marek/MtoRagSystem
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

patch 15

Browse Source
This commit is contained in:
team 1
2026-05-01 17:40:48 +02:00
parent 17cb098235
commit ad7cac72be
19 changed files with 1084 additions and 157 deletions
Download Patch File Download Diff File Expand all files Collapse all files

209
src/Config/RetriexEffectiveConfigProvider.php
View File

@@ -26,6 +26,7 @@ final readonly class RetriexEffectiveConfigProvider
private ShopServiceConfig $shopServiceConfig,
private StopWordsConfig $stopWordsConfig,
private QueryEnricherConfig $queryEnricherConfig,
private GovernanceConfig $governanceConfig,
private CatalogIntentConfig $catalogIntentConfig,
private ContextServiceConfig $contextServiceConfig,
) {
@@ -51,6 +52,7 @@ final readonly class RetriexEffectiveConfigProvider
'search_repair' => $this->searchRepairEffectiveConfig(),
'intent' => $this->intentConfig(),
'vocabulary' => $this->domainVocabularyConfig->toArray(),
'governance' => $this->governanceConfig->toArray(),
'language' => $this->languageConfig(),
'query_enrichment' => $this->queryEnrichmentConfig(),
'catalog_intent' => $this->catalogIntentConfig(),
@@ -80,6 +82,7 @@ final readonly class RetriexEffectiveConfigProvider
$this->validateSearchRepair($config['search_repair'], $errors, $warnings);
$this->validateIntent($config['intent'], $errors, $warnings);
$this->validateVocabulary($config['vocabulary'], $errors, $warnings);
$this->validateGovernance($config['governance'], $errors, $warnings);
$this->validateLanguage($config['language'], $errors, $warnings);
$this->validateQueryEnrichment($config['query_enrichment'], $errors, $warnings);
@@ -114,8 +117,8 @@ final readonly class RetriexEffectiveConfigProvider
}
$importantShortModelTokens = $this->retrieverConfig->importantShortModelTokens();
foreach (['th', 'tc', 'tp', 'tm', 'ph', 'rx'] as $token) {
$key = 'important_short_model_token_' . $token;
foreach ($this->governanceConfig->getRegressionProtectedShortModelTokens() as $token) {
$key = 'important_short_model_token_' . $this->guardrailCheckKey($token);
$checks[$key] = in_array($token, $importantShortModelTokens, true);
if (!$checks[$key]) {
$errors[] = 'Missing protected short model token: ' . $token;
@@ -123,20 +126,23 @@ final readonly class RetriexEffectiveConfigProvider
}
$measurementPattern = $this->commerceQueryParserConfig->getMeasurementValueTokenPattern();
$checks['measurement_value_0_02_matches'] = @preg_match($measurementPattern, '0,02') === 1;
if (!$checks['measurement_value_0_02_matches']) {
$errors[] = 'Commerce query parser no longer recognizes 0,02 as a measurement value.';
}
$filterTokens = $this->commerceQueryParserConfig->getFilterSearchTokens();
$checks['measurement_value_0_02_not_filtered'] = !in_array('0,02', $filterTokens, true);
if (!$checks['measurement_value_0_02_not_filtered']) {
$errors[] = 'Commerce query parser filters the protected token 0,02.';
foreach ($this->governanceConfig->getRegressionProtectedMeasurementValues() as $measurementValue) {
$keySuffix = $this->guardrailCheckKey($measurementValue);
$checks['measurement_value_' . $keySuffix . '_matches'] = @preg_match($measurementPattern, $measurementValue) === 1;
if (!$checks['measurement_value_' . $keySuffix . '_matches']) {
$errors[] = 'Commerce query parser no longer recognizes protected measurement value: ' . $measurementValue . '.';
}
$checks['measurement_value_' . $keySuffix . '_not_filtered'] = !in_array($measurementValue, $filterTokens, true);
if (!$checks['measurement_value_' . $keySuffix . '_not_filtered']) {
$errors[] = 'Commerce query parser filters protected measurement value: ' . $measurementValue . '.';
}
}
$technicalKeywords = $this->promptConfig->getTechnicalProductKeywords();
foreach (['testomat', 'indikator', 'grenzwert', 'messbereich', 'gemessen'] as $term) {
$key = 'technical_keyword_' . $term;
foreach ($this->governanceConfig->getRegressionProtectedTechnicalPromptKeywords() as $term) {
$key = 'technical_keyword_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $technicalKeywords, true);
if (!$checks[$key]) {
$errors[] = 'Missing technical prompt keyword: ' . $term;
@@ -144,19 +150,20 @@ final readonly class RetriexEffectiveConfigProvider
}
$technicalPriorityRules = implode("\n", $this->promptConfig->getOutputPriorityTechnicalRules());
$checks['technical_priority_rules_present'] = trim($technicalPriorityRules) !== '';
$checks['technical_priority_prevents_runner_up'] = str_contains($technicalPriorityRules, 'runner-up')
|| str_contains($technicalPriorityRules, 'second-lowest')
|| str_contains($technicalPriorityRules, 'comparison');
$checks['technical_priority_required_markers_present'] = $this->containsAnyConfiguredMarker(
$technicalPriorityRules,
$this->governanceConfig->getRegressionTechnicalPriorityRequiredMarkers()
);
if (!$checks['technical_priority_rules_present']) {
$errors[] = 'Missing technical output priority rules.';
}
if (!$checks['technical_priority_prevents_runner_up']) {
$errors[] = 'Technical output priority no longer guards against runner-up/comparison expansion.';
if (!$checks['technical_priority_required_markers_present']) {
$errors[] = 'Technical output priority no longer contains a required governance marker.';
}
$accessoryKeywords = $this->promptConfig->getAccessoryRequestKeywords();
foreach (['indikator', 'reagenz'] as $term) {
$key = 'accessory_keyword_' . $term;
foreach ($this->governanceConfig->getRegressionProtectedAccessoryPromptKeywords() as $term) {
$key = 'accessory_keyword_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $accessoryKeywords, true);
if (!$checks[$key]) {
$errors[] = 'Missing accessory prompt keyword: ' . $term;
@@ -164,8 +171,8 @@ final readonly class RetriexEffectiveConfigProvider
}
$searchRepairTerms = $this->searchRepairConfig->getSpecificityBoostTerms();
foreach (['indikator', 'testomat', 'reagenz'] as $term) {
$key = 'search_repair_specificity_' . $term;
foreach ($this->governanceConfig->getRegressionProtectedSearchRepairSpecificityTerms() as $term) {
$key = 'search_repair_specificity_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $searchRepairTerms, true);
if (!$checks[$key]) {
$errors[] = 'Missing search repair specificity term: ' . $term;
@@ -173,30 +180,46 @@ final readonly class RetriexEffectiveConfigProvider
}
$reagentWords = $this->retrieverConfig->looksLikeReagentWords();
$deviceWords = $this->retrieverConfig->looksLikeDeviceWords();
$checks['retrieval_reagent_word_indikator'] = in_array('indikator', $reagentWords, true);
$checks['retrieval_device_word_geraet'] = in_array('geraet', $deviceWords, true) || in_array('gerät', $deviceWords, true);
if (!$checks['retrieval_reagent_word_indikator']) {
$errors[] = 'Missing retrieval reagent word: indikator.';
}
if (!$checks['retrieval_device_word_geraet']) {
$errors[] = 'Missing retrieval device word: geraet/geraet equivalent.';
foreach ($this->governanceConfig->getRegressionProtectedRetrievalReagentWords() as $term) {
$key = 'retrieval_reagent_word_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $reagentWords, true);
if (!$checks[$key]) {
$errors[] = 'Missing retrieval reagent word: ' . $term . '.';
}
}
$shopPrompt = $this->agentRunnerConfig->getShopPrompt('testomat 808 0,02', '');
$checks['shop_prompt_contains_output_instruction'] = str_contains($shopPrompt, 'Output only the final search query.')
