Skip to content

Latest commit

 

History

History
159 lines (111 loc) · 10.8 KB

CHANGELOG.md

File metadata and controls

159 lines (111 loc) · 10.8 KB

Changelog

All notable changes to the Ralph Loop extension will be documented in this file.

The format is based on Keep a Changelog, and this project adheres to Semantic Versioning.

[Unreleased]

Fixed

  • Select dependency-ready work across Setup, Foundational, user-story, and final phases, including tasks without story labels. Keep each iteration within one story or one non-story phase and allow validated partial commits in fallback prompts.
  • Stop both orchestrators after three consecutive iterations without validated completed work, independently of agent exit codes. Count unsuccessful subject repairs, retain immediate validation failures, and accept completion with follow-up task additions as progress.
  • Report remaining tasks and available blocker context when the no-progress circuit breaker stops a run.
  • Recognize task IDs wrapped in Markdown emphasis (- [x] **T1. …**, __T1__, *T1*) in both orchestrators. Since 1.4.2 such a completed task yielded no ID, and a fully completed iteration was rejected as failed-iteration-advanced-head (#59).

[1.5.0] - 2026-09-11

Added

  • Added official OpenCode CLI support in both orchestrators, with non-interactive fresh iterations, model and prompt forwarding, streamed output, and the existing failure handling (#3).

Fixed

  • Fixed the Bash failure counter exiting on the first failed agent call under set -e, allowing the three-consecutive-failure circuit breaker and failure summary to run.
  • Required speckit.ralph.run to dispatch the orchestrator and verify fresh startup output before reporting success, with explicit in-app/native terminal fallbacks, a bounded startup check, and actionable failed or unverified launch results (#29).

[1.4.2] - 2026-08-23

Fixed

  • Accepted valid task-expansion iterations that complete existing tasks while adding follow-up unchecked tasks, and kept add-only task churn rejected (#49).
  • Reconciled the iterate command's partial-progress instructions with the orchestrator's commit validation: a validated task subset is now committed as a coordinated work unit each iteration, so a multi-task user story can span several iterations without terminating the loop as FAILED (#50).

[1.4.1] - 2026-07-24

Fixed

  • Accepted coordinated state-only commits when an iteration intentionally completes review or analysis tasks, while continuing to reject bookkeeping commits that do not advance task state.

[1.4.0] - 2026-07-18

Added

  • Added configurable nested Ralph commit policy with legacy and conventional styles, optional scope selection, inferred issue suffixes, runtime subject enforcement, and matching Bash and PowerShell coverage.

Changed

  • Amended the constitution to v2.1.0 to allow a narrow pre-acceptance retry for subject-only commit-subject-invalid defects from explicitly configured commit policy, while keeping broader cleanup, recovery, and history-rewrite behavior forbidden.

[1.3.2] - 2026-07-13

Fixed

  • Allowed Ralph to rerun after clean human-authored spec or task refinements by limiting coordinated commit-shape validation to commits created within the current iteration (#39).

[1.3.1] - 2026-07-13

Changed

  • Reduced fresh-install payloads by excluding repository-only tests, community and security documents, and root Git metadata files; package-local attributes retain required LF checkouts for shell scripts and the canonical memory template. Removed the redundant ralph-config.template.yml while retaining ralph-config.yml as the manifest's canonical configuration source.
  • Expanded the contributing guide with the main pull request target, changelog requirements, cross-platform test commands, release ownership, and repository-specific review guidance; CI no longer retains obsolete master branch triggers.

[1.3.0] - 2026-07-11

Added

  • Added a packaged canonical templates/ralph-memory.md and cross-platform create-new initialization with aggregate, byte-preserving validation for malformed feature memory.
  • Added read-only coordinated-commit and bookkeeping-only validation for work-unit history.

Changed

  • Fresh iterations now read compact ralph-memory.md before tasks and design artifacts; progress.md is append-only audit history and only optional recent context.
  • Completed work now persists task state, durable memory, and audit before one substantive commit. Failed or no-work attempts retain useful memory/audit changes without advancing HEAD.
  • Completion now requires zero tasks, the exact terminal handoff, valid coordinated history, and an empty repository-wide git status --short --untracked-files=all; dirty or inconsistent states stop immediately without repair or another agent iteration.

[1.2.1] - 2026-07-04

Fixed

  • Corrected the required Spec Kit version to >=0.8.5 so installs enforce the Copilot skills-mode integration metadata required by Ralph's dispatch logic.
  • Updated compatibility documentation and direct archive install examples for the v1.2.1 release.

[1.2.0] - 2026-07-04

Added

  • Official Claude Code support via a dedicated claude invocation path (--dangerously-skip-permissions) in both Bash and PowerShell orchestrators (#8)
  • Regression coverage for Claude CLI detection and the Claude iteration codepath

Changed

  • Documented claude as a supported agent_cli value and marked it as an optional tool requirement

Fixed

  • PowerShell Copilot dispatch now reads Spec Kit's nested integration_settings.copilot settings, so skills-mode repositories invoke /speckit-ralph-iterate instead of the dotted speckit.ralph.iterate agent.
  • Agent CLI detection now works on bash 3.2 (the default on macOS); the previous ${var,,} lowercasing failed with bad substitution, causing every agent_cli to be reported as unsupported
  • Claude iterations now pass the speckit.ralph.iterate command text in the prompt instead of --agent speckit.ralph.iterate; Claude Code has no registered agent to select, so the old invocation always failed
  • Completion signal is now recognized only when <promise>COMPLETE</promise> stands alone on a line, so agents mentioning the token in prose (e.g. "no <promise>COMPLETE</promise>") no longer terminate the loop prematurely

[1.1.2] - 2026-06-19

Fixed

  • Hardened speckit.ralph.run so free-form launcher text like Implement US1 is warned about and ignored, preventing the host agent from implementing tasks inline instead of launching the Ralph loop (#18).

[1.1.1] - 2026-06-05

Fixed

  • Install-time Ralph config placement now targets .specify/extensions/ralph/ralph-config.yml, matching the path loaded by the orchestrator scripts.

[1.1.0] - 2026-06-01

Added

  • Official Codex CLI support via a dedicated codex exec invocation path in both Bash and PowerShell orchestrators
  • Regression coverage for agent CLI detection and Codex prompt assembly

Changed

  • Documented supported agent_cli values and marked Copilot/Codex tool requirements as alternative optional agent CLIs

[1.0.2] - 2026-05-01

Changed

  • Updated repository references from Rubiss/spec-kit-ralph to Rubiss-Projects/spec-kit-ralph after the repository transfer
  • Updated the README installation example to point at the v1.0.2 release archive

[1.0.1] - 2026-04-12

Added

  • Two-workflow release pipeline: release.yml (workflow_dispatch) creates a version-bump PR, and release-publish.yml creates the tag and GitHub Release when the PR merges — respects branch protection without elevated tokens
  • .github/workflows/tests.yml — CI workflow running bash tests on Ubuntu and PowerShell tests on Windows for PRs and pushes to main
  • Regression test suites: 25 bash tests (tests/regression/bash/) and 26 PowerShell tests (tests/regression/powershell/)

Fixed

  • get_incomplete_task_count in ralph-loop.sh returning "0 0" instead of "0" when no incomplete tasks exist — grep -c outputs "0" with exit code 1, then || echo 0 duplicated it (#1)
  • Hardcoded model: Claude Haiku 4.5 (copilot) in run.md frontmatter preventing use with non-Copilot CLIs or setups without Haiku access (#1)

[1.0.0] - 2026-03-08

Added

Extension Manifest

  • extension.yml — schema v1.0 manifest declaring 2 commands, 1 hook, 1 config template, and tool requirements (copilot, git)

Commands

  • speckit.ralph.run — thin launcher that validates prerequisites, resolves configuration, and launches the platform-appropriate orchestrator script in a visible terminal
  • speckit.ralph.iterate — single-iteration agent command that completes one work unit from tasks.md, commits, and updates progress.md

Orchestrator Scripts

  • ralph-loop.ps1 — PowerShell orchestrator for Windows with real-time agent output streaming
  • ralph-loop.sh — Bash orchestrator for macOS/Linux with real-time agent output streaming
  • 5-layer configuration precedence: extension defaults → project config → local config → environment variables → CLI parameters
  • 3-consecutive-failure circuit breaker
  • Graceful Ctrl+C / SIGINT handling (exit code 130)
  • Summary block on all 4 termination paths (completed, interrupted, failed, iteration limit)
  • Cross-iteration progress tracking via progress.md

Configuration

  • ralph-config.template.yml — config template with model, max_iterations, and agent_cli settings
  • Environment variable overrides: SPECKIT_RALPH_MODEL, SPECKIT_RALPH_MAX_ITERATIONS, SPECKIT_RALPH_AGENT_CLI

Hooks

  • after_tasks hook for optional post-task-generation loop start

Project Files

  • README.md with installation, usage (agent command + direct script), configuration reference, loop architecture diagram, and extension structure
  • CONTRIBUTING.md with PR guidelines
  • LICENSE (MIT)
  • CODEOWNERS — auto-request review from @Rubiss
  • .extensionignore — excludes .github/, .specify/, .vscode/, and specs/ from extension packaging
  • .gitignore for local config and build artifacts

Spec Documentation

  • Full spec-kit design artifacts under specs/001-port-ralph-extension/: spec, plan, research, data model, quickstart, tasks, requirements checklist, and contracts (command schemas, config schema, extension manifest)