Skip to content

v1.37.0

Choose a tag to compare

View all tags
@github-actions github-actions released this 09 Jun 12:40
· 63 commits to main since this release
v1.37.0
03457e9
This commit was created on GitHub.com and signed with GitHub’s verified signature.
GPG key ID: B5690EEEBB952194
Verified
Learn about vigilant mode.

✨ Highlights

  • New agent: Hermes — full support: detection, adapter, registration, MCP/engram/persona/skill-registry injection, and SDD orchestrator routing.
  • chained-pr skill bound across all 12 SDD orchestrators (#792) — sdd-tasks/sdd-apply now load and follow the chained-pr skill before planning or creating any chained PR.

🚀 Features

  • Hermes: model constants, detect-only adapter, registration (factory/catalog/config-scan/cli/tui/engram), permissions handling
  • Hermes injectors: MCP context7, engram, persona (per-agent neutral + gentleman), SDD orchestrator routing
  • Hermes skill-registry scan dirs (~/.hermes/skills, .hermes/skills)
  • YAML MCP server block helpers (filemerge)
  • chained-pr skill binding in all 12 SDD orchestrator templates (#792)

🐛 Fixes

  • filemerge: inline comments in YAML server/key matching, command-recovery normalization, quote stripping
  • mcp: YAML-accurate error messages
  • hermes: detection docs + engram stabilization assertion
  • test: config_scan alignment with 16-entry known agent config dirs

🧹 Maintenance

  • Refactors (misleading comments in engram/sdd/persona, stale test names)
  • Added coverage (filemerge inline comments, hermes cross-cutting: registry, assets embed, language contract, MCP round-trip)
  • Docs (agent matrix, delegation/SDD tables, usage, persona marker vs identity behavior)

📦 Upgrade

brew upgrade gentle-ai

(or self-update on the next run)

Full changelog: v1.36.8...v1.37.0

Assets 9
Loading