@xulthekl/team-flow 0.22.4
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/.agents/plugins/marketplace.json +20 -0
- package/.agents/skills +1 -0
- package/.claude/always/phase-guard.md +3 -0
- package/.claude-plugin/marketplace.json +20 -0
- package/.claude-plugin/plugin.json +31 -0
- package/.codex-plugin/plugin.json +45 -0
- package/.codexignore +6 -0
- package/.cursor-plugin/marketplace.json +17 -0
- package/.cursor-plugin/plugin.json +31 -0
- package/.github/copilot-instructions.md +15 -0
- package/.github/dependabot.yml +10 -0
- package/.github/plugin/marketplace.json +42 -0
- package/.github/workflows/ci.yml +98 -0
- package/.github/workflows/hol-plugin-scanner.yml +17 -0
- package/.opencode/INSTALL.md +61 -0
- package/.opencode/plugins/team-flow.js +70 -0
- package/AGENTS.md +280 -0
- package/CHANGELOG.md +635 -0
- package/CONTRIBUTING.md +115 -0
- package/GEMINI.md +14 -0
- package/HANDOFF.md +219 -0
- package/INSTALL.md +810 -0
- package/LICENSE +21 -0
- package/README.md +185 -0
- package/SECURITY.md +37 -0
- package/agents/bug-investigator.md +180 -0
- package/agents/change-split-auditor.md +257 -0
- package/agents/code-reviewer.md +171 -0
- package/agents/cross-change-consistency-checker.md +215 -0
- package/agents/prd-completeness-reviewer.md +197 -0
- package/agents/prototype-builder.md +230 -0
- package/agents/prototype-env-scout.md +156 -0
- package/agents/prototype-reviewer.md +226 -0
- package/assets/icon.svg +6 -0
- package/dist/index.d.ts +13 -0
- package/dist/index.js +5 -0
- package/dist/parsing/change-parser.d.ts +12 -0
- package/dist/parsing/change-parser.js +54 -0
- package/dist/parsing/requirement-blocks.d.ts +31 -0
- package/dist/parsing/requirement-blocks.js +192 -0
- package/dist/schema/base.d.ts +7 -0
- package/dist/schema/base.js +1 -0
- package/dist/schema/change.d.ts +25 -0
- package/dist/schema/change.js +1 -0
- package/dist/schema/index.d.ts +3 -0
- package/dist/schema/index.js +1 -0
- package/dist/schema/spec.d.ts +11 -0
- package/dist/schema/spec.js +1 -0
- package/dist/validation/constants.d.ts +42 -0
- package/dist/validation/constants.js +42 -0
- package/dist/validation/tokenizer.d.ts +17 -0
- package/dist/validation/tokenizer.js +173 -0
- package/dist/validation/types.d.ts +40 -0
- package/dist/validation/types.js +1 -0
- package/dist/validation/validator.d.ts +21 -0
- package/dist/validation/validator.js +489 -0
- package/docs/README_en.md +358 -0
- package/docs/artifact-contract.md +96 -0
- package/docs/decision-points.md +88 -0
- package/docs/e2e-integration-design.md +207 -0
- package/docs/examples/README.md +25 -0
- package/docs/examples/add-dark-mode/README.md +13 -0
- package/docs/examples/add-dark-mode/design.md +49 -0
- package/docs/examples/add-dark-mode/execution-contract.md +56 -0
- package/docs/examples/add-dark-mode/proposal.md +46 -0
- package/docs/examples/add-dark-mode/specs/ui-theme/spec.md +35 -0
- package/docs/examples/add-dark-mode/tasks.md +26 -0
- package/docs/examples/refactor-auth-boundary/README.md +15 -0
- package/docs/examples/refactor-auth-boundary/design.md +41 -0
- package/docs/examples/refactor-auth-boundary/execution-contract.md +61 -0
- package/docs/examples/refactor-auth-boundary/proposal.md +47 -0
- package/docs/examples/refactor-auth-boundary/specs/auth-boundary/spec.md +45 -0
- package/docs/examples/refactor-auth-boundary/tasks.md +25 -0
- package/docs/plans/2026-07-07-fix-batch-design.md +68 -0
- package/docs/plans/2026-07-20-001-refactor-skill-collaboration-protocol-plan.md +128 -0
- package/docs/platform-matrix.md +45 -0
- package/docs/prototype-design-research.md +206 -0
- package/docs/release-checklist.md +96 -0
- package/docs/showcase.html +699 -0
- package/docs/skill-rename-v0.8.0.md +49 -0
- package/docs/state-machine.md +162 -0
- package/gemini-extension.json +6 -0
- package/hooks/hooks-cursor.json +8 -0
- package/hooks/hooks.json +26 -0
- package/hooks/pre-tool-use-guard +116 -0
- package/hooks/session-start +14 -0
- package/llms.txt +51 -0
- package/package.json +48 -0
- package/plugin.json +27 -0
- package/prd/v1/plan.md +443 -0
- package/prd/v1/prd.md +580 -0
- package/scripts/check-update.mjs +91 -0
- package/scripts/check-version-consistency.mjs +345 -0
- package/scripts/ensure-branch.mjs +71 -0
- package/scripts/get-config +31 -0
- package/scripts/guard/checks/artifacts-exist.mjs +36 -0
- package/scripts/guard/checks/contract-current.mjs +33 -0
- package/scripts/guard/checks/contract-fresh.mjs +17 -0
- package/scripts/guard/checks/dp-gate-passed.mjs +35 -0
- package/scripts/guard/checks/dp3-approved.mjs +22 -0
- package/scripts/guard/checks/execution-plan-ready.mjs +40 -0
- package/scripts/guard/checks/execution-reviews-passed.mjs +36 -0
- package/scripts/guard/checks/schema-valid.mjs +63 -0
- package/scripts/guard/checks/specs-merged.mjs +51 -0
- package/scripts/guard/checks/tasks-complete.mjs +31 -0
- package/scripts/guard/checks/tests-passing.mjs +31 -0
- package/scripts/guard/design-token-guard.mjs +237 -0
- package/scripts/guard/guard.mjs +205 -0
- package/scripts/infer-workflow.mjs +136 -0
- package/scripts/install-amazon-q.mjs +9 -0
- package/scripts/install-cline.mjs +9 -0
- package/scripts/install-continue.mjs +9 -0
- package/scripts/install-cursor.mjs +265 -0
- package/scripts/install-git-hooks.mjs +82 -0
- package/scripts/install-kiro.mjs +9 -0
- package/scripts/install-pi.mjs +9 -0
- package/scripts/install-qoder.mjs +9 -0
- package/scripts/install-qwen.mjs +9 -0
- package/scripts/install-roocode.mjs +9 -0
- package/scripts/install-windsurf.mjs +9 -0
- package/scripts/install-zcode.mjs +265 -0
- package/scripts/lib/cmd-audit.mjs +127 -0
- package/scripts/lib/cmd-checkpoint.mjs +118 -0
- package/scripts/lib/cmd-config.mjs +88 -0
- package/scripts/lib/cmd-doctor.mjs +267 -0
- package/scripts/lib/cmd-execution.mjs +206 -0
- package/scripts/lib/cmd-handoff.mjs +94 -0
- package/scripts/lib/cmd-inject.mjs +310 -0
- package/scripts/lib/cmd-install-amazon-q.mjs +11 -0
- package/scripts/lib/cmd-install-cline.mjs +11 -0
- package/scripts/lib/cmd-install-continue.mjs +11 -0
- package/scripts/lib/cmd-install-cursor.mjs +14 -0
- package/scripts/lib/cmd-install-kiro.mjs +11 -0
- package/scripts/lib/cmd-install-pi.mjs +11 -0
- package/scripts/lib/cmd-install-qoder.mjs +11 -0
- package/scripts/lib/cmd-install-qwen.mjs +11 -0
- package/scripts/lib/cmd-install-roocode.mjs +11 -0
- package/scripts/lib/cmd-install-windsurf.mjs +11 -0
- package/scripts/lib/cmd-install-workbuddy.mjs +359 -0
- package/scripts/lib/cmd-install-zcode.mjs +14 -0
- package/scripts/lib/cmd-isolate.mjs +37 -0
- package/scripts/lib/cmd-list.mjs +71 -0
- package/scripts/lib/cmd-runtime.mjs +85 -0
- package/scripts/lib/cmd-solutions.mjs +71 -0
- package/scripts/lib/cmd-state.mjs +231 -0
- package/scripts/lib/cmd-sync.mjs +102 -0
- package/scripts/lib/cmd-validate.mjs +105 -0
- package/scripts/lib/cmd-version.mjs +148 -0
- package/scripts/lib/config-loader.mjs +107 -0
- package/scripts/lib/execution-plan.mjs +492 -0
- package/scripts/lib/execution-recommendation.mjs +221 -0
- package/scripts/lib/hash.mjs +74 -0
- package/scripts/lib/install.mjs +267 -0
- package/scripts/lib/platform-runtime-inventory.mjs +27 -0
- package/scripts/lib/platforms.mjs +165 -0
- package/scripts/lib/prototype-sync.mjs +192 -0
- package/scripts/lib/sdd-overlay.mjs +262 -0
- package/scripts/lib/shell-quote.mjs +4 -0
- package/scripts/lib/solutions-capture.mjs +102 -0
- package/scripts/lib/solutions-index-gen.mjs +112 -0
- package/scripts/lib/solutions-inject.mjs +77 -0
- package/scripts/lib/solutions-promote.mjs +145 -0
- package/scripts/lib/spec-paths.mjs +85 -0
- package/scripts/lib/state-loader.mjs +154 -0
- package/scripts/lint/lint-skills.mjs +149 -0
- package/scripts/lint/rules/behavior-consistency.mjs +56 -0
- package/scripts/lint/rules/dp-trigger-points.mjs +60 -0
- package/scripts/lint/rules/exception-handling.mjs +59 -0
- package/scripts/lint/rules/no-contradictory-instructions.mjs +67 -0
- package/scripts/lint/rules/no-redundant-checks.mjs +50 -0
- package/scripts/lint/rules/token-rules.mjs +122 -0
- package/scripts/review-package +44 -0
- package/scripts/task-brief +40 -0
- package/scripts/team-flow.mjs +164 -0
- package/scripts/token-baseline.mjs +158 -0
- package/scripts/validate-artifacts +96 -0
- package/scripts/verify-marketplace-release.mjs +59 -0
- package/skills/architecture-design/SKILL.md +140 -0
- package/skills/architecture-design/chapters/ch01-4a-domains.md +27 -0
- package/skills/architecture-design/chapters/ch02-change-cascade.md +27 -0
- package/skills/architecture-design/chapters/ch03-architecture-outputs.md +25 -0
- package/skills/architecture-design/chapters/ch04-entity-to-aggregate.md +27 -0
- package/skills/architecture-design/chapters/ch05-cqrs.md +32 -0
- package/skills/architecture-design/chapters/ch06-integration.md +54 -0
- package/skills/architecture-design/cheatsheet.md +51 -0
- package/skills/architecture-design/glossary.md +23 -0
- package/skills/architecture-design/patterns.md +32 -0
- package/skills/bug-investigator/SKILL.md +77 -0
- package/skills/build-executor/SKILL.md +163 -0
- package/skills/build-executor/implementer-prompt.md +162 -0
- package/skills/build-executor/references/execution-modes.md +86 -0
- package/skills/build-executor/task-reviewer-prompt.md +195 -0
- package/skills/ce-brainstorm/SKILL.md +415 -0
- package/skills/ce-brainstorm/references/agents/slack-researcher.md +127 -0
- package/skills/ce-brainstorm/references/blindspot-pass.md +70 -0
- package/skills/ce-brainstorm/references/brainstorm-sections.md +285 -0
- package/skills/ce-brainstorm/references/handoff.md +168 -0
- package/skills/ce-brainstorm/references/html-rendering.md +634 -0
- package/skills/ce-brainstorm/references/markdown-rendering.md +241 -0
- package/skills/ce-brainstorm/references/model-tiers.md +9 -0
- package/skills/ce-brainstorm/references/prd-mapping.md +71 -0
- package/skills/ce-brainstorm/references/product-pressure-test.md +42 -0
- package/skills/ce-brainstorm/references/reasoning-elevation.md +63 -0
- package/skills/ce-brainstorm/references/settled-decisions.md +45 -0
- package/skills/ce-brainstorm/references/synthesis-summary.md +282 -0
- package/skills/ce-brainstorm/references/universal-brainstorming.md +73 -0
- package/skills/ce-brainstorm/references/verdict-routing.md +26 -0
- package/skills/ce-brainstorm/references/visual-probes.md +158 -0
- package/skills/ce-brainstorm/scripts/visual-probe-server.js +418 -0
- package/skills/ce-compound/SKILL.md +114 -0
- package/skills/ce-compound/assets/resolution-template.md +94 -0
- package/skills/ce-compound/references/agents/best-practices-researcher.md +115 -0
- package/skills/ce-compound/references/agents/data-integrity-guardian.md +68 -0
- package/skills/ce-compound/references/agents/framework-docs-researcher.md +93 -0
- package/skills/ce-compound/references/agents/pattern-recognition-specialist.md +55 -0
- package/skills/ce-compound/references/agents/performance-oracle.md +108 -0
- package/skills/ce-compound/references/agents/security-sentinel.md +91 -0
- package/skills/ce-compound/references/agents/session-historian.md +83 -0
- package/skills/ce-compound/references/concepts-vocabulary.md +78 -0
- package/skills/ce-compound/references/full-mode-workflow.md +413 -0
