Skip to content

v0.1.87

Choose a tag to compare

@Henry-811 Henry-811 released this 15 May 17:00
· 145 commits to main since this release
cccc43d

πŸš€ Release Highlights β€” v0.1.87 (2026-05-15)

πŸ“š Framework Comparison Pages

  • Three new "MassGen vs ..." pages (#1094): crewai.rst, langgraph.rst, autogen.rst under docs/source/reference/comparisons/ β€” each positions MassGen's parallel-refinement-with-voting model against the target framework's coordination shape and lists when to reach for one versus the other
  • Docs landing page update (#1094): "How Does MassGen Compare?" now lists all four comparisons (LLM Council + the three new ones); parent comparisons.rst drops "coming soon" and gains a toctree

πŸ€– llms.txt for AI Agents

  • Curated index (#1094): docs/source/_extra/llms.txt published at the docs site root via Sphinx html_extra_path, following the llmstxt.org spec
  • Full-corpus dump (#1094): llms-full.txt (~1 MB, 59 files) generated by a Sphinx build-finished hook in docs/source/conf.py
  • README pointer: One-line pointer in README.md / README_PYPI.md directing AI agents and crawlers to llms.txt / llms-full.txt

πŸ”§ bootstrap_subagent Single-Shot Fix

  • refine=False (#1094): Orchestrator._run_bootstrap_discriminator_step now passes refine=False to SubagentManager.spawn_subagent. Without it, the orchestrator's max_new_answers_per_agent: 3 default shadowed the coordination-dict overrides and let the discriminator refine instead of running single-shot. Found via live log inspection
  • Test (#1094): massgen/tests/test_bootstrap_criteria.py asserts discriminator must pass refine=False to spawn_subagent for single-shot

βœ… Issues Closed

  • #1082 β€” publish llms.txt + llms-full.txt at docs.massgen.ai
  • #1083 β€” add MassGen vs CrewAI / LangGraph / AutoGen comparison pages

πŸ“– Getting Started

What's Changed

Full Changelog: v0.1.86...v0.1.87