Issue Station
Sign In
Tools hereToolbox

openclaw - 💡(How to fix) Fix [Bug]: Missing "image-generation" capability in Google plugin – Technical evidence [1 participants]

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…
GitHub stats
openclaw/openclaw#53744•Fetched 2026-04-08 01:24:04
View on GitHub
Comments
0
Participants
1
Timeline
2
Reactions
0
Author
ilcorsairilcorsair
Participants
ilcorsairilcorsair
Timeline (top)
labeled ×2

Hi everyone,

I would like to report an issue regarding Gemini's integration for image generation in OpenClaw. Despite google/gemini-3-pro-image-preview being mentioned in the documentation, the Google plugin does not seem to register the necessary capabilities to handle these requests. Source Analysis

I performed a check on the distributed files in the extensions directory to verify which plugins actually declare the image-generation capability: Bash

grep -rl "image-generation" ./openclaw/dist/extensions/

Results:

    .../extensions/openai/index.js

    .../extensions/fal/index.js

    .../extensions/fal/openclaw.plugin.json

As shown, the Google plugin is completely missing from the results, confirming that the capability is not implemented in the code or metadata for this extension. Plugin Configuration Analysis (google/openclaw.plugin.json)

Examining the Google plugin configuration file, it is clear that references to image generation are missing. The plugin currently only focuses on google and google-gemini-cli providers and webSearch grounding: JSON

{
  "id": "google",
  "providers": ["google", "google-gemini-cli"],
  "providerAuthEnvVars": {
    "google": ["GEMINI_API_KEY", "GOOGLE_API_KEY"]
  },
  // ... (references to image-generation or image-models are missing)
}

The Issue

When calling the image_generate function targeting Google, the system fails because the OpenClaw router cannot find the necessary mapping to route the request, as the Google plugin does not "self-declare" as capable of generating images.

Is anyone successfully using Gemini for image generation, or is this a planned feature that hasn't been implemented in the plugin core yet?

Currently, the only working workaround for image generation seems to be using fal or openai plugins.

Root Cause

When calling the image_generate function targeting Google, the system fails because the OpenClaw router cannot find the necessary mapping to route the request, as the Google plugin does not "self-declare" as capable of generating images.

Fix Action

Fix / Workaround

Currently, the only working workaround for image generation seems to be using fal or openai plugins.

The Google plugin should register the image-generation capability in its openclaw.plugin.json and index.js, allowing the router to dispatch image requests to Gemini models. Actual Behavior

Code Example

.../extensions/openai/index.js

    .../extensions/fal/index.js

    .../extensions/fal/openclaw.plugin.json

---

{
  "id": "google",
  "providers": ["google", "google-gemini-cli"],
  "providerAuthEnvVars": {
    "google": ["GEMINI_API_KEY", "GOOGLE_API_KEY"]
  },
  // ... (references to image-generation or image-models are missing)
}

---
RAW_BUFFERClick to expand / collapse

Bug type

Behavior bug (incorrect output/state without crash)

Summary

Hi everyone,

I would like to report an issue regarding Gemini's integration for image generation in OpenClaw. Despite google/gemini-3-pro-image-preview being mentioned in the documentation, the Google plugin does not seem to register the necessary capabilities to handle these requests. Source Analysis

I performed a check on the distributed files in the extensions directory to verify which plugins actually declare the image-generation capability: Bash

grep -rl "image-generation" ./openclaw/dist/extensions/

Results:

    .../extensions/openai/index.js

    .../extensions/fal/index.js

    .../extensions/fal/openclaw.plugin.json

As shown, the Google plugin is completely missing from the results, confirming that the capability is not implemented in the code or metadata for this extension. Plugin Configuration Analysis (google/openclaw.plugin.json)

Examining the Google plugin configuration file, it is clear that references to image generation are missing. The plugin currently only focuses on google and google-gemini-cli providers and webSearch grounding: JSON

{
  "id": "google",
  "providers": ["google", "google-gemini-cli"],
  "providerAuthEnvVars": {
    "google": ["GEMINI_API_KEY", "GOOGLE_API_KEY"]
  },
  // ... (references to image-generation or image-models are missing)
}

The Issue

When calling the image_generate function targeting Google, the system fails because the OpenClaw router cannot find the necessary mapping to route the request, as the Google plugin does not "self-declare" as capable of generating images.

