feat(acr,yaml): v5.6 Foundation — load-pattern enumeration + block-seq parser

Foundation chunk of v5.6 "steering-model II" (internal plumbing for B/C;
no command-output change, so --json/--raw/SC-5/6/7 stay byte-stable, count
stays 13).

active-config-reader.mjs:
- deriveLoadPattern(kind,{scoped}) — pure helper mapping each source kind to
  loadPattern {always,on-demand,external} + survivesCompaction {yes,no,n/a}
  + derivationConfidence {confirmed,inferred}, traced to the published
  loading model (V-rows in docs/v5.5-steering-model-plan.md).
- enumerateRules / enumerateAgents / enumerateOutputStyles — the three
  source kinds previously unenumerated (mirror enumerateSkills). Output-style
  discovery is direct (not a new file-discovery type) to keep the discovery
  surface stable.
- readActiveConfig now exposes rules/agents/outputStyles arrays + totals
  counts/subtotals (folded into grandTotal).

yaml-parser.mjs:
- parseSimpleYaml now reads YAML block sequences (paths:\n  - a), not just
  inline paths:. An empty-valued key with no `- ` items stays null
  (backcompat). Resolves a pre-existing RUL false-positive (a block-seq-scoped
  rule was misread as unscoped) — fix flows through unchanged RUL code.

Tests +35 (961 -> 996): block-seq parser cases, RUL block-seq regression
(no-misflag + durability-fires), deriveLoadPattern table, three enumerators
(positive+negative). Amended two existing ACR asserts (top-level key shape +
grandTotal sum). self-audit A/A, readmeCheck passed, mismatches []. tests
badge 961+->996+; README testing prose de-staled (635/36 -> 996/56);
CLAUDE.md Foundation note.

B (manifest/tokens render + snapshot regen) and C (CA-OST, count->14)
deferred to their own sessions/GO.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
This commit is contained in:
Kjell Tore Guttormsen 2026-06-20 16:57:52 +02:00
commit 62d910ed6d
8 changed files with 575 additions and 25 deletions

