.github/ISSUE_TEMPLATE/1.bug.yml

name: Bug report 🐛
description: Create a bug report for Auto-GPT.
labels: ['status: needs triage']
body:
  - type: markdown
    attributes:
      value: |
        ### ⚠️ Before you continue
        * Check out our [backlog], [roadmap] and join our [discord] to discuss what's going on
        * If you need help, you can ask in the [discussions] section or in [#tech-support]
        * **Throughly search the [existing issues] before creating a new one**

        [backlog]: https://github.com/orgs/Significant-Gravitas/projects/1
        [roadmap]: https://github.com/orgs/Significant-Gravitas/projects/2  
        [discord]: https://discord.gg/autogpt
        [discussions]: https://github.com/Significant-Gravitas/Auto-GPT/discussions
        [#tech-support]: https://discord.com/channels/1092243196446249134/1092275629602394184
        [existing issues]: https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue
  - type: checkboxes
    attributes:
      label: ⚠️ Search for existing issues first ⚠️
      description: >
        Please [search the history](https://github.com/Torantulino/Auto-GPT/issues)
        to see if an issue already exists for the same problem.
      options:
        - label: I have searched the existing issues, and there is no existing issue for my problem
          required: true
  - type: markdown
    attributes:
      value: |
        Please provide a searchable summary of the issue in the title above ⬆️.

        ⚠️ SUPER-busy repo, please help the volunteer maintainers.
        The less time we spend here, the more time we spend building AutoGPT.
        
        Please help us help you:
        - Does it work on `stable` branch (https://github.com/Torantulino/Auto-GPT/tree/stable)?
        - Does it work on current `master` (https://github.com/Torantulino/Auto-GPT/tree/master)?
        - Search for existing issues, "add comment" is tidier than "new issue"
        - Ask on our Discord (https://discord.gg/autogpt)
        - Provide relevant info:
          - Provide commit-hash (`git rev-parse HEAD` gets it)
          - If it's a pip/packages issue, provide pip version, python version
          - If it's a crash, provide traceback.
  - type: dropdown
    attributes:
      label: Which Operating System are you using?
      description: >
        Please select the operating system you were using to run Auto-GPT when this problem occurred.
      options:
        - Windows
        - Linux
        - MacOS
        - Docker
        - Devcontainer / Codespace
        - Windows Subsystem for Linux (WSL)
        - Other (Please specify in your problem)
    validations:
      required: true
  - type: dropdown
    attributes:
      label: GPT-3 or GPT-4?
      description: >
        If you are using Auto-GPT with `--gpt3only`, your problems may be caused by
        the [limitations](https://github.com/Significant-Gravitas/Auto-GPT/issues?q=is%3Aissue+label%3A%22AI+model+limitation%22) of GPT-3.5.
      options:
        - GPT-3.5
        - GPT-4
    validations:
      required: true
  - type: textarea
    attributes:
      label: Steps to reproduce 🕹
      description: |
        **⚠️ Issues that we can't reproduce will be closed.**
  - type: textarea
    attributes:
      label: Current behavior 😯
      description: Describe what happens instead of the expected behavior.
  - type: textarea
    attributes:
      label: Expected behavior 🤔
      description: Describe what should happen.
  - type: textarea
    attributes:
      label: Your prompt 📝
      description: >
        If applicable please provide the prompt you are using. Your prompt is stored in your `ai_settings.yaml` file.
      value: |
        ```yaml
        # Paste your prompt here
        ```
  - type: textarea
    attributes:
      label: Your Logs 📒
      description: |
        Please include the log showing your error and the command that caused it, if applicable.
        You can copy it from your terminal or from `logs/activity.log`.
        This will help us understand your issue better!
        
        <details>
        <summary><i>Example</i></summary>
        ```log
        INFO NEXT ACTION:  COMMAND = execute_shell  ARGUMENTS = {'command_line': 'some_command'}
        INFO -=-=-=-=-=-=-= COMMAND AUTHORISED BY USER -=-=-=-=-=-=-=
        Traceback (most recent call last):
        File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 619, in _interpret_response
        self._interpret_response_line(
        File "/home/anaconda3/lib/python3.9/site-packages/openai/api_requestor.py", line 682, in _interpret_response_line
        raise self.handle_error_response(
        openai.error.InvalidRequestError: This model's maximum context length is 8191 tokens, however you requested 10982 tokens (10982 in your prompt; 0 for the completion). Please reduce your prompt; or completion length.
        ```
        </details>
      value: |
        ```log
        <insert your logs here>
        ```