Is anyone successfully using Gemini for image generation, or is this a planned feature that hasn't been implemented in the plugin core yet?

Currently, the only working workaround for image generation seems to be using fal or openai plugins.

Steps to reproduce

Configure Google Plugin: Set up the Google provider with a valid GEMINI_API_KEY.

Attempt Image Generation: Run a command or an agent task that triggers the image_generate function using the google/gemini-3-pro-image-preview model.

Observe the Failure: The system fails to route the request because it doesn't recognize the Google plugin as an image provider.

Verify via CLI: Run the following command in the OpenClaw installation directory to see which extensions are registered for image generation:
Bash

grep -rl "image-generation" ./dist/extensions/

Result: You will notice that while openai and fal extensions appear in the results, the google extension is missing, confirming the capability is not registered.

Expected behavior

Expected Behavior

The Google plugin should register the image-generation capability in its openclaw.plugin.json and index.js, allowing the router to dispatch image requests to Gemini models. Actual Behavior

Actual behavior

The Google plugin only registers text and web search capabilities, ignoring image generation even if the model is specified in the configuration.

OpenClaw version

2026.03.22

Operating system

debian 12 bookworm

Install method

npm global

Model

google/gemini-3-pro-image-preview

Provider / routing chain

openclaw

Additional provider/model setup details

No response

Logs, screenshots, and evidence

Impact and severity

No response

Additional information

No response

extent analysis

Fix Plan

To fix the issue, we need to update the Google plugin to register the image-generation capability. Here are the steps:

  • Update the openclaw.plugin.json file in the Google plugin directory to include the image-generation capability:
{
  "id": "google",
  "providers": ["google", "google-gemini-cli"],
  "providerAuthEnvVars": {
    "google": ["GEMINI_API_KEY", "GOOGLE_API_KEY"]
  },
  "capabilities": ["text", "webSearch", "image-generation"]
}
  • Update the index.js file in the Google plugin directory to include the image generation functionality. For example:
const { ImageGeneration } = require('./image-generation');

module.exports = {
  // ... existing code ...
  imageGenerate: async (model, prompt) => {
    const imageGeneration = new ImageGeneration(model, prompt);
    return imageGeneration.generate();
  }
};
  • Create a new file image-generation.js in the Google plugin directory to handle the image generation logic. For example:
const { GeminiClient } = require('google-gemini-cli');

class ImageGeneration {
  constructor(model, prompt) {
    this.model = model;
    this.prompt = prompt;
    this.client = new GeminiClient();
  }

  async generate() {
    const response = await this.client.generateImage(this.model, this.prompt);
    return response;
  }
}

module.exports = { ImageGeneration };

Verification

To verify that the fix worked, run the following command in the OpenClaw installation directory:

grep -rl "image-generation" ./dist/extensions/

The Google plugin should now appear in the results, indicating that the image-generation capability is registered. Additionally, try running a command or agent task that triggers the image_generate function using the google/gemini-3-pro-image-preview model to verify that the image generation works as expected.

Extra Tips

Make sure to update the openclaw.plugin.json and index.js files in the correct directory, and that the image-generation.js file is properly required and used in the index.js file. Also, ensure that the google-gemini-cli package is installed and configured correctly.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

FAQ

Expected behavior

Expected Behavior

The Google plugin should register the image-generation capability in its openclaw.plugin.json and index.js, allowing the router to dispatch image requests to Gemini models. Actual Behavior

#api#installation#retriever error#indexing error#inference speed

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

openclaw - 💡(How to fix) Fix [Bug]: Missing "image-generation" capability in Google plugin – Technical evidence [1 participants]