igdb search + capped http reads: native fulltext, full-page fetch

search_games used `where name ~ "<q>"*`: prefix-only, diacritic- and
word-order-sensitive -- "MARVEL Tōkon" found nothing though IGDB has
it. Switch to IGDB's native `search` clause (relevance-ranked,
diacritic-insensitive).

fetch_url and image downloads read bodies with content.read(n), which
returns only the first buffered chunk (~7 KB): pages collapsed to
their <title>. httpread.read_capped collects chunks up to the byte
cap; image downloads read limit+1 so over-limit files are still
rejected instead of cached truncated (IMG-10).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

config.toml

@@ -80,3 +80,15 @@ enable-game-info = true
 # Ops (SPEC-012): consecutive OpenAI failures before a staff alert
 # api-error-alert-threshold = 5
 # Backups: cron runs deploy/backup_db.py daily -> ~/backups/<bot>/ (keep 14)
+
+# News digest (SPEC-013) — `python -m fjerkroa_bot.news --config X.toml` via cron;
+# writes the {news} file. Feeds are [url, label] pairs (RSS or Atom):
+# news = "news_feed.txt"
+# news-per-feed = 3
+# news-max-items = 15
+# news-feeds = [
+#   ["https://blog.playstation.com/feed/", "PS"],
+#   ["https://kotaku.com/rss", "Kotaku"],
+#   ["https://www.pushsquare.com/feeds/latest", "Push"],
+#   ["https://mein-mmo.de/feed/", "MeinMMO"],
+# ]

fjerkroa_bot/httpread.py

@@ -0,0 +1,18 @@
+"""Bounded HTTP body read (leaf module, no intra-package imports).
+
+`response.content.read(n)` returns whatever is buffered, not n bytes,
+so it silently truncates large or chunked bodies (and web feeds/pages
+parse to garbage). This accumulates decompressed chunks up to a hard
+cap instead.
+"""
+
+CHUNK = 65536
+
+
+async def read_capped(response, max_bytes: int) -> bytes:
+    buf = bytearray()
+    async for chunk in response.content.iter_chunked(CHUNK):
+        buf.extend(chunk)
+        if len(buf) > max_bytes:
+            break
+    return bytes(buf[:max_bytes])

fjerkroa_bot/igdblib.py

@@ -56,8 +56,12 @@ class IGDBQuery(object):
         return requests.post(igdb_url, headers=headers, data=query_body)
 
     @staticmethod
-    def build_query(fields, filters=None, limit=10, offset=None):
-        query = f"fields {','.join(fields) if fields is not None and len(fields) > 0 else '*'}; limit {limit};"
+    def build_query(fields, filters=None, limit=10, offset=None, search_term=None):
+        query = ""
+        if search_term:
+            escaped = search_term.replace("\\", "\\\\").replace('"', '\\"')
+            query += f'search "{escaped}"; '
+        query += f"fields {','.join(fields) if fields is not None and len(fields) > 0 else '*'}; limit {limit};"
         if offset is not None:
             query += f" offset {offset};"
         if filters:
@@ -65,12 +69,12 @@ class IGDBQuery(object):
             query += " where " + " & ".join(filter_statements) + ";"
         return query
 
-    def generalized_igdb_query(self, params, endpoint, fields, additional_filters=None, limit=10, offset=None):
+    def generalized_igdb_query(self, params, endpoint, fields, additional_filters=None, limit=10, offset=None, search_term=None):
         all_filters = {key: f'~ "{value}"*' for key, value in params.items() if value}
         if additional_filters:
             all_filters.update(additional_filters)
 
