-
Notifications
You must be signed in to change notification settings - Fork 5.3k
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
feat: Merge the modifications resulting from integrating with the agent store. #768
Conversation
fixbug: recursive search for provider
… geekan/v0.6-release
feat: Disable the DEFAULT_PROVIDER in console mode.
…re is nothing to do.
fixbug: an unexpected UserRequirement type message is thrown when there is nothing to do.
fixbug: unit test
fixbug: rename folder does not work in windows os
fixbug: fix todo_description
feat: Moderation + llm arg feat: +log
… geekan/v0.6-release
fixbug: RPC think
metagpt/roles/role.py
Outdated
@@ -524,6 +524,7 @@ def is_idle(self) -> bool: | |||
|
|||
async def think(self) -> Action: | |||
"""The exported `think` function""" | |||
await self._observe() |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
why _observe here?
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
These interfaces are designed for use by the agent store.
In the early design of the agent store interface, the observation behavior was implemented externally through direct memory operations without being encapsulated into an "observe" interface.
To ensure compatibility, the observation behavior has now been incorporated into the "think" interface.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
There are still some counter-instincts in the think _observe, can you add the reason to the comments?
Features
Role.think()
first_action
toaction_description
numpy==1.24.3
tonumpy>=1.24.3