yj6jhXGBsNBUBaN8-vmCcda620JebM1U4dCtLhwsW_4J2B-S9gaYIXWtV10kIO-yKW_L8QCZQAtB44pOfKwPjy_n4PHoMV4IibbNDCDclVl8cAnO7-RJH5sewDmU1M_u5llf1x6wd8nWBKh1_kBlc6jPIZ8hkVTxy6QvthAYPV5_BPGtOEhbxj8po60tBU5d-kZMEkLBFQdKjiwTOMTBBe5SsdC32vnqL7ZZEj5ZK6xiCY4jYA8ykTyE9jTtx_rdnSpPMLviBw2gbOmlOVGoUw_AX71pojMTYDuVT_mnXrid5Dd7vVaBe8-3a9p0dnxX29k5JEo48yT9DY5JqXo2Dvg5YAadq4uueww8VGOrM25V",
"summary": [],
}
],
},
"provider_specific_fields": {},
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"completion_tokens": 141,
"prompt_tokens": 312,
"total_tokens": 453,
"completion_tokens_details": {"reasoning_tokens": 76},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"access_programs": {"cyber": "daybreak_blue"},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"system_fingerprint": None,
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
},
)
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "openai/gpt-6.1-sol",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "openai/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6.1-sol",
"max_completion_tokens": 64,
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "chatcmpl-EVhy2Sc0BN5sjJZK2Wa6l3CtsQ2ot",
"object": "chat.completion",
"created": 1791225886,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"choices": [
"id": "resp_0e8134ce088f63e7006ad023a2e5b887d0a0f422419e0bfbe7",
"created_at": 1792025506,
"completed_at": 1792025510,
"instructions": (
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect."
),
"output": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!", "refusal": None, "annotations": []},
"finish_reason": "stop",
}
"id": "rs_0e8134ce088f63e7006ad023a3ff5887d0801528ceb0190f4b",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COmpSSf5bN4H0xC2pbhfp_niGPAm58n4-JyZsHy0ytyhg6KzzTZiR0cjuNAHvZR_w8oavaY1zzH-MkWItVhAx-PQJQ560Da0Dwqi_wwJ0831R8W6lxyeFxgBZXpZ4_TsbT1qwt7IwVC6fJE4gDeFGiuo4H7plTfbE7C2DaO_0fkI5Zt_iRZLA3VOJPFnzegipK4A5AxckZNVZLI705xzMfi7KU6J886jCmsqCxjrQKLwP4fB0jQoRidBCensrctV2C7imXgTAlTwOysSd8gf7Yhu7A9qD1rUj_jvLGJCiqBCe9Cyv9I7cX82VewV4029mGOngvQOUAgVbqT_i9LkQ3HfBXu4SYTK_LXU2P0lw_P69qKYGTZfdwxqui8VVtgJI7kDrZY-l7DvqaIncKJ-LgDJBvxaYDMM7H1Co68Yd64RM3U1v4kTezKN_MBg-1Ku0m1e3Zi7YZDHOHkFDDGFXzXCpbGkgDJCHsG7i-UTE1uAjkgdP9h0MUFosMYB8pl2NxtN8NnEHsBfyYBV56Sms8ObilQaK2eEWvnDH_wkGLt2RAGOJwfovSEwKnWgOemEZtA_IYbxhRNupRJkPy0oJ4xPdAxIICncSkwaF_NMYeIetF-0tvqK2mqWZVnI13w_CPUW0WI0nlfSnlqO-7gD4Xh80-cvFAqr44X_yaRODPOOc6aWoXb_23A2AoFW6vEKufFf3zni2JEHiCREgvUAp8p931WYo7H_lDpOqIHGiQVjvRfUN9pRPnpPbF6NwCUNalgQPt4UZal_ubh3kdF1NRqKuTQMcalPfuw7Zdc7-ZFTV3JdUApBwsF2jGFXzAfmwHytnOohHOAm79n_7ORaJV3ecKjyg0t-N777eu-7LJX79tvy1tNXR-0DsodobU-mHuyxqC4Qhmqk8jC1IeNG7du1IUwpFJnOyM4O1D6xUYGslBWXsIa_exQpTkxH0PYSYeCGA9GCeWsrn8gSkOgwBmtsC56Bow8VldAr_t_AS5UIrSUsNvn1SF-nZJKbe1mvL-egWOuQq8dZb3wEF7vVxqgn4_f54pGXyDeEdxPdxAKhqT672MKb3l_K11Yn10kbhNr1XqX-m323zLcNizjPlH8rJGUWht7RGQd6VOxEjmhKC_ZWFsu7wQgqsGX0BQ2e-6hZE2Kq_9u_MfSieYJyt9jb6XXrqefSP2tyWsrrS6HrBBrSkh2d5PfiP4MQ2gTesP9tj-yVlq4JU3FZMgqS5W7m2BmhD8gGonaLSK5zJboTYjpZHoS0swfxX2_BJDiARNrPFZ58t6sSXDZauTZq8CbdLdXUBA6RaO1kp-yscPIuB2DHjPjPUVrRYbNWSPIcjqHDYY11UHPs7lWL8U5j-j3EfYwiwQ85YnVfoB7jzJFeiywAUvbum20MJXBOE2wrvrR6zXJAGYlEwxKbl_ibZULRRuJ-VSGeijiDNtavD5v5-AAmow5yPuuVUH9_kx7Un8ZbbESZH1rptCToDmxeRrIa51Xw8fIbONz1fVNzljCUvqvsoyjPQAlaZy_YfLIOYD5MVhVX8XiR8mIeSna4ELdWXu8EEmPWyl676GbSZvMzQmBVqDFeELEusHm_UNX3oI5oOMJQ8ZA9p-JyJlx8LWDe3wqTaKKzoajxn2Wz6qvjKFStkGrk0voFzEPEnBbIAIPkh7Uv2ORupzlQeF6Hor11DxlDAIaUQf1344U37C-a1ODbqL8tg7HOm1WSKdwWeKG2-SYk9K8yB1hEZuqmxHquiXybUU-EYrQFGv88d-K0ou-wAjolMdXlIUaT5-OmqA8HCprI4Nr1BdxQYLLwlNyxm5Y610a1Bd9clo8YbW-I_zSNVm74nF1_HzKP3Ym9H3_f1ZWj55BOAw9i1jmk6kb7P2SAomQ9WVCHvhbyPUhrMMlDxc5VpQOMlFRIZjCEb4wirnD4oonK5mt_TY1l_XMc7DAFb91wpdF3dB6Nh8W2_YYC8_vHfvvSq5WtVKBVIBzZM7l188EX3zHUoe4a9pbQj2Yj2-fAF4qnae4DZ1IwYvoUrln3YETLC37Qb7c3cwM_-i9YLiB_F-qA-pVnmwH8Ah2a3cOF-sl50BE7ey_rHw0fhnflc2bicoLMA82gXdE3iuAsPX-sJvouXgLB1KYmFZt_8Hm3QlrT2c8mj_Jt10YdPC_haBCvzOQDvi5kfPM2upPrvgm7bPEgyjLZECEaQj7bjgAsZc7PqnNp0u41Quq2WxUbjMrE6BPjcrhF5Llx6PQjrz2d5_023M1xBMGxKNXaLNmyi91YpvC0Sqd9qUKndUQ6fPA4z03_FP7-UnzYPuJQaBX662f1Vd-sSUvvM4zdPw6YX-muGqHF5qld2He6eMaUUXhjDuwvy2LW5WRQfSbWJ89XsUYqDwDM0j8TEexma6UZ07uNV_xjse6P8JfL-L8BDiHkR7ZNRMDSYqsHQjqwoYZNUs25XwWPr7kjn-43H0mW_dXPcManZ6qBlKKETmdtr8CZrtNxZ1_TnHUeNkATzhmtzyLQRmouxUq6tbPMumlcXcwhvDBSKSR33a4LZG1kknf_YlTDLA4x7sHImDRMYgM9d6SYxBuTSq1OfTtSv7i4Wz5_Pef3iNFI8JH6Q6b24vED1lnWvVEImDKReDYdDLoNJr2BbSt6iZ0hsGSQ5EMsE3jlizNIBwdqI5z2MKTCYWAXSbxXe62zgaklRD6IoCER9h4SqjsnOh9esKu1bg-AkSa04Le9PP4i2whspq6Xa7f4DJpRYb-hEdY",
"summary": [],
},
{
"id": "msg_0e8134ce088f63e7006ad023a5aa0c87d0aee7de2e31f58a5c",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to see how it handles zero, negative "
"values, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0e8134ce088f63e7006ad023a615bc87d0b7aaafc731d1f086",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_sPhtuzlfkfNe16kBteKPS72V",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 5,
"total_tokens": 24,
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0,
},
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 166,
"output_tokens_details": {"reasoning_tokens": 100},
"total_tokens": 478,
},
"service_tier": "default",
"system_fingerprint": None,
},
expected_litellm_response={
"id": "chatcmpl-EVhy2Sc0BN5sjJZK2Wa6l3CtsQ2ot",
"created": 1791225886,
**CHAT_COMPLETIONS_RESPONSE,
"model": "openai/gpt-6.1-sol",
"object": "chat.completion",
"id": "resp_0e8134ce088f63e7006ad023a2e5b887d0a0f422419e0bfbe7",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello!",
"content": "I’ll read `shop/validation.py` first to see how it handles zero, "
"negative values, and non-integer quantities.",
"role": "assistant",
"refusal": None,
"annotations": [],
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_sPhtuzlfkfNe16kBteKPS72V",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0e8134ce088f63e7006ad023a3ff5887d0801528ceb0190f4b",
"encrypted_content": "gAAAAABq0COmpSSf5bN4H0xC2pbhfp_niGPAm58n4-JyZsHy0ytyhg6KzzTZiR0cjuNAHvZR_w8oavaY1zzH-MkWItVhAx-PQJQ560Da0Dwqi_wwJ0831R8W6lxyeFxgBZXpZ4_TsbT1qwt7IwVC6fJE4gDeFGiuo4H7plTfbE7C2DaO_0fkI5Zt_iRZLA3VOJPFnzegipK4A5AxckZNVZLI705xzMfi7KU6J886jCmsqCxjrQKLwP4fB0jQoRidBCensrctV2C7imXgTAlTwOysSd8gf7Yhu7A9qD1rUj_jvLGJCiqBCe9Cyv9I7cX82VewV4029mGOngvQOUAgVbqT_i9LkQ3HfBXu4SYTK_LXU2P0lw_P69qKYGTZfdwxqui8VVtgJI7kDrZY-l7DvqaIncKJ-LgDJBvxaYDMM7H1Co68Yd64RM3U1v4kTezKN_MBg-1Ku0m1e3Zi7YZDHOHkFDDGFXzXCpbGkgDJCHsG7i-UTE1uAjkgdP9h0MUFosMYB8pl2NxtN8NnEHsBfyYBV56Sms8ObilQaK2eEWvnDH_wkGLt2RAGOJwfovSEwKnWgOemEZtA_IYbxhRNupRJkPy0oJ4xPdAxIICncSkwaF_NMYeIetF-0tvqK2mqWZVnI13w_CPUW0WI0nlfSnlqO-7gD4Xh80-cvFAqr44X_yaRODPOOc6aWoXb_23A2AoFW6vEKufFf3zni2JEHiCREgvUAp8p931WYo7H_lDpOqIHGiQVjvRfUN9pRPnpPbF6NwCUNalgQPt4UZal_ubh3kdF1NRqKuTQMcalPfuw7Zdc7-ZFTV3JdUApBwsF2jGFXzAfmwHytnOohHOAm79n_7ORaJV3ecKjyg0t-N777eu-7LJX79tvy1tNXR-0DsodobU-mHuyxqC4Qhmqk8jC1IeNG7du1IUwpFJnOyM4O1D6xUYGslBWXsIa_exQpTkxH0PYSYeCGA9GCeWsrn8gSkOgwBmtsC56Bow8VldAr_t_AS5UIrSUsNvn1SF-nZJKbe1mvL-egWOuQq8dZb3wEF7vVxqgn4_f54pGXyDeEdxPdxAKhqT672MKb3l_K11Yn10kbhNr1XqX-m323zLcNizjPlH8rJGUWht7RGQd6VOxEjmhKC_ZWFsu7wQgqsGX0BQ2e-6hZE2Kq_9u_MfSieYJyt9jb6XXrqefSP2tyWsrrS6HrBBrSkh2d5PfiP4MQ2gTesP9tj-yVlq4JU3FZMgqS5W7m2BmhD8gGonaLSK5zJboTYjpZHoS0swfxX2_BJDiARNrPFZ58t6sSXDZauTZq8CbdLdXUBA6RaO1kp-yscPIuB2DHjPjPUVrRYbNWSPIcjqHDYY11UHPs7lWL8U5j-j3EfYwiwQ85YnVfoB7jzJFeiywAUvbum20MJXBOE2wrvrR6zXJAGYlEwxKbl_ibZULRRuJ-VSGeijiDNtavD5v5-AAmow5yPuuVUH9_kx7Un8ZbbESZH1rptCToDmxeRrIa51Xw8fIbONz1fVNzljCUvqvsoyjPQAlaZy_YfLIOYD5MVhVX8XiR8mIeSna4ELdWXu8EEmPWyl676GbSZvMzQmBVqDFeELEusHm_UNX3oI5oOMJQ8ZA9p-JyJlx8LWDe3wqTaKKzoajxn2Wz6qvjKFStkGrk0voFzEPEnBbIAIPkh7Uv2ORupzlQeF6Hor11DxlDAIaUQf1344U37C-a1ODbqL8tg7HOm1WSKdwWeKG2-SYk9K8yB1hEZuqmxHquiXybUU-EYrQFGv88d-K0ou-wAjolMdXlIUaT5-OmqA8HCprI4Nr1BdxQYLLwlNyxm5Y610a1Bd9clo8YbW-I_zSNVm74nF1_HzKP3Ym9H3_f1ZWj55BOAw9i1jmk6kb7P2SAomQ9WVCHvhbyPUhrMMlDxc5VpQOMlFRIZjCEb4wirnD4oonK5mt_TY1l_XMc7DAFb91wpdF3dB6Nh8W2_YYC8_vHfvvSq5WtVKBVIBzZM7l188EX3zHUoe4a9pbQj2Yj2-fAF4qnae4DZ1IwYvoUrln3YETLC37Qb7c3cwM_-i9YLiB_F-qA-pVnmwH8Ah2a3cOF-sl50BE7ey_rHw0fhnflc2bicoLMA82gXdE3iuAsPX-sJvouXgLB1KYmFZt_8Hm3QlrT2c8mj_Jt10YdPC_haBCvzOQDvi5kfPM2upPrvgm7bPEgyjLZECEaQj7bjgAsZc7PqnNp0u41Quq2WxUbjMrE6BPjcrhF5Llx6PQjrz2d5_023M1xBMGxKNXaLNmyi91YpvC0Sqd9qUKndUQ6fPA4z03_FP7-UnzYPuJQaBX662f1Vd-sSUvvM4zdPw6YX-muGqHF5qld2He6eMaUUXhjDuwvy2LW5WRQfSbWJ89XsUYqDwDM0j8TEexma6UZ07uNV_xjse6P8JfL-L8BDiHkR7ZNRMDSYqsHQjqwoYZNUs25XwWPr7kjn-43H0mW_dXPcManZ6qBlKKETmdtr8CZrtNxZ1_TnHUeNkATzhmtzyLQRmouxUq6tbPMumlcXcwhvDBSKSR33a4LZG1kknf_YlTDLA4x7sHImDRMYgM9d6SYxBuTSq1OfTtSv7i4Wz5_Pef3iNFI8JH6Q6b24vED1lnWvVEImDKReDYdDLoNJr2BbSt6iZ0hsGSQ5EMsE3jlizNIBwdqI5z2MKTCYWAXSbxXe62zgaklRD6IoCER9h4SqjsnOh9esKu1bg-AkSa04Le9PP4i2whspq6Xa7f4DJpRYb-hEdY",
"summary": [],
}
],
},
"provider_specific_fields": {},
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"completion_tokens": 166,
"prompt_tokens": 312,
"total_tokens": 478,
"completion_tokens_details": {"reasoning_tokens": 100},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"system_fingerprint": None,
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
},
)
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "openai/gpt-6-astra",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "openai/gpt-6-astra"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"model": "gpt-6-astra",
"max_completion_tokens": 64,
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS, "model": "gpt-6-astra"},
mock_provider_response={
"id": "chatcmpl-EZ37nFHKO9u4Sc7LwqNWTR0iHbIwn",
"object": "chat.completion",
"created": 1792022199,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-astra",
"choices": [
"id": "resp_0dd9c3f2f13006a2006ad0238bcfa087d0ae1a00e93e9dcfa5",
"created_at": 1792025483,
"completed_at": 1792025487,
"instructions": (
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect."
),
"output": [
{
"index": 0,
"message": {"role": "assistant", "content": "Hello!", "refusal": None, "annotations": []},
"finish_reason": "stop",
}
"id": "rs_0dd9c3f2f13006a2006ad0238ce43887d08314c8e2f0619171",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COPW81YCmA7VJWEaMeFZwZsixHXQg1hUZ8RoBpCteWdhDHmuIxYPWc-lwYTsH28yN7Hjlrgvtmvn5jtVILJozkIcXbLvyXzNi3hswFvpK0NOfkzIeepbxIkFPbEWmAHnGy12UpwFSaQHWNnq3n3_yx1QHg-6L84uhXb_gVLWbQpPfJSUHvqfymkwAH1GoqMKv5GRU1vQQzxs5O8WTfgNLyX0riq6mbYoO8jjRd-QzqkHf5w0fbNsQ0a1npvML0f6vzPdDsBKUrmDiwrd5HjM5tn62CI5ApllJFemVCTa_pXf0d7ws71b-g8d9jIVFtSoDe_oIZ6ZDTiGSRrdgRW3HzZG-hOS85nqwzYcUbXnZ_2dtZUelx1bFpGgH3udKhXIJ1YYXBoTsbYubHskPIWf0DE_rnbLUogslDawx9SBcYJ5dXTD0ipUYtIsW830XTVV1cOl2sFtp4SUrtJiV55G_r7sAxxUyQvF0-OlByS-wEbEvaQfylbFkHZUOcOs69DmgcGP1a_hdD5ZiiY3k1KG63JeIYFzDo1UomGzDFpbbihgq73-FD1JgHARe1vrwJ_0Y3BhhZjJ8UmeLGqyy4C6NQAmaLEg2iK4X-bzItSD-esAhENq-ZmUUKAY74SsGCdPK9srakfVz05rGN0_XKLkkoyW74UzWY89hkYAzrQOw5zGMghVKAioFcpyjX7JVz6fEdL4OWoaTknzhjnQKv1DEq2v8RsZVg3wWuU0t1WB562OQEIaScCVH4knjEtgCB8erZyStk65uwlXK5hQ6rof6Z4-jpd4xp89rAqNcX5OxnXG1SfST50s4C_YddfNe7Y0NQ9_yORz6TChuP3weUXnqlMOWHe4bMSTRLDITfLToWr4KwgajtQ_EmvCrbQWX5BHwSMHOCRKj92eSThzJ2EStpCmV-fihb6onbQk-x3i8pB0J3hkhfRzzsd2vEpy-E4RG9AgKhntN_gwP0Uez_hgEtfv9vipI8qVe-ivu168qU5N8siLollCok_DmIpnjsupxjNlifsv6LhKr97Y7S3TDnpdRL17Mt8lXJpuChunCDC7URHf990u4_j6tuQ9WLGKAq7F8lPoh8HzVdM5ozE-proWaEzFVd035l7q0dQxhQvw0JkhhcRMkjnmIFnTCQ3vAhHc2WCsy-gR5YI472RZoxU6x9q1KOVpTonw6ioUxZoB_QxZGxUT3FPdfMU6pOS0DZ0Ws1qL-49UOSuIleiEAhmX3E_lG_QD5dcxRbCOFHo3-JML3pTrXU49GZi7ZPqzmNcRSK7nxq1751e-YmBt_KYkqLI0sRM0Wwz1X1XTSv7S97iefaAj6xXhnlyc3hi5ofzj8iTGGF-mWYrC-F6GhCizpM91ePu6uugP-FWdtaQ5YXO-9Kq7mFwGB8NE-vftRZBr6p4TbGgXgrZk9rwMpgyC60WACV24UpJhaaBfnPgojE_nuskalMjAy41VA0CyMDCRBJ29MPE9R-dVMNIld9hfBSz2kMCaDXGw83fWPNAcUPQ2fvMBrBhkSLgTRhX7CDElb4foRJS6vTnTgW-es6mk9Ja-3-O013xo09WkqPyYieF1OIWyiALlUVqDtFYdWbUrIHUVV69D03XM3zIgy05HMI5uj46gT8l_X_nDnUI8zolKjB0STnTuzwwK4xvcwl7ank70dIvKatv62MrI-ZEp7QD00ZHeos5fh2X0YxNCsavuKF6UiT_hjWo-v9Sb2qJYKwiv_Bz_pqMqrQyQP-S35FkmWLzfu_ipbNxqE9z_u4WwvPUSdyAdMsJtBc41MJFtYAsBZc5jU0o7Sd2uiVQaUG51Q19jwq6MU68DxcTWukmdB4rQMd4EHYjtNJYr_zGGqzwJAO7gmKeAPxqbwbI5xg_JYGqdVfKBWKdZCCGljYW8DoimGJugt8OJvFFVu3wAOG9KRhaNtdmDnjYd24jxpqWtn5BZSNgwtQP1nh07a7aa-jsJmNpDxu9WH9fax7FXBjz8L9UlG47kBNTpQzKuW_8GRbe2Xvx5jJ0Rh9EFoW1XOiDap3s--MBUDwcRpQvxcU7Ip9gA7JNlsQJoglTvgZiQArlVlbkx7I6UOMHGzJ68UtuFyg3Z6eyAAXTBauozf2VCtbucac_f6kOC80xwZBxfTKG8iXlKOqa3_h_Q66kzPP6h6Ni4-FW-Z5b2aVCUGP_TnG4PkqS-ciRQz2CAdXcHkgy1bXbe-qWXpPBSYs0jnkBygX_v6sa3k8k2wXFenRz0nZ0D684585Axe5Kz5gvW5sR4n2LiN_x95cqDvXCLqzJ-T6kawaRBEoI2Ym3uw7tfOx3o1qyLAvZ9eX4c-dI1kVrC6WzJeeFy2OPOjY=",
"summary": [],
},
{
"id": "msg_0dd9c3f2f13006a2006ad0238e66f487d0b8321be613a40623",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0dd9c3f2f13006a2006ad0238ee75087d0aeb5c9d34c955fb5",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_EEr3oYtEWt2tw0HIjEYCvhL4",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"prompt_tokens": 19,
"completion_tokens": 5,
"total_tokens": 24,
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "audio_tokens": 0},
"completion_tokens_details": {
"reasoning_tokens": 0,
"audio_tokens": 0,
"accepted_prediction_tokens": 0,
"rejected_prediction_tokens": 0,
},
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 135,
"output_tokens_details": {"reasoning_tokens": 70},
"total_tokens": 447,
},
"service_tier": "default",
"system_fingerprint": None,
},
expected_litellm_response={
"id": "chatcmpl-EZ37nFHKO9u4Sc7LwqNWTR0iHbIwn",
"created": 1792022199,
**CHAT_COMPLETIONS_RESPONSE,
"model": "openai/gpt-6-astra",
"object": "chat.completion",
"id": "resp_0dd9c3f2f13006a2006ad0238bcfa087d0ae1a00e93e9dcfa5",
"choices": [
{
"finish_reason": "stop",
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "Hello!",
"content": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
"role": "assistant",
"refusal": None,
"annotations": [],
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_EEr3oYtEWt2tw0HIjEYCvhL4",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0dd9c3f2f13006a2006ad0238ce43887d08314c8e2f0619171",
"encrypted_content": "gAAAAABq0COPW81YCmA7VJWEaMeFZwZsixHXQg1hUZ8RoBpCteWdhDHmuIxYPWc-lwYTsH28yN7Hjlrgvtmvn5jtVILJozkIcXbLvyXzNi3hswFvpK0NOfkzIeepbxIkFPbEWmAHnGy12UpwFSaQHWNnq3n3_yx1QHg-6L84uhXb_gVLWbQpPfJSUHvqfymkwAH1GoqMKv5GRU1vQQzxs5O8WTfgNLyX0riq6mbYoO8jjRd-QzqkHf5w0fbNsQ0a1npvML0f6vzPdDsBKUrmDiwrd5HjM5tn62CI5ApllJFemVCTa_pXf0d7ws71b-g8d9jIVFtSoDe_oIZ6ZDTiGSRrdgRW3HzZG-hOS85nqwzYcUbXnZ_2dtZUelx1bFpGgH3udKhXIJ1YYXBoTsbYubHskPIWf0DE_rnbLUogslDawx9SBcYJ5dXTD0ipUYtIsW830XTVV1cOl2sFtp4SUrtJiV55G_r7sAxxUyQvF0-OlByS-wEbEvaQfylbFkHZUOcOs69DmgcGP1a_hdD5ZiiY3k1KG63JeIYFzDo1UomGzDFpbbihgq73-FD1JgHARe1vrwJ_0Y3BhhZjJ8UmeLGqyy4C6NQAmaLEg2iK4X-bzItSD-esAhENq-ZmUUKAY74SsGCdPK9srakfVz05rGN0_XKLkkoyW74UzWY89hkYAzrQOw5zGMghVKAioFcpyjX7JVz6fEdL4OWoaTknzhjnQKv1DEq2v8RsZVg3wWuU0t1WB562OQEIaScCVH4knjEtgCB8erZyStk65uwlXK5hQ6rof6Z4-jpd4xp89rAqNcX5OxnXG1SfST50s4C_YddfNe7Y0NQ9_yORz6TChuP3weUXnqlMOWHe4bMSTRLDITfLToWr4KwgajtQ_EmvCrbQWX5BHwSMHOCRKj92eSThzJ2EStpCmV-fihb6onbQk-x3i8pB0J3hkhfRzzsd2vEpy-E4RG9AgKhntN_gwP0Uez_hgEtfv9vipI8qVe-ivu168qU5N8siLollCok_DmIpnjsupxjNlifsv6LhKr97Y7S3TDnpdRL17Mt8lXJpuChunCDC7URHf990u4_j6tuQ9WLGKAq7F8lPoh8HzVdM5ozE-proWaEzFVd035l7q0dQxhQvw0JkhhcRMkjnmIFnTCQ3vAhHc2WCsy-gR5YI472RZoxU6x9q1KOVpTonw6ioUxZoB_QxZGxUT3FPdfMU6pOS0DZ0Ws1qL-49UOSuIleiEAhmX3E_lG_QD5dcxRbCOFHo3-JML3pTrXU49GZi7ZPqzmNcRSK7nxq1751e-YmBt_KYkqLI0sRM0Wwz1X1XTSv7S97iefaAj6xXhnlyc3hi5ofzj8iTGGF-mWYrC-F6GhCizpM91ePu6uugP-FWdtaQ5YXO-9Kq7mFwGB8NE-vftRZBr6p4TbGgXgrZk9rwMpgyC60WACV24UpJhaaBfnPgojE_nuskalMjAy41VA0CyMDCRBJ29MPE9R-dVMNIld9hfBSz2kMCaDXGw83fWPNAcUPQ2fvMBrBhkSLgTRhX7CDElb4foRJS6vTnTgW-es6mk9Ja-3-O013xo09WkqPyYieF1OIWyiALlUVqDtFYdWbUrIHUVV69D03XM3zIgy05HMI5uj46gT8l_X_nDnUI8zolKjB0STnTuzwwK4xvcwl7ank70dIvKatv62MrI-ZEp7QD00ZHeos5fh2X0YxNCsavuKF6UiT_hjWo-v9Sb2qJYKwiv_Bz_pqMqrQyQP-S35FkmWLzfu_ipbNxqE9z_u4WwvPUSdyAdMsJtBc41MJFtYAsBZc5jU0o7Sd2uiVQaUG51Q19jwq6MU68DxcTWukmdB4rQMd4EHYjtNJYr_zGGqzwJAO7gmKeAPxqbwbI5xg_JYGqdVfKBWKdZCCGljYW8DoimGJugt8OJvFFVu3wAOG9KRhaNtdmDnjYd24jxpqWtn5BZSNgwtQP1nh07a7aa-jsJmNpDxu9WH9fax7FXBjz8L9UlG47kBNTpQzKuW_8GRbe2Xvx5jJ0Rh9EFoW1XOiDap3s--MBUDwcRpQvxcU7Ip9gA7JNlsQJoglTvgZiQArlVlbkx7I6UOMHGzJ68UtuFyg3Z6eyAAXTBauozf2VCtbucac_f6kOC80xwZBxfTKG8iXlKOqa3_h_Q66kzPP6h6Ni4-FW-Z5b2aVCUGP_TnG4PkqS-ciRQz2CAdXcHkgy1bXbe-qWXpPBSYs0jnkBygX_v6sa3k8k2wXFenRz0nZ0D684585Axe5Kz5gvW5sR4n2LiN_x95cqDvXCLqzJ-T6kawaRBEoI2Ym3uw7tfOx3o1qyLAvZ9eX4c-dI1kVrC6WzJeeFy2OPOjY=",
"summary": [],
}
],
},
"provider_specific_fields": {},
}
],
"usage": {
"completion_tokens": 5,
"prompt_tokens": 19,
"total_tokens": 24,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"prompt_tokens_details": {
"audio_tokens": 0,
"cached_tokens": 0,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
},
"completion_tokens": 135,
"prompt_tokens": 312,
"total_tokens": 447,
"completion_tokens_details": {"reasoning_tokens": 70},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"system_fingerprint": None,
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
},
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "openai/gpt-5.6-terra"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS, "model": "gpt-5.6-terra"},
mock_provider_response={
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-5.6-terra",
"id": "resp_0b9dd9372c7413ec006ad02386760487d08468a2a84f9e6871",
"created_at": 1792025478,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025479,
"instructions": (
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect."
),
"output": [
{
"id": "rs_0b9dd9372c7413ec006ad023870a4087d0a4a8f5a9ef33dd2e",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COIulgFZHAIST02Ob7jMU14QKmgY_QYY0QhjIokwGaR_TwJrp4Ipb5-_NFswljdp2HFfgxzTV24tE6ueee6YavBUQAU0IW576eke0inwgG9fpAS8jCmhEjrldcu8mjx4tMPnzltz46Mj4z9r-nsH6C4wufPbjV3dpEGOnZ4OfaJwaO_tEFAz_0a7c3PhbkHsIiBkdgN_w88NdR4_hz5A8Sk-n0z7_MN75nKnzkEM0x5xL739fjnbAxEXNMn5Ezw3ctwuwab61YzmLua32kk0BtnHqhMjEm62UOX53zCFeoD1esiY2NhB4Ceq3i88gvLBtWqvo68zprjJhplhaJ6AaOTIAPSRWjrtw0ONDTLcqRb_mwsW7vbym3LUwakUqA5qMGYke9V9XzgQ44Acv9EHgr_6f2gwdVwjeupv9v4Kn6t1omYSi3HrjDl7tVJ-Hxn8TpHxQzK2i22vjHpjldJux4OnKKN-2Dh3KgT5qFa1NfcVSex5pfbxFDjhh12acNLRsPHJ3eRAx308BI2fkG7RdQ5Qb22Ezc8MY0AxERYHxgCxFBXInVHBBxOdciNPogBLKTTQSUFz0utIGEPwTpaNx2Akanb4H0o2sHCLA12Zq0C8h7EUGT9Kd4NrTIq1hAwzCn6cQyAw1SWatwIxaD49wyBq9xgeouNaOPKEkKGQSPHbTKsFuy3qZ8or7WvsOhudVF3RCk8chzm-CF8Dxqc5a3QZzKmMrBsBNILSLx1MQrq4kmUaYwt5V_moG1jT3_c9dTq4YmmhISUHOohjXz6HylzWGXMZXKW2_skr1ypaMtnlRoO-ngjraJisUheMuJQtoubouShhm6UiLDA_352QXxQX8Or0sxqm80Pn52u2k7oG0RSu4ltmERsBayQLnsZTIns6nXnfyTVDJ64vrSiX3UBBzzkJfCWifNb5dBervyf4gzdNhtBivQnR0bhKp8gJ3YSOl0t-SzEiQ4VIL6cu6OvnMtGCQ84s6BDS8-196It4RsP7hNkxL3tVAIwgb9Euncn3tVfRxz4suPS_b-2UhlFb7rxgz0H26DxNtCprPlaawp4pk4puKno1k7G2zx_BWP6vw8mC4E0ws0bUOWl5icgdWVjZvAQn2t76Vxb9DdZaWDDN6WrNGU85DcAgSOl_LwAnwEZ0IfSuZT3Ys7os_HFqJ-Isnrsv1YtcSg1fLL9KooIWZOEI9sH_PKLIBLyZTYSardtyb2izficMFTz_cJS3tHARyY_L1sfphULymlRSBXpI0Evr-d4PW-4dxcYIBMELEklJwgze9wjeFKwHlv1iZjuGlnr6ieoZ9aJXkQuxSQ-uom3DZdAs0hoW5Xgd1h0X9Tnu9bcJKA3KBVzDMPYLHkZYRD5J1nEifcDpXryBFRBFk4yYAOrPYEuwXg__1qtipv7-IoTc3J0pVmid_q6rHFrl0-tRfqM8-sG-C6QJMahzsDccevWyntC2o-8tAsuUuA3gkmrWR3Yepsj8LydSrqGlXYi_o-rE-XwNjIkyS-rCsweT1iBl3JvWX_ZDXEoLFSC50Hevf7Ti2HmbnMFm6HoRz0kIuAC91EvcY3xWXXKOsb-owbUiYhuoOPSo3xtiHxMjLARPwymWN4LkdsiSndglL7lsJgK1fsZR-fF4QI=",
"summary": [],
},
{
"id": "msg_0b9dd9372c7413ec006ad02387358887d091024ccc4d1075e9",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I need `shop/validation.py` next to verify the current handling of zero, "
"negative, and non-integer quantities before reviewing the corresponding "
"tests.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0b9dd9372c7413ec006ad0238795a087d0aa5e2e27ec92e9b8",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_6kurIo7rXnkqfZEy2J7ldPNG",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 87,
"output_tokens_details": {"reasoning_tokens": 17},
"total_tokens": 399,
},
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "openai/gpt-5.6-terra",
"id": "resp_0b9dd9372c7413ec006ad02386760487d08468a2a84f9e6871",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I need `shop/validation.py` next to verify the current handling of zero, "
"negative, and non-integer quantities before reviewing the corresponding "
"tests.",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_6kurIo7rXnkqfZEy2J7ldPNG",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0b9dd9372c7413ec006ad023870a4087d0a4a8f5a9ef33dd2e",
"encrypted_content": "gAAAAABq0COIulgFZHAIST02Ob7jMU14QKmgY_QYY0QhjIokwGaR_TwJrp4Ipb5-_NFswljdp2HFfgxzTV24tE6ueee6YavBUQAU0IW576eke0inwgG9fpAS8jCmhEjrldcu8mjx4tMPnzltz46Mj4z9r-nsH6C4wufPbjV3dpEGOnZ4OfaJwaO_tEFAz_0a7c3PhbkHsIiBkdgN_w88NdR4_hz5A8Sk-n0z7_MN75nKnzkEM0x5xL739fjnbAxEXNMn5Ezw3ctwuwab61YzmLua32kk0BtnHqhMjEm62UOX53zCFeoD1esiY2NhB4Ceq3i88gvLBtWqvo68zprjJhplhaJ6AaOTIAPSRWjrtw0ONDTLcqRb_mwsW7vbym3LUwakUqA5qMGYke9V9XzgQ44Acv9EHgr_6f2gwdVwjeupv9v4Kn6t1omYSi3HrjDl7tVJ-Hxn8TpHxQzK2i22vjHpjldJux4OnKKN-2Dh3KgT5qFa1NfcVSex5pfbxFDjhh12acNLRsPHJ3eRAx308BI2fkG7RdQ5Qb22Ezc8MY0AxERYHxgCxFBXInVHBBxOdciNPogBLKTTQSUFz0utIGEPwTpaNx2Akanb4H0o2sHCLA12Zq0C8h7EUGT9Kd4NrTIq1hAwzCn6cQyAw1SWatwIxaD49wyBq9xgeouNaOPKEkKGQSPHbTKsFuy3qZ8or7WvsOhudVF3RCk8chzm-CF8Dxqc5a3QZzKmMrBsBNILSLx1MQrq4kmUaYwt5V_moG1jT3_c9dTq4YmmhISUHOohjXz6HylzWGXMZXKW2_skr1ypaMtnlRoO-ngjraJisUheMuJQtoubouShhm6UiLDA_352QXxQX8Or0sxqm80Pn52u2k7oG0RSu4ltmERsBayQLnsZTIns6nXnfyTVDJ64vrSiX3UBBzzkJfCWifNb5dBervyf4gzdNhtBivQnR0bhKp8gJ3YSOl0t-SzEiQ4VIL6cu6OvnMtGCQ84s6BDS8-196It4RsP7hNkxL3tVAIwgb9Euncn3tVfRxz4suPS_b-2UhlFb7rxgz0H26DxNtCprPlaawp4pk4puKno1k7G2zx_BWP6vw8mC4E0ws0bUOWl5icgdWVjZvAQn2t76Vxb9DdZaWDDN6WrNGU85DcAgSOl_LwAnwEZ0IfSuZT3Ys7os_HFqJ-Isnrsv1YtcSg1fLL9KooIWZOEI9sH_PKLIBLyZTYSardtyb2izficMFTz_cJS3tHARyY_L1sfphULymlRSBXpI0Evr-d4PW-4dxcYIBMELEklJwgze9wjeFKwHlv1iZjuGlnr6ieoZ9aJXkQuxSQ-uom3DZdAs0hoW5Xgd1h0X9Tnu9bcJKA3KBVzDMPYLHkZYRD5J1nEifcDpXryBFRBFk4yYAOrPYEuwXg__1qtipv7-IoTc3J0pVmid_q6rHFrl0-tRfqM8-sG-C6QJMahzsDccevWyntC2o-8tAsuUuA3gkmrWR3Yepsj8LydSrqGlXYi_o-rE-XwNjIkyS-rCsweT1iBl3JvWX_ZDXEoLFSC50Hevf7Ti2HmbnMFm6HoRz0kIuAC91EvcY3xWXXKOsb-owbUiYhuoOPSo3xtiHxMjLARPwymWN4LkdsiSndglL7lsJgK1fsZR-fF4QI=",
"summary": [],
}
],
},
}
],
"usage": {
"completion_tokens": 87,
"prompt_tokens": 312,
"total_tokens": 399,
"completion_tokens_details": {"reasoning_tokens": 17},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"access_programs": {"cyber": "daybreak_blue"},
"billing": {"payer": "developer"},
"frequency_penalty": 0.0,
"presence_penalty": 0.0,
"service_tier": "default",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
},
)

197
tests/integration/translation/chat_completions/bases/openai_responses.py
View file

@ -2,6 +2,11 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_REQUEST, CHAT_COMPLETIONS_RESPONSE
from integration.translation.templates.openai import (
OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS,
OPENAI_RESPONSES_RESPONSE,
)
GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -121,98 +126,140 @@ GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/chat/completions",
litellm_request={
"model": "openai/responses/gpt-6.1-sol",
"max_tokens": 64,
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
"cache": {"no-cache": True},
},
litellm_request={**CHAT_COMPLETIONS_REQUEST, "model": "openai/responses/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={"authorization": "Bearer synthetic-openai-key", "content-type": "application/json"},
expected_provider_request={
"model": "gpt-6.1-sol",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"stream": False,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "resp_0ff994dd79332d97006ac3f04a429487d09618de316e259d7f",
"object": "response",
"created_at": 1791225930,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225933,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"moderation": None,
"id": "resp_0e8134ce088f63e7006ad023a2e5b887d0a0f422419e0bfbe7",
"created_at": 1792025506,
"completed_at": 1792025510,
"instructions": (
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect."
),
"output": [
{
"id": "msg_0ff994dd79332d97006ac3f04cfcf487d088bec15ca90ae36b",
"id": "rs_0e8134ce088f63e7006ad023a3ff5887d0801528ceb0190f4b",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COmpSSf5bN4H0xC2pbhfp_niGPAm58n4-JyZsHy0ytyhg6KzzTZiR0cjuNAHvZR_w8oavaY1zzH-MkWItVhAx-PQJQ560Da0Dwqi_wwJ0831R8W6lxyeFxgBZXpZ4_TsbT1qwt7IwVC6fJE4gDeFGiuo4H7plTfbE7C2DaO_0fkI5Zt_iRZLA3VOJPFnzegipK4A5AxckZNVZLI705xzMfi7KU6J886jCmsqCxjrQKLwP4fB0jQoRidBCensrctV2C7imXgTAlTwOysSd8gf7Yhu7A9qD1rUj_jvLGJCiqBCe9Cyv9I7cX82VewV4029mGOngvQOUAgVbqT_i9LkQ3HfBXu4SYTK_LXU2P0lw_P69qKYGTZfdwxqui8VVtgJI7kDrZY-l7DvqaIncKJ-LgDJBvxaYDMM7H1Co68Yd64RM3U1v4kTezKN_MBg-1Ku0m1e3Zi7YZDHOHkFDDGFXzXCpbGkgDJCHsG7i-UTE1uAjkgdP9h0MUFosMYB8pl2NxtN8NnEHsBfyYBV56Sms8ObilQaK2eEWvnDH_wkGLt2RAGOJwfovSEwKnWgOemEZtA_IYbxhRNupRJkPy0oJ4xPdAxIICncSkwaF_NMYeIetF-0tvqK2mqWZVnI13w_CPUW0WI0nlfSnlqO-7gD4Xh80-cvFAqr44X_yaRODPOOc6aWoXb_23A2AoFW6vEKufFf3zni2JEHiCREgvUAp8p931WYo7H_lDpOqIHGiQVjvRfUN9pRPnpPbF6NwCUNalgQPt4UZal_ubh3kdF1NRqKuTQMcalPfuw7Zdc7-ZFTV3JdUApBwsF2jGFXzAfmwHytnOohHOAm79n_7ORaJV3ecKjyg0t-N777eu-7LJX79tvy1tNXR-0DsodobU-mHuyxqC4Qhmqk8jC1IeNG7du1IUwpFJnOyM4O1D6xUYGslBWXsIa_exQpTkxH0PYSYeCGA9GCeWsrn8gSkOgwBmtsC56Bow8VldAr_t_AS5UIrSUsNvn1SF-nZJKbe1mvL-egWOuQq8dZb3wEF7vVxqgn4_f54pGXyDeEdxPdxAKhqT672MKb3l_K11Yn10kbhNr1XqX-m323zLcNizjPlH8rJGUWht7RGQd6VOxEjmhKC_ZWFsu7wQgqsGX0BQ2e-6hZE2Kq_9u_MfSieYJyt9jb6XXrqefSP2tyWsrrS6HrBBrSkh2d5PfiP4MQ2gTesP9tj-yVlq4JU3FZMgqS5W7m2BmhD8gGonaLSK5zJboTYjpZHoS0swfxX2_BJDiARNrPFZ58t6sSXDZauTZq8CbdLdXUBA6RaO1kp-yscPIuB2DHjPjPUVrRYbNWSPIcjqHDYY11UHPs7lWL8U5j-j3EfYwiwQ85YnVfoB7jzJFeiywAUvbum20MJXBOE2wrvrR6zXJAGYlEwxKbl_ibZULRRuJ-VSGeijiDNtavD5v5-AAmow5yPuuVUH9_kx7Un8ZbbESZH1rptCToDmxeRrIa51Xw8fIbONz1fVNzljCUvqvsoyjPQAlaZy_YfLIOYD5MVhVX8XiR8mIeSna4ELdWXu8EEmPWyl676GbSZvMzQmBVqDFeELEusHm_UNX3oI5oOMJQ8ZA9p-JyJlx8LWDe3wqTaKKzoajxn2Wz6qvjKFStkGrk0voFzEPEnBbIAIPkh7Uv2ORupzlQeF6Hor11DxlDAIaUQf1344U37C-a1ODbqL8tg7HOm1WSKdwWeKG2-SYk9K8yB1hEZuqmxHquiXybUU-EYrQFGv88d-K0ou-wAjolMdXlIUaT5-OmqA8HCprI4Nr1BdxQYLLwlNyxm5Y610a1Bd9clo8YbW-I_zSNVm74nF1_HzKP3Ym9H3_f1ZWj55BOAw9i1jmk6kb7P2SAomQ9WVCHvhbyPUhrMMlDxc5VpQOMlFRIZjCEb4wirnD4oonK5mt_TY1l_XMc7DAFb91wpdF3dB6Nh8W2_YYC8_vHfvvSq5WtVKBVIBzZM7l188EX3zHUoe4a9pbQj2Yj2-fAF4qnae4DZ1IwYvoUrln3YETLC37Qb7c3cwM_-i9YLiB_F-qA-pVnmwH8Ah2a3cOF-sl50BE7ey_rHw0fhnflc2bicoLMA82gXdE3iuAsPX-sJvouXgLB1KYmFZt_8Hm3QlrT2c8mj_Jt10YdPC_haBCvzOQDvi5kfPM2upPrvgm7bPEgyjLZECEaQj7bjgAsZc7PqnNp0u41Quq2WxUbjMrE6BPjcrhF5Llx6PQjrz2d5_023M1xBMGxKNXaLNmyi91YpvC0Sqd9qUKndUQ6fPA4z03_FP7-UnzYPuJQaBX662f1Vd-sSUvvM4zdPw6YX-muGqHF5qld2He6eMaUUXhjDuwvy2LW5WRQfSbWJ89XsUYqDwDM0j8TEexma6UZ07uNV_xjse6P8JfL-L8BDiHkR7ZNRMDSYqsHQjqwoYZNUs25XwWPr7kjn-43H0mW_dXPcManZ6qBlKKETmdtr8CZrtNxZ1_TnHUeNkATzhmtzyLQRmouxUq6tbPMumlcXcwhvDBSKSR33a4LZG1kknf_YlTDLA4x7sHImDRMYgM9d6SYxBuTSq1OfTtSv7i4Wz5_Pef3iNFI8JH6Q6b24vED1lnWvVEImDKReDYdDLoNJr2BbSt6iZ0hsGSQ5EMsE3jlizNIBwdqI5z2MKTCYWAXSbxXe62zgaklRD6IoCER9h4SqjsnOh9esKu1bg-AkSa04Le9PP4i2whspq6Xa7f4DJpRYb-hEdY",
"summary": [],
},
{
"id": "msg_0e8134ce088f63e7006ad023a5aa0c87d0aee7de2e31f58a5c",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to see how it handles zero, negative "
"values, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_0e8134ce088f63e7006ad023a615bc87d0b7aaafc731d1f086",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_sPhtuzlfkfNe16kBteKPS72V",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 166,
"output_tokens_details": {"reasoning_tokens": 100},
"total_tokens": 478,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
"id": "resp_0ff994dd79332d97006ac3f04a429487d09618de316e259d7f",
"created": ANY,
**CHAT_COMPLETIONS_RESPONSE,
"model": "openai/responses/gpt-6.1-sol",
"object": "chat.completion",
"choices": [{"finish_reason": "stop", "index": 0, "message": {"content": "Hello!", "role": "assistant"}}],
"id": "resp_0e8134ce088f63e7006ad023a2e5b887d0a0f422419e0bfbe7",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I’ll read `shop/validation.py` first to see how it handles zero, "
"negative values, and non-integer quantities.",
"role": "assistant",
"tool_calls": [
{
"index": 0,
"function": {
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"name": "read_file",
},
"id": "call_sPhtuzlfkfNe16kBteKPS72V",
"type": "function",
}
],
"reasoning_items": [
{
"type": "reasoning",
"id": "rs_0e8134ce088f63e7006ad023a3ff5887d0801528ceb0190f4b",
"encrypted_content": "gAAAAABq0COmpSSf5bN4H0xC2pbhfp_niGPAm58n4-JyZsHy0ytyhg6KzzTZiR0cjuNAHvZR_w8oavaY1zzH-MkWItVhAx-PQJQ560Da0Dwqi_wwJ0831R8W6lxyeFxgBZXpZ4_TsbT1qwt7IwVC6fJE4gDeFGiuo4H7plTfbE7C2DaO_0fkI5Zt_iRZLA3VOJPFnzegipK4A5AxckZNVZLI705xzMfi7KU6J886jCmsqCxjrQKLwP4fB0jQoRidBCensrctV2C7imXgTAlTwOysSd8gf7Yhu7A9qD1rUj_jvLGJCiqBCe9Cyv9I7cX82VewV4029mGOngvQOUAgVbqT_i9LkQ3HfBXu4SYTK_LXU2P0lw_P69qKYGTZfdwxqui8VVtgJI7kDrZY-l7DvqaIncKJ-LgDJBvxaYDMM7H1Co68Yd64RM3U1v4kTezKN_MBg-1Ku0m1e3Zi7YZDHOHkFDDGFXzXCpbGkgDJCHsG7i-UTE1uAjkgdP9h0MUFosMYB8pl2NxtN8NnEHsBfyYBV56Sms8ObilQaK2eEWvnDH_wkGLt2RAGOJwfovSEwKnWgOemEZtA_IYbxhRNupRJkPy0oJ4xPdAxIICncSkwaF_NMYeIetF-0tvqK2mqWZVnI13w_CPUW0WI0nlfSnlqO-7gD4Xh80-cvFAqr44X_yaRODPOOc6aWoXb_23A2AoFW6vEKufFf3zni2JEHiCREgvUAp8p931WYo7H_lDpOqIHGiQVjvRfUN9pRPnpPbF6NwCUNalgQPt4UZal_ubh3kdF1NRqKuTQMcalPfuw7Zdc7-ZFTV3JdUApBwsF2jGFXzAfmwHytnOohHOAm79n_7ORaJV3ecKjyg0t-N777eu-7LJX79tvy1tNXR-0DsodobU-mHuyxqC4Qhmqk8jC1IeNG7du1IUwpFJnOyM4O1D6xUYGslBWXsIa_exQpTkxH0PYSYeCGA9GCeWsrn8gSkOgwBmtsC56Bow8VldAr_t_AS5UIrSUsNvn1SF-nZJKbe1mvL-egWOuQq8dZb3wEF7vVxqgn4_f54pGXyDeEdxPdxAKhqT672MKb3l_K11Yn10kbhNr1XqX-m323zLcNizjPlH8rJGUWht7RGQd6VOxEjmhKC_ZWFsu7wQgqsGX0BQ2e-6hZE2Kq_9u_MfSieYJyt9jb6XXrqefSP2tyWsrrS6HrBBrSkh2d5PfiP4MQ2gTesP9tj-yVlq4JU3FZMgqS5W7m2BmhD8gGonaLSK5zJboTYjpZHoS0swfxX2_BJDiARNrPFZ58t6sSXDZauTZq8CbdLdXUBA6RaO1kp-yscPIuB2DHjPjPUVrRYbNWSPIcjqHDYY11UHPs7lWL8U5j-j3EfYwiwQ85YnVfoB7jzJFeiywAUvbum20MJXBOE2wrvrR6zXJAGYlEwxKbl_ibZULRRuJ-VSGeijiDNtavD5v5-AAmow5yPuuVUH9_kx7Un8ZbbESZH1rptCToDmxeRrIa51Xw8fIbONz1fVNzljCUvqvsoyjPQAlaZy_YfLIOYD5MVhVX8XiR8mIeSna4ELdWXu8EEmPWyl676GbSZvMzQmBVqDFeELEusHm_UNX3oI5oOMJQ8ZA9p-JyJlx8LWDe3wqTaKKzoajxn2Wz6qvjKFStkGrk0voFzEPEnBbIAIPkh7Uv2ORupzlQeF6Hor11DxlDAIaUQf1344U37C-a1ODbqL8tg7HOm1WSKdwWeKG2-SYk9K8yB1hEZuqmxHquiXybUU-EYrQFGv88d-K0ou-wAjolMdXlIUaT5-OmqA8HCprI4Nr1BdxQYLLwlNyxm5Y610a1Bd9clo8YbW-I_zSNVm74nF1_HzKP3Ym9H3_f1ZWj55BOAw9i1jmk6kb7P2SAomQ9WVCHvhbyPUhrMMlDxc5VpQOMlFRIZjCEb4wirnD4oonK5mt_TY1l_XMc7DAFb91wpdF3dB6Nh8W2_YYC8_vHfvvSq5WtVKBVIBzZM7l188EX3zHUoe4a9pbQj2Yj2-fAF4qnae4DZ1IwYvoUrln3YETLC37Qb7c3cwM_-i9YLiB_F-qA-pVnmwH8Ah2a3cOF-sl50BE7ey_rHw0fhnflc2bicoLMA82gXdE3iuAsPX-sJvouXgLB1KYmFZt_8Hm3QlrT2c8mj_Jt10YdPC_haBCvzOQDvi5kfPM2upPrvgm7bPEgyjLZECEaQj7bjgAsZc7PqnNp0u41Quq2WxUbjMrE6BPjcrhF5Llx6PQjrz2d5_023M1xBMGxKNXaLNmyi91YpvC0Sqd9qUKndUQ6fPA4z03_FP7-UnzYPuJQaBX662f1Vd-sSUvvM4zdPw6YX-muGqHF5qld2He6eMaUUXhjDuwvy2LW5WRQfSbWJ89XsUYqDwDM0j8TEexma6UZ07uNV_xjse6P8JfL-L8BDiHkR7ZNRMDSYqsHQjqwoYZNUs25XwWPr7kjn-43H0mW_dXPcManZ6qBlKKETmdtr8CZrtNxZ1_TnHUeNkATzhmtzyLQRmouxUq6tbPMumlcXcwhvDBSKSR33a4LZG1kknf_YlTDLA4x7sHImDRMYgM9d6SYxBuTSq1OfTtSv7i4Wz5_Pef3iNFI8JH6Q6b24vED1lnWvVEImDKReDYdDLoNJr2BbSt6iZ0hsGSQ5EMsE3jlizNIBwdqI5z2MKTCYWAXSbxXe62zgaklRD6IoCER9h4SqjsnOh9esKu1bg-AkSa04Le9PP4i2whspq6Xa7f4DJpRYb-hEdY",
"summary": [],
}
],
},
}
],
"usage": {
"completion_tokens": 6,
"prompt_tokens": 19,
"total_tokens": 25,
"completion_tokens_details": {"reasoning_tokens": 0},
"completion_tokens": 166,
"prompt_tokens": 312,
"total_tokens": 478,
"completion_tokens_details": {"reasoning_tokens": 100},
"prompt_tokens_details": {"cached_tokens": 0, "cache_write_tokens": 0, "cache_creation_tokens": 0},
},
"billing": {"payer": "developer"},

1375
tests/integration/translation/chat_completions/bases/vertex_ai.py
View file

File diff suppressed because it is too large Load diff

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_anthropic.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_azure.py
View file

@ -6,6 +6,7 @@ from integration.translation.chat_completions.bases.azure import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_azure_ai.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_bedrock_converse.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_bedrock_invoke.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

4
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_bedrock_mantle.py
View file

@ -9,7 +9,9 @@ from integration.translation.chat_completions.bases.bedrock_mantle import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -26,6 +28,8 @@ from integration.translation.runner import assert_translation
GPT_5_6_LUNA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

8
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_gemini.py
View file

@ -6,13 +6,19 @@ from integration.translation.chat_completions.bases.gemini import (
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@pytest.mark.parametrize(
"case",
[GEMINI_3_5_FLASH_TEST_CASE, GEMINI_3_8_FLASH_TEST_CASE, GEMINI_3_1_PRO_PREVIEW_TEST_CASE],
[
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)
def test_chat_completions_basic_gemini(case: TranslationTestCase, gateway: Gateway, provider: SharedProvider) -> None:

2
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_openai.py
View file

@ -6,6 +6,7 @@ from integration.translation.chat_completions.bases.openai import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

11
tests/integration/translation/chat_completions/basic/test_chat_completions_basic_vertex_ai.py
View file

@ -1,19 +1,19 @@
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.bases.vertex_ai import (
CLAUDE_FABLE_5_1_TEST_CASE,
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -31,6 +31,7 @@ from integration.translation.runner import assert_translation
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)

215
tests/integration/translation/chat_completions/prompt_caching/test_chat_completions_prompt_caching_azure_ai.py Normal file
View file

@ -0,0 +1,215 @@
from dataclasses import replace
from typing import Final
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.chat_completions.bases.azure_ai import (
CLAUDE_FABLE_5_1_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
)
from integration.translation.runner import assert_translation
CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0: Final = (
"CAQS3gYKEAgSGAI4AUIIdGhpbmtpbmcSDEoUbRA8/sNqRoVoJRoMjpP0glsrmS7QMeraIjDxIxhKjyeY5Y65IZo5YTWEVqymcjH8k7a0mAjW"
"bQoNTG9gw0R+WqIckDwWmnUrlFgq+wUl+/iw8hZ5IAryY71AHQuvdYaGuEgmN8jqzGujRvAeW4tw3zLG0td8x1lyoJk02iTU5aQV0wO5uO87"
"wJqAEJ6bbheWT9m9l+M3tW9DOFsQMHYpj95wz6crrlZxzhBgMN7dZMzy+l+ATwMSxpQHX4FXRNAsz63J2tOADTeHSFXeP6Evn5abAhSiznHf"
"ezSB2bRv6eBRVi7hDR2MgVJ1CEo5b2YtGroJPzVJxZRZpyHKg04dRkAUn0uQb+N5FxJ5I4v2phqqMLqpvDR8sU14Q91v7SstrT7NyRlAFhv9"
"pzocddLhJkyHJpFctQr0D1k1oiyPCWpWdRVMEPrAybvkh6vVij2l6CP/kBfD8JUUulRCPO+xoyfAglQJsA4zc1gRCggBKbim+26oazBYat8K"
"+1RO5iRzQe/gvs8DwQSPML/YWqzGK/qd1G7yJujaMnkBt9Jew44DQ/eUgKP5030zKd/ft+jmj8uu2PNP6zZrvZA5grdTSY6pSnu4X++1wE5r"
"NExLgC/TJgDejVzCazAP9MsDnXz7nv+6yVytEsL//xOVq7s5nF0IYpNdawt1bAzNaHAnIMH8meeksDnnRJuBKt4mhg0nPgueOXgo7RLEUHWm"
"MYakXV5wFNLY1oAUV4RpQJ+zF+/mJ/f7AHmghcxoPnPPPlISar3f9w00CQRVQjJDkm8ozxWyLN6AXhDQfQEDvYWPl33VaOcv7TpLAJ7HkWyk"
"AJA8oB3LflgBJCSOXL67LGiGeSw8eR0bp89+Yux2C9MzORRvE8asjfl1W6NFWJzsvpNYcRYm0QREuNDRabg+mkcfwpDJyeaopSsNZLOMS7zq"
"mwFMPrmW9CY+MJTxG0pQX1G8Ln59hhPu242z8l6wP1eqBbRzV54RMjE0wBGV7vfoPkqBzxGAj0Cr+/BeNbM4ne9k4pL9s5JYRsWhhhF1mkN7"
"pFlOxz8cswlKkAaq/KnCWp2ptVgzxJazuokShk4hnnbwcdxaDVX2NynBGnmbcpfG8zso2GC52Ke+GAE="
)
CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_HAIKU_5_5_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.mock_provider_response,
"id": "msg_011Cg37bzPpF6nmTd4cxR6zH",
"content": [
{
"type": "thinking",
"thinking": "I'll start by reading shop/validation.py to understand its contents, focusing on the "
"first portion of the file before deciding if more context is needed.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around the `validate_quantity` definition at line 18 "
"to see how it treats zero, negative, and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_01L2rdexX7pthHtxd9WR8UbE",
"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": 0,
"cache_read_input_tokens": 876,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 252,
"output_tokens_details": {"thinking_tokens": 103},
"service_tier": "standard",
"inference_geo": "global",
},
},
expected_litellm_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.expected_litellm_response,
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read `shop/validation.py` around the `validate_quantity` definition at line 18 "
"to see how it treats zero, negative, and non-integer values.",
"role": "assistant",
"tool_calls": [
{
"index": 2,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"name": "read_file",
},
"id": "toolu_01L2rdexX7pthHtxd9WR8UbE",
"type": "function",
},
],
"reasoning_content": "I'll start by reading shop/validation.py to understand its contents, focusing on the "
"first portion of the file before deciding if more context is needed.\n\n",
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll start by reading shop/validation.py to understand its contents, focusing on the "
"first portion of the file before deciding if more context is needed.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
],
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll start by reading shop/validation.py to understand its contents, focusing on the "
"first portion of the file before deciding if more context is needed.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
],
},
},
},
],
"usage": {
"completion_tokens": 252,
"prompt_tokens": 880,
"total_tokens": 1132,
"completion_tokens_details": {"reasoning_tokens": 103, "text_tokens": 149},
"prompt_tokens_details": {
"cached_tokens": 876,
"text_tokens": 4,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 876,
"inference_geo": "global",
"service_tier": "standard",
},
},
)
CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_FABLE_5_1_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_FABLE_5_1_TEST_CASE.mock_provider_response,
"id": "msg_011Cg37V6cvTmK19kQhSJPvQ",
"content": [
{
"type": "text",
"text": "I'll read the validation file to see how zero and negative quantities are handled.",
},
{
"type": "tool_use",
"id": "toolu_01Gk8RXusGMKa2tw97hQjuzk",
"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": 0,
"cache_read_input_tokens": 876,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 123,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
},
expected_litellm_response={
**CLAUDE_FABLE_5_1_TEST_CASE.expected_litellm_response,
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": "I'll read the validation file to see how zero and negative quantities are handled.",
"role": "assistant",
"tool_calls": [
{
"index": 1,
"caller": {"type": "direct"},
"function": {
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"name": "read_file",
},
"id": "toolu_01Gk8RXusGMKa2tw97hQjuzk",
"type": "function",
},
],
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
},
],
"usage": {
"completion_tokens": 123,
"prompt_tokens": 880,
"total_tokens": 1003,
"completion_tokens_details": {"reasoning_tokens": 0, "text_tokens": 123},
"prompt_tokens_details": {
"cached_tokens": 876,
"text_tokens": 4,
"cache_write_tokens": 0,
"cache_creation_tokens": 0,
"cache_creation_token_details": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
},
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 876,
"inference_geo": "not_available",
"service_tier": "standard",
},
},
)
@pytest.mark.parametrize(
"case",
[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE],
ids=[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE.id, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE.id],
)
def test_chat_completions_prompt_cache_hit_azure_ai(
case: TranslationTestCase, gateway: Gateway, provider: SharedProvider
) -> None:
assert_translation(case, gateway, provider)

