feat: overhaul UI styling, improve templates, enhance services and tests

app/services/crawler.py

@@ -38,20 +38,29 @@ async def fetch_daily(target_date: str, top_n: int | None = None) -> list[dict]:
     async with make_http_client() as client:
         for attempt in range(1, settings.HTTP_MAX_RETRIES + 1):
             try:
-                logger.info("Fetching HF Daily Papers: date=%s attempt=%d", target_date, attempt)
+                logger.info(
+                    "Fetching HF Daily Papers: date=%s attempt=%d", target_date, attempt
+                )
                 resp = await client.get(url, params=params)
                 resp.raise_for_status()
                 data = resp.json()
                 break
             except (httpx.HTTPError, httpx.HTTPStatusError) as exc:
-                logger.warning("Fetch failed (attempt %d/%d): %s", attempt, settings.HTTP_MAX_RETRIES, exc)
+                logger.warning(
+                    "Fetch failed (attempt %d/%d): %s",
+                    attempt,
+                    settings.HTTP_MAX_RETRIES,
+                    exc,
+                )
                 if attempt == settings.HTTP_MAX_RETRIES:
                     raise
         else:
             data = []
 
     papers = data[:top_n]
-    logger.info("Fetched %d papers for %s (raw=%d)", len(papers), target_date, len(data))
+    logger.info(
+        "Fetched %d papers for %s (raw=%d)", len(papers), target_date, len(data)
+    )
     return papers
 
 
@@ -75,8 +84,14 @@ def _parse_paper(item: dict) -> dict:
         "hf_url": f"https://huggingface.co/papers/{arxiv_id}" if arxiv_id else "",
         "arxiv_url": f"https://arxiv.org/abs/{arxiv_id}" if arxiv_id else "",
         "pdf_url": f"https://arxiv.org/pdf/{arxiv_id}.pdf" if arxiv_id else "",
-        "authors": [a.get("name", a) if isinstance(a, dict) else a for a in paper_info.get("authors", [])],
-        "tags": [t.get("name", t) if isinstance(t, dict) else t for t in (paper_info.get("tags") or [])],
+        "authors": [
+            a.get("name", a) if isinstance(a, dict) else a
+            for a in paper_info.get("authors", [])
+        ],
+        "tags": [
+            t.get("name", t) if isinstance(t, dict) else t
+            for t in (paper_info.get("tags") or [])
+        ],
     }
 
 
@@ -133,15 +148,25 @@ def upsert_papers(db: Session, papers_raw: list[dict], paper_date: str) -> list[
                     "INSERT INTO papers_fts(rowid, title_en, abstract, authors, tags) "
                     "VALUES (:id, :title, :abstract, :authors, :tags)"
                 ),
-                {"id": paper.id, "title": meta["title_en"], "abstract": meta["abstract"] or "",
-                 "authors": authors_text, "tags": tags_text},
+                {
+                    "id": paper.id,
+                    "title": meta["title_en"],
+                    "abstract": meta["abstract"] or "",
+                    "authors": authors_text,
+                    "tags": tags_text,
+                },
             )
 
             new_papers.append(paper)
             logger.debug("Inserted new paper: %s", arxiv_id)
 
     db.commit()
-    logger.info("Upserted %d papers (%d new) for %s", len(papers_raw), len(new_papers), paper_date)
+    logger.info(
+        "Upserted %d papers (%d new) for %s",
+        len(papers_raw),
+        len(new_papers),
+        paper_date,
+    )
     return new_papers
 
 
@@ -165,7 +190,12 @@ async def crawl_daily(db: Session, target_date: str, top_n: int | None = None) -
         log_entry.papers_new = len(new_papers)
         log_entry.completed_at = datetime.now(timezone.utc)
         db.commit()
-        return {"found": len(raw_papers), "new": len(new_papers), "status": "success", "error": None}
+        return {
+            "found": len(raw_papers),
+            "new": len(new_papers),
+            "status": "success",
+            "error": None,
+        }
     except Exception as exc:
         logger.exception("Crawl failed for %s", target_date)
         log_entry.status = "failed"