fix(agent): detect bold suggested slash commands#94
Merged
simongdavies merged 1 commit intomainfrom Apr 29, 2026
Merged
Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR improves Hyperagent’s suggested slash-command extraction so the agent can detect actionable commands even when the assistant formats them with Markdown emphasis (notably bold), and adds tests to lock in the new behavior.
Changes:
- Added a
cleanCommandCandidate()helper to normalize command candidates by trimming and stripping leading/trailing Markdown markers. - Extended
extractSuggestedCommands()to extract commands wrapped in Markdown bold (**...**) and refactored command insertion through a sharedaddCommand()path. - Expanded Vitest coverage with bold-command scenarios, including inline bold and wildcard-containing arguments.
Reviewed changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated no comments.
| File | Description |
|---|---|
src/agent/command-suggestions.ts |
Adds candidate-normalization helper and bold-pattern extraction to improve robustness of suggested command parsing. |
tests/command-suggestions.test.ts |
Adds regression tests covering bold-formatted commands and wildcard arguments inside bold. |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
This pull request enhances the extraction and testing of actionable slash commands from assistant responses, particularly improving support for commands formatted with markdown emphasis. The changes refactor command cleaning logic, add support for bolded commands, and expand test coverage to ensure correct extraction in these scenarios.
Improvements to command extraction:
cleanCommandCandidatehelper function incommand-suggestions.tsto consistently trim and remove markdown formatting from command candidates before processing.extractSuggestedCommandsto support detection and extraction of commands wrapped in markdown bold (e.g.,**/mcp enable ...**), and refactored code to use the new cleaning helper for all command patterns.Testing enhancements:
command-suggestions.test.tsto verify extraction of bolded commands, inline bold commands, and commands with wildcard arguments inside bold formatting.