225
tests/integration/translation/chat_completions/sampling/test_chat_completions_sampling_gemini.py
View file

@ -9,7 +9,11 @@ from integration.translation.chat_completions.bases.gemini import GEMINI_3_8_FLA
from integration.translation.chat_completions.bases.vertex_ai import (
GEMINI_3_8_FLASH_TEST_CASE as VERTEX_AI_GEMINI_3_8_FLASH_TEST_CASE,
)
from integration.translation.chat_completions.templates import CHAT_COMPLETIONS_RESPONSE
from integration.translation.runner import assert_translation
from integration.translation.templates.vertex_ai import (
VERTEX_AI_GEMINI_GENERATE_CONTENT_RESPONSE,
)
GEMINI_GENERATION_CONFIG: Final = object_value(GEMINI_3_8_FLASH_TEST_CASE.expected_provider_request["generationConfig"])
VERTEX_AI_GENERATION_CONFIG: Final = object_value(
@ -49,6 +53,29 @@ GEMINI_3_8_FLASH_REASONING_EFFORT_TEST_CASE: Final = replace(
},
)
VERTEX_AI_GEMINI_3_8_FLASH_TEMPERATURE_THOUGHT_SIGNATURE_0: Final = (
"AY89a18+3vC8Y6wtLQ8YLNoWj0pZ1qcMTAdhuIp6v+o7VjO8nN81l72KF3fiSKtgKQYvOKc4hz38BNeldTuj8NebwQ7BneePvMzc"
"hDx/5j5DXPVIIW7bRE2vYMhffaNpyjdltlQRDAxhiqjbSHIIGZQdxxAE7GfdGxlhstemN91VzQR4KnPKk6MXh0at/4JacXcOFRRX"
"DnYmUqj1a1tSIoSjeTsHMvSj5OpJyxxa8Fafd/yqwL8g4scNZgGzckn4O5quaQmJT9VPtoAsmh8qgXUr/qzNSZoFGzRN6m7OzSuT"
"yQ246hxKwp0+ZB9P+Nn5fvG96JVXsRq7dF00HBAbhebjUfbNTmIQauZHGSGbF2e+ck0aG5Lf8se2qRu6NCqiF+EnTFMUg7g+1cN1"
"nIXLw7X6cAPPrpXvVdkfAoHksgSFWY5uUYwW9yDTZYwOWqF6bxDapPFU5HmJj/Bf5YuVH7VhGB7fyO8SVW6AUe0/S/o0/e//wn6A"
"aFomUST2wXw0hsi/OSZLEhRAi16AeUI0Y4SenblpEYtDAyhzFi77mqsceuF7QIq672m5yWq2qoGhPh7S+5lMEvuD8YLITzrC81Xc"
"b4HN3rxOvi6skmP4WJqZO8zPIw65WQUhRdhadhxM81HE+3InBToo1IhAF+11qt6hK0EuUf1guaGrUEDZRPAgomcOLBSdK6gQ9pn5"
"z3SiRPpw9SV4LWMqBjulGRD6K8u7XHXLPAiGZTF1cr/N2sEQuyri57XytugNISVcxh0q/Lvz0v0DyUAZM8H2ymbusxnKdIHanI9Z"
"US/XIXdia3PwqiOCgXDQaceOmotUnl8i0IXvSKwMjv3wB7UaC4YKyDurZ+gJJOzbjVjZ/mEf9h4JW1ZetNWVtQl2s+oZXCHOtVJD"
"2qLDyuMPO7EuafP8w7mbpKBTmw4ZAyCfrTL73FnEYhp6M3IEG+c4fdUCHMvT6ecG42DLKhdmWfCqzTdXmXFLj/bePo7YzfYpLOLl"
"hEzVdO5ojXPd6squqM+YHQS640UkdQ4v20UQ9ghFRkW1xUl7uPQkIAI0KWiDmaoi0YGFBxWpTs1U+wN2K6hfqgtJy80rl5ceUT7f"
"6B3MnwiIoAjzVc3n3TH6GodPIO08vrhrf4oz+G3OkdCaMHXURfzYkhji50/ThfAxgD7XDuzUYlUWGotbx0FiYEDBbi2b7t7L/w3f"
"P3nXYoSgaaHumXEnOAtugy6immasBFawtZq+GrOIYHJbH2tZhMpUysSTSnGF3BmqczIctDCwC82AbXU5sKEKFShEGnJSw9B0OlWu"
"Pa6kC/Yfapk6NzDyNB2ttsLhy0hCkT0BmgDn2P4h5T4PCVgLWUbA7LGQoYO5zbsUFBwtPUsVFK0yLyf/Gg9h4ebosT6NVh7AkzS2"
"riaNfm//lGUKK/8YDY49PAu0jpHp6JoXYg/z1+BjPvITdIQgf/8a0X36uqO+Yp2HZPzZzl/Ed8sC3ZadKxulNV9kkXN2Gc3v/VyB"
"ruICqdhHSXJkusQJw+vtClqbP2uT18wQN4SRLjFTC3/ZruElXJFipevCQcC8KNVkXW39qZNWJGmKAR15mprXot6VKXkRHfyQJJz0"
"lAMTaACA5LJoA1dDn7+UaikqUsfrlLE6ObbCasA5/wIp5zFsGvslVq/vJqGWk2mdXbas2fpWTSUECEB3gGoIFo9rmHTURX4cAALa"
"oZnjSkaKy1IdC3XDQsqT2vmAX3XjvaLhkCwWg56pst5LvS0AlcRGo49QHATNsY4h0SFkUmMyAGgS7+Pa2VwmCgWUoFFHRbO8ryoy"
"W57qONicyCxA2/OL28OrKGC/e25UsXwKBAXx+9uamcdxFvOQr9WqEJK1g4Q="
)
VERTEX_AI_GEMINI_3_8_FLASH_TEMPERATURE_TEST_CASE: Final = replace(
VERTEX_AI_GEMINI_3_8_FLASH_TEST_CASE,
scenario="temperature",
@ -57,6 +84,204 @@ VERTEX_AI_GEMINI_3_8_FLASH_TEMPERATURE_TEST_CASE: Final = replace(
**VERTEX_AI_GEMINI_3_8_FLASH_TEST_CASE.expected_provider_request,
"generationConfig": {**VERTEX_AI_GENERATION_CONFIG, "temperature": 0.4},
},
mock_provider_response={
**VERTEX_AI_GEMINI_GENERATE_CONTENT_RESPONSE,
"candidates": [
{
"content": {
"role": "model",
"parts": [
{
"text": (
"**My Thought Process on Handling Quantity Validation**\n\nAlright, to properly address the handling "
"of zero, negative, and potentially non-integer quantities, my immediate next step needs to be "
"understanding the existing validation logic. This is crucial before I can even begin to think about "
'suggesting any fixes or further code. My protocol dictates that I must "read the relevant files '
"before suggesting a fix,\" and that's exactly what I'm prioritizing.\n\nTherefore, I need to examine "
"the `shop/validation.py` file. This is where I anticipate finding the rules and checks that govern "
"how different types of quantities are processed and validated. My plan is to read a reasonable "
"initial segment of this file, say lines 1 through 50, to get a solid grasp of the current "
"implementation. After that, I'll be able to determine precisely *which* other files, if any, I'll "
"need to investigate next, keeping in mind the specific constraints of zero, negative, and "
'non-integer values.\n\nTo do this, I will now use the `read_file` tool:\n\n```json\n{\n "tool_code": '
"\"print(read_file(path='shop/validation.py', start_line=1, end_line=50))\"\n}\n```\n\n"
),
"thought": True,
},
{
"text": (
"To examine how zero, negative, and non-integer quantities are handled, I need to inspect "
"`shop/validation.py` next."
),
},
{
"functionCall": {
"name": "read_file",
"args": {"start_line": 1, "end_line": 50, "path": "shop/validation.py"},
"id": "call_1464376",
},
"thoughtSignature": VERTEX_AI_GEMINI_3_8_FLASH_TEMPERATURE_THOUGHT_SIGNATURE_0,
},
],
},
"finishReason": "STOP",
},
],
"usageMetadata": {
"promptTokenCount": 246,
"candidatesTokenCount": 61,
"totalTokenCount": 646,
"trafficType": "ON_DEMAND",
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 246}],
"candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 61}],
"thoughtsTokenCount": 339,
},
"modelVersion": "gemini-3.8-flash",
"createTime": "2026-10-15T01:22:48.202504Z",
"responseId": "6CrQaoiuDNKZq8YPjZCokAw",
},
expected_litellm_response={
**CHAT_COMPLETIONS_RESPONSE,
"model": "vertex_ai/gemini-3.8-flash",
"choices": [
{
"finish_reason": "tool_calls",
"index": 0,
"message": {
"content": (
"To examine how zero, negative, and non-integer quantities are handled, I need to inspect "
"`shop/validation.py` next."
),
"role": "assistant",
"tool_calls": [
{
"index": 0,
"provider_specific_fields": {
"thought_signature": (
"AY89a18+3vC8Y6wtLQ8YLNoWj0pZ1qcMTAdhuIp6v+o7VjO8nN81l72KF3fiSKtgKQYvOKc4hz38BNeldTuj8NebwQ7BneePvMzc"
"hDx/5j5DXPVIIW7bRE2vYMhffaNpyjdltlQRDAxhiqjbSHIIGZQdxxAE7GfdGxlhstemN91VzQR4KnPKk6MXh0at/4JacXcOFRRX"
"DnYmUqj1a1tSIoSjeTsHMvSj5OpJyxxa8Fafd/yqwL8g4scNZgGzckn4O5quaQmJT9VPtoAsmh8qgXUr/qzNSZoFGzRN6m7OzSuT"
"yQ246hxKwp0+ZB9P+Nn5fvG96JVXsRq7dF00HBAbhebjUfbNTmIQauZHGSGbF2e+ck0aG5Lf8se2qRu6NCqiF+EnTFMUg7g+1cN1"
"nIXLw7X6cAPPrpXvVdkfAoHksgSFWY5uUYwW9yDTZYwOWqF6bxDapPFU5HmJj/Bf5YuVH7VhGB7fyO8SVW6AUe0/S/o0/e//wn6A"
"aFomUST2wXw0hsi/OSZLEhRAi16AeUI0Y4SenblpEYtDAyhzFi77mqsceuF7QIq672m5yWq2qoGhPh7S+5lMEvuD8YLITzrC81Xc"
"b4HN3rxOvi6skmP4WJqZO8zPIw65WQUhRdhadhxM81HE+3InBToo1IhAF+11qt6hK0EuUf1guaGrUEDZRPAgomcOLBSdK6gQ9pn5"
"z3SiRPpw9SV4LWMqBjulGRD6K8u7XHXLPAiGZTF1cr/N2sEQuyri57XytugNISVcxh0q/Lvz0v0DyUAZM8H2ymbusxnKdIHanI9Z"
"US/XIXdia3PwqiOCgXDQaceOmotUnl8i0IXvSKwMjv3wB7UaC4YKyDurZ+gJJOzbjVjZ/mEf9h4JW1ZetNWVtQl2s+oZXCHOtVJD"
"2qLDyuMPO7EuafP8w7mbpKBTmw4ZAyCfrTL73FnEYhp6M3IEG+c4fdUCHMvT6ecG42DLKhdmWfCqzTdXmXFLj/bePo7YzfYpLOLl"
"hEzVdO5ojXPd6squqM+YHQS640UkdQ4v20UQ9ghFRkW1xUl7uPQkIAI0KWiDmaoi0YGFBxWpTs1U+wN2K6hfqgtJy80rl5ceUT7f"
"6B3MnwiIoAjzVc3n3TH6GodPIO08vrhrf4oz+G3OkdCaMHXURfzYkhji50/ThfAxgD7XDuzUYlUWGotbx0FiYEDBbi2b7t7L/w3f"
"P3nXYoSgaaHumXEnOAtugy6immasBFawtZq+GrOIYHJbH2tZhMpUysSTSnGF3BmqczIctDCwC82AbXU5sKEKFShEGnJSw9B0OlWu"
"Pa6kC/Yfapk6NzDyNB2ttsLhy0hCkT0BmgDn2P4h5T4PCVgLWUbA7LGQoYO5zbsUFBwtPUsVFK0yLyf/Gg9h4ebosT6NVh7AkzS2"
"riaNfm//lGUKK/8YDY49PAu0jpHp6JoXYg/z1+BjPvITdIQgf/8a0X36uqO+Yp2HZPzZzl/Ed8sC3ZadKxulNV9kkXN2Gc3v/VyB"
"ruICqdhHSXJkusQJw+vtClqbP2uT18wQN4SRLjFTC3/ZruElXJFipevCQcC8KNVkXW39qZNWJGmKAR15mprXot6VKXkRHfyQJJz0"
"lAMTaACA5LJoA1dDn7+UaikqUsfrlLE6ObbCasA5/wIp5zFsGvslVq/vJqGWk2mdXbas2fpWTSUECEB3gGoIFo9rmHTURX4cAALa"
"oZnjSkaKy1IdC3XDQsqT2vmAX3XjvaLhkCwWg56pst5LvS0AlcRGo49QHATNsY4h0SFkUmMyAGgS7+Pa2VwmCgWUoFFHRbO8ryoy"
"W57qONicyCxA2/OL28OrKGC/e25UsXwKBAXx+9uamcdxFvOQr9WqEJK1g4Q="
),
},
"function": {
"arguments": '{"start_line": 1, "end_line": 50, "path": "shop/validation.py"}',
"name": "read_file",
},
"id": (
"call_1464376__thought__AY89a18+3vC8Y6wtLQ8YLNoWj0pZ1qcMTAdhuIp6v+o7VjO8nN81l72KF3fiSKtgKQYvOKc4hz38B"
"NeldTuj8NebwQ7BneePvMzchDx/5j5DXPVIIW7bRE2vYMhffaNpyjdltlQRDAxhiqjbSHIIGZQdxxAE7GfdGxlhstemN91VzQR4K"
"nPKk6MXh0at/4JacXcOFRRXDnYmUqj1a1tSIoSjeTsHMvSj5OpJyxxa8Fafd/yqwL8g4scNZgGzckn4O5quaQmJT9VPtoAsmh8qg"
"XUr/qzNSZoFGzRN6m7OzSuTyQ246hxKwp0+ZB9P+Nn5fvG96JVXsRq7dF00HBAbhebjUfbNTmIQauZHGSGbF2e+ck0aG5Lf8se2q"
"Ru6NCqiF+EnTFMUg7g+1cN1nIXLw7X6cAPPrpXvVdkfAoHksgSFWY5uUYwW9yDTZYwOWqF6bxDapPFU5HmJj/Bf5YuVH7VhGB7fy"
"O8SVW6AUe0/S/o0/e//wn6AaFomUST2wXw0hsi/OSZLEhRAi16AeUI0Y4SenblpEYtDAyhzFi77mqsceuF7QIq672m5yWq2qoGhP"
"h7S+5lMEvuD8YLITzrC81Xcb4HN3rxOvi6skmP4WJqZO8zPIw65WQUhRdhadhxM81HE+3InBToo1IhAF+11qt6hK0EuUf1guaGrU"
"EDZRPAgomcOLBSdK6gQ9pn5z3SiRPpw9SV4LWMqBjulGRD6K8u7XHXLPAiGZTF1cr/N2sEQuyri57XytugNISVcxh0q/Lvz0v0Dy"
"UAZM8H2ymbusxnKdIHanI9ZUS/XIXdia3PwqiOCgXDQaceOmotUnl8i0IXvSKwMjv3wB7UaC4YKyDurZ+gJJOzbjVjZ/mEf9h4JW"
"1ZetNWVtQl2s+oZXCHOtVJD2qLDyuMPO7EuafP8w7mbpKBTmw4ZAyCfrTL73FnEYhp6M3IEG+c4fdUCHMvT6ecG42DLKhdmWfCqz"
"TdXmXFLj/bePo7YzfYpLOLlhEzVdO5ojXPd6squqM+YHQS640UkdQ4v20UQ9ghFRkW1xUl7uPQkIAI0KWiDmaoi0YGFBxWpTs1U+"
"wN2K6hfqgtJy80rl5ceUT7f6B3MnwiIoAjzVc3n3TH6GodPIO08vrhrf4oz+G3OkdCaMHXURfzYkhji50/ThfAxgD7XDuzUYlUWG"
"otbx0FiYEDBbi2b7t7L/w3fP3nXYoSgaaHumXEnOAtugy6immasBFawtZq+GrOIYHJbH2tZhMpUysSTSnGF3BmqczIctDCwC82Ab"
"XU5sKEKFShEGnJSw9B0OlWuPa6kC/Yfapk6NzDyNB2ttsLhy0hCkT0BmgDn2P4h5T4PCVgLWUbA7LGQoYO5zbsUFBwtPUsVFK0yL"
"yf/Gg9h4ebosT6NVh7AkzS2riaNfm//lGUKK/8YDY49PAu0jpHp6JoXYg/z1+BjPvITdIQgf/8a0X36uqO+Yp2HZPzZzl/Ed8sC3"
"ZadKxulNV9kkXN2Gc3v/VyBruICqdhHSXJkusQJw+vtClqbP2uT18wQN4SRLjFTC3/ZruElXJFipevCQcC8KNVkXW39qZNWJGmKA"
"R15mprXot6VKXkRHfyQJJz0lAMTaACA5LJoA1dDn7+UaikqUsfrlLE6ObbCasA5/wIp5zFsGvslVq/vJqGWk2mdXbas2fpWTSUEC"
"EB3gGoIFo9rmHTURX4cAALaoZnjSkaKy1IdC3XDQsqT2vmAX3XjvaLhkCwWg56pst5LvS0AlcRGo49QHATNsY4h0SFkUmMyAGgS7"
"+Pa2VwmCgWUoFFHRbO8ryoyW57qONicyCxA2/OL28OrKGC/e25UsXwKBAXx+9uamcdxFvOQr9WqEJK1g4Q="
),
"type": "function",
},
],
"images": [],
"reasoning_content": (
"**My Thought Process on Handling Quantity Validation**\n\nAlright, to properly address the handling "
"of zero, negative, and potentially non-integer quantities, my immediate next step needs to be "
"understanding the existing validation logic. This is crucial before I can even begin to think about "
'suggesting any fixes or further code. My protocol dictates that I must "read the relevant files '
"before suggesting a fix,\" and that's exactly what I'm prioritizing.\n\nTherefore, I need to examine "
"the `shop/validation.py` file. This is where I anticipate finding the rules and checks that govern "
"how different types of quantities are processed and validated. My plan is to read a reasonable "
"initial segment of this file, say lines 1 through 50, to get a solid grasp of the current "
"implementation. After that, I'll be able to determine precisely *which* other files, if any, I'll "
"need to investigate next, keeping in mind the specific constraints of zero, negative, and "
'non-integer values.\n\nTo do this, I will now use the `read_file` tool:\n\n```json\n{\n "tool_code": '
"\"print(read_file(path='shop/validation.py', start_line=1, end_line=50))\"\n}\n```\n\n"
),
"thinking_blocks": [
{
"type": "thinking",
"thinking": (
"**My Thought Process on Handling Quantity Validation**\n\nAlright, to properly address the handling "
"of zero, negative, and potentially non-integer quantities, my immediate next step needs to be "
"understanding the existing validation logic. This is crucial before I can even begin to think about "
'suggesting any fixes or further code. My protocol dictates that I must "read the relevant files '
"before suggesting a fix,\" and that's exactly what I'm prioritizing.\n\nTherefore, I need to examine "
"the `shop/validation.py` file. This is where I anticipate finding the rules and checks that govern "
"how different types of quantities are processed and validated. My plan is to read a reasonable "
"initial segment of this file, say lines 1 through 50, to get a solid grasp of the current "
"implementation. After that, I'll be able to determine precisely *which* other files, if any, I'll "
"need to investigate next, keeping in mind the specific constraints of zero, negative, and "
'non-integer values.\n\nTo do this, I will now use the `read_file` tool:\n\n```json\n{\n "tool_code": '
"\"print(read_file(path='shop/validation.py', start_line=1, end_line=50))\"\n}\n```\n\n"
),
},
],
"provider_specific_fields": {
"thought_signatures": [
(
"AY89a18+3vC8Y6wtLQ8YLNoWj0pZ1qcMTAdhuIp6v+o7VjO8nN81l72KF3fiSKtgKQYvOKc4hz38BNeldTuj8NebwQ7BneePvMzc"
"hDx/5j5DXPVIIW7bRE2vYMhffaNpyjdltlQRDAxhiqjbSHIIGZQdxxAE7GfdGxlhstemN91VzQR4KnPKk6MXh0at/4JacXcOFRRX"
"DnYmUqj1a1tSIoSjeTsHMvSj5OpJyxxa8Fafd/yqwL8g4scNZgGzckn4O5quaQmJT9VPtoAsmh8qgXUr/qzNSZoFGzRN6m7OzSuT"
"yQ246hxKwp0+ZB9P+Nn5fvG96JVXsRq7dF00HBAbhebjUfbNTmIQauZHGSGbF2e+ck0aG5Lf8se2qRu6NCqiF+EnTFMUg7g+1cN1"
"nIXLw7X6cAPPrpXvVdkfAoHksgSFWY5uUYwW9yDTZYwOWqF6bxDapPFU5HmJj/Bf5YuVH7VhGB7fyO8SVW6AUe0/S/o0/e//wn6A"
"aFomUST2wXw0hsi/OSZLEhRAi16AeUI0Y4SenblpEYtDAyhzFi77mqsceuF7QIq672m5yWq2qoGhPh7S+5lMEvuD8YLITzrC81Xc"
"b4HN3rxOvi6skmP4WJqZO8zPIw65WQUhRdhadhxM81HE+3InBToo1IhAF+11qt6hK0EuUf1guaGrUEDZRPAgomcOLBSdK6gQ9pn5"
"z3SiRPpw9SV4LWMqBjulGRD6K8u7XHXLPAiGZTF1cr/N2sEQuyri57XytugNISVcxh0q/Lvz0v0DyUAZM8H2ymbusxnKdIHanI9Z"
"US/XIXdia3PwqiOCgXDQaceOmotUnl8i0IXvSKwMjv3wB7UaC4YKyDurZ+gJJOzbjVjZ/mEf9h4JW1ZetNWVtQl2s+oZXCHOtVJD"
"2qLDyuMPO7EuafP8w7mbpKBTmw4ZAyCfrTL73FnEYhp6M3IEG+c4fdUCHMvT6ecG42DLKhdmWfCqzTdXmXFLj/bePo7YzfYpLOLl"
"hEzVdO5ojXPd6squqM+YHQS640UkdQ4v20UQ9ghFRkW1xUl7uPQkIAI0KWiDmaoi0YGFBxWpTs1U+wN2K6hfqgtJy80rl5ceUT7f"
"6B3MnwiIoAjzVc3n3TH6GodPIO08vrhrf4oz+G3OkdCaMHXURfzYkhji50/ThfAxgD7XDuzUYlUWGotbx0FiYEDBbi2b7t7L/w3f"
"P3nXYoSgaaHumXEnOAtugy6immasBFawtZq+GrOIYHJbH2tZhMpUysSTSnGF3BmqczIctDCwC82AbXU5sKEKFShEGnJSw9B0OlWu"
"Pa6kC/Yfapk6NzDyNB2ttsLhy0hCkT0BmgDn2P4h5T4PCVgLWUbA7LGQoYO5zbsUFBwtPUsVFK0yLyf/Gg9h4ebosT6NVh7AkzS2"
"riaNfm//lGUKK/8YDY49PAu0jpHp6JoXYg/z1+BjPvITdIQgf/8a0X36uqO+Yp2HZPzZzl/Ed8sC3ZadKxulNV9kkXN2Gc3v/VyB"
"ruICqdhHSXJkusQJw+vtClqbP2uT18wQN4SRLjFTC3/ZruElXJFipevCQcC8KNVkXW39qZNWJGmKAR15mprXot6VKXkRHfyQJJz0"
"lAMTaACA5LJoA1dDn7+UaikqUsfrlLE6ObbCasA5/wIp5zFsGvslVq/vJqGWk2mdXbas2fpWTSUECEB3gGoIFo9rmHTURX4cAALa"
"oZnjSkaKy1IdC3XDQsqT2vmAX3XjvaLhkCwWg56pst5LvS0AlcRGo49QHATNsY4h0SFkUmMyAGgS7+Pa2VwmCgWUoFFHRbO8ryoy"
"W57qONicyCxA2/OL28OrKGC/e25UsXwKBAXx+9uamcdxFvOQr9WqEJK1g4Q="
),
],
},
},
"provider_specific_fields": {"native_finish_reason": "STOP"},
},
],
"usage": {
"completion_tokens": 400,
"prompt_tokens": 246,
"total_tokens": 646,
"completion_tokens_details": {"reasoning_tokens": 339, "text_tokens": 61},
"prompt_tokens_details": {"text_tokens": 246},
},
"vertex_ai_grounding_metadata": [],
"vertex_ai_url_context_metadata": [],
"vertex_ai_safety_results": [],
"vertex_ai_citation_metadata": [],
},
)

780
tests/integration/translation/messages/bases/anthropic.py
View file

@ -6,75 +6,6 @@ from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGE
from integration.translation.templates.anthropic import ANTHROPIC_MESSAGES_REQUEST, ANTHROPIC_MESSAGES_RESPONSE
from pydantic import JsonValue
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-opus-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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-5-5",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-opus-5-5",
"id": "msg_011CfgC5HKvyve78CTFAw97f",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-opus-5-5",
"id": "msg_011CfgC5HKvyve78CTFAw97f",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
@ -209,76 +140,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-haiku-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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-5-5",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-haiku-5-5",
"id": "msg_011CfoboJT2cSWAvpvJEPTBy",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-haiku-5-5",
"id": "msg_011CfoboJT2cSWAvpvJEPTBy",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
@ -525,16 +386,253 @@ CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
)
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSuQcKEAgSGAI4AUIIdGhpbmtpbmcSDKFGmJVRB+s8d6jjphoMrzic91ngVwSk+KnFIjALyD2lz/FJl0zwfGQJCf/81TXhJ1N49s46WltO"
"EwVctdFi/mNtBuz/H8qLT6nZnJIq1gbvKJzD4syhoHZof3EHkaAfHxNRootT8J6SwvRw82stIfRyxoH3+xjCQq6iZzkkQ9HaQvdEeCexjN8N"
"RFpwhhS/O183u+EESQtikc5PGw7Yzdwrl7YZ1wkQP6XVjyRrhHkqZHryYo1nf6G6g6jSE9eFyIc9abw6cBNwizPDuuXpcockqrQtpKabaO5B"
"o2GBtKltSR8M/aOCDwCKhCJfentm1d9bcRVgT5Nfksz33HjoD5ADev3d+NnM6co0fWZesi4brJPdN21JZW5LjaHkgIFc2NbnSsR9eQkzIx9g"
"G17kFtiCuaEzv25/G2gkTEbrj/aORXWQgQIcQQ0M+fBKDSFDfUy9tK3H45tEPoW6ej1c/oeYh+fCjJRgGone08Hp/B2F+f5YdAC94Y04+7bD"
"UyAm3RlHTPiHRq5HnpHChIrhGldYQ3QU10Etr0dWj2N9UL5BbnMGVDxrGV8K8zjxAlGTZbGQNnhNWHWt5pcMR8afGOv/1R25jK5sO74gbKAZ"
"HfNuWCBfGytBeyjM+yvYpLEaNROmrEX1uQvFPHmWxS/3x44BvJKHWvSrJ0LsDbP+eoOjFIzKma6HHqicJG8TraHIEpIaNF1XfAKyUWtXytlU"
"Uiv1hdVjWqWuEUalOXeF2eOWQENZGfX6A3X2v61JKtsAh8BEB0IIL6ztu9YnW1aVClJN3mBPYedtNLSMQfjc5CXhLQYsFo8q/OwCqCvmhc0t"
"SvZKH/j5beXTSGhEafdxWFLGilrEPE3qhNyHWGjW42/7n342t3kwE4TDt9MhnGuBQGOFtoO/YD/rbGJBq1nDYOBPhg/g6wJx4eMbY1+YpzmM"
"1TcJ07X/Zwd2NgbZ8YugR8Fkxbz+wNwLgm3Wx4TB5Parg78jdek0p5DlfZ1aP8jluIxnlvzBc2al3yrNlWX79OYQSJvcJsn2P74HCWjwRmsX"
"4lqhklY7/GiQP/dDFw8tPxFvfcU6AqAfv9OUICp0PvP3ATGhpTon06mQIo6rR6r7HUtGQdPUA1rAw2XgvUpoXl3f0l/SC2aIShpWjQUwu+Zn"
"1VLaGBnNfj5moS5HtzbKVW9IqU/d9HDRsTlI07JB4LuDleS1JCS4mJv3vQVX1rq1mk5ETNXW/JjrhKHlB8Vxm6cOghgB"
)
CLAUDE_HAIKU_5_5_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg36zuYtPFhEEpad7wiAq",
"content": [
{
"type": "thinking",
"thinking": "I need to read shop/validation.py to look at the edge case handling around zero, "
"negative, and non-integer values. I'll read a generous range starting around line "
"1-80 since I don't know the exact file length.\n"
"\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` first, starting at the `validate_quantity` definition "
"on line 18. I'm also checking the lines above it for helpers or constants that affect "
"how zero, negative, or non-integer values are treated.",
},
{
"type": "tool_use",
"id": "toolu_01J9fZnNpvkQDk28Zj62Cc47",
"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": 289,
"output_tokens_details": {"thinking_tokens": 117},
"service_tier": "standard",
"inference_geo": "global",
},
}
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_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",
"messages": MESSAGES_REQUEST["messages"],
"system": MESSAGES_REQUEST["system"],
"tools": MESSAGES_REQUEST["tools"],
"stream": False,
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
**CLAUDE_HAIKU_5_5_RESPONSE_FIELDS,
"model": "claude-haiku-5-5",
},
expected_litellm_response={
**MESSAGES_RESPONSE,
**CLAUDE_HAIKU_5_5_RESPONSE_FIELDS,
"model": "anthropic/claude-haiku-5-5",
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSwQYKEAgSGAI4AUIIdGhpbmtpbmcSDE4DraHPnzJaL5XCExoMhZYoXkhSWfwTcx8lIjBt8d8pYV0VNCDIdfuGLWpioTySeXeUjAmK11R+"
"18SifTQpg+l0fRdIaI1HPrvqpikq3gX//sW77xYgKmFhC/pig1WvEWEErbbxw6XtLwFIuq+x62J2Vka5GeZeT5CBp4TcrFY718D90jSPqYm+"
"b1a/Zg+2njnVpSLFTFss7vNmNa1YiUND2W4cIODegkc1tRQ/SRZRslMzZ9Xh39VAu2FsjJ0A9W+r6619hN9/ixT2yfxY1LT2Vf1YtTGhyDvb"
"Cn8+GXmYfzCUiQKN1KzX8qjMoUIiaNVZgJy4kYTlqTHXHA+hkYe/I/dkoNc5Nb/arHCSBqmCW2/Jh4T7gTlokfS1YNIZbOMe4S+vByzm3r48"
"sjf+Wf4utdKOkZCizLWjTdKA37qPQq3EN8dMeqywLODKR/4SoxojI8t0d+0Shfv7xYP9kS679M6bUpBiLbiRofIMBR+tiBfZJIMRt+/36c4M"
"JKYYtYiU8l2xMH206+onxNvADUUBk/1WLE0AJ1up/5ZZJO3bXAubC/y3+2icxVCQ4wOjTd1N2+pCSQAD80yOdqNIYHokX9dvbFcgBP5SlpOV"
"1Ast2tXCpcfSsdd4dP2e6Rr0APxrFEevkWiss5EVxk/STjehW1Rq4WFoxhhlQ8wibT2zAbUnaeR1aAQW4JPBrZsC8RNs+tu1HIs++mq4lQC9"
"ls/pEn0L8QSQMbxtCGDHOmdjSDkzFuDZt01KqYKK+pnckSfhd2VxOLWXCtFZbxwviIisafYbL7ex8kOmazXXPrFBAsKLo84Y0ym2f2fmGnvS"
"9p+ibGgizHLF3WPQJVDBdxIn9GEszB2vCWq4zdYZ3HUs+nHFCTFU3FT+MMGtxrnSFKhVcgwis627+XqmsXP0oJbsv3Txw9GaC9v6jD1OKil0"
"WQpc1a/hTb3SwroE7x7gmEVe6QHnJjrrqG1tCWlpa9Dt6GZ82BCuU4326iPlZHdCtWOwvlLZqgreZM8RMPbdTa/rcfrGFcO/bT0q9yThzX7I"
"ecnuu8D28QJlT3Vp779WakHBeNgvNq05GD6dvhgB"
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1: Final = (
"CAQS6QYKEQgSGAI4AUIJbmFycmF0aW9uEgw+f8JSDrP1OzQWjmgaDC+5fzOQbkLuJcHCICIwMCi871N6wTZlw9YxH6IC09M+IrnPgjtTz7lc"
"SPv+bzBSksfh4tcVEvWKJdPcZObhKoUGONxWS5haAeeIk4yEZWsYuSP9a7PYWTyt0IhnYArjFQPGxT6p13RSod4N5u3QKo/iVz4tWT5m+vxl"
"u+w3IUtcC7sOChRgMR+cN/kaj7O81NCdTXlxAp6w8VshNjTVSKKCxcDP8C6xBE5Fa14FPTwQeHwqyOmNeSzta1vmof1SB3u3NUYb5YAYQ5YB"
"zszgyXpl8BakycxtgX8Q3V0jrS4D08YFXFCbPAEa6REPbcbDqGqnFnWPxOXoIpGAOXs21hk90asOqJH6AToFK4p0UWIMG9RFkvCbQ7otPI86"
"tb8Xx5LtL6SG0BAuYqKhB0JewYrmuOLT4OyzlVYWhUVn5aEwpJmR3qc900LkVmUA2SkyUMwgVPIgzoEMrPYWtmwABoMHjRg088WZB5FRmo7h"
"uf9VE4P5tUPUfHYipgMsK3h9WAuvV9a1+4YtRSB74woVdoDAIawRCwFg/T+Njl84mBr6mND5eTn6UmqNdqT0w3VucwLq6KChClA7ZnWItamC"
"dZwm8LtA9ysd/xuE20fonf1Y5DhW4KI7A/P4W72TLUwyYBc+1BAMy5IFYKGZiE8yXRMLDAUsYuW5YAbQua3sDFR1DInlNexNuExlVN9lI7BC"
"IS1tQKultivKpg2j9SJGDP1kFwwMMQzBee69ii3ACozf+kcnDY7Xch5yeLkKnZn1Qz0IMBPOkbe8kWBB1sVGYVXplDNuwNmE6SRwNIqeVdeo"
"ps86SpZ2bPXSk3H6614J2vVpV8SHQgoVv+7BZcsVXIKIAOhO3q/JQA835W+M7sESaAs1XFH54MfD+6UUlIhep9iq+3ck25zuDkoBT5xk9N3v"
"NeBm5JlUM33Bk8cIknUq35W/+jllBk5gEe+RQ1x85aNgTGzxIJDGhxP2tZG4pV8o0fkYR5n7PD1n0FbA3mJf8nnFcKDj0RevTz/y2woydaOd"
"S+OGnbuOtIJsJ2dpUFgDom9QDXNs1Bfx8PV29ND2bPOIYG+TqMP09e0zFvLVDF3Cz2+3zlHbaXj0xy44tD41+EpWYJcYAQ=="
)
CLAUDE_OPUS_5_5_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg371xxoDKT2pPQfVcP6e",
"content": [
{
"type": "thinking",
"thinking": "Since the user explicitly asked for the validation file first, I'll read "
"shop/validation.py around line 18 rather than parallelizing with the test file.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll open `shop/validation.py` around line 18 to see how `validate_quantity` handles "
"zero, negative, and non-integer inputs before checking the tests.\n"
"\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_011bPgnPBMCrDsv9vkTKQsFL",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 45},
"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": 248,
"output_tokens_details": {"thinking_tokens": 150},
"service_tier": "standard",
"inference_geo": "global",
},
}
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_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",
"messages": MESSAGES_REQUEST["messages"],
"system": MESSAGES_REQUEST["system"],
"tools": MESSAGES_REQUEST["tools"],
"stream": False,
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
**CLAUDE_OPUS_5_5_RESPONSE_FIELDS,
"model": "claude-opus-5-5",
},
expected_litellm_response={
**MESSAGES_RESPONSE,
**CLAUDE_OPUS_5_5_RESPONSE_FIELDS,
"model": "anthropic/claude-opus-5-5",
},
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0: Final = (
"CAQS1gYKEAgSGAI4AUIIdGhpbmtpbmcSDGejrLS2VrnijeVfRxoM9JoxxlmEbYEIEjtoIjDZE1H+Mf2sV36GpDiZ6qmC9yPoLvEpR9SvLktB"
"uczCkKWCCiSMfKz3aswvNY+eX0Qq8wUeup4+/o2u5QfFgk6jxQgz4ZFZAlapXhbfwG2kcLegVjWxqnGBexyWZXd3Uu1l74YVsvig5pj8kIEJ"
"xKPkRb1J4Ts+q5bOF6sJjVLZLgtclDs0Qdwj73dUcqlrTqVlwWZP5jFxwjdzD7h19kZP7NEWFN8+tYKNjnNLiNYBq3RdnioxWPfsAC97L1rY"
"VcD1tHiRc3Wml/y5poBpvOGU/gDi96jlGELiZdqkYOPOYz01oI7snrYZZ+t1Um8FemhFBFSq1h2SSl7xihYB34cDPd7929obEKBoAexbPY2K"
"T+NtodCZ4DINMsj1dkAkZCx/QU27lOtRiPBS7JfgOvOXHFlfXho91r9tS9p4N4a1WQeTX96w83iGLXQK2DkcUChe22cUMdyRVzJn2hnoVN3m"
"Rl/bMQZxRiF0lcmq3fen6kWG3kbSpXIKCzbEZhfkRN1uVfZC1ed0JE8qgTYIUh4ZbXIDS1ZxEDbC086pZupahW5b00K7Q2bPuekv8QwIJsW9"
"G+FIdUYmMCDJuRQloY4TFYeNmCwOUT5ZMNoB0N0snFobDj744j8ME3IInjX03+FqWtRWJ2tsb0E0GvQlk9AisxHviaHJ0ejIwsgcdCtOeB8n"
"GWRlVh+GUTWoFtr75B6WN3jaIVpc57BmOWG0xiEqfJWDGSPxfMNx2FVQDF45PWBodL8hTYru0KSHaSD54h1txGFkJGeX8GDlLxe6B5xEYYpx"
"OU3+/4+DNtg7bsGvBRjtZ2TdzrE1N89j3hGlw/ShNS7tNarAfxwCLBbgKh/1uF3IcYfDt891lvvALQG1CupaXyyJiWxCr1oizeFlVe/FLSmg"
"H3yMwKVO8ol20DIlqrVjjqRWHH5wURpOVfNiQN8GMNAwRa20sUsbVl5aTTPkyVwYox+7s/QuW26zqdDztKasEToFU21SLyqSEnkxqNTTO2TN"
"55HYaq5g/GWqAaVIbfdHgwgbf25NL0CEmrWADytfBY4NCLEPNHTVCES5CKErwiGKkBgB"
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_1: Final = (
"CAQSxQcKEQgSGAI4AUIJbmFycmF0aW9uEgxy5XyCv93dBoadwgoaDJlmUXHZn84IYPqUnSIwEAQvf5RKgehIVEOImDwlE5JQqhqPR9hP6TRD"
"c8VHaIIO0ajqrIvzmhC+qU5q+80vKuEGspcWI4tDdYEV8Op3nTUrfE1iU46R7zlVrkZb9bjdv+VZvamiz6RMNv0UAiQNaBOgA3E8qEa21LeK"
"nWB00LCD9lNSAtJQmLTEn9Eps9BLutgDKMBqMIKE9tpjBSDjJ738+6O3fGhc9+PghdrNUdiP2tvCIEHRDdVkSmSXO44BpqK4tbVaG08rZAwp"
"dLETvIpH8dgneIormOZWkW0vvlQ4tC47G2KZ861kXD4KAHxhfPzMET6yuaD2phSl/+BWvhNBgvCRqaDYf6LqExDZSy5XrIzt+SGzR8ZWpsVq"
"mY0QTAw5ECHlsj37Cilkw49OrY5zg9sQ1m7KuopASkT3gEes+TjPdofHms2Dgpfcx5svqF2kpCJBAj9ZaRqVVUMzWlIbrx2+QIrW9FR0wi2O"
"XmxdSrw2fjlp3m1ixjy/0jjyaKCfK0N09VTih3Q/OigXuDghsF7oXjjqYqHXxzRMkULGGjmunM6CcdJGcjzWRbSef2grS/KmsZZ7Xh/l/lRc"
"JXCZPaSHCgz8YwLSPOjRvEjMardae94UEXb/sKeAKczImcq5a0iVFvMjmUp7khBo+ygDh5uGmcos7+amUO3FiiSh0rxWbN20pHMGTsUURVXE"
"p2dzBvZ33egIaGVVjT5iQphQbMj/aY4IP8Mq/BaFqz0tvbffE4fv4bXz8VZYY9yxu6KxYLZYghzAvWyBujcZyK8Ju79ShlKpdTD2NE8rHZh8"
"X4IHKkL57qbcUf1onAxkEYt8fRR7o0aEuM+tZJX/vSorD1QAvuufraq6y8hP3pOtztVyRb1TFzqxwJwfaUavS2sKzPRf9DSguxK8aeaV0jXB"
"H66hLCfXE5bPB4+ez1LWqCPOXNEGVBPFE8Z+8VRXCkDGOyG3p428KKc+5o2qc6Wj6muqJayRenHO54TtEVzGc5h6vIhjHWT8TBEd6QktdByp"
"ino3ysKvuAEIT8jpPB+ucIMOaMZgMkJenSxKn7A+A/rNSQoLXX9uqpJDUE9+ZjucFABKApxej0o4PAsS5QSONURp+OUSjxJbEt4328Cl7LNW"
"MY8/X/fsyyxI20j5FBn5RzU8bHk9OWauNQO+vAf9/yGnMfLyjGZNRQKqVoURbO5/YwZ13y9pscRTOGxClYbG9XlilFluGnMeSCOPpsyufhgB"
)
CLAUDE_FABLE_5_1_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg372jZvQrwtebLxTc8Ph",
"content": [
{
"type": "thinking",
"thinking": "The user specifically asked to read the validation file first, so even though both "
"files are independent, I'll honor that order and read validation.py now.\n"
"\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "Reading shop/validation.py around line 18 to see the full validate_quantity function "
"and check how it handles zero, negatives, and non-integers.\n"
"\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_01RgnHAg9GpXpfL13hyRodfh",
"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": 269,
"output_tokens_details": {"thinking_tokens": 171},
"service_tier": "standard",
"inference_geo": "global",
},
}
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-fable-5-1",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "anthropic/claude-fable-5-1"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
@ -542,395 +640,21 @@ CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-fable-5-1",
"max_tokens": 64,
"messages": MESSAGES_REQUEST["messages"],
"system": MESSAGES_REQUEST["system"],
"tools": MESSAGES_REQUEST["tools"],
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
**CLAUDE_FABLE_5_1_RESPONSE_FIELDS,
"model": "claude-fable-5-1",
"id": "msg_011Cg33tMTaEU15ciNQxuvgV",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
**MESSAGES_RESPONSE,
**CLAUDE_FABLE_5_1_RESPONSE_FIELDS,
"model": "anthropic/claude-fable-5-1",
"id": "msg_011Cg33tMTaEU15ciNQxuvgV",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-sonnet-4-6",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-sonnet-4-6",
"id": "msg_011CffzUNHaEfzVxCh5hskBG",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"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": 5,
"service_tier": "standard",
"inference_geo": "global",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-sonnet-4-6",
"id": "msg_011CffzUNHaEfzVxCh5hskBG",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"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": 5,
"service_tier": "standard",
"inference_geo": "global",
},
"diagnostics": None,
},
)
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-haiku-4-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-haiku-4-5-20251001",
"id": "msg_011CfgDz9Vj8wXvKzhoM4MQA",
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-haiku-4-5",
"id": "msg_011CfgDz9Vj8wXvKzhoM4MQA",
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-sonnet-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-sonnet-5",
"id": "msg_011CfgDzLXmJmnHRTpeBoDmZ",
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-sonnet-5",
"id": "msg_011CfgDzLXmJmnHRTpeBoDmZ",
"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",
},
"diagnostics": None,
},
)
CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-opus-4-8",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-opus-4-8",
"id": "msg_011CfgDzSFYYPC3aYE9rH98J",
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-opus-4-8",
"id": "msg_011CfgDzSFYYPC3aYE9rH98J",
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "anthropic/claude-sonnet-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "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-5-5",
"max_tokens": 64,
"stream": False,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-sonnet-5-5",
"id": "msg_011CfgDzY6H6Rnp7FC7LsZvm",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "anthropic/claude-sonnet-5-5",
"id": "msg_011CfgDzY6H6Rnp7FC7LsZvm",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
)

707
tests/integration/translation/messages/bases/azure.py
View file

@ -1,6 +1,9 @@
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_BRIDGE_RESPONSE, MESSAGES_REQUEST
from integration.translation.templates.azure import AZURE_RESPONSES_BRIDGE_REQUEST, AZURE_RESPONSES_RESPONSE
from pydantic import JsonValue
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -290,290 +293,526 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_text": {"detected": False, "filtered": False},
"protected_material_code": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 388, "check_offset": 0},
},
]
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "azure/gpt-6-luna",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6-luna/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
litellm_request={**MESSAGES_REQUEST, "model": "azure/gpt-6-luna"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
**AZURE_RESPONSES_BRIDGE_REQUEST,
"model": "gpt-6-luna",
"max_completion_tokens": 64,
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
"choices": [
**AZURE_RESPONSES_RESPONSE,
"id": "resp_0534b0c3898d6d1b006ad023ba700c8195b63f1819ab327ab3",
"created_at": 1792025530,
"completed_at": 1792025531,
"content_filters": GPT_6_LUNA_CONTENT_FILTERS,
"instructions": MESSAGES_REQUEST["system"],
"model": "gpt-6-luna",
"output": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1791231868,
"id": "chatcmpl-EVjWWeBeTmIBg80iLiSeFNeYYY20z",
"model": "gpt-6-luna-2026-09-22",
"object": "chat.completion",
"prompt_filter_results": [
"id": "rs_0534b0c3898d6d1b006ad023bb09b8819590793fe299bffdcf",
"type": "reasoning",
"content": [],
"encrypted_content": (
"gAAAAABq0CO7N77UmN8oIxFPRrP2rvE9LuqnrGGHsFzckseHLpNB24KIlg0OKnfemaCgYarrVksxeJBK"
"goiQ79xkF1NR9RI8-82w4OGNB0ViGNYNA7nf5kOqOTrMh1_gHecIN0Evxn8I0meiqOds7h1biKfkiZlm"
"19b-9r_Y2K--KXONVKFEbe8kP54_ka9KCxQ3_5XnL4IRfRS7lsLfoMjORKnapkVSnMjueRVVOprw_897"
"JJypeT61mzzBYM_18T6k68OE70JndMsr4GNRq4c_Lf_rSRoHg7_iFrdHsBdvMfN79dfp_PeLu5MZVRgc"
"ag-qM9aKUAvzhTD2-EutMw1C1ZNabU2S5Qa4RXq2OiU_iZljJI6JhpnJ9jT9g_M3W_0mklmFU2HBhQ6O"
"csIFmPePVcSaQlmofKgvq2ZThSHyFpLsT15ftBL2ZMZ3OWeodDnkfRr2fY5NDM7v7U1TLcAx7xCnP88W"
"03kyb3SuJGSsbPnYTGbNZN7ye3SBJRkCMpRgUfguSYdC46mmMjPdvdkLnTWHZ23GOoDG5A2lffUJZ4WX"
"NgPrMdG2FNThtHT0otHeDC75ahpa6i5xtqIsCGiFRVH_iSxhItArxFXoc7e6oBU9YxsgkUkyXW_zz6h5"
"h5E6DoJz4QckOAdL8E3SwL1nu6ovpS3_QgeiHa5RewKs6WclFCxeiwiyXO6bfjhl_VtOA8KyWqkO-rt4"
"T0RneV_bZHav6KoVanyCX-ZsAYj1WIhn4xEOXh6RdBjZJJB-yDw5cq6zdXkmN1hxs_nmA7hUemHkPclb"
"2lGF41N28IwMpcXq1rx2jrw2XleLnqFVKwgCLysinS9erU2vRN1CmmDQrGl7C5lIOrfSVCpB2W_p3BZW"
"NDKwAfF4i8uXCxy1_5-EjJ08CJXXYVchceOreHYNYxAXhVTHhJArQqVWQgTwJl9e_HhyA0OFZHojB54B"
"jlkMr7QJMm9VE9LIkOJgRgIrtUM2ULIy1tZ-EzuzEy9HYx5NuUKe_12ExKuUVrQmaJ2HRHvj_pPcmSk6"
"lOVrN5VvVBMj_KHd3MfkbUWVeVfzIsgWc149TexK6FPtvHGPxf_VQBdyA4Jl77dPp671wxH7puzy184L"
"V1IMdxq5eY1JG4QdCOluIDkkqbw_qYEiKGNXImGnp9LsXCcYa6JivYmSAw_vgZ5YhO98L49aLEI6nT3H"
"WRWuzY3H39aCkFdA8Y0DttzwXYvhz8UuenFgoGvIk0W7WSOLBxi6pSefdczpRizWLMm10zlrYVFvdMzU"
"PEx7OyDUhSXag61gYcsm6L5mcXGb2cojThdHEXcFZg36bQYjQVJzu_ASlvN-Z9AFNajIIyw8qKx3Q8pR"
"Vg3HCpQcSyRiDhicvT_Gp8d0X7VhoAhG_-LPg4AOz7U985JqP0wB2dB4sYhRgMZpQ29x7wgvgjNtsyqb"
"CA=="
),
"summary": [],
},
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
"id": "msg_0534b0c3898d6d1b006ad023bb52f881958af6ee45425a3b25",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I need `shop/validation.py` next to see how it handles zero, negative, and "
"non-integer quantities."
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0534b0c3898d6d1b006ad023bb83a881958d95537bd9e16f3e",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":120}',
"call_id": "call_G1yFCqI4OnAJbTANskb1ROdb",
"name": "read_file",
},
],
"routing": {"serving_pipereplica": "d20260930053954-f91e8c7b-prefill-r6-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 3,
"engine_ttft_ms": 63,
"engine_ttlt_ms": 79,
"pre_inference_ms": 81,
"service_tbt_ms": 4,
"service_ttft_ms": 280,
"service_ttlt_ms": 301,
"user_visible_ttft_ms": 199,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 114,
"output_tokens_details": {"reasoning_tokens": 50},
"total_tokens": 423,
},
},
expected_litellm_response={
"id": "chatcmpl-EVjWWeBeTmIBg80iLiSeFNeYYY20z",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_0534b0c3898d6d1b006ad023ba700c8195b63f1819ab327ab3",
"model": "azure/gpt-6-luna",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 5},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 114},
"content": [
{
"type": "text",
"text": (
"I need `shop/validation.py` next to see how it handles zero, negative, and non-integer quantities."
),
},
{
"type": "tool_use",
"id": "call_G1yFCqI4OnAJbTANskb1ROdb",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 120},
},
],
},
)
GPT_6_1_SOL_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_text": {"detected": False, "filtered": False},
"protected_material_code": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 475, "check_offset": 0},
},
]
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "azure/gpt-6.1-sol",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6.1-sol/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
litellm_request={**MESSAGES_REQUEST, "model": "azure/gpt-6.1-sol"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
**AZURE_RESPONSES_BRIDGE_REQUEST,
"model": "gpt-6.1-sol",
"max_completion_tokens": 64,
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
"choices": [
**AZURE_RESPONSES_RESPONSE,
"id": "resp_0a4a896afe94ce65006ad023b047248193999d7c3a0c4fec39",
"created_at": 1792025520,
"completed_at": 1792025524,
"content_filters": GPT_6_1_SOL_CONTENT_FILTERS,
"instructions": MESSAGES_REQUEST["system"],
"output": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1791231869,
"id": "chatcmpl-EVjWXoW5I8J7jZD6gsZ3ONxzOqZ27",
"model": "gpt-6.1-sol-2026-09-29",
"object": "chat.completion",
"prompt_filter_results": [
"id": "rs_0a4a896afe94ce65006ad023b19f8481938d51de793f83feed",
"type": "reasoning",
"content": [],
"encrypted_content": (
"gAAAAABq0CO0QoINZ4oOVkvDvinFAJAMUBmzqqpXLoppdlyP4fFQsNqPOh-L08mQt8yf4OUtOwzk3E6Q"
"7CLHieco0s_tfuYHRlTU0Blr62KF_C77RScOjKYa6p4E2fjdwO44Y2HIiGfIo_GnUpkfwW1EiVZmj6L8"
"PO0biPqihvK3KJ-GNKB_R4-lLyKXrrvVN-985glSdHg-_fRrmyVGBvVxPFyERlD-WPm8fPujqMmXnUcA"
"v3N-wUoIEccd7PfJGqBs52UzllpH27mNCI71C_qbc2nZ97jZgSabTvAZKF8Q9zSJzWA_Gs72iQqd0X55"
"F5vD0-xrMuVdXFTYLV-y-S_1rN8tY1bEbdJWr7Dl84NvNWCYqA5byZgsMxAVyjADWXcVaagrZhNtQ1ol"
"II2oePJL2WyrKrOs4d7ZuGFW5BcFCDS5zxk6MwckKbLkSi3HM34z-AhIOjr6SNc5qcR8yur4Phm9pSJQ"
"qFscqQwtmEgbAzXqC9U5rwQ_c11N7o6Xc2bnoRXxeXQvKyGCPZWOqQr8AffHBCCOmeKjbPMV0ITek7Hy"
"RiOWg_Pjq-_xlVCoUGM7gIq5nq3HG1SqH7Yr6qev5Arq24UALiBbr0NAtmq3p-YGRgia3oDnSrnygIX8"
"AbqhnGrHz1kjBbwGr6fXF2XruSKuL96bQghfWGx6nhsbIDH4FI3akERb6Rh1B9XIWsWw4Zzo6-tg6Dnj"
"zfaJteZqIY4qS5mHSD9stXEVqu_CfnGh7EdOlZlnkG6kIQ3m6oAo2ZG9E58m32X-KEqZDjD4yUgWss9y"
"7cnFbYeEzntQneytoBpaTNXtSEsM1fUoz73Ol7FzqPI0CKIsp3UGje2K7LqAwkV54JrhqCfxkD5HmPJn"
"yEOnP0dODvyqD3CK-cbkoPoszI2Ba0dk11re5kF985he-Fjm7dXDNhQX93__nj4awDCtnX8_Ke5ld7O3"
"sA1ou7WHhgfGo-Jr4ZcGL5JWflPbI9oPpGOOvLsS-e8CUjTcTRb_eA2jApeGU2nAdW42U-CnXeScaR5e"
"JE1RoXTFXIP6MMSpxqpTRWYBfhIDyPEzwTveki-WOWgJtyNJ5W3GJxaEZla2uJ5_cdiD4-HgRy1UwxIJ"
"ODUh0F2hKC6niDVIZqoZ6Z4nb4OUvJP00_nGBA5-IL31Ij8I8U740RAZvnOsMOIsKelsJioM8Ii4MdPi"
"O2FYSdKjijEJmXLDdbYkQEXeqwfKGC7trXBOyRwO5AF6mLR9Yf8Bu_eiKbuf5DT9sw88P4JtfPi5LLIs"
"o2Ki44UnxePraO7vinqg7H7oOi-1gw7BbDaKH7tJs3vUOaxl6mA0BNTg5cDt6TtFZMpFgKNRyanWzSwG"
"WQGYlYbfUGVUnM_tjtgoBNFJAQz1s8fd-qOl1NQDggjlryl6TJk3RSiNYKyJ3fmpE10LM3LUtN3AoFMD"
"FbEEBstDuVg0zzvwe64zaKosn7PIh_Ym-y7QlMdcvUbsqO-T6pfsq8iqEz2anv3yujHkAXIaa3292lbA"
"dFIq80ycQSJbWNd2MtkYQHdWtWmQQoqMX1PdyJGp6N3GG45A4A=="
),
"summary": [],
},
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
"id": "msg_0a4a896afe94ce65006ad023b2cc3081939533c6e664038345",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n"
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0a4a896afe94ce65006ad023b3229881938388d9bef2b4a8ef",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_5drWfeHZt2S3rfVa9SYefgB1",
"name": "read_file",
},
],
"routing": {"serving_pipereplica": "d20260929014647-f3a90410-prefill-r11-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 9,
"engine_ttft_ms": 477,
"engine_ttlt_ms": 530,
"pre_inference_ms": 44,
"service_tbt_ms": 8,
"service_ttft_ms": 795,
"service_ttlt_ms": 833,
"user_visible_ttft_ms": 750,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 137,
"output_tokens_details": {"reasoning_tokens": 72},
"total_tokens": 446,
},
},
expected_litellm_response={
"id": "chatcmpl-EVjWXoW5I8J7jZD6gsZ3ONxzOqZ27",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_0a4a896afe94ce65006ad023b047248193999d7c3a0c4fec39",
"model": "azure/gpt-6.1-sol",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 5},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 137},
"content": [
{
"type": "text",
"text": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n"
),
},
{
"type": "tool_use",
"id": "call_5drWfeHZt2S3rfVa9SYefgB1",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)
GPT_6_ASTRA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
}
]
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "azure/gpt-6-astra",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/deployments/gpt-6-astra/chat/completions?api-version=2025-04-01-preview",
expected_provider_headers={
"content-type": "application/json",
"api-key": "synthetic-azure-key",
"authorization": "Bearer synthetic-azure-key",
},
litellm_request={**MESSAGES_REQUEST, "model": "azure/gpt-6-astra"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={
"messages": [
{"role": "system", "content": "You are a terse assistant."},
{"role": "user", "content": "Say hello."},
],
**AZURE_RESPONSES_BRIDGE_REQUEST,
"model": "gpt-6-astra",
"max_completion_tokens": 64,
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
"choices": [
**AZURE_RESPONSES_RESPONSE,
"id": "resp_019af305501e4822006ad023c3a50881958c4cf40623699cf8",
"created_at": 1792025539,
"completed_at": 1792025543,
"content_filters": GPT_6_ASTRA_CONTENT_FILTERS,
"instructions": MESSAGES_REQUEST["system"],
"model": "gpt-6-astra",
"output": [
{
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
"finish_reason": "stop",
"index": 0,
"logprobs": None,
"message": {"annotations": [], "content": "Hello!", "refusal": None, "role": "assistant"},
}
],
"created": 1792022239,
"id": "chatcmpl-EZ38RBBvY1sBntKZmxDuJDJetT1Tq",
"model": "gpt-6-astra-2026-09-03",
"object": "chat.completion",
"prompt_filter_results": [
"id": "rs_019af305501e4822006ad023c49ce4819590da413b9879e06b",
"type": "reasoning",
"content": [],
"encrypted_content": (
"gAAAAABq0CPHdct5jJ3BolLC7QmXutcBsSZ0YzHiI8z2uK07jqwLifVhEROdF12ygdCVRtcrLrHPyHSh"
"pVbh41ULxn2L3SyVYLHbbkFMcwbzfky_kqZdUe_1D-PLxsVyI1KFMPLg0Fb9K-N9u_ElvkFcXXsmAhRQ"
"CcB4SE9TMe_5tKBHiZbqvOI112wig7cc57rDbvM0mEoKyFn3WgprP_ewHeCeP6DSEvVGDEMjUd_TIXAH"
"H7y2Ae3y0WRW7WUag_wAiO7xzAH13mh4S6eKeBTKh62krmYeUH3wETO8BF1WnkuZ_86lS0zWLBzeLJJn"
"JiXKXVquKatJ6HvO3m6FkPF0tBXhdc8YYtTF1B_WBMECARKcw4n3mPL3R6J2jpHe05Eo7W7uZkcY5E-q"
"mE_cqUK8YQXTXx-mR339iuAvqSe0N2Rgl9Ey1l7z0MBATIV0c6J4wRav6Di5aAxEEXkgDVk1jF9LZSHo"
"mcGjh2B2UWFiAZEELRDD7ovpP3c7B05h0QvwazXlZnskJf-xYZEHAl2CNZk0iqagFs6EtNrFguM5W2AH"
"6dsuaGjNGmdWM_kt4JqIUeScZLNgMty8qTOHFzd7tiBpuLkQgcnHzOigWb2vY_8ahy_zfzM2lVL-JQxP"
"9SB7Gq1m49Ln-byC1O_kPyqEFXELhhQ8peXQY5do2R2T-3I0WLOhDhP5rruLsL66vNHAAMjka6WmjI2g"
"oiy-JF_nVCplJd791Wqa3yf7Q7ksfasnSKtjR7-cgTtMcXX7n_5joMnqf4_LsqSq6gHdeKw4VTeT8wGB"
"Uo3MHLkgi8PnAIphdb3PKgifSjstE_oH4_ZbmlyCsHaFYq2aoy-S85ndlrR_PAHBtU8II-Ud_42EPzS-"
"Etdt5d1Qjjri3KTyPjPO7fAm8aPFr1k3GbjwASPMQ7cUs7yLhPmI-TCm5U-zgK1pIALviiU2o4IM7kdH"
"0-Dg1eyyZN8hsFGSHaUB7G_tGB0fj0H0GSztH8ltNjTK_276IOh8Jv5csxjjmlcMOHVBmDCkkE_DlVjv"
"NQtWQS9QBt9jd1gFSzaOhXVkKZJK3vTIaq8JxTvYtgLc8WM5pRHbnQr71TfWB-eLEYgN-aX5PueKkXGr"
"GauDpKkzVJyNZ6mZ_dVXwl1p5IiNNJ1xzhmZK2GVDFWt0nfOBYyxmCDfIxvQL8YAhXXAi1Hrjal82c68"
"lw7UBauyMojDOcbH7EDG9KNbVV-kmkhCW3aH0QCIALzHqO_cukXDqnYX-iVNuxWpW5KUAJdg9cfgwX35"
"O246HxDoSpoIYQ1GooqIWSImYrlNQajPHpJcpxnWeSgKOSYIAYCAr70MouYhUg-lsId7n2pr4gspPf1Z"
"UrBhAG3h4n9qSguKTlpnAYlln_2MzgVVN1cH5sopvgJJLr20HKS1cfu9lB-CHDF5h74z7q3ydZJljn8d"
"QLBqL3csr0ovOZkTjP21rOjPhdsedg4CLKnylgk5nTewbQz99lKxKPhfYK0-XxiDdE6aKvobQUoRupGN"
"Hv-gMLqJjehMUynaC6XzBwJ63pPNhH3AlCj3zSte0Mj1FkPQQIY2PjhMB49CmXBV8Z9YJv0="
),
"summary": [],
},
{
"prompt_index": 0,
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
"self_harm": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
},
}
"id": "msg_019af305501e4822006ad023c5f73c819597a30ebb95c43472",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative "
"values, and non-integer quantities.\n"
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_019af305501e4822006ad023c65c408195b9fa8c35e75b1ebd",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_zAt0ZCuKW07iCDDK2RlX7lAX",
"name": "read_file",
},
],
"routing": {"serving_pipereplica": "d20260921004409-52a9ff06-prefill-r28-dp0-prefill"},
"service_tier": "default",
"system_fingerprint": None,
"usage": {
"completion_tokens": 5,
"completion_tokens_details": {
"accepted_prediction_tokens": 0,
"audio_tokens": 0,
"reasoning_tokens": 0,
"rejected_prediction_tokens": 0,
},
"latency_checkpoint": {
"engine_tbt_ms": 12,
"engine_ttft_ms": 546,
"engine_ttlt_ms": 619,
"pre_inference_ms": 44,
"service_tbt_ms": 14,
"service_ttft_ms": 1023,
"service_ttlt_ms": 1092,
"user_visible_ttft_ms": 979,
},
"prompt_tokens": 19,
"prompt_tokens_details": {"audio_tokens": 0, "cache_write_tokens": 0, "cached_tokens": 0},
"total_tokens": 24,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 138,
"output_tokens_details": {"reasoning_tokens": 72},
"total_tokens": 447,
},
},
expected_litellm_response={
"id": "chatcmpl-EZ38RBBvY1sBntKZmxDuJDJetT1Tq",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_019af305501e4822006ad023c3a50881958c4cf40623699cf8",
"model": "azure/gpt-6-astra",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 5},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 138},
"content": [
{
"type": "text",
"text": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative "
"values, and non-integer quantities.\n"
),
},
{
"type": "tool_use",
"id": "call_zAt0ZCuKW07iCDDK2RlX7lAX",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)
GPT_5_6_TERRA_CONTENT_FILTERS: Final[JsonValue] = [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 313, "check_offset": 0},
},
]
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "azure/gpt-5.6-terra"},
expected_provider_endpoint="/openai/responses?api-version=2025-04-01-preview",
expected_provider_headers={"content-type": "application/json", "api-key": "synthetic-azure-key"},
expected_provider_request={
**AZURE_RESPONSES_BRIDGE_REQUEST,
"model": "gpt-5.6-terra",
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
**AZURE_RESPONSES_RESPONSE,
"id": "resp_0d178c5d2401a624006ad023cf1c588194ab41d5803ed29401",
"created_at": 1792025551,
"completed_at": 1792025552,
"content_filters": GPT_5_6_TERRA_CONTENT_FILTERS,
"instructions": MESSAGES_REQUEST["system"],
"model": "gpt-5.6-terra",
"output": [
{
"id": "rs_0d178c5d2401a624006ad023cfe304819486bdf040ec55eab7",
"type": "reasoning",
"content": [],
"encrypted_content": (
"gAAAAABq0CPQDJzIdOV-2rO0aGYCUhKcJifPRv4ZkBaIrKZEARo0rk8CqAe8IV0c2kyBwOFe4M70GMM-"
"HrR1L3hIUxan9dcDB5_S7e45yDaxFMiKpbr20izrXNktdwBQfvYOKoMMd07fslVRR-GHOEtz8JvU98v5"
"81sxXgVTxNAWGSl_Kb22g2Fds02t1-1g2hT304vsi1sBxbA6P2b-NFNQ8N3NEfX6FoWi7UF0nH69-Dg3"
"sCMb4dpZ0gGZaZSHwvzXXHESEuiMv1nJSX18tfrFIt29gmw3Mq3sUxZ3eALkPZ54yDUlfYXl6sm2MHXT"
"2xn3l5x6jlG4X8hEqgdfHI76otxmfsXvgtbXCADCes87f00bkWatqWgq27oluRYsY02xDMhtrT4h4C4s"
"PIpV7PA9tdhS6Lo3znsQiOEQvMqnSS3dH1NKnZsAiyjNwVZVZa0opIzI5fpNCGjBmMv_4hB3jBRgenG-"
"Ku75OcwPp6HXMej9McvpLIKtXb8FMKS5wqiZzYBLp-F25hzOHI0QVl0pGFL5ya9mWU4hkQYeu6HuH6Zj"
"Sujzyy-8ZmlBjnRZSQp8mN4t34u2ofk4RtyuZKJkgjJfN2m5MxBTT3AccMalmbiEa7lJv7GV9kLcqR0G"
"T2Rzd6UMX6qPG92VdfjIgCj1Rzh1IWrJvMloKkMj5qB3nN2dABqfCtjBleStNoTjO2VDensXf11ceG9-"
"KKWeCjfrG0ONgTVXPjTTUPHR0BxtoixnRxIYBZFb8sKdYAPI_QINjby2SVhhQH7UtookBf7N7OqmIJKb"
"zR4CLshKnvthH4fJQAZdsfoEPR9I943uBpZi4HnF8mQPF61Aiw9B3bh3USBc9_Oh2rJL044B6qYVD3QK"
"KGydzcplRxQWA31m-4Zn9eVxn-xOtx4Tvpdh6BhlFPKX9p2W0mSnb7kjpzX51Ec0J2AsTNUOonaaMFt8"
"2MJDELTGcAb3tsAkPzzNK0M_zjQ43CCH5Cu1yV2WhbUzxCu4UM0spAIuzpAZv6JGmW1wF4RtAgLfJjc2"
"LxoxcS9MJbLOUPAYdRlwBTj_IL9PIDeNlGVRgVQYL-9xnNKiWD8Iyu2vj8AoslM41wVTEXvOAYyEs25E"
"yo9ia2km8909d42DjFi2_ngA5ofZI89KQHtCzGwfCf_VTLbpMmrOB4NDFVTUYQlAMBvuSsXLXJJp0QPl"
"n2UBHhZ3erIcQ1D990SFRdx1uY47-E2FnCCPljyhJrWHnFxTlGbuEY4i5vPOweqYzj-uBbLVeDbcfjCL"
"jSLFgM4Fa5Zg"
),
"summary": [],
},
{
"id": "msg_0d178c5d2401a624006ad023d011388194a221b5ec1cb6e8bd",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I need `shop/validation.py` next to verify the current behavior for zero, "
"negative, and non-integer quantities before reviewing the corresponding tests."
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0d178c5d2401a624006ad023d04f708194bb3ccd55f7afb1d0",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_xFsX3SKb9MppLeAL2L0aGZ8J",
"name": "read_file",
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 92,
"output_tokens_details": {"reasoning_tokens": 22},
"total_tokens": 401,
},
},
expected_litellm_response={
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_0d178c5d2401a624006ad023cf1c588194ab41d5803ed29401",
"model": "azure/gpt-5.6-terra",
"usage": {"input_tokens": 309, "output_tokens": 92},
"content": [
{
"type": "text",
"text": (
"I need `shop/validation.py` next to verify the current behavior for zero, "
"negative, and non-integer quantities before reviewing the corresponding tests."
),
},
{
"type": "tool_use",
"id": "call_xFsX3SKb9MppLeAL2L0aGZ8J",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)

