Gemini 3.8 Flash është tani në dispozicion. Provojeni .

Google përdor teknologjinë e IA-së për të përkthyer përmbajtjet në gjuhën tënde të preferuar. Përkthimet nga IA-ja mund të përmbajnë gabime.

Po ndërtohen agjentët e menaxhuar

Agjentët e menaxhuar në Gemini API të lejojnë të zgjerosh agjentin Antigravity me udhëzimet, aftësitë dhe të dhënat e tua. Mund ta personalizosh agjentin në linjë në kohën e ndërveprimit ose ta ruash konfigurimin si një agjent të menaxhuar që e aktivizon me ID.

Personalizo agjentin e Antigravity

Mënyra më e shpejtë për të ndërtuar një agjent të personalizuar është të kalosh konfigurimin tënd në linjë gjatë krijimit të një ndërveprimi të ri pa kërkuar asnjë hap regjistrimi. Mund ta zgjerosh agjentin në disa mënyra kryesore:

Zgjedhja e modelit: Zgjidh modelin bazë të Gemini nëpërmjet agent_config (parazgjedhja është Gemini 3.8 Flash).
Udhëzimet e sistemit: Kaloni tekstin e integruar nëpërmjet system_instruction për të formuar sjelljen.
Veglat: Zëvendëso veglat e parazgjedhura (ekzekutimi i kodit, kërkimi, konteksti i URL-së), regjistro serverët e largët MCP ose përcakto funksione të personalizuara (thirrja e funksioneve).
Skedarët dhe aftësitë: Monto skedarët si AGENTS.md dhe SKILL.md në mjedis.

Këtu është një shembull i kalimit të të trejave në linjë:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Analyze the Q1 revenue data and create a slide deck.",
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Analyze the Q1 revenue data and create a slide deck.",
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/AGENTS.md")
            .content("Always use matplotlib for charts. Include a summary table in every report.")
            .build(),
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/skills/slide-maker/SKILL.md")
            .content("---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.")
            .build()
    ))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Analyze the Q1 revenue data and create a slide deck."))
    .systemInstruction("You are a data analyst. Always include visualizations and export results as PDF.")
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    env := interactions.Environment{
        Sources: []interactions.Source{
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/AGENTS.md"),
                Content: genai.Ptr("Always use matplotlib for charts. Include a summary table in every report."),
            },
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/skills/slide-maker/SKILL.md"),
                Content: genai.Ptr("---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."),
            },
        },
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:             interactions.AgentOption("antigravity-preview-09-2026"),
            Input:             interactions.NewInteractionsInput("Analyze the Q1 revenue data and create a slide deck."),
            SystemInstruction: genai.Ptr("You are a data analyst. Always include visualizations and export results as PDF."),
            Environment:       genai.Ptr(interactions.NewCreateAgentInteractionEnvironment(env)),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "agent": "antigravity-preview-09-2026",
    "input": "Analyze the Q1 revenue data and create a slide deck.",
    "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
    "environment": {
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report."
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
            }
        ]
    }
}'

Gjithçka përcaktohet në kohën e ndërveprimit. Nuk ka nevojë të regjistrosh asgjë në fillim. Brezi i agjentit të antigravitetit ofron kohën e ekzekutimit (ekzekutimi i kodit, menaxhimi i skedarëve, qasja në ueb) dhe shtresat e tua të konfigurimit mbi të.

Veglat dhe udhëzimet e sistemit

Mund të personalizosh sjelljen dhe aftësitë e agjentit për një ndërveprim specifik duke përdorur parametrat system_instruction dhe tools.

Udhëzimet e sistemit: Përdor parametrin system_instruction për të kaluar tekstin e integruar që formëson sjelljen e agjentit. Kjo është ideale për rregullime të shpejta që dëshiron t'i ndryshosh për çdo telefonatë. system_instruction dhe AGENTS.md janë shtesë; të dyja zbatohen kur janë të pranishme.
Veglat: Si parazgjedhje, agjenti i Antigravity ka qasje te code_execution, google_search dhe url_context. Mund ta zëvendësosh këtë listë duke kaluar parametrin tools në kohën e ndërveprimit. Gjithashtu, mund të regjistrosh serverë të largët MCP ose të përcaktosh funksione të personalizuara (thirrja e funksioneve) për të lidhur agjentin me API-të dhe bazat e të dhënave të tua. Për detaje të plota mbi veglat e disponueshme, shiko Antigravity Agent: Veglat e mbështetura.

Personalizimi bazuar në skedar

Struktura e direktorisë së agjentit

Edhe pse mund të kalosh konfigurimin në linjë, ne rekomandojmë organizimin e skedarëve të agjentit tënd në një direktori të strukturuar. Kjo e bën më të lehtë menaxhimin, kontrollin e versionit dhe montimin në mjedisin e agjentit.

