devrites 5.5.0 → 5.6.0
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/CHANGELOG.md +6 -0
- package/README.md +8 -6
- package/engine/internal/devritespaths/paths.go +3 -0
- package/engine/internal/hostpack/hostpack.go +45 -6
- package/engine/internal/hostpack/hostpack_test.go +29 -13
- package/engine/internal/install/apply.go +14 -5
- package/engine/internal/install/install.go +8 -2
- package/engine/internal/install/install_test.go +12 -5
- package/engine/internal/install/merge.go +5 -0
- package/engine/internal/install/preflight.go +20 -2
- package/engine/internal/install/uninstall.go +5 -0
- package/engine/internal/install/update.go +1 -1
- package/install.sh +4 -1
- package/pack/generated/README.md +5 -1
- package/pack/generated/pi/AGENTS.md +22 -0
- package/pack/generated/pi/agents/devrites-code-reviewer.md +142 -0
- package/pack/generated/pi/agents/devrites-devex-reviewer.md +124 -0
- package/pack/generated/pi/agents/devrites-doubt-reviewer.md +88 -0
- package/pack/generated/pi/agents/devrites-evidence-scout.md +72 -0
- package/pack/generated/pi/agents/devrites-frontend-reviewer.md +116 -0
- package/pack/generated/pi/agents/devrites-performance-reviewer.md +115 -0
- package/pack/generated/pi/agents/devrites-plan-drafter.md +99 -0
- package/pack/generated/pi/agents/devrites-plan-reviewer.md +142 -0
- package/pack/generated/pi/agents/devrites-proof-runner.md +74 -0
- package/pack/generated/pi/agents/devrites-retrospector.md +61 -0
- package/pack/generated/pi/agents/devrites-security-auditor.md +109 -0
- package/pack/generated/pi/agents/devrites-simplifier-reviewer.md +94 -0
- package/pack/generated/pi/agents/devrites-slice-wright.md +204 -0
- package/pack/generated/pi/agents/devrites-spec-reviewer.md +96 -0
- package/pack/generated/pi/agents/devrites-strategy-reviewer.md +100 -0
- package/pack/generated/pi/agents/devrites-test-analyst.md +94 -0
- package/pack/generated/pi/agents/devrites-upgrade-planner.md +89 -0
- package/pack/generated/pi/prompts/rite-adopt.md +5 -0
- package/pack/generated/pi/prompts/rite-autocomplete.md +5 -0
- package/pack/generated/pi/prompts/rite-build.md +5 -0
- package/pack/generated/pi/prompts/rite-clarify.md +5 -0
- package/pack/generated/pi/prompts/rite-converge.md +5 -0
- package/pack/generated/pi/prompts/rite-customize.md +5 -0
- package/pack/generated/pi/prompts/rite-define.md +5 -0
- package/pack/generated/pi/prompts/rite-doctor.md +5 -0
- package/pack/generated/pi/prompts/rite-dogfood.md +5 -0
- package/pack/generated/pi/prompts/rite-explain.md +5 -0
- package/pack/generated/pi/prompts/rite-frame.md +5 -0
- package/pack/generated/pi/prompts/rite-handoff.md +5 -0
- package/pack/generated/pi/prompts/rite-learn.md +5 -0
- package/pack/generated/pi/prompts/rite-plan.md +5 -0
- package/pack/generated/pi/prompts/rite-polish.md +5 -0
- package/pack/generated/pi/prompts/rite-pov.md +5 -0
- package/pack/generated/pi/prompts/rite-pr-feedback.md +5 -0
- package/pack/generated/pi/prompts/rite-pressure-test.md +5 -0
- package/pack/generated/pi/prompts/rite-prototype.md +5 -0
- package/pack/generated/pi/prompts/rite-prove.md +5 -0
- package/pack/generated/pi/prompts/rite-quick.md +5 -0
- package/pack/generated/pi/prompts/rite-resolve.md +5 -0
- package/pack/generated/pi/prompts/rite-review.md +5 -0
- package/pack/generated/pi/prompts/rite-seal.md +5 -0
- package/pack/generated/pi/prompts/rite-ship.md +5 -0
- package/pack/generated/pi/prompts/rite-spec.md +5 -0
- package/pack/generated/pi/prompts/rite-status.md +5 -0
- package/pack/generated/pi/prompts/rite-temper.md +5 -0
- package/pack/generated/pi/prompts/rite-upgrade.md +5 -0
- package/pack/generated/pi/prompts/rite-vet.md +5 -0
- package/pack/generated/pi/prompts/rite-watch-pr.md +5 -0
- package/pack/generated/pi/prompts/rite-zoom-out.md +5 -0
- package/pack/generated/pi/prompts/rite.md +5 -0
- package/pack/generated/pi/skills/devrites-api-interface/SKILL.md +63 -0
- package/pack/generated/pi/skills/devrites-audit/SKILL.md +50 -0
- package/pack/generated/pi/skills/devrites-browser-proof/SKILL.md +76 -0
- package/pack/generated/pi/skills/devrites-browser-proof/reference/browser-performance.md +15 -0
- package/pack/generated/pi/skills/devrites-browser-proof/reference/visual-verdict.md +34 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/SKILL.md +96 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/build-the-loop.md +58 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/cleanup-and-classify.md +34 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/hypotheses.md +17 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/instrumentation.md +21 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/regression-test.md +30 -0
- package/pack/generated/pi/skills/devrites-debug-recovery/reference/trace.md +25 -0
- package/pack/generated/pi/skills/devrites-doubt/SKILL.md +79 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/SKILL.md +86 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/craft.md +63 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/design-references.md +116 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/fullstack.md +46 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/quality-standards.md +294 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/reuse-first.md +53 -0
- package/pack/generated/pi/skills/devrites-frontend-craft/reference/shape.md +56 -0
- package/pack/generated/pi/skills/devrites-interview/SKILL.md +102 -0
- package/pack/generated/pi/skills/devrites-lib/SKILL.md +58 -0
- package/pack/generated/pi/skills/devrites-lib/reference/candidate-integrity.md +42 -0
- package/pack/generated/pi/skills/devrites-lib/reference/intent-map.md +64 -0
- package/pack/generated/pi/skills/devrites-lib/reference/orchestration-profiles.md +27 -0
- package/pack/generated/pi/skills/devrites-lib/reference/parallel-dispatch.md +73 -0
- package/pack/generated/pi/skills/devrites-lib/reference/reply-contract.md +88 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/README.md +60 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/acceptance-preserving-reslice.md +30 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/afk-hitl.md +398 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/agents.md +99 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/anti-patterns.md +48 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/browser-proof-checklist.md +24 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/ci-cd.md +50 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/code-navigation.md +43 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/code-review.md +108 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/coding-style.md +48 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/context-hygiene.md +109 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/core.md +167 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/data-integrity.md +118 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/debug-recovery.md +28 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/definition-of-done.md +19 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/deprecation.md +31 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/developer-experience.md +119 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/development-workflow.md +29 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/documentation.md +43 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/edge-case-trace.md +92 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/elicitation.md +85 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/error-handling.md +47 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/git-workflow.md +49 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/hooks.md +25 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/integration-reliability.md +102 