diff --git a/litellm/llms/bedrock/chat/agentcore/transformation.py b/litellm/llms/bedrock/chat/agentcore/transformation.py index 44ba1ce3c8..9b9b96aae0 100644 --- a/litellm/llms/bedrock/chat/agentcore/transformation.py +++ b/litellm/llms/bedrock/chat/agentcore/transformation.py @@ -157,8 +157,8 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM): def _get_agent_runtime_arn(self, model: str) -> str: """ Extract ARN from model string - model = "agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC" - returns: "arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC" + model = "agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp" + returns: "arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp" """ parts = model.split("/", 1) if len(parts) != 2 or parts[0] != "agentcore": @@ -170,7 +170,7 @@ class AmazonAgentCoreConfig(BaseConfig, BaseAWSLLM): def _extract_region_from_arn(self, arn: str) -> str: """ Extract region from ARN - arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC + arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp returns: us-west-2 """ parts = arn.split(":") diff --git a/litellm/proxy/example_config_yaml/oai_misc_config.yaml b/litellm/proxy/example_config_yaml/oai_misc_config.yaml index 16cc69c19a..0b647de8a0 100644 --- a/litellm/proxy/example_config_yaml/oai_misc_config.yaml +++ b/litellm/proxy/example_config_yaml/oai_misc_config.yaml @@ -23,11 +23,11 @@ model_list: model: bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0 ######################################################### ########## batch specific params ######################## - s3_bucket_name: litellm-proxy + s3_bucket_name: litellm-proxy-941277531214 s3_region_name: us-west-2 s3_access_key_id: os.environ/AWS_ACCESS_KEY_ID s3_secret_access_key: os.environ/AWS_SECRET_ACCESS_KEY - aws_batch_role_arn: arn:aws:iam::888602223428:role/service-role/AmazonBedrockExecutionRoleForAgents_BB9HNW6V4CV + aws_batch_role_arn: arn:aws:iam::941277531214:role/service-role/AmazonBedrockExecutionRoleForAgents_BB9HNW6V4CV model_info: mode: batch diff --git a/litellm/proxy/example_config_yaml/otel_test_config.yaml b/litellm/proxy/example_config_yaml/otel_test_config.yaml index c05e2b1b5d..9c7937efba 100644 --- a/litellm/proxy/example_config_yaml/otel_test_config.yaml +++ b/litellm/proxy/example_config_yaml/otel_test_config.yaml @@ -55,7 +55,7 @@ guardrails: litellm_params: guardrail: bedrock # supported values: "bedrock", "lakera" mode: "during_call" - guardrailIdentifier: ff6ujrregl1q + guardrailIdentifier: 4w3d1di3snt5 guardrailVersion: "DRAFT" - guardrail_name: "custom-pre-guard" litellm_params: diff --git a/tests/agent_tests/local_only_agent_tests/test_a2a_completion_bridge.py b/tests/agent_tests/local_only_agent_tests/test_a2a_completion_bridge.py index a9268da4c3..95d76ba580 100644 --- a/tests/agent_tests/local_only_agent_tests/test_a2a_completion_bridge.py +++ b/tests/agent_tests/local_only_agent_tests/test_a2a_completion_bridge.py @@ -168,7 +168,7 @@ async def test_a2a_completion_bridge_bedrock_agentcore(): litellm._turn_on_debug() # Bedrock AgentCore ARN (streaming-capable runtime) - agentcore_arn = "arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC" + agentcore_arn = "arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp" send_message_payload = { "message": { diff --git a/tests/batches_tests/test_bedrock_files_and_batches.py b/tests/batches_tests/test_bedrock_files_and_batches.py index 5148ea4db9..97c0802ec9 100644 --- a/tests/batches_tests/test_bedrock_files_and_batches.py +++ b/tests/batches_tests/test_bedrock_files_and_batches.py @@ -38,7 +38,7 @@ async def test_async_create_file(): file=open(file_path, "rb"), purpose="batch", custom_llm_provider="bedrock", - s3_bucket_name="litellm-proxy", + s3_bucket_name="litellm-proxy-941277531214", ) @@ -55,7 +55,7 @@ async def test_async_file_and_batch(): file=open(file_path, "rb"), purpose="batch", custom_llm_provider="bedrock", - s3_bucket_name="litellm-proxy", + s3_bucket_name="litellm-proxy-941277531214", ) print("CREATED FILE RESPONSE=", file_obj) @@ -70,7 +70,7 @@ async def test_async_file_and_batch(): # bedrock specific params ######################################################### model="us.anthropic.claude-haiku-4-5-20251001-v1:0", - aws_batch_role_arn="arn:aws:iam::888602223428:role/service-role/AmazonBedrockExecutionRoleForAgents_BB9HNW6V4CV", + aws_batch_role_arn="arn:aws:iam::941277531214:role/service-role/AmazonBedrockExecutionRoleForAgents_BB9HNW6V4CV", ) print("CREATED BATCH RESPONSE=", create_batch_response) @@ -129,7 +129,7 @@ async def test_mock_bedrock_file_url_mapping(): ), purpose="batch", custom_llm_provider="bedrock", - s3_bucket_name="litellm-proxy", + s3_bucket_name="litellm-proxy-941277531214", ) print(f"PUT URL: {captured_put_url}") diff --git a/tests/guardrails_tests/test_bedrock_guardrails.py b/tests/guardrails_tests/test_bedrock_guardrails.py index 6e78a8c428..ea50fe08ae 100644 --- a/tests/guardrails_tests/test_bedrock_guardrails.py +++ b/tests/guardrails_tests/test_bedrock_guardrails.py @@ -20,7 +20,7 @@ async def test_bedrock_guardrails_pii_masking(): mock_user_api_key_dict = UserAPIKeyAuth() guardrail = BedrockGuardrail( - guardrailIdentifier="wf0hkdb5x07f", + guardrailIdentifier="zgkmukebruil", guardrailVersion="DRAFT", ) @@ -60,7 +60,7 @@ async def test_bedrock_guardrails_pii_masking_content_list(): mock_user_api_key_dict = UserAPIKeyAuth() guardrail = BedrockGuardrail( - guardrailIdentifier="wf0hkdb5x07f", + guardrailIdentifier="zgkmukebruil", guardrailVersion="DRAFT", ) @@ -115,7 +115,7 @@ async def test_bedrock_guardrails_block_messages_api(): mock_user_api_key_dict = UserAPIKeyAuth() guardrail = BedrockGuardrail( - guardrailIdentifier="ff6ujrregl1q", + guardrailIdentifier="4w3d1di3snt5", guardrailVersion="DRAFT", ) @@ -166,7 +166,7 @@ async def test_bedrock_guardrails_block_responses_api(): mock_user_api_key_dict = UserAPIKeyAuth() guardrail = BedrockGuardrail( - guardrailIdentifier="ff6ujrregl1q", + guardrailIdentifier="4w3d1di3snt5", guardrailVersion="DRAFT", ) @@ -211,7 +211,7 @@ async def test_bedrock_guardrails_with_streaming(): ) guardrail = BedrockGuardrail( - guardrailIdentifier="ff6ujrregl1q", + guardrailIdentifier="4w3d1di3snt5", guardrailVersion="DRAFT", supported_event_hooks=[GuardrailEventHooks.post_call], guardrail_name="bedrock-post-guard", @@ -255,7 +255,7 @@ async def test_bedrock_guardrails_with_streaming_no_violation(): ) guardrail = BedrockGuardrail( - guardrailIdentifier="ff6ujrregl1q", + guardrailIdentifier="4w3d1di3snt5", guardrailVersion="DRAFT", supported_event_hooks=[GuardrailEventHooks.post_call], guardrail_name="bedrock-post-guard", @@ -299,7 +299,7 @@ async def test_bedrock_guardrails_streaming_request_body_mock(): # Create the guardrail guardrail = BedrockGuardrail( - guardrailIdentifier="wf0hkdb5x07f", + guardrailIdentifier="zgkmukebruil", guardrailVersion="DRAFT", supported_event_hooks=[GuardrailEventHooks.post_call], guardrail_name="bedrock-post-guard", @@ -382,7 +382,7 @@ async def test_bedrock_guardrail_aws_param_persistence(): from litellm.types.guardrails import GuardrailEventHooks guardrail = BedrockGuardrail( - guardrailIdentifier="wf0hkdb5x07f", + guardrailIdentifier="zgkmukebruil", guardrailVersion="DRAFT", aws_access_key_id="test-access-key", aws_secret_access_key="test-secret-key", diff --git a/tests/image_gen_tests/test_bedrock_image_gen_unit_tests.py b/tests/image_gen_tests/test_bedrock_image_gen_unit_tests.py index 36ae9e1df6..181691b730 100644 --- a/tests/image_gen_tests/test_bedrock_image_gen_unit_tests.py +++ b/tests/image_gen_tests/test_bedrock_image_gen_unit_tests.py @@ -1,3 +1,4 @@ +import json import logging import os import sys @@ -44,6 +45,9 @@ from litellm.llms.bedrock.image_generation.image_handler import ( ) from litellm.llms.bedrock.common_utils import BedrockError +# Base64 placeholder used for mocked Bedrock image responses (a 1x1 PNG). +_MOCK_BEDROCK_IMAGE_B64 = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==" + @pytest.mark.parametrize( "model,expected", @@ -528,17 +532,34 @@ def test_backward_compatibility_regular_nova_model(): def test_amazon_titan_image_gen(): - """Test Amazon Titan image generation with cost tracking.""" - from litellm import image_generation + """Test Amazon Titan image generation with cost tracking. + + The Bedrock CI account is not entitled to amazon.titan-image-generator, so + the network call is mocked and only the transform + cost-tracking path is + exercised. + """ + from litellm.llms.custom_httpx.http_handler import HTTPHandler # Use v2 as v1 has reached end of life model_id = "bedrock/amazon.titan-image-generator-v2:0" - response = litellm.image_generation( - model=model_id, - prompt="A serene mountain landscape at sunset with a lake reflection", - aws_region_name="us-east-1", - ) + mock_payload = {"images": [_MOCK_BEDROCK_IMAGE_B64]} + mock_response = MagicMock() + mock_response.status_code = 200 + mock_response.json.return_value = mock_payload + mock_response.text = json.dumps(mock_payload) + mock_response.headers = {} + + client = HTTPHandler() + with patch.object(client, "post", return_value=mock_response): + response = litellm.image_generation( + model=model_id, + prompt="A serene mountain landscape at sunset with a lake reflection", + aws_region_name="us-east-1", + aws_access_key_id="fake-access-key-id", + aws_secret_access_key="fake-secret-access-key", + client=client, + ) print(f"response cost: {response._hidden_params['response_cost']}") diff --git a/tests/image_gen_tests/test_image_generation.py b/tests/image_gen_tests/test_image_generation.py index 873777189c..23a94ef389 100644 --- a/tests/image_gen_tests/test_image_generation.py +++ b/tests/image_gen_tests/test_image_generation.py @@ -7,7 +7,6 @@ import sys import traceback from unittest.mock import AsyncMock, MagicMock, patch - sys.path.insert( 0, os.path.abspath("../..") ) # Adds the parent directory to the system path @@ -136,6 +135,51 @@ class TestVertexAIGeminiImageGeneration(BaseImageGenTest): } +# Base64 