|| str_contains($shopPrompt, 'Output format:');
$checks['shop_prompt_contains_original_query'] = str_contains($shopPrompt, 'testomat 808 0,02');
$deviceWords = $this->retrieverConfig->looksLikeDeviceWords();
foreach ($this->governanceConfig->getRegressionProtectedRetrievalDeviceWordGroups() as $groupKey => $terms) {
$key = 'retrieval_device_word_' . $this->guardrailCheckKey((string) $groupKey);
$checks[$key] = false;
foreach ($terms as $term) {
if (in_array($term, $deviceWords, true)) {
$checks[$key] = true;
break;
}
}
if (!$checks[$key]) {
$errors[] = 'Missing retrieval device word group: ' . (string) $groupKey . '.';
}
}
$shopPromptOriginalQuery = $this->governanceConfig->getRegressionShopPromptOriginalQuery();
$shopPrompt = $this->agentRunnerConfig->getShopPrompt($shopPromptOriginalQuery, '');
$checks['shop_prompt_contains_output_instruction'] = $this->containsAnyConfiguredMarker(
$shopPrompt,
$this->governanceConfig->getRegressionShopPromptRequiredOutputInstructionMarkers()
);
$checks['shop_prompt_contains_original_query'] = str_contains($shopPrompt, $shopPromptOriginalQuery);
if (!$checks['shop_prompt_contains_output_instruction']) {
$errors[] = 'Shop query optimizer prompt no longer contains the expected output instruction.';
$errors[] = 'Shop query optimizer prompt no longer contains a required output instruction marker.';
}
if (!$checks['shop_prompt_contains_original_query']) {
$errors[] = 'Shop query optimizer prompt no longer contains the original query.';
$errors[] = 'Shop query optimizer prompt no longer contains the configured original query.';
}
$metaOnlyTerms = $this->agentRunnerConfig->getShopQueryMetaOnlyTerms();
foreach (['shop', 'suche'] as $term) {
$key = 'shop_query_meta_guard_term_' . $term;
foreach ($this->governanceConfig->getRegressionShopQueryMetaGuardTerms() as $term) {
$key = 'shop_query_meta_guard_term_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $metaOnlyTerms, true);
if (!$checks[$key]) {
$errors[] = 'Missing shop query meta guard term: ' . $term;
@@ -208,8 +231,8 @@ final readonly class RetriexEffectiveConfigProvider
}
$contextFallbackFilterTerms = $this->agentRunnerConfig->getShopQueryContextFallbackFilterTerms();
foreach (['welchem', 'kann', 'messen'] as $term) {
$key = 'shop_query_context_fallback_filter_' . $term;
foreach ($this->governanceConfig->getRegressionShopQueryContextFallbackFilterTerms() as $term) {
$key = 'shop_query_context_fallback_filter_' . $this->guardrailCheckKey($term);
$checks[$key] = in_array($term, $contextFallbackFilterTerms, true);
if (!$checks[$key]) {
$errors[] = 'Missing shop query context fallback filter term: ' . $term;
@@ -244,7 +267,26 @@ final readonly class RetriexEffectiveConfigProvider
'warnings' => $warnings,
];
}
/** @param string[] $markers */
private function containsAnyConfiguredMarker(string $haystack, array $markers): bool
{
foreach ($markers as $marker) {
if ($marker !== '' && str_contains($haystack, $marker)) {
return true;
}
}
return false;
}
private function guardrailCheckKey(string $term): string
{
$key = mb_strtolower($term, 'UTF-8');
$key = preg_replace('/[^\p{L}\p{N}]+/u', '_', $key) ?? $key;
$key = trim($key, '_');
return $key !== '' ? $key : 'value';
}
/** @return array<string, mixed> */
private function runtimeConfig(): array
{
@@ -740,6 +782,37 @@ final readonly class RetriexEffectiveConfigProvider
];
}
/**
* @param array<string, mixed> $governance
* @param list<string> $errors
* @param list<string> $warnings
*/
private function validateGovernance(array $governance, array &$errors, array &$warnings): void
{
if ($governance === []) {
$errors[] = 'governance config must not be empty.';
return;
}
try {
$this->governanceConfig->getRegressionProtectedShortModelTokens();
$this->governanceConfig->getRegressionProtectedMeasurementValues();
$this->governanceConfig->getRegressionProtectedTechnicalPromptKeywords();
$this->governanceConfig->getRegressionTechnicalPriorityRequiredMarkers();
$this->governanceConfig->getRegressionProtectedAccessoryPromptKeywords();
$this->governanceConfig->getRegressionProtectedSearchRepairSpecificityTerms();
$this->governanceConfig->getRegressionProtectedRetrievalReagentWords();
$this->governanceConfig->getRegressionProtectedRetrievalDeviceWordGroups();
$this->governanceConfig->getRegressionShopPromptOriginalQuery();
$this->governanceConfig->getRegressionShopPromptRequiredOutputInstructionMarkers();
$this->governanceConfig->getRegressionShopQueryMetaGuardTerms();
$this->governanceConfig->getRegressionShopQueryContextFallbackFilterTerms();
$this->governanceConfig->getVocabularyProtectedShortModelTokens();
$this->governanceConfig->getLanguageProtectedStopwordTerms();
} catch (\InvalidArgumentException $e) {
$errors[] = $e->getMessage();
}
}
/**
* @param array<string, mixed> $runtime
* @param list<string> $errors
@@ -847,6 +920,11 @@ final readonly class RetriexEffectiveConfigProvider
$inventory = $retrieval['inventory_parameter'] ?? [];
if (is_array($inventory)) {
foreach ($inventory as $key => $value) {
$key = (string) $key;
if (!$this->shouldCompareRetrievalInventoryKey($key, $retrieval)) {
continue;
}
if (array_key_exists($key, $retrieval) && $retrieval[$key] != $value) {
$warnings[] = 'retrieval.inventory.' . $key . ' differs from active retriever config.';
}
@@ -854,6 +932,41 @@ final readonly class RetriexEffectiveConfigProvider
}
}
/**
* Retrieval vocabulary lists can be resolved from dedicated vocabulary views.
