Merge remote-tracking branch 'upstream/main' into add-mcp-authentication-param

Author: Omar Abdelwahab

.github/workflows/python-build-test.yml

@@ -31,15 +31,15 @@ jobs:
         version: 0.7.6
 
     - name: Build Llama Stack API package
-      working-directory: src/llama-stack-api
+      working-directory: src/llama_stack_api
       run: uv build
 
     - name: Build Llama Stack package
       run: uv build
 
     - name: Install Llama Stack package (with api stubs from local build)
       run: |
-        uv pip install --find-links src/llama-stack-api/dist dist/*.whl
+        uv pip install --find-links src/llama_stack_api/dist dist/*.whl
 
     - name: Verify Llama Stack package
       run: |

.pre-commit-config.yaml

@@ -42,7 +42,7 @@ repos:
     hooks:
     -   id: ruff
         args: [ --fix ]
-        exclude: ^(src/llama_stack/strong_typing/.*|src/llama-stack-api/llama_stack_api/strong_typing/.*)$
+        exclude: ^(src/llama_stack_api/strong_typing/.*)$
     -   id: ruff-format
 
 -   repo: https://github.com/adamchainz/blacken-docs

pyproject.toml

@@ -181,7 +181,7 @@ install-wheel-from-presigned = "llama_stack.cli.scripts.run:install_wheel_from_p
 
 [tool.setuptools.packages.find]
 where = ["src"]
-include = ["llama_stack", "llama_stack.*", "llama-stack-api", "llama-stack-api.*"]
+include = ["llama_stack", "llama_stack.*", "llama_stack_api", "llama_stack_api.*"]
 
 [[tool.uv.index]]
 name = "pytorch-cpu"
@@ -191,7 +191,7 @@ explicit = true
 [tool.uv.sources]
 torch = [{ index = "pytorch-cpu" }]
 torchvision = [{ index = "pytorch-cpu" }]
-llama-stack-api = [{ path = "src/llama-stack-api", editable = true }]
+llama-stack-api = [{ path = "src/llama_stack_api", editable = true }]
 
 [tool.ruff]
 line-length = 120
@@ -258,7 +258,7 @@ unfixable = [
 ] # Using import * is acceptable (or at least tolerated) in an __init__.py of a package API
 
 [tool.mypy]
-mypy_path = ["src", "src/llama-stack-api"]
+mypy_path = ["src"]
 packages = ["llama_stack", "llama_stack_api"]
 plugins = ['pydantic.mypy']
 disable_error_code = []
@@ -281,14 +281,12 @@ exclude = [
     "^src/llama_stack/core/store/registry\\.py$",
     "^src/llama_stack/core/utils/exec\\.py$",
     "^src/llama_stack/core/utils/prompt_for_config\\.py$",
-    # Moved to llama-stack-api but still excluded
     "^src/llama_stack/models/llama/llama3/interface\\.py$",
     "^src/llama_stack/models/llama/llama3/tokenizer\\.py$",
     "^src/llama_stack/models/llama/llama3/tool_utils\\.py$",
     "^src/llama_stack/models/llama/llama3/generation\\.py$",
     "^src/llama_stack/models/llama/llama3/multimodal/model\\.py$",
     "^src/llama_stack/models/llama/llama4/",
-    "^src/llama-stack-api/llama_stack_api/core/telemetry/telemetry\\.py$",
     "^src/llama_stack/providers/inline/agents/meta_reference/",
     "^src/llama_stack/providers/inline/datasetio/localfs/",
     "^src/llama_stack/providers/inline/eval/meta_reference/eval\\.py$",
@@ -342,9 +340,7 @@ exclude = [
     "^src/llama_stack/providers/utils/telemetry/dataset_mixin\\.py$",
     "^src/llama_stack/providers/utils/telemetry/trace_protocol\\.py$",
     "^src/llama_stack/providers/utils/telemetry/tracing\\.py$",
-    "^src/llama-stack-api/llama_stack_api/core/telemetry/trace_protocol\\.py$",
-    "^src/llama-stack-api/llama_stack_api/core/telemetry/tracing\\.py$",
-    "^src/llama-stack-api/llama_stack_api/strong_typing/auxiliary\\.py$",
+    "^src/llama_stack_api/strong_typing/auxiliary\\.py$",
     "^src/llama_stack/distributions/template\\.py$",
 ]
 