placeholder used for mocked Bedrock image responses (a 1x1 PNG). +_MOCK_BEDROCK_IMAGE_B64 = "iVBORw0KGgoAAAANSUhEUgAAAAEAAAABCAQAAAC1HAwCAAAAC0lEQVR42mNk+M9QDwADhgGAWjR9awAAAABJRU5ErkJggg==" + + +async def _assert_mocked_bedrock_image_generation(call_args: dict) -> None: + """Run ``aimage_generation`` with the Bedrock HTTP call mocked. + + The CI account is not entitled to Nova Canvas, so the network call is + replaced with a canned Bedrock response. This keeps the request transform, + response transform, and cost-tracking path under test without live access. + """ + mock_payload = {"images": [_MOCK_BEDROCK_IMAGE_B64]} + mock_response = MagicMock() + mock_response.status_code = 200 + mock_response.json.return_value = mock_payload + mock_response.text = json.dumps(mock_payload) + mock_response.headers = {} + + custom_logger = TestCustomLogger() + litellm.logging_callback_manager._reset_all_callbacks() + litellm.callbacks = [custom_logger] + + with patch( + "litellm.llms.custom_httpx.http_handler.AsyncHTTPHandler.post", + new_callable=AsyncMock, + return_value=mock_response, + ): + response = await litellm.aimage_generation( + **call_args, + prompt="A image of a otter", + aws_access_key_id="fake-access-key-id", + aws_secret_access_key="fake-secret-access-key", + ) + + await asyncio.sleep(1) + + assert custom_logger.standard_logging_payload is not None + assert custom_logger.standard_logging_payload["response_cost"] is not None + assert custom_logger.standard_logging_payload["response_cost"] > 0 + assert response.data is not None + for d in response.data: + assert isinstance(d, Image) + assert d.b64_json is not None or d.url is not None + + class TestBedrockNovaCanvasTextToImage(BaseImageGenTest): def get_base_image_generation_call_args(self) -> dict: litellm.in_memory_llm_clients_cache = InMemoryCache() @@ -148,6 +192,12 @@ class TestBedrockNovaCanvasTextToImage(BaseImageGenTest): "aws_region_name": "us-east-1", } + @pytest.mark.asyncio(scope="module") + async def test_basic_image_generation(self): + await _assert_mocked_bedrock_image_generation( + self.get_base_image_generation_call_args() + ) + class TestBedrockNovaCanvasColorGuidedGeneration(BaseImageGenTest): def get_base_image_generation_call_args(self) -> dict: @@ -162,6 +212,12 @@ class TestBedrockNovaCanvasColorGuidedGeneration(BaseImageGenTest): "aws_region_name": "us-east-1", } + @pytest.mark.asyncio(scope="module") + async def test_basic_image_generation(self): + await _assert_mocked_bedrock_image_generation( + self.get_base_image_generation_call_args() + ) + class TestOpenAIGPTImage1(BaseImageGenTest): def get_base_image_generation_call_args(self) -> dict: diff --git a/tests/litellm_utils_tests/test_litellm_overhead.py b/tests/litellm_utils_tests/test_litellm_overhead.py index 3a428e9d58..60ee849f8e 100644 --- a/tests/litellm_utils_tests/test_litellm_overhead.py +++ b/tests/litellm_utils_tests/test_litellm_overhead.py @@ -82,7 +82,7 @@ async def _vertex_ai_mocks(): "bedrock/mistral.mistral-7b-instruct-v0:2", "openai/gpt-4o", "openai/self_hosted", - "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0", + "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0", "vertex_ai/gemini-1.5-flash", ], ) @@ -147,7 +147,7 @@ async def test_litellm_overhead_non_streaming(model): [ "bedrock/mistral.mistral-7b-instruct-v0:2", "openai/gpt-4o", - "bedrock/anthropic.claude-3-5-haiku-20241022-v1:0", + "bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0", "openai/self_hosted", ], ) diff --git a/tests/llm_translation/reasoning_effort_grid/grid_spec.py b/tests/llm_translation/reasoning_effort_grid/grid_spec.py index ed5346dad7..993643e0fc 100644 --- a/tests/llm_translation/reasoning_effort_grid/grid_spec.py +++ b/tests/llm_translation/reasoning_effort_grid/grid_spec.py @@ -1,7 +1,6 @@ from dataclasses import dataclass, field from typing import Dict, FrozenSet, List, Optional, Tuple - OMIT = object() @@ -22,6 +21,7 @@ class ModelEntry: extra_params: Tuple[Tuple[str, str], ...] = field(default_factory=tuple) required_env: FrozenSet[str] = field(default_factory=frozenset) caps: FrozenSet[str] = field(default_factory=frozenset) + fail_reason: Optional[str] = None def params(self) -> Dict[str, str]: return dict(self.extra_params) @@ -205,6 +205,12 @@ BEDROCK_CONVERSE_MODELS: Tuple[ModelEntry, ...] = ( extra_params=(("aws_region_name", "us-east-1"),), required_env=_BEDROCK_REQ, caps=_CAPS_OPUS_4_7, + fail_reason=( + "claude-opus-4-7 is not entitled on the Bedrock CI account " + "941277531214 (model access requires an AWS Sales request, not " + "self-serve); this cell fails on purpose so it stays loud in CI — " + "remove this fail_reason once access is granted" + ), ), ModelEntry( alias="bedrock-claude-opus-4-6", diff --git a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py index 28e2e402d6..e0b6290ad7 100644 --- a/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py +++ b/tests/llm_translation/reasoning_effort_grid/test_reasoning_effort_grid.py @@ -15,7 +15,6 @@ from .grid_spec import ( all_cells, ) - _PROMPT_MESSAGES: List[Dict[str, str]] = [ {"role": "user", "content": "Step by step, calculate 47 * 53. Show your work."