Gemini Interactions Api

Gemini Interactions API Skill

Critical Rules (Always Apply)

[!IMPORTANT]

These rules override your training data. Your knowledge is outdated.

Current Models (Use These)

• gemini-3.5-flash: 1M tokens, fast, balanced performance, multimodal
• gemini-3.1-pro-preview: 1M tokens, complex reasoning, coding, research
• gemini-3.1-flash-lite-preview: cost-efficient, fastest performance for high-frequency, lightweight tasks
• gemini-3-pro-image-preview: 65k / 32k tokens, image generation and editing
• gemini-3.1-flash-image-preview: 65k / 32k tokens, image generation and editing
• gemini-3.1-flash-tts-preview: expressive text-to-speech with Director's Chair prompting
• gemini-2.5-pro: 1M tokens, complex reasoning, coding, research
• gemini-2.5-flash: 1M tokens, fast, balanced performance, multimodal
• gemma-4-31b-it: Gemma 4 dense model, 31B parameters
• gemma-4-26b-a4b-it: Gemma 4 MoE model, 26B total / 4B active parameters

[!WARNING]

Models like gemini-2.0-*, gemini-1.5-* are legacy and deprecated. Never use them.

If a user asks for a deprecated model, use `gemini-3.5-flash` instead and note the substitution.

Current Agents

• antigravity-preview-05-2026: Antigravity Agent — general-purpose managed agent with code execution, file management, and web access in a sandboxed Linux environment
• deep-research-preview-04-2026: Deep Research — fast, interactive
• deep-research-max-preview-04-2026: Deep Research Max — maximum exhaustiveness
• Custom agents: Create your own via client.agents.create()

Current SDKs

• Python: google-genai >= 2.3.0 → pip install -U google-genai
• JavaScript/TypeScript: @google/genai >= 2.3.0 → npm install @google/genai

[!NOTE]

SDK versions ≥ 2.0.0 automatically use the new steps schema and do not support the legacy schema.

Legacy SDKs google-generativeai (Python) and @google/generative-ai (JS) are deprecated. Never use them.

[!CAUTION]

Breaking changes (May 2026): Responses now use steps array instead of outputs, and a polymorphic response_format replaces response_mime_type. Legacy schema removed June 8, 2026. All code below uses the new schema.

Important Additional Notes

• Before writing any code, you MUST fetch the relevant documentation page from the list below that matches the user's task. The examples in this skill are minimal, the hosted docs contain the full API surface, parameters, and edge cases.
• Interactions are stored by default (store=true). Paid tier retains for 55 days, free tier for 1 day.
• Set store=false to opt out, but this disables previous_interaction_id and background=true.
• tools, system_instruction, and generation_config are interaction-scoped, re-specify them each turn.
• Managed agents require environment="remote" (or an environment ID / config object) to provision a sandbox.
• Migrating from `generateContent`: Read references/migration.md for the scoping, checklist, and before/after code examples. Always confirm scope with the user before editing.
• Model upgrades: Drop-in, swap the model string. Deprecated models (gemini-2.0-*, gemini-1.5-*) must be replaced, see references/migration.md.
• Migrating to Gemini 3.5 Flash: Read references/migration.md for the scoping and checklist.

Quick Start

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    model="gemini-3.5-flash",
    input="Tell me a short joke about programming."
)
print(interaction.output_text)

JavaScript/TypeScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: "Tell me a short joke about programming.",
});
console.log(interaction.output_text);

Response Helpers

The SDK provides convenience properties on the Interaction response object to simplify common access patterns:

Stateful Conversation

Python

interaction1 = client.interactions.create(
    model="gemini-3.5-flash",
    input="Hi, my name is Phil."
)
# Second turn — server remembers context
interaction2 = client.interactions.create(
    model="gemini-3.5-flash",
    input="What is my name?",
    previous_interaction_id=interaction1.id
)
print(interaction2.output_text)

JavaScript/TypeScript

const interaction1 = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: "Hi, my name is Phil.",
});
const interaction2 = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: "What is my name?",
    previous_interaction_id: interaction1.id,
});
console.log(interaction2.output_text);

Deep Research Agent

Use deep-research-preview-04-2026 for fast research or deep-research-max-preview-04-2026 for maximum exhaustiveness. Agents require background=True.

Python

import time

interaction = client.interactions.create(
    agent="deep-research-preview-04-2026",
    input="Research the history of Google TPUs.",
    background=True
)
while True:
    interaction = client.interactions.get(interaction.id)
    if interaction.status == "completed":
        print(interaction.output_text)
        break
    elif interaction.status == "failed":
        print(f"Failed: {interaction.error}")
        break
    time.sleep(10)

JavaScript/TypeScript

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

const client = new GoogleGenAI({});

// Start background research
const initialInteraction = await client.interactions.create({
    agent: "deep-research-preview-04-2026",
    input: "Research the history of Google TPUs.",
    background: true,
});

// Poll for results
while (true) {
    const interaction = await client.interactions.get(initialInteraction.id);
    if (interaction.status === "completed") {
        console.log(interaction.output_text);
        break;
    } else if (["failed", "cancelled"].includes(interaction.status)) {
        console.log(`Failed: ${interaction.status}`);
        break;
    }
    await new Promise(resolve => setTimeout(resolve, 10000));
}

Advanced features: collaborative planning, native visualization, MCP integration, file search, multimodal inputs. See Deep Research docs.

