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 +1,23 @@
|
|
|
1
|
+
# Pre-flight: ew-auto-test
|
|
2
|
+
|
|
3
|
+
Confirm scenario source routing, Knowledge Gate test conventions, and RED-GREEN invariants before running [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Modes & Arguments
|
|
6
|
+
|
|
7
|
+
- **Source priority**: (1) bound spec/requirement artifacts (`current-blueprint` / `current-plan`), (2) `latest-verification` / coverage gaps, else (3) code exploration (`current-execution` + `evolve code search`).
|
|
8
|
+
- **`--max-iter N`**: outer convergence iteration cap (`5` default; `1` = single-pass generation).
|
|
9
|
+
- **`--layer L0|L1|L2|L3`**: start from or restrict execution to one test layer (`L0` unit/pure -> `L1` integration -> `L2` CLI/API -> `L3` E2E).
|
|
10
|
+
- **`--dry-run`**: generate scenario plan and traceability matrix without writing or running test files.
|
|
11
|
+
- **`--re-run`** / **`-c`**: resume or re-run only previously failed scenarios from `.tests/auto-test/state.json`.
|
|
12
|
+
|
|
13
|
+
## Knowledge Gate
|
|
14
|
+
|
|
15
|
+
Reuse bound `session-priors` (`test`/`coding`); otherwise query `wiki_context` + `wiki_reference` (or CLI `evolve context "<module> test conventions" --task auto-test --session <session> --include-memory --reads "<run_dir>/knowledge-reads.json"` + `--from-search <search-id>`).
|
|
16
|
+
|
|
17
|
+
## Pipeline Invariants
|
|
18
|
+
|
|
19
|
+
- **Test isolation**: write new test files only in the project's test directory matching existing framework conventions; NEVER modify production source or weaken/overwrite existing tests to make tests pass.
|
|
20
|
+
- **RED-GREEN integrity**: confirm each newly written test captures real failing behavior (or exercises live assertion paths) before counting GREEN; trivial always-true assertions are forbidden.
|
|
21
|
+
- **Strict layer ordering**: run `L0 -> L1 -> L2 -> L3` in order, stopping early on layer blocker (`fail-fast`).
|
|
22
|
+
- **Dual storage**: keep resumable workspace state under `.tests/auto-test/` if resuming across Runs, AND always publish final `{run_dir}/outputs/auto-test-report.json` (plus `outputs/traceability.md` for spec routes) for Runtime registration.
|
|
23
|
+
- **Exit gates**: `tests-generated` (scenarios traced & generated cleanly) and `execution-converged` (layers executed fail-fast with actual pass-rate metrics within `--max-iter` and `<= 3` defect retries per scenario).
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
# Workflow: ew-auto-test
|
|
2
|
+
|
|
3
|
+
Unified layered automated test pipeline: `Route Source -> Plan Layers -> Write Tests -> Execute L0..L3 -> Diagnose & Iterate -> Publish & Seal`.
|
|
4
|
+
|
|
5
|
+
## Step 1: Resolve Source & Test Infrastructure
|
|
6
|
+
|
|
7
|
+
1. Complete the Knowledge Gate and inspect bound artifacts (`latest-verification`, `current-execution`, `latest-review`, `latest-debug`).
|
|
8
|
+
2. Identify the project's test runner, existing test patterns, fixture helpers, and coverage tooling.
|
|
9
|
+
3. Map target behaviors into ordered layers (`L0` unit, `L1` integration, `L2` API/CLI contract, `L3` E2E) and assign every spec-derived scenario a requirement trace ID (`outputs/traceability.md`).
|
|
10
|
+
|
|
11
|
+
## Step 2: Author Tests (`tests-generated` gate)
|
|
12
|
+
|
|
13
|
+
Skip file creation under `--dry-run` (emit plan only). Otherwise:
|
|
14
|
+
- Group independent scenario sets by non-overlapping new test files; fan out parallel test-authoring subagents (`invoke_subagent` / host equivalent, **always joined or cancelled before advancing**) if multiple modules are targeted.
|
|
15
|
+
- Verify each generated test actually exercises the target module and executes assertions (RED-first check when adding regression tests for known defects).
|
|
16
|
+
- Confirm zero edits to existing test files or production source.
|
|
17
|
+
|
|
18
|
+
## Step 3: Layered Execution & Bounded Convergence (`execution-converged` gate)
|
|
19
|
+
|
|
20
|
+
Run up to `--max-iter` rounds (default `5`):
|
|
21
|
+
1. Execute layers `L0 -> L1 -> L2 -> L3` sequentially; fail-fast if a lower layer breaks structurally.
|
|
22
|
+
2. When scenarios fail: dispatch read-only diagnosis (`test_defect` vs `app_defect`).
|
|
23
|
+
- Fix `test_defect` (bad mock/setup in newly generated test) up to `3` attempts per scenario, then escalate.
|
|
24
|
+
- Never alter production source for an `app_defect` — record it clearly for `ew-debug` / `ew-plan --gaps`.
