eyeprolog 1.5.22 → 1.5.23

package/conformance-report.md

@@ -8,9 +8,9 @@ when this report is generated; it is not inferred from fixture counts.
 
 | Gate | Passed | Total | Status |
 |---|---:|---:|---|
-| WG17 syntax | 372 | 372 | pass |
+| WG17 syntax | 366 | 366 | pass |
 
-The WG17 syntax row executes the vendored 372-case conformity-testing matrix
+The WG17 syntax row executes the vendored 366-case conformity-testing matrix
 against EyeProlog's strict ISO reader/writer. A behavior fix such as operator-token
 spelling therefore changes this report even when no corpus file is added or removed.
 

package/package.json

@@ -3,7 +3,7 @@
   "publishConfig": {
     "access": "public"
   },
-  "version": "1.5.22",
+  "version": "1.5.23",
   "description": "EyeProlog turns facts and rules into answers and proofs.",
   "type": "module",
   "main": "./index.js",

package/test/benchmark.mjs

@@ -128,6 +128,48 @@ function changeText(item) {
   return `${change < 0 ? '↓' : '↑'} ${value}`;
 }
 
+function summarizeResults(results) {
+  const comparable = results.filter((item) =>
+    Number.isFinite(item.medianMs) &&
+    item.medianMs > 0 &&
+    Number.isFinite(item.baselineMs) &&
+    item.baselineMs > 0);
+
+  if (comparable.length === 0) {
+    return {
+      comparable: 0,
+      total: results.length,
+      ratio: null,
+      changePercent: null,
+      currentTotalMs: null,
+      baselineTotalMs: null,
+      totalRatio: null,
+      totalChangePercent: null,
+    };
+  }
+
+  const ratio = Math.exp(
+    comparable.reduce(
+      (sum, item) => sum + Math.log(item.medianMs / item.baselineMs),
+      0,
+    ) / comparable.length,
+  );
+  const currentTotalMs = comparable.reduce((sum, item) => sum + item.medianMs, 0);
+  const baselineTotalMs = comparable.reduce((sum, item) => sum + item.baselineMs, 0);
+  const totalRatio = currentTotalMs / baselineTotalMs;
+
+  return {
+    comparable: comparable.length,
+    total: results.length,
+    ratio,
+    changePercent: (ratio - 1) * 100,
+    currentTotalMs,
+    baselineTotalMs,
+    totalRatio,
+    totalChangePercent: (totalRatio - 1) * 100,
+  };
+}
+
 function runWorker(item) {
   const child = spawnSync(process.execPath, [
     path.join(root, 'test', 'benchmark-worker.mjs'),
@@ -176,6 +218,8 @@ for (const item of selected) {
   });
 }
 
+const summary = summarizeResults(results);
+
 if (options.save != null) {
   await fs.mkdir(path.dirname(options.save), { recursive: true });
   const saved = {
@@ -202,6 +246,7 @@ if (options.json) {
     targetMs: options.targetMs,
     baseline: baselinePath,
     baselineWarning,
+    summary,
     results,
   }, null, 2)}\n`);
 } else {
@@ -220,9 +265,25 @@ if (options.json) {
   printRow(headers);
   printRow(widths.map((width) => '-'.repeat(width)));
   for (const row of rows) printRow(row);
+
+  if (summary.comparable > 0) {
+    process.stdout.write(
+      `\nSuite score: ${summary.ratio.toFixed(3)}x baseline ` +
+      `(${changeText({ changePercent: summary.changePercent })}); ` +
+      `equal-weight geometric mean across ${summary.comparable}/${summary.total} comparable benchmarks.\n`,
+    );
+    process.stdout.write(
+      `Time-weighted total: ${formatMs(summary.currentTotalMs)} vs ${formatMs(summary.baselineTotalMs)} ` +
+      `(${changeText({ changePercent: summary.totalChangePercent })}).\n`,
+    );
+  }
+
   process.stdout.write(`\n${results.length} benchmarks; ${options.runs} measured batch${options.runs === 1 ? '' : 'es'} each after ${options.warmup} warm-up batch${options.warmup === 1 ? '' : 'es'}, calibrated after one priming execution toward ${options.targetMs} ms per batch.\n`);
   if (baselineWarning) process.stdout.write(`${baselineWarning}\n`);
   if (baselinePath == null && !baselineWarning) process.stdout.write('No timing baseline found; run npm run benchmark:baseline to create .benchmarks/baseline.json.\n');
   if (options.save != null) process.stdout.write(`Saved timing baseline: ${path.relative(root, options.save)}\n`);
   process.stdout.write('Change compares the current median/op directly with the saved baseline median/op; the measured range is shown separately.\n');
+  if (summary.comparable > 0) {
+    process.stdout.write('Suite score is the geometric mean of current/baseline ratios, so every benchmark has equal relative weight; Time-weighted total compares summed medians and is dominated by longer workloads.\n');
+  }
 }

