4.4 KiB
title
| title |
|---|
| Troubleshooting |
Troubleshooting
Goose, like any system, may run into occasional issues. This guide provides solutions for common problems.
Goose Edits Files
Goose can and will edit files as part of its workflow. To avoid losing personal changes, use version control to stage your personal edits. Leave Goose edits unstaged until reviewed. Consider separate commits for Goose's edits so you can easily revert them if needed.
Interrupting Goose
If Goose is heading in the wrong direction or gets stuck, you can interrupt it by pressing CTRL+C. This will stop Goose and give you the opportunity to correct its actions or provide additional information.
Stuck in a Loop or Unresponsive
In rare cases, Goose may enter a "doom spiral" or become unresponsive during a long session. This is often resolved by ending the current session, and starting a new session.
- Hold down
Ctrl + Cto cancel - Start a new session:
goose session
:::tip For particularly large or complex tasks, consider breaking them into smaller sessions. :::
Context Length Exceeded Error
This error occurs when the input provided to Goose exceeds the maximum token limit of the LLM being used. To resolve this try breaking down your input into smaller parts. You can also use .goosehints as a way to provide goose with detailed context. Refer to the Using Goosehints Guide for more information.
Handling Rate Limit Errors
Goose may encounter a 429 error (rate limit exceeded) when interacting with LLM providers. The recommended solution is to use OpenRouter. See Handling LLM Rate Limits for more info.
Hermit Errors
If you see an issue installing an extension in the app that says "hermit:fatal", you may need to reset your hermit cache. We use a copy of hermit to ensure npx and uvx are consistently available. If you have already used an older version of hermit, you may need to cleanup the cache - on Mac this cache is at
sudo rm -rf ~/Library/Caches/hermit
API Errors
Users may run into an error like the one below when there are issues with their LLM API tokens, such as running out of credits or incorrect configuration:
Traceback (most recent call last):
File "/Users/admin/.local/pipx/venvs/goose-ai/lib/python3.13/site-packages/exchange/providers/utils.py",
line 30, in raise_for_status
response.raise_for_status()
~~~~~~~~~~~~~~~~~~~~~~~~~^^
File "/Users/admin/.local/pipx/venvs/goose-ai/lib/python3.13/site-packages/httpx/_models.py",
line 829, in raise_for_status
raise HTTPStatusError(message, request=request, response=self)
httpx.HTTPStatusError: Client error '404 Not Found' for url
'https://api.openai.com/v1/chat/completions'
...
This error typically occurs when LLM API credits are exhausted or your API key is invalid. To resolve this issue:
- Check Your API Credits:
- Log into your LLM provider's dashboard
- Verify that you have enough credits. If not, refill them
- Verify API Key:
- Run the following command to reconfigure your API key:
goose configure
For detailed steps on updating your LLM provider, refer to the Installation Guide.
Remove Cached Data
Goose stores data in a few places. Secrets, such as API keys, are stored exclusively in the system keychain.
Logs and configuration data are stored in ~/.config/goose. And the app stores a small amount of data in
~/Library/Application Support/Goose.
You can remove all of this data by following these steps.
- stop any copies of goose running (CLI or GUI)
- consider confirming you've stopped them all via the activity monitor
- open the keychain and delete the credential called "goose", which contains all secrets stored by goose
rm -rf ~/.config/goose- For the App on macos,
rm -rf ~/Library/Application Support/Goose - Delete the "Goose" app from your Applications folder
After this cleanup, if you are looking to try out a fresh install of Goose, you can now start from the usual install instructions.
Need Further Help?
If you have questions, run into issues, or just need to brainstorm ideas join the Discord Community!