ata-validator 1.19.0 → 1.21.0

package/lib/plan-compiler.js

@@ -1,4 +1,9 @@
 'use strict';
+const { collapseBranches } = require('./branch-collapse');
+
+// One branch title, for the collapsed anyOf/oneOf error. The compiled node
+// keeps the schema it came from, which is where a `title` lives.
+const branchTitle = (n) => (n && n.schema && typeof n.schema.title === 'string' ? n.schema.title : '');
 
 // Compiles interpreter Plans into a tree of specialized closures. No source
 // generation, no `new Function`: this is plain closure composition, so it
@@ -334,13 +339,13 @@ function install(deps) {
       if (collect) {
         cstep = (data, errors, instancePath, schemaPath, stack, rec) => {
           const pl = pLen(rec), n0 = rec.n, xl = xLen(rec);
-          const ok = target.c(data, errors, instancePath, schemaPath + seg, stack, rec);
+          const ok = target.c(data, errors, instancePath, schemaPath, stack, rec);
           if (!ok) undo(rec, pl, n0, xl);
           return ok;
         };
         vstep = (data, stack, rec) => target.v(data, stack, rec);
       } else {
-        cstep = (data, errors, instancePath, schemaPath, stack) => target.c(data, errors, instancePath, schemaPath + seg, stack);
+        cstep = (data, errors, instancePath, schemaPath, stack) => target.c(data, errors, instancePath, schemaPath, stack);
         vstep = target.v;
       }
       if (ctx.guard) {
@@ -447,7 +452,10 @@ function install(deps) {
           ok = false;
         }
         if (maxC !== undefined && matched > maxC) {
-          if (errors !== NOERRORS) errors.push(err('maxContains', 'maxContains', instancePath, schemaPath + '/maxContains', { limit: maxC }, `must NOT contain more than ${maxC} valid item(s)`));
+          // Reported as `contains` at `#/contains`, the way the generated code
+          // and the reference implementation both do it: maxContains bounds the
+          // same keyword rather than being one of its own.
+          if (errors !== NOERRORS) errors.push(err('contains', 'contains', instancePath, schemaPath + '/contains', { minContains: minC, maxContains: maxC }, `must NOT contain more than ${maxC} valid item(s)`));
           ok = false;
         }
         return ok;
@@ -493,6 +501,13 @@ function install(deps) {
         ? P.patternProperties.map((e) => ({ re: e.re, src: e.src, fn: child(e.node) }))
         : null;
       const apFn = P.additionalProperties !== undefined ? child(P.additionalProperties) : null;
+      // `additionalProperties: false` is a boolean subschema, but its error is
+      // not the generic "boolean schema is false": every consumer switches on
+      // keyword === 'additionalProperties' and reads params.additionalProperty
+      // to learn which key was rejected. Reporting it as `not` at the key's own
+      // path loses both, and that shape is what the generated code emits, so
+      // the two engines have to agree here.
+      const apFalse = P.additionalProperties === false;
       const pnFn = P.propertyNames !== undefined ? child(P.propertyNames) : null;
       steps.push((data, errors, instancePath, schemaPath, stack, rec) => {
         if (dataBits(data) !== T_OBJECT) return true;
@@ -500,7 +515,12 @@ function install(deps) {
         const keys = collect ? keysOf(rec, data) : Object.keys(data);
         if (pnFn !== null) {
           for (const k of keys) {
-            if (!pnFn.c(k, errors, instancePath + '/' + escapePointer(k), schemaPath + '/propertyNames', stack)) {
+            // propertyNames applies its subschema to the property NAME, not to
+            // the value sitting at that key, so the failure is reported against
+            // the object that carries the name rather than against `/<key>`.
+            // The generated code and the compat shim both do it this way, and
+            // the shim has to because that is where the reference puts it.
+            if (!pnFn.c(k, errors, instancePath, schemaPath + '/propertyNames', stack)) {
               ok = false;
               if (errors === NOERRORS) return false;
             }
@@ -530,7 +550,11 @@ function install(deps) {
             }
           }
           if (!evaluated && apFn !== null) {
-            if (!apFn.c(data[key], errors, instancePath + '/' + escapePointer(key), schemaPath + '/additionalProperties', stack)) {
+            if (apFalse) {
+              ok = false;
+              if (errors === NOERRORS) return false;
+              errors.push(err('additionalProperties', 'additionalProperties', instancePath, schemaPath + '/additionalProperties', { additionalProperty: key }, 'must NOT have additional properties'));
+            } else if (!apFn.c(data[key], errors, instancePath + '/' + escapePointer(key), schemaPath + '/additionalProperties', stack)) {
               ok = false;
               if (errors === NOERRORS) return false;
             }
@@ -717,20 +741,31 @@ function install(deps) {
     }
     if (P.anyOf !== null) {
       const fns = P.anyOf.map((v) => inPlace(v, base));
+      const titles = P.anyOf.map(branchTitle);
       steps.push((data, errors, instancePath, schemaPath, stack, rec) => {
         const scratch = errors === NOERRORS ? NOERRORS : [];
         let any = false;
+        // Per-branch errors, taken as slices of the shared scratch rather than
+        // an array each, so a branch that passes costs nothing extra.
+        const branches = errors === NOERRORS ? null : [];
         for (let i = 0; i < fns.length; i++) {
+          const mark = branches === null ? 0 : scratch.length;
+          let ok;
           if (collect) {
             const pl = pLen(rec), n0 = rec.n, xl = xLen(rec);
-            if (fns[i].c(data, scratch, instancePath, schemaPath + '/anyOf/' + i, stack, rec)) any = true;
+            ok = fns[i].c(data, scratch, instancePath, schemaPath + '/anyOf/' + i, stack, rec);
+            if (ok) any = true;
             else undo(rec, pl, n0, xl);
-          } else if (fns[i].c(data, scratch, instancePath, schemaPath + '/anyOf/' + i, stack)) any = true;
+          } else {
+            ok = fns[i].c(data, scratch, instancePath, schemaPath + '/anyOf/' + i, stack);
+            if (ok) any = true;
+          }
+          if (branches !== null) branches.push({ valid: ok, errors: scratch.slice(mark), title: titles[i] });
         }
         if (!any) {
-          if (errors !== NOERRORS) {
-            for (const e of scratch) errors.push(e);
-            errors.push(err('anyOf', 'anyOf', instancePath, schemaPath + '/anyOf', {}, 'must match a schema in anyOf'));
+          if (branches !== null) {
+            const collapsed = collapseBranches({ keyword: 'anyOf', branchResults: branches, parentPath: instancePath, parentSchemaPath: schemaPath + '/anyOf' });
+            if (collapsed !== null) errors.push(collapsed);
           }
           return false;
         }
@@ -756,25 +791,36 @@ function install(deps) {
     }
     if (P.oneOf !== null) {
       const fns = P.oneOf.map((v) => inPlace(v, base));
+      const titles = P.oneOf.map(branchTitle);
       steps.push((data, errors, instancePath, schemaPath, stack, rec) => {
         const scratch = errors === NOERRORS ? NOERRORS : [];
         let count = 0;
+        // Per-branch results, so a failing oneOf collapses to the branch that
+        // came closest instead of every branch's complaints at once.
+        const branches = errors === NOERRORS ? null : [];
         // With a record: the winner's annotations stay, every other branch's
         // are undone, and a second winner undoes everything since the node
         // fails and merges nothing.
         const pl0 = collect ? pLen(rec) : 0, n00 = collect ? rec.n : 0, xl0 = collect ? xLen(rec) : 0;
         for (let i = 0; i < fns.length; i++) {
+          const mark = branches === null ? 0 : scratch.length;
+          let ok;
           if (collect) {
             const pl = pLen(rec), n0 = rec.n, xl = xLen(rec);
-            if (fns[i].c(data, scratch, instancePath, schemaPath + '/oneOf/' + i, stack, rec)) count++;
+            ok = fns[i].c(data, scratch, instancePath, schemaPath + '/oneOf/' + i, stack, rec);
+            if (ok) count++;
             else undo(rec, pl, n0, xl);
-          } else if (fns[i].c(data, scratch, instancePath, schemaPath + '/oneOf/' + i, stack)) count++;
+          } else {
+            ok = fns[i].c(data, scratch, instancePath, schemaPath + '/oneOf/' + i, stack);
+            if (ok) count++;
+          }
+          if (branches !== null) branches.push({ valid: ok, errors: scratch.slice(mark), title: titles[i] });
         }
         if (count !== 1) {
           if (collect) undo(rec, pl0, n00, xl0);
-          if (errors !== NOERRORS) {
-            if (count === 0) for (const e of scratch) errors.push(e);
-            errors.push(err('oneOf', 'oneOf', instancePath, schemaPath + '/oneOf', { passingSchemas: count }, 'must match exactly one schema in oneOf'));
+          if (branches !== null) {
+            const collapsed = collapseBranches({ keyword: 'oneOf', branchResults: branches, parentPath: instancePath, parentSchemaPath: schemaPath + '/oneOf' });
+            if (collapsed !== null) errors.push(collapsed);
           }
           return false;
         }

package/lib/retry-message.js

@@ -0,0 +1,52 @@
+'use strict';
+
+// The string to send back to a model when its structured output failed
+// validation.
+//
+// This exists because of a measurement rather than a preference. Feeding the
+// conventional error text back into a retry loop, one model, an invoice schema,
+// paired so the same failing output went to both arms:
+//
+//   constraints the model could infer from context   40 of 40 recovered
+//   constraints it could not (an internal vocabulary) 0 of 30 recovered
+//
+// With the expected values named in the message, the second case was 30 of 30.
+// The conventional message for `enum` is "must be equal to one of the allowed
+// values", which names neither the values nor what arrived, so the model
+// guesses. It guesses plausibly and it is always wrong: "HH" for a Hamburg
+// office, "FR" for a Lyon desk. Every retry came back well formed and still
+// invalid, and no number of further retries can fix it, because what is needed
+// was never in the loop.
+//
+// ata already carries the missing halves on each error, `detail` and
+// `received`. The trap is that joining `message`, which is the obvious thing to
+// do, throws both away. So this is one call that does not.
+
+function line (error) {
+  const where = error.instancePath || error.path || '';
+  const body = typeof error.detail === 'string' && error.detail ? error.detail : error.message;
+  // `detail` usually quotes the offending value already; saying it twice reads
+  // like a stutter in a string that is going into a prompt. A container is
+  // summarised as `[object, ~0.1KB]` rather than shown, which tells a model
+  // nothing it cannot see in its own output, so that is left out too.
+  const raw = error.received === undefined || error.received === null ? '' : String(error.received);
+  const useless = raw.charAt(0) === '[' && /^\[(object|array)\b/.test(raw);
+  const received = useless ? '' : raw;
+  const got = received && body && !body.includes(received) ? `, got ${received}` : '';
+  return `${where || '/'}: ${body}${got}`;
+}
+
+// toRetryMessage(errors, opts)
+//   opts.limit  most errors to include (default 20). A model does not act on
+//               forty complaints, and the prompt is not free.
+function toRetryMessage (errors, opts) {
+  if (!errors || typeof errors.length !== 'number' || errors.length === 0) return '';
+  const limit = opts && typeof opts.limit === 'number' ? opts.limit : 20;
+  const shown = errors.length > limit ? Array.prototype.slice.call(errors, 0, limit) : errors;
+  const lines = [];
+  for (let i = 0; i < shown.length; i++) lines.push(line(shown[i]));
+  if (errors.length > shown.length) lines.push(`and ${errors.length - shown.length} more`);
+  return lines.join('\n');
+}
+
+module.exports = { toRetryMessage };

package/lib/version.js

@@ -7,4 +7,4 @@
 //
 // Kept in lockstep with package.json by `tests/test_version_sync.js`.
 
-module.exports = '1.19.0';
+module.exports = '1.21.0';

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ata-validator",
-  "version": "1.19.0",
+  "version": "1.21.0",
   "description": "JSON Schema validation with first-class TypeScript and zero runtime cost. AOT compile to per-schema ESM modules with zero validator dependency. Generic Validator<T> for TypeBox/Zod/Valibot composition. Optional runtime API. Standard Schema V1 compatible.",
   "main": "index.js",
   "module": "index.mjs",
@@ -51,7 +51,7 @@
     "release:check": "node scripts/regen-safe-regex-source.js && node tests/test_pack_purity.js && node scripts/check-doc-coverage.js && node tests/test_error_codes_lock.js && node tests/test_safe_regex_source_sync.js && node tests/test_version_sync.js",
     "build": "cmake-js build --target ata",
     "rebuild": "cmake-js rebuild --target ata",
-    "test": "node test.js && node tests/test_removed_aot_methods.js && node tests/test_no_native.js && node tests/test_no_eval.js && node tests/test_property_dependencies.js && node tests/test_v1_dialect.js && node tests/test_buffer_path_parity.js && node tests/test_buffer_gate.js && node tests/test_buffer_reject_cost.js && node tests/test_nan_verdict.js && node tests/test_remove_additional_nested.js && node tests/test_exclusive_bounds.js && node tests/test_engine_differential.js && node tests/test_aot_parse.js && node tests/test_draft7_semantics.js && node tests/test_metaschema_ref.js && node tests/test_pure_js_unsupported.js && node tests/test_native_load_order.js && node tests/test_pack_purity.js && node tests/test_make_native_package.js && node tests/test_browser_nofs.js && node tests/test_browser_imports_guard.js && node tests/test_version_sync.js && node tests/test_native_loaded.js && node tests/test_safe_regex_source_sync.js && node tests/test_t_builder.js && node tests/test_async_refine.js && node tests/test_safe_regex.js && node tests/test_safe_regex_integration.js && node tests/test_aot_build.js && node tests/test_aot_differential.js && node tests/test_aot_cli_build.js && node tests/test_aot_cli_smoke.js && node tests/test_bundle_standalone.js && node tests/test_standalone_anyof.js && node tests/test_standalone_formats.js && node tests/test_aot_format_mode.js && node tests/test_aot_additional_props_errors.js && node tests/test_id_anchor_refs.js && node tests/test_engine_routing.js && node tests/test_engine_diagnostic.js && node tests/test_format_engine_parity.js && node tests/test_formats_single_pass.js && node tests/test_format_single_error.js && node tests/test_defs_pointer_alias.js && node tests/test_cross_doc_root_ref.js && node tests/test_codegen_entrypoint_agreement.js && node tests/test_hybrid_agreement.js && node tests/test_codegen_edge_shapes.js && node tests/test_ajv_errors.js && node tests/test_custom_keywords.js && node tests/test_ajv_parity.js && node tests/test_user_format_error_path.js && node tests/test_unevaluated_error_path.js && node tests/test_pattern_properties_errors.js && node tests/test_no_input_mutation.js && node tests/test_typed_validator_runner.js && node tests/test_define_schema.js && node tests/test_error_codes_lock.js && node tests/test_error_code_lookup.js && node tests/test_error_order.js && node tests/test_error_order_ordinal.js && node tests/test_rejection_shape.js && node tests/test_lazy_normalization.js && node tests/test_value_equality.js && node tests/test_vocabulary.js && node tests/test_schema_scan.js && node tests/test_lazy_errors.js && node tests/test_lazy_instance.js && node tests/test_cyclic_input.js && node tests/test_native_error_codes.js && node tests/test_verdict_preprocess.js && node tests/test_plan_compiler.js && node tests/test_nullable.js && node tests/test_validate_and_parse.js && node tests/test_validate_data.js && node tests/test_enrich_error.js && node tests/test_enrich_received.js && node tests/test_rich_errors_optout.js && node tests/test_error_messages.js && node tests/test_source_positions.js && node tests/fuzz_positions.js && node tests/test_data_positions.js && node tests/test_render_shared.js && node tests/test_renderers.js && node tests/test_additive_fields.js && node tests/test_diagnostic_source.js && node tests/test_diagnose.js && node tests/test_correlate.js && node tests/test_diagnostics_score.js && node tests/test_runtime_error_dx.js && node tests/test_aot_error_dx.js && node tests/test_abort_early.js && node tests/test_branch_collapse.js && node tests/test_suggestions.js && node tests/test_cli_validate.js && node tests/test_cli_version.js && node benchmark/bench_aot_size.mjs",
+    "test": "node test.js && node tests/test_removed_aot_methods.js && node tests/test_no_native.js && node tests/test_no_eval.js && node tests/test_property_dependencies.js && node tests/test_v1_dialect.js && node tests/test_buffer_path_parity.js && node tests/test_buffer_gate.js && node tests/test_buffer_reject_cost.js && node tests/test_nan_verdict.js && node tests/test_remove_additional_nested.js && node tests/test_exclusive_bounds.js && node tests/test_engine_differential.js && node tests/test_error_shape_differential.js && node tests/test_output_format.js && node tests/test_retry_message.js && node tests/test_describe_schema.js && node tests/test_aot_parse.js && node tests/test_draft7_semantics.js && node tests/test_metaschema_ref.js && node tests/test_pure_js_unsupported.js && node tests/test_native_load_order.js && node tests/test_pack_purity.js && node tests/test_make_native_package.js && node tests/test_browser_nofs.js && node tests/test_browser_imports_guard.js && node tests/test_version_sync.js && node tests/test_native_loaded.js && node tests/test_safe_regex_source_sync.js && node tests/test_t_builder.js && node tests/test_async_refine.js && node tests/test_safe_regex.js && node tests/test_safe_regex_integration.js && node tests/test_aot_build.js && node tests/test_aot_differential.js && node tests/test_aot_cli_build.js && node tests/test_aot_cli_smoke.js && node tests/test_bundle_standalone.js && node tests/test_standalone_anyof.js && node tests/test_standalone_formats.js && node tests/test_aot_format_mode.js && node tests/test_aot_additional_props_errors.js && node tests/test_id_anchor_refs.js && node tests/test_engine_routing.js && node tests/test_engine_diagnostic.js && node tests/test_format_engine_parity.js && node tests/test_formats_single_pass.js && node tests/test_format_single_error.js && node tests/test_defs_pointer_alias.js && node tests/test_cross_doc_root_ref.js && node tests/test_codegen_entrypoint_agreement.js && node tests/test_hybrid_agreement.js && node tests/test_codegen_edge_shapes.js && node tests/test_ajv_errors.js && node tests/test_custom_keywords.js && node tests/test_aot_external_checks.js && node tests/test_ajv_parity.js && node tests/test_user_format_error_path.js && node tests/test_unevaluated_error_path.js && node tests/test_pattern_properties_errors.js && node tests/test_no_input_mutation.js && node tests/test_typed_validator_runner.js && node tests/test_define_schema.js && node tests/test_error_codes_lock.js && node tests/test_error_code_lookup.js && node tests/test_error_order.js && node tests/test_error_order_ordinal.js && node tests/test_rejection_shape.js && node tests/test_lazy_normalization.js && node tests/test_value_equality.js && node tests/test_vocabulary.js && node tests/test_schema_scan.js && node tests/test_lazy_errors.js && node tests/test_lazy_instance.js && node tests/test_cyclic_input.js && node tests/test_native_error_codes.js && node tests/test_verdict_preprocess.js && node tests/test_plan_compiler.js && node tests/test_nullable.js && node tests/test_validate_and_parse.js && node tests/test_validate_data.js && node tests/test_enrich_error.js && node tests/test_enrich_received.js && node tests/test_rich_errors_optout.js && node tests/test_error_messages.js && node tests/test_source_positions.js && node tests/fuzz_positions.js && node tests/test_data_positions.js && node tests/test_render_shared.js && node tests/test_renderers.js && node tests/test_additive_fields.js && node tests/test_diagnostic_source.js && node tests/test_diagnose.js && node tests/test_correlate.js && node tests/test_diagnostics_score.js && node tests/test_runtime_error_dx.js && node tests/test_aot_error_dx.js && node tests/test_abort_early.js && node tests/test_branch_collapse.js && node tests/test_suggestions.js && node tests/test_cli_validate.js && node tests/test_cli_version.js && node benchmark/bench_aot_size.mjs",
     "bench:size": "node benchmark/bench_aot_size.mjs",
     "test:suite": "node tests/run_suite.js && node tests/run_suite.js draft7 && node tests/run_suite.js v1",
     "test:compat": "node tests/test_compat.js",
@@ -122,13 +122,13 @@
     "LICENSE"
   ],
   "optionalDependencies": {
-    "@ata-validator/native-darwin-arm64": "1.19.0",
-    "@ata-validator/native-darwin-x64": "1.19.0",
-    "@ata-validator/native-linux-arm64-gnu": "1.19.0",
-    "@ata-validator/native-linux-arm64-musl": "1.19.0",
-    "@ata-validator/native-linux-x64-gnu": "1.19.0",
-    "@ata-validator/native-linux-x64-musl": "1.19.0",
-    "@ata-validator/native-win32-x64": "1.19.0"
+    "@ata-validator/native-darwin-arm64": "1.21.0",
+    "@ata-validator/native-darwin-x64": "1.21.0",
+    "@ata-validator/native-linux-arm64-gnu": "1.21.0",
+    "@ata-validator/native-linux-arm64-musl": "1.21.0",
+    "@ata-validator/native-linux-x64-gnu": "1.21.0",
+    "@ata-validator/native-linux-x64-musl": "1.21.0",
+    "@ata-validator/native-win32-x64": "1.21.0"
   },
   "peerDependencies": {
     "yaml": "^2.0.0"