third step

RETRIEX_INTENT_LIGHT_SALES_YAML_ONLY_PATCH_README.md

@@ -0,0 +1,91 @@
+# RetrieX Patch 3: IntentLight + SalesIntent YAML-only
+
+This patch continues the incremental YAML-source-of-truth migration.
+
+## Scope
+
+Only these intent areas are changed:
+
+- `IntentLightConfig`
+- `SalesIntentConfig`
+- direct usages of their former PHP constants
+- the effective-config dump for these values
+- `config/retriex/intent.yaml`
+
+No retrieval, prompt, shop, commerce-parser, SSE, or answer-generation logic is changed.
+
+## What changed
+
+### IntentLightConfig
+
+Removed PHP defaults:
+
+- `LIST_THRESHOLD`
+- `QUANTITY_WORDS`
+- `STRONG_PATTERNS`
+
+Added required YAML-backed accessors:
+
+- `getListThreshold()`
+- `getQuantityWords()`
+- `getStrongPatterns()`
+
+The previous values now live in:
+
+```yaml
+retriex.intent.light.config:
+  list_threshold: 4
+  quantity_words: [...]
+  strong_patterns: [...]
+```
+
+### SalesIntentConfig
+
+Removed PHP defaults:
+
+- `DOMINANCE_DELTA`
+- `MIN_SCORE_THRESHOLD`
+- `SALES_SIGNALS`
+- `COMPARISON_SIGNALS`
+- `OBJECTION_SIGNALS`
+- `IMPLEMENTATION_SIGNALS`
+- `ROI_SIGNALS`
+
+Added required YAML-backed accessors:
+
+- `getDominanceDelta()`
+- `getMinScoreThreshold()`
+- `getSalesSignals()`
+- `getComparisonSignals()`
+- `getObjectionSignals()`
+- `getImplementationSignals()`
+- `getRoiSignals()`
+
+The previous values now live in:
+
+```yaml
+retriex.intent.sales.config:
+  dominance_delta: 2
+  min_score_threshold: 3
+  sales_signals: [...]
+  comparison_signals: [...]
+  objection_signals: [...]
+  implementation_signals: [...]
+  roi_signals: [...]
+```
+
+## Validation performed
+
+Static validation in the patch workspace:
+
+```bash
+php -l src/Config/IntentLightConfig.php
+php -l src/Config/SalesIntentConfig.php
+php -l src/Intent/IntentLite.php
+php -l src/Intent/SalesIntentLite.php
+php -l src/Config/RetriexEffectiveConfigProvider.php
+```
+
+YAML was parsed successfully with the new keys.
+
+The full Symfony regression commands were not executed in the extracted ZIP workspace because `vendor/` is not part of the uploaded archive.

config/retriex/intent.yaml

@@ -1,5 +1,6 @@
 # Intent vocabulary and pattern configuration.
-# Lists mirror the previous PHP defaults exactly; PHP defaults remain as fallback.
+# Lists and thresholds mirror the previous PHP defaults exactly.
+# Migrated config areas are YAML-only; remaining areas are migrated incrementally.
 parameters:
   retriex.intent.commerce.config:
     strong_signals:
@@ -141,6 +142,7 @@ parameters:
     max_allowed_score: 1.0
 
   retriex.intent.light.config:
+    list_threshold: 4
     quantity_words:
       - alle
       - sämtliche
@@ -175,6 +177,8 @@ parameters:
       - '/\btop\s*\d+\b/u'
 
   retriex.intent.sales.config:
+    dominance_delta: 2
+    min_score_threshold: 3
     sales_signals:
       - preis
       - preise

src/Config/IntentLightConfig.php

@@ -4,71 +4,72 @@ declare(strict_types=1);
 
 namespace App\Config;
 
-class IntentLightConfig
+/**
+ * YAML-backed deterministic list-intent configuration.
+ *
+ * This class intentionally has no PHP fallback values. Missing or invalid
+ * configuration must be fixed in config/retriex/intent.yaml.
+ */
+final class IntentLightConfig
 {
-    public const LIST_THRESHOLD = 4;
-
-    private const QUANTITY_WORDS = [
-        'alle',
-        'sämtliche',
-        'saemtliche',
-        'mehrere',
-        'verschiedene',
-        'einige',
-        'viele',
-        'optionen',
-        'möglichkeiten',
-        'moeglichkeiten',
-        'varianten',
-        'arten',
-        'modelle',
-        'funktionen',
-        'punkte',
-        'schritte',
-        'kategorien',
-        'übersicht',
-        'uebersicht',
-    ];
-
-    private const STRONG_PATTERNS = [
-        '/\bliste(n)?\b/u',
-        '/\bauflisten\b/u',
-        '/\baufz(a|ä)hl(en)?\b/u',
-        '/\bnenn(e)?\b/u',
-        '/\bzeig(e)?\b/u',
-        '/\bwelche\s+sind\b/u',
-        '/\bwelche\s+gibt\s+es\b/u',
-        '/\bwas\s+sind\b/u',
-        '/\bwie\s+viele\b/u',
-        '/\branking\b/u',
-        '/\btop\s*\d+\b/u',
-    ];
-
     /**
      * @param array<string, mixed> $config
      */
-    public function __construct(private readonly array $config = [])
+    public function __construct(private readonly array $config)
     {
     }
 
+    public function getListThreshold(): int
+    {
+        return $this->requiredPositiveInt('list_threshold');
+    }
+
     /** @return string[] */
     public function getQuantityWords(): array
     {
-        return $this->stringList('quantity_words', self::QUANTITY_WORDS);
+        return $this->requiredStringList('quantity_words');
     }
 
     /** @return string[] */
     public function getStrongPatterns(): array
     {
-        return $this->stringList('strong_patterns', self::STRONG_PATTERNS);
+        return $this->requiredStringList('strong_patterns');
+    }
+
+    private function requiredPositiveInt(string $key): int
+    {
+        if (!array_key_exists($key, $this->config)) {
+            throw new \InvalidArgumentException(sprintf('Missing required RetrieX light intent config key "%s".', $key));
+        }
+
+        $value = $this->config[$key];
+
+        if (is_int($value)) {
+            $intValue = $value;
+        } elseif (is_string($value) && preg_match('/^-?\d+$/', trim($value)) === 1) {
+            $intValue = (int) trim($value);
+        } else {
+            throw new \InvalidArgumentException(sprintf('RetrieX light intent config key "%s" must be an integer.', $key));
+        }
+
+        if ($intValue <= 0) {
+            throw new \InvalidArgumentException(sprintf('RetrieX light intent config key "%s" must be greater than 0.', $key));
+        }
+
+        return $intValue;
     }
 
     /** @return string[] */
-    private function stringList(string $key, array $default): array
+    private function requiredStringList(string $key): array
     {
-        $value = $this->config[$key] ?? $default;
+        if (!array_key_exists($key, $this->config)) {
+            throw new \InvalidArgumentException(sprintf('Missing required RetrieX light intent config key "%s".', $key));
+        }
+
+        $value = $this->config[$key];
+
         if (!is_array($value)) {
-            return $default;
+            throw new \InvalidArgumentException(sprintf('RetrieX light intent config key "%s" must be a list.', $key));
         }
 
         $out = [];
@@ -78,13 +79,19 @@ class IntentLightConfig
             }
 
             $item = trim((string) $item);
-            if ($item === '' || in_array($item, $out, true)) {
+            if ($item === '') {
                 continue;
             }
 
+            if (!in_array($item, $out, true)) {
                 $out[] = $item;
             }
+        }
 
