Fix opencode max-steps assistant prefill for Anthropic#26
Open
Mucka wants to merge 1 commit into
Open
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes Anthropic request failures when opencode appends its max-steps instruction as an assistant prefill.
When an opencode agent reaches its configured
stepslimit, opencode appends a final assistant-role message beginning with:CRITICAL - MAXIMUM STEPS REACHEDAnthropic rejects that shape for some Claude models with:
This model does not support assistant message prefill. The conversation must end with a user message.The bridge already strips the older synthetic
Continue with your tasks.assistant prefill. This change extends that handling for opencode's max-steps prefill by converting it into a final user message instead of dropping it. That keeps the intended "tools are disabled, summarize text-only" instruction while satisfying Anthropic's requirement that the conversation ends with a user message.