Merge branch 'main' into fix/nvidia-safety-provider-endpoint-4189

src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/distributions/ci-tests/run.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/distributions/starter-gpu/run.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/distributions/starter/run-with-postgres-store.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/distributions/starter/run.yaml

@@ -47,7 +47,7 @@ providers:
   - provider_id: bedrock
     provider_type: remote::bedrock
     config:
-      api_key: ${env.AWS_BEDROCK_API_KEY:=}
+      api_key: ${env.AWS_BEARER_TOKEN_BEDROCK:=}
       region_name: ${env.AWS_DEFAULT_REGION:=us-east-2}
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia

src/llama_stack/providers/remote/inference/bedrock/bedrock.py

@@ -37,7 +37,7 @@ class BedrockInferenceAdapter(OpenAIMixin):
     """
 
     config: BedrockConfig
-    provider_data_api_key_field: str = "aws_bedrock_api_key"
+    provider_data_api_key_field: str = "aws_bearer_token_bedrock"
 
     def get_base_url(self) -> str:
         """Get base URL for OpenAI client."""
@@ -111,7 +111,7 @@ class BedrockInferenceAdapter(OpenAIMixin):
                 logger.error(f"AWS Bedrock authentication token expired: {error_msg}")
                 raise ValueError(
                     "AWS Bedrock authentication failed: Bearer token has expired. "
-                    "The AWS_BEDROCK_API_KEY environment variable contains an expired pre-signed URL. "
+                    "The AWS_BEARER_TOKEN_BEDROCK environment variable contains an expired pre-signed URL. "
                     "Please refresh your token by generating a new pre-signed URL with AWS credentials. "
                     "Refer to AWS Bedrock documentation for details on OpenAI-compatible endpoints."
                 ) from e

src/llama_stack/providers/remote/inference/bedrock/config.py

@@ -12,9 +12,9 @@ from llama_stack.providers.utils.inference.model_registry import RemoteInference
 
 
 class BedrockProviderDataValidator(BaseModel):
-    aws_bedrock_api_key: str | None = Field(
+    aws_bearer_token_bedrock: str | None = Field(
         default=None,
-        description="API key for Amazon Bedrock",
+        description="API Key (Bearer token) for Amazon Bedrock",
     )
 
 
@@ -27,6 +27,6 @@ class BedrockConfig(RemoteInferenceProviderConfig):
     @classmethod
     def sample_run_config(cls, **kwargs):
         return {
-            "api_key": "${env.AWS_BEDROCK_API_KEY:=}",
+            "api_key": "${env.AWS_BEARER_TOKEN_BEDROCK:=}",
             "region_name": "${env.AWS_DEFAULT_REGION:=us-east-2}",
         }

src/llama_stack/providers/remote/inference/vertexai/vertexai.py

@@ -51,4 +51,4 @@ class VertexAIInferenceAdapter(OpenAIMixin):
 
         :return: An iterable of model IDs
         """
-        return ["vertexai/gemini-2.0-flash", "vertexai/gemini-2.5-flash", "vertexai/gemini-2.5-pro"]
+        return ["google/gemini-2.0-flash", "google/gemini-2.5-flash", "google/gemini-2.5-pro"]