v2.16.0

Highlights

Evolve idle hardening — 52% of evolve commits in production were idle noise. Now idle cycles aren't committed, stagnation is disk-derived (survives compaction), and a 60-minute circuit breaker stops runaway sessions.
Evolve --quality mode — New flag inverts the priority cascade: post-mortem findings before goals. Harvested work has 100% first-attempt success rate in production (15/15 items). Quality scoring tracks unconsumed findings.
6-phase RPI E2E tests — Full lifecycle validation: gate retries, complexity scaling, phase summaries, promise tags. Catches integration regressions that unit tests miss.
8 ao CLI bug fixes — Pool matching, artifact counts, score display, symlink detection, JSON truncation, and more (#41-#48).

What's New

Evolve Skill Overhaul

The evolve skill received three major improvements based on analysis of 179 production cycles (117 commits, 7.5 days of autonomous operation):

Idle cycles are no longer committed to git, reducing commit noise by ~52%
Rolling fitness files (fitness-latest.json) replace per-cycle snapshots
Canonical cycle-history.jsonl schema standardized across all entry types
New --quality mode prioritizes unconsumed post-mortem findings

CLI Fixes

Eight bugs fixed across ao subcommands, all with issue tracking (#41-#48). Notable: v1 GOALS.yaml now accepted with deprecation warning + migration path.

Skill Maintenance

13 skills received targeted fixes: dead links, stale references, missing catalog entries, vaporware sections removed, fixture paths corrected.

Testing

Fixture-based CLI regression tests and a 6-phase RPI E2E test suite added for comprehensive lifecycle validation.

All Changes

Full changelog (click to expand)

Added

Evolve idle hardening, --quality mode, schema standardization
heal-skill checks 7-10 with --strict CI gate
6-phase E2E validation for RPI lifecycle
Fixture-based CLI regression and parity tests
ao goals migrate command (#48)
Goal failure taxonomy script and tests

Changed

6 architecture concerns addressed (CLI taxonomy, shared resolver, skill versioning, doctor dogfooding)
GoReleaser action v6 → v7
Evolve build detection generalized to multi-language

Fixed

ao pool list --wide and prefix matching (#47)
Artifact count consistency (#46)
Vibe-check score double multiplication (#45)
Symlink skill detection (#44)
Learnings frontmatter ID resolution (#43)
JSON output truncation (#42)
Hook event count display (#41)
13 skill fixes (post-mortem, handoff, quickstart, openai-docs, provenance, oss-docs, reverse-engineer-rpi, evolve, crank, codex-team, security, using-agentops, vibe)
Post-mortem schema migration
Evolve oscillation detection
Embedded skills and CLI docs sync

Full Changelog: See CHANGELOG.md

2.8 KiB Raw Blame History