fix: address gemini-code-assist 12th review on PR #1

All 5 findings legitimate, all applied:

Defensive exception handling:
- collect_github._get_page: add ValueError to except. urlopen raises
  it for malformed URLs ("unknown url type" etc.), e.g. a sources.yaml
  entry with a missing scheme. [MEDIUM]
- collect_rss._fetch: same ValueError addition. [MEDIUM]
- score.score: wrap json.loads(normalized.json) in try/except. A
  corrupt or truncated file (disk-full mid-write etc.) used to crash
  the whole scoring step instead of leaving the previous scored.json
  in place. [MEDIUM]
- report.render: same try/except around json.loads(scored.json).
  [MEDIUM]

Stale guidance:
- new-track.sh: the "next steps" message still told users to edit
  TRACKS in the root Makefile, but Makefile now auto-discovers tracks
  via `wildcard tracks/*/`. Updated to point at the two places that
  do still need a manual update for a new track:
    .github/workflows/{daily-update,weekly-digest}.yml matrix.track
    web/src/lib/data.ts TRACKS const
  with a footnote that the root Makefile is auto. [MEDIUM]

Author: kanywst

scripts/awsdd/collect_github.py

@@ -67,7 +67,9 @@ def _get_page(url: str) -> tuple[list[dict], str | None]:
     except HTTPError as e:
         print(f"[collect_github] {url}: HTTP {e.code}")
         return [], None
-    except (URLError, TimeoutError, UnicodeDecodeError, json.JSONDecodeError) as e:
+    except (URLError, TimeoutError, UnicodeDecodeError, ValueError, json.JSONDecodeError) as e:
+        # ValueError covers urlopen's "unknown url type" / malformed-URL path
+        # in case sources.yaml smuggles in an unsupported scheme.
         print(f"[collect_github] {url}: error {e}")
         return [], None
     # GitHub returns a JSON object (not a list) on error envelopes (rate-limit etc.);

scripts/awsdd/collect_rss.py

@@ -47,7 +47,9 @@ def _fetch(url: str, timeout: int = FETCH_TIMEOUT) -> bytes | None:
             # truncated XML body to feedparser would just bozo-error silently
             # and partially populate the track. Better to skip the feed loudly.
             raw = r.read(MAX_FEED_BYTES + 1)
-    except (URLError, TimeoutError) as e:
+    except (URLError, TimeoutError, ValueError) as e:
+        # ValueError catches urlopen's "unknown url type" path so a typo in
+        # sources.yaml (missing scheme, etc.) doesn't crash the whole track.
         print(f"[collect_rss] fetch {url}: {e}")
         return None
     if len(raw) > MAX_FEED_BYTES:

scripts/awsdd/report.py

@@ -20,7 +20,12 @@ def _filename(mode: str, now: datetime) -> str:
 
 def render(track: str, mode: str) -> None:
     p = track_dir(track) / "data" / "scored.json"
-    items: list[dict] = json.loads(p.read_text(encoding="utf-8")) if p.exists() else []
+    items: list[dict] = []
+    if p.exists():
+        try:
+            items = json.loads(p.read_text(encoding="utf-8"))
+        except (OSError, json.JSONDecodeError) as e:
+            print(f"[report] {track}: failed to load scored.json: {e}")
     now = datetime.now(UTC)
     cutoff = now - WINDOW[mode]
     fresh = [it for it in items if parse_iso(it.get("published_at", "")) >= cutoff]

scripts/awsdd/score.py

@@ -69,7 +69,12 @@ def score_item(item: dict, sources: dict, now: datetime) -> dict[str, float]:
 
 def score(track: str) -> None:
     p = track_dir(track) / "data" / "normalized.json"
-    items: list[dict] = json.loads(p.read_text(encoding="utf-8")) if p.exists() else []
+    items: list[dict] = []
+    if p.exists():
+        try:
+            items = json.loads(p.read_text(encoding="utf-8"))
+        except (OSError, json.JSONDecodeError) as e:
+            print(f"[score] {track}: failed to load normalized.json: {e}")
     sources = load_sources(track)
     now = datetime.now(UTC)
     for it in items:

scripts/new-track.sh

@@ -25,5 +25,7 @@ fi
 echo "Created tracks/$name"
 echo "Next:"
 echo "  1. edit tracks/$name/config/sources.yaml"
-echo "  2. add '$name' to TRACKS in Makefile and to matrix.track in .github/workflows/*.yml"
-echo "  3. make -C tracks/$name install update"
+echo "  2. add '$name' to matrix.track in .github/workflows/daily-update.yml and weekly-digest.yml"
+echo "  3. add '$name' to TRACKS in web/src/lib/data.ts so the site renders it"
+echo "  4. make -C tracks/$name install update"
+echo "(The root Makefile auto-discovers tracks via wildcard, no edit needed.)"