-
Notifications
You must be signed in to change notification settings - Fork 99
refactor: clients only use generic llm.Message #1168
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
Merged
teamdandelion
merged 1 commit into
v2
from
08-04-refactor_clients_only_use_generic_llm.message
Aug 5, 2025
Merged
refactor: clients only use generic llm.Message #1168
teamdandelion
merged 1 commit into
v2
from
08-04-refactor_clients_only_use_generic_llm.message
Aug 5, 2025
Conversation
This file contains hidden or 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
This was referenced Aug 4, 2025
Collaborator
Author
Deploying with
|
| Status | Name | Latest Commit | Preview URL | Updated (UTC) |
|---|---|---|---|---|
| ✅ Deployment successful! View logs |
v2-docs | 633b611 | Commit Preview URL | Aug 05 2025, 03:13 AM |
willbakst
approved these changes
Aug 4, 2025
59b1f5f to
ee0bff7
Compare
90b3895 to
1b845d5
Compare
ee0bff7 to
42332a0
Compare
This was referenced Aug 4, 2025
Collaborator
Author
Merge activity
|
In offline discussion, we agreed that trying to support provider-specific messages creates a leaky abstraction / incomplete abstraction, especially since the Response will only have generic messages, and supporting provider-specific input messages also raises the unaddressed question of what we do with provider-specific output messages and potentially unsupported content.
42332a0 to
633b611
Compare
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.

In offline discussion, we agreed that trying to support provider-specific messages creates a leaky abstraction / incomplete abstraction, especially since the Response will only have generic messages.
Supporting provider-specific input messages also raises the unaddressed question of what we do with provider-specific output messages and potentially unsupported content.
I left the
AnthropicMessage,GoogleMessageetc type aliases, as I think it'll be a nice convention to alias whatever the provider-specific message representation may be, to a consistent type alias.