Esecuzione in background

Per le attività di lunga durata come ricerche approfondite, ragionamenti complessi o esecuzioni di agenti in più passaggi, i timeout di connessione possono interrompere le richieste HTTP standard (che in genere si chiudono dopo 60 secondi). L'API Interactions fornisce l'esecuzione in background per eseguire queste attività in modo asincrono.

Per consentire all'interazione di essere eseguita fino al completamento dell'attività sul server, imposta "background": true durante la creazione dell'interazione. L'API restituisce immediatamente un ID interazione, che le applicazioni client possono utilizzare per eseguire il polling dello stato, trasmettere in streaming l'avanzamento o riconnettersi a uno stream disconnesso.

L'esecuzione in background è supportata per i modelli Gemini standard (come gemini-3.8-flash e gemini-3.1-pro-preview) e gli agenti gestiti (come antigravity-preview-09-2026).

Crea un'interazione in background

Per avviare un'interazione in background, imposta il parametro background su true durante la creazione della risorsa.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.8-flash",
    input="Write a guide on space exploration.",
    background=True,
)
print(f"Created background interaction ID: {interaction.id}")

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.8-flash",
    input: "Write a guide on space exploration.",
    background: true,
});
console.log(`Created background interaction ID: ${interaction.id}`);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;

Client client = new Client();

CreateModelInteraction params =
    CreateModelInteraction.builder()
        .model("gemini-3.8-flash")
        .input(InteractionsInput.of("Write a guide on space exploration."))
        .background(true)
        .build();

Interaction interaction =
    client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println("Created background interaction ID: " + interaction.id().orElse(""));

REST

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "model": "gemini-3.8-flash",
    "input": "Write a guide on space exploration.",
    "background": true
  }'

Come funziona l'esecuzione in background

Quando crei un'interazione in background, l'attività viene eseguita in modo asincrono sul server. L'interazione passa attraverso vari stati di esecuzione:

  • in_progress: il server sta eseguendo attivamente l'interazione (ad esempio eseguendo codice o ricerche).
  • requires_action: l'interazione è in pausa e attende l'input del client (ad esempio la conferma dell'esecuzione di uno strumento o la risposta a una domanda).
  • completed: l'interazione è terminata correttamente e l'output è disponibile.
  • failed: si è verificato un errore durante l'esecuzione (ad esempio errore dello strumento o limiti di frequenza).
  • cancelled: una richiesta client ha interrotto l'esecuzione.

Casi d'uso

Utilizza l'esecuzione in background per:

  • Esecuzioni di agenti:attività che richiedono l'esecuzione di codice, la navigazione web o l'orchestrazione di sub-agenti (ad esempio antigravity-preview-09-2026).

  • Deep Research: viene eseguito utilizzando deep-research-preview-04-2026 o deep-research-max-preview-04-2026, che richiedono diversi minuti.

  • Motivazione lunga: attività in cui i passaggi di ragionamento del modello superano i limiti standard di connessione HTTP.

Recuperare i risultati

Ottieni i risultati dell'interazione in background utilizzando il polling o lo streaming.

Pattern di polling (non bloccante)

Il polling controlla periodicamente lo stato dell'interazione utilizzando richieste GET non bloccanti finché non raggiunge uno stato terminale.

Python

import time
from google import genai

client = genai.Client()

interaction = client.interactions.get(id="YOUR_INTERACTION_ID")

while interaction.status == "in_progress":
    time.sleep(5)
    interaction = client.interactions.get(id=interaction.id)

if interaction.status == "completed":
    print(interaction.output_text)
else:
    print(f"Finished with status: {interaction.status}")

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

let interaction = await client.interactions.get("YOUR_INTERACTION_ID");

while (interaction.status === "in_progress") {
    await new Promise(resolve => setTimeout(resolve, 5000));
    interaction = await client.interactions.get(interaction.id);
}

if (interaction.status === "completed") {
    console.log(interaction.output_text);
} else {
    console.log(`Finished with status: ${interaction.status}`);
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionStatus;
import com.google.genai.gaos.models.operations.GetInteractionByIdRequest;

Client client = new Client();

Interaction interaction =
    client.interactions
        .get(GetInteractionByIdRequest.builder().id("YOUR_INTERACTION_ID").build())
        .interaction()
        .get();

while (InteractionStatus.IN_PROGRESS.equals(interaction.status().orElse(null))) {
  Thread.sleep(5000);
  interaction =
      client.interactions
          .get(GetInteractionByIdRequest.builder().id(interaction.id().get()).build())
          .interaction()
          .get();
}

if (InteractionStatus.COMPLETED.equals(interaction.status().orElse(null))) {
  System.out.println(interaction.outputText().orElse(""));
} else {
  System.out.println(
      "Finished with status: " + interaction.status().map(InteractionStatus::value).orElse(""));
}

REST

curl -X GET "https://generativelanguage.googleapis.com/v1beta/interactions/YOUR_INTERACTION_ID" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20"

Pattern di streaming

Se un'interruzione di rete disconnette uno stream, lo streaming può riprendere dall'ultimo evento ricevuto. Ogni delta contiene un event_id univoco nel payload. Se passi questo ID come last_event_id, lo stream riprende da quell'evento.

