feat(config-audit): --accurate-tokens API calibration (v5 N5) [skip-docs]

plugins/config-audit/scanners/token-hotspots-cli.mjs

@@ -6,22 +6,46 @@
  *
  * Usage:
  *   node token-hotspots-cli.mjs [path] [--json] [--output-file <path>] [--global]
- *                               [--with-telemetry-recipe]
+ *                               [--with-telemetry-recipe] [--accurate-tokens]
  *
  * Exit codes: 0=ok, 3=unrecoverable error.
  * Zero external dependencies.
  */
 
-import { resolve, dirname, join } from 'node:path';
+import { resolve, dirname } from 'node:path';
 import { fileURLToPath } from 'node:url';
-import { writeFile, stat } from 'node:fs/promises';
+import { writeFile, readFile, stat } from 'node:fs/promises';
 import { discoverConfigFiles } from './lib/file-discovery.mjs';
 import { resetCounter } from './lib/output.mjs';
 import { scan } from './token-hotspots.mjs';
+import * as tokenizerApi from './lib/tokenizer-api.mjs';
 
 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);
   let targetPath = '.';
@@ -29,11 +53,13 @@ async function main() {
   let jsonMode = false;
   let includeGlobal = false;
   let withTelemetryRecipe = false;
+  let accurateTokens = false;
 
   for (let i = 0; i < args.length; i++) {
     if (args[i] === '--json') jsonMode = 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] === '--output-file' && args[i + 1]) outputFile = args[++i];
     else if (!args[i].startsWith('-')) targetPath = args[i];
   }
@@ -69,6 +95,22 @@ async function main() {
     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 };
+      }
+    }
+  }
+
   const json = JSON.stringify(payload, null, 2);
 
   if (outputFile) {