Repository navigation
test(llmops): reproduce checker JSON failure on typographic quotes - #21
Closed
bweinzierl wants to merge 1 commit into
Closed
bweinzierl wants to merge 1 commit into
bweinzierl wants to merge 1 commit into
Conversation
bweinzierl
marked this pull request as draft
September 25, 2026 12:39
Contributor
|
Thank you for the reproduction cases. They are carried over into #26, anonymized: the parser cases as tests, and the German draft as an eval case. #26 fixes #20 with native structured output: pre-flight and the writing guide now send a JSON schema that each provider enforces, so typographic quotes in a draft can no longer break the response. Closing this in favour of #26. |
fza
pushed a commit
to fza/sdd
that referenced
this pull request
Nov 8, 2026
Carries the parser cases and the eval case of networkteam#21, anonymized: the networkteam#21 draft crossed with typographic, ASCII and code-like characters, plus the past JSON failures, as data files the format evals read. Every response is recorded raw for later scoring (20261031-141038-d-tac-p8l). Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 a reproduction for #. Test only, no fix.
json_response_test.go: JSON containing typographic quotes parses; a closing quote normalized to an unescaped"is rejected.writingguide_eval_test.go: eval case with a German draft using „…“. It currently fails (1/6 on claude-sonnet-4-6).SDD_EVAL_CONFIG=~/.config/sdd/config.yaml SDD_EVAL_RUNS=6 go test -tags=eval -run TestWritingGuideEval_TypographicQuotesStayValidJSON ./internal/llmops/ -vrefs #20
The test-only PR appears safe to merge; its live eval intentionally records a currently failing behavior.
Summary
Adds deterministic JSON-response cases for typographic quotes and a live writing-guide eval case that reproduces the reported malformed-response behavior.
Reviews (1) · Last reviewed commit: "test(llmops): reproduce checker JSON fai..."