refactor(opencode): skip per-token schema validation in AI-SDK adapter - #41272
Open
Celibistrial wants to merge 1 commit into
Open
refactor(opencode): skip per-token schema validation in AI-SDK adapter#41272Celibistrial wants to merge 1 commit into
Celibistrial wants to merge 1 commit into
Conversation
Schema.is() was recompiled per call and the LLMEvent.*Delta() constructors run Schema validation on every streamed token. Hoist the validators and emit plain typed literals for the per-token delta events; the return type still checks them against the LLMEvent union.
Contributor
|
Hey! Your PR title Please update it to start with one of:
Where See CONTRIBUTING.md for details. |
Celibistrial
changed the title
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Issue for this PR
Closes #41270
Type of change
What does this PR do?
toLLMEventsruns per streamed token. It rebuilt theSchema.isrefinement on everyproviderMetadatacall, and theLLMEvent.*Deltaconstructors ran schema validation on objects the adapter had just built itself. I hoisted the two validators to module scope so they compile once, and for the three per-token delta events I return a plain typed literal instead of the validating constructor. The function return type still checks those literals against theLLMEventunion, so a wrong shape is a type error rather than something that slips through at runtime. Lower frequency events keep the validated constructors.How did you verify your code works?
bun test packages/opencode/test/session/llm.test.tspasses (28 tests, covers the native and AI-SDK streaming paths), andtscis clean. The type annotation on the literals is what guards against shape drift.Screenshots / recordings
N/A, not a UI change.
Checklist