Një direktori tipike e projektit të agjentit duket si kjo:

my-agent/
├── AGENTS.md        # Instructions on how the agent should operate
├── skills/          # Custom skills (subfolders and SKILL.md files)
│   └── slide-maker/
│       └── SKILL.md
└── workspace/       # Initial data files and knowledge

Mjedisi ekzekutues i Antigravity skanon .agents/ (dhe rrënjën e mjedisit) për këta skedarë.

AGENTS.md

Agenti ngarkon automatikisht .agents/AGENTS.md (ose /.agents/AGENTS.md) nga mjedisi si udhëzime të sistemit në nisje. Përdor AGENTS.md për përkufizime të personazheve të gjata, udhëzime të detajuara dhe udhëzime që dëshiron të kontrollosh versionin së bashku me kodin tënd.

Monto një AGENTS.md duke përdorur një burim të ndërfutur:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Analyze the Q1 revenue data and create a report.",
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Analyze the Q1 revenue data and create a report.",
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/AGENTS.md")
            .content("Always use matplotlib for charts. Include a summary table in every report.")
            .build()
    ))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Analyze the Q1 revenue data and create a report."))
    .systemInstruction("You are a data analyst. Always include visualizations and export results as PDF.")
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    env := interactions.Environment{
        Sources: []interactions.Source{
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/AGENTS.md"),
                Content: genai.Ptr("Always use matplotlib for charts. Include a summary table in every report."),
            },
        },
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:             interactions.AgentOption("antigravity-preview-09-2026"),
            Input:             interactions.NewInteractionsInput("Analyze the Q1 revenue data and create a report."),
            SystemInstruction: genai.Ptr("You are a data analyst. Always include visualizations and export results as PDF."),
            Environment:       genai.Ptr(interactions.NewCreateAgentInteractionEnvironment(env)),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "antigravity-preview-09-2026",
      "input": "Analyze the Q1 revenue data and create a report.",
      "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
      "environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "inline",
                  "target": ".agents/AGENTS.md",
                  "content": "Always use matplotlib for charts. Include a summary table in every report."
              }
          ]
      }
  }'

Aftësitë: SKILL.md

Aftësitë janë skedarë që zgjerojnë aftësitë e agjentit. Vendosi ato nën .agents/skills/<skill-name>/SKILL.md dhe pajisja e zbulon dhe i regjistron automatikisht ato.

.agents/
├── AGENTS.md
└── skills/
    └── slide-maker/
        └── SKILL.md

Monto një aftësi duke përdorur një burim të ndërfutur:

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Create a presentation about our Q1 results.",
    system_instruction="You create presentations from data.",
    environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
            },
        ],
    },
)

print(interaction.output_text)

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Create a presentation about our Q1 results.",
    system_instruction: "You create presentations from data.",
    environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html",
            },
        ],
    },
}, { timeout: 300000 });

console.log(interaction.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/skills/slide-maker/SKILL.md")
            .content("---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html")
            .build()
    ))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Create a presentation about our Q1 results."))
    .systemInstruction("You create presentations from data.")
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction interaction = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(interaction.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    env := interactions.Environment{
        Sources: []interactions.Source{
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/skills/slide-maker/SKILL.md"),
                Content: genai.Ptr("---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html"),
            },
        },
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:             interactions.AgentOption("antigravity-preview-09-2026"),
            Input:             interactions.NewInteractionsInput("Create a presentation about our Q1 results."),
            SystemInstruction: genai.Ptr("You create presentations from data."),
            Environment:       genai.Ptr(interactions.NewCreateAgentInteractionEnvironment(env)),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "antigravity-preview-09-2026",
      "input": "Create a presentation about our Q1 results.",
      "system_instruction": "You create presentations from data.",
      "environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "inline",
                  "target": ".agents/skills/slide-maker/SKILL.md",
                  "content": "---\nname: slide-maker\ndescription: Create HTML slide decks\n---\n# Slide Maker\n\nWhen asked to create a presentation:\n1. Analyze the input data\n2. Create an HTML slide deck with reveal.js\n3. Save to /workspace/output/slides.html"
              }
          ]
      }
  }'

Aftësitë e ngarkuara nga .agents/skills/ dhe /.agents/skills/ zbulohen automatikisht.

Krijo një agjent të menaxhuar

Pasi të kesh përsëritur konfigurimin, mund ta krijosh atë si një agjent të menaxhuar me agents.create. Kjo të lejon të thërrasësh agjentin me ID pa përsëritur konfigurimin çdo herë.

id që specifikon kur krijon një agjent të menaxhuar duhet të jetë unik për projektin tënd dhe nuk duhet të fillojë me prefikse të rezervuara (p.sh. google-, gemini-). Shih Kufizimet e ID-së së agjentit për listën e plotë të prefikseve të kufizuara.

Nga burimet

Specifiko base_agent, id, agent_config, system_instruction dhe base_environment me burime. Platforma përgatit një mjedis të ri testimi me skedarët e tu në çdo thirrje. Shiko Mjediset për llojet e disponueshme të burimeve (Git, GCS, inline).

