-
Notifications
You must be signed in to change notification settings - Fork 1
2.0.19 #23
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
2.0.19 #23
Conversation
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Pull Request Overview
This release (2.0.19) introduces several new writing task types and adds transcript generation capabilities to existing session tasks. The changes focus on expanding content generation capabilities with specialized tasks for journalism, business proposals, email campaigns, interactive stories, and articles.
Key Changes:
- Added five new writing task types: JournalismReasoningTask, ArticleGenerationTask, BusinessProposalTask, EmailCampaignTask, and InteractiveStoryTask
- Enhanced existing session tasks (SeleniumSessionTask, RunShellCommandTask, CommandSessionTask) with optional transcript file generation
- Updated NarrativeGenerationTask to support input files and transcript generation
- Minor code formatting improvements in Selenium.kt
Reviewed Changes
Copilot reviewed 82 out of 92 changed files in this pull request and generated 3 comments.
Show a summary per file
| File | Description |
|---|---|
| gradle.properties | Version bump from 2.0.18 to 2.0.19 |
| NarrativeGenerationTask.kt | Added input_files support, transcript generation, and moved from reasoning to writing package |
| JournalismReasoningTask.kt | New task for journalistic investigation and fact-checking |
| ArticleGenerationTask.kt | New task extending JournalismReasoningTask for complete article generation |
| BusinessProposalTask.kt | New task for generating comprehensive business proposals with ROI analysis |
| EmailCampaignTask.kt | New task for creating email marketing campaigns with A/B testing variants |
| InteractiveStoryTask.kt | New task for generating choose-your-own-adventure style narratives |
| SeleniumSessionTask.kt | Added optional transcript generation capability |
| RunShellCommandTask.kt | Added transcript generation for shell command sessions |
| CommandSessionTask.kt | Added transcript generation for command sessions |
| Selenium.kt | Minor formatting improvements |
| tests.md | File deleted (removed test documentation) |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| ) { | ||
| override val task_type: String = NarrativeGeneration.name | ||
| override var task_description: String? = "Generate full narrative for '$subject'" | ||
| override fun validate(): String? { | ||
| // First validate parent class | ||
| // First validate parent class |
Copilot
AI
Oct 24, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Duplicate comment on consecutive lines. Remove one of the duplicate '// First validate parent class' comments.
| // First validate parent class |
| if (claim.isBlank()) { | ||
| return "Fact claim must not be blank" | ||
| } | ||
| if (verification_status.isNotBlank()) { |
Copilot
AI
Oct 24, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Logic error in validation. The condition checks if verification_status is NOT blank and then returns an error saying it must not be blank. This should be if (verification_status.isBlank()) instead.
| if (verification_status.isNotBlank()) { | |
| if (verification_status.isBlank()) { |
| "## Command\n\n$TRIPLE_TILDE\n${response.code}\n$TRIPLE_TILDE\n" + | ||
| "## Result\n$TRIPLE_TILDE\n${response.result.resultValue}\n$TRIPLE_TILDE\n" + // STDOUT | ||
| "## Output\n$TRIPLE_TILDE\n${response.result.resultOutput}\n$TRIPLE_TILDE\n" // STDERR | ||
| resultFn(resultString) |
Copilot
AI
Oct 24, 2025
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Lines 124-126 create a string that is not assigned to any variable and is immediately discarded. This appears to be duplicate code that should be removed, as the same result string was already processed on lines 121-123.
| "## Command\n\n$TRIPLE_TILDE\n${response.code}\n$TRIPLE_TILDE\n" + | |
| "## Result\n$TRIPLE_TILDE\n${response.result.resultValue}\n$TRIPLE_TILDE\n" + // STDOUT | |
| "## Output\n$TRIPLE_TILDE\n${response.result.resultOutput}\n$TRIPLE_TILDE\n" // STDERR | |
| resultFn(resultString) |
No description provided.