patch 15

src/Config/GovernanceConfig.php

@@ -0,0 +1,216 @@
+<?php
+
+declare(strict_types=1);
+
+namespace App\Config;
+
+final class GovernanceConfig
+{
+    /**
+     * @param array<string, mixed> $config
+     */
+    public function __construct(private readonly array $config = [])
+    {
+    }
+
+    /** @return array<string, mixed> */
+    public function toArray(): array
+    {
+        return $this->config;
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedShortModelTokens(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_short_model_tokens');
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedMeasurementValues(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_measurement_values');
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedTechnicalPromptKeywords(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_technical_prompt_keywords');
+    }
+
+    /** @return string[] */
+    public function getRegressionTechnicalPriorityRequiredMarkers(): array
+    {
+        return $this->requiredStringList('regression_baseline.technical_priority_required_markers');
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedAccessoryPromptKeywords(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_accessory_prompt_keywords');
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedSearchRepairSpecificityTerms(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_search_repair_specificity_terms');
+    }
+
+    /** @return string[] */
+    public function getRegressionProtectedRetrievalReagentWords(): array
+    {
+        return $this->requiredStringList('regression_baseline.protected_retrieval_reagent_words');
+    }
+
+    /** @return array<string, string[]> */
+    public function getRegressionProtectedRetrievalDeviceWordGroups(): array
+    {
+        $value = $this->requiredValue('regression_baseline.protected_retrieval_device_word_groups');
+        if (!is_array($value)) {
+            throw $this->invalid('regression_baseline.protected_retrieval_device_word_groups', 'must be a map of string lists');
+        }
+
+        $out = [];
+        foreach ($value as $key => $item) {
+            if (is_string($key) && is_array($item)) {
+                $normalizedKey = trim($key);
+                $terms = $this->normalizeStringList($item);
+                if ($normalizedKey !== '' && $terms !== []) {
+                    $out[$normalizedKey] = $terms;
+                }
+                continue;
+            }
+
+            // Backwards-compatible reader for the temporary p15/p15b list-of-groups shape.
+            if (is_array($item)) {
+                $groupKey = isset($item['key']) && is_scalar($item['key']) ? trim((string) $item['key']) : '';
+                $terms = $this->normalizeStringList($item['terms'] ?? []);
+                if ($groupKey !== '' && $terms !== []) {
+                    $out[$groupKey] = $terms;
+                }
+            }
+        }
+
+        if ($out === []) {
+            throw $this->invalid('regression_baseline.protected_retrieval_device_word_groups', 'must contain at least one valid group');
+        }
+
+        return $out;
+    }
+
+    public function getRegressionShopPromptOriginalQuery(): string
+    {
+        return $this->requiredString('regression_baseline.shop_prompt_regression_original_query');
+    }
+
+    /** @return string[] */
+    public function getRegressionShopPromptRequiredOutputInstructionMarkers(): array
+    {
+        return $this->requiredStringList('regression_baseline.shop_prompt_required_output_instruction_markers');
+    }
+
+    /** @return string[] */
+    public function getRegressionShopQueryMetaGuardTerms(): array
+    {
+        return $this->requiredStringList('regression_baseline.shop_query_meta_guard_terms');
+    }
+
+    /** @return string[] */
+    public function getRegressionShopQueryContextFallbackFilterTerms(): array
+    {
+        return $this->requiredStringList('regression_baseline.shop_query_context_fallback_filter_terms');
+    }
+
+    /** @return string[] */
+    public function getVocabularyProtectedShortModelTokens(): array
+    {
+        return $this->requiredStringList('vocabulary.protected_short_model_tokens');
+    }
+
+    /** @return string[] */
+    public function getLanguageProtectedStopwordTerms(): array
+    {
+        return $this->requiredStringList('language.protected_stopword_terms');
+    }
+
+    private function requiredString(string $path): string
+    {
+        $value = $this->requiredValue($path);
+        if (!is_scalar($value)) {
+            throw $this->invalid($path, 'must be a scalar string');
+        }
+
+        $value = trim((string) $value);
+        if ($value === '') {
+            throw $this->invalid($path, 'must not be empty');
+        }
+
+        return $value;
+    }
+
+    /** @return string[] */
+    private function requiredStringList(string $path): array
+    {
+        return $this->nonEmptyStringList($path, $this->requiredValue($path));
+    }
+
+    /** @return string[] */
+    private function nonEmptyStringList(string $path, mixed $value): array
+    {
+        if (!is_array($value)) {
+            throw $this->invalid($path, 'must be a string list');
+        }
+
+        $out = $this->normalizeStringList($value);
+        if ($out === []) {
+            throw $this->invalid($path, 'must contain at least one value');
+        }
+
+        return $out;
+    }
+
+    /** @return string[] */
+    private function normalizeStringList(mixed $value): array
+    {
+        if (!is_array($value)) {
+            return [];
+        }
+
+        $out = [];
+        foreach ($value as $item) {
+            if (!is_scalar($item)) {
+                continue;
+            }
+
+            $item = trim((string) $item);
+            if ($item !== '' && !in_array($item, $out, true)) {
+                $out[] = $item;
+            }
+        }
+
+        return $out;
+    }
+
+    private function requiredValue(string $path): mixed
+    {
+        $value = $this->config;
+        foreach (explode('.', $path) as $segment) {
+            if (!is_array($value) || !array_key_exists($segment, $value)) {
+                throw $this->missing($path);
+            }
+
+            $value = $value[$segment];
+        }
+
+        return $value;
+    }
+
+    private function missing(string $path): \InvalidArgumentException
+    {
+        return new \InvalidArgumentException(sprintf('RetrieX governance config "%s" is missing.', $path));
+    }
+
+    private function invalid(string $path, string $reason): \InvalidArgumentException
+    {
+        return new \InvalidArgumentException(sprintf('RetrieX governance config "%s" %s.', $path, $reason));
+    }
+}