|
|
25
|
+
3. Compute pass rate and confidence strictly from live command exit codes and test output counts.
|
|
26
|
+
|
|
27
|
+
## Step 4: Publish Report & Seal
|
|
28
|
+
|
|
29
|
+
1. Write `{run_dir}/outputs/auto-test-report.json` (`_meta: { kind: "auto-test-report", schema: "auto-test-report/1.0", role: "primary", alias: "latest-auto-test" }`, `route`, `iterations_run`, `layers`, `summary: { total, passed, failed, skipped, pass_rate }`, `app_defects[]`, `commands_run[]`; under `--dry-run`, populate `route` + planned layers + `summary: { total: <planned>, passed: 0, failed: 0, skipped: <planned>, pass_rate: null }` so sealing holds without fabricated runs) and `outputs/traceability.md`.
|
|
30
|
+
2. Write `{run_dir}/report.md` (`next` proposing `ew-debug --from-test` or `ew-plan --gaps` if `app_defects[]` remain).
|
|
31
|
+
3. Seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate tests-generated --gate execution-converged --summary "<summary>" --verdict done|done_with_concerns`. Stage reusable testing findings via `ew-knowledge`.
|
|
@@ -0,0 +1,122 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-blueprint
|
|
3
|
+
description: Generate a formal specification package (Product Brief, PRD, Architecture, Epics) through a 6-phase document chain
|
|
4
|
+
argument-hint: '<idea|@file> [-y] [-c] [--from <alias>]'
|
|
5
|
+
wiki_categories: [arch, review]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: [constraints, references]
|
|
8
|
+
memory: [decision, correction]
|
|
9
|
+
session-mode: run
|
|
10
|
+
required_links:
|
|
11
|
+
- references/prepare.md
|
|
12
|
+
- references/workflow.md
|
|
13
|
+
contract:
|
|
14
|
+
consumes:
|
|
15
|
+
- kind: blueprint
|
|
16
|
+
alias: current-blueprint
|
|
17
|
+
required: false
|
|
18
|
+
schema: blueprint/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/product-brief.md
|
|
34
|
+
kind: blueprint
|
|
35
|
+
alias: current-blueprint
|
|
36
|
+
role: primary
|
|
37
|
+
required: true
|
|
38
|
+
schema: blueprint/1.0
|
|
39
|
+
- path: outputs/blueprint-config.json
|
|
40
|
+
kind: blueprint-config
|
|
41
|
+
role: evidence
|
|
42
|
+
required: false
|
|
43
|
+
schema: blueprint-config/1.0
|
|
44
|
+
- path: outputs/discovery-context.json
|
|
45
|
+
kind: discovery-context
|
|
46
|
+
role: evidence
|
|
47
|
+
required: false
|
|
48
|
+
schema: discovery-context/1.0
|
|
49
|
+
- path: outputs/refined-requirements.json
|
|
50
|
+
kind: refined-requirements
|
|
51
|
+
role: evidence
|
|
52
|
+
required: false
|
|
53
|
+
schema: refined-requirements/1.0
|
|
54
|
+
- path: outputs/glossary.json
|
|
55
|
+
kind: glossary
|
|
56
|
+
role: attachment
|
|
57
|
+
required: false
|
|
58
|
+
schema: glossary/1.0
|
|
59
|
+
- path: outputs/requirements/_index.md
|
|
60
|
+
kind: requirements-spec
|
|
61
|
+
role: attachment
|
|
62
|
+
required: false
|
|
63
|
+
schema: requirements-spec/1.0
|
|
64
|
+
- path: outputs/requirements/REQ-{slug}.md
|
|
65
|
+
kind: requirements-spec
|
|
66
|
+
role: attachment
|
|
67
|
+
required: false
|
|
68
|
+
schema: requirements-spec/1.0
|
|
69
|
+
- path: outputs/requirements/NFR-{slug}.md
|
|
70
|
+
kind: requirements-spec
|
|
71
|
+
role: attachment
|
|
72
|
+
required: false
|
|
73
|
+
schema: requirements-spec/1.0
|
|
74
|
+
- path: outputs/architecture/_index.md
|
|
75
|
+
kind: architecture-spec
|
|
76
|
+
role: attachment
|
|
77
|
+
required: false
|
|
78
|
+
schema: architecture-spec/1.0
|
|
79
|
+
- path: outputs/architecture/ADR-{slug}.md
|
|
80
|
+
kind: architecture-spec
|
|
81
|
+
role: attachment
|
|
82
|
+
required: false
|
|
83
|
+
schema: architecture-spec/1.0
|
|
84
|
+
- path: outputs/epics/_index.md
|
|
85
|
+
kind: epics-spec
|
|
86
|
+
role: attachment
|
|
87
|
+
required: false
|
|
88
|
+
schema: epics-spec/1.0
|
|
89
|
+
- path: outputs/epics/EPIC-{slug}.md
|
|
90
|
+
kind: epics-spec
|
|
91
|
+
role: attachment
|
|
92
|
+
required: false
|
|
93
|
+
schema: epics-spec/1.0
|
|
94
|
+
- path: outputs/readiness-report.md
|
|
95
|
+
kind: readiness-report
|
|
96
|
+
role: evidence
|
|
97
|
+
required: false
|
|
98
|
+
schema: readiness-report/1.0
|
|
99
|
+
- path: outputs/blueprint-summary.md
|
|
100
|
+
kind: blueprint-summary
|
|
101
|
+
role: attachment
|
|
102
|
+
required: false
|
|
103
|
+
schema: blueprint-summary/1.0
|
|
104
|
+
- path: outputs/context-package.json
|
|
105
|
+
kind: context-package
|
|
106
|
+
alias: upstream-context
|
|
107
|
+
role: attachment
|
|
108
|
+
required: false
|
|
109
|
+
schema: context-package/1.0
|
|
110
|
+
gates:
|
|
111
|
+
exit:
|
|
112
|
+
- phases-complete
|
|
113
|
+
- readiness-passed
|
|
114
|
+
contract_version: 2.1
|
|
115
|
+
---
|
|
116
|
+
|
|
117
|
+
# Blueprint
|
|
118
|
+
|
|
119
|
+
Read [preparation](references/prepare.md), then follow the [blueprint workflow](references/workflow.md).