Python

import time
from google import genai

client = genai.Client()
interaction_id = "YOUR_INTERACTION_ID"

def stream_with_reconnect(interaction_id: str):
    last_event_id = None
    while True:
        try:
            # Retrieve the stream. If resuming, pass last_event_id
            stream = client.interactions.get(
                id=interaction_id,
                stream=True,
                last_event_id=last_event_id
            )

            for event in stream:
                # Log event updates and capture event_id if present
                if event.event_id:
                    last_event_id = event.event_id

                if event.event_type == "step.delta" and event.delta.type == "text":
                    print(event.delta.text, end="", flush=True)

                if event.event_type == "interaction.completed":
                    return

        except Exception as e:
            print(f"\n[Connection lost: {e}. Reconnecting in 3s...]")
            time.sleep(3)

stream_with_reconnect(interaction_id)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});
const interactionId = "YOUR_INTERACTION_ID";

async function streamWithReconnect(id) {
    let lastEventId = undefined;
    while (true) {
        try {
            // Retrieve the stream. If resuming, pass last_event_id in options
            const stream = await client.interactions.get(id, {
                stream: true,
                last_event_id: lastEventId
            });

            for await (const event of stream) {
                // Capture event_id if present
                const idVal = event.event_id || event.id;
                if (idVal) {
                    lastEventId = idVal;
                }

                if (event.event_type === "step.delta" && event.delta?.type === "text") {
                    process.stdout.write(event.delta.text);
                }

                if (event.event_type === "interaction.completed") {
                    return;
                }
            }
        } catch (error) {
            console.log(`\n[Connection lost: ${error.message}. Reconnecting in 3s...]`);
            await new Promise(resolve => setTimeout(resolve, 3000));
        }
    }
}

await streamWithReconnect(interactionId);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.InteractionCompletedEvent;
import com.google.genai.gaos.models.interactions.InteractionSSEEvent;
import com.google.genai.gaos.models.interactions.InteractionSSEStreamEvent;
import com.google.genai.gaos.models.interactions.StepDelta;
import com.google.genai.gaos.models.interactions.TextDelta;
import com.google.genai.gaos.models.operations.GetInteractionByIdRequest;
import com.google.genai.gaos.utils.EventStream;

Client client = new Client();
String interactionId = "YOUR_INTERACTION_ID";
String lastEventId = null;
boolean completed = false;

while (!completed) {
  try (EventStream<InteractionSSEStreamEvent> stream =
      client.interactions
          .get(
              GetInteractionByIdRequest.builder()
                  .id(interactionId)
                  .stream(true)
                  .lastEventId(lastEventId)
                  .build())
          .events()) {
    for (InteractionSSEStreamEvent streamEvent : stream) {
      InteractionSSEEvent event = streamEvent.data().orElse(null);
      if (event instanceof StepDelta) {
        StepDelta stepDelta = (StepDelta) event;
        if (stepDelta.eventId().isPresent()) {
          lastEventId = stepDelta.eventId().get();
        }
        if (stepDelta.delta().isPresent() && stepDelta.delta().get() instanceof TextDelta) {
          System.out.print(((TextDelta) stepDelta.delta().get()).text().orElse(""));
          System.out.flush();
        }
      } else if (event instanceof InteractionCompletedEvent) {
        completed = true;
        break;
      }
    }
  } catch (Exception e) {
    System.out.println("\n[Connection lost: " + e.getMessage() + ". Reconnecting in 3s...]");
    Thread.sleep(3000);
  }
}

REST

curl -N -X GET "https://generativelanguage.googleapis.com/v1beta/interactions/YOUR_INTERACTION_ID?stream=true&last_event_id=YOUR_LAST_EVENT_ID" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20"

Conversazioni a più turni

Le interazioni successive possono concatenarsi a una conversazione in background utilizzando previous_interaction_id, nel rispetto di questi vincoli:

  1. Le esecuzioni attive sono bloccate:il concatenamento di un'interazione successiva a una con stato in_progress restituisce un errore 400 Bad Request. Attendi che l'interazione raggiunga lo stato completed prima di iniziare la successiva.
  2. Parametro dell'ambiente per gli agenti gestiti:quando si concatenano le interazioni per gli agenti gestiti (ad esempio antigravity-preview-09-2026), le richieste devono includere sia previous_interaction_id che environment.

