fix(gateway:moderationAgent): Update model response handling

1 files changed, 17 insertions, 2 deletions

diff --git a/packages/gateway/src/listeners/moderationAgent/utilities.ts b/packages/gateway/src/listeners/moderationAgent/utilities.ts
index eb520c7..2e6542e 100644
--- a/packages/gateway/src/listeners/moderationAgent/utilities.ts
+++ b/packages/gateway/src/listeners/moderationAgent/utilities.ts
@@ -272,16 +272,18 @@ CONFIDENCE GUIDELINES:
 - 0-39%: Low confidence, likely false positive
 
 RESPONSE FORMAT:
-You must respond with valid JSON in this exact format:
+You must respond with ONLY valid JSON in this exact format. Do not include any text before or after the JSON:
 {
   "violation": boolean,
   "rule": "Rule number and brief description if violation found, empty string if none",
   "severity": "low|medium|high|critical",
   "explanation": "Detailed explanation of the violation or why it's acceptable",
   "brief": "Short one-sentence explanation for why it was flagged (if violation) or why it's acceptable (if no violation)",
-  "confidence": number (0-100, how confident you are in this assessment)
+  "confidence": number
 }
 
+CRITICAL: Your response must be ONLY the JSON object above. No explanations, no markdown, no additional text. Start with { and end with }. All string values must use double quotes, not single quotes. Escape any quotes in string values with backslashes.
+
 If no violation is found, set "violation" to false and provide a brief explanation of why the message is acceptable.
 
 Remember: Only enforce the exact rules provided. Do not make assumptions or interpretations beyond what is explicitly stated in the SERVER_RULES section. Adult sexual content between adults is NOT a violation unless it explicitly breaks a stated rule.`;
@@ -350,6 +352,19 @@ Remember: Only enforce the exact rules provided. Do not make assumptions or inte
         }
       }
 
+      if (!jsonContent.startsWith("{")) {
+        const jsonMatch = jsonContent.match(/\{[\s\S]*\}/);
+
+        if (jsonMatch) jsonContent = jsonMatch[0];
+      }
+
+      jsonContent = jsonContent
+        .replace(/\\'/g, "'")
+        .replace(/'/g, '"')
+        .replace(/(\w+):/g, '"$1":')
+        .replace(/,\s*}/g, "}")
+        .replace(/,\s*]/g, "]");
+
       return JSON.parse(jsonContent);
     } catch (parseError) {
       console.error("Failed to parse OpenRouter response as JSON:", content);