Python

from google import genai

client = genai.Client()

agent = client.agents.create(
    id="data-analyst",
    base_agent="antigravity-preview-09-2026",
    agent_config={
        "type": "antigravity",
        "model": "gemini-3.8-flash",
    },
    system_instruction="You are a data analyst. Always include visualizations and export results as PDF.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
            {
                "type": "repository",
                "source": "https://github.com/my-org/analysis-templates",
                "target": "/workspace/templates",
            },
        ],
    },
)

print(f"Created agent: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const agent = await client.agents.create({
    id: "data-analyst",
    base_agent: "antigravity-preview-09-2026",
    agent_config: {
        type: "antigravity",
        model: "gemini-3.8-flash",
    },
    system_instruction: "You are a data analyst. Always include visualizations and export results as PDF.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "inline",
                target: ".agents/AGENTS.md",
                content: "Always use matplotlib for charts. Include a summary table in every report.",
            },
            {
                type: "inline",
                target: ".agents/skills/slide-maker/SKILL.md",
                content: "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.",
            },
            {
                type: "repository",
                source: "https://github.com/my-org/analysis-templates",
                target: "/workspace/templates",
            },
        ],
    },
});

console.log(`Created agent: ${agent.id}`);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.agents.Agent;
import com.google.genai.gaos.models.agents.AgentConfig;
import com.google.genai.gaos.models.agents.BaseEnvironment;
import com.google.genai.gaos.models.interactions.AntigravityAgentConfig;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import java.util.List;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/AGENTS.md")
            .content("Always use matplotlib for charts. Include a summary table in every report.")
            .build(),
        Source.builder()
            .type(SourceType.INLINE)
            .target(".agents/skills/slide-maker/SKILL.md")
            .content("---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results.")
            .build(),
        Source.builder()
            .type(SourceType.REPOSITORY)
            .source("https://github.com/my-org/analysis-templates")
            .target("/workspace/templates")
            .build()
    ))
    .build();

Agent agentParams = Agent.builder()
    .id("data-analyst")
    .baseAgent("antigravity-preview-09-2026")
    .agentConfig(AgentConfig.of(
        AntigravityAgentConfig.builder()
            .model("gemini-3.8-flash")
            .build()
    ))
    .systemInstruction("You are a data analyst. Always include visualizations and export results as PDF.")
    .baseEnvironment(BaseEnvironment.of(env))
    .build();

Agent agent = client.agents.create(agentParams).agent().get();
System.out.println("Created agent: " + agent.id().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/agents"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    env := interactions.Environment{
        Sources: []interactions.Source{
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/AGENTS.md"),
                Content: genai.Ptr("Always use matplotlib for charts. Include a summary table in every report."),
            },
            {
                Type:    interactions.SourceTypeInline.ToPointer(),
                Target:  genai.Ptr(".agents/skills/slide-maker/SKILL.md"),
                Content: genai.Ptr("---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."),
            },
            {
                Type:   interactions.SourceTypeRepository.ToPointer(),
                Source: genai.Ptr("https://github.com/my-org/analysis-templates"),
                Target: genai.Ptr("/workspace/templates"),
            },
        },
    }

    res, err := client.Agents.Create(ctx, operations.CreateAgentRequest{
        Body: agents.Agent{
            ID:        genai.Ptr("data-analyst"),
            BaseAgent: genai.Ptr("antigravity-preview-09-2026"),
            AgentConfig: genai.Ptr(agents.NewAgentConfig(interactions.AntigravityAgentConfig{
                Model: genai.Ptr("gemini-3.8-flash"),
            })),
            SystemInstruction: genai.Ptr("You are a data analyst. Always include visualizations and export results as PDF."),
            BaseEnvironment:   genai.Ptr(agents.NewBaseEnvironment(env)),
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Printf("Created agent: %s\n", *res.Agent.ID)
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
-H "Content-Type: application/json" \
-H "x-goog-api-key: $GEMINI_API_KEY" \
-d '{
    "id": "data-analyst",
    "base_agent": "antigravity-preview-09-2026",
    "agent_config": {
        "type": "antigravity",
        "model": "gemini-3.8-flash"
    },
    "system_instruction": "You are a data analyst. Always include visualizations and export results as PDF.",
    "base_environment": {
        "type": "remote",
        "sources": [
            {
                "type": "inline",
                "target": ".agents/AGENTS.md",
                "content": "Always use matplotlib for charts. Include a summary table in every report."
            },
            {
                "type": "inline",
                "target": ".agents/skills/slide-maker/SKILL.md",
                "content": "---\nname: slide-maker\n---\n# Slide Maker\nCreate HTML slide decks from data analysis results."
            },
            {
                "type": "repository",
                "source": "https://github.com/my-org/analysis-templates",
                "target": "/workspace/templates"
            }
        ]
    }
}'

Nga një mjedis ekzistues (pirun)

Përsërit me agjentin bazë të Antigravity derisa mjedisi të jetë i duhuri (paketimet e instaluara, skedarët në vend), më pas krijo një degë të tij në një agjent të menaxhuar.

Python

from google import genai

client = genai.Client()

# Step 1: set up the environment interactively
interaction = client.interactions.create(
    agent="antigravity-preview-09-2026",
    input="Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
    environment="remote",
)

# Step 2: fork that environment into a managed agent

agent = client.agents.create(
    id="my-data-analyst",
    base_agent="antigravity-preview-09-2026",
    system_instruction="You are a data analyst. Use the template at /workspace/template.py for all reports.",
    base_environment=interaction.environment_id,
)

print(f"Forked agent successfully: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-09-2026",
    input: "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
    environment: "remote",
}, { timeout: 300000 });

const agent = await client.agents.create({
    id: "my-data-analyst",
    base_agent: "antigravity-preview-09-2026",
    system_instruction: "You are a data analyst. Use the template at /workspace/template.py for all reports.",
    base_environment: interaction.environment_id,
});

console.log(`Forked agent successfully: ${agent.id}`);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.agents.Agent;
import com.google.genai.gaos.models.agents.BaseEnvironment;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
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();

// Step 1: set up the environment interactively
CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("antigravity-preview-09-2026"))
    .input(InteractionsInput.of("Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py."))
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();

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

// Step 2: fork that environment into a managed agent
Agent agentParams = Agent.builder()
    .id("my-data-analyst")
    .baseAgent("antigravity-preview-09-2026")
    .systemInstruction("You are a data analyst. Use the template at /workspace/template.py for all reports.")
    .baseEnvironment(BaseEnvironment.of(interaction.environmentId().orElse("")))
    .build();

Agent agent = client.agents.create(agentParams).agent().get();
System.out.println("Forked agent successfully: " + agent.id().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/agents"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    // Step 1: set up the environment interactively
    intRes, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:       interactions.AgentOption("antigravity-preview-09-2026"),
            Input:       interactions.NewInteractionsInput("Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py."),
            Environment: genai.Ptr(interactions.NewCreateAgentInteractionEnvironment("remote")),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    interaction := intRes.Interaction

    // Step 2: fork that environment into a managed agent
    agentRes, err := client.Agents.Create(ctx, operations.CreateAgentRequest{
        Body: agents.Agent{
            ID:                genai.Ptr("my-data-analyst"),
            BaseAgent:         genai.Ptr("antigravity-preview-09-2026"),
            SystemInstruction: genai.Ptr("You are a data analyst. Use the template at /workspace/template.py for all reports."),
            BaseEnvironment:   genai.Ptr(agents.NewBaseEnvironment(*interaction.EnvironmentID)),
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Printf("Forked agent successfully: %s\n", *agentRes.Agent.ID)
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "antigravity-preview-09-2026",
      "input": "Install pandas, matplotlib, and seaborn. Create an analysis template at /workspace/template.py.",
      "environment": "remote"
  }'

Me rregullat e rrjetit

Mund të kyçësh qasjen dalëse ose të injektosh kredencialet kur ruan një agjent të menaxhuar. Për skemën e plotë të listës së lejimeve, modelet e kredencialeve dhe kartat e zëvendësimit, shiko Mjediset: Konfigurimi i rrjetit.

Referoju një kredencialeje të ruajtur sipas ID-së në një rregull të listës së lejimeve ("credential": "github-production") dhe proksi i daljes injekton sekretin në kohën e kërkesës, në mënyrë që ai të mos përfundojë asnjëherë në përkufizimin e agjentit. Ky shembull e vendos titullin në rresht me transform në vend të kësaj. Proksi i zbaton të dyja format në të njëjtën mënyrë, një kredencial të lejon gjithashtu të ripërdorësh sekretin nëpër agjentë dhe ta ndryshosh atë në një vend të vetëm.

Shembulli i mëposhtëm krijon një agjent të issue-resolver që mund të qaset vetëm në GitHub dhe PyPI, me kredencialet e injektuara për GitHub:

Python

from google import genai

client = genai.Client()

agent = client.agents.create(
    id="issue-resolver",
    base_agent="antigravity-preview-09-2026",
    system_instruction="You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/my-org/backend",
                "target": "/workspace/repo",
            }
        ],
        "network": {
            "allowlist": [
                {
                    "domain": "api.github.com",
                    "transform": {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    },
                },
                {"domain": "pypi.org"},
            ]
        },
    },
)

print(f"Created issue-resolver agent successfully: {agent.id}")