- package/skills/ce-compound/references/grounding-validation.md +84 -0
- package/skills/ce-compound/references/lightweight-mode.md +53 -0
- package/skills/ce-compound/references/output-standards.md +182 -0
- package/skills/ce-compound/references/promotion-rules.md +38 -0
- package/skills/ce-compound/references/schema.yaml +231 -0
- package/skills/ce-compound/references/three-tier-index.md +55 -0
- package/skills/ce-compound/references/v0.5-upgrade.md +32 -0
- package/skills/ce-compound/references/write-flow.md +36 -0
- package/skills/ce-compound/references/yaml-schema.md +118 -0
- package/skills/ce-compound/scripts/session-history/discover-sessions.sh +130 -0
- package/skills/ce-compound/scripts/session-history/extract-errors.py +254 -0
- package/skills/ce-compound/scripts/session-history/extract-metadata.py +456 -0
- package/skills/ce-compound/scripts/session-history/extract-skeleton.py +575 -0
- package/skills/ce-compound/scripts/validate-doc-claims.py +346 -0
- package/skills/ce-compound/scripts/validate-frontmatter.py +137 -0
- package/skills/ce-ideate/SKILL.md +402 -0
- package/skills/ce-ideate/references/agents/issue-intelligence-analyst.md +200 -0
- package/skills/ce-ideate/references/agents/learnings-researcher.md +247 -0
- package/skills/ce-ideate/references/agents/slack-researcher.md +127 -0
- package/skills/ce-ideate/references/agents/web-researcher.md +121 -0
- package/skills/ce-ideate/references/divergent-ideation.md +89 -0
- package/skills/ce-ideate/references/html-rendering.md +634 -0
- package/skills/ce-ideate/references/ideation-sections.md +191 -0
- package/skills/ce-ideate/references/markdown-rendering.md +238 -0
- package/skills/ce-ideate/references/post-ideation-workflow.md +167 -0
- package/skills/ce-ideate/references/universal-ideation.md +107 -0
- package/skills/ce-ideate/references/web-research-cache.md +56 -0
- package/skills/ce-plan/SKILL.md +137 -0
- package/skills/ce-plan/references/agents/agent-native-planning-strategist.md +62 -0
- package/skills/ce-plan/references/agents/architecture-strategist.md +46 -0
- package/skills/ce-plan/references/agents/best-practices-researcher.md +114 -0
- package/skills/ce-plan/references/agents/data-integrity-guardian.md +68 -0
- package/skills/ce-plan/references/agents/data-migration-reviewer.md +103 -0
- package/skills/ce-plan/references/agents/deployment-verification-agent.md +157 -0
- package/skills/ce-plan/references/agents/framework-docs-researcher.md +93 -0
- package/skills/ce-plan/references/agents/git-history-analyzer.md +40 -0
- package/skills/ce-plan/references/agents/learnings-researcher.md +247 -0
- package/skills/ce-plan/references/agents/pattern-recognition-specialist.md +55 -0
- package/skills/ce-plan/references/agents/performance-oracle.md +108 -0
- package/skills/ce-plan/references/agents/repo-research-analyst.md +258 -0
- package/skills/ce-plan/references/agents/security-sentinel.md +91 -0
- package/skills/ce-plan/references/agents/slack-researcher.md +127 -0
- package/skills/ce-plan/references/agents/spec-flow-analyzer.md +80 -0
- package/skills/ce-plan/references/agents/web-researcher.md +121 -0
- package/skills/ce-plan/references/approach-altitude.md +55 -0
- package/skills/ce-plan/references/change-splitting.md +65 -0
- package/skills/ce-plan/references/completion-contract.md +33 -0
- package/skills/ce-plan/references/core-principles.md +40 -0
- package/skills/ce-plan/references/deepening-workflow.md +263 -0
- package/skills/ce-plan/references/dependency-graph.md +36 -0
- package/skills/ce-plan/references/html-rendering.md +634 -0
- package/skills/ce-plan/references/intake-routing.md +189 -0
- package/skills/ce-plan/references/markdown-rendering.md +238 -0
- package/skills/ce-plan/references/plan-handoff.md +150 -0
- package/skills/ce-plan/references/plan-sections.md +427 -0
- package/skills/ce-plan/references/plan-structure.md +120 -0
- package/skills/ce-plan/references/planning-modes.md +69 -0
- package/skills/ce-plan/references/reasoning-elevation.md +63 -0
- package/skills/ce-plan/references/research-workflow.md +165 -0
- package/skills/ce-plan/references/review-and-write.md +127 -0
- package/skills/ce-plan/references/settled-decisions.md +45 -0
- package/skills/ce-plan/references/synthesis-summary.md +418 -0
- package/skills/ce-plan/references/universal-planning.md +168 -0
- package/skills/ce-proof/SKILL.md +346 -0
- package/skills/ce-strategy/SKILL.md +97 -0
- package/skills/ce-strategy/references/interview.md +143 -0
- package/skills/ce-strategy/references/strategy-template.md +89 -0
- package/skills/code-reviewer/SKILL.md +84 -0
- package/skills/code-reviewer/code-reviewer-prompt.md +195 -0
- package/skills/contract-builder/SKILL.md +72 -0
- package/skills/design-system/SKILL.md +75 -0
- package/skills/design-system/references/agents/design-system-architect.md +138 -0
- package/skills/design-system/references/creation-flow.md +170 -0
- package/skills/design-system/references/preview-template.html +319 -0
- package/skills/design-system/references/token-derivation.md +115 -0
- package/skills/design-system/references/variant-schema.md +60 -0
- package/skills/e2e/SKILL.md +56 -0
- package/skills/e2e/references/test-verifier.md +40 -0
- package/skills/need-explorer/SKILL.md +79 -0
- package/skills/prototype/SKILL.md +98 -0
- package/skills/prototype/references/agents/design-system-architect.md +122 -0
- package/skills/prototype/references/checklist.md +82 -0
- package/skills/prototype/references/craft/accessibility-baseline.md +71 -0
- package/skills/prototype/references/craft/anti-ai-slop.md +87 -0
- package/skills/prototype/references/craft/laws-of-ux.md +60 -0
- package/skills/prototype/references/craft/state-coverage.md +81 -0
- package/skills/prototype/references/craft/typography-hierarchy.md +50 -0
- package/skills/prototype/references/layouts.md +223 -0
- package/skills/prototype/references/orchestration-flow.md +101 -0
- package/skills/prototype/references/prototype-scaffold/assets/design-tokens.css +19 -0
- package/skills/prototype/references/prototype-scaffold/components/button.html +3 -0
- package/skills/prototype/references/prototype-scaffold/design-system.md +7 -0
- package/skills/prototype/references/prototype-scaffold/flow.md +11 -0
- package/skills/prototype/references/prototype-scaffold/index.html +20 -0
- package/skills/prototype/references/prototype-scaffold/pages/index.html +11 -0
- package/skills/prototype/references/template.html +396 -0
- package/skills/release-archivist/SKILL.md +166 -0
- package/skills/release-archivist/references/closing-procedures.md +81 -0
- package/skills/session-handoff/SKILL.md +110 -0
- package/skills/session-handoff/references/context-extraction.md +70 -0
- package/skills/session-handoff/references/handoff-template.md +90 -0
- package/skills/session-handoff/references/skill-recommendation.md +43 -0
- package/skills/spec-merger/SKILL.md +66 -0
- package/skills/spec-writer/SKILL.md +149 -0
- package/skills/workflow-bootstrap/SKILL.md +148 -0
- package/skills/workflow-bootstrap/references/agents/codebase-recon-analyst.md +121 -0
- package/skills/workflow-bootstrap/references/b1-reconnaissance.md +80 -0
- package/skills/workflow-bootstrap/scripts/recon-probe.sh +328 -0
- package/skills/workflow-feedback/SKILL.md +120 -0
- package/skills/workflow-feedback/references/category-guide.md +121 -0
- package/skills/workflow-feedback/references/feedback-template.md +73 -0
- package/skills/workflow-feedback/references/review-mode.md +92 -0
- package/skills/workflow-orchestrator/SKILL.md +94 -0
- package/skills/workflow-orchestrator/references/feedback-loops.md +56 -0
- package/skills/workflow-orchestrator/references/s1-path-router.md +81 -0
- package/skills/workflow-orchestrator/references/s2-prd-prototype-loop.md +96 -0
- package/skills/workflow-orchestrator/references/s3-plan-pipeline.md +50 -0
- package/skills/workflow-orchestrator/references/s4-split-validate.md +108 -0
- package/skills/workflow-orchestrator/references/s5-monitoring.md +61 -0
- package/skills/workflow-orchestrator/references/state-model.md +185 -0
- package/skills/workflow-start/SKILL.md +147 -0
- package/skills/workflow-start/references/routing-rules.md +155 -0
- package/src/index.ts +16 -0
- package/src/parsing/change-parser.ts +79 -0
- package/src/parsing/requirement-blocks.ts +244 -0
- package/src/schema/base.ts +8 -0
- package/src/schema/change.ts +29 -0
- package/src/schema/index.ts +3 -0
- package/src/schema/spec.ts +12 -0
- package/src/validation/constants.ts +53 -0
- package/src/validation/tokenizer.ts +180 -0
- package/src/validation/types.ts +47 -0
- package/src/validation/validator.ts +552 -0
- package/templates/abandonment-summary.md +29 -0
- package/templates/design.md +37 -0
- package/templates/execution-contract.md +99 -0
- package/templates/plan.md +86 -0
- package/templates/prd.md +468 -0
- package/templates/proposal.md +37 -0
- package/templates/spec.md +31 -0
- package/templates/tasks.md +47 -0
- package/tests/e2e.test.mjs +266 -0
- package/tests/lib/cmd-audit.test.mjs +202 -0
- package/tests/lib/cmd-checkpoint.test.mjs +98 -0
- package/tests/lib/cmd-config.test.mjs +101 -0
- package/tests/lib/cmd-doctor.test.mjs +450 -0
- package/tests/lib/cmd-execution.test.mjs +647 -0
- package/tests/lib/cmd-handoff.test.mjs +137 -0
- package/tests/lib/cmd-inject.test.mjs +218 -0
- package/tests/lib/cmd-install-workbuddy.test.mjs +113 -0
- package/tests/lib/cmd-install-zcode.test.mjs +42 -0
- package/tests/lib/cmd-isolate.test.mjs +68 -0
- package/tests/lib/cmd-list.test.mjs +127 -0
- package/tests/lib/cmd-runtime.test.mjs +83 -0
- package/tests/lib/cmd-state-missing.test.mjs +65 -0
- package/tests/lib/cmd-state.test.mjs +365 -0
- package/tests/lib/cmd-sync-paths.test.mjs +84 -0
- package/tests/lib/cmd-validate-paths.test.mjs +90 -0
- package/tests/lib/config-loader.test.mjs +175 -0
- package/tests/lib/ensure-branch.test.mjs +59 -0
- package/tests/lib/execution-control-plane.test.mjs +168 -0
- package/tests/lib/execution-plan.test.mjs +474 -0
- package/tests/lib/guard-specs-merged.test.mjs +108 -0
- package/tests/lib/guard-tests-passing.test.mjs +112 -0
- package/tests/lib/guard-transitions.test.mjs +262 -0
- package/tests/lib/guard.test.mjs +611 -0
- package/tests/lib/hash.test.mjs +138 -0
- package/tests/lib/infer-workflow.test.mjs +161 -0
- package/tests/lib/install-git-hooks.test.mjs +20 -0
- package/tests/lib/marketplace-release-docs.test.mjs +31 -0
- package/tests/lib/minimality-discipline.test.mjs +37 -0
- package/tests/lib/model-profiles-docs.test.mjs +33 -0
- package/tests/lib/node20-compatibility.test.mjs +73 -0
- package/tests/lib/node20-test-entry.test.mjs +17 -0
- package/tests/lib/platform-runtime-distribution.test.mjs +150 -0
- package/tests/lib/raw-mode-smoke.test.mjs +42 -0
- package/tests/lib/sdd-overlay.test.mjs +118 -0
- package/tests/lib/spec-paths.test.mjs +80 -0
- package/tests/lib/state-loader.test.mjs +251 -0
- package/tests/lib/token-baseline.test.mjs +72 -0
- package/tests/lib/token-rules.test.mjs +94 -0
- package/tests/lib/verify-marketplace-release.test.mjs +128 -0
- package/tests/tsconfig.json +12 -0
- package/token-baseline.json +95 -0
- package/tsconfig.json +14 -0
package/CHANGELOG.md
ADDED
|
@@ -0,0 +1,635 @@
|
|
|
1
|
+
# Changelog
|
|
2
|
+
|
|
3
|
+
All notable changes to `team-flow` will be documented in this file.
