harden history find tokens

src/Config/RetriexEffectiveConfigProvider.php

@@ -527,6 +527,14 @@ final readonly class RetriexEffectiveConfigProvider
             'enabled' => $this->searchRepairConfig->isEnabled(),
             'max_repair_queries' => $this->searchRepairConfig->getMaxRepairQueries(),
             'min_primary_results_without_repair' => $this->searchRepairConfig->getMinPrimaryResultsWithoutRepair(),
+            'strict_requested_accessory_code_repair' => $this->searchRepairConfig->shouldRestrictRequestedAccessoryCodeRepair(),
+            'prefer_prompt_anchored_model_for_requested_accessory_code' => $this->searchRepairConfig->shouldPreferPromptAnchoredModelForRequestedAccessoryCode(),
+            'requested_accessory_code_fallback_query_templates' => $this->searchRepairConfig->getRequestedAccessoryCodeFallbackQueryTemplates(),
+            'requested_accessory_code_fallback_terms' => $this->searchRepairConfig->getRequestedAccessoryCodeFallbackTerms(),
+            'requested_accessory_code_context_prefix_terms' => $this->searchRepairConfig->getRequestedAccessoryCodeContextPrefixTerms(),
+            'requested_accessory_code_proximity_window' => $this->searchRepairConfig->getRequestedAccessoryCodeProximityWindow(),
+            'specific_model_candidate_patterns' => $this->searchRepairConfig->getSpecificModelCandidatePatterns(),
+            'model_candidate_exclude_terms' => $this->searchRepairConfig->getModelCandidateExcludeTerms(),
             'generic_candidate_tokens' => $this->searchRepairConfig->getGenericCandidateTokens(),
             'accessory_candidate_terms' => $this->searchRepairConfig->getAccessoryCandidateTerms(),
             'accessory_or_bundle_terms' => $this->searchRepairConfig->getAccessoryOrBundleTerms(),
@@ -546,6 +554,7 @@ final readonly class RetriexEffectiveConfigProvider
             'patterns' => [
                 'model_candidate' => $this->searchRepairConfig->getModelCandidatePattern(),
                 'accessory_candidate' => $this->searchRepairConfig->getAccessoryCandidatePattern(),
+                'requested_accessory_code' => $this->searchRepairConfig->getRequestedAccessoryCodePattern(),
                 'accessory_or_bundle' => $this->searchRepairConfig->getAccessoryOrBundlePattern(),
                 'model_like' => $this->searchRepairConfig->getModelLikePattern(),
                 'specificity_boost' => $this->searchRepairConfig->getSpecificityBoostPattern(),

src/Config/SearchRepairConfig.php

@@ -85,6 +85,66 @@ final class SearchRepairConfig
         return $this->minPrimaryResultsWithoutRepair;
     }
 
+    public function shouldRestrictRequestedAccessoryCodeRepair(): bool
+    {
+        return $this->bool('strict_requested_accessory_code_repair', true);
+    }
+
+    public function shouldPreferPromptAnchoredModelForRequestedAccessoryCode(): bool
+    {
+        return $this->bool('prefer_prompt_anchored_model_for_requested_accessory_code', true);
+    }
+
+    /** @return string[] */
+    public function getRequestedAccessoryCodeFallbackQueryTemplates(): array
+    {
+        return $this->stringList(
+            'requested_accessory_code_fallback_query_templates',
+            ['{term} {code}']
+        );
+    }
+
+    /** @return string[] */
+    public function getRequestedAccessoryCodeFallbackTerms(): array
+    {
+        return $this->stringList(
+            'requested_accessory_code_fallback_terms',
+            $this->getAccessoryCandidateTerms()
+        );
+    }
+
+    /** @return string[] */
+    public function getRequestedAccessoryCodeContextPrefixTerms(): array
+    {
+        return $this->stringList(
+            'requested_accessory_code_context_prefix_terms',
+            $this->getAccessoryCandidateTerms()
+        );
+    }
+
+    public function getRequestedAccessoryCodeProximityWindow(): int
+    {
+        return $this->int('requested_accessory_code_proximity_window', 1600);
+    }
+
+    /** @return string[] */
+    public function getSpecificModelCandidatePatterns(): array
+    {
+        return $this->stringList(
+            'specific_model_candidate_patterns',
+            [$this->getModelLikePattern()]
+        );
+    }
+
+    /** @return string[] */
+    public function getModelCandidateExcludeTerms(): array
+    {
+        return $this->stringList(
+            'model_candidate_exclude_terms',
+            array_merge($this->getAccessoryCandidateTerms(), ['verfuegbarkeit', 'verfügbarkeit', 'shop'])
+        );
+    }
+
     public function getTopProductLogLimit(): int
     {
         return 3;
@@ -100,6 +160,21 @@ final class SearchRepairConfig
         return '/\b((?:' . implode('|', $this->getAccessoryCandidateTerms()) . ')\s+\d{1,5}[A-Za-z0-9\-]*)\b/iu';
     }
 
+    public function getRequestedAccessoryCodePattern(): string
+    {
+        $fallbackTerms = array_map(
+            static fn(string $term): string => preg_quote($term, '/'),
+            $this->getRequestedAccessoryCodeContextPrefixTerms()
+        );
+        $fallbackTerms = array_filter($fallbackTerms, static fn(string $term): bool => $term !== '');
+
+        $fallbackPattern = $fallbackTerms === []
+            ? '/\b([A-Za-z]{0,3}\s*\d{1,5}[A-Za-z0-9\-]*)\b/iu'
+            : '/\b(?:' . implode('|', $fallbackTerms) . ')\s*([A-Za-z]{0,3}\s*\d{1,5}[A-Za-z0-9\-]*)\b/iu';
+
+        return $this->string('requested_accessory_code_pattern', $fallbackPattern);
+    }
+
     public function getAccessoryOrBundlePattern(): string
     {
         return '/\b(' . implode('|', $this->getAccessoryOrBundleTerms()) . ')\b/iu';
@@ -232,6 +307,59 @@ final class SearchRepairConfig
         return $this->vocabulary?->view($path, $fallback) ?? $fallback;
     }
 
+    private function string(string $key, string $default): string
+    {
+        $value = $this->config[$key] ?? $default;
+
+        if (!is_scalar($value)) {
+            return $default;
+        }
+
+        $value = trim((string) $value);
+
+        return $value !== '' ? $value : $default;
+    }
+
+    private function int(string $key, int $default): int
+    {
+        $value = $this->config[$key] ?? $default;
+
+        if (is_int($value)) {
+            return $value;
+        }
+
+        if (is_numeric($value)) {
+            return (int) $value;
+        }
+
+        return $default;
+    }
+
+    private function bool(string $key, bool $default): bool
+    {
+        $value = $this->config[$key] ?? $default;
+
+        if (is_bool($value)) {
+            return $value;
+        }
+
+        if (is_int($value)) {
+            return $value !== 0;
+        }
+
+        if (is_string($value)) {
+            $normalized = strtolower(trim($value));
+            if (in_array($normalized, ['1', 'true', 'yes', 'on'], true)) {
+                return true;
+            }
+            if (in_array($normalized, ['0', 'false', 'no', 'off'], true)) {
+                return false;
+            }
+        }
+
+        return $default;
+    }
+
     /** @return string[] */
     private function stringList(string $key, array $default): array
     {