fix(js): reflection context is always an object for runAction

[Ehesp]

In the reflection API, when we POST /api/runAction, the reflection server forwards context from the request body. When the client (e.g. Dev UI) omits it, context is undefined and is passed through to action.run():

const { key, input, context, telemetryLabels } = request.body;
// ...
await action.run(input, { context, ... });

That leads to runWithContext(undefined, actFn). In that case no context is stored in async context, so getContext() / ai.currentContext() returns undefined for the whole run. Any code that assumes a run-scoped context object then breaks. So if something like a plugin wants to write to context, e.g. getContext().someKey = value, getContext() is undefined.

So the actual problem is in code that writes to context (plugins or flows) and assumes getContext() is a mutable object. The reflection fix (defaulting to {}) makes that assumption valid for runs started via the reflection API.

Checklist (if applicable):

• PR title is following https://www.conventionalcommits.org/en/v1.0.0/
• Tested (manually, unit tested, etc.)
• Docs updated (updated docs or a docs bug required)

[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 addresses a subtle but critical issue in the reflection API's handling of action contexts. Previously, if a client did not explicitly provide a context when calling POST /api/runAction, the context parameter would be undefined, leading to getContext() returning undefined throughout the action's execution. This change ensures that context is always an object, even if empty, thereby maintaining the expected behavior for any code that relies on a mutable context object.

Highlights

• Context Handling: Ensured that the context parameter passed to action.run() always defaults to an empty object ({}) if it is undefined.
• Bug Fix: Resolved an issue where getContext() could return undefined for the entire run if the client omitted context in POST /api/runAction requests.
• Plugin Compatibility: Prevented potential errors in plugins and flows that assume getContext() returns a mutable object, making their assumption valid for runs initiated via the reflection API.

🧠 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.

Changelog

• js/core/src/reflection.ts
  • Modified the action.run calls within the ReflectionServer class to explicitly set the context parameter to context || {}.

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.

You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension.

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 addresses a bug where runAction in the reflection API could pass an undefined context, leading to potential runtime errors. The proposed change ensures the context is always an object by defaulting to {} when it's not provided, which is a correct and robust fix. I've added one suggestion to refactor the implementation slightly to avoid code duplication and improve long-term maintainability.

[gemini-code-assist]

While this correctly fixes the issue, the same logic context || {} is duplicated for the non-streaming case on line 307. To improve maintainability and adhere to the DRY (Don't Repeat Yourself) principle, you could define the default context before the if (stream === 'true') block and reuse it in both action.run calls.

For example:

const { key, input, context, telemetryLabels } = request.body;
const effectiveContext = context || {};
// ...
// in streaming case:
await action.run(input, {
  context: effectiveContext,
  // ...
});
// ...
// in non-streaming case:
await action.run(input, {
  context: effectiveContext,
  // ...
});

This would centralize the logic for handling the context.