Merge branch 'main' into elasticsearch-integration

.github/CODEOWNERS

@@ -2,4 +2,4 @@
 
 # These owners will be the default owners for everything in
 # the repo. Unless a later match takes precedence,
-* @ashwinb @raghotham @ehhuang @leseb @bbrowning @mattf @franciscojavierarceo
+* @ashwinb @raghotham @ehhuang @leseb @bbrowning @mattf @franciscojavierarceo @cdoern

.github/workflows/integration-tests.yml

@@ -95,7 +95,7 @@ jobs:
 
       - name: Setup Node.js for TypeScript client tests
         if: ${{ matrix.client == 'server' }}
-        uses: actions/setup-node@39370e3970a6d050c480ffad4ff0ed4d3fdee5af # v4.1.0
+        uses: actions/setup-node@2028fbc5c25fe9cf00d9f06a71cc4710d4507903 # v6.0.0
         with:
           node-version: '20'
           cache: 'npm'

docs/docs/providers/inference/remote_bedrock.mdx

@@ -22,6 +22,6 @@ AWS Bedrock inference provider using OpenAI compatible endpoint.
 ## Sample Configuration
 
 ```yaml
-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/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"]

tests/unit/providers/inference/test_bedrock_adapter.py

@@ -40,8 +40,8 @@ def test_api_key_from_header_overrides_config():
     """Test API key from request header overrides config via client property"""
     config = BedrockConfig(api_key="config-key", region_name="us-east-1")
     adapter = BedrockInferenceAdapter(config=config)
-    adapter.provider_data_api_key_field = "aws_bedrock_api_key"
+    adapter.provider_data_api_key_field = "aws_bearer_token_bedrock"
-    adapter.get_request_provider_data = MagicMock(return_value=SimpleNamespace(aws_bedrock_api_key="header-key"))
+    adapter.get_request_provider_data = MagicMock(return_value=SimpleNamespace(aws_bearer_token_bedrock="header-key"))
 
     # The client property is where header override happens (in OpenAIMixin)
     assert adapter.client.api_key == "header-key"

tests/unit/providers/inference/test_bedrock_config.py

@@ -9,7 +9,7 @@ from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig
 
 def test_bedrock_config_defaults_no_env(monkeypatch):
     """Test BedrockConfig defaults when env vars are not set"""
-    monkeypatch.delenv("AWS_BEDROCK_API_KEY", raising=False)
+    monkeypatch.delenv("AWS_BEARER_TOKEN_BEDROCK", raising=False)
     monkeypatch.delenv("AWS_DEFAULT_REGION", raising=False)
     config = BedrockConfig()
     assert config.auth_credential is None
@@ -35,5 +35,5 @@ def test_bedrock_config_sample():
     sample = BedrockConfig.sample_run_config()
     assert "api_key" in sample
     assert "region_name" in sample
-    assert sample["api_key"] == "${env.AWS_BEDROCK_API_KEY:=}"
+    assert sample["api_key"] == "${env.AWS_BEARER_TOKEN_BEDROCK:=}"
     assert sample["region_name"] == "${env.AWS_DEFAULT_REGION:=us-east-2}"