-        return $out !== [] ? $out : $default;
+        if ($out === []) {
+            throw new \InvalidArgumentException(sprintf('RetrieX light intent config key "%s" must not be empty.', $key));
+        }
+
+        return $out;
     }
 }

src/Config/RetriexEffectiveConfigProvider.php

@@ -658,13 +658,13 @@ final readonly class RetriexEffectiveConfigProvider
                 ],
             ],
             'light' => [
-                'list_threshold' => IntentLightConfig::LIST_THRESHOLD,
+                'list_threshold' => $this->intentLightConfig->getListThreshold(),
                 'quantity_words' => $this->intentLightConfig->getQuantityWords(),
                 'strong_patterns' => $this->intentLightConfig->getStrongPatterns(),
             ],
             'sales' => [
-                'dominance_delta' => SalesIntentConfig::DOMINANCE_DELTA,
+                'dominance_delta' => $this->salesIntentConfig->getDominanceDelta(),
-                'min_score_threshold' => SalesIntentConfig::MIN_SCORE_THRESHOLD,
+                'min_score_threshold' => $this->salesIntentConfig->getMinScoreThreshold(),
                 'sales_signals' => $this->salesIntentConfig->getSalesSignals(),
                 'comparison_signals' => $this->salesIntentConfig->getComparisonSignals(),
                 'objection_signals' => $this->salesIntentConfig->getObjectionSignals(),

src/Config/SalesIntentConfig.php

@@ -4,123 +4,95 @@ declare(strict_types=1);
 
 namespace App\Config;
 
-class SalesIntentConfig
+/**
+ * YAML-backed deterministic sales-intent configuration.
+ *
+ * This class intentionally has no PHP fallback values. Missing or invalid
+ * configuration must be fixed in config/retriex/intent.yaml.
+ */
+final class SalesIntentConfig
 {
-    // Minimum gap between Top 1 and Top 2 so that an intent is truly dominant.
-    public const DOMINANCE_DELTA = 2;
-
-    // Minimum score required for any non-discovery intent to be accepted.
-    public const MIN_SCORE_THRESHOLD = 3;
-
-    private const SALES_SIGNALS = [
-        'preis',
-        'preise',
-        'kosten',
-        'lizenz',
-        'lizenzmodell',
-        'tarif',
-        'tarife',
-        'gebuehr',
-        'gebühr',
-        'monatlich',
-        'jaehrlich',
-        'jährlich',
-        'abo',
-        'subscription',
-    ];
-
-    private const COMPARISON_SIGNALS = [
-        '/\bvergleich(en)?\b/u',
-        '/\bvs\b/u',
-        '/\bgegenueber\b/u',
-        '/\balternative(n)?\b/u',
-        '/\bunterschied(e)?\b/u',
-        '/\bbesser\b/u',
-    ];
-
-    private const OBJECTION_SIGNALS = [
-        'problem',
-        'risiko',
-        'nachteil',
-        'datenschutz',
-        'dsgvo',
-        'sicherheit',
-        'compliance',
-        'kritik',
-        'zweifel',
-        'unsicher',
-    ];
-
-    private const IMPLEMENTATION_SIGNALS = [
-        'implementierung',
-        'implementieren',
-        'integration',
-        'integrieren',
-        'einführung',
-        'einfuehrung',
-        'aufwand',
-        'setup',
-        'rollout',
-        'migration',
-        'installation',
-        'api',
-        'schnittstelle',
-    ];
-
-    private const ROI_SIGNALS = [
-        'roi',
-        'rentabilitaet',
-        'rentabilität',
-        'business case',
-        'einsparung',
-        'kosten senken',
-        'umsatz steigern',
-        'effizienz steigern',
-    ];
-
     /**
      * @param array<string, mixed> $config
      */
-    public function __construct(private readonly array $config = [])
+    public function __construct(private readonly array $config)
     {
     }
 
+    public function getDominanceDelta(): int
+    {
+        return $this->requiredNonNegativeInt('dominance_delta');
+    }
+
+    public function getMinScoreThreshold(): int
+    {
+        return $this->requiredNonNegativeInt('min_score_threshold');
+    }
+
     /** @return string[] */
     public function getSalesSignals(): array
     {
-        return $this->stringList('sales_signals', self::SALES_SIGNALS);
+        return $this->requiredStringList('sales_signals');
     }
 
