Update src/llm_utils.py

src/llm_utils.py

@@ -1,32 +1,39 @@
-# src/llm_utils.py
 import os
 from openai import OpenAI
 
-# You can either:
-# - Set OPENAI_API_KEY as a secret in Hugging Face, OR
-# - Replace "YOUR_OPENAI_API_KEY" directly (less secure)
 API_KEY = os.getenv("OPENAI_API_KEY", "YOUR_OPENAI_API_KEY")
-
 client = OpenAI(api_key=API_KEY)
 
 
 def explain_savings_plan(payload: dict) -> str:
     """
-    Calls a small LLM model to explain the numeric savings plan.
+    Uses a small LLM model to turn the numeric savings plan into a
+    short, plain-English explanation.
+
     Guardrails:
-    - Do NOT invent new numbers
-    - Use ONLY fields from payload
-    - Explanation-only; no decisions
+    - MUST NOT invent or change any numbers
+    - Uses ONLY the fields in `payload`
+    - Explanation only; it does not make credit decisions
     """
+
     system_prompt = """
-You are an AI assistant that explains home down-payment savings plans for first-time buyers.
-You MUST NOT invent or change any numeric values.
-Use ONLY the fields provided in the JSON payload.
-Write 2–3 short sentences that:
-  1) State what the user is trying to achieve (reach a down payment).
-  2) Explain why this recommended monthly savings amount makes sense.
-  3) Mention the timeline (years and months).
-Be neutral, concise, and non-promotional.
+You are an AI coach explaining a down-payment savings plan for a first-time homebuyer.
+
+Rules:
+- Do NOT invent or change any numeric values.
+- Use ONLY the numbers provided in the JSON.
+- Be clear, friendly, and non-promotional.
+- Write 3–4 short sentences, no bullet points.
+
+Content to cover:
+1) Start with the goal: buying a home at the given home_budget with the given down_payment_percent.
+2) Explain how much they already have (current_savings) and how much more they need (remaining_need).
+3) Explain the recommended_monthly_savings over timeline_years / timeline_months.
+4) If savings_to_income_ratio is provided:
+   - Briefly say whether this monthly amount is a light, moderate, or heavy lift
+     (around 0.10 = light, 0.20 = moderate, 0.30+ = heavy), BUT use only that ratio,
+     do not guess at after-tax income.
+5) Encourage them to adjust the timeline or budget sliders if the amount feels too high.
     """.strip()
 
     user_content = f"Here is the JSON for this user's plan: {payload}"
@@ -38,16 +45,25 @@ Be neutral, concise, and non-promotional.
                 {"role": "system", "content": system_prompt},
                 {"role": "user", "content": user_content},
             ],
-            max_tokens=220,
-            temperature=0.3,
+            max_tokens=230,
+            temperature=0.35,
         )
         explanation = completion.choices[0].message.content.strip()
         return explanation
+
     except Exception:
-        # Safe fallback if LLM fails
+        # Safe fallback if the LLM call fails
+        hb = payload.get("home_budget")
+        dp_pct = payload.get("down_payment_percent")
+        dp_amt = payload.get("down_payment_amount")
+        rem = payload.get("remaining_need")
+        m = payload.get("timeline_months")
+        rec = payload.get("recommended_monthly_savings")
+
         return (
-            "We calculated your recommended monthly savings using your home budget, "
-            "target down payment percentage, current savings, and chosen timeline. "
-            "The remaining amount is spread over the available months, with estimated "
-            "closing costs added and expected interest on savings subtracted."
-        )
+            "We calculated your plan using your home budget, down-payment percentage, "
+            f"and current savings. For example, to buy a home around ${hb:,} with a "
+            f"{dp_pct}% down payment (about ${dp_amt:,}), you still need roughly "
+            f"${rem:,}. Spreading that over about {m} months leads to a recommended "
+            f"savings of about ${rec:,} per month, including closing cost and interest assumptions."
+        )