feat: WP-0005 adoption polish — doc sync, fleet parity, CI lint
- Add make agents-sync-package and release-check parity gate - Add tests/test_packaged_agents_parity.py; sync packaged agents with agents/ - Update install docs (HELLO_WORLD, CLI_CHEAT_SHEET, AGENT_DISTRIBUTION) - Expand PACKAGE_RELEASE.md secrets setup and pre-tag checklist - Add flake8 to Gitea CI; CHANGELOG Unreleased for v1.2.0 - Expand INTEGRATION_PATTERNS activity-core handoff checklist
This commit is contained in:
@@ -27,5 +27,8 @@ jobs:
|
||||
- name: Format check (black)
|
||||
run: black --check src tests
|
||||
|
||||
- name: Lint (flake8)
|
||||
run: pip install flake8 && flake8 src/ --max-line-length=100
|
||||
|
||||
- name: Run tests
|
||||
run: pytest tests/ -q --ignore=tests/test_cli_error_handling.py
|
||||
@@ -7,6 +7,15 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
|
||||
|
||||
## [Unreleased]
|
||||
|
||||
### Added
|
||||
- **`make agents-sync-package`** — sync `agents/` into packaged `data/agents/`
|
||||
- **Packaged agent parity test** — `release-check` fails when wheel data drifts from source
|
||||
- **Gitea CI flake8** — lint gate on `src/` in `.gitea/workflows/ci.yml`
|
||||
|
||||
### Changed
|
||||
- **Install documentation** — HELLO_WORLD, CLI_CHEAT_SHEET, AGENT_DISTRIBUTION use Gitea PyPI extra index
|
||||
- **`docs/PACKAGE_RELEASE.md`** — secrets setup and pre-tag release checklist
|
||||
|
||||
## [1.1.0] - 2026-06-18
|
||||
|
||||
### Added
|
||||
|
||||
@@ -32,6 +32,12 @@ pip install -e . # project venv
|
||||
pipx install -e . --force # global pipx install
|
||||
```
|
||||
|
||||
**Consumers (pip install from registry):** see [docs/PACKAGE_RELEASE.md](docs/PACKAGE_RELEASE.md)
|
||||
for Gitea PyPI credentials and `--extra-index-url` install paths.
|
||||
|
||||
**Maintainers (release):** `make agents-sync-package` before tagging when `agents/` changes;
|
||||
`make package-check` and the pre-tag checklist in `docs/PACKAGE_RELEASE.md`.
|
||||
|
||||
## Development Workflow
|
||||
|
||||
### Project Structure
|
||||
|
||||
61
Makefile
61
Makefile
@@ -1,6 +1,6 @@
|
||||
# Makefile for Kaizen Agentic development tasks
|
||||
|
||||
.PHONY: help setup-complete setup-structure setup-python setup-tools setup-docs setup-tests setup-verify ensure-project-structure install-dev install-local install-global standards-check standards-fix standards-test test test-all build clean lint format venv-status agents-list agents-update agents-validate agents-status agents-install-cli release-check release-prepare release-test release-publish publish-gitea package-check release-finalize release-rollback
|
||||
.PHONY: help setup-complete setup-structure setup-python setup-tools setup-docs setup-tests setup-verify ensure-project-structure install-dev install-local install-global standards-check standards-fix standards-test test test-all build clean lint format venv-status agents-list agents-update agents-validate agents-status agents-sync-package agents-install-cli release-check release-prepare release-test release-publish publish-gitea package-check release-finalize release-rollback
|
||||
|
||||
# Variables
|
||||
VENV = .venv
|
||||
@@ -41,6 +41,7 @@ help:
|
||||
@echo " agents-update - Update agents to latest versions"
|
||||
@echo " agents-validate - Validate agent definitions"
|
||||
@echo " agents-status - Show agent status and project info"
|
||||
@echo " agents-sync-package - Sync agents/ into packaged data/agents/ (DRY_RUN=1 to preview)"
|
||||
@echo " agents-install-cli - Install kaizen-agentic CLI tool"
|
||||
@echo ""
|
||||
@echo "Release Management:"
|
||||
@@ -811,7 +812,9 @@ agents-update: $(VENV)/bin/activate
|
||||
@if command -v kaizen-agentic >/dev/null 2>&1; then \
|
||||
kaizen-agentic update; \
|
||||
else \
|
||||
echo "⚠️ kaizen-agentic CLI not found. Install with: pip install kaizen-agentic"; \
|
||||
echo "⚠️ kaizen-agentic CLI not found."; \
|
||||
echo " Dev install: make agents-install-cli (or pip install -e .)"; \
|
||||
echo " Registry: see docs/PACKAGE_RELEASE.md"; \
|
||||
fi
|
||||
|
||||
# Validate installed agents
|
||||
@@ -820,7 +823,9 @@ agents-validate:
|
||||
@if command -v kaizen-agentic >/dev/null 2>&1; then \
|
||||
kaizen-agentic validate; \
|
||||
else \
|
||||
echo "⚠️ kaizen-agentic CLI not found. Install with: pip install kaizen-agentic"; \
|
||||
echo "⚠️ kaizen-agentic CLI not found."; \
|
||||
echo " Dev install: make agents-install-cli (or pip install -e .)"; \
|
||||
echo " Registry: see docs/PACKAGE_RELEASE.md"; \
|
||||
fi
|
||||
|
||||
# Show agent status and project information
|
||||
@@ -829,7 +834,9 @@ agents-status:
|
||||
@if command -v kaizen-agentic >/dev/null 2>&1; then \
|
||||
kaizen-agentic status; \
|
||||
else \
|
||||
echo "⚠️ kaizen-agentic CLI not found. Install with: pip install kaizen-agentic"; \
|
||||
echo "⚠️ kaizen-agentic CLI not found."; \
|
||||
echo " Dev install: make agents-install-cli (or pip install -e .)"; \
|
||||
echo " Registry: see docs/PACKAGE_RELEASE.md"; \
|
||||
echo ""; \
|
||||
echo "Manual agent check:"; \
|
||||
if [ -d "agents" ]; then \
|
||||
@@ -839,6 +846,34 @@ agents-status:
|
||||
fi; \
|
||||
fi
|
||||
|
||||
# Sync canonical agents/ into packaged wheel data
|
||||
AGENTS_SRC_DIR = agents
|
||||
AGENTS_PKG_DIR = src/kaizen_agentic/data/agents
|
||||
|
||||
agents-sync-package:
|
||||
@echo "📦 Syncing packaged agents from $(AGENTS_SRC_DIR)/ ..."
