fix(output): bound and reject empty LLM feedback text for TTS - #33
Open
Bartok9 wants to merge 1 commit into
Open
fix(output): bound and reject empty LLM feedback text for TTS#33Bartok9 wants to merge 1 commit into
Bartok9 wants to merge 1 commit into
Conversation
Sanitize/truncate feedback before Polly; skip synthesis on empty input. Pure helper + offline unit tests.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
Raw LLM feedback strings were passed straight into AWS Polly. Empty whitespace, non-strings, or multi-thousand-character dumps should not reach TTS. Adds
sanitize_feedback_text(strip / empty→None / truncate default 3000) and skips synthesis withoutput_errorwhen invalid.Motivation
Fail-closed output path; avoid useless Polly calls and overly long Speech Synthesis requests.
Changes
llm_output/llm_output/feedback_text.pyllm_audio_output.feedback_for_user_callbacktest_feedback_text.pyVerification
Path-orthogonal to credential helper PR (separate module). AI-assisted; human-reviewed.