     /** @return string[] */
     public function getComparisonSignals(): array
     {
-        return $this->stringList('comparison_signals', self::COMPARISON_SIGNALS);
+        return $this->requiredStringList('comparison_signals');
     }
 
     /** @return string[] */
     public function getObjectionSignals(): array
     {
-        return $this->stringList('objection_signals', self::OBJECTION_SIGNALS);
+        return $this->requiredStringList('objection_signals');
     }
 
     /** @return string[] */
     public function getImplementationSignals(): array
     {
-        return $this->stringList('implementation_signals', self::IMPLEMENTATION_SIGNALS);
+        return $this->requiredStringList('implementation_signals');
     }
 
     /** @return string[] */
     public function getRoiSignals(): array
     {
-        return $this->stringList('roi_signals', self::ROI_SIGNALS);
+        return $this->requiredStringList('roi_signals');
+    }
+
+    private function requiredNonNegativeInt(string $key): int
+    {
+        if (!array_key_exists($key, $this->config)) {
+            throw new \InvalidArgumentException(sprintf('Missing required RetrieX sales intent config key "%s".', $key));
+        }
+
+        $value = $this->config[$key];
+
+        if (is_int($value)) {
+            $intValue = $value;
+        } elseif (is_string($value) && preg_match('/^-?\d+$/', trim($value)) === 1) {
+            $intValue = (int) trim($value);
+        } else {
+            throw new \InvalidArgumentException(sprintf('RetrieX sales intent config key "%s" must be an integer.', $key));
+        }
+
+        if ($intValue < 0) {
+            throw new \InvalidArgumentException(sprintf('RetrieX sales intent config key "%s" must be greater than or equal to 0.', $key));
+        }
+
+        return $intValue;
     }
 
     /** @return string[] */
-    private function stringList(string $key, array $default): array
+    private function requiredStringList(string $key): array
     {
-        $value = $this->config[$key] ?? $default;
+        if (!array_key_exists($key, $this->config)) {
+            throw new \InvalidArgumentException(sprintf('Missing required RetrieX sales intent config key "%s".', $key));
+        }
+
+        $value = $this->config[$key];
+
         if (!is_array($value)) {
-            return $default;
+            throw new \InvalidArgumentException(sprintf('RetrieX sales intent config key "%s" must be a list.', $key));
         }
 
         $out = [];
@@ -130,13 +102,19 @@ class SalesIntentConfig
             }
 
             $item = trim((string) $item);
-            if ($item === '' || in_array($item, $out, true)) {
+            if ($item === '') {
                 continue;
             }
 
+            if (!in_array($item, $out, true)) {
                 $out[] = $item;
             }
+        }
 
-        return $out !== [] ? $out : $default;
+        if ($out === []) {
+            throw new \InvalidArgumentException(sprintf('RetrieX sales intent config key "%s" must not be empty.', $key));
+        }
+
+        return $out;
     }
 }

src/Intent/IntentLite.php

@@ -78,7 +78,7 @@ final readonly class IntentLite
         // --------------------------------------------------------
         // Entscheidung
         // --------------------------------------------------------
-        $isList = $score >= IntentLightConfig::LIST_THRESHOLD;
+        $isList = $score >= $this->config->getListThreshold();
 
         return [
             'is_list' => $isList,

src/Intent/SalesIntentLite.php

@@ -98,7 +98,7 @@ final class SalesIntentLite
         $secondScore = $values[1] ?? 0;
 
         // Kein relevanter Score → Discovery
-        if ($topScore < SalesIntentConfig::MIN_SCORE_THRESHOLD) {
+        if ($topScore < $this->config->getMinScoreThreshold()) {
             return [
                 'intent' => self::DISCOVERY,
                 'score' => 0,
@@ -106,7 +106,7 @@ final class SalesIntentLite
         }
 
         // Keine klare Dominanz → Discovery
-        if (($topScore - $secondScore) < SalesIntentConfig::DOMINANCE_DELTA) {
+        if (($topScore - $secondScore) < $this->config->getDominanceDelta()) {
             return [
                 'intent' => self::DISCOVERY,
                 'score' => $topScore,