JavaScript

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

const client = new GoogleGenAI({});

const agent = await client.agents.create({
    id: "issue-resolver",
    base_agent: "antigravity-preview-09-2026",
    system_instruction: "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/my-org/backend",
                target: "/workspace/repo",
            }
        ],
        network: {
            allowlist: [
                {
                    domain: "api.github.com",
                    transform: {
                        "Authorization": "Basic YOUR_BASE64_TOKEN"
                    },
                },
                { domain: "pypi.org" },
            ]
        }
    },
});

console.log(`Created issue-resolver agent successfully: ${agent.id}`);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.agents.Agent;
import com.google.genai.gaos.models.agents.BaseEnvironment;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Source;
import com.google.genai.gaos.models.interactions.SourceType;
import com.google.genai.gaos.models.interactions.Transform;
import java.util.List;
import java.util.Map;

Client client = new Client();

Environment env = Environment.builder()
    .sources(List.of(
        Source.builder()
            .type(SourceType.REPOSITORY)
            .source("https://github.com/my-org/backend")
            .target("/workspace/repo")
            .build()
    ))
    .network(Network.of(
        EnvironmentNetworkEgressAllowlist.builder()
            .allowlist(Allowlist.of(List.of(
                AllowlistEntry.builder()
                    .domain("api.github.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Basic YOUR_BASE64_TOKEN"
                    )))
                    .build(),
                AllowlistEntry.builder().domain("pypi.org").build()
            )))
            .build()
    ))
    .build();

Agent agentParams = Agent.builder()
    .id("issue-resolver")
    .baseAgent("antigravity-preview-09-2026")
    .systemInstruction("You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.")
    .baseEnvironment(BaseEnvironment.of(env))
    .build();

Agent agent = client.agents.create(agentParams).agent().get();
System.out.println("Created issue-resolver agent successfully: " + agent.id().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/agents"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    env := interactions.Environment{
        Sources: []interactions.Source{
            {
                Type:   interactions.SourceTypeRepository.ToPointer(),
                Source: genai.Ptr("https://github.com/my-org/backend"),
                Target: genai.Ptr("/workspace/repo"),
            },
        },
        Network: genai.Ptr(interactions.NewNetwork(interactions.EnvironmentNetworkEgressAllowlist{
            Allowlist: genai.Ptr(interactions.NewAllowlist([]interactions.AllowlistEntry{
                {
                    Domain: "api.github.com",
                    Transform: genai.Ptr(interactions.NewTransform(map[string]string{
                        "Authorization": "Basic YOUR_BASE64_TOKEN",
                    })),
                },
                {
                    Domain: "pypi.org",
                },
            })),
        })),
    }

    res, err := client.Agents.Create(ctx, operations.CreateAgentRequest{
        Body: agents.Agent{
            ID:                genai.Ptr("issue-resolver"),
            BaseAgent:         genai.Ptr("antigravity-preview-09-2026"),
            SystemInstruction: genai.Ptr("You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR."),
            BaseEnvironment:   genai.Ptr(agents.NewBaseEnvironment(env)),
        },
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Printf("Created issue-resolver agent successfully: %s\n", *res.Agent.ID)
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/agents" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "id": "issue-resolver",
      "base_agent": "antigravity-preview-09-2026",
      "system_instruction": "You resolve GitHub issues. Clone the repo, find the bug, write the fix, run the tests, and open a PR.",
      "base_environment": {
          "type": "remote",
          "sources": [
              {
                  "type": "repository",
                  "source": "https://github.com/my-org/backend",
                  "target": "/workspace/repo"
              }
          ],
          "network": {
              "allowlist": [
                  {
                      "domain": "api.github.com",
                      "transform": {
                          "Authorization": "Basic YOUR_BASE64_TOKEN"
                      }
                  },
                  {"domain": "pypi.org"}
              ]
          }
      }
  }'

Thirr agjentin

Telefono agjentin tënd të menaxhuar me ID-në e agjentit duke krijuar një ndërveprim të ri. Çdo thirrje krijon një degë të mjedisit bazë, kështu që çdo ekzekutim fillon i pastër.

Python

result = client.interactions.create(
    agent="data-analyst",
    input="Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
    environment="remote",
)

print(result.output_text)

JavaScript

const result = await client.interactions.create({
    agent: "data-analyst",
    input: "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
    environment: "remote",
}, { timeout: 300000 });

console.log(result.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
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();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("data-analyst"))
    .input(InteractionsInput.of("Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck."))
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();

Interaction result = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(result.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:       interactions.AgentOption("data-analyst"),
            Input:       interactions.NewInteractionsInput("Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck."),
            Environment: genai.Ptr(interactions.NewCreateAgentInteractionEnvironment("remote")),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "data-analyst",
      "input": "Analyze Q1 revenue data from /workspace/templates/sample.csv and create a slide deck.",
      "environment": "remote"
  }'

Për bisedat me shumë kthesa dhe transmetimin, shiko Fillimin e shpejtë. Të njëjtat modele të previous_interaction_id dhe environment zbatohen për agjentët e menaxhuar.

Agjentët e menaxhuar mbështesin gjithashtu ekzekutimin dhe anulimin në sfond. Për detaje dhe shembuj kodesh, shiko Antigravity Agent: Ekzekutimi në sfond.

