← Search

Gemini Interactions API: stateful multi-turn agent conversations on GEAP
AI 🧪 Install ran in our test sandbox · Nov 18, 2026 📌 Pinned version: commit 82f5db4
Install test only, on the date shown. This does not guarantee the code is safe.
⚙ Needs: a Google Cloud project with…

Gemini Interactions API: stateful multi-turn agent conversations on GEAP

Build stateful Gemini agent conversations on the Enterprise Agent Platform — multi-turn, streaming, structured output, function calling — in Python, TypeScript, or REST

At a glance
What
Build stateful Gemini agent conversations on the Enterprise Agent Platform — multi-turn, streaming, structured output, function calling — in Python, TypeScript, or REST
Cost
Free
Needs
a Google Cloud project with aiplatform.googleapis.com enabled; ADC credentials (gcloud auth application-default login); a provisioned GEAP agent ID; google-genai SDK >= 2.3.0 for Python or @google/genai >= 2.3.0 for JS/TS (legacy SDKs unsupported)
Install
Copy the installer prompt below into your Muse — your agent does the rest.

Version:

Quick answer

Gemini Interactions API is a free Muse skill, the official Google skill for the Gemini Interactions API on the Gemini Enterprise Agent Platform: auth setup via ADC, client initialization with the unified Gen AI SDK in Python and TypeScript, stateful multi-turn conversations via previous_interaction_id, real-time streaming event handling, structured output, and agent tool use with flat function-call steps.

⌁

Install

Copy the install package below, then paste it into Muse🧪 Install ran in our test sandbox · Nov 18, 2026📌 Pinned version: commit 82f5db4

Step 0 — before installing anything: read this install prompt, summarize in a few lines what this build does and what installing it involves, then ask me to confirm before you proceed. Prerequisites: a Google Cloud project with aiplatform.googleapis.com enabled; ADC credentials (gcloud auth application-default login); a provisioned GEAP agent ID; google-genai SDK >= 2.3.0 for Python or @google/genai >= 2.3.0 for JS/TS (legacy SDKs unsupported) Install "Gemini Interactions API: stateful multi-turn agent conversations on GEAP" for me. It covers auth, client init, stateful multi-turn conversations, streaming, structured output, function calling, REST usage, and the step data model for the Gemini Interactions API on the Enterprise Agent Platform. Repository: https://raw.githubusercontent.com/google/skills/82f5db4c8b72a5801957b5a087c2fb14209ddcc4/skills/cloud/gemini-interactions-api/SKILL.md Pinned version: install the code at commit 82f5db4c8b72a5801957b5a087c2fb14209ddcc4 exactly (Skill Harbor tested this version). Do not substitute a newer version. If this commit is unreachable, stop and tell me. 1. Fetch the SKILL.md file (and any helper files) from the repository path into a temporary folder 2. Safety check: review the SKILL.md and scripts for anything suspicious (unexpected network calls, shell commands, credential harvesting). This repo should contain zero secrets in code, credentials only via the secure vault, allowed hosts declared in the SKILL.md. Verify that holds here; STOP on any red flag and tell me. 3. Install it as a skill: copy SKILL.md and its helper files into the agent's skills directory, in a folder named "gemini-interactions-api". 4. Verify with no network calls: frontmatter valid, files in place. 5. Report what was installed, where, and what I still need to do myself (e.g. run gcloud auth application-default login, set my project env vars, provision my agent and save its ID in the vault). GitHub is optional: if I have a GitHub account or the gh CLI, you may use it; otherwise public access is fine. Never require it unless it's in the prerequisites above. Rules: don't touch anything outside the temp folder and the install target. If anything looks off, stop and ask me.

🔒 Security, provenance and what this touches
🧭 What this touches
Based on the install prompt we scanned, this skill does not run commands, make third-party network calls, install packages, write files, or ask for API keys.
Install prompt analysis · 2026-10-13
🔒 Security and provenance
📌 Pinned version: commit 82f5db4 · 2026-10-13
🧪 Install ran in our test sandbox · Nov 18, 2026
👁 Observed during the install test · Nov 18, 2026 : no network contact
🔎 Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify
Wanna be extra careful?

The install prompt below already includes the vetting steps: your agent follows the community checklist before installing anything with executable code. Want more?

How to check a skill before installing →

✓

Verification certificate

Dated facts about what was checked for this listing, and how. This is not a safety certification.

Pinned version
82f5db4 · 2026-10-13
Sandbox install test
Install ran in our test sandbox · Nov 18, 2026
Creator identity
Not verified
Fingerprint watch
Last checked · Nov 19, 2026 : no change detected in the files linked by this install prompt
Install prompt analysis
2026-10-13 : No commands, network calls, packages, file writes or API keys detected.

Skill Harbor never reviews the code of a listed skill. These are dated facts about the install prompt and our install test, not a safety certification. Review a skill yourself before you install it. How we verify

?

Questions

How do I install a skill?

Every product page includes a copy-paste install prompt. Paste it into your Muse and it sets the skill up for you — no manual configuration.

Where does my money go?

Straight to the seller. Skill Harbor never processes payments: checkout happens on the seller’s own page, usually Stripe.

What does the ✓ next to a creator’s name mean?

It means we confirmed the identity of the person behind the listing. It says nothing about the code itself — always check a skill before installing it.