241
tests/integration/translation/messages/bases/azure_ai.py
View file

@ -1,6 +1,10 @@
from collections.abc import Mapping
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGES_RESPONSE
from integration.translation.templates.anthropic import ANTHROPIC_MESSAGES_REQUEST, ANTHROPIC_MESSAGES_RESPONSE
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -69,76 +73,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "azure_ai/claude-haiku-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-haiku-5-5",
"max_tokens": 64,
"stream": False,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-haiku-5-5",
"id": "msg_011CfoboMv8t1SZhyzZeXDH3",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"model": "azure_ai/claude-haiku-5-5",
"id": "msg_011CfoboMv8t1SZhyzZeXDH3",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
@ -482,17 +416,55 @@ CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSqgcKEAgSGAI4AUIIdGhpbmtpbmcSDJhRZ6mJjwWk7Qp33hoMdnwv42chh3ronr/mIjA/ti2oyTG92CZPcqNiCgjiqzwhodkEUejDgKoH"
"fbOEwwLS6iSCqSKrLMCu9PQAp5gqxwZJ+Z/ZX5JUifYdc1pNfnYmlWpJJoBDLv30nDIpOQq73DNraWtbsW0Wm1ZWdrZAapLtVP4pPFrDlen3"
"3gj1ZOfbLh/3tM1yfQb3reW/p8c9DMc54gQTlDqVEm0wSuqtmk0epMxueMh9Vu97JxR2SbeG/kU3M22oqt2HqsDXIxC4z8GQfuhJVa4CFvoV"
"kPLudM9VrYwLzPQ9iOEVvjjw5fYFLf5KOBFI95+z0LHqBopKpPLeQFT9J4jO4h6jsRMkmeCK0GIPKAdvIl6XlFKEC8z1sUi8aIsU216w/8yS"
"HDQdw6p5pe2jwG9XZqs98xRfELsxn29J7WaxzaWI3YQvMxaLJG0ze1InomeGzBZi46QCqlW7dK0XwnDSNbkcnN/1I4JIJlJhnSVZsbirzgK2"
"B8EZXaloWxRSRzC4Aw4tJ3/hKw2R966UgQzp8vkr/Ezms3v0cnRjayopPCUHNcuHkuCuww2X69J22HcULSUcvEaQSLlVHxTw2cS4hOjhvXc5"
"ySJTZPYlKNQhaioYvELPq5ULD/k2hj9JZp+Go/fvIt3F9ysuC5PRnvgN8V357N0L9a79S8lbw2eituEWmjRZzOQujGdVfz+d4NU0v0Btihuc"
"/am2liAB+hY4JatYsXyRRx/tV9HcV5ZTjh5I8bV5NHC/MsP0dFWM9XmsRcxQ+X/SyNHWvZUaSzYd+oKtv4RLDvanfNdG8kIcSzrSJe6DdqY9"
"7d6DWU2/mcbIIBZm94Wv40Snxg/CEnaVB3SdK/E4cTmlUfvaRZvaUMWUSk4wPrIA5De3htk7d2AP97fv2QayaS0PlvdnwbAO+kOSmEEvBKq/"
"yI/0LoSrPCi08CRJ8rO2KNXv5spyCJAfLTG8im6KaeENj0M7+e/BWYVOlZfgqNqaXUu5a2EUlO/0QycPe0NEIZ70SdG54C1zkE9MTjzYoYXM"
"EFXaawPQ61dheOHClEyEbLlfKSa9IUX19hhht9GD6wJIjAGQ3A+YqS1HIqZEvI7gnkQlk19BWPHs4UCF8JhnTsJQ+KZLTYFO7kfX5shhPYff"
"DTlrCRGUrArdsM9ooNXDAqgEA6O0xMuX8G2eg13+4tmcZGv407LHLWtreo8fgrBmS1yWMRgB"
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
CLAUDE_HAIKU_5_5_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg37NEs5KS227ncBai4Sg",
"content": [
{
"type": "thinking",
"thinking": "I should read shop/validation.py to check how it handles zero, negative, and "
"non-integer quantities before moving to the next file. I'll grab a reasonable line "
"range since I don't know the exact file length.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_012CKWjp8JY4UGL1TC5Lj79N",
"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": 220,
"output_tokens_details": {"thinking_tokens": 120},
"service_tier": "standard",
"inference_geo": "global",
},
}
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "azure_ai/claude-fable-5-1",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "azure_ai/claude-haiku-5-5"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
@ -500,54 +472,79 @@ CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-fable-5-1",
"max_tokens": 64,
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-haiku-5-5",
"messages": MESSAGES_REQUEST["messages"],
"system": [{"type": "text", "text": MESSAGES_REQUEST["system"]}],
"tools": MESSAGES_REQUEST["tools"],
"stream": False,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"messages": [{"role": "user", "content": "Say hello."}],
},
mock_provider_response={
"model": "claude-fable-5-1",
"id": "msg_011Cg33vny3NNaurNqZaL94u",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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": "not_available",
},
"diagnostics": None,
**ANTHROPIC_MESSAGES_RESPONSE,
**CLAUDE_HAIKU_5_5_RESPONSE_FIELDS,
"model": "claude-haiku-5-5",
},
expected_litellm_response={
"model": "azure_ai/claude-fable-5-1",
"id": "msg_011Cg33vny3NNaurNqZaL94u",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello!"}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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": "not_available",
},
"diagnostics": None,
**MESSAGES_RESPONSE,
**CLAUDE_HAIKU_5_5_RESPONSE_FIELDS,
"model": "azure_ai/claude-haiku-5-5",
},
)
CLAUDE_FABLE_5_1_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg37Nrg7YQTVeZkczeqqj",
"content": [
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, negative, "
"and non-integer quantities are handled.",
},
{
"type": "tool_use",
"id": "toolu_01TCWoDbheT9e18mtVDH3xnQ",
"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": 143,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
}
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "azure_ai/claude-fable-5-1"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-fable-5-1",
"messages": MESSAGES_REQUEST["messages"],
"system": [{"type": "text", "text": MESSAGES_REQUEST["system"]}],
"tools": MESSAGES_REQUEST["tools"],
"stream": False,
},
mock_provider_response={
**ANTHROPIC_MESSAGES_RESPONSE,
**CLAUDE_FABLE_5_1_RESPONSE_FIELDS,
"model": "claude-fable-5-1",
},
expected_litellm_response={
**MESSAGES_RESPONSE,
**CLAUDE_FABLE_5_1_RESPONSE_FIELDS,
"model": "azure_ai/claude-fable-5-1",
},
)

517
tests/integration/translation/messages/bases/bedrock_converse.py
View file

@ -1,7 +1,14 @@
from collections.abc import Mapping
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGES_RESPONSE
from integration.translation.templates.bedrock_converse import (
BEDROCK_CONVERSE_REQUEST,
BEDROCK_CONVERSE_RESPONSE,
)
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -48,52 +55,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
},
mock_provider_response={
"metrics": {"latencyMs": 954},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
"usage": {
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"serverToolUsage": {},
"totalTokens": 29,
},
},
expected_litellm_response={
"id": ANY,
"type": "message",
"role": "assistant",
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"stop_sequence": None,
"usage": {"input_tokens": 23, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
@ -229,138 +190,444 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
BEDROCK_CONVERSE_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in MESSAGES_RESPONSE.items() if key not in ("container", "diagnostics")
}
BEDROCK_CONVERSE_MESSAGES_SYSTEM: Final[JsonValue] = [
{
"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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
},
]
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSowcKEggSEAEYAjgBQgh0aGlua2luZxIMk7YkOhrvQi9zueMRGgz/wtD/BSP6B5NwRzYiML9G20YP9l1wNfsLU7KSBDRmwZRu6x21pAZl"
"Wi/ABO1zIPZcSdHWKXKYtMMiben4LCq+BscUTDnI69W7DmSmw2Z/AtQHNqUYtIqAwZ1KP/kuDEmOlF/q/QvdhYOm73hRzbJUjEmVkwU+yxX7"
"sXM9DB18oM7KbPLbIAHNu5cM0D1uQ7jKNmLv2w2Y61M0iv4Ff+hU2r8zCXHEGsBA3EP6OsfkmhI3CmUWkAorSt1UYPmjSNbW0sQG9qA3fhVN"
"leKcTQkVpKRV5rY2wcB0Y1OmLdCZCdSj3MXpmjL+Qxh2fW8nFQ1o3XXVIZNTgoJ43J95PtZUJrRMjQGPULeri4oHwXhZowtZmMbnNctjqolX"
"TqXHAqBZLR7UqtOvaAihr8blpdiU5LrWn8qGuV/j4Me25hjC68jW45xHPW/J3IGg5pNOCGNVCA0ZOFkFkHVjGUGjl0jL0KnjC95I1ngiRhdQ"
"DiEyfQq/ozP2nwgk7SD4Wdq5T3QtvJpBB7tLYSMiJOPR8s4gyIE0gjG1kLdOHcEROhz5sezE40sCftRKbishKYw3ZE3badsbkBgVVy7sYevj"
"Hg2E+FycNLGp7VeX3SZgn+zdn2y6ZR427yS7Fhh84PKQMIiX8YQUsg8M4ISBtv0gvqfcrODZeTGKcCprEFC4NNcf9DfunhE9WrVDNaaHAKql"
"/G3uTl6akwmUyAGWomY7YEGGDymxYYGzhucyYuJiyOC9ncLrXJftPadZvz302hOv/ng15Uh/jQwuWsWCs0BjRWEhkmVje76JbmK4Zau9EEx8"
"iy7V9ltWvB20iTn1pfgY40+QFv1j75n7yXD0/oJHehfkRqm8feEs0ERnB6C+iF9XAqBoRSlUh728bbxNzK+ogApwtEbBpmnpFz5j7xLJLG8e"
"a53TCKMyemzqv9bA3xNnenrgO/QYJ1o2heQ6Tyv01cop8EpF5nSqWIorCEbf7yp3f50ABdfZZSnT8Up5hAYHDhTJ/NZBVE8oQaQGbcGRuhl2"
"5sN156XvCS3GcEP4mHu1L9hoT+bfasIx4aCdwQMB86E5lSAtCjphz3m4sBTT67/7RqVf4ymvPxjEsZroz/pujM7oJN2QEvZKkvKIWpHDXPt9"
"efVjUpeQcpoSTuazPtnWVWbLvA4FvVXpnDP+Ed7bfkrXw4enrKqw0QYEbJpmGAE="
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_MESSAGES_SYSTEM,
},
mock_provider_response={
"metrics": {"latencyMs": 892},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 147}}},
"metrics": {"latencyMs": 4031},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
"text": "I should check shop/validation.py to handle edge cases like zero, "
"negative, and non-integer values before deciding on the next file to read. "
"I'll read through the file, starting with the first chunk of lines.\n\n",
},
},
},
{
"text": "I'll read `shop/validation.py` around the `validate_quantity` definition at line "
"18, starting from the top of the file so the surrounding helpers are included.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_fjdXCsIbwCrVLDv3Pzvn3B",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 297,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1154,
},
},
expected_litellm_response={
**BEDROCK_CONVERSE_MESSAGES_RESPONSE,
"id": ANY,
"type": "message",
"role": "assistant",
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"stop_sequence": None,
"usage": {"input_tokens": 23, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"usage": {"input_tokens": 4, "output_tokens": 297, "cache_creation_input_tokens": 853},
"content": [
{
"type": "thinking",
"thinking": "I should check shop/validation.py to handle edge cases like zero, negative, and "
"non-integer values before deciding on the next file to read. I'll read through the file, "
"starting with the first chunk of lines.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around the `validate_quantity` definition at line 18, "
"starting from the top of the file so the surrounding helpers are included.",
},
{
"type": "tool_use",
"id": "tooluse_fjdXCsIbwCrVLDv3Pzvn3B",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS7wcKEggSEAEYAjgBQgh0aGlua2luZxIMTkG89+rWhZvnNujjGgy9ueQHNGYTXVgc2TsiMOfc/JR8YWRFuzvOfDDqCuTj51nOgpQyrrmL"
"r5fylFkkoYwi2WWTjeBjxS70RiBErSqKB3OzMtrLHgImTbinps+XcdvrRao0nkPqkXGo1FFfKLf1Tb3/Qytx1scxregT8j4LBtTirSlLJlUX"
"9zmQOi1DVInxJFYVl6p5KObZBKG8PSiVhdOwMxfnV/euyCWZO3JIZTywuOlsHhpb7k5QW6Ygn8Hciikz+A4dLMdBLdbFVT1y61nbTvGNITkO"
"0MngJu3DDe3XKO5v/WjMbNJHm7wEa40ZKaU5q6H7gMD/hJIhHuSWQjtNsD9A/uFBw/6o42gaEmndewGx593NobUz9hf5iWfmwezpqGBs+wsr"
"IMyie0VxW8KNwSR9dpkJfNAToId9EcDHVSlBGdGiQXlaz0Efed6PF57WgV6glU0HVyLKZ1sIDb1G1hhwTe6LKw6mxT/gcakl5S4GB6MJKvEi"
"vTVAqSWjlvSQPktHDvM4nwPejOt+HFcipmE1Wx8Gopfvg1eE1rwslB+wjUO1EOC31483lw5J14KOz1swzjiZcOTVj85CEFtadz8fPK5SCOsP"
"VNcdvpV8rh7KCdkDTnD7vTtS18Mu9QoOw0hl66l4O3uEuGa0wiQ1/0H2Mmul/+P+zMxrkYNkVicyDF7UQH9J22lPOaJylisuyZuW6Tamn7PK"
"sbhnTHbIeZpm37BsL4ZBN33aAtB5FGVjXevjt9/mJAuljybiFyA3WuoCov1/9j50vR+UIBW2XeqFbTqrfymqWzFiNWWM+6qGt6UR1S3o0wlO"
"2SXXVNhsNkXVRuR/4cJtjjpReVcrYL+LZNtFgHyWAMhRd4NOCLGQ4wQSeHRFyjqJA7xguls6spfcnBZXlgUFsdYWzyDBqbg8EANBfwI0cTQG"
"X0CZy/beSSxLl9YwDT6cHhQaZU0sJ7yl1AzUuVaf4T5IFDheDn9GKKNCjF6VdY7ycLaH9JfuKvPIM1tzioKcLoNDppFFGtHD+2bwHdw3NAT0"
"RQjuU7XLoUm9p1roY1m7RltcTl1nl/2K5G7x1//Fl4vN9MoyjiL5OF/vCoyaZuswAxZIQeDWxXvDBQVVZvTy5WA9qJmG8OX0QQM1+XKe84IV"
"Z/9lqwrTW3ktVSVuNsFHBFypo9KXONnd99ekwaiFyVeCs0W17Gt3qIwk+LEF0yuFEantdcMoJBMXa3V7oxTgu9a42mrpNOtVwQ2RcU2rLsGl"
"hvj4nDpPAnkNixpyX+SzCJ81FlutT1p5Wpw2GuL2gyZRfNpi8gJOYxgB"
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1: Final = (
"CAQSigYKEwgSEAEYAjgBQgluYXJyYXRpb24SDAwiB8XjpzUcjkdimhoMwIGz3+l5MeF2P8mjIjAhc1Uec4tzG5fzDJrcwUiHfLl9hpYALDND"
"+ykJZqmCUizSbZOB45cey71j2vi6fpMqpAWB5p+izlwQyOdW2tEZygJWj2ag/CSfLMDFz4FxatYYUcivtmo/ujCCBekTBt3hDhph2fE64sj3"
"xsueYPHqSuAdn2n30TPAxBXIR5coXHz6nTZpjouC2A6zXy8grDdO9jSeS1vPprkyCsJw17+jigjWDIkmrjUv8DR1s64GCfuV5dWQ2PdYBI/1"
"8o0OhR77veuPdOcNGcLfP15XX7vbtxJMP9LWOR5MLTgPjLjSAEL++eiisr52H4rB4Lvhz7n2KMfMClL7hqdxArHMpHh00wPi2NR8CGjKNTIP"
"HvI/3e13aZDzW8JEDnD22CMmRx7NLgPD8nuncPqoZdVE7jYOECQldD3iHT7Li+m7CAbimbSksM91rzSP2S3CR/FYGtkjqJP5dDlPuRuWVgat"
"jVM/xUEJl058GNMbTukUAFq2SStLHCCZh6upTBg9DtSNMmNi67602YHuQ+p8g8WRYIJh1PmkU8Y3u1coBp2LKQNuiq7MXT880DxtZ2Fldfi4"
"xnY4vkYyB8pylwb1MrhUxh/7xHEesoSO18+SB/rHosHX7BQM1zf8KIDP4wqSBJER0EOPu6h+u1wiD6VYsRQXFWGcZ2S77GyNhaIQnvcc8Sp1"
"sKoXtjNSek706MHLreobNqFfMZBTWtxcmYuzzYIQyPdJMKcdFHSsXLgaoV+5O2ZQmQbhm5Iw/pvLWYobWRXjwHbqR0tka6bzW0nTrX2REUbA"
"gUV3jAOuZKU2P7DtCDReemU6W0TJpsNIi1/2j2oYwa/Fhgne1WWhadCRN5tHbsAAdrwYbksR6mwIydsu8/on2QBYLRYiLNMN5CtbLMY4zZHB"
"sKzVE8MUAfiGKwhxBE3usWbXb+RhCo93uKe9RrCnikcdD6z53qQb24EpaAfm+rVvKzCElgZtGAE="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_MESSAGES_SYSTEM,
},
mock_provider_response={
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 155}}},
"metrics": {"latencyMs": 6213},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
"text": "The user asked to read the validation file first, but since reading the "
"test file is independent, I can batch both reads together rather than "
"doing them sequentially. I'll read validation.py around line 18 (lines "
"1-60) along with the relevant test file section.\n\n",
},
},
},
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
"text": "Opening both `shop/validation.py` and `tests/test_validation.py` to check "
"how `validate_quantity` handles zero, negative, and non-integer inputs.\n\n",
},
},
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_1r54N0OeCEZFcknGLsKsaa",
"type": "tool_use",
},
},
{
"toolUse": {
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 40},
"name": "read_file",
"toolUseId": "tooluse_VOzhTwpZcyOfeZH2KdVtDj",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 430,
"serverToolUsage": {},
"totalTokens": 1287,
},
},
expected_litellm_response={
**BEDROCK_CONVERSE_MESSAGES_RESPONSE,
"id": ANY,
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"usage": {"input_tokens": 4, "output_tokens": 430, "cache_creation_input_tokens": 853},
"content": [
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, but since reading the test file is "
"independent, I can batch both reads together rather than doing them sequentially. I'll "
"read validation.py around line 18 (lines 1-60) along with the relevant test file section.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "Opening both `shop/validation.py` and `tests/test_validation.py` to check how "
"`validate_quantity` handles zero, negative, and non-integer inputs.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
{"type": "text", "text": ""},
{
"type": "tool_use",
"id": "tooluse_1r54N0OeCEZFcknGLsKsaa",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
{
"type": "tool_use",
"id": "tooluse_VOzhTwpZcyOfeZH2KdVtDj",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 40},
},
],
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSxgQKEggSEAEYAjgBQgh0aGlua2luZxIMaxDDsYU61QS1+n8RGgz156K29uKC1HWPNQkiMFcfXYkUyc+WiXLtgYu9mq4bS8cW7hn9MRw8"
"Sjvb5kO5dd7cwmt0bJHftIBtaLIANSrhA3JiSUmAaZwpmq3AgfM0LliKLK/KbQface14HtzKtd/5MF5Nil1AiqDmDblS1U03sFU5L3PyuCc+"
"hrSaftK7Z1ZBXIB8tOzsko5jeGex0cTsPHFrthM1cH1pay0NMmwU+r1ufrR4EaW7K30oyy3oLol3JpgNF433ra6tRB5EVW2Da1aGlJi6anmp"
"pp4Zq6VBJdGOFmZqTOQULt6dq5j1tg8pzcuQqkrYRipJREtdyxZSx8t98bdNrAWro5o4UW9cGcIZuWK24E994inMN0H4DAZliIHqpwAqwzAY"
"pbvild9GOu8lLpIMwyB2mlLADSzwK+J5/gxFSh2WZ1t56d5AlkGd55IywS7EB+AlZelbCCuyEDwJV9d3woohXmGUvEEuaT7dD6K7gHCIPcvI"
"nVdMnHzb6wlXmtKOUxl8mltIwm4PBBi2uoM8tgPq87fhXxGJgVOSzOdwhaJlbfkHCrVSXAloRx6qwvAZ8JcWBla26lKQo+4vxXo8Y4KgadCR"
"TMLNfymY5BUsz2eJa0fPm4k5CqR5updBjj8PIcUPU2FF9ZUTWQ3BwEhIJHiSdkSrRKhEy8Ifw8Cdzsbq4WxVlYWJ2H9sdycc43+qO9bgf+xB"
"gSeNP/G7uwmR2WcZocbodrIG97UYAQ=="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_MESSAGES_SYSTEM,
},
mock_provider_response={
"metrics": {"latencyMs": 10460},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 35}}},
"metrics": {"latencyMs": 3730},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
"text": "The user wants the validation file checked first, so I'll look around line "
"18 there and hold off on tests for now.\n\n",
},
},
},
{
"text": "I'll open `shop/validation.py` around `validate_quantity` (line 18) to see how it "
"treats zero, negative and non-integer values. After that I'll check the test file.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
"name": "read_file",
"toolUseId": "tooluse_g2htBkaHk6egShGW6MsbjH",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 190,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1047,
},
},
expected_litellm_response={
**BEDROCK_CONVERSE_MESSAGES_RESPONSE,
"id": ANY,
"type": "message",
"role": "assistant",
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"stop_sequence": None,
"usage": {"input_tokens": 23, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 4, "output_tokens": 190, "cache_creation_input_tokens": 853},
"content": [
{
"type": "thinking",
"thinking": "The user wants the validation file checked first, so I'll look around line 18 there and "
"hold off on tests for now.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll open `shop/validation.py` around `validate_quantity` (line 18) to see how it treats "
"zero, negative and non-integer values. After that I'll check the test file.",
},
{
"type": "tool_use",
"id": "tooluse_g2htBkaHk6egShGW6MsbjH",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
},
],
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_MESSAGES_SYSTEM,
"toolConfig": {
"tools": [
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
"name": "search_files",
"description": "Search source and test files for a literal term.",
},
},
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
"name": "read_file",
"description": "Read a range of lines from a project file.",
},
},
],
},
},
mock_provider_response={
"metrics": {"latencyMs": 2352},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 0}}},
"metrics": {"latencyMs": 4888},
"output": {
"message": {
"content": [
{
"text": "I'll read the validation module to see how zero and negative quantities are "
"currently treated.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"name": "read_file",
"toolUseId": "tooluse_ykxX1UplXkgne3EfgDI4Cv",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 873, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 873,
"cacheWriteInputTokens": 873,
"inputTokens": 4,
"outputTokens": 125,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1002,
},
},
expected_litellm_response={
**BEDROCK_CONVERSE_MESSAGES_RESPONSE,
"id": ANY,
"type": "message",
"role": "assistant",
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"stop_sequence": None,
"usage": {"input_tokens": 23, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 4, "output_tokens": 125, "cache_creation_input_tokens": 873},
"content": [
{
"type": "text",
"text": "I'll read the validation module to see how zero and negative quantities are currently "
"treated.",
},
{
"type": "tool_use",
"id": "tooluse_ykxX1UplXkgne3EfgDI4Cv",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
},
],
},
)

478
tests/integration/translation/messages/bases/bedrock_invoke.py
View file

@ -1,6 +1,13 @@
from collections.abc import Mapping
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGES_RESPONSE
from integration.translation.templates.bedrock_invoke import (
BEDROCK_INVOKE_REQUEST,
BEDROCK_INVOKE_RESPONSE,
)
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -60,67 +67,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": "Say hello."}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
mock_provider_response={
"model": "claude-haiku-5-5",
"id": "msg_bdrk_4eoumg4voyx6qt55ft5ts2sze3seufnqcvaqbdsjwfyd67wehaoa",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
},
expected_litellm_response={
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"id": "msg_bdrk_4eoumg4voyx6qt55ft5ts2sze3seufnqcvaqbdsjwfyd67wehaoa",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
@ -299,181 +245,363 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
BEDROCK_INVOKE_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in MESSAGES_RESPONSE.items() if key not in ("diagnostics",)
}
BEDROCK_INVOKE_MESSAGES_SYSTEM: Final[JsonValue] = [
{
"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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
},
]
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS0AUKEggSEAEYAjgBQgh0aGlua2luZxIM9tsaCdqj5UGVQgHOGgylOg8RDlmh3f1L79YiMFFshwFAzn8fQTRWSqaR7dpBkcadG+cFDccq"
"6Cu6MZxJNVXFtqpmgsWFQR5WGlEgKirrBMjA2IESdj0ySte+0ETFtNXPDkfiovCk9en3WHVYW+jvrAIJzOA7Y9oF52rkQUYY/oIeksjLdriJ"
"3dTogQyx1PR+LkdBZp63sAr+Zn92Q/7/ZBj4k8f6/wlICa/KiRtklkGz/KfLpCJlhzCoxDZ9nqaMKeWLHBX5/UlJ7Lf8j4VrW4Tr9oQ3VRia"
"iue189vHibmvLtb0lSOoiMq4hEvE2dA0x7RZnLXQ+mULWd7TVnEeQ1NnGt8SNV56ru58gCU6t6Z/KylY3K5H0EEkFImpOigKlNrdDrk7wRxj"
"hCaFKsc88HUJ15V+3iA0ys3IcZarEFeuDj3fjiKYGtDzaWWDGpmQs7CsKVjAs6YfVh3Eks0KGuDppfnM8QyvmUz8y7aIkeuuES1u9F82g3NQ"
"3FoReR4wwdy76xypUHY415wLODfAiSoJjqsI9DArNQc//8UeQX++ECLuvwNm72CgbcN7L13BznbeSQdV1Un65uXS2wT+1eGvDBgGuwuXgvY5"
"ri2U5YgvnowPboiziBMaUxKNEhNouvD+l+p1bxalC03JcCUCA1MJzqAafufTscOdR1mTSl5V2+PPHz964pvxDCMRR0n+nBGsc3obeoS+9Vqp"
"yRG2lrPQj8t9GYzL93C2gbB3o0mdBB2dZTlKPxTnkCanL+1PwLjuKiy7lklHNo/upTP84kISsX+pOSrSNRW//BDbC5wkqgXHx/GsVL9OfrBe"
"P7f4SmUh6VWykR44kEO7vfR2LF1N3LRsHrI4OuNXlh6AbxShwGMvdimckzK5IjCTPX6DKQBXWmlmNJyeNzw2U37e44S9+vhdz5TBhfcYAQ=="
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/invoke",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": "Say hello."}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"messages": MESSAGES_REQUEST["messages"],
"system": BEDROCK_INVOKE_MESSAGES_SYSTEM,
"tools": MESSAGES_REQUEST["tools"],
},
mock_provider_response={
"model": "claude-sonnet-5-5",
"id": "msg_bdrk_g36x73tqvgb222xutjv3lkmjrff6fbfmtc23hkagpgosftu4tjda",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**BEDROCK_INVOKE_RESPONSE,
"id": "msg_bdrk_wzz4hwc4dbdg5xyblodt4ucbo6racirmvwxrmm7knfhbqy4m2tfq",
"content": [
{
"type": "thinking",
"thinking": "I'll take a look at shop/validation.py to check how it handles edge cases like zero, "
"negative, or non-integer quantities before deciding what to review next.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01SAJFKxZ5AbvBAPai5cpFSs",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 185,
"output_tokens_details": {"thinking_tokens": 85},
"service_tier": "standard",
},
},
expected_litellm_response={
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"id": "msg_bdrk_g36x73tqvgb222xutjv3lkmjrff6fbfmtc23hkagpgosftu4tjda",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**BEDROCK_INVOKE_MESSAGES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"id": "msg_bdrk_wzz4hwc4dbdg5xyblodt4ucbo6racirmvwxrmm7knfhbqy4m2tfq",
"content": [
{
"type": "thinking",
"thinking": "I'll take a look at shop/validation.py to check how it handles edge cases like zero, "
"negative, or non-integer quantities before deciding what to review next.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01SAJFKxZ5AbvBAPai5cpFSs",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 185,
"output_tokens_details": {"thinking_tokens": 85},
"service_tier": "standard",
},
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSnwYKEggSEAEYAjgBQgh0aGlua2luZxIM5Rdi0bxwZPzY53K/Ggz5v0FGebtekQAdYi0iML9pU9O153URlvQmE61tNy33MyzsPW3gebf0"
"uYHHYrfZvthRnZNKNSSJpftkUOnBHiq6BQpuaRBOmr5jlQmx/nra8YP41PjKMwpGTJHkjh2COy2g0Ex2ZJk2Zi5A4jdms8plNf0vG3bXg01s"
"woW+wMC8KnoLBoDYQ5rrR+kSVwQUUir1/UMP0Si3Ep96qLJ9923Tf8ypQe/lTP5Ta/iWJ8jEc5SgMp/7HquIvNxyz3efFSyhUF/82y1WwPdQ"
"YcITad5XfHA/gz/fdCOGCmYJndI6aauKBHXsq4dk+B3ZDbSr1URb29NolM2lWfHb3FngvRknZoHuMX7bVz6hrt2gsSRUoEaME/JNvf+L430t"
"h/lhfk5dHljt8YVf6wI4ZMAwty5ViM43M4In1AEaTJ4VEd9VfYgZ48zpxRqjRFXQvBORAqoOEempYRDphZZcPuxjbrcqW2fzwMDH+rfMZlGu"
"ssDEySgfxj3/ODN0W9US6zdQqJ1YgaOBTH+TEEmcsw0Y5Mq1qioYPeLJjVj9FVLjpwf+9xGBUGoTi5+20T6/o0R7KOMl7iUx7I7HanKoIHHQ"
"uAl/eFlBNSB7nlv7L7i1VC8VFTQ83mk9vVyg74guzcidr8QNn6lCFh8b2sGEUj5uEYLoRFhSAa7uw0ja6cyLOw/62OwXKlJaoV8Yy2awvYYY"
"/ojYlskRB31Ux+wVcSX4J4RqKUwz/067iQecmpXYKMSB6mxc6ig9oyZYbqNd0w4x7L129svgFAY0k3cDS2jUePia9Y+SXJgCNXgjU8BLMj82"
"NUy6WNtjCBXb89yxHWEhXdyNQEtOruc/zWDM6pdHnMsbbgK8q+anyttH6wFsorXwLfJnPTIR4dYujPxRph+ac52uHbhMQKtNB9N0Hd8kT8E+"
"kq9RXXwYjGoMj3CGc5KN0PELEpujCkx6omfN+6yMCJntks/78q4Zv1coVeb4SP22doPtMyjPR1wbBVMCoM+6cPF766uvFCg+J2oDGAE="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
**BEDROCK_INVOKE_REQUEST,
"messages": MESSAGES_REQUEST["messages"],
"system": BEDROCK_INVOKE_MESSAGES_SYSTEM,
"tools": MESSAGES_REQUEST["tools"],
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-sonnet-5-5",
"id": "msg_bdrk_rcnbkubesv2zarg2r6uit3hne2znqytllke3i5jo6sm6eh7ml7za",
"content": [
{
"type": "thinking",
"thinking": "Since the user asked me to look at the validation file first, I'll start there and read "
"through roughly the first 60 lines to get the context I need before considering the tests.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I need `shop/validation.py` first. It defines `validate_quantity` at line 18, so it will "
"show how zero, negative and non-integer values are handled. I'll read the tests after "
"that.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_012x6zRfbMwPWH1TvwvtJcTd",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"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": 257,
"output_tokens_details": {"thinking_tokens": 98},
"service_tier": "standard",
},
},
expected_litellm_response={
**BEDROCK_INVOKE_MESSAGES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"id": "msg_bdrk_rcnbkubesv2zarg2r6uit3hne2znqytllke3i5jo6sm6eh7ml7za",
"content": [
{
"type": "thinking",
"thinking": "Since the user asked me to look at the validation file first, I'll start there and read "
"through roughly the first 60 lines to get the context I need before considering the tests.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I need `shop/validation.py` first. It defines `validate_quantity` at line 18, so it will "
"show how zero, negative and non-integer values are handled. I'll read the tests after "
"that.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_012x6zRfbMwPWH1TvwvtJcTd",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"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": 257,
"output_tokens_details": {"thinking_tokens": 98},
"service_tier": "standard",
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSigUKEggSEAEYAjgBQgh0aGlua2luZxIMo+bg7J1athsROSzTGgz8CIhzKVCiV3U3zR8iMFgRZ0GxT3RyB90ZBPfccjWj9SmeP5Su7x5K"
"v4XcUof6Yw7d+Q31UhW8CTZdeivdDCqlBOkneYlYuN0wm6pkFQG8Cg+ThPVN8HGn/QiZPBihOr5ZJK1joYur01TDHIYWzKuBOHJ/fmYfdgoG"
"I0d6WAsw3FdL4zsbhWSEHbbD8+RFz/wk/LqOdaQNYS4I42fytuO9+i5bVthVB3UVl0QEDxPw9s/4c/RaFMQpIyuCigqyJpZC6UKFCtAPHgPW"
"ASOJtP7s0Yrv+S6MBqJOP3oic95i1IPy873PVLJu+mmyKp8yWRqiK8EN4oNE1HuXKqpvPhm+aCKQK7rUJgtoTxNfpiGeZCDaA8am0ysM1M5y"
"2Zi1V8N4sKDz2+SbEDF8EaHp6eicIZ9f6Z5xII7tR/xS2gP7ZNvSt+HNC7pYoQ5rA9xEWO541RvtcloVj3D7OWeaCLgzP3rsp+XIrNMw5017"
"+98q2G3FAHiCa25VLM3nUyxcG9yi6t6AQFl4ISByj6oh22xrcQJ7b+fiLabG48PtdeVZip/LUAeWm1Dw6e3Vl9kmRZi07/gT+bCp3FhnOHSW"
"bkZKuWB0LWEWa1dBWWNllTDgc2t+jnOL9hVu3j92quUcauOQXA1de746z0l2A8M0bl+Vqf4dWrBk/rvdu5uumIUqgEk3YM8ClKy7m5ylOmct"
"QI8Z9Rsuvt+ianHftrp7VckHdX4BFxmvvtjC+7NljF+aOUJbZpasecjeLT5hf72Xh/OTxKCoylsxrPYbFvT06ZAM12sLHiQ4II+FtF9nXvQl"
"xBY7c4C7qxgB"
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1: Final = (
"CAQS7wUKEwgSEAEYAjgBQgluYXJyYXRpb24SDIDG/3Oi4Lc/e5FR9BoM/dTQTa3LvgbUByp9IjBRgDtuGyPNi3LkPeVXyLT98JrhBRqJktyj"
"WMovEVaNb0VsiF+Q3xFd1i/Mtp/aHX0qiQVkW5ID1q6VrZOWTLrM7vI2Rz4WYUV8fOSa7n8kamwNbwrEKY+uQ7vsgjge+f0Yr9bllDitTOsg"
"P19+CxdUmgLXTva7uu5w44S+KtSj+sSmYVW8Wl/S1DWBKVxL/8pXeJf6t6vQlHMu58EYfW2pY43v+7xUPNBRU+l4+UfBz4DRZHAJpQq82e5z"
"QHjdyU6nSqcxlE1zDrAmmiSiCskbg6CwH0VAredEgdVwRFrdCK+A9NiqzDRSASmZu2VYoPZwgWdd/ufIJ2oqH56p+6JszgX92U0d9yJ8o6uw"
"fvFrP08YYayBhJn7Ba2lpDTdlCtYLT9qsLyXwQ4NIwPr36nzBbDWhRhF5Z5sGdA8vRnyue/CYpbLdI8Qg3JiXaXXTsGhDvbAmX6x55PhXiag"
"WaQSsQ6UzsJIdSUdjeD5bnrJ841oSnsG5qKaUfz+yr3cRn4ZnIHqDbZ4o9o/0lQC4++WHe2VddIIET3vVITKF+jKUsHo62vr5nx6tyUj5dGj"
"ZMyFsEMYmf4b9hgij84/mgCOGLNQ5Nu1PM1GKnMpm2dEaosjmSB14pTkuJCzUWGrLANWcgKJRRfv1Wy6n1xaORcm8w7mIWaYbqcxBPddTVOi"
"sXQ2Gr5pZRsbmcMnYcsDF/LejdLT7m1w4WEeOG7B7kXue2FkVaBq0k5K/mgGuIpdmhuwEYuzA5nf+E91Ik0+ktTT5tX/LfhlTc1RqIT07G86"
"ufm8yKpp6Uc7PvWXGm7tR+/70sN5O4ltSiamehskjtAHj1ev3zc/dQJ3oQP6ljf1AY7/ZB9v6YgLY1c0tZ+cHUQ/0+ND+7sraZu/Xiihggfc"
"s8SMejElcBxTWV86zG2ijctI5UlotIclfNMiGAE="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": "Say hello."}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"messages": MESSAGES_REQUEST["messages"],
"system": BEDROCK_INVOKE_MESSAGES_SYSTEM,
"tools": MESSAGES_REQUEST["tools"],
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-opus-5-5",
"id": "msg_bdrk_lq3occizkeecj263kns2j73zgj4lnn3kzlgll5xnqvk3etlf4pqq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_twd7a5k6nmlhwudxctflvx44se2jpvhjrwimhwul2gwzgnni3zsa",
"content": [
{
"type": "thinking",
"thinking": "I'll start by reading the validation file around line 18, as the user requested first, "
"before checking the tests.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "Now I'll check `validate_quantity` in `shop/validation.py` around line 18 to see how it "
"handles zero, negative, and non-integer inputs before reviewing the test.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Kf2DAxymu3xTnb2AwxZZgB",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 221,
"output_tokens_details": {"thinking_tokens": 50},
"service_tier": "standard",
},
},
expected_litellm_response={
**BEDROCK_INVOKE_MESSAGES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"id": "msg_bdrk_lq3occizkeecj263kns2j73zgj4lnn3kzlgll5xnqvk3etlf4pqq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_twd7a5k6nmlhwudxctflvx44se2jpvhjrwimhwul2gwzgnni3zsa",
"content": [
{
"type": "thinking",
"thinking": "I'll start by reading the validation file around line 18, as the user requested first, "
"before checking the tests.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "Now I'll check `validate_quantity` in `shop/validation.py` around line 18 to see how it "
"handles zero, negative, and non-integer inputs before reviewing the test.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Kf2DAxymu3xTnb2AwxZZgB",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 221,
"output_tokens_details": {"thinking_tokens": 50},
"service_tier": "standard",
},
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": "Say hello."}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"messages": MESSAGES_REQUEST["messages"],
"system": BEDROCK_INVOKE_MESSAGES_SYSTEM,
"tools": MESSAGES_REQUEST["tools"],
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_bdrk_dljkl2he4crmo25l5bqtvtdl4fesopljelt4povcvsjcln2vntaq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_gh2vug2tpleguniqdb6ry6otz5y4x2jxg3lneudi2hx4wrv6xp5q",
"content": [
{
"type": "text",
"text": "I'll read the validation function around line 18 in shop/validation.py.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Wr8tPMkYit6TSkCn7oBKcr",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 122,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
},
},
expected_litellm_response={
**BEDROCK_INVOKE_MESSAGES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"id": "msg_bdrk_dljkl2he4crmo25l5bqtvtdl4fesopljelt4povcvsjcln2vntaq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_gh2vug2tpleguniqdb6ry6otz5y4x2jxg3lneudi2hx4wrv6xp5q",
"content": [
{
"type": "text",
"text": "I'll read the validation function around line 18 in shop/validation.py.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Wr8tPMkYit6TSkCn7oBKcr",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 122,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
},

475
tests/integration/translation/messages/bases/bedrock_mantle.py
View file

@ -1,7 +1,13 @@
from collections.abc import Mapping
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGES_RESPONSE
from integration.translation.templates.bedrock_mantle import (
BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
)
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -456,176 +462,351 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock_mantle/openai.gpt-6-luna",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
"model": "openai.gpt-6-luna",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
},
mock_provider_response={
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791240608,
"created_at": 1791240608,
"error": None,
"frequency_penalty": 0.0,
"id": "resp_o2at36wcxwspffhlmvydms2hpl24bse46blsmsm52ov4xtt4ordq",
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
"metadata": {},
"model": "openai.gpt-6-luna",
"object": "response",
"output": [
{
"content": [{"annotations": [], "logprobs": [], "text": "Hello!", "type": "output_text"}],
"id": "msg_333c149682be50c9b9baebeecbee8f18",
"phase": "final_answer",
"role": "assistant",
"status": "completed",
"type": "message",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "in_memory",
"reasoning": {"summary": None, "effort": "medium", "context": "all_turns"},
"safety_identifier": None,
"service_tier": "default",
"status": "completed",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
},
"user": None,
"moderation": None,
},
expected_litellm_response={
"id": "resp_o2at36wcxwspffhlmvydms2hpl24bse46blsmsm52ov4xtt4ordq",
"type": "message",
"role": "assistant",
"model": "bedrock_mantle/openai.gpt-6-luna",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
},
)
BEDROCK_MANTLE_OPENAI_RESPONSES_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in MESSAGES_RESPONSE.items() if key not in ("container", "diagnostics")
}
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "bedrock_mantle/openai.gpt-6.1-sol",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "bedrock_mantle/openai.gpt-6.1-sol"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
"model": "openai.gpt-6.1-sol",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791240611,
"created_at": 1791240611,
"error": None,
"frequency_penalty": 0.0,
"id": "resp_o2fd3mpsaqp564aclj3nmh5776564wp3h5ljwc4dsjgjfncqvonq",
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
"metadata": {},
"model": "openai.gpt-6.1-sol",
"object": "response",
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027274,
"created_at": 1792027272,
"id": "resp_n4higs7hpzdjowbay2ujeesbgcxavsl4pbkzhbh7pjpimjjaciaa",
"instructions": "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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
"output": [
{
"content": [{"annotations": [], "logprobs": [], "text": "Hello!", "type": "output_text"}],
"id": "msg_597e5fe9c0fd506dae6deaac23093e3d",
"phase": "final_answer",
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_187e1b0bc4995fc9b7fd2796a1889637",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, negative, "
"and non-integer quantities.\n",
"type": "output_text",
},
],
"id": "msg_56724f55f0ce5b10a7909c73300f34df",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
}
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":120}',
"call_id": "call_c70cf00600395be0bd35d0db3b1cfa42",
"id": "fc_8bca96735a2c548c9f7777553cf8e5d0",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "in_memory",
"reasoning": {"summary": None, "effort": "medium", "context": "all_turns"},
"safety_identifier": None,
"service_tier": "default",
"status": "completed",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 141,
"output_tokens_details": {"reasoning_tokens": 76},
"total_tokens": 450,
},
"user": None,
"moderation": None,
},
expected_litellm_response={
"id": "resp_o2fd3mpsaqp564aclj3nmh5776564wp3h5ljwc4dsjgjfncqvonq",
"type": "message",
"role": "assistant",
**BEDROCK_MANTLE_OPENAI_RESPONSES_MESSAGES_RESPONSE,
"id": "resp_n4higs7hpzdjowbay2ujeesbgcxavsl4pbkzhbh7pjpimjjaciaa",
"model": "bedrock_mantle/openai.gpt-6.1-sol",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 141},
"content": [
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n",
},
{
"type": "tool_use",
"id": "call_c70cf00600395be0bd35d0db3b1cfa42",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 120},
},
],
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock_mantle/openai.gpt-6-luna"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-6-luna",
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027280,
"created_at": 1792027279,
"id": "resp_di3jhnf3mehuuht6smddkuygfeo7rzxdxmwvrc52aigdygbts5ca",
"instructions": "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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
"model": "openai.gpt-6-luna",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_8de42923e05d5521b0dbd93c1adcea91",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check the behavior for zero, "
"negative, and non-integer quantities.",
"type": "output_text",
},
],
"id": "msg_6a34dc1447f85d8c8a2f9010dd4bee2a",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":120}',
"call_id": "call_316578feac6a57098276bb1f2671b00b",
"id": "fc_c76fa3372e0257699637cc6777775026",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 119,
"output_tokens_details": {"reasoning_tokens": 54},
"total_tokens": 428,
},
},
expected_litellm_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_MESSAGES_RESPONSE,
"id": "resp_di3jhnf3mehuuht6smddkuygfeo7rzxdxmwvrc52aigdygbts5ca",
"model": "bedrock_mantle/openai.gpt-6-luna",
"usage": {"input_tokens": 309, "output_tokens": 119},
"content": [
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check the behavior for zero, negative, and "
"non-integer quantities.",
},
{
"type": "tool_use",
"id": "call_316578feac6a57098276bb1f2671b00b",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 120},
},
],
},
)
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock_mantle/openai.gpt-6-astra"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-6-astra",
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027287,
"created_at": 1792027285,
"id": "resp_eznficwibpblmnocp4vuvti6d5bxboyxws4vqf5bk2lboyvvbx7q",
"instructions": "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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
"model": "openai.gpt-6-astra",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_e6237911ea3e5775acee304296484fab",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, negative, "
"and non-integer quantities.\n",
"type": "output_text",
},
],
"id": "msg_f652378c5e52535290a315cff41a7694",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_3986bff59655522d95c62139330145fd",
"id": "fc_aec0dbb1671153029ab817c03715462f",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 138,
"output_tokens_details": {"reasoning_tokens": 73},
"total_tokens": 447,
},
},
expected_litellm_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_MESSAGES_RESPONSE,
"id": "resp_eznficwibpblmnocp4vuvti6d5bxboyxws4vqf5bk2lboyvvbx7q",
"model": "bedrock_mantle/openai.gpt-6-astra",
"usage": {"input_tokens": 309, "output_tokens": 138},
"content": [
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n",
},
{
"type": "tool_use",
"id": "call_3986bff59655522d95c62139330145fd",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "bedrock_mantle/openai.gpt-5.6-terra"},
expected_provider_endpoint="/openai/v1/responses",
expected_provider_headers={
"authorization": "Bearer synthetic-bedrock-mantle-key",
"content-type": "application/json",
},
expected_provider_request={
**BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST,
"model": "openai.gpt-5.6-terra",
"instructions": MESSAGES_REQUEST["system"],
},
mock_provider_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE,
"completed_at": 1792027295,
"created_at": 1792027294,
"id": "resp_fqwklh5v6lnfftfaq6ddfbclshh3vkgmth75hufjjxjrhn726b2a",
"instructions": "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 messages "
"client for this project review. Consider zero, negative and non-integer quantities before choosing "
"the next file to inspect.",
"model": "openai.gpt-5.6-terra",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_a4e6e9898f225c88b4d948b6488bfacc",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to verify the current handling of zero, "
"negative, and non-integer quantities; after that, `tests/test_validation.py` is "
"the next file needed to confirm the expected coverage.",
"type": "output_text",
},
],
"id": "msg_a6c79276e3bd594f99585696b01148d2",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_ea239067d1ea5b4f8b96b9240bca0523",
"id": "fc_fb9f552a9d7b5f80917959284de3e9aa",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 109,
"output_tokens_details": {"reasoning_tokens": 23},
"total_tokens": 418,
},
},
expected_litellm_response={
**BEDROCK_MANTLE_OPENAI_RESPONSES_MESSAGES_RESPONSE,
"id": "resp_fqwklh5v6lnfftfaq6ddfbclshh3vkgmth75hufjjxjrhn726b2a",
"model": "bedrock_mantle/openai.gpt-5.6-terra",
"usage": {"input_tokens": 309, "output_tokens": 109},
"content": [
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to verify the current handling of zero, "
"negative, and non-integer quantities; after that, `tests/test_validation.py` is the next "
"file needed to confirm the expected coverage.",
},
{
"type": "tool_use",
"id": "call_ea239067d1ea5b4f8b96b9240bca0523",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)