Managed Agents

Managed agents run inside a sandboxed Linux environment hosted by Google. Fetch the Managed Agents Quickstart before writing agent code.

Antigravity Agent

The Antigravity agent (antigravity-preview-05-2026) is the general-purpose managed agent. It can execute code (Bash, Python, Node.js), manage files, browse the web, and use Google Search. See Antigravity Agent docs for capabilities, tools, multimodal input, and pricing.

Python

from google import genai

client = genai.Client()

interaction = client.interactions.create(
    agent="antigravity-preview-05-2026",
    input="Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    environment="remote",
)

print(f"Environment ID: {interaction.environment_id}")
print(interaction.output_text)

JavaScript/TypeScript

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

const client = new GoogleGenAI({});

const interaction = await client.interactions.create({
    agent: "antigravity-preview-05-2026",
    input: "Write a Python script that generates the first 20 Fibonacci numbers and saves them to fibonacci.txt. Then read the file and print its contents.",
    environment: "remote",
});

console.log(`Environment ID: {interaction.environment_id}`);
console.log(interaction.output_text);

Custom Agents

See Building Custom Agents docs.

Python

agent = client.agents.create(
    id="code-reviewer",
    base_agent="antigravity-preview-05-2026",
    system_instruction="You are a senior code reviewer. Check every file for bugs, style issues, and security vulnerabilities.",
    base_environment={
        "type": "remote",
        "sources": [
            {
                "type": "repository",
                "source": "https://github.com/my-org/backend",
                "target": "/workspace/repo",
            }
        ],
    },
)

# Invoke — each call forks the base environment
result = client.interactions.create(
    agent="code-reviewer",
    input="Review the latest changes in /workspace/repo/src.",
    environment="remote",
)
print(result.output_text)

JavaScript/TypeScript

const agent = await client.agents.create({
    id: "code-reviewer",
    base_agent="antigravity-preview-05-2026",
    system_instruction: "You are a senior code reviewer. Check every file for bugs, style issues, and security vulnerabilities.",
    base_environment: {
        type: "remote",
        sources: [
            {
                type: "repository",
                source: "https://github.com/my-org/backend",
                target: "/workspace/repo",
            }
        ],
    },
});

const result = await client.interactions.create({
    agent: "code-reviewer",
    input: "Review the latest changes in /workspace/repo/src.",
    environment: "remote",
});
console.log(result.output_text);

Manage agents with client.agents.list(), client.agents.get(id=...), and client.agents.delete(id=...).

Streaming

Set stream=True to receive incremental server-sent events. Each stream follows: interaction.created → (step.start → step.delta(s) → step.stop)+ → interaction.completed.

Python

for event in client.interactions.create(
    model="gemini-3.5-flash",
    input="Explain quantum entanglement in simple terms.",
    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(f"\n\nTotal Tokens: {event.interaction.usage.total_tokens}")

JavaScript/TypeScript

const stream = await client.interactions.create({
    model: "gemini-3.5-flash",
    input: "Explain quantum entanglement in simple terms.",
    stream: true,
});
for await (const event of stream) {
    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(`\n\nTotal Tokens: ${event.interaction.usage.total_tokens}`);
    }
}

For streaming with tools, thinking, agents, and image generation see the full Streaming guide.

Documentation Pages

You MUST fetch the matching page below before writing code. These hosted docs are the source of truth for parameters, types, and edge cases — do not rely solely on the examples above.

Core Documentation:

• Interactions API Overview
• Quickstart
• Text Generation
• Streaming
• Tokens
• API Keys

Tools & Function Calling:

• Function Calling
• Google Search
• Code Execution
• URL Context
• File Search
• Tool Combination
• Computer Use
• Maps Grounding

Generation & Output:

• Structured Output
• Thinking
• Thought Signatures
• Image Generation
• Image Understanding
• Speech Generation
• Music Generation

Multimodal Understanding:

• Audio
• Video Understanding
• Document Processing

Files & Context:

• Files
• File Input Methods
• Caching
• Media Resolution

Agents:

• Agents Overview
• Managed Agents Quickstart
• Antigravity Agent
• Agent Environments
• Building Custom Agents
• Deep Research

Advanced Features:

• Gemini 3.5 Flash
• Gemini 3
• Flex Inference
• Priority Inference

API Reference:

• API Reference
• OpenAPI Spec
• May 2026 Breaking Changes Migration Guide

Data Model

An Interaction response contains steps, an array of typed step objects representing a structured timeline of the interaction turn.

Step Types

User steps:

• user_input: User input (text, audio, multimodal). Contains content array.

