Repository navigation
Add Claude Sonnet 5.5, Fable 5.1, and Mythos 5.1 model support - #206
Merged
Merged
Conversation
Register claude-sonnet-5-5 with adaptive thinking and max effort. Non-default sampling parameters are rejected, and forced tool choice is rejected on every request. Co-authored-by: Florian Reifschneider <florian@omnifact.ai>
Share one forced-tool-choice rejection list across Opus 5.5, Sonnet 5.5, Fable 5.1, and Mythos 5.1. Fable 5.1 and Mythos 5.1 use always-on adaptive thinking, max effort, and always-restricted sampling. Co-authored-by: Florian Reifschneider <florian@omnifact.ai>
flore2003
marked this pull request as ready for review
September 29, 2026 19:57
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Registers three Claude models and shares one forced-tool-choice rule across the models that reject it on every request.
claude-sonnet-5-5uses adaptive thinking and acceptsmaxeffort. Omittingreasoningleaves the API default ofhigh. Up-front thinking can be turned off, soreasoning.modestaysoptional.claude-fable-5-1andclaude-mythos-5-1use always-on adaptive thinking, acceptmaxeffort, and default tohigh. Mythos 5.1 matches Fable 5.1.claude-opus-5-5,claude-sonnet-5-5,claude-fable-5-1, andclaude-mythos-5-1reject forced tool choice (requiredand{ type: 'tool' }) on every request, including whenreasoningis omitted.'auto'and'none'stay valid. Claude Fable 5 and Claude Mythos 5 still allow forced tool choice whenreasoningis omitted.temperature,topP, andtopKon every request.Test plan
npm run test -w @core-ai/anthropicnpm run lint -w @core-ai/anthropicnpm run check-types -w @core-ai/anthropic