-        query = self.build_query(fields, all_filters, limit, offset)
+        query = self.build_query(fields, all_filters, limit, offset, search_term)
         data = self.send_igdb_request(endpoint, query)
         print(f"{endpoint}: {query} -> {data}")
         return data
@@ -134,9 +138,10 @@ class IGDBQuery(object):
             return None
 
         try:
-            # Search for games with fuzzy matching
+            # IGDB native full-text search: diacritic- and word-order-insensitive,
+            # unlike a `name ~ "..."*` prefix filter
             games = self.generalized_igdb_query(
-                {"name": query.strip()},
+                {},
                 "games",
                 [
                     "id",
@@ -155,6 +160,7 @@ class IGDBQuery(object):
                 ],
                 additional_filters={"game_type": "= 0"},  # Main games only (IGDB renamed category -> game_type)
                 limit=limit,
+                search_term=query.strip(),
             )
 
             if not games:

fjerkroa_bot/images.py

@@ -14,6 +14,7 @@ from typing import Any, Callable, Dict, List, Optional
 
 import aiohttp
 
+from .httpread import read_capped
 from .persistence import PersistentStore
 
 DEFAULT_CACHE_MB = 500
@@ -79,7 +80,9 @@ class ImageCache:
         async with aiohttp.ClientSession(timeout=timeout) as session:
             async with session.get(url) as response:
                 response.raise_for_status()
-                return await response.content.read(limit + 1)
+                # limit + 1: an over-limit body must stay over-limit so
+                # ingest_bytes rejects it instead of caching it truncated
+                return await read_capped(response, limit + 1)
 
     def data_url(self, sha256: str, ext: str) -> Optional[str]:
         path = self._path(sha256, ext)