|
||||
@mkdir -p $(AGENTS_PKG_DIR); \
|
||||
SYNCED=0; \
|
||||
for f in $(AGENTS_SRC_DIR)/agent-*.md; do \
|
||||
dest="$(AGENTS_PKG_DIR)/$$(basename $$f)"; \
|
||||
if [ -n "$(DRY_RUN)" ]; then \
|
||||
if [ -f "$$dest" ] && cmp -s "$$f" "$$dest"; then \
|
||||
echo " = $$(basename $$f) (unchanged)"; \
|
||||
else \
|
||||
echo " → $$(basename $$f)"; \
|
||||
fi; \
|
||||
else \
|
||||
cp "$$f" "$$dest"; \
|
||||
echo " ✓ $$(basename $$f)"; \
|
||||
SYNCED=$$((SYNCED + 1)); \
|
||||
fi; \
|
||||
done; \
|
||||
if [ -z "$(DRY_RUN)" ]; then \
|
||||
echo "✅ Synced $$SYNCED file(s) to $(AGENTS_PKG_DIR)/"; \
|
||||
else \
|
||||
echo "ℹ️ DRY_RUN preview only — no files copied"; \
|
||||
fi
|
||||
|
||||
# Install agent distribution CLI
|
||||
agents-install-cli: $(VENV)/bin/activate
|
||||
@echo "📦 Installing Kaizen Agentic CLI..."
|
||||
@@ -895,6 +930,21 @@ release-check: $(VENV)/bin/activate
|
||||
echo " ❌ Build system not configured"; \
|
||||
ISSUES=$$((ISSUES + 1)); \
|
||||
fi; \
|
||||
echo " • Packaged Agent Parity:"; \
|
||||
PARITY_OK=1; \
|
||||
for f in agents/agent-*.md; do \
|
||||
dest="src/kaizen_agentic/data/agents/$$(basename $$f)"; \
|
||||
if [ ! -f "$$dest" ] || ! cmp -s "$$f" "$$dest"; then \
|
||||
PARITY_OK=0; \
|
||||
break; \
|
||||
fi; \
|
||||
done; \
|
||||
if [ $$PARITY_OK -eq 1 ] && ls agents/agent-*.md >/dev/null 2>&1; then \
|
||||
echo " ✅ agents/ matches data/agents/"; \
|
||||
else \
|
||||
echo " ❌ Packaged agents drift from agents/ — run: make agents-sync-package"; \
|
||||
ISSUES=$$((ISSUES + 1)); \
|
||||
fi; \
|
||||
echo ""; \
|
||||
if [ $$ISSUES -eq 0 ]; then \
|
||||
echo "✅ Release readiness: PASSED"; \
|
||||
@@ -1009,7 +1059,8 @@ release-finalize: $(VENV)/bin/activate
|
||||
echo ""; \
|
||||
echo " • Documentation:"; \
|
||||
echo " 💡 Verify installation instructions work:"; \
|
||||
echo " pip install kaizen-agentic==$$VERSION"; \
|
||||
echo " pip install kaizen-agentic==$$VERSION --extra-index-url <gitea-pypi-simple>"; \
|
||||
echo " See docs/PACKAGE_RELEASE.md"; \
|
||||
echo ""; \
|
||||
echo "✅ Release finalization checklist provided"; \
|
||||
echo " Complete manual steps above to finish release process"
|
||||
|
||||
@@ -12,4 +12,3 @@ You are responsible for evaluating alternatives to effectively achieving project
|
||||
You look out for important decisions or variants of how to move forward and use weighted shortest job first to score tasks and issues to provide perspective and guidance.
|
||||
|
||||
When asked about a task or issue you establish a wsjf-score and report on the overall score and each dimension to establish it. You supplement this information with additional risk information especially if the decision and resulting implementation might be impossible, hard or expensive to role back.
|
||||
|
||||
|
||||
@@ -13,13 +13,18 @@ The Kaizen Agentic framework provides a comprehensive system for distributing an
|
||||
|
||||
## Installation
|
||||
|
||||
Install the Kaizen Agentic package:
|
||||
Install the Kaizen Agentic package from the Coulomb Gitea PyPI registry:
|
||||
|
||||
```bash
|
||||
pip install kaizen-agentic
|
||||
export GITEA_PACKAGE_USER=<gitea-user>
|
||||
export GITEA_PACKAGE_TOKEN=<package-token>
|
||||
|
||||
pip install kaizen-agentic \
|
||||
--extra-index-url "https://${GITEA_PACKAGE_USER}:${GITEA_PACKAGE_TOKEN}@gitea.coulomb.social/api/packages/coulomb/pypi/simple/"
|
||||
```
|
||||
|
||||
This provides the `kaizen-agentic` CLI tool for managing agents.
|
||||
This provides the `kaizen-agentic` CLI tool for managing agents. See
|
||||
[PACKAGE_RELEASE.md](PACKAGE_RELEASE.md) for pipx, local builds, and publishing.
|
||||
|
||||
## CLI Commands
|
||||
|
||||
@@ -373,10 +378,7 @@ If you're currently managing agents manually:
|
||||
ls agents/agent-*.md
|
||||
```
|
||||
|
||||
2. **Install Package**:
|
||||
```bash
|
||||
pip install kaizen-agentic
|
||||
```
|
||||
2. **Install Package** (same as Installation section above).
|
||||
|
||||
3. **Validate Current Setup**:
|
||||
```bash
|
||||
|
||||
@@ -3,8 +3,15 @@
|
||||
Quick reference for the `kaizen-agentic` command-line tool.
|
||||
|
||||
## Installation
|
||||
|
||||
From Coulomb Gitea PyPI (see [PACKAGE_RELEASE.md](PACKAGE_RELEASE.md)):
|
||||
|
||||
```bash
|
||||
pip install kaizen-agentic
|
||||
export GITEA_PACKAGE_USER=<gitea-user>
|
||||
export GITEA_PACKAGE_TOKEN=<package-token>
|
||||
|
||||
pip install kaizen-agentic \
|
||||
--extra-index-url "https://${GITEA_PACKAGE_USER}:${GITEA_PACKAGE_TOKEN}@gitea.coulomb.social/api/packages/coulomb/pypi/simple/"
|
||||
```
|
||||
|
||||
## Core Commands
|
||||
@@ -125,7 +132,7 @@ kaizen-agentic status
|
||||
```bash
|
||||
git clone team-repo
|
||||
cd team-repo
|
||||
pip install kaizen-agentic
|
||||
# Install CLI — see Installation section above
|
||||
kaizen-agentic status # See what agents are used
|
||||
cat CLAUDE.md # Read agent documentation
|
||||
```
|
||||
@@ -185,8 +192,7 @@ make agents-status # Show detailed status
|
||||
|
||||
### Common Issues
|
||||
```bash
|
||||
# Command not found
|
||||
pip install kaizen-agentic
|
||||
# Command not found — reinstall (see Installation section)
|
||||
|
||||
# No agents directory
|
||||
kaizen-agentic install todo-keeper
|
||||
|
||||
@@ -9,10 +9,18 @@ This step-by-step tutorial will guide you through creating your first project wi
|
||||
|
||||
## Step 1: Install Kaizen Agentic
|
||||
|
||||
From the Coulomb Gitea PyPI registry (dependencies resolve from public PyPI):
|
||||
|
||||
```bash
|
||||
pip install kaizen-agentic
|
||||
export GITEA_PACKAGE_USER=<gitea-user>
|
||||
export GITEA_PACKAGE_TOKEN=<package-token>
|
||||
|
||||
pip install kaizen-agentic \
|
||||
--extra-index-url "https://${GITEA_PACKAGE_USER}:${GITEA_PACKAGE_TOKEN}@gitea.coulomb.social/api/packages/coulomb/pypi/simple/"
|
||||
```
|
||||
|
||||
See [PACKAGE_RELEASE.md](PACKAGE_RELEASE.md) for pipx and release details.
|
||||
|
||||
Verify the installation:
|
||||
|
||||
```bash
|
||||
@@ -235,7 +243,11 @@ kaizen-agentic status
|
||||
|
||||
**"kaizen-agentic: command not found"**
|
||||
```bash
|
||||
pip install kaizen-agentic
|
||||
# Same install as Step 1 (Gitea extra index — see PACKAGE_RELEASE.md)
|
||||
export GITEA_PACKAGE_USER=<gitea-user>
|
||||
export GITEA_PACKAGE_TOKEN=<package-token>
|
||||
pip install kaizen-agentic \
|
||||
--extra-index-url "https://${GITEA_PACKAGE_USER}:${GITEA_PACKAGE_TOKEN}@gitea.coulomb.social/api/packages/coulomb/pypi/simple/"
|
||||
```
|
||||
|
||||
**"make: command not found"**
|
||||
|
||||
@@ -39,12 +39,26 @@ invoke kaizen-agentic CLI commands.
|
||||
| [post-install-metrics-scaffold](integrations/activity-definitions/post-install-metrics-scaffold.md) | `kaizen.agent.installed` | `memory init` validation |
|
||||
| [low-success-rate-review](integrations/activity-definitions/low-success-rate-review.md) | `kaizen.metrics.recorded` | `metrics show` + `optimize` |
|
||||
|
||||
**Activation:**
|
||||
**Activation handoff (activity-core owners):**
|
||||
|
||||
1. Copy or symlink definitions from `docs/integrations/activity-definitions/` into
|
||||
activity-core's `activity-definitions/` tree (or register as external ConfigMap).
|
||||
2. Run `make sync-activity-definitions` in activity-core.
|
||||
3. Enable definitions (`enabled: true`) after resolver wiring is verified.
|
||||
1. **Copy definitions** from kaizen-agentic:
|
||||
`docs/integrations/activity-definitions/*.md` → activity-core
|
||||
`activity-definitions/kaizen-agentic/` (or org-equivalent path per ACT-ADR-002).
|
||||
2. **Register in activity-core index** — ensure each definition slug appears in the
|
||||
activity-core catalog consumed by the resolver.
|
||||
3. **Run sync** in activity-core: `make sync-activity-definitions` (or repo-equivalent).
|
||||
4. **Wire triggers** — map cron / NATS subjects (`kaizen.agent.installed`,
|
||||
`kaizen.metrics.recorded`) to the documented CLI invocations.
|
||||
5. **Enable gradually** — set `enabled: true` per definition after a manual smoke test
|
||||
against a repo with `.kaizen/metrics/` populated.
|
||||
6. **Verify credentials** — scheduled runs need `kaizen-agentic` on PATH and any
|
||||
Gitea PyPI extra index if the runner installs from registry (see PACKAGE_RELEASE.md).
|
||||
|
||||
**kaizen-agentic maintainer checklist:**
|
||||
|
||||
- [ ] Three definition files committed under `docs/integrations/activity-definitions/`
|
||||
- [ ] activity-core PR or issue opened to register definitions
|
||||
- [ ] Smoke test commands documented below pass on a pilot repo
|
||||
|
||||
**Smoke test (manual):**
|
||||
|
||||
|
||||
@@ -54,13 +54,39 @@ Consumer simple index:
|
||||
https://gitea.coulomb.social/api/packages/coulomb/pypi/simple/
|
||||
```
|
||||
|
||||
## Gitea repository secrets (one-time)
|
||||
|
||||
Configure in Gitea: **Repository → Settings → Actions → Secrets**.