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/loop-operations.md +85 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/observability.md +88 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/one-shot-actions.md +97 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/patterns.md +68 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/performance.md +51 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/principles.md +42 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/prose-style.md +123 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/release/ship-checklist.md +8 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/repository-topology.md +80 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/review-checklist.md +12 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/security-checklist.md +25 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/security.md +202 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/skill-authoring.md +209 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/spec-grammar.md +197 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/test-proof-checklist.md +13 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/testing.md +212 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/tooling.md +92 -0
- package/pack/generated/pi/skills/devrites-lib/reference/standards/workflow-artifacts.md +427 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/code.md +44 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/comparison.md +42 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/diagram.md +51 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/index.md +66 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/input.md +46 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/outline-template.md +106 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/plan.md +48 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/slides.md +40 -0
- package/pack/generated/pi/skills/devrites-lib/reference/visual-playbooks/table.md +42 -0
- package/pack/generated/pi/skills/devrites-lib/reference/workspace-artifact-schema.md +267 -0
- package/pack/generated/pi/skills/devrites-prose-craft/SKILL.md +73 -0
- package/pack/generated/pi/skills/devrites-prose-craft/reference/banned-phrases.md +132 -0
- package/pack/generated/pi/skills/devrites-prose-craft/reference/examples.md +131 -0
- package/pack/generated/pi/skills/devrites-prose-craft/reference/structures.md +196 -0
- package/pack/generated/pi/skills/devrites-source-driven/SKILL.md +52 -0
- package/pack/generated/pi/skills/devrites-ux-shape/SKILL.md +134 -0
- package/pack/generated/pi/skills/devrites-ux-shape/reference/brief-template.md +108 -0
- package/pack/generated/pi/skills/devrites-ux-shape/reference/visual-direction-probe.md +48 -0
- package/pack/generated/pi/skills/rite/SKILL.md +148 -0
- package/pack/generated/pi/skills/rite/reference/menu.md +48 -0
- package/pack/generated/pi/skills/rite-adopt/SKILL.md +52 -0
- package/pack/generated/pi/skills/rite-adopt/reference/adoption.md +19 -0
- package/pack/generated/pi/skills/rite-adopt/reference/anti-patterns.md +19 -0
- package/pack/generated/pi/skills/rite-autocomplete/SKILL.md +132 -0
- package/pack/generated/pi/skills/rite-autocomplete/reference/decision-policy.md +41 -0
- package/pack/generated/pi/skills/rite-autocomplete/reference/loop.md +148 -0
- package/pack/generated/pi/skills/rite-autocomplete/reference/stop-conditions.md +92 -0
- package/pack/generated/pi/skills/rite-build/SKILL.md +96 -0
- package/pack/generated/pi/skills/rite-build/reference/afk-discipline.md +145 -0
- package/pack/generated/pi/skills/rite-build/reference/anti-patterns.md +23 -0
- package/pack/generated/pi/skills/rite-build/reference/checkpoint-protocol.md +120 -0
- package/pack/generated/pi/skills/rite-build/reference/checkpoint.md +44 -0
- package/pack/generated/pi/skills/rite-build/reference/frontend-trigger.md +39 -0
- package/pack/generated/pi/skills/rite-build/reference/one-slice-cycle.md +50 -0
- package/pack/generated/pi/skills/rite-build/reference/output.md +33 -0
- package/pack/generated/pi/skills/rite-build/reference/parallel-batch.md +205 -0
- package/pack/generated/pi/skills/rite-build/reference/phase-contract.md +87 -0
- package/pack/generated/pi/skills/rite-build/reference/spec-drift-guard.md +84 -0
- package/pack/generated/pi/skills/rite-build/reference/tdd.md +27 -0
- package/pack/generated/pi/skills/rite-build/reference/wright-dispatch.md +89 -0
- package/pack/generated/pi/skills/rite-clarify/SKILL.md +99 -0
- package/pack/generated/pi/skills/rite-clarify/reference/anti-patterns.md +24 -0
- package/pack/generated/pi/skills/rite-clarify/reference/decision-coverage.md +55 -0
- package/pack/generated/pi/skills/rite-converge/SKILL.md +145 -0
- package/pack/generated/pi/skills/rite-converge/reference/anti-patterns.md +35 -0
- package/pack/generated/pi/skills/rite-converge/reference/convergence-assessment.md +65 -0
- package/pack/generated/pi/skills/rite-customize/SKILL.md +60 -0
- package/pack/generated/pi/skills/rite-define/SKILL.md +169 -0
- package/pack/generated/pi/skills/rite-define/reference/anti-patterns.md +26 -0
- package/pack/generated/pi/skills/rite-define/reference/gates.md +154 -0
- package/pack/generated/pi/skills/rite-define/reference/plan-template.md +149 -0
- package/pack/generated/pi/skills/rite-doctor/SKILL.md +69 -0
- package/pack/generated/pi/skills/rite-dogfood/SKILL.md +55 -0
- package/pack/generated/pi/skills/rite-explain/SKILL.md +152 -0
- package/pack/generated/pi/skills/rite-explain/reference/intake.md +89 -0
- package/pack/generated/pi/skills/rite-frame/SKILL.md +115 -0
- package/pack/generated/pi/skills/rite-frame/reference/failure-modes.md +66 -0
- package/pack/generated/pi/skills/rite-handoff/SKILL.md +97 -0
- package/pack/generated/pi/skills/rite-handoff/reference/handoff-template.md +44 -0
- package/pack/generated/pi/skills/rite-learn/SKILL.md +72 -0
- package/pack/generated/pi/skills/rite-plan/SKILL.md +186 -0
- package/pack/generated/pi/skills/rite-plan/reference/anti-patterns.md +34 -0
- package/pack/generated/pi/skills/rite-plan/reference/dependency-graph.md +48 -0
- package/pack/generated/pi/skills/rite-plan/reference/replan-and-repair.md +105 -0
- package/pack/generated/pi/skills/rite-plan/reference/slicing.md +167 -0
- package/pack/generated/pi/skills/rite-plan/reference/task-breakdown.md +42 -0
- package/pack/generated/pi/skills/rite-polish/SKILL.md +104 -0
- package/pack/generated/pi/skills/rite-polish/reference/adr-promotion.md +11 -0
- package/pack/generated/pi/skills/rite-polish/reference/anti-ai-slop.md +187 -0
- package/pack/generated/pi/skills/rite-polish/reference/anti-patterns.md +30 -0
- package/pack/generated/pi/skills/rite-polish/reference/backend-polish.md +80 -0
- package/pack/generated/pi/skills/rite-polish/reference/browser-polish-evidence.md +33 -0
- package/pack/generated/pi/skills/rite-polish/reference/code.md +82 -0
- package/pack/generated/pi/skills/rite-polish/reference/design-memory.md +117 -0
- package/pack/generated/pi/skills/rite-polish/reference/design-system-discovery.md +8 -0
- package/pack/generated/pi/skills/rite-polish/reference/harden-checklist.md +109 -0
- package/pack/generated/pi/skills/rite-polish/reference/ledger.md +65 -0
- package/pack/generated/pi/skills/rite-polish/reference/ui.md +137 -0
- package/pack/generated/pi/skills/rite-pov/SKILL.md +58 -0
- package/pack/generated/pi/skills/rite-pr-feedback/SKILL.md +54 -0
- package/pack/generated/pi/skills/rite-pressure-test/SKILL.md +67 -0
- package/pack/generated/pi/skills/rite-prototype/SKILL.md +104 -0
- package/pack/generated/pi/skills/rite-prove/SKILL.md +120 -0
- package/pack/generated/pi/skills/rite-prove/reference/acceptance-proof.md +88 -0
- package/pack/generated/pi/skills/rite-prove/reference/anti-patterns.md +25 -0
- package/pack/generated/pi/skills/rite-prove/reference/browser-proof.md +51 -0
- package/pack/generated/pi/skills/rite-prove/reference/failure-triage.md +43 -0
- package/pack/generated/pi/skills/rite-prove/reference/proof-ladder.md +28 -0
- package/pack/generated/pi/skills/rite-prove/reference/test-command-discovery.md +30 -0
- package/pack/generated/pi/skills/rite-quick/SKILL.md +82 -0
- package/pack/generated/pi/skills/rite-resolve/SKILL.md +95 -0
- package/pack/generated/pi/skills/rite-resolve/reference/answer-protocol.md +118 -0
- package/pack/generated/pi/skills/rite-review/SKILL.md +170 -0
- package/pack/generated/pi/skills/rite-review/reference/anti-patterns.md +32 -0
- package/pack/generated/pi/skills/rite-review/reference/cognitive-load.md +90 -0
- package/pack/generated/pi/skills/rite-review/reference/feature-scoped-review.md +26 -0
- package/pack/generated/pi/skills/rite-review/reference/five-axis-review.md +66 -0
- package/pack/generated/pi/skills/rite-review/reference/nielsen-heuristics.md +126 -0
- package/pack/generated/pi/skills/rite-review/reference/performance-checklist.md +80 -0
- package/pack/generated/pi/skills/rite-review/reference/performance-review.md +14 -0
- package/pack/generated/pi/skills/rite-review/reference/security-review.md +42 -0
- package/pack/generated/pi/skills/rite-seal/SKILL.md +75 -0
- package/pack/generated/pi/skills/rite-seal/reference/anti-patterns.md +29 -0
- package/pack/generated/pi/skills/rite-seal/reference/final-evidence.md +41 -0
- package/pack/generated/pi/skills/rite-seal/reference/go-no-go.md +29 -0
- package/pack/generated/pi/skills/rite-seal/reference/output.md +5 -0
- package/pack/generated/pi/skills/rite-seal/reference/phase-contract.md +47 -0
- package/pack/generated/pi/skills/rite-seal/reference/risk-and-rollback.md +56 -0
- package/pack/generated/pi/skills/rite-seal/reference/seal-template.md +27 -0
- package/pack/generated/pi/skills/rite-ship/SKILL.md +88 -0
- package/pack/generated/pi/skills/rite-ship/reference/anti-patterns.md +28 -0
- package/pack/generated/pi/skills/rite-ship/reference/close-out.md +68 -0
- package/pack/generated/pi/skills/rite-ship/reference/git-ship.md +120 -0
- package/pack/generated/pi/skills/rite-ship/reference/rollout.md +62 -0
- package/pack/generated/pi/skills/rite-ship/reference/ship-template.md +39 -0
- package/pack/generated/pi/skills/rite-spec/SKILL.md +150 -0
- package/pack/generated/pi/skills/rite-spec/reference/acceptance-criteria.md +31 -0
- package/pack/generated/pi/skills/rite-spec/reference/ai-spec-template.md +40 -0
- package/pack/generated/pi/skills/rite-spec/reference/anti-patterns.md +27 -0
- package/pack/generated/pi/skills/rite-spec/reference/interview-patterns.md +56 -0
- package/pack/generated/pi/skills/rite-spec/reference/investigation.md +83 -0
- package/pack/generated/pi/skills/rite-spec/reference/question-protocol.md +36 -0
- package/pack/generated/pi/skills/rite-spec/reference/references-intake.md +62 -0
- package/pack/generated/pi/skills/rite-spec/reference/spec-checklists.md +89 -0
- package/pack/generated/pi/skills/rite-spec/reference/spec-template.md +154 -0
- package/pack/generated/pi/skills/rite-spec/reference/state-workspace.md +227 -0
- package/pack/generated/pi/skills/rite-status/SKILL.md +57 -0
- package/pack/generated/pi/skills/rite-temper/SKILL.md +130 -0
- package/pack/generated/pi/skills/rite-temper/reference/anti-patterns.md +30 -0
- package/pack/generated/pi/skills/rite-temper/reference/review-dimensions.md +66 -0
- package/pack/generated/pi/skills/rite-temper/reference/scope-modes.md +53 -0
- package/pack/generated/pi/skills/rite-temper/reference/significance.md +46 -0
- package/pack/generated/pi/skills/rite-temper/reference/strategy-template.md +90 -0
- package/pack/generated/pi/skills/rite-upgrade/SKILL.md +121 -0
- package/pack/generated/pi/skills/rite-vet/SKILL.md +193 -0
- package/pack/generated/pi/skills/rite-vet/reference/anti-patterns.md +43 -0
- package/pack/generated/pi/skills/rite-vet/reference/artifacts.md +202 -0
- package/pack/generated/pi/skills/rite-vet/reference/cross-model.md +19 -0
- package/pack/generated/pi/skills/rite-vet/reference/depth.md +59 -0
- package/pack/generated/pi/skills/rite-vet/reference/eng-lenses.md +48 -0
- package/pack/generated/pi/skills/rite-vet/reference/review-axes.md +201 -0
- package/pack/generated/pi/skills/rite-watch-pr/SKILL.md +85 -0
- package/pack/generated/pi/skills/rite-zoom-out/SKILL.md +69 -0
- package/package.json +3 -2
- package/scripts/build-host-artifacts.sh +54 -4
- package/scripts/pi-generate.sh +198 -0
|
@@ -0,0 +1,44 @@
|
|
|
1
|
+
# Checkpoint: proven slices land as local WIP commits
|
|
2
|
+
|
|
3
|
+
A slice's source never stays uncommitted after its gates are green: at RECORD
|
|
4
|
+
the orchestrator commits the proven slice as a local `WIP`, so the working
|
|
5
|
+
tree stays clean and the work survives a crash or compaction.
|
|
6
|
+
|
|
7
|
+
## The checkpoint commit: orchestrator, at RECORD, after gates are green
|
|
8
|
+
A checkpoint records a **proven** slice only after its gates are green. Stage the exact
|
|
9
|
+
slice-owned candidate paths from the manifest, passing each literal path separately.
|
|
10
|
+
Never stage `touched-files.md`, a directory, glob, unrelated path, or user change.
|
|
11
|
+
Verify the staged set, then commit locally with a `[devrites-context]` body:
|
|
12
|
+
|
|
13
|
+
```bash
|
|
14
|
+
git commit -m "WIP(<slug>): <slice>" -m "$(cat <<'BODY'
|
|
15
|
+
[devrites-context]
|
|
16
|
+
decisions: <one-line delta this slice added to decisions.md>
|
|
17
|
+
remaining: <pending slices — count or names>
|
|
18
|
+
dead-ends: <approaches ruled out this slice, if any>
|
|
19
|
+
BODY
|
|
20
|
+
)"
|
|
21
|
+
```
|
|
22
|
+
|
|
23
|
+
When host reconciliation already landed the isolated transfer commit, nothing
|
|
24
|
+
is staged and the step no-ops. **Local-only:** never push a checkpoint or let
|
|
25
|
+
scratch work trigger CI.
|
|
26
|
+
|
|
27
|
+
## Restore
|
|
28
|
+
After a crash, a fresh session may read the last `WIP(<slug>)` body as crash context.
|
|
29
|
+
Authoritative state remains in `.devrites/`: validate the body against that workspace;
|
|
30
|
+
never reconstruct or advance state from the commit body. Reload per
|
|
31
|
+
[`context-hygiene.md`](../../devrites-lib/reference/standards/context-hygiene.md)
|
|
32
|
+
(`.devrites/ACTIVE`, `state.md`, `questions.md`, `decisions.md`, `test-plan.md`/`evidence.md`).
|
|
33
|
+
|
|
34
|
+
## Collapse at ship
|
|
35
|
+
WIP commits are scratch and never reach shared history. `/rite-ship` folds them into the
|
|
36
|
+
one atomic feature commit before the Conventional-Commit ladder: see the collapse step in
|
|
37
|
+
[git-ship.md](../../rite-ship/reference/git-ship.md). Result: one clean commit, bisect
|
|
38
|
+
stays green.
|
|
39
|
+
|
|
40
|
+
## Autocomplete
|
|
41
|
+
Checkpoints are unconditional; `/rite-autocomplete` needs no sentinel arming.
|
|
42
|
+
Each wright returns after one slice; HITL stops, while explicit `.devrites/AFK`
|
|
43
|
+
lets the controlling Build root chain another green slice only under its cap
|
|
44
|
+
and pause rules.
|
|
@@ -0,0 +1,39 @@
|
|
|
1
|
+
# Frontend trigger
|
|
2
|
+
|
|
3
|
+
A slice is **frontend/UI** if it touches or plans to touch any of:
|
|
4
|
+
|
|
5
|
+
- React / TSX / JSX; Vue, Svelte, Astro, Angular;
|
|
6
|
+
- Rails Slim / Haml / ERB views; any server-rendered template;
|
|
7
|
+
- CSS, SCSS, Tailwind, design tokens, theme files;
|
|
8
|
+
- components, forms, layout, navigation, dashboard, landing/marketing page;
|
|
9
|
+
- UI copy, empty states, error states, onboarding, settings;
|
|
10
|
+
- screenshots, mockups, visual direction;
|
|
11
|
+
- browser behavior, responsive behavior, accessibility, frontend performance.
|
|
12
|
+
|
|
13
|
+
## When triggered
|
|
14
|
+
- `/rite-spec` applies **`devrites-ux-shape`** (spec step 3a) to write the feature-level
|
|
15
|
+
**`design-brief.md`** before any code: design direction, key states, interaction model,
|
|
16
|
+
optional Figma/image visual-direction probe.
|
|
17
|
+
- `/rite-build` applies **`devrites-frontend-craft`** to the vetted `design-brief.md`
|
|
18
|
+
(register, system, states, anti-AI-slop). If missing or materially changed, shape it
|
|
19
|
+
and return through `/rite-vet` before code.
|
|
20
|
+
- `/rite-prove` applies **`devrites-browser-proof`** (proof ladder + evidence schema).
|
|
21
|
+
- `/rite-polish` runs the full **normalize + polish** workflow.
|
|
22
|
+
- `/rite-review` and `/rite-seal` include frontend UX / a11y / responsive / design-
|
|
23
|
+
system checks.
|
|
24
|
+
|
|
25
|
+
## Fullstack (UI slice that also needs backend)
|
|
26
|
+
If the slice spans both layers, it's both a frontend **and** a backend slice. Define the
|
|
27
|
+
**API/data contract first** (`devrites-api-interface`), build it as one **vertical slice**
|
|
28
|
+
(DB → service → API → UI), apply the engineering rules to the backend and
|
|
29
|
+
`devrites-frontend-craft` to the UI, map each contract error to a real UI state, and
|
|
30
|
+
**prove both layers** (contract tests + browser proof). See
|
|
31
|
+
`devrites-frontend-craft/reference/fullstack.md`.
|
|
32
|
+
|
|
33
|
+
## When NOT triggered
|
|
34
|
+
Pure backend/data/CLI/infra slices skip craft and browser proof, but still get tests
|
|
35
|
+
and evidence. If unsure whether a slice is "UI enough", treat copy/empty/error states
|
|
36
|
+
and any rendered output as UI.
|
|
37
|
+
|
|
38
|
+
Mark `Frontend craft required: yes/no` and `Browser proof required: yes/no` on the
|
|
39
|
+
slice in `tasks.md` so the trigger is explicit, not rediscovered each cycle.
|
|
@@ -0,0 +1,50 @@
|
|
|
1
|
+
# One-slice cycle
|
|
2
|
+
|
|
3
|
+
One wright dispatch builds one thin, proven slice. HITL stops; only explicit
|
|
4
|
+
`.devrites/AFK` lets the controlling root chain another pending slice under the
|
|
5
|
+
green-proof, cap, and pause rules. Each wright returns after exactly one slice.
|
|
6
|
+
This serial cycle is the default `/rite-build`. Opt-in fan-out: [`parallel-batch.md`](parallel-batch.md) (`--parallel N`).
|
|
7
|
+
|
|
8
|
+
## The cycle
|
|
9
|
+
|
|
10
|
+
The orchestrator (`/rite-build`) gates and records; the **wright** writes. See
|
|
11
|
+
[`wright-dispatch.md`](wright-dispatch.md).
|
|
12
|
+
|
|
13
|
+
```text
|
|
14
|
+
SELECT → orchestrator: restate slice goal + acceptance + scope boundary; HITL gate (pause pre-code)
|
|
15
|
+
(SHAPE) → orchestrator: missing UI design-brief.md → shape it, then /rite-vet before dispatch
|
|
16
|
+
DISPATCH → hand the slice contract to devrites-slice-wright (fresh context). Inside the wright:
|
|
17
|
+
ORIENT → load only the files this slice touches; learn the project's idiom; reuse-first
|
|
18
|
+
(RED) → if behavior change: write the failing test first
|
|
19
|
+
IMPLEMENT → smallest complete version; match conventions; devrites-frontend-craft for UI
|
|
20
|
+
VERIFY → writer-safe tests/types/lint; return code + tests
|
|
21
|
+
(DOUBT) → orchestrator, on return: devrites-doubt each non-trivial decision the wright stood up
|
|
22
|
+
— dispatch the initial read-only reviews of distinct decisions in parallel
|
|
23
|
+
(independent claims, fresh contexts); wright fixes stay serial — writers share files
|
|
24
|
+
PROVE → root: required build/browser/E2E, then returned-diff/path review; fail-on-red
|
|
25
|
+
RECORD → orchestrator: after green verification, update state.md/evidence.md and
|
|
26
|
+
upsert the authoritative candidate manifest from the actual scoped diff
|
|
27
|
+
(CHECKPOINT) → orchestrator: commit the proven slice local-only as WIP(<slug>)
|
|
28
|
+
with a [devrites-context] body → clean tree, survives a crash (checkpoint.md)
|
|
29
|
+
NEXT → HITL root reports and stops; AFK root may repeat only under afk-discipline.md
|
|
30
|
+
```
|
|
31
|
+
|
|
32
|
+
## Why the boundary matters
|
|
33
|
+
|
|
34
|
+
Reviewable diffs, early drift signal, HITL decision point, no unproven pile-ups.
|
|
35
|
+
|
|
36
|
+
## Restate the scope boundary
|
|
37
|
+
|
|
38
|
+
Before coding, write what this slice will and will **not** touch. This is the contract
|
|
39
|
+
you check yourself against: anything outside it is scope creep or a drift event.
|
|
40
|
+
|
|
41
|
+
## When the slice can't be completed cleanly
|
|
42
|
+
|
|
43
|
+
- Discovered the plan is wrong → **Spec Drift Guard** (record, classify;
|
|
44
|
+
sweep every remaining contract assumption, then one folded repair+vet inline;
|
|
45
|
+
ask only for product/policy/irreversible-risk).
|
|
46
|
+
- Slice is bigger than one cycle → `/rite-plan reslice` inline when AC is
|
|
47
|
+
preserved; do not emit a human Fix.
|
|
48
|
+
- Blocked on a failing dependency → record in `state.md`, `/rite-plan unblock`
|
|
49
|
+
inline when the reroute is technical.
|
|
50
|
+
Never power through by guessing.
|
|
@@ -0,0 +1,33 @@
|
|
|
1
|
+
# rite-build output
|
|
2
|
+
|
|
3
|
+
**Slices remain:**
|
|
4
|
+
|
|
5
|
+
```text
|
|
6
|
+
Done: built slice <n> — <name>.
|
|
7
|
+
Changed: <files>; state.md, touched-files.md, evidence.md
|
|
8
|
+
Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <none|handled>
|
|
9
|
+
Open: <none|blockers|questions>
|
|
10
|
+
Next: /rite-build
|
|
11
|
+
Record: .devrites/work/<slug>/evidence.md
|
|
12
|
+
↻ Hygiene: /clear between slices; /rite-handoff if away > a few hours
|
|
13
|
+
```
|
|
14
|
+
|
|
15
|
+
**All built:**
|
|
16
|
+
|
|
17
|
+
```text
|
|
18
|
+
Done: built slice <n> — <name>; all slices built.
|
|
19
|
+
Changed: <files>; state.md, touched-files.md, evidence.md
|
|
20
|
+
Evidence: acceptance met; tests <cmd> → pass; browser <summary|n/a>; drift <none|handled>
|
|
21
|
+
Open: <none|blockers|questions>
|
|
22
|
+
Next: /rite-prove
|
|
23
|
+
Record: .devrites/work/<slug>/evidence.md
|
|
24
|
+
↻ Hygiene: /clear before /rite-prove; /rite-handoff if away > a few hours
|
|
25
|
+
```
|
|
26
|
+
|
|
27
|
+
HITL returns after one green slice. Only explicit `.devrites/AFK` lets the
|
|
28
|
+
controlling root chain another pending slice after green-proof, cap, and pause
|
|
29
|
+
gates. Every `devrites-slice-wright` returns after exactly one slice.
|
|
30
|
+
|
|
31
|
+
At all built, Build never enters `/rite-prove` automatically; a higher-level
|
|
32
|
+
orchestrator may invoke it only under its own contract. Awaiting-human or
|
|
33
|
+
stopped states use the shared reply contract.
|
|
@@ -0,0 +1,205 @@
|
|
|
1
|
+
# Parallel batch (`--parallel N`)
|
|
2
|
+
|
|
3
|
+
Opt-in only. Default `/rite-build` stays [`one-slice-cycle.md`](one-slice-cycle.md).
|
|
4
|
+
|
|
5
|
+
## Entry
|
|
6
|
+
|
|
7
|
+
| Input | Behavior |
|
|
8
|
+
| --- | --- |
|
|
9
|
+
| omitted / `--parallel 1` | Serial one-slice |
|
|
10
|
+
| `--parallel N` (**2≤N≤10**) | N is a **cap**, not a quota: run the largest eligible set ≤ N |
|
|
11
|
+
| non-integer / `N≤0` / `N>10` | Hard refuse (no silent clamp) |
|
|
12
|
+
| Autocomplete, no flag | Same path, cap from sentinel `max_parallel` else 10; serial only when ineligible |
|
|
13
|
+
|
|
14
|
+
AFK caps `N`. Charge green siblings once after integrate; abort /
|
|
15
|
+
integrate-failed → **0**. `parallel create` refuses while a lease exists.
|
|
16
|
+
Reconcile retained repair-round artifacts by exact causal fingerprint before honoring a stored blocked status/verdict. Blocked status, round count, or distinct finding alone cannot stop cold resume: establish missing or stale review coverage under step 4; repair unless a stop condition remains evidenced.
|
|
17
|
+
|
|
18
|
+
## Dynamic selection and re-batching
|
|
19
|
+
|
|
20
|
+
Size each batch by what is runnable **now**, never by the requested number:
|
|
21
|
+
|
|
22
|
+
```text
|
|
23
|
+
N_eff = min(
|
|
24
|
+
cap -- --parallel N | sentinel max_parallel | 10 (autocomplete default)
|
|
25
|
+
eligible set -- dependency-satisfied pending slices, pairwise path-disjoint
|
|
26
|
+
AFK headroom -- remaining max_slices, max_agents, max_minutes, review queue
|
|
27
|
+
host capacity -- concurrent worktree writers + the runtime isolation table
|
|
28
|
+
)
|
|
29
|
+
```
|
|
30
|
+
|
|
31
|
+
Select **greedily in plan order**: walk pending slices whose `depends_on` are built and
|
|
32
|
+
add each one while it stays pairwise disjoint with the selected set and the cap is not
|
|
33
|
+
reached. Then `N_eff ≥ 2` → parallel batch; `N_eff = 1` → the serial one-slice cycle;
|
|
34
|
+
nothing pending → Prove. A cap that cannot be filled is normal: take fewer.
|
|
35
|
+
|
|
36
|
+
**Re-batch automatically.** After integrate + cleanup are green, re-read `state.md`,
|
|
37
|
+
the pending slices (`observe slice`), and the updated tree, then recompute: integrated
|
|
38
|
+
siblings leave the pending set and free their paths, and satisfied dependencies unlock
|
|
39
|
+
new slices. Repeat until no pending slice remains. Under `.devrites/AFK` and
|
|
40
|
+
`/rite-autocomplete` the repeat is part of the same run — a new batch is another
|
|
41
|
+
`/rite-build --parallel` round inside it, not a new user invocation; HITL stops after
|
|
42
|
+
each batch. A batch of three followed by one of four and then two is the expected shape.
|
|
43
|
+
|
|
44
|
+
## Path-disjoint
|
|
45
|
+
|
|
46
|
+
Exact project-relative source/test paths only. Normalize `\`→`/`. Reject `..`,
|
|
47
|
+
duplicates, absolutes, `.devrites/**`. Empty pairwise intersection required.
|
|
48
|
+
|
|
49
|
+
**SSOT:** `devrites-engine check path-disjoint [--root <dir>] [<json-file>|-]`
|
|
50
|
+
(N≥2 only; pass `--root`). Input is `{"slices":[{"id":"SLICE-002","paths":["src/policy.rs","src/policy/mod.rs"]}]}`
|
|
51
|
+
(or a top-level array) built from each candidate's `Files likely touched`.
|
|
52
|
+
Exit `0` → fan-out; else force serial. Inspect-time
|
|
53
|
+
overlap → sibling **gap** (a shared path is a contract defect). **Failing
|
|
54
|
+
case:** two parallel wrights share a path and fan-out proceeds without that
|
|
55
|
+
check.
|
|
56
|
+
|
|
57
|
+
## Control vs workers
|
|
58
|
+
|
|
59
|
+
Control owns `.devrites/work/<slug>/` (lease + bookkeeping).
|
|
60
|
+
Workers: `.scratch/parallel-wt/<batch>/<slice>/` on
|
|
61
|
+
`devrites/parallel/<slug>/<batch>/<slice>` @ base `B`. Wrights never write
|
|
62
|
+
`.devrites/**`.
|
|
63
|
+
|
|
64
|
+
Lease: `batch_id`, `created_at`, `base_sha`, `n`,
|
|
65
|
+
`status` (`running|aborted|integrate-failed|complete`), `control_pid_or_session`,
|
|
66
|
+
`slices[]` (`id`, `paths`, `worktree_path`, `branch`, `wright_status`,
|
|
67
|
+
`transfer_commit`).
|
|
68
|
+
|
|
69
|
+
## Lifecycle
|
|
70
|
+
|
|
71
|
+
1. Orient/gate; parse the cap; compute `N_eff` and select the eligible set
|
|
72
|
+
([Dynamic selection and re-batching](#dynamic-selection-and-re-batching)) —
|
|
73
|
+
candidates from `orient` `task_graph.slices` + built list, each candidate's
|
|
74
|
+
`Files likely touched` via `observe slice`, disjointness via `check path-disjoint`.
|
|
75
|
+
2. Write lease; freeze `B=HEAD`; `parallel create` worktrees.
|
|
76
|
+
3. Dispatch ≤10 wrights in parallel (cwd=worktree; allowlist; prove `HEAD==B`).
|
|
77
|
+
4. Inspect each returned path list, cumulative diff from `B`, transfer identity,
|
|
78
|
+
and required result fields against the immutable contract. Reject malformed,
|
|
79
|
+
stale, or out-of-scope work. Apply
|
|
80
|
+
[independent Build review](phase-contract.md#independent-build-review): first
|
|
81
|
+
full inventory, then bounded owning-role rechecks after repairs. Gap or
|
|
82
|
+
Critical/Important → `gap`; else approved proof → `green|red|gap`.
|
|
83
|
+
Reviewer fan-out for a batch is itself batched under
|
|
84
|
+
[`parallel-dispatch.md`](../../devrites-lib/reference/parallel-dispatch.md#scale-limits)
|
|
85
|
+
(≈4 concurrent read-only reviewers, 8 only with disjoint paths), and `max_agents`
|
|
86
|
+
headroom bounds the batch size — one batch never assumes unbounded reviewers.
|
|
87
|
+
5. Non-green siblings → **repair round** (below) in the same worktrees; lease
|
|
88
|
+
stays `running` — no abort while repair budget remains. A green sibling →
|
|
89
|
+
`parallel record-green`. No partial integrate. All green → integrate.
|
|
90
|
+
A recoverable RED blocks integration but does not cancel independent safe running siblings.
|
|
91
|
+
Expected test-first RED is not a terminal gate failure. Cancel only for a shared
|
|
92
|
+
invalid foundation, safety/access failure, resource boundary, or explicit stop;
|
|
93
|
+
preserve completed and in-progress recoverable work and classify each result.
|
|
94
|
+
6. Integrate: each `transfer_commit` descends from `B` and diffs path-exact vs
|
|
95
|
+
`B`; squash-apply all in plan order into one `WIP(<slug>):` commit on the
|
|
96
|
+
staging branch (Ship collapses it). Conflict → reset to `B`,
|
|
97
|
+
`integrate-failed`; classify under repair rounds (siblings stay in place).