fjerkroa_bot/news.py

@@ -0,0 +1,153 @@
+"""News digest fetcher (SPEC-013, FDB-012 news rewrite).
+
+Replaces the broken pre-1.0-openai `news_feed.py`. Fetches configured
+RSS/Atom feeds (stdlib, no feedparser dep), builds a compact sanitized
+headline digest, and writes it to the `{news}` file the responder
+injects (AIResponder.message). Feeds are external input: titles are
+sanitized (SAF-03) and each feed URL is SSRF-guarded before fetching.
+
+CLI: python -m fjerkroa_bot.news --config kroa.toml
+"""
+
+import argparse
+import logging
+import sys
+import time
+from typing import Any, Dict, List, Optional, Tuple
+
+import defusedxml.ElementTree as ElementTree  # hardened XML: feeds are untrusted (XXE/billion-laughs)
+
+from .ai_responder import sanitize_external_text
+
+DEFAULT_PER_FEED = 3
+DEFAULT_MAX_ITEMS = 15
+FETCH_TIMEOUT_S = 15
+_ATOM = "{http://www.w3.org/2005/Atom}"
+
+
+def parse_feed(data: bytes, source: str = "") -> List[Dict[str, str]]:
+    """Parse RSS or Atom bytes into [{title, link, source}] (tolerant)."""
+    try:
+        root = ElementTree.fromstring(data)
+    except Exception as err:
+        # malformed XML or a blocked entity/DTD attack — tolerate, never raise (NEWS-01)
+        logging.warning(f"news: unparseable/unsafe feed {source!r}: {err!r}")
+        return []
+    items: List[Dict[str, str]] = []
+    # RSS: <rss><channel><item><title/><link/>
+    for item in root.iter("item"):
+        title = (item.findtext("title") or "").strip()
+        link = (item.findtext("link") or "").strip()
+        if title:
+            items.append({"title": title, "link": link, "source": source})
+    # Atom: <feed><entry><title/><link href=/>
+    for entry in root.iter(f"{_ATOM}entry"):
+        title = (entry.findtext(f"{_ATOM}title") or "").strip()
+        link_el = entry.find(f"{_ATOM}link")
+        link = link_el.get("href", "") if link_el is not None else ""
+        if title:
+            items.append({"title": title, "link": link, "source": source})
+    return items
+
+
+def render_digest(items: List[Dict[str, str]], max_items: int = DEFAULT_MAX_ITEMS) -> str:
+    """Compact sanitized digest for the {news} prompt slot."""
+    lines = []
+    for item in items[:max_items]:
+        title = sanitize_external_text(item["title"], 200)
+        source = item.get("source", "")
+        link = item.get("link", "")
+        prefix = f"[{source}] " if source else ""
+        lines.append(f"- {prefix}{title}" + (f" ({link})" if link else ""))
+    return "\n".join(lines)
+
+
+class NewsFetcher:
+    def __init__(self, guard, fetch_bytes) -> None:
+        # injected so tests need no network; production wires aiohttp + guard_url
+        self._guard = guard
+        self._fetch_bytes = fetch_bytes
+
+    async def collect(self, feeds: List[Tuple[str, str]], per_feed: int) -> List[Dict[str, str]]:
+        """feeds = [(url, label)]; returns deduped items, order preserved."""
+        seen = set()
+        out: List[Dict[str, str]] = []
+        for url, label in feeds:
+            reason = self._guard(url)
+            if reason:
+                logging.warning(f"news: skipping feed {label} — {reason}")
+                continue
+            try:
+                data = await self._fetch_bytes(url)
+            except Exception as err:
+                logging.warning(f"news: fetch failed for {label}: {repr(err)}")
+                continue
+            for item in parse_feed(data, label)[:per_feed]:
+                key = item["title"]
+                if key not in seen:
+                    seen.add(key)
+                    out.append(item)
+        return out
+
+
+def _feeds_from_config(config: Dict[str, Any]) -> List[Tuple[str, str]]:
+    """news-feeds = [["url", "label"], ...] or ["url", ...]."""
+    feeds = []
+    for entry in config.get("news-feeds", []):
+        if isinstance(entry, (list, tuple)):
+            feeds.append((str(entry[0]), str(entry[1]) if len(entry) > 1 else ""))
+        else:
+            feeds.append((str(entry), ""))
+    return feeds
+
+
+async def _aiohttp_fetch(url: str) -> bytes:
+    import aiohttp
+
+    from .httpread import read_capped
+
+    timeout = aiohttp.ClientTimeout(total=FETCH_TIMEOUT_S)
+    async with aiohttp.ClientSession(timeout=timeout, headers={"User-Agent": "Mozilla/5.0 (compatible; FjerkroaBot-news/1.0)"}) as session:
+        async with session.get(url) as response:
+            response.raise_for_status()
+            return await read_capped(response, 4 * 1024 * 1024)
+
+
+async def run(config: Dict[str, Any]) -> Optional[str]:
+    from .url_reader import guard_url
+
+    out_path = config.get("news")
+    if not out_path:
+        logging.error("news: no `news` output path in config")
+        return None
+    feeds = _feeds_from_config(config)
+    if not feeds:
+        logging.error("news: no `news-feeds` configured")
+        return None
+    fetcher = NewsFetcher(guard_url, _aiohttp_fetch)
+    items = await fetcher.collect(feeds, int(config.get("news-per-feed", DEFAULT_PER_FEED)))
+    digest = render_digest(items, int(config.get("news-max-items", DEFAULT_MAX_ITEMS)))
+    header = f"News as of {time.strftime('%Y-%m-%d %H:%M UTC', time.gmtime())}:\n"
+    with open(out_path, "w", encoding="utf-8") as fd:
+        fd.write(header + digest + "\n")
+    logging.info(f"news: wrote {len(items)} items to {out_path}")
+    return out_path
+
+
+def main() -> int:
+    import asyncio
+
+    import tomlkit
+
+    logging.basicConfig(level=logging.INFO, format="%(asctime)s [%(levelname)s] %(message)s")
+    parser = argparse.ArgumentParser(description="Fetch RSS/Atom feeds into the {news} digest file")
+    parser.add_argument("--config", required=True)
+    args = parser.parse_args()
+    with open(args.config, encoding="utf-8") as fd:
+        config = tomlkit.load(fd)
+    result = asyncio.run(run(config))
+    return 0 if result else 1
+
+
+if __name__ == "__main__":
+    sys.exit(main())

fjerkroa_bot/url_reader.py

@@ -18,6 +18,7 @@ from urllib.parse import urljoin, urlparse
 import aiohttp
 
 from .ai_responder import sanitize_external_text
+from .httpread import read_capped
 
 DEFAULT_MAX_BYTES = 2 * 1024 * 1024
 DEFAULT_MAX_CHARS = 6000
@@ -115,7 +116,7 @@ class URLReader:
                     current = urljoin(current, response.headers["Location"])
                     continue
                 response.raise_for_status()
-                return str(response.url), await response.content.read(max_bytes + 1)
+                return str(response.url), await read_capped(response, max_bytes)
         raise ValueError("too many redirects")
 
     async def fetch(self, url: str, channel: str, user: str) -> Dict[str, Any]:

pyproject.toml

@@ -15,6 +15,7 @@ dependencies = [
     "tomlkit>=0.13",
     "watchdog>=6",
     "requests>=2.32",
+    "defusedxml>=0.7",
 ]
 
 [project.scripts]

specs/SPEC-013-news.md

@@ -0,0 +1,25 @@
+# SPEC-013 — News digest
+
+Replaces the broken pre-1.0-openai `news_feed.py`. A CLI
+(`python -m fjerkroa_bot.news --config <cfg>`) fetches the
+`news-feeds` and writes a compact digest to the `news` file that
+`AIResponder.message` injects into the `{news}` slot. Feeds are
+external input and operator-configured.
+
+### NEWS-01 — RSS and Atom parse to items (coverage: test)
+
+`parse_feed(bytes, label)` extracts `{title, link, source}` from both
+RSS (`<item>`) and Atom (`<entry>`) documents, tolerates malformed
+XML (returns an empty list, logs), and never raises.
+
+### NEWS-02 — Digest is sanitized and bounded (coverage: test)
+
+`render_digest` caps at `news-max-items`, and every headline passes
+`sanitize_external_text` (SAF-03) — a feed cannot inject `@everyone`
+or control characters into the prompt via a headline.
+
+### NEWS-03 — Feeds are SSRF-guarded and deduped (coverage: test)
+
+`NewsFetcher.collect` skips any feed URL the SSRF guard rejects,
+skips feeds that fail to fetch (one bad feed never sinks the run),
+and drops duplicate headlines across feeds.

tests/test_igdblib.py

@@ -174,6 +174,25 @@ class TestIGDBQuery(unittest.TestCase):
         self.assertEqual(result, [{"id": 1, "name": "Super Mario Bros"}])
 
 
+class TestIGDBNativeSearch(unittest.TestCase):
+    def test_build_query_with_search_term(self):
+        """search_games uses IGDB full-text search, not a name prefix filter."""
+        query = IGDBQuery.build_query(["name"], {"game_type": "= 0"}, limit=5, search_term="Marvel Tōkon")
+        self.assertEqual(query, 'search "Marvel Tōkon"; fields name; limit 5; where game_type = 0;')
+
+    def test_search_term_escapes_quotes_and_backslashes(self):
+        query = IGDBQuery.build_query(["name"], search_term='say "hi" \\ bye')
+        self.assertIn('search "say \\"hi\\" \\\\ bye";', query)
+
+    @patch.object(IGDBQuery, "generalized_igdb_query")
+    def test_search_games_passes_search_term(self, mock_query):
+        mock_query.return_value = []
+        IGDBQuery("cid", "token").search_games("Elden Ring", limit=3)
+        _, kwargs = mock_query.call_args
+        self.assertEqual(kwargs["search_term"], "Elden Ring")
+        self.assertEqual(mock_query.call_args.args[0], {})
+
+
 class TestIGDBTokenRefresh(unittest.TestCase):
     @staticmethod
     def _oauth_response(token="fresh_token", expires_in=5_000_000):

tests/test_spec_imgcache.py

@@ -45,6 +45,45 @@ class TestIngest(unittest.TestCase):
             self.assertIsNone(cache.ingest_bytes(PNG, "chat", "alice", "1"))
 
