mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-03 07:23:33 +00:00
7b7604f0ed
* 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>
475 lines
22 KiB
Python
475 lines
22 KiB
Python
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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"
|
|
|
|
GEMINI_3_5_FLASH_TEST_CASE: Final = TranslationTestCase(
|
|
scenario="basic",
|
|
litellm_endpoint="/v1/messages",
|
|
litellm_request={
|
|
"model": "gemini/gemini-3.5-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-3.5-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_5_FLASH_THOUGHT_SIGNATURE}],
|
|
"role": "model",
|
|
},
|
|
"finishReason": "STOP",
|
|
"index": 0,
|
|
}
|
|
],
|
|
"usageMetadata": {
|
|
"promptTokenCount": 10,
|
|
"candidatesTokenCount": 2,
|
|
"totalTokenCount": 137,
|
|
"promptTokensDetails": [{"modality": "TEXT", "tokenCount": 10}],
|
|
"thoughtsTokenCount": 125,
|
|
"serviceTier": "standard",
|
|
},
|
|
"modelVersion": "gemini-3.5-flash",
|
|
"responseId": "4hjEav32Mt6P6dkPn5iDqAg",
|
|
},
|
|
expected_litellm_response={
|
|
"id": "4hjEav32Mt6P6dkPn5iDqAg",
|
|
"type": "message",
|
|
"role": "assistant",
|
|
"model": "gemini/gemini-3.5-flash",
|
|
"stop_sequence": None,
|
|
"usage": {"input_tokens": 10, "output_tokens": 127},
|
|
"content": [{"type": "text", "text": "Hello."}],
|
|
"stop_reason": "end_turn",
|
|
"stop_details": None,
|
|
},
|
|
)
|