|
|
98
|
+
7. Success: FF control to the squash commit — the batch lands as one local
|
|
99
|
+
commit, never pushed; union `touched-files.md`; update state/evidence;
|
|
100
|
+
AFK +1 per integrated sibling; optional `check candidate`.
|
|
101
|
+
8. Cleanup runs only after `integrate` marks the lease `complete` — work
|
|
102
|
+
landed in control, so `parallel cleanup` removes worktrees/branches.
|
|
103
|
+
Blocked/human-stopped batches keep lease, worktrees, branches — nothing is
|
|
104
|
+
removed while the batch may resume. `parallel abort` + `cleanup --force`
|
|
105
|
+
abandons the batch — the explicit human discard path; the single
|
|
106
|
+
orchestrator-emitted use is the automatic re-batch under Repair rounds,
|
|
107
|
+
where it acts as the salvage step only (uncommitted allowlisted changes →
|
|
108
|
+
slice-branch commit; branches past `B` kept; a failed salvage keeps the
|
|
109
|
+
worktree) and prints retained refs for the record. `abort` marks the lease
|
|
110
|
+
only — never rewinds control: a moved HEAD is external work, reported not
|
|
111
|
+
reset. Never integrate a rejected transfer commit.
|
|
112
|
+
|
|
113
|
+
## Repair rounds
|
|
114
|
+
|
|
115
|
+
Repair rejected work in place; never discard/rebuild while budget remains.
|
|
116
|
+
|
|
117
|
+
- Record each round as `build-parallel-<batch>-repair-<round>.json`: each
|
|
118
|
+
non-green sibling's status, verbatim findings, transfer_commit/null.
|
|
119
|
+
- Use step 4's initial inventory or affected recheck as appropriate; never start
|
|
120
|
+
a correction from an early reviewer result while required accounts are pending.
|
|
121
|
+
- Classify the complete inventory: **implementation defect** (review
|
|
122
|
+
Critical/Important on the diff, red wright/proof) → one repair-all wright in
|
|
123
|
+
the same worktree with the full inventory. **Durable-plan defect**
|
|
124
|
+
(falsified contract assumption, AC unchanged) →
|
|
125
|
+
[`spec-drift-guard.md`](spec-drift-guard.md): batch-sweep contract
|
|
126
|
+
assumptions, one folded `/rite-plan repair` + one `/rite-vet` recheck
|
|
127
|
+
inline, resume repair in the same worktrees under the amended contract;
|
|
128
|
+
never emit `Fix:`. **Frozen-lease scope defect** (correction needs
|
|
129
|
+
out-of-allowlist paths or re-slicing; lease allowlists are immutable) →
|
|
130
|
+
**automatic re-batch, no human gate**: `parallel cleanup --force` salvages
|
|
131
|
+
and records refs; `parallel create` starts from control `HEAD` under the
|
|
132
|
+
corrected decomposition. Give each new wright its salvaged
|
|
133
|
+
`devrites/parallel/<slug>/<old-batch>/<slice>` ref. If the inventory proves the accepted
|
|
134
|
+
approach unsound and no corrected decomposition exists, that is exhaustion
|
|
135
|
+
→ blocked, preserve, STOP. **Reviewer stall/cancel or missing
|
|
136
|
+
verdict** → re-dispatch the reviewer, not the wright. **Product/policy/
|
|
137
|
+
irreversible** → stops for the human.
|
|
138
|
+
- Dispatch one fresh repair-all `devrites-slice-wright` (cwd=worktree; step 3
|
|
139
|
+
rules) with the original contract + complete inventory +
|
|
140
|
+
"preserve what works; fix every finding; **then attack your own correction** —
|
|
141
|
+
probe the changed hunks for defects the fix itself introduced (adjacent cases of
|
|
142
|
+
the same rule, new observation/ordering windows, alias or boundary escapes) and
|
|
143
|
+
fold them in before returning; return a new `transfer_commit`". A correction whose
|
|
144
|
+
own diff is unexamined is not ready: a green writer gate plus an unexamined fix is
|
|
145
|
+
how the same defect family reappears one case deeper each round. Never reset
|
|
146
|
+
to `B` — that destroys the work under repair. The commit must still descend
|
|
147
|
+
from `B` and diff path-exact vs `B`.
|
|
148
|
+
- Budget and exhaustion follow only
|
|
149
|
+
[the canonical retry contract](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve).
|
|
150
|
+
Record one failed invariant, mechanism, reproduction, correction, and decisive
|
|
151
|
+
recheck per fingerprint; never use an umbrella like "covering" or "review is red again".
|
|
152
|
+
- A distinct post-repair Critical/Important gets a new fingerprint: refresh the
|
|
153
|
+
inventory and affected owning-role rechecks. It proves neither plan defect nor
|
|
154
|
+
exhaustion. Use plan path only if inventory proves the approach unsound.
|
|
155
|
+
- Stop under the canonical retry/authority/resource conditions, or when evidence
|
|
156
|
+
proves the approach unsound and no in-scope corrected decomposition exists.
|
|
157
|
+
- Exhaustion is not abort: record one technical blocker (`Status: blocked`;
|
|
158
|
+
`Next step: none — technical recovery exhausted; requires new evidence or changed failure conditions`), preserve
|
|
159
|
+
lease/worktrees/branches, STOP — same fingerprint stays blocked on
|
|
160
|
+
reinvoke; new evidence resumes repair in place. Human-owned decisions use
|
|
161
|
+
the drift-guard question and wait.
|
|
162
|
+
|
|
163
|
+
## Engine verbs
|
|
164
|
+
|
|
165
|
+
```text
|
|
166
|
+
devrites-engine parallel create --root <repo> --slug <slug> --batch <id> --base <B> --json <file>|-
|
|
167
|
+
devrites-engine parallel record-green --root <repo> --slug <slug> --slice <id> --commit <sha>
|
|
168
|
+
devrites-engine parallel integrate --root <repo> --slug <slug> --apply-to-control
|
|
169
|
+
devrites-engine parallel status --root <repo> --slug <slug>
|
|
170
|
+
devrites-engine parallel lease-write|lease-read|lease-clear --root <repo> --slug <slug>
|
|
171
|
+
# abandoning the batch is human discard only; a frozen-lease re-batch may emit
|
|
172
|
+
# cleanup --force as its salvage step (see Repair rounds):
|
|
173
|
+
# parallel abort --root <repo> --slug <slug>
|
|
174
|
+
# parallel cleanup --root <repo> --slug <slug> --force (salvages, prints retained refs)
|
|
175
|
+
```
|
|
176
|
+
|
|
177
|
+
`integrate` without `--apply-to-control` stages the squash commit, leaves the
|
|
178
|
+
lease `running` and control at `B`; cleanup still refuses — the commit cannot
|
|
179
|
+
be lost. `record-green` and `integrate` also accept an `integrate-failed`
|
|
180
|
+
lease, so a failed integrate retries after repair. `--apply-to-control`
|
|
181
|
+
refuses when control moved past `B` or holds uncommitted changes on slice
|
|
182
|
+
paths — commit/stash and retry; the batch is untouched. Go is SSOT; never
|
|
183
|
+
ad-hoc git/bash orchestration.
|
|
184
|
+
|
|
185
|
+
## Runtime isolation
|
|
186
|
+
|
|
187
|
+
Each parallel worktree must own isolated runtime resources. Before fan-out,
|
|
188
|
+
assign per-slice env (document in the lease or worktree README):
|
|
189
|
+
|
|
190
|
+
| Resource | Pattern |
|
|
191
|
+
| --- | --- |
|
|
192
|
+
| HTTP port | `PORT=<base+N>` or `DEVRITES_PARALLEL_PORT_<slice>` |
|
|
193
|
+
| Compose | `COMPOSE_PROJECT_NAME=devrites-<slug>-<batch>-<slice>` |
|
|
194
|
+
| SQLite/DB file | separate path under the worktree or `/tmp` |
|
|
195
|
+
| Dev server | one process per worktree; never share a listener |
|
|
196
|
+
|
|
197
|
+
Reusing the control worktree's running server, DB, or compose stack across
|
|
198
|
+
siblings causes cross-slice pollution and flaky proof. Force serial if
|
|
199
|
+
isolation cannot be established.
