From dc4665af179e83b8f93d5e3a004e5751761e55a5 Mon Sep 17 00:00:00 2001 From: Ken Dreyer Date: Fri, 21 Nov 2025 09:48:05 -0500 Subject: [PATCH 1/3] feat!: change bedrock bearer token env variable to match AWS docs & boto3 convention (#4152) Rename `AWS_BEDROCK_API_KEY` to `AWS_BEARER_TOKEN_BEDROCK` to align with the naming convention used in AWS Bedrock documentation and the AWS web console UI. This reduces confusion when developers compare LLS docs with AWS docs. Closes #4147 --- docs/docs/providers/inference/remote_bedrock.mdx | 2 +- .../distributions/ci-tests/run-with-postgres-store.yaml | 2 +- src/llama_stack/distributions/ci-tests/run.yaml | 2 +- .../distributions/starter-gpu/run-with-postgres-store.yaml | 2 +- src/llama_stack/distributions/starter-gpu/run.yaml | 2 +- .../distributions/starter/run-with-postgres-store.yaml | 2 +- src/llama_stack/distributions/starter/run.yaml | 2 +- .../providers/remote/inference/bedrock/bedrock.py | 4 ++-- .../providers/remote/inference/bedrock/config.py | 6 +++--- tests/unit/providers/inference/test_bedrock_adapter.py | 4 ++-- tests/unit/providers/inference/test_bedrock_config.py | 4 ++-- 11 files changed, 16 insertions(+), 16 deletions(-) diff --git a/docs/docs/providers/inference/remote_bedrock.mdx b/docs/docs/providers/inference/remote_bedrock.mdx index 86bef3000..0b36ea01a 100644 --- a/docs/docs/providers/inference/remote_bedrock.mdx +++ b/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} ``` diff --git a/src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml b/src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml index d942c23a4..7721138c7 100644 --- a/src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml +++ b/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 diff --git a/src/llama_stack/distributions/ci-tests/run.yaml b/src/llama_stack/distributions/ci-tests/run.yaml index 8b1cd2bb2..b791e1488 100644 --- a/src/llama_stack/distributions/ci-tests/run.yaml +++ b/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 diff --git a/src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml b/src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml index 75cc9d188..9c250c05a 100644 --- a/src/llama_stack/distributions/starter-gpu/run-with-postgres-store.yaml +++ b/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 diff --git a/src/llama_stack/distributions/starter-gpu/run.yaml b/src/llama_stack/distributions/starter-gpu/run.yaml index 09c7be5a1..65f9ae326 100644 --- a/src/llama_stack/distributions/starter-gpu/run.yaml +++ b/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 diff --git a/src/llama_stack/distributions/starter/run-with-postgres-store.yaml b/src/llama_stack/distributions/starter/run-with-postgres-store.yaml index f59c809d2..3314bb9e9 100644 --- a/src/llama_stack/distributions/starter/run-with-postgres-store.yaml +++ b/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 diff --git a/src/llama_stack/distributions/starter/run.yaml b/src/llama_stack/distributions/starter/run.yaml index 435bb22a7..e88539e6a 100644 --- a/src/llama_stack/distributions/starter/run.yaml +++ b/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 diff --git a/src/llama_stack/providers/remote/inference/bedrock/bedrock.py b/src/llama_stack/providers/remote/inference/bedrock/bedrock.py index 70ee95916..451549db8 100644 --- a/src/llama_stack/providers/remote/inference/bedrock/bedrock.py +++ b/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 diff --git a/src/llama_stack/providers/remote/inference/bedrock/config.py b/src/llama_stack/providers/remote/inference/bedrock/config.py index 631a6e7ef..f31db63aa 100644 --- a/src/llama_stack/providers/remote/inference/bedrock/config.py +++ b/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}", } diff --git a/tests/unit/providers/inference/test_bedrock_adapter.py b/tests/unit/providers/inference/test_bedrock_adapter.py index a20f2860a..2a1ca769b 100644 --- a/tests/unit/providers/inference/test_bedrock_adapter.py +++ b/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.get_request_provider_data = MagicMock(return_value=SimpleNamespace(aws_bedrock_api_key="header-key")) + adapter.provider_data_api_key_field = "aws_bearer_token_bedrock" + 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" diff --git a/tests/unit/providers/inference/test_bedrock_config.py b/tests/unit/providers/inference/test_bedrock_config.py index 4c1fd56a2..622080426 100644 --- a/tests/unit/providers/inference/test_bedrock_config.py +++ b/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}" From 74dceb30da601fac809f7d9d04d83c66c1aac7d2 Mon Sep 17 00:00:00 2001 From: raghotham Date: Sat, 22 Nov 2025 00:30:36 +0530 Subject: [PATCH 2/3] chore: Add @cdoern as a code owner (#4209) We went through the nomination process for CODEOWNERS in the codeowners discord channel. Welcome to the code owners group @cdoern! Thanks for your contributions and we look forward to working with you! --- .github/CODEOWNERS | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/.github/CODEOWNERS b/.github/CODEOWNERS index 418d3113a..75636525e 100644 --- a/.github/CODEOWNERS +++ b/.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 From dabebdd2303af1401c5dd9d92654b530c4db5050 Mon Sep 17 00:00:00 2001 From: Ken Dreyer Date: Fri, 21 Nov 2025 16:12:01 -0500 Subject: [PATCH 3/3] fix: update hard-coded google model names (#4212) # What does this PR do? When we send the model names to Google's openai API, we must use the "google" name prefix. Google does not recognize the "vertexai" model names. Closes #4211 ## Test Plan ```bash uv venv --python python312 . .venv/bin/activate llama stack list-deps starter | xargs -L1 uv pip install llama stack run starter ``` Test that this shows the gemini models with their correct names: ```bash curl http://127.0.0.1:8321/v1/models | jq '.data | map(select(.custom_metadata.provider_id == "vertexai"))' ``` Test that this chat completion works: ```bash curl -X POST -H "Content-Type: application/json" "http://127.0.0.1:8321/v1/chat/completions" -d '{ "model": "vertexai/google/gemini-2.5-flash", "messages": [ { "role": "system", "content": "You are a helpful assistant." }, { "role": "user", "content": "Hello! Can you tell me a joke?" } ], "temperature": 1.0, "max_tokens": 256 }' ``` --- src/llama_stack/providers/remote/inference/vertexai/vertexai.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/llama_stack/providers/remote/inference/vertexai/vertexai.py b/src/llama_stack/providers/remote/inference/vertexai/vertexai.py index b91430fd0..7941f8c89 100644 --- a/src/llama_stack/providers/remote/inference/vertexai/vertexai.py +++ b/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"]