5.4 KiB
5.4 KiB
Changelog
[0.3.0] - 2026-11-03
Breaking:
- Skills: every skill is now kvb-category-name; the old names are gone
- Skills: the category skills is now skill, e.g. kvb-skill-tune
- Skills: kvb-create-feature is now kvb-think-gaps
- Skills: kvb-skill-dream is now kvb-dream
- Skills: kvb-skills-shortcuts and tokens such as sobu are gone
Added:
- Org: kvb-org-rasci keeps one RASCI/OKR register of every agent task
- Org: kvb-org-artefacts tracks images, volumes and worktrees per task
- Org: kvb-org-wsjf ranks the register by WSJF from Fibonacci estimates
- Org: kvb-org-operator lists every command only the operator can run
- Commit: commit skills show worktree, branch, confidence and risk first
- Transcend: kvb-transcend carries session scripts and tests into repos
- Requirements: kvb-create-requirement with user story, Mermaid and tests
- Think: kvb-think-brainstorm scores options from seven fixed lenses
- Skills: kvb-skill-compile turns deterministic steps into scripts
- Skills: kvb-skill-cleanup deletes legacy skills that renames left behind
- Dream: kvb-optimize runs all nine optimization skills in one pass
- Dream: a GNOME notification recommends /kvb-dream daily at 17:00
- Coach: kvb-coach suggests the next step for mind, body, food and tasks
- Coach: kvb-coach-meditation plays alpha-wave music with fractals
- Coach: a short coach note at the first prompt of every full hour
Changed:
- Dream: covers every repository and session, then optimizes and cleans up
- Dream: one hint per agent every 12 h replaces the tune and dream hints
- Tune: kvb-code-tune always checks language, framework and recursion
- Cleanup: worktrees are listed by size and integration line
- Coordination: hotfix gates take the next free test slot
- Coordination: an agent may end its own job after 60 min without progress
Upgrade notes:
- Install: run make install and restart the agent to load the new names
- Install: run make install-skills in each project to drop old copies
- Install: /kvb-skill-cleanup lists any legacy skill left behind
- Install: the global install enables the kvb-dream-notify.timer unit
- Settings: remove autotune and dream hooks from ~/.claude/settings.json
[0.2.0] - 2026-10-31
Added:
- Git: branch-gc clears merged branches and worktrees with pkgmgr
- Agents: subagent-model uses a cheaper model only at 90 % same result
- Agents: subagent-model hooks log every spawn and its rated quality
Changed:
- Coordination: never cut a running job or agent short, not even at its cap
- Resources: watch.py admit grants test slots only below CPU and RAM limits
- Coordination: a relayer writes an operator rule to shared memory first
Fixed:
- Resources: stop-stage cleanup now skips worktrees where make still runs
- Resources: the block hook ignores heavy commands in quotes and heredocs
- Update: make update now updates every locked source, not just the first
- Update: make update installs for Claude Code only
- CI: ci-artifacts signs lint failures by finding, ignores later steps
- Release: changelog warns when a workflow on HEAD already failed
- CI: ruff pinned in pyproject.toml; local and CI lint now agree
Upgrade notes:
- 0.1.0 was never published (its CI failed); its upgrade notes follow
- Install: restart the agent after make install to load skills and hooks
- Resources: watch.py needs ~/.config/agents-council/config.json
- Resources: add busy_processes and load_limits to that config
[0.1.0] - 2026-10-30
Added:
- Install: make install and make project install every locked skill
- Install: enables caveman and ponytail; adds autotune and dream reminders
- Commit: commit-next commits a bundle and stages the next one
- Commit: comments-clean and advocate audit every commit before it lands
- Commit: confidence and break-risk report measured fix and break numbers
- Coordination: democracy elects the first agent to claim work as its owner
- Coordination: council.py claims work; a hook blocks edits without a claim
- Coordination: funnel keeps agent work in worktrees until it clears 90/5
- Resources: watch.py blocks heavy jobs and cleans up before the disk fills
- Cleanup: cleanup frees disk space after asking every peer agent
- CI: triage, observe and ci-artifacts with ci_failures.py clustering
- CI: tune finds speed-ups that never cut logic, coverage or correctness
- Git: merge-fix with find_fix.py finds a fix on any branch and merges it
- Reasoning: active-listening and dialectic pin requirements and causes
- Review: criticize and sceptic give critique hardened by dialectic
- Autonomy: plan hands an objective-oriented plan to robot
- Quality: test runs Makefile targets; --fix loops until they are green
- Quality: refactor, no-defaults and scope-guard keep changes lean
- Skills: autotune, autoskill, dream and essence improve the skills
- Release: changelog writes the pkgmgr release message since the last tag
- Status: status-matrix lists everything in flight with its confidence
- Help: explain and help-skills explain code and the skill set
- Chat: shortcuts expands operator tokens such as sobu and socon
- Security: medusa runs the MEDUSA scanner on repos and secret stores
- Docs: the README skill map shows how the skills invoke each other
Upgrade notes:
- Install: restart the agent after make install to load skills and hooks
- Resources: watch.py needs ~/.config/agents-council/config.json