From d49114b101411f72d083b9ba7e1458d0d59e2dcc Mon Sep 17 00:00:00 2001 From: Yuneng Jiang Date: Tue, 11 Aug 2026 18:49:47 -0700 Subject: [PATCH] test(bedrock): repoint live Claude tests off the retired Claude 3 Sonnet AWS no longer serves `anthropic.claude-3-sonnet-20240229-v1:0`. The streaming path returns a plain 404, "Model with the provided id anthropic.claude-3-sonnet-20240229-v1:0 is not found", and the non-streaming path answers 500 for the same reason. Our own cost map has carried a 2026-07-30 deprecation date for it since #36538 That accounts for 20 failures across local_testing_part1, local_testing_part2 and llm_translation_testing. litellm maps both statuses correctly, so the tests are what went stale, not the client Replacement is `us.anthropic.claude-sonnet-4-5-20250929-v1:0`: a like-for-like Sonnet, and the newest Bedrock Sonnet this repo exercises against the real API in tests/e2e. Newer ids exist in the cost map, but nothing in the repo calls them live, so picking one would be an unverified guess about model access on the CI account Scope is limited to the tests that actually issue a request. The occurrences that assert on the model string itself, or that feed mocked transformations, keep the old id so their assertions stay meaningful --- tests/llm_translation/test_bedrock_completion.py | 12 ++++++------ tests/local_testing/test_completion.py | 8 ++++---- tests/local_testing/test_function_calling.py | 8 ++++---- tests/local_testing/test_streaming.py | 6 +++--- 4 files changed, 17 insertions(+), 17 deletions(-) diff --git a/tests/llm_translation/test_bedrock_completion.py b/tests/llm_translation/test_bedrock_completion.py index 8ab2feaf896..94b81737654 100644 --- a/tests/llm_translation/test_bedrock_completion.py +++ b/tests/llm_translation/test_bedrock_completion.py @@ -475,7 +475,7 @@ def test_bedrock_claude_3(image_url): ], } response: ModelResponse = completion( - model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", num_retries=3, **data, ) # type: ignore @@ -498,7 +498,7 @@ def test_bedrock_claude_3(image_url): @pytest.mark.parametrize( "model", [ - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", # "meta.llama3-70b-instruct-v1:0", # "anthropic.claude-v2", # "mistral.mixtral-8x7b-instruct-v0:1", @@ -537,7 +537,7 @@ def test_bedrock_stop_value(stop, model): @pytest.mark.parametrize( "model", [ - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "mistral.mixtral-8x7b-instruct-v0:1", ], ) @@ -602,7 +602,7 @@ def test_bedrock_claude_3_tool_calling(): } ] response: ModelResponse = completion( - model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", messages=messages, tools=tools, tool_choice="auto", @@ -630,7 +630,7 @@ def test_bedrock_claude_3_tool_calling(): ) # In the second response, Claude should deduce answer from tool results second_response = completion( - model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", messages=messages, tools=tools, tool_choice="auto", @@ -2327,7 +2327,7 @@ def test_bedrock_cross_region_inference(monkeypatch): def test_bedrock_empty_content_real_call(): completion( - model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", messages=[ { "role": "user", diff --git a/tests/local_testing/test_completion.py b/tests/local_testing/test_completion.py index b4f0359cf9d..eee0de9aa24 100644 --- a/tests/local_testing/test_completion.py +++ b/tests/local_testing/test_completion.py @@ -271,7 +271,7 @@ def test_completion_claude_3(): @pytest.mark.parametrize( "model", - ["anthropic/claude-sonnet-4-5-20250929", "anthropic.claude-3-sonnet-20240229-v1:0"], + ["anthropic/claude-sonnet-4-5-20250929", "us.anthropic.claude-sonnet-4-5-20250929-v1:0"], ) def test_completion_claude_3_function_call(model): litellm.set_verbose = True @@ -357,7 +357,7 @@ def test_completion_claude_3_function_call(model): [ ("gpt-3.5-turbo", None, None), ("claude-sonnet-4-5-20250929", None, None), - ("anthropic.claude-3-sonnet-20240229-v1:0", None, None), + ("us.anthropic.claude-sonnet-4-5-20250929-v1:0", None, None), # ( # "azure_ai/command-r-plus", # os.getenv("AZURE_COHERE_API_KEY"), @@ -1550,7 +1550,7 @@ def test_completion_openai(): [ # ("gpt-4o-2024-08-06", None), # ("azure/gpt-4.1-mini", None), - ("bedrock/anthropic.claude-3-sonnet-20240229-v1:0", None), + ("bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", None), # ("azure/gpt-4o-new-test", "2024-08-01-preview"), ], ) @@ -2887,7 +2887,7 @@ def response_format_tests(response: litellm.ModelResponse): [ "bedrock/mistral.mistral-large-2407-v1:0", "bedrock/cohere.command-r-plus-v1:0", - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", "mistral.mistral-7b-instruct-v0:2", "meta.llama3-8b-instruct-v1:0", ], diff --git a/tests/local_testing/test_function_calling.py b/tests/local_testing/test_function_calling.py index 3c7e004b62e..4095962f91d 100644 --- a/tests/local_testing/test_function_calling.py +++ b/tests/local_testing/test_function_calling.py @@ -49,7 +49,7 @@ def get_current_weather(location, unit="fahrenheit"): "mistral/mistral-large-latest", "claude-haiku-4-5-20251001", "gemini/gemini-2.5-flash-lite", - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", ], ) @pytest.mark.flaky(retries=3, delay=1) @@ -303,7 +303,7 @@ _PARALLEL_TOOL_HISTORY_MESSAGES = [ [ # Bedrock Converse still requires modify_params to inject the dummy tool. ( - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", _PARALLEL_TOOL_HISTORY_MESSAGES, True, ), @@ -314,7 +314,7 @@ _PARALLEL_TOOL_HISTORY_MESSAGES = [ False, ), ( - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", [ { "role": "user", @@ -579,7 +579,7 @@ def test_groq_parallel_function_call(): @pytest.mark.parametrize( "model", [ - "bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + "bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", ], ) def test_passing_tool_result_as_list(model): diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py index 10f351714e1..a4f564b227f 100644 --- a/tests/local_testing/test_streaming.py +++ b/tests/local_testing/test_streaming.py @@ -1174,7 +1174,7 @@ async def test_completion_replicate_llama3_streaming(sync_mode): [ # ["bedrock/ai21.jamba-instruct-v1:0", "us-east-1"], # ["bedrock/cohere.command-r-plus-v1:0", None], - ["anthropic.claude-3-sonnet-20240229-v1:0", None], + ["us.anthropic.claude-sonnet-4-5-20250929-v1:0", None], # ["mistral.mistral-7b-instruct-v0:2", None], # ["meta.llama3-8b-instruct-v1:0", None], ], @@ -1246,7 +1246,7 @@ def test_bedrock_claude_3_streaming(): try: litellm.set_verbose = True response: ModelResponse = completion( # type: ignore - model="bedrock/anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", messages=messages, max_tokens=10, # type: ignore stream=True, @@ -3500,7 +3500,7 @@ def test_unit_test_perplexity_citations_chunk(): [ "gpt-3.5-turbo", "claude-sonnet-4-5-20250929", - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-sonnet-4-5-20250929-v1:0", # "vertex_ai/claude-3-5-sonnet@20240620", ], )