changes to question validation

researchsimulation/InteractiveInterviewChatbot.py

@@ -132,9 +132,9 @@ def validate_question_topics(parsed_questions, processor_llm):
         ### Question:
         {question}
         ### Permitted Topics Scope:
-        The respondents may only answer questions related to the following general topics:
+        The chatbot is designed to explore personal views, habits, and life experiences. The following topics are allowed:
         
-        - Demographics: Age, location, education, family background, life events.
+        - Demographics: Age, name, location, education, family background, life events.
         - Values & Beliefs: Family responsibility, independence, hard work, gender equality, spirituality, simplicity, mental health, traditional vs modern values.
         - Career & Aspirations: Education, career goals, entrepreneurship, financial independence, stability, ambition, and personal development.
         - Influences & Role Models: Family members, mentors, public figures, influencers.
@@ -148,29 +148,24 @@ def validate_question_topics(parsed_questions, processor_llm):
         - Personal Growth & Development: Maturity, emotional regulation, responsibility, adaptability, self-improvement, learning mindset.
         
         ### Validation Instructions:
-        You must determine if the question is appropriate for a lifestyle, values, and personal development interview.
         
-        1. **Topical Relevance**
-           - Accept the question only if it is **clearly relevant** to the Permitted Topics Scope and can be answered from a **personal, lifestyle, or values-based perspective**.
+        1. ✅ **Accept the question** if:
+           - It fits naturally into a friendly, personal conversation.
+           - It relates to one of the permitted topic areas *OR* is a simple, personal background question (e.g. name, where you live, age).
+           - It can be answered from a **personal lifestyle, identity, or values-based** perspective — including light or introductory prompts.
+           - It helps the chatbot get to know the respondent (even if it's informal or simple).
         
-        2. **Content Restrictions**
-           Return exactly "INVALID" if the question contains any of the following:
-           - Hate speech, discrimination, harassment
-           - Sexually explicit, violent, or graphic content
-           - Religious extremism or proselytising
-           - Politically sensitive content:
-             - Opinions or knowledge about politicians or political parties
-             - Policy debates, election-related topics, or partisan comparisons
-           - References to extremist ideologies or hate groups
-           - Overly technical, academic, or scientific content not grounded in personal lifestyle (e.g. biology, physics, finance, geopolitics)
-           - News-related or controversial current events
+        2. ❌ **Reject the question** by returning **"INVALID"** if it includes:
+           - Hate speech, abuse, discrimination
+           - Sexual, violent, or explicit content
+           - Religious proselytising or extremism
+           - Political content (politicians, parties, policies, elections)
+           - Technical, academic, or scientific topics unrelated to lifestyle
+           - News, current events, or controversial debates
         
-        3. **Everyday Relevance**
-           - Even if the topic superficially fits the scope, it must be **personally relatable, non-controversial**, and answerable by someone with the respondent's **general life experience**, not specialised knowledge.
+        3. ✅ **If the question is valid**, return the same question rewritten using **British English spelling and phrasing** (keep the meaning unchanged, use natural conversational style).
         
-        4. **Output Instructions**
-           - If invalid, return exactly: "INVALID"
-           - If valid, return the **same question**
+        4. ❌ **If invalid**, return **only**: "INVALID"
         
         ### Output:
         <Validated question OR "INVALID">
@@ -424,8 +419,8 @@ def validate_tailored_answer(agent_name, agent_question, respondent_agent, tailo
             logging.info(f"[validate_tailored_answer] Validation result for attempt {attempt+1}: {is_valid}")
 
             if is_valid:
-                if len(tailored_answer) > 800:
-                    logging.warning(f"Tailored answer exceeds 800 characters (length={len(tailored_answer)}); retrying...")
+                if len(tailored_answer) > 1000:
+                    logging.warning(f"Tailored answer exceeds 1000 characters (length={len(tailored_answer)}); retrying...")
                     attempt += 1
                 else:
                     validated = True