Konfigurimi i mbivendosjes në thirrje

Mund të zëvendësosh konfigurimin e parazgjedhur të rrjetit system_instruction, tools dhe environment të agjentit kur krijon një ndërveprim. Kjo të lejon të modifikosh sjelljen, aftësitë ose kredencialet e agjentit për një ekzekutim specifik pa ndryshuar përkufizimin e ruajtur të agjentit.

Zëvendëso udhëzimet dhe veglat e sistemit

Python

result = client.interactions.create(
    agent="data-analyst",
    input="Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
    system_instruction="You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
    tools=[{"type": "code_execution"}], # Override to only use code execution
    environment="remote",
)
print(result.output_text)

JavaScript

const result = await client.interactions.create({
    agent: "data-analyst",
    input: "Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
    system_instruction: "You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
    tools: [{ type: "code_execution" }], // Override to only use code execution
    environment: "remote",
}, { timeout: 300000 });

console.log(result.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.CodeExecution;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;

Client client = new Client();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("data-analyst"))
    .input(InteractionsInput.of("Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table."))
    .systemInstruction("You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.")
    .tools(List.of(CodeExecution.builder().build())) // Override to only use code execution
    .environment(CreateAgentInteractionEnvironment.of("remote"))
    .build();

Interaction result = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(result.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:             interactions.AgentOption("data-analyst"),
            Input:             interactions.NewInteractionsInput("Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table."),
            SystemInstruction: genai.Ptr("You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides."),
            Tools:             []interactions.Tool{interactions.NewTool(interactions.CodeExecution{})}, // Override to only use code execution
            Environment:       genai.Ptr(interactions.NewCreateAgentInteractionEnvironment("remote")),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "data-analyst",
      "input": "Analyze Q1 revenue data, but do not create a slide deck. Just output a summary table.",
      "system_instruction": "You are a data analyst. Focus ONLY on summary tables. Ignore default instructions about slides.",
      "tools": [{"type": "code_execution"}],
      "environment": "remote"
  }'

Anulo konfigurimin e rrjetit (rifresko kredencialet)

Nëse agjenti yt i menaxhuar ka kredenciale rrjeti të integruara në base_environment, mund t'i zëvendësosh ato në kohën e aktivizimit për të rifreskuar kodet e skaduara ose për të rrotulluar çelësat e API-së. Kaloni një objekt environment me një konfigurim të ri network. Rregullat e reja të rrjetit zëvendësojnë plotësisht ato të mëparshmet për atë ndërveprim. Burimet (skedarët, depotë) e mjedisit bazë ruhen.

Nëse base_environment i referohet një kredencialeje të ruajtur në vend të një kodi të integruar, nuk është e nevojshme të anulosh asgjë. Rrotullo kredencialin me një PATCH dhe çdo agjent që i referohet atij merr sekretin e ri në ekzekutimin e radhës.

Python

# Invoke the agent with a fresh token, overriding the base_environment credentials
result = client.interactions.create(
    agent="issue-resolver",
    input="Fix issue #42 and open a PR.",
    environment={
        "type": "remote",
        "network": {
            "allowlist": [
                {
                    "domain": "api.github.com",
                    "transform": {
                        "Authorization": "Bearer ghp_REFRESHED_TOKEN"
                    },
                },
                {"domain": "pypi.org"},
            ]
        },
    },
)

print(result.output_text)

JavaScript

// Invoke the agent with a fresh token, overriding the base_environment credentials
const result = await client.interactions.create({
    agent: "issue-resolver",
    input: "Fix issue #42 and open a PR.",
    environment: {
        type: "remote",
        network: {
            allowlist: [
                {
                    domain: "api.github.com",
                    transform: {
                        "Authorization": "Bearer ghp_REFRESHED_TOKEN"
                    },
                },
                { domain: "pypi.org" },
            ]
        },
    },
}, { timeout: 300000 });

console.log(result.output_text);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.interactions.AgentOption;
import com.google.genai.gaos.models.interactions.Allowlist;
import com.google.genai.gaos.models.interactions.AllowlistEntry;
import com.google.genai.gaos.models.interactions.CreateAgentInteraction;
import com.google.genai.gaos.models.interactions.CreateAgentInteractionEnvironment;
import com.google.genai.gaos.models.interactions.Environment;
import com.google.genai.gaos.models.interactions.EnvironmentNetworkEgressAllowlist;
import com.google.genai.gaos.models.interactions.Interaction;
import com.google.genai.gaos.models.interactions.InteractionsInput;
import com.google.genai.gaos.models.interactions.Network;
import com.google.genai.gaos.models.interactions.Transform;
import com.google.genai.gaos.models.operations.CreateInteractionRequestBody;
import java.util.List;
import java.util.Map;

Client client = new Client();

