Agents智能体是一个独立的执行单元旨在自主行动以实现特定目标。智能体可以执行任务、与用户互动、使用外部工具以及与其他智能体协调。基于BaseAgent扩展成LlmAgent、WorkflowAgent、CustomAgentLLM agentsLearn more about LLM Agents…code_writer_agent LlmAgent( nameCodeWriterAgent, modelGEMINI_MODEL, # Change 3: Improved instruction instructionYou are a Python Code Generator. Based *only* on the users request, write Python code that fulfills the requirement. Output *only* the complete Python code block, enclosed in triple backticks (python ... ). Do not add any other text before or after the code block. , descriptionWrites initial Python code based on a specification., output_keygenerated_code # Stores output in state[generated_code] )Workflow agentsLearn more about Workflow Agents…Sequential agentscode_pipeline_agent SequentialAgent( nameCodePipelineAgent, sub_agents[code_writer_agent, code_reviewer_agent, code_refactorer_agent], descriptionExecutes a sequence of code writing, reviewing, and refactoring., # The agents will run in the order provided: Writer - Reviewer - Refactorer )Loop agents# Part of agent.py -- Follow https://google.github.io/adk-docs/get-started/quickstart/ to learn the setup import asyncio import os from google.adk.agents import LoopAgent, LlmAgent, BaseAgent, SequentialAgent from google.genai import types from google.adk.runners import InMemoryRunner from google.adk.agents.invocation_context import InvocationContext from google.adk.tools.tool_context import ToolContext from typing import AsyncGenerator, Optional from google.adk.events import Event, EventActions # --- Constants --- APP_NAME doc_writing_app_v3 # New App Name USER_ID dev_user_01 SESSION_ID_BASE loop_exit_tool_session # New Base Session ID GEMINI_MODEL gemini-2.0-flash STATE_INITIAL_TOPIC initial_topic # --- State Keys --- STATE_CURRENT_DOC current_document STATE_CRITICISM criticism # Define the exact phrase the Critic should use to signal completion COMPLETION_PHRASE No major issues found. # --- Tool Definition --- def exit_loop(tool_context: ToolContext): Call this function ONLY when the critique indicates no further changes are needed, signaling the iterative process should end. print(f [Tool Call] exit_loop triggered by {tool_context.agent_name}) tool_context.actions.escalate True # Return empty dict as tools should typically return JSON-serializable output return {} # --- Agent Definitions --- # STEP 1: Initial Writer Agent (Runs ONCE at the beginning) initial_writer_agent LlmAgent( nameInitialWriterAgent, modelGEMINI_MODEL, include_contentsnone, # MODIFIED Instruction: Ask for a slightly more developed start instructionfYou are a Creative Writing Assistant tasked with starting a story. Write the *first draft* of a short story (aim for 2-4 sentences). Base the content *only* on the topic provided below. Try to introduce a specific element (like a character, a setting detail, or a starting action) to make it engaging. Topic: {{initial_topic}} Output *only* the story/document text. Do not add introductions or explanations. , descriptionWrites the initial document draft based on the topic, aiming for some initial substance., output_keySTATE_CURRENT_DOC ) # STEP 2a: Critic Agent (Inside the Refinement Loop) critic_agent_in_loop LlmAgent( nameCriticAgent, modelGEMINI_MODEL, include_contentsnone, # MODIFIED Instruction: More nuanced completion criteria, look for clear improvement paths. instructionfYou are a Constructive Critic AI reviewing a short document draft (typically 2-6 sentences). Your goal is balanced feedback. **Document to Review:** {{current_document}} **Task:** Review the document for clarity, engagement, and basic coherence according to the initial topic (if known). IF you identify 1-2 *clear and actionable* ways the document could be improved to better capture the topic or enhance reader engagement (e.g., Needs a stronger opening sentence, Clarify the characters goal): Provide these specific suggestions concisely. Output *only* the critique text. ELSE IF the document is coherent, addresses the topic adequately for its length, and has no glaring errors or obvious omissions: Respond *exactly* with the phrase {COMPLETION_PHRASE} and nothing else. It doesnt need to be perfect, just functionally complete for this stage. Avoid suggesting purely subjective stylistic preferences if the core is sound. Do not add explanations. Output only the critique OR the exact completion phrase. , descriptionReviews the current draft, providing critique if clear improvements are needed, otherwise signals completion., output_keySTATE_CRITICISM ) # STEP 2b: Refiner/Exiter Agent (Inside the Refinement Loop) refiner_agent_in_loop LlmAgent( nameRefinerAgent, modelGEMINI_MODEL, # Relies solely on state via placeholders include_contentsnone, instructionfYou are a Creative Writing Assistant refining a document based on feedback OR exiting the process. **Current Document:** {{current_document}} **Critique/Suggestions:** {{criticism}} **Task:** Analyze the Critique/Suggestions. IF the critique is *exactly* {COMPLETION_PHRASE}: You MUST call the exit_loop function. Do not output any text. ELSE (the critique contains actionable feedback): Carefully apply the suggestions to improve the Current Document. Output *only* the refined document text. Do not add explanations. Either output the refined document OR call the exit_loop function. , descriptionRefines the document based on critique, or calls exit_loop if critique indicates completion., tools[exit_loop], # Provide the exit_loop tool output_keySTATE_CURRENT_DOC # Overwrites state[current_document] with the refined version ) # STEP 2: Refinement Loop Agent refinement_loop LoopAgent( nameRefinementLoop, # Agent order is crucial: Critique first, then Refine/Exit sub_agents[ critic_agent_in_loop, refiner_agent_in_loop, ], max_iterations5 # Limit loops ) # STEP 3: Overall Sequential Pipeline # For ADK tools compatibility, the root agent must be named root_agent root_agent SequentialAgent( nameIterativeWritingPipeline, sub_agents[ initial_writer_agent, # Run first to create initial doc refinement_loop # Then run the critique/refine loop ], descriptionWrites an initial document and then iteratively refines it with critique using an exit tool. )Parallel agentsCustom agentsMulti-agent systems