gemini-interactions-api

name gemini-interactions-api metadata {"category":"AiAndMachineLearning"} description Guides the usage of Gemini Interactions API on Gemini Enterprise Agent Platform. Use when the user wants to use the stateful, server-managed Interactions API for multi-turn conversations, background execution, streaming, structured output, and function calling on the Agent Platform. Gemini Interactions API Skill This skill provides instructions for authenticating, connecting to, and utilizing the stateful, server-managed Gemini Interactions API on Gemini Enterprise Agent Platform. The Interactions API is the modern, recommended way to execute Generative AI agent conversations, background research tasks, multi-turn chats, and structured, multi-step workflows. [!IMPORTANT] CRITICAL: Unified SDK, Latest Models & GEAP Targeting * Unified SDK : Use the Google Gen AI SDK ( google-genai >= 2.3.0 for Python, @google/genai >= 2.3.0 for JS/TS). SDK versions >= 2.0.0 are the minimum floor at which the steps schema activates, but >= 2.3.0 is the supported/recommended floor. Legacy SDKs like google-cloud-aiplatform , @google-cloud/vertexai , and google-generativeai are strictly unsupported for Interactions. * Mandatory Instruction : When explaining client initialization or writing import code, you must explicitly state/warn the user that legacy packages like google-cloud-aiplatform or google-generativeai are strictly unsupported for interactions. * Latest Models Only : Use gemini-3.5-flash (fast, balanced, multimodal — the recommended default), gemini-3.1-pro-preview (complex reasoning, coding, research), or gemini-3.1-flash-lite (cost-efficient, high-frequency lightweight tasks). Refer to the latest model versions to check for new updates. Legacy models ( gemini-3-flash-preview , gemini-2.5-* , gemini-2.0-* , gemini-1.5-* ) are deprecated and do not support interactions. * Mandatory Instruction : In any interaction response, you must warn the user that legacy models like gemini-2.5-* , gemini-2.0-* , or gemini-1.5-* are deprecated and unsupported for the Interactions API. * GEAP requires a provisioned agent (no direct base-model calls yet) : On Gemini Enterprise Agent Platform (GEAP), direct/base-model calls ( model="..." ) via the Interactions API are not supported yet . You must target a provisioned agent or endpoint with the agent="<AGENT_ID>" parameter instead of model="..." . The code examples in this skill use agent=... for this reason. (This is the primary difference from the ai.google.dev documentation for Interactions, which uses model=... — while model=... is valid for other Gemini API contexts, it is not supported on the Agent Platform .) Provision an agent per the Agent Platform docs and pass its ID as agent . * Turn-Scoped Parameters : Parameters like tools , system_instruction , and generation_config are turn-scoped. They MUST be passed with each interaction request. 1. Authentication Before running any code, ensure you are authenticated with Application Default Credentials (ADC) and have the necessary API enabled. Login : gcloud auth application-default login Enable API (if not already enabled): gcloud services enable aiplatform.googleapis.com 2. Client Initialization You can initialize the client using environment variables (recommended) or by passing explicit configuration parameters. Option A: Environment Variables (Recommended) Configure environment variables to let the SDK automatically resolve settings: export GOOGLE_GENAI_USE_ENTERPRISE= true export GOOGLE_CLOUD_PROJECT= "your-project-id" export GOOGLE_CLOUD_LOCATION= "global" Python from google import genai # The SDK automatically picks up the environment variables client = genai.Client() TypeScript/JavaScript import { GoogleGenAI } from "@google/genai" ; // The SDK automatically picks up the environment variables const ai = new GoogleGenAI (); Option B: Explicit Inline Parameters Alternatively, pass configuration values directly inside your code: Python from google import genai import google.auth _, project_id = google.auth.default() client = genai.Client(enterprise= True , project=project_id, location= "global" ) TypeScript/JavaScript import { GoogleGenAI } from "@google/genai" ; const ai = new GoogleGenAI ({ enterprise : { project : "your-project-id" , location : "global" } }); 3. Core Interactions API Usage Quick Start (Single-Turn) Submit a single prompt and read the final text response. Under the modern schema, output content is retrieved from the steps list. Python interaction = client.interactions.create( agent= "your-agent-id" , # GEAP: target a provisioned agent, not a base model input = "Explain serverless computing in one sentence." ) # Use the output_text convenience accessor (combined text from the trailing model_output steps) print (interaction.output_text) TypeScript/JavaScript const interaction = await ai. interactions . create ({ agent : "your-agent-id" , // GEAP: target a provisioned agent, not a base model input : "Explain serverless computing in one sentence." }); console . log (interaction. output_text ); Stateful Conversation (Multi-Turn) Interactions are stateful by default. Store the conversation state in the cloud and reference it in the subsequent turn using previous_interaction_id . Python # Turn 1: Introduce ourselves # Interactions are stored by default (store=True); pass store=False to disable # server-side retention (which also disables previous_interaction_id and background). turn1 = client.interactions.create( agent= "your-agent-id" , input = "Hi! My name is John. I am working on AI agents." , store= True ) print ( f"Turn 1: {turn1.output_text} " ) # Turn 2: Refer back to the stored turn state turn2 = client.interactions.create( agent= "your-agent-id" , input = "What is my name?" , previous_interaction_id=turn1. id ) print ( f"Turn 2: {turn2.output_text} " ) TypeScript/JavaScript // Turn 1 (interactions are stored by default; pass store: false to disable) const turn1 = await ai. interactions . create ({ agent : "your-agent-id" , input : "Hi! My name is John. I am working on AI agents." , store : true }); // Turn 2 const turn2 = await ai. interactions . create ({ agent : "your-agent-id" , input : "What is my name?" , previousInteractionId : turn1. id }); console . log (turn2. output_text ); Real-Time Streaming Stream responses in real-time. Passing stream=True returns an iterable chunk generator. Python # The stream yields typed events, not full interaction snapshots. The sequence is: # interaction.created -> (step.start -> step.delta(s) -> step.stop)+ -> interaction.completed for event in client.interactions.create( agent= "your-agent-id" , input = "Write a short poem about debugging." , stream= True ): if event.event_type == "step.delta" : if event.delta. type == "text" : print (event.delta.text, end= "" , flush= True ) elif event.event_type == "interaction.completed" : print () TypeScript/JavaScript // The stream yields typed events, not full interaction snapshots. The sequence is: // interaction.created -> (step.start -> step.delta(s) -> step.stop)+ -> interaction.completed const responseStream = await ai. interactions . create ({ agent : "your-agent-id" , input : "Write a short poem about debugging." , stream : true }); for await ( const event of responseStream) { if (event. event_type === "step.delta" ) { if (event. delta . type === "text" ) { process. stdout . write (event. delta . text ); } } else if (event. event_type === "interaction.completed" ) { console . log (); } } Structured Output (Pydantic / Polymorphic response_format ) Retrieve structured, type-safe JSON matching a schema. Under the modern Interactions API, a polymorphic response_format argument directly takes the target schema structure. Python from pydantic import BaseModel, Field class Book ( BaseModel ): title: str = Field(description= "The title of the book" ) author: str = Field(description= "The book's author" ) year_published: int interaction = client.interactions.create( agent= "your-agent-id" , input = "Recommend one famous sci-fi book." , response_format=Book ) # The text will be a valid JSON matching the Book schema print (interaction.output_text) TypeScript/JavaScript import { Type } from "@google/genai" ; const BookSchema = { type : Type . OBJECT , properties : { title : { type : Type . STRING , description : "The title of the book" }, author : { type : Type . STRING , description : "The book's author" }, yearPublished : { type : Type . INTEGER } }, required : [ "title" , "author" , "yearPublished" ] }; const interaction = await ai. interactions . create ({ agent : "your-agent-id" , input : "Recommend one famous sci-fi book." , responseFormat : BookSchema }); console . log (interaction. output_text ); Function Calling (Agent Tool Use) Define local tools (functions) and submit execution results to the stateful interaction history. Python import json def get_stock_price ( ticker: str ) -> float : """Gets the stock price for a given ticker symbol.""" if ticker.upper() == "GOOG" : return 175.50 return 100.0 # Turn 1: Pass tools to the model interaction = client.interactions.create( agent= "your-agent-id" , input = "What is the stock price of GOOG?" , tools=[get_stock_price] ) # In the flat steps schema, a tool request is a top-level step of type # "function_call" with flat `name` and `arguments` fields (no nested tool_calls). for step in interaction.steps: if step. type == "function_call" and step.name == "get_stock_price" : ticker_arg = step.arguments.get( "ticker" ) price = get_stock_price(ticker_arg) # Turn 2: Submit the result back as a function_result step. Reference the # originating call via call_id=step.id, and pass tools again (turn-scoped). final_turn = client.interactions.create( agent= "your-agent-id" , input =[ { "type" : "function_result" , "name" : step.name, "call_id" : step. id , "result" : [{ "type" : "text" , "text" : json.dumps(price)}], } ], tools=[get_stock_price], previous_interaction_id=interaction. id ) print (final_turn.output_text) TypeScript/JavaScript import { Type } from "@google/genai" ; // Define local tool function getStockPrice ( { ticker }: { ticker: string } ): number { if (ticker. toUpperCase () === "GOOG" ) { return 175.50 ; } return 100.00 ; } // Turn 1: Pass tools to the model const toolDeclaration = { functionDeclarations : [{ name : "getStockPrice" , description : "Gets the stock price for a given ticker symbol." , parameters : { type : Type . OBJECT , properties : { ticker : { type : Type . STRING , description : "The stock ticker symbol" } }, required : [ "ticker" ] } }] }; const interaction = await ai. interactions . create ({ agent : "your-agent-id" , input : "What is the stock price of GOOG?" , tools : [toolDeclaration] }); // In the flat steps schema, a tool request is a top-level step of type // "function_call" with flat `name` and `arguments` fields (no nested toolCalls). const fcStep = interaction. steps . find ( s => s. type === "function_call" ); if (fcStep && fcStep. name === "getStockPrice" ) { const tickerArg = fcStep. arguments . ticker as string ; const price = getStockPrice ({ ticker : tickerArg }); // Turn 2: Submit the result back as a function_result step. Reference the // originating call via call_id=fcStep.id, and pass tools again (turn-scoped). const finalTurn = await ai. interactions . create ({ agent : "your-agent-id" , input : [{ type : "function_result" , name : fcStep. name ,