Skip to content

fix(core): increase A2A agent timeout to 30 minutes#21028

Merged
adamfweidman merged 1 commit intomainfrom
fix/a2a-timeout-increase
Mar 3, 2026
Merged

fix(core): increase A2A agent timeout to 30 minutes#21028
adamfweidman merged 1 commit intomainfrom
fix/a2a-timeout-increase

Conversation

@adamfweidman
Copy link
Copy Markdown
Contributor

@adamfweidman adamfweidman commented Mar 3, 2026

Summary

Increases the timeout for A2A (Agent-to-Agent) client requests to 30 minutes. This ensures that long-running remote agents, like Deep Research, can complete their tasks without being cut off by the default 5-minute timeout.

Details

  • Added a dedicated UndiciAgent (dispatcher) with headersTimeout and bodyTimeout set to 30 minutes (1,800,000ms).
  • Replaced the global fetch calls in A2AClientManager with a custom a2aFetch that uses this dispatcher.
  • This change prevents remote agents from timing out on long operations while leaving the global fetch timeout unaffected for other operations.

Related Issues

Fixes #21027

How to Validate

  1. Run a long-running A2A agent (e.g., Deep Research).
  2. Verify that the request does not time out after 5 minutes and continues until completion (up to 30 minutes).

Pre-Merge Checklist

  • Updated relevant documentation and README (if needed)
  • Added/updated tests (if needed)
  • Noted breaking changes (if any)
  • Validated on required platforms/methods:
    • MacOS
      • npm run

@adamfweidman adamfweidman requested a review from a team as a code owner March 3, 2026 22:36
@gemini-cli
Copy link
Copy Markdown
Contributor

gemini-cli bot commented Mar 3, 2026

Hi @adamfweidman, thank you so much for your contribution to Gemini CLI! We really appreciate the time and effort you've put into this.

We're making some updates to our contribution process to improve how we track and review changes. Please take a moment to review our recent discussion post: Improving Our Contribution Process & Introducing New Guidelines.

Key Update: Starting January 26, 2026, the Gemini CLI project will require all pull requests to be associated with an existing issue. Any pull requests not linked to an issue by that date will be automatically closed.

Thank you for your understanding and for being a part of our community!

@gemini-code-assist
Copy link
Copy Markdown
Contributor

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 an issue where long-running remote agents were timing out due to a default 5-minute fetch limit. By implementing a dedicated dispatcher with an extended 30-minute timeout specifically for Agent-to-Agent communications, it ensures these agents can complete their tasks without interruption, while preserving the existing timeout behavior for all other fetch operations.

Highlights

  • Increased A2A Agent Timeout: The timeout for Agent-to-Agent (A2A) client requests has been extended to 30 minutes (1,800,000ms) to accommodate long-running remote agents like Deep Research.
  • Dedicated UndiciAgent Dispatcher: A new UndiciAgent dispatcher (a2aDispatcher) was introduced with headersTimeout and bodyTimeout specifically set to 30 minutes for A2A requests.
  • Isolated Timeout Change: The global fetch timeout remains unaffected, as A2A client requests now use a custom a2aFetch function that leverages the dedicated a2aDispatcher.
Changelog
  • packages/core/src/agents/a2a-client-manager.ts
    • Imported Agent from undici.
    • Defined A2A_TIMEOUT constant set to 30 minutes (1,800,000ms).
    • Created a2aDispatcher using UndiciAgent with extended headersTimeout and bodyTimeout.
    • Implemented a2aFetch to use the a2aDispatcher for A2A requests.
    • Modified A2AClientManager to use a2aFetch instead of the global fetch for agent resolution, including when createAuthenticatingFetchWithRetry is applied.
Activity
  • No specific activity (comments, reviews, or progress updates) has been recorded for this pull request since its creation.
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.

Copy link
Copy Markdown
Contributor

@gemini-code-assist gemini-code-assist bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Code Review

This pull request increases the timeout for A2A client requests to 30 minutes to support long-running agents. The implementation correctly creates a custom undici dispatcher with the longer timeout and uses it for A2A fetch calls without affecting the global fetch timeout. My review includes one suggestion to improve type safety and code clarity around the custom fetch implementation by using // @ts-expect-error instead of a misleading type assertion.

@github-actions
Copy link
Copy Markdown

github-actions bot commented Mar 3, 2026

Size Change: +471 B (0%)

Total Size: 25.9 MB

ℹ️ View Unchanged
Filename Size Change
./bundle/gemini.js 25.4 MB +471 B (0%)
./bundle/node_modules/@google/gemini-cli-devtools/dist/client/main.js 221 kB 0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/_client-assets.js 227 kB 0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/index.js 11.5 kB 0 B
./bundle/node_modules/@google/gemini-cli-devtools/dist/src/types.js 132 B 0 B
./bundle/sandbox-macos-permissive-open.sb 890 B 0 B
./bundle/sandbox-macos-permissive-proxied.sb 1.31 kB 0 B
./bundle/sandbox-macos-restrictive-open.sb 3.36 kB 0 B
./bundle/sandbox-macos-restrictive-proxied.sb 3.56 kB 0 B
./bundle/sandbox-macos-strict-open.sb 4.82 kB 0 B
./bundle/sandbox-macos-strict-proxied.sb 5.02 kB 0 B

compressed-size-action

@adamfweidman adamfweidman force-pushed the fix/a2a-timeout-increase branch from ab25dab to 779c6e8 Compare March 3, 2026 22:47
@gemini-cli gemini-cli bot added area/agent Issues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Quality 🔒 maintainer only ⛔ Do not contribute. Internal roadmap item. labels Mar 3, 2026
@adamfweidman adamfweidman enabled auto-merge March 3, 2026 22:49
}

let fetchImpl: typeof fetch = fetch;
let fetchImpl: typeof fetch = a2aFetch;
Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

can you add a test that verifies that the timeout passed in is actually respected? particularly given we ware passing it in getting around the type system.

@adamfweidman adamfweidman added this pull request to the merge queue Mar 3, 2026
Merged via the queue into main with commit 066b0cc Mar 3, 2026
27 checks passed
@adamfweidman adamfweidman deleted the fix/a2a-timeout-increase branch March 3, 2026 23:11
BryanBradfo pushed a commit to BryanBradfo/gemini-cli that referenced this pull request Mar 5, 2026
struckoff pushed a commit to struckoff/gemini-cli that referenced this pull request Mar 6, 2026
liamhelmer pushed a commit to badal-io/gemini-cli that referenced this pull request Mar 12, 2026
yashodipmore pushed a commit to yashodipmore/geemi-cli that referenced this pull request Mar 21, 2026
warrenzhu25 pushed a commit to warrenzhu25/gemini-cli that referenced this pull request Apr 9, 2026
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

area/agent Issues related to Core Agent, Tools, Memory, Sub-Agents, Hooks, Agent Quality 🔒 maintainer only ⛔ Do not contribute. Internal roadmap item.

Projects

None yet

Development

Successfully merging this pull request may close these issues.

Make Remote Agent Timeout 30 mins

4 participants