526
tests/integration/translation/messages/bases/gemini.py
View file

@ -1,6 +1,424 @@
from collections.abc import Mapping
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_REQUEST, MESSAGES_RESPONSE
from integration.translation.templates.gemini import GEMINI_GENERATE_CONTENT_REQUEST, GEMINI_GENERATE_CONTENT_RESPONSE
from pydantic import JsonValue
GEMINI_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in MESSAGES_RESPONSE.items() if key not in ("container", "diagnostics")
}
GEMINI_3_8_FLASH_THOUGHT: Final = (
"**My Analysis of the Task and Next Steps**\n\n"
"Okay, let's break this down. The user's directive is clear: they want me to understand how the s"
"ystem handles quantities, specifically zero, negative, and non-integer values. The constraints a"
"re equally clear: *I can't modify any files*, I have to explain *which* file I'm reading *before"
"* I read it, and I need to use the messaging client.\n\n"
"So, the first thing I need to do is identify the relevant file that likely contains the quantity"
" validation logic. Based on the user's explicit mention, I'm going to start with `shop/validatio"
"n.py`. This is where I'd expect to find the `validate_quantity` function or related code.\n\n"
"Therefore, my next action is to request the contents of this file using the `read_file` tool. I'"
"ll need to specify the correct path, likely `shop/validation.py`, and I'll include a line range "
"to make sure I get the relevant code (I'll err on the side of caution and specify a larger range"
" until I can see the structure of the file). I'll also ensure that I use the message client to f"
"ulfill the user's requirement.\n\n"
'My response will follow this structure: "I need to read `shop/validation.py` next to inspect the'
" implementation of `validate_quantity` and see how zero, negative, and non-integer quantities ar"
"e validated.\" Then, I'll initiate the `read_file` call with the path and line range. My focus wi"
"ll be on identifying the precise validation rules implemented in this file.\n\n\n"
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = (
"EoUMCoIMAWkUfRNAt6WiTWGx73C1cgarbMkd0STsaBTv0DSrICGKWeyBN9ogaaR8u/oA25JfVEENowEsZIoFwKX85uOsevrt"
"So/sB0HCD+9aN1brlZmpOT413RxVKqvnsk5hBEN6JmhOulxKgpcwftZKsNTnn9NWlvM8DOAXsjiK+4pHx5jNtGQe+T8vd2Wg"
"uqLWu4Gky8NMq+kde0q4jSlC+DYEZ8v5DXO8Tgb+gob/jhGOhvDip7WFY9CPF0X2MI4pbOAAeX2GT+XhteIuYMfEJuA7HAs3"
"IEHTkgqjS/pp6CneKt/BE4jisIalNN1A0xrd+fWd+oQsG6PkOfXpUmQdF//5qVOHKVI8PPIPF3oGH7CD4i7FqBeDnYGCPxrt"
"lTY4DT9nMkOXE6D6wh7hUoJ+Pihckl2JcnJKFIlcnFA5WlG3ph2vgF9iULhhQpRSP3WMu3CTmppGfrZiLRzpi4AztkrwlPRk"
"PZvXd8rFhddD6+o0Oc8Wj3jPHg9FhuAHOQyVGrM6WNLWuTCHQQjvGRfamniStmfOFSOvaBVStHQJ3FTL+y1MVqn+6PDSxjCP"
"1uVmCO0A0bjWxeSEN1pm8Fn8iNIE+oxGbPOPmTOX/I/viZEs7w6vBiIUNna9mMS2pw1asUn3gDCTEl47YtuUa4rMavR7CdsX"
"uaULaPZcYU9LhGr5he1tWdKe1RCvLyUM9Cah8za3ByyQUbqpwE2qmJeQpJc1bmhbMvD3za58oCRWDS6P6EWfJBdyPNhtPhbc"
"gP8w/8uEq1aeoAVcLwJr48bVwWnsUEZ0INRPtgpy55lRayzGo131gtFnt/5lFxz6Q3lopEZlaJgd3X416LngnkS1Yw6uU/J1"
"GPaFlVsYkw/Z/8BkD+Q9pREcYg5Kgq54BOn8fws3TsBtW5g80X8AksR1sCxmwyZkfZx8quis+0gNVmTo3dFtcnW4Q2uk0PUn"
"h8Kv9tTkf0njAZx1ExkgxGLPnS0/7IkpkihF6AuznOl9Hz3+jNjHvscHdx0pFudTFgEa4TcYnQhuj70RJ0NdHC4XgWTUHjeo"
"tlwkunLpmUOavMYLBBrjPcmN8+9czz6d46GGDg2wTqV7jYQT1uyuTOaCF0/y7wWeGeU7gn8KqkgpwcQCXQU2AvqkMCdY4dq/"
"uxh/tlhkzVeMwtTCeMjnMtCMgwarj5VAwivS6e9fc3hbls0qZpJahNkSk4K3+5qABqy0rvcdNEXgMIq02mM5EJab+LJwgY9U"
"BVN67FV5lV9of/p104w3yVPFt7lZlCh3d5xaosZyxjmSt1WlR1b+t/2Wj/08vm2qrpw4lJYa64PwkB6TeQTNiAYaqu6iuVEs"
"/wnZBcAI6Ik3pg4nZ776igMXLgw6zOBKU0uS2gqQcidMNK2mdZGOYWuSjHsMRHztlC+z//Rc9KMuAJ9uEAT+mAH+jEHv+q7G"
"ErL2nMrc4LmViqZ+QKvfpCupH0LvsG/Ab2hThlwAyt/W+vLYtjgNcYnFV5IWVwfuXkYaMkAEZZJf3TO8ja0UZh2VZnuXhbp/"
"rrjaxKQv6CWsXXvbBviBaH3OEKir8m9+SsQVioqheegPSY1bLeDprxrryDhiDUw3bcz/jtCWsGFoTXeN3g0Thdn5DIFfpIq+"
"cQqFOwyyzRpEEYzL78K3VsThS+i7L3dj1WubhgSZ0R6MBtE2BfMWLQYKwU3TOWgiv+GpQGorqXdPN95BVI27+ykf7dVO7NEX"
"S23M4ucImSq6Zd3uDRZaRpHoMSGOTwNcNVNpyrpCIa7kg3MqnBdqjdPDyUDa/cj522XXwzvrj112CGTNOcw3wCbEivSOtT9b"
"Yagt3Zg1uKgKSyQZPQx5qmxVBXBqgo/MViybYA3HYohmtrbwPWXUWzoKNDmjd5rvkzaIfjPGMhYLgKXS5f2gekpAqb6rndYH"
"MgONwdfCmWLr/m+oHuOvlO1tHHcXtrdvbr7TU94/OPYoSFLgDGv7Q2mk1GFdz2xFQYzMH1JdEYtXGwmYXUKIUbVJ6ZQXB750"
"td/Lfz1tZ7G2nPJMMIKl5b123IDjKrY0fZD19tevY54="
)
GEMINI_3_8_FLASH_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_8_FLASH_THOUGHT,
"thought": True,
},
{
"text": (
"I need to inspect `shop/validation.py` next to see how `validate_quantity` handles zero, negativ"
"e, and non-integer values."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"end_line": 50,
"start_line": 1,
},
"id": "call_43752",
},
"thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 354,
"candidatesTokenCount": 64,
"totalTokenCount": 773,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 354,
},
],
"thoughtsTokenCount": 355,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "5ibQasrzCsbUz7IP89eBkAM",
}
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "gemini/gemini-3.8-flash"},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": MESSAGES_REQUEST["system"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_3_8_FLASH_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_MESSAGES_RESPONSE,
"id": "5ibQasrzCsbUz7IP89eBkAM",
"model": "gemini/gemini-3.8-flash",
"content": [
{
"type": "thinking",
"thinking": GEMINI_3_8_FLASH_THOUGHT,
"signature": "",
},
{
"type": "text",
"text": (
"I need to inspect `shop/validation.py` next to see how `validate_quantity` handles zero, negativ"
"e, and non-integer values."
),
},
{
"type": "tool_use",
"id": "call_43752",
"name": "read_file",
"input": {
"path": "shop/validation.py",
"end_line": 50,
"start_line": 1,
},
"provider_specific_fields": {
"signature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 354,
"output_tokens": 419,
},
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT: Final = (
"**Analyzing Quantity Validation in shop/validation.py**\n\n"
"Okay, so the goal is to get a handle on how quantity validation works, specifically how zero and"
" negative quantities are dealt with in our system. I need to see the implementation. I'm going t"
"o use `default_api:read_file` - that's the obvious choice here.\n\n"
"Now, let's get the parameters right. The file I want is, of course, \"shop/validation.py\". I don'"
"t need the *entire* file, just the relevant section. Let's start at line 1 and go to line 30 for"
" good measure. That should give me enough context, perhaps including the function definition and"
" some surrounding code. I'm expecting to see the `validate_quantity` function in there, probably"
" around line 18 or so, but let's be sure to grab a bit above to get any relevant imports or help"
"er functions.\n\nSo, I'll be reading `shop/validation.py` from line 1 through 30. That should give"
" me the information I need to understand how we're handling quantity validation, especially thos"
'e pesky zeros and negatives. Now, let\'s run the tool call: `path: "shop/validation.py"`, `start_'
"line: 1`, `end_line: 30`. I'm expecting the output to contain the validation logic.\n\n\n"
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = (
"EqsHCqgHAWkUfROgGyzkZ+pi4VHIZ0/S9yiD/m9VZs8L+Rm8Hnfv6gV25Dw2Yc5P0GA0XK9w2l9T1N12/8TW6Jdh15A58C3R"
"hiVDYeyIkhLlk00QjCI3VtdLasRR6T9wieHiXKKIrm/WbfAu5GougrYnUnt9OKFjiH4l8SxQQfXISCA7Fj/+/N0LCzNRug8P"
"DI5X3x3Wug86RcIa9WwNhK1FQ00V2kMzGCdt64Ieg9YqA9sTtgWqRzEc7QbD73tS15WzeSjogaFI1aXbtpTPJCYPrUN3aUqs"
"yXlqhn5sbKJCuDg7M7zOmneh8TbJwTrcpxvHfn8xEHZouCQhY1/WyFGWXvBjzZnJpwoheNkyA7GTOSE1vhB0I5oyS3OwSHn4"
"zLYrcNvwu+2NZp7zc5fImPLxkIOpK2sl8N3q6M01Qnvae4XXtfZ3wNNviM1N72s8I6ZWAYkeS+U+14TZFrL3jsx/Mewi/6be"
"1Y874WiAuq8B3lF3ACnnJ9E8PDTYripxNwhjtveOJC3YCQncxd6CMIf13Xgnj17G9MEdD1HqKnBkLDsfENAfbauaxF+pouX9"
"+JPPHZHyQ91AzcsnXchnFHkZ61goISJILsRikIfzkiVLSopWlsOESzw2ckIA7uxl3WEpON5Qf5/YXEgMIb3OuakYEgLnHdKd"
"WXmmzkel8yc0xxYLzk9uAy2X+ZcKJwbmmU0oJkSOe48zc26xcBZEouznB+LO9q7S9qzh3nN9owa/OAVp/z/5OA+jGCxr6VbI"
"/7bMHcbI1S5oZXN0jjKAlMqNzlo6UWWBB/TPqH2c2PtEYYcNZWhpoQruvBGyGFtT+fj/YrumG1c8EAsBC4NmBecdTMFqfZsH"
"imnQ/qPenuO+qof7iyxZKRhSRTC5qL5PlwuE4tKL4QzwjDDUrOJQ4EapDjYGC7fR143nP52KZGTONQlYtl8HMOh5FT07PExO"
"tHvXMfCh10xkfkWGVAbVWO2mcp5naAAK9eoSeLydygv2P3fZCProx/xPU3RvzDafLGbc2xEO2N67RQnvCIUQ9SwD9iFy4AZR"
"HPaxjxamQLgHW0hDQuRjBzqtXkO5z7y2AKQi1twxv2UAbbZ6ZR605/1ZNbJXHlsf6TCGKZ1/4TXjeQHjLTGf/qb0Jj9ZFxgo"
"0ffs0HxBygsZY7AXvIMVHwgHeyt9nGiz8yPGReQ/1WJEdcmy0GNnYebPuYgWOk9IHAjrpO/zna9cznwDdmzOjmbXlggwqyFI"
"kudjw2Yz"
)
GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"thought": True,
},
{
"text": (
"I will read the `shop/validation.py` file to examine the `validate_quantity` function and unders"
"tand how it handles zero, negative, and non-integer quantities."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"start_line": 1,
"path": "shop/validation.py",
"end_line": 30,
},
"id": "call_29922",
},
"thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 354,
"candidatesTokenCount": 69,
"totalTokenCount": 656,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 354,
},
],
"thoughtsTokenCount": 233,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "7CbQarXiCMOb6dkPso3s2Ao",
}
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "gemini/gemini-3.1-pro-preview"},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": MESSAGES_REQUEST["system"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_MESSAGES_RESPONSE,
"id": "7CbQarXiCMOb6dkPso3s2Ao",
"model": "gemini/gemini-3.1-pro-preview",
"content": [
{
"type": "thinking",
"thinking": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"signature": "",
},
{
"type": "text",
"text": (
"I will read the `shop/validation.py` file to examine the `validate_quantity` function and unders"
"tand how it handles zero, negative, and non-integer quantities."
),
},
{
"type": "tool_use",
"id": "call_29922",
"name": "read_file",
"input": {
"start_line": 1,
"path": "shop/validation.py",
"end_line": 30,
},
"provider_specific_fields": {
"signature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 354,
"output_tokens": 302,
},
},
)
GEMINI_4_ARGON_THOUGHT: Final = (
"**My Approach to Addressing Potential Quantity Issues**\n\n"
"Okay, before I make any suggestions, I need to fully understand how this system handles potentia"
"lly problematic quantities like zero, negatives, and non-integers. The instructions are clear: I"
" should examine the relevant files first. Therefore, my immediate next step is to examine the va"
"lidation logic. I'm going to start by reading the `shop/validation.py` file. This is where I ant"
"icipate finding the rules around quantity checks. I need to understand this to determine if the "
"reported issue is, in fact, an issue, and also to understand the context. So, I'll start by read"
"ing that file. I will use the `read_file` tool and specify `shop/validation.py` so that I can ge"
"t the contents.\n\n\n"
)
GEMINI_4_ARGON_THOUGHT_SIGNATURE: Final = (
"EukECuYEAWkUfRP1AGBm+VfUg2RBxd+BkfJYxv3HJpn4BHb8bKt8sO2dnYDaU7aro4ErMNkRlXK4cJ/2fewoubknteog7q1r"
"huhmhyZ3Ez8UX5nfeiRktTczwkCT2RL0qY0Yd/qaIWoZcI+QM2XKqHbbHEwW5+MJ9kaQBBzoIz+nyFVfvBmsus9QatIjp2Kk"
"BDXa5HiuVyXobtRz4pgHIJQ0IUb7EBVshaFsa1hwLhKvWBTa9kNOrXWdbcLExvRTzPSyIOC3cxMxwV6UDLmEwrSgqPD+hZ+C"
"YWT9SuQqc1EtbvzNWN2/y4y7ZwekleAEF1Wz+njeqWF01FX4+Der/Cc2lWkoCY9u7jJd4InpLnhKdBUGiSEtTubGMiTVWyAd"
"RKBct6bfstopgnGgqGPM8cW/PCof7+c0gW2nWHU7IDpxB9E5bVb4GIE79+TpWAfVt+qR3nAnk0xN2k6USC8lnf6d9bvhJ+J+"
"Z6loijZBaTOCL8FBMmZFwpwlLyj/9HojuS8DIL8OP1umNF4xqIz8FoGMjUyaeoFX6kHSim3r7kjkfP7h+yZa3seFTqjRLjGu"
"PWrB8abJkP39TNqNaWtGspmAg4Z2PDBSrkW8G29BXkfdbRzV1/1MCqcVed0RE+D3d42/jhzG2j5ul1c0kuZ0RkACrX4WQUWU"
"RhmE4s2z8jaSo6sTmi7nMjKSPV5p2tn9n/yaJoZyDXyXlVMhVTIE5+22YvPEnxWHPQ/aTthfxoi31Mq2fwCrTbkf1OoW/VK/"
"QL903naPf4jpJexUiFDLgylJu+PHEkowuWE0QDC27kgSydvF0wHIcCHHsdU="
)
GEMINI_4_ARGON_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_4_ARGON_THOUGHT,
"thought": True,
},
{
"text": (
"I will read `shop/validation.py` to examine how `validate_quantity` handles zero, negative, and "
"non-integer quantities."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"end_line": 50,
"path": "shop/validation.py",
"start_line": 1,
},
"id": "call_1649114",
},
"thoughtSignature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 412,
"candidatesTokenCount": 68,
"totalTokenCount": 604,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 412,
},
],
"candidatesTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 68,
},
],
"thoughtsTokenCount": 124,
},
"modelVersion": "gemini-4-argon",
"responseId": "8ibQavD9KaOO6dkPs7f0GQ",
}
GEMINI_4_ARGON_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "gemini/gemini-4-argon"},
expected_provider_endpoint="/models/gemini-4-argon:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": MESSAGES_REQUEST["system"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_4_ARGON_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_MESSAGES_RESPONSE,
"id": "8ibQavD9KaOO6dkPs7f0GQ",
"model": "gemini/gemini-4-argon",
"content": [
{
"type": "thinking",
"thinking": GEMINI_4_ARGON_THOUGHT,
"signature": "",
},
{
"type": "text",
"text": (
"I will read `shop/validation.py` to examine how `validate_quantity` handles zero, negative, and "
"non-integer quantities."
),
},
{
"type": "tool_use",
"id": "call_1649114",
"name": "read_file",
"input": {
"end_line": 50,
"path": "shop/validation.py",
"start_line": 1,
},
"provider_specific_fields": {
"signature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 412,
"output_tokens": 192,
},
},
)
GEMINI_3_5_FLASH_THOUGHT_SIGNATURE: Final = "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"
@ -55,111 +473,3 @@ GEMINI_3_5_FLASH_TEST_CASE: Final = TranslationTestCase(
"stop_details": None,
},
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = "EtsDCtgDAWkUfRODYoLRWC+DajYQxOvsLgPh0m8j4NTnd7BflzgPBKFfPW+PU1XsMQuEzviI1qk5mYI0qCfOQNf84PAXXvFA5hMYl+YObaND4G+ZtCdYcolFVfPJQqgK6Kpv20n9hZfLt5JzOS2+HRCLZaokIsZFadN++wqEeEkWQhnKdLGH1lM0fn8Fj/pYq95YLGnB90B8Oaj4qyG6ost2dzRAeAzFSXAko1mD/IgsDrDhEumngCqotdAbPW4jUGYOGDpoXLrBzQZvGa9blRC3ep6NLT0EYMnXImLFoZaLLIBMzVDsmmL0qOg4Gu+uNJlY6cDmtqRgkrcvuvGhh8+lrjUMJVigSsTAoKsTnT3OyCqdNqa+R2aD4WTl1uBFyGY7yXpZ9skQPkV210QNOylZ6exaMA51+W/mohL5j5+OJX7xtVfRIpjp4e0PLkEPxnuviX6OU4ykWZSSiztSXzogbrmnwP7faclRXTXHE5pFlM8y7gDJ9NEwxd5vvIMLdaK2dRWBNtvjI3Cj56sLKygH/j0mQSnt3PonE6Jv6XMJDPbuIzsjzX8t/j3u6WP0bVGnifNNEfIqt6YcKgeWlUTnabRGkWg/fBSyYbiTTEIGhketv57hA9oH7jJZbw=="
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "gemini/gemini-3.8-flash",
"max_tokens": 1024,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 120,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 108,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "5BjEaunaCtadz7IP-8WKsAk",
},
expected_litellm_response={
"id": "5BjEaunaCtadz7IP-8WKsAk",
"type": "message",
"role": "assistant",
"model": "gemini/gemini-3.8-flash",
"stop_sequence": None,
"usage": {"input_tokens": 10, "output_tokens": 110},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = "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"
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "gemini/gemini-3.1-pro-preview",
"max_tokens": 1024,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 115,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 103,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "5RjEaqfwC7XYqtsPp6TuoAY",
},
expected_litellm_response={
"id": "5RjEaqfwC7XYqtsPp6TuoAY",
"type": "message",
"role": "assistant",
"model": "gemini/gemini-3.1-pro-preview",
"stop_sequence": None,
"usage": {"input_tokens": 10, "output_tokens": 105},
"content": [{"type": "text", "text": "Hello."}],
"stop_reason": "end_turn",
"stop_details": None,
},
)

652
tests/integration/translation/messages/bases/openai.py
View file

@ -1,7 +1,8 @@
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_BRIDGE_RESPONSE, MESSAGES_REQUEST
from integration.translation.templates.openai import OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, OPENAI_RESPONSES_RESPONSE
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -290,289 +291,496 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "openai/gpt-6-luna",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "openai/gpt-6-luna"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6-luna",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"include": ["reasoning.encrypted_content"],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, "model": "gpt-6-luna"},
mock_provider_response={
"id": "resp_0dda38229cbb1547006ac3f0195a8487d0818613a635a9e0e2",
"object": "response",
"created_at": 1791225881,
"status": "completed",
"access_programs": {"cyber": "daybreak_blue"},
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225882,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-luna",
"moderation": None,
"id": "resp_03ec491c5caae029006ad0239c083487d099a21d60be6b5fde",
"created_at": 1792025500,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025503,
"instructions": (
"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 "
"messages client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
"output": [
{
"id": "msg_0dda38229cbb1547006ac3f019f55887d08644c44c51109378",
"id": "rs_03ec491c5caae029006ad0239c80c487d0b425db4d74878ab3",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COfZvmrZboi5Ffbs6U_yMF1jaQmGVq5BnqydEOn98Tt_afVrM4H653kYvwFlbyesZJUOa4MLSEHMVc5ZNHlI88WpsGB2C0cdOmXO-S8Xz2wv2TYaf-d7ux1ejKPGkbop3sk2yS2XxQahiybVv5r_opD4YkEVxPoKhnVTfNF0bcglJj1JQbXYSE5qNyAVFeO6kkYN_sRP628gc_-txGgIgJbLn-uTsZ_3aQZ8TmejJJaiXLcauCUyCnYHtw0BncdwxaRiDsAUhrL_HuwLgGc3KHP0mc_IjapNLhVAcqeihSO4rmidsYX6Y7bjb4yhqPqE0-NnPZRO8BOcpIb-qU89htZHrkaSA_MrZj2FD4fk8_btQHTF9C9hM-UjRUJxqMtyuOyNMZdWjBgErNoCzslro-Sty8pWlIYRjzOlQQHZLBrC3EuKvOTEBNNjWXeRCGwZTZR6C5SyE0mj11YCwi67QeYfp8ujvrziJq1Bt7u78vnlPY8bMd0AUz0SURgP2jnlreu11EMWZuR-u6ZMLqyu1HeunBMs82y-5ef37g3evBV7Ym6AjwsiP0SqTM3KeaY5HMkgaZi9G2gwO2g8ZkLsJpy-Bk01KwNYD7QXAxrUXziEAzby_AqAOOZ9_w5mkZSSoJuelWs6nB4stKCaj8lXIanf58DkNjze2Ocd9irMxIz4HUzXcYWyjDa1-0isrR_gQiOWOaCzuIFWPcVrin4Mli-niDnPYcTnNkP4ab1jmTztYb74x2seE9d5voFc7suPLzmqGuFya8fx42A-i7EP-bXM1D5_fWiTAGWbappILLOJzs3ohcO0jBe1NkkxrfVMIJD5m7CVzmOQ5ydhyWHgSNRueFPE2Bz6wqmfnU7bzrAK8DOH1NiA1LMogV7iGBlu4egfKgs7B1m7u1x1YCG5OcBHbm_67VkxxhO95IfwYYEMawg-uxXYUbAx-L_vKnIpyKq1pSaKm-hsvGMm8MvxSviOD2xkxBHElb1rZ6tkWRdR60tSRELtad5F5ItHHZe27tq-XMFZAB2UwxtvwwTZ5wD2C5PmxREMk7XF_YFR8vdVdEqfaLelx6NoeARXQ5Hm7kdiPT33RAVtyvaXuOgAPt4afpmSb0_iW9VpyU7HnHStXoKdw8gWjW-BnjJ7ZDsqy-KFTRRlj8ikcR0pAFafz-GXmiyn7EVc7rfTFYNN7c91SADAhBg2Gtk1c5EGVLCa9uocAYan6MTkzb-bOorPCI-zE-rztEp9L2Lm1TfyUNEFaIRHuG7GAwIsKvnXBwJlwlJA5McCehhqc1V6-1kqcGFSenXBvzRdXr4Wh-hAqT5gZyG0bRQIVjAiITYCbeQtahw3ioGkxUwoTq0XRZPvy0_B71b76QSbEpnVYL0b5oaBia-4qy7tJpaRkhS6pDY3bjxgWt6yPzk6sTWr_Gbt-nMgxCpkHFYI_KMSI4XvOOcPkNGgVK7X278xisXj3cx72rSaBhpRlNKkEtqsIxDTHOWNk9NZooClcTlTrHPPjo0D_3nLMdw94z5V-x0qsRsk3YrUzfIMUPeBV5ctPo5shpr4ycmLPhrnbT5U4FeaZ27AdgFDuhAeXb6AYPJ6VfOVcyZUibLQ50l2XtxjTP0uiM3fMt_7TiyYjQL_3cBv-vQRViXQyI7_7glU0b9EK-SEfl_6f9NRqWiLabP_bb0ZIrGItQ2DxEJpUmhRAErRlq0a5rlnt-We644LT-i8dvBybsnbbkwV8mqRQrAWCFHrCzPALskgmzRpuUaVBXtBhPKkUKnpwav-TseWr-Pog2iLNNfBD37EAQMPsnslLhuNeZ7-bnNJCerPiiCuNJaPd2Iy71quHCOznW7PDajSa4XvFv3GPeT_WluUD_hPRnDxFR0pFX266UJcNcNmP62ogUtfIByf5dyuwvQAFBk0Tplox1U08fKo8KabYWYVzEYQ9XiLXWgq1OSLdc9teuPP5_aFTL2VjvLgIJ8E8H8xhbk9qnPFvng0e-twGn_rKbEqIceWJ7wVqJSTMAqjJy8nBDelgPWCJVVXQ3NAgGlcAUHO0wv-9YGagfklvXrDfMrjKF8Y9YVqmg8a6FFFmCykZSmiCl-MwjHhxO9c1SlT4pDN3c5dt-V9lYGkGv-K1j392wPZOxnoH92AhX1k-lJirRrgMSj6TgQuUQynaxTL01zwD1ilNuAa6966U-KP7V5peoq-4oENlEhhRdW8HjoHl1jQlP00_7K2f5TFmzKyNPHxq7londzlTpautQp59102404xO7CRjTq4hncweSopzlR0CsSQZmy9ZDwbfOIQczBwY1lwfLvlEflZAzRgDPu-CcXTLivLNmHlXKKBKHQd35sxO3KDmgscSZuO61DvEE3SvWK_XYA46vSSHa4OSWZG1V7IDJHddPQJ65kWHbHfxCVhPY_yH52_jtgjOTUBRt_3mMFizWGenQY-tpWoe7Fy-Ex9vzXGDPi-D9QlmluqCZ1Oj0hv5LJbv65AAh5sLSR2lb_Gs1lEI8_ZMoypadUWUTAdiIQqx4nEDn6Yf9oSWVGxiPxgPlFcn_Upkf0MZqookTf7ZVlpgon2lA5MRP9O3-V9EdU8WsAfw2VV3UlygpAOHs0UQA0C691CY3PHjckcRonszezCd2JPmPlIdm-gh2aubk2IUE9NMaVdgRtc-8ysv7GHnGCvmp8FKDS5f4XytuXO_hEOOn5T8Ug-iENW4WOkIJ0jbtmz15NITlrVbPAnGhMSW0y6BfsSn-b9kloFDCA-Mbb4S-IMY8v80M4OkuhV83WPHsXl3yFEiokO02MphzPvhjoixb4OhnsTKG9vUyw4E4wJgGlxGSczNdkBcqiRISJviiRAxnpPQ4XEQ-RkuOjs1AB_cegluyWezH5LovF4S598IJYOAi1oL6Txe0gw4kJVhBmG2hKBscezt30Deu26Qx3Etk9cN3XMirfot7dBoyNZS1Jj2fpsoMbPpxwLhsIIWbWUuN2nKDqDrK199AzGD8-lki0LZh0QOxBcqbtgDDMWp_BpUtutFWL6TZm8DObtIbl4fGy12y1t4kaN-E9mLpzXQXOVjrUbP_tQlNZk7p5YOTeV_NnpunzpNpAbHXXQIukQ1xOlGvHFZ6CRFC-Yknx72aizrZf6aZH_gy9pWKmOhdqWFQ2PJLqGVLIo3mS4yoFC04AivGXdAjdrZB7odufujij9dspXWBO4Tv-dzL29O-j6p-eT6y0HuKachlFpLKpJxzsjIU1DjX0P_0pSVhemfpZDh_nV9eC2w7XNm6logVPIolXiQeypd70LOKnb-wGwxRNlcus6BUSF_BIlplV1S0TTne5PgYU3OCuOPJAwSEW0Q0lkm3lTU8nLyiQd25bV5UeD2wPvxACIPM7_cUyoGkSQ96Ip-NM607-e912AEVR93ZIVK-UHcu8MxSwWCykNaokgs4mEVK5QkY=",
"summary": [],
},
{
"id": "msg_03ec491c5caae029006ad0239e411c87d0bfb3c2c04bc6cd9c",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I need `shop/validation.py` next to see how it treats zero, negative, and "
"non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_03ec491c5caae029006ad0239e978c87d0a3ad2d7a8026ad6f",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":120}',
"call_id": "call_6JuM80yE9acKhYmgxQKWll9Z",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 214,
"output_tokens_details": {"reasoning_tokens": 150},
"total_tokens": 523,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDo0ZmY4OWU3OTgyMGFkZDVjMmM1ZmZlM2MyODk4ZDNkOGEzZDczY2IxY2ExN2JmZGMxYTRmNTRlZmFlNzhkMTIzO3Jlc3BvbnNlX2lkOnJlc3BfMGRkYTM4MjI5Y2JiMTU0NzAwNmFjM2YwMTk1YTg0ODdkMDgxODYxM2E2MzVhOWUwZTI=",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDo0ZmY4OWU3OTgyMGFkZDVjMmM1ZmZlM2MyODk4ZDNkOGEzZDczY2IxY2ExN2JmZGMxYTRmNTRlZmFlNzhkMTIzO3Jlc3BvbnNlX2lkOnJlc3BfMDNlYzQ5MWM1Y2FhZTAyOTAwNmFkMDIzOWMwODM0ODdkMDk5YTIxZDYwYmU2YjVmZGU=",
"model": "openai/gpt-6-luna",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 214},
"content": [
{
"type": "redacted_thinking",
"data": "litellm_encrypted_reasoning:gAAAAABq0COfZvmrZboi5Ffbs6U_yMF1jaQmGVq5BnqydEOn98Tt_afVrM4H653kYvwFlbyesZJUOa4MLSEHMVc5ZNHlI88WpsGB2C0cdOmXO-S8Xz2wv2TYaf-d7ux1ejKPGkbop3sk2yS2XxQahiybVv5r_opD4YkEVxPoKhnVTfNF0bcglJj1JQbXYSE5qNyAVFeO6kkYN_sRP628gc_-txGgIgJbLn-uTsZ_3aQZ8TmejJJaiXLcauCUyCnYHtw0BncdwxaRiDsAUhrL_HuwLgGc3KHP0mc_IjapNLhVAcqeihSO4rmidsYX6Y7bjb4yhqPqE0-NnPZRO8BOcpIb-qU89htZHrkaSA_MrZj2FD4fk8_btQHTF9C9hM-UjRUJxqMtyuOyNMZdWjBgErNoCzslro-Sty8pWlIYRjzOlQQHZLBrC3EuKvOTEBNNjWXeRCGwZTZR6C5SyE0mj11YCwi67QeYfp8ujvrziJq1Bt7u78vnlPY8bMd0AUz0SURgP2jnlreu11EMWZuR-u6ZMLqyu1HeunBMs82y-5ef37g3evBV7Ym6AjwsiP0SqTM3KeaY5HMkgaZi9G2gwO2g8ZkLsJpy-Bk01KwNYD7QXAxrUXziEAzby_AqAOOZ9_w5mkZSSoJuelWs6nB4stKCaj8lXIanf58DkNjze2Ocd9irMxIz4HUzXcYWyjDa1-0isrR_gQiOWOaCzuIFWPcVrin4Mli-niDnPYcTnNkP4ab1jmTztYb74x2seE9d5voFc7suPLzmqGuFya8fx42A-i7EP-bXM1D5_fWiTAGWbappILLOJzs3ohcO0jBe1NkkxrfVMIJD5m7CVzmOQ5ydhyWHgSNRueFPE2Bz6wqmfnU7bzrAK8DOH1NiA1LMogV7iGBlu4egfKgs7B1m7u1x1YCG5OcBHbm_67VkxxhO95IfwYYEMawg-uxXYUbAx-L_vKnIpyKq1pSaKm-hsvGMm8MvxSviOD2xkxBHElb1rZ6tkWRdR60tSRELtad5F5ItHHZe27tq-XMFZAB2UwxtvwwTZ5wD2C5PmxREMk7XF_YFR8vdVdEqfaLelx6NoeARXQ5Hm7kdiPT33RAVtyvaXuOgAPt4afpmSb0_iW9VpyU7HnHStXoKdw8gWjW-BnjJ7ZDsqy-KFTRRlj8ikcR0pAFafz-GXmiyn7EVc7rfTFYNN7c91SADAhBg2Gtk1c5EGVLCa9uocAYan6MTkzb-bOorPCI-zE-rztEp9L2Lm1TfyUNEFaIRHuG7GAwIsKvnXBwJlwlJA5McCehhqc1V6-1kqcGFSenXBvzRdXr4Wh-hAqT5gZyG0bRQIVjAiITYCbeQtahw3ioGkxUwoTq0XRZPvy0_B71b76QSbEpnVYL0b5oaBia-4qy7tJpaRkhS6pDY3bjxgWt6yPzk6sTWr_Gbt-nMgxCpkHFYI_KMSI4XvOOcPkNGgVK7X278xisXj3cx72rSaBhpRlNKkEtqsIxDTHOWNk9NZooClcTlTrHPPjo0D_3nLMdw94z5V-x0qsRsk3YrUzfIMUPeBV5ctPo5shpr4ycmLPhrnbT5U4FeaZ27AdgFDuhAeXb6AYPJ6VfOVcyZUibLQ50l2XtxjTP0uiM3fMt_7TiyYjQL_3cBv-vQRViXQyI7_7glU0b9EK-SEfl_6f9NRqWiLabP_bb0ZIrGItQ2DxEJpUmhRAErRlq0a5rlnt-We644LT-i8dvBybsnbbkwV8mqRQrAWCFHrCzPALskgmzRpuUaVBXtBhPKkUKnpwav-TseWr-Pog2iLNNfBD37EAQMPsnslLhuNeZ7-bnNJCerPiiCuNJaPd2Iy71quHCOznW7PDajSa4XvFv3GPeT_WluUD_hPRnDxFR0pFX266UJcNcNmP62ogUtfIByf5dyuwvQAFBk0Tplox1U08fKo8KabYWYVzEYQ9XiLXWgq1OSLdc9teuPP5_aFTL2VjvLgIJ8E8H8xhbk9qnPFvng0e-twGn_rKbEqIceWJ7wVqJSTMAqjJy8nBDelgPWCJVVXQ3NAgGlcAUHO0wv-9YGagfklvXrDfMrjKF8Y9YVqmg8a6FFFmCykZSmiCl-MwjHhxO9c1SlT4pDN3c5dt-V9lYGkGv-K1j392wPZOxnoH92AhX1k-lJirRrgMSj6TgQuUQynaxTL01zwD1ilNuAa6966U-KP7V5peoq-4oENlEhhRdW8HjoHl1jQlP00_7K2f5TFmzKyNPHxq7londzlTpautQp59102404xO7CRjTq4hncweSopzlR0CsSQZmy9ZDwbfOIQczBwY1lwfLvlEflZAzRgDPu-CcXTLivLNmHlXKKBKHQd35sxO3KDmgscSZuO61DvEE3SvWK_XYA46vSSHa4OSWZG1V7IDJHddPQJ65kWHbHfxCVhPY_yH52_jtgjOTUBRt_3mMFizWGenQY-tpWoe7Fy-Ex9vzXGDPi-D9QlmluqCZ1Oj0hv5LJbv65AAh5sLSR2lb_Gs1lEI8_ZMoypadUWUTAdiIQqx4nEDn6Yf9oSWVGxiPxgPlFcn_Upkf0MZqookTf7ZVlpgon2lA5MRP9O3-V9EdU8WsAfw2VV3UlygpAOHs0UQA0C691CY3PHjckcRonszezCd2JPmPlIdm-gh2aubk2IUE9NMaVdgRtc-8ysv7GHnGCvmp8FKDS5f4XytuXO_hEOOn5T8Ug-iENW4WOkIJ0jbtmz15NITlrVbPAnGhMSW0y6BfsSn-b9kloFDCA-Mbb4S-IMY8v80M4OkuhV83WPHsXl3yFEiokO02MphzPvhjoixb4OhnsTKG9vUyw4E4wJgGlxGSczNdkBcqiRISJviiRAxnpPQ4XEQ-RkuOjs1AB_cegluyWezH5LovF4S598IJYOAi1oL6Txe0gw4kJVhBmG2hKBscezt30Deu26Qx3Etk9cN3XMirfot7dBoyNZS1Jj2fpsoMbPpxwLhsIIWbWUuN2nKDqDrK199AzGD8-lki0LZh0QOxBcqbtgDDMWp_BpUtutFWL6TZm8DObtIbl4fGy12y1t4kaN-E9mLpzXQXOVjrUbP_tQlNZk7p5YOTeV_NnpunzpNpAbHXXQIukQ1xOlGvHFZ6CRFC-Yknx72aizrZf6aZH_gy9pWKmOhdqWFQ2PJLqGVLIo3mS4yoFC04AivGXdAjdrZB7odufujij9dspXWBO4Tv-dzL29O-j6p-eT6y0HuKachlFpLKpJxzsjIU1DjX0P_0pSVhemfpZDh_nV9eC2w7XNm6logVPIolXiQeypd70LOKnb-wGwxRNlcus6BUSF_BIlplV1S0TTne5PgYU3OCuOPJAwSEW0Q0lkm3lTU8nLyiQd25bV5UeD2wPvxACIPM7_cUyoGkSQ96Ip-NM607-e912AEVR93ZIVK-UHcu8MxSwWCykNaokgs4mEVK5QkY=",
},
{
"type": "text",
"text": "I need `shop/validation.py` next to see how it treats zero, negative, and "
"non-integer quantities.",
},
{
"type": "tool_use",
"id": "call_6JuM80yE9acKhYmgxQKWll9Z",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 120},
},
],
},
)
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "openai/gpt-6.1-sol",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "openai/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6.1-sol",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"include": ["reasoning.encrypted_content"],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "resp_03474a48789eb520006ac3f01d28ec87d092a151bed4f1cde6",
"object": "response",
"created_at": 1791225885,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225886,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"moderation": None,
"id": "resp_0af67cb78bead2c6006ad023a7273487d0b1768b77f6956b73",
"created_at": 1792025511,
"completed_at": 1792025514,
"instructions": (
"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 "
"messages client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
"output": [
{
"id": "msg_03474a48789eb520006ac3f01e31e887d0a7384c283c8d0934",
"id": "rs_0af67cb78bead2c6006ad023a85d5c87d0810de0f56bf80208",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COqmCc2HPj-8NSt1bzfstH4-YXiTtNvZLyVMciprSqFmNbPXwcPXWrps8lsryqoAY5MuRQ_pO9yNIsCVBRlHXitSdObtJRB5Ld7TGQnbUekIsl2TNIFPsnnc8PYSdVrJlcG3FZmykyeSVHblM5F9SaPzHFzOfvCdYQtN52yt2lPhjYailjRidMwkl4KDGQ1BlcR3U29KKxo0020AqMMvsAht5kx5aAFaKfaIum5jctQrjgL8Y99h6sV3gc3LwI0W6ZR2IIqs6e6ADrVIGdVmSpn2GZTHmz6vUFaROU2-UTbVL7QrCy0BUg5CEqjnZ563lqsEYuWOxTVK0RXCPonWwmhfSllKffjLxtGuaq4dtl6v3lGIt-BW3-gJ1WqhtfTDV5VWTAliJhx09kgGhXz7VuxQRQMBSy--M9nBhdNJ1KfkbC0YDUcq5LT_cKh-KZU_-jNWCSQa7hvNJP-aCQ85oL-av-9fT5Wb5ovLUzELiBDooQLH8SalXQgFo-GX_wvSF-IH7byXwCka0F9fyIW6FjmRkirX8h_WF7pLDJeZDO5_8BWbxGOxDI6hEURHW9HLGG-e8S_lp1cVc7i37r-3KNqOwVlnlxEn2hj9TmDvTxRk4yv71AoSuwF8j3Wsh-im1HgmsNf9sdKZIZUTJTdvGCNuf54xXedUEdfoInFspUuiLXj_5KwWpckwJD0y1Fs8oEfTq2Y0Bn3LdBvwrAGgijcwnDsj6nRa2L9oMLrbHROG3xWIuTC6JyKIlVo8o7cGsM6XdxV6P9f3Wc-UgScNzc-fleF3oWzVq2gENtufLiwn9y3z1k_Hb62pbgIV6dmhLepqVH7WAyHajYt9GyxHB_FZbni-_rujbci3-3Jcj451W8PFg0TjhlyUzETBQwv6y6-zORZcbD7TqKe6XnUUGxHEMbPKBCmiIxOIUuOHpNOEjmdQpgOuPR16k_j0YjoA1gJJovIqwB1g6w44nebjzzsky0uRWmIhqeNaIFPPtIUDr05z1ocxgFeHJxum5YAh4d46vUY18dpffRyghwrd1rvIxk2EWW2rmruR4nEDTT405t3RX4kjnhGHuyShSLM_jinQm5LcpLDXUWgRnilpB1RVB8eZUSNYePAhgDRbacr8IC4AvQ7X8xUtcglbDJmMYQZQRFrkGfVoMUcyAkEJamLjccYDFrO5rxUFfyUHmGVxFUY85NW9XCwAFOx7h3606gjN9KVKQPMAg-dUnXbfhc4PCY3iRaS0djErOEugRN6f7iniy8td2YRI2WhPD5O1-qsvTDfiIhymTFq2L0v4f3UEeIa2wnfq4EdnAgla4D14w7T1D1Wg4SiP-dnF0_vKy8md5vlQjpbPGbYJkzB9DBNwJ8qR-7s1jCtZj2fViHuIGwTReI3OXUoeao4FHC8pndoAZbEpbTmax7BEYw7JqlUhIXWF2x8NzeYr-sjBbo1kbzKbtnidxOwrngjU428TzTPEjr9WA9VpmxXNoSOPL7I_qsN8ulnGegsnxQOEIarRK9CE7C8AwtMRMi8lClAFaMwMAoD8jWMNCSEa6mtyv08AikNCt3ij6cW2JszTRO3Qu4lRTsSnta41Qyk16Zc4xEPOs58PhY90t_atHYUWRpydUerE2nvRnPF9eTbQvSe8-iZ0BqkXqdlnVAAIzwOIfVZRua0p8eU3iPlzKteg9F02Jb5HkOsvi2Y4M-ZS5i0Tg4iOeuKHkeiFdZs6EMytIwz6lPGKLhYii6HW0Oe0KU_WQrIVNdXMcs5EWZGqMIdEhf09ZpO3ONcWIYswjgng6W8WMqwplHyHMcjnhzaVbIhs6rsVgTwGJawtbmD5q6aYnJCRq4zI68wzKOe7d6av8jwMGZS-dd8cdHj_XyShws1cWLhLJCaGW_vHKA0i-D1WTDeKSev31IQKCXBSRMB5URPkHu6dNDm1UyDiLGlJBx6iuKTizGeGhb4o2SQ1y1ISKyQRhKuNih0XgY40hn4x-6Scqu6_thPey-4F32BeTnbzNLGQ0wXE--dcIVRbAZMEB7wn7V4mRczG4gTG9ZnqarfZnHMPVUTZ0AxxZ2d_ifef1wQv9aRyKNRVLiBxvSqJtu7NnDMZT_U8mXCc_OIREi9wn-6esDbmxYYeBpNPR6Oq0fbsBbr--A_nVUz99MAAvkSnLhV3zdAHmMgjqNJNCmr2kPtGyle-GqdBx0LYQh4mtc5FdqLZUz9dz6gv_ERua952na3S1UnJr__8zVwofLEPGjiC5_g1nQuVCRE3QVSufMmw4gQL5kdUSuZGEm3RN__6DwAIS_X-E-aBv3utOMs92JWGandVEze8K7p4wQr3gSL5zlepjWHeYPZjiXCnGY=",
"summary": [],
},
{
"id": "msg_0af67cb78bead2c6006ad023a9b1e487d09ad5bb0d5cc96bde",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_0af67cb78bead2c6006ad023aa22c487d0b76512608a221ae3",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_H6dablHqZFScV63Y29mQXJvf",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 140,
"output_tokens_details": {"reasoning_tokens": 75},
"total_tokens": 449,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDphMTYxN2NmYzNlODRjNzYxNDdjNTgxMmFhMjIwNGU0MDczOTM0M2YyMTg4YzQxNzIxMzRlOTc1ZTQ0YzQ3MjgyO3Jlc3BvbnNlX2lkOnJlc3BfMDM0NzRhNDg3ODllYjUyMDAwNmFjM2YwMWQyOGVjODdkMDkyYTE1MWJlZDRmMWNkZTY=",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDphMTYxN2NmYzNlODRjNzYxNDdjNTgxMmFhMjIwNGU0MDczOTM0M2YyMTg4YzQxNzIxMzRlOTc1ZTQ0YzQ3MjgyO3Jlc3BvbnNlX2lkOnJlc3BfMGFmNjdjYjc4YmVhZDJjNjAwNmFkMDIzYTcyNzM0ODdkMGIxNzY4Yjc3ZjY5NTZiNzM=",
"model": "openai/gpt-6.1-sol",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 140},
"content": [
{
"type": "redacted_thinking",
"data": "litellm_encrypted_reasoning:gAAAAABq0COqmCc2HPj-8NSt1bzfstH4-YXiTtNvZLyVMciprSqFmNbPXwcPXWrps8lsryqoAY5MuRQ_pO9yNIsCVBRlHXitSdObtJRB5Ld7TGQnbUekIsl2TNIFPsnnc8PYSdVrJlcG3FZmykyeSVHblM5F9SaPzHFzOfvCdYQtN52yt2lPhjYailjRidMwkl4KDGQ1BlcR3U29KKxo0020AqMMvsAht5kx5aAFaKfaIum5jctQrjgL8Y99h6sV3gc3LwI0W6ZR2IIqs6e6ADrVIGdVmSpn2GZTHmz6vUFaROU2-UTbVL7QrCy0BUg5CEqjnZ563lqsEYuWOxTVK0RXCPonWwmhfSllKffjLxtGuaq4dtl6v3lGIt-BW3-gJ1WqhtfTDV5VWTAliJhx09kgGhXz7VuxQRQMBSy--M9nBhdNJ1KfkbC0YDUcq5LT_cKh-KZU_-jNWCSQa7hvNJP-aCQ85oL-av-9fT5Wb5ovLUzELiBDooQLH8SalXQgFo-GX_wvSF-IH7byXwCka0F9fyIW6FjmRkirX8h_WF7pLDJeZDO5_8BWbxGOxDI6hEURHW9HLGG-e8S_lp1cVc7i37r-3KNqOwVlnlxEn2hj9TmDvTxRk4yv71AoSuwF8j3Wsh-im1HgmsNf9sdKZIZUTJTdvGCNuf54xXedUEdfoInFspUuiLXj_5KwWpckwJD0y1Fs8oEfTq2Y0Bn3LdBvwrAGgijcwnDsj6nRa2L9oMLrbHROG3xWIuTC6JyKIlVo8o7cGsM6XdxV6P9f3Wc-UgScNzc-fleF3oWzVq2gENtufLiwn9y3z1k_Hb62pbgIV6dmhLepqVH7WAyHajYt9GyxHB_FZbni-_rujbci3-3Jcj451W8PFg0TjhlyUzETBQwv6y6-zORZcbD7TqKe6XnUUGxHEMbPKBCmiIxOIUuOHpNOEjmdQpgOuPR16k_j0YjoA1gJJovIqwB1g6w44nebjzzsky0uRWmIhqeNaIFPPtIUDr05z1ocxgFeHJxum5YAh4d46vUY18dpffRyghwrd1rvIxk2EWW2rmruR4nEDTT405t3RX4kjnhGHuyShSLM_jinQm5LcpLDXUWgRnilpB1RVB8eZUSNYePAhgDRbacr8IC4AvQ7X8xUtcglbDJmMYQZQRFrkGfVoMUcyAkEJamLjccYDFrO5rxUFfyUHmGVxFUY85NW9XCwAFOx7h3606gjN9KVKQPMAg-dUnXbfhc4PCY3iRaS0djErOEugRN6f7iniy8td2YRI2WhPD5O1-qsvTDfiIhymTFq2L0v4f3UEeIa2wnfq4EdnAgla4D14w7T1D1Wg4SiP-dnF0_vKy8md5vlQjpbPGbYJkzB9DBNwJ8qR-7s1jCtZj2fViHuIGwTReI3OXUoeao4FHC8pndoAZbEpbTmax7BEYw7JqlUhIXWF2x8NzeYr-sjBbo1kbzKbtnidxOwrngjU428TzTPEjr9WA9VpmxXNoSOPL7I_qsN8ulnGegsnxQOEIarRK9CE7C8AwtMRMi8lClAFaMwMAoD8jWMNCSEa6mtyv08AikNCt3ij6cW2JszTRO3Qu4lRTsSnta41Qyk16Zc4xEPOs58PhY90t_atHYUWRpydUerE2nvRnPF9eTbQvSe8-iZ0BqkXqdlnVAAIzwOIfVZRua0p8eU3iPlzKteg9F02Jb5HkOsvi2Y4M-ZS5i0Tg4iOeuKHkeiFdZs6EMytIwz6lPGKLhYii6HW0Oe0KU_WQrIVNdXMcs5EWZGqMIdEhf09ZpO3ONcWIYswjgng6W8WMqwplHyHMcjnhzaVbIhs6rsVgTwGJawtbmD5q6aYnJCRq4zI68wzKOe7d6av8jwMGZS-dd8cdHj_XyShws1cWLhLJCaGW_vHKA0i-D1WTDeKSev31IQKCXBSRMB5URPkHu6dNDm1UyDiLGlJBx6iuKTizGeGhb4o2SQ1y1ISKyQRhKuNih0XgY40hn4x-6Scqu6_thPey-4F32BeTnbzNLGQ0wXE--dcIVRbAZMEB7wn7V4mRczG4gTG9ZnqarfZnHMPVUTZ0AxxZ2d_ifef1wQv9aRyKNRVLiBxvSqJtu7NnDMZT_U8mXCc_OIREi9wn-6esDbmxYYeBpNPR6Oq0fbsBbr--A_nVUz99MAAvkSnLhV3zdAHmMgjqNJNCmr2kPtGyle-GqdBx0LYQh4mtc5FdqLZUz9dz6gv_ERua952na3S1UnJr__8zVwofLEPGjiC5_g1nQuVCRE3QVSufMmw4gQL5kdUSuZGEm3RN__6DwAIS_X-E-aBv3utOMs92JWGandVEze8K7p4wQr3gSL5zlepjWHeYPZjiXCnGY=",
},
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
},
{
"type": "tool_use",
"id": "call_H6dablHqZFScV63Y29mQXJvf",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "openai/gpt-6-astra",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "openai/gpt-6-astra"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6-astra",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"include": ["reasoning.encrypted_content"],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, "model": "gpt-6-astra"},
mock_provider_response={
"id": "resp_023f789546179f0e006ad016c0984487d08dba1308aa780ef6",
"object": "response",
"created_at": 1792022208,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792022211,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-astra",
"moderation": None,
"id": "resp_0964a41f58153ac5006ad0238f9bc087d0a9e79fda375bee3c",
"created_at": 1792025487,
"completed_at": 1792025491,
"instructions": (
"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 "
"messages client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
"output": [
{
"id": "msg_023f789546179f0e006ad016c2ef2c87d0b9d8f5ef59e691cd",
"id": "rs_0964a41f58153ac5006ad02391213887d0a1c21052bdd0c548",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COTU7GaEIVpMk00EB_rxvW069YSty7ozHW12516PLbLq0b935jCB0GevftK_27zbuIgpBhSTV-H3eiUTLx-CrGm41k8lA9CdDmFNKWBGef5fUtpfXIKNAPT3WRIkUe6ZrrMCLRa3zMhaitRJjxMf8RWRQGf0LqeomxdgNtJPU_YjiG2gapnmiUh8KSlqt30UqjcUVgjbw6isCgofeLdsvBDjy1GWfE81FTcapzObq-LzPlR6Lw838JvbjKJmBaT6B-g3UIy4ZpHCEOsLKRHdlSG97KHy84JwcRU4W1GB259oCQmWs7TRyA8BJao1vs5JrCmT0XdABCyrhUOERc7d8N0qBri6XJaVz3v1FmUObP1oz4I7Z47lqjX0a32_keE4AqjTP2evWOvjOnGsH5PVMsWknZWuvmKMYZefWuy0d7L5IUpPZ9pL4oZDgygSTH4nQ5t1ZWeYDIOKDf4oB0aTHAfgLO_IS-XgbRNMloPbeRm4acU9BI9KqGZShTVhBX34ZEc4ov7hpSmzTSUl1ukSsUmmxHqNLtKbz5CAZaYbBFM53KAyS6Bkexp6F1y8z6zKmy-LFENx-W8bZQIVaYmFAWwajro57XZE3qugHkWwCTOrP1HANsXIXXZ0wYhUdgvDqLxeRkOcaw7DAINL8K6zK71wt7Qc_j177tZjIr9uxXzEpQ3mu2p7Ji-ZBR6YRYx9sNrS55Xt5iMZYhW1X73I04pXIR5xsGO7hWZV1cGXCpWBXJ5vmMfpi4AXERmas0PAnDXEX4CRtdXflugJw7AvYDq5nY24xDYdCV9DuFF4VBzUXrWHG29OWbVzGwIegWrBEXiNIEoL4vJ05l_SqljbzKZtDg0kvY-6DnV7NwBkCYk6UgfRvJ5h8IKb7KPj7qcUhI3Zi7WXQf4yk2tH_MnM713aQ4ywDQorMJfzTcs11TABEPUwyuWt5_IHLB76c6bK97Uf8N7PkgseQ3BmPf9COF0K2JpyyUxBQOn8V5KjMK_2VTLGHQYsMA3AnX13t-_cde99USqDGqQa67C0EcbIbmHsAuctgYQP1rA_1GUB7A6oY2e1RUSoTNR3agm1FOnvAsVIjU9RW65gsI0uyz1VyIh6ZN3Ju7nqWldSDh00hIqT9bX6ctkSCZjb0Juhws_7yD7mIrykX51AfijJqCxOwI4clnITCrt2SLjuviYKxzfjCvj95107ui2fNVyWj7ksEFOX4gyA23ANATQgCWO0ITxVGnYAmZpiBSUNiJYsRUtCT6qQ1-NULhAn9UWuQJROqfJ4zACjY34kD9TtGhaLXJpKJjGw-YZ1iDUPGRG0NqPLBvI__8abyYLvA_une1qnEE49xseuR5-9uC51CpWr-Z5r40Q-Ner12_Em0p52GP52w3R14BHbuKqIDG0I1Xd47LjoNRLx7p25iivbyrcq-veIQJfKIPs4DGoAFkSyJe7z1kIuThQlusfYSaMffWXsOyWGS5jLsPSF8bRyUdfpR28wUqvbwkQFXs_5GRJLzAtBLSIJRW_SZ4mCt65B4kzkwzXJJBPvrmx0Vh2_rz-eufHW3S5S4VPsQg6nED3PB213LNzlMwwcm1KuEj0CpUXbffrKslKhEFfIFDdMchXP99i9UteCUipYdAWcXZCRYhAgMWQMdmEVVxtQRM34D-YVonMxnCQivNWYp99EhWGBfZZ-ffKV9c2WWboXUpVV_Oj8tqDIADyvRzJOd2-dGpDY2OdMzG31-ADUK-bXg68gHNSMRubpwPi7h_GBfYzPFCOFl3xaGRGE-6CH7AtzvHkZvUnrq-N5ArEv6hdhBA3qQZIh0rlyLXgNLbNz2KnP8lD7SOnGGz2sHVXoXHpW4Zu8V0coR6bxlAJ4Q5BTpcygg0q_BBWL2gr8uhxmP95XE0ANrRX8anoFoOmpS75iAsxBmkjYw8XyLWKUTj_4api4Xb1826PVTRW5x2rScJzmjVLM9AI3QiT05WSXE68NwOTO3GtYkNhDZYzBV6Aoya9f4lJwQKK76mfF8HRUen1AK4fD1X7cyI9NX9kisBrPS9YplUqF0PyFUsrL1aH6DXXmgrnsQ_V7QkMPEVwzd7NEFhHf1VbuJVzWMwzGK5OqROKxCjAY1mb34iK2r6LytJ6pX-oBIzKE7XfxcVTzzOutKdVnp_I3O9uI-BG-5Xj3degzcAdOZZbiPXNmh0kERrBgE620s6bAGiG5OGIfpS5mu4JbA1wL1nBfAC_pgdgh-62Kgo2GunkczL8Zrddxj_Xia_VBDyk6ptWYhETE4P-WWq-3wS2kUKEtuf_VPij-xi2imKOoF-NaA6rDUSoEKxqndBJsAZlAQOfX1OvkN8q44Am4RiZkzEfQEbHlde7ziC1WCVU9zsjWXe8V4EJ78CxWENhtbmF3BhUHTYaywoItp0PhYf1l7FVI7FWxXQCOX5h5MvOIzr4nf-8dMyMRR7q35aHyosc6RqOGY6OofOBcDcqFHpHAcW602H-vS2_fj7fOqCqBDmqcmEriPIBFbczBbFFZQ==",
"summary": [],
},
{
"id": "msg_0964a41f58153ac5006ad02392bf8487d0ba759f0a48ebb3c9",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.\n",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_0964a41f58153ac5006ad0239340f887d0a46fc41789aa1a55",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_eqYF3Vli8ZUYaCLw3MAUvxKq",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 152,
"output_tokens_details": {"reasoning_tokens": 87},
"total_tokens": 461,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDphODRkZDk3MTcwNzk0ZDlhYzQ5ODhlZWMzOTJmN2Q5YjQwN2MyNDY1YmJhZTA4MGE1ZGYzMThlOTViOTA2NzlkO3Jlc3BvbnNlX2lkOnJlc3BfMDIzZjc4OTU0NjE3OWYwZTAwNmFkMDE2YzA5ODQ0ODdkMDhkYmExMzA4YWE3ODBlZjY=",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDphODRkZDk3MTcwNzk0ZDlhYzQ5ODhlZWMzOTJmN2Q5YjQwN2MyNDY1YmJhZTA4MGE1ZGYzMThlOTViOTA2NzlkO3Jlc3BvbnNlX2lkOnJlc3BfMDk2NGE0MWY1ODE1M2FjNTAwNmFkMDIzOGY5YmMwODdkMGE5ZTc5ZmRhMzc1YmVlM2M=",
"model": "openai/gpt-6-astra",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 152},
"content": [
{
"type": "redacted_thinking",
"data": "litellm_encrypted_reasoning:gAAAAABq0COTU7GaEIVpMk00EB_rxvW069YSty7ozHW12516PLbLq0b935jCB0GevftK_27zbuIgpBhSTV-H3eiUTLx-CrGm41k8lA9CdDmFNKWBGef5fUtpfXIKNAPT3WRIkUe6ZrrMCLRa3zMhaitRJjxMf8RWRQGf0LqeomxdgNtJPU_YjiG2gapnmiUh8KSlqt30UqjcUVgjbw6isCgofeLdsvBDjy1GWfE81FTcapzObq-LzPlR6Lw838JvbjKJmBaT6B-g3UIy4ZpHCEOsLKRHdlSG97KHy84JwcRU4W1GB259oCQmWs7TRyA8BJao1vs5JrCmT0XdABCyrhUOERc7d8N0qBri6XJaVz3v1FmUObP1oz4I7Z47lqjX0a32_keE4AqjTP2evWOvjOnGsH5PVMsWknZWuvmKMYZefWuy0d7L5IUpPZ9pL4oZDgygSTH4nQ5t1ZWeYDIOKDf4oB0aTHAfgLO_IS-XgbRNMloPbeRm4acU9BI9KqGZShTVhBX34ZEc4ov7hpSmzTSUl1ukSsUmmxHqNLtKbz5CAZaYbBFM53KAyS6Bkexp6F1y8z6zKmy-LFENx-W8bZQIVaYmFAWwajro57XZE3qugHkWwCTOrP1HANsXIXXZ0wYhUdgvDqLxeRkOcaw7DAINL8K6zK71wt7Qc_j177tZjIr9uxXzEpQ3mu2p7Ji-ZBR6YRYx9sNrS55Xt5iMZYhW1X73I04pXIR5xsGO7hWZV1cGXCpWBXJ5vmMfpi4AXERmas0PAnDXEX4CRtdXflugJw7AvYDq5nY24xDYdCV9DuFF4VBzUXrWHG29OWbVzGwIegWrBEXiNIEoL4vJ05l_SqljbzKZtDg0kvY-6DnV7NwBkCYk6UgfRvJ5h8IKb7KPj7qcUhI3Zi7WXQf4yk2tH_MnM713aQ4ywDQorMJfzTcs11TABEPUwyuWt5_IHLB76c6bK97Uf8N7PkgseQ3BmPf9COF0K2JpyyUxBQOn8V5KjMK_2VTLGHQYsMA3AnX13t-_cde99USqDGqQa67C0EcbIbmHsAuctgYQP1rA_1GUB7A6oY2e1RUSoTNR3agm1FOnvAsVIjU9RW65gsI0uyz1VyIh6ZN3Ju7nqWldSDh00hIqT9bX6ctkSCZjb0Juhws_7yD7mIrykX51AfijJqCxOwI4clnITCrt2SLjuviYKxzfjCvj95107ui2fNVyWj7ksEFOX4gyA23ANATQgCWO0ITxVGnYAmZpiBSUNiJYsRUtCT6qQ1-NULhAn9UWuQJROqfJ4zACjY34kD9TtGhaLXJpKJjGw-YZ1iDUPGRG0NqPLBvI__8abyYLvA_une1qnEE49xseuR5-9uC51CpWr-Z5r40Q-Ner12_Em0p52GP52w3R14BHbuKqIDG0I1Xd47LjoNRLx7p25iivbyrcq-veIQJfKIPs4DGoAFkSyJe7z1kIuThQlusfYSaMffWXsOyWGS5jLsPSF8bRyUdfpR28wUqvbwkQFXs_5GRJLzAtBLSIJRW_SZ4mCt65B4kzkwzXJJBPvrmx0Vh2_rz-eufHW3S5S4VPsQg6nED3PB213LNzlMwwcm1KuEj0CpUXbffrKslKhEFfIFDdMchXP99i9UteCUipYdAWcXZCRYhAgMWQMdmEVVxtQRM34D-YVonMxnCQivNWYp99EhWGBfZZ-ffKV9c2WWboXUpVV_Oj8tqDIADyvRzJOd2-dGpDY2OdMzG31-ADUK-bXg68gHNSMRubpwPi7h_GBfYzPFCOFl3xaGRGE-6CH7AtzvHkZvUnrq-N5ArEv6hdhBA3qQZIh0rlyLXgNLbNz2KnP8lD7SOnGGz2sHVXoXHpW4Zu8V0coR6bxlAJ4Q5BTpcygg0q_BBWL2gr8uhxmP95XE0ANrRX8anoFoOmpS75iAsxBmkjYw8XyLWKUTj_4api4Xb1826PVTRW5x2rScJzmjVLM9AI3QiT05WSXE68NwOTO3GtYkNhDZYzBV6Aoya9f4lJwQKK76mfF8HRUen1AK4fD1X7cyI9NX9kisBrPS9YplUqF0PyFUsrL1aH6DXXmgrnsQ_V7QkMPEVwzd7NEFhHf1VbuJVzWMwzGK5OqROKxCjAY1mb34iK2r6LytJ6pX-oBIzKE7XfxcVTzzOutKdVnp_I3O9uI-BG-5Xj3degzcAdOZZbiPXNmh0kERrBgE620s6bAGiG5OGIfpS5mu4JbA1wL1nBfAC_pgdgh-62Kgo2GunkczL8Zrddxj_Xia_VBDyk6ptWYhETE4P-WWq-3wS2kUKEtuf_VPij-xi2imKOoF-NaA6rDUSoEKxqndBJsAZlAQOfX1OvkN8q44Am4RiZkzEfQEbHlde7ziC1WCVU9zsjWXe8V4EJ78CxWENhtbmF3BhUHTYaywoItp0PhYf1l7FVI7FWxXQCOX5h5MvOIzr4nf-8dMyMRR7q35aHyosc6RqOGY6OofOBcDcqFHpHAcW602H-vS2_fj7fOqCqBDmqcmEriPIBFbczBbFFZQ==",
},
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.\n",
},
{
"type": "tool_use",
"id": "call_eqYF3Vli8ZUYaCLw3MAUvxKq",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={**MESSAGES_REQUEST, "model": "openai/gpt-5.6-terra"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, "model": "gpt-5.6-terra"},
mock_provider_response={
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-5.6-terra",
"id": "resp_08526ccab9aa653e006ad023884a1c87d09a23f6d5c61d65d3",
"created_at": 1792025480,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025481,
"instructions": (
"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 "
"messages client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
"output": [
{
"id": "rs_08526ccab9aa653e006ad02388d60087d0909f13870c67fc8c",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COJ5vm7lH4CvuQJznQ9B0y2iQwRylfHyiFtKnR3At3jt1oCNRl_9-mCg3S5oBCgnMLM9u4EviSSArrlNlXBn1QqjilF0jg47ecCqzcLjNkSXQfvCFKM3N9QUb33bNkruIA9VTZFJb2Dh4CWd_8uP4W2lHVfLiTcp5WGy301lO_5a8hbuO2sv08S4I0Ug67I-EFi_BMZyauCNqY8Zmbf7CodUc6cDluIeFClKOnXPaM-I4SunKVAvTZz_BsvmO-hhV2ajhBia68VqMhlioEyJQR0g5ouQrY_mhhMs99sOn4-V8aIrlkDfIGz4SEwXGRd55MSGRa095JCZig1Jzm_CdublE9Dkc0EsbJB6xjrJZfAyJZVGB95xOOsWHafy0MW878IqJNivjj6XULFSHOuVwm3WqA4_L0GKv5o0eor3OYggauA4AgKx0FiTaUAlCm5tNy2qSGMzCcKWp85CrItPYZUhWgkn4lcwGhGpJ20kmOHQbOGxnMtSpaTJL6PuMC0oyXWJli9qjaaIaB5cGhvoOtkBzifPh8pSZVsRNAnO7q7S72Lk4MtpRqCVIAVeB6kXTmkqMLhLghRowcd8xemlswAOCLqnR2usZncZIbY3kGqprxWA7u9w_acwISRcQZE6rmnefcK4I7NpA2zEuVcEVJndBWZbApBZE_OZFg7doNuw9cqhk-4y3VePW6fjSA8e68gX0VslTHODd2W6o16LQuGA-Zp84T0W0NuYI0Y2zY6AEY63DW2fDbKlbvRc5Shm5sPIugD0bWsR2SRkEMgvFnYalZFlwSojKIsxw1ET55tXqjiP4TLg1-Q4vnSkIR4dxP6lubbeN-SLCY2Nq6MVW5rqnh6o_AkFZHemKqdjFNzy5lR3JYs_4bhYetICCYSqLQVp8Cy1wmUkNeleyPjayQJFAF7lhY4mN9VUJxut-H7aizH9W0QGfoIukNLJOc3gZ7svAa3jElXtTef8Qv-rmQFA_y-AMRfHZeDLzhtxQnaDmKDeiqimbREwqG1BGvQeEKWCGPba7RGNuks9yYhNvi5NyVsEYXJe5Omy-pTZ47vrRUinlR4ecl75NPz1bL-lLtYhIMtvLtuJvkJ_ieD6g7oP3qEcsS34ARmBq6ZpEkelgL9ifh8DGX9gerq-JbsmnyI-c8aG9Go--hJWXs2dKJSfBq1ABLhhW3rK3Ms5163BkdtZp67F0LPISjU8i4Kh_wSxZbqXkdJy-4oYgAqG_YGQMz5tyM3GFMj-ozDuznqivj3GcD7xRTTA2CfDTbFxT1mrTpLv_NjKsfjMOSH5KF5RLwP8fatr76F0YUKW75korD9RG0tJpbSHBq67r4u0jwyNRJFZMPsmvOohr4GaTOW3-kBfUZqVU7x2X6cjmfw50jY4EOQb1r4sJBbVkgqTcw36zPSzR46dkJHUtEZMqNgb0u8AUze_Z1Or3x0DInw6xMSAs2jzYNEiIYzJ0EJ62_ciEcWT5aYUGSZGhNy2i9dIEJiOTYfzL-b7dNzs-6MoWMHzMaPPPcp4e8BLCgDJd6ryDuuHRd7NZmEnt2jdUlKr4iqEstENijjJjdl1xolCtUMPYQahG9iYPMa2tKqXAZYTyf6_cEdv6_7kUdFd6iUuU7kOplokkOi9A-GbA0Lhhct5HP3QYxMSymUoMv_NO6xjgAImYwesVohnAaN1hNmraWuavZKj4w95byYav83k0xFB_mz3xKYjLsCtTw3rF90UsWk4KgXnoZRZv0FcesyyNAXfzizkgsI0Ndt4i8EIHhP6upFi473ZMqbWo5_RQtAiKsHBD1L5NG51Lai2caL5bnvOrHtfW_aZcLGNdFQbziTpTFwafefusBSGR0hLHc0LzKpMg-XDCwzU8AnK3yngTTKnOb9j0_avEdz5xv9xnLlp5rnHtMrYRna-5HPQ2xKIXmGzbMx2h8OQYdWTqmVayubLoc-KpW0qKYxYJRRIgo=",
"summary": [],
},
{
"id": "msg_08526ccab9aa653e006ad023892c7087d0870b4b072127659f",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "Next I need `shop/validation.py` to inspect the validation branches for "
"zero, negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_08526ccab9aa653e006ad02389692887d0ab14a9eaef763aee",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_iom4KPAiRrGmsYIsEHwM2vZo",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 107,
"output_tokens_details": {"reasoning_tokens": 42},
"total_tokens": 416,
},
},
expected_litellm_response={
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDo0Mjg5MWEzMzRjNTlhMjhlMjQ2MjQ0YTQ4YTJjOGVlMTM5NGYyZGNhZWMxYmVjZDhmZDk2N2NmNjYxNWNmZDM5O3Jlc3BvbnNlX2lkOnJlc3BfMDg1MjZjY2FiOWFhNjUzZTAwNmFkMDIzODg0YTFjODdkMDlhMjNmNmQ1YzYxZDY1ZDM=",
"model": "openai/gpt-5.6-terra",
"usage": {"input_tokens": 309, "output_tokens": 107},
"content": [
{
"type": "redacted_thinking",
"data": "litellm_encrypted_reasoning:gAAAAABq0COJ5vm7lH4CvuQJznQ9B0y2iQwRylfHyiFtKnR3At3jt1oCNRl_9-mCg3S5oBCgnMLM9u4EviSSArrlNlXBn1QqjilF0jg47ecCqzcLjNkSXQfvCFKM3N9QUb33bNkruIA9VTZFJb2Dh4CWd_8uP4W2lHVfLiTcp5WGy301lO_5a8hbuO2sv08S4I0Ug67I-EFi_BMZyauCNqY8Zmbf7CodUc6cDluIeFClKOnXPaM-I4SunKVAvTZz_BsvmO-hhV2ajhBia68VqMhlioEyJQR0g5ouQrY_mhhMs99sOn4-V8aIrlkDfIGz4SEwXGRd55MSGRa095JCZig1Jzm_CdublE9Dkc0EsbJB6xjrJZfAyJZVGB95xOOsWHafy0MW878IqJNivjj6XULFSHOuVwm3WqA4_L0GKv5o0eor3OYggauA4AgKx0FiTaUAlCm5tNy2qSGMzCcKWp85CrItPYZUhWgkn4lcwGhGpJ20kmOHQbOGxnMtSpaTJL6PuMC0oyXWJli9qjaaIaB5cGhvoOtkBzifPh8pSZVsRNAnO7q7S72Lk4MtpRqCVIAVeB6kXTmkqMLhLghRowcd8xemlswAOCLqnR2usZncZIbY3kGqprxWA7u9w_acwISRcQZE6rmnefcK4I7NpA2zEuVcEVJndBWZbApBZE_OZFg7doNuw9cqhk-4y3VePW6fjSA8e68gX0VslTHODd2W6o16LQuGA-Zp84T0W0NuYI0Y2zY6AEY63DW2fDbKlbvRc5Shm5sPIugD0bWsR2SRkEMgvFnYalZFlwSojKIsxw1ET55tXqjiP4TLg1-Q4vnSkIR4dxP6lubbeN-SLCY2Nq6MVW5rqnh6o_AkFZHemKqdjFNzy5lR3JYs_4bhYetICCYSqLQVp8Cy1wmUkNeleyPjayQJFAF7lhY4mN9VUJxut-H7aizH9W0QGfoIukNLJOc3gZ7svAa3jElXtTef8Qv-rmQFA_y-AMRfHZeDLzhtxQnaDmKDeiqimbREwqG1BGvQeEKWCGPba7RGNuks9yYhNvi5NyVsEYXJe5Omy-pTZ47vrRUinlR4ecl75NPz1bL-lLtYhIMtvLtuJvkJ_ieD6g7oP3qEcsS34ARmBq6ZpEkelgL9ifh8DGX9gerq-JbsmnyI-c8aG9Go--hJWXs2dKJSfBq1ABLhhW3rK3Ms5163BkdtZp67F0LPISjU8i4Kh_wSxZbqXkdJy-4oYgAqG_YGQMz5tyM3GFMj-ozDuznqivj3GcD7xRTTA2CfDTbFxT1mrTpLv_NjKsfjMOSH5KF5RLwP8fatr76F0YUKW75korD9RG0tJpbSHBq67r4u0jwyNRJFZMPsmvOohr4GaTOW3-kBfUZqVU7x2X6cjmfw50jY4EOQb1r4sJBbVkgqTcw36zPSzR46dkJHUtEZMqNgb0u8AUze_Z1Or3x0DInw6xMSAs2jzYNEiIYzJ0EJ62_ciEcWT5aYUGSZGhNy2i9dIEJiOTYfzL-b7dNzs-6MoWMHzMaPPPcp4e8BLCgDJd6ryDuuHRd7NZmEnt2jdUlKr4iqEstENijjJjdl1xolCtUMPYQahG9iYPMa2tKqXAZYTyf6_cEdv6_7kUdFd6iUuU7kOplokkOi9A-GbA0Lhhct5HP3QYxMSymUoMv_NO6xjgAImYwesVohnAaN1hNmraWuavZKj4w95byYav83k0xFB_mz3xKYjLsCtTw3rF90UsWk4KgXnoZRZv0FcesyyNAXfzizkgsI0Ndt4i8EIHhP6upFi473ZMqbWo5_RQtAiKsHBD1L5NG51Lai2caL5bnvOrHtfW_aZcLGNdFQbziTpTFwafefusBSGR0hLHc0LzKpMg-XDCwzU8AnK3yngTTKnOb9j0_avEdz5xv9xnLlp5rnHtMrYRna-5HPQ2xKIXmGzbMx2h8OQYdWTqmVayubLoc-KpW0qKYxYJRRIgo=",
},
{
"type": "text",
"text": "Next I need `shop/validation.py` to inspect the validation branches for "
"zero, negative, and non-integer quantities.",
},
{
"type": "tool_use",
"id": "call_iom4KPAiRrGmsYIsEHwM2vZo",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)

