API Updates (#73)

* API Keys passed from Client instead of distro configuration

* delete distribution registry

* Rename the "package" word away

* Introduce a "Router" layer for providers

Some providers need to be factorized and considered as thin routing
layers on top of other providers. Consider two examples:

- The inference API should be a routing layer over inference providers,
  routed using the "model" key
- The memory banks API is another instance where various memory bank
  types will be provided by independent providers (e.g., a vector store
  is served by Chroma while a keyvalue memory can be served by Redis or
  PGVector)

This commit introduces a generalized routing layer for this purpose.

* update `apis_to_serve`

* llama_toolchain -> llama_stack

* Codemod from llama_toolchain -> llama_stack

- added providers/registry
- cleaned up api/ subdirectories and moved impls away
- restructured api/api.py
- from llama_stack.apis.<api> import foo should work now
- update imports to do llama_stack.apis.<api>
- update many other imports
- added __init__, fixed some registry imports
- updated registry imports
- create_agentic_system -> create_agent
- AgenticSystem -> Agent

* Moved some stuff out of common/; re-generated OpenAPI spec

* llama-toolchain -> llama-stack (hyphens)

* add control plane API

* add redis adapter + sqlite provider

* move core -> distribution

* Some more toolchain -> stack changes

* small naming shenanigans

* Removing custom tool and agent utilities and moving them client side

* Move control plane to distribution server for now

* Remove control plane from API list

* no codeshield dependency randomly plzzzzz

* Add "fire" as a dependency

* add back event loggers

* stack configure fixes

* use brave instead of bing in the example client

* add init file so it gets packaged

* add init files so it gets packaged

* Update MANIFEST

* bug fix

---------

Co-authored-by: Hardik Shah <hjshah@fb.com>
Co-authored-by: Xi Yan <xiyan@meta.com>
Co-authored-by: Ashwin Bharambe <ashwin@meta.com>

llama_stack/providers/impls/meta_reference/agents/agents.py

@@ -0,0 +1,135 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the terms described in the LICENSE file in
+# the root directory of this source tree.
+
+
+import logging
+import tempfile
+import uuid
+from typing import AsyncGenerator
+
+from llama_stack.apis.inference import Inference
+from llama_stack.apis.memory import Memory
+from llama_stack.apis.safety import Safety
+from llama_stack.apis.agents import *  # noqa: F403
+
+from .agent_instance import ChatAgent
+from .config import MetaReferenceImplConfig
+from .tools.builtin import (
+    CodeInterpreterTool,
+    PhotogenTool,
+    SearchTool,
+    WolframAlphaTool,
+)
+from .tools.safety import with_safety
+
+
+logger = logging.getLogger()
+logger.setLevel(logging.INFO)
+
+
+AGENT_INSTANCES_BY_ID = {}
+
+
+class MetaReferenceAgentsImpl(Agents):
+    def __init__(
+        self,
+        config: MetaReferenceImplConfig,
+        inference_api: Inference,
+        memory_api: Memory,
+        safety_api: Safety,
+    ):
+        self.config = config
+        self.inference_api = inference_api
+        self.memory_api = memory_api
+        self.safety_api = safety_api
+
+    async def initialize(self) -> None:
+        pass
+
+    async def create_agent(
+        self,
+        agent_config: AgentConfig,
+    ) -> AgentCreateResponse:
+        agent_id = str(uuid.uuid4())
+
+        builtin_tools = []
+        for tool_defn in agent_config.tools:
+            if isinstance(tool_defn, WolframAlphaToolDefinition):
+                tool = WolframAlphaTool(tool_defn.api_key)
+            elif isinstance(tool_defn, SearchToolDefinition):
+                tool = SearchTool(tool_defn.engine, tool_defn.api_key)
+            elif isinstance(tool_defn, CodeInterpreterToolDefinition):
+                tool = CodeInterpreterTool()
+            elif isinstance(tool_defn, PhotogenToolDefinition):
+                tool = PhotogenTool(dump_dir=tempfile.mkdtemp())
+            else:
+                continue
+
+            builtin_tools.append(
+                with_safety(
+                    tool,
+                    self.safety_api,
+                    tool_defn.input_shields,
+                    tool_defn.output_shields,
+                )
+            )
+
+        AGENT_INSTANCES_BY_ID[agent_id] = ChatAgent(
+            agent_config=agent_config,
+            inference_api=self.inference_api,
+            safety_api=self.safety_api,
+            memory_api=self.memory_api,
+            builtin_tools=builtin_tools,
+        )
+
+        return AgentCreateResponse(
+            agent_id=agent_id,
+        )
+
+    async def create_agent_session(
+        self,
+        agent_id: str,
+        session_name: str,
+    ) -> AgentSessionCreateResponse:
+        assert agent_id in AGENT_INSTANCES_BY_ID, f"System {agent_id} not found"
+        agent = AGENT_INSTANCES_BY_ID[agent_id]
+
+        session = agent.create_session(session_name)
+        return AgentSessionCreateResponse(
+            session_id=session.session_id,
+        )
+
+    async def create_agent_turn(
+        self,
+        agent_id: str,
+        session_id: str,
+        messages: List[
+            Union[
+                UserMessage,
+                ToolResponseMessage,
+            ]
+        ],
+        attachments: Optional[List[Attachment]] = None,
+        stream: Optional[bool] = False,
+    ) -> AsyncGenerator:
+        # wrapper request to make it easier to pass around (internal only, not exposed to API)
+        request = AgentTurnCreateRequest(
+            agent_id=agent_id,
+            session_id=session_id,
+            messages=messages,
+            attachments=attachments,
+            stream=stream,
+        )
+
+        agent_id = request.agent_id
+        assert agent_id in AGENT_INSTANCES_BY_ID, f"System {agent_id} not found"
+        agent = AGENT_INSTANCES_BY_ID[agent_id]
+
+        assert (
+            request.session_id in agent.sessions
+        ), f"Session {request.session_id} not found"
+        async for event in agent.create_and_execute_turn(request):
+            yield event