context_servers: Return messages from prompts/get #17794
+77
−3
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
The underlying protocol now allows for returning messages with roles. We need to reflect this appropriately.
Since slash commands don't fully support writing proper messages with roles into the assistant panel just yet, we need to just write it out in text for now. Most likely, we only receive user messages anywhere, which we special case and insert directly without a role.
cla-bot
bot
added
the
cla-signed
dsp-ant
force-pushed
the
davidsp/protocol-change
branch
from
3337047
to
99f04ec
Compare
|
For posterity, @dsp-ant @nathansobo and I chatted about this and the idea is to restructure the This will make slash commands feel more responsive thanks to streaming, and it will allow inserting arbitrary message boundaries in a context. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This is a change in protocol. Since the protocol is marked as experimental, we don't just yet bump the version. We now return messages with user or assistant roles from prompt/get. In zed, we do the 'easy' thing at the moment and create a simple text that says
Assistant:/User:respectively. The right fix would be to change the way we render slash command and allow for proper User/Assistant labels. I chose to not do this here, as it's a complicated change that likely needs to bake longer and I likely need help from someone at Zed to implement it.The reasoning behind changing this, as this in the future would allow to nicely move complete existing conversations between Zed, e.g. claude.ai, which i think would be very useful in the future, e.g. imagine a world where someone create an artifact in claude.ai and pulls it into Zed + conversation.
Release Notes: