[PR #108] [MERGED] Update preset configurations for better termination and pragmatic reviews #139

New issue

Closed

opened 2026-02-27 10:22:23 +03:00 by kerem · 0 comments

kerem commented

2026-02-27 10:22:23 +03:00

Owner

📋 Pull Request Information

Original PR: https://github.com/mikeyobrien/ralph-orchestrator/pull/108
Author: @mikeyobrien
Created: 1/25/2026
Status: ✅ Merged
Merged: 1/25/2026
Merged by: @mikeyobrien

Base: main ← Head: preset-updates

📝 Commits (1)

e939f8e Update preset configurations

📊 Changes

7 files changed (+58 additions, -22 deletions)

View changed files

📝 presets/api-design.yml (+8 -2)
📝 presets/code-archaeology.yml (+5 -1)
📝 presets/documentation-first.yml (+8 -2)
📝 presets/mob-programming.yml (+8 -2)
📝 presets/socratic-learning.yml (+5 -4)
📝 presets/spec-driven.yml (+8 -1)
📝 tools/preset-test-tasks.yml (+16 -10)

📄 Description

Summary

Add pragmatic review guidance to prevent infinite rejection loops in reviewer hats (api-design, documentation-first, spec-driven)
Fix termination conditions in mob-programming and socratic-learning presets to use LOOP_COMPLETE correctly
Update complexity ratings based on observed iteration counts (socratic-learning, mob-programming, code-archaeology)
Increase timeouts to account for multi-hat presets with exploration (~75-90s/iteration)

Test plan

Run cargo test to verify no regressions
Test affected presets with sample tasks to verify proper termination

_{🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.}

## 📋 Pull Request Information **Original PR:** https://github.com/mikeyobrien/ralph-orchestrator/pull/108 **Author:** [@mikeyobrien](https://github.com/mikeyobrien) **Created:** 1/25/2026 **Status:** ✅ Merged **Merged:** 1/25/2026 **Merged by:** [@mikeyobrien](https://github.com/mikeyobrien) **Base:** `main` ← **Head:** `preset-updates` --- ### 📝 Commits (1) - [`e939f8e`](https://github.com/mikeyobrien/ralph-orchestrator/commit/e939f8e04593c5195c98e078a43fdfa3bc426cb5) Update preset configurations ### 📊 Changes **7 files changed** (+58 additions, -22 deletions) <details> <summary>View changed files</summary> 📝 `presets/api-design.yml` (+8 -2) 📝 `presets/code-archaeology.yml` (+5 -1) 📝 `presets/documentation-first.yml` (+8 -2) 📝 `presets/mob-programming.yml` (+8 -2) 📝 `presets/socratic-learning.yml` (+5 -4) 📝 `presets/spec-driven.yml` (+8 -1) 📝 `tools/preset-test-tasks.yml` (+16 -10) </details> ### 📄 Description ## Summary - Add pragmatic review guidance to prevent infinite rejection loops in reviewer hats (api-design, documentation-first, spec-driven) - Fix termination conditions in mob-programming and socratic-learning presets to use `LOOP_COMPLETE` correctly - Update complexity ratings based on observed iteration counts (socratic-learning, mob-programming, code-archaeology) - Increase timeouts to account for multi-hat presets with exploration (~75-90s/iteration) ## Test plan - [ ] Run `cargo test` to verify no regressions - [ ] Test affected presets with sample tasks to verify proper termination --- <sub>🔄 This issue represents a GitHub Pull Request. It cannot be merged through Gitea due to API limitations.</sub>