Merge pull request #29 from Qredence/0.2.3

0.2.3

Author: Zochory

.pre-commit-config.yaml

@@ -0,0 +1,32 @@
+repos:
+  - repo: https://github.com/pre-commit/pre-commit-hooks
+    rev: v4.5.0
+    hooks:
+      - id: trailing-whitespace
+      - id: end-of-file-fixer
+      - id: check-yaml
+      - id: check-added-large-files
+      - id: check-toml
+      - id: debug-statements
+
+  - repo: https://github.com/psf/black
+    rev: 24.10.0
+    hooks:
+      - id: black
+
+  - repo: https://github.com/pycqa/isort
+    rev: 5.13.2
+    hooks:
+      - id: isort
+
+  - repo: https://github.com/charliermarsh/ruff-pre-commit
+    rev: v0.3.0
+    hooks:
+      - id: ruff
+        args: [ --fix, --exit-non-zero-on-fix ]
+
+  - repo: https://github.com/pre-commit/mirrors-mypy
+    rev: v1.9.0
+    hooks:
+      - id: mypy
+        additional_dependencies: [ types-requests>=2.32.0, types-tabulate>=0.9.0 ]

.python-version

@@ -1 +1 @@
-3.12.9
+3.13

Dockerfile

@@ -111,7 +111,11 @@ Follow these steps to get Agentic Kernel up and running on your local machine.
 2. **Configure Environment Variables:** Ensure you have the necessary API keys set in your `.env` file (or the specific `.env` within the `adk_chat` directory if you prefer):
    ```
    OPENAI_API_KEY=your_openai_api_key
-   GOOGLE_API_KEY=your_google_api_key
+   GOOGLE_VERTIAI_API_KEY=your_google_vertai_api_key
+   GEMINI_API_KEY=your_google_ai_studio_key
+
+   # Note: The old GOOGLE_API_KEY is deprecated. Please migrate to GOOGLE_VERTIAI_API_KEY and GEMINI_API_KEY.
+
    ```
 
 ## Running the Example
@@ -222,9 +226,9 @@ bug fixes and improvements, and coding standards.
 
 ## 📜 License
 
-This project is licensed under the MIT License. See the [LICENSE](LICENSE) file for details.
+This project is licensed under the MIT License. See the [LICENSE](LICENSE.md) file for details.
 
 ## 🐛 Debugging
 
 * The `src/debug/` directory contains scripts useful for isolating and testing specific components of the kernel.
-  Explore these scripts if you encounter issues or want to understand individual parts better.
+  Explore these scripts if you encounter issues or want to understand individual parts better.

LICENSE LICENSE.mdLICENSE renamed to LICENSE.md

@@ -0,0 +1,40 @@
+# AgenticKernel Architecture
+
+This document details the architecture and component interactions within AgenticKernel, focusing on how agents
+communicate, collaborate, and accomplish complex tasks.
+
+## Table of Contents
+
+1. Communication Patterns
+2. Agent Collaboration Models
+3. Data Flow Between Components
+4. System Integration Points
+5. Synchronization Mechanisms
+6. Sequence Diagrams
+
+---
+
+## Communication Patterns
+
+AgenticKernel implements several communication patterns for effective agent collaboration:
+
+### Point-to-Point Communication
+
+Direct communication between two agents, typically used for specific queries or responses:
+
+```
+Agent A → Agent B: Direct request or information transfer
+Agent B → Agent A: Direct response or acknowledgment
+```
+
+### Broadcast Communication
+
+(See full details in the original component_interaction.md)
+
+---
+
+## Additional Architectural Docs
+
+- [Component Interaction](../architecture/component_interaction.md)
+- [System Overview](../architecture/system-overview.md)
+- [Workflow Architecture](../architecture/workflow_architecture.md)

README.md

@@ -0,0 +1,35 @@
+# AgenticKernel Concepts
+
+AgenticKernel is built around several core concepts that enable flexible and powerful AI agent systems.
+
+## Core Concepts
+
+### Agents
+
+Autonomous entities capable of perceiving, reasoning, and acting within an environment. Agents can communicate,
+collaborate, and delegate tasks.
+
+### Tasks
+
+Discrete units of work that agents can execute, delegate, or decompose. Managed by the TaskManager.
+
+### Memory
+
+Short-term and long-term memory modules for agents, enabling context retention and learning.
+
+### Communication (A2A Protocol)
+
+Support for the Agent-to-Agent (A2A) protocol, enabling discovery, messaging, and collaboration between agents via
+HTTP/JSON-RPC 2.0.
+
+### Plugins & Extensions
+
+Extend agent capabilities via plugins for tools, integrations, and new behaviors.
+
+### Orchestration
+
+Coordinating multi-agent workflows, task decomposition, and lifecycle management.
+
+---
+
+For more details, see [architecture.md](architecture.md) and the API reference.

docs/agentic-kernel/architecture.md

@@ -0,0 +1,26 @@
+# Advanced AgenticKernel Usage
+
+This guide covers advanced topics for power users and developers extending AgenticKernel.
+
+## Custom Agents
+
+- How to implement and register your own agent classes
+- Example: Creating a custom agent with specialized reasoning
+
+## Plugins and Extensions
+
+- How to add plugins for new tools, memory types, or integrations
+- Example: Writing a plugin for a third-party API
+
+## Debugging and Troubleshooting
+
+- Logging, error handling, and diagnostics
+- Tips for debugging multi-agent workflows
+
+## Integrating with AgenticFleet
+
+- How to use AgenticKernel as part of a larger AgenticFleet deployment
+- Best practices for interoperability
+
+---
+For more, see the [API Reference](../api/).

docs/agentic-kernel/concepts.md

@@ -0,0 +1,20 @@
+# Agent Communication Protocols in AgenticKernel
+
+This guide covers the communication protocols and interaction patterns available in AgenticKernel, including A2A (
+Agent-to-Agent) protocol support.
+
+## Supported Protocols
+
+- **A2A (Agent-to-Agent):** HTTP/JSON-RPC 2.0 based protocol for agent interoperability. Key features include discovery,
+  tasks, messages, artifacts, lifecycle states, and streaming.
+- **Custom Protocols:** Extendable via plugins for custom agent communication.
+
+## Key Concepts
+
+- **AgentCard:** Published at `/.well-known/agent.json` for discovery.
+- **Task Lifecycle:** States like `submitted`, `working`, `completed`.
+- **Messages & Artifacts:** Rich data exchange between agents.
+
+For implementation details,
+see [developer/agent_communication_protocols.md](../../developer/agent_communication_protocols.md)
+and [developer/creating_a2a_compatible_agents.md](../../developer/creating_a2a_compatible_agents.md).

docs/agentic-kernel/guides/advanced.md

@@ -0,0 +1,16 @@
+# Memory in AgenticKernel
+
+AgenticKernel provides flexible memory management for agents, supporting both short-term and long-term memory modules.
+This guide covers core memory concepts and configuration options.
+
+## Types of Memory
+
+- **Short-term memory:** For immediate task context and working memory.
+- **Long-term memory:** Persistent, extensible storage for agent knowledge.
+
+## Customizing Memory
+
+- Configure memory modules via agent configuration options.
+- Extend memory with plugins for new storage backends or retrieval strategies.
+
+For more details, see [developer/memory.md](../../developer/memory.md).