176
tests/integration/translation/messages/bases/openai_responses.py
View file

@ -1,6 +1,8 @@
from typing import Final
from integration.translation.case import TranslationTestCase
from integration.translation.messages.templates import MESSAGES_BRIDGE_RESPONSE, MESSAGES_REQUEST
from integration.translation.templates.openai import OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, OPENAI_RESPONSES_RESPONSE
GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -100,94 +102,122 @@ GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/messages",
litellm_request={
"model": "openai/responses/gpt-6.1-sol",
"max_tokens": 64,
"system": "You are a terse assistant.",
"messages": [{"role": "user", "content": "Say hello."}],
"cache": {"no-cache": True},
},
litellm_request={**MESSAGES_REQUEST, "model": "openai/responses/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={"authorization": "Bearer synthetic-openai-key", "content-type": "application/json"},
expected_provider_request={
"model": "gpt-6.1-sol",
"input": [{"type": "message", "role": "user", "content": [{"type": "input_text", "text": "Say hello."}]}],
"include": ["reasoning.encrypted_content"],
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST_FROM_MESSAGES, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "resp_03446eafdb61cd31006ac3f046b20c87d0af12e5a0e55548fd",
"object": "response",
"created_at": 1791225926,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225928,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"moderation": None,
"id": "resp_0af67cb78bead2c6006ad023a7273487d0b1768b77f6956b73",
"created_at": 1792025511,
"completed_at": 1792025514,
"instructions": (
"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 "
"messages client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
"output": [
{
"id": "msg_03446eafdb61cd31006ac3f048804087d0a22e0e94d0a6d50e",
"id": "rs_0af67cb78bead2c6006ad023a85d5c87d0810de0f56bf80208",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COqmCc2HPj-8NSt1bzfstH4-YXiTtNvZLyVMciprSqFmNbPXwcPXWrps8lsryqoAY5MuRQ_pO9yNIsCVBRlHXitSdObtJRB5Ld7TGQnbUekIsl2TNIFPsnnc8PYSdVrJlcG3FZmykyeSVHblM5F9SaPzHFzOfvCdYQtN52yt2lPhjYailjRidMwkl4KDGQ1BlcR3U29KKxo0020AqMMvsAht5kx5aAFaKfaIum5jctQrjgL8Y99h6sV3gc3LwI0W6ZR2IIqs6e6ADrVIGdVmSpn2GZTHmz6vUFaROU2-UTbVL7QrCy0BUg5CEqjnZ563lqsEYuWOxTVK0RXCPonWwmhfSllKffjLxtGuaq4dtl6v3lGIt-BW3-gJ1WqhtfTDV5VWTAliJhx09kgGhXz7VuxQRQMBSy--M9nBhdNJ1KfkbC0YDUcq5LT_cKh-KZU_-jNWCSQa7hvNJP-aCQ85oL-av-9fT5Wb5ovLUzELiBDooQLH8SalXQgFo-GX_wvSF-IH7byXwCka0F9fyIW6FjmRkirX8h_WF7pLDJeZDO5_8BWbxGOxDI6hEURHW9HLGG-e8S_lp1cVc7i37r-3KNqOwVlnlxEn2hj9TmDvTxRk4yv71AoSuwF8j3Wsh-im1HgmsNf9sdKZIZUTJTdvGCNuf54xXedUEdfoInFspUuiLXj_5KwWpckwJD0y1Fs8oEfTq2Y0Bn3LdBvwrAGgijcwnDsj6nRa2L9oMLrbHROG3xWIuTC6JyKIlVo8o7cGsM6XdxV6P9f3Wc-UgScNzc-fleF3oWzVq2gENtufLiwn9y3z1k_Hb62pbgIV6dmhLepqVH7WAyHajYt9GyxHB_FZbni-_rujbci3-3Jcj451W8PFg0TjhlyUzETBQwv6y6-zORZcbD7TqKe6XnUUGxHEMbPKBCmiIxOIUuOHpNOEjmdQpgOuPR16k_j0YjoA1gJJovIqwB1g6w44nebjzzsky0uRWmIhqeNaIFPPtIUDr05z1ocxgFeHJxum5YAh4d46vUY18dpffRyghwrd1rvIxk2EWW2rmruR4nEDTT405t3RX4kjnhGHuyShSLM_jinQm5LcpLDXUWgRnilpB1RVB8eZUSNYePAhgDRbacr8IC4AvQ7X8xUtcglbDJmMYQZQRFrkGfVoMUcyAkEJamLjccYDFrO5rxUFfyUHmGVxFUY85NW9XCwAFOx7h3606gjN9KVKQPMAg-dUnXbfhc4PCY3iRaS0djErOEugRN6f7iniy8td2YRI2WhPD5O1-qsvTDfiIhymTFq2L0v4f3UEeIa2wnfq4EdnAgla4D14w7T1D1Wg4SiP-dnF0_vKy8md5vlQjpbPGbYJkzB9DBNwJ8qR-7s1jCtZj2fViHuIGwTReI3OXUoeao4FHC8pndoAZbEpbTmax7BEYw7JqlUhIXWF2x8NzeYr-sjBbo1kbzKbtnidxOwrngjU428TzTPEjr9WA9VpmxXNoSOPL7I_qsN8ulnGegsnxQOEIarRK9CE7C8AwtMRMi8lClAFaMwMAoD8jWMNCSEa6mtyv08AikNCt3ij6cW2JszTRO3Qu4lRTsSnta41Qyk16Zc4xEPOs58PhY90t_atHYUWRpydUerE2nvRnPF9eTbQvSe8-iZ0BqkXqdlnVAAIzwOIfVZRua0p8eU3iPlzKteg9F02Jb5HkOsvi2Y4M-ZS5i0Tg4iOeuKHkeiFdZs6EMytIwz6lPGKLhYii6HW0Oe0KU_WQrIVNdXMcs5EWZGqMIdEhf09ZpO3ONcWIYswjgng6W8WMqwplHyHMcjnhzaVbIhs6rsVgTwGJawtbmD5q6aYnJCRq4zI68wzKOe7d6av8jwMGZS-dd8cdHj_XyShws1cWLhLJCaGW_vHKA0i-D1WTDeKSev31IQKCXBSRMB5URPkHu6dNDm1UyDiLGlJBx6iuKTizGeGhb4o2SQ1y1ISKyQRhKuNih0XgY40hn4x-6Scqu6_thPey-4F32BeTnbzNLGQ0wXE--dcIVRbAZMEB7wn7V4mRczG4gTG9ZnqarfZnHMPVUTZ0AxxZ2d_ifef1wQv9aRyKNRVLiBxvSqJtu7NnDMZT_U8mXCc_OIREi9wn-6esDbmxYYeBpNPR6Oq0fbsBbr--A_nVUz99MAAvkSnLhV3zdAHmMgjqNJNCmr2kPtGyle-GqdBx0LYQh4mtc5FdqLZUz9dz6gv_ERua952na3S1UnJr__8zVwofLEPGjiC5_g1nQuVCRE3QVSufMmw4gQL5kdUSuZGEm3RN__6DwAIS_X-E-aBv3utOMs92JWGandVEze8K7p4wQr3gSL5zlepjWHeYPZjiXCnGY=",
"summary": [],
},
{
"id": "msg_0af67cb78bead2c6006ad023a9b1e487d09ad5bb0d5cc96bde",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_0af67cb78bead2c6006ad023aa22c487d0b76512608a221ae3",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_H6dablHqZFScV63Y29mQXJvf",
"name": "read_file",
},
],
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 140,
"output_tokens_details": {"reasoning_tokens": 75},
"total_tokens": 449,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDo3ZGE3NDY3Njc3N2IyZjVkYmQ3MDI1MTI1ZjEzMDdlYWQ0MjM3YTgzN2QxZTJmZDhkY2FkNjhlODM4ODU1Zjg2O3Jlc3BvbnNlX2lkOnJlc3BfMDM0NDZlYWZkYjYxY2QzMTAwNmFjM2YwNDZiMjBjODdkMGFmMTJlNWEwZTU1NTQ4ZmQ=",
"type": "message",
"role": "assistant",
**MESSAGES_BRIDGE_RESPONSE,
"id": "resp_bGl0ZWxsbTpjdXN0b21fbGxtX3Byb3ZpZGVyOm9wZW5haTttb2RlbF9pZDo3ZGE3NDY3Njc3N2IyZjVkYmQ3MDI1MTI1ZjEzMDdlYWQ0MjM3YTgzN2QxZTJmZDhkY2FkNjhlODM4ODU1Zjg2O3Jlc3BvbnNlX2lkOnJlc3BfMGFmNjdjYjc4YmVhZDJjNjAwNmFkMDIzYTcyNzM0ODdkMGIxNzY4Yjc3ZjY5NTZiNzM=",
"model": "openai/responses/gpt-6.1-sol",
"stop_sequence": None,
"usage": {"input_tokens": 19, "output_tokens": 6},
"content": [{"type": "text", "text": "Hello!"}],
"stop_reason": "end_turn",
"stop_details": None,
"usage": {"input_tokens": 309, "output_tokens": 140},
"content": [
{
"type": "redacted_thinking",
"data": "litellm_encrypted_reasoning:gAAAAABq0COqmCc2HPj-8NSt1bzfstH4-YXiTtNvZLyVMciprSqFmNbPXwcPXWrps8lsryqoAY5MuRQ_pO9yNIsCVBRlHXitSdObtJRB5Ld7TGQnbUekIsl2TNIFPsnnc8PYSdVrJlcG3FZmykyeSVHblM5F9SaPzHFzOfvCdYQtN52yt2lPhjYailjRidMwkl4KDGQ1BlcR3U29KKxo0020AqMMvsAht5kx5aAFaKfaIum5jctQrjgL8Y99h6sV3gc3LwI0W6ZR2IIqs6e6ADrVIGdVmSpn2GZTHmz6vUFaROU2-UTbVL7QrCy0BUg5CEqjnZ563lqsEYuWOxTVK0RXCPonWwmhfSllKffjLxtGuaq4dtl6v3lGIt-BW3-gJ1WqhtfTDV5VWTAliJhx09kgGhXz7VuxQRQMBSy--M9nBhdNJ1KfkbC0YDUcq5LT_cKh-KZU_-jNWCSQa7hvNJP-aCQ85oL-av-9fT5Wb5ovLUzELiBDooQLH8SalXQgFo-GX_wvSF-IH7byXwCka0F9fyIW6FjmRkirX8h_WF7pLDJeZDO5_8BWbxGOxDI6hEURHW9HLGG-e8S_lp1cVc7i37r-3KNqOwVlnlxEn2hj9TmDvTxRk4yv71AoSuwF8j3Wsh-im1HgmsNf9sdKZIZUTJTdvGCNuf54xXedUEdfoInFspUuiLXj_5KwWpckwJD0y1Fs8oEfTq2Y0Bn3LdBvwrAGgijcwnDsj6nRa2L9oMLrbHROG3xWIuTC6JyKIlVo8o7cGsM6XdxV6P9f3Wc-UgScNzc-fleF3oWzVq2gENtufLiwn9y3z1k_Hb62pbgIV6dmhLepqVH7WAyHajYt9GyxHB_FZbni-_rujbci3-3Jcj451W8PFg0TjhlyUzETBQwv6y6-zORZcbD7TqKe6XnUUGxHEMbPKBCmiIxOIUuOHpNOEjmdQpgOuPR16k_j0YjoA1gJJovIqwB1g6w44nebjzzsky0uRWmIhqeNaIFPPtIUDr05z1ocxgFeHJxum5YAh4d46vUY18dpffRyghwrd1rvIxk2EWW2rmruR4nEDTT405t3RX4kjnhGHuyShSLM_jinQm5LcpLDXUWgRnilpB1RVB8eZUSNYePAhgDRbacr8IC4AvQ7X8xUtcglbDJmMYQZQRFrkGfVoMUcyAkEJamLjccYDFrO5rxUFfyUHmGVxFUY85NW9XCwAFOx7h3606gjN9KVKQPMAg-dUnXbfhc4PCY3iRaS0djErOEugRN6f7iniy8td2YRI2WhPD5O1-qsvTDfiIhymTFq2L0v4f3UEeIa2wnfq4EdnAgla4D14w7T1D1Wg4SiP-dnF0_vKy8md5vlQjpbPGbYJkzB9DBNwJ8qR-7s1jCtZj2fViHuIGwTReI3OXUoeao4FHC8pndoAZbEpbTmax7BEYw7JqlUhIXWF2x8NzeYr-sjBbo1kbzKbtnidxOwrngjU428TzTPEjr9WA9VpmxXNoSOPL7I_qsN8ulnGegsnxQOEIarRK9CE7C8AwtMRMi8lClAFaMwMAoD8jWMNCSEa6mtyv08AikNCt3ij6cW2JszTRO3Qu4lRTsSnta41Qyk16Zc4xEPOs58PhY90t_atHYUWRpydUerE2nvRnPF9eTbQvSe8-iZ0BqkXqdlnVAAIzwOIfVZRua0p8eU3iPlzKteg9F02Jb5HkOsvi2Y4M-ZS5i0Tg4iOeuKHkeiFdZs6EMytIwz6lPGKLhYii6HW0Oe0KU_WQrIVNdXMcs5EWZGqMIdEhf09ZpO3ONcWIYswjgng6W8WMqwplHyHMcjnhzaVbIhs6rsVgTwGJawtbmD5q6aYnJCRq4zI68wzKOe7d6av8jwMGZS-dd8cdHj_XyShws1cWLhLJCaGW_vHKA0i-D1WTDeKSev31IQKCXBSRMB5URPkHu6dNDm1UyDiLGlJBx6iuKTizGeGhb4o2SQ1y1ISKyQRhKuNih0XgY40hn4x-6Scqu6_thPey-4F32BeTnbzNLGQ0wXE--dcIVRbAZMEB7wn7V4mRczG4gTG9ZnqarfZnHMPVUTZ0AxxZ2d_ifef1wQv9aRyKNRVLiBxvSqJtu7NnDMZT_U8mXCc_OIREi9wn-6esDbmxYYeBpNPR6Oq0fbsBbr--A_nVUz99MAAvkSnLhV3zdAHmMgjqNJNCmr2kPtGyle-GqdBx0LYQh4mtc5FdqLZUz9dz6gv_ERua952na3S1UnJr__8zVwofLEPGjiC5_g1nQuVCRE3QVSufMmw4gQL5kdUSuZGEm3RN__6DwAIS_X-E-aBv3utOMs92JWGandVEze8K7p4wQr3gSL5zlepjWHeYPZjiXCnGY=",
},
{
"type": "text",
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
},
{
"type": "tool_use",
"id": "call_H6dablHqZFScV63Y29mQXJvf",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 200},
},
],
},
)

990
tests/integration/translation/messages/bases/vertex_ai.py
View file

File diff suppressed because it is too large Load diff

2
tests/integration/translation/messages/basic/test_messages_basic_anthropic.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/messages/basic/test_messages_basic_azure.py
View file

@ -6,6 +6,7 @@ from integration.translation.messages.bases.azure import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

2
tests/integration/translation/messages/basic/test_messages_basic_azure_ai.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/messages/basic/test_messages_basic_bedrock_converse.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/messages/basic/test_messages_basic_bedrock_invoke.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

4
tests/integration/translation/messages/basic/test_messages_basic_bedrock_mantle.py
View file

@ -9,7 +9,9 @@ from integration.translation.messages.bases.bedrock_mantle import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -26,6 +28,8 @@ from integration.translation.runner import assert_translation
GPT_5_6_LUNA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

8
tests/integration/translation/messages/basic/test_messages_basic_gemini.py
View file

@ -6,13 +6,19 @@ from integration.translation.messages.bases.gemini import (
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@pytest.mark.parametrize(
"case",
[GEMINI_3_5_FLASH_TEST_CASE, GEMINI_3_8_FLASH_TEST_CASE, GEMINI_3_1_PRO_PREVIEW_TEST_CASE],
[
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)
def test_messages_basic_gemini(case: TranslationTestCase, gateway: Gateway, provider: SharedProvider) -> None:

2
tests/integration/translation/messages/basic/test_messages_basic_openai.py
View file

@ -6,6 +6,7 @@ from integration.translation.messages.bases.openai import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

11
tests/integration/translation/messages/basic/test_messages_basic_vertex_ai.py
View file

@ -1,19 +1,19 @@
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.messages.bases.vertex_ai import (
CLAUDE_FABLE_5_1_TEST_CASE,
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -31,6 +31,7 @@ from integration.translation.runner import assert_translation
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)

126
tests/integration/translation/messages/prompt_caching/test_messages_prompt_caching_azure_ai.py Normal file
View file

@ -0,0 +1,126 @@
from collections.abc import Mapping
from dataclasses import replace
from typing import Final
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.messages.bases.azure_ai import CLAUDE_FABLE_5_1_TEST_CASE, CLAUDE_HAIKU_5_5_TEST_CASE
from integration.translation.runner import assert_translation
from pydantic import JsonValue
CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0: Final = (
"CAQS6gUKEAgSGAI4AUIIdGhpbmtpbmcSDLQu922okJauVttVBBoMAgcnYaXPP2pLp7kWIjBjWY/rKcIkRW/cK1zER1RvizqI4Z+33qxyJw9F"
"e+n1/BHcFPZB/YEHmGpyettyI5QqhwUoNUlt00bsx60ekxYVjn/ocAkKHVywtpoVpn65SrGRBSzMIfVoEtecE/05Gzvy1GgO8L1995thSB+M"
"E9+Lzc+bvIdirQ/jLWnlnE1L/Vg6/YtM4eUy8a4c8nd//zCPBxgHkZZDrvOKfFE2Md8eKPoB6Uh64DxV0qdcWpPqxdCviDEJzhARb0WMxOWt"
"irKLLOTF+oc546ftUkF5xsbk+qN/96EVdjNwsYWr8OGv+OQdpEpJsT1ANkkverU2iFQ4oNJnW3ORn0uv6uccIRqFuyTFqXN4JefRGUvc8vtV"
"iMdrUr3rIu6j/HCu9Lstm2+SVBnV1wWFzFi8HiIupfOebCGYb5LhvYlWR6UJPk8snpbw9/MfiCqLn+wW/pKvaTSQtuKvQUORftkyVeBmy0Mx"
"UoeSiImk/CqbZ7u7t6wakbFXVZPc5zB1FJe9ymWVCACAFPayHJRLFU93wHjZ2ChPwYhG75HpiA3OordlF5usKP6orO95WU4h8w2FPuX0M2Zz"
"K78MvESEUn/tcf0qthco+y9A1RCPF+NAdgagx3dDXNatT7/4W33yTdf/ZjFFS8UFKJ/vS83Ehp+OhUzVNB4g1g9134JqvUz040Mrctqnibt1"
"+7YKm4nLOHuYxETr5JyHW/noo2X/aNVz8dbL64F6grNe/yofT/D2u7YuaiYnYCwmkQLCK5VmmwExUq43pklgYmgv3X2jaF2f4B6Ph84e3rDV"
"1PQ9AvTgM3WKf0c57NtoMAg4K8NalHtPBELETqI0BnoZt6BW1ltm8ezQoiShdkr8Jy0SpjuaxQmaX9RsoLo1z6LfzaMAf5sXWQFHF8ata5t0"
"bCzIKmeGV5j0+YHZ+wn4HAWu5XjrLhgB"
)
CLAUDE_HAIKU_5_5_CACHE_HIT_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg37cRp2MtyQ7pW4fdgJX",
"content": [
{
"type": "thinking",
"thinking": "I'll read shop/validation.py, starting with a reasonable initial range to see its "
"contents.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_01P1gGqhK77Zpmcf2DrLYAUX",
"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": 0,
"cache_read_input_tokens": 873,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 167,
"output_tokens_details": {"thinking_tokens": 67},
"service_tier": "standard",
"inference_geo": "global",
},
}
CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_HAIKU_5_5_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.mock_provider_response,
**CLAUDE_HAIKU_5_5_CACHE_HIT_RESPONSE_FIELDS,
},
expected_litellm_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.expected_litellm_response,
**CLAUDE_HAIKU_5_5_CACHE_HIT_RESPONSE_FIELDS,
},
)
CLAUDE_FABLE_5_1_CACHE_HIT_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"id": "msg_011Cg37VFyjKTzJLau9mXGWM",
"content": [
{
"type": "text",
"text": "I'll read the validation function along with its surrounding context, since the test "
"file also matters but doesn't depend on what the validator says, so I'll fetch both "
"in one go.",
},
{
"type": "tool_use",
"id": "toolu_01Dr7SroCW5TuKG8UrXY8vad",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
{
"type": "tool_use",
"id": "toolu_0161J4pCkkCDr4kTDeBdrLFE",
"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": 0,
"cache_read_input_tokens": 873,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 248,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
}
CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_FABLE_5_1_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_FABLE_5_1_TEST_CASE.mock_provider_response,
**CLAUDE_FABLE_5_1_CACHE_HIT_RESPONSE_FIELDS,
},
expected_litellm_response={
**CLAUDE_FABLE_5_1_TEST_CASE.expected_litellm_response,
**CLAUDE_FABLE_5_1_CACHE_HIT_RESPONSE_FIELDS,
},
)
@pytest.mark.parametrize(
"case",
[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE],
ids=[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE.id, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE.id],
)
def test_messages_prompt_cache_hit_azure_ai(
case: TranslationTestCase, gateway: Gateway, provider: SharedProvider
) -> None:
assert_translation(case, gateway, provider)

5
tests/integration/translation/messages/templates.py
View file

@ -82,3 +82,8 @@ MESSAGES_REQUEST: Final[Mapping[str, JsonValue]] = {
}
MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = ANTHROPIC_MESSAGES_RESPONSE
MESSAGES_BRIDGE_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in MESSAGES_RESPONSE.items() if key not in {"container", "diagnostics"}
}

550
tests/integration/translation/responses/bases/anthropic.py
View file

@ -1,3 +1,4 @@
import json
from typing import Final
from unittest.mock import ANY
@ -105,103 +106,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "anthropic/claude-haiku-5-5",
"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-5-5",
"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-5-5",
"id": "msg_011CfoboJTmCCdzhHCYYzodZ",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"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-5-5",
"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": 23,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"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",
@ -563,16 +467,24 @@ CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
expected_litellm_response={**RESPONSES_RESPONSE, "model": "anthropic/claude-sonnet-5-5"},
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
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={
"model": "anthropic/claude-opus-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-haiku-5-5"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
@ -580,96 +492,308 @@ CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-opus-5-5",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
**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={
"model": "claude-opus-5-5",
"id": "msg_011CfgDzp3URQ38dAAc8F3RP",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**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": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"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",
},
"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-5-5",
"object": "response",
**RESPONSES_RESPONSE,
"model": "anthropic/claude-haiku-5-5",
"output": [
{
"type": "message",
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"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",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 167,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 67, "text_tokens": 100},
"total_tokens": 1044,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": 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",
},
},
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={
"model": "anthropic/claude-fable-5-1",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "anthropic/claude-fable-5-1"},
expected_provider_endpoint="/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-anthropic-key",
@ -677,81 +801,95 @@ CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
"content-type": "application/json",
},
expected_provider_request={
**ANTHROPIC_MESSAGES_REQUEST,
"model": "claude-fable-5-1",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"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_011Cg343GgaNGYZ8EW5CiKWy",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"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": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**RESPONSES_RESPONSE,
"model": "anthropic/claude-fable-5-1",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"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",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 155,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 155},
"total_tokens": 1032,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)

1338
tests/integration/translation/responses/bases/azure.py
View file

File diff suppressed because it is too large Load diff

386
tests/integration/translation/responses/bases/azure_ai.py
View file

@ -1,7 +1,10 @@
import json
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import 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",
@ -99,104 +102,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "azure_ai/claude-haiku-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"api-key": "synthetic-azure-ai-key",
"anthropic-version": "2023-06-01",
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-haiku-5-5",
"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-5-5",
"id": "msg_011CfoboMutM3uKRT9qW3upD",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "azure_ai/claude-haiku-5-5",
"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": 23,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"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",
@ -681,17 +586,23 @@ CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQShAYKEAgSGAI4AUIIdGhpbmtpbmcSDEZBSweh3n+zsTFBbxoMzZxq5YKILAjNCjcbIjA/E3kpf/AnHsoj/+k5/+kv+0Zyyl0oHryOrbao"
"+0ht+2v/fbBUPGLQ38xdnNmiFE4qoQXePJCj6Q5is8kKxhEYNop4kKbvzRimV2ER8yql54QSaKONKuCgt0W52r1s0b+7iLw+P2Le5sju8XVy"
"9/c9h06rqUQu2ALeRsVDdTecLqPBWdfLtuePuMrRmLBDNERphdLekxUr9ABAFts/hhybR/HLiDSMkj08Axp+45skaChj7TPaGAQVg/dw7cWi"
"QSA4atcKZk+CfkUu955LX6qaDRoNUOAC4i15y4VbfForUdVk7LBgvI4ynDZ0L4lAtwSIcfNj7sCBY6zyPAD/POQkuTo2jm2UtbMVx4bC6+Ci"
"B6hAtvmA/MY6iIVUTGtordaFtKFcc8hTgr4uya2jeOp1pGN9dmABK2U4wIbyeCiYhJYskqQiVH3Va82hIHkg9oJvc4/4TMLT6nhmuaBsR9Eo"
"8VgFlwmkw9gXF+8FMD/rPdwLjr7aHvyNDe2gW9YxEaiHk5g0ldtyRPj5hLZpMX4CJ1Uqjf2k5LJ5kXljJihoT5/Je516iVPoA0V7alAr1dOY"
"Dxfajmd2o16yOrmJox/BwUGGqh4kPTgaavIKMWNwjaSeGTmd+pccQt4aKEzIk+X/Cst1UOS0vVVGdu/Z0q7MyrRMbfkne8B0i1lPRVhNtNwb"
"32fig40YgYmLIagkHA+jXhBxvLUaB5Xj/TtEMXe6ZVdq7A3fJ72baBTcDQ5uXW4yd0G12QrFEaA2TGt8PNZsA2/G1ZW/iU6oZZIKx5o7Sgeg"
"KNQk/tdXeS3cru7/bIlO6jMaGhYjDn3g42XKj16i6ri5WUVrrFeXq8Oq2Oh3IGIw+tL9RVf/lI/vp487EJcnMPiwWYeuIRwyyN8x/XiudCeE"
"S8mAFwadQyCUHYyeOr/a2tRXwx0o0/lpXb4htqEZHdkOJmXtlR4Whda4NrzO7utcGAE="
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "azure_ai/claude-fable-5-1",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "azure_ai/claude-haiku-5-5"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
@ -700,81 +611,252 @@ CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
"content-type": "application/json",
},
expected_provider_request={
"model": "claude-fable-5-1",
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
**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={
"model": "claude-fable-5-1",
"id": "msg_011Cg344Nycw3eBjJcjxMMpq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**ANTHROPIC_MESSAGES_RESPONSE,
"model": "claude-haiku-5-5",
"id": "msg_011Cg37NSjwYJSDCvonTBaww",
"content": [
{
"type": "thinking",
"thinking": "I need to look at shop/validation.py to understand its contents, so I'll read "
"through the first chunk of the file.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py`, starting with the `validate_quantity` function found "
"in the search.",
},
{
"type": "tool_use",
"id": "toolu_01NiAAsMCJRXggv46Zro96cN",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"caller": {"type": "direct"},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 205,
"output_tokens_details": {"thinking_tokens": 73},
"service_tier": "standard",
"inference_geo": "global",
},
},
expected_litellm_response={
**RESPONSES_RESPONSE,
"model": "azure_ai/claude-haiku-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I need to look at shop/validation.py to understand its contents, so I'll read "
"through the first chunk of the file.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I need to look at shop/validation.py to understand its contents, so I'll read "
"through the first chunk of the file.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll read `shop/validation.py`, starting with the `validate_quantity` function found "
"in the search.",
"annotations": [],
},
],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "toolu_01NiAAsMCJRXggv46Zro96cN",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01NiAAsMCJRXggv46Zro96cN",
"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": 205,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 73, "text_tokens": 132},
"total_tokens": 1082,
"cost": None,
},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I need to look at shop/validation.py to understand its contents, so I'll read "
"through the first chunk of the file.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
},
},
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "azure_ai/claude-fable-5-1"},
expected_provider_endpoint="/anthropic/v1/messages",
expected_provider_headers={
"x-api-key": "synthetic-azure-ai-key",
"api-key": "synthetic-azure-ai-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_011Cg37P2hrNhVAyq9ahS7H9",
"content": [
{
"type": "text",
"text": "I'll read the validation function; reading the test file at the same time is "
"independent of it, so I'll fetch both now.",
},
{
"type": "tool_use",
"id": "toolu_01XZZ8P93YHKzXM5XGRZN7hs",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"caller": {"type": "direct"},
},
{
"type": "tool_use",
"id": "toolu_01MpgANqoXoBcnhnsz81Q4Q7",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 30},
"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": 232,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
"diagnostics": None,
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**RESPONSES_RESPONSE,
"model": "azure_ai/claude-fable-5-1",
"object": "response",
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll read the validation function; reading the test file at the same time is "
"independent of it, so I'll fetch both now.",
"annotations": [],
},
],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"call_id": "toolu_01XZZ8P93YHKzXM5XGRZN7hs",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01XZZ8P93YHKzXM5XGRZN7hs",
"namespace": None,
"status": "completed",
},
{
"arguments": '{"path": "tests/test_validation.py", "start_line": 1, "end_line": 30}',
"call_id": "toolu_01MpgANqoXoBcnhnsz81Q4Q7",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01MpgANqoXoBcnhnsz81Q4Q7",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 232,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 232},
"total_tokens": 1109,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)

791
tests/integration/translation/responses/bases/bedrock_converse.py
View file

@ -1,7 +1,15 @@
import json
from collections.abc import Mapping
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import RESPONSES_REQUEST, RESPONSES_RESPONSE
from integration.translation.templates.bedrock_converse import (
BEDROCK_CONVERSE_REQUEST,
BEDROCK_CONVERSE_RESPONSE,
)
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -86,90 +94,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
},
mock_provider_response={
"metrics": {"latencyMs": 954},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
"usage": {
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"serverToolUsage": {},
"totalTokens": 29,
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"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": 23,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"cost": None,
},
"user": None,
"store": None,
},
)
CLAUDE_SONNET_4_6_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
@ -419,252 +343,669 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
BEDROCK_CONVERSE_RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in RESPONSES_RESPONSE.items() if key not in ("provider_specific_fields",)
}
BEDROCK_CONVERSE_RESPONSES_SYSTEM: Final[JsonValue] = [
{
"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.",
},
]
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS3AYKEggSEAEYAjgBQgh0aGlua2luZxIMvtg77qfREr4ZWBn7GgzxzrtNwc5N8DqpBHgiMMJUcH5Vw6hj0kYyAwbI34q5FDQHs+VeRDCU"
"N9EDE5JENmjhQSbLvD87AP+BtUfZPSr3BegcgjSctkyUvfkBNE3E+FvfkZAAwgvBMZ904om1Ua3usYegKOyyc4dHlwRSvDFvJFDSeIrtTek2"
"ugzdsjeSeJLr8FoiYxqVIDSfe40IraTHZs5omadfA/F2I9Yj6nGHUCkGQK/TKZWA4G+3+H4FiPK84gjyFL4686p/8ljiWsz11SO862UHRR7J"
"QAl9e6tprj4qpJRawR58Ky+JyOAUzUD/DpZyFYjYFwsgAiv5IY7kCfW/osGKrwnEr9dYX8JQu6h5kZBxFBxETdASJQBHrIWC/zrYADuzIO7Q"
"YzRwnQqc0v/hCnuf01rBX+q41iRVHlJIDsEmdkxiNB4tGE/Azo+RUbTd4fBBGH2t9iY4zi+5ykBZ38BzjTIQAjBc5Ip3LSoNHqNzFAj65wBj"
"nI1L21+jANpMxjZ1DvXCkMc2ZMh/hkPNGqnEKPaIZjYTp6ZX4MJ1G7orq1VqFUYKJ39whqkQR2i64iaBRJ7f+n4eHYNR0ZAGF6E0/pJzpB27"
"2lsWrz2Ky6OsK0UU5HsGgFmkOLI1IGEvXqeE4gmRz8AMseNY1RobNPmNmv4nj7DjLrg9wnkDLlQP0Vg8N6LXqGPlIZeICtcNEM/7KhiqIwzf"
"KZnPc5erpBrCS3qcM0jzP/vGwOdpuZWbiDfn8iwJatVEYgwzsZOi1kIJDGHSCLyznM8CiGGpTBY5BIh8yj2k6D8JIOdKOLfVVJtrCE+LowpB"
"BTGLnC9mEQkJ4ZD/wS4rHQOeWiN2tvbm6casvCvzDDRPISoLI0mQa7WXr+ovbScBIgmZhoJFAwaU5b0ii5hoizTDx6Uc4Ak5zr/DETMNvVde"
"dTvD0MWzZ0Olo1W3bUoHfu+I7yiPGE9jmp3Yugj293UtIUm5GDJpuXwDeDTrcu+dYrFCWm68qn7dRAk2/47a9BqknHboVsD+Z0Zxi3DItUBa"
"/iFxdh7kgJSVZ+oHy2EcEu3Tlg1vEDDPXoivGCzV/sSQ1L2kimTI2jtYhHkWZU7kn7VUmCXdsRgB"
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_RESPONSES_SYSTEM,
},
mock_provider_response={
"metrics": {"latencyMs": 892},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 116}}},
"metrics": {"latencyMs": 3114},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
"text": "I need to check shop/validation.py to answer this, so I'll read the first "
"chunk of lines to see its contents before responding.\n\n",
},
},
},
{
"text": "I'll read `shop/validation.py` first, since that's where `validate_quantity` is "
"defined and where the zero-quantity rejection should come from.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_l8Pc3cjAkezdGOeQoxs9XG",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 262,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1119,
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"object": "response",
**BEDROCK_CONVERSE_RESPONSES_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-haiku-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I need to check shop/validation.py to answer this, so I'll read the first chunk of "
"lines to see its contents before responding.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I need to check shop/validation.py to answer this, so I'll read the first "
"chunk of lines to see its contents before responding.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll read `shop/validation.py` first, since that's where `validate_quantity` is "
"defined and where the zero-quantity rejection should come from.",
"annotations": [],
},
],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "tooluse_l8Pc3cjAkezdGOeQoxs9XG",
"name": "read_file",
"type": "function_call",
"id": "fc_tooluse_l8Pc3cjAkezdGOeQoxs9XG",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 857,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 853,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 262,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 116, "text_tokens": 146},
"total_tokens": 1119,
"cost": None,
},
"user": None,
"store": None,
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS6gkKEggSEAEYAjgBQgh0aGlua2luZxIM5Rk71l/Z9rkMtA6ZGgwuf1QIpmmol0EDZgwiMAXhxIVSflqszyyicoACM0MZMWNy03vjepAm"
"b4tmo7kCof9sNzr0fhQHwTSdDGzUlyqFCdgG/z4e8K7FKJQXQvtfpj0ubUZ0e3Cipo/DjMOZdQlMuAy+mywzO73iQG/afjuWcEMc0NKMgPki"
"0EFN23Fy6adXfSQXvRej3PxBT16bNSth1ytGBnoby/VgtMa1JVW3E9h9kCkbEnA8+AT1XSgqQs1pigN5LbTPDN13nYutXxd3BoP/cnPsR5vN"
"znslFbfjd19eup0W0iKTk9xpP1HEvcuYnYlIIVDHYGDP7rzUXtWIqI9ZG1KdzVHFBa9qhEcmKMeWks4iXcKVAiNRcdip3kdowlGZWyG4MEmJ"
"94BWm9JJbn6f+DpxsDk6bFyqq1RJW5l+aApuKX/yN915Ccd6gARvz+nuxpjuDZOln/DzHiBqlnDBPRgn82q+csvQ3iXAxIeNEcTscEu+zsIU"
"zwtZciFKXs1TlMIiBAtoQ3NE7HM9vJNkWWiQRHtE5n4jhtN2Yqs5hnvg05vTGvXnfqs5sGjbP2yj18TOYmu2HlZd6NFADuLTulA/zovgGm5t"
"gNzJE26Blh/4QoiT3TMUMjvOJtRhPz2VmdkKbbiBn1R3Nf1CTStND00zdOQ6NQululcU5Y74fbnzADHl1dOAw7AkoHlp953vkEOJvK1N9kPw"
"ZOwBz5Nc0XRRoZ4zXSM50wg6OdTWqS8vT2nlJslvKT9AghPV3LHyY5HBUpZPR0Up2OZQKZr/G5/BAKpM5Jr5P0tIAf9gHLBiHNKcpk+Upkzv"
"HfT8QV3dl0x80yaUyQrU1Glv8K56pI3OUe/NkmJw7CMhVSUfPt4U609XzzKNEEwFKUjoUtJt/ZOsBxESqGfs3hSayF6i9kFzIzWdHKE6RnAj"
"7JtjVQlff0aIpoAH89oq5ZhFaA8xkqbxu8eDY0L4HtNRVTEyNiGrnJBlp0O7eEoL/4ZRW+j6HcK9bB7O/8diJ/JXk3MEpyYt8MLBHbhVbzzX"
"PJuIZM5NObOchFbR53EjBHMvyRVvF4SnZaZAW3DxOeA49UpuiBDbDPiPe0XOmtM3BwK+vRnmeI61nWfn4mAOVQeNZLjf+spO+3bDxXtHt1bz"
"yK1Z4pLO3dkBEhZKEk6Ha6fRPSPBi2/xcK80R1WyWbVhGvgYK0hP9Uy36ZK6WvTMiEVL9b5/+t+yNNJsflstuMYLNuASU0PE7ne35zYao/gc"
"qKzM8t9gjJpqGUtPoR9ndaBlilgHOkgXV+h29jA4OIPtJnFfI49sztRrA0thymK+lm8LY0F1nnhsPkxc1dohz8EykdV18vO8y2cyeZHNwVrp"
"OEW3nWGz+/GFyRCKsfexlGk6npiFvk5ZJQFZY/Kdh4VuTDKEhmm9QhZTwEYFrh3B5OlO8UjaiIliJ+4Xx642I2MvRbkeqDbJGxSCqxNIS1yJ"
"Yq9UVZzkFXhPvy9/9XFfXH3tedoDceTGG8YD4IummDngMs204wz7VHve814/eTD3qS70oX5O36aY/Aswnz9lS4PhYrAtITp0YmNyBingiqpi"
"Csxq8ePR2IQXawltEYg3cS+weEVJBUaxusjRf/3SdwhyoDuXqaqtrr/r4L7UMf5HGAE="
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1: Final = (
"CAQS9wUKEwgSEAEYAjgBQgluYXJyYXRpb24SDNP7b6gtJ4xvIEG9ohoMqC7J3vxdFt/qo/sOIjC6trR5FvvYWW/MCffxtMIugtRws7utg3y+"
"18ZIygEbDw4yGfS2DkcGZ9q6obx1Zs4qkQV27sYDMo7sDReqPo0XpOQHMt7NOsJmrJQ9IdAfTOXPqKPwnC6LU3dnS6lvSWw5gDrdXgXd9iHu"
"Yb1+pVCrkpBnYwrb5N7tOqMQvRI60qxGBOarSLTpvhysv5G3ZIXfmliYZbmITa3I8tlvKoqIIAGXc7zqgI7VfMU8yuK/dtDbCO6/Q+/qPnIL"
"lrY+F4NIaByk9WcjJMXGarMfuohw2acciumMpDu1rqxUpLaPMjhaTFv17lu07uOOu3cuiySN06Fzwp7TbWiKS2pi1aORKXYDowrF59gyTppc"
"G6Y3M5983lXB2oLtz7Gnyr8uBbcjayWDqZCMitoa8m5twh+VEOnHdzay+a4glnSiPr5A1D3nH1ENocWj6+eKS+LXkdvOUse5XkDaOUPAfAm1"
"4f3tn9G1+0S6Zo6Lmwjw/+79OfUPFEHgkZ6Ih6xhMR0yM/3FIAjSXMm+t7VNH23Ei7EkCWdv4OrSPA5PweCX8lnMwQ5avMuna6ZeiAV3A/tu"
"SGy2tYkbjpUJ3JPGfuRmwfCV499fkJJY6oZthK1ot0746frbEgHAnYFyts064x+/yp9D0KariKPuCpfyFqDYn4EhoA+ROvBTxkrQu1KveTAC"
"55/v1tOBlLAZsVzXT7XqbCItMt+AXQSA3jaOmtrU425oOyhc9AUKSxvSR+jTBCcGmJCWKrnEWUjqTW5AbG5byposBH3tYor6L769fli2cTRy"
"IerlH8AHj2CgjuXNtGbxP2Acjf6TjGyY2WeIhT/dQXWKQNzfsvdVtfLRyEESr7QKyiBC/vOFeTTMfQoFB7+Q6mTh6mnYmw52ytfociSKPi3x"
"yAYXpJQGxmCINv++wCIocN3xp703kU+Yt+9I4wKL2+JuN7IYAQ=="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_RESPONSES_SYSTEM,
},
mock_provider_response={
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 235}}},
"metrics": {"latencyMs": 5698},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
"text": "The user asked to read validation first, though both files could "
"technically be read independently. I'll follow their sequencing and read "
"the validation file first.\n\n",
},
},
},
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
"text": "Now checking shop/validation.py to see how validate_quantity handles zero, "
"negative, and non-integer inputs, starting with imports and helper "
"functions near the top.\n\n",
},
},
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_HZpviLzbdTE4T0GMawHsmi",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 404,
"serverToolUsage": {},
"totalTokens": 1261,
},
},
expected_litellm_response={
**BEDROCK_CONVERSE_RESPONSES_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-sonnet-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The user asked to read validation first, though both files could technically be "
"read independently. I'll follow their sequencing and read the validation file "
"first.\n\nNow checking shop/validation.py to see how validate_quantity handles "
"zero, negative, and non-integer inputs, starting with imports and helper functions "
"near the top.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "The user asked to read validation first, though both files could technically "
"be read independently. I'll follow their sequencing and read the validation "
"file first.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "Now checking shop/validation.py to see how validate_quantity handles zero, "
"negative, and non-integer inputs, starting with imports and helper functions "
"near the top.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "", "annotations": []}],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "tooluse_HZpviLzbdTE4T0GMawHsmi",
"name": "read_file",
"type": "function_call",
"id": "fc_tooluse_HZpviLzbdTE4T0GMawHsmi",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 857,
"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": 853,
},
"output_tokens": 404,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 235, "text_tokens": 169},
"total_tokens": 1261,
"cost": None,
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSzQUKEggSEAEYAjgBQgh0aGlua2luZxIMBQgAH/utL+SlHBltGgxDyOhF0rniv4pJNTQiMNmF1xF0QjswZwV2rMEyccqYlGdGvMcM6/MX"
"lTjznngJK6CmT4WJ0ueKjnCuwChARCroBMQXhDXHvXCbvjESc/c/WnSjWeZtFvycp287jestqbK0BDZ8v9ErwC6iSx2yBNgVFHzpJuOmO06e"
"8Y49ALNuhk9VMl4CGjfbGVdgeGGDrjkk4m9oo0JlYvBykNJiSf6Tu82PuYLgirixNBOf5ZMRX19v6oMZA7RHxJz72XlNAde6VBEjMy6LV/Jy"
"0tcrYI12e9sxjJaDZ4wF2Si6/+VRMRM0QkQHFhVALNFnxvb4kawAPEkx/I1gdBvEB76ACTOjmKYnYdPZPdqu9eScnTamuOGxpet6+82cSPnb"
"IsUXD1XXT0eJUFi40ot60YFcFWTX3vpJYkzMjndouRx998TaLS7TxqUiYFPu2kquJBOY/pDtkh0oysaXBQ0XnZyHtXIRuzFkfWgjkmvPL+UJ"
"ZxDUA0RMuUUM3b6cqjvOgGBg7/1qBFfgc5cr8nPOeec+0E1zk0szyTQ+14fwMMkRte0emSjhPiIIKk2HspOP2IMahYKXx8Ni9xp4WSXwylp6"
"gXyikRTmJRlnknU9NK/VlqJEAcOlZMSPC55ug53ZppDw71ssCiFeCcEGQCMajAbG5DEfLxxY4h4fqGxCqj2qJI8ATA4caGytPY0lBS3+DsrJ"
"sUuzBdVtHiMceMJtEsPVpvAc9ITzl2+rwXiC2+MMeJVXgGpEyCCcksI2Bs2wIoly1/1J9rG9kz71neIhItwY9B3r5LgSEliWYpuSI/LbiZHB"
"9ZwZJj87gKYH/C3U5w8oc+OLZO7zOQ/8bbLIQTyuk+hepc8KZgq5eouSMvhWGbmE+eA+0On+mB+85EmSmFu1JTXt2+D5/BVVbnQYAQ=="
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1: Final = (
"CAQS6gUKEwgSEAEYAjgBQgluYXJyYXRpb24SDJFe0B/jn7Vc9l86UxoM+3QEi7NVYrrEAJXWIjDH/Ye9cV6IW0LpbnOf4ZukC5Dm+ug53eFV"
"0Aad2kQp1qLUJ3qu6oXbevVE6AGblSYqhAUYC6yg3pfX1HlZfxFG2YmiNPSo4jxv/nXTib4cG6c64wVIKb7lcnUKVhqsbii2eBZ3+dcyeqah"
"LqgqhS5gz8qM0JWf8erzMW27BwS4z+VflWHyDNcYxZ0N5xg8hxKObWmDNJ1hv46wCUL3BVB2q4IcKMsdxWtIIz6PAllot/4G6ton3kESWcVj"
"k6Q1Moj+RzvX1pDESbIaWry84vTfuH8vq2x5p3yTICKl6+lHFrxt9HWPRW6SebPOJ/7y2Y6qOb6h4bEb8M8sRdm5p/LbhfwBc3DVQ7plPic2"
"IkS7mMwCInmJYbjRdefnUX5fneCwccH56O9IarBZ/s1VM0D/Xv1tgalZb9bNaaw7BvJX/5IkBP6yjYhbtPeh9I/J9XPYeOcNRn1QgbskbEJ1"
"Ff3lvL4jEqydqRyuQcyasCXGxAsFkNqA6grC5sFNBBlk5lcR1T8poXh7d/36BMNTcU5AzEBjzA/i0QQvKwVVw4IkjphHd3r+6ZgRSHGc0m6R"
"WY6NlKfTCQEhF0fZeL77TURzs921CXiynXmSyqvuuEOU6aEy6n56AkjlxdpZ4UgEzGMiij4i21qOpBsS18Fb5lIBC12DqhEXWu/NFthVDlG/"
"7Gwu4o/v1RQIXHaM8Kvxobt75gyaIWp1NIeN9GN/SAiTOjc/zos+HDFzGQYSmV5tPcly/xItwTBDgtJChfujxwd09b6j2WH38Mds89Cdz7CT"
"aplQBwhdVmVTRXhAv9nRDxPWzVnYAtI9hHeLoxU8jJAAXq5f2DErZxF7TdYwR4UGVrj21w+eQ97yPMyPAYP9XbKmo6xp56fMz+TmpBfiNJM9"
"fU+/b+ImXYstTNT/cNu7z7gwZv6fthgB"
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_RESPONSES_SYSTEM,
},
mock_provider_response={
"metrics": {"latencyMs": 10460},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 71}}},
"metrics": {"latencyMs": 12388},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
"text": "Since the user asked for the validation file first, I'll read "
"shop/validation.py around line 18 before looking at the test file.\n\n",
},
},
},
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
"text": "I'll check `shop/validation.py`, reading lines 1–50 to see "
"`validate_quantity` along with any related imports or constants.\n\n",
},
},
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
"name": "read_file",
"toolUseId": "tooluse_ZbXhsiKlmJB473d9A8N5ZI",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 853, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 853,
"cacheWriteInputTokens": 853,
"inputTokens": 4,
"outputTokens": 245,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1102,
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**BEDROCK_CONVERSE_RESPONSES_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-opus-5-5",
"object": "response",
"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 read shop/validation.py "
"around line 18 before looking at the test file.\n\nI'll check "
"`shop/validation.py`, reading lines 1–50 to see `validate_quantity` along "
"with any related imports or constants.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "Since the user asked for the validation file first, I'll read "
"shop/validation.py around line 18 before looking at the test file.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll check `shop/validation.py`, reading lines 1–50 to see "
"`validate_quantity` along with any related imports or constants.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_1,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [{"type": "output_text", "text": "", "annotations": []}],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"call_id": "tooluse_ZbXhsiKlmJB473d9A8N5ZI",
"name": "read_file",
"type": "function_call",
"id": "fc_tooluse_ZbXhsiKlmJB473d9A8N5ZI",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 857,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 853,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 245,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 71, "text_tokens": 174},
"total_tokens": 1102,
"cost": None,
},
"user": None,
"store": None,
},
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0: Final = (
"CAQS4gYKEggSEAEYAjgBQgh0aGlua2luZxIMwBPNPxtNdRTj9z+3GgwSLCcSbOT5eOdg4a0iMMMEuXnI1wytKqyHTo9ejWTxkMM26SCWUqTI"
"H8eIgHNrJHcYTESawe9nmU18j4tufir9Bdw7vFeVYpvoISrtD0A+reIZiKHpRSyvhuL7aiOVQmX8Nm+o9LWnDjMzO8VeHw/JhmEY53nv/kb/"
"aU2CxklgPf+LYWHzlvVUNt+z4vWca/66spf3iduVP1rofkqnKNNSe1q6ECXv9x5/esewnGGjtuxLOB/lTYU3j67KUSGbTmoV9008oLpTnAkC"
"9XOfWprSoh12L0XSqip8rorUlcyD3XLbiVu6MZt+mGbaVv7Qip7tOzOcAwPl/vQKPAFlV7Fwk7Jg/l4vwErw7s+xqANYxZRNPOs/quWe2/tc"
"stL5T7Cm2sGNJx0LI022V9Xfu+MihJvl54c3IWh0duPIU4DToEkNHeRJY++DjrynqXdeWH8eydrtdzbuNhWCGW936UlUKfYoziUhkSS+7MpZ"
"R1hhK7TErXI+5CWbghy7c4KdH8darDfyLCb0KLwYM9A4PqzLL2ZpIZS4oL7EvuXFTC/Wa40Omtmtn4klBwGHmTUHL6JXXaZGXTtz5HqGSaK4"
"8Ia/W+YG+q0IaApw1NSs8MMdnOlt5eF7qVla73EjF8JE3TLYn/NKPqBAdoPKoe+PxxtFY9fkHIHNrnJupT7nt9YR7nf8nzPm6Y7+KeGHkJ6x"
"LHTiv58t2iV2E5jbDP1awcQg4azhpTr/cBz7cyUnTiGJGjwt/NS55rNnfnH24E3F3yUMLGVySc035LaInTJOVTzWfmT9BKmc3T18WQERUEs2"
"SFO6X7BHWV0Dcx4XqedsR//Fjp9v3lspa2fVqd5/+g4xq8z2kBZlBnXkLQMFNpFwd4ZRiVzRx94u3AzSza2fHFByDhLSHkaQpblg79lo1JDG"
"Op2fbO0TZnwwUsth4Qq/9QvvtpYtAEMox9ISsqMGCELZeT8StjFfAmro7iwp2nGmVfGfjvoTpOZ8oaQChOdi7V/cy7An1v/58GMapRqEKWCj"
"JtuI5qNyka4ECp7FdT++oQJeU7U85PQurp55wlEf4drBvjYl/aICnnxH6ueg8izsmC/hya5IRdRfD7dQoxgB"
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/converse/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/converse",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"text": "Say hello."}]}],
"inferenceConfig": {"maxTokens": 64},
"system": [{"text": "You are a terse assistant."}],
**BEDROCK_CONVERSE_REQUEST,
"system": BEDROCK_CONVERSE_RESPONSES_SYSTEM,
"toolConfig": {
"tools": [
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
"name": "search_files",
"description": "Search source and test files for a literal term.",
},
},
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
"name": "read_file",
"description": "Read a range of lines from a project file.",
},
},
],
},
},
mock_provider_response={
"metrics": {"latencyMs": 2671},
"output": {"message": {"content": [{"text": "Hello."}], "role": "assistant"}},
"stopReason": "end_turn",
**BEDROCK_CONVERSE_RESPONSE,
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 102}}},
"metrics": {"latencyMs": 9400},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
"text": "The user wants validation read first even though the files are "
"independent, so I'll respect that order: read validation.py now, then the "
"test file next.\n\n",
},
},
},
{
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, "
"negative, and non-integer values are treated; the test file comes next.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
"name": "read_file",
"toolUseId": "tooluse_IZcZuTirqaML2t3hxtMt9K",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"usage": {
"cacheDetails": [{"inputTokens": 873, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 0,
"cacheWriteInputTokens": 0,
"inputTokens": 23,
"outputTokens": 6,
"cacheWriteInputTokenCount": 873,
"cacheWriteInputTokens": 873,
"inputTokens": 4,
"outputTokens": 250,
"serverToolUsage": {},
"totalTokens": 29,
"totalTokens": 1127,
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**BEDROCK_CONVERSE_RESPONSES_RESPONSE,
"model": "bedrock/converse/us.anthropic.claude-fable-5-1",
"object": "response",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The user wants validation read first even though the files are independent, so "
"I'll respect that order: read validation.py now, then the test file next.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "The user wants validation read first even though the files are independent, so "
"I'll respect that order: read validation.py now, then the test file next.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, "
"negative, and non-integer values are treated; the test file comes next.",
"annotations": [],
},
],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"call_id": "tooluse_IZcZuTirqaML2t3hxtMt9K",
"name": "read_file",
"type": "function_call",
"id": "fc_tooluse_IZcZuTirqaML2t3hxtMt9K",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 250,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 102, "text_tokens": 148},
"total_tokens": 1127,
"cost": None,
},
"user": None,
"store": None,
},
)

