[Fix] NanoGPT Muse Spark fails during tool use - #1310
Merged
Conversation
Codecov Report✅ All modified and coverable lines are covered by tests. 📢 Thoughts on this report? Let us know! |
taltas
marked this pull request as ready for review
August 22, 2026 14:38
taltas
requested review from
JamesRobert20,
edelauna,
hannesrudolph,
navedmerchant and
taltas
as code owners
August 22, 2026 14:38
taltas
approved these changes
Aug 22, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What changed
NanoGPT requests for
meta/muse-spark-1.2-contributornow keep mixed tool-result and environment context in one contiguous tool message when replaying multi-turn history. A focused regression test reproduces repeated tool-call/result cycles from the diagnostics while confirming that parallel tool calls remain enabled.Why this change was made
The diagnostics showed four valid, sequential tool calls before NanoGPT rejected the fifth response with
Upstream emitted malformed tool call data that could not be repaired. Each tool result was followed by environment text that Zoo previously replayed as a separate user message, so this compatibility mitigation preserves that context on the matching tool message instead of changing unrelated parallel-call behavior.Impact
Muse Spark 1.2 Contributor receives a more stable multi-turn tool history without losing environment context or parallel tool support. Other NanoGPT models keep their existing message conversion.
Related PRs