chore(release/v2-candidate): release 2.0.0-alpha.1

[Jacksunwei]

🤖 I have created a release beep boop

Changelog

2.0.0-alpha.1 (2026-03-18)

Features

Introduces two major capabilities:

• Workflow runtime: graph-based execution engine for composing
  deterministic execution flows for agentic apps, with support for
  routing, fan-out/fan-in, loops, retry, state management, dynamic
  nodes, human-in-the-loop, and nested workflows
• Task API: structured agent-to-agent delegation with multi-turn
  task mode, single-turn controlled output, mixed delegation
  patterns, human-in-the-loop, and task agents as workflow nodes

[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 officially releases version 2.0.0-alpha.1 of the ADK Python library. It delivers a substantial set of new features, including advanced LLM integrations with streaming capabilities, significant enhancements to agent optimization and evaluation frameworks, and expanded functionalities for various tools. The release also incorporates crucial bug fixes, refactors existing code for improved maintainability, and updates documentation to reflect these changes.

Highlights

• Breaking Changes: The default skill system instruction (SI) has been collocated with the skill toolset, and the credential manager now accepts tool_context instead of callback_context.
• Enhanced LLM Integrations: Added streaming support for Apigee LLM and Anthropic models, enabled output schema with tools for LiteLLM models, and introduced a base_url option for the Gemini LLM class.
• Agent Capabilities & Evaluation: Introduced an interface for agent optimizers, added a demo prompt optimizer, implemented a post-hoc per-turn evaluator for user simulations, and integrated user personas into the ADK evaluation framework.
• Tooling & Infrastructure Improvements: Added a new database schema for DatabaseSessionService with migration commands, enhanced OpenTelemetry spans for tool execution and model usage, and introduced SkillToolset with support for ADK tools and a BashTool.
• Bug Fixes & Stability: Addressed various issues including NoneType object iteration errors, improved LiteLLM content conversion and streaming response parsing, fixed database session locking race conditions, and resolved an SSRF vulnerability in load_web_page.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

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 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 counter productive. 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 updates the release manifest to 2.0.0-alpha.1 and introduces a new changelog file, CHANGELOG-v2.md. The changes are consistent with a release operation. I've identified a couple of minor formatting and typo issues within the newly added changelog file that should be addressed for improved clarity and correctness.

I am having trouble creating individual review comments. Click here to see my feedback.

CHANGELOG-v2.md (125)

The markdown for @experimental appears to be malformed. It seems like it was intended to be plain text rather than a link.

* Remove @experimental decorator from AgentEngineSandboxCodeExecutor ([135f763](https://github.com/google/adk-python/commit/135f7633253f6a415302142abc3579b664601d5b))

CHANGELOG-v2.md (220)

There appears to be a typo here: "EscapieClick’s" should likely be "Escape Click's".

* Escape Click’s Wrapping in adk eval help ([#4258](https://github.com/google/adk-python/issues/4258)) ([3bcd8f7](https://github.com/google/adk-python/commit/3bcd8f7f7a0683f838005bc209f7d39dc93f850b))