|
|
200
|
+
|
|
201
|
+
## Host
|
|
202
|
+
|
|
203
|
+
pi: N concurrent `subagent` wrights (`acceptEdits`, cwd=worktree). Codex: require
|
|
204
|
+
host-explicit concurrent worktree writers + native reconcile; else force serial.
|
|
205
|
+
Never two writers in one worktree; never root-emulated concurrency.
|
|
@@ -0,0 +1,87 @@
|
|
|
1
|
+
# rite-build phase contract
|
|
2
|
+
|
|
3
|
+
Apply [`one-slice-cycle.md`](one-slice-cycle.md) and
|
|
4
|
+
[`candidate-integrity.md`](../../devrites-lib/reference/candidate-integrity.md).
|
|
5
|
+
Opt-in `--parallel N` replaces steps 2–8 with [`parallel-batch.md`](parallel-batch.md);
|
|
6
|
+
Spec Drift Guard still applies.
|
|
7
|
+
|
|
8
|
+
1. **Gate.** Read core, `.devrites/ACTIVE`, then `devrites-engine orient <slug>`
|
|
9
|
+
and the Build read-next in
|
|
10
|
+
[`workspace-artifact-schema.md`](../../devrites-lib/reference/workspace-artifact-schema.md#read-next-by-phase):
|
|
11
|
+
the selected slice via `devrites-engine observe slice <slug> <SLICE-ID>`, not whole
|
|
12
|
+
`tasks.md`; over-budget or `bulk_files` artifacts are read by anchor only. Require
|
|
13
|
+
`Implementation readiness: READY`, current `Readiness inputs SHA-256`, exact
|
|
14
|
+
required accounts, ID/meaning traceability and green proof preflight.
|
|
15
|
+
Run `devrites-engine check readiness <slug>`; any miss/nonzero blocks.
|
|
16
|
+
2. **Select.** Pick the lowest pending slice whose `depends_on` are all built, using
|
|
17
|
+
`orient` `task_graph.slices` plus the `state.md` built list — never by scanning
|
|
18
|
+
`tasks.md`; then `observe slice` it. Restate its goal, ACs, exclusions and exact paths. Include
|
|
19
|
+
applicable topology/data/integration invariants and failure/recovery/proof cases.
|
|
20
|
+
Verify relevant assumptions live; falsified acceptance/architecture/scope/proof
|
|
21
|
+
routes through Spec Drift Guard. Resolve human-owned/irreversible gates before
|
|
22
|
+
source work; AFK follows its ceiling. Vet-ready Workflow Artifacts use
|
|
23
|
+
[`workflow-artifacts.md`](../../devrites-lib/reference/standards/workflow-artifacts.md).
|
|
24
|
+
3. **Dispatch.** Apply [`wright-dispatch.md`](wright-dispatch.md). Put the smallest
|
|
25
|
+
exact project-relative source/test path list directly in the task;
|
|
26
|
+
dispatch the exact `devrites-slice-wright` fresh. Root never writes product
|
|
27
|
+
paths; wright cannot widen scope; missing profile blocks.
|
|
28
|
+
<!-- workflow-artifact-adapter: {"module":"devrites-lib/reference/standards/workflow-artifacts.md","entry":"Build gate enters or resumes transaction","action":"invoke canonical operation table; reconcile exact result","return":"same slice/checkpoint cursor or Plan/Vet route"} -->
|
|
29
|
+
4. **Inspect.** Wait; compare returned paths and `git diff --name-only` with the
|
|
30
|
+
contract. Reject stale/partial/malformed/out-of-scope work; preserve user work.
|
|
31
|
+
Restoration uses the bounded wright.
|
|
32
|
+
5. **Review.** Apply [Independent Build review](#independent-build-review).
|
|
33
|
+
Missing verdicts, principle breaches and open Critical/Important block acceptance.
|
|
34
|
+
6. **Prove.** Against the frozen pre-slice candidate inspect
|
|
35
|
+
test hunks for deletion, skipping/focus, tautology, or weaker expectations.
|
|
36
|
+
Use step 5's exact test-analyst account; missing/adverse criterion verdict is
|
|
37
|
+
Critical. Run only `test-plan.md` repository/CI commands, record output, recheck
|
|
38
|
+
`git diff --name-only`. Missing/weakened/red/source-mutating proof cannot pass.
|
|
39
|
+
Pre-existing/environment-specific claims need a predating same-command,
|
|
40
|
+
same-environment baseline; otherwise unresolved.
|
|
41
|
+
|
|
42
|
+
Technical failure uses `devrites-debug-recovery` and
|
|
43
|
+
[canonical recovery](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve).
|
|
44
|
+
Reapply host admission before correction; affected proof/evidence follows candidate
|
|
45
|
+
integrity. Human gates remain product/irreversible/access decisions.
|
|
46
|
+
7. **Record green.** Upsert actual scoped `present`/`deleted` rows in `touched-files.md`;
|
|
47
|
+
update state, evidence and applicable UI/browser proof. Manifest stays mutable
|
|
48
|
+
until Polish. For a release milestone, after the last slice's rows run
|
|
49
|
+
`devrites-engine state merge-manifest <slug>` to fold the recorded
|
|
50
|
+
predecessor chain into the union manifest before Prove. Record stood
|
|
51
|
+
decisions/dead ends; refresh verified/falsified
|
|
52
|
+
assumptions. Propose reviewed durable project rules in the nearest guidance.
|
|
53
|
+
8. **Account/reply.** Apply `afk-discipline.md`: charge
|
|
54
|
+
exactly once after each green built slice; never negative, stop at zero,
|
|
55
|
+
malformed budget fails closed. Reply names next pending slice or `/rite-prove`
|
|
56
|
+
only when all built; no decorative renderer/dispatch telemetry.
|
|
57
|
+
|
|
58
|
+
One contract builds one slice: preserve TDD, exact paths and independent judgment.
|
|
59
|
+
|
|
60
|
+
## Independent Build review
|
|
61
|
+
|
|
62
|
+
After inspection, freeze full slice scope and cumulative baseline diff. Initial
|
|
63
|
+
inventory: one full-diff `devrites-code-reviewer`, one `devrites-test-analyst`,
|
|
64
|
+
and one exact `devrites-doubt-reviewer` per stood decision that meets
|
|
65
|
+
`devrites-doubt` § When to use (boundary, data model, auth, public API, migration,
|
|
66
|
+
user flow, assumption tests cannot prove); other stood decisions are recorded in
|
|
67
|
+
`decisions.md` without dispatch. Dispatch fresh,
|
|
68
|
+
read-only under [`parallel-dispatch.md`](../../devrites-lib/reference/parallel-dispatch.md).
|
|
69
|
+
Wait for every required account to become terminal; missing/gap needs a valid result.
|
|
70
|
+
Fold supported in-scope Critical/Important findings by cause into one inventory.
|
|
71
|
+
Dispatch one repair-all wright instructed to fix every finding, then attack its own
|
|
72
|
+
correction for fix-introduced defects before returning; durable contract defects use Spec
|
|
73
|
+
Drift Guard.
|
|
74
|
+
Suggestion/Nit/FYI cannot prolong recovery.
|
|
75
|
+
|
|
76
|
+
Rechecks use Vet's bounded pattern: each exact responsible reviewer checks
|
|
77
|
+
all open findings owned by that role and affected dependency/regression closure
|
|
78
|
+
in one fresh dispatch. Supply new candidate, inventory, correction diff, tests
|
|
79
|
+
and unchanged-coverage evidence under candidate integrity; include newly triggered
|
|
80
|
+
roles. A changed contract or uncertain impact requires the full inventory.