} ] @@ -168,6 +167,9 @@ async def test_reasoning_effort_grid( if skip_reason: pytest.skip(skip_reason) + if model.fail_reason: + pytest.xfail(model.fail_reason) + if route_name == "bedrock_invoke_messages": status, exc = await _call_messages(model, effort) else: diff --git a/tests/llm_translation/test_bedrock_agentcore.py b/tests/llm_translation/test_bedrock_agentcore.py index 40774cf3d6..95a814e97e 100644 --- a/tests/llm_translation/test_bedrock_agentcore.py +++ b/tests/llm_translation/test_bedrock_agentcore.py @@ -19,8 +19,8 @@ import httpx @pytest.mark.parametrize( "model", [ - "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_13sf6-cALnp38iZD", # non-streaming invocation - "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", # streaming invocation + "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_13sf6-4046UzHSwy", # non-streaming invocation + "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", # streaming invocation ], ) def test_bedrock_agentcore_basic(model): @@ -44,7 +44,7 @@ def test_bedrock_agentcore_basic(model): @pytest.mark.parametrize( "model", [ - "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_13sf6-cALnp38iZD", # streaming invocation + "bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_13sf6-4046UzHSwy", # streaming invocation ], ) async def test_bedrock_agentcore_with_streaming(model): @@ -54,7 +54,7 @@ async def test_bedrock_agentcore_with_streaming(model): print("running streming test for model=", model) # litellm._turn_on_debug() response = await litellm.acompletion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -82,7 +82,7 @@ def test_bedrock_agentcore_with_custom_params(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -105,7 +105,7 @@ def test_bedrock_agentcore_with_custom_params(): url = call_kwargs["url"] print(f"URL: {url}") assert ( - "/runtimes/arn%3Aaws%3Abedrock-agentcore%3Aus-west-2%3A888602223428%3Aruntime%2Fhosted_agent_r9jvp-3ySZuRHjLC/invocations" + "/runtimes/arn%3Aaws%3Abedrock-agentcore%3Aus-west-2%3A941277531214%3Aruntime%2Fhosted_agent_r9jvp-Rq79QFC2fp/invocations" in url ) assert "qualifier=DEFAULT" in url @@ -150,7 +150,7 @@ def test_bedrock_agentcore_with_runtime_user_id(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -189,7 +189,7 @@ def test_bedrock_agentcore_with_session_and_user(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -234,7 +234,7 @@ def test_bedrock_agentcore_with_api_key_bearer_token(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -282,7 +282,7 @@ def test_bedrock_agentcore_with_all_parameters(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -350,7 +350,7 @@ def test_bedrock_agentcore_without_api_key_uses_sigv4(): with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", @@ -625,7 +625,7 @@ def test_agentcore_synchronous_non_streaming_response(): with patch.object(client, "post", return_value=mock_response) as mock_post: # Make a synchronous (non-streaming) completion call response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/hosted_agent_r9jvp-3ySZuRHjLC", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/hosted_agent_r9jvp-Rq79QFC2fp", messages=[ { "role": "user", diff --git a/tests/llm_translation/test_bedrock_completion.py b/tests/llm_translation/test_bedrock_completion.py index 15f950224d..69c87d1d23 100644 --- a/tests/llm_translation/test_bedrock_completion.py +++ b/tests/llm_translation/test_bedrock_completion.py @@ -115,7 +115,7 @@ def test_completion_bedrock_guardrails(streaming): ], max_tokens=10, guardrailConfig={ - "guardrailIdentifier": "ff6ujrregl1q", + "guardrailIdentifier": "4w3d1di3snt5", "guardrailVersion": "DRAFT", "trace": "enabled", }, @@ -144,7 +144,7 @@ def test_completion_bedrock_guardrails(streaming): stream=True, max_tokens=10, guardrailConfig={ - "guardrailIdentifier": "ff6ujrregl1q", + "guardrailIdentifier": "4w3d1di3snt5", "guardrailVersion": "DRAFT", "trace": "enabled", }, @@ -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", @@ -737,7 +737,7 @@ def test_bedrock_ptu(): from openai.types.chat import ChatCompletion model_id = ( - "arn:aws:bedrock:us-west-2:888602223428:provisioned-model/8fxff74qyhs3" + "arn:aws:bedrock:us-west-2:941277531214:provisioned-model/8fxff74qyhs3" ) try: response = litellm.completion( @@ -752,7 +752,7 @@ def test_bedrock_ptu(): assert "url" in mock_client_post.call_args.kwargs assert ( mock_client_post.call_args.kwargs["url"] - == "https://bedrock-runtime.us-west-2.amazonaws.com/model/arn%3Aaws%3Abedrock%3Aus-west-2%3A888602223428%3Aprovisioned-model%2F8fxff74qyhs3/converse" + == "https://bedrock-runtime.us-west-2.amazonaws.com/model/arn%3Aaws%3Abedrock%3Aus-west-2%3A941277531214%3Aprovisioned-model%2F8fxff74qyhs3/converse" ) mock_client_post.assert_called_once() @@ -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 cce6d33e79..c7abdb5f49 100644 --- a/tests/local_testing/test_completion.py +++ b/tests/local_testing/test_completion.py @@ -299,7 +299,10 @@ 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 @@ -385,7 +388,7 @@ 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"), @@ -1578,7 +1581,7 @@ 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"), ], ) @@ -1666,15 +1669,13 @@ def custom_callback( ################################################# - print( - f""" + print(f""" Model: {model}, Messages: {messages}, User: {user}, Seed: {kwargs["seed"]}, temperature: {kwargs["temperature"]}, - """ - ) + """) assert kwargs["user"] == "ishaans app" assert kwargs["model"] == "gpt-3.5-turbo-1106" @@ -2699,7 +2700,7 @@ def test_bedrock_deepseek_custom_prompt_dict(): def test_bedrock_deepseek_known_tokenizer_config(monkeypatch): model = ( - "deepseek_r1/arn:aws:bedrock:us-west-2:888602223428:imported-model/bnnr6463ejgf" + "deepseek_r1/arn:aws:bedrock:us-west-2:941277531214:imported-model/bnnr6463ejgf" ) from litellm.llms.custom_httpx.http_handler import HTTPHandler from unittest.mock import Mock @@ -2914,8 +2915,8 @@ def response_format_tests(response: litellm.ModelResponse): "model", [ "bedrock/mistral.mistral-large-2407-v1:0", - "bedrock/cohere.command-r-plus-v1:0", - "anthropic.claude-3-sonnet-20240229-v1:0", + "us.anthropic.claude-haiku-4-5-20251001-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_call_parsing.py b/tests/local_testing/test_function_call_parsing.py index f9582fcc57..2453571f1c 100644 --- a/tests/local_testing/test_function_call_parsing.py +++ b/tests/local_testing/test_function_call_parsing.py @@ -142,7 +142,8 @@ def trade(model_name: str) -> List[Trade]: # type: ignore @pytest.mark.parametrize( - "model", ["claude-haiku-4-5-20251001", "anthropic.claude-3-haiku-20240307-v1:0"] + "model", + ["claude-haiku-4-5-20251001", "us.anthropic.claude-haiku-4-5-20251001-v1:0"], ) @pytest.mark.flaky(retries=6, delay=10) def test_function_call_parsing(model): diff --git a/tests/local_testing/test_function_calling.py b/tests/local_testing/test_function_calling.py index 3c7e004b62..1cad7d1421 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) @@ -267,7 +267,6 @@ def test_aaparallel_function_call_with_anthropic_thinking(model): from litellm.types.utils import ChatCompletionMessageToolCall, Function, Message - _PARALLEL_TOOL_HISTORY_MESSAGES = [ { "role": "user", @@ -303,7 +302,7 @@ _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 +313,7 @@ _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 +578,7 @@ 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_sagemaker.py b/tests/local_testing/test_sagemaker.py index d4c5a5a857..fdc8347c36 100644 --- a/tests/local_testing/test_sagemaker.py +++ b/tests/local_testing/test_sagemaker.py @@ -57,7 +57,7 @@ async def test_completion_sagemaker(sync_mode): print("testing sagemaker") if sync_mode is True: response = litellm.completion( - model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + model="sagemaker/litellm-ci-textgen", messages=[ {"role": "user", "content": "hi"}, ], @@ -67,7 +67,7 @@ async def test_completion_sagemaker(sync_mode): ) else: response = await litellm.acompletion( - model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + model="sagemaker/litellm-ci-textgen", messages=[ {"role": "user", "content": "hi"}, ], @@ -158,7 +158,7 @@ async def test_completion_sagemaker_messages_api(sync_mode): "model", [ # "sagemaker_chat/huggingface-pytorch-tgi-inference-2024-08-23-15-48-59-245", - "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "sagemaker/litellm-ci-textgen", ], ) # @pytest.mark.flaky(retries=3, delay=1) @@ -218,7 +218,7 @@ async def test_completion_sagemaker_stream(sync_mode, model): "model", [ # "sagemaker_chat/huggingface-pytorch-tgi-inference-2024-08-23-15-48-59-245", - "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "sagemaker/litellm-ci-textgen", ], ) async def test_completion_sagemaker_streaming_bad_request(sync_mode, model): @@ -256,7 +256,7 @@ async def test_acompletion_sagemaker_non_stream(): "id": "cmpl-mockid", "object": "text_completion", "created": 1629800000, - "model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "model": "sagemaker/litellm-ci-textgen", "choices": [ { "text": "This is a mock response from SageMaker.", @@ -282,7 +282,7 @@ async def test_acompletion_sagemaker_non_stream(): ) as mock_post: # Act: Call the litellm.acompletion function response = await litellm.acompletion( - model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + model="sagemaker/litellm-ci-textgen", messages=[ {"role": "user", "content": "hi"}, ], @@ -302,7 +302,7 @@ async def test_acompletion_sagemaker_non_stream(): assert args_to_sagemaker == expected_payload assert ( kwargs["url"] - == "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations" + == "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/litellm-ci-textgen/invocations" ) @@ -316,7 +316,7 @@ async def test_completion_sagemaker_non_stream(): "id": "cmpl-mockid", "object": "text_completion", "created": 