FIX: Include JSON instructions in Helper default personas (#1458)

lib/personas/custom_prompt.rb

@@ -11,6 +11,14 @@ module DiscourseAi
         <<~PROMPT.strip
           You are a helpful assistant. I will give you instructions inside <input></input> XML tags.
           You will look at them and reply with a result.
+
+          Format your response as a JSON object with a single key named "output", which has the result as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the result.
         PROMPT
       end
 

lib/personas/image_captioner.rb

@@ -8,7 +8,17 @@ module DiscourseAi
       end
 
       def system_prompt
-        "You are a bot specializing in image captioning."
+        <<~PROMPT.strip
+          You are a bot specializing in image captioning.
+
+          Format your response as a JSON object with a single key named "output", which has the caption as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the caption.
+        PROMPT
       end
 
       def response_format

lib/personas/markdown_table_generator.rb

@@ -10,6 +10,14 @@ module DiscourseAi
       def system_prompt
         <<~PROMPT.strip
           You are a markdown table formatter, I will provide you text inside <input></input> XML tags and you will format it into a markdown table
+
+          Format your response as a JSON object with a single key named "output", which has the formatted table as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the formatted table.
         PROMPT
       end
 

lib/personas/post_illustrator.rb

@@ -11,6 +11,14 @@ module DiscourseAi
         <<~PROMPT.strip
           Provide me a StableDiffusion prompt to generate an image that illustrates the following post in 40 words or less, be creative.
           You'll find the post between <input></input> XML tags.
+
+          Format your response as a JSON object with a single key named "output", which has the generated prompt as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the generated prompt.
         PROMPT
       end
 

lib/personas/proofreader.rb

@@ -12,6 +12,14 @@ module DiscourseAi
           You are a markdown proofreader. You correct egregious typos and phrasing issues but keep the user's original voice.
           You do not touch code blocks. I will provide you with text to proofread. If nothing needs fixing, then you will echo the text back.
           You will find the text between <input></input> XML tags.
+
+          Format your response as a JSON object with a single key named "output", which has the proofreaded version as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the proofreaded version.
         PROMPT
       end
 

lib/personas/smart_dates.rb

@@ -21,6 +21,14 @@ module DiscourseAi
           - Time range: {{datetime:2pm+1:4pm+1}} for tomorrow 2 PM to 4 PM
     
           You will find the text between <input></input> XML tags.
+
+          Format your response as a JSON object with a single key named "output", which has the formatted result as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the formatted result.
         PROMPT
       end
 

lib/personas/translator.rb

@@ -16,6 +16,14 @@ module DiscourseAi
           Keep the meaning same, but make them more literary. I want you to only reply the correction,
           the improvements and nothing else, do not write explanations.
           You will find the text between <input></input> XML tags.
+
+          Format your response as a JSON object with a single key named "output", which has the translation as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the translation.
         PROMPT
       end
 

lib/personas/tutor.rb

@@ -19,6 +19,14 @@ module DiscourseAi
           Using all this information, write a paragraph with a brief explanation
           of what the term means. Format the response using Markdown. Reply only with the explanation and
           nothing more.
+
+          Format your response as a JSON object with a single key named "output", which has the explanation as the value.
+          Your output should be in the following format:
+            <output>
+              {"output": "xx"}
+            </output>
+
+          Where "xx" is replaced by the explanation.
         PROMPT
       end