chore: import upstream snapshot with attribution

contributing/samples/integrations/files_retrieval_agent/data/adk_overview.txt

@@ -0,0 +1,23 @@
+Agent Development Kit (ADK) Overview
+
+ADK is a Python framework for building AI agents powered by large language models.
+It provides a structured way to create agents that can reason, use tools, and
+collaborate with other agents.
+
+Key Features:
+- Multi-agent orchestration with sequential, parallel, and loop patterns
+- Built-in tool support including function tools, retrieval, and code execution
+- Session management for maintaining conversation state
+- Memory services for long-term recall across sessions
+- Support for multiple LLM backends including Gemini, Anthropic, and Ollama
+
+Architecture:
+The core abstractions are Agent, Runner, Tool, Session, and Memory.
+The Runner orchestrates the reason-act loop, processing user turns and
+streaming events back to the caller.
+
+Agent Types:
+- LlmAgent: Main agent with LLM integration
+- SequentialAgent: Runs sub-agents in sequence
+- ParallelAgent: Runs sub-agents in parallel
+- LoopAgent: Runs sub-agents in a loop

contributing/samples/integrations/files_retrieval_agent/data/tools_guide.txt

@@ -0,0 +1,28 @@
+ADK Tools Guide
+
+Tools are capabilities that agents can invoke during their reasoning process.
+ADK supports several types of tools:
+
+1. Function Tools
+   Define Python functions and pass them directly to an agent.
+   The function signature and docstring become the tool schema.
+
+2. Retrieval Tools
+   - FilesRetrieval: Index and search local files using embeddings.
+     Uses gemini-embedding-2-preview by default.
+   - VertexAiRagRetrieval: Search Vertex AI RAG corpora.
+
+3. Code Execution
+   Agents can generate and execute code in a sandboxed environment.
+
+4. Third-Party Tool Integration
+   - LangchainTool: Wraps LangChain tools for use in ADK.
+   - CrewaiTool: Wraps CrewAI tools for use in ADK.
+
+5. MCP Tools
+   Connect to Model Context Protocol servers for external tool access.
+
+Tool Configuration:
+Tools can be configured with authentication, rate limiting, and custom
+schemas. The ToolContext provides access to session state, artifacts,
+and other contextual information during tool execution.