Pin DeepState mirror, prefer HTTPS for Madrid/KiwiSDR, document outbound data (#362–#364).

Operators can set DEEPSTATE_MIRROR_COMMIT for immutable frontline ingest; Madrid KML tries HTTPS then HTTP without changing camera image URLs or proxy Referers.

Co-authored-by: Cursor <cursoragent@cursor.com>

backend/.env.example

@@ -87,6 +87,12 @@ AIS_API_KEY=              # https://aisstream.io/ — free tier WebSocket key
 # Free MAP_KEY from https://firms.modaps.eosdis.nasa.gov/map/#d:24hrs;@0.0,0.0,3.0z
 # FIRMS_MAP_KEY=
 
+# Ukraine frontline mirror (GitHub). Default follows cyterat/deepstate-map-data@main.
+# Pin an immutable commit SHA so ingest cannot silently change if main is force-pushed (#362).
+# Example (verify on GitHub before use): main @ b479954e94696bc5622c7818fd20a64a699f4fe8
+# DEEPSTATE_MIRROR_COMMIT=b479954e94696bc5622c7818fd20a64a699f4fe8
+# DEEPSTATE_MIRROR_REPO=cyterat/deepstate-map-data
+
 # Ukraine air raid alerts from alerts.in.ua — free token from https://alerts.in.ua/
 # ALERTS_IN_UA_TOKEN=
 

backend/services/cctv_pipeline.py

@@ -1012,14 +1012,33 @@ def _extract_img_src(html_fragment: str):
 class MadridCityIngestor(BaseCCTVIngestor):
     """Madrid City Hall traffic cameras from datos.madrid.es KML feed."""
 
-    KML_URL = "http://datos.madrid.es/egob/catalogo/202088-0-trafico-camaras.kml"
+    KML_URL_HTTPS = "https://datos.madrid.es/egob/catalogo/202088-0-trafico-camaras.kml"
+    KML_URL_HTTP = "http://datos.madrid.es/egob/catalogo/202088-0-trafico-camaras.kml"
+
+    def _fetch_kml(self):
+        """Prefer HTTPS; fall back to legacy HTTP if the catalog is HTTP-only (#363)."""
+        last_error: Exception | None = None
+        for url in (self.KML_URL_HTTPS, self.KML_URL_HTTP):
+            try:
+                response = fetch_with_curl(url, timeout=20)
+                response.raise_for_status()
+                if url == self.KML_URL_HTTP:
+                    logger.warning(
+                        "MadridCityIngestor: HTTPS KML unavailable, using HTTP catalog feed"
+                    )
+                return response
+            except Exception as e:
+                last_error = e
+                logger.debug("MadridCityIngestor: KML fetch failed for %s: %s", url, e)
+        if last_error is not None:
+            raise last_error
+        raise RuntimeError("Madrid KML fetch failed")
 
     def fetch_data(self) -> List[Dict[str, Any]]:
         import defusedxml.ElementTree as ET
 
         try:
-            response = fetch_with_curl(self.KML_URL, timeout=20)
-            response.raise_for_status()
+            response = self._fetch_kml()
         except Exception as e:
             logger.error(f"MadridCityIngestor: failed to fetch KML: {e}")
             return []

backend/services/geopolitics.py

@@ -1,3 +1,4 @@
+import os
 import requests
 import logging
 import zipfile
@@ -20,6 +21,50 @@ logger = logging.getLogger(__name__)
 # Cache Frontline data for 30 minutes, it doesn't move that fast
 frontline_cache = TTLCache(maxsize=1, ttl=1800)
 
+_DEFAULT_DEEPSTATE_MIRROR_REPO = "cyterat/deepstate-map-data"
+
+
+def _deepstate_mirror_ref() -> tuple[str, str]:
+    """Return (github_repo_slug, git_ref) for the DeepState mirror.
+
+    When ``DEEPSTATE_MIRROR_COMMIT`` is set, ingest is pinned to that immutable
+    SHA instead of following the mutable ``main`` branch (#362).
+    """
+    repo = (os.environ.get("DEEPSTATE_MIRROR_REPO") or _DEFAULT_DEEPSTATE_MIRROR_REPO).strip()
+    if repo.count("/") != 1:
+        repo = _DEFAULT_DEEPSTATE_MIRROR_REPO
+    commit = (os.environ.get("DEEPSTATE_MIRROR_COMMIT") or "").strip()
+    ref = commit if commit else "main"
+    return repo, ref
+
+
+def _latest_deepstate_geo_path(tree_items: list) -> str | None:
+    geo_files = [
+        item["path"]
+        for item in tree_items
+        if isinstance(item, dict)
+        and str(item.get("path", "")).startswith("data/deepstatemap_data_")
+        and str(item.get("path", "")).endswith(".geojson")
+    ]
+    return sorted(geo_files)[-1] if geo_files else None
+
+
+def _annotate_deepstate_geojson(data: dict) -> dict:
+    name_map = {
+        0: "Russian-occupied areas",
+        1: "Russian advance",
+        2: "Liberated area",
+        3: "Russian-occupied areas",  # Crimea / LPR / DPR
+        4: "Directions of UA attacks",
+    }
+    if "features" in data:
+        for idx, feature in enumerate(data["features"]):
+            if "properties" not in feature or feature["properties"] is None:
+                feature["properties"] = {}
+            feature["properties"]["name"] = name_map.get(idx, "Russian-occupied areas")
+            feature["properties"]["zone_id"] = idx
+    return data
+
 
 @cached(frontline_cache)
 def fetch_ukraine_frontlines():
@@ -27,67 +72,34 @@ def fetch_ukraine_frontlines():
     Fetches the latest GeoJSON data representing the Ukraine frontline.
     We use the cyterat/deepstate-map-data github mirror since the public API is locked.
     """
+    repo, ref = _deepstate_mirror_ref()
     try:
-        logger.info("Fetching DeepStateMap from GitHub mirror...")
+        logger.info("Fetching DeepStateMap from GitHub mirror (%s @ %s)...", repo, ref)
 
-        # First, query the repo tree to find the latest file name
-        tree_url = (
-            "https://api.github.com/repos/cyterat/deepstate-map-data/git/trees/main?recursive=1"
-        )
+        tree_url = f"https://api.github.com/repos/{repo}/git/trees/{ref}?recursive=1"
         res_tree = requests.get(tree_url, timeout=10)
 
         if res_tree.status_code == 200:
-            tree_data = res_tree.json().get("tree", [])
-            # Filter for geojson files in data folder
-            geo_files = [
-                item["path"]
-                for item in tree_data
-                if item["path"].startswith("data/deepstatemap_data_")
-                and item["path"].endswith(".geojson")
-            ]
-
-            if geo_files:
-                # Get the alphabetically latest file (since it's named with YYYYMMDD)
-                latest_file = sorted(geo_files)[-1]
-
-                raw_url = f"https://raw.githubusercontent.com/cyterat/deepstate-map-data/main/{latest_file}"
-                logger.info(f"Downloading latest DeepStateMap: {raw_url}")
+            latest_file = _latest_deepstate_geo_path(res_tree.json().get("tree", []))
+            if latest_file:
+                raw_url = f"https://raw.githubusercontent.com/{repo}/{ref}/{latest_file}"
+                logger.info("Downloading DeepStateMap: %s", raw_url)
 