package/test/conformance/ISO-COMPLIANCE.md

@@ -19,7 +19,7 @@ relevant implementation-dependent overlap choice to an explicit audit outcome.
 
 | Requirement | Status | EyeProlog evidence / remaining work |
 | --- | --- | --- |
-| 5.1(a) prepare conforming Prolog text | covered | Clause 6 token/term production and rejection families are mapped by the strict production gate and the complete 372-case vendored WG17 syntax matrix; 7.4 preparation/directive behavior is separately closed. |
+| 5.1(a) prepare conforming Prolog text | covered | Clause 6 token/term production and rejection families are mapped by the strict production gate and the complete 366-case vendored WG17 syntax matrix; 7.4 preparation/directive behavior is separately closed. |
 | 5.1(b) execute conforming Prolog goals | covered | Clause 7 term/control/execution semantics, the higher-level 7.10 stream model, 7.11 flags, the 7.12 error envelope, all 8.2-8.17 built-in rows, and Clause 9 arithmetic have explicit executable dispositions. |
 | 5.1(c) reject nonconforming text/read-terms | covered | WG17 negative syntax cases, focused malformed-production/escape/comment/operator cases, read-term syntax errors, and strict rejection of implementation-specific syntax provide explicit rejection evidence across the Clause 6 families. |
 | 5.1(d) document permitted variations | covered | The clause-by-clause [ISO 5.4 decision index](ISO-IMPLEMENTATION-DEFINED.md) records every explicit implementation-defined decision found in the Part 1 + Corrigenda baseline and separately inventories implementation-specific extension families. The index retains an `audit gap` category for future discoveries; no current release-facing row depends on one. |
@@ -31,7 +31,7 @@ relevant implementation-dependent overlap choice to an explicit audit outcome.
 
 | Standard area | Status | Current evidence |
 | --- | --- | --- |
-| Clause 6 — tokens, terms, lists, operators, quoted text | covered | The strict Clause 6 gate maps atomic/variable/compound/operator/list/curly/double-quoted term forms, layout/comments, quoted escapes, integer bases/character codes, floating tokens, and solo/meta token boundaries, with malformed counterparts rejected. The complete 372-case WG17 syntax matrix provides independent production-level coverage, and a cross-profile gate verifies that normal syntax extensions preserve every strict-accepted standard observation. The implementation-defined 6.5/6.6 PCS/collation choices are documented separately. |
+| Clause 6 — tokens, terms, lists, operators, quoted text | covered | The strict Clause 6 gate maps atomic/variable/compound/operator/list/curly/double-quoted term forms, layout/comments, quoted escapes, integer bases/character codes, floating tokens, and solo/meta token boundaries, with malformed counterparts rejected. The complete 366-case WG17 syntax matrix provides independent production-level coverage, and a cross-profile gate verifies that normal syntax extensions preserve every strict-accepted standard observation. The implementation-defined 6.5/6.6 PCS/collation choices are documented separately. |
 | 7.1-7.3 — term types, term order, unification | covered | [ISO-TERM-SEMANTICS-MATRIX.md](ISO-TERM-SEMANTICS-MATRIX.md) records the five mutually exclusive strict term types, derived variable/compound/list notions, the complete standard-order classes and implementation-dependent variable-order choice, NSTO MGU/failure behavior, and EyeProlog's permitted consistent occurs-check failure for Part 1's undefined STO ordinary-unification cases. The normal JavaScript API string term is documented as a 5.5.4 extension and rejected at strict program/goal entry. |
 | 7.4 — Prolog text and directives | covered | [ISO-PROLOG-TEXT-EXECUTION-MATRIX.md](ISO-PROLOG-TEXT-EXECUTION-MATRIX.md) closes the preparation/directive rows: declaration semantics, source clauses, cross-text operators/character conversion/flags, initialization order/lifetime, `include/1`, and one-time `ensure_loaded/1`, with implementation-defined cross-text choices indexed under 5.4. |
 | 7.5-7.6 — database and term/clause conversion | covered | [ISO-PROLOG-TEXT-EXECUTION-MATRIX.md](ISO-PROLOG-TEXT-EXECUTION-MATRIX.md) closes static/dynamic and private/public procedure semantics, clause order, logical-update visibility, empty/unknown lifetime, and term/body/clause conversion. Source and runtime assertion conversion recurse through `,/2`, `;/2`, and `->/2`, preserve variable identity, and protect standardized static/control procedures. |
@@ -286,7 +286,7 @@ post-N289 STC drafts remain review input until standardized.
 | Criterion | Status | Evidence |
 | --- | --- | --- |
 | Clause 5 processor obligations have explicit dispositions | covered | `ISO-PROCESSOR-REQUIREMENTS.md` gives explicit outcomes for 5.1-5.5, including the strict/normal extension boundary. |
-| Clause 6 lexical/syntactic requirements have explicit dispositions | covered | the strict Clause 6 production/rejection gate and the 372-case vendored WG17 matrix cover the standard families; cross-profile preservation verifies that normal extensions do not reinterpret strict-accepted text. |
+| Clause 6 lexical/syntactic requirements have explicit dispositions | covered | the strict Clause 6 production/rejection gate and the 366-case vendored WG17 matrix cover the standard families; cross-profile preservation verifies that normal extensions do not reinterpret strict-accepted text. |
 | Clause 7 semantic requirements have explicit dispositions | covered | 7.1-7.12 now have explicit semantic, implementation-defined, or error-envelope dispositions backed by strict tests and the specialized matrices. |
 | Clause 8 built-in modes/errors have explicit dispositions | covered | `ISO-BUILTIN-MODE-ERROR-MATRIX.md` closes 8.2-8.17 row by row |
 | Clause 9 evaluable-functor requirements have explicit dispositions | covered | `ISO-EVALUABLE-FUNCTOR-MATRIX.md` plus the strict arithmetic regression closes the published Part 1 + Corrigenda arithmetic rows |
@@ -294,7 +294,7 @@ post-N289 STC drafts remain review input until standardized.
 | Implementation-specific strict/normal boundary is documented and tested | covered | all 5.5 hooks have explicit dispositions; the WG17 cross-profile gate verifies syntax-preservation for standard text accepted by the strict reader. |
 | Published Corrigenda 1-3 are incorporated | covered | dedicated conformance/strict tests and this ledger track all three published Corrigenda |
 | Current post-N289 draft is tracked without silently changing the published baseline | covered | `STC-DRAFT-STATUS.md` tracks reviewed draft items separately from normative requirements |
-| Independent external syntax corpus is an offline release gate | covered | the vendored WG17 syntax matrix has 372 executable dispositions checked against its upstream expectations |
+| Independent external syntax corpus is an offline release gate | covered | the vendored WG17 syntax matrix has 366 executable dispositions checked against its upstream expectations |
 | Third-party standard-core regression provenance is retained | covered | adapted Logtalk, Scryer, Trealla, and SWI-Prolog cases retain source identifiers and licenses in `THIRD_PARTY.md` |
 | No unexplained deviation remains in the release-facing ledger | covered | the release-facing ledger contains no remaining `audit` rows; documented variation points are implementation-defined/specific or draft-only rather than unexplained deviations. |
 

package/test/conformance/README.md

@@ -145,7 +145,7 @@ are recorded in [THIRD_PARTY.md](THIRD_PARTY.md).
 
