refactor: migrate from search/replace to hole-filling strategy for gh… #3391
Conversation
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
…ost autocomplete BREAKING CHANGE: Complete rewrite of autocomplete response format Changes: - Updated CURSOR_MARKER from <<<AUTOCOMPLETE_HERE>>> to <<HOLE>> - Replaced complex search/replace XML format with simple <HOLE>content</HOLE> format - Removed ~200 lines of fuzzy matching logic from GhostStreamingParser - Simplified prompt generation in AutoTriggerStrategy - Updated all test files to match new hole-filling format - Removed obsolete fuzzy-length-bug tests Benefits: - Simpler parsing: No fuzzy matching or search pattern logic needed - Clearer intent: LLM just fills the hole at cursor position - Less error-prone: No CDATA escaping issues - Faster: Direct insertion without pattern matching - More predictable: Single insertion point All 155 tests passing.
|
Use XML-style tags for consistency with response format. Changes: - Updated CURSOR_MARKER constant in ghostConstants.ts - Updated all prompt references in AutoTriggerStrategy.ts - Updated test mock data in GhostStreamingParser.sanitization.test.ts - Updated documentation files (hole-filling-strategy-plan.md, hole-filling-todo.md) All 155 tests passing.
Enhanced prompts to provide clearer instructions and better context: System Instructions: - Added detailed completion quality guidelines - Included context awareness instructions - Provided multiple examples for different scenarios - Emphasized code quality and style matching User Prompts: - Restructured for better clarity and organization - Added explicit task breakdown - Included completion guidelines for different code contexts - Better formatting with clear sections Comment-Driven Prompts: - Enhanced with detailed comment type handling - Added production-ready code requirements - Clearer task structure and requirements All 155 tests passing.
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.
…ost autocomplete
(VIBECODED! needs selfreview)
BREAKING CHANGE: Complete rewrite of autocomplete response format
Changes:
Benefits:
All 155 tests passing.
Context
Implementation
Screenshots
How to Test
Get in Touch