|
|
4
|
+
|
|
5
|
+
The format loosely follows Keep a Changelog.
|
|
6
|
+
|
|
7
|
+
## [Unreleased]
|
|
8
|
+
|
|
9
|
+
## [0.22.4] - 2026-07-27
|
|
10
|
+
|
|
11
|
+
### Changed(npm 包名 scope 化,发布至 npm)
|
|
12
|
+
|
|
13
|
+
- **npm 包名**:`team-flow` → `@xulthekl/team-flow`(scoped package,解决 npm publish 权限冲突)
|
|
14
|
+
- **author**:`MageByte` → `xulthekl`
|
|
15
|
+
- **npx 引用**:全部 `npx --yes --package team-flow@X.Y.Z tf` → `npx --yes --package @xulthekl/team-flow@X.Y.Z tf`(179 处)
|
|
16
|
+
- **版本号**:bump 0.22.3 → 0.22.4(全量同步:plugin.json、marketplace.json、phase-guard.md、llms.txt、INSTALL.md、README.md 等 15 个文件)
|
|
17
|
+
|
|
18
|
+
### Verified
|
|
19
|
+
|
|
20
|
+
- 待执行 check-version-consistency + npm test
|
|
21
|
+
|
|
22
|
+
## [0.22.3] - 2026-07-27
|
|
23
|
+
|
|
24
|
+
### Changed(身份统一 spec-superflow → team-flow,P1-6 第二阶段)
|
|
25
|
+
|
|
26
|
+
- **npm 包名**:`spec-superflow` → `team-flow`(package.json `name` 字段)
|
|
27
|
+
- **CLI 前缀**:`ssf` → `tf`(package.json `bin` 字段,移除旧别名)
|
|
28
|
+
- **状态文件**:`.spec-superflow.yaml` → `.team-flow.yaml`(全局替换)
|
|
29
|
+
- **配置文件**:`spec-superflow.config.json` → `team-flow.config.json`
|
|
30
|
+
- **CLI 脚本**:`scripts/spec-superflow.mjs` → `scripts/team-flow.mjs`(git mv)
|
|
31
|
+
- **npx 引用**:99 处 `npx --yes --package spec-superflow@x.y.z ssf` → `npx --yes --package team-flow@x.y.z tf`
|
|
32
|
+
- **全量引用迁移**:721+ 处跨 skills/、scripts/、tests/、docs/、README、INSTALL、AGENTS、templates/、plugin manifests 等完成 spec-superflow → team-flow 和 ssf → tf 的文本替换
|
|
33
|
+
- **check-version-consistency.mjs**:RUNTIME_FILES 正则更新为匹配 `tf` 命令
|
|
34
|
+
- **install 脚本(install-cursor/zcode/workbuddy)**:npx 替换正则同步更新
|
|
35
|
+
- **dist/validation/tokenizer.js + src/validation/tokenizer.ts**:注释更新
|
|
36
|
+
|
|
37
|
+
### Verified
|
|
38
|
+
|
|
39
|
+
- check-version-consistency:✅ PASS(全部 0.22.3)
|
|
40
|
+
- npm test:✅ 421/421 通过
|
|
41
|
+
- Skill 计数一致性:✅ 23 skills(manifest 与实际目录匹配)
|
|
42
|
+
- spec-superflow/ssf 残留扫描:✅ 零残留(排除 CHANGELOG 历史记录和 package-lock.json)
|
|
43
|
+
|
|
44
|
+
---
|
|
45
|
+
|
|
46
|
+
## [0.22.2] - 2026-07-27
|
|
47
|
+
|
|
48
|
+
### Added(架构设计显式编排与产物独立化,设计 v0.9 §26)
|
|
49
|
+
|
|
50
|
+
- **workflow-start 显式编排 architecture-design**:路由表新增 architecture-design 子代理调用(exploring→specifying 之间),作为架构设计必经之门。子代理承担判断+执行一体化职责(五项检查判定是否涉及架构变更,涉及则执行完整 4A+DDD 增量设计,不涉及则返回 skip+理由)。workflow-start 接收结果后做合理性确认(skipped reason 与 scope 一致性 / required artifacts 存在性),写入 yaml 字段 `arch_design_decision` / `arch_design_reason` / `arch_design_artifacts` / `arch_design_timestamp`。null 状态硬阻断,不允许路由到 spec-writer。hotfix / tweak 不豁免。详细编排协议抽取到 `references/routing-rules.md`「Route to architecture-design」。
|
|
51
|
+
- **architecture-design 判断+执行一体化 SOP**:SKILL.md 新增「Workflow Integration」段,定义五项检查(聚合变更/限界上下文变更/读写模型变更/API 变更/DB schema 变更)、结构化输出契约(decision/reason/artifacts)、产出目录独立为 `architecture/`(不混入 `specs/`)。支持 workflow-start 编排调用和用户独立调用两种模式。
|
|
52
|
+
- **spec-writer 显式读取 architecture/ 约束**:Required Inputs 新增「Architecture Design Outputs (v0.9 §26)」段,读取 `architecture/architecture.md` / `database.md` / `api.md` 作为 design.md / tasks.md 的架构约束输入。Working Rules 新增「Honor Architecture」。Validation Checklist 新增 Architecture alignment 检查项。
|
|
53
|
+
- **contract-builder 读取 architecture/ 约束**:Artifact Mapping 表新增 `architecture/` 行,确保 execution-contract.md 的 Implementation Constraints 段包含架构设计的关键约束(聚合边界/CQRS 分流/API 契约/schema 变更)。
|
|
54
|
+
- **ch06-integration.md 产物布局修正**:从 `specs/<cap>/` 修正为独立 `architecture/` 目录,完整列出 change 容器内全部目录结构。
|
|
55
|
+
|
|
56
|
+
### Changed
|
|
57
|
+
|
|
58
|
+
- **s4-split-validate.md**:路径约束说明增加 `architecture/` 目录(与 `specs/<cap>/` 并列说明)。
|
|
59
|
+
- **state-model.md**:change_dir 说明增加 `architecture/` 目录(与 `specs/<cap>/` 并列说明)。
|
|
60
|
+
- **routing-rules.md**:Fast-Path 段补充「architecture-design 不豁免」提示(v0.9 §26)。
|
|
61
|
+
|
|
62
|
+
### Verified
|
|
63
|
+
|
|
64
|
+
- check-version-consistency:✅ PASS(全部 0.22.2)
|
|
65
|
+
- npm test:✅ 421/421 通过
|
|
66
|
+
- plugin-validator:✅ 0 Critical / 0 Important / 5 Advisory(1 个可操作性 Advisory 已修复)
|
|
67
|
+
- SKILL.md 行数:✅ 全部 ≤150(workflow-start 147 / architecture-design 140 / spec-writer 149 / contract-builder 72)
|
|
68
|
+
|
|
69
|
+
## [0.21.0] - 2026-07-25
|
|
70
|
+
|
|
71
|
+
### Added(子代理决策点 SendMessage stop-and-resume 交互协议,设计 §22.1.1,修订 §18.1.2)
|
|
72
|
+
|
|
73
|
+
- **决策点 SendMessage stop-and-resume(P1-14,完成 P1-13 的 SendMessage 子项)**:子代理工具集不含 AskUserQuestion,决策点需用户/主代理输入时经 `SendMessage(to: main)` 发结构化提问后**主动停止**(status=completed);主代理经 `task-notification` 收到(零 TaskOutput 轮询)→ `AskUserQuestion` 代问用户 → `SendMessage(to: agentId)` 回传**自动 resume** 子代理带答案续跑(上下文经 transcript 保留)。LT 实证确认(Session d6801ab4,单轮/多轮追问/三子代理并行/多问合并四形态)。
|
|
74
|
+
- **请求-应答匹配纪律**:主代理维护未决提问台账、仅回传子代理实际所问;子代理收到回传校验对应性,不匹配按「正确优先」拒绝将错就错(实证暴露的真风险,必设)。
|
|
75
|
+
- **跨平台降级**:harness 不支持 resume → 降级 `blocked` + 携答案重派(承 §17.8 / §18.1.2)。
|
|
76
|
+
- 落点:`prototype-builder.md`(Decision-Point Interaction)+ `prototype-env-scout.md`(决策点交互)+ `prototype/references/orchestration-flow.md`(主代理中继协议)。
|
|
77
|
+
|
|
78
|
+
### Changed
|
|
79
|
+
|
|
80
|
+
- **§18.1.2 修订**:「不引入 agent team」明确指不采用**常驻 teammate 架构**,不排斥决策点 SendMessage stop-and-resume 中途交互;结构化返回仍为终态主协议。
|
|
81
|
+
- **AGENTS.md**:§4 prototype 增 v0.21.0 决策点中继说明;Agents 索引 prototype-builder 补注;**Skills 索引补 `design-system` 行**(v0.19.0 漏登,标题「23 个」与表体 22 行不一致修复,plugin-validator W1)。
|
|
82
|
+
|
|
83
|
+
### Deferred → Adopted
|
|
84
|
+
|
|
85
|
+
- v0.20.0 §22.1.1 曾标 Deferred(CC 误判为类 agent-team 常驻),经 LT 指认实证实录后纠正:实为 stop-and-resume,与 §18.1.2 兼容,采纳实施。
|
|
86
|
+
|
|
87
|
+
## [0.20.0] - 2026-07-25
|
|
88
|
+
|
|
89
|
+
### Added(工作流反馈三件套落地,设计增强方案 v0.8 §22)
|
|
90
|
+
|
|
91
|
+
- **产出型子代理质量闸门(P1-13,§22.1,修订 §18.1.1 返回契约)**:`prototype-builder` 新增 Deliverable Hard Gate——声明的 deliverable(`index.html`)未落盘非空禁止返回 `done`,终态交接前自检 `test -f && test -s` 通过方可 `done`;规划过重/预算将尽时诚实返回 `blocked` 交主代理 resume,杜绝「谎报 completed」。新增大产出分片纪律(先 Write 骨架 → Edit 分段追加)。`prototype-env-scout` 同步加简报完整性闸门。
|
|
92
|
+
- **编排层交接后产物校验(defense in depth)**:`prototype/references/orchestration-flow.md` builder→reviewer 间主代理强制校验入口产物落盘,不信 `status=done` 字面值,缺失则 resume,不空转评审。
|
|
93
|
+
- **编排层完成通知等待范式(P2-11,§22.2)**:`workflow-orchestrator` / `prototype` 明文派发后台子代理后依赖 `<task-notification>` 完成通知再行动,禁反复 `TaskOutput(block=true)` 阻塞轮询(其对长任务超时返回会倾泻完整 transcript 撑爆主上下文)。
|
|
94
|
+
- **S1 路由第 7 种入口「原型补跑/重跑」(P2-12,§22.3)**:PRD 冻结 ∧ `prototype/` 缺失/需重做 → 部分重入 S2 原型循环(PRD 不动、保留有效 S3/S4、闭环恢复原 phase)。`workflow-orchestrator/SKILL.md` 路由表 6→7 + `s1-path-router.md` 判据分支 + `state-model.md` 部分重入冻结语义与状态转换。
|
|