* The backwards-compatible inventory parameter may still contain raw legacy
* list values for those keys, so comparing it against the active retriever
* facade would produce false-positive validation warnings.
*
* @param array<string, mixed> $retrieval
*/
private function shouldCompareRetrievalInventoryKey(string $key, array $retrieval): bool
{
if (in_array($key, $this->retrievalVocabularyBackedInventoryKeys(), true)) {
return false;
}
$vocabulary = $retrieval['vocabulary'] ?? [];
return !is_array($vocabulary) || !array_key_exists($key, $vocabulary);
}
/** @return string[] */
private function retrievalVocabularyBackedInventoryKeys(): array
{
return [
'generic_product_tokens',
'important_short_model_tokens',
'family_descriptor_tokens',
'looks_like_reagent_tokens',
'looks_like_safety_docs',
'looks_like_reagent_words',
'looks_like_document_words',
'looks_like_safety_words',
'looks_like_device_words',
];
}
/**
* @param array<string, mixed> $prompt
* @param list<string> $errors
@@ -964,13 +1077,15 @@ final readonly class RetriexEffectiveConfigProvider
}
$measurementPattern = $patterns['measurement_value_token'] ?? null;
if (is_string($measurementPattern) && @preg_match($measurementPattern, '0,02') !== 1) {
$errors[] = 'commerce_query.patterns.measurement_value_token must match 0,02.';
}
$filterTokens = $commerceQuery['filter_search_tokens'] ?? [];
if (is_array($filterTokens) && in_array('0,02', $filterTokens, true)) {
$errors[] = 'commerce_query.filter_search_tokens must not remove protected decimal token 0,02.';
foreach ($this->governanceConfig->getRegressionProtectedMeasurementValues() as $measurementValue) {
if (is_string($measurementPattern) && @preg_match($measurementPattern, $measurementValue) !== 1) {
$errors[] = 'commerce_query.patterns.measurement_value_token must match protected measurement value: ' . $measurementValue . '.';
}
if (is_array($filterTokens) && in_array($measurementValue, $filterTokens, true)) {
$errors[] = 'commerce_query.filter_search_tokens must not remove protected measurement value: ' . $measurementValue . '.';
}
}
}
@@ -1033,7 +1148,7 @@ final readonly class RetriexEffectiveConfigProvider
if (is_array($retrievalViews)) {
$shortModel = $retrievalViews['important_short_model_tokens']['add'] ?? [];
if (is_array($shortModel)) {
foreach (['th', 'tc', 'tp', 'tm', 'ph', 'rx'] as $token) {
foreach ($this->governanceConfig->getVocabularyProtectedShortModelTokens() as $token) {
if (!in_array($token, $shortModel, true)) {
$warnings[] = 'vocabulary.views.retrieval.important_short_model_tokens should contain protected token ' . $token . '.';
}
@@ -1051,7 +1166,7 @@ final readonly class RetriexEffectiveConfigProvider
{
$this->validateStringListMap($language, 'language', $errors, $warnings);
$stopwords = is_array($language['stopwords'] ?? null) ? $language['stopwords'] : [];
foreach (['nicht', 'kein', 'welche', 'testomat', 'indikator', '0,02'] as $protected) {
foreach ($this->governanceConfig->getLanguageProtectedStopwordTerms() as $protected) {
if (in_array($protected, $stopwords, true)) {
$errors[] = 'language.stopwords must not contain protected term: ' . $protected . '.';
}