smarter: factual-model routing (beh-10), fetch_url main-content extraction + 8k cap (url-08), get_weather via met.no (spec-016)

Makefile

@@ -1,6 +1,6 @@
 # Fjerkroa Bot Development Makefile (uv-managed)
 
-.PHONY: help install install-dev clean test test-cov test-fast lint format format-check type-check security-check audit trace check all-checks pre-commit run run-dev build ci
+.PHONY: deploy backup help install install-dev clean test test-cov test-fast lint format format-check type-check security-check audit trace check all-checks pre-commit run run-dev build ci
 
 # Default target
 help: ## Show this help message

fjerkroa_bot/ai_responder.py

@@ -105,6 +105,7 @@ class AIMessage(AIMessageBase):
         self.channel = channel
         self.direct = direct
         self.historise_question = historise_question
+        self.factual = False  # classifier verdict; may route to factual-model (BEH-10)
         self.vars = ["user", "message", "channel", "direct", "historise_question"]
 
 
@@ -340,6 +341,9 @@ class AIResponder(AIResponderBase):
         # Get the history limit from the configuration
         limit = self.config["history-limit"]
 
+        # Factual verdict routes this call to factual-model if configured (BEH-10)
+        self._factual = bool(getattr(message, "factual", False))
+
         # Check if a short path applies, return an empty AIResponse if it does
         if self.short_path(message, limit):
             await self._persist_history()

fjerkroa_bot/discord_bot.py

@@ -1,5 +1,6 @@
 import argparse
 import asyncio
+import fnmatch
 import logging
 import random
 import re
@@ -68,11 +69,41 @@ def split_answer(text: str, threshold: int, max_parts: int) -> list:
 
 
 class ConfigFileHandler(FileSystemEventHandler):
-    def __init__(self, on_modified):
+    """Rename-safe config watch (CFG-05).
-        self._on_modified = on_modified
 
+    Editors and tools save atomically — write a temp file, then rename it
+    over the target — which fires a *moved*/*created* event (not
+    *modified*) and swaps the inode, so watching the file directly goes
+    deaf after the first save. We watch the config's *directory* and react
+    to any event whose src or dest path is the config file.
+    """
+
+    def __init__(self, config_path: str, on_change):
+        self._config_path = str(Path(config_path).resolve())
+        self._on_change = on_change
+
+    def _hits_config(self, event) -> bool:
+        for attr in ("src_path", "dest_path"):
+            path = getattr(event, attr, "")
+            if path and str(Path(path).resolve()) == self._config_path:
+                return True
+        return False
+
+    def _dispatch(self, event):
+        if not event.is_directory and self._hits_config(event):
+            self._on_change()
+
+    # Only write/rename events — NOT on_opened/on_closed, whose read-opens
+    # (our own load_config re-reads the file) would otherwise feed back into
+    # a reload loop (CFG-05).
     def on_modified(self, event):
-        self._on_modified(event)
+        self._dispatch(event)
+
+    def on_created(self, event):
+        self._dispatch(event)
+
+    def on_moved(self, event):
+        self._dispatch(event)
 
 
 class FjerkroaBot(commands.Bot):
@@ -102,8 +133,10 @@ class FjerkroaBot(commands.Bot):
 
     def init_observer(self):
         self.observer = Observer()
-        self.file_handler = ConfigFileHandler(self.on_config_file_modified)
+        config_path = Path(self.config_file).resolve()
-        self.observer.schedule(self.file_handler, path=self.config_file, recursive=False)
+        self.file_handler = ConfigFileHandler(str(config_path), self.on_config_file_changed)
+        # Watch the directory, not the file — atomic saves replace the inode (CFG-05)
+        self.observer.schedule(self.file_handler, path=str(config_path.parent), recursive=False)
         self.observer.start()
 
     def init_aichannels(self):
@@ -415,12 +448,10 @@ class FjerkroaBot(commands.Bot):
             airesponder.image_cache.purge_message(str(message.id))  # IMG-14
         await airesponder.observe_event(message.author.name, "delete", f"deleted: {message.content}")
 
-    def on_config_file_modified(self, event):
+    def on_config_file_changed(self):
         # Runs on the watchdog observer thread — the swap itself is
         # scheduled onto the event loop so no request reads a
         # half-swapped config (CFG-04 / D9)
-        if event.src_path != self.config_file:
-            return
         new_config = self.load_config(self.config_file)
         if repr(new_config) == repr(self.config):
             return
@@ -451,7 +482,7 @@ class FjerkroaBot(commands.Bot):
             return fallback_channel
         if channel_name.startswith("#"):
             channel_name = channel_name[1:]
-        if not no_ignore and channel_name in self.config.get("ignore-channels", []):
+        if not no_ignore and self.channel_ignored(channel_name):
             return fallback_channel
         for guild in self.guilds:
             channel = discord.utils.get(guild.channels, name=channel_name)
@@ -464,8 +495,12 @@ class FjerkroaBot(commands.Bot):
             return str(channel.recipient.name)
         return str(channel.id) if isinstance(channel, DMChannel) else str(channel.name)
 
