promptwheel 0.8.4 → 0.8.6

package/bin/promptwheel.d.ts

@@ -254,6 +254,8 @@ export interface SetupFailure {
 // ---------------------------------------------------------------------------
 
 /** The Contract revision this build implements; bumps only when the verdict schema or the exit codes change. */
+/** The output lines read as a missing dependency in the clean copy (module not found, a shell's "command not found"). */
+export declare const MISSING_DEP: RegExp;
 export declare const CONTRACT_VERSION: '1';
 export declare const VERDICTS: readonly ['pass', 'fail', 'gamed', 'inconclusive'];
 export declare const METRIC_STATUSES: readonly ['improved', 'regressed', 'unchanged', 'inconclusive', 'unmeasurable'];

package/bin/promptwheel.mjs

@@ -165,7 +165,7 @@ const exitCodes = new WeakMap();
 const neverRan = (samples) => { const c = exitCodes.get(samples) || []; return c.length > 0 && c.every((x) => x == null || x === 126 || x === 127); };
 // Why a metric's command failed, read from its output: a dependency the clean copy does not have reads differently
 // from tests that simply fail. A hint for the person, never part of a verdict.
-const MISSING_DEP = /Cannot find (?:module|package) ['"][^'"\n]+['"]|ERR_MODULE_NOT_FOUND[^\n]*|ModuleNotFoundError: [^\n]+|No module named [^\n]+|error TS2307: [^\n]+|[^\n:]*: (?:command )?not found[^\n]*|can't find crate[^\n]*|cannot find package [^\n]+/i;
+const MISSING_DEP = /Cannot find (?:module|package) ['"][^'"\n]+['"]|ERR_MODULE_NOT_FOUND[^\n]*|ModuleNotFoundError: [^\n]+|No module named [^\n]+|error TS2307: [^\n]+|(?:^|\n)[^\n:]*(?:sh|bash|zsh|dash)(?::\s*\d+)?:[^\n]*?: (?:command )?not found[^\n]*|(?:^|\n)\S+: command not found[^\n]*|can't find crate[^\n]*|cannot find package [^\n]+/i;
 function whyFailed(text) {
   const m = String(text || '').replace(/\x1b\[[0-9;]*m/g, '').match(MISSING_DEP);
   return m ? { cause: 'missing-dependency', detail: m[0].trim().slice(0, 200) } : { cause: 'failing' };
@@ -356,6 +356,13 @@ const NON_SOURCE = [
   /(^|\/)(tests?|__tests?__|spec|e2e|fixtures|snapshots|__snapshots__|__mocks__)\//i,
   /\.(test|spec)\.[cm]?[jt]sx?$/i,
   /(^|\/)tests?\.[cm]?[jt]sx?$/i,                 // a file literally named test.js / tests.ts
+  // hyphen names (ava's and node --test's test-*.js, *-test.js, *-spec.js) count outside src/, lib/ and scripts/ only: real
+  // production code is named test-patterns.ts or generate-test.ts (found across 18k files, 2026-11-10). A fixed
+  // test-release.js at the root read as a source win before this (sendback bench, p-map).
+  /^(?!(?:.*\/)?(?:src|lib|scripts)\/)(?:.*\/)?tests?-[^/]*\.[cm]?[jt]sx?$/i,
+  /^(?!(?:.*\/)?(?:src|lib|scripts)\/)(?:.*\/)?[^/]+-(test|spec)\.[cm]?[jt]sx?$/i,
+  /_test\.[cm]?[jt]sx?$/i,                          // node --test's, Deno's and Bun's *_test.js, anywhere (a strong signal)
+  /\.test-d\.[cm]?tsx?$/i,                         // tsd type tests (index.test-d.ts), run by a test script like xo && ava && tsd
   /(^|\/)test_[^/]*\.py$/i, /_test\.py$/i, /(^|\/)conftest\.py$/i,
   // cross-language test-filename conventions, strong-signal tokens only (a dedicated
   // _test / _spec / Test(s) suffix, or a file literally named test.<lang>), so production
@@ -367,7 +374,15 @@ const NON_SOURCE = [
   /(^|\/)test_[^/]*\.(c|cc|cpp|cxx|h|hpp|go|rs)$/i,
   /_test\.(c|cc|cpp|cxx|h|hpp|go|rs|rb)$/i,
   /_spec\.rb$/i,
-  /[a-z0-9](Test|Tests)\.(java|kt|kts|scala)$/,
+  /[a-z0-9](Test|Tests)\.(java|kt|kts|scala|cs|php|swift)$/,   // JUnit, xUnit/NUnit (.NET), PHPUnit, XCTest
+  /(^|\/)[^/]+\.Tests?(\/|\.csproj$)/,                    // a .NET test project: MyApp.Tests/ and MyApp.Tests.csproj
+  /_spec\.[cm]?[jt]sx?$/i,                                 // Bun's *_spec.ts
+  /\.cy\.[cm]?[jt]sx?$/i,                                  // Cypress specs (login.cy.ts)
+  /_test\.(exs|dart)$/i, /(^|\/)integration_test\//i,    // ExUnit, Dart and Flutter
+  /(^|\/)testdata\//i, /(^|\/)benches\//i,               // Go test data at any depth, Rust benchmarks
+  // test runner and coverage-gate config: editing these skips tests or loosens a threshold
+  /(^|\/)\.(mocharc|nycrc|c8rc|coveragerc)[^/]*$/i, /(^|\/)\.rspec$/i, /(^|\/)codecov\.ya?ml$/i,
+  /(^|\/)phpunit\.xml(\.dist)?$/i, /(^|\/)vitest\.workspace\.[^/]+$/i, /(^|\/)setupTests\.[cm]?[jt]sx?$/i,
   /\.snap$/i, /(^|\/)golden[^/]*$/i, /\.golden$/i,
   // a grader/eval/score FILE by name in a scripting language (eval.py, grader-x.js, grade.sh, scoring.ts), never a
   // prefix: evaluate.ts, evaluation.py, scoreboard.js stay source. Compiled names stay source too (eval.c, eval.go
@@ -1368,7 +1383,7 @@ function parseArgs(argv) {
 
 // pure, side-effect-free helpers are exported for unit testing; the CLI below only
 // runs when this file is executed directly (not when imported by the test suite).
-export { extract, evaluate, median, spread, renderMarkdown, isNonSource, evaluatorMatcher, gain, judgeGaming, verdictFingerprint };
+export { MISSING_DEP, extract, evaluate, median, spread, renderMarkdown, isNonSource, evaluatorMatcher, gain, judgeGaming, verdictFingerprint };
 
 // ─────────────────────────────────────────────────────────────────────────────
 // Public library API: the Verified-Outcome Contract, in process.

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "promptwheel",
-  "version": "0.8.4",
+  "version": "0.8.6",
   "description": "A deterministic, zero-LLM check for your coding loop. A win must survive a re-run from the agent's source edits alone, so a test that went green by editing the test reads GAMED. Runs in CI or a Claude Code plugin.",
   "type": "module",
   "bin": {