config-audit/scanners/cache-prefix-scanner.mjs

/**
 * CPS Scanner — Cache-Prefix Stability Analyzer (v5 N3)
 *
 * Walks the CLAUDE.md cascade and flags volatile content anywhere in the
 * cached prefix (≤ CACHED_PREFIX_LINES). Distinguishes from TOK Pattern A,
 * which only inspects the top 30 lines: CPS catches a `!git log` at line 60
 * or a `${TIMESTAMP}` at line 100. Volatile content anywhere in the cached
 * prefix breaks prompt-cache reuse from that line forward.
 *
 * Volatile patterns extend the TOK set with shell-exec `!` prefix and
 * `${VAR}` substitutions — both common cache-busters in real CLAUDE.md files.
 *
 * Finding ID: CA-CPS-NNN. Severity: medium.
 *
 * Zero external dependencies.
 */

import { resolve, dirname } from 'node:path';
import { tmpdir } from 'node:os';
import { readTextFile } from './lib/file-discovery.mjs';
import { finding, scannerResult } from './lib/output.mjs';
import { SEVERITY } from './lib/severity.mjs';
import { findImports } from './lib/yaml-parser.mjs';

const SCANNER = 'CPS';

// Cache-prefix line threshold: content below this line is unlikely to be
// part of a stable cached prefix in typical sessions. The number is
// heuristic — the goal is to flag volatility that genuinely costs cache
// hits per turn, not to chase every inline date in a long backlog file.
const CACHED_PREFIX_LINES = 150;

// Volatile-pattern set (extends token-hotspots.mjs Pattern A).
const VOLATILE_PATTERNS = [
  { rx: /\{timestamp\}/i, label: '{timestamp} placeholder' },
  { rx: /\{uuid\}/i, label: '{uuid} placeholder' },
  { rx: /\{date\}/i, label: '{date} placeholder' },
  { rx: /\{session(?:_id)?\}/i, label: '{session_id} placeholder' },
  { rx: /\bactivity log\b/i, label: 'activity-log section' },
  { rx: /^\s*\d{4}-\d{2}-\d{2}T\d{2}:\d{2}/, label: 'ISO timestamp at line start' },
  { rx: /^\s*\[\d{4}-\d{2}-\d{2}/, label: 'dated log line [YYYY-MM-DD ...]' },
  // v5 N3 extensions:
  { rx: /^\s*!/, label: 'shell-exec line (! prefix)' },
  { rx: /\$\{[A-Z_][A-Z0-9_]*\}/, label: '${VAR} substitution' },
];

/**
 * Resolve an @import path relative to the file that declares it.
 * Mirrors import-resolver.mjs / token-hotspots.mjs path semantics.
 * @param {string} importPath
 * @param {string} containingFile
 * @returns {string} absolute resolved path
 */
function resolveImportPath(importPath, containingFile) {
  if (importPath.startsWith('~')) {
    const home = process.env.HOME || process.env.USERPROFILE || tmpdir();
    return resolve(importPath.replace(/^~/, home));
  }
  if (importPath.startsWith('/')) return importPath;
  return resolve(dirname(containingFile), importPath);
}

/**
 * Scan content for volatile lines within the cached prefix window.
 * Returns array of {line, label, snippet}.
 */
function findVolatileLines(content) {
  const out = [];
  if (!content) return out;
  const lines = content.split('\n').slice(0, CACHED_PREFIX_LINES);
  for (let i = 0; i < lines.length; i++) {
    for (const { rx, label } of VOLATILE_PATTERNS) {
      if (rx.test(lines[i])) {
        out.push({
          line: i + 1,
          label,
          snippet: lines[i].length > 120 ? lines[i].slice(0, 117) + '...' : lines[i],
        });
        break;
      }
    }
  }
  return out;
}

/**
 * Main scanner entry point.
 *
 * @param {string} targetPath
 * @param {{files: Array<{absPath:string, relPath:string, type:string, scope:string, size:number}>}} discovery
 */
export async function scan(targetPath, discovery) {
  const start = Date.now();
  const findings = [];
  let filesScanned = 0;

  // Files already scanned in-file below — an @import resolving to one of these
  // is reported by its own iteration, not duplicated as an import finding.
  const discoveredClaudeMd = new Set(
    discovery.files.filter(f => f.type === 'claude-md').map(f => f.absPath));
  // @imported files reported once, even when several CLAUDE.md files import them.
  const reportedImports = new Set();

  for (const f of discovery.files) {
    if (f.type !== 'claude-md') continue;
    filesScanned++;
    const content = await readTextFile(f.absPath);
    if (!content) continue;

    // --- In-file volatility (unchanged behavior) ---
    const volatile = findVolatileLines(content);
    // Skip volatility that's already covered by TOK Pattern A (lines 1–30) —
    // CPS' value is in the 31–150 range. Pattern A handles 1–30.
    const beyondTopThirty = volatile.filter(v => v.line > 30);
    if (beyondTopThirty.length > 0) {
      const evidence =
        beyondTopThirty.slice(0, 5)
          .map(v => `line ${v.line} (${v.label}): ${v.snippet}`)
          .join('; ');
      findings.push(finding({
        scanner: SCANNER,
        severity: SEVERITY.medium,
        title: 'Volatile content inside cached prefix breaks reuse',
        description:
          `${f.relPath || f.absPath} contains ${beyondTopThirty.length} volatile ` +
          `entr${beyondTopThirty.length === 1 ? 'y' : 'ies'} between lines 31 and ` +
          `${CACHED_PREFIX_LINES}. The prompt cache covers the file's prefix; ` +
          'any volatility forces a fresh cache write from that line down on every turn.',
        file: f.absPath,
        evidence,
        recommendation:
          'Move volatile sections (timestamps, !shell-exec, ${VAR} substitutions, dated logs) ' +
          `below line ${CACHED_PREFIX_LINES} or extract them to an @import-ed file outside the ` +
          'cached prefix. Stable content above, volatile content below.',
        category: 'token-efficiency',
      }));
    }

    // --- v5.10 B6: volatility inside @imported files ---
    // @import-ed content is inlined into the cached prefix at the import site.
    // TOK Pattern A and the in-file scan above never look past the importing
    // file, so volatility in an imported file is otherwise invisible. We scan
    // direct imports only (one hop); IMP owns deep-chain analysis. The whole
    // imported-file prefix counts (no lines-1–30 skip — that exclusion is
    // root-file-specific to avoid Pattern A overlap, which does not reach here).
    for (const imp of findImports(content)) {
      if (imp.line > CACHED_PREFIX_LINES) continue; // import site outside prefix
      const resolved = resolveImportPath(imp.path, f.absPath);
      if (discoveredClaudeMd.has(resolved)) continue; // scanned in its own iteration
      if (reportedImports.has(resolved)) continue;
      reportedImports.add(resolved);
      const importedContent = await readTextFile(resolved);
      if (!importedContent) continue;
      const importedVolatile = findVolatileLines(importedContent);
      if (importedVolatile.length === 0) continue;

      const importEvidence =
        `imported by ${f.relPath || f.absPath} (@${imp.path} at line ${imp.line}); ` +
        importedVolatile.slice(0, 5)
          .map(v => `line ${v.line} (${v.label}): ${v.snippet}`)
          .join('; ');
      findings.push(finding({
        scanner: SCANNER,
        severity: SEVERITY.medium,
        title: 'Volatile content in @imported file breaks cached prefix',
        description:
          `@${imp.path} (imported by ${f.relPath || f.absPath} at line ${imp.line}) contains ` +
          `${importedVolatile.length} volatile entr${importedVolatile.length === 1 ? 'y' : 'ies'} ` +
          `within its first ${CACHED_PREFIX_LINES} lines. @import-ed content is inlined into the ` +
          'prompt-cache prefix, so volatility there forces a fresh cache write every turn — even ' +
          'when the importing CLAUDE.md is itself byte-stable.',
        file: resolved,
        evidence: importEvidence,
        recommendation:
          'Move volatile content (timestamps, !shell-exec, ${VAR} substitutions, dated logs) out ' +
          'of the @imported file, or import it below the cached-prefix window. Keep imported config ' +
          'byte-stable so the importing file\'s cache survives.',
        category: 'token-efficiency',
      }));
    }
  }

  return scannerResult(SCANNER, 'ok', findings, filesScanned, Date.now() - start);
}