Skip to content

Releases: javiarmesto/ALDC-AL-Development-Collection

Release v4.2.0

12 Jun 16:06
0aea659

Choose a tag to compare

[4.2.0] - 2026-06-12

Fixed

  • Fase 0 conformidad (PR #74): contadores contradictorios en CLAUDE.md, 3 enlaces rotos en README, primitivos sin declarar en aldc.yaml (al-triage, skill-manifest, skill-contribution-assistant, al-agent.build-instructions), y fichero packages/foundation/skills/skill-manifest/SKILL.md truncado (afectaba al empaquetado del VSIX).
  • Contadores del banner de install.js alineados con la realidad (10 agentes / 16 skills / 11 workflows / 9 instructions).

Added

  • ARCHITECTURE.md — mapa fuente ↔ generado ↔ canal de distribución.
  • scripts/check-conformance.js — verificador de conformidad, integrado en CI.
  • scripts/sync-foundation.js — sincronización raíz → packages/foundation (fuente del VSIX), con modo --check en CI.
  • Nota de contexto del ecosistema (CIRCE → Copilot Studio, DELFOS → Power BI) en skill-manifest.

Removed

  • packages/foundation/skills/skill-manifest/samples/ (duplicado de examples/, sin referencias).

What's Changed

  • style(web): promote 4.1.0 in the hero banner, demote the workshop link (EN + ES) by @javiarmesto in #58
  • fix(agents): explicit .github/-prefixed paths in primitive prose by @javiarmesto in #60
  • fix(skills): audit remediation - frontmatter, broken pointers, conditional refs, JIT splits by @javiarmesto in #61
  • style(al-conductor): lightweight, token-conscious progress format by @javiarmesto in #62
  • feat(agents): lightweight BCQuality status badge (review/dredd/triage) by @javiarmesto in #63
  • refactor(tools): least-privilege tool audit across agents + spec.create by @javiarmesto in #64
  • feat(bcquality): explicit enabled switch, resolved once by the conductor by @javiarmesto in #65
  • perf(review): cut token waste in the conductor→review/BCQuality path by @javiarmesto in #66
  • perf(triage): mirror the #2 "don't re-read in context" guard into al-triage by @javiarmesto in #67
  • feat(spec): spec as single source of truth for event integration points by @javiarmesto in #68
  • feat(orchestration): actually load instructions + skills in agent runtime by @javiarmesto in #70
  • feat(conductor): modernize the checkpoint card with an evidence row by @javiarmesto in #71
  • docs(plugin): modernize Claude Code plugin tool prose + sync agent improvements by @javiarmesto in #69
  • fix: conformidad Fase 0 - contadores, enlaces README, aldc.yaml, foun… by @javiarmesto in #74
  • chore: alinear version 4.2.0 con el Marketplace + changelog 4.1.x by @javiarmesto in #75

Full Changelog: v4.1.0...v4.2.0

Release v4.1.0

05 Jun 15:46
07d8e07

Choose a tag to compare

[4.1.0] - 2026-06-05

Changed

  • Trimmed always-on entrypoint (~31% lighter) — consuming projects receive the leaner Copilot entrypoint on install; less context injected on every request.
  • Narrow instruction globs (applyTo by object type) — only rules for the file being edited are loaded.
  • Conductor context passing — passes curated context excerpts to subagents instead of whole files.
  • Condensed primitives (agents, instructions, skills) — behavior and orchestration preserved.
  • BCQuality task-context built once and passed inline — no re-derivation per call.

Added

  • BCQuality — optional external, citable BC knowledge layer for reviews & audits: a pinned fork consumed externally (multi-root), external.bcquality configuration, install scripts (tools/bcquality/), a multi-root aldc.code-workspace, evidence validation (pin coherence + citation resolvability) wired into CI, and a full guide (docs/bcquality.md). Graceful native A–G fallback when absent — never blocks.
  • @AL Triage — reactive diagnosis agent (read-only on code).
  • @Dredd — independent static auditor (read-only on code; BCQuality-cited advisory verdict).
  • skill-contribution-assistant — guided contribution workflow.
  • Restored full architecture and spec templates with section-complete authoring guidance.

Release v4.0.0

30 May 19:47
3ead7ba

Choose a tag to compare

[4.0.0] - 2026-05-30

Token Efficiency & Foundation Restructure

Breaking Changes:

  • Primitives reorganized into a packages/foundation/ structure (agents, instructions, prompts, skills) alongside the existing root layout
  • Agent, instruction, and skill content condensed to reduce token consumption — wording and structure changed, behavior preserved

Added:

  • packages/foundation/ package layout for framework primitives
  • Architecture Decision Records (docs/decisions/): ADR-0001 (Phase 1 restructure), ADR-0002 (distribution lifecycle), ADR-0003 (package structure)
  • al-agent.build-instructions prompt
  • skill-manifest SKILL entry and skill-agent-task-patterns usage examples

Changed:

  • Agents, instructions, and skills optimized for lower token footprint while preserving behavior and orchestration
  • Documentation templates (spec, architecture, delivery, technical-spec, test-plan) condensed for token efficiency
  • Prompts revised for conciseness and clearer GitHub Copilot alignment
  • All instruction files and templates translated to English

What's Changed

  • feat(docs): restyle MkDocs site with Base44 Softly Lit Gradient Canvas by @javiarmesto in #39
  • Claude/xenodochial elgamal 05d3f8 by @javiarmesto in #40
  • Claude/xenodochial elgamal 05d3f8 by @javiarmesto in #41
  • feat: add packages/foundation structure and architecture decision records by @javiarmesto in #44
  • refactor: optimize agents, skills, instructions and prompts for token efficiency by @javiarmesto in #45
  • refactor(templates): optimize documentation templates for token efficiency by @javiarmesto in #46
  • refactor(instructions): translate all instruction files to English by @javiarmesto in #47
  • refactor(instructions+templates): translate all content to English by @javiarmesto in #48
  • docs: update README and CHANGELOG for v4.0.0 release by @javiarmesto in #49
  • chore: bump package.json to 4.0.0 for release by @javiarmesto in #50

Full Changelog: v3.2.3...v4.0.0

Release v3.2.3

27 Apr 17:27

Choose a tag to compare

[3.2.3] - 2026-04-24

Updated

  • Agents updated with improved model references and refined LLM prompting strategies
  • Prompts revised for clarity and better GitHub Copilot alignment
  • Tools and workflows enhanced with latest framework improvements
  • New skill-manifest skill: Extension Manifest Generator for BC extensions
  • Claude plugin updated: commands, rules, and skills aligned with framework v3.2.3

What's Changed

  • Add bilingual QUICK-START documentation with AI disclaimers by @Copilot in #29
  • Add 2025 EMEA Community Keynote: Knowledge-First AI Development Workflow by @JeremyVyska in #30
  • Reorganize repository structure (Phases 1-3) by @javiarmesto in #32
  • feat: ALDC Core v3.2.0 — Skills restructure & agent coherence by @javiarmesto in #33
  • Feature/claude code migration by @javiarmesto in #34
  • Actualizar README by @javiarmesto in #35
  • feat: add Claude Code support and official plugin package by @javiarmesto in #36
  • Merge audit changes into main by @javiarmesto in #37

New Contributors

Full Changelog: v2.7.0...v3.2.3