revert: remove reasoning workarounds from PR #101, keep Claude reasoning enabled #248
+15
−300
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
…ing enabled Revert the thinking block stripping, toolCallId normalization skip, and caching skip workarounds from PR #101. Keep Claude reasoning enabled via Kilo Gateway using the standard OpenRouter reasoning format. Known issue: provider error on second message with Claude when reasoning is enabled (thinking block signature validation failure).
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Outdated suggestions cannot be applied.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.
Summary
Partially revert #101 — remove the workarounds that were added for thinking block signature validation, while keeping Claude reasoning enabled via Kilo Gateway.
Reverted
toolCallIdnormalization skip for OpenRouter/Kilo GatewayKept
reasoning: { effort }formatsdkKeymapping for@kilocode/kilo-gatewayKnown issue
There is still a provider error on the second message when using Claude with reasoning enabled via Kilo Gateway. Anthropic's API requires thinking blocks to have valid cryptographic signatures that are unchanged, but our message storage reconstructs them which breaks validation. The workarounds that were reverted here were addressing this — a proper fix is still needed.