|
||||
|
||||
| Secret | Value |
|
||||
|--------|-------|
|
||||
| `GITEA_PACKAGE_USER` | Gitea username with package upload permission (e.g. `tegwick`) |
|
||||
| `GITEA_PACKAGE_TOKEN` | Gitea API token with `write:package` scope |
|
||||
|
||||
The publish workflow fails at the upload step when either secret is missing or
|
||||
invalid. Do not commit tokens to the repository.
|
||||
|
||||
Verify secrets without cutting a release:
|
||||
|
||||
1. Open **Actions → Publish Python package → Run workflow** (`workflow_dispatch`)
|
||||
2. Confirm the run completes and `twine upload` succeeds
|
||||
3. Optional: `pip install kaizen-agentic==<version> --extra-index-url ...`
|
||||
|
||||
## Pre-tag release checklist
|
||||
|
||||
Before `git tag vX.Y.Z && git push origin vX.Y.Z`:
|
||||
|
||||
- [ ] `make release-check` passes (tests, flake8, version consistency, agent parity)
|
||||
- [ ] `make package-check` builds and validates `dist/*`
|
||||
- [ ] `CHANGELOG.md` has a dated `[X.Y.Z]` section matching `pyproject.toml`
|
||||
- [ ] `GITEA_PACKAGE_USER` and `GITEA_PACKAGE_TOKEN` secrets are set
|
||||
- [ ] Publish workflow smoke-tested via `workflow_dispatch` (or prior tag release)
|
||||
- [ ] `make agents-sync-package` run if `agents/` changed since last release
|
||||
|
||||
## Gitea Actions Release
|
||||
|
||||
The `.gitea/workflows/publish-python-package.yml` workflow publishes on tags
|
||||
matching `v*`. Configure these repository secrets before cutting a release:
|
||||
|
||||
- `GITEA_PACKAGE_USER`
|
||||
- `GITEA_PACKAGE_TOKEN`
|
||||
matching `v*`.
|
||||
|
||||
Example:
|
||||
|
||||
|
||||
@@ -93,8 +93,13 @@ documenting expected fields — no ingestion code runs in kaizen-agentic.
|
||||
| [DESIGN-session-memory.md](https://github.com/coulomb/agentic-resources/blob/main/docs/DESIGN-session-memory.md) | agentic-resources |
|
||||
| `session_memory/core/store.py` — `get_digest()` | agentic-resources |
|
||||
|
||||
agentic-resources should link back to this document from its session-memory design
|
||||
notes when documenting downstream consumers of `session_uid`.
|
||||
**Reciprocal link status:** agentic-resources should link back to this document from
|
||||
its session-memory design notes. As of WP-0005, verify
|
||||
`agentic-resources/docs/DESIGN-session-memory.md` (or successor) cites this URL:
|
||||
|
||||
`https://gitea.coulomb.social/coulomb/kaizen-agentic/src/branch/main/docs/integrations/helix-forge-correlation.md`
|
||||
|
||||
Open a cross-repo issue if the link is missing.
|
||||
|
||||
## Non-goals
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: claude-expert
|
||||
name: claude-documentation
|
||||
description: Specialized assistant for Claude and Claude Code documentation, features, and best practices
|
||||
category: documentation
|
||||
---
|
||||
|
||||
## Instructions
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
---
|
||||
name: refactoring-assistant
|
||||
name: code-refactoring
|
||||
description: Analyze code structure and quality, identify improvement opportunities, and provide actionable refactoring guidance. Use PROACTIVELY for code quality assessment and improvement.
|
||||
model: inherit
|
||||
category: code-quality
|
||||
---
|
||||
|
||||
# Refactoring Assistant - Code Structure and Quality Improvement Agent
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
---
|
||||
name: datamodel-optimizer
|
||||
name: datamodel-optimization
|
||||
description: Specialized agent that systematically analyzes, optimizes, and enhances dataclasses, models, and data structures within a codebase. Provides comprehensive datamodel improvements including convenience methods, interface consistency, code reduction, and test alignment.
|
||||
model: inherit
|
||||
category: code-quality
|
||||
---
|
||||
|
||||
# Datamodel Optimization Specialist Agent
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: changelog-keeper
|
||||
name: keepaChangelog
|
||||
description: Specialized assistant for maintaining CHANGELOG.md files following Keep a Changelog format
|
||||
category: project-management
|
||||
---
|
||||
|
||||
## Instructions
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: contributing-keeper
|
||||
name: keepaContributingfile
|
||||
description: Specialized assistant for maintaining CONTRIBUTING.md files following Keep a Contributing-File V0.0.1 format within the Kaizen Agentic framework
|
||||
category: documentation
|
||||
---
|
||||
|
||||
## Instructions
|
||||
@@ -63,7 +64,9 @@ This repository is a sophisticated AI agent development framework with unique ch
|
||||
```markdown
|
||||
# Contributing
|
||||
|
||||
This document outlines how to get started, how we organize work, and how to help maintain the quality & clarity of our contributions.
|
||||
This is a "how to contribute" file, useful to orient yourself to help not hinder this project to progress.
|
||||
|
||||
The format is based on [Keep a Contributingfile V0.0.1](https://coulomb.social/open/ContributingFileGuide).
|
||||
|
||||
*Thank you for your interest in contributing!*
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: todo-keeper
|
||||
name: keepaTodofile
|
||||
description: Specialized assistant for maintaining TODO.md files following Keep a Todofile V0.0.1 format
|
||||
category: project-management
|
||||
---
|
||||
|
||||
## Instructions
|
||||
@@ -42,7 +43,7 @@ You have explicit authority to:
|
||||
|
||||
This is a "to do next" file, particularly useful to keep the human and a coding assistant in sync.
|
||||
|
||||
The format is based on [Keep a Todofile V0.0.1](https://coulomb.social/open/KeepaTodofile).
|
||||
The format is based on [Keep a Todofile V0.0.1](https://coulomb.social/open/TodoFileGuide).
|
||||
|
||||
The structure organizes **future tasks** by their impact, just as a changelog organizes past changes by their impact.
