fix(taps): align with integrator resilience patterns

Port critical patterns from the working integrator into Singer taps:
- GIAS: add 404 fallback to yesterday's date, increase timeout to 300s,
  use latin-1 encoding, use dated URL for links (static URL returns 500)
- FBIT: add GIAS date fallback, increase timeout, fix encoding to latin-1
- IDACI: use dated GIAS URL with fallback instead of undated static URL,
  fix encoding to latin-1, increase timeout to 300s
- Ofsted: try utf-8-sig then fall back to latin-1 encoding

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

pipeline/plugins/extractors/tap-uk-gias/tap_uk_gias/tap.py

@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from datetime import date
+from datetime import date, timedelta
 
 from singer_sdk import Stream, Tap
 from singer_sdk import typing as th
@@ -12,6 +12,11 @@ GIAS_URL_TEMPLATE = (
     "/edubase/downloads/public/edubasealldata{date}.csv"
 )
 
+GIAS_LINKS_URL_TEMPLATE = (
+    "https://ea-edubase-api-prod.azurewebsites.net"
+    "/edubase/downloads/public/links_edubasealldata{date}.csv"
+)
+
 
 class GIASEstablishmentsStream(Stream):
     """Stream: GIAS establishments (one row per URN)."""
@@ -40,23 +45,30 @@ class GIASEstablishmentsStream(Stream):
         import pandas as pd
         import requests
 
-        today = date.today().strftime("%Y%m%d")
-        url = GIAS_URL_TEMPLATE.format(date=today)
+        today = date.today()
+        url = GIAS_URL_TEMPLATE.format(date=today.strftime("%Y%m%d"))
 
         self.logger.info("Downloading GIAS bulk CSV: %s", url)
-        resp = requests.get(url, timeout=120)
+        resp = requests.get(url, timeout=300)
+
+        # GIAS may not have today's file yet — fall back to yesterday
+        if resp.status_code == 404:
+            yesterday = (today - timedelta(days=1)).strftime("%Y%m%d")
+            url = GIAS_URL_TEMPLATE.format(date=yesterday)
+            self.logger.info("Today's file not available, trying yesterday: %s", url)
+            resp = requests.get(url, timeout=300)
+
         resp.raise_for_status()
 
         df = pd.read_csv(
             io.StringIO(resp.text),
-            encoding="utf-8-sig",
+            encoding="latin-1",
             dtype=str,
             keep_default_na=False,
         )
 
         for _, row in df.iterrows():
             record = row.to_dict()
-            # Cast URN to int
             try:
                 record["URN"] = int(record["URN"])
             except (ValueError, KeyError):
@@ -85,18 +97,24 @@ class GIASLinksStream(Stream):
         import pandas as pd
         import requests
 
-        url = (
-            "https://ea-edubase-api-prod.azurewebsites.net"
-            "/edubase/downloads/public/links_edubasealldata.csv"
-        )
+        today = date.today()
+        url = GIAS_LINKS_URL_TEMPLATE.format(date=today.strftime("%Y%m%d"))
 
         self.logger.info("Downloading GIAS links CSV: %s", url)
-        resp = requests.get(url, timeout=120)
+        resp = requests.get(url, timeout=300)
+
+        # Fall back to yesterday if today's file isn't available
+        if resp.status_code in (404, 500):
+            yesterday = (today - timedelta(days=1)).strftime("%Y%m%d")
+            url = GIAS_LINKS_URL_TEMPLATE.format(date=yesterday)
+            self.logger.info("Today's links file not available, trying yesterday: %s", url)
+            resp = requests.get(url, timeout=300)
+
         resp.raise_for_status()
 
         df = pd.read_csv(
             io.StringIO(resp.text),
-            encoding="utf-8-sig",
+            encoding="latin-1",
             dtype=str,
             keep_default_na=False,
         )