BREAKING CHANGE: the {NNN} in CA-{SCANNER}-{NNN} identifies the check that
produced the finding. It used to be the finding's position in that scanner's
output for that run, which made it unstable across CONFIGURATIONS, not just
across releases as STATE framed it. Measured on two fixtures: "No custom
subagents" was CA-GAP-007 on minimal-project and CA-GAP-004 on healthy-project.
A user who fixed an unrelated earlier gap silently renumbered every later one,
so a .config-audit-ignore pin retargeted to a neighbouring finding with no
version change at all.
Second measured arm: README already documented the opposite scheme. It and the
scanner headers describe ~20 numbers as check codes (CA-SKL-003 = oversized
body, CA-PLH-015 = folder shadowing, CA-TOK-006 = schema deferral), and the
counter could only produce those in the all-fire case -- source-order positions
are 4, 3 and 8. The documentation described the scheme; the implementation was
what was wrong. Every published number is preserved by construction and pinned
exhaustively in tests/lib/finding-codes.test.mjs.
scanners/lib/finding-codes.mjs is the single authority. Every finding() call
passes a `code`; an undeclared or missing one THROWS. No counter fallback --
that would reproduce D1's findGapId -> 'unknown' silent degradation and let a
half-converted scanner ship IDs that look valid. findingCounter/resetCounter
are deleted outright, not left as no-ops. Retirement is now a mechanism:
RETIRED_CODES tombstones a withdrawn key so its number is never reissued,
seeded with GAP t3_8 -- the D1 removal that opened this chunk.
IDs are consequently NOT unique per finding: one check failing in three files
emits three findings sharing an ID. That inverts which consumer is correct, so
every f.id/findingId site was classified before the change. diff-engine and
most of fix-engine already keyed on scanner+title+file (drift was never lying);
fix-engine's verification did not, and keyed on the ID alone -- fixing one of
two sibling instances marked both fixed, and the untouched one, still present
in the re-scan, was reported as a REGRESSION. Red test first, then keyed on
(findingId, file), which both planFixes and applyFixes already carry.
plugin-health's crossIds Set was measured and is a clean negative: cross
findings are allFindings.slice(crossPluginStart) and codes 18/19 are emitted
only in that tail, so the partition holds by construction.
unknownSuppressions() reports a pin that names no declared check, in the
--output-file payload (ux-rules rule 2 -- a stderr-only warning is invisible to
the commands) and only when one exists, so a clean config is byte-identical.
That is what makes the break safe: a stale pin goes loud instead of dying quiet.
Frozen tests/snapshots/v5.0.0/ untouched on disk. IDs are masked out of that
comparison (mask-finding-ids.mjs) rather than re-derived -- re-deriving
positional IDs would assert the retired scheme against itself, and #58's
isGapEntry off-by-one is the measured example of that misfiring. The dead
re-derivation is removed from strip-retired-gap.mjs. default-output snapshots
re-approved after confirming the diff is IDs and nothing else.
Guards, each seen red against its own defect: a missing code (scanner errors
out mid-sweep), an orphan declaration, a resurrected retired key, and a
documented ID naming no check. The sweep asserts the union across all 16
scanners, never per scanner -- a per-scanner assertion goes green on a partial
conversion.
Fasit written before implementation: docs/mbug28-id-semantics-fasit.local.md,
including one correction made before running (CML has 12 checks over 13 call
sites -- the anchored and calibrated char-budget arms are one check, which a
repeated-title sweep found and my call-site count had missed).
Suite 1535 -> 1573, 0 failing.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01MyqCQKK2ornJ1jFWwqx17E
158 lines
5.1 KiB
JavaScript
Executable file
158 lines
5.1 KiB
JavaScript
Executable file
#!/usr/bin/env node
|
|
|
|
/**
|
|
* token-hotspots CLI — emit ranked token hotspots and prompt-cache pattern findings
|
|
* for a target repo path.
|
|
*
|
|
* Usage:
|
|
* node token-hotspots-cli.mjs [path] [--json] [--output-file <path>] [--global]
|
|
* [--with-telemetry-recipe] [--accurate-tokens]
|
|
*
|
|
* Exit codes: 0=ok, 3=unrecoverable error.
|
|
* Zero external dependencies.
|
|
*/
|
|
|
|
import { resolve, dirname } from 'node:path';
|
|
import { fileURLToPath } from 'node:url';
|
|
import { readFile, stat } from 'node:fs/promises';
|
|
import { writeOutputFile } from './lib/write-output.mjs';
|
|
import { discoverConfigFiles } from './lib/file-discovery.mjs';
|
|
import { scan } from './token-hotspots.mjs';
|
|
import * as tokenizerApi from './lib/tokenizer-api.mjs';
|
|
import { humanizeFindings } from './lib/humanizer.mjs';
|
|
import { requireValidArgs } from './lib/cli-args.mjs';
|
|
|
|
/** Flag surface, measured 2026-08-09. Anything else is exit 3. */
|
|
const ARG_SPEC = {
|
|
boolean: [
|
|
'--json', '--raw', '--global', '--with-telemetry-recipe',
|
|
'--accurate-tokens', '--exclude-cache', '--no-exclude-cache',
|
|
],
|
|
value: ['--output-file'],
|
|
};
|
|
|
|
const __dirname = dirname(fileURLToPath(import.meta.url));
|
|
const TELEMETRY_RECIPE_PATH = resolve(__dirname, '..', 'knowledge', 'cache-telemetry-recipe.md');
|
|
|
|
const ACCURATE_TOKENS_SAMPLE_SIZE = 3;
|
|
|
|
async function calibrateAgainstApi(hotspots, apiKey) {
|
|
const sampled = hotspots.slice(0, ACCURATE_TOKENS_SAMPLE_SIZE);
|
|
let actualTokens = 0;
|
|
for (const hotspot of sampled) {
|
|
if (!hotspot?.path) continue;
|
|
let content;
|
|
try {
|
|
content = await readFile(hotspot.path, 'utf-8');
|
|
} catch {
|
|
continue;
|
|
}
|
|
const result = await tokenizerApi.callCountTokensApi(content, apiKey);
|
|
actualTokens += result.input_tokens;
|
|
}
|
|
return {
|
|
actual_tokens: actualTokens,
|
|
source: 'count_tokens_api',
|
|
sampled_hotspots: sampled.length,
|
|
};
|
|
}
|
|
|
|
async function main() {
|
|
const args = process.argv.slice(2);
|
|
if (!requireValidArgs(args, ARG_SPEC)) return;
|
|
let targetPath = '.';
|
|
let outputFile = null;
|
|
let jsonMode = false;
|
|
let rawMode = false;
|
|
let includeGlobal = false;
|
|
let withTelemetryRecipe = false;
|
|
let accurateTokens = false;
|
|
// Default ON for this live-cost scan: stale plugin-cache versions pollute the
|
|
// hotspot ranking with config that loads on zero turns. --no-exclude-cache
|
|
// restores the full walk. (B3)
|
|
let excludeCache = true;
|
|
|
|
for (let i = 0; i < args.length; i++) {
|
|
if (args[i] === '--json') jsonMode = true;
|
|
else if (args[i] === '--raw') rawMode = true;
|
|
else if (args[i] === '--global') includeGlobal = true;
|
|
else if (args[i] === '--with-telemetry-recipe') withTelemetryRecipe = true;
|
|
else if (args[i] === '--accurate-tokens') accurateTokens = true;
|
|
else if (args[i] === '--exclude-cache') excludeCache = true;
|
|
else if (args[i] === '--no-exclude-cache') excludeCache = false;
|
|
else if (args[i] === '--output-file' && args[i + 1]) outputFile = args[++i];
|
|
else if (!args[i].startsWith('-')) targetPath = args[i];
|
|
}
|
|
|
|
const absPath = resolve(targetPath);
|
|
try {
|
|
const s = await stat(absPath);
|
|
if (!s.isDirectory()) {
|
|
process.stderr.write(`Error: ${absPath} is not a directory\n`);
|
|
process.exitCode = 3;
|
|
return;
|
|
}
|
|
} catch {
|
|
process.stderr.write(`Error: path does not exist: ${absPath}\n`);
|
|
process.exitCode = 3;
|
|
return;
|
|
}
|
|
|
|
const discovery = await discoverConfigFiles(absPath, { includeGlobal, excludeCache });
|
|
const result = await scan(absPath, discovery);
|
|
|
|
const payload = {
|
|
scanner: result.scanner,
|
|
status: result.status,
|
|
files_scanned: result.files_scanned,
|
|
duration_ms: result.duration_ms,
|
|
total_estimated_tokens: result.total_estimated_tokens,
|
|
hotspots: result.hotspots,
|
|
findings: result.findings,
|
|
counts: result.counts,
|
|
};
|
|
|
|
if (withTelemetryRecipe) {
|
|
payload.telemetry_recipe_path = TELEMETRY_RECIPE_PATH;
|
|
}
|
|
|
|
if (accurateTokens) {
|
|
const apiKey = process.env.ANTHROPIC_API_KEY;
|
|
if (!apiKey || apiKey.length === 0) {
|
|
process.stderr.write('ANTHROPIC_API_KEY not set — skipping API calibration\n');
|
|
payload.calibration = { skipped: 'no-api-key' };
|
|
} else {
|
|
try {
|
|
payload.calibration = await calibrateAgainstApi(result.hotspots || [], apiKey);
|
|
} catch (err) {
|
|
// Error message is already key-masked by tokenizer-api.mjs.
|
|
process.stderr.write(`Calibration error: ${err.message}\n`);
|
|
payload.calibration = { skipped: 'api-error', error: err.message };
|
|
}
|
|
}
|
|
}
|
|
|
|
// Default mode humanizes payload.findings (NOT result.findings).
|
|
// --json and --raw bypass for v5.0.0 byte-equal output.
|
|
if (!jsonMode && !rawMode) {
|
|
payload.findings = humanizeFindings(payload.findings);
|
|
}
|
|
|
|
const json = JSON.stringify(payload, null, 2);
|
|
|
|
if (outputFile) {
|
|
await writeOutputFile(outputFile, json, 'utf-8');
|
|
}
|
|
|
|
if (jsonMode || rawMode || !outputFile) {
|
|
process.stdout.write(json + '\n');
|
|
}
|
|
}
|
|
|
|
const isDirectRun = process.argv[1] && resolve(process.argv[1]) === resolve(new URL(import.meta.url).pathname);
|
|
if (isDirectRun) {
|
|
main().catch(err => {
|
|
process.stderr.write(`Fatal: ${err.message}\n`);
|
|
process.exitCode = 3;
|
|
});
|
|
}
|