patch 20

config/retriex/agent.yaml

@@ -8,6 +8,113 @@ parameters:
     optimized_shop_query_prefix_pattern: '/^(?:keywords?|suchquery|search\s*query|query)\s*:\s*/iu'
     optimized_shop_query_trim_characters: " \t\n\r\0\x0B\"'`"
 
+    input_normalization:
+      enabled: true
+      max_input_chars: 500
+      max_output_chars: 700
+      max_added_tokens: 2
+      max_length_ratio_percent: 150
+      heartbeat_message: 'Ich prüfe die Eingabe auf Tippfehler…'
+      output_prefix_pattern: '/^(?:normalisiert|korrigiert|corrected|normalized)\s*:\s*/iu'
+      skip_patterns:
+        - '/https?:\/\//iu'
+        - '/\bwww\./iu'
+        - '/```/u'
+      prompt:
+        intro: 'Normalize the following user input for RetrieX routing before intent detection.'
+        output_format_block: |-
+          Output format:
+          <normalized user input>
+        current_user_input_label: 'USER INPUT'
+        rules:
+          - '- Output only the normalized user input.'
+          - '- Correct only obvious typing mistakes, transposed letters, missing umlauts, spacing, and punctuation that clearly preserve the same meaning.'
+          - '- Do not add product names, model numbers, article numbers, measurement values, parameters, brands, or application areas that are not already present in the input.'
+          - '- Preserve product names, model numbers, article numbers, chemical symbols, units, pH, Redox, ORP, and measurement values exactly unless only letter casing is corrected.'
+          - '- Preserve the input language; do not translate German into English or English into German.'
+          - '- Preserve vague references such as "der indikator", "das gerät", "suche im shop", or "dazu" without resolving them from context.'
+          - '- If the input is already clear or you are uncertain, return the original input unchanged.'
+          - '- No introduction, no explanation, no quotation marks.'
+
+      fuzzy_routing:
+        enabled: true
+        min_token_length: 4
+        medium_token_length: 7
+        long_token_length: 11
+        max_distance_short: 1
+        max_distance_medium: 2
+        max_distance_long: 3
+        min_similarity_percent: 72
+        # Canonical routing terms only, not typo variants.
+        # The code fuzzy-matches user tokens against these terms when the LLM leaves
+        # an obvious routing typo unchanged.
+        terms:
+          - shop
+          - suche
+          - suchen
+          - such
+          - finde
+          - finden
+          - kostet
+          - kosten
+          - preis
+          - preise
+          - preiswert
+          - preiswerte
+          - günstig
+          - guenstig
+          - kaufen
+          - bestellen
+          - produkt
+          - produkte
+          - artikel
+          - sku
+          - online
+          - analysegerät
+          - analysegeraet
+          - messgerät
+          - messgeraet
+          - handmessgerät
+          - handmessgeraet
+          - pockettester
+          - analysator
+          - analyzer
+          - indikator
+          - indikatoren
+          - reagenz
+          - reagenzien
+          - verbrauchsmaterial
+          - zubehör
+          - zubehoer
+          - ersatzteil
+          - ersatzteile
+          - anschlusskabel
+          - kabel
+          - sensorkabel
+          - elektrode
+          - elektrodenkabel
+          - puffer
+          - kalibrierpuffer
+          - kalibrierlösung
+          - kalibrierloesung
+          - kalibrierung
+          - lösung
+          - loesung
+          - messen
+          - messung
+          - überwachen
+          - ueberwachen
+          - kontrollieren
+          - schwimmbad
+          - pool
+          - becken
+          - wasseranalyse
+          - geeignet
+          - passend
+          - empfehlung
+          - empfehlen
+          - empfiehl
+
     follow_up_context:
       strong_reference_patterns:
         - '/\bder\s+wert\b/u'