feat(models): allow SystemContentBlocks in LiteLLMModel #1141
+352
−20
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
dbschmigelski
changed the title
dbschmigelski
had a problem deploying
to
auto-approve
GitHub Actions
Failure
Codecov Report❌ Patch coverage is
📢 Thoughts on this report? Let us know! |
6 tasks
dbschmigelski
had a problem deploying
to
auto-approve
GitHub Actions
Failure
pgrayy
reviewed
Nov 5, 2025
| # Apply cache control to the immediately preceding content block | ||
| # for LiteLLM/Anthropic compatibility | ||
| if system_content: | ||
| system_content[-1]["cache_control"] = {"type": "ephemeral"} |
There was a problem hiding this comment.
Do we know the other types? What if we set type to block["cachePoint"].get("type", "ephemeral")?
pgrayy
reviewed
Nov 5, 2025
| "totalTokens": event["data"].total_tokens, | ||
| } | ||
|
|
||
| # Only LiteLLM over Anthropic supports cache cache write tokens |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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.
Description
This is the followup to
feat(models): add SystemContentBlock support for provider-agnostic caching#1112. We are now processing SystemContentBlocks within LiteLLM which enables prompt caching.Note, this will be breaking for some integrators. At launch, it was a mistake to not apply kwargs to all public methods. This leaves us with two options.
For the sake of maintainability, and the expectation that very few people will be extending the OpenAIModel as a base model, the proposal in this PR is to add kwargs to the existing public methods. This will enable future changes in a backwards compatible way.
Related Issues
#937
Documentation PR
To come after the merge.
Type of Change
New feature
Testing
How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli
hatch run prepareChecklist
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.