753
tests/integration/translation/responses/bases/bedrock_invoke.py
View file

@ -1,7 +1,14 @@
import json
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import RESPONSES_REQUEST, RESPONSES_RESPONSE
from integration.translation.templates.bedrock_invoke import (
BEDROCK_INVOKE_REQUEST,
BEDROCK_INVOKE_RESPONSE,
)
from pydantic import JsonValue
CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -92,97 +99,6 @@ CLAUDE_HAIKU_4_5_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
},
mock_provider_response={
"model": "claude-haiku-5-5",
"id": "msg_bdrk_prp4tfjg2ibow6km7wkqw5euejxxssl2ngm6wbgjxyg7xd32tkja",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 23,
"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",
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"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": 23,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"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",
@ -452,273 +368,602 @@ CLAUDE_OPUS_4_8_TEST_CASE: Final = TranslationTestCase(
},
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
BEDROCK_INVOKE_RESPONSES_SYSTEM: Final[JsonValue] = [
{
"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.",
},
]
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSuQUKEggSEAEYAjgBQgh0aGlua2luZxIMkzWpvtxVqloRdTejGgySvyYIIigSiTigYwsiMOl8XJI9rkOBrw8tVJltn2ZOQqbsCTr8UQ1o"
"5xBXnkf4Pj+F0fd7GRGRGWVhSLbFCSrUBMeafwRFgNCuZyPdn7n38LWOXm7+Lg8tjM0m2PfA04geMhUvcih7RPypybFHnZgmoxqTnoxhyMYA"
"BJ6CuZ1PHCKCXXTLGF2SsBJCCKhOeDwlBnVbwgbxvTUScOtpx/12go2VloE1aRsFTdpG4oZlziwPqV8GYUv0Pzw8zlEAbdlK/A/pu7vH1eM+"
"08tFzjRwl5/ACM8NIQ3s/baA58Y1Cfu2yTUyzxV13+MaBnGEhEMPhI/3muGRHhT20ga9jOhGz4uH67he+BTschcNoIi6Pw2ZUy6PAnfjs9Sx"
"3tJMQyUCThBsmKS1nGSTu4R8NQMKJWnMGr0X6fyk5PphRmC4YEYTjJ4nw3Ad6Kog06Bh1LbJTphVX3V3qc4sMBbrKSPH/vd/f4OCgrWU572B"
"lxYl3HNT+gwJa+uBfQShW11KQR8A0v8T33jnHAmysQ87+iJpTm1u+W3oMoemDsUddpICg6JQdxDSA4Ft2iuDds3XgeeOmXYl8mc8pYzuep40"
"zUjmyJ9cPZYjWNArd1IQAFk6s5wa47jHxP72gXiiXDJabXGT1/xvsafaM9WjZ/cxmmyF2K3122br9OWknau/rJa0gg1+PluGe/vUptHi0Acx"
"a4pNbvcQFiRutnwjPr9uqQMqk+cqRdBVS2pZAc/vnmGi7m02MjBuHRqZeFMIkc4WYK3fgt0BxnMyXMJCzQcx64oGg5ZgU15crKV/thvRkvsI"
"AjIl4ScwNIsYlQcz3fx7c1yH2hRIWb+ahmdGbJvnDlcNmliO50qWyhRyzYBoCU55cvXtnJTHGAE="
)
CLAUDE_HAIKU_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/invoke",
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-haiku-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-haiku-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"system": BEDROCK_INVOKE_RESPONSES_SYSTEM,
},
mock_provider_response={
"model": "claude-sonnet-5-5",
"id": "msg_bdrk_tozg7mwrkjb7fisuua7q5ylekeypufs6he64a2tlncr4bvdg4dha",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
**BEDROCK_INVOKE_RESPONSE,
"id": "msg_bdrk_ytkmzvqioxcm74hxqxgoycuu6vt3orsozxii4miswb5tk57ya2ra",
"content": [
{
"type": "thinking",
"thinking": "I'll open shop/validation.py to check how it handles zero, negative, and non-integer "
"inputs before deciding what to look at next, starting with the first chunk of lines.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Uivu38DoXo46h5UDP3hKz9",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 175,
"output_tokens_details": {"thinking_tokens": 75},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"object": "response",
**RESPONSES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-haiku-5-5",
"output": [
{
"type": "message",
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll open shop/validation.py to check how it handles zero, negative, and "
"non-integer inputs before deciding what to look at next, starting with the first "
"chunk of lines.\n\n",
"annotations": [],
},
],
"phase": None,
}
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I'll open shop/validation.py to check how it handles zero, negative, and "
"non-integer inputs before deciding what to look at next, starting with the "
"first chunk of lines.\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_bdrk_01Uivu38DoXo46h5UDP3hKz9",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_bdrk_01Uivu38DoXo46h5UDP3hKz9",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 175,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 75, "text_tokens": 100},
"total_tokens": 1052,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll open shop/validation.py to check how it handles zero, negative, and non-integer "
"inputs before deciding what to look at next, starting with the first chunk of lines.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
],
},
},
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSiwoKEggSEAEYAjgBQgh0aGlua2luZxIMOIdSxTR4GjBHazgyGgzAFsCOD/EpsKJodeAiMLAgKd6UJh7VQCix7AFKFkbf6rPK16fItxJ9"
"PI5nOnHUS0SfBCxVY4LZmRg71SmHYiqmCTfFsnMccIbkeJS2+Xap1iQw/HZ7KYHJJsCqDxm9Ua2I8LHYyL3s2OVT9NzUiCMKZQWPQ2DqBWZ0"
"gsnrDQ9ZYkNrtXWxypuIDhHQw7dOs89033JTcFGdnxpFwvpvARtjSHPS7O9UOY48wLeD+K0AL6bzJlmbarntN3xeqYnYFU9cAIhyjSrCYWtE"
"5Y37pblxLuwXjHI20rSyT2carPP7whuU2LDg8GVIu0JdDO4seHyys9s+BaiMJEPnn2naeK3WAyOvM5wTyvYj81cxx9xJBlVuFyeyxxyTQgnL"
"DyM7OtCiy35affvC1oKXwYQyiRUYso/4IuEBTiziluiO+wYg/NAHUycI+HEdFp7zOIK9AdC1WtB5xbUtclcCObYpPgdSfR8RtcgaUpltqIfJ"
"VA+9K+hDDNTKKh/Xa4+WFvVj++6NHe7glBlQeasGOtNtrFbRJUB6dgnorTWblMq8NyzCASK5FoQo77Fv3lKdAleW9ujj1eGA2hon5UoO9BGQ"
"w0pnLzColC0V3NtAbpuC8Jl9mm5te2ChvJJV7bYa6/3RYlA3fRTAvP6grSCRTMYkxnqtJCliTb6sjly99vkD4zV7gMvjY8BW08rVruhMShUk"
"gHRC6XBMw6kvUboxDnMs1yCJCYyHqUI1AHaP2g24VigzgWwOPpNSRm1lgodCYZUM8/gznj1JuAwe2XoBXgfBvkRQCYXorCulmvjK3NMIBzdU"
"fsfyGExkFdaQUJLbhWq6IF6L0b9iKLuugkavPUaodPpsg6L3Z1XHsFDZgO7GxRoHcKvV1/cEtO6DU7cc+gu4D/dSsnp8K2BY00UKfDyBqG90"
"OwLw6IDyaiw829KOc+3lVBW0vwxhbA3AV++soacROCplQ/Uy9qQy8lB63whvFu4wGypT6yn+2k9TUSNSbgimfvO3SzuWUenEpnkSVO8CFvRQ"
"iffW03nhllZyHHlwB9B+NSrghpom2VvAd4OBg7J4353Favtsv/nu6LRpUUalVbkmX37iwZ/Q8gEYooxqa/EZodr0+1mwHvRJiascYs67I+MV"
"+9EMffg2inNTIKfDu5GzRJOKWULP4e60/9Q5oJYZ5Pw+LkUyrIQphe+jNAczMq4N/TBPVIQhJWgJaCNfSV3JGvvLPOgPEtZjaIQHYIVn+sID"
"XH/+DsPUWSLKDLibTDPAoCgIQQN2U2TJLEzrs4fr1wej4fJlQ7ufZRXcRisAmbsM4AUqRXrErjjcfgg2cgtPN3Ol1Yfg7XNm5fw09WJD/DKC"
"C34ocjCqBXsZDQtb8T3w54OxIiRLn9VMj1pizbgC+x2htmyBt6BNHns7K08DM67SiG7ph049Ze/SFoZqb4waCUu1dRYZAUKUo50Uy25Xi5Qi"
"cHhcUOWHxIiTl50THEQCA884azGo9ZNpby+krX1dfVuGSovwvESk0GGNM+LgKNw1tpj2srpQZIsMG8Oo1fFxriIX5dCJq1v4J8gHw75q38wx"
"ySwPds/XHbkgK3KgkVrL/XcfUP3myMke3shNr8o7tm8SulaUZn0J4hWawGegO6wS/44Q76OoeLluOvOHyERd6wMPquKzo9lZqATi0x8CrpC5"
"GAE="
)
CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1: Final = (
"CAQSwwYKEwgSEAEYAjgBQgluYXJyYXRpb24SDHTsA0CfvetGZFL8axoM4khrNWxDqnQ4bENWIjDrerGCpIXFI6LZF2Hk4OYvtcRO6Ytxz5kc"
"E7vKFBT57mJF6FitCHcxRNk1M7/C2L8q3QUy4sf0KVQTWQbGHFutqk/OUkcyJvaS/tPjOrhqUWhsWRsInGBGX3sjSLMWWNQ3bHdnql0bVDFc"
"YgLfO2K+1Ta2P3pna3jpvBO+BM+W1xQ1FrenEWqbXtNwueTC6kQqGUZnmULo3cbMb5l1Yo2nui6i87a3Bs03jtomyzjRb+xMH2XNpePzURLf"
"ADvZIHyAPOlHOnK6ZTk4rugCEHHTAudo9Hz/6ZDTjXTpqzDD69lxgcdviZ2oNMpExhPxJctgzNBuYdFYjT09B0Atag0HLXYdUL6L5Cz1599n"
"AiTQl60CWALeyuJS65GikY3FNn5tXt1IPHLUsNsoEzBr07lvZ1WeyyiyoExBOCSgH0KuxSIP9TL4hQsMiI9kduv3w4J9ybSyViI4sXg3nlUz"
"5UqNonSx9487qwcmlZxZQquU85UtyA6Kcym6oAUH3cr1+VrYvpBZzwku00ccQQ2faJGZ18AIBYwvY+HZQ0bPop7AkYSqIyeLe5A8vcm3O+o1"
"sRpj05W9C649sYuPo9qXUabkB/WlkoLydG3X+erc1ry3c6yur9XYrtGfXcVCdA2xtYOkzYlBXrYTbVL/oes3aBTt2Yg+0OLaa8XM7rvajpF0"
"QkYwtAQwWwyBe2gPtMWVJUuvljICUwMhKPz2bD3/7X/cuNKmso3Y+sGzoCtylrggSkdVdMNB1zTebX5iPmIk2LDGuEDyqyiJGugGo04yEzyv"
"Q1icaJmssvQprgCmJJkHB1PnR3Lw2tMwCFgyrJxXLi8lDSyFmcl9YoHF0OBcw0+HFAuZsgkbjHXeVU/K3jFAj+GP3a7HBrwoN2jBHI9RfU74"
"Un4iBaoK8JWdy+/vR0vdGiifISnlzmSOL9y+mmJubPkLMxwH4+vnfXuDMYvDhgn1M7vSUwiHePupdVz6HxS2LjY7XrwVgLSZHoGmvdP6NoeB"
"kwzjb7hXaitkAzyqZls63keq+Hw+tPTlMGO5NtPeGAE="
)
CLAUDE_SONNET_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-sonnet-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
**BEDROCK_INVOKE_REQUEST,
"system": BEDROCK_INVOKE_RESPONSES_SYSTEM,
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-sonnet-5-5",
"id": "msg_bdrk_i3avv2mb3domrfdrl6s7b5mubzt6vckxqeea6ieovrsgmyzby7ca",
"content": [
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, though reading the test file in parallel "
"wouldn't conflict with that instruction. I'll prioritize following the explicit order and "
"read the validation file first.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll open `shop/validation.py` to see how `validate_quantity` handles zero, negative, and "
"non-integer inputs, along with `tests/test_validation.py` to check the expected "
"zero-quantity behavior.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_bdrk_01FfS5J9LzLxLwq5caHEM4xW",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
{
"type": "tool_use",
"id": "toolu_bdrk_01FTMGZf7C2vzjc2Ux2SJyoU",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 40},
},
],
"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": 536,
"output_tokens_details": {"thinking_tokens": 242},
"service_tier": "standard",
},
},
expected_litellm_response={
**RESPONSES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-sonnet-5-5",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The user asked to read the validation file first, though reading the test file in "
"parallel wouldn't conflict with that instruction. I'll prioritize following the "
"explicit order and read the validation file first.\n\nI'll open "
"`shop/validation.py` to see how `validate_quantity` handles zero, negative, and "
"non-integer inputs, along with `tests/test_validation.py` to check the expected "
"zero-quantity behavior.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, though reading the test file "
"in parallel wouldn't conflict with that instruction. I'll prioritize following "
"the explicit order and read the validation file first.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll open `shop/validation.py` to see how `validate_quantity` handles zero, "
"negative, and non-integer inputs, along with `tests/test_validation.py` to "
"check the expected zero-quantity behavior.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
],
separators=(",", ":"),
),
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "toolu_bdrk_01FfS5J9LzLxLwq5caHEM4xW",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_bdrk_01FfS5J9LzLxLwq5caHEM4xW",
"namespace": None,
"status": "completed",
},
{
"arguments": '{"path": "tests/test_validation.py", "start_line": 1, "end_line": 40}',
"call_id": "toolu_bdrk_01FTMGZf7C2vzjc2Ux2SJyoU",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_bdrk_01FTMGZf7C2vzjc2Ux2SJyoU",
"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": 536,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 242, "text_tokens": 294},
"total_tokens": 1413,
"cost": None,
},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, though reading the test file in "
"parallel wouldn't conflict with that instruction. I'll prioritize following the "
"explicit order and read the validation file first.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": "I'll open `shop/validation.py` to see how `validate_quantity` handles zero, negative, "
"and non-integer inputs, along with `tests/test_validation.py` to check the expected "
"zero-quantity behavior.\n\n",
"signature": CLAUDE_SONNET_5_5_THINKING_SIGNATURE_1,
},
],
},
},
)
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSgwUKEggSEAEYAjgBQgh0aGlua2luZxIMT1FeqW5PaXtFp114GgyoxyN+NbjKsT1yxB4iMF13gzAPt/OOukSm+Is78v7dbu1WcrJvArvI"
"HMK3ZeviwjQPyQ0zywjsqDWnepR7/iqeBAFSYFwVgmpUGxZIoN7tQ+XnRVF+YNYPY9HbKw6lE89F3jejjSkPFYWIUkfW2KsB3/kEmkWrXzV7"
"dIWAxKfGGI6gvIvzVGl8UoKB7cYJqtx1888mqoLH8mGjYRtMrPang71iBUoiJjThOdSiPSTr+HnvGb6e9CpXduwBsuCATo+ZKAKiyDoYEqr9"
"HRmvz7fi6RuKSErHfG9Zod7muUKjqw2Y/kaVJenornm8JuMYuYIfnv0II3MBHtH0nKr6ZyPuaALFl+L7sh3eazeahWzC3CeZ8LZmLp5NuOg+"
"xsHNJQDjWJuXIUrCoYdc3gnCgcnuEYd2dz2+tmrR7K509+uCOe9EEoO1SuKU+YM9qkSBVPo3VR99cf2XpUc3K+4v1KLocUjtLlgoLmxlpES6"
"uJLhyP65XlvIFAOGAYH0hiwvbUq55i36T9LHG4mbUdwzjum1CSzZ8trx3k1lzcsxlLVPIY3JuBE63HfqWZs/T8UobfsPbTCrMgBqpmR+wBdi"
"8wKJPiasyregTVYWuhMrg1LFodr80/co5TLeLAvoI/oXs6Syz8ME8IMpKD4iHNr7Pj7/Le/XEAU6W+2n/b8Hx6NVRysrl729eIqV4Y2pk2Xl"
"CUCVx0wfuAlvw5TR4Ft6Eb7/wbSOlxU/E5iqaJusZbpQLEtCTUXU4IKgmaPJZFxKWIEv3hbROZ477bvTyROQgaDlcabkiPH1o6FREM5BeGI1"
"GAE="
)
CLAUDE_OPUS_5_5_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-opus-5-5"},
expected_provider_endpoint="/model/us.anthropic.claude-opus-5-5/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"system": BEDROCK_INVOKE_RESPONSES_SYSTEM,
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-opus-5-5",
"id": "msg_bdrk_mxljoibckai4wqyt4wd7cmslqjtlkals5cbwms2hackerasjglha",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_cwcayjjtio2jq5g6a45acoimfxqughi7fphihxe5toxmhqojwboq",
"content": [
{
"type": "thinking",
"thinking": "I'll read shop/validation.py near line 18 first, as the user asked, before looking at the "
"test file.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how it handles "
"zero, negative and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01J5u6tgn3ppV4c2VpmD2xy6",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
},
],
"usage": {
"input_tokens": 23,
"cache_creation_input_tokens": 0,
"input_tokens": 4,
"cache_creation_input_tokens": 873,
"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},
"cache_creation": {"ephemeral_5m_input_tokens": 873, "ephemeral_1h_input_tokens": 0},
"output_tokens": 196,
"output_tokens_details": {"thinking_tokens": 51},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**RESPONSES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-opus-5-5",
"object": "response",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll read shop/validation.py near line 18 first, as the user asked, before looking "
"at the test file.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I'll read shop/validation.py near line 18 first, as the user asked, before "
"looking at the test file.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how it "
"handles zero, negative and non-integer values.",
"annotations": [],
},
],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"call_id": "toolu_bdrk_01J5u6tgn3ppV4c2VpmD2xy6",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_bdrk_01J5u6tgn3ppV4c2VpmD2xy6",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
"cache_write_tokens": 873,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 196,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 51, "text_tokens": 145},
"total_tokens": 1073,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll read shop/validation.py near line 18 first, as the user asked, before looking at "
"the test file.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
],
},
},
)
CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0: Final = (
"CAQSxgcKEggSEAEYAjgBQgh0aGlua2luZxIM93CYh6+fYNYfl0lvGgw7Sq5PzeOUQaR9JKoiMK9/V24UwNwvJbJdQjDEFCLEIn3lZgk7//Uw"
"Hr6kTvOTtxS6Xdgt1IphkLtCfI1rWCrhBvKpjQHMVva70EZuEDWg2HPEMrmnrvUOXJniTRUiArTXQTR6itTG2XXqxHHsARUCq/1ECbBG9j5X"
"Ti6iF/bgGEVkeWr4rmCNYnQtGS1Rn+f83bHPbnBwyMOH29aX0JS9kstQFoaPOa4G4BnzVgFg5Tnj6JN9hh+aSoBMCliraNTo1lirHHpQXqCZ"
"jupkIKRjDyvRfpE96tGjtWTJFJ3f8HTm2PiTGUOhCz7PoypLgCfOQWyfaptuIUKa9sZXtJVlLBmoj1XDqIqQKsCcvDKPjDnAVVsTr4dAExxP"
"g/3ujwP5Y/+LDHFE9XPetApyfiIh3qy5L9UH1Yv9RwKLqfn3KWPlXEWoCrvgOTj7e5EfTk7Cu3WxDNp8SNs0TeFnGsCKQGASuqTtgZTYzrpD"
"Jc1EbTZOt+CRVUgVhcbadMSdhpy/PcAtgiZ8/MvZCCv7BeORzmVYb9cYaVFVQK4/tchF/lcK+4YVvDHCCSXAwhj6Y9NyQ7j94JmFNqhjsSK4"
"t4qALhhmOcJuCispP6ZRhf1SCoajBsRVRdtvPbFnOH1GqdErrzAEcD9VZk1mkmUN6fs9Vl9Uva6XjVr7YzQHjdkGZ5fEHcIpmJrS1ZMI+YuC"
"quoy4qMJvp8g8YgoLYjt6GFWqwOwePTuFmMnL7VadlmEtwAionrUqEXCwSh8FVOeN8mvaoA2V2AtGp5zA4SDmbrF+XhuNS77ac0dCcQbs8iy"
"H1a1oSySzqGf+muJBkoSCVtIAPQ48+9ha3fGM49fj2EQINCu4NhcBylZqFhHV7FJA620qqEJV8kWBJqc6j9pYHQYSirhnBLxPFPFQS3UNItx"
"k4c5oPs3VGPea++KQhhbRnlAEPu1pKzKMM7yg9+rT28l2XiIGnWSqBo/J8ipsL/uFcthzptNtoK75pxhGduvynAI7wRbArxT6UMegIsPdRlH"
"uXBbyXKuXhbnCoCkbb7VNbsO2tWWqE5rUdLgKyHd57SL3BlJDVd+V+/bW84zqP7QiSIMmrv3Q8lVFjFyOEXfeRZF7pXapgdAK5CWgoKXwdVF"
"oar+HuszSP6LPqJggfD+9eqZhpZI6wmUzSVc9TlZAV+fB7pWcDVgBYG2Vk6bckiXOZrJigDuAbHObeZ6BcKQpID/9TvvtNKnQGJy4Uva2p8Y"
"AQ=="
)
CLAUDE_FABLE_5_1_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "bedrock/invoke/us.anthropic.claude-fable-5-1"},
expected_provider_endpoint="/model/us.anthropic.claude-fable-5-1/invoke",
expected_provider_headers={"authorization": "Bearer synthetic-bedrock-key", "content-type": "application/json"},
expected_provider_request={
"messages": [{"role": "user", "content": [{"type": "text", "text": "Say hello."}]}],
"max_tokens": 64,
"system": [{"type": "text", "text": "You are a terse assistant."}],
"anthropic_version": "bedrock-2023-05-31",
**BEDROCK_INVOKE_REQUEST,
"system": BEDROCK_INVOKE_RESPONSES_SYSTEM,
},
mock_provider_response={
**BEDROCK_INVOKE_RESPONSE,
"model": "claude-fable-5-1",
"id": "msg_bdrk_kct3wlyhliymwyvqmjn6uy72qpg4hekwep4upsfqdec3b7wqf5vq",
"type": "message",
"role": "assistant",
"content": [{"type": "text", "text": "Hello."}],
"container": None,
"stop_reason": "end_turn",
"stop_sequence": None,
"stop_details": None,
"id": "msg_bdrk_ehpngdq5umo3xytr46gfdb3ifglm2bsofgtx5zargdynfbgdvepa",
"content": [
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, so I'll follow that order and read "
"shop/validation.py before moving on to the test file.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, negative, and "
"non-integer values are handled.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Ee5Sz4v3R2bgHS6gQV5m8N",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 40},
},
],
"usage": {
"input_tokens": 23,
"input_tokens": 4,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 0,
"cache_read_input_tokens": 873,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"thinking_tokens": 0},
"output_tokens": 283,
"output_tokens_details": {"thinking_tokens": 142},
"service_tier": "standard",
},
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
**RESPONSES_RESPONSE,
"model": "bedrock/invoke/us.anthropic.claude-fable-5-1",
"object": "response",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "The user asked to read the validation file first, so I'll follow that order and "
"read shop/validation.py before moving on to the test file.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, so I'll follow that order "
"and read shop/validation.py before moving on to the test file.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [{"type": "output_text", "text": "Hello.", "annotations": []}],
"content": [
{
"type": "output_text",
"text": "I'll read `shop/validation.py` around `validate_quantity` to see how zero, "
"negative, and non-integer values are handled.",
"annotations": [],
},
],
"phase": None,
}
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"call_id": "toolu_bdrk_01Ee5Sz4v3R2bgHS6gQV5m8N",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_bdrk_01Ee5Sz4v3R2bgHS6gQV5m8N",
"namespace": None,
"status": "completed",
},
],
"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": 23,
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens": 873,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 23,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 6},
"total_tokens": 29,
"output_tokens": 283,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 142, "text_tokens": 141},
"total_tokens": 1160,
"cost": None,
},
"user": None,
"store": None,
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "The user asked to read the validation file first, so I'll follow that order and read "
"shop/validation.py before moving on to the test file.\n\n",
"signature": CLAUDE_FABLE_5_1_THINKING_SIGNATURE_0,
},
],
},
},
)

1113
tests/integration/translation/responses/bases/bedrock_mantle.py
View file

File diff suppressed because it is too large Load diff

676
tests/integration/translation/responses/bases/gemini.py
View file

@ -1,7 +1,501 @@
from collections.abc import Mapping
from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import RESPONSES_REQUEST, RESPONSES_RESPONSE
from integration.translation.templates.gemini import GEMINI_GENERATE_CONTENT_REQUEST, GEMINI_GENERATE_CONTENT_RESPONSE
from pydantic import JsonValue
GEMINI_RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in RESPONSES_RESPONSE.items() if key != "provider_specific_fields"
}
GEMINI_3_8_FLASH_THOUGHT: Final = (
"**My Approach to Analyzing Quantity Validation**\n\n"
"Okay, the user wants me to understand how zero and negative quantities are handled, and they’ve "
"given me a specific constraint: explain my next move and then call a read-only tool. I need to b"
"e careful to avoid making any changes. The overall goal is to review the project, so it's a good"
" approach to use the responses client to keep track of the process. I also need to be mindful of"
" zero, negative, and non-integer quantities in my analysis.\n\n"
'The user specifically mentions "reading the validation file first." Let\'s start with `shop/valid'
"ation.py`. I need to figure out how they are checked in the `validate_quantity` function, so it "
"makes sense to examine that file. But before diving too deep into all lines, I should try to min"
"imize how much data I read. Given that the tool's performance might become degraded when reading"
" large files, I should consider reading only a portion of the file. To get an overview, I will r"
"ead the first 50 lines to see if that's enough information.\n\n"
"Following the instructions, I need to clearly state my next step before executing it. Therefore,"
" I'll explain that I need to examine `shop/validation.py` to understand how the system handles z"
"ero, negative, and non-integer quantities, focusing specifically on the `validate_quantity` func"
'tion, then I\'ll use `read_file(path="shop/validation.py", start_line=1, end_line=50)` to read th'
"e start of the file.\n\n\n"
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = (
"Er8KCrwKAWkUfROyraCcwrIYpIws/Jh5cMTrVJ2ShZLiHvXJuIq/KdxErXHBEeWq4H9FXkFOU5eZFSvo6lnkwhw09W+nukH2"
"Jgcjan4KoNsFIGvNKhF/mT66xCr40t/LHRSIxu4o585L29auyheBJmh3cR4NjnZPYwLKzmnI3W2ePhcD5tjLU/pt6LOX4IBN"
"jsDho8ep9wW2foJDkEorvAYRI8RiXJ2loNEjagJAaSo2Rt3URPz3KzvwKo8QlJAYGiQ+5eUkVnwcCsNs0NNY5+RVggqnJflK"
"okqjOsaIXAxo2jupI4amtI+NpQ59K5TddnJ8eh+fiQSphB2Ex2AlhczWhoXbYqdkjRfYtXF1KiTO4w4L74ApYd7iMSm1Ix5U"
"76yYiB5+sRaZYzuBIdD01O+SMqPXil9Ft73kzuH6CROVi5Xf3RMRAQvmuJcRYciprH0kcba7E2Z6c0v7Ht6kegzoWrpAtGgW"
"hL2KTMewyWQF7IZmYLGoo20hniIliBs+7bLAPJ3DEsp1HU55dAsdvV1IwQZtFuqKffE7MB0uQws/snCf6w9mpCbVOYRVuzZe"
"LTbWzar84bmsp1dfHGS2gOkvsi5fi8IUs/be9aK/budI6nkSXborMoESSG3Z5BTXgi5U0vJcS2FTO6oFMpE1lPBL/vIpPDKR"
"ujjqtUT+QA89SJmLZDORPc3aLd36dEErhlSZ+9LYsU3EkKNruomCdiSrbClIRK50YYu/ocG9lXF4yhUp3dgKbMWCw9jGZv+a"
"KPz8sXVgbXSm+zLuvtByXHSfiVmu7hP1Oc7BmdL+lJW03rgMAxtDb39rbP8l+5sm4EDJil9mcGGOYpcBSKRmDacoqk9D8AWG"
"PwlYJ6L1EfsxKXQNFXa9l4kEv4QXn2d5BQnfCjFwsnolQmeSWP2XYh8O+R/YmhhFIAZhvzMctHnQ/XRRMnjADlpnM1mioyy4"
"poDsUDKIyr92JvDK+T+1NRU/uQva9ScCF9YJCM3uLdxkocwx8eBN0hsOZYosrUq9FLL0+aNgHgybUyn4Kef197W4fht3yS2Z"
"AUuNm4nM3VXRKlLgP3MYJnkOlBTVooyEoqC6raGH2RMdIegAs5JSIyd6xHkg8J2DaLhy+7WbpwqcHHCnM67sVyfRqQC9TP1a"
"D0C0saoNL8sAZfHiDQPOLmvxt9z2+QpYeNZprWgGIGw5iZmLPexGHNLFd+i063HUpf5dYmjPwdL7970CW8PPQgjxW7OMOTlm"
"Gkbf4YMsyiTrHbmVBjVPm3dA93q7wE3zsuhJ2icHkT7zlvHzz+nYtgJlWyoMtOPOjUunNM2pVXmMtXou0Rp0aR7YDIy9uqnY"
"GIfBKYriMp/wL1apCyzih0EqcGhqNVspDDPJV0Slj3VKP7LaBTqz0LdTFo1WZAZNUZJW2sOHC8c9oXjNCM/o25qOPHowmzN9"
"kWFBAtuetPHn5lD5PFvIdYMyjOtwRpFsPyAM8E6Nb7hP3pQnW8zvQ9YrfT6nqst39f5JHyjXh0HtVJgF+EjETS8H2EJSY3a9"
"ExXPCRmCyXnKR9haJ95o+XRVMlJRucw9C34RwZ/po7oivV5jV+hSSOnTZuxx7rGH6md0ELhMKXO3PwaNE/s14SqOCBc9s9yj"
"vGbC9fVe89KWNigVeejbIVlSs8uoHld9Bhespx8zZVheVQP9Oc9lVLXzmLteo4GNKkFYoJ7a5kCvx85vj9vAqKISOBuc6Vfu"
"zH3cl8BYRVo5JiaxWRQxcTAtTbhH/RxOXHm+gc8gtdisilWLHaS13D0gmaq28gkUTCg="
)
GEMINI_3_8_FLASH_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_8_FLASH_THOUGHT,
"thought": True,
},
{
"text": (
"I need to inspect `shop/validation.py` next to see how `validate_quantity` handles zero, negativ"
"e, and non-integer quantities."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"start_line": 1,
"end_line": 50,
},
"id": "call_23592",
},
"thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 354,
"candidatesTokenCount": 64,
"totalTokenCount": 750,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 354,
},
],
"thoughtsTokenCount": 332,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "-CbQavzyBouHz7IP-Ma2uQw",
}
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "gemini/gemini-3.8-flash"},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": RESPONSES_REQUEST["instructions"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_3_8_FLASH_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_RESPONSES_RESPONSE,
"model": "gemini/gemini-3.8-flash",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": GEMINI_3_8_FLASH_THOUGHT,
"annotations": [],
},
],
"phase": None,
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": (
"I need to inspect `shop/validation.py` next to see how `validate_quantity` handles zero, negativ"
"e, and non-integer quantities."
),
"annotations": [],
},
],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"call_id": "call_23592__thought__" + GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
"name": "read_file",
"type": "function_call",
"id": "fc_call_23592__thought__" + GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
"namespace": None,
"status": "completed",
"provider_specific_fields": {
"thought_signature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 354,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 354,
"video_tokens": None,
},
"output_tokens": 396,
"output_tokens_details": {
"audio_tokens": None,
"reasoning_tokens": 332,
"text_tokens": 64,
},
"total_tokens": 750,
"cost": None,
},
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT: Final = (
"Okay, here's my summary, taking on the persona you requested:\n\n"
"**Navigating the Validation Landscape**\n\n"
"Alright, before I dive into the core logic, I really need to understand how the system handles t"
"he edge cases – specifically, zero and negative quantities. I've got a gut feeling those could b"
"e potential vulnerabilities or, at the very least, a source of unexpected behavior. So, my initi"
"al move is clear: I'm going to dig into `shop/validation.py`. Understanding the validation strat"
"egy upfront is critical; it informs everything downstream. This will give me a clear picture of "
"how the system is designed to handle invalid or potentially malicious inputs and will set the st"
"age for a more focused review of the main logic. I'll read that file first.\n\n\n"
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = (
"Ev8BCvwBAWkUfRM62a1j2olCssVKs9GECDQ5L1C7yrRsGmPVGbcIm+MrafD721G6/xzw4hoxWRaLYt24NwcS8gLJMwZMKF2U"
"xOKF2qPxQIrxVkY0JG8s9A1vVBlu4mNsDGoBMPLc3CEX/Wb7sJ8u/oaXz8n/4yWDc9NgLwxdpzrDH9An0fmu2MGpZ+rL1nHj"
"E+ZoNp6gKpaiRe3MmdBF2+Oy3MI6JZQnU9C/T9InT2F6NyzdZMhqSXhTf5qddxt9XLeabg8TKO4+GLKlmjB/T9NBOP00fQqS"
"rLtPHkoQgxhn3S0Qj5kDAOgNXvJM4lyhlGyWIfBuHNN3VI9LpfVMhKU2"
)
GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"thought": True,
},
{
"text": "I will read the validation code first.",
},
{
"functionCall": {
"name": "read_file",
"args": {
"end_line": 50,
"start_line": 1,
"path": "shop/validation.py",
},
"id": "call_25410",
},
"thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 354,
"candidatesTokenCount": 41,
"totalTokenCount": 429,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 354,
},
],
"thoughtsTokenCount": 34,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "_ibQasKwGeCBqtsP84vwkAk",
}
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "gemini/gemini-3.1-pro-preview"},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": RESPONSES_REQUEST["instructions"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_3_1_PRO_PREVIEW_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_RESPONSES_RESPONSE,
"model": "gemini/gemini-3.1-pro-preview",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": GEMINI_3_1_PRO_PREVIEW_THOUGHT,
"annotations": [],
},
],
"phase": None,
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I will read the validation code first.",
"annotations": [],
},
],
"phase": None,
},
{
"arguments": '{"end_line": 50, "start_line": 1, "path": "shop/validation.py"}',
"call_id": "call_25410__thought__" + GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
"name": "read_file",
"type": "function_call",
"id": "fc_call_25410__thought__" + GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
"namespace": None,
"status": "completed",
"provider_specific_fields": {
"thought_signature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 354,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 354,
"video_tokens": None,
},
"output_tokens": 75,
"output_tokens_details": {
"audio_tokens": None,
"reasoning_tokens": 34,
"text_tokens": 41,
},
"total_tokens": 429,
"cost": None,
},
},
)
GEMINI_4_ARGON_THOUGHT: Final = (
"Okay, here's my thought process on this task:\n\n**My Approach to Quantity Validation**\n\n"
"Alright, the instructions are clear: I need to understand how this system deals with potentially"
" problematic quantities like zero, negative numbers, and non-integers. The prompt explicitly dir"
"ects me to start with `shop/validation.py`. This makes perfect sense; it's the logical starting "
"point for understanding the system's core logic regarding quantity checks. I also need to rememb"
"er the system instructions regarding the use of the `read_file` tool and not making file changes"
".\n\nSo, I will state clearly that my next step is to examine `shop/validation.py` to understand i"
"ts handling of these edge cases. I'll then use the `read_file` tool on that specific file. This "
"will provide the necessary context before I can even *consider* any potential fixes or further f"
"ile inspections. This approach aligns with the instructions and ensures I'm building a solid fou"
"ndation of understanding before I start looking for specific issues.\n\n\n"
)
GEMINI_4_ARGON_THOUGHT_SIGNATURE: Final = (
"EsIFCr8FAWkUfROZ8zCh3vM4ufC+mcdQi7BamG510F5TkuWeQp8lVro8DkxrDl/ZyWgcPR4JVCGdPY4copLFyp/2Qz4zjr2P"
"oQxUmWbFtBm66uN4aYxLhcGXwwB3BIWXezLRJXaVoJl6ex/VrXnos2M/3+CHVKM3ThtPYYsZjpeqJgnHsYYZi3X/sl+G4214"
"OL2X+pSGsxESSoj4EFOqHb774e9smvmLzNbca2cEDuo5dvoGlkdgALSL2ODIVi/625uid3Sbf+YAhj8aIoD4/e0LDgbRYilG"
"o5MsGgLFQfyEjjFc0N0NxL02T+9qjlagPHSe74VAsWydKGgFQhgk9MOy9bIdJ+9RE1CWYjAaHXwagQenSa9tLq1bCNo5RXJF"
"2aRrT+pWc8KwUL8HaqYEytvT9yHyTm99nMDFTMPpCDcsjIKmlG0FABQfEpBT9cCjZMsRR5hfK2voTRcjFvGecHBD71XX3Q+N"
"0p12WK87Z9Hw8OQgWIYdamOtMDw2n24m1fhC1fEJbSzOC3PzDwZOAUPemFxHpi9Vo1TnONRBX4wEAWhdigP5qr/CSmUPiiFm"
"c7Ay8rxezmoqQ8bs1zBYnFzAhBMAHfc+lZ2uEmoaIK1b0FydfDTZXpeF+ayxLz9OPhU4jrKJ3n5tywrQvx7ruwhIlJpX1sfx"
"OfyRbrNbOkX0ruTvyvGRI34kIQUoMK4M6oAUo8n+W3DGu7AO+lljNkVanLaAlJwCc/9r4E8GMKpRnqpit+ia2NUDi+U4/Ob3"
"XOxODNUzd2DgAmgXmcHczCXa/SSfy/wFqW21QYXzbPgpAboF/qVV17q7NU1DCXtPamowkMERCPB6Z5FZI34dPToDXyYQGxak"
"MVAH6f0vZUrpakrs6uXFR5RdwOEUzcPfQq7nwskzrvWCzyNk8YnXJjccpGCF/cXRQW+MKV17bj9xjWZguw=="
)
GEMINI_4_ARGON_RESPONSE_FIELDS: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_4_ARGON_THOUGHT,
"thought": True,
},
{
"text": (
"I will read `shop/validation.py` next to see how zero, negative, and non-integer quantities are "
"validated."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"start_line": 1,
"end_line": 50,
},
"id": "call_31641",
},
"thoughtSignature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 412,
"candidatesTokenCount": 65,
"totalTokenCount": 614,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 412,
},
],
"candidatesTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 65,
},
],
"thoughtsTokenCount": 137,
},
"modelVersion": "gemini-4-argon",
"responseId": "AyfQauWvIqOO6dkPs7f0GQ",
}
GEMINI_4_ARGON_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "gemini/gemini-4-argon"},
expected_provider_endpoint="/models/gemini-4-argon:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
**GEMINI_GENERATE_CONTENT_REQUEST,
"system_instruction": {"parts": [{"text": RESPONSES_REQUEST["instructions"]}]},
},
mock_provider_response={**GEMINI_GENERATE_CONTENT_RESPONSE, **GEMINI_4_ARGON_RESPONSE_FIELDS},
expected_litellm_response={
**GEMINI_RESPONSES_RESPONSE,
"model": "gemini/gemini-4-argon",
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": GEMINI_4_ARGON_THOUGHT,
"annotations": [],
},
],
"phase": None,
},
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": (
"I will read `shop/validation.py` next to see how zero, negative, and non-integer quantities are "
"validated."
),
"annotations": [],
},
],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 50}',
"call_id": "call_31641__thought__" + GEMINI_4_ARGON_THOUGHT_SIGNATURE,
"name": "read_file",
"type": "function_call",
"id": "fc_call_31641__thought__" + GEMINI_4_ARGON_THOUGHT_SIGNATURE,
"namespace": None,
"status": "completed",
"provider_specific_fields": {
"thought_signature": GEMINI_4_ARGON_THOUGHT_SIGNATURE,
},
},
],
"usage": {
"input_tokens": 412,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 412,
"video_tokens": None,
},
"output_tokens": 202,
"output_tokens_details": {
"audio_tokens": None,
"reasoning_tokens": 137,
"text_tokens": 65,
},
"total_tokens": 614,
"cost": None,
},
},
)
GEMINI_3_5_FLASH_THOUGHT_SIGNATURE: Final = "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"
@ -93,185 +587,3 @@ GEMINI_3_5_FLASH_TEST_CASE: Final = TranslationTestCase(
"store": None,
},
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = "EtsDCtgDAWkUfRODYoLRWC+DajYQxOvsLgPh0m8j4NTnd7BflzgPBKFfPW+PU1XsMQuEzviI1qk5mYI0qCfOQNf84PAXXvFA5hMYl+YObaND4G+ZtCdYcolFVfPJQqgK6Kpv20n9hZfLt5JzOS2+HRCLZaokIsZFadN++wqEeEkWQhnKdLGH1lM0fn8Fj/pYq95YLGnB90B8Oaj4qyG6ost2dzRAeAzFSXAko1mD/IgsDrDhEumngCqotdAbPW4jUGYOGDpoXLrBzQZvGa9blRC3ep6NLT0EYMnXImLFoZaLLIBMzVDsmmL0qOg4Gu+uNJlY6cDmtqRgkrcvuvGhh8+lrjUMJVigSsTAoKsTnT3OyCqdNqa+R2aD4WTl1uBFyGY7yXpZ9skQPkV210QNOylZ6exaMA51+W/mohL5j5+OJX7xtVfRIpjp4e0PLkEPxnuviX6OU4ykWZSSiztSXzogbrmnwP7faclRXTXHE5pFlM8y7gDJ9NEwxd5vvIMLdaK2dRWBNtvjI3Cj56sLKygH/j0mQSnt3PonE6Jv6XMJDPbuIzsjzX8t/j3u6WP0bVGnifNNEfIqt6YcKgeWlUTnabRGkWg/fBSyYbiTTEIGhketv57hA9oH7jJZbw=="
GEMINI_3_8_FLASH_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "gemini/gemini-3.8-flash",
"max_output_tokens": 1024,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.8-flash:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 120,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 108,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "5BjEaunaCtadz7IP-8WKsAk",
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "gemini/gemini-3.8-flash",
"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": 1024,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 10,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 10,
"video_tokens": None,
},
"output_tokens": 110,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 108, "text_tokens": 2},
"total_tokens": 120,
"cost": None,
},
"user": None,
"store": None,
},
)
GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE: Final = "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"
GEMINI_3_1_PRO_PREVIEW_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "gemini/gemini-3.1-pro-preview",
"max_output_tokens": 1024,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
expected_provider_endpoint="/models/gemini-3.1-pro-preview:generateContent",
expected_provider_headers={"content-type": "application/json", "x-goog-api-key": "synthetic-gemini-key"},
expected_provider_request={
"contents": [{"parts": [{"text": "Say hello."}], "role": "user"}],
"generationConfig": {"max_output_tokens": 1024},
"system_instruction": {"parts": [{"text": "You are a terse assistant."}]},
},
mock_provider_response={
"candidates": [
{
"content": {
"parts": [{"text": "Hello.", "thoughtSignature": GEMINI_3_1_PRO_PREVIEW_THOUGHT_SIGNATURE}],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
}
],
"usageMetadata": {
"promptTokenCount": 10,
"candidatesTokenCount": 2,
"totalTokenCount": 115,
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
"thoughtsTokenCount": 103,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.1-pro-preview",
"responseId": "5RjEaqfwC7XYqtsPp6TuoAY",
},
expected_litellm_response={
"id": ANY,
"created_at": ANY,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"model": "gemini/gemini-3.1-pro-preview",
"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": 1024,
"previous_response_id": None,
"reasoning": None,
"status": "completed",
"text": {},
"truncation": None,
"usage": {
"input_tokens": 10,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 10,
"video_tokens": None,
},
"output_tokens": 105,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 103, "text_tokens": 2},
"total_tokens": 115,
"cost": None,
},
"user": None,
"store": None,
},
)