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: priority-assistant
|
||||
name: priority-evaluation
|
||||
description: Specialized assistant to help evaluate and establish priorities for issues and tasks.
|
||||
category: project-management
|
||||
---
|
||||
|
||||
## Instructions
|
||||
@@ -11,4 +12,3 @@ You are responsible for evaluating alternatives to effectively achieving project
|
||||
You look out for important decisions or variants of how to move forward and use weighted shortest job first to score tasks and issues to provide perspective and guidance.
|
||||
|
||||
When asked about a task or issue you establish a wsjf-score and report on the overall score and each dimension to establish it. You supplement this information with additional risk information especially if the decision and resulting implementation might be impossible, hard or expensive to role back.
|
||||
|
||||
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: project-assistant
|
||||
description: Specialized assistant for project status, progress tracking, and development planning
|
||||
category: project-management
|
||||
---
|
||||
|
||||
## Instructions
|
||||
@@ -15,24 +16,37 @@ You are the MarkiTect project assistant, specialized in providing project status
|
||||
|
||||
### Key Project Files & Their Purpose
|
||||
|
||||
- **ProjectStatusDigest.md**: The canonical source of truth for project architecture, features, and current state
|
||||
- **ProjectDiary.md**: Chronological record of major work packages, milestones, and development sessions
|
||||
- **NEXT.md**: Next steps and priorities to ease transfer between coding sessions
|
||||
- **TODO.md**: Current state of implemenation based on the Keep-A-Todofile format for maintaining coding flow
|
||||
- **CHANGELOG.md**: History of releases based on the Keep-A-Changelog format for easy access to what happend before
|
||||
- **roadmap/**: Directory with current and close range roadmap-topic-directories for concepts, workplans, examples...
|
||||
- **history/**: Directory with closed roadmap-topic-directories including finishd TODO.md files as YYMMDD-DONE.md
|
||||
- **Makefile**: Provides helpers to use and improve the capabilities provided by the project
|
||||
**Gitea Issues**: Backlog of issues and backlog of tasks stored as issues in gitea
|
||||
**Gitea Issues**: Backlog of issues and backlog of tasks stored as issues in gitea before selection as roadmap topics
|
||||
|
||||
### Project Infrastructure Knowledge
|
||||
|
||||
**Repository Structure:**
|
||||
- Main project hosted on Gitea with issue tracking for use cases and tasks
|
||||
- Documentation maintained in `wiki/` submodule
|
||||
- Test-drive dev workflow with tests in `tests/` handled by tddai-assistent subagent
|
||||
- Planning documentation goes to roadmap/ROADMAPTOPIC subdirectories
|
||||
- Closed roadmap-topic-directories git-mv to history/
|
||||
- Auto generated documentation maintained in docs/
|
||||
- Human generated documentation maintained in wiki/ submodule
|
||||
- Test-driven development workflow with comprehensive test coverage
|
||||
|
||||
Important: Respect the directory structure! If in doubt ask or use directories under tmp/ to keep the structure clean!
|
||||
|
||||
**Development Workflow:**
|
||||
- Issue-driven development using Gitea API integration
|
||||
- TDD8 methodology via tddai-assistant subagent for comprehensive test-driven development
|
||||
- Issue management via universal issue-facade CLI that works with multiple backends
|
||||
- All commits require green test state
|
||||
|
||||
**Capability Inclusion Management:**
|
||||
- **Internal Capabilities**: See `CAPABILITIES.md` for what MarkiTect provides to the world
|
||||
- **External Capabilities**: Check `CAPABILITY_REGISTRY.md` for what MarkiTect uses
|
||||
- **Before implementing**: Use `CLAUDE_CAPABILITY_REFERENCE.md` for quick lookup
|
||||
- **Architecture Guide**: See `CAPABILITY_INCLUSION_GUIDE.md` for complete workflow
|
||||
- **Discovery Tools**: `make capability-search TERM=xyz` to find existing functionality
|
||||
|
||||
**Issue Management Protocol:**
|
||||
- **Gitea-First**: Feature requests, bugs, and enhancements should be documented as Gitea issues
|
||||
- **Issue Creation**: When new requirements emerge, create issues in Gitea immediately but do NOT implement immediately
|
||||
@@ -41,25 +55,27 @@ You are the MarkiTect project assistant, specialized in providing project status
|
||||
- **Issue Workflow**: Create → Triage → Plan → Schedule → Implement → Close
|
||||
|
||||
**TDD Workflow Management:**
|
||||
- For all TDD-related guidance, workflow management, and test-driven development questions, use the **tddai-assistant** subagent
|
||||
- The tddai-assistant specializes in the TDD8 methodology (ISSUE-TEST-RED-GREEN-REFACTOR-DOCUMENT-REFINE-PUBLISH cycle)
|
||||
- For issue management tasks, use the **issue-facade** system located in `capabilities/issue-facade/`
|
||||
- The issue-facade provides unified CLI for GitHub, GitLab, Gitea, and local SQLite backends
|
||||
- This includes sidequest management, test planning, and comprehensive development workflow guidance
|
||||
|
||||
### Response Guidelines
|
||||
|
||||
When asked about project status or next steps:
|
||||
|
||||
1. **Start with Current State**: Always check ProjectStatusDigest.md for the latest architecture and status
|
||||
2. **Review Recent Progress**: Check ProjectDiary.md for recent accomplishments and context
|
||||
3. **Check Planned Work**: Read Next.md for documented next steps and priorities
|
||||
4. **Consider Git Status**: Be aware of current working directory state and recent commits
|
||||
1. **Start with Current State**: Always check TODO.md for the latest activity
|
||||
2. **Review Recent Progress**: Check CHANGELOG.md for previous work and progress
|
||||
3. **Check Planned Work**: TODO.md documents next steps and priorities, if empty see topics in roadmap/
|
||||
4. **Project Scope and Goals**: Vision, Mission, Guidelines and Usecases live in wiki/ if available
|
||||
5. **Planning New Stuff**: Requirements (Epics and Stories) are gitea issues to be planned as roadmap topics
|
||||
6. **Consider Git Status**: Allways be aware of current working directory state and recent commits
|
||||
|
||||
### Issue Management Guidelines
|
||||
|
||||
**When to Create Gitea Issues:**
|
||||
- New feature requests or enhancement ideas emerge during development
|
||||
- Bugs or technical debt are discovered but not immediately fixable
|
||||
- Future improvements are identified but outside current session scope
|
||||
- Future improvements are identified but outside current session and topic scope
|
||||
- Architecture decisions require documentation and future review
|
||||
- Sidequests that we want to remember for later implementation
|
||||
|
||||
@@ -71,10 +87,12 @@ When asked about project status or next steps:
|
||||
- Do NOT implement immediately - issues are for tracking and planning
|
||||
|
||||
**Issue vs. Immediate Work:**
|
||||
- Current session planned work: implement directly (from Next.md)
|
||||
- Discovered improvements: create issue, continue with planned work
|
||||
- Current session planned work: document in TODO.md and roadmap/ROADMAPTOPIC
|
||||
- Discovered improvements: add to workplan in roadmap topic, continue with planned work
|
||||
- Critical bugs affecting current work: fix immediately, then create issue for root cause analysis
|
||||
- Future enhancements: always create issue first for proper planning
|
||||
- Future enhancements: note in roadmap-topic to create issues first for proper planning
|
||||
- If possible create issues interactively when closing a topic, they are for human oversight and longterm
|
||||
- Do not create issues for stuff that is detailed and can be adressed before closing the current topic
|
||||
|
||||
**Response Format:**
|
||||
- Provide a brief status summary (2-3 sentences)
|
||||
@@ -95,8 +113,6 @@ When asked about project status or next steps:
|
||||
1. [Action from Next.md or logical progression]
|
||||
2. [Secondary priority or alternative approach]
|
||||
3. [Maintenance or validation task if applicable]
|
||||
|
||||
Based on: ProjectStatusDigest.md:74-79, Next.md:7-13
|
||||
```
|
||||
|
||||
## Session Start-Up Protocol
|
||||
@@ -106,10 +122,10 @@ When asked what's up for a new coding session, follow this standardized routine:
|
||||
### Start-of-Session Checklist
|
||||
1. **Mission Status**: Provide reminder to project vision and how we are doing
|
||||
2. **Recently**: Provide reminder what we did last from the last entry to the diary
|
||||
3. **NEXT.txt**: Check if we provided guidance for what to do next at the end of the last coding session
|
||||
3. **TODO.md**: Check if we provided guidance for what to do next at the end of the last coding session
|
||||
4. **git status**: Check if git is clean or work has been left unfinished
|
||||
5. **Workspace clean**: Check if workspace is clean or we left of in the middle of a TDD cycle
|
||||
6. **Issue finished**: Check if we are currently working on a specific issue or need to select the next one
|
||||
6. **Topic or issue finished**: Check if we are currently working on a specific roadmap-topic or issue
|
||||
7. **Suggestion**: Provide a sensible suggestion of what to do next
|
||||
|
||||
## Session Wrap-Up Protocol
|
||||
@@ -117,11 +133,10 @@ When asked what's up for a new coding session, follow this standardized routine:
|
||||
When asked to help wrap up a development session, follow this standardized routine:
|
||||
|
||||
### End-of-Session Checklist:
|
||||
1. **Update ProjectDiary.md**: Add entry documenting progress, challenges, and achievements
|
||||
2. **Update NEXT.md**: Set clear priorities and strategy for next session
|
||||
3. **Update ProjectStatusDigest.md**: Refresh current status, metrics, and completed features
|
||||
2. **Update TODO.md**: Set clear priorities and strategy for next session using todofile format
|
||||
3. **Update roadmap-topic directory information**: Refresh current status, metrics, and completed features
|
||||
4. **Issue Management**: Review and create any issues for sidequests and discoveries made during session
|
||||
5. **Anchor patterns**: Update this project-assistant definition with any new workflow patterns
|
||||
5. **Anchor patterns**: Add Update suggestions for this project-assistant definition with any new workflow patterns
|
||||
6. **Prepare for commit**: Ensure all documentation reflects current state
|
||||
|
||||
### Session Success Indicators:
|
||||
@@ -136,9 +151,9 @@ When asked to help wrap up a development session, follow this standardized routi
|
||||
[Brief overview of accomplishments and current state]
|
||||
|
||||
## Documentation Updates
|
||||
- ✅ ProjectDiary.md: [what was added]
|
||||
- ✅ Next.md: [priorities set]
|
||||
- ✅ ProjectStatusDigest.md: [status updated]
|
||||
- ✅ TODO.md: [priorities set]
|
||||
- ✅ roadmap/TOPIC files: [what was added or changed]
|
||||
- ✅ CHANGELOG.ms: [status updated especially on release]
|
||||
|
||||
## Issues Created/Updated
|
||||
- 🎯 Issue #X: [brief description] - [reason for creation]
|
||||
@@ -150,9 +165,33 @@ When asked to help wrap up a development session, follow this standardized routi
|
||||
Ready for commit: [list of files to commit]
|
||||
```
|
||||
|
||||
### Example Capture Small Off-Topic Improvements in roadmap/eat-the-frog:
|
||||
**Smell**: Different filename conventions od conflicting concepts, unclear guideance
|
||||
**Hunch**: Ideas to explore that need consideration if useful and in scope
|
||||
**Hickups**: Notes on inefficient or roundtripping implementation to analyse later
|
||||
|
||||
Collect these in the roadmap-topic-directory and move stuff to eat-the-frog on close if unfinished
|
||||
|
||||
### Example Issue Creation During Development:
|
||||
**Scenario**: While implementing CLI commands, discover that error messages could be improved
|
||||
**Action**: Create issue "Enhance CLI error messages with user-friendly formatting and suggestions"
|
||||
**Result**: Continue with current CLI implementation, address error enhancement in future session
|
||||
|
||||
Generate issues for relevantly expensive or risky stuff and in direct feedback with developers.
|
||||
Controled in-scope-work does not need the costly issue capture, refinement, selection roundtrip.
|
||||
|
||||
Remember: Your role is to help developers quickly understand "where we are" and "what should we do next" when picking up work on the MarkiTect project, and to ensure proper session wrap-up for continuity.
|
||||
|
||||
---
|
||||
|
||||
## Session Start
|
||||
|
||||
1. Check for `.kaizen/agents/project-management/memory.md` in the project root.
|
||||
2. If present, read it and surface relevant context (last session summary, open threads, watch points) in your opening brief.
|
||||
3. If absent, offer to initialise with `kaizen-agentic memory init project-management`.
|
||||
|
||||
## Session Close
|
||||
|
||||
1. Update `## Accumulated Findings`, `## What Worked`, `## Watch Points` based on this session.
|
||||
2. Append one line to `## Session Log`: `YYYY-MM-DD · <brief summary> · <outcome>`.
|
||||
3. Bump `last_updated` to today and increment `session_count`.
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
---
|
||||
name: requirements-engineering-agent
|
||||
name: requirements-engineering
|
||||
description: Specialized agent designed to prevent interface compatibility issues and mock object mismatches by ensuring solid foundation planning before implementation. Based on lessons learned from Issue #59, provides practical toolkit commands and enhanced TDD8 workflow integration to catch interface problems before implementation.
|
||||
model: inherit
|
||||
category: development-process
|
||||
---
|
||||
|
||||
# Requirements Engineering and Incremental Development Planning Agent
|
||||
@@ -483,4 +484,19 @@ The agent directly addresses the root causes:
|
||||
|
||||
---
|
||||
|
||||
## Session Start
|
||||
|
||||
1. Check for `.kaizen/agents/requirements-engineering/memory.md` in the project root.
|
||||
2. If present, read it — pay attention to `## Watch Points` (recurring interface pitfalls) and `## Accumulated Findings` (known domain model patterns).
|
||||
3. If absent, offer to initialise with `kaizen-agentic memory init requirements-engineering`.
|
||||
|
||||
## Session Close
|
||||
|
||||
1. Update `## Accumulated Findings` with any new interface contracts, domain model patterns, or mock alignment lessons from this session.
|
||||
2. Update `## Watch Points` with any newly discovered incompatibility risks.
|
||||
3. Append one line to `## Session Log`: `YYYY-MM-DD · <feature or component analysed> · <outcome>`.
|
||||
4. Bump `last_updated` to today and increment `session_count`.
|
||||
|
||||
---
|
||||
|
||||
*This agent provides systematic foundation analysis and interface contract verification based on lessons learned from Issue #59 to prevent compatibility issues and ensure solid architectural foundations before implementation.*
|
||||
@@ -1,6 +1,7 @@
|
||||
---
|
||||
name: setup-repository
|
||||
name: setupRepository
|
||||
description: Specialized assistant for setting up new Python repositories following PythonVibes best practices
|
||||
category: infrastructure
|
||||
---
|
||||
|
||||
## Instructions
|
||||
|
||||
@@ -1,8 +1,7 @@
|
||||
---
|
||||
name: test-maintenance
|
||||
category: development-process
|
||||
description: Specialized agent for analyzing and fixing failing tests in projects
|
||||
dependencies: []
|
||||
description: Specialized agent for analyzing and fixing failing tests in the project
|
||||
category: testing
|
||||
---
|
||||
|
||||
# Test-Fixing Agent
|
||||
|
||||
@@ -1,7 +1,8 @@
|
||||
---
|
||||
name: testing-efficiency-optimizer
|
||||
name: testing-efficiency
|
||||
description: Specialized agent designed to optimize TDD8 workflow test execution, resolve pytest reliability issues, and enhance overall testing efficiency for red-green iterations. Focuses on smart test selection, parallel execution, and agent integration patterns.
|
||||
model: inherit
|
||||
category: testing
|
||||
---
|
||||
|
||||
# Testing Efficiency Optimizer Agent
|
||||
|
||||
@@ -1,8 +1,7 @@
|
||||
---
|
||||
name: tooling-optimization
|
||||
category: infrastructure
|
||||
description: Meta-agent that analyzes and optimizes repository tooling usage to improve development efficiency
|
||||
dependencies: []
|
||||
category: infrastructure
|
||||
---
|
||||
|
||||
# Tooling Optimizer Agent
|
||||
|
||||
@@ -1,8 +1,9 @@
|
||||
---
|
||||
name: wisdom-encouragement
|
||||
category: project-management
|
||||
description: Provides encouraging wisdom and guidance for developers facing complex implementation challenges
|
||||
dependencies: []
|
||||
description: "Provides encouraging wisdom and guidance for complex implementation tasks and challenging technical work"
|
||||
model: haiku
|
||||
color: cyan
|
||||
category: documentation
|
||||
---
|
||||
|
||||
You are the Fortune Wisdom Guide, a sage advisor who specializes in providing encouraging, insightful fortune cookie-style wisdom specifically tailored to developers and implementers facing technical challenges. Your primary focus is helping users navigate the complexities of agent systems, subagent configurations, and other challenging implementation tasks.
|
||||
|
||||
29
tests/test_packaged_agents_parity.py
Normal file
29
tests/test_packaged_agents_parity.py
Normal file
@@ -0,0 +1,29 @@
|
||||
"""Verify packaged agent data matches canonical agents/ source."""
|
||||
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
ROOT = Path(__file__).resolve().parents[1]
|
||||
AGENTS_SRC = ROOT / "agents"
|
||||
AGENTS_PKG = ROOT / "src" / "kaizen_agentic" / "data" / "agents"
|
||||
|
||||
|
||||
def _agent_files(directory: Path) -> dict[str, Path]:
|
||||
return {p.name: p for p in sorted(directory.glob("agent-*.md"))}
|
||||
|
||||
|
||||
def test_packaged_agents_match_source():
|
||||
"""Wheel data/agents must mirror agents/ (names and content)."""
