self-evolving-workflow 0.0.0-stage → 0.1.4
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/LICENSE +27 -0
- package/README.md +195 -2
- package/dist/agent-memory-prompts.d.ts +13 -0
- package/dist/agent-memory-prompts.js +55 -0
- package/dist/cli.d.ts +2 -0
- package/dist/cli.js +6 -0
- package/dist/closeout.d.ts +105 -0
- package/dist/closeout.js +473 -0
- package/dist/code.d.ts +39 -0
- package/dist/code.js +124 -0
- package/dist/codex-memory.d.ts +24 -0
- package/dist/codex-memory.js +217 -0
- package/dist/common.d.ts +16 -0
- package/dist/common.js +52 -0
- package/dist/context-envelope.d.ts +59 -0
- package/dist/context-envelope.js +23 -0
- package/dist/host-adapters.d.ts +34 -0
- package/dist/host-adapters.js +151 -0
- package/dist/http.d.ts +3 -0
- package/dist/http.js +90 -0
- package/dist/index.d.ts +16 -0
- package/dist/index.js +13 -0
- package/dist/knowledge-cli.d.ts +198 -0
- package/dist/knowledge-cli.js +761 -0
- package/dist/knowledge-reads.d.ts +72 -0
- package/dist/knowledge-reads.js +201 -0
- package/dist/memory-config.d.ts +44 -0
- package/dist/memory-config.js +204 -0
- package/dist/memory-evidence.d.ts +13 -0
- package/dist/memory-evidence.js +40 -0
- package/dist/memory-history.d.ts +46 -0
- package/dist/memory-history.js +432 -0
- package/dist/memory.d.ts +96 -0
- package/dist/memory.js +362 -0
- package/dist/retrospective.d.ts +57 -0
- package/dist/retrospective.js +240 -0
- package/dist/search.d.ts +36 -0
- package/dist/search.js +112 -0
- package/dist/skill-addition.d.ts +25 -0
- package/dist/skill-addition.js +89 -0
- package/dist/skill-design.d.ts +96 -0
- package/dist/skill-design.js +226 -0
- package/dist/skill-replay.d.ts +55 -0
- package/dist/skill-replay.js +448 -0
- package/dist/skill-route.d.ts +30 -0
- package/dist/skill-route.js +75 -0
- package/dist/transcript-evidence.d.ts +3 -0
- package/dist/transcript-evidence.js +58 -0
- package/dist/upstream/chunker.d.ts +24 -0
- package/dist/upstream/chunker.js +96 -0
- package/dist/upstream/file-protocol.d.ts +45 -0
- package/dist/upstream/file-protocol.js +117 -0
- package/dist/upstream/frontmatter.d.ts +47 -0
- package/dist/upstream/frontmatter.js +86 -0
- package/dist/upstream/graph-search.d.ts +33 -0
- package/dist/upstream/graph-search.js +67 -0
- package/dist/upstream/l1-extraction.d.ts +26 -0
- package/dist/upstream/l1-extraction.js +405 -0
- package/dist/upstream/llm.d.ts +8 -0
- package/dist/upstream/llm.js +1 -0
- package/dist/upstream/merge.d.ts +50 -0
- package/dist/upstream/merge.js +153 -0
- package/dist/upstream/prompts.d.ts +53 -0
- package/dist/upstream/prompts.js +181 -0
- package/dist/upstream/search-utils.d.ts +34 -0
- package/dist/upstream/search-utils.js +55 -0
- package/dist/upstream/slug.d.ts +26 -0
- package/dist/upstream/slug.js +103 -0
- package/dist/upstream/template.d.ts +29 -0
- package/dist/upstream/template.js +80 -0
- package/dist/upstream/tokenize.d.ts +4 -0
- package/dist/upstream/tokenize.js +29 -0
- package/dist/wiki-change.d.ts +76 -0
- package/dist/wiki-change.js +299 -0
- package/dist/wiki-entry.d.ts +26 -0
- package/dist/wiki-entry.js +93 -0
- package/dist/wiki-ingest.d.ts +12 -0
- package/dist/wiki-ingest.js +126 -0
- package/dist/wiki-migration.d.ts +16 -0
- package/dist/wiki-migration.js +268 -0
- package/dist/wiki-tokens.d.ts +1 -0
- package/dist/wiki-tokens.js +46 -0
- package/dist/wiki.d.ts +103 -0
- package/dist/wiki.js +330 -0
- package/dist/workflow-cli.d.ts +2 -0
- package/dist/workflow-cli.js +319 -0
- package/dist/workflow-install.d.ts +37 -0
- package/dist/workflow-install.js +148 -0
- package/dist/workflow-knowledge.d.ts +18 -0
- package/dist/workflow-knowledge.js +32 -0
- package/dist/workflow-mcp.d.ts +2 -0
- package/dist/workflow-mcp.js +137 -0
- package/dist/workflow-names.d.ts +4 -0
- package/dist/workflow-names.js +31 -0
- package/dist/workflow-runtime.d.ts +735 -0
- package/dist/workflow-runtime.js +747 -0
- package/dist/workflow-skills.d.ts +48 -0
- package/dist/workflow-skills.js +141 -0
- package/docs/images/impeccable-skill.png +0 -0
- package/docs/images/workflow-overview.png +0 -0
- package/docs/images/workflow-skills.png +0 -0
- package/package.json +77 -4
- package/skills/ew-impeccable/LICENSE +191 -0
- package/skills/ew-impeccable/NOTICE.md +19 -0
- package/skills/ew-impeccable/SKILL.md +91 -0
- package/skills/ew-impeccable/UPSTREAM.md +23 -0
- package/skills/ew-impeccable/reference/adapt.md +314 -0
- package/skills/ew-impeccable/reference/adapt.native.md +60 -0
- package/skills/ew-impeccable/reference/android.md +46 -0
- package/skills/ew-impeccable/reference/animate.md +91 -0
- package/skills/ew-impeccable/reference/audit.md +138 -0
- package/skills/ew-impeccable/reference/audit.native.md +141 -0
- package/skills/ew-impeccable/reference/bolder.md +35 -0
- package/skills/ew-impeccable/reference/clarify.md +96 -0
- package/skills/ew-impeccable/reference/colorize.md +88 -0
- package/skills/ew-impeccable/reference/craft-floor.md +44 -0
- package/skills/ew-impeccable/reference/craft.md +5 -0
- package/skills/ew-impeccable/reference/critique.md +808 -0
- package/skills/ew-impeccable/reference/degraded/asset-producer.md +36 -0
- package/skills/ew-impeccable/reference/degraded/documenter.md +23 -0
- package/skills/ew-impeccable/reference/degraded/finish-reviewer.md +72 -0
- package/skills/ew-impeccable/reference/degraded/manual-edit-applier.md +91 -0
- package/skills/ew-impeccable/reference/delight.md +72 -0
- package/skills/ew-impeccable/reference/distill.md +113 -0
- package/skills/ew-impeccable/reference/doctor.md +56 -0
- package/skills/ew-impeccable/reference/document.md +418 -0
- package/skills/ew-impeccable/reference/extract.md +68 -0
- package/skills/ew-impeccable/reference/harden.md +338 -0
- package/skills/ew-impeccable/reference/hooks.md +113 -0
- package/skills/ew-impeccable/reference/init.md +133 -0
- package/skills/ew-impeccable/reference/ios.md +51 -0
- package/skills/ew-impeccable/reference/layout.md +86 -0
- package/skills/ew-impeccable/reference/live-setup.md +102 -0
- package/skills/ew-impeccable/reference/live.md +326 -0
- package/skills/ew-impeccable/reference/new-work.md +209 -0
- package/skills/ew-impeccable/reference/onboard.md +236 -0
- package/skills/ew-impeccable/reference/operate.md +61 -0
- package/skills/ew-impeccable/reference/optimize.md +260 -0
- package/skills/ew-impeccable/reference/overdrive.md +127 -0
- package/skills/ew-impeccable/reference/polish.md +105 -0
- package/skills/ew-impeccable/reference/quieter.md +101 -0
- package/skills/ew-impeccable/reference/routing.md +20 -0
- package/skills/ew-impeccable/reference/shape.md +59 -0
- package/skills/ew-impeccable/reference/typeset.md +82 -0
- package/skills/ew-impeccable/reference/visualize.md +46 -0
- package/skills/ew-impeccable/scripts/build-phase.mjs +1022 -0
- package/skills/ew-impeccable/scripts/command-metadata.json +94 -0
- package/skills/ew-impeccable/scripts/comp-diff.mjs +391 -0
- package/skills/ew-impeccable/scripts/comp-spec.mjs +513 -0
- package/skills/ew-impeccable/scripts/concept-seed.mjs +814 -0
- package/skills/ew-impeccable/scripts/context-signals.mjs +325 -0
- package/skills/ew-impeccable/scripts/context.mjs +1521 -0
- package/skills/ew-impeccable/scripts/critique-storage.mjs +473 -0
- package/skills/ew-impeccable/scripts/data/font-index-failures.json +121 -0
- package/skills/ew-impeccable/scripts/data/font-index.json +1 -0
- package/skills/ew-impeccable/scripts/detect-csp.mjs +246 -0
- package/skills/ew-impeccable/scripts/detect.mjs +30 -0
- package/skills/ew-impeccable/scripts/detector/browser/injected/index.mjs +2580 -0
- package/skills/ew-impeccable/scripts/detector/cli/main.mjs +498 -0
- package/skills/ew-impeccable/scripts/detector/design-system.mjs +1311 -0
- package/skills/ew-impeccable/scripts/detector/detect-antipatterns-browser.js +9486 -0
- package/skills/ew-impeccable/scripts/detector/detect-antipatterns.mjs +51 -0
- package/skills/ew-impeccable/scripts/detector/engines/browser/detect-url.mjs +434 -0
- package/skills/ew-impeccable/scripts/detector/engines/regex/detect-text.mjs +1439 -0
- package/skills/ew-impeccable/scripts/detector/engines/static-html/css-cascade.mjs +1242 -0
- package/skills/ew-impeccable/scripts/detector/engines/static-html/detect-html.mjs +263 -0
- package/skills/ew-impeccable/scripts/detector/engines/visual/screenshot-contrast.mjs +189 -0
- package/skills/ew-impeccable/scripts/detector/findings.mjs +23 -0
- package/skills/ew-impeccable/scripts/detector/node/file-system.mjs +225 -0
- package/skills/ew-impeccable/scripts/detector/profile/profiler.mjs +166 -0
- package/skills/ew-impeccable/scripts/detector/registry/antipatterns.mjs +636 -0
- package/skills/ew-impeccable/scripts/detector/rules/checks.mjs +5750 -0
- package/skills/ew-impeccable/scripts/detector/shared/color.mjs +596 -0
- package/skills/ew-impeccable/scripts/detector/shared/constants.mjs +127 -0
- package/skills/ew-impeccable/scripts/detector/shared/fonts.mjs +30 -0
- package/skills/ew-impeccable/scripts/detector/shared/inline-ignores.mjs +148 -0
- package/skills/ew-impeccable/scripts/detector/shared/page.mjs +7 -0
- package/skills/ew-impeccable/scripts/detector/vendor/MDN-DATA-LICENSE +116 -0
- package/skills/ew-impeccable/scripts/detector/vendor/THIRD_PARTY_LICENSES.md +227 -0
- package/skills/ew-impeccable/scripts/detector/vendor/static-html-parser.build-entry.txt +11 -0
- package/skills/ew-impeccable/scripts/detector/vendor/static-html-parser.bundle.mjs +9121 -0
- package/skills/ew-impeccable/scripts/doctor.mjs +330 -0
- package/skills/ew-impeccable/scripts/embed-prompt.mjs +166 -0
- package/skills/ew-impeccable/scripts/font-match.mjs +457 -0
- package/skills/ew-impeccable/scripts/generate-image.mjs +447 -0
- package/skills/ew-impeccable/scripts/hook-admin.mjs +829 -0
- package/skills/ew-impeccable/scripts/hook-before-edit.mjs +538 -0
- package/skills/ew-impeccable/scripts/hook-lib.mjs +2493 -0
- package/skills/ew-impeccable/scripts/hook.mjs +79 -0
- package/skills/ew-impeccable/scripts/lib/artifact-schema.mjs +93 -0
- package/skills/ew-impeccable/scripts/lib/composition-catalog.mjs +200 -0
- package/skills/ew-impeccable/scripts/lib/concept-catalog.mjs +395 -0
- package/skills/ew-impeccable/scripts/lib/design-parser.mjs +880 -0
- package/skills/ew-impeccable/scripts/lib/font-fingerprint.mjs +564 -0
- package/skills/ew-impeccable/scripts/lib/font-index.mjs +130 -0
- package/skills/ew-impeccable/scripts/lib/hero-checks.mjs +246 -0
- package/skills/ew-impeccable/scripts/lib/image-metrics.mjs +306 -0
- package/skills/ew-impeccable/scripts/lib/impeccable-config.mjs +640 -0
- package/skills/ew-impeccable/scripts/lib/impeccable-paths.mjs +137 -0
- package/skills/ew-impeccable/scripts/lib/is-generated.mjs +72 -0
- package/skills/ew-impeccable/scripts/lib/live-path-globs.mjs +37 -0
- package/skills/ew-impeccable/scripts/lib/open-system-browser.mjs +26 -0
- package/skills/ew-impeccable/scripts/lib/png.mjs +281 -0
- package/skills/ew-impeccable/scripts/lib/provider.mjs +5 -0
- package/skills/ew-impeccable/scripts/lib/raster.mjs +194 -0
- package/skills/ew-impeccable/scripts/lib/roll-selection.mjs +369 -0
- package/skills/ew-impeccable/scripts/lib/staleness-deep.mjs +491 -0
- package/skills/ew-impeccable/scripts/lib/staleness-notice.mjs +169 -0
- package/skills/ew-impeccable/scripts/lib/staleness.mjs +532 -0
- package/skills/ew-impeccable/scripts/lib/surface-briefs.mjs +149 -0
- package/skills/ew-impeccable/scripts/lib/target-args.mjs +42 -0
- package/skills/ew-impeccable/scripts/lib/target-slug.mjs +33 -0
- package/skills/ew-impeccable/scripts/lib/template-extensions.mjs +146 -0
- package/skills/ew-impeccable/scripts/live/accept-css.mjs +617 -0
- package/skills/ew-impeccable/scripts/live/accept-verify.mjs +60 -0
- package/skills/ew-impeccable/scripts/live/browser-script-parts.mjs +84 -0
- package/skills/ew-impeccable/scripts/live/completion.mjs +28 -0
- package/skills/ew-impeccable/scripts/live/event-validation.mjs +199 -0
- package/skills/ew-impeccable/scripts/live/frameworks/astro.mjs +47 -0
- package/skills/ew-impeccable/scripts/live/frameworks/detect-utils.mjs +73 -0
- package/skills/ew-impeccable/scripts/live/frameworks/index.mjs +143 -0
- package/skills/ew-impeccable/scripts/live/frameworks/journal.mjs +197 -0
- package/skills/ew-impeccable/scripts/live/frameworks/nextjs.mjs +49 -0
- package/skills/ew-impeccable/scripts/live/frameworks/nuxt.mjs +161 -0
- package/skills/ew-impeccable/scripts/live/frameworks/script-src.mjs +17 -0
- package/skills/ew-impeccable/scripts/live/frameworks/static-html.mjs +26 -0
- package/skills/ew-impeccable/scripts/live/frameworks/sveltekit.mjs +71 -0
- package/skills/ew-impeccable/scripts/live/frameworks/tag-strategy.mjs +247 -0
- package/skills/ew-impeccable/scripts/live/frameworks/tanstack-start.mjs +70 -0
- package/skills/ew-impeccable/scripts/live/frameworks/vite-generic.mjs +42 -0
- package/skills/ew-impeccable/scripts/live/generation-preflight.mjs +149 -0
- package/skills/ew-impeccable/scripts/live/insert-ui.mjs +458 -0
- package/skills/ew-impeccable/scripts/live/instructions.mjs +142 -0
- package/skills/ew-impeccable/scripts/live/manual-apply.mjs +939 -0
- package/skills/ew-impeccable/scripts/live/manual-edit-routes.mjs +357 -0
- package/skills/ew-impeccable/scripts/live/manual-edits-buffer.mjs +152 -0
- package/skills/ew-impeccable/scripts/live/poll-lanes.mjs +14 -0
- package/skills/ew-impeccable/scripts/live/project-ignores.mjs +139 -0
- package/skills/ew-impeccable/scripts/live/roots.mjs +508 -0
- package/skills/ew-impeccable/scripts/live/session-store.mjs +563 -0
- package/skills/ew-impeccable/scripts/live/source-lock.mjs +105 -0
- package/skills/ew-impeccable/scripts/live/source-search.mjs +105 -0
- package/skills/ew-impeccable/scripts/live/svelte-ast.mjs +969 -0
- package/skills/ew-impeccable/scripts/live/svelte-component.mjs +1366 -0
- package/skills/ew-impeccable/scripts/live/sveltekit-adapter.mjs +304 -0
- package/skills/ew-impeccable/scripts/live/tanstack-adapter.mjs +259 -0
- package/skills/ew-impeccable/scripts/live/ui-surfaces.mjs +75 -0
- package/skills/ew-impeccable/scripts/live/vocabulary.mjs +171 -0
- package/skills/ew-impeccable/scripts/live-accept.mjs +938 -0
- package/skills/ew-impeccable/scripts/live-browser-dom.js +167 -0
- package/skills/ew-impeccable/scripts/live-browser-ignores.js +242 -0
- package/skills/ew-impeccable/scripts/live-browser-session.js +144 -0
- package/skills/ew-impeccable/scripts/live-browser.js +12851 -0
- package/skills/ew-impeccable/scripts/live-commit-manual-edits.mjs +1200 -0
- package/skills/ew-impeccable/scripts/live-complete.mjs +107 -0
- package/skills/ew-impeccable/scripts/live-copy-edit-agent.mjs +800 -0
- package/skills/ew-impeccable/scripts/live-discard-manual-edits.mjs +51 -0
- package/skills/ew-impeccable/scripts/live-inject.mjs +463 -0
- package/skills/ew-impeccable/scripts/live-insert.mjs +292 -0
- package/skills/ew-impeccable/scripts/live-manual-edit-evidence.mjs +368 -0
- package/skills/ew-impeccable/scripts/live-poll.mjs +430 -0
- package/skills/ew-impeccable/scripts/live-resume.mjs +123 -0
- package/skills/ew-impeccable/scripts/live-server.mjs +1698 -0
- package/skills/ew-impeccable/scripts/live-status.mjs +71 -0
- package/skills/ew-impeccable/scripts/live-target.mjs +30 -0
- package/skills/ew-impeccable/scripts/live-wrap.mjs +927 -0
- package/skills/ew-impeccable/scripts/live.mjs +334 -0
- package/skills/ew-impeccable/scripts/modern-screenshot.umd.js +14 -0
- package/skills/ew-impeccable/scripts/palette.mjs +628 -0
- package/skills/ew-impeccable/scripts/pin.mjs +352 -0
- package/skills/ew-impeccable/scripts/serve-question.mjs +1783 -0
- package/skills/ew-impeccable/scripts/surface-brief.mjs +74 -0
- package/skills/ew-knowledge/SKILL.md +35 -0
- package/skills/ew-knowledge/references/closeout-protocol.md +68 -0
- package/skills/ew-knowledge/references/knowledge-route.md +73 -0
- package/skills/ew-knowledge/references/wiki-maintenance.md +27 -0
- package/skills/ew-odyssey/SKILL.md +106 -0
- package/skills/ew-odyssey/references/audit-artifacts.md +7 -0
- package/skills/ew-odyssey/references/odyssey-base.md +104 -0
- package/skills/ew-odyssey/references/odyssey-debug.md +264 -0
- package/skills/ew-odyssey/references/odyssey-defensive.md +351 -0
- package/skills/ew-odyssey/references/odyssey-improve.md +230 -0
- package/skills/ew-odyssey/references/odyssey-planex.md +294 -0
- package/skills/ew-odyssey/references/odyssey-review.md +233 -0
- package/skills/ew-odyssey/references/odyssey-security.md +231 -0
- package/skills/ew-odyssey/references/odyssey-ui.md +232 -0
- package/skills/ew-odyssey/references/prepare/odyssey-debug.md +102 -0
- package/skills/ew-odyssey/references/prepare/odyssey-defensive.md +117 -0
- package/skills/ew-odyssey/references/prepare/odyssey-improve.md +95 -0
- package/skills/ew-odyssey/references/prepare/odyssey-planex.md +105 -0
- package/skills/ew-odyssey/references/prepare/odyssey-review.md +105 -0
- package/skills/ew-odyssey/references/prepare/odyssey-security.md +91 -0
- package/skills/ew-odyssey/references/prepare/odyssey-ui.md +88 -0
- package/skills/ew-odyssey/references/runtime-adapters.md +31 -0
- package/skills/ew-orchestrate/SKILL.md +89 -0
- package/skills/ew-orchestrate/references/auto-policy.md +66 -0
- package/skills/ew-orchestrate/references/boundary-grill.md +51 -0
- package/skills/ew-orchestrate/references/companion-route.md +40 -0
- package/skills/ew-orchestrate/references/ew-orchestrate.md +44 -0
- package/skills/ew-orchestrate/references/goal.md +51 -0
- package/skills/ew-orchestrate/references/orchestrator-run-loop.md +33 -0
- package/skills/ew-orchestrate/references/planning.md +54 -0
- package/skills/ew-orchestrate/steps/ew-analyze/SKILL.md +70 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/issue-gaps-analyze.md +24 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/prepare.md +8 -0
- package/skills/ew-orchestrate/steps/ew-analyze/references/workflow.md +138 -0
- package/skills/ew-orchestrate/steps/ew-auto-test/SKILL.md +80 -0
- package/skills/ew-orchestrate/steps/ew-auto-test/references/prepare.md +23 -0
- package/skills/ew-orchestrate/steps/ew-auto-test/references/workflow.md +31 -0
- package/skills/ew-orchestrate/steps/ew-blueprint/SKILL.md +122 -0
- package/skills/ew-orchestrate/steps/ew-blueprint/references/prepare.md +21 -0
- package/skills/ew-orchestrate/steps/ew-blueprint/references/workflow.md +28 -0
- package/skills/ew-orchestrate/steps/ew-brainstorm/SKILL.md +49 -0
- package/skills/ew-orchestrate/steps/ew-companion/SKILL.md +50 -0
- package/skills/ew-orchestrate/steps/ew-debug/SKILL.md +85 -0
- package/skills/ew-orchestrate/steps/ew-debug/references/prepare.md +27 -0
- package/skills/ew-orchestrate/steps/ew-debug/references/workflow.md +31 -0
- package/skills/ew-orchestrate/steps/ew-execute/SKILL.md +74 -0
- package/skills/ew-orchestrate/steps/ew-execute/references/prepare.md +27 -0
- package/skills/ew-orchestrate/steps/ew-execute/references/workflow.md +87 -0
- package/skills/ew-orchestrate/steps/ew-grill/SKILL.md +62 -0
- package/skills/ew-orchestrate/steps/ew-grill/references/prepare.md +26 -0
- package/skills/ew-orchestrate/steps/ew-grill/references/workflow.md +31 -0
- package/skills/ew-orchestrate/steps/ew-init/SKILL.md +56 -0
- package/skills/ew-orchestrate/steps/ew-init/references/prepare.md +25 -0
- package/skills/ew-orchestrate/steps/ew-init/references/workflow.md +28 -0
- package/skills/ew-orchestrate/steps/ew-plan/SKILL.md +131 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/prepare.md +8 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/tdd.md +53 -0
- package/skills/ew-orchestrate/steps/ew-plan/references/workflow.md +100 -0
- package/skills/ew-orchestrate/steps/ew-retrospective/SKILL.md +68 -0
- package/skills/ew-orchestrate/steps/ew-retrospective/references/prepare.md +18 -0
- package/skills/ew-orchestrate/steps/ew-retrospective/references/workflow.md +34 -0
- package/skills/ew-orchestrate/steps/ew-review/SKILL.md +45 -0
- package/skills/ew-orchestrate/steps/ew-review/references/prepare.md +17 -0
- package/skills/ew-orchestrate/steps/ew-review/references/workflow.md +116 -0
- package/skills/ew-orchestrate/steps/ew-roadmap/SKILL.md +62 -0
- package/skills/ew-orchestrate/steps/ew-roadmap/references/prepare.md +27 -0
- package/skills/ew-orchestrate/steps/ew-roadmap/references/workflow.md +28 -0
- package/skills/ew-orchestrate/steps/ew-test/SKILL.md +99 -0
- package/skills/ew-orchestrate/steps/ew-test/references/prepare.md +23 -0
- package/skills/ew-orchestrate/steps/ew-test/references/workflow.md +23 -0
- package/skills/ew-orchestrate/steps/ew-verify/SKILL.md +73 -0
- package/skills/ew-orchestrate/steps/ew-verify/references/prepare.md +21 -0
- package/skills/ew-orchestrate/steps/ew-verify/references/workflow.md +29 -0
- package/skills/ew-skill-design/SKILL.md +30 -0
- package/skills/ew-skill-design/references/package-contract.md +40 -0
- package/skills/ew-skill-design/references/validation.md +21 -0
- package/skills/team-swarm/SKILL.md +68 -0
- package/skills/team-swarm/references/mcp-coordination.md +14 -0
- package/skills/team-swarm/roles/analyst/role.md +181 -0
- package/skills/team-swarm/roles/ant/role.md +149 -0
- package/skills/team-swarm/roles/coordinator/commands/converge.md +112 -0
- package/skills/team-swarm/roles/coordinator/commands/init-swarm.md +136 -0
- package/skills/team-swarm/roles/coordinator/commands/iterate.md +171 -0
- package/skills/team-swarm/roles/coordinator/role.md +170 -0
- package/skills/team-swarm/roles/scorer/role.md +150 -0
- package/skills/team-swarm/scripts/aco.py +646 -0
- package/skills/team-swarm/scripts/pheromone.py +144 -0
- package/skills/team-swarm/scripts/scoring.py +111 -0
- package/skills/team-swarm/scripts/test_aco.py +606 -0
- package/skills/team-swarm/specs/ant-output-schema.md +127 -0
- package/skills/team-swarm/specs/convergence-criteria.md +108 -0
- package/skills/team-swarm/specs/pheromone-schema.md +125 -0
- package/skills/team-swarm/specs/swarm-config-template.json +71 -0
- package/skills/team-swarm/specs/swarm-protocol.md +119 -0
- package/skills/workflow-evolve/SKILL.md +64 -0
- package/skills/workflow-evolve/references/agy-gate.md +27 -0
- package/skills/workflow-evolve/references/auto-loop.md +23 -0
- package/skills/workflow-evolve/references/history-review.md +15 -0
- package/skills/workflow-evolve/scripts/codex-memory-replay.mjs +86 -0
- package/skills/workflow-evolve/scripts/codex-replay.mjs +1 -0
- package/skills/workflow-evolve/scripts/evolve-loop.mjs +260 -0
- package/skills/workflow-evolve/scripts/memory-codex-mcp.mjs +124 -0
- package/workflows/index.json +33 -0
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
# Workflow: Execute
|
|
2
|
+
|
|
3
|
+
Wave-based parallel execution with checkpoint resume, optional atomic commits (`--auto-commit`), and a scoped smoke self-check handing off to `ew-review`.
|
|
4
|
+
|
|
5
|
+
## Iron Law
|
|
6
|
+
|
|
7
|
+
Never mark a task completed without running its convergence criteria, verifying outputs match the task definition, and recording reproducible evidence.
|
|
8
|
+
|
|
9
|
+
---
|
|
10
|
+
|
|
11
|
+
## Step 0: Plan Availability & Degradation Routing
|
|
12
|
+
|
|
13
|
+
Resolve `current-plan` via the Run packet's `upstream_aliases`:
|
|
14
|
+
- **Plan present**: proceed to Step 1.
|
|
15
|
+
- **Plan absent**: follow the Degradation Routing table in [preparation](prepare.md). Use `evolve run cancel` or `evolve run transition <run_id> blocked` with `--session`, `--actor`, `--expected-orchestration-revision`, and `--expected-run-revision`, documenting reason, available upstream, and target command in `report.md` `next`/`concerns`. **Never proceed to Step 1+ without a plan.**
|
|
16
|
+
|
|
17
|
+
## Step 1: Parse Execution Options
|
|
18
|
+
|
|
19
|
+
If `-y` is set (skipping all interactive prompts) or `plan` already specifies execution settings, use defaults. Otherwise resolve via structured prompt (`ask_question` or host equivalent) across enabled tools (`agent` / `codex` / `agy`):
|
|
20
|
+
- `executionMethod` (`auto` | `agent` | `cli` | tool) and `domainRouting` (`{frontend, backend, default: "agent"}`)
|
|
21
|
+
- `codeReviewTool` (optional post-execution diff review tool or `Skip`)
|
|
22
|
+
- `verificationTool` (smoke self-check tool or `Skip`)
|
|
23
|
+
|
|
24
|
+
## Step 2: Load & Normalize Plan
|
|
25
|
+
|
|
26
|
+
Read `current-plan`:
|
|
27
|
+
- If `plan.source_format == "pi-markdown"`, derive tasks, explicit/sequential dependencies, waves, and acceptance checks in memory from `plan.markdown` without overwriting `current-plan` or requiring `task_ids`/`wave_ids`.
|
|
28
|
+
- Otherwise load structured waves/tasks directly.
|
|
29
|
+
|
|
30
|
+
Resolve `executionMethod`, `defaultExecutor`, and `domainRouting`. **Checkpoint resume**: scan persisted task statuses (or `current-execution`/checkpoint records for `pi-markdown`) and start from the first wave containing incomplete tasks.
|
|
31
|
+
|
|
32
|
+
## Step 3: Load Project Rules
|
|
33
|
+
|
|
34
|
+
Reuse bound `session-priors` for covered `coding` Wiki scope. Query `wiki_context` + `wiki_reference` (or CLI fallback `evolve context "<query>" --session <session> --include-memory --reads "<run-dir>/knowledge-reads.json"` with `--from-search`) for additional paths/categories, and pass resolved constraints into each Step 4 task prompt.
|
|
35
|
+
|
|
36
|
+
## Step 4: Wave Parallel Execution
|
|
37
|
+
|
|
38
|
+
- **Executor routing** (priority: task assignment > explicit method > auto domain routing):
|
|
39
|
+
- `frontend` (`.tsx/.jsx/.vue/.css/.html` or UI scope), `backend` (`.go/.rs/.java/.py/.sql/.proto` or API/DB scope), `general` (mixed, `.ts/.js`, config, tests). Log before dispatch: `TASK-001 [frontend] -> <executor>`.
|
|
40
|
+
- **Prompt skeleton**: include `PURPOSE`, `TASK`, `MODE: write`, `CONTEXT`, `EXPECTED`, `CONSTRAINTS` (task files + specs), task definition (`Files`, `Read First`, `Implementation`, `Convergence Criteria`), prior wave summaries, and resolved Wiki constraints.
|
|
41
|
+
- **Execution loop** (serial across waves, parallel per independent task inside each wave — never merge unrelated tasks into one delegate call; join all spawned subagents before ending a wave):
|
|
42
|
+
- **`agent` path**: launch executor subagent (`invoke_subagent` / host subagent with fresh context) to implement -> verify convergence -> auto-fix (<=3 attempts) -> commit only if `--auto-commit` -> write `evidence/summaries/${task.id}.md` -> report status/checkpoint.
|
|
43
|
+
- **`cli` path**: run `evolve delegate "${prompt}" --to ${executor} --mode write` (include `--session ${session_id} --run ${run_id}` when `--to codex`; note `--to agy` runs standalone without `--session`/`--run`), verify convergence criteria against disk, write `evidence/summaries/${task.id}.md`, and commit only if `--auto-commit`.
|
|
44
|
+
- **Failure handling**: up to 3 focused retries (for CLI retries, narrow prompt then fall back to a subagent). After 3 failures, mark `blocked` with checkpoint `{attempt: 3, last_error, partial_files, executor}` and mark unmet downstream dependents `upstream_blocked`. Between waves, prompt only if a task blocked and `-y` is unset.
|
|
45
|
+
|
|
46
|
+
## Step 5: Post-Wave Validation
|
|
47
|
+
|
|
48
|
+
1. Check completed tasks have `evidence/summaries/${task.id}.md` (`missing_summary` warning).
|
|
49
|
+
2. Cross-check task statuses vs wave results (mismatch = critical).
|
|
50
|
+
3. Scan changed files against spec `allowed_languages`/`disallowed_imports` (hit = critical `tech_stack_violation`).
|
|
51
|
+
4. Optional CLI diff check via `evolve delegate "<review changed files for cycles/dead code/breaking changes>" --to codex|agy --mode analysis`.
|
|
52
|
+
|
|
53
|
+
Any critical failure marks the run `blocked` with recorded violations.
|
|
54
|
+
|
|
55
|
+
## Step 6: Optional Diff Review
|
|
56
|
+
|
|
57
|
+
Unless `codeReviewTool == "Skip"`, run `evolve delegate "<review git diff>" --to ${codeReviewTool} --mode analysis` and record summary findings.
|
|
58
|
+
|
|
59
|
+
## Step 7: Scoped Smoke Self-Check
|
|
60
|
+
|
|
61
|
+
Unless `verificationTool == "Skip"` or zero tasks completed, run one scoped smoke pass (narrowest build/test suites covering changed files + convergence evidence, existence, substance, wiring, and anti-pattern scan for `TODO`/`FIXME`/disabled tests) and write `outputs/self-check.json` (`overall: "passed"|"gaps_found"`). Note: `gaps_found` does **not** fail `self-check-passed`; record concerns for formal acceptance in `ew-review`.
|
|
62
|
+
|
|
63
|
+
## Step 8: Write Outputs & `report.md`
|
|
64
|
+
|
|
65
|
+
Write `outputs/execution.json` (`_meta: { kind: "artifact", schema: "artifacts/1.0", role: "primary", alias: "current-execution" }`, `plan_ref`, `status: completed|partial|blocked`, `waves[]`, `completed_tasks[]`, `blocked_tasks[]`), `outputs/task-results.json`, `outputs/change-manifest.json`, plus `outputs/self-check.json` (each JSON carrying matching `_meta`).
|
|
66
|
+
|
|
67
|
+
Write `report.md` with fixed sections (`Summary`, `Conclusion/Verdict`, `Discussion/Retrospective`, `Artifacts`, `Handoff/Next`), inline GateRecords for `execution-complete` and `self-check-passed`, and frontmatter:
|
|
68
|
+
- `verdict`: `ready` (all succeeded), `ready_with_concerns` (non-critical blocked or smoke gaps), `blocked` (critical failure), `failed` (execution errored).
|
|
69
|
+
- `next`: `[{ command: ew-verify, reason: implementation complete, needs: [current-execution] }]`.
|
|
70
|
+
|
|
71
|
+
## Step 9: Knowledge Staging & Seal
|
|
72
|
+
|
|
73
|
+
Inspect `evidence/summaries/*.md`, deduplicate new patterns/pitfalls against Step 3 rules, and stage reusable findings through `report.md` frontmatter (`constraints`/`decisions`) for closeout via `ew-knowledge` (`evolve workflows show knowledge`). Never write Wiki files directly.
|
|
74
|
+
Seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate execution-complete --gate self-check-passed --summary "<summary>" --verdict done|done_with_concerns` (recover blocked/failed attempts via `evolve run check` + `evolve run transition`).
|
|
75
|
+
|
|
76
|
+
---
|
|
77
|
+
|
|
78
|
+
## Error Codes
|
|
79
|
+
|
|
80
|
+
| Code | Condition | Recovery |
|
|
81
|
+
|------|-----------|----------|
|
|
82
|
+
| `E001` | No plan and no usable upstream | Run `ew-plan` first or route per Step 0 |
|
|
83
|
+
| `E002` | Entire wave blocked | Stop execution, mark dependents `upstream_blocked`, report checkpoint |
|
|
84
|
+
| `W001` | Task definition missing | Record error, skip task, continue wave |
|
|
85
|
+
| `W002` | Subagent dispatch failed | Retry once, mark `blocked` if still failing |
|
|
86
|
+
| `W003` | Delegate failed | Retry with narrowed prompt or subagent (max 3), then checkpoint `blocked` |
|
|
87
|
+
| `W004` | `--auto-commit` failed | Record warning; do not claim commit completion |
|
|
@@ -0,0 +1,62 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-grill
|
|
3
|
+
description: Socratic codebase-grounded pressure test of a plan, idea, or requirement to surface contradictions and terminology collisions
|
|
4
|
+
argument-hint: '<topic|plan> [-y] [-c] [--from <alias>] [--depth shallow|standard|deep]'
|
|
5
|
+
wiki_categories: [arch, review]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: [constraints, references]
|
|
8
|
+
memory: [correction, error]
|
|
9
|
+
session-mode: run
|
|
10
|
+
required_links:
|
|
11
|
+
- references/prepare.md
|
|
12
|
+
- references/workflow.md
|
|
13
|
+
contract:
|
|
14
|
+
consumes:
|
|
15
|
+
- kind: grill-report
|
|
16
|
+
alias: current-grill
|
|
17
|
+
required: false
|
|
18
|
+
schema: grill-report/1.0
|
|
19
|
+
role: primary
|
|
20
|
+
accepts_negative_evidence: true
|
|
21
|
+
- kind: context-package
|
|
22
|
+
alias: upstream-context
|
|
23
|
+
required: false
|
|
24
|
+
schema: context-package/1.0
|
|
25
|
+
role: attachment
|
|
26
|
+
accepts_negative_evidence: true
|
|
27
|
+
- kind: priors
|
|
28
|
+
alias: session-priors
|
|
29
|
+
required: false
|
|
30
|
+
schema: priors/1.0
|
|
31
|
+
role: evidence
|
|
32
|
+
produces:
|
|
33
|
+
- path: outputs/grill-report.md
|
|
34
|
+
kind: grill-report
|
|
35
|
+
alias: current-grill
|
|
36
|
+
role: primary
|
|
37
|
+
required: true
|
|
38
|
+
schema: grill-report/1.0
|
|
39
|
+
- path: outputs/terminology.md
|
|
40
|
+
kind: terminology
|
|
41
|
+
role: attachment
|
|
42
|
+
required: false
|
|
43
|
+
schema: terminology/1.0
|
|
44
|
+
- path: outputs/context-package.json
|
|
45
|
+
kind: context-package
|
|
46
|
+
alias: upstream-context
|
|
47
|
+
role: attachment
|
|
48
|
+
required: false
|
|
49
|
+
schema: context-package/1.0
|
|
50
|
+
gates:
|
|
51
|
+
exit:
|
|
52
|
+
- terminology-aligned
|
|
53
|
+
- branches-walked
|
|
54
|
+
contract_version: 2.1
|
|
55
|
+
---
|
|
56
|
+
|
|
57
|
+
# Grill
|
|
58
|
+
|
|
59
|
+
Read [preparation](references/prepare.md), then follow the [grill workflow](references/workflow.md).
|
|
60
|
+
|
|
61
|
+
- Adversarial Socratic pressure test grounded in concrete `file:line` codebase evidence and project Wiki constraints (`session-mode: run`).
|
|
62
|
+
- Challenge terminology collisions and contradictions on the spot before synthesis into `outputs/grill-report.md`, `outputs/terminology.md`, and `outputs/context-package.json`.