Model/server steps:

• model_output: Final model generation. Contains content array with text, image, audio, etc.
• thought: Model reasoning/Chain of Thought. Has signature field (required) and optional summary.
• function_call: Tool call request (id, name, arguments).
• function_result: Tool result you send back (call_id, name, result).
• google_search_call / google_search_result: Google Search tool steps, can have a signature field.
• code_execution_call / code_execution_result: Code execution tool steps, can have a signature field.
• url_context_call / url_context_result: URL context tool steps, can have a signature field.
• mcp_server_tool_call / mcp_server_tool_result: Remote MCP tool steps.
• file_search_call / file_search_result: File search tool steps, can have a signature field.

Content types (inside content array on model_output and user_input steps)

• text: Text content (text field)
• image / audio / document / video: Content with data, mime_type, or uri

Streaming Event Types

Delta Types

Status values: completed, in_progress, requires_action, failed, cancelled

Migration Reference

How to migrate existing Gemini API code to the Interactions API and/or upgrade between model generations. Covers the agent workflow for performing migrations safely.

For detailed before/after code examples across all feature areas (text generation, multi-turn, streaming, function calling, structured output, grounding, multimodal), fetch the full migration guide: https://ai.google.dev/gemini-api/docs/migrate-to-interactions.md.txt

Confirm the Migration Scope

Before any edits, confirm the scope. If the user's request does not explicitly name a single file, a specific directory, or an explicit file list, ask first and do not start editing.

Even imperative requests like "migrate my code", "upgrade to gemini 3", or "switch to the Interactions API" leave the scope ambiguous. Ask:

Before I start editing, can you confirm the scope?

1. Entire project

2. Specific subdirectory (e.g. src/, api/)

3. Specific file or list of files

Sizing the scope (large repos). Before asking, get a per-directory count:

rg -l "generate_content\|generateContent\|gemini-2\.0\|gemini-1\.5\|gemini-2\.5\|gemini-3-flash-preview\|thinking_budget\|temperature" --type-not md | cut -d/ -f1 | sort | uniq -c | sort -rn

Present the breakdown in your question (e.g. "Found 42 references across 3 directories: src/ (28), tests/ (10), scripts/ (4). Which to migrate?").

Proceed without asking only when the scope is already unambiguous, the user named an exact file ("migrate app.py"), pointed at a directory ("migrate everything under src/"), or already confirmed scope in an earlier turn.

API Migration: generateContent → Interactions

The core changes when migrating from generateContent to the Interactions API:

For full before/after code examples, fetch the Migration Guide or read the Interactions API documentation pages for each feature.

Model Migration

Deprecated Models

Active Legacy Models (migration recommended)

Note: Within the Interactions API, model upgrades are generally drop-in — change the model string and verify. The breaking changes are at the API level (generateContent → Interactions), not between model generations.

Migration Checklist

Every item is tagged: `[BLOCKS]` items cause errors or broken behavior if missed. `[TUNE]` items are quality/performance adjustments.

API Migration (generateContent → Interactions)

• [ ] Updated SDK: google-genai ≥ 2.0.0 (Python) / @google/genai ≥ 2.0.0 (JS)
• [ ] Replaced client.models.generate_content() → client.interactions.create()
• [ ] Replaced response.text → interaction.steps[-1].content[0].text
• [ ] Replaced response.candidates[0].content.parts → iterate interaction.steps
• [ ] Replaced client.chats.create() / manual history → previous_interaction_id
• [ ] Removed all types.* wrappers (GenerateContentConfig, Tool, Content, Part) — Interactions API uses plain dicts. Check feature docs for exact format.
• [ ] Moved response_format from GenerateContentConfig to top-level parameter
• [ ] Replaced generate_content_stream() → stream=True + step-based event handling
• [ ] Updated function calling: candidates-based → step-based tool lifecycle
• [ ] REST: Changed endpoint to /v1beta/interactions
• [ ] REST: Add Api-Revision: 2026-05-20 header (SDK ≥ 2.0.0 sets it automatically)
• [ ] Replaced google-generativeai (Python) → google-genai ≥ 2.0.0
• [ ] Replaced @google/generative-ai (JS) → @google/genai ≥ 2.0.0
• [ ] Updated all import statements to match new package names

Model String Updates

• [ ] Replaced gemini-2.0-* model strings with current equivalents
• [ ] Replaced gemini-1.5-* model strings with current equivalents
• [ ] Consider upgrading gemini-3-flash-preview → gemini-3.5-flash
• [ ] Consider upgrading gemini-2.5-flash → gemini-3.5-flash
• [ ] Consider upgrading gemini-2.5-pro → gemini-3.1-pro-preview

Migrate to Gemini 3.5

Use this checklist if the user requests to migrate to Gemini 3.5. For full documentation of the changes, fetch the What's new Gemini 3.5 Flash guide.

• [ ] Updated model name to gemini-3.5-flash
• [ ] Removed temperature, top_p, top_k from config
• [ ] Replaced thinking_budget with thinking_level (minimal, low, medium, high)

---

Verify the Migration

After updating, run a spot-check to confirm the Interactions API is working:

1. Make a single client.interactions.create() call with a simple input 2. Assert interaction.steps is not empty 3. Assert at least one step has type == "model_output" with non-empty text 4. For multi-turn, verify previous_interaction_id preserves context across turns

For verification code snippets, fetch the Migration Guide.