mirror of
https://github.com/BerriAI/litellm.git
synced 2026-11-17 09:34:48 +00:00
fix(bedrock): build the Responses endpoint from the region's partition suffix
get_complete_url hardcoded amazonaws.com in an f-string, so every non-commercial partition got the wrong host: cn-north-1 resolved to amazonaws.com instead of amazonaws.com.cn, and GovCloud/ISO regions were wrong the same way. Defer to BaseAWSLLM._select_default_endpoint_url, which this config already inherits and which resolves the suffix per partition. test_no_fstring_hardcodes_the_commercial_dns_suffix scans the whole tree, so it caught this even though it is not one of this PR's test files. Register the config in ENDPOINT_BUILDERS so the cn/GovCloud endpoint sweep covers this surface from now on rather than only the f-string guard. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
This commit is contained in:
parent
0d17346b67
commit
48cf730230
3 changed files with 11 additions and 3 deletions
|
|
@ -1,7 +1,7 @@
|
|||
"""Amazon Bedrock Runtime - native OpenAI Responses API.
|
||||
|
||||
AWS serves the OpenAI models on ``bedrock-runtime`` through an OpenAI-compatible
|
||||
surface at ``https://bedrock-runtime.{region}.amazonaws.com/openai/v1/responses``,
|
||||
surface at ``https://bedrock-runtime.{region}.{dns_suffix}/openai/v1/responses``,
|
||||
alongside Converse. Without this config the ``bedrock`` provider has no Responses
|
||||
config at all, so ``/v1/responses`` falls back to the Chat Completions bridge and
|
||||
the request is translated into Converse. A realistic Codex session does not
|
||||
|
|
@ -86,7 +86,11 @@ class BedrockOpenAIResponsesConfig(BaseAWSLLM, OpenAIResponsesAPIConfig):
|
|||
or litellm_params.get("aws_bedrock_runtime_endpoint")
|
||||
or get_secret_str("AWS_BEDROCK_RUNTIME_ENDPOINT")
|
||||
)
|
||||
host: Final = (override or f"https://bedrock-runtime.{region}.amazonaws.com").rstrip("/")
|
||||
# Partition-aware: bedrock-runtime is amazonaws.com.cn in China, and other
|
||||
# suffixes in GovCloud/ISO, so defer to the shared endpoint builder.
|
||||
host: Final = (
|
||||
override or self._select_default_endpoint_url(endpoint_type="runtime", aws_region_name=region)
|
||||
).rstrip("/")
|
||||
if host.endswith(BEDROCK_RUNTIME_OPENAI_RESPONSES_PATH):
|
||||
return host
|
||||
base: Final = next(
|
||||
|
|
|
|||
|
|
@ -59,7 +59,6 @@ _BEDROCK_MANTLE_SUPPORTED_SERVICE_TIERS: Final = frozenset({"auto", "default"})
|
|||
_BEDROCK_MANTLE_OPENAI_PATH_SUPPORTED_REASONING_SUMMARIES: Final = frozenset({"auto"})
|
||||
|
||||
|
||||
|
||||
class BedrockMantleResponsesAPIConfig(BedrockMantleAuthMixin, OpenAIResponsesAPIConfig):
|
||||
def __init__(
|
||||
self,
|
||||
|
|
|
|||
|
|
@ -21,6 +21,7 @@ from litellm.llms.bedrock.base_aws_llm import BaseAWSLLM
|
|||
from litellm.llms.bedrock.batches.transformation import BedrockBatchesConfig
|
||||
from litellm.llms.bedrock.chat.agentcore.transformation import AmazonAgentCoreConfig
|
||||
from litellm.llms.bedrock.common_utils import init_bedrock_client
|
||||
from litellm.llms.bedrock.responses.transformation import BedrockOpenAIResponsesConfig
|
||||
from litellm.llms.sagemaker.chat.transformation import SagemakerChatConfig
|
||||
|
||||
|
||||
|
|
@ -152,6 +153,10 @@ ENDPOINT_BUILDERS: Final = {
|
|||
litellm_params={},
|
||||
stream=True,
|
||||
),
|
||||
"bedrock_openai_responses": lambda region: BedrockOpenAIResponsesConfig().get_complete_url(
|
||||
api_base=None,
|
||||
litellm_params={"aws_region_name": region},
|
||||
),
|
||||
"s3_object_url": _s3_object_url,
|
||||
}
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Reference in a new issue