1629800000, - "model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "model": "sagemaker/litellm-ci-textgen", "choices": [ { "text": "This is a mock response from SageMaker.", @@ -342,7 +342,7 @@ async def test_completion_sagemaker_non_stream(): ) as mock_post: # Act: Call the litellm.acompletion function response = litellm.completion( - model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + model="sagemaker/litellm-ci-textgen", messages=[ {"role": "user", "content": "hi"}, ], @@ -362,7 +362,7 @@ async def test_completion_sagemaker_non_stream(): assert args_to_sagemaker == expected_payload assert ( kwargs["url"] - == "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations" + == "https://runtime.sagemaker.us-west-2.amazonaws.com/endpoints/litellm-ci-textgen/invocations" ) @@ -377,7 +377,7 @@ async def test_completion_sagemaker_prompt_template_non_stream(): "id": "cmpl-mockid", "object": "text_completion", "created": 1629800000, - "model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "model": "sagemaker/litellm-ci-textgen", "choices": [ { "text": "This is a mock response from SageMaker.", @@ -433,7 +433,7 @@ async def test_completion_sagemaker_non_stream_with_aws_params(): "id": "cmpl-mockid", "object": "text_completion", "created": 1629800000, - "model": "sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + "model": "sagemaker/litellm-ci-textgen", "choices": [ { "text": "This is a mock response from SageMaker.", @@ -459,7 +459,7 @@ async def test_completion_sagemaker_non_stream_with_aws_params(): ) as mock_post: # Act: Call the litellm.acompletion function response = litellm.completion( - model="sagemaker/jumpstart-dft-hf-textgeneration1-mp-20240815-185614", + model="sagemaker/litellm-ci-textgen", messages=[ {"role": "user", "content": "hi"}, ], @@ -482,5 +482,5 @@ async def test_completion_sagemaker_non_stream_with_aws_params(): assert args_to_sagemaker == expected_payload assert ( kwargs["url"] - == "https://runtime.sagemaker.us-west-5.amazonaws.com/endpoints/jumpstart-dft-hf-textgeneration1-mp-20240815-185614/invocations" + == "https://runtime.sagemaker.us-west-5.amazonaws.com/endpoints/litellm-ci-textgen/invocations" ) diff --git a/tests/local_testing/test_streaming.py b/tests/local_testing/test_streaming.py index 10f351714e..eb153404a4 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, @@ -1276,7 +1276,7 @@ def test_bedrock_claude_3_streaming(): "model", [ "claude-haiku-4-5-20251001", - "cohere.command-r-plus-v1:0", # bedrock + "us.anthropic.claude-haiku-4-5-20251001-v1:0", # bedrock "gpt-3.5-turbo", ], ) @@ -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", ], ) diff --git a/tests/logging_callback_tests/test_amazing_s3_logs.py b/tests/logging_callback_tests/test_amazing_s3_logs.py index dab2a0cc0b..e6291a9404 100644 --- a/tests/logging_callback_tests/test_amazing_s3_logs.py +++ b/tests/logging_callback_tests/test_amazing_s3_logs.py @@ -27,7 +27,7 @@ async def test_basic_s3_logging(sync_mode, streaming): verbose_logger.setLevel(level=logging.DEBUG) litellm.success_callback = ["s3"] litellm.s3_callback_params = { - "s3_bucket_name": "load-testing-oct", + "s3_bucket_name": "load-testing-oct-941277531214", "s3_aws_secret_access_key": "os.environ/AWS_SECRET_ACCESS_KEY", "s3_aws_access_key_id": "os.environ/AWS_ACCESS_KEY_ID", "s3_region_name": "us-west-2", @@ -64,14 +64,14 @@ async def test_basic_s3_logging(sync_mode, streaming): await asyncio.sleep(2) print(f"response: {response}") - total_objects, all_s3_keys = list_all_s3_objects("load-testing-oct") + total_objects, all_s3_keys = list_all_s3_objects("load-testing-oct-941277531214") # assert that atlest one key has response.id in it assert any(response_id in key for key in all_s3_keys) s3 = boto3.client("s3") # delete all objects for key in all_s3_keys: - s3.delete_object(Bucket="load-testing-oct", Key=key) + s3.delete_object(Bucket="load-testing-oct-941277531214", Key=key) @pytest.mark.asyncio @@ -82,7 +82,7 @@ async def test_basic_s3_v2_logging(streaming): from litellm.integrations.s3_v2 import S3Logger litellm.s3_callback_params = { - "s3_bucket_name": "load-testing-oct", + "s3_bucket_name": "load-testing-oct-941277531214", "s3_aws_secret_access_key": "test-secret", "s3_aws_access_key_id": "test-key", "s3_region_name": "us-west-2", diff --git a/tests/logging_callback_tests/test_bedrock_knowledgebase_hook.py b/tests/logging_callback_tests/test_bedrock_knowledgebase_hook.py index d6d0652ed7..0d4405094b 100644 --- a/tests/logging_callback_tests/test_bedrock_knowledgebase_hook.py +++ b/tests/logging_callback_tests/test_bedrock_knowledgebase_hook.py @@ -2,7 +2,6 @@ import io import os import sys - sys.path.insert(0, os.path.abspath("../..")) import asyncio @@ -67,7 +66,7 @@ def setup_vector_store_registry(): litellm.vector_store_registry = VectorStoreRegistry( vector_stores=[ LiteLLM_ManagedVectorStore( - vector_store_id="T37J8R4WTM", custom_llm_provider="bedrock" + vector_store_id="LCYXFBR2TU", custom_llm_provider="bedrock" ) ] ) @@ -111,7 +110,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_with_completion( response = await litellm.acompletion( model="anthropic/claude-3.5-sonnet", messages=[{"role": "user", "content": "what is litellm?"