keep replies in the user's language across tool rounds#74
Merged
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The agent's first reply matched the user's language but drifted to English (or other languages) after tool rounds, because each tool-result is a user-role message full of English logs and the only language guidance lived in the cache-pinned system prompt far from the generation point. This rewrites the base system prompt into principle-driven guidance with an environment block (cwd/os) and a three-way language policy, anchors the language rule on each tool-result message of the top-level run so it survives recency decay within a turn, and preserves the user's language through compaction.
Verification
cargo fmt --all --check— passedcargo clippy --workspace --all-targets -- -D warnings— passedcargo test --workspace— passed