Skip to content

Conversation

@Rubiss
Copy link

@Rubiss Rubiss commented Jan 20, 2026

No description provided.

Copilot AI review requested due to automatic review settings January 20, 2026 02:34
@Rubiss Rubiss mentioned this pull request Jan 20, 2026
Copy link
Contributor

Copilot AI left a 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 pull request adds autonomous implementation support to the Specify CLI through a new "Ralph Loop" command. The feature enables controlled iteration through task execution using GitHub Copilot CLI with fresh agent contexts per iteration.

Changes:

  • Adds new specify ralph CLI command with configurable iteration limits and AI model selection
  • Implements cross-platform loop orchestrators (PowerShell and Bash scripts)
  • Creates progress tracking with iteration history and codebase pattern discovery
  • Adds comprehensive documentation including spec, plan, research, and task breakdowns

Reviewed changes

Copilot reviewed 48 out of 49 changed files in this pull request and generated 3 comments.

Show a summary per file
File Description
src/specify_cli/init.py Adds ralph command with prerequisite validation, script detection, and invocation
scripts/powershell/ralph-loop.ps1 PowerShell orchestrator for Windows with iteration management and Copilot CLI integration
scripts/bash/ralph-loop.sh Bash orchestrator for Unix/Linux with parallel functionality to PowerShell version
specs/001-ralph-loop-implement/*.md Complete specification documents (spec, plan, tasks, research, contracts, checklists)
.github/agents/speckit.ralph.agent.md Agent profile defining work unit scope and execution constraints
templates and other support files Templates, configuration updates, and agent context files

💡 Add Copilot custom instructions for smarter, more guided reviews. Learn how to get started.

if models_list:
console.print("[green]Available models:[/green]")
for m in models_list:
default_marker = " [yellow](default)[/yellow]" if m == "claude-sonnet-4.5" else ""
Copy link

Copilot AI Jan 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The default model name "claude-sonnet-4.5" appears to be hardcoded, but this model version may not exist. Based on typical Claude versioning, this should likely be "claude-sonnet-3.5" or verify that version 4.5 actually exists in the Copilot CLI.

Copilot uses AI. Check for mistakes.
Write-Host "--- Copilot Agent Output ---" -ForegroundColor DarkCyan
$outputLines = @()
# Use speckit.ralph agent - it already knows to complete one work unit
& copilot --agent speckit.ralph -p $prompt --model $Model --allow-all-tools -s 2>&1 | ForEach-Object {
Copy link

Copilot AI Jan 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The scripts reference agent "speckit.ralph" but the specification documents repeatedly reference "speckit.implement" as the agent profile to use. This inconsistency needs to be resolved - either both scripts and documentation should use "speckit.ralph" or both should use "speckit.implement".

Copilot uses AI. Check for mistakes.
while IFS= read -r line; do
echo "$line"
output_lines+=("$line")
done < <(copilot --agent speckit.ralph -p "$prompt" --model "$model" --allow-all-tools -s 2>&1) || exit_code=$?
Copy link

Copilot AI Jan 20, 2026

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The scripts reference agent "speckit.ralph" but the specification documents repeatedly reference "speckit.implement" as the agent profile to use. This inconsistency needs to be resolved - either both scripts and documentation should use "speckit.ralph" or both should use "speckit.implement".

Copilot uses AI. Check for mistakes.
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant