v9.2.1 — Steadfast Hephaestus

Steadfast Hephaestus — 2026-05-22

Upgrade flowr 1.1.0 → 1.2.0 (Whole Rye) to fix flowr serve crash from missing static frontend assets in the wheel.

Fixed

• flowr serve crash: upgraded flowr from 1.1.0 to 1.2.0 (Whole Rye) which includes the missing static frontend assets in the wheel. The flowr serve command now finds index.html, css/, and js/ and starts the visualization server without errors.
• Dropped html extra: flowr[html,viz] changed to flowr[viz] — the html extra never existed in flowr and caused a resolution warning.

Changed

• flowr: >=1.1.0 → >=1.2.0
• flowr[viz]: >=1.0.0 → >=1.2.0

v9.2.0 — consistency audit, feature_title convention, 7-principle review

Changes

Convention fixes

• feature_id → feature_title: Unified across 5 flow YAML files, 4 skills, 1 knowledge file, AGENTS.md, CHANGELOG.md. Template rename: <feature_name> → <feature_title>.
• flowr 1.0.0 → 1.1.0: pyproject.toml and uv.lock.

Design principle review (7 checks)

• review-gate: step 5 split into 5a–5g — one sub-step per design principle (YAGNI, KISS, DRY, ObjCal, Smells, SOLID, Patterns), each matching tdd-cycle exit conditions with dedicated knowledge references.
• refactor: explicit knowledge references added for all 7 principles at detection point.

beehave status integration

• verify-traceability: beehave status --json now mandatory gate — stage ok skips beehave check.
• review-gate tier 2: beehave status --json as pre-check before beehave check.

Flow YAML fixes

• Added params: [feature_title] to define-flow.yaml
• Removed unreachable cancelled exit from develop-flow.yaml
• Removed stale needs-reinterview exit from define-flow.yaml

Agent and skill ownership

• SE agent: explicit ownership — fix existing issues regardless of origin, never noqa, never pyproject.toml
• implement-minimum: fix existing test/beehave failures in touched files
• polish-code: fix all violations codebase-wide
• write-test: anti-noise rules for Spec Value Fidelity

Templates

• New test stub template `.templates/tests/features/<rule_slug>_test.py.template"
• Template rename: <feature_name> → <feature_title>

Cleanup

• Removed stale @id references from AGENTS.md, README.md, docs/audit/
• Updated test-stubs.md to use <feature_title> convention

v9.1.0 — beehave 1.0.0 knowledge integration

Knowledge

• test-stubs.md: Full rewrite incorporating beehave 1.0.0 features — beehave status (6 development stages, --json, --include-unmapped), beehave list/list -v, beehave clean, collision detection, feature stem = title slug requirement
• source-stubs.md: Updated creation order to include beehave status
• gherkin.md: Updated Related link to reference beehave status

Skills

• select-feature: Replaced manual checking with beehave status --json for project-wide overview
• accept-feature, verify-traceability: Added beehave status --json pre-check
• review-gate: Added test-stubs to available knowledge

Project

• Added [dependency-groups] with flowr>=1.0.0 in dev (PEP 735)

v9.0.1

What's Changed

• release: bump version 9.0.0 → 9.0.1 (derive delivery order from context map) by @nullhack in #162

Changed

• Derived delivery order: Removed static Delivery Order section from product_definition.md. Feature selection now derives order from context map dependency count (lowest first), ties broken by WSJF.
• Research template restructured: Moved to domain/subdomain hierarchy.
• Template cleanup: Simplified domain_spec, glossary, and product_definition templates.

Full Changelog: v9.0.0+20260518...v9.0.1

v9.0.0+20260518

What's Changed

• release: bump version 8.6.0 → 9.0.0 (Adversarial Audit) by @nullhack in #160

Full Changelog: v8.6.0+20260515...v9.0.0+20260518

v8.6.0+20260515

What's Changed

• ci(deps): bump authlib from 1.7.0 to 1.7.1 by @dependabot[bot] in #152
• ci(deps): bump urllib3 from 2.6.3 to 2.7.0 by @dependabot[bot] in #151
• ci(deps): bump astral-sh/setup-uv from 05143d3dcd540a42aa638bb0920ac4e3123808a5 to 853401723d6d6622f431a3b4e6385bf65e8035b7 by @dependabot[bot] in #150
• ci(deps): bump actions/dependency-review-action from 4.9.0 to 5.0.0 by @dependabot[bot] in #149
• refactor: standardise terminology, restructure spec architecture, deprecate As a/I want/So that by @nullhack in #156
• release: bump version 8.5.1 → 8.6.0 (Dialogic Chronos) by @nullhack in #157
• fix: sync uv.lock after version bump and dependabot merges by @nullhack in #158

Full Changelog: v8.5.1...v8.6.0+20260515

v8.5.1

What's Changed

• Adversarial design principle verification in review-gate: Reviewer now independently checks YAGNI > KISS > DRY > ObjCal > Smells > SOLID > patterns by loading knowledge files, rather than relying solely on SE self-declaration.
• Updated code-review.md: Two-Tier Review concept and structure table now document adversarial design principle checks with knowledge file references.

Full Changelog: v8.5.0...v8.5.1

v8.5.0

What's Changed

Domain Spec Merge

• Merged domain_model.md + behavioral_spec.md → domain_spec.md: Single monolithic document combining context map, entities, relationships, aggregate boundaries, data shapes, integration points, state machines, and behavioral specifications

Review Gate Restructure

• Collapsed review-gate from 3 tiers to 2: Design + Structure (with functional ruff). Conventions moved to post-acceptance polish state
• New polish-code skill: Applies full conventions (formatting, docstrings, naming, type annotations) after PO acceptance

BDD Pipeline Improvements

• Scenario Outline guidance in gherkin.md with placeholder/literal extraction
• Richer test-stubs.md with strategy inference and literal verification
• New external-fixtures.md for real API fixture capture
• Title length constraints (3-8 words) across skills
• E2E completeness validation step in simulate-spec

Ruff/Coverage Pipeline

• Default ruff check . runs functional rules only (bugs, security, complexity)
• New task conventions for full rules (formatting, naming, docstrings)
• Coverage in default task test with minimal output
• Removed --fix from ruff-check task
• fail_under = 80

Full Changelog: v8.4.0...v8.5.0

v8.4.0+20260514

What's Changed

• feat: consolidate spec docs, improve discovery flow, add feature derivation by @nullhack in #145
• ci(deps): bump astral-sh/setup-uv from c0c76fcf76c37099e6a452584d04b015240faefc to 05143d3dcd540a42aa638bb0920ac4e3123808a5 by @dependabot[bot] in #137
• feat: behavior coverage, pre-mortem levels, Status elimination, disk-evidence selection by @nullhack in #146
• feat: harden flow architecture — review-gate consolidation, planning simplification, flow hardening by @nullhack in #147
• feat: remove Questions table from feature files, consolidate Q&A to interview notes by @nullhack in #148
• feat: spec simulation loop, pytest-beehave integration, flow system overhaul (v8.4.0) by @nullhack in #153

Full Changelog: v8.3.0+20260506...v8.4.0+20260514

v8.3.0+20260506 — Rigorous Euclid

What's New

Added

• README FAQ section — Five questions covering Kiro, Cursor/Copilot, Claude Code/opencode, tool compatibility, and non-software workflows
• README "Who is this for" rewrite — Refocused around vibe coding, agentic engineering, and spec-driven development
• agents-smith quick start — One-command adoption for existing projects
• Workflow flexibility paragraph — Flows are not hardcoded; any state machine process fits

Changed

• Tagline — "production-ready Python, without the ceremony" → "Spec-driven agent orchestration. Any workflow. Any LLM. Zero lock-in."
• Branding sync — docs/branding/branding.md tagline updated to match
• flowr 1.0.0 — Upgraded from >=0.5 to >=1.0.0; knowledge files synced to v1.0.0 spec
• ~= operator removed, when forms documented, conformance levels added, validation streamlined

Fixed

• Line length lint in generate-flowviz-data.py
• uv.lock regenerated for CI --locked compatibility

Full Changelog: v8.2.0+20260505...v8.3.0+20260506