|
|
120
|
+
|
|
121
|
+
- Produces pure specification artifacts (`Product Brief → PRD → Architecture → Epics → Readiness`) inside `{run_dir}/outputs/` without writing application code.
|
|
122
|
+
- Passes `current-blueprint` and `outputs/context-package.json` downstream to `ew-roadmap`, `ew-analyze`, or `ew-plan`.
|
|
@@ -0,0 +1,21 @@
|
|
|
1
|
+
# Pre-flight: ew-blueprint
|
|
2
|
+
|
|
3
|
+
Confirm input source, depth, Knowledge Gate constraints, and document-only boundaries before executing [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Input & Mode
|
|
6
|
+
|
|
7
|
+
- **Direct text / `@file`**: fresh specification pipeline starting from P1 Discovery & P1.5 Clarification.
|
|
8
|
+
- **`--from <alias>` / `upstream-context`**: load bound `context-package.json` (`requirements[]`, `constraints[]`, `domain.terminology[]`, `non_goals[]`, `insights[]`) and skip redundant P1.5 expansion.
|
|
9
|
+
- **`-c` / `--continue`**: inspect prior `blueprint-config.json` and resume from the first incomplete phase.
|
|
10
|
+
- **`-y`**: auto-select default profile (`service` / `standard` depth) and non-ambiguous suggestions; stop if broad requirements lack minimum domain truth.
|
|
11
|
+
|
|
12
|
+
## Knowledge Gate & Research
|
|
13
|
+
|
|
14
|
+
1. Reuse bound `session-priors` for architectural/spec constraints; otherwise query `wiki_context` + `wiki_reference` (or CLI `evolve context "<idea keywords>" --task blueprint --session <session> --include-memory --reads "<run_dir>/knowledge-reads.json"` + `--from-search <search-id>`).
|
|
15
|
+
2. Exclude already-shipped features from spec scope and carry lessons learned into P1 risk assessment and P4 ADRs.
|
|
16
|
+
|
|
17
|
+
## Boundaries & Exit Gates
|
|
18
|
+
|
|
19
|
+
- **Document-only**: zero implementation code edits; write outputs exclusively under `{run_dir}/outputs/`.
|
|
20
|
+
- **Phase gates**: P2 requires `outputs/product-brief.md` + `>=5` terms in `outputs/glossary.json`; P3 requires `outputs/requirements/_index.md` with MoSCoW prioritization & traceability.
|
|
21
|
+
- **Exit gates**: `phases-complete` (P2–P5 documents written and cross-linked) and `readiness-passed` (P6 readiness check `>= 80%`, or `60–79%` documented with explicit caveats after up to 2 auto-fix passes).
|
|
@@ -0,0 +1,28 @@
|
|
|
1
|
+
# Workflow: ew-blueprint
|
|
2
|
+
|
|
3
|
+
6-phase formal specification chain: `P1 Discovery -> P1.5 Clarification -> P2 Product Brief -> P3 PRD -> P4 Architecture -> P5 Epics -> P6 Readiness Check`.
|
|
4
|
+
|
|
5
|
+
## Phase Execution
|
|
6
|
+
|
|
7
|
+
1. **P1 Discovery**:
|
|
8
|
+
- Confirm spec profile (`service` / `api` / `library` / `platform`) and depth (`light` / `standard` / `comprehensive`), saving `outputs/blueprint-config.json`.
|
|
9
|
+
- Ground existing system context via read-only codebase exploration (`evolve code search` + optional subagent, joined before P2) -> write `outputs/discovery-context.json`. Use `search_web` only if external API constraints are needed.
|
|
10
|
+
2. **P1.5 Requirement Expansion** (skip if `upstream-context` already supplies confirmed requirements):
|
|
11
|
+
- Analyze completeness across functional scope, user scenarios, NFRs, integrations, data model, and failure modes.
|
|
12
|
+
- Clarify critical gaps via structured prompt (`ask_question` or host equivalent, up to 5 rounds) -> write `outputs/refined-requirements.json`.
|
|
13
|
+
3. **P2 Product Brief**:
|
|
14
|
+
- Author `outputs/product-brief.md` (vision, target users, scope, non-goals, KPIs) and `outputs/glossary.json` (`>= 5` domain terms).
