Skip to content

Codex-generated pull request#45

Merged
rad1092 merged 1 commit intomainfrom
codex/add-synonym-definitions-in-schema_semantics_ko.json
Feb 15, 2026
Merged

Codex-generated pull request#45
rad1092 merged 1 commit intomainfrom
codex/add-synonym-definitions-in-schema_semantics_ko.json

Conversation

@rad1092
Copy link
Copy Markdown
Owner

@rad1092 rad1092 commented Feb 15, 2026

Codex generated this pull request, but encountered an unexpected error after generation. This is a placeholder PR message.


Codex Task

@rad1092 rad1092 merged commit 75a5074 into main Feb 15, 2026
4 checks passed
@rad1092 rad1092 deleted the codex/add-synonym-definitions-in-schema_semantics_ko.json branch February 15, 2026 05:12
Copy link
Copy Markdown

@chatgpt-codex-connector chatgpt-codex-connector Bot left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: ff1668a3f4

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

  • Open a pull request for review
  • Mark a draft as ready
  • Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

Comment on lines +101 to +105
if term and term in question:
match = match_alias_to_column(term, columns, concepts)
mappings.append(match)
if match.status == "success" and match.matched_column:
normalized_question = normalized_question.replace(term, match.matched_column)
Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

P1 Badge Replace only whole entity tokens during normalization

normalize_question_entities matches aliases with plain substring checks and then runs global str.replace, so terms that appear inside longer words are rewritten incorrectly. For example, with column 시군구명 and question 시군구명 별 ..., the canonical term 시군구 matches and replacement produces 시군구명명 ..., which then feeds a corrupted question into the prompt. This can silently degrade analysis whenever a concept term is a prefix/subsequence of another token.

Useful? React with 👍 / 👎.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant