refactor: run progress metrics as TypeScript

Author: thymikee

docs/adr/0001-provider-first-integration-scenarios.md

@@ -58,7 +58,7 @@ Coverage is expected to improve over the old handler-heavy unit suite, but the f
 
 Operational metrics are generated by `pnpm test:integration:progress`. CI runs `pnpm test:integration:progress:check` after integration tests so public-command coverage, device-observable workflow flag coverage, and public-flag classification cannot silently regress. The script is the source of truth for provider-backed integration size, handler-unit size, mock-heavy handler pressure, public-command coverage, command-family ownership, device-observable workflow flag coverage, provider transcript pressure, and low-coverage files after a coverage run. Config, remote transport, Metro preparation, parser/client-only, report-writing, and boot-fallback flags stay in their owning unit/CLI suites and are reported as explicit exclusions rather than silently missing from the denominator. Provider pressure separates semantic Apple `simctl`/`devicectl`, macOS helper, and macOS host usage from generic Apple host-tool usage, and separates semantic Linux desktop/accessibility/clipboard/screenshot/input usage from generic Linux tool usage, so remote-adapter pressure is visible without treating named subproviders as raw shell intent.
 
-The progress CLI should stay a thin report and check runner over a progress model. The model owns discovery, coverage classification, provider-pressure accounting, and check-failure derivation; the CLI owns Markdown output and process exit behavior. Source parsing inside the model is an implementation detail, not the desired long-term interface. It should move to command-family metadata only when the progress script can consume that metadata without changing Node runtime assumptions or importing command modules with unrelated side effects.
+The progress CLI should stay a thin report and check runner over a progress model. The model owns discovery, coverage classification, provider-pressure accounting, and check-failure derivation; the CLI owns Markdown output and process exit behavior. The progress script runs as a Node type-stripped TypeScript script and should consume command metadata directly when the metadata API exposes the needed facet. Source parsing inside the model is an implementation detail, not the desired long-term interface, and should remain limited to facets that are not yet represented as runtime metadata, such as mapping typed client method calls back to command names.
 
 Every public command should have at least one provider-backed integration scenario that runs through the request router and request-scoped provider seams. Unit tests remain for parser matrices, selector matching, capability maps, malformed inputs, state machines, cleanup behavior, provider scope routing, and platform error boundaries.
 

package.json

@@ -132,8 +132,8 @@
     "test:unit": "vitest run --project unit",
     "test:coverage": "vitest run --coverage",
     "test:integration:provider": "vitest run --project provider-integration",
-    "test:integration:progress": "node scripts/integration-progress.mjs",
-    "test:integration:progress:check": "node scripts/integration-progress.mjs --check",
+    "test:integration:progress": "node --experimental-strip-types scripts/integration-progress.ts",
+    "test:integration:progress:check": "node --experimental-strip-types scripts/integration-progress.ts --check",
     "test:skillgym": "node test/skillgym/runner-environment.ts && pnpm build && skillgym run ./test/skillgym/suites/agent-device-smoke-suite.ts --config ./test/skillgym/skillgym.config.ts",
     "test:skillgym:case": "node test/skillgym/runner-environment.ts && pnpm build && skillgym run ./test/skillgym/suites/agent-device-smoke-suite.ts --config ./test/skillgym/skillgym.config.ts --case",
     "test:smoke": "node --test test/integration/smoke-*.test.ts",

scripts/integration-progress-model.mjs scripts/integration-progress-model.tsscripts/integration-progress-model.mjs renamed to scripts/integration-progress-model.ts

@@ -1,24 +1,23 @@
 import fs from 'node:fs';
 import path from 'node:path';
+import { PUBLIC_COMMANDS } from '../src/command-catalog.ts';
+import { listCommandMetadata } from '../src/commands/command-metadata.ts';
 
 const EMPTY_COVERAGE_METRIC = { pct: 0 };
 const EMPTY_STATEMENT_COVERAGE = { covered: 0, pct: 0, total: 0 };
 
 let ROOT = process.cwd();
 let COVERAGE_SUMMARY = path.join(ROOT, 'coverage/coverage-summary.json');
-let COMMAND_CATALOG_SOURCE = '';
 let clientCommandMethods = new Map();
 
 export function buildIntegrationProgressModel({ root = process.cwd() } = {}) {
   ROOT = root;
   COVERAGE_SUMMARY = path.join(ROOT, 'coverage/coverage-summary.json');
   const handlerTestDir = path.join(ROOT, 'src/daemon/handlers/__tests__');
   const providerScenarioDir = path.join(ROOT, 'test/integration/provider-scenarios');
-  const commandCatalog = path.join(ROOT, 'src/command-catalog.ts');
   const commandContractFiles = listFiles(path.join(ROOT, 'src/commands'), (file) =>
     file.endsWith(`${path.sep}index.ts`),
   );
-  COMMAND_CATALOG_SOURCE = fs.readFileSync(commandCatalog, 'utf8');
   clientCommandMethods = readClientCommandMethods(commandContractFiles);
 
   const handlerTests = listFiles(handlerTestDir, (file) => file.endsWith('.test.ts'));
@@ -417,19 +416,15 @@ function summarizePublicCommandCoverage(files) {
 }
 
 function readPublicCommands() {
-  return [...readPublicCommandEntries().values()].sort();
-}
-
-function readPublicCommandEntries() {
-  const match = COMMAND_CATALOG_SOURCE.match(/export const PUBLIC_COMMANDS = \{([\s\S]*?)\} as const;/);
-  if (!match) {
-    throw new Error('Unable to find PUBLIC_COMMANDS in src/command-catalog.ts');
-  }
-  const commands = new Map();
-  for (const command of match[1].matchAll(/\b([A-Za-z0-9_]+):\s*'([^']+)'/g)) {
-    commands.set(command[1], command[2]);
-  }
-  return commands;
+  const metadataNames = new Set(listCommandMetadata().map((metadata) => metadata.name));
+  return Object.values(PUBLIC_COMMANDS)
+    .map((name) => {
+      if (!metadataNames.has(name)) {
+        throw new Error(`Missing command metadata for public command: ${name}`);
+      }
+      return name;
+    })
+    .sort();
 }
 
 function readClientCommandMethods(commandContractFiles) {

scripts/integration-progress.mjs scripts/integration-progress.tsscripts/integration-progress.mjs renamed to scripts/integration-progress.ts

@@ -4,7 +4,7 @@ import {
   buildIntegrationProgressFailures,
   buildIntegrationProgressModel,
   formatPercent,
-} from './integration-progress-model.mjs';
+} from './integration-progress-model.ts';
 
 const CHECK_MODE = process.argv.includes('--check');
 const progress = buildIntegrationProgressModel({ root: process.cwd() });