|
|
15
|
+
4. **P3 Detailed PRD**:
|
|
16
|
+
- Write `outputs/requirements/_index.md` (summary + MoSCoW table + traceability) plus `outputs/requirements/REQ-NNN-*.md` and `NFR-*.md`.
|
|
17
|
+
5. **P4 Architecture**:
|
|
18
|
+
- Write `outputs/architecture/_index.md` (system boundaries, components, tech stack, data flow) plus `outputs/architecture/ADR-NNN-*.md` reflecting active Wiki constraints.
|
|
19
|
+
6. **P5 Epics & Stories**:
|
|
20
|
+
- Write `outputs/epics/_index.md` (dependency map, MVP cut) and `outputs/epics/EPIC-NNN-*.md`, deriving realistic slice sizes from P4.
|
|
21
|
+
7. **P6 Readiness Check & Packaging**:
|
|
22
|
+
- Validate requirement coverage, ADR traceability, terminology consistency, and testability -> write `outputs/readiness-report.md` and `outputs/blueprint-summary.md`.
|
|
23
|
+
- If readiness `< 60%`, run at most 2 targeted revision passes before escalating (`blocked` / caveats); `60–79%` proceeds with explicit caveats; `>= 80%` passes cleanly.
|
|
24
|
+
- Emit `outputs/context-package.json` (`context-package/1.0`) for downstream `ew-roadmap`, `ew-analyze`, or `ew-plan`.
|
|
25
|
+
|
|
26
|
+
## Wrap-up & Seal
|
|
27
|
+
|
|
28
|
+
Write `{run_dir}/report.md` (`next` proposing `ew-roadmap` or `ew-plan`) and seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate phases-complete --gate readiness-passed --summary "<summary>" --verdict done|done_with_concerns`. Route reusable architectural decisions after sealing through `ew-knowledge` (`evolve workflows show knowledge`).
|
|
@@ -0,0 +1,49 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-brainstorm
|
|
3
|
+
description: Explore a problem space and produce bounded options for the Evolve chain
|
|
4
|
+
argument-hint: '<intent> [--from <artifact-alias>] [-y]'
|
|
5
|
+
wiki_categories: [arch, learning]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: references
|
|
8
|
+
memory: optional
|
|
9
|
+
session-mode: run
|
|
10
|
+
contract:
|
|
11
|
+
consumes:
|
|
12
|
+
- kind: context-package
|
|
13
|
+
alias: upstream-context
|
|
14
|
+
required: false
|
|
15
|
+
schema: context-package/1.0
|
|
16
|
+
role: attachment
|
|
17
|
+
accepts_negative_evidence: true
|
|
18
|
+
- kind: priors
|
|
19
|
+
alias: session-priors
|
|
20
|
+
required: false
|
|
21
|
+
schema: priors/1.0
|
|
22
|
+
role: evidence
|
|
23
|
+
produces:
|
|
24
|
+
- path: outputs/brainstorm.json
|
|
25
|
+
kind: brainstorm
|
|
26
|
+
alias: current-brainstorm
|
|
27
|
+
role: primary
|
|
28
|
+
required: true
|
|
29
|
+
schema: brainstorm/1.0
|
|
30
|
+
- path: outputs/context-package.json
|
|
31
|
+
kind: context-package
|
|
32
|
+
alias: upstream-context
|
|
33
|
+
role: attachment
|
|
34
|
+
required: false
|
|
35
|
+
schema: context-package/1.0
|
|
36
|
+
contract_version: 2.1
|
|
37
|
+
---
|
|
38
|
+
|
|
39
|
+
# Brainstorm
|
|
40
|
+
|
|
41
|
+
Brainstorm is a planning step inside the Evolve Skill. Explore the problem space, record assumptions and alternatives, and leave a bounded option set for the next chain step.
|
|
42
|
+
|
|
43
|
+
1. Read the current Session objective, `boundary_contract`, optional `upstream-context`, and available Wiki evidence. Reuse `session-priors` when the lookup scope matches; otherwise query `wiki_context` + `wiki_reference` (Run MCP) or `evolve context "<intent keywords>" --category arch --include-memory --session <session> --reads "<run_dir>/knowledge-reads.json"` + `--from-search` (CLI fallback).
|
|
44
|
+
2. Separate observed facts, user constraints, open questions, and proposed options.
|
|
45
|
+
3. Compare options against scope, risk, reversibility, and verification cost.
|
|
46
|
+
4. Write `{run_dir}/outputs/brainstorm.json` (with `_meta: { kind: "brainstorm", schema: "brainstorm/1.0", role: "primary", alias: "current-brainstorm" }`) and optional `outputs/context-package.json` (`_meta` matching `context-package/1.0`), citing source evidence for every material conclusion.
|
|
47
|
+
5. Write `{run_dir}/report.md` (`next` proposing `ew-blueprint`, `ew-roadmap`, `ew-analyze`, or `ew-plan` only when durable follow-up artifacts are needed), then seal via `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --summary "<summary>" --verdict done|done_with_concerns`. If blocked, inspect `evolve run check` and recover via `evolve run transition` / `run cancel`.
|
|
48
|
+
|
|
49
|
+
Do not implement changes in this step. Do not replace the Session chain with an untracked recommendation.
