Conversation
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 15d2967696
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".
|
|
||
| logger.debug("OpenAI 전체 응답: $rawResponse") | ||
|
|
||
| return objectMapper.readValue<OpenAiResponse>(rawResponse) |
There was a problem hiding this comment.
When OpenAI returns a 200 response whose envelope deserializes but output_text is missing or the summary JSON is malformed, this returns before those checks run, so the finally records outcome=success and the new error counter is not incremented; parseSummary then throws outside this catch path. That makes the new OpenAI metrics report failed user-facing summary generations as successful, so the output-text/schema parsing should be included in the measured error path or otherwise update the outcome before propagating the failure.
Useful? React with 👍 / 👎.
1 participant
No description provided.