harden retrieve logic part 3

src/Agent/PromptBuilder.php

@@ -56,6 +56,7 @@ final readonly class PromptBuilder
         'modell',
         'model',
         'messprinzip',
+        'measurement principle',
         'schnittstelle',
         'interface',
         'relais',
@@ -111,15 +112,19 @@ final readonly class PromptBuilder
         $urlContent = $this->normalizeBlockText($urlContent);
         $swagFullOutPut = $this->normalizeNullableBlockText($swagFullOutPut);
 
+        $hasShopResults = $shopResults !== [];
+
         $systemBlock = $this->buildSystemBlock();
         $shopBlock = $this->buildShopBlock($shopResults, $swagFullOutPut);
-        $knowledgeBlock = $this->buildKnowledgeBlock($knowledgeChunks, $urlContent, $prompt);
+        $outputPriorityBlock = $this->buildOutputPriorityBlock($hasShopResults);
+        $knowledgeBlock = $this->buildKnowledgeBlock($knowledgeChunks, $urlContent, $prompt, $hasShopResults);
         $userBlock = $this->buildUserBlock($prompt);
 
         // Build fixed blocks first so history only receives the remaining budget.
         $fixedPrompt = $this->implodeBlocks([
             $systemBlock,
             $shopBlock,
+            $outputPriorityBlock,
             $knowledgeBlock,
             $userBlock,
         ]);
@@ -133,6 +138,7 @@ final readonly class PromptBuilder
         return $this->implodeBlocks([
             $systemBlock,
             $shopBlock,
+            $outputPriorityBlock,
             $knowledgeBlock,
             $contextBlock,
             $userBlock,
@@ -200,7 +206,10 @@ final readonly class PromptBuilder
     }
 
     /**
-     * Build the shop block with the highest business priority for product facts.
+     * Build the shop block.
+     *
+     * Shop data is the most current source for commercial details.
+     * It should not override technical matching logic.
      */
     private function buildShopBlock(array $shopResults, ?string $swagFullOutPut): string
     {
@@ -275,24 +284,40 @@ final readonly class PromptBuilder
 
         if ($lines !== []) {
             $parts[] =
-                "LIVE SHOP RESULTS (authoritative for products):\n" .
+                "LIVE SHOP RESULTS (authoritative for current commercial details):\n" .
-                "Use these results as authoritative for product identity, availability, pricing, and shop-visible product details.\n" .
+                "Use these results as the primary source for current price, availability, URL, and current shop-visible product naming.\n" .
-                "If retrieved documents conflict with live shop data on product availability or price, prefer the live shop data.\n" .
+                "If retrieved documents conflict with shop data on price, availability, URL, or current naming, prefer the shop data.\n" .
-                "Do not infer undocumented technical specifications from live shop data.\n" .
+                "Output real URL values exactly as provided in the shop results. Do not replace them with placeholders, link labels, or product names.\n" .
-                "Do not derive technical benefits or operational conclusions from shop data unless explicitly stated.\n\n" .
+                "Do not infer undocumented technical specifications from shop data.\n\n" .
                 implode("\n\n", $lines);
         }
 
         return $this->implodeBlocks($parts);
     }
 
+    /**
+     * Build a small priority block that tells the model what to surface first.
+     */
+    private function buildOutputPriorityBlock(bool $hasShopResults): string
+    {
+        if (!$hasShopResults) {
+            return '';
+        }
+
+        return
+            "OUTPUT PRIORITY:\n" .
+            "Use retrieved knowledge first to determine the technically matching product or answer.\n" .
+            "If shop results are present, use them afterwards to add current price, availability, and the actual URL.\n" .
+            "Do not let bundles, accessories, or service items override a better technical match unless the user explicitly asks for them.\n";
+    }
+
     /**
      * Build the knowledge block.
      *
-     * Retrieved knowledge is authoritative for factual statements that are present in the sources.
+     * Retrieved knowledge remains the main source for technical matching and explanation.
-     * Missing facts must not be invented.
+     * Shop data is preferred for current commercial fields.
      */
-    private function buildKnowledgeBlock(array $knowledgeChunks, string $urlContent, string $prompt): string
+    private function buildKnowledgeBlock(array $knowledgeChunks, string $urlContent, string $prompt, bool $hasShopResults): string
     {
         $knowledgeParts = [];
         $isTechnicalProductQuestion = $this->isLikelyTechnicalProductQuestion($prompt);
@@ -312,12 +337,17 @@ final readonly class PromptBuilder
             }
 
             if ($lines !== []) {
-                $knowledgeParts[] =
+                $parts = [
+                    "LANGUAGE RULES:\n" .
+                    implode("\n", $this->buildLanguageRules()),
                     "FACT GROUNDING RULES:\n" .
-                    implode("\n", $this->buildFactGroundingRules($isTechnicalProductQuestion)) . "\n\n" .
+                    implode("\n", $this->buildFactGroundingRules($isTechnicalProductQuestion, $hasShopResults)),
-                    "RETRIEVED KNOWLEDGE (authoritative for facts):\n" .
+                    "RETRIEVED KNOWLEDGE (primary for technical matching and factual explanation):\n" .
                     "Source: Documents\n" .
-                    implode("\n\n", $lines);
+                    implode("\n\n", $lines),
+                ];
+
+                $knowledgeParts[] = implode("\n\n", $parts);
             }
         }
 
@@ -371,10 +401,22 @@ final readonly class PromptBuilder
     /**
      * @return string[]
      */
-    private function buildFactGroundingRules(bool $isTechnicalProductQuestion): array
+    private function buildLanguageRules(): array
+    {
+        return [
+            "- Answer only in the same language as the user question.",
+            "- All headings, labels, notes, and structural elements must be in the same language as the user question.",
+            "- Do not switch languages unless the user does.",
+            "- If headings are used, write them in the user's language.",
+        ];
+    }
+
+    /**
+     * @return string[]
+     */
+    private function buildFactGroundingRules(bool $isTechnicalProductQuestion, bool $hasShopResults): array
     {
         $rules = [
-            "- Use retrieved knowledge as authoritative for factual answers.",
             "- State only facts that are explicitly present in the provided sources.",
             "- Extract concrete values exactly when they are present, including units, ranges, model names, indicator names, IP classes, temperatures, pressures, dimensions, counts, relay outputs, current outputs, and error codes.",
             "- Do not invent missing values.",
@@ -388,6 +430,17 @@ final readonly class PromptBuilder
             "- If a sentence cannot be traced to the provided sources, do not write it.",
         ];
 
+        if ($hasShopResults) {
+            $rules = array_merge($rules, [
+                "- Use shop data as highest priority only for current commercial fields: price, availability, URL, and current shop-visible naming.",
+                "- Use retrieved knowledge as highest priority for technical matching, thresholds, measurement principles, and technical explanation.",
+                "- When shop results are present and relevant, include current price and the actual URL if available.",
+                "- Do not let accessories, bundles, or service items override a technically better product match unless the user explicitly asks for them.",
+            ]);
+        } else {
+            $rules[] = "- Use retrieved knowledge as authoritative for factual answers.";
+        }
+
         if ($isTechnicalProductQuestion) {
             $rules = array_merge($rules, [
                 "- For technical product questions, answer primarily with explicitly stated facts.",
@@ -399,9 +452,11 @@ final readonly class PromptBuilder
                 "- Do not use persuasive summaries or advisory conclusions.",
                 "- If the retrieved knowledge describes one specific named product, stay within that product and do not merge related product families or variants.",
                 "- Use neutral engineering language.",
-                "- If the source states signal logic such as green/red, output that signal logic only and do not expand it into operational recommendations unless explicitly stated.",
+                "- Do not name specific chemicals, indicator substances, standards, or mechanisms unless explicitly stated in the source.",
+                "- If the source states signal logic such as green/red, output that signal logic only and do not expand it into operational recommendations or alarm semantics unless explicitly stated.",
                 "- If the source lists application areas, repeat only those areas and do not broaden them.",
                 "- If the source names an indicator and threshold, reproduce that exactly without extrapolation.",
+                "- If the source states only a threshold function, do not expand it into broader control logic.",
                 "- If a detail is not explicitly stated in the provided sources, say so plainly.",
                 "- Prefer short, source-close sentences over explanatory expansion.",
             ]);

src/Config/NdjsonHybridRetrieverConfig.php

@@ -12,7 +12,7 @@ final class NdjsonHybridRetrieverConfig
      * Chosen to stay selective enough for product-family-heavy data
      * while not cutting off too many useful fallback hits.
      */
-    public const VECTOR_SCORE_THRESHOLD = 0.80;
+    public const VECTOR_SCORE_THRESHOLD = 0.82;
 
     /**
      * Absolute safety caps.