                 res_geo = requests.get(raw_url, timeout=20)
                 if res_geo.status_code == 200:
-                    data = res_geo.json()
-
-                    # The Cyterat GitHub mirror strips all properties and just provides a raw array of Feature polygons.
-                    # Based on DeepStateMap's frontend mapping, the array index corresponds to the zone type:
-                    # 0: Russian-occupied areas
-                    # 1: Russian advance
-                    # 2: Liberated area
-                    # 3: Uncontested/Crimea (often folded into occupied)
-                    name_map = {
-                        0: "Russian-occupied areas",
-                        1: "Russian advance",
-                        2: "Liberated area",
-                        3: "Russian-occupied areas",  # Crimea / LPR / DPR
-                        4: "Directions of UA attacks",
-                    }
-
-                    if "features" in data:
-                        for idx, feature in enumerate(data["features"]):
-                            if "properties" not in feature or feature["properties"] is None:
-                                feature["properties"] = {}
-
-                            feature["properties"]["name"] = name_map.get(
-                                idx, "Russian-occupied areas"
-                            )
-                            feature["properties"]["zone_id"] = idx
-
-                    return data
-                else:
-                    logger.error(
-                        f"Failed to fetch parsed Github Raw GeoJSON: {res_geo.status_code}"
-                    )
+                    return _annotate_deepstate_geojson(res_geo.json())
+                logger.error(
+                    "Failed to fetch parsed Github Raw GeoJSON: %s", res_geo.status_code
+                )
+            else:
+                logger.error("No deepstatemap_data_*.geojson files in mirror tree at %s", ref)
         else:
-            logger.error(f"Failed to fetch Github Tree for Deepstatemap: {res_tree.status_code}")
+            logger.error(
+                "Failed to fetch Github tree for Deepstatemap (%s @ %s): %s",
+                repo,
+                ref,
+                res_tree.status_code,
+            )
     except (requests.RequestException, ConnectionError, TimeoutError, ValueError, KeyError) as e:
         logger.error(f"Error fetching DeepStateMap: {e}")
     return None

backend/services/kiwisdr_fetcher.py

@@ -32,7 +32,8 @@ logger = logging.getLogger(__name__)
 _REFRESH_SECONDS = 24 * 3600
 kiwisdr_cache: TTLCache = TTLCache(maxsize=1, ttl=_REFRESH_SECONDS)
 
-_SOURCE_URL = "http://rx.linkfanel.net/kiwisdr_com.js"
+_SOURCE_URL_HTTP = "http://rx.linkfanel.net/kiwisdr_com.js"
+_SOURCE_URL_HTTPS = "https://rx.linkfanel.net/kiwisdr_com.js"
 _CACHE_FILE = Path(__file__).resolve().parent.parent / "data" / "kiwisdr_cache.json"
 # Bundled fallback — shipped with the codebase so the KiwiSDR layer always
 # has something to render even when the upstream is unreachable, returns
@@ -184,6 +185,29 @@ def _validate_fetched_nodes(nodes: list[dict]) -> bool:
     return True
 
 
+def _fetch_mirror_payload_text() -> str | None:
+    """Try HTTPS first, then HTTP. Shape validation still applies (#364)."""
+    from services.network_utils import fetch_with_curl
+
+    last_error: Exception | None = None
+    for url in (_SOURCE_URL_HTTPS, _SOURCE_URL_HTTP):
+        try:
+            res = fetch_with_curl(url, timeout=20)
+            if res and res.status_code == 200:
+                if url == _SOURCE_URL_HTTP:
+                    logger.info(
+                        "KiwiSDR: HTTPS mirror unavailable; using HTTP with shape validation"
+                    )
+                return res.text
+            last_error = RuntimeError(f"HTTP {getattr(res, 'status_code', 'unknown')}")
+        except Exception as e:
+            last_error = e
+            logger.debug("KiwiSDR mirror fetch failed for %s: %s", url, e)
+    if last_error is not None:
+        logger.warning("KiwiSDR mirror fetch failed: %s", last_error)
+    return None
+
+
 def _load_bundled_fallback() -> list[dict]:
     """Last-resort directory shipped with the codebase. Always returns a
     list (may be empty if the bundle is missing in older deployments)."""
@@ -216,8 +240,6 @@ def fetch_kiwisdr_nodes() -> list[dict]:
     tampered upstream returning garbage is caught by _validate_fetched_nodes()
     and falls through to whatever previously-trusted snapshot we have.
     """
-    from services.network_utils import fetch_with_curl
-
     # 1. Trust on-disk cache if fresh.
     cached_nodes = _load_disk_cache()
     if cached_nodes is not None:
@@ -230,14 +252,12 @@ def fetch_kiwisdr_nodes() -> list[dict]:
     fresh_nodes: list[dict] = []
     fetch_succeeded = False
     try:
-        res = fetch_with_curl(_SOURCE_URL, timeout=20)
-        if res and res.status_code == 200:
-            fresh_nodes = _parse_mirror_payload(res.text)
+        body = _fetch_mirror_payload_text()
+        if body:
+            fresh_nodes = _parse_mirror_payload(body)
             fetch_succeeded = True
         else:
-            logger.warning(
-                f"KiwiSDR fetch returned HTTP {res.status_code if res else 'no response'}"
-            )
+            logger.warning("KiwiSDR fetch returned no usable mirror payload")
     except (requests.RequestException, ConnectionError, TimeoutError, ValueError, KeyError) as e:
         logger.warning(f"KiwiSDR fetch exception: {e}")
 

backend/tests/test_deepstate_mirror_pin.py

@@ -0,0 +1,46 @@
+"""DeepState GitHub mirror pinning (#362)."""
+from __future__ import annotations
+
+import os
+from unittest.mock import MagicMock, patch
+
+import services.geopolitics as gp
+
+
+def test_deepstate_mirror_ref_defaults(monkeypatch):
+    monkeypatch.delenv("DEEPSTATE_MIRROR_COMMIT", raising=False)
+    monkeypatch.delenv("DEEPSTATE_MIRROR_REPO", raising=False)
+    repo, ref = gp._deepstate_mirror_ref()
+    assert repo == "cyterat/deepstate-map-data"
+    assert ref == "main"
+
+
+def test_deepstate_mirror_ref_pinned_commit(monkeypatch):
+    monkeypatch.setenv("DEEPSTATE_MIRROR_COMMIT", "abc123def456")
+    monkeypatch.setenv("DEEPSTATE_MIRROR_REPO", "cyterat/deepstate-map-data")
+    repo, ref = gp._deepstate_mirror_ref()
+    assert repo == "cyterat/deepstate-map-data"
+    assert ref == "abc123def456"
+
+
+def test_fetch_ukraine_frontlines_uses_pinned_tree_url(monkeypatch):
+    monkeypatch.setenv("DEEPSTATE_MIRROR_COMMIT", "deadbeef")
+    gp.frontline_cache.clear()
+
+    tree_resp = MagicMock(status_code=200)
+    tree_resp.json.return_value = {
+        "tree": [{"path": "data/deepstatemap_data_20260101.geojson"}]
+    }
+    geo_resp = MagicMock(status_code=200)
+    geo_resp.json.return_value = {"features": []}
+
+    with patch("services.geopolitics.requests.get", side_effect=[tree_resp, geo_resp]) as get:
+        result = gp.fetch_ukraine_frontlines()
+
+    assert result == {"features": []}
+    tree_call = get.call_args_list[0][0][0]
+    raw_call = get.call_args_list[1][0][0]
+    assert "/git/trees/deadbeef" in tree_call
+    assert "raw.githubusercontent.com/cyterat/deepstate-map-data/deadbeef/" in raw_call
+
+    gp.frontline_cache.clear()

backend/tests/test_kiwisdr_https_first.py

@@ -0,0 +1,29 @@
+"""KiwiSDR mirror prefers HTTPS (#364)."""
+from __future__ import annotations
+
+from unittest.mock import MagicMock, patch
+
+from services.kiwisdr_fetcher import (
+    _SOURCE_URL_HTTP,
+    _SOURCE_URL_HTTPS,
+    _fetch_mirror_payload_text,
+)
+
+
+def test_fetch_mirror_tries_https_before_http():
+    calls: list[str] = []
+
+    def fake_fetch(url, **kwargs):
+        calls.append(url)
+        if url == _SOURCE_URL_HTTPS:
+            raise ConnectionError("tls not available")
+        res = MagicMock()
+        res.status_code = 200
+        res.text = "var kiwisdr_com = [];"
+        return res
+
+    with patch("services.network_utils.fetch_with_curl", side_effect=fake_fetch):
+        body = _fetch_mirror_payload_text()
+
+    assert body == "var kiwisdr_com = [];"
+    assert calls == [_SOURCE_URL_HTTPS, _SOURCE_URL_HTTP]