|
|
@@ -0,0 +1,26 @@
|
|
|
1
|
+
# Pre-flight: ew-grill
|
|
2
|
+
|
|
3
|
+
Confirm mode, depth, upstream seed, and read-only invariants before executing [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Input & Mode
|
|
6
|
+
|
|
7
|
+
| Mode | Trigger | Behavior |
|
|
8
|
+
| --- | --- | --- |
|
|
9
|
+
| Resume | `-c` / `--continue` | Resume from prior Run's bound `grill-report.md` and unresolved branches |
|
|
10
|
+
| Auto | `-y` | Codebase evidence answers Socratic branches automatically (still walks all branches — never skips grilling) |
|
|
11
|
+
| Interactive | `<topic>` or `--from <alias>` | Full adversarial Socratic Q&A with structured user prompts (`ask_question` or host equivalent) |
|
|
12
|
+
|
|
13
|
+
- `--depth shallow|standard|deep`: sets branch count to `3`, `5` (default), or `8`.
|
|
14
|
+
- Missing topic and no `--from` / `-c` -> fail cleanly (`E001`).
|
|
15
|
+
|
|
16
|
+
## Knowledge & Context Pre-load
|
|
17
|
+
|
|
18
|
+
1. Reuse bound `session-priors` when `arch`/`review` scope matches; otherwise query Run MCP `wiki_context` + `wiki_reference` (or CLI `evolve context "<topic keywords>" --task grill --session <session> --include-memory --reads "<run_dir>/knowledge-reads.json"` + `--from-search <search-id>`).
|
|
19
|
+
2. Run `evolve code search "<topic>"` only after the Knowledge Gate when mapping overlapping symbols.
|
|
20
|
+
|
|
21
|
+
## Boundaries & Invariants
|
|
22
|
+
|
|
23
|
+
- **Read-only on repository source**: write artifacts only under `{run_dir}/outputs/` and `{run_dir}/evidence/`.
|
|
24
|
+
- **Evidence-anchored challenges**: every questioned assumption must cite concrete `file:line` anchors or observed command output, never abstract opinion.
|
|
25
|
+
- **Immediate contradiction checks**: whenever an answer conflicts with codebase evidence or an earlier answer, challenge it on the spot before moving to the next branch.
|
|
26
|
+
- **Exit gate intent**: `terminology-aligned` (all candidate terms collision-checked in `outputs/terminology.md`) and `branches-walked` (full depth `3/5/8` walked from basic -> specific -> adversarial, producing `outputs/grill-report.md` and `outputs/context-package.json`).
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
# Workflow: ew-grill
|
|
2
|
+
|
|
3
|
+
Adversarial Socratic pressure testing: `Parse & Route -> Discovery & Terminology -> Branch Walking -> Synthesis -> Context Package -> Wrap-up`.
|
|
4
|
+
|
|
5
|
+
## Step 1: Discovery & Codebase Grounding
|
|
6
|
+
|
|
7
|
+
1. Load optional upstream artifact via Run MCP (`read_artifact`) or `evolve run artifact-read <run> upstream-context --session <session>` (or read `--from @file` / `--from <blueprint>`).
|
|
8
|
+
2. Complete the Knowledge Gate (`session-priors` / `wiki_context` / CLI `--reads`) to surface architectural constraints and domain decisions.
|
|
9
|
+
3. Launch a read-only exploration subagent (`invoke_subagent` / host equivalent, joined before Step 2) + `evolve code search` to map overlapping modules, naming conventions, error-handling patterns, and integration boundaries -> save summary to `{run_dir}/evidence/codebase-context.json`. If grounding fails, mark findings `[LOW CONFIDENCE]`.
|
|
10
|
+
|
|
11
|
+
## Step 2: Terminology Alignment (`terminology-aligned` gate)
|
|
12
|
+
|
|
13
|
+
Compare proposal nouns/verbs/states against existing codebase identifiers and Wiki concepts:
|
|
14
|
+
- Flag every naming collision, overloaded term, or vague abstraction.
|
|
15
|
+
- Arbitrate canonical names with the user (or codebase convention under `-y`).
|
|
16
|
+
- Write `{run_dir}/outputs/terminology.md` before walking deep branches.
|
|
17
|
+
|
|
18
|
+
## Step 3: Socratic Branch Walking (`branches-walked` gate)
|
|
19
|
+
|
|
20
|
+
Walk `3` (`shallow`), `5` (`standard`), or `8` (`deep`) risk branches in order from **basic -> specific -> adversarial**:
|
|
21
|
+
- For each branch, form 1 concrete assumption vs codebase `file:line` reality.
|
|
22
|
+
- In interactive mode, ask targeted questions through the host structured question tool (`ask_question` or equivalent), surfacing real trade-offs instead of generic menus.
|
|
23
|
+
- Under `-y`, answer branches directly from codebase evidence, recording `source: code-grounded` and explicit assumptions.
|
|
24
|
+
- Challenge any contradiction immediately before closing the branch.
|
|
25
|
+
|
|
26
|
+
## Step 4: Synthesis, Context Package & Seal
|
|
27
|
+
|
|
28
|
+
1. Write `{run_dir}/outputs/grill-report.md` (decisions, rejected assumptions, `file:line` evidence, open risks, residual severity).
|
|
29
|
+
2. Write `{run_dir}/outputs/context-package.json` (`context-package/1.0`: `domain`, `requirements[]`, `constraints[]`, `non_goals[]`, `insights[]`, `references[]`) for downstream `ew-brainstorm` / `ew-plan` / `ew-blueprint`.
|
|
30
|
+
3. Write `{run_dir}/report.md` with frontmatter (`verdict`, `summary`, `constraints`, `decisions`, `concerns`, `next` proposing `ew-brainstorm` or `ew-plan` only when justified).
|
|
31
|
+
4. Seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate terminology-aligned --gate branches-walked --summary "<summary>" --verdict done|done_with_concerns`. Stage reusable architectural constraints afterward through `ew-knowledge` (`evolve workflows show knowledge`).
|
|
@@ -0,0 +1,56 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-init
|
|
3
|
+
description: Initialize and onboard a greenfield, brownfield, or legacy Maestro project into Evolve (CodeGraph, Wiki, and context packaging)
|
|
4
|
+
argument-hint: '[-y] [--from <alias>] [<idea|@file>]'
|
|
5
|
+
wiki_categories: [arch, coding]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: [constraints, references]
|
|
8
|
+
memory: [decision, work_method]
|
|
9
|
+
session-mode: run
|
|
10
|
+
required_links:
|
|
11
|
+
- references/prepare.md
|
|
12
|
+
- references/workflow.md
|
|
13
|
+
contract:
|
|
14
|
+
consumes:
|
|
15
|
+
- kind: context-package
|
|
16
|
+
alias: upstream-context
|
|
17
|
+
required: false
|
|
18
|
+
schema: context-package/1.0
|
|
19
|
+
role: attachment
|
|
20
|
+
accepts_negative_evidence: true
|
|
21
|
+
- kind: priors
|
|
22
|
+
alias: session-priors
|
|
23
|
+
required: false
|
|
24
|
+
schema: priors/1.0
|
|
25
|
+
role: evidence
|
|
26
|
+
produces:
|
|
27
|
+
- path: outputs/init-report.json
|
|
28
|
+
kind: init-report
|
|
29
|
+
alias: current-init
|
|
30
|
+
role: primary
|
|
31
|
+
required: true
|
|
32
|
+
schema: init-report/1.0
|
|
33
|
+
- path: outputs/project-brief.md
|
|
34
|
+
kind: project-brief
|
|
35
|
+
role: attachment
|
|
36
|
+
required: false
|
|
37
|
+
schema: project-brief/1.0
|
|
38
|
+
- path: outputs/context-package.json
|
|
39
|
+
kind: context-package
|
|
40
|
+
alias: upstream-context
|
|
41
|
+
role: attachment
|
|
42
|
+
required: false
|
|
43
|
+
schema: context-package/1.0
|
|
44
|
+
gates:
|
|
45
|
+
exit:
|
|
46
|
+
- state-detected
|
|
47
|
+
- context-initialized
|
|
48
|
+
contract_version: 2.1
|
|
49
|
+
---
|
|
50
|
+
|
|
51
|
+
# Init
|
|
52
|
+
|
|
53
|
+
Read [preparation](references/prepare.md), then follow the [init workflow](references/workflow.md).
|
|
54
|
+
|
|
55
|
+
- Detects project state (`greenfield`, `brownfield`, `legacy-maestro`, or `initialized`) and onboards it into Evolve's native SQLite/Git/Wiki/CodeGraph stack without creating legacy `.workflow/state.json` or writing `wiki/entries/` directly.
|
|
56
|
+
- Outputs `outputs/init-report.json`, `outputs/project-brief.md`, and `outputs/context-package.json` for downstream `ew-blueprint`, `ew-roadmap`, or `ew-brainstorm`.
|
|
@@ -0,0 +1,25 @@
|
|
|
1
|
+
# Pre-flight: ew-init
|
|
2
|
+
|
|
3
|
+
Confirm repository state, bootstrap prerequisites, and Evolve-native boundaries before running [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Modes & Input
|
|
6
|
+
|
|
7
|
+
- **Interactive (default)**: auto-detects greenfield vs brownfield vs legacy Maestro vs already-initialized, then collects missing project context.
|
|
8
|
+
- **`-y`**: auto-initializes from `--from`, `@file`/prompt text, or brownfield codebase scan without interactive interviews (`-y` still NEVER authorizes unapproved Wiki publication).
|
|
9
|
+
- **`--from <alias>`**: consume bound `upstream-context` (`context-package.json`) to populate vision, goals, locked constraints, non-goals, and terminology without repeating discovery.
|
|
10
|
+
|
|
11
|
+
## State Detection Rules (`state-detected` gate)
|
|
12
|
+
|
|
13
|
+
Inspect repository root before scanning or proposing writes:
|
|
14
|
+
- **Worktree guard**: refuse to initialize a fresh project baseline inside a linked `.git` temporary worktree; run initialization on the main repository checkout.
|
|
15
|
+
- **Path A (`greenfield`)**: no application source files yet -> run deep questioning ("What do you want to build?" -> core value, target users, 2–5 primary goals, constraints/non-goals, tech preferences).
|
|
16
|
+
- **Path B (`brownfield`)**: existing codebase, no `wiki/` / `.agent-memory/` yet -> run `evolve code build` + multi-angle codebase onboarding scan.
|
|
17
|
+
- **Path C (`legacy-maestro`)**: `.workflow/specs/` or `.workflow/knowhow/` exists -> surface `evolve knowledge import` migration preview (`ew-knowledge`) rather than duplicating knowledge.
|
|
18
|
+
- **Path D (`initialized`)**: `.agent-memory/` + `wiki/` already present -> warn idempotently (`E002`), report existing status, and never overwrite active Wiki or Session state silently.
|
|
19
|
+
|
|
20
|
+
## Boundaries & Invariants
|
|
21
|
+
|
|
22
|
+
- **No legacy `.workflow/` generation**: NEVER create `.workflow/project.md`, `.workflow/state.json`, `.workflow/config.json`, or `.workflow/specs/`. State lives in `.agent-memory/` SQLite; durable conventions belong in `wiki/` via `evolve wiki propose` + explicit user-approved `evolve wiki apply`.
|
|
23
|
+
- **Idempotent & scope-guarded**: only establish project identity, code/knowledge baseline, and initial `context-package.json` — do NOT pre-split `ew-roadmap` Sessions or `ew-plan` tasks.
|
|
24
|
+
- **Bootstrap note**: if the repository has not yet installed/committed `skills/` (so no Session Run can bind yet), run pre-Session bootstrap (`evolve install --scope project --yes`, `git add`/`commit` Skills, `evolve code build`) before opening the onboarding Session.
|
|
25
|
+
- **Exit gates**: `state-detected` (path A/B/C/D resolved accurately) and `context-initialized` (`outputs/init-report.json` + `outputs/context-package.json` ready, CodeGraph built when codebase exists).
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
# Workflow: ew-init
|
|
2
|
+
|
|
3
|
+
Project onboarding: `Pre-flight & State Detection -> Greenfield Questioning or Brownfield Scan -> Knowledge & CodeGraph Setup -> Package & Seal`.
|
|
4
|
+
|
|
5
|
+
## Step 1: Detect State & Check Bootstrap (`state-detected` gate)
|
|
6
|
+
|
|
7
|
+
1. Check Git main-worktree status (`git rev-parse --git-common-dir`), `AGENTS.md` / `skills/`, `.agent-memory/`, `.codegraph/`, `wiki/`, source manifests (`package.json`, `tsconfig.json`, `pyproject.toml`, `go.mod`, etc.), and legacy `.workflow/`.
|
|
8
|
+
2. Run the Knowledge Gate (`session-priors`, or `wiki_context` / CLI `evolve context "project conventions architecture" --task init --session <session> --include-memory --reads "<run_dir>/knowledge-reads.json"`) to load any already-recorded project rules.
|
|
9
|
+
3. Classify into **Path A (`greenfield`)**, **Path B (`brownfield`)**, **Path C (`legacy-maestro`)**, or **Path D (`initialized`)**. If Path D and no refresh/re-scan was explicitly requested, emit idempotent status into `outputs/init-report.json` (`_meta: { kind: "init-report", schema: "init-report/1.0", role: "primary", alias: "current-init" }`) without mutating existing knowledge and seal cleanly.
|
|
10
|
+
|
|
11
|
+
## Step 2: Gather Context by Path
|
|
12
|
+
|
|
13
|
+
- **Path A (Greenfield)** (skip questioning if `--from` / `upstream-context` or `-y` with `@file`):
|
|
14
|
+
- Conduct focused discovery via structured prompt (`ask_question` or host equivalent) covering: vision & core value (the one thing that must work), target users, 2–5 primary goals, tech preferences, hard constraints, and non-goals.
|
|
15
|
+
- **Path B (Brownfield)** / **Path C (Legacy)**:
|
|
16
|
+
1. Ensure code graph is indexed via `evolve code build` (if `.codegraph/` is absent or stale).
|
|
17
|
+
2. Spawn up to 4 read-only parallel subagents (`invoke_subagent` / host equivalent, **always joined or cancelled before Step 3**) mapping `stack`, `architecture`, `conventions`, and `pitfalls` -> write summaries under `{run_dir}/evidence/`.
|
|
18
|
+
3. Under Path C, run `evolve knowledge import` (dry-run preview; pass `--knowhow-only` if requested) and summarize pending Spec/Knowhow migration candidates cleanly for `ew-knowledge`.
|
|
19
|
+
|
|
20
|
+
## Step 3: Knowledge Seeding & Artifact Packaging (`context-initialized` gate)
|
|
21
|
+
|
|
22
|
+
1. Never write `wiki/entries/` directly. If onboarding surfaced stable baseline architectural conventions or glossary constraints, prepare proposal JSON and stage previews via `evolve wiki propose <change.json> --evidence <receipt-or-session>` — defer `evolve wiki apply` to explicit user approval via `ew-knowledge` (never treat `-y` as Wiki approval).
|
|
23
|
+
2. Write `{run_dir}/outputs/project-brief.md` (vision, core value, validated capabilities for brownfield, active goals, constraints, non-goals, key decisions).
|
|
24
|
+
3. Write `{run_dir}/outputs/context-package.json` (`context-package/1.0`: `domain`, `requirements[]`, `constraints[]`, `non_goals[]`, `insights[]`, `references[]`) and `{run_dir}/outputs/init-report.json` (`init-report/1.0`: `path`, `codegraph_status`, `wiki_entries_count`, `legacy_import_preview`, `suggested_next`).
|
|
25
|
+
|
|
26
|
+
## Step 4: Seal & Route Next
|
|
27
|
+
|
|
28
|
+
Write `{run_dir}/report.md` (`next` proposing `ew-roadmap`, `ew-blueprint`, or `ew-brainstorm` based on user intent) and seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate state-detected --gate context-initialized --summary "<summary>" --verdict done|done_with_concerns`. All JSON outputs must include matching `_meta` and Markdown outputs matching YAML frontmatter; recover blocked/failed attempts via `evolve run check` + `evolve run transition`.
|
|
@@ -0,0 +1,131 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-plan
|
|
3
|
+
wiki_categories: [arch]
|
|
4
|
+
search_profile:
|
|
5
|
+
wiki: [constraints, references]
|
|
6
|
+
memory: [work_method, error, retry]
|
|
7
|
+
description: Decompose confirmed analysis or requirements into an executable DAG, waves, and collision-free tasks
|
|
8
|
+
argument-hint: '[scope] [--gaps] [--tdd] [--revise [instructions]] [--check <plan-dir>] [-y]'
|
|
9
|
+
contract:
|
|
10
|
+
consumes:
|
|
11
|
+
- kind: findings
|
|
12
|
+
alias: current-analysis
|
|
13
|
+
required: false
|
|
14
|
+
schema: findings/1.0
|
|
15
|
+
role: primary
|
|
16
|
+
accepts_negative_evidence: true
|
|
17
|
+
- kind: diagnosis
|
|
18
|
+
alias: latest-debug
|
|
19
|
+
required: false
|
|
20
|
+
schema: diagnosis/1.0
|
|
21
|
+
role: primary
|
|
22
|
+
accepts_negative_evidence: true
|
|
23
|
+
- kind: review-findings
|
|
24
|
+
alias: latest-review
|
|
25
|
+
required: false
|
|
26
|
+
schema: review-findings/1.0
|
|
27
|
+
role: primary
|
|
28
|
+
accepts_negative_evidence: true
|
|
29
|
+
- kind: verification
|
|
30
|
+
alias: latest-verification
|
|
31
|
+
required: false
|
|
32
|
+
schema: verification/1.0
|
|
33
|
+
role: primary
|
|
34
|
+
accepts_negative_evidence: true
|
|
35
|
+
- kind: test-results
|
|
36
|
+
alias: latest-test
|
|
37
|
+
required: false
|
|
38
|
+
schema: test-results/1.0
|
|
39
|
+
role: primary
|
|
40
|
+
accepts_negative_evidence: true
|
|
41
|
+
- kind: auto-test-report
|
|
42
|
+
alias: latest-auto-test
|
|
43
|
+
required: false
|
|
44
|
+
schema: auto-test-report/1.0
|
|
45
|
+
role: primary
|
|
46
|
+
accepts_negative_evidence: true
|
|
47
|
+
- kind: uat-log
|
|
48
|
+
alias: uat-log
|
|
49
|
+
required: false
|
|
50
|
+
schema: uat-log/1.0
|
|
51
|
+
role: attachment
|
|
52
|
+
accepts_negative_evidence: true
|
|
53
|
+
- kind: blueprint
|
|
54
|
+
alias: current-blueprint
|
|
55
|
+
required: false
|
|
56
|
+
schema: blueprint/1.0
|
|
57
|
+
role: primary
|
|
58
|
+
accepts_negative_evidence: true
|
|
59
|
+
- kind: roadmap
|
|
60
|
+
alias: current-roadmap
|
|
61
|
+
required: false
|
|
62
|
+
schema: roadmap/1.0
|
|
63
|
+
role: primary
|
|
64
|
+
accepts_negative_evidence: true
|
|
65
|
+
- kind: context-package
|
|
66
|
+
alias: upstream-context
|
|
67
|
+
required: false
|
|
68
|
+
schema: context-package/1.0
|
|
69
|
+
role: attachment
|
|
70
|
+
accepts_negative_evidence: true
|
|
71
|
+
- kind: plan
|
|
72
|
+
required: false
|
|
73
|
+
schema: plan/1.0
|
|
74
|
+
role: primary
|
|
75
|
+
accepts_negative_evidence: true
|
|
76
|
+
- kind: priors
|
|
77
|
+
alias: session-priors
|
|
78
|
+
required: false
|
|
79
|
+
schema: priors/1.0
|
|
80
|
+
role: evidence
|
|
81
|
+
produces:
|
|
82
|
+
- path: outputs/plan.json
|
|
83
|
+
kind: plan
|
|
84
|
+
alias: current-plan
|
|
85
|
+
role: primary
|
|
86
|
+
required: true
|
|
87
|
+
schema: plan/1.0
|
|
88
|
+
- path: outputs/tasks/TASK-{NNN}.json
|
|
89
|
+
kind: plan-task
|
|
90
|
+
role: attachment
|
|
91
|
+
required: false
|
|
92
|
+
schema: plan-task/1.0
|
|
93
|
+
- path: outputs/waves.json
|
|
94
|
+
kind: execution-waves
|
|
95
|
+
role: attachment
|
|
96
|
+
required: false
|
|
97
|
+
schema: execution-waves/1.0
|
|
98
|
+
- path: outputs/dependency-graph.json
|
|
99
|
+
kind: dependency-graph
|
|
100
|
+
role: evidence
|
|
101
|
+
required: false
|
|
102
|
+
schema: dependency-graph/1.0
|
|
103
|
+
- path: outputs/collision-report.json
|
|
104
|
+
kind: collision-report
|
|
105
|
+
role: evidence
|
|
106
|
+
required: false
|
|
107
|
+
schema: collision-report/1.0
|
|
108
|
+
- path: outputs/plan-check.json
|
|
109
|
+
kind: plan-check
|
|
110
|
+
role: evidence
|
|
111
|
+
required: false
|
|
112
|
+
schema: plan-check/1.0
|
|
113
|
+
gates:
|
|
114
|
+
exit:
|
|
115
|
+
- context-collected
|
|
116
|
+
- plan-generated
|
|
117
|
+
- plan-checked
|
|
118
|
+
- plan-confirmed
|
|
119
|
+
contract_version: 2.1
|
|
120
|
+
required_links:
|
|
121
|
+
- references/prepare.md
|
|
122
|
+
- references/workflow.md
|
|
123
|
+
session-mode: run
|
|
124
|
+
---
|
|
125
|
+
|
|
126
|
+
# Plan
|
|
127
|
+
|
|
128
|
+
Read [preparation](references/prepare.md), then follow the [workflow](references/workflow.md).