|
|
81
|
+
Collect all required rechecks before another folded correction. Canonical recovery
|
|
82
|
+
owns fingerprints/budget and the
|
|
83
|
+
[late-finding rule](../../devrites-lib/reference/standards/afk-hitl.md#retry-cap-no-progress-loops-and-self-resolve):
|
|
84
|
+
a recheck's `Late:` rows on hunks unchanged since that role's previous pass go to
|
|
85
|
+
`touched-files.md` `## Review trail` for `/rite-review`, not into another slice
|
|
86
|
+
repair, unless Critical with a failure path. Evidenced scope coverage never
|
|
87
|
+
guarantees no later defect; the feature-level Review and Seal gates still run.
|
|
@@ -0,0 +1,84 @@
|
|
|
1
|
+
# Spec Drift Guard (build phase)
|
|
2
|
+
|
|
3
|
+
Canonical Spec Drift Guard, active in `/rite-build` and referenced by other
|
|
4
|
+
phases. Never silently code against a known-wrong plan.
|
|
5
|
+
|
|
6
|
+
## Drift has occurred when
|
|
7
|
+
- the spec says X but the code makes X impossible/wrong;
|
|
8
|
+
- the plan assumes a file/API/component/route/model/command that doesn't exist;
|
|
9
|
+
- tests show the acceptance criteria are incomplete or wrong;
|
|
10
|
+
- browser evidence shows the intended UX doesn't work as described;
|
|
11
|
+
- an official doc contradicts the planned approach;
|
|
12
|
+
- the design system / existing UX pattern contradicts the planned UI;
|
|
13
|
+
- a missing user decision that affects product behavior surfaces.
|
|
14
|
+
|
|
15
|
+
## Workflow
|
|
16
|
+
```
|
|
17
|
+
1. STOP coding.
|
|
18
|
+
2. Record drift.md (assumed vs observed, when).
|
|
19
|
+
3. Classify: requirement ambiguity | implementation-plan error | codebase reality
|
|
20
|
+
mismatch | design-system mismatch | test/evidence mismatch | external-doc mismatch
|
|
21
|
+
| user-decision required.
|
|
22
|
+
4. Local repair that preserves behavior/scope/architecture/data/UX/security/migration?
|
|
23
|
+
YES, active-slice technical/tool failure → log it and use Build's bounded debug
|
|
24
|
+
recovery. Do not ask for retry authorization and do not re-plan unless the
|
|
25
|
+
durable remaining-work instructions are wrong.
|
|
26
|
+
YES, durable plan is wrong → run the batch sweep below, log every
|
|
27
|
+
violation, save the caller's return cursor, then invoke `/rite-plan repair` and `/rite-vet` inline
|
|
28
|
+
without a question — ONE folded repair for all open entries, ONE
|
|
29
|
+
recheck for every open fingerprint — and resume.
|
|
30
|
+
NO, product/policy/irreversible-risk decision → ask the user (format below).
|
|
31
|
+
5. Never continue on a known-wrong durable plan. A repaired active-slice implementation
|
|
32
|
+
may continue only after bounded recovery, returned-diff review, and proof gates pass.
|
|
33
|
+
```
|
|
34
|
+
|
|
35
|
+
## Batch sweep (before repair)
|
|
36
|
+
|
|
37
|
+
Repair durable-plan drift as a folded set:
|
|
38
|
+
|
|
39
|
+
1. Trace the falsified assumption's full dependency/consumer closure and affected
|
|
40
|
+
frontier, including dependent future slices. Verify unchecked paths, symbols/APIs/
|
|
41
|
+
signatures, routes, commands, versions, and artifacts there against live source.
|
|
42
|
+
Reuse the wright inventory and unchanged evidence; deterministic existence checks
|
|
43
|
+
need no dispatch. Do not rescan unrelated slices. Broaden unknown closure or shared
|
|
44
|
+
contract changes until coverage is justified; retain every known gap.
|
|
45
|
+
2. Record each violation as its own `drift.md` entry/fingerprint; one folded
|
|
46
|
+
repair + one batched recheck resolves the set.
|
|
47
|
+
3. A recheck-surfaced gap is a new fingerprint with its own budget — loop
|
|
48
|
+
internally, never hand an intermediate command to the human. When
|
|
49
|
+
consecutive folded repairs keep landing on the same clause set, the
|
|
50
|
+
repair packet's `convergence_pressure` marking applies (see `/rite-plan`
|
|
51
|
+
repair): bounded declared residuals may close refinements of
|
|
52
|
+
already-pinned clauses; a newly surfaced failure mode is never
|
|
53
|
+
residual-eligible. A suspect seam's declare-limitation-or-continue choice
|
|
54
|
+
routes to `/rite-clarify` like any human-owned gate — it is not an
|
|
55
|
+
intermediate command.
|
|
56
|
+
4. Nothing skips or defers silently: every entry ends resolved, human-escalated,
|
|
57
|
+
or fingerprint-exhausted. Execution-only gaps (tests, UX, evidence) get the
|
|
58
|
+
identical path when they surface.
|
|
59
|
+
|
|
60
|
+
## User question format
|
|
61
|
+
```
|
|
62
|
+
I hit spec drift:
|
|
63
|
+
- Spec/plan assumed: ...
|
|
64
|
+
- Code/evidence shows: ...
|
|
65
|
+
- Why it matters: ...
|
|
66
|
+
|
|
67
|
+
Which direction should DevRites take?
|
|
68
|
+
1. Keep the requirement, change architecture by ...
|
|
69
|
+
2. Adjust the requirement to match existing behavior ...
|
|
70
|
+
3. Split into a follow-up feature ...
|
|
71
|
+
4. Custom: describe the intended behavior
|
|
72
|
+
```
|
|
73
|
+
|
|
74
|
+
Never turn an objective defect, environment repair, tool bug, or proof rerun into a
|
|
75
|
+
human permission question. Re-plan only when the durable plan changed.
|
|
76
|
+
|
|
77
|
+
## Inline return contract
|
|
78
|
+
|
|
79
|
+
The detecting phase owns backtracking and the batch sweep. Save
|
|
80
|
+
`return_phase`/`return_next_action`; consume nested Plan/Vet `STOP` internally, complete
|
|
81
|
+
vetted acceptance-preserving remediation, then restore the cursor and failed step.
|
|
82
|
+
Never hand the human an intermediate command. The shared three-attempt causal-fingerprint
|
|
83
|
+
cap still applies: exhaustion produces one technical blocker, while a genuinely
|
|
84
|
+
human-owned decision uses the question format below.
|
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
# TDD / Prove-It pattern
|
|
2
|
+
|
|
3
|
+
When a slice changes behavior, prove the change with a test that fails first, so you
|
|
4
|
+
know the test can fail, and that your code is what makes it pass.
|
|
5
|
+
|
|
6
|
+
## Red → Green → Refactor
|
|
7
|
+
1. **Red:** write the smallest test that expresses the new behavior. Run it; watch it
|
|
8
|
+
fail for the *expected* reason (not a typo/import error).
|
|
9
|
+
2. **Green:** write the minimum code to pass. Resist gold-plating.
|
|
10
|
+
3. **Refactor:** clean up with the test as a safety net. Re-run; stay green.
|
|
11
|
+
|
|
12
|
+
## Prove-It (when strict TDD doesn't fit)
|
|
13
|
+
For code where a test-first flow is awkward (exploratory glue, config, some UI), still
|
|
14
|
+
produce evidence:
|
|
15
|
+
- Capture the current (wrong/absent) behavior: a failing assertion, a screenshot, a
|
|
16
|
+
log line.
|
|
17
|
+
- Make the change.
|
|
18
|
+
- Capture the new behavior the same way. The before/after pair *is* the proof.
|
|
19
|
+
|
|
20
|
+
## Rules
|
|
21
|
+
- Use the project's existing test framework and commands (per the discovery contract
|
|
22
|
+
`rite-prove/reference/test-command-discovery.md`). Don't introduce a new test runner
|
|
23
|
+
to prove a slice.
|
|
24
|
+
- One behavior per test; name it for the behavior, not the function.
|
|
25
|
+
- A green test you never saw fail proves nothing: always see red first.
|
|
26
|
+
- Don't delete or weaken a failing test to "pass". If it's wrong, that may be drift.
|
|
27
|
+
- Record the test command + result in `evidence.md`.
|