Conversation
Adds RFD 068, which proposes a mechanism to automatically retry a forced tool call with reasoning disabled when the model ignores a soft-force directive. Anthropic's API doesn't support `tool_choice` with extended thinking enabled. JP works around this with a soft-force via a system prompt, but the model occasionally ignores it and responds with text. The RFD designs a turn-loop-level retry that keeps the conversation context intact, disables reasoning for the second attempt, and applies the original `tool_choice` so the real API parameter is honoured. Signed-off-by: Jean Mertz <git@jeanmertz.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Adds RFD 068, which proposes a mechanism to automatically retry a forced tool call with reasoning disabled when the model ignores a soft-force directive.
Anthropic's API doesn't support
tool_choicewith extended thinking enabled. JP works around this with a soft-force via a system prompt, but the model occasionally ignores it and responds with text. The RFD designs a turn-loop-level retry that keeps the conversation context intact, disables reasoning for the second attempt, and applies the originaltool_choiceso the real API parameter is honoured.