Merge branch 'main' into update-api-docs

llama_stack/apis/datatypes.py

@@ -4,15 +4,83 @@
 # This source code is licensed under the terms described in the LICENSE file in
 # the root directory of this source tree.
 
-from enum import Enum
+from enum import Enum, EnumMeta
 
-from pydantic import BaseModel
+from pydantic import BaseModel, Field
 
 from llama_stack.schema_utils import json_schema_type
 
 
+class DynamicApiMeta(EnumMeta):
+    def __new__(cls, name, bases, namespace):
+        # Store the original enum values
+        original_values = {k: v for k, v in namespace.items() if not k.startswith("_")}
+
+        # Create the enum class
+        cls = super().__new__(cls, name, bases, namespace)
+
+        # Store the original values for reference
+        cls._original_values = original_values
+        # Initialize _dynamic_values
+        cls._dynamic_values = {}
+
+        return cls
+
+    def __call__(cls, value):
+        try:
+            return super().__call__(value)
+        except ValueError as e:
+            # If this value was already dynamically added, return it
+            if value in cls._dynamic_values:
+                return cls._dynamic_values[value]
+
+            # If the value doesn't exist, create a new enum member
+            # Create a new member name from the value
+            member_name = value.lower().replace("-", "_")
+
+            # If this member name already exists in the enum, return the existing member
+            if member_name in cls._member_map_:
+                return cls._member_map_[member_name]
+
+            # Instead of creating a new member, raise ValueError to force users to use Api.add() to
+            # register new APIs explicitly
+            raise ValueError(f"API '{value}' does not exist. Use Api.add() to register new APIs.") from e
+
+    def __iter__(cls):
+        # Allow iteration over both static and dynamic members
+        yield from super().__iter__()
+        if hasattr(cls, "_dynamic_values"):
+            yield from cls._dynamic_values.values()
+
+    def add(cls, value):
+        """
+        Add a new API to the enum.
+        Used to register external APIs.
+        """
+        member_name = value.lower().replace("-", "_")
+
+        # If this member name already exists in the enum, return it
+        if member_name in cls._member_map_:
+            return cls._member_map_[member_name]
+
+        # Create a new enum member
+        member = object.__new__(cls)
+        member._name_ = member_name
+        member._value_ = value
+
+        # Add it to the enum class
+        cls._member_map_[member_name] = member
+        cls._member_names_.append(member_name)
+        cls._member_type_ = str
+
+        # Store it in our dynamic values
+        cls._dynamic_values[value] = member
+
+        return member
+
+
 @json_schema_type
-class Api(Enum):
+class Api(Enum, metaclass=DynamicApiMeta):
     """Enumeration of all available APIs in the Llama Stack system.
     :cvar providers: Provider management and configuration
     :cvar inference: Text generation, chat completions, and embeddings
@@ -35,7 +103,6 @@ class Api(Enum):
     :cvar files: File storage and management
     :cvar inspect: Built-in system inspection and introspection
     """
-
     providers = "providers"
     inference = "inference"
     safety = "safety"
@@ -77,3 +144,12 @@ class Error(BaseModel):
     title: str
     detail: str
     instance: str | None = None
+
+
+class ExternalApiSpec(BaseModel):
+    """Specification for an external API implementation."""
+
+    module: str = Field(..., description="Python module containing the API implementation")
+    name: str = Field(..., description="Name of the API")
+    pip_packages: list[str] = Field(default=[], description="List of pip packages to install the API")
+    protocol: str = Field(..., description="Name of the protocol class for the API")

llama_stack/apis/inference/inference.py

@@ -911,12 +911,6 @@ class OpenAIEmbeddingsResponse(BaseModel):
 class ModelStore(Protocol):
     async def get_model(self, identifier: str) -> Model: ...
 
-    async def update_registered_llm_models(
-        self,
-        provider_id: str,
-        models: list[Model],
-    ) -> None: ...
-
 
 class TextTruncation(Enum):
     """Config for how to truncate text for embedding when text is longer than the model's max sequence length. Start and End semantics depend on whether the language is left-to-right or right-to-left.

llama_stack/apis/telemetry/telemetry.py

@@ -22,6 +22,8 @@ from llama_stack.schema_utils import json_schema_type, register_schema, webmetho
 # Add this constant near the top of the file, after the imports
 DEFAULT_TTL_DAYS = 7
 
+REQUIRED_SCOPE = "telemetry.read"
+
 
 @json_schema_type
 class SpanStatus(Enum):
@@ -422,7 +424,7 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/traces", method="POST")
+    @webmethod(route="/telemetry/traces", method="POST", required_scope=REQUIRED_SCOPE)
     async def query_traces(
         self,
         attribute_filters: list[QueryCondition] | None = None,
@@ -440,7 +442,7 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/traces/{trace_id:path}", method="GET")
+    @webmethod(route="/telemetry/traces/{trace_id:path}", method="GET", required_scope=REQUIRED_SCOPE)
     async def get_trace(self, trace_id: str) -> Trace:
         """Get a trace by its ID.
 
@@ -449,7 +451,9 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/traces/{trace_id:path}/spans/{span_id:path}", method="GET")
+    @webmethod(
+        route="/telemetry/traces/{trace_id:path}/spans/{span_id:path}", method="GET", required_scope=REQUIRED_SCOPE
+    )
     async def get_span(self, trace_id: str, span_id: str) -> Span:
         """Get a span by its ID.
 
@@ -459,7 +463,7 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/spans/{span_id:path}/tree", method="POST")
+    @webmethod(route="/telemetry/spans/{span_id:path}/tree", method="POST", required_scope=REQUIRED_SCOPE)
     async def get_span_tree(
         self,
         span_id: str,
@@ -475,7 +479,7 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/spans", method="POST")
+    @webmethod(route="/telemetry/spans", method="POST", required_scope=REQUIRED_SCOPE)
     async def query_spans(
         self,
         attribute_filters: list[QueryCondition],
@@ -508,7 +512,7 @@ class Telemetry(Protocol):
         """
         ...
 
-    @webmethod(route="/telemetry/metrics/{metric_name}", method="POST")
+    @webmethod(route="/telemetry/metrics/{metric_name}", method="POST", required_scope=REQUIRED_SCOPE)
     async def query_metrics(
         self,
         metric_name: str,