From c2bb48db193ee16c470a4b813219d7dcc501f2a7 Mon Sep 17 00:00:00 2001
From: "yves.gugger" <yves.gugger@gentwo.com>
Date: Mon, 8 Dec 2025 12:03:08 +0100
Subject: [PATCH] fix: Ensure 100% price consistency across all TLD pages
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ROOT CAUSE:
- Overview API prioritized database data (only Porkbun prices)
- Compare API prioritized static data (5+ registrars)
- This caused price mismatches between Overview table and Detail page

SOLUTION:
- Changed Overview API to prioritize static data for TLDs with rich
  multi-registrar pricing (like Compare API does)
- Database data now used only for TLDs NOT in static data
- This ensures all APIs return identical prices for same TLDs

VERIFICATION:
- .com: Overview=$10.75, Compare=$10.75 ✓
- .io: Overview=$32.33, Compare=$32.33 ✓
- .ai: Overview=$71.63, Compare=$71.63 ✓
- .xyz: Overview=$6.86, Compare=$6.86 ✓

DATA FLOW (now consistent):
1. Static TLDs (18): Use rich multi-registrar data
2. DB-only TLDs (869): Use Porkbun scraped data
3. Total: 887 TLDs with consistent pricing
---
 backend/app/api/tld_prices.py | 69 ++++++++++++++++++++++-------------
 1 file changed, 43 insertions(+), 26 deletions(-)

diff --git a/backend/app/api/tld_prices.py b/backend/app/api/tld_prices.py
index 3f38884..6759dc6 100644
--- a/backend/app/api/tld_prices.py
+++ b/backend/app/api/tld_prices.py
@@ -346,40 +346,25 @@ async def get_tld_overview(
 ):
     """Get overview of TLDs with current pricing, pagination, and search.
     
+    Data source priority:
+    - For TLDs with rich static data (multiple registrars): Use static data for consistency
+    - For TLDs only in database: Use database data
+    - This ensures Overview and Compare/Detail pages show identical prices
+    
     Args:
         limit: Number of results per page (default 25)
         offset: Skip N results for pagination
         search: Filter TLDs by name (e.g., "com", "io")
         sort_by: Sort order - popularity (default), price_asc, price_desc, name
-        source: Data source - "auto" (DB first, fallback to static), "db" (only DB), "static" (only static)
+        source: Data source - "auto" (best available), "db" (only DB), "static" (only static)
     """
     tld_list = []
-    data_source = "static"
+    tld_seen = set()
+    data_source = "combined"
     
-    # Try database first if auto or db
-    if source in ["auto", "db"]:
-        db_count = await get_db_price_count(db)
-        if db_count > 0:
-            db_prices = await get_db_prices(db)
-            data_source = "database"
-            
-            for tld, data in db_prices.items():
-                prices = data["prices"]
-                tld_list.append({
-                    "tld": tld,
-                    "type": guess_tld_type(tld),
-                    "description": TLD_DATA.get(tld, {}).get("description", f".{tld} domain"),
-                    "avg_registration_price": round(sum(prices) / len(prices), 2),
-                    "min_registration_price": min(prices),
-                    "max_registration_price": max(prices),
-                    "registrar_count": len(data["registrars"]),
-                    "trend": TLD_DATA.get(tld, {}).get("trend", "stable"),
-                    "popularity_rank": TOP_TLDS_BY_POPULARITY.index(tld) if tld in TOP_TLDS_BY_POPULARITY else 999,
-                })
-    
-    # Use static data as fallback or if requested
-    if not tld_list and source in ["auto", "static"]:
-        data_source = "static"
+    # FIRST: Add all static data TLDs (these have rich multi-registrar data)
+    # This ensures consistency with /compare endpoint which also uses static data first
+    if source in ["auto", "static"]:
         for tld, data in TLD_DATA.items():
             tld_list.append({
                 "tld": tld,
@@ -392,6 +377,38 @@ async def get_tld_overview(
                 "trend": data["trend"],
                 "popularity_rank": TOP_TLDS_BY_POPULARITY.index(tld) if tld in TOP_TLDS_BY_POPULARITY else 999,
             })
+            tld_seen.add(tld)
+    
+    # SECOND: Add TLDs from database that are NOT in static data
+    # This adds the 800+ TLDs scraped from Porkbun
+    if source in ["auto", "db"]:
+        db_count = await get_db_price_count(db)
+        if db_count > 0:
+            db_prices = await get_db_prices(db)
+            
+            for tld, data in db_prices.items():
+                if tld not in tld_seen:  # Only add if not already from static
+                    prices = data["prices"]
+                    tld_list.append({
+                        "tld": tld,
+                        "type": guess_tld_type(tld),
+                        "description": f".{tld} domain extension",
+                        "avg_registration_price": round(sum(prices) / len(prices), 2),
+                        "min_registration_price": min(prices),
+                        "max_registration_price": max(prices),
+                        "registrar_count": len(data["registrars"]),
+                        "trend": "stable",
+                        "popularity_rank": TOP_TLDS_BY_POPULARITY.index(tld) if tld in TOP_TLDS_BY_POPULARITY else 999,
+                    })
+                    tld_seen.add(tld)
+    
+    # Determine source label
+    if source == "static":
+        data_source = "static"
+    elif source == "db":
+        data_source = "database"
+    else:
+        data_source = "combined"
     
     # Apply search filter
     if search: