You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I have searched the existing issues, and there is no existing issue for my problem
Which Operating System are you using?
Linux
Which version of Auto-GPT are you using?
Stable (branch)
GPT-3 or GPT-4?
GPT-4
Steps to reproduce 🕹
It happens sometime, I let autogpt to analyze two repos, after reading some code, with expected analyze, reasoning, plans, it start dead loop.
Current behavior 😯
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
short bulleted
list that conveys
long-term plan
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
short bulleted
list that conveys
long-term plan
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
short bulleted
list that conveys
long-term plan
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
short bulleted
list that conveys
long-term plan
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
Expected behavior 🤔
It should find exist commands, choose to use them.
Your prompt 📝
# Paste your prompt here
Your Logs 📒
<insert your logs here>
The text was updated successfully, but these errors were encountered:
This issue has automatically been marked as stale because it has not had any activity in the last 50 days. You can unstale it by commenting or removing the label. Otherwise, this issue will be closed in 10 days.
Which Operating System are you using?
Linux
Which version of Auto-GPT are you using?
Stable (branch)
GPT-3 or GPT-4?
GPT-4
Steps to reproduce 🕹
It happens sometime, I let autogpt to analyze two repos, after reading some code, with expected analyze, reasoning, plans, it start dead loop.
Current behavior 😯
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
SYSTEM: Command command name returned: Unknown command 'command name'. Please refer to the 'COMMANDS' list for available commands and only respond in the specified JSON format.
THOUGHTS: thought
REASONING: reasoning
PLAN:
CRITICISM: constructive self-criticism
NEXT ACTION: COMMAND = command name ARGUMENTS = {'arg name': 'value'}
Expected behavior 🤔
It should find exist commands, choose to use them.
Your prompt 📝
# Paste your prompt here
Your Logs 📒
The text was updated successfully, but these errors were encountered: