meshagent-agents 0.0.37__tar.gz → 0.0.38__tar.gz

{meshagent_agents-0.0.37 → meshagent_agents-0.0.38}/CHANGELOG.md

@@ -1,3 +1,6 @@
+## [0.0.38]
+- Stability
+
 ## [0.0.37]
 - Stability
 

meshagent_agents-0.0.38/PKG-INFO

@@ -0,0 +1,64 @@
+Metadata-Version: 2.4
+Name: meshagent-agents
+Version: 0.0.38
+Summary: Agent Building Blocks for Meshagent
+License-Expression: Apache-2.0
+Project-URL: Documentation, https://docs.meshagent.com
+Project-URL: Website, https://www.meshagent.com
+Project-URL: Source, https://www.meshagent.com
+Requires-Python: >=3.12
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: pyjwt~=2.10
+Requires-Dist: pytest~=8.4
+Requires-Dist: pytest-asyncio~=0.26
+Requires-Dist: meshagent-api~=0.0.38
+Requires-Dist: meshagent-tools~=0.0.38
+Requires-Dist: meshagent-openai~=0.0.38
+Requires-Dist: pydantic~=2.11
+Requires-Dist: opentelemetry-distro~=0.54b1
+Provides-Extra: all
+Requires-Dist: meshagent-api[all]~=0.0.38; extra == "all"
+Requires-Dist: chonkie~=0.5.1; extra == "all"
+Requires-Dist: chonkie[semantic]~=0.5.1; extra == "all"
+Requires-Dist: chonkie[openai]~=0.5.1; extra == "all"
+Requires-Dist: aiosmtplib~=4.0.1; extra == "all"
+Provides-Extra: sync
+Requires-Dist: meshagent-api[sync]~=0.0.38; extra == "sync"
+Provides-Extra: mail
+Requires-Dist: aiosmtplib~=4.0.1; extra == "mail"
+Provides-Extra: rag
+Requires-Dist: chonkie~=0.5.1; extra == "rag"
+Requires-Dist: chonkie[semantic]~=0.5.1; extra == "rag"
+Requires-Dist: chonkie[openai]~=0.5.1; extra == "rag"
+Dynamic: license-file
+
+### MeshAgent Agents
+
+The ``meshagent.agents`` package provides higher-level agent classes that orchestrate tools and tasks. The primary agents you will build will use the ``TaskRunner``, ``Worker``, and ``ChatBot`` agent types. These agents extend the base ``Agent`` and ``SingleRoomAgent`` classes which setup the fundamentals for working with Agents in MeshAgent Rooms.
+
+Note that agents use LLMAdapters and ToolResponseAdapters to translate between language model calls and tool executions. They also use the ServiceHost to run. 
+
+### Agent
+The ``Agent`` base class handles static info such as the agent name, description, and requirements. This class is not used directly, but is the foundation for specialized agents. 
+
+### SingleRoomAgent
+The ``SingleRoomAgent``extends the ``Agent`` class, connects to a ``RoomClient``, and installs any declared schemas or toolkits when the agent starts up. All other MeshAgent Agent types extend the ``SingleRoomAgent`` class with additional functionality.
+
+### TaskRunner
+The ``TaskRunner`` agent is useful when you want to invoke an agent with a well-defined JSON schemas for input and output. This is important for running agents-as-tools or running remote tasks. Often you will define a ``TaskRunner`` and pass it to a ``ChatBot`` or ``VoiceBot`` as a tool for that agent to use. 
+
+### Worker
+The ``Worker`` is a queue-based ``SingleRoomAgent`` that processes queued messages with an LLM and optional tools. This is particularly helpful for running asynchronous jobs. With the ``Worker`` agent you can create a set of tasks that need to run in a Room and the ``Worker`` will execute all of the tasks in the queue. 
+
+### ChatBot
+The ``ChatBot`` is a conversational agent derived from the ``SingleRoomAgent``. It wires an LLMAdapter, optoinal tools, and manages chat threads for each user. This means multiple users can be in the same room interacting with a chat agent, but each user will have private messages with the agent. Check out the [Build and Deploy a Chat Agent](https://docs.meshagent.com/agents/standard/buildanddeploychatbot) example to learn how to create a simple Chat Agent without tools then add built-in MeshAgent tools and custom tools to the agent.
+
+---
+### Learn more about MeshAgent on our website or check out the docs for additional examples!
+
+**Website**: [www.meshagent.com](https://www.meshagent.com/)
+
+**Documentation**: [docs.meshagent.com](https://docs.meshagent.com/)
+
+---

