From 82640709d6dcc884c5c0312070a1c457cd835a0d Mon Sep 17 00:00:00 2001
From: Barrett Ruth <62671086+barrettruth@users.noreply.github.com>
Date: Fri, 6 Mar 2026 15:23:55 -0500
Subject: [PATCH] fix(kattis,usaco): precision, open URLs, and Kattis submit
 error surface (#335)

## Problem

Kattis and USACO problem tests never extracted float precision, so
epsilon problems got no tolerance. Kattis `scrape_contest_metadata`
omitted `contest_url` and `standings_url`, breaking `:CP open
contest/standings`. Kattis submit always returned success even when the
server responded with an error (e.g. "You need to join the contest").

## Solution

Call `extract_precision` on problem HTML in both scrapers and emit it in
the JSON payload. Set `contest_url` and `standings_url` on Kattis
metadata paths. After Kattis submit, check for `Submission ID:` in the
response and surface the error text if absent.
---
 scrapers/kattis.py | 18 +++++++++++++++---
 scrapers/usaco.py  |  6 +++++-
 2 files changed, 20 insertions(+), 4 deletions(-)

diff --git a/scrapers/kattis.py b/scrapers/kattis.py
index 7741847..2c5c1fc 100644
--- a/scrapers/kattis.py
+++ b/scrapers/kattis.py
@@ -10,7 +10,7 @@ from pathlib import Path
 
 import httpx
 
-from .base import BaseScraper
+from .base import BaseScraper, extract_precision
 from .timeouts import HTTP_TIMEOUT
 from .models import (
     ContestListResult,
@@ -173,6 +173,7 @@ async def _stream_single_problem(client: httpx.AsyncClient, slug: str) -> None:
 
     timeout_ms, memory_mb = _parse_limits(html)
     interactive = _is_interactive(html)
+    precision = extract_precision(html)
 
     tests: list[TestCase] = []
     try:
@@ -200,6 +201,7 @@ async def _stream_single_problem(client: httpx.AsyncClient, slug: str) -> None:
                 "memory_mb": memory_mb,
                 "interactive": interactive,
                 "multi_test": False,
+                "precision": precision,
             }
         ),
         flush=True,
@@ -254,6 +256,8 @@ class KattisScraper(BaseScraper):
                             ProblemSummary(id=slug, name=name) for slug, name in slugs
                         ],
                         url=f"{BASE_URL}/problems/%s",
+                        contest_url=f"{BASE_URL}/contests/{contest_id}",
+                        standings_url=f"{BASE_URL}/contests/{contest_id}/standings",
                     )
                 try:
                     html = await _fetch_text(
@@ -273,6 +277,8 @@ class KattisScraper(BaseScraper):
                     contest_id=contest_id,
                     problems=[ProblemSummary(id=contest_id, name=name)],
                     url=f"{BASE_URL}/problems/%s",
+                    contest_url=f"{BASE_URL}/problems/{contest_id}",
+                    standings_url="",
                 )
         except Exception as e:
             return self._metadata_error(str(e))
@@ -373,9 +379,15 @@ class KattisScraper(BaseScraper):
                     return self._submit_error(f"Submit request failed: {e}")
 
             sid_m = re.search(r"Submission ID:\s*(\d+)", r.text, re.IGNORECASE)
-            sid = sid_m.group(1) if sid_m else ""
+            if not sid_m:
+                return self._submit_error(
+                    r.text.strip() or "Submit failed (no submission ID)"
+                )
             return SubmitResult(
-                success=True, error="", submission_id=sid, verdict="submitted"
+                success=True,
+                error="",
+                submission_id=sid_m.group(1),
+                verdict="submitted",
             )
 
     async def login(self, credentials: dict[str, str]) -> LoginResult:
diff --git a/scrapers/usaco.py b/scrapers/usaco.py
index 074cbf9..5ab89f7 100644
--- a/scrapers/usaco.py
+++ b/scrapers/usaco.py
@@ -8,7 +8,7 @@ from typing import Any, cast
 
 import httpx
 
-from .base import BaseScraper
+from .base import BaseScraper, extract_precision
 from .timeouts import HTTP_TIMEOUT
 from .models import (
     ContestListResult,
@@ -130,12 +130,14 @@ def _parse_problem_page(html: str) -> dict[str, Any]:
     memory_mb = int(mm.group(1)) if mm else 256
 
     interactive = "interactive problem" in html.lower()
+    precision = extract_precision(html)
 
     return {
         "tests": tests,
         "timeout_ms": timeout_ms,
         "memory_mb": memory_mb,
         "interactive": interactive,
+        "precision": precision,
     }
 
 
@@ -375,6 +377,7 @@ class USACOScraper(BaseScraper):
                             "timeout_ms": 4000,
                             "memory_mb": 256,
                             "interactive": False,
+                            "precision": None,
                         }
 
                     tests = cast(list[TestCase], info["tests"])
@@ -396,6 +399,7 @@ class USACOScraper(BaseScraper):
                         "memory_mb": info["memory_mb"],
                         "interactive": info["interactive"],
                         "multi_test": False,
+                        "precision": info["precision"],
                     }
 
             tasks = [run_one(cpid) for cpid, _ in problems_raw]