95
|
+
|
|
96
|
+
### Changed
|
|
97
|
+
|
|
98
|
+
- **AGENTS.md 能力概览**:§4 prototype / §6 orchestrator 补 v0.20.0 说明;Agents 索引 prototype-builder / env-scout 标注产物落盘硬闸门。
|
|
99
|
+
- **.cursor-plugin/plugin.json 描述横展对齐**:17 skills → 23 skills + 8 agents(与主清单一致,修 P0-3 遗漏的 cursor 副本)。
|
|
100
|
+
|
|
101
|
+
### Deferred
|
|
102
|
+
|
|
103
|
+
- **决策点 SendMessage 交互协议(§22.1.1,修订 §18.1.2)**:与「不引入 agent team / 统一返回结构」有张力;硬闸门已根治谎报完成,作为可选扩展待 LT 确认是否采纳后再写入 agent 定义。
|
|
104
|
+
|
|
105
|
+
## [0.16.0] - 2026-07-25
|
|
106
|
+
|
|
107
|
+
### Added(会话交接 + 工作流反馈)
|
|
108
|
+
|
|
109
|
+
- **session-handoff skill(设计增强方案 v0.8 §21.1)**:上下文腐化时将当前会话压缩为结构化交接文档(10 节),供新会话无缝继续。自动检测 `.team-flow/` 状态文件构建工作流快照;无状态文件时降级为通用 handoff。输出到 `.team-flow/handoffs/`(.gitignore,临时性质)。区别于 change 级 `tf handoff`(任务委派)和 `.team-flow/` yaml(结构化状态自动恢复)。含 3 个 references(交接文档模板 / 上下文萃取规则 / skill 推荐矩阵)。
|
|
110
|
+
- **workflow-feedback skill(设计增强方案 v0.8 §21.2)**:工作流使用问题结构化记录(10 类分类),转化为可追踪的改进项。与 ce-compound 互补——ce-compound 是"经验沉淀端",workflow-feedback 是"问题发现端"。输出到 `.team-flow/feedback/`(git 跟踪,改进输入持久化)。含 3 个 references(问题记录模板 / 分类指南 / 回顾模式信号识别)。
|
|
111
|
+
- **release-archivist 收尾联动**:change 收尾时建议触发 workflow-feedback 回顾工作流问题。
|
|
112
|
+
- **产物目录**:`.team-flow/handoffs/`(.gitignore)+ `.team-flow/feedback/`(git 跟踪)。
|
|
113
|
+
|
|
114
|
+
### Changed
|
|
115
|
+
|
|
116
|
+
- **Skill 计数 20 → 22**(九套能力):plugin.json / .claude-plugin/ / .cursor-plugin/ / .codex-plugin/ / gemini-extension.json / README / AGENTS.md 全链路同步。
|
|
117
|
+
- **AGENTS.md 能力概览**:新增第 8 节(session-handoff)和第 9 节(workflow-feedback);触发域分层表登记为「步骤级 - 独立工具」。
|
|
118
|
+
- **CLAUDE.md**:skills 表新增 2 行、产物结构追加 handoffs/feedback/、Roadmap 追加 v0.16.0 里程碑、P1-9 横展补入 ce-ideate/ce-proof 超标。
|
|
119
|
+
|
|
120
|
+
## [0.15.0] - 2026-07-25
|
|
121
|
+
|
|
122
|
+
### Added(subagent 编排下沉 + 状态治理)
|
|
123
|
+
|
|
124
|
+
- **subagent 结构化交接协议(设计增强方案 v0.8 §18.1)**:统一 `done / done_with_questions / blocked` + `blockers[] / outstanding_questions[]` 返回契约——主代理只编排、执行下沉子代理;非阻断疑问按默认假设继续后批量返回,阻断疑问立即返回 `blocked`。不引入 agent team,保跨平台健壮性。
|
|
125
|
+
- **多需求并行状态模型**:`.team-flow/registry.yaml` 注册表 + 每需求一份 `.team-flow/requirements/<req-id>/orchestrator.yaml`,状态天然隔离(原单文件 `.workflow-orchestrator.yaml` 自动迁移)。
|
|
126
|
+
- **3 个新插件 agent**:`prd-completeness-reviewer`(PRD 完整性评审,冻结前门禁,只读)、`prototype-builder`(原型绘制执行者,有 Write)、`prototype-env-scout`(原型环境探查,只读)。agents 5 → 8。
|
|
127
|
+
- **2 个新种子提示**:`codebase-recon-analyst`(bootstrap 侦察)、`design-system-architect`(设计系统创建/迭代)。
|
|
128
|
+
- **`recon-probe.sh` 确定性侦察脚本**(workflow-bootstrap):固定化代码库质量采集(目录树/依赖/LOC/测试计数含 `.mjs`/DB 迁移/文档),可复现可横展对比。
|
|
129
|
+
- **prototype 内部编排器重构**:主代理只编排不实施——env-scout 探查 → 方案/人工评审 → builder 绘制 → reviewer 评审 → 循环 → 人工路由;新增设计系统生命周期(创建→引用→增量更新)。
|
|
130
|
+
- **PRD 完整性评审门禁**:ce-brainstorm/orchestrator S2 冻结前派 `prd-completeness-reviewer`(管"说得全不全",区别于 claim verifier 管"说得对不对")。
|
|
131
|
+
- **PRD 版本格式规范**:迭代版本 `vN` / 文档修订次版本 `vN.M` / 文档状态枚举(编辑中/已冻结-下游/已冻结-绝对),与 frontmatter `frozen` 一致性硬约束。
|
|
132
|
+
|
|
133
|
+
### Changed
|
|
134
|
+
|
|
135
|
+
- **ce-plan 收窄**:模式强制询问(pipeline 下 orchestrator 问定后显式传 `plan_mode`,禁止隐式默认一人公司);一人公司模式收窄到「高阶技术设计」,**删除接口清单段**(接口/字段/签名属各 change 的 spec-writer);SKILL.md 顶部新增产品级/变更级作用边界硬声明。
|
|
136
|
+
- **workflow-bootstrap B1 重构**:主代理只编排,先跑 `recon-probe.sh` 脚本再并行派发侦察子代理;SKILL.md 瘦身至 ≤150 行(细节进 `references/b1-reconnaissance.md`)。
|
|
137
|
+
- **状态文件治理(P1-6 第一阶段)**:产品级编排状态迁入 `.team-flow/`(变更级 `.team-flow.yaml`→`.team-flow.yaml` 改名归 P1-6 第二阶段 v1.0.0,与 npm 包名/CLI 同批)。
|
|
138
|
+
|
|
139
|
+
### Fixed
|
|
140
|
+
|
|
141
|
+
- **冻结措辞 BUG**:ce-brainstorm 把 `frozen_downstream` 误写成「升版 vN+1」语义,违反反馈环路「迭代内变更不升版」设计;已修正为区分双层冻结(frozen_downstream 可 vN 内修订 / frozen_absolute 才升版),并横展到 PRD 模板与 prd-mapping。
|
|
142
|
+
|
|
143
|
+
## [0.10.0] - 2026-07-16
|
|
144
|
+
|
|
145
|
+
### Added
|
|
146
|
+
|
|
147
|
+
- **#60 — Qoder 平台支持**:新增 `tf install-qoder` 一键安装命令,部署 skills 到 `.qoder/skills/`、运行时依赖到 `.qoder/team-flow/`、phase-guard 规则到 `.qoder/rules/phase-guard.md`。采用共享库安装器模式(Pattern A),与 Cline/Kiro/Windsurf 等平台一致。平台支持数从 17 增至 18。
|
|
148
|
+
|
|
149
|
+
## [0.9.1] - 2026-07-15
|
|
150
|
+
|
|
151
|
+
### Changed
|
|
152
|
+
|
|
153
|
+
- **#52 — isolate optional name**: `tf isolate <change-dir>` no longer forwards an absent optional name as the literal string `undefined`; explicit names and `--force` retain their existing behavior.
|
|
154
|
+
- **#43 — portable skill runtime**: all nine canonical skills no longer require `${CLAUDE_PLUGIN_ROOT}`. Raw marketplace, cache, copy, and symlink loading use a semver-pinned package CLI; local installers rewrite that prefix to their bundled runtime tree.
|
|
155
|
+
- **Cross-platform runtime diagnostics**: `tf doctor` now detects stale root placeholders and missing runtime trees, while version sync and CI consistency checks include all nine canonical skill prefixes.
|
|
156
|
+
- **Linked-worktree version hook**: `npm run setup-hooks` now locates Git's shared hooks directory, upgrades stale team-flow hooks, and validates the worktree being committed rather than a sibling checkout.
|
|
157
|
+
- **#45 — Execution-mode recommendation**: DP-4 now runs `tf execution recommend` to list Inline, Batch Inline, and SDD from task and wave evidence, with a recommendation. Every persisted plan at `<change>/.superpowers/sdd/execution-plan.json` requires explicit `--confirm`; a non-recommended selection records `--acknowledge-recommendation` instead of treating Inline as an override. Named waves, dependencies, and review receipts remain mandatory.
|
|
158
|
+
|
|
159
|
+
### Added
|
|
160
|
+
|
|
161
|
+
- Runtime distribution inventory for all 17 documented platforms plus the ZCODE compatibility installer path.
|
|
162
|
+
- `npm run test:raw-mode` packages the current source and proves the canonical runtime works without plugin-root variables or a global `tf` command.
|
|
163
|
+
|
|
164
|
+
## [0.9.0] - 2026-07-11
|
|
165
|
+
|
|
166
|
+
### Added
|
|
167
|
+
|
|
168
|
+
- **#37 — Model profiles**:可在 `team-flow.config.json` 中为 `mechanical`、`standard`、`strong`、`review` 配置平台模型 ID,并用 `tf config --resolve-model <profile>` 只读解析;不执行跨平台自动模型切换,也不新增 runtime dependency。
|
|
169
|
+
- **#38 — Minimality discipline**:code-reviewer 现要求用任务依据审查无请求的依赖、配置、抽象与无关重构;保留 TDD、验证、安全和错误处理,不引入 Ponytail 或任何 runtime dependency。
|
|
170
|
+
|
|
171
|
+
## [0.8.17] - 2026-07-10
|
|
172
|
+
|
|
173
|
+
### Fixed
|
|
174
|
+
|
|
175
|
+
- Fixed canonical delta spec paths: validation, guard checks, hashing, sync, examples, and docs now use `specs/<capability>/spec.md`.