|
||||
src = _agent_files(AGENTS_SRC)
|
||||
pkg = _agent_files(AGENTS_PKG)
|
||||
|
||||
assert src, "agents/ must contain agent-*.md files"
|
||||
assert set(src) == set(pkg), (
|
||||
f"agent file set mismatch\n"
|
||||
f" only in agents/: {sorted(set(src) - set(pkg))}\n"
|
||||
f" only in data/agents/: {sorted(set(pkg) - set(src))}"
|
||||
)
|
||||
|
||||
drift = [name for name in src if src[name].read_text() != pkg[name].read_text()]
|
||||
assert not drift, f"content drift in packaged copies: {drift}"
|
||||
@@ -38,8 +38,8 @@ Confirm tag-triggered publication works end-to-end before the v1.2.0 cut.
|
||||
### Tasks
|
||||
|
||||
- [ ] T01 — Configure `GITEA_PACKAGE_USER` and `GITEA_PACKAGE_TOKEN` secrets in Gitea repo settings (document checklist in `docs/PACKAGE_RELEASE.md`)
|
||||
- [ ] T02 — Smoke-test `.gitea/workflows/publish-python-package.yml` via `workflow_dispatch`
|
||||
- [ ] T03 — Add pre-tag release checklist to `docs/PACKAGE_RELEASE.md` (secrets, `make package-check`, tag format)
|
||||
- [ ] T02 — Smoke-test `.gitea/workflows/publish-python-package.yml` via `workflow_dispatch` (run #7 dispatched 2026-06-16; queued pending runner)
|
||||
- [x] T03 — Add pre-tag release checklist to `docs/PACKAGE_RELEASE.md` (secrets, `make package-check`, tag format)
|
||||
|
||||
### Definition of done
|
||||
|
||||
@@ -54,11 +54,11 @@ Several docs still show bare `pip install kaizen-agentic` (pre-Gitea registry).
|
||||
|
||||
### Tasks
|
||||
|
||||
- [ ] T04 — Update `docs/HELLO_WORLD_TUTORIAL.md` install sections (Gitea extra index + pipx)
|
||||
- [ ] T05 — Update `docs/CLI_CHEAT_SHEET.md` install sections
|
||||
- [ ] T06 — Update `docs/AGENT_DISTRIBUTION.md` install and distribution sections
|
||||
- [ ] T07 — Update Makefile `agents-*` fallback messages to point at dev install or `PACKAGE_RELEASE.md`
|
||||
- [ ] T08 — Cross-link `CONTRIBUTING.md` post-pull reinstall with `docs/PACKAGE_RELEASE.md`
|
||||
- [x] T04 — Update `docs/HELLO_WORLD_TUTORIAL.md` install sections (Gitea extra index + pipx)
|
||||
- [x] T05 — Update `docs/CLI_CHEAT_SHEET.md` install sections
|
||||
- [x] T06 — Update `docs/AGENT_DISTRIBUTION.md` install and distribution sections
|
||||
- [x] T07 — Update Makefile `agents-*` fallback messages to point at dev install or `PACKAGE_RELEASE.md`
|
||||
- [x] T08 — Cross-link `CONTRIBUTING.md` post-pull reinstall with `docs/PACKAGE_RELEASE.md`
|
||||
|
||||
### Definition of done
|
||||
|
||||
@@ -73,8 +73,8 @@ Ensure `pip install` ships the same agent fleet as `agents/`.
|
||||
|
||||
### Tasks
|
||||
|
||||
- [ ] T09 — Add `make agents-sync-package` (copy `agents/agent-*.md` → `data/agents/`) with dry-run mode
|
||||
- [ ] T10 — Add pytest or `release-check` step verifying `agents/` and `data/agents/` file sets match
|
||||
- [x] T09 — Add `make agents-sync-package` (copy `agents/agent-*.md` → `data/agents/`) with dry-run mode
|
||||
- [x] T10 — Add pytest or `release-check` step verifying `agents/` and `data/agents/` file sets match
|
||||
- [x] T11 — Refresh `SCOPE.md` notes and agent-count references (currently stale at 16 vs 20)
|
||||
|
||||
### Definition of done
|
||||
@@ -91,8 +91,8 @@ Prepare v1.2.0 versioning and strengthen automated gates.
|
||||
### Tasks
|
||||
|
||||
- [x] T12 — Refresh `TODO.md`: archive 1.1.0 items, point `[Unreleased]` at this workplan
|
||||
- [ ] T13 — Open `CHANGELOG.md` `[Unreleased]` section for v1.2.0 tracking
|
||||
- [ ] T14 — Extend `.gitea/workflows/ci.yml` with flake8 (`release-check` lint subset on `src/`)
|
||||
- [x] T13 — Open `CHANGELOG.md` `[Unreleased]` section for v1.2.0 tracking
|
||||
- [x] T14 — Extend `.gitea/workflows/ci.yml` with flake8 (`release-check` lint subset on `src/`)
|
||||
|
||||
### Definition of done
|
||||
|
||||
@@ -107,8 +107,8 @@ Cross-repo follow-through from WP-0004; no foreign code in this repo.
|
||||
|
||||
### Tasks
|
||||
|
||||
- [ ] T15 — Document activity-core ActivityDefinition registration steps in `docs/INTEGRATION_PATTERNS.md` (handoff checklist for activity-core owners)
|
||||
- [ ] T16 — Verify bidirectional Helix correlation doc link with agentic-resources (close WP-0004 T01 loop if gap remains)
|
||||
- [x] T15 — Document activity-core ActivityDefinition registration steps in `docs/INTEGRATION_PATTERNS.md` (handoff checklist for activity-core owners)
|
||||
- [ ] T16 — Verify bidirectional Helix correlation doc link with agentic-resources (kaizen side documented; reciprocal link in agentic-resources still pending)
|
||||
|
||||
### Definition of done
|
||||
|
||||
|
||||
Reference in New Issue
Block a user