Add audit command suggestion to run command output#4445
Merged
Conversation
Add friendly suggestion to use 'gh aw audit <run-id>' after workflow is triggered. This makes it easier for AI agents and users to analyze workflow runs. - Added audit suggestion message with run ID - Includes lightbulb emoji for visual friendliness - Shows specific command with run ID (no lookup needed) - Added comprehensive tests for message format and agent-friendliness Co-authored-by: pelikhan <4175913+pelikhan@users.noreply.github.com>
Copilot
AI
changed the title
[WIP] Suggest running audit to analyze the run command output
Add audit command suggestion to run command output
Nov 21, 2025
Contributor
|
✅ Agentic Changeset Generator completed successfully. |
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR adds a helpful audit command suggestion after workflow runs are triggered, improving discoverability of the audit feature for both users and AI agents. The implementation is minimal (3 lines) and includes comprehensive test coverage.
Key Changes
- Added audit command suggestion to run command output with run ID
- Created dedicated test file with 3 test functions covering message format and agent-friendliness
- Message displays only when run info is successfully retrieved
Reviewed Changes
Copilot reviewed 2 out of 2 changed files in this pull request and generated 1 comment.
| File | Description |
|---|---|
| pkg/cli/run_command.go | Adds 3 lines to display audit suggestion with run ID after workflow URL |
| pkg/cli/run_command_test.go | New test file with 128 lines covering message format, exact output, and agent-friendly characteristics |
💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.
| runLog.Printf("Workflow run URL: %s (ID: %d)", runInfo.URL, runInfo.DatabaseID) | ||
|
|
||
| // Suggest audit command for analysis | ||
| fmt.Printf("\n💡 To analyze this run, use: %s audit %d\n", constants.CLIExtensionPrefix, runInfo.DatabaseID) |
There was a problem hiding this comment.
The codebase uses console.FormatInfoMessage() for informational messages with emojis to maintain consistent styling across the CLI. This pattern is used in other parts of the codebase (e.g., mcp_inspect_mcp.go line 533, 568).
Consider using:
fmt.Printf("\n%s\n", console.FormatInfoMessage(fmt.Sprintf("💡 To analyze this run, use: %s audit %d", constants.CLIExtensionPrefix, runInfo.DatabaseID)))This ensures the message uses the standard info message styling (with ℹ prefix) applied by FormatInfoMessage().
Suggested change
| fmt.Printf("\n💡 To analyze this run, use: %s audit %d\n", constants.CLIExtensionPrefix, runInfo.DatabaseID) | |
| fmt.Printf("\n%s\n", console.FormatInfoMessage(fmt.Sprintf("💡 To analyze this run, use: %s audit %d", constants.CLIExtensionPrefix, runInfo.DatabaseID))) |
github-actions bot
added a commit
that referenced
this pull request
Nov 21, 2025
Updated documentation based on merged pull requests from the last 24 hours. Features documented: - --progress flag for run command (PR #4450) - Noop message parsing in logs/audit commands (PR #4428) - close-discussion safe output type (PR #4411) - debug-agentic-workflow custom agent (PR #4449) - Audit command suggestion in run output (PR #4445) Changes: - Updated docs/setup/cli.md to document --progress flag and noop parsing - Updated docs/reference/safe-outputs.md to add close-discussion safe output - Updated docs/reference/custom-agents.md to mention debug-agentic-workflow 🤖 Generated with [Claude Code](https://claude.com/claude-code) Co-Authored-By: Claude <noreply@anthropic.com>
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.
After triggering a workflow, users and AI agents had no immediate guidance on how to analyze the run results.
Changes
Display audit command suggestion with run ID after workflow trigger:
Add test coverage for message format and agent-friendly characteristics
Implementation
Added 3 lines in
pkg/cli/run_command.goafter the workflow URL display:The suggestion appears only when run info is successfully retrieved, providing immediate actionable guidance without requiring users to extract the run ID from the URL.
Original prompt
💬 We'd love your input! Share your thoughts on Copilot coding agent in our 2 minute survey.