|
|
176
|
+
- Fixed `tf inject` default behavior so ambiguous projects require `--platforms` instead of writing every platform file.
|
|
177
|
+
- Fixed hotfix fast-path guards so hotfix can skip full planning artifacts while still requiring a fresh minimal contract and DP-3 approval.
|
|
178
|
+
|
|
179
|
+
## [0.8.16] - 2026-07-07
|
|
180
|
+
|
|
181
|
+
### Fixed
|
|
182
|
+
|
|
183
|
+
- **Plugin Scanner 门禁**:回归测试 `guard-tests-passing.test.mjs` / `guard-specs-merged.test.mjs` 此前用字符串形式 `execSync(\`node ${...}\`)` 触发 `SHELL_INJECTION_PATTERN`(8 high),改为参数数组 `execFileSync('node', [...])`。扫描分数 85/high:8 → 99/high:0 (A)。
|
|
184
|
+
- **产线 .mjs 硬化**:`ensure-branch.mjs` 去掉变量参数包装、改字面参数数组;`cmd-isolate.mjs` 去掉 `...extra` 展开;`config-loader.mjs` `execSync(字符串)` → `execFileSync(数组)`。均为去 shell 注入面的质量提升,运行时行为不变。
|
|
185
|
+
- **CI 稳定性**:`.github/workflows/hol-plugin-scanner.yml` 把 `ai-plugin-scanner-action@v1`(移动 tag,07-06→07-07 静默从 2.0.992 升到 2.0.997 导致门禁忽然挂掉)锁到 SHA `c4737ed2f724`(= 2.0.992),顺带修掉「Third-party Actions 未锁 SHA」中危项。
|
|
186
|
+
|
|
187
|
+
## [0.8.15] - 2026-07-07
|
|
188
|
+
|
|
189
|
+
### Fixed
|
|
190
|
+
|
|
191
|
+
- **BUG-A(致命)— `executing→closing` 收口跳转永久失败**:`release-archivist` 从不写 `test_result: pass`,而 `tests-passing` 守卫强制要求它,导致 `tf state transition closing` 永远 `exit(1)`。现守卫同时接受 `dp_6_result` 以 `pass` 开头,且 `release-archivist` 在 DP-6 后显式执行 `tf state set <change-dir> test_result pass`。
|
|
192
|
+
- **BUG-B — 状态漂移**:`cmd-state` 非 init 子命令在 `.team-flow.yaml` 缺失时静默返回默认态、会幽灵式创建状态文件。现缺失即报错退出;`state-loader` 增加 `spec_merged: false` 默认值并持久化。
|
|
193
|
+
- **#28 — `executing→closing` 缺「spec 已合并」闸门**:新增 `specs-merged` 守卫,残留未合并的 delta spec 会阻断收口;`spec-merger` 同步后置 `spec_merged: true`。
|
|
194
|
+
- **#15 — git 隔离仅为建议性、无强制**:新增 `ensure-branch.mjs` + `cmd-isolate.mjs`,拒绝在 `main`/`master` 上直接提交(除非 `--force`);`build-executor` 的 `tf isolate` 改为强制 pre-flight。
|
|
195
|
+
- **#26 / #27.2 — skill 依赖 PATH 解析的裸 `tf`**:所有 `skills/**/SKILL.md` 改为安装时重写的绝对路径 `node "${CLAUDE_PLUGIN_ROOT}/scripts/team-flow.mjs"`,修复 cursor / marketplace 用户必失败的问题。
|
|
196
|
+
|
|
197
|
+
### Added
|
|
198
|
+
|
|
199
|
+
- **#29 — ZCODE(gemini-cli)安装器**:新增 `install-zcode.mjs` + `cmd-install-zcode.mjs`,注册进 CLI;`INSTALL.md` 平台表补充 ZCODE 行。
|
|
200
|
+
|
|
201
|
+
## [0.8.14] - 2026-07-06
|
|
202
|
+
|
|
203
|
+
### Fixed
|
|
204
|
+
|
|
205
|
+
- **WorkBuddy 安装器重构** — `tf install-workbuddy` 现在部署为标准 marketplace 插件,修复了 v0.8.13 中存在的三个缺陷:
|
|
206
|
+
- **运行时依赖缺失** — 旧安装器不复制 `scripts/`、`docs/`、`templates/`、`dist/`、`hooks/`,导致 skill 中引用的脚本和模板无法解析。现在全部复制到插件根目录。
|
|
207
|
+
- **`${CLAUDE_PLUGIN_ROOT}` 未重写** — 旧安装器直接复制 SKILL.md 而不重写路径变量,导致所有脚本引用断裂。现在重写为 marketplace 插件绝对路径。
|
|
208
|
+
- **插件结构错误** — 旧安装器为每个 skill 创建独立的 marketplace 插件目录(9 个插件 × 9 个 enabledPlugins 键)。现在部署为单个 `team-flow` 插件,包含 `skills/` 子目录、`.codebuddy-plugin/plugin.json` 清单、`rules/phase-guard.md` 规则,settings.json 中仅需 `team-flow@cb_teams_marketplace` 单个启用键。旧安装产生的 per-skill 键会在升级时自动清理。
|
|
209
|
+
|
|
210
|
+
### Added
|
|
211
|
+
|
|
212
|
+
- WorkBuddy 安装器新增 `--dry-run` 预览模式和 `--tag` 指定版本安装。
|
|
213
|
+
- WorkBuddy 平台现在有 phase-guard 规则(`rules/phase-guard.md`,WorkBuddy 自动加载为常驻上下文)。
|
|
214
|
+
|
|
215
|
+
## [0.8.13] - 2026-07-06
|
|
216
|
+
|
|
217
|
+
### Added
|
|
218
|
+
|
|
219
|
+
- **跨平台安装支持扩展至 17 个平台** — 新增 8 个 AI 编程平台的一键安装器,平台覆盖面对齐 comet:
|
|
220
|
+
- `tf install-cline` — Cline(`.cline/skills/` + `.clinerules/phase-guard.md`)
|
|
221
|
+
- `tf install-kiro` — Kiro(`.kiro/skills/` + `.kiro/steering/phase-guard.md`)
|
|
222
|
+
- `tf install-windsurf` — Windsurf(`.windsurf/skills/` + `.windsurf/rules/phase-guard.md`)
|
|
223
|
+
- `tf install-qwen` — Qwen Code(`.qwen/skills/` + `.qwen/rules/phase-guard.md`)
|
|
224
|
+
- `tf install-amazon-q` — Amazon Q Developer(`.amazonq/skills/` + `.amazonq/rules/phase-guard.md`)
|
|
225
|
+
- `tf install-roocode` — Roo Code(`.roo/skills/` + `.roo/rules/phase-guard.md`)
|
|
226
|
+
- `tf install-continue` — Continue(`.continue/skills/` + `.continue/rules/phase-guard.md`)
|
|
227
|
+
- `tf install-pi` — Pi(`.pi/skills/`,无规则目录,手动 `/workflow-start`)
|
|
228
|
+
- **共享安装器架构** — 新增 `scripts/lib/platforms.mjs`(平台注册表)与 `scripts/lib/install.mjs`(共享安装器),8 个 `install-<id>.mjs` 为薄壳调用,路径全部与 comet `src/core/platforms.ts` 交叉核实。`install-cursor.mjs` / `install-workbuddy` 保持原样。
|
|
229
|
+
- **平台支持矩阵文档** — 新增 `docs/platform-matrix.md`,17 平台 × Skills/Rules/Hooks 三层接入透明化。
|
|
230
|
+
- **CLI 命令** — `tf` 注册 8 个 `install-<id>` 子命令,`npx team-flow@latest install-<id>` 一键部署。
|
|
231
|
+
|
|
232
|
+
### Changed
|
|
233
|
+
|
|
234
|
+
- INSTALL.md 平台总览表从 9 行扩至 17 行,新增 8 个平台完整安装/升级/卸载/验证章节。
|
|
235
|
+
- README.md 安装区表格与 CLI 命令表同步扩充。
|
|
236
|
+
|
|
237
|
+
### Notes
|
|
238
|
+
|
|
239
|
+
- Kiro / Windsurf / Qwen / Amazon Q 原生支持 hooks,但 team-flow 的 SessionStart 钩子在这些平台的可用性未逐一验证,v0.8.13 暂不写入 hook 配置;上下文注入由 phase-guard 规则(平台自动加载)承担,后续版本验证后补齐。
|
|
240
|
+
- 剩余 14 个 comet 平台(Junie / Bob / ForgeCode / Crush / iFlow / CoStrict / Factory / KiloCode / Auggie / Lingma / KimiCode / Antigravity ×2 等)留待 v0.8.14+ 分批跟进。
|
|
241
|
+
|
|
242
|
+
## [0.8.12] - 2026-07-06
|
|
243
|
+
|
|
244
|
+
### Fixed
|
|
245
|
+
|
|
246
|
+
- **Workflow mode inference** — hotfix/tweak auto-detection now recognizes common non-JavaScript source files, including Java, Go, Python, Rust, Kotlin, Swift, C/C++, C#, Ruby, PHP, and shell scripts, so multi-task code changes are no longer misclassified as config/doc-only tweaks.
|
|
247
|
+
|
|
248
|
+
## [0.8.11] - 2026-07-06
|
|
249
|
+
|
|
250
|
+
### Fixed
|
|
251
|
+
|
|
252
|
+
- **DP-0 audit consistency** — `tf audit` now treats existing `dp_0_confirmed: true` state as a recorded DP-0 confirmation, and `dp_0_result` is now persisted by the state loader instead of being dropped after `tf state set`.
|
|
253
|
+
|
|
254
|
+
## [0.8.10] - 2026-07-06
|
|
255
|
+
|
|
256
|
+
### Fixed
|
|
257
|
+
|
|
258
|
+
- **Guard fast-path gating** — `exploring -> bridging` now requires `hotfix` or `tweak`, and `exploring -> approved-for-build` now requires `tweak`; `full`/`auto` workflows no longer skip `contract-builder` and approval gates.
|
|
259
|
+
- **State transition safety** — `tf state transition` now fails closed when guard execution fails, returns malformed output, reports non-boolean `pass`, or exits unsuccessfully, preventing state writes after unreliable guard checks.
|
|
260
|
+
- **Execution branch isolation** — `build-executor` now requires branch/worktree preflight before implementation and stops for explicit approval before editing `main` or `master`.
|
|
261
|
+
|
|
262
|
+
## [0.8.9] - 2026-07-04
|
|
263
|
+
|
|
264
|
+
### Added
|
|
265
|
+
|
|
266
|
+
- **WorkBuddy installer** — New `tf install-workbuddy` command deploys all 9 skills into WorkBuddy's marketplace plugin directory and enables them in `~/.workbuddy/settings.json`.
|
|
267
|
+
- **WorkBuddy installer tests** — Covers target path planning, skill copy behavior, settings preservation, and package-root resolution for `npx` usage.
|
|
268
|
+
|
|
269
|
+
### Changed
|
|
270
|
+
|
|
271
|
+
- **Installation docs** — Updated README, English README, INSTALL.md, OpenCode notes, AGENTS.md, and llms.txt to reflect current mainstream installation paths for Claude Code, Cursor, OpenAI Codex CLI/App, GitHub Copilot CLI, Gemini CLI, OpenCode, WorkBuddy, and Trae.
|
|
272
|
+
- **Update guidance** — Added WorkBuddy upgrade command to the version reminder output.
|
|
273
|
+
|
|
274
|
+
### Fixed
|
|
275
|
+
|
|
276
|
+
- **Doctor manifest coverage** — `tf doctor` now checks `.cursor-plugin/marketplace.json` and `.github/plugin/marketplace.json`, and correctly handles multiple version fields in the same manifest file.