|
|
129
|
+
|
|
130
|
+
- Follow `skills/ew-orchestrate/references/boundary-grill.md` when task boundaries or file writes conflict (write findings into `plan.json#boundary_grill[]` + `report.md`; never append raw Markdown into `.json`).
|
|
131
|
+
- Read [test-first planning](references/tdd.md) when invoked with `--tdd`.
|
|
@@ -0,0 +1,8 @@
|
|
|
1
|
+
# Pre-flight: ew-plan
|
|
2
|
+
|
|
3
|
+
Confirm inputs, agent topology, and non-negotiable task quality rules before running [workflow](workflow.md) (open [test-first planning](tdd.md) when `--tdd` is active):
|
|
4
|
+
|
|
5
|
+
- **Input resolution**: read upstream artifacts only via injected `upstream_aliases` (`current-analysis` takes priority; `--gaps` combines issues + `latest-review` + `latest-verification` + `latest-debug`). Fail with `E001` if no usable context exists.
|
|
6
|
+
- **Mode & topology**: `--revise` modifies an existing plan in place; `--check` validates read-only; `--tdd` enforces RED -> GREEN -> REFACTOR chains. Scope <=3 modules -> single planner subagent (<=8 tasks); >3 modules -> 2+1 split (<=16 tasks total). Inline planning in the main flow is forbidden.
|
|
7
|
+
- **Knowledge reuse**: consume bound `session-priors` without re-searching identical scope; query `wiki_context`/`wiki_reference` (or CLI `--reads`) when introducing new paths or categories, and forward resolved Wiki constraints to planners.
|
|
8
|
+
- **Task quality**: one feature = one task (vertical UI slices with >=1 `[UI-observable]` criterion per delivery wave; batch trivial <5-minute edits); concrete `action`/`implementation` values (no "align X with Y"); grep/command-verifiable `convergence.criteria`; complete `read_first[]`; no same-wave `files[]` write collisions.
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
# TDD Task-Chain Generation
|
|
2
|
+
|
|
3
|
+
Protocol for `plan --tdd`: decompose each behavior into a test-first task triplet so the executor is forced through Red-Green-Refactor. This governs how the plan is *shaped*; the executor enforces the cycle at run time.
|
|
4
|
+
|
|
5
|
+
## Iron Law
|
|
6
|
+
|
|
7
|
+
**NO PRODUCTION-CODE TASK WITHOUT A FAILING-TEST TASK BEFORE IT.**
|
|
8
|
+
|
|
9
|
+
Every behavior's GREEN task must `depends_on` its RED task. A plan that ships an implementation task with no preceding test task violates TDD and must be re-generated.
|
|
10
|
+
|
|
11
|
+
## Red-Green-Refactor Triplet
|
|
12
|
+
|
|
13
|
+
For each behavior `B` (derived from requirements or convergence criteria), emit up to three tasks:
|
|
14
|
+
|
|
15
|
+
```
|
|
16
|
+
TASK-{N}a RED Write a failing test for B
|
|
17
|
+
TASK-{N}b GREEN Write minimal code to make B pass (depends_on {N}a)
|
|
18
|
+
TASK-{N}c REFACTOR Clean up B's implementation (depends_on {N}b, optional)
|
|
19
|
+
```
|
|
20
|
+
|
|
21
|
+
REFACTOR is omitted when there is nothing to clean. RED and GREEN are never merged or skipped.
|
|
22
|
+
|
|
23
|
+
## Per-task requirements
|
|
24
|
+
|
|
25
|
+
### RED — `type: test`
|
|
26
|
+
|
|
27
|
+
- `action`: write a test describing the expected behavior; it MUST fail before the implementation exists.
|
|
28
|
+
- `convergence.criteria` (grep/run-verifiable):
|
|
29
|
+
- test file exists at `{test_path}`
|
|
30
|
+
- test run exits non-zero (**fails**, not errors)
|
|
31
|
+
- failure message matches the expected behavior gap
|
|
32
|
+
- `meta`: `{ tdd_phase: "red", tdd_group: "{N}" }`
|
|
33
|
+
- Use real code, not mocks (unless the dependency is external). One behavior per test.
|
|
34
|
+
|
|
35
|
+
### GREEN — `type: feature`, `depends_on: [TASK-{N}a]`
|
|
36
|
+
|
|
37
|
+
- `action`: write the simplest code that makes the failing test pass — nothing beyond what the test requires.
|
|
38
|
+
- `convergence.criteria`: the RED test now passes AND all pre-existing tests still pass.
|
|
39
|
+
- `meta`: `{ tdd_phase: "green", tdd_group: "{N}" }`.
|
|
40
|
+
|
|
41
|
+
### REFACTOR — `type: refactor`, `depends_on: [TASK-{N}b]`, optional
|
|
42
|
+
|
|
43
|
+
- `action`: improve structure/naming/duplication without changing behavior.
|
|
44
|
+
- `convergence.criteria`: all tests still pass; no new behavior introduced.
|
|
45
|
+
- `meta`: `{ tdd_phase: "refactor", tdd_group: "{N}" }`.
|
|
46
|
+
|
|
47
|
+
## Convergence quality
|
|
48
|
+
|
|
49
|
+
Criteria must be grep/run/test-verifiable with the exact command or string — never subjective ("looks correct", "properly tested"). Prefer concrete forms like `test exits non-zero` (RED) / `test exits 0` (GREEN) / `<test-command> passes`.
|
|
50
|
+
|
|
51
|
+
## Interaction with plan gates
|
|
52
|
+
|
|
53
|
+
The generated triplets flow through the standard plan checker: dependency correctness must show every GREEN depending on its RED, and the Readiness Gate treats a GREEN task with no preceding RED as a blocking violation.
|
|
@@ -0,0 +1,100 @@
|
|
|
1
|
+
# Workflow: Plan
|
|
2
|
+
|
|
3
|
+
5-step pipeline: Context Collection -> Clarification -> Planning -> Plan Checking & Collision -> Confirmation.
|
|
4
|
+
|
|
5
|
+
Produces `outputs/plan.json` + `outputs/tasks/TASK-{NNN}.json` + `outputs/waves.json`, `outputs/dependency-graph.json`, `outputs/collision-report.json` (plus `outputs/plan-check.json` when checked).
|
|
6
|
+
|
|
7
|
+
## Modes & Topology
|
|
8
|
+
|
|
9
|
+
```
|
|
10
|
+
Create (default): Step 1 -> Step 2 -> Step 3 -> Step 4 -> Step 4.5 -> Step 5
|
|
11
|
+
--tdd: Step 1 -> Step 2 -> Step 3 (TDD chain) -> Step 4 -> Step 4.5 -> Step 5
|
|
12
|
+
--revise: Load existing plan -> apply targeted diff -> Step 4 -> Step 4.5 -> Confirm
|
|
13
|
+
--check <dir>: Step 4 only (read-only)
|
|
14
|
+
```
|
|
15
|
+
|
|
16
|
+
- **Scope selection**: `--from <alias>` uses upstream `implementation_scope`; `--gaps` plans issue/review/verification/debug gap fixes (skipping Step 1 exploration); numeric arg / active milestone targets milestone scope; otherwise use latest `ew-analyze` findings or fail `E001`.
|
|
17
|
+
- **Agent topology**: <=3 modules -> 1 planner subagent (<=8 tasks); >3 modules -> 2+1 (2 parallel planners <=8 tasks each + 1 synthesis subagent, <=16 tasks total). Always join/await all spawned subagents before advancing.
|
|
18
|
+
|
|
19
|
+
## Blocking Step Gates (Create mode)
|
|
20
|
+
|
|
21
|
+
| Gate | Requirement to advance |
|
|
22
|
+
|------|------------------------|
|
|
23
|
+
| `context-collected` (1 -> 2) | Upstream context/exploration and codebase/Wiki rules loaded (`E001` if zero context) |
|
|
24
|
+
| `plan-generated` (3 -> 4) | Planner subagent produced `outputs/plan.json` + `outputs/tasks/TASK-*.json` (inline planning forbidden) |
|
|
25
|
+
| `plan-checked` (4 -> 5) | Plan checker passed (zero unresolved criticals), boundary grill + 5-dim confidence + >=1 pressure pass completed, UI waves cover `[UI-observable]` |
|
|
26
|
+
| `plan-confirmed` (5 -> wrap-up) | User confirmed (`-y` auto-confirms) before registering/reporting completion |
|
|
27
|
+
|
|
28
|
+
---
|
|
29
|
+
|
|
30
|
+
## Process
|
|
31
|
+
|
|
32
|
+
### Step 1: Context Collection
|
|
33
|
+
|
|
34
|
+
1. **Upstream decisions** (via injected aliases):
|
|
35
|
+
- `current-analysis`: treat `decisions[class=locked]` as hard constraints, `[free]` as implementer discretion, `[deferred]` as excluded; map `implementation_scope` 1:1 to tasks when present (skipping parallel exploration).