I seguenti esempi mostrano come concatenare le interazioni:

Python

import time
from google import genai

client = genai.Client()
agent_model = "antigravity-preview-09-2026"

# First interaction: Provision sandbox environment and execute first instruction
interaction1 = client.interactions.create(
    agent=agent_model,
    input="Create a folder named project/ and write hello.py inside.",
    environment="remote",
    background=True
)

# Wait for completion
while True:
    check = client.interactions.get(id=interaction1.id)
    if check.status != "in_progress":
        break
    time.sleep(2)

# Second interaction: Chain using previous_interaction_id and environment
interaction2 = client.interactions.create(
    agent=agent_model,
    input="List all files in the project/ directory.",
    previous_interaction_id=interaction1.id,
    environment="remote",
    background=True
)

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});
const agentModel = "antigravity-preview-09-2026";

// First interaction: Provision sandbox environment and execute first instruction
const interaction1 = await client.interactions.create({
    agent: agentModel,
    input: "Create a folder named project/ and write hello.py inside.",
    environment: "remote",
    background: true
});

// Wait for completion
while (true) {
    const check = await client.interactions.get(interaction1.id);
    if (check.status !== "in_progress") {
        break;
    }
    await new Promise(resolve => setTimeout(resolve, 2000));
}

// Second interaction: Chain using previous_interaction_id and environment
const interaction2 = await client.interactions.create({
    agent: agentModel,
    input: "List all files in the project/ directory.",
    previous_interaction_id: interaction1.id,
    environment: "remote",
    background: true
});

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.CreateModelInteraction;
import com.google.genai.gaos.models.interactions.CreateModelInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionStatus;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import com.google.genai.gaos.models.operations.GetInteractionByIdRequest;

Client client = new Client();
String agentModel = "antigravity-preview-09-2026";

// First interaction: Provision sandbox environment and execute first instruction
CreateModelInteraction params1 =
    CreateModelInteraction.builder()
        .model(agentModel)
        .input(InteractionsInput.of("Create a folder named project/ and write hello.py inside."))
        .environment(CreateModelInteractionEnvironment.of("remote"))
        .background(true)
        .build();

Interaction interaction1 =
    client.interactions.create(CreateInteractionRequestBody.of(params1)).interaction().get();

// Wait for completion
while (true) {
  Interaction check =
      client.interactions
          .get(GetInteractionByIdRequest.builder().id(interaction1.id().get()).build())
          .interaction()
          .get();
  if (!InteractionStatus.IN_PROGRESS.equals(check.status().orElse(null))) {
    break;
  }
  Thread.sleep(2000);
}

// Second interaction: Chain using previousInteractionId and environment
CreateModelInteraction params2 =
    CreateModelInteraction.builder()
        .model(agentModel)
        .input(InteractionsInput.of("List all files in the project/ directory."))
        .previousInteractionId(interaction1.id().get())
        .environment(CreateModelInteractionEnvironment.of("remote"))
        .background(true)
        .build();

Interaction interaction2 =
    client.interactions.create(CreateInteractionRequestBody.of(params2)).interaction().get();

REST

# Chain second interaction (Make sure FIRST_INTERACTION_ID has status 'completed')
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Api-Revision: 2026-05-20" \
  -d '{
    "agent": "antigravity-preview-09-2026",
    "input": "List all files in the project/ directory.",
    "previous_interaction_id": "FIRST_INTERACTION_ID",
    "environment": "remote",
    "background": true
  }'

Annullamento ed eliminazione

Controlla le esecuzioni in corso e gestisci lo spazio di archiviazione utilizzando le richieste di annullamento ed eliminazione:

  • Annulla (POST /interactions/{id}/cancel): interrompe l'attività in esecuzione. Lo stato passa a cancelled. Le azioni di pulizia sul server possono causare un leggero ritardo prima degli aggiornamenti dello stato nelle richieste GET.

  • Elimina (DELETE /interactions/{id}): rimuove i record di interazione dal server. Le successive richieste GET restituiscono un errore 404 Not Found.

Python

from google import genai

client = genai.Client()

# Cancel a running interaction
client.interactions.cancel(id="YOUR_INTERACTION_ID")

# Delete the interaction record entirely
client.interactions.delete(id="YOUR_INTERACTION_ID")

JavaScript

import { GoogleGenAI } from "@google/genai";

const client = new GoogleGenAI({});

// Cancel a running interaction
await client.interactions.cancel("YOUR_INTERACTION_ID");

// Delete the interaction record entirely
await client.interactions.delete("YOUR_INTERACTION_ID");

Java

import com.google.genai.Client;

Client client = new Client();

// Cancel a running interaction
client.interactions.cancel("YOUR_INTERACTION_ID");

// Delete the interaction record entirely
client.interactions.delete("YOUR_INTERACTION_ID");

REST

# Cancel the interaction
curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions/YOUR_INTERACTION_ID/cancel" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20"

# Delete the interaction
curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/interactions/YOUR_INTERACTION_ID" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -H "Api-Revision: 2026-05-20"

Passaggi successivi