fix(planning): handle empty LLM response in macro plan parsing (#162)#171
Open
liaoyl830 wants to merge 1 commit into
Open
fix(planning): handle empty LLM response in macro plan parsing (#162)#171liaoyl830 wants to merge 1 commit into
liaoyl830 wants to merge 1 commit into
Conversation
…inglinyi#162) When using glm-4.5-air or other models that occasionally return empty responses, _parse_llm_response would throw a cryptic JSONDecodeError instead of a clear error message. Add a check for empty cleaned content before attempting json.loads(), raising a descriptive ValueError that autopilot_daemon can handle gracefully via its existing error handling.
Contributor
📝 WalkthroughWalkthroughThis PR adds defensive error handling and improves EPUB export robustness. LLM response parsing now validates and fails early with a user-friendly error when content is empty. EPUB export adds diagnostic logging for missing chapter content and explicitly generates proper EPUB 3 navigation documents. ChangesError Handling and Export Improvements
Estimated code review effort🎯 2 (Simple) | ⏱️ ~10 minutes Possibly related PRs
Suggested reviewers
Poem
🚥 Pre-merge checks | ✅ 4 | ❌ 1❌ Failed checks (1 warning)
✅ Passed checks (4 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
🧹 Nitpick comments (1)
application/core/services/export_service.py (1)
200-203: ⚡ Quick winInclude nav in spine for EPUB 3 reader compatibility.
At Line 203,
EpubNav()is added, but the spine still excludes"nav". Some readers rely on nav being in reading order; adding it to spine improves compatibility.Proposed change
- book.spine = spine_items + book.spine = ["nav", *spine_items]🤖 Prompt for AI Agents
Verify each finding against current code. Fix only still-valid issues, skip the rest with a brief reason, keep changes minimal, and validate. In `@application/core/services/export_service.py` around lines 200 - 203, The EPUB spine currently assigns book.spine = spine_items after adding book.add_item(epub.EpubNav()), but it never includes the "nav" item id in the spine; modify the spine construction so the nav id is included in the reading order (e.g., insert or append "nav" into the spine_items list before assigning book.spine) so the epub.EpubNav() item added by book.add_item(epub.EpubNav()) is present in the spine for EPUB 3 compatibility.
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Nitpick comments:
In `@application/core/services/export_service.py`:
- Around line 200-203: The EPUB spine currently assigns book.spine = spine_items
after adding book.add_item(epub.EpubNav()), but it never includes the "nav" item
id in the spine; modify the spine construction so the nav id is included in the
reading order (e.g., insert or append "nav" into the spine_items list before
assigning book.spine) so the epub.EpubNav() item added by
book.add_item(epub.EpubNav()) is present in the spine for EPUB 3 compatibility.
ℹ️ Review info
⚙️ Run configuration
Configuration used: defaults
Review profile: CHILL
Plan: Pro Plus
Run ID: f5b19975-a32b-4796-90ec-19ad7b0969cd
📒 Files selected for processing (2)
application/blueprint/services/continuous_planning_service.pyapplication/core/services/export_service.py
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.
变更类型
fixBug 修复变更说明
修复使用 glm-4.5-air 等模型时，LLM 偶尔返回空响应导致的
JSONDecodeError: Expecting value: line 1 column 1 (char 0)错误。根因
_parse_llm_response()方法在清理 LLM 返回内容后，直接调用json.loads()。当模型返回空字符串时（可能由于 API 限流、网络问题或模型自身问题），json.loads("")会抛出难以理解的 JSONDecodeError。修复
在
json.loads()之前增加空内容检查，返回描述性ValueError，便于autopilot_daemon的现有错误处理逻辑识别并优雅降级。架构影响
applicationSummary by CodeRabbit