#857·fonoster

[Bug] Autopilot crashes with GoogleGenerativeAIFetchError 404 — model gemini-2.0-flash is no longer available

Author: psandersCreated Jun 23, 2026Updated Jul 22, 2026
Labelsbugvoice

Summary

Autopilot crashes on startup/request because the Google Generative AI model gemini-2.0-flash has been retired and returns a 404.

Steps to Reproduce

  1. Run autopilot with the current default Google GenAI configuration (model gemini-2.0-flash).
  2. Trigger a request that calls generateContent.
  3. Observe the unhandled rejection that crashes the process.

Expected Behavior

Autopilot should use a supported Gemini model and continue to generate content without crashing.

Actual Behavior

The request fails and crashes the process with:

GoogleGenerativeAIFetchError: [GoogleGenerativeAI Error]: Error fetching from https://generativelanguage.googleapis.com/v1beta/models/gemini-2.0-flash:generateContent: [404 Not Found] This model models/gemini-2.0-flash is no longer available. Please update your code to use a newer model for the latest features and improvements.
    at handleResponseNotOk (/home/appuser/autopilot/node_modules/@google/generative-ai/dist/index.js:434:11)
    at async makeRequest (/home/appuser/autopilot/node_modules/@google/generative-ai/dist/index.js:403:9)
    at async generateContent (/home/appuser/autopilot/node_modules/@google/generative-ai/dist/index.js:867:22)
    at async /home/appuser/autopilot/node_modules/@langchain/google-genai/dist/chat_models.cjs:602:12
  status: 404,
  statusText: 'Not Found',
}

Priority

P1 – High