Move tool/tool call encoding logic from completion to encoding #548
+195
−121
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
eb8680
commented
Feb 9, 2026
| includes the raw assistant message for retry handling. | ||
| """ | ||
| tool_specs = {k: _function_model(t) for k, t in tools.items()} | ||
| response_model = pydantic.create_model( |
Contributor
Author
There was a problem hiding this comment.
Removing response_model here was the original motivation for this PR because it was causing problems with less capable LLMs in #545, but I ended up doing a bit more cleanup along the way.
Draft
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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 refactoring PR cleans up some logic in
handlers.llm.completionsrelated to tool call encoding and decoding by coercing it into the existingEncodableAPI.