|
|
277
|
+
|
|
278
|
+
## [0.8.8] - 2026-07-03
|
|
279
|
+
|
|
280
|
+
### Changed
|
|
281
|
+
|
|
282
|
+
- **Token efficiency optimization**: Compressed all prompt injection surfaces by 60.3% (from ~24,387 estimated tokens to ~9,669).
|
|
283
|
+
- `hooks/session-start`: 23→15 lines, comments compressed, platform branches share message variable.
|
|
284
|
+
- 9 skill SKILL.md files: 2,461→750 lines total (−69.5%). Each skill ≤250 lines, 0 token lint issues.
|
|
285
|
+
- Phase guard files (`.claude/always/phase-guard.md`, `GEMINI.md`): 14→3 lines each, reference state machine instead of enumerating operations.
|
|
286
|
+
- `workflow-start` initialization simplified: deferred non-critical checks to target skills.
|
|
287
|
+
|
|
288
|
+
### Added
|
|
289
|
+
|
|
290
|
+
- **Token baseline tool** (`scripts/token-baseline.mjs`): Measures lines, characters, and estimated tokens for all injection components. Supports `--compare` for pre/post compression analysis.
|
|
291
|
+
- **Token lint rules** (`scripts/lint/rules/token-rules.mjs`): 4 rules — max lines, max chars, emphasis marker limits, code block length limits. Banned markers: `EXTREMELY_IMPORTANT`, `CRITICAL`.
|
|
292
|
+
- **`--include token`** support in `lint-skills.mjs` for token-specific linting.
|
|
293
|
+
- **CI token lint step**: Warning-only check in both build-and-test and release jobs.
|
|
294
|
+
- **Phase guard files** now included in version consistency checks.
|
|
295
|
+
|
|
296
|
+
## [0.8.7] - 2026-07-03
|
|
297
|
+
|
|
298
|
+
### Added
|
|
299
|
+
|
|
300
|
+
- **Skill lint framework**: `scripts/lint/lint-skills.mjs` with 5 rules for static analysis of skill instruction quality.
|
|
301
|
+
- **Guard transition tests**: 43 regression tests covering all 21 legal transitions and 8 illegal rejections.
|
|
302
|
+
- **Exception handling**: All 9 skills now include guidance for parse failures, missing files, and user interruption recovery.
|
|
303
|
+
|
|
304
|
+
### Fixed (Bug)
|
|
305
|
+
|
|
306
|
+
- **Parser bilingual support**: `parseChangeMarkdown` now correctly extracts sections from bilingual headings (e.g., `## 背景(Why)`). Previously it used English-only exact matching, silently returning empty strings.
|
|
307
|
+
- **Guard workflow normalization**: `tf state transition` no longer silently skips guard checks when workflow is `auto`. The `auto` mode is now normalized to `full` before guard invocation.
|
|
308
|
+
- **Guard error handling**: Terminal states (`abandoned`, `closing`) now correctly reject further transitions instead of allowing them through.
|
|
309
|
+
|
|
310
|
+
### Changed
|
|
311
|
+
|
|
312
|
+
- **build-executor**: Added DP-4 and DP-5 record commands.
|
|
313
|
+
- **contract-builder**: Added DP-3 record command and exception handling guidance.
|
|
314
|
+
- **release-archivist**: Added DP-6/DP-7 record commands and DP gap detection.
|
|
315
|
+
- **workflow-start**: Fixed "Route to abandonment" → "Route to abandoned state".
|
|
316
|
+
- All 9 skills: Added standardized exception handling sections.
|
|
317
|
+
|
|
318
|
+
## [0.8.6] - 2026-07-03
|
|
319
|
+
|
|
320
|
+
### Fixed (Bug)
|
|
321
|
+
|
|
322
|
+
- **CI**: Correct `actions/setup-node` SHA — the previously pinned `v4.5.0` release didn't exist. Changed to `v4.4.0` (latest actual v4). This was silently breaking all CI runs on main.
|
|
323
|
+
|
|
324
|
+
### Changed
|
|
325
|
+
|
|
326
|
+
- **Deps**: Bump `actions/checkout` from 4.2.2 to 7.0.0 (SHA-pinned, `tsc` verified).
|
|
327
|
+
- **Deps**: Bump `typescript` from 5.9.3 to 6.0.3 (devDependency, `tsc --noEmit` zero errors).
|
|
328
|
+
- **Branch protection**: Main branch now requires PR + CI checks (`Build & Test (22)`, `scan`) before merge.
|
|
329
|
+
|
|
330
|
+
## [0.8.5] - 2026-07-03
|
|
331
|
+
|
|
332
|
+
### Fixed (Bug)
|
|
333
|
+
|
|
334
|
+
- **Issue #9**: Cursor installation (`install-cursor.mjs`) now copies the full runtime tree (`scripts/`, `docs/`, `templates/`, `dist/`, `hooks/`) instead of just `skills/`. Fixes 24 broken `${CLAUDE_PLUGIN_ROOT}` references in skills.
|
|
335
|
+
|
|
336
|
+
### Added
|
|
337
|
+
|
|
338
|
+
- **`tf install-cursor` CLI command**: Deploys team-flow to `.cursor/` directory.
|
|
339
|
+
- **Multi-platform marketplace support**:
|
|
340
|
+
- `.cursor-plugin/marketplace.json` — Cursor marketplace submission
|
|
341
|
+
- `.opencode/plugins/team-flow.js` — OpenCode plugin entry
|
|
342
|
+
- `.codex-plugin/plugin.json` — `composerIcon` for Codex
|
|
343
|
+
- `gemini-extension.json` — Gemini CLI verified install
|
|
344
|
+
- **Codex scanner**: `SECURITY.md`, `assets/icon.svg`, `.codexignore`, `.github/dependabot.yml`, `hol-plugin-scanner.yml` CI workflow. Scanner score: 92/130.
|
|
345
|
+
- **Branch protection setup** for main branch.
|
|
346
|
+
|
|
347
|
+
### Changed
|
|
348
|
+
|
|
349
|
+
- **README**: Restructured with quick start first. English README fully synced with Chinese version.
|
|
350
|
+
|
|
351
|
+
## [0.8.4] - 2026-07-03
|
|
352
|
+
|
|
353
|
+
### Fixed (Bug)
|
|
354
|
+
|
|
355
|
+
- **Critical: C-1** — Validator bilingual heading support: `extractSection` regex now matches both `## Why` and `## 背景(Why)` style headings. Chinese templates no longer fail schema validation.
|
|
356
|
+
- **Critical: C-2** — Guard dead transition `bridging:approved` fixed to `bridging:approved-for-build` (matching canonical state name).
|
|
357
|
+
- **Critical: C-3** — Cursor workflow-orchestrator guard call fixed to use `approved-for-build` instead of `approved`, preventing "Unknown transition" errors.
|
|
358
|
+
- **High: H-1** — Guard transition matrix extended with 6 missing rewind transitions (`specifying:exploring`, `bridging:specifying`, `approved-for-build:bridging`, `executing:specifying`, `executing:bridging`, `closing:specifying`).
|
|
359
|
+
- **High: H-2** — `tf state transition` now runs guard checks before writing state. Guard is no longer bypassable via direct CLI.
|
|
360
|
+
- **High: H-3** — `tasks-complete.mjs` now matches both `[x]` and `[X]` (case-insensitive) and supports indented/nested tasks (`[ \t]*` prefix).
|
|
361
|
+
- **High: H-4** — `build-executor` SKILL.md: 3 script paths fixed to use `${CLAUDE_PLUGIN_ROOT}` prefix, preventing breakage after worktree `cd`.
|
|
362
|
+
- **High: H-5** — `spec-merger` SKILL.md: removed non-existent `workflow/` path prefix from 7 spec locations.
|
|
363
|
+
- **High: H-6** — `infer-workflow.mjs`: fixed `import.meta.url` comparison for relative-path invocation (added `import.meta.filename` fallback for Node 22+).
|
|
364
|
+
- **High: H-7** — `cmd-state.mjs` transition now validates state names against `VALID_STATES` whitelist, rejecting typos that corrupt the state machine.
|
|
365
|
+
- **Medium: M-1** — 6 skill H1 titles updated from v0.7 old names to v0.8.x current names (e.g., "Spec Explorer" → "Need Explorer").
|
|
366
|
+
- **Medium: M-2** — `state-loader.mjs`: `||` replaced with `??` across 10 fields, preventing empty string → null data loss.
|
|
367
|
+
- **Medium: M-3** — `hash.mjs`: specs hash now only includes `spec.md` files (not all `.md` files), preventing false hash mismatch from README.md changes.
|
|
368
|
+
- **Medium: M-4** — `schema-valid.mjs`: WARNING-level issues now captured and returned alongside ERRORs instead of being silently discarded.
|
|
369
|
+
- **Medium: M-6** — `schema-valid.mjs`: dynamic `import()` now wrapped in try/catch with helpful "Run 'npm run build'" error message.
|
|
370
|
+
- **Medium: M-7** — `infer-workflow.mjs`: explicit `workflow: full` no longer overridden by auto-detection heuristic.
|
|
371
|
+
- **Medium: M-8** — `workflow-start` SKILL.md: 8 relative script paths fixed to use `${CLAUDE_PLUGIN_ROOT}` prefix.
|
|
372
|
+
- **Medium: M-9** — `cmd-state.mjs` SETTABLE_FIELDS extended with 25 missing fields (`batches_completed`, `dp_0_result`, `dp_N_decisions`, `dp_N_confirmed` for DP-1 through DP-7).
|
|
373
|
+
- **Medium: M-10** — `bug-investigator` SKILL.md: added DP-5 (调试升级) reference near 3+ failure escalation rule.
|
|
374
|
+
- **Low: L-1** — `CLAUDE.md` ASCII state diagram: `approved` → `approved-for-build`.
|
|
375
|
+
- **Low: L-2** — `team-flow.mjs` CLI help: example uses `approved-for-build` instead of `approved`.
|
|
376
|
+
- **Low: L-3** — `cmd-state.mjs` get: blocks prototype property reads (`__proto__`, `constructor`, etc.).
|
|
377
|
+
- **Low: L-4** — `cmd-state.mjs` init: auto-creates change directory if missing.
|
|
378
|
+
- **Low: L-7** — `docs/state-machine.md`: added fast-path transitions (`exploring→bridging`, `exploring→approved-for-build`).
|
|
379
|
+
|
|
380
|
+
### Changed (Token Optimization)
|
|
381
|
+
|
|
382
|
+
- **T-1** — `session-start` hook injection reduced from ~100 tokens to ~40 tokens (~60% reduction). Removed `set -euo pipefail` and no-op `| cat` pipes.
|
|
383
|
+
- **T-2** — `install-cursor.mjs`: now cleans old skill directories before copying, preventing stale v0.7 names from accumulating.
|
|
384
|
+
- **T-3** — `cmd-inject.mjs`: `claude` platform writer no longer writes duplicate `rules/phase-guard.md` (`.claude/always/phase-guard.md` suffices).
|
|
385
|
+
- **T-4** — `.cursor/skills/`: removed 8 stale v0.7 skill directories (spec-explorer, spec-forger, spec-syncer, bridge-contract, execution-governor, systematic-debugger, closure-archivist, workflow-orchestrator). Now has only 9 current skills.
|
|
386
|
+
- **T-5** — Deleted stale `rules/phase-guard.md` file.
|
|
387
|
+
|
|
388
|
+
### Changed (Internal)
|
|
389
|
+
|
|
390
|
+
- `package.json` test script now runs all 152 tests (e2e + lib), not just e2e.
|
|
391
|
+
- Guard test updated for `bridging→approved-for-build` transition name.
|
|
392
|
+
|
|
393
|
+
## [0.8.3] - 2026-07-01
|
|
394
|
+
|
|
395
|
+
### Added
|
|
396
|
+
|
|
397
|
+
- **130 new tests** — CLI scripts (`cmd-list`, `cmd-state`, `cmd-audit`, `cmd-doctor`, `cmd-inject`) and guard system now have comprehensive test coverage. 152 total tests (up from 22), covering config loading, state management, hash computation, guard transitions, workflow inference, and phase guard generation.