// Invoke the agent with a fresh token, overriding the base_environment credentials
Environment env = Environment.builder()
    .network(Network.of(
        EnvironmentNetworkEgressAllowlist.builder()
            .allowlist(Allowlist.of(List.of(
                AllowlistEntry.builder()
                    .domain("api.github.com")
                    .transform(Transform.of(Map.of(
                        "Authorization", "Bearer ghp_REFRESHED_TOKEN"
                    )))
                    .build(),
                AllowlistEntry.builder().domain("pypi.org").build()
            )))
            .build()
    ))
    .build();

CreateAgentInteraction params = CreateAgentInteraction.builder()
    .agent(AgentOption.of("issue-resolver"))
    .input(InteractionsInput.of("Fix issue #42 and open a PR."))
    .environment(CreateAgentInteractionEnvironment.of(env))
    .build();

Interaction result = client.interactions.create(CreateInteractionRequestBody.of(params)).interaction().get();
System.out.println(result.outputText().orElse(""));

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/interactions"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    // Invoke the agent with a fresh token, overriding the base_environment credentials
    env := interactions.Environment{
        Network: genai.Ptr(interactions.NewNetwork(interactions.EnvironmentNetworkEgressAllowlist{
            Allowlist: genai.Ptr(interactions.NewAllowlist([]interactions.AllowlistEntry{
                {
                    Domain: "api.github.com",
                    Transform: genai.Ptr(interactions.NewTransform(map[string]string{
                        "Authorization": "Bearer ghp_REFRESHED_TOKEN",
                    })),
                },
                {
                    Domain: "pypi.org",
                },
            })),
        })),
    }

    res, err := client.Interactions.Create(ctx, operations.CreateInteractionRequest{
        Body: operations.NewCreateInteractionRequestBody(interactions.CreateAgentInteraction{
            Agent:       interactions.AgentOption("issue-resolver"),
            Input:       interactions.NewInteractionsInput("Fix issue #42 and open a PR."),
            Environment: genai.Ptr(interactions.NewCreateAgentInteractionEnvironment(env)),
        }),
    })
    if err != nil {
        log.Fatal(err)
    }
    if res.Interaction.OutputText != nil {
        fmt.Println(*res.Interaction.OutputText)
    }
}

QETËSI

curl -X POST "https://generativelanguage.googleapis.com/v1beta/interactions" \
  -H "Content-Type: application/json" \
  -H "x-goog-api-key: $GEMINI_API_KEY" \
  -d '{
      "agent": "issue-resolver",
      "input": "Fix issue #42 and open a PR.",
      "environment": {
          "type": "remote",
          "network": {
              "allowlist": [
                  {
                      "domain": "api.github.com",
                      "transform": {
                          "Authorization": "Bearer ghp_REFRESHED_TOKEN"
                      }
                  },
                  {"domain": "pypi.org"}
              ]
          }
      }
  }'

Menaxho agjentët

Mund të listosh, të marrësh dhe të fshish agjentët.

Listo agjentët

Python

agents = client.agents.list()
for a in agents.agents:
    print(f"{a.id}: {a.description}")

JavaScript

const agents = await client.agents.list();
if (agents.agents) {
    for (const a of agents.agents) {
        console.log(`${a.id}: ${a.description}`);
    }
}

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.agents.Agent;
import java.util.List;

Client client = new Client();

List<Agent> agents = client.agents.listDirect().agentListResponse().get().agents().orElse(List.of());
for (Agent a : agents) {
    System.out.println(a.id().orElse("") + ": " + a.description().orElse(""));
}

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Agents.List(ctx, operations.ListAgentsRequest{})
    if err != nil {
        log.Fatal(err)
    }

    if res.AgentListResponse != nil {
        for _, a := range res.AgentListResponse.Agents {
            fmt.Printf("%s: %v\n", *a.ID, a.Description)
        }
    }
}

QETËSI

curl -X GET "https://generativelanguage.googleapis.com/v1beta/agents" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

Merr një agjent

Python

agent = client.agents.get(id="data-analyst")
print(agent)

JavaScript

const agent = await client.agents.get("data-analyst");
console.log(agent);

Java

import com.google.genai.Client;
import com.google.genai.gaos.models.agents.Agent;

Client client = new Client();

Agent agent = client.agents.get("data-analyst").agent().get();
System.out.println(agent);

Go

package main

import (
    "context"
    "fmt"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    res, err := client.Agents.Get(ctx, operations.GetAgentRequest{
        ID: "data-analyst",
    })
    if err != nil {
        log.Fatal(err)
    }

    fmt.Printf("%+v\n", res.Agent)
}

QETËSI

curl -X GET "https://generativelanguage.googleapis.com/v1beta/agents/data-analyst" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

Fshi një agjent

Fshirja e heq konfigurimin. Mjediset dhe ndërveprimet ekzistuese të krijuara nga agjenti nuk preken.