761
tests/integration/translation/responses/bases/openai.py
View file

@ -2,7 +2,8 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import RESPONSES_NATIVE_RESPONSE, RESPONSES_REQUEST
from integration.translation.templates.openai import OPENAI_RESPONSES_REQUEST, OPENAI_RESPONSES_RESPONSE
GPT_5_4_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -471,120 +472,148 @@ GPT_5_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "openai/gpt-6-luna",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "openai/gpt-6-luna"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6-luna",
"input": "Say hello.",
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST, "model": "gpt-6-luna"},
mock_provider_response={
"id": "resp_05a79fb530391552006ac3f01c4cec87d0881e61192e1046ba",
"object": "response",
"created_at": 1791225884,
"status": "completed",
"access_programs": {"cyber": "daybreak_blue"},
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225884,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-luna",
"moderation": None,
"id": "resp_042cbd1ba73eb559006ad0239f6dc087d08fd7ff5fff84b06a",
"created_at": 1792025503,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025506,
"output": [
{
"id": "msg_05a79fb530391552006ac3f01cb60c87d082152e269d863aa4",
"id": "rs_042cbd1ba73eb559006ad023a0481487d0aea8635e4b717121",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COiaJAwBRbzsaBwqI_w56uTvcixfz0ImWwpaGwIbCDMXDOodeG_MedwCPLjagtmdVPeq1GAF21VbUncSo2oasMY26z31MMbmZQPKUXWfts9Dajf6g-11D0hZMUupKeeUOT_rcE_GBj6smH3d1PUf-FBMEsY1VQy0gr0am-GUa0dZjw3ukAX0K10gkPCrrqRgp7mlfEi9kAwXhlQ1WEVm7IdHdZnGBbWzKaIRDVkULZQlh9NHIFYCP-2OQbnmqK9vyUxLj3vYXIXGv9B0V3-9TPe8AfDg2tm3AH-tJ-XXJ8D6xDG4E-1avSe4vUrYggFM7_6ztYSrimWqtJ_PfvRQF4cZfcCDf3vxxzLreg3y0jtuZnEOejZYybCa72ZDBbI9OSgNvAZBkU6k9DLT_tQf9uCvN1vtoiGXu0Sk4yr1fw-hAnuEVJK_Tb_FfQBNEk7ILVK7UJaX1rZWTFe2GLhsp6ctz3Kp-c2w2JD5ZHvV22EDQ5DmP8ng9l_5COYQGSsS9ZLiyd06agQ3PvQvBTg5XnDL46DtZ1yfVkB1cuwwlUiWkKD6MQ-VifToT3s4aG0q1Bnl9b_AvtOM0lG-TblA-mdOaRDz3c9s4QfbQjt6Z75oQcNr5QkUujZoV4YiynIBpec5i2gr6Uv0SMJZZbzjY5PLiogj_gvUDxwVbWJkuMXjEPJ3WHWMjceJE4sHwuM95zWV80Ul-MSXknlBj-AZJGQ44_wl0765P--vLyq18jfKDCdorP3Lvq6lYxnXooYMnZ-lFgnWo92OHfX97d6FCyQ46ygzQaRjrhQwUyAioAZiFtugMnHUm7t-EfNb_C7TjLeyXLiJ9iVlGHIt17VJMJIIq_xrQeMCOHAxUKgUE21XkSwsVPdJ0I-4_OP5l3IwkiV0pctG1x-oYX7kCaIYDus-dJUehQNJWNEa_r6QPfn7txUoxMrNCCIyzRUfH3hgwCHudDJ26dj15RPGfiP3wQmX8oZKdy5VkQcNPWb4Gv6b-cjyI7U-8VmwlodUN5FlCj-LJbeL8C8Wxuf1LRzDW-kxNadEhxlQaDSq4nQfTnGARMcmlH8-XqZfXK-3hJD84xHuyjTHq7aBr85gM6vISoYOHf6d-5GIr3-z9cTXvE7tCuxoJ7DdZYWzRK0Bws6tCerRuuvlVzQhlS_CsPwoel-eQ4SJucxvFBI_RaA3LYi3GtLqUPSKTAW6QqnQvyK-GvGvfDFxlgHgByGB0sf3dBAYLFKwHYspVsA4JqX8LDXNLJzMl5_9OkEsOkOcnTdPQSwImve3XZeM8mZwcHWRXOq6viGM9kGcVBrGZoqg--bUJZshNp2EdQivXJ4APh0E17Ro0gUSvvPTrwwI4m3MS0YHACkf1MbidrTxeyI7fiuADGpLKuC2n83Xbs7xjln0p-IwylsHOKs5cd6Jlrjf1RjyECm9jLMexUpSx5iBxcoIRG5TvyJA3SicZU-_psosM-7ABr7sWWy3F8_e1Q9cIze10_6U7XwqZjIUls007qiE97TFUX7YTlP0zTUwy4xmaSHW94LjhjaJnle49iDdqyRQJCdJbGNHPAhFSHGT6Iyy5vPADzIqPYmASOWxJ_7-IX9LRZQxa2NCRdXou0yAvbSbuq9LL3xFhJQ9S0pvJkY02np0GpMRlWXQpzHlww1i8ptRTsyELKGlrVJdPsdKc2d9ZgHGPvGVxG-e7ESPnA9m1aLP7vVH8NP2qnPSOGQk4SDEw6rxlv5Kjkv56kAXzdKj2PvxuclfWTxG5Peo84gaMNwP_Mi6S4XSuNJt7RhNdTEdQPFIQ0bNcc3O5jnz_xDw76mF3YvRMm_kXxdaOsFP9GSfzaEY56CQ9VGOkziwqrPwWu6fDT7VpkVvi58UDDWJdnk3G-nvcxGHLERU1es-Qy6Pe2qWOdY-nU70YSqgVIj5MMyx6XMJcYMeJDi5831kzr3VgOAggT8K-yYibn4_K2M0OHO0oQW-sUKsljU08Eu60C4MLrSJB40qJGCgwuiFwfXZfKckRmGE-oE6X8uS1ZIgd3S7OSCpYXfNSW7PlRAobBB2ArFFtacVEeH4pjmgcbrjkXHCV_ddCHvo26aBXh_AiBgJkjQ-oqrOS3pgC9J9U-coE-yfNbTl_UcdfFfusG6tvMNV8rl9Pkao6-pG9PTM9E25XZj0rEHOW_Vj9JMqX_kTEP7AKTJr8VZH_fKPbYR-EKlf12hStW--S5P4ng1hDFRcXcYAxmb9panxXRD2mxBBkEUGd3TdG4lxR02K0f9DaDJH2_-u3l4WKQdcGh1ma7m5RYl94o794hvNm2moOazjhIUWseixhZRM0AtS50RHzxaBl3t-vp4QA657xwts-Ng2ERKH2gDR1IIpA9rCvYjRo4Xwif9mTB7hYggs6YqrUZiIHrfNth9Am5e3B5z11hnxgGHPC0Rq1DodR1oV-rmyXM_L8-UpwUrM3Xbg31E_k0p7vIjn635OjUZt9aSe-yXEexGaDpxP5rUHQW3A-X4lZ3a_cL_786Dyzr9Sgma1bM2rpi3j5XfhpQe-DZk4KMP0C_d9rEcSoC46DTNjksrQkb421C5xpRoyJQ2-iSZBplpXRWX3GKwuiGvdtxCdSRcqZ0JHEf3ScOvOVs4gLpLRi5NcTuofbQYAsOATXtDzSPGd07h42Mk65qttYHLwVkt--4WPAIdsgU4SX_P",
"summary": [],
},
{
"id": "msg_042cbd1ba73eb559006ad023a198dc87d0a13500a8fdffc2d3",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to see how it handles zero, negative, "
"and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_042cbd1ba73eb559006ad023a20c5487d09f05bf43be3ac720",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":160}',
"call_id": "call_YeruxIVkbMog0O7xEjBn8luk",
"name": "read_file",
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 159,
"output_tokens_details": {"reasoning_tokens": 94},
"total_tokens": 468,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
**RESPONSES_NATIVE_RESPONSE,
"id": ANY,
"created_at": 1791225884,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"created_at": 1792025503,
"model": "openai/gpt-6-luna",
"object": "response",
"output": [
{
"id": "msg_05a79fb530391552006ac3f01cb60c87d082152e269d863aa4",
"content": [{"annotations": [], "text": "Hello!", "type": "output_text", "logprobs": []}],
"id": "rs_042cbd1ba73eb559006ad023a0481487d0aea8635e4b717121",
"summary": [],
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COiaJAwBRbzsaBwqI_w56uTvcixfz0ImWwpaGwIbCDMXDOodeG_MedwCPLjagtmdVPeq1GAF21VbUncSo2oasMY26z31MMbmZQPKUXWfts9Dajf6g-11D0hZMUupKeeUOT_rcE_GBj6smH3d1PUf-FBMEsY1VQy0gr0am-GUa0dZjw3ukAX0K10gkPCrrqRgp7mlfEi9kAwXhlQ1WEVm7IdHdZnGBbWzKaIRDVkULZQlh9NHIFYCP-2OQbnmqK9vyUxLj3vYXIXGv9B0V3-9TPe8AfDg2tm3AH-tJ-XXJ8D6xDG4E-1avSe4vUrYggFM7_6ztYSrimWqtJ_PfvRQF4cZfcCDf3vxxzLreg3y0jtuZnEOejZYybCa72ZDBbI9OSgNvAZBkU6k9DLT_tQf9uCvN1vtoiGXu0Sk4yr1fw-hAnuEVJK_Tb_FfQBNEk7ILVK7UJaX1rZWTFe2GLhsp6ctz3Kp-c2w2JD5ZHvV22EDQ5DmP8ng9l_5COYQGSsS9ZLiyd06agQ3PvQvBTg5XnDL46DtZ1yfVkB1cuwwlUiWkKD6MQ-VifToT3s4aG0q1Bnl9b_AvtOM0lG-TblA-mdOaRDz3c9s4QfbQjt6Z75oQcNr5QkUujZoV4YiynIBpec5i2gr6Uv0SMJZZbzjY5PLiogj_gvUDxwVbWJkuMXjEPJ3WHWMjceJE4sHwuM95zWV80Ul-MSXknlBj-AZJGQ44_wl0765P--vLyq18jfKDCdorP3Lvq6lYxnXooYMnZ-lFgnWo92OHfX97d6FCyQ46ygzQaRjrhQwUyAioAZiFtugMnHUm7t-EfNb_C7TjLeyXLiJ9iVlGHIt17VJMJIIq_xrQeMCOHAxUKgUE21XkSwsVPdJ0I-4_OP5l3IwkiV0pctG1x-oYX7kCaIYDus-dJUehQNJWNEa_r6QPfn7txUoxMrNCCIyzRUfH3hgwCHudDJ26dj15RPGfiP3wQmX8oZKdy5VkQcNPWb4Gv6b-cjyI7U-8VmwlodUN5FlCj-LJbeL8C8Wxuf1LRzDW-kxNadEhxlQaDSq4nQfTnGARMcmlH8-XqZfXK-3hJD84xHuyjTHq7aBr85gM6vISoYOHf6d-5GIr3-z9cTXvE7tCuxoJ7DdZYWzRK0Bws6tCerRuuvlVzQhlS_CsPwoel-eQ4SJucxvFBI_RaA3LYi3GtLqUPSKTAW6QqnQvyK-GvGvfDFxlgHgByGB0sf3dBAYLFKwHYspVsA4JqX8LDXNLJzMl5_9OkEsOkOcnTdPQSwImve3XZeM8mZwcHWRXOq6viGM9kGcVBrGZoqg--bUJZshNp2EdQivXJ4APh0E17Ro0gUSvvPTrwwI4m3MS0YHACkf1MbidrTxeyI7fiuADGpLKuC2n83Xbs7xjln0p-IwylsHOKs5cd6Jlrjf1RjyECm9jLMexUpSx5iBxcoIRG5TvyJA3SicZU-_psosM-7ABr7sWWy3F8_e1Q9cIze10_6U7XwqZjIUls007qiE97TFUX7YTlP0zTUwy4xmaSHW94LjhjaJnle49iDdqyRQJCdJbGNHPAhFSHGT6Iyy5vPADzIqPYmASOWxJ_7-IX9LRZQxa2NCRdXou0yAvbSbuq9LL3xFhJQ9S0pvJkY02np0GpMRlWXQpzHlww1i8ptRTsyELKGlrVJdPsdKc2d9ZgHGPvGVxG-e7ESPnA9m1aLP7vVH8NP2qnPSOGQk4SDEw6rxlv5Kjkv56kAXzdKj2PvxuclfWTxG5Peo84gaMNwP_Mi6S4XSuNJt7RhNdTEdQPFIQ0bNcc3O5jnz_xDw76mF3YvRMm_kXxdaOsFP9GSfzaEY56CQ9VGOkziwqrPwWu6fDT7VpkVvi58UDDWJdnk3G-nvcxGHLERU1es-Qy6Pe2qWOdY-nU70YSqgVIj5MMyx6XMJcYMeJDi5831kzr3VgOAggT8K-yYibn4_K2M0OHO0oQW-sUKsljU08Eu60C4MLrSJB40qJGCgwuiFwfXZfKckRmGE-oE6X8uS1ZIgd3S7OSCpYXfNSW7PlRAobBB2ArFFtacVEeH4pjmgcbrjkXHCV_ddCHvo26aBXh_AiBgJkjQ-oqrOS3pgC9J9U-coE-yfNbTl_UcdfFfusG6tvMNV8rl9Pkao6-pG9PTM9E25XZj0rEHOW_Vj9JMqX_kTEP7AKTJr8VZH_fKPbYR-EKlf12hStW--S5P4ng1hDFRcXcYAxmb9panxXRD2mxBBkEUGd3TdG4lxR02K0f9DaDJH2_-u3l4WKQdcGh1ma7m5RYl94o794hvNm2moOazjhIUWseixhZRM0AtS50RHzxaBl3t-vp4QA657xwts-Ng2ERKH2gDR1IIpA9rCvYjRo4Xwif9mTB7hYggs6YqrUZiIHrfNth9Am5e3B5z11hnxgGHPC0Rq1DodR1oV-rmyXM_L8-UpwUrM3Xbg31E_k0p7vIjn635OjUZt9aSe-yXEexGaDpxP5rUHQW3A-X4lZ3a_cL_786Dyzr9Sgma1bM2rpi3j5XfhpQe-DZk4KMP0C_d9rEcSoC46DTNjksrQkb421C5xpRoyJQ2-iSZBplpXRWX3GKwuiGvdtxCdSRcqZ0JHEf3ScOvOVs4gLpLRi5NcTuofbQYAsOATXtDzSPGd07h42Mk65qttYHLwVkt--4WPAIdsgU4SX_P",
},
{
"id": "msg_042cbd1ba73eb559006ad023a198dc87d0a13500a8fdffc2d3",
"content": [
{
"annotations": [],
"text": "I’ll read `shop/validation.py` first to see how it handles "
"zero, negative, and non-integer quantities.",
"type": "output_text",
"logprobs": [],
}
],
"role": "assistant",
"status": "completed",
"type": "message",
"phase": "final_answer",
}
"phase": "commentary",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":160}',
"call_id": "call_YeruxIVkbMog0O7xEjBn8luk",
"name": "read_file",
"type": "function_call",
"id": "fc_042cbd1ba73eb559006ad023a20c5487d09f05bf43be3ac720",
"namespace": None,
"status": "completed",
},
],
"parallel_tool_calls": True,
"temperature": 1.0,
"tool_choice": "auto",
"tools": [],
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Search source and test files for a literal term.",
"output_schema": None,
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Read a range of lines from a project file.",
"output_schema": None,
},
],
"top_p": 0.98,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"status": "completed",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
@ -594,17 +623,16 @@ GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": None},
"total_tokens": 25,
"output_tokens": 159,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 94, "text_tokens": None},
"total_tokens": 468,
"cost": None,
},
"user": None,
"store": True,
"access_programs": {"cyber": "daybreak_blue"},
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225884,
"completed_at": 1792025506,
"frequency_penalty": 0.0,
"max_tool_calls": None,
"moderation": None,
@ -627,120 +655,104 @@ GPT_6_LUNA_TEST_CASE: Final = TranslationTestCase(
},
)
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "openai/gpt-6.1-sol",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "openai/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6.1-sol",
"input": "Say hello.",
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "resp_05eee41d540f8798006ac3f01fff8887d0bf3cdc6e114644ae",
"object": "response",
"created_at": 1791225888,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225889,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"moderation": None,
"output": [
{
"id": "msg_05eee41d540f8798006ac3f02102c887d08143f5010642dc50",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
**RESPONSES_NATIVE_RESPONSE,
"id": ANY,
"created_at": 1791225888,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"created_at": 1792025514,
"model": "openai/gpt-6.1-sol",
"object": "response",
"output": [
{
"id": "msg_05eee41d540f8798006ac3f02102c887d08143f5010642dc50",
"content": [{"annotations": [], "text": "Hello!", "type": "output_text", "logprobs": []}],
"id": "rs_0207c20ae125feee006ad023abed4087d09d32a32ad2d3182c",
"summary": [],
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COvx3R_lOOaYJijiIokUKBq9tt_p3mhoPHnm4KR0Pj_t0wf1sP7WEDHfYSzylhHilYoKjU4guIz-TAqBV6HNUpIx5ggp3aukKEW6zks2ERT3a40sCFFdUdKHk6py5trFuwYn6lHLwifwDkd7rI7MKIP7C7pZSHnXh8cmfk0t96p4nBplQ93C4m917Kyx6PqvWSxPP78h5s_RMEdhkWRU20xMhminpIBNArOkPYT4xsmBEuONlndM5-DHG7ZeLk2yMZw8b_hxk2LZ4mC66b5RHfJKVKfw4egn4K8tkr8mQSR4bnjpY56DsIRj4fjSH5GpoDZyolFFBh1BNkGMoVsicye_4gZn0eELuOWxCw7lVVsMpIzTLw8CHJkCo_8vKtNCFSZcKjOPKDDfX1bsFJ7LMonmqijHPV_kZi_YXjVNNJBhJLiGjYrVUFZzjS0OKQx-RnZf5luO3UM2Ff3Ilvx1eQtuWlsvJjPBRwObzk5zlPEdYwoh5OjUREbgGb4H71Q7A9YYjUIms2h5e13Z5s8X0onRVr9SUcSbbMA0FXWn6QGQ5qgiQV56xec7xk62SrxKBXeILgBttBf68YfLAbdINCPL89G5Z1X2toQLlFM7e0jKYUOvSmpWyPLZ3q1040oDf2Q92v6NjOwk4WlLtZF_4xrZ7bEIWmea7zcDEnsvNBRdKaUbeUOm0SfRuIH4gQfbbueSqM3i12eK4TQhTbJ9VivUUovUv7pCKvizdQuunf2MMXWhq79wLYQYXIleQ06E9hbx6QT-Ue5ELQVC3NSLhXiwucOSqd-NZFDQA5wgW2Uaq_-bFYzNOPwtArfaqnHOILmr5mDvWCrlnLs-DUPHU-DtzYH7Eu1VSlcEZLaZX4vC9ui3x2aOpTtmVCILZpw7MkouVxSR4rFE48doVoCamJHhey-TZ7OMl0A5JdacTt6oUE8Z2HEcuVh9yGAZe_Q-YB3p4egLbxO8ICWUkwSSNgrPq3WRbT9sbT-Ko7N7KDAfgyvzzdEYMKDmci6GBrVsAiscc97-gxbhVhlrMyIXmgTluW07o591YjlOkvERXeJobEfby-VUJCu0cHd0nMudzrhCpHIhU3aUMkk9GMlSNDPFnKeV-gylycLhYRb0xo1kXMRom82fKmvUgO5Wh_BhsCdeGaVQ2bm5wyLT4x9VhEe-uOwaYG02XxoSiIFqqSrf0J8auFHIRpUTKzNWMK_GcIaU6o3ON0wOLKaga3wcyrGkG6wtvGkNLCrvmDIXg0bmvFGZrmybQvys_u636NXVS-Y9irqUv2ghu5tyKI_F8uwibi9JkKa5XcotQGbAToTE8qaHfowZOdTyjIKrU3BjL_Hs5M41KXwrNkk_X5ttJxEPW1qCjyusFb9yeGa9wzHMsp_VO0ysdO8L2KSRAY4LHpGI175VxUmnSg66PtCPln0OYxWsX2FWE1A7B_la662tO4VoS3bcslVZreRWFDJ_7X8qKx2fStxd77B7JkG1ZElxlZYlBRN5_Lo_w1yM9SvqHzzewQYEprSA1gltjxAbIzy7xXReaT86PNI8ojSLfXOkXa6Cybu3hIxsIomkZwTtAEx85BoIDn2B8oTp744Lwkwn4ualAfV9TebiqOWCUYp47fX9rimte71X6Hnvf7tWEBZMMwSb0pTqY0boMOS0w3XKKyEVRNyCoGWMgyvhAxk9E5iao5N6i5W3aSel27QwsUaE4YDGKKMKSryH3BqP6X7d0kdUcAx-nd5yudVbePQyc-UC7EbISj5QXY8g6cTOy-IkwpBe68DvfcNGIhuaH6UscqrewXQjKZFJC_BJSl-ICOfMw-FCTumzCDXPqTeLBPHf1g5kd5lBd6HLPUldHtJfD48V12KCRtaoksZ4g2NibuClnmZRpnDMPDUr7r_D8-RfoLEiJeh8SbOSnLvMPVAJIB95F73B-UX5u0e0aWeyfG5QjBq-kB7vVGsRiMyHEVQW810xo2qULVIyVO03s7rAWwTxFY-EHmKkaAIbKU2b-qAasytni7f1Aq61OSIYqSCRdFhpUX6HpnQeCFC_s6_Q9P3CFx120ZaTB_HPeRJO6dhVSJ3nL3PiNi8sCnhRiNIXkJfm9l1TxRS8ok9s1NY8oi4Y98J4Ay52EkX6f9F9FtWHNu4GX_Z50jDNnVTVqQo3L3slpwxECsTAEU-0MsmIa-1RqJ00VqBLKtIDVbbnQ==",
},
{
"id": "msg_0207c20ae125feee006ad023ade23487d093e272f84cb35723",
"content": [
{
"annotations": [],
"text": "I’ll read `shop/validation.py` first to check how it handles "
"zero, negative, and non-integer quantities.",
"type": "output_text",
"logprobs": [],
}
],
"role": "assistant",
"status": "completed",
"type": "message",
"phase": "final_answer",
}
"phase": "commentary",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_S4WtfrQwa6ZLEUZf1BVtA8ON",
"name": "read_file",
"type": "function_call",
"id": "fc_0207c20ae125feee006ad023ae893c87d08068561e36e665ad",
"namespace": None,
"status": "completed",
},
],
"parallel_tool_calls": True,
"temperature": 1.0,
"tool_choice": "auto",
"tools": [],
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Search source and test files for a literal term.",
"output_schema": None,
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Read a range of lines from a project file.",
"output_schema": None,
},
],
"top_p": 0.98,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"status": "completed",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
@ -750,17 +762,16 @@ GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": None},
"total_tokens": 25,
"output_tokens": 118,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 53, "text_tokens": None},
"total_tokens": 427,
"cost": None,
},
"user": None,
"store": True,
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225889,
"completed_at": 1792025519,
"frequency_penalty": 0.0,
"max_tool_calls": None,
"moderation": None,
@ -786,116 +797,144 @@ GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "openai/gpt-6-astra",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "openai/gpt-6-astra"},
expected_provider_endpoint="/responses",
expected_provider_headers={"content-type": "application/json", "authorization": "Bearer synthetic-openai-key"},
expected_provider_request={
"model": "gpt-6-astra",
"input": "Say hello.",
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST, "model": "gpt-6-astra"},
mock_provider_response={
"id": "resp_09642d0a94fde0c6006ad016cb1e4c87d0bf52dd7767aa00c2",
"object": "response",
"created_at": 1792022219,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792022220,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6-astra",
"moderation": None,
"id": "resp_0552d3d37f56f8e8006ad02393df1487d08cd567c9669c6b15",
"created_at": 1792025491,
"completed_at": 1792025495,
"output": [
{
"id": "msg_09642d0a94fde0c6006ad016cbe8bc87d0a9da8d51688a029e",
"id": "rs_0552d3d37f56f8e8006ad02395050087d0954cb16260eceabd",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COXbYvBd4No2o1mKicIiH9j9eRzT8OGbkVyS-7zuUXSU6YKYudPsLUl2WsonyL61adFZSVoTsnF028sqP7sbKTb4PJS8w6eMYLETqeIxL20JUkHB93j798SzS50qm_X4_cSDnH7mh5rcnTNOcdk9BAlrjFTKuK_ARzCswFDmqH2mk4zZiD767r4iXv0QyxKxsEWq-exnoaJOw39XRFQQA_1ATo1J6dP6AmQkpmhQKlIY8NPKwNiR34X2jpN9yskz9PeJs_a1jA4R1m2Xh7ISAS2gmKX3vaBJL4sM8K7sV7KgAuSboorGK9N-L0737_zPJSKvnqI0-2uovkBaYzKwpfpUGs5zFK6zE6_eQJ5JLCCFUfarz_iIyQXMExN5jKoqD7rfP8eMjEAuW2OqWVrL6i-cnBp96G8erGV7y2uD0_iIbEJ6dj2dWE9u81jrpMilRDo4VRDeff7kpWCNYdvn_LRzgKwhDSLHunrZKp-yi3056kNaNDiw8ra9_BwrfEAduOnMvbdLNSCRKJ8WbkL4JNZU3KOfsDCeoqXRWHsJOgUXMjruTgDBKJccKjYF5kzhNRxeb4dAKZqKgEqvCV3QX9wQhXVEnqVct3KHU0QDQLYTs4EwfBTf_ReVWYtIowJrRZrtjW6Qdq9z7v6HY3-wiRkwnDoXJriySRuZviX3y3m4cwCe63gc3DqFvS22UWXk4cIw3XCdsJ5l-uJNWs_-FXUvGv4H2l2iunVPMWBVlorL-SdkGa9ftdpb7gPtZD8gxjryYO7vJO7Sjk1K7A0gqAZHvIwJMdFJxED0yxpPv7hEqw_3DFQDJr3elnjmOwHVBueWYggjN-6oyYJwQOo0o2_M3pyUsOuS8eGIm2TEL8LKXl-QeHbUbISQm_ZZYcUqwnhvTRlslx2Z9dTwgN5u2HwL1CArcAQ_j1pyAJIKoHCgIp7EWgS0zsgaiU1wJRs3aw1wzUQJ5EGKKkle3EIDJnhLA9l_UOQ1xAchhIExf76-eGuAiEQi7v0Gz6SMiLSlUH2xh7fyve3_mLuOYGidn73xCr91y8TjuAxRYiC0oJP6jYgUtVZ0MpWHYFwhdgtuVM-t4c3XNrNLpBqyWZl7ubi4Jy513NTqr4m4ExktN-5HkKkjb5P-35WccTeXVu8o_NN42ysHO3_mPwPe6-Jr3k-7CrwCPiEhR4rStyuitp_PeGBDPCVgW6vj7urfDe11zAZ84shO4yBVtG26c_CqtLq7MWxKQVrTLx1911InHrIDf7BJjFceVzfYiGEplBNT3OzBDJsbjmZYB_ppdiZeyaDSML93ysldny_6KYKx7cGcdHPyU4hVii-nlr0FdH_v9hngcWj4RUO6k9N9W3XHcmxoNLbX6calO2UMD4O94IiS-pLd-zpMdm-Bo5ncucxfMMc3WuCpVLDIpgzrfF_5F_9BYfO1PdYhCGclFfVij6znXR9CuKOXHhcUAG0kmUb_u_lyTpixNv-B4AJLgI1eONjazeSbGHxRwmVOFF11fIY28T3E0kHO940CxteM3eQKCxEUJmpOc6o1iPuy5jr8NOUrW_Bvp-QF1yS4SZHrSqvPUkUjpjzTy41KrbBgHqtoJ_8GwUrTLvUSPsec1nrErNMJE1oZB_6PDP477aer4gbZOil6N73kGVl2-2HeWMgOFh3qiosi71SsJJ9XmGV3bU7zPjLhtKsyoSOTlhmep-7Rs81V8MSvzhBqWBRA-EI2a07Cc24wsIRDgf366sg9tbbsOK3OdgXG3a3vyQNbflzbMnkRyqzzDCDmkWzRz_BBXydi19tKPPFuLpwEZ12oZE7bfy9uPaAfHMPNFPuZhcV3vVNaCgOX-hNht5RqRQTO8esmOemEtN0hpOEnc7cgS8xGNjMQBzvDnvXEU1eJSnwSkdWwUvlDz_OTwgorvzLcr20cHsZTCL9nP4F_-12eWJvn37at6uSJN3aNrDyWoUe9sSee0NiI3ne2seWkqi6wF8_mOxheeQBQcZtLL0agyGXg_YrcnvqjcUrOyjLNBEutMLMVCjVehyhKmYPh-WHzajm9d8hMD91juCft6ufCe52APO1TmNxqUuphA-gFT4Xo1crf7lx6QJVp8em2NmfNMFDVvx-xzi84epgkulTk95GLqH1ZtsXNt-WBinvx737nLtsA06iA9c946KfNTZxARfe9cb1VVjNo0cnFpTkO6GBVwZC83g540pmAdi57yjjFmTk7uf8sVF-ZQ2LheqVDs2VTl1Z74NJIFPH1tapSawFDL6jhFgekEWOAsUlTshMrhsBVfqY1rBw5JFQKOXfz7H33_KlmBBHl0EkRrqy75mHxuVRW9nxisCXg85lvEOAiOIizLu9HMEJvpmzDdkcZSrc3PvaYVRup5y6w2Pwr4Dj37t1y_ls3YPnnoVkyiXdCoP_wHxgFeUbfNAfKisQxbRy2d-VG_5hRul3F0AqGhr86rT0X1eTb752Up2eFoL6CfAtc5h-oIck8JdJbE34ELHCXg36hx1o1I-WnnHemhIJZGDDfyvGx-KQdoz55SkP4FMxsc-4SnQeOa7nn0-KruRaNTiq6NDhjCILlEZ6M6kIN7nDWYgZgsuWJCKqEoHbi4yodzpUpH9jr0kVlaP4R74WibiSmS-fdQIKnbh9tUcrF_rzbc1VIxI34ODmStok02kmDeao33n8CSb4WA_RW-glw3D138j-HGprBOHR1l0DdcOX0PPk1cvMzsz87b-RgnVVGmv-DqWKL1GgoUItHUp22wpOpPWLb6W71xPHmc2e0CuiqSsAd2Qz1lOYXImJk90BRX-09V4FOB7G9MIGZ5EJ-J4lirYTM5DZrNuU9RFGvi0Gv1EJa_9ejTm6kArC1D_SAXJqoLL8q647FxfyGzJPyhgQn3BbXfclnJRmMFeoZA==",
"summary": [],
},
{
"id": "msg_0552d3d37f56f8e8006ad02396d75087d0a2c8b7137ba77a35",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello!"}],
"phase": "final_answer",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles zero, "
"negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
{
"id": "fc_0552d3d37f56f8e8006ad02397444087d09ede3b901e93cb70",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_wVrKXoGNLx7ClNV8cmG0E8pP",
"name": "read_file",
},
],
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
"output_tokens": 177,
"output_tokens_details": {"reasoning_tokens": 112},
"total_tokens": 486,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
**RESPONSES_NATIVE_RESPONSE,
"id": ANY,
"created_at": 1792022219,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"created_at": 1792025491,
"model": "openai/gpt-6-astra",
"object": "response",
"output": [
{
"id": "msg_09642d0a94fde0c6006ad016cbe8bc87d0a9da8d51688a029e",
"content": [{"annotations": [], "text": "Hello!", "type": "output_text", "logprobs": []}],
"id": "rs_0552d3d37f56f8e8006ad02395050087d0954cb16260eceabd",
"summary": [],
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COXbYvBd4No2o1mKicIiH9j9eRzT8OGbkVyS-7zuUXSU6YKYudPsLUl2WsonyL61adFZSVoTsnF028sqP7sbKTb4PJS8w6eMYLETqeIxL20JUkHB93j798SzS50qm_X4_cSDnH7mh5rcnTNOcdk9BAlrjFTKuK_ARzCswFDmqH2mk4zZiD767r4iXv0QyxKxsEWq-exnoaJOw39XRFQQA_1ATo1J6dP6AmQkpmhQKlIY8NPKwNiR34X2jpN9yskz9PeJs_a1jA4R1m2Xh7ISAS2gmKX3vaBJL4sM8K7sV7KgAuSboorGK9N-L0737_zPJSKvnqI0-2uovkBaYzKwpfpUGs5zFK6zE6_eQJ5JLCCFUfarz_iIyQXMExN5jKoqD7rfP8eMjEAuW2OqWVrL6i-cnBp96G8erGV7y2uD0_iIbEJ6dj2dWE9u81jrpMilRDo4VRDeff7kpWCNYdvn_LRzgKwhDSLHunrZKp-yi3056kNaNDiw8ra9_BwrfEAduOnMvbdLNSCRKJ8WbkL4JNZU3KOfsDCeoqXRWHsJOgUXMjruTgDBKJccKjYF5kzhNRxeb4dAKZqKgEqvCV3QX9wQhXVEnqVct3KHU0QDQLYTs4EwfBTf_ReVWYtIowJrRZrtjW6Qdq9z7v6HY3-wiRkwnDoXJriySRuZviX3y3m4cwCe63gc3DqFvS22UWXk4cIw3XCdsJ5l-uJNWs_-FXUvGv4H2l2iunVPMWBVlorL-SdkGa9ftdpb7gPtZD8gxjryYO7vJO7Sjk1K7A0gqAZHvIwJMdFJxED0yxpPv7hEqw_3DFQDJr3elnjmOwHVBueWYggjN-6oyYJwQOo0o2_M3pyUsOuS8eGIm2TEL8LKXl-QeHbUbISQm_ZZYcUqwnhvTRlslx2Z9dTwgN5u2HwL1CArcAQ_j1pyAJIKoHCgIp7EWgS0zsgaiU1wJRs3aw1wzUQJ5EGKKkle3EIDJnhLA9l_UOQ1xAchhIExf76-eGuAiEQi7v0Gz6SMiLSlUH2xh7fyve3_mLuOYGidn73xCr91y8TjuAxRYiC0oJP6jYgUtVZ0MpWHYFwhdgtuVM-t4c3XNrNLpBqyWZl7ubi4Jy513NTqr4m4ExktN-5HkKkjb5P-35WccTeXVu8o_NN42ysHO3_mPwPe6-Jr3k-7CrwCPiEhR4rStyuitp_PeGBDPCVgW6vj7urfDe11zAZ84shO4yBVtG26c_CqtLq7MWxKQVrTLx1911InHrIDf7BJjFceVzfYiGEplBNT3OzBDJsbjmZYB_ppdiZeyaDSML93ysldny_6KYKx7cGcdHPyU4hVii-nlr0FdH_v9hngcWj4RUO6k9N9W3XHcmxoNLbX6calO2UMD4O94IiS-pLd-zpMdm-Bo5ncucxfMMc3WuCpVLDIpgzrfF_5F_9BYfO1PdYhCGclFfVij6znXR9CuKOXHhcUAG0kmUb_u_lyTpixNv-B4AJLgI1eONjazeSbGHxRwmVOFF11fIY28T3E0kHO940CxteM3eQKCxEUJmpOc6o1iPuy5jr8NOUrW_Bvp-QF1yS4SZHrSqvPUkUjpjzTy41KrbBgHqtoJ_8GwUrTLvUSPsec1nrErNMJE1oZB_6PDP477aer4gbZOil6N73kGVl2-2HeWMgOFh3qiosi71SsJJ9XmGV3bU7zPjLhtKsyoSOTlhmep-7Rs81V8MSvzhBqWBRA-EI2a07Cc24wsIRDgf366sg9tbbsOK3OdgXG3a3vyQNbflzbMnkRyqzzDCDmkWzRz_BBXydi19tKPPFuLpwEZ12oZE7bfy9uPaAfHMPNFPuZhcV3vVNaCgOX-hNht5RqRQTO8esmOemEtN0hpOEnc7cgS8xGNjMQBzvDnvXEU1eJSnwSkdWwUvlDz_OTwgorvzLcr20cHsZTCL9nP4F_-12eWJvn37at6uSJN3aNrDyWoUe9sSee0NiI3ne2seWkqi6wF8_mOxheeQBQcZtLL0agyGXg_YrcnvqjcUrOyjLNBEutMLMVCjVehyhKmYPh-WHzajm9d8hMD91juCft6ufCe52APO1TmNxqUuphA-gFT4Xo1crf7lx6QJVp8em2NmfNMFDVvx-xzi84epgkulTk95GLqH1ZtsXNt-WBinvx737nLtsA06iA9c946KfNTZxARfe9cb1VVjNo0cnFpTkO6GBVwZC83g540pmAdi57yjjFmTk7uf8sVF-ZQ2LheqVDs2VTl1Z74NJIFPH1tapSawFDL6jhFgekEWOAsUlTshMrhsBVfqY1rBw5JFQKOXfz7H33_KlmBBHl0EkRrqy75mHxuVRW9nxisCXg85lvEOAiOIizLu9HMEJvpmzDdkcZSrc3PvaYVRup5y6w2Pwr4Dj37t1y_ls3YPnnoVkyiXdCoP_wHxgFeUbfNAfKisQxbRy2d-VG_5hRul3F0AqGhr86rT0X1eTb752Up2eFoL6CfAtc5h-oIck8JdJbE34ELHCXg36hx1o1I-WnnHemhIJZGDDfyvGx-KQdoz55SkP4FMxsc-4SnQeOa7nn0-KruRaNTiq6NDhjCILlEZ6M6kIN7nDWYgZgsuWJCKqEoHbi4yodzpUpH9jr0kVlaP4R74WibiSmS-fdQIKnbh9tUcrF_rzbc1VIxI34ODmStok02kmDeao33n8CSb4WA_RW-glw3D138j-HGprBOHR1l0DdcOX0PPk1cvMzsz87b-RgnVVGmv-DqWKL1GgoUItHUp22wpOpPWLb6W71xPHmc2e0CuiqSsAd2Qz1lOYXImJk90BRX-09V4FOB7G9MIGZ5EJ-J4lirYTM5DZrNuU9RFGvi0Gv1EJa_9ejTm6kArC1D_SAXJqoLL8q647FxfyGzJPyhgQn3BbXfclnJRmMFeoZA==",
},
{
"id": "msg_0552d3d37f56f8e8006ad02396d75087d0a2c8b7137ba77a35",
"content": [
{
"annotations": [],
"text": "I’ll read `shop/validation.py` first to check how it handles "
"zero, negative, and non-integer quantities.",
"type": "output_text",
"logprobs": [],
}
],
"role": "assistant",
"status": "completed",
"type": "message",
"phase": "final_answer",
}
"phase": "commentary",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_wVrKXoGNLx7ClNV8cmG0E8pP",
"name": "read_file",
"type": "function_call",
"id": "fc_0552d3d37f56f8e8006ad02397444087d09ede3b901e93cb70",
"namespace": None,
"status": "completed",
},
],
"parallel_tool_calls": True,
"temperature": 1.0,
"tool_choice": "auto",
"tools": [],
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Search source and test files for a literal term.",
"output_schema": None,
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Read a range of lines from a project file.",
"output_schema": None,
},
],
"top_p": 0.98,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"status": "completed",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
@ -905,17 +944,199 @@ GPT_6_ASTRA_TEST_CASE: Final = TranslationTestCase(
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": None},
"total_tokens": 25,
"output_tokens": 177,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 112, "text_tokens": None},
"total_tokens": 486,
"cost": None,
},
"user": None,
"store": True,
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792022220,
"completed_at": 1792025495,
"frequency_penalty": 0.0,
"max_tool_calls": None,
"moderation": None,
"presence_penalty": 0.0,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"safety_identifier": None,
"service_tier": "default",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"top_logprobs": 0,
},
)
GPT_5_6_TERRA_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={**RESPONSES_REQUEST, "model": "openai/gpt-5.6-terra"},
expected_provider_endpoint="/responses",
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST, "model": "gpt-5.6-terra"},
mock_provider_response={
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-5.6-terra",
"id": "resp_01818bf6930dd01f006ad0238a1f4087d0a5a47aea04e9cd47",
"created_at": 1792025482,
"access_programs": {"cyber": "daybreak_blue"},
"completed_at": 1792025483,
"output": [
{
"id": "rs_01818bf6930dd01f006ad0238abb8c87d0be1dc53bb1de580f",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COL8ir7ZwXbPOmVEOgRTL-aqfraf_1ghm0mkA8sdY9ksq7Sk_hwTMNcBH1zIfS7hFMRLuTRtwXIntfzRjxwisfCfN1fr76Fy_Nx9M0lEUQjPrTL0hgfAjCYoiOptHRO-v5EKTApgnrKVxPxuwDMYQ3GdGAFmN15SNSaWaqpYRbP96XmcvnnMZHLE-BtfbVxtdxSXpVuGLgfCC-11NKJSIG7kZHKi0iSsQBs4tG_Ga3iy1ZDHvrmgduDHR357yfT-Zdufjgm_cQ_KgmSXzcIvzS4Fv3wwTiUzH1SpFfW58Bbbr7gf6fYeLyszpMAMAQePBntjXdNSFV3-DmtKz8HPcZ2UjeAkwQkBWLsJfJoS7XTKP4U2xriGSvVpoCV4vx-GSAGEZGyOt3TyY8jAqOPMViSPGOLWiId0upWOolJUV_nDqRGjKlk8K-k4b_B2k0RiGD6AbUi3_8Ru2i1V0rkA451uOideERDk4LPCVJlgIwtGXOy-jySI17HeYNBjrNtH1mFojojsjt6KIaj3a38r6Xh0fvUfQZAKJJXVqmSIgMebFOI4iiesJxDuVK2qlBTS3mE_FNAfw3AkmKqRUyvEARYNJU_0Yt31EEFAED3xJ-KpSzx-WAfJec-kIT-PiRxvod_PKXObT2u5kJwy9Z8FLj37K1mWYKHHpY9dYwnm0z9o49S4K_f-fIgoGzDtRybAPrglZlDFmf_RSSrVCGo-h_F4Z07wme4zUpnwbGq5I0KmNZVa3d_JlTXpjEPsyDHhK6VHGOvKvOpESgH-7zekvV2_NLheXsAKqpCe3eZ_yI5FkYma5Uiw5lE30GuCT7Dm__eoHllH1AajuIJMvUQ4kF9d1RPXCSk9l9WE34IesApxU--bT1wd1rqedZSsgOW9AkKAq1NC9QEhXG-83_7R0wuUcDeCSdWs4vWqJ0YDjIWEg9LliHm5fypEOW-qftdlBoDWzdqwqMu0XEJvTT1IXtZTNFhekrTgTLpaFJtGw6T8bsaY4csZnb-0jQ9IZyHaRRwPX8JKb3ajvdq_33v_8kLGrVRYjZmd2MwFf2ysaNu_Ob7mNd2UdopntQ98XCbPAkzvvsTPfRYVs4Nf8fg5vAd6QvPy7xoRYxrvQGkppeOVbcPI-EuJSqN_WhTmbXKOpl69MDDyR7xLfuIYLuAbiSO1lS74JuhIgyGkVvO-hUUxL2utZhZdjr_N8AAg0CTKxuMlURkfXRVWrSpm7pm_u-0Xmi4XkrMDb1he5vZmgebI7KiQGkX_jKISBrK0fLwNYWJwY_6cF0QjiIvUt2gucGr7GBUEKeIo3r7oPPEZ3IzBWbiVWHPpjDDJdtliwDAxtzhd-FQwq6N3Rnmj1_4HiUFT3Akj61CYaKXj4IUyamTUdUc3cLcXge2Drv3Kno0ysPf-EHTm0syMRk8URfO9WnFPnjJGH0hIsffSkApE0WJ0Hk8wdzZGvP0QnRZ5lLlEtOBftxW8_-9D457g9kUDiBbnYqOekuQKotQfWfrOKNcEuQeyV1wV1HNrbS4T9Ul6gKFgkDk-wWaciavm2eElMM13OjXJpPsnZpat3pCXxKqrmFLiB4G4NFASz0RzowbnaPoc6OEv2j-c8QzpXX0ftVM0jVsTnl_izTcEobOjU7ipFLBBalJN3aq9K8OYNPKE0fegSQ5ywtERUqk4-X83ggwpDBBZe8tfkPf0KxwRyVmExW4kcepm8zZUzLxeZbipirXd3awzxaD5q-NiN1tvZC7bqb3-cy5du0H_7OScR2QGy7Wt3u2m3zixab8j1foXw6vvBQgV31sTL5RSdZlFtbyI1yu2T9SeOLzfknx14nUCWGyZsLpP3MSCmAOTlHFF6HMa-hnkoWrCtJBuWdq2BuQ9Q==",
"summary": [],
},
{
"id": "msg_01818bf6930dd01f006ad0238b00a487d0aaa092bcd2431bed",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I need `shop/validation.py` next to inspect the validation branches for "
"zero, negative, and non-integer inputs.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_01818bf6930dd01f006ad0238b33dc87d0866bf763c4861a74",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_FI1PXRT2XNjueqLOd8GliYTF",
"name": "read_file",
},
],
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 100,
"output_tokens_details": {"reasoning_tokens": 35},
"total_tokens": 409,
},
},
expected_litellm_response={
**RESPONSES_NATIVE_RESPONSE,
"id": ANY,
"created_at": 1792025482,
"model": "openai/gpt-5.6-terra",
"output": [
{
"id": "rs_01818bf6930dd01f006ad0238abb8c87d0be1dc53bb1de580f",
"summary": [],
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COL8ir7ZwXbPOmVEOgRTL-aqfraf_1ghm0mkA8sdY9ksq7Sk_hwTMNcBH1zIfS7hFMRLuTRtwXIntfzRjxwisfCfN1fr76Fy_Nx9M0lEUQjPrTL0hgfAjCYoiOptHRO-v5EKTApgnrKVxPxuwDMYQ3GdGAFmN15SNSaWaqpYRbP96XmcvnnMZHLE-BtfbVxtdxSXpVuGLgfCC-11NKJSIG7kZHKi0iSsQBs4tG_Ga3iy1ZDHvrmgduDHR357yfT-Zdufjgm_cQ_KgmSXzcIvzS4Fv3wwTiUzH1SpFfW58Bbbr7gf6fYeLyszpMAMAQePBntjXdNSFV3-DmtKz8HPcZ2UjeAkwQkBWLsJfJoS7XTKP4U2xriGSvVpoCV4vx-GSAGEZGyOt3TyY8jAqOPMViSPGOLWiId0upWOolJUV_nDqRGjKlk8K-k4b_B2k0RiGD6AbUi3_8Ru2i1V0rkA451uOideERDk4LPCVJlgIwtGXOy-jySI17HeYNBjrNtH1mFojojsjt6KIaj3a38r6Xh0fvUfQZAKJJXVqmSIgMebFOI4iiesJxDuVK2qlBTS3mE_FNAfw3AkmKqRUyvEARYNJU_0Yt31EEFAED3xJ-KpSzx-WAfJec-kIT-PiRxvod_PKXObT2u5kJwy9Z8FLj37K1mWYKHHpY9dYwnm0z9o49S4K_f-fIgoGzDtRybAPrglZlDFmf_RSSrVCGo-h_F4Z07wme4zUpnwbGq5I0KmNZVa3d_JlTXpjEPsyDHhK6VHGOvKvOpESgH-7zekvV2_NLheXsAKqpCe3eZ_yI5FkYma5Uiw5lE30GuCT7Dm__eoHllH1AajuIJMvUQ4kF9d1RPXCSk9l9WE34IesApxU--bT1wd1rqedZSsgOW9AkKAq1NC9QEhXG-83_7R0wuUcDeCSdWs4vWqJ0YDjIWEg9LliHm5fypEOW-qftdlBoDWzdqwqMu0XEJvTT1IXtZTNFhekrTgTLpaFJtGw6T8bsaY4csZnb-0jQ9IZyHaRRwPX8JKb3ajvdq_33v_8kLGrVRYjZmd2MwFf2ysaNu_Ob7mNd2UdopntQ98XCbPAkzvvsTPfRYVs4Nf8fg5vAd6QvPy7xoRYxrvQGkppeOVbcPI-EuJSqN_WhTmbXKOpl69MDDyR7xLfuIYLuAbiSO1lS74JuhIgyGkVvO-hUUxL2utZhZdjr_N8AAg0CTKxuMlURkfXRVWrSpm7pm_u-0Xmi4XkrMDb1he5vZmgebI7KiQGkX_jKISBrK0fLwNYWJwY_6cF0QjiIvUt2gucGr7GBUEKeIo3r7oPPEZ3IzBWbiVWHPpjDDJdtliwDAxtzhd-FQwq6N3Rnmj1_4HiUFT3Akj61CYaKXj4IUyamTUdUc3cLcXge2Drv3Kno0ysPf-EHTm0syMRk8URfO9WnFPnjJGH0hIsffSkApE0WJ0Hk8wdzZGvP0QnRZ5lLlEtOBftxW8_-9D457g9kUDiBbnYqOekuQKotQfWfrOKNcEuQeyV1wV1HNrbS4T9Ul6gKFgkDk-wWaciavm2eElMM13OjXJpPsnZpat3pCXxKqrmFLiB4G4NFASz0RzowbnaPoc6OEv2j-c8QzpXX0ftVM0jVsTnl_izTcEobOjU7ipFLBBalJN3aq9K8OYNPKE0fegSQ5ywtERUqk4-X83ggwpDBBZe8tfkPf0KxwRyVmExW4kcepm8zZUzLxeZbipirXd3awzxaD5q-NiN1tvZC7bqb3-cy5du0H_7OScR2QGy7Wt3u2m3zixab8j1foXw6vvBQgV31sTL5RSdZlFtbyI1yu2T9SeOLzfknx14nUCWGyZsLpP3MSCmAOTlHFF6HMa-hnkoWrCtJBuWdq2BuQ9Q==",
},
{
"id": "msg_01818bf6930dd01f006ad0238b00a487d0aaa092bcd2431bed",
"content": [
{
"annotations": [],
"text": "I need `shop/validation.py` next to inspect the validation "
"branches for zero, negative, and non-integer inputs.",
"type": "output_text",
"logprobs": [],
}
],
"role": "assistant",
"status": "completed",
"type": "message",
"phase": "commentary",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_FI1PXRT2XNjueqLOd8GliYTF",
"name": "read_file",
"type": "function_call",
"id": "fc_01818bf6930dd01f006ad0238b33dc87d0866bf763c4861a74",
"namespace": None,
"status": "completed",
},
],
"parallel_tool_calls": True,
"temperature": 1.0,
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Search source and test files for a literal term.",
"output_schema": None,
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Read a range of lines from a project file.",
"output_schema": None,
},
],
"top_p": 0.98,
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"truncation": "disabled",
"usage": {
"input_tokens": 309,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": None,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 100,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 35, "text_tokens": None},
"total_tokens": 409,
"cost": None,
},
"store": True,
"access_programs": {"cyber": "daybreak_blue"},
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792025483,
"frequency_penalty": 0.0,
"max_tool_calls": None,
"moderation": None,

176
tests/integration/translation/responses/bases/openai_responses.py
View file

@ -2,6 +2,8 @@ from typing import Final
from unittest.mock import ANY
from integration.translation.case import TranslationTestCase
from integration.translation.responses.templates import RESPONSES_NATIVE_RESPONSE, RESPONSES_REQUEST
from integration.translation.templates.openai import OPENAI_RESPONSES_REQUEST, OPENAI_RESPONSES_RESPONSE
GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
@ -161,116 +163,101 @@ GPT_5_6_SOL_TEST_CASE: Final = TranslationTestCase(
GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
scenario="basic",
litellm_endpoint="/v1/responses",
litellm_request={
"model": "openai/responses/gpt-6.1-sol",
"max_output_tokens": 64,
"instructions": "You are a terse assistant.",
"input": "Say hello.",
"cache": {"no-cache": True},
},
litellm_request={**RESPONSES_REQUEST, "model": "openai/responses/gpt-6.1-sol"},
expected_provider_endpoint="/responses",
expected_provider_headers={"authorization": "Bearer synthetic-openai-key", "content-type": "application/json"},
expected_provider_request={
"model": "gpt-6.1-sol",
"input": "Say hello.",
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
expected_provider_headers={
"content-type": "application/json",
"authorization": "Bearer synthetic-openai-key",
},
expected_provider_request={**OPENAI_RESPONSES_REQUEST, "model": "gpt-6.1-sol"},
mock_provider_response={
"id": "resp_069a914d6d8c0f52006ac3f04d744887d0a3f54d9df9741033",
"object": "response",
"created_at": 1791225933,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225934,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"max_output_tokens": 64,
"max_tool_calls": None,
**OPENAI_RESPONSES_RESPONSE,
"model": "gpt-6.1-sol",
"moderation": None,
"output": [
{
"id": "msg_069a914d6d8c0f52006ac3f04e984087d095c875b7ae7b5542",
"type": "message",
"status": "completed",
"content": [{"type": "output_text", "annotations": [], "logprobs": [], "text": "Hello."}],
"phase": "final_answer",
"role": "assistant",
}
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 6,
"output_tokens_details": {"reasoning_tokens": 0},
"total_tokens": 25,
},
"user": None,
"metadata": {},
},
expected_litellm_response={
**RESPONSES_NATIVE_RESPONSE,
"id": ANY,
"created_at": 1791225933,
"error": None,
"incomplete_details": None,
"instructions": "You are a terse assistant.",
"metadata": {},
"created_at": 1792025514,
"model": "openai/responses/gpt-6.1-sol",
"object": "response",
"output": [
{
"id": "msg_069a914d6d8c0f52006ac3f04e984087d095c875b7ae7b5542",
"content": [{"annotations": [], "text": "Hello.", "type": "output_text", "logprobs": []}],
"id": "rs_0207c20ae125feee006ad023abed4087d09d32a32ad2d3182c",
"summary": [],
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COvx3R_lOOaYJijiIokUKBq9tt_p3mhoPHnm4KR0Pj_t0wf1sP7WEDHfYSzylhHilYoKjU4guIz-TAqBV6HNUpIx5ggp3aukKEW6zks2ERT3a40sCFFdUdKHk6py5trFuwYn6lHLwifwDkd7rI7MKIP7C7pZSHnXh8cmfk0t96p4nBplQ93C4m917Kyx6PqvWSxPP78h5s_RMEdhkWRU20xMhminpIBNArOkPYT4xsmBEuONlndM5-DHG7ZeLk2yMZw8b_hxk2LZ4mC66b5RHfJKVKfw4egn4K8tkr8mQSR4bnjpY56DsIRj4fjSH5GpoDZyolFFBh1BNkGMoVsicye_4gZn0eELuOWxCw7lVVsMpIzTLw8CHJkCo_8vKtNCFSZcKjOPKDDfX1bsFJ7LMonmqijHPV_kZi_YXjVNNJBhJLiGjYrVUFZzjS0OKQx-RnZf5luO3UM2Ff3Ilvx1eQtuWlsvJjPBRwObzk5zlPEdYwoh5OjUREbgGb4H71Q7A9YYjUIms2h5e13Z5s8X0onRVr9SUcSbbMA0FXWn6QGQ5qgiQV56xec7xk62SrxKBXeILgBttBf68YfLAbdINCPL89G5Z1X2toQLlFM7e0jKYUOvSmpWyPLZ3q1040oDf2Q92v6NjOwk4WlLtZF_4xrZ7bEIWmea7zcDEnsvNBRdKaUbeUOm0SfRuIH4gQfbbueSqM3i12eK4TQhTbJ9VivUUovUv7pCKvizdQuunf2MMXWhq79wLYQYXIleQ06E9hbx6QT-Ue5ELQVC3NSLhXiwucOSqd-NZFDQA5wgW2Uaq_-bFYzNOPwtArfaqnHOILmr5mDvWCrlnLs-DUPHU-DtzYH7Eu1VSlcEZLaZX4vC9ui3x2aOpTtmVCILZpw7MkouVxSR4rFE48doVoCamJHhey-TZ7OMl0A5JdacTt6oUE8Z2HEcuVh9yGAZe_Q-YB3p4egLbxO8ICWUkwSSNgrPq3WRbT9sbT-Ko7N7KDAfgyvzzdEYMKDmci6GBrVsAiscc97-gxbhVhlrMyIXmgTluW07o591YjlOkvERXeJobEfby-VUJCu0cHd0nMudzrhCpHIhU3aUMkk9GMlSNDPFnKeV-gylycLhYRb0xo1kXMRom82fKmvUgO5Wh_BhsCdeGaVQ2bm5wyLT4x9VhEe-uOwaYG02XxoSiIFqqSrf0J8auFHIRpUTKzNWMK_GcIaU6o3ON0wOLKaga3wcyrGkG6wtvGkNLCrvmDIXg0bmvFGZrmybQvys_u636NXVS-Y9irqUv2ghu5tyKI_F8uwibi9JkKa5XcotQGbAToTE8qaHfowZOdTyjIKrU3BjL_Hs5M41KXwrNkk_X5ttJxEPW1qCjyusFb9yeGa9wzHMsp_VO0ysdO8L2KSRAY4LHpGI175VxUmnSg66PtCPln0OYxWsX2FWE1A7B_la662tO4VoS3bcslVZreRWFDJ_7X8qKx2fStxd77B7JkG1ZElxlZYlBRN5_Lo_w1yM9SvqHzzewQYEprSA1gltjxAbIzy7xXReaT86PNI8ojSLfXOkXa6Cybu3hIxsIomkZwTtAEx85BoIDn2B8oTp744Lwkwn4ualAfV9TebiqOWCUYp47fX9rimte71X6Hnvf7tWEBZMMwSb0pTqY0boMOS0w3XKKyEVRNyCoGWMgyvhAxk9E5iao5N6i5W3aSel27QwsUaE4YDGKKMKSryH3BqP6X7d0kdUcAx-nd5yudVbePQyc-UC7EbISj5QXY8g6cTOy-IkwpBe68DvfcNGIhuaH6UscqrewXQjKZFJC_BJSl-ICOfMw-FCTumzCDXPqTeLBPHf1g5kd5lBd6HLPUldHtJfD48V12KCRtaoksZ4g2NibuClnmZRpnDMPDUr7r_D8-RfoLEiJeh8SbOSnLvMPVAJIB95F73B-UX5u0e0aWeyfG5QjBq-kB7vVGsRiMyHEVQW810xo2qULVIyVO03s7rAWwTxFY-EHmKkaAIbKU2b-qAasytni7f1Aq61OSIYqSCRdFhpUX6HpnQeCFC_s6_Q9P3CFx120ZaTB_HPeRJO6dhVSJ3nL3PiNi8sCnhRiNIXkJfm9l1TxRS8ok9s1NY8oi4Y98J4Ay52EkX6f9F9FtWHNu4GX_Z50jDNnVTVqQo3L3slpwxECsTAEU-0MsmIa-1RqJ00VqBLKtIDVbbnQ==",
},
{
"id": "msg_0207c20ae125feee006ad023ade23487d093e272f84cb35723",
"content": [
{
"annotations": [],
"text": "I’ll read `shop/validation.py` first to check how it handles "
"zero, negative, and non-integer quantities.",
"type": "output_text",
"logprobs": [],
}
],
"role": "assistant",
"status": "completed",
"type": "message",
"phase": "final_answer",
}
"phase": "commentary",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_S4WtfrQwa6ZLEUZf1BVtA8ON",
"name": "read_file",
"type": "function_call",
"id": "fc_0207c20ae125feee006ad023ae893c87d08068561e36e665ad",
"namespace": None,
"status": "completed",
},
],
"parallel_tool_calls": True,
"temperature": 1.0,
"tool_choice": "auto",
"tools": [],
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Search source and test files for a literal term.",
"output_schema": None,
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
"defer_loading": None,
"description": "Read a range of lines from a project file.",
"output_schema": None,
},
],
"top_p": 0.98,
"max_output_tokens": 64,
"previous_response_id": None,
"reasoning": {"context": "all_turns", "effort": "medium", "mode": "standard", "summary": None},
"status": "completed",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"truncation": "disabled",
"usage": {
"input_tokens": 19,
"input_tokens": 309,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 0,
@ -280,17 +267,16 @@ GPT_6_1_SOL_TEST_CASE: Final = TranslationTestCase(
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 6,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": None},
"total_tokens": 25,
"output_tokens": 118,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 53, "text_tokens": None},
"total_tokens": 427,
"cost": None,
},
"user": None,
"store": True,
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1791225934,
"completed_at": 1792025519,
"frequency_penalty": 0.0,
"max_tool_calls": None,
"moderation": None,

1729
tests/integration/translation/responses/bases/vertex_ai.py
View file

File diff suppressed because it is too large Load diff

2
tests/integration/translation/responses/basic/test_responses_basic_anthropic.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/responses/basic/test_responses_basic_azure.py
View file

@ -6,6 +6,7 @@ from integration.translation.responses.bases.azure import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

2
tests/integration/translation/responses/basic/test_responses_basic_azure_ai.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/responses/basic/test_responses_basic_bedrock_converse.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

2
tests/integration/translation/responses/basic/test_responses_basic_bedrock_invoke.py
View file

@ -19,12 +19,12 @@ from integration.translation.runner import assert_translation
"case",
[
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_HAIKU_5_5_TEST_CASE,
CLAUDE_FABLE_5_1_TEST_CASE,
],
ids=lambda case: case.id,

4
tests/integration/translation/responses/basic/test_responses_basic_bedrock_mantle.py
View file

@ -9,7 +9,9 @@ from integration.translation.responses.bases.bedrock_mantle import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -26,6 +28,8 @@ from integration.translation.runner import assert_translation
GPT_5_6_LUNA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

8
tests/integration/translation/responses/basic/test_responses_basic_gemini.py
View file

@ -6,13 +6,19 @@ from integration.translation.responses.bases.gemini import (
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@pytest.mark.parametrize(
"case",
[GEMINI_3_5_FLASH_TEST_CASE, GEMINI_3_8_FLASH_TEST_CASE, GEMINI_3_1_PRO_PREVIEW_TEST_CASE],
[
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)
def test_responses_basic_gemini(case: TranslationTestCase, gateway: Gateway, provider: SharedProvider) -> None:

2
tests/integration/translation/responses/basic/test_responses_basic_openai.py
View file

@ -6,6 +6,7 @@ from integration.translation.responses.bases.openai import (
GPT_5_4_TEST_CASE,
GPT_5_6_LUNA_TEST_CASE,
GPT_5_6_SOL_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_6_LUNA_TEST_CASE,
@ -22,6 +23,7 @@ from integration.translation.runner import assert_translation
GPT_6_LUNA_TEST_CASE,
GPT_6_1_SOL_TEST_CASE,
GPT_6_ASTRA_TEST_CASE,
GPT_5_6_TERRA_TEST_CASE,
],
ids=lambda case: case.id,
)

11
tests/integration/translation/responses/basic/test_responses_basic_vertex_ai.py
View file

@ -1,19 +1,19 @@
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.responses.bases.vertex_ai import (
CLAUDE_FABLE_5_1_TEST_CASE,
CLAUDE_HAIKU_4_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
CLAUDE_OPUS_4_8_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_OPUS_5_5_TEST_CASE,
CLAUDE_SONNET_4_6_TEST_CASE,
CLAUDE_SONNET_5_5_TEST_CASE,
CLAUDE_SONNET_5_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
)
from integration.translation.runner import assert_translation
@ -31,6 +31,7 @@ from integration.translation.runner import assert_translation
GEMINI_3_5_FLASH_TEST_CASE,
GEMINI_3_8_FLASH_TEST_CASE,
GEMINI_3_1_PRO_PREVIEW_TEST_CASE,
GEMINI_4_ARGON_TEST_CASE,
],
ids=lambda case: case.id,
)

210
tests/integration/translation/responses/prompt_caching/test_responses_prompt_caching_azure_ai.py Normal file
View file

@ -0,0 +1,210 @@
import json
from dataclasses import replace
from typing import Final
from unittest.mock import ANY
import pytest
from integration._support.client import Gateway
from integration._support.provider import SharedProvider
from integration.translation.case import TranslationTestCase
from integration.translation.responses.bases.azure_ai import CLAUDE_FABLE_5_1_TEST_CASE, CLAUDE_HAIKU_5_5_TEST_CASE
from integration.translation.runner import assert_translation
CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0: Final = (
"CAQSigYKEAgSGAI4AUIIdGhpbmtpbmcSDN/XoZMwEppAeWDGmxoM/11DgkoGMFpDINNAIjCfFDmj3tewcz8c9UjL+01psTk6E1rlkSIYmcJH"
"Hx6XtPWsgJDUgKSz2IfPM/CADUMqpwUIur1FUoHdWfUasx1dqp3FuKO96MPj2UY+TH5Youusp0VbxMwTm1f03+bmK6mZkZkmgwk5qRgj56vT"
"p6vd99GSvO3AOVdjBQrAU8m1VT1Npw1cDxDa2a0TZPxJDaAt6j2M0ujvcNHE+d3KEFsC4HTJA6qIlYJrgbuOYH90PhqVCh7TjlEpNQ/OMZ/l"
"vSVBVvxVugSXAn01U1fhPE40RYuQxFzoAa5v0wvHzEjVOFV+piv/Wbm4QkNVxQ3OmEGuFwLAwK18XHQjqkqchQDctMJIiODTCu2s8mtTXGfX"
"fC2Zowpyt+k8csmXbZa0QVaVY8EpmmaDv2aeunUgiPehivaXJHBl1fJA9UB9XxmQhfappJHNHvHS78GcFfRRflv4TrcpVBUFYzoerw3PKN2U"
"vkaAwV0MlnLeOoAPsG0UcJm+ETTfh/ZbR74vPBDiFy3BSmsqQHjbBk4OGUsV15/9+/2ftIkv/2+j+4kP2wZDlMTHAwY7nNwBhdgjpdJ1Ty8K"
"/PnzHGjNocCjLIaupO85mXFPXBLY5vsS2tq4OirPRHFrrsYOKIMY49oBVGAYcRxgFh++Zc2P7ENgrGB1AuPJmTmIN2srt2kjXfdldffHRina"
"GeImXB1+G31+7CHmZvzeicDCUa8V3rl1h2eXufnHT9ZoGBERbzfPzW/f99EWT4UxTrPO6beZR5U7KxS6gb+B48j+6NvOuVsIOQfCt4wUxaHQ"
"W3w8mBXZrmjxcZzRq7sgDu47pvb33GddMF22wY6ZKy9i1bfCqxewdM9CdAJATJ6U+YJDwg1bqon5D+LjernnjPgk8pXpIWewLdt0kHVAFQQz"
"o4xTC0ofJp3L8/xNaxwmLFJ6P43o7VHsxWRKmGq/6XSJQJv9psAnccAhIF4dWxMaMHioSfj1GAE="
)
CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_HAIKU_5_5_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.mock_provider_response,
"id": "msg_011Cg37cq1Hecba5uoPsLUid",
"content": [
{
"type": "thinking",
"thinking": "I'll read shop/validation.py to check its contents, starting with the first 60 lines "
"or so since I don't know the file's full length yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
{
"type": "tool_use",
"id": "toolu_01MnZE6CSPdC7bHqEiAaKehz",
"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": 0,
"cache_read_input_tokens": 873,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 175,
"output_tokens_details": {"thinking_tokens": 75},
"service_tier": "standard",
"inference_geo": "global",
},
},
expected_litellm_response={
**CLAUDE_HAIKU_5_5_TEST_CASE.expected_litellm_response,
"output": [
{
"type": "reasoning",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll read shop/validation.py to check its contents, starting with the first 60 lines "
"or so since I don't know the file's full length yet.\n\n",
"annotations": [],
},
],
"phase": None,
"encrypted_content": json.dumps(
[
{
"type": "thinking",
"thinking": "I'll read shop/validation.py to check its contents, starting with the first 60 lines "
"or so since I don't know the file's full length yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
],
separators=(",", ":"),
),
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 60}',
"call_id": "toolu_01MnZE6CSPdC7bHqEiAaKehz",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01MnZE6CSPdC7bHqEiAaKehz",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 873,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 175,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 75, "text_tokens": 100},
"total_tokens": 1052,
"cost": None,
},
"provider_specific_fields": {
"citations": None,
"thinking_blocks": [
{
"type": "thinking",
"thinking": "I'll read shop/validation.py to check its contents, starting with the first 60 lines "
"or so since I don't know the file's full length yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_CACHE_HIT_THINKING_SIGNATURE_0,
},
],
},
},
)
CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE: Final = replace(
CLAUDE_FABLE_5_1_TEST_CASE,
scenario="prompt_cache_hit",
mock_provider_response={
**CLAUDE_FABLE_5_1_TEST_CASE.mock_provider_response,
"id": "msg_011Cg37VYYdzvnhETMSHzcVV",
"content": [
{"type": "text", "text": "I'll read the validation function in `shop/validation.py`."},
{
"type": "tool_use",
"id": "toolu_01SamuxVRxpP9kLotKTnYMfn",
"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": 0,
"cache_read_input_tokens": 873,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 119,
"output_tokens_details": {"thinking_tokens": 0},
"service_tier": "standard",
"inference_geo": "not_available",
},
},
expected_litellm_response={
**CLAUDE_FABLE_5_1_TEST_CASE.expected_litellm_response,
"output": [
{
"type": "message",
"id": ANY,
"status": "completed",
"role": "assistant",
"content": [
{
"type": "output_text",
"text": "I'll read the validation function in `shop/validation.py`.",
"annotations": [],
},
],
"phase": None,
},
{
"arguments": '{"path": "shop/validation.py", "start_line": 1, "end_line": 40}',
"call_id": "toolu_01SamuxVRxpP9kLotKTnYMfn",
"name": "read_file",
"type": "function_call",
"id": "fc_toolu_01SamuxVRxpP9kLotKTnYMfn",
"namespace": None,
"status": "completed",
},
],
"usage": {
"input_tokens": 877,
"input_tokens_details": {
"audio_tokens": None,
"cached_tokens": 873,
"cached_tokens_details": None,
"image_tokens": None,
"text_tokens": 4,
"video_tokens": None,
"cache_write_tokens": 0,
},
"output_tokens": 119,
"output_tokens_details": {"audio_tokens": None, "reasoning_tokens": 0, "text_tokens": 119},
"total_tokens": 996,
"cost": None,
},
"provider_specific_fields": {"citations": None, "thinking_blocks": None},
},
)
@pytest.mark.parametrize(
"case",
[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE],
ids=[CLAUDE_HAIKU_5_5_CACHE_HIT_TEST_CASE.id, CLAUDE_FABLE_5_1_CACHE_HIT_TEST_CASE.id],
)
def test_responses_prompt_cache_hit_azure_ai(
case: TranslationTestCase, gateway: Gateway, provider: SharedProvider
) -> None:
assert_translation(case, gateway, provider)

5
tests/integration/translation/responses/templates.py
View file

@ -285,3 +285,8 @@ RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
],
},
}
RESPONSES_NATIVE_RESPONSE: Final[Mapping[str, JsonValue]] = {
key: value for key, value in RESPONSES_RESPONSE.items() if key not in {"provider_specific_fields"}
}

354
tests/integration/translation/templates/azure.py Normal file
View file

@ -0,0 +1,354 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
AZURE_RESPONSES_REQUEST: Final[Mapping[str, JsonValue]] = {
"input": [
{
"role": "user",
"content": [
{
"type": "input_text",
"text": ("The checkout rejects quantities of zero. Find the validation code and its tests."),
}
],
},
{
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": (
'{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", "line": 7, '
'"text": "def test_zero_quantity():"}]}'
),
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": (
"Read the validation file first so we can understand how zero and negative "
"quantities are handled."
),
}
],
},
],
"instructions": (
"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."
),
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"tools": [
{
"type": "function",
"name": "search_files",
"description": "Search source and test files for a literal term.",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
{
"type": "function",
"name": "read_file",
"description": "Read a range of lines from a project file.",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
],
}
AZURE_RESPONSES_BRIDGE_REQUEST: Final[Mapping[str, JsonValue]] = {
"input": [
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": ("The checkout rejects quantities of zero. Find the validation code and its tests."),
}
],
},
{
"type": "message",
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": [
{
"type": "input_text",
"text": (
'{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", "line": 7, '
'"text": "def test_zero_quantity():"}]}'
),
}
],
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": (
"Read the validation file first so we can understand how zero and negative "
"quantities are handled."
),
}
],
},
],
"instructions": (
"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 chat_completions client for this project review. "
"Consider zero, negative and non-integer quantities before choosing the next file "
"to inspect."
),
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Search source and test files for a literal term.",
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Read a range of lines from a project file.",
},
],
}
AZURE_RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
"id": "resp_03952e888f4f1827006ad023aa00108190b24e51d376e9a373",
"object": "response",
"created_at": 1792025514,
"status": "completed",
"background": False,
"completed_at": 1792025519,
"content_filters": [
{
"blocked": False,
"source_type": "prompt",
"content_filter_raw": [],
"content_filter_results": {
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
"jailbreak": {"detected": False, "filtered": False},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 575, "check_offset": 0},
},
{
"blocked": False,
"source_type": "completion",
"content_filter_raw": [],
"content_filter_results": {
"protected_material_code": {"detected": False, "filtered": False},
"protected_material_text": {"detected": False, "filtered": False},
"hate": {"filtered": False, "severity": "safe"},
"sexual": {"filtered": False, "severity": "safe"},
"violence": {"filtered": False, "severity": "safe"},
"self_harm": {"filtered": False, "severity": "safe"},
},
"content_filter_offsets": {"start_offset": 0, "end_offset": 578, "check_offset": 0},
},
],
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": (
"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 chat_completions client for this project review. "
"Consider zero, negative and non-integer quantities before choosing the next file "
"to inspect."
),
"max_output_tokens": 1024,
"max_tool_calls": None,
"model": "gpt-6.1-sol",
"moderation": None,
"output": [
{
"id": "rs_03952e888f4f1827006ad023ae0c048190acdee29b5d20c5b3",
"type": "reasoning",
"content": [],
"encrypted_content": (
"gAAAAABq0COvgomuqwo0Z3KFAStLOih2JmYOubPtUjtpD1zCRSCXdDnHGkj8asyVemaCsQr8szo_esDZ"
"PIT2Y9ghPTx1d5moHnS_lyX4nn3Almf4SYZ1pm8maTgEdntGFzcNtPRwW70-CgpeKe5z8zTwxsxyyKDb"
"OYTjt4hjUbAa4pM0K9JR9u5Q_P-LKgfcv3SNCeNSMs5lSV1aBMpuWEGJrlYF020C4wtmru3lH9VjQlOn"
"nW8uD1SCcPm7Sp1_Mm16PJBX4j2grbcIOJZDqj7OcjzRMAb2Gw96QfIg1_efR4BDVHzACkDClzPaiWuI"
"rAmGMA8bJDtQBPijZN3Hahu8eMoMd-XZDVQPx_7XM3F5OWUiuos_kEZNAhIIQHcLrXvyyf7slWvbT4Af"
"c8bvO45t1wOu5E_ALLhWcUCvbfPKBmHrlsRtBEVd_5n0q8jRwR1e5nyjPhMo3YsHvPmwHUJ5Gi1DZycD"
"-FDj6NpwlLcV3eeKaD8c-wNnHuXwfzi_KzIwU1phF_QxJ3ofegtM-3HwCqgaxxVFEhtIh3yezUKeqC7R"
"fSSHpmI-Q59TRf6-R7h6NFJKMG4Hg6C5twvVloHV2YMUHfBrgWr44X9FTzEwxJ89niDRtaB9Xvo2Qzme"
"9LUF-CWuGYTKj5QyRUQFOtclmBL335YTvTDWT8V-eN6KTE33XQNDEPSKuecES6fGHVCuIOeyQkWkvrW8"
"O2OrPJAmoW5g9AFWSWbeLWmDTTav6vbTyu0Ef9cvaRHRTOMq6q8VlEQoTQkJNUM8OKguY7Ad-1VSoIFW"
"D4_LvhuRsDsQiBu1diEq3hRNhXssBUd5wkFLOXw7UITRHONHhk7TDmVh0yjOwBr_e323vmL2e4BouKoX"
"x_0Umeb1jkjFlGgmpW59LmqXd91aXxjioYLxVMOMC7ib7O01_dD-OvWavSxAy9GLnex06mgThS2T5_u4"
"MRmpXIVVqdniqvoxx6YwX5F3TwRoIVc511oXyOG0QkKVLD1k0pI9OdFjiWNVH6XuhWPpVnAhqR6KYejn"
"hQQwuHA4KV4Nd6wOMFbhPjKPCuRcaN1vbgTbRJlwD8O2OV537hjDq6TQaezFJMk3HPK5bB_-J3kmUCul"
"YOXw0jgw-Ze8EmKLDZoCz3jq4NjNA9s0sLGd_Xg0kR6GeOmpLMWtT024yQ7gowGendkcHjIw3S-fIfiI"
"zJtZ-Hk9_iMBk8FE5Syb-j0kmzGF2gFj7ywTTdGoMsM3aTOvusVL14D1N_IfMryUdeoNJ41G8SvqGjtH"
"gyqCER9grGItYgKueDjt6IC5I086__HogkmrpzLZxSIpFCXX6rArVDsIYdS9XFgLW1oBKsVUs5DLnIYe"
"Ncv_cC-oTvEDBaYdhDPYbn_5N6q0q7dtbvohO-XJxOfLh0jC3TelEn7m5EXMPpAygQP2sPtI4_SmhA1C"
"Tji-B-6J60kBUiKmp65ZVxx8BDMI9dv3PLxsw4R0zh6fP_Fsok0UKJOQlfC6k47yhDuTcdN_vq7sAc3q"
"6P9b7Ud7Bz3JtY8Lg516vLK2vti4iwu7dcHlNiIoNZTGMANKYccO-XSRuJbX09bypgJB9sSR56_-Cb1i"
"b1C5RtkTv3ueRvq58Hw1RIINmiTTJn2MiYi_P-yXAirR39YTxcyRNUk4UDgK1lK73lrnpiBELJe-CPQg"
"wgLlalzjk8j0CnIMUA=="
),
"summary": [],
},
{
"id": "msg_03952e888f4f1827006ad023ae6e608190afabb95cbcebf3c9",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": (
"I’ll read `shop/validation.py` first to check how it handles zero, negative, and "
"non-integer quantities.\n"
),
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_03952e888f4f1827006ad023aeb68881909fd9d88d37ef120a",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_mWfqifVeCXVWLiiNM1Ac2MjL",
"name": "read_file",
},
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": False,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": False,
},
],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 154,
"output_tokens_details": {"reasoning_tokens": 89},
"total_tokens": 466,
},
"user": None,
"metadata": {},
}