scripts/generate_prompt_format.py

@@ -14,11 +14,11 @@
 from pathlib import Path
 
 import fire
-from llama_stack_api import ModelNotFoundError
 
 from llama_stack.models.llama.llama3.generation import Llama3
 from llama_stack.models.llama.llama4.generation import Llama4
 from llama_stack.models.llama.sku_list import resolve_model
+from llama_stack_api import ModelNotFoundError
 
 THIS_DIR = Path(__file__).parent.resolve()
 

src/llama_stack/cli/stack/_list_deps.py

@@ -9,7 +9,6 @@
 from pathlib import Path
 
 import yaml
-from llama_stack_api import Api
 from termcolor import cprint
 
 from llama_stack.cli.stack.utils import ImageType
@@ -22,6 +21,7 @@
 from llama_stack.core.distribution import get_provider_registry
 from llama_stack.core.stack import replace_env_vars
 from llama_stack.log import get_logger
+from llama_stack_api import Api
 
 TEMPLATES_PATH = Path(__file__).parent.parent.parent / "templates"
 

src/llama_stack/cli/stack/utils.py

@@ -11,7 +11,6 @@
 from pathlib import Path
 
 import yaml
-from llama_stack_api import Api
 from termcolor import cprint
 
 from llama_stack.core.datatypes import (
@@ -33,6 +32,7 @@
 from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.image_types import LlamaStackImageType
+from llama_stack_api import Api
 
 TEMPLATES_PATH = Path(__file__).parent.parent.parent / "distributions"
 

src/llama_stack/core/build.py

@@ -6,14 +6,14 @@
 
 import sys
 
-from llama_stack_api import Api
 from pydantic import BaseModel
 from termcolor import cprint
 
 from llama_stack.core.datatypes import BuildConfig
 from llama_stack.core.distribution import get_provider_registry
 from llama_stack.distributions.template import DistributionTemplate
 from llama_stack.log import get_logger
+from llama_stack_api import Api
 
 log = get_logger(name=__name__, category="core")
 

src/llama_stack/core/client.py

@@ -12,10 +12,11 @@
 from typing import Any, Union, get_args, get_origin
 
 import httpx
-from llama_stack_api import RemoteProviderConfig
 from pydantic import BaseModel, parse_obj_as
 from termcolor import cprint
 
+from llama_stack_api import RemoteProviderConfig
+
 _CLIENT_CLASSES = {}
 
 

src/llama_stack/core/configure.py

@@ -6,8 +6,6 @@
 import textwrap
 from typing import Any
 
-from llama_stack_api import Api, ProviderSpec
-
 from llama_stack.core.datatypes import (
     LLAMA_STACK_RUN_CONFIG_VERSION,
     DistributionSpec,
@@ -22,6 +20,7 @@
 from llama_stack.core.utils.dynamic import instantiate_class_type
 from llama_stack.core.utils.prompt_for_config import prompt_for_config
 from llama_stack.log import get_logger
+from llama_stack_api import Api, ProviderSpec
 
 logger = get_logger(name=__name__, category="core")
 

src/llama_stack/core/conversations/conversations.py

@@ -8,6 +8,13 @@
 import time
 from typing import Any, Literal
 
+from pydantic import BaseModel, TypeAdapter
+
+from llama_stack.core.datatypes import AccessRule, StackRunConfig
+from llama_stack.log import get_logger
+from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
+from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
+from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 from llama_stack_api import (
     Conversation,
     ConversationDeletedResource,
@@ -18,13 +25,6 @@
     Conversations,
     Metadata,
 )
-from pydantic import BaseModel, TypeAdapter
-
-from llama_stack.core.datatypes import AccessRule, StackRunConfig
-from llama_stack.log import get_logger
-from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType
-from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore
-from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl
 
 logger = get_logger(name=__name__, category="openai_conversations")