fix p57

RETRIEX_PATCH_57_SINGLE_GENRE_SOURCE_AUDIT_README.md

@@ -0,0 +1,64 @@
+# RetrieX Patch p57 - Single-Genre Source Audit / Legacy Cleanup Guard
+
+## Ziel
+
+Dieser Patch ist der naechste kleine Schritt nach p56. Er loescht noch keine Legacy-YAML-Werte, sondern haertet die zentrale Single-Genre-Pflegeflaeche fuer den spaeteren Cleanup.
+
+Es bleibt strikt bei: eine Installation = ein Genre. Es gibt keine Multi-Genre-Umschaltung, keinen Tenant-Kontext und keinen Request-/Host-Resolver.
+
+## Warum dieser Schritt
+
+Nach p55/p56 sind viele fachliche Werte bevorzugt in `config/retriex/genre.yaml` gepflegt, waehrend die alten Pfade als Fallback bestehen bleiben. Damit diese Uebergangsphase kontrollierbar bleibt, muessen die in `genre.configuration_values.*.source_paths` dokumentierten Legacy-/Effective-Pfade selbst validierbar und auditierbar sein.
+
+p57 macht diese Source-Path-Metadaten maschinenlesbar und sichtbar.
+
+## Was geaendert wurde
+
+- `GenreConfig` erhaelt `getConfigurationValueSourcePaths()`.
+- `RetriexEffectiveConfigProvider` validiert nun auch die `source_paths` unter `genre.configuration_values` gegen bekannte effektive bzw. Legacy-Config-Pfade.
+- `ConfigSourceAuditProvider` sammelt die Single-Genre-Source-Path-Metadaten fuer `mto:agent:config:audit-source --json`.
+- `ConfigSourceAuditCommand --details` zeigt zusaetzlich eine Tabelle der Single-Genre-Source-Pfade.
+
+## Nicht geaendert
+
+- Keine Fachlogik-Aenderung.
+- Keine neuen fachlichen Listen.
+- Keine neuen Defaults.
+- Keine Entfernung von Legacy-Fallback-Werten.
+- Keine Shopware-Kriterien-, Ranking-, Retrieval- oder LLM-Verhaltensaenderung.
+- Keine Multi-Genre-/Tenant-Loesung.
+
+## Erwartetes Verhalten
+
+Das Antwortverhalten bleibt unveraendert. Der Unterschied ist nur, dass die zentrale Genre-Konfiguration besser validiert und auditierbar ist.
+
+Wenn spaeter ein falscher oder veralteter `source_paths`-Eintrag in `genre.yaml` entsteht, meldet `mto:agent:config:validate` eine Warnung statt den Fehler unbemerkt zu lassen.
+
+## Geaenderte Dateien
+
+- `src/Config/GenreConfig.php`
+- `src/Config/RetriexEffectiveConfigProvider.php`
+- `src/Config/ConfigSourceAuditProvider.php`
+- `src/Command/ConfigSourceAuditCommand.php`
+- `RETRIEX_PATCH_57_SINGLE_GENRE_SOURCE_AUDIT_README.md`
+
+## Lokale Checks
+
+```bash
+php -l src/Config/GenreConfig.php
+php -l src/Config/RetriexEffectiveConfigProvider.php
+php -l src/Config/ConfigSourceAuditProvider.php
+php -l src/Command/ConfigSourceAuditCommand.php
+```
+
+YAML-Parsing fuer alle Dateien unter `config/retriex/*.yaml`.
+
+Projektchecks nach dem Einspielen:
+
+```bash
+bin/console cache:clear
+bin/console mto:agent:config:validate
+bin/console mto:agent:regression:test
+bin/console mto:agent:config:audit-source --details
+bin/console mto:agent:config:audit-patterns --details
+```

src/Command/ConfigSourceAuditCommand.php

@@ -63,7 +63,9 @@ final class ConfigSourceAuditCommand extends Command
             ['fallback_accessors_with_yaml' => (string) ($summary['fallback_accessors_with_yaml'] ?? 0)],
             ['fallback_accessors_missing_yaml' => (string) ($summary['fallback_accessors_missing_yaml'] ?? 0)],
             ['constructor_defaults' => (string) ($summary['constructor_defaults'] ?? 0)],
-            ['constructor_defaults_without_yaml_mapping' => (string) ($summary['constructor_defaults_without_yaml_mapping'] ?? 0)]
+            ['constructor_defaults_without_yaml_mapping' => (string) ($summary['constructor_defaults_without_yaml_mapping'] ?? 0)],
+            ['genre_value_paths_with_source_paths' => (string) ($summary['genre_value_paths_with_source_paths'] ?? 0)],
+            ['genre_declared_source_paths' => (string) ($summary['genre_declared_source_paths'] ?? 0)]
         );
 
         $warnings = is_array($result['warnings'] ?? null) ? $result['warnings'] : [];
@@ -98,5 +100,25 @@ final class ConfigSourceAuditCommand extends Command
             $io->section('Fallback accessors');
             $io->table(['Class', 'Line', 'Key', 'YAML', 'Source'], $fallbackRows);
         }
+
+        $genreSourceRows = [];
+        foreach (($result['genre_configuration_source_paths'] ?? []) as $valuePath => $sourcePaths) {
+            if (!is_string($valuePath) || !is_array($sourcePaths)) {
+                continue;
+            }
+
+            foreach ($sourcePaths as $sourcePath) {
+                if (!is_string($sourcePath)) {
+                    continue;
+                }
+
+                $genreSourceRows[] = [$valuePath, $sourcePath];
+            }
+        }
+
+        if ($genreSourceRows !== []) {
+            $io->section('Single-genre configuration source paths');
+            $io->table(['Genre value path', 'Legacy/effective source path'], $genreSourceRows);
+        }
     }
 }

src/Config/ConfigSourceAuditProvider.php

@@ -57,6 +57,7 @@ final readonly class ConfigSourceAuditProvider
     public function audit(): array
     {
         $yamlPaths = $this->collectYamlParameterPaths();
+        $genreSourcePaths = $this->collectGenreConfigurationSourcePaths();
         $fallbackAccessors = [];
         $constructorDefaults = [];
         $phpConstants = [];
@@ -135,14 +136,30 @@ final readonly class ConfigSourceAuditProvider
                 'fallback_accessors_missing_yaml' => count($missingYamlFallbacks),
                 'constructor_defaults' => count($constructorDefaults),
                 'constructor_defaults_without_yaml_mapping' => count($constructorPhpDefaults),
+                'genre_value_paths_with_source_paths' => count($genreSourcePaths),
+                'genre_declared_source_paths' => $this->countGenreDeclaredSourcePaths($genreSourcePaths),
             ],
             'warnings' => $this->buildWarnings($missingYamlFallbacks, $phpOnlyConstants, $constructorPhpDefaults),
             'fallback_accessors' => $fallbackAccessors,
             'constructor_defaults' => $constructorDefaults,
             'php_constants' => $phpConstants,
+            'genre_configuration_source_paths' => $genreSourcePaths,
         ];
     }
 
+    /**
+     * @param array<string, string[]> $sourcePaths
+     */
+    private function countGenreDeclaredSourcePaths(array $sourcePaths): int
+    {
+        $count = 0;
+        foreach ($sourcePaths as $paths) {
+            $count += count($paths);
+        }
+
+        return $count;
+    }
+
     /**
      * @return list<array<string, mixed>>
      */
@@ -158,6 +175,78 @@ final readonly class ConfigSourceAuditProvider
         return $files;
     }
 
+
+    /**
+     * @return array<string, string[]>
+     */
+    private function collectGenreConfigurationSourcePaths(): array
+    {
+        $file = $this->projectDir . '/config/retriex/genre.yaml';
+        if (!is_file($file)) {
+            return [];
+        }
+
+        $parsed = Yaml::parseFile($file);
+        if (!is_array($parsed)) {
+            return [];
+        }
+
+        $parameters = $parsed['parameters'] ?? [];
+        if (!is_array($parameters)) {
+            return [];
+        }
+
+        $genreConfig = $parameters['retriex.genre.config'] ?? [];
+        if (!is_array($genreConfig)) {
+            return [];
+        }
+
+        $configurationValues = $genreConfig['configuration_values'] ?? [];
+        if (!is_array($configurationValues)) {
+            return [];
+        }
+
+        $out = [];
+        $this->collectGenreSourcePathsRecursive($configurationValues, '', $out);
+
+        return $out;
+    }
+
+    /**
+     * @param array<int|string, mixed> $value
+     * @param array<string, string[]> $out
+     */
+    private function collectGenreSourcePathsRecursive(array $value, string $path, array &$out): void
+    {
+        $sourcePaths = $value['source_paths'] ?? null;
+        if (is_array($sourcePaths)) {
+            $clean = [];
+            foreach ($sourcePaths as $sourcePath) {
+                if (!is_string($sourcePath) || trim($sourcePath) === '') {
+                    continue;
+                }
+
+                $sourcePath = trim($sourcePath);
+                if (!in_array($sourcePath, $clean, true)) {
+                    $clean[] = $sourcePath;
+                }
+            }
+
+            if ($clean !== [] && $path !== '') {
+                $out[$path] = $clean;
+            }
+        }
+
+        foreach ($value as $key => $child) {
+            if ($key === 'source_paths' || !is_string($key) || !is_array($child)) {
+                continue;
+            }
+
+            $childPath = $path === '' ? $key : $path . '.' . $key;
+            $this->collectGenreSourcePathsRecursive($child, $childPath, $out);
+        }
+    }
+
     /**
      * @return array<string, true>
      */

src/Config/GenreConfig.php

@@ -64,6 +64,25 @@ final class GenreConfig
         return is_array($groupValues) ? $groupValues : [];
     }
 
