Troubleshooting troubleshooting
IMPORTANT
Adobe LLM Apps is currently in Beta.
Features, workflows, and UI shown here do not necessarily represent the final state of the product. To join the Beta, send an email to llm-apps-beta@adobe.com.
Start with the symptom you can see. Do not share credentials, tokens, private MCP URLs, or sensitive handler results while troubleshooting.
App creation and onboarding
Symptom
What to try
New repositories do not appear
Select Manage repos on GitHub, grant the Adobe LLM Apps GitHub App access to both repositories, return to the dialog, and refresh the lists
EDS repository requires AEM Code Sync
Install AEM Code Sync for the EDS repository, then return to the Create LLM App dialog
EDS validation says you are not an administrator
Select Open AEM Live Admin, add yourself as an administrator for the EDS site, then refresh the repository
Onboarding is still generating
Allow approximately 15 minutes. You can leave the page and return later
Onboarding reports failure
Confirm that both repositories are accessible and that the website is public over HTTPS, then contact the Beta team with the visible error message
Actions and handlers
Symptom
What to try
Action is not invoked
Attach the ChatGPT plugin, confirm Expose to AI model is enabled, improve the action description, and redeploy metadata changes
Empty or error response
Run
npm test, then call the handler with MCP Inspector or curl. See Local handler development and testingHandler works locally but not after deployment
Confirm the latest commit was pushed, runtime configuration is present, and the action code identifier matches
actions/<code-identifier>/index.jsGenerated action cannot be marked as reviewed
Confirm handler and widget generation succeeded. Check the generated pull requests for merge conflicts, reload the action, and select Mark as reviewed again
Widgets
Symptom
What to try
Widget does not render
Verify the Script URL, Widget URL, HTTPS, EDS publication, CSP domains, and CORS headers
Widget renders but shows no data
Call the handler with MCP Inspector and compare its
structuredContent shape with the fields read from bridge.toolResultWidget works in direct preview but not in ChatGPT
Direct preview might use sample data. Test the deployed handler result and verify the EDS origin is allowed by CORS and CSP
Browser request is blocked
Add only the required origin to the correct CSP field and redeploy
HTTP Headers Editor cannot save the configuration
Use the AEM Configuration Service or ask the EDS administrator to initialize the site headers configuration
Do not log complete bridge.toolResult values when they can contain personal or sensitive data.
Deployment
Symptom
What to try
Deployment fails during Preparing
Verify the handler repository is linked and your Adobe Developer Console access is still valid
Deployment fails during Build app
Run
npm install, npm test, and npm run build locally. Fix dependency, syntax, or test failures and push the changesDeployment succeeds but changes are missing
Confirm the expected commit was pushed and redeploy to the same environment
Action remains Not deployed
Deploy again after reviewing the action or changing its metadata
ChatGPT plugins
Symptom
What to try
Plugin does not appear
Enable developer mode, open chatgpt.com/plugins, verify the plugin exists, and select Connect
Plugin creation fails
Confirm developer mode is enabled, copy the MCP server URL again from Test the app, and use Server URL with No Auth
Plugin connects but cannot invoke actions
Confirm the plugin is attached to the chat, the actions are exposed to the model, and the latest version is deployed
Plugin uses the wrong environment
Edit or recreate the plugin with the intended Stage or Production MCP server URL
If the issue persists, record the app name, environment, failed step, time, and visible error message before contacting the Beta team. Do not include secrets or sensitive customer data.
recommendation-more-help
llm-apps-help-main-toc