|
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-companion
|
|
3
|
+
description: Execute and verify one bounded edit or state-changing task in an Evolve Run without multi-step decomposition.
|
|
4
|
+
argument-hint: '<intent> [--from <alias>]'
|
|
5
|
+
wiki_categories: [coding]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: [constraints, references]
|
|
8
|
+
memory: [error, correction, verified_fix]
|
|
9
|
+
session-mode: run
|
|
10
|
+
contract:
|
|
11
|
+
consumes:
|
|
12
|
+
- kind: review-findings
|
|
13
|
+
alias: latest-review
|
|
14
|
+
required: false
|
|
15
|
+
schema: review-findings/1.0
|
|
16
|
+
role: primary
|
|
17
|
+
accepts_negative_evidence: true
|
|
18
|
+
- kind: diagnosis
|
|
19
|
+
alias: latest-debug
|
|
20
|
+
required: false
|
|
21
|
+
schema: diagnosis/1.0
|
|
22
|
+
role: primary
|
|
23
|
+
accepts_negative_evidence: true
|
|
24
|
+
- kind: fix-directions
|
|
25
|
+
alias: latest-fix-directions
|
|
26
|
+
required: false
|
|
27
|
+
schema: fix-directions/1.0
|
|
28
|
+
role: attachment
|
|
29
|
+
accepts_negative_evidence: true
|
|
30
|
+
- kind: priors
|
|
31
|
+
alias: session-priors
|
|
32
|
+
required: false
|
|
33
|
+
schema: priors/1.0
|
|
34
|
+
role: evidence
|
|
35
|
+
produces:
|
|
36
|
+
- path: outputs/companion-log.md
|
|
37
|
+
kind: companion-log
|
|
38
|
+
role: attachment
|
|
39
|
+
required: false
|
|
40
|
+
schema: companion-log/1.0
|
|
41
|
+
contract_version: 2.1
|
|
42
|
+
---
|
|
43
|
+
|
|
44
|
+
# Companion
|
|
45
|
+
|
|
46
|
+
Execute one bounded single-concern edit or verifiable check inside an Evolve Run (`skills/ew-orchestrate/references/companion-route.md`):
|
|
47
|
+
|
|
48
|
+
1. Read the bound task, complete the Knowledge Gate (`wiki_context`/`wiki_reference` or CLI `--reads`), and inspect any bound `latest-review` / `latest-debug` inputs (`evolve run artifact-read`).
|
|
49
|
+
2. Perform the minimal scoped change and run the narrowest direct verification command.
|
|
50
|
+
3. Record actions, modified files, and observed command results in `{run_dir}/outputs/companion-log.md` (YAML frontmatter `kind: companion-log`, `schema: companion-log/1.0`, `role: attachment`), then seal via `evolve run complete` (or escalate via `evolve run transition ... blocked` / `run cancel` if scope expands past a single concern).
|
|
@@ -0,0 +1,85 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-debug
|
|
3
|
+
description: Scientific root-cause isolation inside the Evolve chain — reproduction, hypothesis testing, backward tracing, and fix directions
|
|
4
|
+
argument-hint: '[issue] [-c] [--from-test <scope>] [--parallel]'
|
|
5
|
+
wiki_categories: [debug, coding]
|
|
6
|
+
search_profile:
|
|
7
|
+
wiki: [constraints, references]
|
|
8
|
+
memory: [error, correction, verified_fix]
|
|
9
|
+
session-mode: run
|
|
10
|
+
required_links:
|
|
11
|
+
- references/prepare.md
|
|
12
|
+
- references/workflow.md
|
|
13
|
+
contract:
|
|
14
|
+
consumes:
|
|
15
|
+
- kind: diagnosis
|
|
16
|
+
alias: latest-debug
|
|
17
|
+
required: false
|
|
18
|
+
schema: diagnosis/1.0
|
|
19
|
+
role: primary
|
|
20
|
+
accepts_negative_evidence: true
|
|
21
|
+
- kind: test-results
|
|
22
|
+
alias: latest-test
|
|
23
|
+
required: false
|
|
24
|
+
schema: test-results/1.0
|
|
25
|
+
role: primary
|
|
26
|
+
accepts_negative_evidence: true
|
|
27
|
+
- kind: auto-test-report
|
|
28
|
+
alias: latest-auto-test
|
|
29
|
+
required: false
|
|
30
|
+
schema: auto-test-report/1.0
|
|
31
|
+
role: primary
|
|
32
|
+
accepts_negative_evidence: true
|
|
33
|
+
- kind: review-findings
|
|
34
|
+
alias: latest-review
|
|
35
|
+
required: false
|
|
36
|
+
schema: review-findings/1.0
|
|
37
|
+
role: primary
|
|
38
|
+
accepts_negative_evidence: true
|
|
39
|
+
- kind: artifact
|
|
40
|
+
alias: current-execution
|
|
41
|
+
required: false
|
|
42
|
+
schema: artifacts/1.0
|
|
43
|
+
role: primary
|
|
44
|
+
accepts_negative_evidence: true
|
|
45
|
+
- kind: priors
|
|
46
|
+
alias: session-priors
|
|
47
|
+
required: false
|
|
48
|
+
schema: priors/1.0
|
|
49
|
+
role: evidence
|
|
50
|
+
produces:
|
|
51
|
+
- path: outputs/diagnosis.json
|
|
52
|
+
kind: diagnosis
|
|
53
|
+
alias: latest-debug
|
|
54
|
+
role: primary
|
|
55
|
+
required: true
|
|
56
|
+
schema: diagnosis/1.0
|
|
57
|
+
- path: outputs/hypotheses.json
|
|
58
|
+
kind: hypotheses
|
|
59
|
+
role: evidence
|
|
60
|
+
required: false
|
|
61
|
+
schema: hypotheses/1.0
|
|
62
|
+
- path: outputs/reproduction.json
|
|
63
|
+
kind: reproduction
|
|
64
|
+
role: evidence
|
|
65
|
+
required: false
|
|
66
|
+
schema: reproduction/1.0
|
|
67
|
+
- path: outputs/fix-directions.json
|
|
68
|
+
kind: fix-directions
|
|
69
|
+
alias: latest-fix-directions
|
|
70
|
+
role: attachment
|
|
71
|
+
required: false
|
|
72
|
+
schema: fix-directions/1.0
|
|
73
|
+
gates:
|
|
74
|
+
exit:
|
|
75
|
+
- hypothesis-tested
|
|
76
|
+
- evidence-grounded
|
|
77
|
+
contract_version: 2.1
|
|
78
|
+
---
|
|
79
|
+
|
|
80
|
+
# Debug
|
|
81
|
+
|
|
82
|
+
Read [preparation](references/prepare.md), then follow the [debug workflow](references/workflow.md).
|
|
83
|
+
|
|
84
|
+
- Bounded scientific diagnosis inside the Evolve Session chain (for multi-iteration standalone repair campaigns, use `ew-odyssey` debug mode).
|
|
85
|
+
- Produces verified root causes and `fix_directions` (`outputs/diagnosis.json`, `outputs/fix-directions.json`) handed off to `ew-plan --gaps` → `ew-execute`.
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
# Pre-flight: ew-debug
|
|
2
|
+
|
|
3
|
+
Confirm entry mode, Knowledge Gate context, and strict read-only diagnosis invariants before running [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Entry Modes
|
|
6
|
+
|
|
7
|
+
| Mode | Trigger | Symptom Source |
|
|
8
|
+
| --- | --- | --- |
|
|
9
|
+
| Standalone | `<issue>` description | Interactive collection (expected, actual, error, regression window, repro steps) + recent `git log`/`diff` |
|
|
10
|
+
| From test / review | `--from-test` or bound `latest-test` / `latest-review` | Failed scenarios / findings clustered by affected module or flow |
|
|
11
|
+
| Parallel | `--parallel` | One isolated debug subagent per non-overlapping failure cluster (all joined before synthesis) |
|
|
12
|
+
| Continuation | `-c` | Resume from prior failed Run's `evidence` / `understanding` via `run brief` |
|
|
13
|
+
|
|
14
|
+
Missing issue and no bound failure artifact -> error `E001`.
|
|
15
|
+
|
|
16
|
+
## Knowledge & Codebase Pre-load
|
|
17
|
+
|
|
18
|
+
1. Reuse bound `session-priors` (`debug`/`coding`); otherwise run `wiki_context` + `wiki_reference` and `memory_search` + `memory_get` (or CLI `evolve context "<symptom keywords>" --task debug --session <session> --include-memory --reads "<run_dir>/knowledge-reads.json"` + `--from-search <search-id>`) to check known pitfalls and prior fixes.
|
|
19
|
+
2. Run `evolve code search` / `evolve code callers` / `evolve code trace` after the Knowledge Gate to trace propagation paths.
|
|
20
|
+
|
|
21
|
+
## Scientific Boundaries (Iron Law)
|
|
22
|
+
|
|
23
|
+
- **Read-only on repository source**: never apply speculative quick fixes or edit production source files during diagnosis; temporary reproduction probes must be reverted or isolated to `{run_dir}/evidence/`. Fixing belongs to `ew-plan --gaps` -> `ew-execute`.
|
|
24
|
+
- **Evidence before confirmation**: a hypothesis stays `"suspected"` until backed by a live reproduction or concrete `file:line`/log evidence.
|
|
25
|
+
- **Single-variable testing & 3-strike escalation**: test one hypothesis at a time and record append-only observations in `{run_dir}/evidence/evidence.ndjson`. If 3 hypotheses fail, STOP proposing ad-hoc theories and escalate to architectural boundary inspection.
|
|
26
|
+
- **Backward tracing**: trace from symptom origin back to where valid data first turned invalid — fix root cause, never surface symptoms.
|
|
27
|
+
- **Exit gates**: `hypothesis-tested` (repro + isolated hypotheses logged) and `evidence-grounded` (pressure pass done, multi-factor confidence recorded, zero unaddressed contradicting evidence, actionable `affected_files` + `fix_direction`).
|
|
@@ -0,0 +1,31 @@
|
|
|
1
|
+
# Workflow: ew-debug
|
|
2
|
+
|
|
3
|
+
Scientific root-cause pipeline: `Symptom Baseline -> Cluster -> Isolated Hypothesis Investigation -> Confidence & Pressure Pass -> Synthesis & Seal`.