|
|
398
|
+
|
|
399
|
+
### Fixed
|
|
400
|
+
|
|
401
|
+
- **`infer-workflow` empty directory** — previously returned `hotfix` for empty change directories (0 tasks, 0 files); now correctly returns `full` as the safe default.
|
|
402
|
+
|
|
403
|
+
### Changed
|
|
404
|
+
|
|
405
|
+
- **Refactored guard run loop** — switch-case replaced with `CHECK_RUNNERS` lookup map for cleaner dimension dispatch.
|
|
406
|
+
- **Deduplicated `cmd-validate`** — `design.md` and `tasks.md` structural validation merged into a single config-driven loop.
|
|
407
|
+
- **Exported internal functions** — `detectChangeStatus` (cmd-list), `generateReport`/`DP_NAMES` (cmd-audit), 7 doctor check functions (cmd-doctor), `generatePhaseGuard`/`toCursorMdc`/`toCopilotInstructions` (cmd-inject) now exported for direct unit testing.
|
|
408
|
+
|
|
409
|
+
## [0.8.2] - 2026-07-01
|
|
410
|
+
|
|
411
|
+
### Added
|
|
412
|
+
|
|
413
|
+
- **DP-1 and DP-2 implementation** — `need-explorer` now records DP-1 (requirement confirmation) before handing off to `spec-writer`; `spec-writer` now records DP-2 (artifact review) before handing off to `contract-builder`.
|
|
414
|
+
|
|
415
|
+
### Fixed
|
|
416
|
+
|
|
417
|
+
- **SessionStart token overhead (issue #5)** — `hooks/session-start` now injects a ~50 token lightweight pointer instead of the full 360-line `workflow-start` SKILL.md, reducing per-session context-window usage by ~2,200 words.
|
|
418
|
+
- **tweak fast-path deadlock** — `guard.mjs` now skips `artifacts-exist` checks for tweak workflow, and `build-executor` accepts tweak mode without requiring `execution-contract.md`. The advertised tweak path now actually works.
|
|
419
|
+
- **State name inconsistency** — `approved` and `approved-for-build` standardized to `approved-for-build` across `guard.mjs`, `cmd-inject.mjs`, `workflow-start`, and `state-machine.md`. Removed duplicate `approved` phase-guard template.
|
|
420
|
+
- **`tf list` false CLOSED** — `detectChangeStatus` now reads `.team-flow.yaml` state instead of inferring closure from file existence. Previously reported BRIDGED changes as CLOSED.
|
|
421
|
+
- **`tf audit` missing DP-0** — DP-0 (user confirmation gate) now included in audit reports alongside DP-1–DP-7.
|
|
422
|
+
- **Guard `artifacts-exist` config-aware** — now respects `artifacts.skip` from `team-flow.config.json`, allowing projects to exclude optional planning artifacts.
|
|
423
|
+
- **Old skill names in guard scripts** — `contract-fresh.mjs` and `tests-passing.mjs` error messages updated to reference `contract-builder` and `release-archivist`.
|
|
424
|
+
- **Sub-prompt path resolution** — `build-executor` and `code-reviewer` now use `${CLAUDE_PLUGIN_ROOT}/skills/<name>/` paths for sub-prompt templates instead of bare filenames.
|
|
425
|
+
- **`tf validate` coverage** — now validates all 4 planning artifacts (`design.md` and `tasks.md` basic structural checks added).
|
|
426
|
+
- **Config default artifact order** — `execution-contract` removed from `artifacts.order` default (it's `contract-builder`'s output, not `spec-writer`'s).
|
|
427
|
+
- **README state count** — corrected from 7 to 8 states (includes `abandoned`).
|
|
428
|
+
|
|
429
|
+
### Changed
|
|
430
|
+
|
|
431
|
+
- **README "不推荐使用" refreshed** — v0.8.x improvements (hotfix, tweak, Batch Inline, reduced token overhead) now cover many previously-excluded scenarios. The "not recommended" section now only lists truly unsuitable cases (throwaway scripts, pure Q&A).
|
|
432
|
+
|
|
433
|
+
## [0.8.1] - 2026-07-01
|
|
434
|
+
|
|
435
|
+
### Added
|
|
436
|
+
|
|
437
|
+
- **Auto-latest Cursor install** — `scripts/install-cursor.mjs` now downloads and deploys the latest GitHub release by default. Use `--local <path>` to deploy from a local repo.
|
|
438
|
+
- **Update check reminder** — New `scripts/check-update.mjs` compares the installed version with npm latest. `workflow-start` runs it on startup and surfaces a non-blocking upgrade reminder when behind.
|
|
439
|
+
|
|
440
|
+
### Changed
|
|
441
|
+
|
|
442
|
+
- **INSTALL.md** now documents `/plugin update team-flow@team-flow` as the Claude Code upgrade path and provides a curl one-liner for Cursor auto-deployment.
|
|
443
|
+
|
|
444
|
+
## [0.8.0] - 2026-07-01
|
|
445
|
+
|
|
446
|
+
### Added
|
|
447
|
+
|
|
448
|
+
- **Intuitive skill names** — All 9 skills renamed to action-object style: `workflow-start`, `need-explorer`, `spec-writer`, `contract-builder`, `build-executor`, `bug-investigator`, `code-reviewer`, `release-archivist`, `spec-merger`.
|
|
449
|
+
- **Batch Inline execution mode** — `build-executor` now supports `Batch Inline` for low-risk, same-module tasks, reducing subagent dispatch overhead for small changes like issue #5.
|
|
450
|
+
- **User confirmation gate (DP-0)** — `workflow-start` confirms key decisions with the user before routing to `spec-writer`; `spec-writer` honors confirmed constraints and pauses on unconfirmed decisions.
|
|
451
|
+
- **Migration guide** — Added `docs/skill-rename-v0.8.0.md` with old→new mapping and per-platform refresh instructions.
|
|
452
|
+
|
|
453
|
+
### Changed
|
|
454
|
+
|
|
455
|
+
- **Documentation sync** — `README.md`, `INSTALL.md`, `CLAUDE.md`, `docs/state-machine.md`, `docs/decision-points.md`, `GEMINI.md`, main `specs/`, `templates/`, and plugin manifests updated to use the new skill names and v0.8.0 install instructions.
|
|
456
|
+
- **Version sync** — `tf version` now also updates `.codex-plugin/plugin.json`; `tf doctor` checks all 7 manifests.
|
|
457
|
+
|
|
458
|
+
## [0.7.1] - 2026-06-30
|
|
459
|
+
|
|
460
|
+
### Fixed
|
|
461
|
+
|
|
462
|
+
- **README consistency** — 移除架构图中不存在的 `schemas/` 目录,补充 `scripts/guard/`、`install-cursor.mjs`、`infer-workflow.mjs`;明确 Cursor 的 session-start hook 需要手动复制到 `.cursor/hooks.json`。
|
|
463
|
+
|
|
464
|
+
## [0.7.0] - 2026-06-30
|
|
465
|
+
|
|
466
|
+
### Added
|
|
467
|
+
|
|
468
|
+
- **Multi-platform phase-guard injection** — `tf inject` now generates phase-guard artifacts for Claude Code (`.claude/always/phase-guard.md`), Cursor (`.cursor/rules/phase-guard.mdc`), Copilot (`.github/copilot-instructions.md`), and Gemini (`GEMINI.md`). New `--platforms` flag limits output to a subset.
|
|
469
|
+
- **Auto workflow-mode detection** — `workflow-orchestrator` infers `hotfix`/`tweak`/`full` from artifact content when `.team-flow.yaml` workflow is `auto`. Added `scripts/infer-workflow.mjs` helper. Explicit workflow values are preserved.
|
|
470
|
+
- **Decision-point audit report** — New `tf audit <change-dir>` command reads `.team-flow.yaml` DP fields and generates `decision-point-audit.md` with a summary table and per-DP interpretation.
|
|
471
|
+
- **Cursor local deploy** — New `scripts/install-cursor.mjs` copies skills to `.cursor/skills/` and creates `.cursor/rules/phase-guard.mdc` for Cursor Agent.
|
|
472
|
+
- **Template localization** — All planning templates under `templates/` are now in Chinese while keeping required parsing markers intact.
|
|
473
|
+
|
|
474
|
+
### Fixed
|
|
475
|
+
|
|
476
|
+
- **Copilot CLI plugin manifest** — Root `plugin.json` `author` is now an object (`{ "name": "..." }`) to satisfy Copilot CLI strict validation.
|
|
477
|
+
- **`tf doctor` author check** — Added validation for root `plugin.json` `author` format.
|
|
478
|
+
- **INSTALL.md accuracy** — Cursor and Copilot CLI install instructions now describe the actual working mechanisms.
|
|
479
|
+
|
|
480
|
+
## [0.6.0] - 2026-06-29
|
|
481
|
+
|
|
482
|
+
### Added
|
|
483
|
+
|
|
484
|
+
- **Fast-path workflow modes** — hotfix and tweak modes skip full planning for small changes. Hotfix: ≤2 files, no new modules, minimal contract. Tweak: ≤4 files, config/doc only, direct edit. Auto-upgrade to full when thresholds exceeded.
|
|
485
|
+
- **Phase-drift prevention** — `tf inject` command generates `rules/phase-guard.md` and installs to `.claude/always/` for per-turn Agent context injection. 9 state templates with allowed/forbidden operations. Forms a soft+hard dual defense with guard.mjs.
|
|
486
|
+
- **Decision point protocol** — `docs/decision-points.md` defines 7 standard decision points (DP-1 through DP-7) with triggers, inputs, outputs, and associated skills. All 4 affected skills reference DP numbers.
|
|
487
|
+
- **Guard mode awareness** — `guard.mjs` accepts `--workflow` parameter (full/hotfix/tweak) for mode-specific check skipping. 2 new transitions: `exploring→bridging`, `exploring→approved`.
|
|
488
|
+
- **State set command** — `tf state set <dir> <field> <value>` with SETTABLE_FIELDS whitelist. 14 new decision point audit fields (dp_N_result + dp_N_timestamp).
|
|
489
|
+
|
|
490
|
+
### Changed
|
|
491
|
+
|
|
492
|
+
- **Guard schema-valid** — Uses `validateDeltaSpec` for change specs, fixing a format mismatch between delta spec and main spec validators.
|
|
493
|
+
- **4 skill files** — workflow-orchestrator (mode detection + fast-path routing + DP refs), bridge-contract (hotfix minimal contract), execution-governor (tweak direct edit), closure-archivist (lightweight closure).
|
|
494
|
+
|
|
495
|
+
## [0.5.0] - 2026-06-29
|
|
496
|
+
|
|
497
|
+
### Added
|
|
498
|
+
|
|
499
|
+
- **Guard script system** — `scripts/guard/guard.mjs` provides dimension-based phase transition validation with 5 check dimensions. Exit code ≠ 0 blocks transitions. Reuses existing Validator engine for schema validation.
|
|
500
|
+
- `artifacts-exist` — checks all 4 planning artifacts + specs/ are present and non-empty
|
|
501
|
+
- `schema-valid` — validates proposal.md and all specs/*/spec.md using the Validator engine
|
|
502
|
+
- `contract-fresh` — compares stored artifacts hash against current artifacts for staleness detection
|
|
503
|
+
- `tasks-complete` — verifies all tasks.md items are checked off
|
|
504
|
+
- `tests-passing` — confirms test_result: pass is recorded in state file
|
|
505
|
+
- **Lightweight state file** — `.team-flow.yaml` as a derived cache (12 fields) for fast context recovery. Always rebuildable from artifacts via `tf state rebuild`. Artifacts are the source of truth; state file is a performance optimization.
