Add Gemini 4 Argon support, long decode examples, and migration guide

[Giom-V]

Summary

Adds support and documentation for Gemini 4 Argon (gemini-4-argon) across the Gemini API Cookbook while keeping gemini-3.8-flash as the default model:

• Model selectors (# @param): Adds "gemini-4-argon" to general-purpose # @param model dropdowns across 96 quickstart and example notebooks (excluding explicit caching and specialized media/live notebooks), and updates .gemini/styleguide.md and CONTRIBUTING.md.
• quickstarts/Get_started.ipynb & quickstarts/Get_started_Generate_Content.ipynb:
  • Adds a dedicated What's new in Gemini 4 Argon (#gemini4) section covering the 1M token output & long decode highlight (1,048,576 unified input-thinking-output token pool), tunable thinking_level ("low", "medium", "high"), background long decode (background=True polling and streaming with last_event_id reconnection in the Interactions API, and automatic_continuation / continuation_token in generateContent), and Managed Agents (antigravity-preview-09-2026 with gemini-4-argon).
  • Consolidates the migration guidance into a unified Migrating from Gemini 3 and 2.5 (#gemini4migration / #gemini3migration) checklist.
• quickstarts/Get_started_thinking.ipynb & quickstarts/Get_started_thinking_REST.ipynb: Updates the thinking levels reference tables and examples for gemini-4-argon.
• README.md & quickstarts/README.md: Updates the top callouts and links directly to #gemini4 and #gemini4migration.

[review-notebook-app]

Check out this pull request on 

See visual diffs & provide feedback on Jupyter Notebooks.

---

Powered by ReviewNB

[gemini-code-assist]

Summary of Changes

Hello, I'm Gemini Code Assist¹! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed!

This pull request introduces comprehensive support for the new gemini-4-argon model across the entire Gemini API Cookbook. The changes include updating model selection dropdowns, adding detailed documentation on new features such as long decode and tunable thinking levels, and providing a unified migration guide to help users transition from previous model generations.

Highlights

• Model Support: Added gemini-4-argon to model selectors across nearly 100 notebooks and documentation files.
• Documentation Updates: Included new sections on long decode, thinking levels, and managed agents in key quickstart notebooks.
• Migration Guidance: Consolidated migration checklists for users transitioning from Gemini 2.5 and 3 models.

Ignored Files

• Ignored by pattern: .gemini/** (1)
  • .gemini/styleguide.md

Using Gemini Code Assist

The full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips.

Invoking Gemini

You can request assistance from Gemini at any point by creating a comment using either /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

Customization

To customize the Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a .gemini/ folder in the base of the repository. Detailed instructions can be found here.

Limitations & Feedback

Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counterproductive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for GitHub and other Google products, sign up here.

Footnotes

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[gemini-code-assist]

Code Review

This pull request introduces support and documentation for the new Gemini 4 Argon model across various quickstarts, examples, and README files, detailing its implicit caching, tunable thinking levels, and agentic video understanding capabilities. The review feedback highlights several critical corrections: in the thinking quickstart, the SDK usage must be corrected to use config with a nested thinking_config instead of generation_config for setting the thinking level; Colab form selectors in the avian magnetoreception and embeddings notebooks need formatting adjustments to comply with the repository style guide; and Python-specific SDK terminology should be removed from the REST-focused thinking notebook to avoid confusing users.