Update conversation_logic.py

conversation_logic.py

@@ -222,12 +222,17 @@ def _specific_topic_from_question(question_text: str, fallback_topic: str, class
         return "median"
     if "range" in q:
         return "range"
+    if any(k in q for k in ["probability", "chance", "odds", "at random", "chosen at random"]):
+        return "probability"
     if (
         "ratio" in q
         or re.search(r"\b[a-z]\s*/\s*[a-z]\b", q)
         or re.search(r"\b\d+\s*/\s*\d+\b", q)
+        or "proportion" in q
     ):
         return "ratio"
+    if "percent" in q or "%" in q:
+        return "percent"
     if topic == "data" and any(k in q for k in ["dataset", "table", "chart", "graph"]):
         return "statistics"
     return topic
@@ -263,6 +268,11 @@ def _build_topic_query_reply(question_text: str, fallback_topic: str, classified
             "- This is a percent question.\n"
             "- The key skill is identifying the correct base quantity before applying the percent relationship."
         )
+    if specific == "probability":
+        return (
+            "- This is a probability question.\n"
+            "- The key skill is deciding what counts as a successful outcome and then comparing favorable outcomes with the total possible outcomes."
+        )
 
     label = specific if specific != "general" else (cat.lower() if cat else "quantitative reasoning")
     return f"- This looks like a {label} question."
@@ -635,6 +645,66 @@ def _question_specific_percent_reply(question_text: str) -> str:
     )
 
 
+
+def _question_specific_probability_reply(question_text: str, options_text: Optional[List[str]] = None) -> str:
+    q = _clean_text(question_text)
+    low = q.lower()
+    option_count = len(options_text or [])
+
+    single_draw_markers = [
+        "chosen at random",
+        "select one",
+        "choose one",
+        "one ball",
+        "one card",
+        "one marble",
+        "one object",
+        "selected at random",
+        "picked at random",
+    ]
+    container_markers = [
+        "box contains",
+        "bag contains",
+        "urn contains",
+        "deck",
+        "balls",
+        "cards",
+        "marbles",
+        "dice",
+        "coin",
+    ]
+
+    if any(m in low for m in single_draw_markers) or (
+        "probability" in low and any(m in low for m in container_markers)
+    ):
+        lines = [
+            "- Start by deciding what counts as a successful outcome in this question.",
+            "- Then count the total number of possible outcomes in the container or sample space.",
+            "- Set up the probability as favorable outcomes over total outcomes before comparing the answer choices.",
+        ]
+        if option_count:
+            lines.append("- Use that fraction to match the answer choices instead of doing extra work.")
+        return "\n".join(lines)
+
+    if "at least" in low:
+        return (
+            "- Start by deciding whether the complement is easier than counting the requested cases directly.\n"
+            "- For an 'at least' question, it is often simpler to find the probability of the opposite event first.\n"
+            "- Then subtract that result from 1 at the end."
+        )
+
+    if any(k in low for k in ["and", "both", "then", "after"]) and any(k in low for k in ["probability", "chosen", "random"]):
+        return (
+            "- First identify whether the events happen together or separately.\n"
+            "- Then decide whether you should multiply probabilities, add them, or use the complement.\n"
+            "- Keep track of whether the total outcomes change after each step."
+        )
+
+    return (
+        "- Start by identifying the favorable outcomes and the total possible outcomes.\n"
+        "- Then build the probability as favorable over total before simplifying or matching an answer choice."
+    )
+
 def _build_question_specific_reply(
     *,
     question_text: str,
@@ -652,9 +722,30 @@ def _build_question_specific_reply(
     if not q:
         return ""
 
+    explicit_help_ask = (
+        input_type in {"hint", "next_hint", "confusion"}
+        or any(
+            phrase in user_low
+            for phrase in [
+                "how do i solve",
+                "how do i do this",
+                "what do i do first",
+                "what should i do first",
+                "how should i start",
+                "where do i start",
+                "first step",
+            ]
+        )
+    )
+
     if any(k in low for k in ["variability", "spread", "standard deviation"]):
         return _question_specific_variability_reply(options_text)
 
+    if topic == "probability" or any(
+        k in low for k in ["probability", "chance", "odds", "at random", "chosen at random"]
+    ):
+        return _question_specific_probability_reply(q, options_text)
+
     if topic in {"ratio", "algebra"}:
         if re.search(r"\b[a-z]\s*/\s*[a-z]\s*=\s*\d+\s*/\s*\d+", low):
             return _question_specific_ratio_reply(q)
@@ -680,10 +771,12 @@ def _build_question_specific_reply(
             "- Then focus on the exact expression the question asks for, rather than solving more than you need to."
         )
 
-    if input_type in {"hint", "next_hint", "confusion"} or any(
-        phrase in user_low for phrase in ["how do i solve", "what do i do first", "what should i do first", "how should i start"]
-    ):
-        return "- Start by identifying the main relationship in the question, then rewrite the target expression using that relationship before simplifying."
+    if explicit_help_ask:
+        if topic == "percent":
+            return _question_specific_percent_reply(q)
+        if topic == "probability":
+            return _question_specific_probability_reply(q, options_text)
+        return "- Start by identifying the main relationship in the question, then use that relationship to set up the first step."
 
     return ""
 
@@ -940,6 +1033,11 @@ class ConversationEngine:
 
         if input_type == "topic_query":
             support_topic = fallback_pack.get("topic") if fallback_pack else ""
+            final_topic = _specific_topic_from_question(
+                solver_input,
+                support_topic,
+                question_topic if question_topic else "general",
+            ) or support_topic or question_topic or "general"
             topic_reply_core = _build_topic_query_reply(
                 question_text=solver_input,
                 fallback_topic=support_topic,
@@ -953,9 +1051,9 @@ class ConversationEngine:
                 transparency=transparency,
                 help_mode="answer",
                 hint_stage=hint_stage,
-                topic=support_topic or question_topic or result.topic,
+                topic=final_topic,
             )
-            result.topic = support_topic or question_topic or result.topic
+            result.topic = final_topic
             result.reply = reply
             result.help_mode = "answer"
             result.meta["response_source"] = "topic_classifier"
@@ -993,15 +1091,8 @@ class ConversationEngine:
 
         if fallback_pack and fallback_pack.get("topic") == "statistics":
             qlow = (solver_input or "").lower()
-            wants_topic = input_type == "topic_query"
             if any(k in qlow for k in ["variability", "spread", "standard deviation"]):
-                if wants_topic:
-                    fallback_reply_core = (
-                        "- This is a statistics / data insight question about variability (spread).\n"
-                        "- Focus on how spread out each dataset is rather than the average.\n"
-                        "- Compare how far the outer values sit from the middle value in each set."
-                    )
-                elif resolved_help_mode == "answer":
+                if resolved_help_mode == "answer":
                     fallback_reply_core = (
                         "- Notice this is asking about variability, which means spread, not the mean.\n"
                         "- Compare how far the smallest and largest values sit from the middle value in each dataset.\n"