|
|
506
|
+
- **SHA256 hash acceleration** — `scripts/lib/hash.mjs` computes artifact hashes for O(1) staleness detection. Reduces staleness detection from ~3500 tokens (full content read) to ~50 tokens (single script call).
|
|
507
|
+
- **ssf state CLI** — New `state` subcommand with 5 operations: `init`, `check`, `transition`, `get`, `rebuild`.
|
|
508
|
+
|
|
509
|
+
### Changed
|
|
510
|
+
|
|
511
|
+
- **workflow-orchestrator** — Each routing rule now includes a guard script invocation step before allowing transitions.
|
|
512
|
+
- **bridge-contract** — Automatically runs `tf state init` after contract generation.
|
|
513
|
+
- **closure-archivist** — Runs `tf state transition` after verification completes.
|
|
514
|
+
- **execution-governor** — Updates `batches_completed` in state file after each batch.
|
|
515
|
+
|
|
516
|
+
## [0.4.0] - 2026-06-29
|
|
517
|
+
|
|
518
|
+
### Added
|
|
519
|
+
|
|
520
|
+
- **CLI toolchain** — `tf` command with 6 subcommands: `list` (scan changes and report status), `validate` (artifact validation via Validator), `doctor` (health check: version sync, hooks, skills, dist, node, docs, config), `version` (one-command version sync to all manifests), `sync` (delta spec merge with conflict detection), `config` (display/modify configuration). Zero dependencies via `node:util.parseArgs`.
|
|
521
|
+
- **Configuration system** — Optional `team-flow.config.json` for customizing artifact order, skip list, execution thresholds, and verification language. Absence = v0.3.0 defaults. Deep-merge with built-in defaults. Skills query config at runtime via `scripts/get-config` bash helper.
|
|
522
|
+
- **Multi-language tokenizer** — `src/validation/tokenizer.ts` with English stemmer (extracted from validator) + Chinese CJK tokenizer (Unicode ranges + 2-5 char sliding window + stop words). Auto-detection based on CJK character ratio. Mixed mode runs both tokenizers and unions results.
|
|
523
|
+
- **Conflict detection** — `Validator.detectSyncConflicts()` detects when multiple changes modify the same requirement across unsynced delta specs. Integrated into `tf sync` command and `spec-syncer` skill pre-flight check.
|
|
524
|
+
- **git worktree isolation** — execution-governor now recommends worktree creation when executing on main/master branch. Pure SKILL.md guidance, no code changes.
|
|
525
|
+
|
|
526
|
+
### Changed
|
|
527
|
+
|
|
528
|
+
- **package.json** — Added `bin` field exposing `tf` and `team-flow` commands.
|
|
529
|
+
- **validateImplementation()** — Refactored to use `tokenize()` instead of inline `stem()`. Added optional `config` parameter for language override (`'auto' | 'en' | 'zh'`). Backward compatible — existing callers work unchanged.
|
|
530
|
+
- **Tokenizer refinements** — CJK sliding window extended to 2-5 chars (covers compound words like "令牌桶算法"). English min token length lowered to 3 (preserves short tokens like "jwt"). Added "based"/"using"/"used" to English stop words.
|
|
531
|
+
- **Version manifests** — `.cursor-plugin/plugin.json` and `gemini-extension.json` now tracked in version sync (previously lagging at 0.2.0 and 0.1.0).
|
|
532
|
+
|
|
533
|
+
### Fixed
|
|
534
|
+
|
|
535
|
+
- **Version consistency** — `tf version` command ensures all 5 manifest files stay in sync. `tf doctor` reports inconsistencies as warnings.
|
|
536
|
+
|
|
537
|
+
## [0.3.0] - 2026-06-27
|
|
538
|
+
|
|
539
|
+
### Added
|
|
540
|
+
|
|
541
|
+
- **Inline execution mode** — Lightweight single-session execution for small changes (≤ 3 tasks, no cross-module dependencies). Parallel to SDD subagent mode. Preserves TDD Iron Law with checkpoint review per task. Automatic mode selection with user override.
|
|
542
|
+
- **Abandoned terminal state** — 8th workflow state allowing graceful change abandonment from any non-terminal state. Generates `abandonment-summary.md` with reason, lessons learned, and recommendations. Blocks delta spec merge for abandoned changes. Partial code preservation supported.
|
|
543
|
+
- **Three-dimensional verification** — closure-archivist now verifies Completeness (all tasks/requirements implemented), Correctness (tests pass, no placeholders), and Coherence (design decisions reflected in code). New `Validator.validateImplementation()` API with word-stemming and keyword matching.
|
|
544
|
+
- **abandonment-summary.md template** — Structured template for documenting abandoned changes.
|
|
545
|
+
- **Verification types** — New exports: `VerificationDimension`, `VerificationStatus`, `VerificationFinding`, `VerificationReport`.
|
|
546
|
+
|
|
547
|
+
### Changed
|
|
548
|
+
|
|
549
|
+
- **spec-forger task planning** — Rewritten with writing-plans methodology: File Structure section, Interfaces block (Consumes/Produces), per-task TDD expansion (5 phases), exact file paths with line ranges, zero placeholder enforcement, 2-5 minute granularity per step.
|
|
550
|
+
- **execution-contract.md template** — Added Execution Mode (SDD | Inline) selection field and Verification Dimensions table.
|
|
551
|
+
- **tasks.md template** — Added File Structure and Interfaces sections for cross-batch dependency tracking.
|
|
552
|
+
- **State machine** — Extended from 7 to 8 states (+abandoned terminal state). Universal abandoned transition from any non-terminal state.
|
|
553
|
+
- **Validator engine** — New `validateImplementation(diffSummary, specContent, designContent)` method with three-dimensional `VerificationReport` return type. Word-stemming for Completeness matching, keyword-based Coherence checking.
|
|
554
|
+
- **closure-archivist** — Verification steps expanded from 3 to 5 (Correctness, Completeness, Coherence, Unintended Scope Detection, Verification Report). Structured output with PASS/CONDITIONAL/FAIL verdict.
|
|
555
|
+
- **spec-syncer** — Pre-flight guard blocks sync for abandoned changes.
|
|
556
|
+
|
|
557
|
+
## [0.2.1] - 2026-06-27
|
|
558
|
+
|
|
559
|
+
### Fixed
|
|
560
|
+
|
|
561
|
+
- **hooks.json format** — Changed from incorrect array format to Claude Code plugin record format. Event name corrected from `Startup|Clear|Compact` to standard `SessionStart`. Command path now uses `${CLAUDE_PLUGIN_ROOT}` environment variable for cross-platform compatibility.
|
|
562
|
+
|
|
563
|
+
## [0.2.0] - 2026-06-26
|
|
564
|
+
|
|
565
|
+
### Added
|
|
566
|
+
|
|
567
|
+
- **Engine layer (`src/`)** — embedded OpenSpec schema/validation/parsing engine in TypeScript
|
|
568
|
+
- `src/schema/` — Requirement, Delta (ADDED/MODIFIED/REMOVED/RENAMED), Spec, Change type definitions
|
|
569
|
+
- `src/validation/` — Validator class with validateSpecContent, validateChangeContent, validateDeltaSpec
|
|
570
|
+
- `src/parsing/` — Requirement block parser + Delta spec parser (self-contained, no external deps)
|
|
571
|
+
- **3 new skills** (6 → 9 total):
|
|
572
|
+
- `systematic-debugger` — 4-phase root cause debugging (Root Cause → Pattern → Hypothesis → Implementation)
|
|
573
|
+
- `code-reviewer` — Unified code review (request + receive), 3 severity levels (Critical/Important/Minor)
|
|
574
|
+
- `spec-syncer` — Delta Spec → Main Spec intelligent merge with conflict detection
|
|
575
|
+
- **SDD (Subagent-Driven Development)** — Full implementation discipline embedded in `execution-governor`:
|
|
576
|
+
- `implementer-prompt.md` — Subagent implementation template with TDD evidence + self-review
|
|
577
|
+
- `task-reviewer-prompt.md` — Dual-verdict review (spec compliance + code quality)
|
|
578
|
+
- `code-reviewer-prompt.md` — Structured code review template
|
|
579
|
+
- **Helper scripts (`scripts/`)** — `task-brief`, `review-package`, `validate-artifacts`
|
|
580
|
+
- **Session-start hooks (`hooks/`)** — Multi-platform bootstrap (Claude Code / Cursor / Copilot CLI)
|
|
581
|
+
- **Content-level stale detection** — `workflow-orchestrator` now compares proposal scope vs contract intent lock
|
|
582
|
+
|
|
583
|
+
### Changed
|
|
584
|
+
|
|
585
|
+
- State machine extended from 6 to 7 states (+`debugging`)
|
|
586
|
+
- All 6 existing skills enhanced with embedded engine capabilities:
|
|
587
|
+
- `spec-explorer` — embedded brainstorming's "one question at a time + 2-3 approach comparison"
|
|
588
|
+
- `spec-forger` — Schema engine validation on every artifact + writing-plans task granularity
|
|
589
|
+
- `bridge-contract` — parsing engine auto-extraction of contract fields
|
|
590
|
+
- `execution-governor` — Full TDD Iron Law + SDD workflow + Review Gates
|
|
591
|
+
- `closure-archivist` — verification-before-completion Iron Law
|
|
592
|
+
- `workflow-orchestrator` — content-level inspection + 3 new routing targets
|
|
593
|
+
- Plugin metadata updated to v0.2.0 with expanded keywords across all manifest files
|
|
594
|
+
|
|
595
|
+
### Release Quality
|
|
596
|
+
|
|
597
|
+
- **TypeScript compilation** — Added `tsconfig.json` (ES2022, NodeNext, strict mode), `npm run build` produces `dist/` with declarations
|
|
598
|
+
- **Integration tests** — 8 test cases using real example artifacts (`docs/examples/`), `npm test` passes
|
|
599
|
+
- **package.json** — `main` points to `dist/index.js`, `types` to `dist/index.d.ts`
|
|
600
|
+
- **Documentation** — Updated English README Current Status to v0.2.0
|
|
601
|
+
|
|
602
|
+
## [0.1.0] - 2026-06-25
|
|
603
|
+
|
|
604
|
+
### Added
|
|
605
|
+
|
|
606
|
+
- Initial self-contained `team-flow` plugin structure
|
|
607
|
+
- Plugin metadata in `.claude-plugin/plugin.json`
|
|
608
|
+
- Six workflow skills:
|
|
609
|
+
- `workflow-orchestrator`
|
|
610
|
+
- `spec-explorer`
|
|
611
|
+
- `spec-forger`
|
|
612
|
+
- `bridge-contract`
|
|
613
|
+
- `execution-governor`
|
|
614
|
+
- `closure-archivist`
|
|
615
|
+
- Planning templates:
|
|
616
|
+
- `proposal.md`
|
|
617
|
+
- `spec.md`
|
|
618
|
+
- `design.md`
|
|
619
|
+
- `tasks.md`
|
|
620
|
+
- `execution-contract.md`
|
|
621
|
+
- Workflow docs:
|
|
622
|
+
- `docs/artifact-contract.md`
|
|
623
|
+
- `docs/state-machine.md`
|
|
624
|
+
- Example change sets:
|
|
625
|
+
- `docs/examples/add-dark-mode/` (net-new UI capability)
|
|
626
|
+
- `docs/examples/refactor-auth-boundary/` (brownfield backend refactor)
|
|
627
|
+
- Installation guide in `INSTALL.md`
|
|
628
|
+
- Chinese publishing README in `README.zh-CN.md`
|
|
629
|
+
- Repository governance files: `.gitignore`, `CONTRIBUTING.md`, `docs/release-checklist.md`
|
|
630
|
+
|
|
631
|
+
### Notes
|
|
632
|
+
|
|
633
|
+
- First release targets Claude Code and Trae style local skill loading
|
|
634
|
+
- Runtime ownership remains inside `team-flow`
|
|
635
|
+
- OpenSpec and Superpowers are reference influences, not runtime dependencies
|