refactor(provider): align reasoning transform with upstream#269
Open
nicko-ai wants to merge 3 commits into
Open
refactor(provider): align reasoning transform with upstream#269nicko-ai wants to merge 3 commits into
nicko-ai wants to merge 3 commits into
Conversation
- restore upstream provider transform behavior for generic reasoning handling - keep fork import-path adaptation for generated model/provider IDs - realign transform tests with upstream coverage available in this fork
Contributor
|
The following comment was made by an LLM, it may be inaccurate: |
- drop fork-only merge precedence for disabled reasoning options - keep tested Anthropic tool ordering guard while provider transforms align upstream
Restore OPENCODE_EXPERIMENTAL_OUTPUT_TOKEN_MAX while keeping the provider reasoning cleanup. Add a focused startup regression test for the exported token maximum.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Not required for refactor PRs.
Type of change
What does this PR do?
Aligns generic provider reasoning transforms and tests with current upstream behavior, while keeping the small Anthropic tool-ordering guard still covered by the fork's LLM test. It also removes a generic LLM reasoning merge override that was fork drift after the provider transform alignment.
How did you verify your code works?
npx --yes bun@1.3.13 test --timeout 30000 test/provider/transform.test.ts test/session/llm.test.tsfrompackages/opencodenpx --yes bun@1.3.13 run typecheckfrompackages/opencodebun turbo typecheckScreenshots / recordings
Not applicable.
Checklist