@haposoft/cafekit 0.16.7 → 0.18.1

package/src/claude/skills/route/references/task-taxonomy.md

@@ -1,48 +0,0 @@
-# Task taxonomy
-
-Classify by the final deliverable the user expects, not by the first verb, file
-type, or tool mentioned. Choose exactly one class; use domains as modifiers.
-
-| Class | Final deliverable |
-|---|---|
-| `answer` | Evidence-backed explanation or factual response |
-| `discover` | Located files, call path, inventory, or blast-radius map |
-| `decide` | Chosen product, architecture, or technical direction |
-| `specify` | Approved bounded plan and executable task packet |
-| `change` | Working implementation or content change |
-| `diagnose` | Root cause and verification-ready repair plan |
-| `repair` | Cause-aligned fix plus regression proof |
-| `verify` | Test or review verdict with owned evidence |
-| `deliver` | Authorized commit, push, deploy, publish, or release result |
-
-When a request contains several verbs, classify by its terminal observable
-result. For example, “research options and implement the winner” is `change`,
-while research is a decision link. “Inspect this failure and tell me why” is
-`diagnose`, not `repair`.
-
-## Size
-
-- `trivial`: one clear reversible outcome, normally one owner and one link.
-- `standard`: multiple dependent links or a bounded cross-file/domain change.
-- `epic`: three or more independently deliverable subsystems; split them into
-  bounded routes instead of creating one oversized chain.
-
-## Risk
-
-Risk is the maximum risk of any retained link, never an average:
-
-- `low`: local, reversible, no material compatibility or data boundary.
-- `elevated`: shared contract, integration, migration, sensitive data, or a
-  meaningful regression surface.
-- `high`: security boundary, irreversible data/action, production delivery,
-  public compatibility, or large blast radius.
-
-## Domains and ambiguity
-
-Count only material domains that need distinct evidence or ownership. A file
-extension alone is not a domain. Ambiguity adds an understand or decide link
-only when unresolved information can change the final deliverable, authority,
-or verification; otherwise choose the shortest valid direct path.
-
-Modifiers constrain a route. They never grant mutation, external-action,
-commit, push, deploy, publish, or release authority.

package/src/claude/skills/specs/templates/design.md

@@ -1,82 +0,0 @@
-# Design
-
-<!-- Delete every optional section that is not relevant. Compact keeps only the four core sections. -->
-
-## Boundary
-
-- **Owns:** {{Behavior/state this design owns}}
-- **Reads:** {{Relevant inputs or existing state, or none}}
-- **Writes/exposes:** {{Outputs, state, route, artifact, or none}}
-- **Outside boundary:** {{Explicit non-goal or delegated responsibility}}
-
-## Typed Anchors
-
-<!-- Files-first. IDs are unique across the whole spec. Design-owned anchors use A-D-NN. Access/Action are machine authority; Role never implies lifecycle. -->
-
-| ID | Type | Target | Role | Access | Action |
-|---|---|---|---|---|---|
-| A-D-01 | file | `{{path/to/existing-or-planned-file}}` | {{owner / consumer / entrypoint / proof / constraint}} | {{read / write}} | {{read / create / modify / delete}} |
-<!-- For a typed proof boundary, add: | A-D-02 | artifact | `{{path/to/proof-artifact}}` | proof evidence owner | write | create | -->
-
-## Decisions and Invariants
-
-<!-- Keep stable D/I/C IDs: every RN.M semantic-review counterexample cites one exact design reference. -->
-
-### D1 — {{Decision name}}
-
-- **Decision:** {{Canonical behavior or boundary}}
-- **Rejects ambiguity:** {{Alternative interpretation implementers must not choose}}
-- **Negative path:** {{Failure/error behavior when relevant}}
-- **Anchors:** A-D-01
-
-### I1 — {{Invariant name}}
-
-{{Property that must remain true across implementation and verification.}}
-
-### Named Contracts (conditional)
-
-<!-- Define each implementation-significant contract once. Tasks reference IDs and never copy bodies. For any public, replay, or operator API contract, include method, route, auth, required headers, request schema, success response, error semantics, and idempotency/concurrency behavior. -->
-
-#### C1 — {{Contract name}}
-
-- **Owner:** {{boundary or future owner task}}
-- **Consumers:** {{boundaries or future consumer tasks}}
-- **Shape/behavior:** {{typed request, response, event, schema, state, or error contract}}
-- **Compatibility:** {{versioning or migration constraint when relevant}}
-
-## Verification Definitions
-
-<!--
-Canonical parser syntax is one single-line definition per V ID. Keep every
-label on the same line; do not replace this with a table or a V heading.
--->
-
-- **V1**: Criteria R{{SUBJECT_REQ}}.{{X}}; Owner A-D-01; Decision refs D1, I1, C1; Method command `{{exact command}}`; Expected {{concrete observable result}}; Negative/failure {{concrete rejected or recovery case}}; Reachability/grounding entrypoint `{{exact/repository/entrypoint}}` via A-D-01.
-
-<!-- Only for a typed proof boundary, insert after Owner: Proof criteria Rn.m; Proof owner <distinct owner>; Evidence anchor <proof-owned anchor>; -->
-
-<!-- Full-only conditional sections follow. Keep only those relevant to this feature. -->
-
-## Flow (Full, conditional)
-
-{{Only multi-step, branching, asynchronous, or cross-boundary flow decisions.}}
-
-## Data and Consistency (Full, conditional)
-
-{{Ownership, schema, constraints, concurrency, lifecycle, or idempotency. For any retention/lifecycle policy, state clock anchor, clock source, timezone/precision, cutoff comparator/inclusivity, enforcement boundary, and a wrong-clock/boundary counterexample.}}
-
-## Errors and Recovery (Full, conditional)
-
-{{Trigger, error contract, retry/rollback/reconciliation, and terminal state.}}
-
-## Security and Privacy (Full, conditional)
-
-{{Trust boundary, authorization, sensitive data, deletion, and retention decisions.}}
-
-## Migration and Compatibility (Full, conditional)
-
-{{Ordering, compatibility window, rollback trigger, and migration proof.}}
-
-## Unresolved Questions
-
-- None.

package/src/claude/skills/specs/templates/requirements-init.md

@@ -1,8 +0,0 @@
-# Requirements Document
-
-## Project Description (Input)
-{{PROJECT_DESCRIPTION}}
-
-## Requirements
-<!-- Will be generated during the cf:specs requirements phase -->
-

package/src/claude/skills/specs/templates/requirements.md

@@ -1,42 +0,0 @@
-# Requirements
-
-## Outcomes
-
-- {{Observable product or system outcome}}
-
-## Scope
-
-### In scope
-
-- {{Approved behavior or boundary}}
-
-### Non-goals
-
-- {{Explicit exclusion that prevents scope inference}}
-
-## Requirements
-
-### Requirement 1: {{Outcome area}}
-
-<!-- Keep Objective/User Story only when role and benefit remove ambiguity. -->
-{{Optional: **Objective:** As a <role>, I want <capability>, so that <benefit>.}}
-
-#### Acceptance Criteria
-
-- **R1.1** When {{event}}, the {{system}} shall {{measurable subject response}}.
-
-<!-- Add a separate proof criterion only when a typed proof boundary exists. -->
-
-<!-- Add state, optional-feature, or ubiquitous EARS criteria only when relevant. -->
-<!-- Add a concrete example only when values, order, boundaries, or transformation could be interpreted differently. -->
-
-#### Examples (conditional)
-
-- {{Input/state}} → {{expected output/state}}
-
-<!-- Repeat Requirement N with literal RN.M acceptance IDs. -->
-<!-- Add feature-specific NFRs in the same numeric sequence only when measurable and relevant. -->
-
-## Unresolved Questions
-
-- None.

package/src/claude/skills/specs/templates/spec-state.json

@@ -1,56 +0,0 @@
-{
-  "schema_version": "2.1",
-  "feature_name": "{{FEATURE_NAME}}",
-  "created_at": "{{TIMESTAMP}}",
-  "updated_at": "{{TIMESTAMP}}",
-  "language": "en",
-  "status": "in_progress",
-  "scope_lock": {
-    "source": "{{PROJECT_DESCRIPTION}}",
-    "in_scope": [],
-    "out_of_scope": [],
-    "expansion_policy": "requires-user-approval"
-  },
-  "authoring": {
-    "requirements": "draft",
-    "design": "draft",
-    "research": "absent",
-    "tasks": "absent"
-  },
-  "coordination": {
-    "boundaries": []
-  },
-  "validation": {
-    "status": "not-run",
-    "semantic_review": {
-      "status": "not-run",
-      "semantic_digest": null,
-      "verdict": null,
-      "lifecycle_disposition": null,
-      "findings": [],
-      "unresolved_decisions": [],
-      "graph_coverage": [],
-      "repair_round": 0,
-      "reviewed_criteria": [],
-      "counterexamples": [],
-      "reviewer_evidence": null
-    },
-    "semantic_review_history": {
-      "lineage_id": "{{LINEAGE_ID}}",
-      "entries": []
-    },
-    "authoring_validation": null
-  },
-  "semantic_model": null,
-  "ready_for_implementation": false,
-  "workflow_policy": {
-    "version": "2.1",
-    "planning_depth": "Compact",
-    "assurance_level": "Routine",
-    "classified_minimum": {
-      "planning_depth": "Compact",
-      "assurance_level": "Routine"
-    },
-    "risks": []
-  }
-}

package/src/claude/skills/specs/templates/task.md

@@ -1,47 +0,0 @@
-# Task R{{REQ_NUMBER}}-{{SEQ}}: {{TITLE}}
-**Status:** pending
-
-## Outcome
-
-{{Concrete observable vertical outcome, named entrypoint, and resulting state delivered by this task.}}
-
-## Scope
-
-- **In scope:** {{Exact behavior owned by this task}}
-- **Out of scope:** {{Explicit exclusions or delegated behavior}}
-
-## Anchors and Ownership
-
-<!-- Compact core: one owned anchor is enough; proof artifact/owner exists only for a typed proof boundary (see Verification Plan). -->
-| ID | Type | Target | Role | Access | Action |
-|---|---|---|---|---|---|
-| A-R{{REQ_NUMBER}}-{{SEQ}}-01 | file | `{{exact/path/to/file}}` | owner | write | modify |
-<!-- For a typed proof boundary, add: | A-R{{REQ_NUMBER}}-{{SEQ}}-02 | file | `{{exact/path/to/test-file}}` | proof | write | create | and set Task role accordingly; otherwise omit. Every executable task must own a concrete test file/artifact anchor or share proof via that typed boundary; bare command is not ownership. -->
-
-## Changes
-
-<!-- Every checkbox maps exact RN.M IDs; the set must equal Acceptance below. -->
-- [ ] {{Implement behavior at the exact owned boundary.}} _Requirements: {{REQ_NUMBER}}.{{X}}_
-- [ ] {{Handle the concrete negative or recovery path.}} _Requirements: {{REQ_NUMBER}}.{{Y}}_
-
-## Acceptance
-
-<!-- Declare each mapped RN.M once with a measurable output/state and negative behavior. -->
-- **R{{REQ_NUMBER}}.{{X}}:** {{Measurable observable outcome}}
-- **R{{REQ_NUMBER}}.{{Y}}:** {{Concrete negative or recovery outcome}}
-
-## Dependencies
-
-- {{DEPENDENCIES}}
-
-## Verification Plan
-
-<!-- Ownership invariant: a bare npm test command without a concrete file/artifact anchor is not ownership; shared proof must use a typed proof boundary. -->
-- **Verification ref:** {{V reference whose structured subject/proof owner matches this task}}
-- **Task role:** {{subject | verifier}}
-- **Command:** `{{Exact project command}}`
-- **Expected:** {{Exit, output, state, artifact, or UI result}}
-- **Negative path:** {{Contract-preserving failure check}}
-- **Reachability:** `{{Real entrypoint/caller or generated artifact}}`
-
-<!-- The table above is the only task anchor/ownership table. Access read requires Action read. Access write requires create, modify, or delete. Targets are exact; globs and parent-directory claims are invalid. A verifier must not repeat the subject's Acceptance criterion. Specs-only never creates or updates docs and never fabricates execution proof; record doc impact as a brief recommendation only. -->

package/src/codex/hooks/completion-authority-check.cjs

@@ -1,67 +0,0 @@
-'use strict';
-
-const fs = require('fs');
-const path = require('path');
-const STATE = require('./completion-authority-state.cjs');
-const { checkFeatureReceipt, checkReceiptDetails } = require('./lib/spec-receipt.cjs');
-const RESOLVER = require('./lib/spec-utils.cjs');
-
-const installedScripts = path.join(__dirname, '..', 'scripts');
-const scripts = fs.existsSync(path.join(installedScripts, 'spec-final-state.cjs'))
-  ? installedScripts
-  : path.resolve(__dirname, '..', '..', 'claude', 'scripts');
-
-function runtimeModule(root, name) {
-  const target = path.join(root, name);
-  const stat = fs.lstatSync(target);
-  if (stat.isSymbolicLink() || !stat.isFile()) throw new Error(`runtime dependency must be a regular non-symlink file: ${name}`);
-  const canonicalRoot = fs.realpathSync(root);
-  const canonical = fs.realpathSync(target);
-  const relative = path.relative(canonicalRoot, canonical);
-  if (relative.startsWith(`..${path.sep}`) || path.isAbsolute(relative)) throw new Error(`runtime dependency escaped scripts root: ${name}`);
-  return require(canonical);
-}
-
-const FINAL_STATE = runtimeModule(scripts, 'spec-final-state.cjs');
-
-function explicitTarget(payload) {
-  for (const key of ['featureName', 'feature', 'explicitFeature']) {
-    if (Object.prototype.hasOwnProperty.call(payload, key)) return { explicitFeature: payload[key] };
-  }
-  for (const key of ['specPath', 'spec_path', 'featurePath']) {
-    if (Object.prototype.hasOwnProperty.call(payload, key)) return { explicitPath: payload[key] };
-  }
-  return null;
-}
-
-function resolveCandidate({ projectRoot, runtime, payload }) {
-  const target = explicitTarget(payload);
-  if (target) return RESOLVER.resolveActiveSpec({ projectRoot, runtime, ...target });
-  // Delegate so both runtimes answer the same question; the count below stays only as a
-  // fallback for an installed resolver older than this wrapper.
-  const shared = RESOLVER.resolvePersistedSpec({ projectRoot, runtime });
-  if (shared !== null) return shared;
-  const candidates = RESOLVER.findAllSpecCandidates(projectRoot, runtime);
-  if (candidates.length > 1) return { error: 'multiple_persisted', candidates: candidates.map((candidate) => candidate.featureName) };
-  return candidates[0] || null;
-}
-
-function dependencies(overrides = {}) {
-  if (!overrides.grounder) runtimeModule(scripts, 'spec-semantic-model.cjs');
-  const grounder = overrides.grounder || runtimeModule(scripts, 'spec-ground.cjs');
-  return {
-    validator: overrides.validator || runtimeModule(scripts, 'validate-spec-output.cjs'),
-    grounder,
-    semanticAuthority: overrides.semanticAuthority || require('./semantic-review-authority.cjs'),
-  };
-}
-
-module.exports = FINAL_STATE.createAuthority({
-  state: STATE,
-  resolveCandidate,
-  dependencies,
-  receipts: {
-    task: (featureDir, taskPath, task, context) => checkReceiptDetails(featureDir, taskPath, task, context),
-    feature: (featureDir, context) => checkFeatureReceipt(featureDir, context),
-  },
-});