|
|
4
|
+
|
|
5
|
+
## Step 1: Collect Symptoms & Baseline
|
|
6
|
+
|
|
7
|
+
1. Complete the Knowledge Gate and check bound inputs (`latest-test`, `latest-review`, `current-execution`).
|
|
8
|
+
2. Extract reproduction baseline: expected vs actual behavior, exact error output, `git log --oneline -10`, and minimal reproduction command (run and record exact exit code/output into `outputs/reproduction.json`).
|
|
9
|
+
3. Under `--from-test`, group failures into independent component/flow clusters.
|
|
10
|
+
|
|
11
|
+
## Step 2: Isolated Hypothesis Investigation (`hypothesis-tested` gate)
|
|
12
|
+
|
|
13
|
+
Dispatch an isolated read-only investigation subagent (`invoke_subagent` / host equivalent; in `--parallel` mode, one subagent per non-overlapping cluster; **join or cancel all spawned subagents cleanly before Step 3**).
|
|
14
|
+
|
|
15
|
+
Each investigator follows strict discipline:
|
|
16
|
+
1. Form 2–3 ranked hypotheses and test ONE variable at a time via backward tracing (`evolve code trace` + reproduction logs).
|
|
17
|
+
2. Append every test step, observed result, and `file:line` anchor to `{run_dir}/evidence/evidence[-<cluster>].ndjson` and summarize active state in `{run_dir}/evidence/understanding[-<cluster>].md`.
|
|
18
|
+
3. Enforce **3-strike stop**: after 3 falsified hypotheses without confirmation, stop guessing and report architectural contradiction (`INVESTIGATION INCONCLUSIVE` / architecture escalation).
|
|
19
|
+
|
|
20
|
+
## Step 3: Confidence Scoring & Pressure Pass (`evidence-grounded` gate)
|
|
21
|
+
|
|
22
|
+
Compute multi-factor confidence (`evidence_depth * 0.30 + evidence_strength * 0.25 + coverage_breadth * 0.20 + reproduction * 0.15 + consistency * 0.10`; `< 40%` low, `40–70%` medium, `> 70%` high) and run two mandatory checks before writing outputs:
|
|
23
|
+
- **Pressure Pass**: cross-check confirmed causes against every refuted hypothesis and contradicting observation.
|
|
24
|
+
- **Devil's Advocate** (when isolation `> 0.7`): verify whether the apparent cause hides a deeper upstream invariant violation.
|
|
25
|
+
- **Readiness check**: confirm evidence completeness `>= 40%`, pressure pass complete, zero unresolved contradicting evidence, and concrete `affected_files[]` + `fix_direction`.
|
|
26
|
+
|
|
27
|
+
## Step 4: Write Outputs & Seal
|
|
28
|
+
|
|
29
|
+
1. Write `{run_dir}/outputs/diagnosis.json` (`diagnosis/1.0`: `status: confirmed|partial|inconclusive`, `clusters[]`, `confidence`, `pressure_pass`), `{run_dir}/outputs/hypotheses.json`, `{run_dir}/outputs/reproduction.json`, and `{run_dir}/outputs/fix-directions.json` (actionable root cause + target `file:line` + verification criteria for `ew-plan --gaps`).
|
|
30
|
+
2. Write `{run_dir}/report.md` (`next` pointing to `ew-plan --gaps` when confirmed fixes are needed).
|
|
31
|
+
3. Seal via fenced `evolve run complete <run_id> --session <session> --actor <actor> --expected-orchestration-revision <rev> --expected-run-revision <rev> --gate hypothesis-tested --gate evidence-grounded --summary "<summary>" --verdict done|done_with_concerns`. Stage verified pitfall/root-cause patterns after sealing via `ew-knowledge`.