}], - vector_store_ids=["T37J8R4WTM"], + vector_store_ids=["LCYXFBR2TU"], client=client, ) except Exception as e: @@ -152,7 +151,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_with_llm_api_call( response = await litellm.acompletion( model="bedrock/us.anthropic.claude-haiku-4-5-20251001-v1:0", messages=[{"role": "user", "content": "what is litellm?"}], - vector_store_ids=["T37J8R4WTM"], + vector_store_ids=["LCYXFBR2TU"], client=async_client, ) print("OPENAI RESPONSE:", json.dumps(dict(response), indent=4, default=str)) @@ -196,7 +195,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_with_llm_api_call_streaming( response = await litellm.acompletion( model=f"anthropic/{os.environ.get('CI_CD_DEFAULT_ANTHROPIC_MODEL', 'claude-haiku-4-5-20251001')}", messages=[{"role": "user", "content": "what is litellm?"}], - vector_store_ids=["T37J8R4WTM"], + vector_store_ids=["LCYXFBR2TU"], stream=True, client=async_client, ) @@ -255,7 +254,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_with_llm_api_call_with_tools( model=f"anthropic/{os.environ.get('CI_CD_DEFAULT_ANTHROPIC_MODEL', 'claude-haiku-4-5-20251001')}", messages=[{"role": "user", "content": "what is litellm?"}], max_tokens=10, - tools=[{"type": "file_search", "vector_store_ids": ["T37J8R4WTM"]}], + tools=[{"type": "file_search", "vector_store_ids": ["LCYXFBR2TU"]}], ) assert response is not None @@ -279,7 +278,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_with_llm_api_call_with_tools_ tools=[ { "type": "file_search", - "vector_store_ids": ["T37J8R4WTM"], + "vector_store_ids": ["LCYXFBR2TU"], "filters": { "key": "user_id", "value": "fake-user-id", @@ -387,7 +386,7 @@ async def test_bedrock_kb_request_body_has_transformed_filters( tools=[ { "type": "file_search", - "vector_store_ids": ["T37J8R4WTM"], + "vector_store_ids": ["LCYXFBR2TU"], "filters": { "key": "user_id", "value": "fake-user-id", @@ -461,7 +460,7 @@ async def test_openai_with_knowledge_base_mock_openai(setup_vector_store_registr await litellm.acompletion( model="gpt-5.5", messages=[{"role": "user", "content": "what is litellm?"}], - vector_store_ids=["T37J8R4WTM"], + vector_store_ids=["LCYXFBR2TU"], client=client, ) except Exception as e: @@ -537,7 +536,7 @@ async def test_openai_with_vector_store_ids_in_tool_call_mock_openai( await litellm.acompletion( model="gpt-5.5", messages=[{"role": "user", "content": "what is litellm?"}], - tools=[{"type": "file_search", "vector_store_ids": ["T37J8R4WTM"]}], + tools=[{"type": "file_search", "vector_store_ids": ["LCYXFBR2TU"]}], client=client, ) except Exception as e: @@ -611,7 +610,7 @@ async def test_openai_with_mixed_tool_call_mock_openai(setup_vector_store_regist model="gpt-5.5", messages=[{"role": "user", "content": "what is litellm?"}], tools=[ - {"type": "file_search", "vector_store_ids": ["T37J8R4WTM"]}, + {"type": "file_search", "vector_store_ids": ["LCYXFBR2TU"]}, {"type": "file_search", "vector_store_ids": ["unknownVS"]}, ], client=client, @@ -645,7 +644,7 @@ async def test_openai_with_mixed_tool_call_mock_openai(setup_vector_store_regist # model="gpt-5.5", # messages=[{"role": "user", "content": "what is litellm?"}], # vector_store_ids = [ -# "T37J8R4WTM" +# "LCYXFBR2TU" # ], # ) @@ -667,7 +666,7 @@ async def test_openai_with_mixed_tool_call_mock_openai(setup_vector_store_regist # # expect the vector store request metadata object to have the correct values # vector_store_request_metadata = standard_logging_vector_store_request_metadata[0] -# assert vector_store_request_metadata.get("vector_store_id") == "T37J8R4WTM" +# assert vector_store_request_metadata.get("vector_store_id") == "LCYXFBR2TU" # assert vector_store_request_metadata.get("query") == "what is litellm?" # assert vector_store_request_metadata.get("custom_llm_provider") == "bedrock" @@ -723,7 +722,7 @@ async def test_e2e_bedrock_knowledgebase_retrieval_without_vector_store_registry response = await litellm.acompletion( model="anthropic/claude-3.5-sonnet", messages=[{"role": "user", "content": "what is litellm?"}], - vector_store_ids=["T37J8R4WTM"], + vector_store_ids=["LCYXFBR2TU"], client=client, ) except Exception as e: diff --git a/tests/test_litellm/llms/bedrock/chat/agentcore/test_agentcore_transformation.py b/tests/test_litellm/llms/bedrock/chat/agentcore/test_agentcore_transformation.py index 64b43b15dc..3287061d37 100644 --- a/tests/test_litellm/llms/bedrock/chat/agentcore/test_agentcore_transformation.py +++ b/tests/test_litellm/llms/bedrock/chat/agentcore/test_agentcore_transformation.py @@ -76,7 +76,7 @@ class TestAgentCoreAcceptHeader: with patch.object(client, "post", return_value=MagicMock()) as mock_post: try: litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/test_runtime", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/test_runtime", messages=[{"role": "user", "content": "test"}], api_key="test-jwt-token", client=client, @@ -281,7 +281,7 @@ class TestAgentCoreStreamingJsonFallback: with patch.object(client, "post", return_value=mock_response): response = litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/test_agent", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/test_agent", messages=[{"role": "user", "content": "test"}], stream=True, client=client, @@ -318,7 +318,7 @@ class TestAgentCoreStreamingJsonFallback: client, "post", new_callable=AsyncMock, return_value=mock_response ): response = await litellm.acompletion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/test_agent", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/test_agent", messages=[{"role": "user", "content": "test"}], stream=True, client=client, @@ -353,7 +353,7 @@ class TestAgentCoreStreamingJsonFallback: Exception, match="Failed to read/parse JSON response body" ): litellm.completion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/test_agent", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/test_agent", messages=[{"role": "user", "content": "test"}], stream=True, client=client, @@ -383,7 +383,7 @@ class TestAgentCoreStreamingJsonFallback: Exception, match="Failed to read/parse JSON response body" ): await litellm.acompletion( - model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:888602223428:runtime/test_agent", + model="bedrock/agentcore/arn:aws:bedrock-agentcore:us-west-2:941277531214:runtime/test_agent", messages=[{"role": "user", "content": "test"}], stream=True, client=client, diff --git a/tests/test_openai_endpoints.py b/tests/test_openai_endpoints.py index e898b88a55..29875a0441 100644 --- a/tests/test_openai_endpoints.py +++ b/tests/test_openai_endpoints.py @@ -446,7 +446,7 @@ async def test_chat_completion_anthropic_structured_output(): client = AsyncOpenAI(api_key="sk-1234", base_url="http://0.0.0.0:4000") res = await client.beta.chat.completions.parse( - model="bedrock/us.anthropic.claude-3-sonnet-20240229-v1:0", + model="bedrock/us.anthropic.claude-sonnet-4-5-20250929-v1:0", messages=messages, response_format=EventsList, timeout=60, diff --git a/tests/vector_store_tests/test_bedrock_vector_store.py b/tests/vector_store_tests/test_bedrock_vector_store.py index d8af1c7188..47e73e61c5 100644 --- a/tests/vector_store_tests/test_bedrock_vector_store.py +++ b/tests/vector_store_tests/test_bedrock_vector_store.py @@ -22,7 +22,7 @@ class TestBedrockVectorStore(BaseVectorStoreTest): def get_base_request_args(self): return { - "vector_store_id": "T37J8R4WTM", + "vector_store_id": "LCYXFBR2TU", "custom_llm_provider": "bedrock", "query": "what happens after we add a model", } @@ -106,7 +106,7 @@ async def test_bedrock_search_with_router(): _router = Router(model_list=[]) search_response = await _router.avector_store_search( query="what happens after we add a model", - vector_store_id="T37J8R4WTM", + vector_store_id="LCYXFBR2TU", custom_llm_provider="bedrock", ) print(search_response) @@ -150,7 +150,7 @@ async def test_bedrock_search_with_credentials_managed_registry(): # Create vector store with credential reference vector_store = LiteLLM_ManagedVectorStore( - vector_store_id="T37J8R4WTM", + vector_store_id="LCYXFBR2TU", custom_llm_provider="bedrock", created_at=datetime.now(timezone.utc), updated_at=datetime.now(timezone.utc), @@ -162,7 +162,7 @@ async def test_bedrock_search_with_credentials_managed_registry(): litellm.vector_store_registry = registry # Verify credentials can be retrieved from registry - retrieved_credentials = registry.get_credentials_for_vector_store("T37J8R4WTM") + retrieved_credentials = registry.get_credentials_for_vector_store("LCYXFBR2TU") assert retrieved_credentials, "Should retrieve credentials from registry" assert retrieved_credentials.get("aws_access_key_id") == "test_access_key" assert retrieved_credentials.get("aws_secret_access_key") == "test_secret_key" @@ -194,7 +194,7 @@ async def test_bedrock_search_with_credentials_managed_registry(): search_response = await _router.avector_store_search( query="what happens after we add a model", - vector_store_id="T37J8R4WTM", + vector_store_id="LCYXFBR2TU", custom_llm_provider="bedrock", ) @@ -203,7 +203,7 @@ async def test_bedrock_search_with_credentials_managed_registry(): call_kwargs = mock_handler.call_args[1] # Verify that the credential accessor was called with the correct vector store ID - mock_get_creds.assert_called_with("T37J8R4WTM") + mock_get_creds.assert_called_with("LCYXFBR2TU") # Verify the credentials were injected into the search call litellm_params = call_kwargs.get("litellm_params", {}) @@ -224,7 +224,7 @@ async def test_bedrock_search_with_credentials_managed_registry(): assert search_response["data"][0]["id"] == "test_result" print( - f"✅ Test passed: Credential accessor was called with vector store ID: T37J8R4WTM" + f"✅ Test passed: Credential accessor was called with vector store ID: LCYXFBR2TU" ) print(f"✅ Retrieved credentials: {retrieved_credentials}") print(f"✅ Credentials were injected into search call")