From b1c8a91ed6ddebf8c056c8b1d4025686e69a6e6c Mon Sep 17 00:00:00 2001
From: Kunthawat Greethong <kunthawat@Kunthawats-MacBook-Pro.local>
Date: Fri, 28 Aug 2026 20:28:25 +0700
Subject: [PATCH] feat(scheduler): daily Siamchart SET50 board collection
 (writes master + vintage, feeds dashboard)

---
 backend/app/scheduler.py | 58 +++++++++++++++++++++++++++++++++++++++-
 1 file changed, 57 insertions(+), 1 deletion(-)

diff --git a/backend/app/scheduler.py b/backend/app/scheduler.py
index d28e29a..655d25b 100644
--- a/backend/app/scheduler.py
+++ b/backend/app/scheduler.py
@@ -53,7 +53,7 @@ _FREQ_SECONDS: dict[str, int] = {
 # Data that legitimately changes every day (or faster) is refreshed separately
 # at a daily cadence rather than on the slow factor loop.
 _DAILY_JOBS: List[dict] = [
-    {"key": "siamchart_vintages", "label": "Siamchart SET50 snapshot (vintage)", "fn": "_record_siamchart_vintages", "frequency": "daily"},
+    {"key": "siamchart_vintages", "label": "Siamchart SET50 snapshot (vintage)", "fn": "_collect_siamchart_daily", "frequency": "daily"},
     {"key": "price_snapshot", "label": "ราคาหุ้น SET50 (Yahoo)", "fn": "_refresh_price_snapshot", "frequency": "daily"},
 ]
 
@@ -279,6 +279,62 @@ class AppDataScheduler:
         except Exception:  # noqa: BLE001
             log.exception("set50 siamchart vintage persist failed (non-fatal)")
 
+    def _collect_siamchart_daily(self) -> None:
+        """Daily: fetch the Siamchart SET50 fundamental board, write the master
+        snapshot, and persist a vintage (so dashboard + strict backtest are fed).
+
+        This is what actually puts stocks on the dashboard page: on a fresh
+        deploy the volume starts empty (no ``set50_master.json``), so the board
+        stays blank until the first successful daily collection. We fetch the
+        group table (``fetch_financial``) then each symbol's stock-info page
+        for ratios/income (``fetch_stock_info``), write ``set50_master.json``
+        (the exact shape ``_load_siamchart_snapshot``/``siamchart_factors``
+        consume), and finally record a vintage.
+
+        Failures are logged to the source-health panel via the caller's
+        exception handling; on network error the previous master is retained.
+        """
+        import datetime as _dt
+        import json
+        from . import siamchart
+        from .siamchart_vintages import SiamchartVintageStore, SiamchartVintageError
+
+        rows = siamchart.fetch_financial("SET50")
+        details: dict = {}
+        for row in rows:
+            try:
+                info = siamchart.fetch_stock_info(row.symbol)
+                details[row.symbol] = info.to_dict()
+            except siamchart.SiamchartError as exc:
+                log.warning("set50 stock-info %s failed: %s", row.symbol, exc)
+                details[row.symbol] = {"error": str(exc)}
+
+        now_utc = _dt.datetime.now(_dt.timezone.utc).strftime("%Y-%m-%dT%H:%M:%SZ")
+        payload = {
+            "source": "siamchart",
+            "retrieved_at": now_utc,
+            "mode": "group",
+            "group": "SET50",
+            "url": siamchart.build_url("SET50"),
+            "count": len(rows),
+            "rows": [row.to_dict() for row in rows],
+            "details": details,
+            "details_count": len(details),
+        }
+        out = self.data_root / "siamchart" / "set50_master.json"
+        out.parent.mkdir(parents=True, exist_ok=True)
+        out.write_text(json.dumps(payload, ensure_ascii=False, sort_keys=True, indent=2),
+                       encoding="utf-8")
+        log.info("set50 siamchart board collected (%d rows, %d details)",
+                 len(rows), len(details))
+
+        # persist a vintage so the strict backtest fundamental is PIT
+        try:
+            store = SiamchartVintageStore(self.data_root)
+            store.persist(payload)
+        except SiamchartVintageError as exc:
+            log.warning("set50 siamchart vintage persist failed after collect: %s", exc)
+
     def _maybe_refresh_dated_dividends(self) -> None:
         """Cooldown-gated fetch of real dated dividend history into the ledger.