View file

@ -53,6 +53,56 @@ export function estimateTokens(bytes, kind = 'markdown', opts = {}) {
return Math.ceil(bytes / 4);
}
// ─────────────────────────────────────────────────────────────────────────
// Load-pattern model (v5.6 Foundation)
// ─────────────────────────────────────────────────────────────────────────
/**
* Derive how a config source loads into context and whether it survives a
* `/compact`, from the published Claude Code loading model. Deterministic,
* side-effect-free. `derivationConfidence` is 'confirmed' when a primary-doc
* row nails the row (V-rows in docs/v5.5-steering-model-plan.md), 'inferred'
* when reasoned from an analogue (so a renderer can choose to mark it).
*
* loadPattern { 'always', 'on-demand', 'external', 'unknown' }
* survivesCompaction { 'yes', 'no', 'n/a' }
*
* @param {string} kind - source kind (see switch)
* @param {{scoped?: boolean}} [opts] - kind-specific discriminators
* @returns {{loadPattern:string, survivesCompaction:string, derivationConfidence:string}}
*/
export function deriveLoadPattern(kind, opts = {}) {
const mk = (loadPattern, survivesCompaction, derivationConfidence) =>
({ loadPattern, survivesCompaction, derivationConfidence });
switch (kind) {
// CLAUDE.md cascade
case 'claude-md-root': return mk('always', 'yes', 'confirmed'); // V1
case 'claude-md-nested': return mk('on-demand', 'no', 'confirmed'); // V3
case 'claude-md-user':
case 'claude-md-managed':
case 'claude-md-import': return mk('always', 'yes', 'inferred');
// Rules
case 'rule':
return opts.scoped
? mk('on-demand', 'no', 'confirmed') // V2, V4 (loads on Read of a match)
: mk('always', 'yes', 'confirmed'); // V1, V6 (unscoped = always-on)
// Skills
case 'skill-listing': return mk('always', 'n/a', 'confirmed'); // V7 (name+desc every turn)
case 'skill-body': return mk('on-demand', 'n/a', 'confirmed'); // V7 (body on invoke)
// Agents — name+description load for delegation each turn (skill analogue;
// no primary-doc row pins it, so 'inferred').
case 'agent': return mk('always', 'n/a', 'inferred');
// Output styles modify the system prompt, re-sent every turn (V10, V12).
case 'output-style': return mk('always', 'yes', 'confirmed');
// Hooks run outside context (V18); the hook itself is external.
case 'hook': return mk('external', 'n/a', 'confirmed');
// MCP tool schemas are part of the per-turn payload (no explicit
// compaction-survival row → 'inferred').
case 'mcp': return mk('always', 'yes', 'inferred');
default: return mk('unknown', 'n/a', 'inferred');
}
}
// ─────────────────────────────────────────────────────────────────────────
// Git root detection
// ─────────────────────────────────────────────────────────────────────────
@ -499,6 +549,126 @@ export async function enumerateSkills(pluginList = []) {
return out;
}
// ─────────────────────────────────────────────────────────────────────────
// Rules, agents, output styles (v5.6 Foundation enumeration)
// ─────────────────────────────────────────────────────────────────────────
/**
* Build the project/user/plugin directory list for a per-kind enumerator.
* Project + user dirs live under `.claude/<dir>`; plugins under each of the
* given subpaths relative to the plugin root.
*/
function configDirs(repoPath, pluginList, subdir, pluginSubdirs = [subdir]) {
const home = process.env.HOME || process.env.USERPROFILE || '';
const dirs = [{ dir: join(repoPath, '.claude', subdir), source: 'project', pluginName: null }];
if (home) dirs.push({ dir: join(home, '.claude', subdir), source: 'user', pluginName: null });
for (const p of pluginList) {
for (const sub of pluginSubdirs) {
dirs.push({ dir: join(p.path, sub), source: 'plugin', pluginName: p.name });
}
}
return dirs;
}
/**
* Enumerate rule files: `<repo>/.claude/rules/`, `~/.claude/rules/`, and each
* plugin's `rules/` + `.claude/rules/`. A rule is path-scoped when its
* frontmatter declares `paths:` (the only documented scoping field, V5) which
* determines its load pattern (scoped = on-demand, unscoped = always, V1/V2/V6).
*
* @param {string} repoPath
* @param {Array<{name:string, path:string}>} [pluginList]
* @returns {Promise<Array<{name:string, source:string, pluginName:string|null, path:string, scoped:boolean, bytes:number, estimatedTokens:number, loadPattern:string, survivesCompaction:string, derivationConfidence:string}>>}
*/
export async function enumerateRules(repoPath, pluginList = []) {
const out = [];
const dirs = configDirs(repoPath, pluginList, 'rules', ['rules', join('.claude', 'rules')]);
for (const { dir, source, pluginName } of dirs) {
const files = await listMarkdownFiles(dir);
for (const f of files) {
let scoped = false;
try {
const content = await readFile(f.path, 'utf-8');
const { frontmatter } = parseFrontmatter(content);
scoped = !!(frontmatter && frontmatter.paths);
} catch { /* unreadable → treat as unscoped */ }
out.push({
name: basename(f.path),
source,
pluginName,
path: f.path,
scoped,
bytes: f.size,
estimatedTokens: estimateTokens(f.size, 'markdown'),
...deriveLoadPattern('rule', { scoped }),
});
}
}
return out;
}
/**
* Enumerate agent definitions: `<repo>/.claude/agents/`, `~/.claude/agents/`,
* and each plugin's `agents/`. Only name+description load for delegation each
* turn, so cost is estimated like other frontmatter-only sources.
*
* @param {string} repoPath
* @param {Array<{name:string, path:string}>} [pluginList]
* @returns {Promise<Array<{name:string, source:string, pluginName:string|null, path:string, bytes:number, estimatedTokens:number, loadPattern:string, survivesCompaction:string, derivationConfidence:string}>>}
*/
export async function enumerateAgents(repoPath, pluginList = []) {
const out = [];
const lp = deriveLoadPattern('agent');
const dirs = configDirs(repoPath, pluginList, 'agents');
for (const { dir, source, pluginName } of dirs) {
const files = await listMarkdownFiles(dir);
for (const f of files) {
out.push({
name: basename(f.path).replace(/\.md$/, ''),
source,
pluginName,
path: f.path,
bytes: f.size,
estimatedTokens: estimateTokens(f.size, 'frontmatter'),
...lp,
});
}
}
return out;
}
/**
* Enumerate output styles: `<repo>/.claude/output-styles/`,
* `~/.claude/output-styles/`, and each plugin's `output-styles/`. An output
* style modifies the system prompt and is re-sent every turn (V10, V12).
* Foundation only enumerates them; the `keep-coding-instructions` /
* `force-for-plugin` checks are the CA-OST scanner (v5.6 C).
*
* @param {string} repoPath
* @param {Array<{name:string, path:string}>} [pluginList]
* @returns {Promise<Array<{name:string, source:string, pluginName:string|null, path:string, bytes:number, estimatedTokens:number, loadPattern:string, survivesCompaction:string, derivationConfidence:string}>>}
*/
export async function enumerateOutputStyles(repoPath, pluginList = []) {
const out = [];
const lp = deriveLoadPattern('output-style');
const dirs = configDirs(repoPath, pluginList, 'output-styles');
for (const { dir, source, pluginName } of dirs) {
const files = await listMarkdownFiles(dir);
for (const f of files) {
out.push({
name: basename(f.path).replace(/\.md$/, ''),
source,
pluginName,
path: f.path,
bytes: f.size,
estimatedTokens: estimateTokens(f.size, 'markdown'),
...lp,
});
}
}
return out;
}
// ─────────────────────────────────────────────────────────────────────────
// Hooks (user + project + plugin)
// ─────────────────────────────────────────────────────────────────────────
@ -841,11 +1011,14 @@ export async function readActiveConfig(repoPath, opts = {}) {
readSettingsCascade(absRepoPath),
]);
// Skills depend on plugins
const [skills, hooks, mcpServers] = await Promise.all([
// Skills, hooks, MCP, and the v5.6 enumerations all depend on plugins
const [skills, hooks, mcpServers, rules, agents, outputStyles] = await Promise.all([
enumerateSkills(plugins),
readActiveHooks(absRepoPath, plugins),
readActiveMcpServers(absRepoPath, claudeJsonSlice, plugins),
enumerateRules(absRepoPath, plugins),
enumerateAgents(absRepoPath, plugins),
enumerateOutputStyles(absRepoPath, plugins),
]);
// Totals
@ -854,6 +1027,9 @@ export async function readActiveConfig(repoPath, opts = {}) {
skills: skills.length,
mcpServers: mcpServers.length,
hooks: hooks.length,
rules: rules.length,
agents: agents.length,
outputStyles: outputStyles.length,
claudeMdFiles: claudeMd.files.length,
estimatedTokens: {
claudeMd: claudeMd.estimatedTokens,
@ -861,6 +1037,9 @@ export async function readActiveConfig(repoPath, opts = {}) {
skills: skills.reduce((s, k) => s + k.estimatedTokens, 0),
mcpServers: mcpServers.reduce((s, m) => s + m.estimatedTokens, 0),
hooks: hooks.reduce((s, h) => s + h.estimatedTokens, 0),
rules: rules.reduce((s, r) => s + r.estimatedTokens, 0),
agents: agents.reduce((s, a) => s + a.estimatedTokens, 0),
outputStyles: outputStyles.reduce((s, o) => s + o.estimatedTokens, 0),
grandTotal: 0,
},
};
@ -869,7 +1048,10 @@ export async function readActiveConfig(repoPath, opts = {}) {
totals.estimatedTokens.plugins +
totals.estimatedTokens.skills +
totals.estimatedTokens.mcpServers +
totals.estimatedTokens.hooks;
totals.estimatedTokens.hooks +
totals.estimatedTokens.rules +
totals.estimatedTokens.agents +
totals.estimatedTokens.outputStyles;
const warnings = [];
@ -898,6 +1080,9 @@ export async function readActiveConfig(repoPath, opts = {}) {
skills,
mcpServers,
hooks,
rules,
agents,
outputStyles,
settings: { cascade: settingsCascade },
totals,
suggestDisables,

View file

@ -34,17 +34,51 @@ export function parseSimpleYaml(yaml) {
let currentKey = null;
let multiLineValue = '';
let inMultiLine = false;
// Block-sequence state: an empty-valued key may be a YAML block sequence
// key:
// - item
// - item
// We defer the decision until the next line: a `- item` line starts an array;
// anything else (or end-of-input) leaves the empty-valued key as `null` —
// indistinguishable from a plain null value, preserving backwards compatibility.
let seqKey = null; // key awaiting/collecting block-sequence items
let seqItems = null; // null until the first `- ` item is seen
let seqPending = false; // an empty-valued key was seen; items may follow
// Commit the current block-sequence (or empty-valued key) to result.
const commitSeq = () => {
if (seqKey !== null) {
result[normalizeKey(seqKey)] = seqItems !== null ? seqItems : null;
}
seqKey = null;
seqItems = null;
seqPending = false;
};
for (const line of lines) {
// Skip comments and empty lines
// Skip comments and empty lines (these do NOT terminate a block sequence)
if (line.trim().startsWith('#') || line.trim() === '') {
if (inMultiLine) multiLineValue += '\n';
continue;
}
// Block-sequence item: only while a sequence is pending or active
const seqMatch = (seqPending || seqItems !== null) && !inMultiLine
? line.match(/^\s+-\s*(.*)$/)
: null;
if (seqMatch) {
if (seqItems === null) seqItems = [];
const itemVal = parseValue(seqMatch[1].trim());
if (itemVal !== null && itemVal !== '') seqItems.push(itemVal);
seqPending = false;
continue;
}
// Key-value pair
const kvMatch = line.match(/^(\w[\w-]*):\s*(.*)/);
if (kvMatch && !inMultiLine) {
// A new key terminates any pending/active block sequence.
commitSeq();
if (currentKey && multiLineValue) {
result[normalizeKey(currentKey)] = multiLineValue.trim();
}
@ -58,6 +92,15 @@ export function parseSimpleYaml(yaml) {
continue;
}
if (value === '') {
// Defer: this may be a block sequence (next line) or a null value.
seqKey = currentKey;
seqItems = null;
seqPending = true;
currentKey = null;
continue;
}
result[normalizeKey(currentKey)] = parseValue(value);
currentKey = null;
continue;
@ -79,6 +122,13 @@ export function parseSimpleYaml(yaml) {
currentKey = null;
}
}
continue;
}
// A non-item, non-key line while a sequence is pending/active terminates it
// (then the line is ignored, as before the fix).
if (seqPending || seqItems !== null) {
commitSeq();
}
}
@ -86,6 +136,8 @@ export function parseSimpleYaml(yaml) {
if (inMultiLine && currentKey) {
result[normalizeKey(currentKey)] = multiLineValue.trim();
}
// Flush a trailing block sequence / empty-valued key
commitSeq();
// Normalize arrays for known list fields
for (const field of ['allowed_tools', 'tools', 'paths', 'globs']) {