 
+class TestOversizedDownloadRejected(unittest.IsolatedAsyncioTestCase):
+    async def test_download_stays_over_limit_and_is_rejected(self):
+        """IMG-10: an over-limit download must be rejected, not cached truncated."""
+        with tempfile.TemporaryDirectory() as tmp:
+            _, cache = make_cache(tmp, {"image-max-bytes": 32})
+
+            class FakeContent:
+                @staticmethod
+                async def iter_chunked(size):
+                    yield PNG  # 72 bytes > 32
+
+            class FakeResp:
+                content = FakeContent()
+
+                async def __aenter__(self):
+                    return self
+
+                async def __aexit__(self, *a):
+                    return False
+
+                def raise_for_status(self):
+                    pass
+
+            class FakeSession:
+                def get(self, url):
+                    return FakeResp()
+
+                async def __aenter__(self):
+                    return self
+
+                async def __aexit__(self, *a):
+                    return False
+
+            with patch("fjerkroa_bot.images.aiohttp.ClientSession", return_value=FakeSession()):
+                data = await cache._download("http://x.com/big.png")
+                self.assertEqual(len(data), 33)  # limit + 1, not silently capped to limit
+                self.assertIsNone(await cache.ingest_url("http://x.com/big.png", "chat", "alice", "1"))
+
+
 class TestVisionDataUrls(OpsBase):
     async def test_attachment_becomes_data_url(self):
         """IMG-11: the model sees a data: URL, never the CDN link."""

tests/test_spec_news.py

@@ -0,0 +1,75 @@
+"""Unit coverage for SPEC-013 news digest (NEWS-01..03)."""
+
+import unittest
+from unittest.mock import AsyncMock
+
+from fjerkroa_bot.news import NewsFetcher, parse_feed, render_digest
+
+RSS = b"""<?xml version="1.0"?><rss><channel>
+<item><title>Game X released</title><link>https://ex.com/x</link></item>
+<item><title>Patch Y notes</title><link>https://ex.com/y</link></item>
+</channel></rss>"""
+
+ATOM = b"""<?xml version="1.0"?><feed xmlns="http://www.w3.org/2005/Atom">
+<entry><title>Atom headline</title><link href="https://ex.com/a"/></entry>
+</feed>"""
+
+
+class TestParse(unittest.TestCase):
+    def test_rss(self):
+        """NEWS-01: RSS items parsed with title + link."""
+        items = parse_feed(RSS, "Src")
+        self.assertEqual([i["title"] for i in items], ["Game X released", "Patch Y notes"])
+        self.assertEqual(items[0]["link"], "https://ex.com/x")
+        self.assertEqual(items[0]["source"], "Src")
+
+    def test_atom(self):
+        """NEWS-01: Atom entries parsed with href link."""
+        items = parse_feed(ATOM, "A")
+        self.assertEqual(items[0]["title"], "Atom headline")
+        self.assertEqual(items[0]["link"], "https://ex.com/a")
+
+    def test_malformed_never_raises(self):
+        """NEWS-01: garbage XML returns [] without raising."""
+        self.assertEqual(parse_feed(b"<not xml", "bad"), [])
+        self.assertEqual(parse_feed(b"", "empty"), [])
+
+
+class TestDigest(unittest.TestCase):
+    def test_sanitized_and_capped(self):
+        """NEWS-02: headlines sanitized, item count capped."""
+        items = [{"title": "@everyone big news \x00", "link": "", "source": "S"} for _ in range(20)]
+        digest = render_digest(items, max_items=5)
+        self.assertEqual(digest.count("\n"), 4)  # 5 lines
+        self.assertNotIn("@everyone", digest)
+        self.assertNotIn("\x00", digest)
+
+
+class TestCollect(unittest.IsolatedAsyncioTestCase):
+    async def test_ssrf_skip_and_dedup(self):
+        """NEWS-03: guarded feed skipped, dup titles dropped, bad fetch survived."""
+
+        def guard(url):
+            return "refused" if "internal" in url else None
+
+        async def fetch(url):
+            if "boom" in url:
+                raise ValueError("boom")
+            return RSS  # same content from two feeds -> dedup
+
+        fetcher = NewsFetcher(guard, fetch)
+        feeds = [
+            ("https://a.com/feed", "A"),
+            ("https://internal/feed", "Internal"),  # SSRF-skipped
+            ("https://boom.com/feed", "Boom"),  # fetch fails
+            ("https://b.com/feed", "B"),  # same RSS -> dup titles dropped
+        ]
+        items = await fetcher.collect(feeds, per_feed=5)
+        titles = [i["title"] for i in items]
+        self.assertEqual(titles, ["Game X released", "Patch Y notes"])  # deduped, internal+boom skipped
+
+    async def test_per_feed_limit(self):
+        """NEWS-03: per-feed cap honored."""
+        fetcher = NewsFetcher(lambda u: None, AsyncMock(return_value=RSS))
+        items = await fetcher.collect([("https://a.com", "A")], per_feed=1)
+        self.assertEqual(len(items), 1)