Python

client.agents.delete(id="data-analyst")

JavaScript

await client.agents.delete("data-analyst");

Java

import com.google.genai.Client;

Client client = new Client();

client.agents.delete("data-analyst");

Go

package main

import (
    "context"
    "log"

    "google.golang.org/genai"
    "google.golang.org/genai/interactions/models/operations"
)

func main() {
    ctx := context.Background()
    client, err := genai.NewClient(ctx, nil)
    if err != nil {
        log.Fatal(err)
    }

    _, err = client.Agents.Delete(ctx, operations.DeleteAgentRequest{
        ID: "data-analyst",
    })
    if err != nil {
        log.Fatal(err)
    }
}

QETËSI

curl -X DELETE "https://generativelanguage.googleapis.com/v1beta/agents/data-analyst" \
  -H "x-goog-api-key: $GEMINI_API_KEY"

Referenca e përkufizimit të agjentit

Fusha	Lloji	Kërkohet	Përshkrimi
`id`	varg	Po	Identifikuesi unik i agjentit brenda projektit të Google Cloud. Përdoret për të aktivizuar agjentin. Nuk duhet të përdorë prefikse të rezervuara. Shiko kufizimet e ID-së së agjentit.
`description`	varg	Jo	Përshkrimi i agjentit i lexueshëm nga njeriu.
`base_agent`	varg	Po	ID-ja e agjentit bazë (p.sh. `antigravity-preview-09-2026`).
`agent_config`	objekt	Jo	Konfigurimi për agjentin bazë, duke përfshirë zgjedhjen e modelit (`{"type": "antigravity", "model": "gemini-3.8-flash"}`). Parazgjedhja është `gemini-3.8-flash` nëse lihet jashtë. Nuk mund të anulohet në kohën e ndërveprimit për agjentët e emërtuar.
`system_instruction`	varg	Jo	Kërkesa e sistemit që përcakton sjelljen dhe personazhin.
`tools`	matrica	Jo	Veglat që mund të përdorë agjenti. Nëse hiqet, parazgjedhja është `code_execution`, `google_search` dhe `url_context`. Veglat e mbështetura përfshijnë `code_execution`, `google_search`, `url_context`, `mcp_server` dhe përkufizime të personalizuara të `function`.
`base_environment`	varg ose objekt	Jo	`"remote"`, një `environment_id` ose një objekt konfigurimi me `sources` dhe `network`. Shiko mjediset.

Kufizimet e ID-së së agjentit

Kur krijon një agjent të menaxhuar, id që specifikon duhet të ndjekë këto rregulla:

Ai duhet të jetë unik për projektin tënd të Google Cloud.
Ajo nuk duhet të fillojë me asnjë nga parashtesat e rezervuara të mëposhtme (të pavarura nga shkronjat e mëdha dhe të vogla), përndryshe krijimi do të dështojë:
- antigravity-
- veo-
- omni-
- lyria-
- imagen-
- gemma-
- gemini-
- google-
- youtube-
- android-
- chrome-
- pixel-
- waze-
- fitbit-
- nest-
- kaggle-

Fluksi i punës i përsëritjes

Prototipi me agjentin bazë të Antigravity. Kalimi i udhëzimeve të sistemit dhe burimeve të mjedisit në linjë. Testo në mënyrë ndërvepruese udhëzimet, aftësitë dhe konfigurimin e mjedisit.
Stabilizo mjedisin. Instalo paketat, monto burimet, verifiko që gjithçka funksionon.
Vazhdo si një agjent i menaxhuar duke krijuar një agjent të ri, ose nga burimet ose duke krijuar një degë të mjedisit.
Përditëso përkufizimin e agjentit. Ndrysho udhëzimin e sistemit, shkëmbe aftësitë ose shto burime. Thirrja e radhës merr konfigurimin e ri.

Kufizimet

Statusi i versionit paraprak: Agjentët e menaxhuar janë në versionin paraprak. Veçoritë dhe skemat mund të ndryshojnë.
Agjenti bazë dhe modelet: Vetëm antigravity-preview-09-2026 mbështetet si base_agent. Opsionet e mbështetura të modelit në agent_config janë gemini-3.8-flash (parazgjedhja), gemini-3.6-flash dhe gemini-3.5-flash-lite. Për agjentët e emërtuar, modeli nuk mund të anulohet në kohën e ndërveprimit.
Nuk ka versionim: Versionimi i agjentit dhe rikthimi nuk ofrohen ende.
Nuk ka nivelizim të nënagentëve: Delegimi i nënagentëve nuk mbështetet ende.
Mund të kesh deri në 1000 agjentë të menaxhuar.

Çfarë ka më pas

Përmbledhja e agjentëve: Mëso rreth koncepteve kryesore të agjentëve të menaxhuar.
Nisja e shpejtë: Fillo të ndërtosh me biseda me shumë kthesa dhe transmetim.
Agenti i antigravitetit: Eksploro aftësitë, veglat dhe çmimet për agjentin e parazgjedhur.
Mjediset e agjentit: Konfiguro mjediset e provës, burimet dhe rrjetin.
API-ja e agjentëve të menaxhuar në platformën e agjentëve: Për krijimin e agjentëve me qeverisje të integruar organizative.