+
+    /**
+     * Returns all declared legacy/effective source paths from the single-genre value surface.
+     *
+     * The returned map uses the configuration_values-relative value path as key and the
+     * declared source paths as value. This is metadata only; runtime value lookup still
+     * happens through the typed getValue* accessors.
+     *
+     * @return array<string, string[]>
+     */
+    public function getConfigurationValueSourcePaths(): array
+    {
+        $values = $this->getConfigurationValues();
+        $out = [];
+        $this->collectSourcePaths($values, '', $out);
+
+        return $out;
+    }
+
     /**
      * Returns a non-empty string list from the central single-genre value surface.
      *
@@ -153,6 +172,31 @@ final class GenreConfig
         return $this->config;
     }
 
+
+    /**
+     * @param array<int|string, mixed> $value
+     * @param array<string, string[]> $out
+     */
+    private function collectSourcePaths(array $value, string $path, array &$out): void
+    {
+        $sourcePaths = $value['source_paths'] ?? null;
+        if (is_array($sourcePaths)) {
+            $clean = $this->uniqueStringList($sourcePaths);
+            if ($clean !== [] && $path !== '') {
+                $out[$path] = $clean;
+            }
+        }
+
+        foreach ($value as $key => $child) {
+            if ($key === 'source_paths' || !is_string($key) || !is_array($child)) {
+                continue;
+            }
+
+            $childPath = $path === '' ? $key : $path . '.' . $key;
+            $this->collectSourcePaths($child, $childPath, $out);
+        }
+    }
+
     private function string(string $path, string $fallback): string
     {
         $value = $this->value($path, $fallback);

src/Config/RetriexEffectiveConfigProvider.php

@@ -1179,6 +1179,18 @@ final readonly class RetriexEffectiveConfigProvider
             }
         }
 
+        foreach ($this->collectGenreConfigurationValueSourcePaths($configurationValues) as $valuePath => $sourcePaths) {
+            foreach ($sourcePaths as $sourcePath) {
+                if (!isset($flattened[$sourcePath])) {
+                    $warnings[] = sprintf(
+                        'genre.configuration_values.%s references unknown source path: %s.',
+                        $valuePath,
+                        $sourcePath
+                    );
+                }
+            }
+        }
+
         foreach (array_keys($surface) as $group) {
             if (!is_string($group) || $group === '') {
                 continue;
@@ -1190,6 +1202,54 @@ final readonly class RetriexEffectiveConfigProvider
         }
     }
 
+
+    /**
+     * @param array<string, mixed> $configurationValues
+     * @return array<string, string[]>
+     */
+    private function collectGenreConfigurationValueSourcePaths(array $configurationValues): array
+    {
+        $out = [];
+        $this->collectGenreSourcePathsRecursive($configurationValues, '', $out);
+
+        return $out;
+    }
+
+    /**
+     * @param array<int|string, mixed> $value
+     * @param array<string, string[]> $out
+     */
+    private function collectGenreSourcePathsRecursive(array $value, string $path, array &$out): void
+    {
+        $sourcePaths = $value['source_paths'] ?? null;
+        if (is_array($sourcePaths)) {
+            $clean = [];
+            foreach ($sourcePaths as $sourcePath) {
+                if (!is_string($sourcePath) || trim($sourcePath) === '') {
+                    continue;
+                }
+
+                $sourcePath = trim($sourcePath);
+                if (!in_array($sourcePath, $clean, true)) {
+                    $clean[] = $sourcePath;
+                }
+            }
+
+            if ($clean !== [] && $path !== '') {
+                $out[$path] = $clean;
+            }
+        }
+
+        foreach ($value as $key => $child) {
+            if ($key === 'source_paths' || !is_string($key) || !is_array($child)) {
+                continue;
+            }
+
+            $childPath = $path === '' ? $key : $path . '.' . $key;
+            $this->collectGenreSourcePathsRecursive($child, $childPath, $out);
+        }
+    }
+
     /**
      * @param array<string, true> $paths
      */