v0.1.85
π Release Highlights β v0.1.85 (2026-05-11)
β οΈ First-stage release β still maturing. Expect further finalization and more thorough end-to-end testing in v0.1.86.
π§ͺ Discriminative Criteria Emergence (criteria_mode)
bootstrap_inlinevariant (fully functional): Neworchestrator.coordination.criteria_mode: bootstrap_inlinemakes each agent emit a shortproposed_criterialist alongside itssubmit_checklistcall β criteria a stronger answer would satisfy that the current answers do not. Proposals are deduped, FIFO-capped (bootstrap_max_total, default 30), persisted tobootstrap_criteria_accumulator.json, and merged into the next round's checklist via the existingEvaluationSection- All backends with checklist tool support: SDK path (Claude Code) gets the field directly in the in-process tool schema; stdio backends (gemini, codex, response, chat_completions, claude, grok) get a JSONL emission channel β
proposed_criteria.jsonlnext to checklist specs, drained by the orchestrator each pass bootstrap_subagentvariant (wired, LLM step deferred): Same accumulator pipeline; in-process LLM discriminator pass queued for v0.1.86- New module
massgen/bootstrap_criteria.pywithmerge_proposals,augment_with_accumulator,is_bootstrap_mode,validate_criteria_mode - Config fields:
CoordinationConfig.{criteria_mode, bootstrap_max_per_agent_per_round, bootstrap_max_total}
π‘οΈ Anti-Goodhart by Construction
- Criteria come from observed gaps, not priors that may not match the task
- Removes cold-start friction: users no longer need to pre-author criteria for new tasks β the first round produces both answers and the criteria the second round must rise to
π¦ New Example Configs
massgen/configs/coordination/bootstrap_inline_criteria.yamlβ fully functional variantmassgen/configs/coordination/bootstrap_subagent_criteria.yamlβ accumulator wired, LLM step in v0.1.86
π§ͺ Tests
- 30 new tests in
massgen/tests/test_bootstrap_criteria.py(476 lines) covering merge/dedup/cap, config validation,AgentState.criteria_proposals, augmentation across criteria sources, rendering gating, and round-N β round-N+1 propagation end-to-end
π Getting Started
- Quick Start Guide
- Try It:
pip install massgen==0.1.85 uv run massgen --config massgen/configs/coordination/bootstrap_inline_criteria.yaml "Create an SVG of an AI agent coding." - Inspect the emerging criteria at
.massgen/massgen_logs/<session>/bootstrap_criteria_accumulator.json
What's Changed
- docs: docs for v0.1.85 by @Henry-811 in #1088
- feat: v0.1.85 by @Henry-811 @ncrispino in #1087
Full Changelog: v0.1.84...v0.1.85