meshagent_agents-0.0.38/README.md

@@ -0,0 +1,29 @@
+### MeshAgent Agents
+
+The ``meshagent.agents`` package provides higher-level agent classes that orchestrate tools and tasks. The primary agents you will build will use the ``TaskRunner``, ``Worker``, and ``ChatBot`` agent types. These agents extend the base ``Agent`` and ``SingleRoomAgent`` classes which setup the fundamentals for working with Agents in MeshAgent Rooms.
+
+Note that agents use LLMAdapters and ToolResponseAdapters to translate between language model calls and tool executions. They also use the ServiceHost to run. 
+
+### Agent
+The ``Agent`` base class handles static info such as the agent name, description, and requirements. This class is not used directly, but is the foundation for specialized agents. 
+
+### SingleRoomAgent
+The ``SingleRoomAgent``extends the ``Agent`` class, connects to a ``RoomClient``, and installs any declared schemas or toolkits when the agent starts up. All other MeshAgent Agent types extend the ``SingleRoomAgent`` class with additional functionality.
+
+### TaskRunner
+The ``TaskRunner`` agent is useful when you want to invoke an agent with a well-defined JSON schemas for input and output. This is important for running agents-as-tools or running remote tasks. Often you will define a ``TaskRunner`` and pass it to a ``ChatBot`` or ``VoiceBot`` as a tool for that agent to use. 
+
+### Worker
+The ``Worker`` is a queue-based ``SingleRoomAgent`` that processes queued messages with an LLM and optional tools. This is particularly helpful for running asynchronous jobs. With the ``Worker`` agent you can create a set of tasks that need to run in a Room and the ``Worker`` will execute all of the tasks in the queue. 
+
+### ChatBot
+The ``ChatBot`` is a conversational agent derived from the ``SingleRoomAgent``. It wires an LLMAdapter, optoinal tools, and manages chat threads for each user. This means multiple users can be in the same room interacting with a chat agent, but each user will have private messages with the agent. Check out the [Build and Deploy a Chat Agent](https://docs.meshagent.com/agents/standard/buildanddeploychatbot) example to learn how to create a simple Chat Agent without tools then add built-in MeshAgent tools and custom tools to the agent.
+
+---
+### Learn more about MeshAgent on our website or check out the docs for additional examples!
+
+**Website**: [www.meshagent.com](https://www.meshagent.com/)
+
+**Documentation**: [docs.meshagent.com](https://docs.meshagent.com/)
+
+---

meshagent_agents-0.0.38/meshagent/agents/__init__.py

@@ -0,0 +1,32 @@
+from .agent import (
+    Agent,
+    AgentCallContext,
+    AgentChatContext,
+    RequiredToolkit,
+    TaskRunner,
+    SingleRoomAgent,
+)
+from .development import connect_development_agent
+from .listener import Listener, ListenerContext
+from .hosting import RemoteTaskRunnerServer
+from .adapter import ToolResponseAdapter, LLMAdapter
+from .thread_schema import thread_schema
+from .version import __version__
+
+
+__all__ = [
+    Agent,
+    AgentCallContext,
+    AgentChatContext,
+    RequiredToolkit,
+    TaskRunner,
+    SingleRoomAgent,
+    connect_development_agent,
+    Listener,
+    ListenerContext,
+    RemoteTaskRunnerServer,
+    ToolResponseAdapter,
+    LLMAdapter,
+    thread_schema,
+    __version__,
+]

{meshagent_agents-0.0.37 → meshagent_agents-0.0.38}/meshagent/agents/adapter.py

@@ -7,40 +7,49 @@ from typing import Any, Optional, Callable, TypeVar, Generic
 
 T = TypeVar("T")
 
+
 class ToolResponseAdapter(ABC):
     def __init__(self):
         pass
-    
+
     @abstractmethod
     async def to_plain_text(self, *, room: RoomClient, response: Response):
         pass
 
     @abstractmethod
-    async def create_messages(self, *, context: AgentChatContext, tool_call: Any, room: RoomClient, response: Response) -> list:
+    async def create_messages(
+        self,
+        *,
+        context: AgentChatContext,
+        tool_call: Any,
+        room: RoomClient,
+        response: Response,
+    ) -> list:
         pass
 
 
 class LLMAdapter(Generic[T]):
-
     def create_chat_context(self) -> AgentChatContext:
         return AgentChatContext()
-    
+
     @abstractmethod
-    async def check_for_termination(self, *, context: AgentChatContext, room: RoomClient):
+    async def check_for_termination(
+        self, *, context: AgentChatContext, room: RoomClient
+    ):
         return True
 
     @abstractmethod
-    async def next(self, 
+    async def next(
+        self,
         *,
         context: AgentChatContext,
         room: RoomClient,
         toolkits: Toolkit,
         tool_adapter: Optional[ToolResponseAdapter] = None,
         output_schema: Optional[dict] = None,
-        event_handler: Optional[Callable[[T],None]] = None
-    ) -> Any:  
+        event_handler: Optional[Callable[[T], None]] = None,
+    ) -> Any:
         pass
 
     def validate(response: dict, output_schema: dict):
         validate(response, output_schema)
-