[PR #107] [CLOSED] Update preset configurations for better termination and pragmatic reviews #137

New issue

Closed

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

kerem commented

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

Owner

📋 Pull Request Information

Original PR: https://github.com/mikeyobrien/ralph-orchestrator/pull/107
Author: @mikeyobrien
Created: 1/25/2026
Status: ❌ Closed

Base: main ← Head: preset-updates

📝 Commits (7)

d8d5f71 feat(ralph-web): add web dashboard with MockLoopManager E2E tests
f7c38b2 feat(ralph-core): add shared session directory for diagnostics
220a520 feat(ralph-core): improve task breakdown guidance
7f19a38 feat(ralph-web): add lazy session loading and mock diagnostics
6f1c8be feat(ralph-web): improve live view session initialization
17d8387 docs: add playwright and diagnostics tips to AGENTS.md
c71aea0 Update preset configurations

📊 Changes

106 files changed (+18931 additions, -506 deletions)

View changed files

📝 .agent/memories.md (+3 -47)
📝 .github/workflows/docs.yml (+11 -8)
📝 AGENTS.md (+13 -305)
📝 Cargo.lock (+386 -1)
📝 Cargo.toml (+1 -0)
📝 PROMPT.md (+25 -2)
📝 crates/ralph-cli/src/main.rs (+23 -5)
📝 crates/ralph-core/src/config.rs (+4 -2)
📝 crates/ralph-core/src/diagnostics/mod.rs (+45 -1)
📝 crates/ralph-core/src/event_loop/mod.rs (+1 -14)
📝 crates/ralph-core/src/hatless_ralph.rs (+26 -18)
📝 crates/ralph-e2e/Cargo.toml (+3 -0)
📝 crates/ralph-e2e/src/lib.rs (+2 -0)
📝 crates/ralph-e2e/src/main.rs (+184 -44)
📝 crates/ralph-e2e/src/runner.rs (+109 -1)
📝 crates/ralph-e2e/src/scenarios/orchestration.rs (+13 -36)
➕ crates/ralph-web/Cargo.toml (+78 -0)
➕ crates/ralph-web/README.md (+106 -0)
➕ crates/ralph-web/frontend/.gitignore (+24 -0)
➕ crates/ralph-web/frontend/README.md (+73 -0)

...and 80 more files

📄 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/107 **Author:** [@mikeyobrien](https://github.com/mikeyobrien) **Created:** 1/25/2026 **Status:** ❌ Closed **Base:** `main` ← **Head:** `preset-updates` --- ### 📝 Commits (7) - [`d8d5f71`](https://github.com/mikeyobrien/ralph-orchestrator/commit/d8d5f713d185095708cac773a77e8089a3e89a55) feat(ralph-web): add web dashboard with MockLoopManager E2E tests - [`f7c38b2`](https://github.com/mikeyobrien/ralph-orchestrator/commit/f7c38b2adc9f7b85e8fb1bce927d11d584e32047) feat(ralph-core): add shared session directory for diagnostics - [`220a520`](https://github.com/mikeyobrien/ralph-orchestrator/commit/220a52004a2a4adf2daf0bbd70409d4f6781eeae) feat(ralph-core): improve task breakdown guidance - [`7f19a38`](https://github.com/mikeyobrien/ralph-orchestrator/commit/7f19a386f0f8c2c514a72c12ee72946753fadb5f) feat(ralph-web): add lazy session loading and mock diagnostics - [`6f1c8be`](https://github.com/mikeyobrien/ralph-orchestrator/commit/6f1c8be85906f19a2ede6ba6cca9ecb2b6825e7a) feat(ralph-web): improve live view session initialization - [`17d8387`](https://github.com/mikeyobrien/ralph-orchestrator/commit/17d8387045e5d16c1996c3afc4a35b471c98e4dc) docs: add playwright and diagnostics tips to AGENTS.md - [`c71aea0`](https://github.com/mikeyobrien/ralph-orchestrator/commit/c71aea03525fc28e0efd4be58b0b4cb0af4fa63f) Update preset configurations ### 📊 Changes **106 files changed** (+18931 additions, -506 deletions) <details> <summary>View changed files</summary> 📝 `.agent/memories.md` (+3 -47) 📝 `.github/workflows/docs.yml` (+11 -8) 📝 `AGENTS.md` (+13 -305) 📝 `Cargo.lock` (+386 -1) 📝 `Cargo.toml` (+1 -0) 📝 `PROMPT.md` (+25 -2) 📝 `crates/ralph-cli/src/main.rs` (+23 -5) 📝 `crates/ralph-core/src/config.rs` (+4 -2) 📝 `crates/ralph-core/src/diagnostics/mod.rs` (+45 -1) 📝 `crates/ralph-core/src/event_loop/mod.rs` (+1 -14) 📝 `crates/ralph-core/src/hatless_ralph.rs` (+26 -18) 📝 `crates/ralph-e2e/Cargo.toml` (+3 -0) 📝 `crates/ralph-e2e/src/lib.rs` (+2 -0) 📝 `crates/ralph-e2e/src/main.rs` (+184 -44) 📝 `crates/ralph-e2e/src/runner.rs` (+109 -1) 📝 `crates/ralph-e2e/src/scenarios/orchestration.rs` (+13 -36) ➕ `crates/ralph-web/Cargo.toml` (+78 -0) ➕ `crates/ralph-web/README.md` (+106 -0) ➕ `crates/ralph-web/frontend/.gitignore` (+24 -0) ➕ `crates/ralph-web/frontend/README.md` (+73 -0) _...and 80 more files_ </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>