159
tests/integration/translation/templates/bedrock_converse.py Normal file
View file

@ -0,0 +1,159 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQS9AUKEggSEAEYAjgBQgh0aGlua2luZxIMQHB9X3K/kC6GNasiGgywUP8bZriTtiro/2MiMAi/+5c3bmdPrprOsDzKxvo/J9NAn2cBfonQ"
"awxkQnqB3W5W5gKuBzPky9UZ+zTK6iqPBQhsFXO/q0Ky2I4cK8AZg1lsxNO6YTzWgD7fyCaEhn4HqY4hm4vK2V88DlytrsSGUTIQ/iEUSGVd"
"83vAHJy9AnRW9pPrgF/nW1D3pSD/Z3xeuMmxjMLuhGTF1JclSqe1onncl6i1Hu3a4fdTxXCKwAkgXjSPGMcYEANs9ziU1Ep+g/lPs4yIddit"
"mXaDnDzcCAq/6bFBnIe5IuN5nPeM4MqnXIXAhpDXa2R7HxUAg0v2dbzEzssSPuvn/PPF5VmusAXMQxM8zrLHdm5zUW6pss9p/OzxvgF6OlSj"
"8iF8YlOQXOa8avjTVUXiOLG4L67euf2YehPWDuWhrv1RsFJ3eDFvrlSESRnXeXIp7U4qqav5G7dJwxnFszrQzN/Oc/VgFvwErqp39goRlZiT"
"T2WpvuCOO8i8XsEg3NZUpTaypy2YfgMWJwVm/V06erqg3VKsVvIhXhp/XVkzu9AIHuPd+pJ1TgmybB4OGMuqYaj1Cs4OuNsH66YKEXSGexjB"
"wbjgPFHBXLbG/Ek/ATXpUShR8Uxu6japXknWqT19rusAv/7KRiqDZR2WiYf/nFLF7zMM6Zjoi/SV1AVC4RS5alTEsom8Pp8w8ZoptXCalOXI"
"fCh6kfqOZHxF9FCQ1i5hcPkvG2d1yzMkcV+i3worR+gXt/xZGT/Rdr28xceL9rOCEQawYT9fugI+BLHGEe/+X+jSAoFZxgcJ8Lqjz2kyoLqk"
"ZTRgYzIEBZgqa+dFrCVuXO9m1B3MSv0+f8gBeZVZKt5ItBWzIfOs1q8KyfqNNRYg3yQAmiWJsF0SkbJZl/MDQXzSXqkzriwclWGnRv0hBC7W"
"u75PM3a8YuBlc7Ww8Vdrw0AaG1s5FX7nhkHiV6DRII0YAQ=="
)
BEDROCK_CONVERSE_REQUEST: Final[Mapping[str, JsonValue]] = {
"messages": [
{
"role": "user",
"content": [{"text": "The checkout rejects quantities of zero. Find the validation code and its tests."}],
},
{
"role": "assistant",
"content": [
{"text": "I will locate the quantity validation and its tests."},
{
"toolUse": {
"input": {"query": "quantity", "paths": ["shop/", "tests/"]},
"name": "search_files",
"toolUseId": "toolu_synthetic_search_01",
},
},
],
},
{
"role": "user",
"content": [
{
"toolResult": {
"content": [
{
"text": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": '
'"def validate_quantity(quantity):"}, {"path": '
'"tests/test_validation.py", "line": 7, "text": "def '
'test_zero_quantity():"}]}',
},
],
"toolUseId": "toolu_synthetic_search_01",
},
},
{
"text": "Read the validation file first so we can understand how zero and negative quantities "
"are handled.",
},
{"cachePoint": {"type": "default", "ttl": "5m"}},
],
},
],
"inferenceConfig": {"maxTokens": 1024},
"additionalModelRequestFields": {
"thinking": {"type": "adaptive", "display": "summarized"},
"output_config": {"effort": "high"},
},
"additionalModelResponseFieldPaths": ["/usage/output_tokens_details"],
"system": [
{
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect.",
},
],
"toolConfig": {
"tools": [
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
},
},
"name": "search_files",
"description": "Search source and test files for a literal term.",
},
},
{
"toolSpec": {
"inputSchema": {
"json": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
},
},
"name": "read_file",
"description": "Read a range of lines from a project file.",
},
},
],
},
}
BEDROCK_CONVERSE_RESPONSE: Final[Mapping[str, JsonValue]] = {
"additionalModelResponseFields": {"usage": {"output_tokens_details": {"thinking_tokens": 96}}},
"metrics": {"latencyMs": 3022},
"output": {
"message": {
"content": [
{
"reasoningContent": {
"reasoningText": {
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
"text": "I need to figure out which file to read for validation, then use a read-only "
"tool to look at it—I'll check the first 60 lines or so since I don't know "
"its exact length.\n\n",
},
},
},
{
"text": "I'll read `shop/validation.py` next, starting with the `validate_quantity` function "
"found at line 18.",
},
{
"toolUse": {
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
"name": "read_file",
"toolUseId": "tooluse_qWzJMc6h58NlspiEa01FUC",
"type": "tool_use",
},
},
],
"role": "assistant",
},
},
"stopReason": "tool_use",
"usage": {
"cacheDetails": [{"inputTokens": 856, "ttl": "5m"}],
"cacheReadInputTokenCount": 0,
"cacheReadInputTokens": 0,
"cacheWriteInputTokenCount": 856,
"cacheWriteInputTokens": 856,
"inputTokens": 4,
"outputTokens": 230,
"serverToolUsage": {},
"totalTokens": 1090,
},
}

144
tests/integration/translation/templates/bedrock_invoke.py Normal file
View file

@ -0,0 +1,144 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0: Final = (
"CAQShwcKEggSEAEYAjgBQgh0aGlua2luZxIMtEbP1UTgPIIXYE/jGgzmQCWS7ivK08RdGfwiMLQLZcccUrbxiBMQBmSloh21MAnvornAsyEF"
"qdKjYweOzk9gu7R5cyTNk5NT0z00kSqiBmieg1Sbhy23Upls1PPy2fC8794rus5qb4NKBmFvnYPn3255F5xzBh4tucc9xoUcjHkA9Q9SwGEK"
"VlBdgSfoIK5gvUMVz/VRPsvoBPfUJbbvEDQ9b2qhauTLOn/zxOwYfUAfKPPQQ/pQGf1Z5+n3GjbvzqcQll8uHra3BZyaJMmWZ2nzUbJTFP6F"
"Jkw95ArvOiyKeBZ65EVLskXAe2ZICsTd1pLESIfxuyeV4Yogt7drR5ytyOn/u1cM67Q0EWuZUQoU3OerB+K3PNxUp74ckJeK4M07IqAf3Bro"
"O7+oN5zWv7w/JfbtX9kDTSLRIu3eT/fmyGPrpgho2YIqcD4CO5pckkcLqhdi58RQ+Jnto9xZecoEdloi7sY6s4NYsa07X1qnOEQW0loS8Vs5"
"kcTpR+kl+KQJpk8pTf9GEqmtQGRo83KE4HKsHnd9pkdpex7thJIpxtgqR8OFY1Urjbj5YKY5mIO3FrsR2PtYK2nxgEzo3t0Ut74xj8ssIR7b"
"PoYxD66+mAZ10WODU4+o7uCm12FbRK/fPeV1uIfLHC5yUC4hw5Wi7mVdaEXjCPc0cwVnUFKpTKzVfH1fL3zNUermhufeqnCoLGhEOzQ5KJdX"
"Be9jAmOPd/Si5O5aZURC+dp8NXrVR1yDKhsWFg3CRi8DZ4wvgKNkmW+XYVB6G99gjHk7GmzcMSy5sxCWFs3qdKRbFyJ97WleW5ljuCz2YyFW"
"uDu3QYqWPOu0UlgzQcf+TDsLML4T8O6ddMqrErhmk52N1HW8rDHlEedB6+LlN2C+fcSEdLzFAdmmmQ8Y/HBmAzSzvsS9CYldAe9MmMKAr+J2"
"XBQBjJfbTvCYptNDuvqIChTBan1FII1w6Xq+NqaPR4f+16LM3HYKtIvwULH05YBRuZxF7B5J3NIKQBb39Rkhv2D/PTaMmdNIrDJqd57AKxSd"
"EKuGc9BFdyzwFz+X/3k/kO0Z6VZeLLIN5vdiz/9Aj1eYa3CnjVLiGH6zVUnhkx6eetUuHRZnrBx0ZXzRhZWf88bAQHgH9LwoTo61cf2Zqv4a"
"H5GvCCyi2gyhwWmBQ/7DeTUYAQ=="
)
BEDROCK_INVOKE_REQUEST: Final[Mapping[str, JsonValue]] = {
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
},
],
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "I will locate the quantity validation and its tests."},
{
"type": "tool_use",
"id": "toolu_synthetic_search_01",
"name": "search_files",
"input": {"query": "quantity", "paths": ["shop/", "tests/"]},
},
],
},
{
"role": "user",
"content": [
{
"type": "tool_result",
"tool_use_id": "toolu_synthetic_search_01",
"content": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", "line": 7, '
'"text": "def test_zero_quantity():"}]}',
},
{
"type": "text",
"text": "Read the validation file first so we can understand how zero and negative quantities "
"are handled.",
"cache_control": {"type": "ephemeral", "ttl": "5m"},
},
],
},
],
"max_tokens": 1024,
"tools": [
{
"name": "search_files",
"input_schema": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"type": "custom",
"description": "Search source and test files for a literal term.",
},
{
"name": "read_file",
"input_schema": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"type": "custom",
"description": "Read a range of lines from a project file.",
},
],
"thinking": {"type": "adaptive", "display": "summarized"},
"output_config": {"effort": "high"},
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect.",
},
],
"anthropic_version": "bedrock-2023-05-31",
}
BEDROCK_INVOKE_RESPONSE: Final[Mapping[str, JsonValue]] = {
"model": "claude-haiku-5-5",
"id": "msg_bdrk_pobluozqaykrnd3exk5nnrtwrxipiquzg7hvvispjxn6qi4sz5vq",
"type": "message",
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": "I should look at shop/validation.py, focusing on how it handles zero, negative, and "
"non-integer inputs before deciding what to read next. I'll check the first 60 lines or so "
"since I don't know the file's full length yet.\n\n",
"signature": CLAUDE_HAIKU_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "I'll read `shop/validation.py` around the `validate_quantity` definition at line 18. I'm "
"checking how it treats zero, negative, and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_01Hfy4YfUU7hZUxEmpp4oDYV",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
],
"container": None,
"stop_reason": "tool_use",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 295,
"output_tokens_details": {"thinking_tokens": 143},
"service_tier": "standard",
},
}

335
tests/integration/translation/templates/bedrock_mantle.py Normal file
View file

@ -0,0 +1,335 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0: Final = (
"CAQSkAQKEggSEAEYAjgBQgh0aGlua2luZxIMAi8mku8BopClY7wPGgwlWfmp5AbEIPA1xuAiMIbNUAxSlU56KwYLJ1P+/QAOb0fy2iNuUIvN"
"uu0NeTLet5Bf5yDruo7S0IwCi/HD+SqrA68zipbpxKWBeB+abRfM6xMZbYGcvRzePKzfZ6CYii1l08tO3fgsqbBitmj/6jvyogZ/a4Zf138x"
"ReoliJfLLudbpQB3rol3BtDrm8YrYqWW/vBn/Ioe3v3wHYRA3r4TllD0tyJwB4eNXENsq8vmxHrlTjQohAVsIyEjNy6xqs/YPW2zrCV85ZTE"
"UQQ2MDoCmAJa/wPgR/i68XIQ3kSWP3SllvhwlGcEUFa+lNUofPIUL7YBPyweBgrBSoS6hGr7LT3XZWNddtvjx6n5n1DF42FpapUdsK2iwerN"
"Gg/c6AHxr44urpLJ3XWjc/jgGs3KrLtfSFJ4pV3oRlZDn9upJKjTl97f6aIJqzxqJXlNIJ8VAWEV6kH/TVkRq5AdlwGQROLEA2taVBP01wAO"
"nxfwTfxj3UG49lVrwgi/+m3kEXOGsP7V876Ieb7wH/2zu+XxCz+k99d3bcc3MZr79VLxXif5QWbt70cm+2NjtCMPDYf0hm5o0KAtz9S9ZBUj"
"528KMDGsVR/rqwWcEV3mq/hWKjZmmeMSbhinrNVng5uM9cBe9YwaulbpS3s2lvQYAQ=="
)
BEDROCK_MANTLE_ANTHROPIC_MESSAGES_REQUEST: Final[Mapping[str, JsonValue]] = {
"messages": [
{
"role": "user",
"content": [
{
"type": "text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
},
],
},
{
"role": "assistant",
"content": [
{"type": "text", "text": "I will locate the quantity validation and its tests."},
{
"type": "tool_use",
"id": "toolu_synthetic_search_01",
"name": "search_files",
"input": {"query": "quantity", "paths": ["shop/", "tests/"]},
},
],
},
{
"role": "user",
"content": [
{
"type": "tool_result",
"tool_use_id": "toolu_synthetic_search_01",
"content": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", "line": 7, '
'"text": "def test_zero_quantity():"}]}',
},
{
"type": "text",
"text": "Read the validation file first so we can understand how zero and negative quantities "
"are handled.",
"cache_control": {"type": "ephemeral", "ttl": "5m"},
},
],
},
],
"max_tokens": 1024,
"tools": [
{
"name": "search_files",
"input_schema": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"type": "custom",
"description": "Search source and test files for a literal term.",
},
{
"name": "read_file",
"input_schema": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"type": "custom",
"description": "Read a range of lines from a project file.",
},
],
"thinking": {"type": "adaptive", "display": "summarized"},
"output_config": {"effort": "high"},
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer "
"quantities before choosing the next file to inspect.",
},
],
"anthropic_version": "bedrock-2023-05-31",
"model": "anthropic.claude-opus-5-5",
}
BEDROCK_MANTLE_ANTHROPIC_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
"model": "claude-opus-5-5",
"id": "msg_bdrk_cs3sdsy2tpe6vxiv7ipubz5hhgknryzkga3mhragbuieyoskse2q",
"type": "message",
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": "I should check the validation file first, starting around line 18.\n\n",
"signature": CLAUDE_OPUS_5_5_THINKING_SIGNATURE_0,
},
{
"type": "text",
"text": "Next I'll read `shop/validation.py` around `validate_quantity` (line 18) to see how it handles "
"zero, negative and non-integer values.",
},
{
"type": "tool_use",
"id": "toolu_bdrk_018J8SJwAgjhRkkmtm3xdJx2",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 50},
},
],
"container": None,
"stop_reason": "tool_use",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 0,
"cache_read_input_tokens": 876,
"cache_creation": {"ephemeral_5m_input_tokens": 0, "ephemeral_1h_input_tokens": 0},
"output_tokens": 166,
"output_tokens_details": {"thinking_tokens": 19},
"service_tier": "standard",
},
}
BEDROCK_MANTLE_OPENAI_RESPONSES_REQUEST: Final[Mapping[str, JsonValue]] = {
"model": "openai.gpt-6.1-sol",
"input": [
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
},
],
},
{
"type": "message",
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": [
{
"type": "input_text",
"text": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", "line": 7, '
'"text": "def test_zero_quantity():"}]}',
},
],
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read the validation file first so we can understand how zero and negative quantities "
"are handled.",
},
],
},
],
"instructions": "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 chat_completions "
"client for this project review. Consider zero, negative and non-integer quantities before choosing the "
"next file to inspect.",
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Search source and test files for a literal term.",
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Read a range of lines from a project file.",
},
],
}
BEDROCK_MANTLE_OPENAI_RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792027271,
"created_at": 1792027269,
"error": None,
"frequency_penalty": 0.0,
"id": "resp_izakuft4jrxwmodefqee2jjt6gkmayywwuuc242pduoydywb3v4a",
"incomplete_details": None,
"instructions": "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 chat_completions "
"client for this project review. Consider zero, negative and non-integer quantities before choosing the "
"next file to inspect.",
"max_output_tokens": 1024,
"max_tool_calls": None,
"metadata": {},
"model": "openai.gpt-6.1-sol",
"object": "response",
"output": [
{
"content": [],
"encrypted_content": "rsn_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",
"id": "rs_7a90cfc98ff653aeb165c2b845bc1e4b",
"summary": [],
"type": "reasoning",
},
{
"content": [
{
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to see how it handles zero, negative, and "
"non-integer quantities before inspecting the tests.",
"type": "output_text",
},
],
"id": "msg_4aeb32a9101256fe89e762125d4ffeee",
"phase": "commentary",
"role": "assistant",
"status": "completed",
"type": "message",
},
{
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_399ba0e7ac865a798b46a6cabe6b6bde",
"id": "fc_db8b798957b65c379754d08da376417f",
"name": "read_file",
"status": "completed",
"type": "function_call",
},
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "in_memory",
"reasoning": {"summary": None, "effort": "high", "context": "all_turns"},
"safety_identifier": None,
"service_tier": "default",
"status": "completed",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tools": [
{
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
},
{
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
"type": "function",
},
],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 312,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 108,
"output_tokens_details": {"reasoning_tokens": 39},
"total_tokens": 420,
},
"user": None,
"moderation": None,
}

257
tests/integration/translation/templates/gemini.py Normal file
View file

@ -0,0 +1,257 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
GEMINI_GENERATE_CONTENT_REQUEST: Final[Mapping[str, JsonValue]] = {
"contents": [
{
"role": "user",
"parts": [
{
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
},
],
},
{
"role": "model",
"parts": [
{
"text": "I will locate the quantity validation and its tests.",
},
{
"function_call": {
"name": "search_files",
"args": {
"query": "quantity",
"paths": [
"shop/",
"tests/",
],
},
"id": "toolu_synthetic_search_01",
},
"thoughtSignature": "c2tpcF90aG91Z2h0X3NpZ25hdHVyZV92YWxpZGF0b3I=",
},
],
},
{
"role": "user",
"parts": [
{
"function_response": {
"name": "search_files",
"response": {
"matches": [
{
"path": "shop/validation.py",
"line": 18,
"text": "def validate_quantity(quantity):",
},
{
"path": "tests/test_validation.py",
"line": 7,
"text": "def test_zero_quantity():",
},
],
},
"id": "toolu_synthetic_search_01",
},
},
],
},
{
"role": "user",
"parts": [
{
"text": (
"Read the validation file first so we can understand how zero and negative quantities are handled"
"."
),
},
],
},
],
"system_instruction": {
"parts": [
{
"text": (
"You help maintain a synthetic Python project. Read the relevant files before suggesting a fix. E"
"xplain which file you need next, then call a read-only tool. Never change files. Use the chat_co"
"mpletions client for this project review. Consider zero, negative and non-integer quantities bef"
"ore choosing the next file to inspect."
),
},
],
},
"tools": [
{
"function_declarations": [
{
"name": "search_files",
"description": "Search source and test files for a literal term.",
"parameters": {
"type": "object",
"properties": {
"query": {
"type": "string",
},
"paths": {
"type": "array",
"items": {
"type": "string",
},
},
},
"required": [
"query",
"paths",
],
},
},
{
"name": "read_file",
"description": "Read a range of lines from a project file.",
"parameters": {
"type": "object",
"properties": {
"path": {
"type": "string",
},
"start_line": {
"type": "integer",
"minimum": 1,
},
"end_line": {
"type": "integer",
"minimum": 1,
},
},
"required": [
"path",
"start_line",
"end_line",
],
},
},
],
},
],
"generationConfig": {
"max_output_tokens": 1024,
"thinkingConfig": {
"thinkingLevel": "high",
"includeThoughts": True,
},
},
}
GEMINI_3_8_FLASH_THOUGHT: Final = (
"**My Thought Process: Initializing Validation File Inspection**\n\n"
"Okay, let's break this down. The user's goal is to help maintain a Python project, but important"
"ly, to *read* relevant files and *never* change them. The instructions explicitly direct me to u"
"nderstand how zero and negative quantities are handled, and to *consider* these before choosing "
"the *next* file. The user's explicit request to read the validation file first immediately trigg"
"ers the appropriate response.\n\n"
"Based on the instructions and the user's initial prompt, I need to focus on `shop/validation.py`"
" which I know is at line 18 (`def validate_quantity(quantity):`). I need to check how the code h"
"andles zero, negative, and potentially non-integer quantities. \n\n"
"Before proceeding, it's essential to confirm the instructions: read the file, explain the choice"
", and use a read-only tool. I need to be precise. To avoid any ambiguity, I'll start by reading "
"lines 1 to 50 of `shop/validation.py`. This range should allow me to see the context of the `val"
"idate_quantity` function.\n\nNow, for the critical step: I'm going to follow the instructions and "
"explain my reasoning, then I'll use the read-only tool.\n\nTherefore, my next step is:\n\n"
"We want to see how `validate_quantity` verifies quantity inputs, specifically whether it properl"
"y handles zero, negative values, and non-integer types (e.g. floats, strings, or None), before w"
"e look at the test suite. Therefore, the next file we need to inspect is `shop/validation.py`.\n\n"
"\n"
)
GEMINI_3_8_FLASH_THOUGHT_SIGNATURE: Final = (
"EoATCv0SAWkUfRPAfPpnzi1FIwmV+NEV1p2Nir3bkvyVz8J7BJ5g940gYIMwrVGMcoDSKUSW4RlG2+bV5u02G0uwFXQsxVCE"
"04rAU5hV/Viy6qJE2RBz6dj2/xUR2klCfwzqf10KF3Zm65efbvNAYTFQuJmLvuPNgavTk57xuBSyRE1iafGbfjkpKyE2ASVM"
"uq/70iQ1tx6XusTyMLAFkFkIg4KYsEgZcrUFZaAsI29vgDIRCKw7ZBA29INSlhZTvEn+ZeQd4Oi3jI983paxvLHewUv1Sb4j"
"PcrZ7ULXhZT8/CNGvTTax4AvqbaAOdPcKJH+kI+oG+yvMhF/nQjrR+qnUB3dhL0mjVcg9QQZh2Z0qZpZH2tsSCl2pqBBdcaU"
"V6C/5nLPktRkMA2PCE63AsMUY+yfbhnY5pGr9s+C62QNl7Tofuc7FrH0UDNZqxb0PNrShTgv0/MpaKbwS6EsYb7rl3NHZuD2"
"Tspu1n9HjhD/imlMTbJXldIko5khSt42o0z8mntYiWAj76TbtKTiELNC6Vbz3YX9jQu/6QXiHgIwZ32pfAUhOH6XYr5mHFRo"
"rsv3lFq7WyZe23j7bS03hn+hzqjOgeGEHUCmOHisL+pRajXXKA/BqrPTbRR92l603tIvFFUjIdmXN5Yn/086YDpcvOYzO9UC"
"zQcHg5vfyy77fpWjTKVxd4iE9PCi/RqqPsfplW0YgiE7635HnyOBUF8v8KNCNeU4BJRjRc1lnZKFHN3mv3t49UWgdPqxIQMp"
"CHlyKL96+88Ot6Sy+r7sRVrttrE4yTWn72IeOBd6N1E+vX427hCcw3MQBaxTaSJcs7h/mJV63jvGAVEQxWOxWRE2lAEJed0l"
"ttQS/rv9V6VU5CDVKR3zDcDE2uLgct7KTDHB1v/jjh5sZqDBZURLEywUP4HAlI14FeFK9ma6ZG6sjp+KVU6EkNQingdAH+zh"
"Nsb2+MkZ3Beccqlf9pEnmiMtT3xyQT8yQfXLL5o7GLIkFLemfe98lvThNiEhZ9udldYZgWi0g1sQcjrxcNu6dvH+O8v9RWvD"
"A87rM2rikA/oJc0IBRDvFNehMtnu3yR5969Q13ORotFWvYLOwAdSYP5H8TIvpEleHQsYGnPUclZqTI51+dbydYBXnqTDtRer"
"7zq4Ul/cuF3LYLRcr4zfkNrOgZK+U3Rfk60WPEi5AyWQ2IO74B7FQqIHKw5mXjlV0Krfn4e2bYJXBRS82xgfK6pYtHWgIbY/"
"18quckh1T4bF9JfRi0JTPYp2sU2FossIjbT98rpd76OBHBnWl2BUcd+0BiZ91DNErQVVaAmsfGA4li2upU0E0QnN87tctY43"
"DLL9YH133uCTV8YQh8hfbh4j30GcongmSd5L30stAv+AGQRFqK8fi/vJdgTXZXWWYSjTlhetY5ar3FnaulztywTqjLbBUxK1"
"jicit6aonk217FYXDzSRy3BcGx5TN879JkvQ22zpsxy41Brxw8MhYT92UduPTXcQwNkh09+Rn7+lP8/u1ppEtE/vttmHGuxe"
"QEyOk8isAtoErC3xdA2fYh16dA2on1HPXlX81/dF4Og1PQdZp3GIS3ftuKMlinGuRyFBaHV5IZYji16r+afCWnz3dh9eKnrs"
"OrdjxyLk1wcsQRzig6nurhBkoOi1p73QyzVyx2hzMkKoNAkV2YM/33kPrwM8mXQYEpQVL0r6P3wgXFP4ep5dYQ+HGZCan5i4"
"QWum9+1FOFAIFUbxp5ePAybhzOhLkOn+2EPwKumY7hR56sVsAyJFp5cy7JlaxPfI/n1Ez9xyOlWimU6mTrzM9VW7J9XvEPGe"
"Nf9DRRMWSTopkGQSwdRVzcoNv2DyGi/7p+pXoI7iEZyvVwe/ascmsE1J/GKnJ8niLmCIJCT0oVyZCnEQIDuCzZ/CBYePfbhx"
"dNFrZWka7k3/mc2+sFo83qatJE3f0twjTwVzrDg6AQ896S2JlGASIpjTkJVo07H2mSyQJheQnA3Y2OpAnWWBtbmDbB0kH/fF"
"WISHelg4DopTdf3WyM18ONMgTiFCH+U7w2qe+PV10bD0jED6P/mN7LMvYr4sNRoBKekpnS71wNzH0J7SPzNV0dVGAei34EeX"
"wOOXivap9YTwtZGCtCVMoeOr+0gsdQBeqjSyLeViDH+FEBWvteKQI7WRB3gHLjGPnKpdxghiqfaZsZ1jD1xCVAAIMpZR8h4L"
"y4IrIz0WHJ6ZCECglEty/iSD+lz+UJmBxKm7T8aaqv3i8wpjlVhM3rpcmoWN9E/ESnS+mkQfFaqjy+uPHUHP0m+bG2xJ/AN9"
"+XEi4eE4mw3dSIlVynXsa7I2iEyAqO8B3+KBmvvQ01aSl1a2kITFf46FdFaBN65gn/k/GlgJAa16BOCARj+uIoKD3GgvetC6"
"IOb0F4j+WGS79UMwXWJ54twqKT4AhBLjoq22yGflFRfBOrkby5iSmMjKanMiFM50FWltbmKm46lJLMzXt+fuZU/7/QRfDoku"
"a8xW4no8mY1nyvpoPqkyf4iQbGkSuJX6kgsUi/Oc5UsYTgfVYA5HJH0BOBuoFZqeTUUY61lUysFnVFJfZRbXL5rbN3kCmP76"
"Ed/k2vb7Tzgs1dtnKjbA1p7I1LQ39lYg6YDKSrTPzr2JtM9RGHkfebesNEYSRSUbpDXpvsVBpBc0tNK0Kf4PEjbcwN+XlPMC"
"8nd8PlMtwM6QQ7Hzd7amukS13rBNFsyTnViUXqDEmbgbpw7A+KJRmixsFYUwGJlramZ2MZt68kXwpG15S4kluZapEBh8HrCT"
"0aUj11aRCPvc78Ojnw8qhOTYX2to3HIzj4FCWN5PQ7Tk7jdaD0rFxoRqa51wIhQjs9DuG2b+6nNpPrlDJX6w6fhA7C3hGJHV"
"kq/vWzgfC2kpVfhYd6KC+ySTTkCSR7JtBpAztwfU0iWaBnqmU7ZdOVidW+bX/DT+yx7An+1ugxf4o/XTWTyY9+YOCrgwKccB"
"S/Md8hYcUvKnSw+WYQZtZTT4QgFLooXeG9epQldH5L9/8dC/tyhdf9aepP7tDe2ENd6BAlv2NkXf4UFDwqA79G4MJRJochrF"
"8WE5UgHy7kMboEgvNWcwKjNo7qv+Lsj+p8UnlJ61Mh+3LRq1l77VUEe/xPo1jrR5LhShIWGht2R1ZJGykwtP5GwZMkmqTkLN"
"uvyRFOKiWZf265aXW89HuHX5SREcOcp5YuFmQGn0vQroptxyIEk9fGZPVfIaoxGxcgP9vzgG43JCdRc="
)
GEMINI_GENERATE_CONTENT_RESPONSE: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"parts": [
{
"text": GEMINI_3_8_FLASH_THOUGHT,
"thought": True,
},
{
"text": (
"To check how zero, negative, and non-integer quantities (such as floats, non-numeric values, or "
"values less than or equal to zero) are validated, I need to inspect `shop/validation.py` next."
),
},
{
"functionCall": {
"name": "read_file",
"args": {
"path": "shop/validation.py",
"end_line": 50,
"start_line": 1,
},
"id": "call_7668",
},
"thoughtSignature": GEMINI_3_8_FLASH_THOUGHT_SIGNATURE,
},
],
"role": "model",
},
"finishReason": "STOP",
"index": 0,
"finishMessage": "Model generated function call(s).",
},
],
"usageMetadata": {
"promptTokenCount": 358,
"candidatesTokenCount": 80,
"totalTokenCount": 1013,
"promptTokensDetails": [
{
"modality": "TEXT",
"tokenCount": 358,
},
],
"thoughtsTokenCount": 575,
"serviceTier": "standard",
},
"modelVersion": "gemini-3.8-flash",
"responseId": "1CbQat_JEK-jqtsPtf-QoQU",
}

371
tests/integration/translation/templates/openai.py Normal file
View file

@ -0,0 +1,371 @@
from collections.abc import Mapping
from typing import Final
from pydantic import JsonValue
OPENAI_RESPONSES_REQUEST_FROM_CHAT_COMPLETIONS: Final[Mapping[str, JsonValue]] = {
"input": [
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
}
],
},
{
"type": "message",
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": [
{
"type": "input_text",
"text": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": '
'"def validate_quantity(quantity):"}, {"path": '
'"tests/test_validation.py", "line": 7, "text": "def '
'test_zero_quantity():"}]}',
}
],
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read the validation file first so we can understand how zero and "
"negative quantities are handled.",
}
],
},
],
"instructions": "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 chat_completions client for this project review. "
"Consider zero, negative and non-integer quantities before choosing the next file "
"to inspect.",
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"stream": False,
"tools": [
{
"name": "search_files",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Search source and test files for a literal term.",
},
{
"name": "read_file",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": None,
"type": "function",
"description": "Read a range of lines from a project file.",
},
],
}
OPENAI_RESPONSES_REQUEST_FROM_MESSAGES: Final[Mapping[str, JsonValue]] = {
"input": [
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
}
],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "message",
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", '
'"line": 7, "text": "def test_zero_quantity():"}]}',
},
{
"type": "message",
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read the validation file first so we can understand how zero and "
"negative quantities are handled.",
}
],
},
],
"include": ["reasoning.encrypted_content"],
"instructions": "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 messages client for this project review. Consider "
"zero, negative and non-integer quantities before choosing the next file to "
"inspect.",
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"tools": [
{
"type": "function",
"name": "search_files",
"strict": False,
"description": "Search source and test files for a literal term.",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
{
"type": "function",
"name": "read_file",
"strict": False,
"description": "Read a range of lines from a project file.",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
],
}
OPENAI_RESPONSES_REQUEST: Final[Mapping[str, JsonValue]] = {
"input": [
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "The checkout rejects quantities of zero. Find the validation code and its tests.",
}
],
},
{
"role": "assistant",
"content": [{"type": "output_text", "text": "I will locate the quantity validation and its tests."}],
},
{
"type": "function_call",
"call_id": "toolu_synthetic_search_01",
"name": "search_files",
"arguments": '{"query": "quantity", "paths": ["shop/", "tests/"]}',
},
{
"type": "function_call_output",
"call_id": "toolu_synthetic_search_01",
"output": '{"matches": [{"path": "shop/validation.py", "line": 18, "text": "def '
'validate_quantity(quantity):"}, {"path": "tests/test_validation.py", '
'"line": 7, "text": "def test_zero_quantity():"}]}',
},
{
"role": "user",
"content": [
{
"type": "input_text",
"text": "Read the validation file first so we can understand how zero and "
"negative quantities are handled.",
}
],
},
],
"instructions": "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.",
"max_output_tokens": 1024,
"reasoning": {"effort": "high"},
"tools": [
{
"type": "function",
"name": "search_files",
"description": "Search source and test files for a literal term.",
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
},
{
"type": "function",
"name": "read_file",
"description": "Read a range of lines from a project file.",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
},
],
}
OPENAI_RESPONSES_RESPONSE: Final[Mapping[str, JsonValue]] = {
"id": "resp_0207c20ae125feee006ad023aada5c87d082ce8ba652474312",
"object": "response",
"created_at": 1792025514,
"status": "completed",
"access_programs": None,
"background": False,
"billing": {"payer": "developer"},
"completed_at": 1792025519,
"error": None,
"frequency_penalty": 0.0,
"incomplete_details": None,
"instructions": "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.",
"max_output_tokens": 1024,
"max_tool_calls": None,
"moderation": None,
"output": [
{
"id": "rs_0207c20ae125feee006ad023abed4087d09d32a32ad2d3182c",
"type": "reasoning",
"content": [],
"encrypted_content": "gAAAAABq0COvx3R_lOOaYJijiIokUKBq9tt_p3mhoPHnm4KR0Pj_t0wf1sP7WEDHfYSzylhHilYoKjU4guIz-TAqBV6HNUpIx5ggp3aukKEW6zks2ERT3a40sCFFdUdKHk6py5trFuwYn6lHLwifwDkd7rI7MKIP7C7pZSHnXh8cmfk0t96p4nBplQ93C4m917Kyx6PqvWSxPP78h5s_RMEdhkWRU20xMhminpIBNArOkPYT4xsmBEuONlndM5-DHG7ZeLk2yMZw8b_hxk2LZ4mC66b5RHfJKVKfw4egn4K8tkr8mQSR4bnjpY56DsIRj4fjSH5GpoDZyolFFBh1BNkGMoVsicye_4gZn0eELuOWxCw7lVVsMpIzTLw8CHJkCo_8vKtNCFSZcKjOPKDDfX1bsFJ7LMonmqijHPV_kZi_YXjVNNJBhJLiGjYrVUFZzjS0OKQx-RnZf5luO3UM2Ff3Ilvx1eQtuWlsvJjPBRwObzk5zlPEdYwoh5OjUREbgGb4H71Q7A9YYjUIms2h5e13Z5s8X0onRVr9SUcSbbMA0FXWn6QGQ5qgiQV56xec7xk62SrxKBXeILgBttBf68YfLAbdINCPL89G5Z1X2toQLlFM7e0jKYUOvSmpWyPLZ3q1040oDf2Q92v6NjOwk4WlLtZF_4xrZ7bEIWmea7zcDEnsvNBRdKaUbeUOm0SfRuIH4gQfbbueSqM3i12eK4TQhTbJ9VivUUovUv7pCKvizdQuunf2MMXWhq79wLYQYXIleQ06E9hbx6QT-Ue5ELQVC3NSLhXiwucOSqd-NZFDQA5wgW2Uaq_-bFYzNOPwtArfaqnHOILmr5mDvWCrlnLs-DUPHU-DtzYH7Eu1VSlcEZLaZX4vC9ui3x2aOpTtmVCILZpw7MkouVxSR4rFE48doVoCamJHhey-TZ7OMl0A5JdacTt6oUE8Z2HEcuVh9yGAZe_Q-YB3p4egLbxO8ICWUkwSSNgrPq3WRbT9sbT-Ko7N7KDAfgyvzzdEYMKDmci6GBrVsAiscc97-gxbhVhlrMyIXmgTluW07o591YjlOkvERXeJobEfby-VUJCu0cHd0nMudzrhCpHIhU3aUMkk9GMlSNDPFnKeV-gylycLhYRb0xo1kXMRom82fKmvUgO5Wh_BhsCdeGaVQ2bm5wyLT4x9VhEe-uOwaYG02XxoSiIFqqSrf0J8auFHIRpUTKzNWMK_GcIaU6o3ON0wOLKaga3wcyrGkG6wtvGkNLCrvmDIXg0bmvFGZrmybQvys_u636NXVS-Y9irqUv2ghu5tyKI_F8uwibi9JkKa5XcotQGbAToTE8qaHfowZOdTyjIKrU3BjL_Hs5M41KXwrNkk_X5ttJxEPW1qCjyusFb9yeGa9wzHMsp_VO0ysdO8L2KSRAY4LHpGI175VxUmnSg66PtCPln0OYxWsX2FWE1A7B_la662tO4VoS3bcslVZreRWFDJ_7X8qKx2fStxd77B7JkG1ZElxlZYlBRN5_Lo_w1yM9SvqHzzewQYEprSA1gltjxAbIzy7xXReaT86PNI8ojSLfXOkXa6Cybu3hIxsIomkZwTtAEx85BoIDn2B8oTp744Lwkwn4ualAfV9TebiqOWCUYp47fX9rimte71X6Hnvf7tWEBZMMwSb0pTqY0boMOS0w3XKKyEVRNyCoGWMgyvhAxk9E5iao5N6i5W3aSel27QwsUaE4YDGKKMKSryH3BqP6X7d0kdUcAx-nd5yudVbePQyc-UC7EbISj5QXY8g6cTOy-IkwpBe68DvfcNGIhuaH6UscqrewXQjKZFJC_BJSl-ICOfMw-FCTumzCDXPqTeLBPHf1g5kd5lBd6HLPUldHtJfD48V12KCRtaoksZ4g2NibuClnmZRpnDMPDUr7r_D8-RfoLEiJeh8SbOSnLvMPVAJIB95F73B-UX5u0e0aWeyfG5QjBq-kB7vVGsRiMyHEVQW810xo2qULVIyVO03s7rAWwTxFY-EHmKkaAIbKU2b-qAasytni7f1Aq61OSIYqSCRdFhpUX6HpnQeCFC_s6_Q9P3CFx120ZaTB_HPeRJO6dhVSJ3nL3PiNi8sCnhRiNIXkJfm9l1TxRS8ok9s1NY8oi4Y98J4Ay52EkX6f9F9FtWHNu4GX_Z50jDNnVTVqQo3L3slpwxECsTAEU-0MsmIa-1RqJ00VqBLKtIDVbbnQ==",
"summary": [],
},
{
"id": "msg_0207c20ae125feee006ad023ade23487d093e272f84cb35723",
"type": "message",
"status": "completed",
"content": [
{
"type": "output_text",
"annotations": [],
"logprobs": [],
"text": "I’ll read `shop/validation.py` first to check how it handles "
"zero, negative, and non-integer quantities.",
}
],
"phase": "commentary",
"role": "assistant",
},
{
"id": "fc_0207c20ae125feee006ad023ae893c87d08068561e36e665ad",
"type": "function_call",
"status": "completed",
"arguments": '{"path":"shop/validation.py","start_line":1,"end_line":200}',
"call_id": "call_S4WtfrQwa6ZLEUZf1BVtA8ON",
"name": "read_file",
},
],
"parallel_tool_calls": True,
"presence_penalty": 0.0,
"previous_response_id": None,
"prompt_cache_key": None,
"prompt_cache_retention": "24h",
"reasoning": {"context": "all_turns", "effort": "high", "mode": "standard", "summary": None},
"safety_identifier": None,
"service_tier": "default",
"store": True,
"temperature": 1.0,
"text": {"format": {"type": "text"}, "verbosity": "medium"},
"tool_choice": "auto",
"tool_usage": {
"image_gen": {
"input_tokens": 0,
"input_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"output_tokens": 0,
"output_tokens_details": {"image_tokens": 0, "text_tokens": 0},
"total_tokens": 0,
},
"web_search": {"num_requests": 0},
},
"tools": [
{
"type": "function",
"description": "Search source and test files for a literal term.",
"name": "search_files",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {"query": {"type": "string"}, "paths": {"type": "array", "items": {"type": "string"}}},
"required": ["query", "paths"],
"additionalProperties": False,
},
"strict": True,
},
{
"type": "function",
"description": "Read a range of lines from a project file.",
"name": "read_file",
"output_schema": None,
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
"additionalProperties": False,
},
"strict": True,
},
],
"top_logprobs": 0,
"top_p": 0.98,
"truncation": "disabled",
"usage": {
"input_tokens": 309,
"input_tokens_details": {"cache_write_tokens": 0, "cached_tokens": 0},
"output_tokens": 118,
"output_tokens_details": {"reasoning_tokens": 53},
"total_tokens": 427,
},
"user": None,
"metadata": {},
}

281
tests/integration/translation/templates/vertex_ai.py Normal file
View file

@ -0,0 +1,281 @@
from collections.abc import Mapping
from typing import Final
from integration.translation.templates.anthropic import ANTHROPIC_MESSAGES_REQUEST
from pydantic import JsonValue
VERTEX_AI_ANTHROPIC_THINKING_SIGNATURE_0: Final = (
"CAQSsAcKEggSEAIYAjgBQgh0aGlua2luZxIM5AdGqr4T05oHxpggGgz1Xe5nFTdJd/ZREp8iMMOP/ne3HrVXil/Qby25EvgVLzla"
"PlAqV9EuGZhZueHwbwVDEAZISWNgb6af+m03KCrLBoxdew1rYrrcHnuY8IsIpAvjDHAWs/wAS1J8xCNJO8pAWdDUkXz9je0gdBkP"
"5EGORxwGsDr2ATCotY/rWi51A5rSI07lMVVEYjko0F1xbLOEW0Q/H76nWrp30p5v6HfxDmxBg3WvzYmu45onzgN/Q0R13KPzAy5A"
"4RWV3ANP+SRwJFQyTSFLqn0O1dNnd7eENp2TvBaV6ruF+qbrEM3Bdfc3XkyCSQMn6RSSNM+LkK6VrMdjOOtQZybFHgmOC+ksFqFJ"
"+nBeLOS0wI2QbaIVVR7k5yFGoGW3DLlIFDSKTzOPnhLJMdSMvLBpf156LuUkjk9cHzgriw8kyZJbVtuw/Myvwc5u2ZQsuAfuqwd8"
"f5Ewf6OPt609o+C0G9dzKlt7jV+ZwVfMIm+MbSO0nxVaFMgZwBFrqcLH/+ie5m2QCBjVJXMUcc4dy2u7NfYxN1UzLJjdHzp/EOox"
"2mieSdI0Llx9sqiWmJRlt73evYTY34Z0V29dFOaJGH6ZecuFj7JnaR4EhLTZZJixesoYKy6b8wJB0ZsLKsQ9N93Kbxc4ODzBZnad"
"Nbxx5JH/weFk5MDKBtIiCoBXusFAvDO5xO7G/iuO3Rq1MB9P1GFf7e+CB6Y5Ej/5yL1nCivCrEd4tYJUnl3DCjSW2QuV+JqwmclM"
"08RgVQKJ50OXYQNgev8aO1JSrs8NpmtodrUrgpwLDSqetMTsm8LkpqZadc+73gGjAscm4o9Q4+m02gpqLklXxgS+QxN8PBTNDC42"
"VJzXowlJJHRXoczxrt54cj/iY8VEcP3o0Y99zNIyvbvCyZypnrkTfYlEQo+1+c5tjcUiMGaXb26UZpr91VO6vYqS06lgLIWYjlf1"
"qF8Ym+EqPRVZsz/YZuy+7laG/9nF4qAIMWqASxL2BFpdPrhePcFrlyefEU3zt5Vl8xvR8K4zv9Glmtd+3mVIwDc6fSAwdm9rWtzg"
"92Mq8LzeyxrNcLijq8iWK1CnFK3ayPJgSicuEhXgD0JpgltQh+lWZ6a8M71+/SGyJJb8hQp5x5wpEKFgGKTCBvl/oV0Op8/Ie44I"
"IYHkm/aOvu+WSnHwU4IrcHwPBSUbk2pYKaWQb1cRlDfXWmuaHluOfiRPo0ORvzOdehgB"
)
VERTEX_AI_ANTHROPIC_THINKING_SIGNATURE_1: Final = (
"CAQS/QUKEwgSEAIYAjgBQgluYXJyYXRpb24SDCLtxRBlqq3WVMEpRxoM5UkHHwV72f1gxZ0HIjB4+DqdmR5Sfg3wso78vOXyUJMZ"
"H7w/XBD3JSH6I78plRQCkTuRWhd+umfXGpb9if4qlwXOtx5CQ1E+AabA3vqpLJarGaCFHO8HclGAk37uPKxmyKk7hSHvMyn3ZIG7"
"aVPOT7f42kI2Kif4/xhMrZ0jANrgbxsT2I+UfbFVXeOaKFjkG3Enn46IXL11N+4vP8RbdGESWDxcWDyLmp0O74W825FHNsrf4tNA"
"mfH19Mq1jXYC//8fsz01HC7mlsTGFQShBdbblbKcV43Mkdsq1OV1EOkUZf5JX1AKr1D2Ywsp11aoU//VfXb2Bq+/o8E/2ZRupoTL"
"d1Sak7H1aNdfJ+5mfDHGLOrlPjxunSxxksfrZopjVFs8fN/OsSX2FjCDeHskShGoAF/75pfDHvQl+vsZgWgprTZ7nZ2Sirx3Asui"
"670zquqc02ke2ZBxFhVvbfXikAm37QK3sSyzMp0xtXx7+B5TqguHMBPcZ2FwMkkejyM/2c8p1UnoimAjEnD7VxWuEgmg72cL62Qb"
"TN1W6qRf50CQnC7yrTh+23804bQ94kea4mobxRPcveyZVCtlcwgKcvFzWSqZ+QYVORHbnBkKIQlUZB81VT7NxM54UN2Lu2clNu3E"
"/6r+0pYrbmJazAtcaT1LLFS5wrfl6ngHGTDdPGIwQPZRclrL+tV3YGApuwauC1QQRD3NG8XAuHhEbtJcxOBmGx1ctOsHiRrhoFjM"
"MQ+/qNprXLGy/JWeSOdJdwpWOIuqKf8g1LH2NDxbMHOnkIN+UbQBBCbMDdV8oLbpu7n8+moK5ggx4sQ3sWcn9/aBl9VTUC9Qjk3/"
"GTNtZNGzlWBVn7w/JnYZINjy40DtReIHdqcZja5XKnYpzfh7G6EcYA7tW4SmtWb2sPB1Msz+S8FW944iQ+AyfZQqic9b8BEw2JYG"
"it0butjvG2EWi4LnL966v5WCZQAYAQ=="
)
VERTEX_AI_GEMINI_THOUGHT_SIGNATURE_0: Final = (
"AY89a1/K8QT9La7l3gDc5jImwnXSF0xUuyg8rAUnAyYS4c2/Yjd/fV3Ve1tHSww5bSooGMdZ0oqljadXXxUqYi+7fkKOWD0Ij80K"
"LFu1O//r13u8cIpIqUxEi3lNiEn8rK6WVW5DPTMTBddZBL+/DcpCEi7U3m5vGYfoJUm9AJwQB8XDRdqLdA1hfiRnCqGpLJsFAQ2g"
"Ln3FpQUPR3+FRoWRlJnNRjk8vWaq3mBKHSHttLMRd3rpvo6VAAZbs2OGoBJXFXA9S+RyN532kDK3fZIGGW2Fk+FSD9EJ1hN1+Qeh"
"v8gzcxyZOin2O/ONFWEQ4zf8lHTzaostuIMLkKFM3v/ssK+Y4VgS0sPFr7VFByhczwoDx73oh141iDD5ch7tqAgnR7YikrWQDuV2"
"8FBSB7+MQ3BrBSt6XUvYgcHsGNbg0giE3D3pFDR7uvLfvgjhFFdIqnCWWmPfBgZ7GOD55unG0IUPA2udP65xg88r8TjfpQOUsOnN"
"KZLOiKovzHrXZX2L0tRGha5nE8ICi427Mc5YF9lm0Ilpo/BrGuuusMG3Zx9RxRyjRa9+zWPANRrvuq7SOVnFvAss4uu9PYf5Orwn"
"nGFJ0xjP1hn22yXOxRYy62ySQQ1ValpWXjPPXvGKZRiUArCuvrBvDEZoUfJhlcVXs26kYnqRikRLev4GZGvBIDnGHyWLvMo0gx4r"
"1kBnAGl5WyfZJu5SFywm/o5fMP70zVUoVdY+zC885uqB5pEV+VsAMyy98NumfmBF7kGtIjbt4l+hAqpzM1ME1z0kRqN7n9JEKn0H"
"DlsQAD9V582O2bBVSTRzF8aFJ7RKohGhrFqyGmYLA+ZAv5Z4kJ1HBZg1LEz2G88MT2vznP6lCEH0m9da48Q5/85pNQ5dlGGEkhpP"
"I+xazh6EZ0cFNGdNY1vAQY5rBQ8LPwizNSKenYvqwMdobWy8xReIQWCsOk2l4QCtlu8kC+iabWrsCPOfjdQmYTlpI+emQwssWXYU"
"UQ+wDGl7QWoaSAnwGu+XQMQ9ndaUycPdBu5+cuw815uiNNtIVfeKejFIbLF66Jq/duKfZ9tgWthPzpoM50u9aie2FZwNOuEtaLIv"
"WcdtBpY9LvnAemSuDUTLLSuiQYwBwRq8HKdFARJ362Wf8gg+ldoeXEV9R6+cscPaeY5j/+E/rsTWyxixg614qiFQyF5xL/7DWjUI"
"LBuIrmJUIVcu8LelTUslepTGF6CBTJ0RABv8pK7S8dUDy+HXtvT8bmz8l9zOsaTagC1jUpvaeGpi44gorN9KU7z56FMxoKSeKF7M"
"B2zuTFBN/GekI9gddLfQRaVK/9LAD4j+uBzdt/XICe2kGqjNu3ds9tnx82/9beezRyTRfFQ+p1V/jfaEt8AMTZ5I2IZQAkgkAnXa"
"KieRKs8qKbkF5yjhtI0krsyg4+BDQZzog+dgkxqYxLDuNyd6hN9HlnMEBAwW8hxWGp4WE8GvL2IU529JVMaBvK/NcrGNnPW/m158"
"BwaIFSfbSxQbqjv6KKqMi30i2bowXBAJit2YQHb3VN1reFBynM9mRm71PGLAbizdVS5VIqNI5zGquZrgpmTqqMF/AjsWpVSTo6Gi"
"WD3O2PJWReehkH3aMJMFeu3jv0/Ru+Ihw1zwFcZr0Yh7rK2NEYQyZjcmf5/vX0rBh89HEVdc78j16arXcFWHNZS2lLAm0NC+Xmak"
"WIP3YUcba6POPYKwqP2huUccyyGg+qFPTcWF488PNm4H86YQRrnUSkPEofjMuaLMrp3vS1TgpjuUZRiZ"
)
VERTEX_AI_ANTHROPIC_MESSAGES_REQUEST: Final[Mapping[str, JsonValue]] = {
**ANTHROPIC_MESSAGES_REQUEST,
"anthropic_version": "vertex-2023-10-16",
}
VERTEX_AI_ANTHROPIC_MESSAGES_RESPONSE: Final[Mapping[str, JsonValue]] = {
"id": "msg_vrtx_011Cg38nogK8THpR3HzMQ1Mt",
"type": "message",
"role": "assistant",
"content": [
{
"type": "thinking",
"thinking": (
"The user asked to read the validation file first, but since reading the tests is independent, I "
"think it's fine to read both files together rather than strictly sequencing them.\n\n"
),
"signature": VERTEX_AI_ANTHROPIC_THINKING_SIGNATURE_0,
},
{
"type": "thinking",
"thinking": (
"I'll check `shop/validation.py` for how `validate_quantity` handles zero, negative, and non-integer "
"values, and review `tests/test_validation.py` for the expected behavior.\n\n"
),
"signature": VERTEX_AI_ANTHROPIC_THINKING_SIGNATURE_1,
},
{
"type": "tool_use",
"id": "toolu_vrtx_01SYkCZM7zmQWqcyokJjiAyf",
"name": "read_file",
"input": {"path": "shop/validation.py", "start_line": 1, "end_line": 60},
},
{
"type": "tool_use",
"id": "toolu_vrtx_01UhxynEUZYnaNhRkRGC2ZGn",
"name": "read_file",
"input": {"path": "tests/test_validation.py", "start_line": 1, "end_line": 50},
},
],
"container": None,
"stop_reason": "tool_use",
"stop_sequence": None,
"stop_details": None,
"usage": {
"input_tokens": 4,
"cache_creation_input_tokens": 876,
"cache_read_input_tokens": 0,
"cache_creation": {"ephemeral_5m_input_tokens": 876, "ephemeral_1h_input_tokens": 0},
"output_tokens": 425,
"output_tokens_details": {"thinking_tokens": 229},
},
}
VERTEX_AI_GEMINI_GENERATE_CONTENT_REQUEST: Final[Mapping[str, JsonValue]] = {
"contents": [
{
"role": "user",
"parts": [{"text": "The checkout rejects quantities of zero. Find the validation code and its tests."}],
},
{
"role": "model",
"parts": [
{"text": "I will locate the quantity validation and its tests."},
{
"function_call": {
"name": "search_files",
"args": {"query": "quantity", "paths": ["shop/", "tests/"]},
"id": "toolu_synthetic_search_01",
},
"thoughtSignature": "c2tpcF90aG91Z2h0X3NpZ25hdHVyZV92YWxpZGF0b3I=",
},
],
},
{
"role": "user",
"parts": [
{
"function_response": {
"name": "search_files",
"response": {
"matches": [
{
"path": "shop/validation.py",
"line": 18,
"text": "def validate_quantity(quantity):",
},
{
"path": "tests/test_validation.py",
"line": 7,
"text": "def test_zero_quantity():",
},
],
},
"id": "toolu_synthetic_search_01",
},
},
],
},
{
"role": "user",
"parts": [
{
"text": "Read the validation file first so we can understand how zero and negative quantities are handled.",
},
],
},
],
"system_instruction": {
"parts": [
{
"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 "
"chat_completions client for this project review. Consider zero, negative and non-integer quantities "
"before choosing the next file to inspect."
),
},
],
},
"tools": [
{
"function_declarations": [
{
"name": "search_files",
"description": "Search source and test files for a literal term.",
"parameters": {
"type": "object",
"properties": {
"query": {"type": "string"},
"paths": {"type": "array", "items": {"type": "string"}},
},
"required": ["query", "paths"],
},
},
{
"name": "read_file",
"description": "Read a range of lines from a project file.",
"parameters": {
"type": "object",
"properties": {
"path": {"type": "string"},
"start_line": {"type": "integer", "minimum": 1},
"end_line": {"type": "integer", "minimum": 1},
},
"required": ["path", "start_line", "end_line"],
},
},
],
},
],
"generationConfig": {
"max_output_tokens": 1024,
"thinkingConfig": {"thinkingLevel": "high", "includeThoughts": True},
},
}
VERTEX_AI_GEMINI_GENERATE_CONTENT_RESPONSE: Final[Mapping[str, JsonValue]] = {
"candidates": [
{
"content": {
"role": "model",
"parts": [
{
"text": (
"**My Thought Process on Analyzing the Request and Planning the Next Action**\n\nRight, so my primary "
"objective here is to fulfill the user's request while adhering strictly to the system's operational "
'guidelines. The user has specifically asked me to "Read the validation file first so we can '
'understand how zero and negative quantities are handled." This is a direct instruction that aligns '
'perfectly with the overarching system instruction to "Read the relevant files before suggesting a '
'fix."\n\nMy internal checklist, based on the system\'s directives, also reminds me to:\n* "Explain '
'which file you need next, then call a read-only tool."\n* "Never change files." (This is a '
'foundational rule, of course.)\n* "Use the chat_completions client for this project review." (This '
"context is already established.)\n* Crucially, and directly relevant to the user's query: "
'"Consider zero, negative and non-integer quantities before choosing the next file to '
'inspect."\n\nNow, looking at the files I have access to, I see `shop/validation.py` and '
"`tests/test_validation.py`. The user's request directly points to `shop/validation.py` as the next "
"file to examine for validation logic. This makes sense, as the name itself implies it's where the "
"core validation rules reside.\n\nBefore I jump straight into invoking a tool, the system requires me "
"to articulate *why* I'm selecting this file and *what* I intend to do with it. So, I need to "
"explain that I'm going to inspect `shop/validation.py` specifically to understand its handling of "
"quantities, particularly concerning zero, negative, and non-integer values, as prompted by the user "
"and reinforced by the system's guidance.\n\nFollowing that explanation, I'll then execute the action "
"by calling a read-only tool, `read_file`. I'll specify `shop/validation.py` as the path, and to get "
"a good initial overview, I'll plan to read a reasonable chunk, say from line 1 to around line 50, "
"to capture the initial validation logic. This seems like a good starting point to gather the "
"necessary context for the user's specific inquiry.\n\n"
),
"thought": True,
},
{
"text": (
"To see how quantities (including zero, negative, and non-integer values) are validated, I need to "
"read `shop/validation.py` next."
),
},
{
"functionCall": {
"name": "read_file",
"args": {"start_line": 1, "end_line": 50, "path": "shop/validation.py"},
"id": "call_267302",
},
"thoughtSignature": VERTEX_AI_GEMINI_THOUGHT_SIGNATURE_0,
},
],
},
"finishReason": "STOP",
},
],
"usageMetadata": {
"promptTokenCount": 246,
"candidatesTokenCount": 65,
"totalTokenCount": 642,
"trafficType": "ON_DEMAND",
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 246}],
"candidatesTokensDetails": [{"modality": "TEXT", "tokenCount": 65}],
"thoughtsTokenCount": 331,
},
"createTime": "2026-10-15T01:13:21.457273Z",
"responseId": "sSjQarn0G-Wb4_UPmobfOA",
}