tests/test_spec_url.py

@@ -91,6 +91,46 @@ class TestTextExtraction(unittest.TestCase):
         self.assertNotIn("x{}", text)
 
 
+class TestBodyReadCollectsAllChunks(unittest.IsolatedAsyncioTestCase):
+    async def test_get_reads_past_first_chunk(self):
+        """URL-05 regression: body arrives in many chunks; all are collected up to the cap."""
+        reader = URLReader(lambda: {}, None)
+        chunks = [b"<title>t</title>", b"<p>middle</p>", b"<p>end</p>"]
+
+        class FakeContent:
+            @staticmethod
+            async def iter_chunked(size):
+                for chunk in chunks:
+                    yield chunk
+
+        class FakeResp:
+            status = 200
+            headers = {}
+            url = "http://safe.example.com"
+            content = FakeContent()
+
+            async def __aenter__(self):
+                return self
+
+            async def __aexit__(self, *a):
+                return False
+
+            def raise_for_status(self):
+                pass
+
+        class FakeSession:
+            def get(self, url, allow_redirects=False):
+                return FakeResp()
+
+        with patch("fjerkroa_bot.url_reader.guard_url", return_value=None):
+            _, body = await reader._get(FakeSession(), "http://safe.example.com", 1000)
+        self.assertEqual(body, b"".join(chunks))
+
+        with patch("fjerkroa_bot.url_reader.guard_url", return_value=None):
+            _, body = await reader._get(FakeSession(), "http://safe.example.com", 20)
+        self.assertEqual(body, b"".join(chunks)[:20])
+
+
 class TestFetchSanitizes(unittest.IsolatedAsyncioTestCase):
     async def test_fetch_result_is_sanitized_and_capped(self):
         """URL-05: fetch output is length-capped and @everyone-neutralized."""

uv.lock

@@ -627,6 +627,7 @@ version = "3.0.0"
 source = { editable = "." }
 dependencies = [
     { name = "aiohttp" },
+    { name = "defusedxml" },
     { name = "discord-py" },
     { name = "openai" },
     { name = "requests" },
@@ -656,6 +657,7 @@ dev = [
 [package.metadata]
 requires-dist = [
     { name = "aiohttp", specifier = ">=3.12" },
+    { name = "defusedxml", specifier = ">=0.7" },
     { name = "discord-py", specifier = ">=2.5,<3" },
     { name = "openai", specifier = ">=2.45" },
     { name = "requests", specifier = ">=2.32" },