|
|
@@ -0,0 +1,74 @@
|
|
|
1
|
+
---
|
|
2
|
+
name: ew-execute
|
|
3
|
+
wiki_categories: [coding]
|
|
4
|
+
search_profile:
|
|
5
|
+
wiki: [constraints, references]
|
|
6
|
+
memory: [error, correction, verified_fix]
|
|
7
|
+
description: Implement code changes following the DAG and waves of current-plan, producing implementation results and a local smoke self-check
|
|
8
|
+
argument-hint: '[scope] [-y] [--task TASK-ID] [--method agent|cli|auto] [--executor <tool>] [--auto-commit]'
|
|
9
|
+
contract:
|
|
10
|
+
consumes:
|
|
11
|
+
- kind: plan
|
|
12
|
+
alias: current-plan
|
|
13
|
+
required: false
|
|
14
|
+
schema: plan/1.0
|
|
15
|
+
role: primary
|
|
16
|
+
- kind: review-findings
|
|
17
|
+
alias: latest-review
|
|
18
|
+
required: false
|
|
19
|
+
schema: review-findings/1.0
|
|
20
|
+
role: primary
|
|
21
|
+
accepts_negative_evidence: true
|
|
22
|
+
- kind: fix-directions
|
|
23
|
+
alias: latest-fix-directions
|
|
24
|
+
required: false
|
|
25
|
+
schema: fix-directions/1.0
|
|
26
|
+
role: attachment
|
|
27
|
+
accepts_negative_evidence: true
|
|
28
|
+
- kind: diagnosis
|
|
29
|
+
alias: latest-debug
|
|
30
|
+
required: false
|
|
31
|
+
schema: diagnosis/1.0
|
|
32
|
+
role: primary
|
|
33
|
+
accepts_negative_evidence: true
|
|
34
|
+
- kind: priors
|
|
35
|
+
alias: session-priors
|
|
36
|
+
required: false
|
|
37
|
+
schema: priors/1.0
|
|
38
|
+
role: evidence
|
|
39
|
+
produces:
|
|
40
|
+
- path: outputs/execution.json
|
|
41
|
+
kind: artifact
|
|
42
|
+
alias: current-execution
|
|
43
|
+
role: primary
|
|
44
|
+
required: true
|
|
45
|
+
schema: artifacts/1.0
|
|
46
|
+
- path: outputs/task-results.json
|
|
47
|
+
kind: task-results
|
|
48
|
+
role: attachment
|
|
49
|
+
required: false
|
|
50
|
+
schema: task-results/1.0
|
|
51
|
+
- path: outputs/self-check.json
|
|
52
|
+
kind: self-check
|
|
53
|
+
role: evidence
|
|
54
|
+
required: false
|
|
55
|
+
schema: self-check/1.0
|
|
56
|
+
- path: outputs/change-manifest.json
|
|
57
|
+
kind: change-manifest
|
|
58
|
+
role: evidence
|
|
59
|
+
required: false
|
|
60
|
+
schema: change-manifest/1.0
|
|
61
|
+
gates:
|
|
62
|
+
exit:
|
|
63
|
+
- execution-complete
|
|
64
|
+
- self-check-passed
|
|
65
|
+
contract_version: 2.1
|
|
66
|
+
required_links:
|
|
67
|
+
- references/prepare.md
|
|
68
|
+
- references/workflow.md
|
|
69
|
+
session-mode: run
|
|
70
|
+
---
|
|
71
|
+
|
|
72
|
+
# Execute
|
|
73
|
+
|
|
74
|
+
Read [preparation](references/prepare.md), then follow the [workflow](references/workflow.md).
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
# Pre-flight: ew-execute
|
|
2
|
+
|
|
3
|
+
Verify plan availability, upstream compatibility, and execution invariants before running [workflow](workflow.md).
|
|
4
|
+
|
|
5
|
+
## Degradation Routing (when `current-plan` is absent)
|
|
6
|
+
|
|
7
|
+
Never proceed to Step 1+ or fabricate a plan artifact. Inspect injected upstreams and route:
|
|
8
|
+
|
|
9
|
+
| Available upstream | Scope | Action |
|
|
10
|
+
|---|---|---|
|
|
11
|
+
| `latest-review` | <=3 findings, each <=2 files | Close/cancel run -> Evolve internal Companion route with findings |
|
|
12
|
+
| `latest-review` | >3 findings or cross-module | Cancel Run -> `ew-plan --gaps` (or `ew-odyssey-planex`) |
|
|
13
|
+
| `latest-debug` (with fix-directions) | <=2 files vs >2 files | `ew-companion` if <=2 files; `ew-plan --gaps` (or `ew-odyssey-planex`) otherwise |
|
|
14
|
+
| None | — | Report `E001`, transition Run `blocked` / cancel, require `ew-plan` first |
|
|
15
|
+
|
|
16
|
+
Never call `run complete` without `outputs/execution.json` — exit degradation via `evolve run cancel` (or `evolve run transition ... blocked`) with current revision fences and record the re-route reason in `report.md` (`concerns`/`next`).
|
|
17
|
+
|
|
18
|
+
## Artifact Compatibility Recovery
|
|
19
|
+
|
|
20
|
+
For an incompatible sealed input, inspect it via `evolve run artifact-read`, cancel the attempt with current revision fences, insert a producer step ahead of the pending consumer to republish a derived compatibility artifact + receipt, verify publication, and dispatch via `evolve run next`. Never bypass with chain skip, Run rebind, registry mutation, or mutating the source artifact.
|
|
21
|
+
|
|
22
|
+
## Execution Invariants
|
|
23
|
+
|
|
24
|
+
- **Plan interpretation**: handle `source_format: pi-markdown` by deriving ordered tasks, dependencies, and acceptance checks from `markdown` without writing back over `current-plan`.
|
|
25
|
+
- **Same-wave safety & commits**: parallelize only non-colliding `files[]` per wave; atomic git commits run only when `--auto-commit` is enabled.
|
|
26
|
+
- **Evidence & smoke scope**: record real per-task commands, files, and convergence checks (<=3 fix attempts before `blocked` checkpoint + `upstream_blocked` propagation). `self-check` is only a scoped build/test smoke for `ew-review` — `gaps_found` does not block completion, and formal acceptance belongs to `ew-review`.
|
|
27
|
+
- **Incremental learnings & issues**: sync `issue_id` status on completion (confirm unless `-y`); hand off candidate staging to `ew-knowledge` (`evolve workflows show knowledge`) at wrap-up without writing Wiki files directly.
|