|
|
36
|
+
- `latest-review`: normalize BLOCK findings (`finding_id`, `affected_files`, `location = file:line`) and cluster shared root causes within normal task guardrails.
|
|
37
|
+
- `current-blueprint` / optional `current-roadmap`: extract seed requirements and milestone boundaries.
|
|
38
|
+
- `architecture_template_evidence`: inherit read-only from `current-analysis`, `blueprint`/`brainstorm` `references[]`, or upstream research findings — never re-search.
|
|
39
|
+
2. **Project knowledge & codebase**: apply bound `session-priors`. When adding new task paths/categories, inspect Wiki/Memory via Run MCP (`wiki_context` + `wiki_reference`, `memory_search` + `memory_get`) or CLI-only fallback (`evolve context "<query>" --session <session> --include-memory --reads "<run-dir>/knowledge-reads.json"` + `--from-search`). Run `evolve code search "<keywords>"` after the Knowledge Gate.
|
|
40
|
+
3. **Design tokens (UI)**: load `design-ref/MASTER.md` if present and include token/layout refs in UI tasks' `read_first[]`.
|
|
41
|
+
4. **Parallel exploration** (skip if `--gaps` or upstream `implementation_scope` exists): launch 1-4 exploration subagents (`invoke_subagent` / host subagent, joined before continuing) covering architecture, implementation, integration, and risk -> write `evidence/exploration-{angle}.json`. Optionally run `evolve delegate "<patterns/dependencies/collisions>" --to codex --mode analysis --session <session> --run <run>` (or `--to agy --mode analysis` outside Run binding).
|
|
42
|
+
5. **Gap mode (`--gaps`)**: merge sources by priority — issue tracker (`registered`/`diagnosed`, mark `planning`) -> `latest-review` -> `verification.json` -> `uat.md` Gaps -> `latest-debug`. Deduplicate by ID then root cause + files, cluster to respect task limits, and error `E001` if empty.
|
|
43
|
+
|
|
44
|
+
### Step 2: Clarification (skip if `-y`)
|
|
45
|
+
|
|
46
|
+
Deduplicate blocking/important `clarification_needs[]`, clarify via structured prompt (`ask_question` or host equivalent, up to 3 rounds x 4 questions), and store `clarificationContext`.
|
|
47
|
+
|
|
48
|
+
### Step 3: Planning
|
|
49
|
+
|
|
50
|
+
Launch a planner subagent (or 2+1 topology; join all subagents before Step 4). **Inline planning in the main flow is forbidden.** Pass upstream context, `session-priors`/Wiki constraints, `explorationContext`, `clarificationContext`, and inherited `architecture_template_evidence`.
|
|
51
|
+
|
|
52
|
+
- **Guardrails**: simple <=4 tasks, medium <=8, large (>3 modules) <=16; 1 feature = 1 substantial task (15-60m, batch <5m trivial edits); `depends_on` only for real output dependencies; vertical UI slices with >=1 `[UI-observable]` criterion per delivery wave.
|
|
53
|
+
- **Every `TASK-NNN.json` must include**:
|
|
54
|
+
1. `read_first[]`: target modified files + source-of-truth/pattern files.
|
|
55
|
+
2. `convergence_criteria`: concrete grep/test/CLI verifiable assertions (zero subjective words like "looks correct").
|
|
56
|
+
3. `action` & `implementation`: exact signatures, keys, values, import paths (never "align X with Y").
|
|
57
|
+
4. `architecture_template_refs`: only resolved `template_id` values present in `plan.json.shared_context.architecture_templates`.
|
|
58
|
+
- **`--gaps` tasks**: `type: fix`, retaining `issue_id` (update matched issues to `planned`) and `finding_refs[]`.
|
|
59
|
+
|
|
60
|
+
### Step 4: Plan Checking & Step 4.5: Collision Detection
|
|
61
|
+
|
|
62
|
+
1. Launch a mandatory **plan checker subagent** (joined before continuing) to verify requirement coverage, DAG acyclicity, grep-verifiable convergence, `read_first[]` completeness, concrete actions, same-wave write non-collision, UI coverage, and valid `architecture_template_evidence` (`kind=template`, `reference_only=true`, resolved IDs only, absent from knowledge consumption fields). Run up to 3 revision loops on criticals.
|
|
63
|
+
2. Score 5 dimensions (`requirements_coverage`, `task_quality`, `dependency_correctness`, `estimation_accuracy`, `collision_safety`) weighted by `completeness .30`, `specificity .25`, `structural_validity .20`, `user_validation .15`, `consistency .10`, plus >=1 mandatory **Pressure Pass** on the highest-complexity task.
|
|
64
|
+
3. Run boundary review (`skills/ew-orchestrate/references/boundary-grill.md`) if boundary/write conflicts arise, writing `boundary_grill[]` inside `outputs/plan.json` (never raw Markdown inside `.json`).
|
|
65
|
+
4. Block before Step 4.5 if coverage <40%, missing `read_first`/`convergence`, no pressure pass, cycle, or invalid template ref (unless user confirms into `residual_risks`).
|
|
66
|
+
5. **Collision Detection (Step 4.5, skip if `standalone`)**: intersect new `task.files[]` (write targets only, not `read_first[]`) against existing milestone plans -> write `outputs/collision-report.json`.
|
|
67
|
+
|
|
68
|
+
### Step 5: Confirmation
|
|
69
|
+
|
|
70
|
+
Present objective, task/wave counts, key dependencies, confidence %, weakest dimension, and pressure pass result. Prompt via structured choice (`Execute now` / `Re-verify stricter` / `View` / `Modify`; `-y` auto-confirms).
|
|
71
|
+
|
|
72
|
+
---
|
|
73
|
+
|
|
74
|
+
## Output Skeleton
|
|
75
|
+
|
|
76
|
+
- **`outputs/plan.json`**: `{ objective, requirement_refs[], task_ids[], wave_ids[], confidence, constraints[], acceptance_criteria[], shared_context: { architecture_template_search, architecture_templates[] } }` (also admits `plan/1.0` `pi-markdown` approved variant).
|
|
77
|
+
- **`outputs/tasks/TASK-NNN.json`**: `{ _meta: { kind: "plan-task", schema: "plan-task/1.0", role: "attachment" }, id, title, description, requirement_refs[], deps[], files[], read_first[], convergence_criteria[], verify[], status: "pending" }`.
|
|
78
|
+
- **`outputs/waves.json`**, **`outputs/dependency-graph.json`**, **`outputs/collision-report.json`**, **`outputs/plan-check.json`**.
|
|
79
|
+
|
|
80
|
+
### Wrap-up
|
|
81
|
+
|
|
82
|
+
Write `outputs/plan.json` (carrying `_meta: { kind: "plan", schema: "plan/1.0", role: "primary", alias: "current-plan" }`) and `TASK-NNN.json` / `waves.json` / `dependency-graph.json` / `collision-report.json` / `plan-check.json` (all with matching `_meta`). Write `report.md` with frontmatter (`verdict`, `summary`, `constraints`, `decisions`, `concerns`, `next: [{ command: ew-execute, reason: plan ready, needs: [current-plan] }]`) and sections `Summary`, `Conclusion/Verdict`, `Discussion/Retrospective`, `Artifacts`, `Handoff/Next`. Reference `current-plan` via `{{aref:...}}` rather than copying JSON. Seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate context-collected --gate plan-generated --gate plan-checked --gate plan-confirmed --summary "<summary>" --verdict done|done_with_concerns` (recover blockers via `evolve run check` + `evolve run transition`). Hand off candidate staging/review to `ew-knowledge` (`evolve workflows show knowledge`) while keeping `report.md` frontmatter staging (`constraints`/`decisions`).
|
|
83
|
+
|
|
84
|
+
---
|
|
85
|
+
|
|
86
|
+
## Revise (`--revise`) & Check (`--check`)
|
|
87
|
+
|
|
88
|
+
- **`--revise`**: locate `--dir` or bound `current-plan` (`E004` if none), parse instructions (or prompt via structured choice), run planner subagent (joined) to update affected tasks in place while preserving upstream `architecture_template_evidence`, re-run Step 4 + 4.5, confirm, and write updated `outputs/plan.json` + tasks before sealing.
|
|
89
|
+
- **`--check <dir>`**: read-only inspection (`E005` if missing) -> run checker, dependency, collision, and milestone alignment checks -> print pass/warn/fail summary without editing repository files (when run inside a bound Run, emit `outputs/plan-check.json` and read-only `outputs/plan.json` copy to satisfy contract gates before sealing).
|
|
90
|
+
|
|
91
|
+
## Error Codes
|
|
92
|
+
|
|
93
|
+
| Code | Condition | Recovery |
|
|
94
|
+
|------|-----------|----------|
|
|
95
|
+
| `E001` | No usable planning context | Supply scope, topic, or upstream artifact first |
|
|
96
|
+
| `E004` | No plan to revise | Specify `--dir` or create a plan first |
|
|
97
|
+
| `E005` | Plan directory missing (`--check`) | Verify path / `--dir` |
|
|
98
|
+
| `E006` | Invalid planner JSON | Retry once with schema reminder, then abort |
|
|
99
|
+
| `W001` | Exploration subagent failed | Retry once; mark missing angle and verify in code before confirming |
|
|
100
|
+
| `W002` | Plan checker exceeded 3 rounds | Surface remaining issues in `outputs/plan-check.json` for user decision |
|