 The corpus has 386 cases in `iso/` and 802 file-based conformance cases in
 total. Of those, 11 cases in `stc/` are explicitly labelled working-draft
-review evidence rather than normative ISO claims. The separate strict-reader WG17 matrix has 372 executable dispositions.
+review evidence rather than normative ISO claims. The separate strict-reader WG17 matrix has 366 executable dispositions.
 The generated `conformance-report.md` is the authoritative source for the current
 executable WG17 syntax result and file-based category totals. Together with regression, documentation-sync, API, example,
 and book-example checks, `npm test` is the release gate.

package/test/conformance/WG17-SYNTAX-STATUS.md

@@ -1,7 +1,7 @@
 # WG17 syntax traceability status
 
 Source: [Conformity Testing I: Syntax](https://www.complang.tuwien.ac.at/ulrich/iso-prolog/conformity_testing)  
-Upstream inventory checked: 2026-08-28
+Upstream inventory checked: 2026-09-01
 
 This ledger counts an upstream case when its WG17 identifier, query, and
 expected ISO disposition are stored in the offline executable matrix. Every
@@ -20,25 +20,25 @@ A represented case still has to pass the executable upstream assertion in
 
 | Measure | Count |
 | --- | ---: |
-| Active upstream cases | 372 |
-| Upstream cases represented in the executable matrix | 372 (100.0%) |
+| Active upstream cases | 366 |
+| Upstream cases represented in the executable matrix | 366 (100.0%) |
 | Not yet traced one-by-one | 0 |
 | Deleted upstream identifiers | #20, #273 |
 
 The matrix runs in strict ISO stream-reader mode as part of `npm test`. The
 3 upstream `waits` cases are checked through EyeProlog's interactive input
-hook. All 372 executable cases are independently checked against the
-upstream Codex expectation. 372 cases additionally retain exact reviewed
-outcomes for stronger regression checking; 0 cases currently rely on the upstream assertion alone.
+hook. All 366 executable cases are independently checked against the
+upstream Codex expectation. 365 cases additionally retain exact reviewed
+outcomes for stronger regression checking; 1 case currently relies on the upstream assertion alone.
 
 ## Traceable evidence
 
 | Executable evidence | Referenced IDs | WG17 cases |
 | --- | ---: | --- |
-| [complete offline executable matrix](../run-wg17.mjs) | 372 | #1–#19, #21–#272, #274–#374 |
+| [complete offline executable matrix](../run-wg17.mjs) | 366 | #1–#19, #21–#272, #274–#368 |
 
-The evidence groups overlap. Their union is **372** active cases:
-#1–#19, #21–#272, #274–#374.
+The evidence groups overlap. Their union is **366** active cases:
+#1–#19, #21–#272, #274–#368.
 
 ## Untraced upstream identifiers
 

package/test/conformance/wg17-syntax-cases.json

@@ -1,6 +1,6 @@
 {
   "source": "https://www.complang.tuwien.ac.at/ulrich/iso-prolog/conformity_testing",
-  "checkedOn": "2026-08-16",
+  "checkedOn": "2026-09-01",
   "protocol": "Each query is read and executed in strict ISO mode; /**/ rows reuse the preceding setup.",
   "cases": [
     {
@@ -4139,16 +4139,8 @@
       "query": "write_canonical(B+B).",
       "input": "write_canonical(B+B).",
       "readCount": 1,
-      "expected": "e.g. +(_1,\n_1)",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": "+(_A,_A)",
-            "variables": "['B'=B]"
-          }
-        ]
-      }
+      "expected": "e.g. +(_1,_1)",
+      "assertion": "upstream"
     },
     {
       "id": 228,
@@ -5565,99 +5557,8 @@
           }
         ]
       }
-    },
-    {
-      "id": 369,
-      "query": "writeq(?-).",
-      "input": "writeq(?-).",
-      "readCount": 1,
-      "expected": "?-",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": "?-",
-            "variables": "[]"
-          }
-        ]
-      }
-    },
-    {
-      "id": 370,
-      "query": "writeq(./*).",
-      "input": "writeq(./*).",
-      "readCount": 1,
-      "expected": "./*",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": "./*",
-            "variables": "[]"
-          }
-        ]
-      }
-    },
-    {
-      "id": 371,
-      "query": "writeq({*}).",
-      "input": "writeq({*}).",
-      "readCount": 1,
-      "expected": "{*}",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": "{*}",
-            "variables": "[]"
-          }
-        ]
-      }
-    },
-    {
-      "id": 372,
-      "query": "writeq(.*).",
-      "input": "writeq(.*).",
-      "readCount": 1,
-      "expected": ".*",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": ".*",
-            "variables": "[]"
-          }
-        ]
-      }
-    },
-    {
-      "id": 373,
-      "query": "writeq(...*).",
-      "input": "writeq(...*).",
-      "readCount": 1,
-      "expected": "...*",
-      "outcome": {
-        "type": "success",
-        "stages": [
-          {
-            "output": "...*",
-            "variables": "[]"
-          }
-        ]
-      }
-    },
-    {
-      "id": 374,
-      "query": "Finis ().",
-      "input": "Finis ().",
-      "readCount": 1,
-      "expected": "syntax err.",
-      "outcome": {
-        "type": "error",
-        "formal": "syntax_error(read_term)"
-      }
     }
   ],
   "sourceRevision": "1.300",
-  "sourceSha256": "d7ca05e90cfafe786d5edca4783e691a356a35508c50b62f5a99bd9057e2cd05"
+  "sourceSha256": "b6590c1c5269e8e62a1ec72a8f04f21f123a77709854a8a66c436df25f3ff418"
 }

package/test/conformance/wg17-syntax-coverage.json

@@ -1,14 +1,14 @@
 {
   "source": "https://www.complang.tuwien.ac.at/ulrich/iso-prolog/conformity_testing",
-  "checkedOn": "2026-08-28",
+  "checkedOn": "2026-09-01",
   "upstream": {
     "firstId": 1,
-    "lastId": 374,
+    "lastId": 368,
     "deletedIds": [
       20,
       273
     ],
-    "activeCases": 372
+    "activeCases": 366
   },
   "evidence": [
     {

package/test/run-regression.mjs

@@ -5387,11 +5387,12 @@ ${profile}`;
         assertEqual(report.total.positive + report.total.errors + report.total.warnings + report.total.proofs, report.total.total, 'conformance total');
         assertEqual(report.rows.some((row) => row.category === 'legacy-numbered'), false, 'legacy-numbered category');
         const wg17 = report.executable.find((gate) => gate.name === 'WG17 syntax');
-        assertEqual(wg17?.total, 372, 'WG17 executable total');
-        assertEqual(wg17?.passed, 372, 'WG17 executable passed');
+        const wg17FixtureTotal = readWg17SyntaxFixture().cases.length;
+        assertEqual(wg17?.total, wg17FixtureTotal, 'WG17 executable total');
+        assertEqual(wg17?.passed, wg17FixtureTotal, 'WG17 executable passed');
         assertArrayEqual(wg17?.failures ?? [], [], 'WG17 executable failures');
         const text = formatConformanceReport(report);
-        assertIncludes(text, '| WG17 syntax | 372 | 372 | pass |', 'report');
+        assertIncludes(text, `| WG17 syntax | ${wg17FixtureTotal} | ${wg17FixtureTotal} | pass |`, 'report');
         assertIncludes(text, '| variables |', 'report');
         assertIncludes(text, '| Proofs |', 'report');
         assertIncludes(text, '| **Total** |', 'report');
@@ -8342,6 +8343,7 @@ function documentedConformanceMetricIssues() {
   const report = buildConformanceReport();
   const iso = report.rows.find((row) => row.category === 'iso')?.total;
   const total = report.total.total;
+  const wg17 = report.executable.find((gate) => gate.name === 'WG17 syntax')?.total;
   const checks = [
     {
       file: path.join(packageRoot, 'the-art-of-eyeprolog.md'),
@@ -8371,6 +8373,21 @@ function documentedConformanceMetricIssues() {
       }
     }
   }
+  for (const file of [
+    path.join(packageRoot, 'test', 'conformance', 'README.md'),
+    path.join(packageRoot, 'test', 'conformance', 'ISO-COMPLIANCE.md'),
+  ]) {
+    const relative = path.relative(packageRoot, file);
+    const text = fs.readFileSync(file, 'utf8');
+    const claims = [
+      ...[...text.matchAll(/\b(\d+)-case[^\n|]*WG17/g)].map((match) => Number(match[1])),
+      ...[...text.matchAll(/WG17[^\n|]*?\b(\d+) executable/g)].map((match) => Number(match[1])),
+    ];
+    if (claims.length === 0) issues.push(`${relative}: WG17 total not found`);
+    for (const claim of claims) {
+      if (claim !== wg17) issues.push(`${relative}: WG17 count ${claim} != ${wg17}`);
+    }
+  }
   return issues.sort();
 }
 

package/tools/upgrade-wg17.mjs

@@ -11,6 +11,11 @@ const syntaxSource = 'https://www.complang.tuwien.ac.at/ulrich/iso-prolog/confor
 const syntaxFixturePath = path.join(packageRoot, 'test', 'conformance', 'wg17-syntax-cases.json');
 const syntaxCoveragePath = path.join(packageRoot, 'test', 'conformance', 'wg17-syntax-coverage.json');
 const syntaxStatusPath = path.join(packageRoot, 'test', 'conformance', 'WG17-SYNTAX-STATUS.md');
+const conformanceReportPath = path.join(packageRoot, 'conformance-report.md');
+const countDocumentationPaths = [
+  path.join(packageRoot, 'test', 'conformance', 'README.md'),
+  path.join(packageRoot, 'test', 'conformance', 'ISO-COMPLIANCE.md'),
+];
 
 const namedEntities = new Map([
   ['amp', '&'], ['lt', '<'], ['gt', '>'], ['quot', '"'], ['apos', "'"],
@@ -318,6 +323,20 @@ function formatIdList(ids) {
   return ids.length === 0 ? 'none' : ids.map((id) => `#${id}`).join(', ');
 }
 
+function updateDocumentedInventoryCount(previousCount, nextCount) {
+  if (previousCount === nextCount) return;
+  for (const filename of countDocumentationPaths) {
+    const original = fs.readFileSync(filename, 'utf8');
+    const updated = original
+      .replaceAll(`${previousCount}-case`, `${nextCount}-case`)
+      .replaceAll(`WG17 matrix has ${previousCount} executable`, `WG17 matrix has ${nextCount} executable`);
+    if (updated === original) {
+      throw new Error(`WG17 inventory count was not found in ${path.relative(packageRoot, filename)}`);
+    }
+    fs.writeFileSync(filename, updated);
+  }
+}
+
 async function readSource(source) {
   if (/^https?:\/\//i.test(source)) {
     const response = await fetch(source, {
@@ -415,6 +434,13 @@ export async function upgradeWg17({ check = false, source = syntaxSource } = {})
   // Generate status after the fixture/manifest are synchronized.
   const { renderWg17SyntaxStatus } = await import('./report-wg17-syntax-coverage.mjs');
   fs.writeFileSync(syntaxStatusPath, renderWg17SyntaxStatus());
+  updateDocumentedInventoryCount(previous.cases.length, fixture.cases.length);
+
+  // The public report executes the refreshed fixture, so keep its measured row
+  // synchronized as part of the same explicit upgrade operation.
+  const { buildConformanceReport, formatConformanceReport } = await import('../test/run-conformance-report.mjs');
+  const conformanceReport = buildConformanceReport();
+  fs.writeFileSync(conformanceReportPath, formatConformanceReport(conformanceReport));
 
   const upstreamAssertions = fixture.cases
     .filter((item) => item.outcome == null)