+    def channel_ignored(self, channel_name) -> bool:
+        """fnmatch patterns; plain names match exactly as before (BEH-09)."""
+        return any(fnmatch.fnmatchcase(str(channel_name), pattern) for pattern in self.config.get("ignore-channels", []))
+
     def ignore_message(self, channel_name, message):
-        return channel_name in self.config.get("ignore-channels", []) and not message.direct
+        return self.channel_ignored(channel_name) and not message.direct
 
     def log_message_action(self, action, message, channel_name):
         logging.info(f"{action} message {repr(message)} for channel {channel_name}")
@@ -491,6 +526,11 @@ class FjerkroaBot(commands.Bot):
 
     async def handle_message_through_responder(self, message):
         """Handle a message through the AI responder"""
+        # Ignored channels are fully silent — before the classifier gate,
+        # so no emoji reaction leaks either (BEH-09). DMs are never ignored.
+        if not isinstance(message.channel, DMChannel) and self.channel_ignored(self.get_channel_name(message.channel)):
+            self.log_message_action("ignore", message, self.get_channel_name(message.channel))
+            return
         message_content = str(message.content).strip()
         if message.reference and message.reference.resolved and isinstance(message.reference.resolved.content, str):
             reference_content = str(message.reference.resolved.content).replace("\n", "> \n")
@@ -661,6 +701,9 @@ class FjerkroaBot(commands.Bot):
         # Get the AI responder based on the channel name
         airesponder = self.get_ai_responder(channel_name)
 
+        # Classifier verdict rides along: factual questions may use factual-model (BEH-10)
+        message.factual = factual
+
         # Send the user message to the AI responder, with typing indicators.
         # A raised call = a broken API path (cf. the gpt-5.6 tools incident):
         # count it, alert staff at threshold, never crash the handler (OPS-16).

fjerkroa_bot/news.py

@@ -198,7 +198,12 @@ GET_NEWS_TOOL = {
     "parameters": {
         "type": "object",
         "properties": {
-            "topic": {"type": "string", "description": "Optional keywords to filter by, e.g. 'Nordland', 'football', 'weather'."},
+            "topic": {
+                "type": "string",
+                "description": "Optional filter: one or two keywords, in the language the feeds are written in "
+                "(e.g. Norwegian for Norwegian news: 'Nordland', 'fotball', 'trafikkulykke'). If nothing matches "
+                "exactly, related or recent items come back with a `note` saying so.",
+            },
             "source": {"type": "string", "description": "Optional source label, e.g. 'NRK', 'Aftenposten', 'Verden', 'Sport'."},
             "limit": {"type": "integer", "description": "How many items to return (default 10, max 30)."},
         },
@@ -220,8 +225,15 @@ def query_news(
     limit = max(1, min(int(limit or 10), 30))
     src = (str(source).strip() or None) if source else None
     terms = _news_terms(topic)
+    note = None
     try:
         rows = store.search_news(terms, limit, src) if terms else store.recent_news(limit, src)
+        if terms and not rows:  # NEWS-13: soft degradation, never empty-handed
+            rows = store.search_news(terms, limit, src, match_any=True)
+            note = "no item matches all keywords; showing items matching some of them"
+        if terms and not rows:
+            rows = store.recent_news(limit, src)
+            note = "nothing matches the topic; showing the newest stored items instead"
     except Exception as err:
         logging.warning(f"news: query failed: {err!r}")
         return {"error": "news lookup failed"}
@@ -234,7 +246,10 @@ def query_news(
         }
         for row in rows
     ]
-    return {"topic": topic or "", "source": src or "", "results": results}
+    payload = {"topic": topic or "", "source": src or "", "results": results}
+    if note:
+        payload["note"] = note
+    return payload
 
 
 def _open_store(config: Dict[str, Any]) -> Any:

fjerkroa_bot/openai_responder.py

@@ -17,6 +17,7 @@ from .leonardo_draw import LeonardoAIDrawMixIn
 from .news import GET_NEWS_TOOL, query_news
 from .quota import QuotaLedger
 from .url_reader import FETCH_URL_TOOL, URLReader
+from .weather import GET_WEATHER_TOOL, Weather
 from .websearch import DEFAULT_RESULTS as WEB_DEFAULT_RESULTS
 from .websearch import WEB_SEARCH_TOOL, WebSearch
 
@@ -170,6 +171,7 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
         self.codex = CodexSearch(lambda: self.config)
         # Web search (SPEC-015) via Exa; general "look it up" beyond fetch_url/news/codex
         self.web_search = WebSearch(lambda: self.config)
+        self.weather = Weather(lambda: self.config)
 
     def _available_tools(self) -> List[Dict[str, Any]]:
         """Assemble the function-tool list from every enabled provider (URL-01)."""
@@ -189,6 +191,8 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
             functions.append(GET_NEWS_TOOL)
         if self.web_search.enabled():  # WEB-01
             functions.append(WEB_SEARCH_TOOL)
+        if self.weather.enabled():  # WEA-01
+            functions.append(GET_WEATHER_TOOL)
         return functions
 
     async def _dispatch_tool(self, name: str, args: Dict[str, Any], author: str) -> Any:
@@ -219,6 +223,12 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
                 return {"error": "daily web search limit reached"}
             self.ledger._add(f"web:{author}", 1)
             return await self.web_search.search(str(args.get("query", "")), int(args.get("num_results", WEB_DEFAULT_RESULTS)))
+        if name == "get_weather":
+            per_user_cap = int(self.config.get("weather-daily-per-user", 30))
+            if self.ledger._get(f"weather:{author}") >= per_user_cap:  # WEA-04
+                return {"error": "daily weather lookup limit reached"}
+            self.ledger._add(f"weather:{author}", 1)
+            return await self.weather.forecast(args.get("location"))
         return await self._execute_igdb_function(name, args)
 
     async def draw_openai(self, description: str, count: int = 1) -> List[BytesIO]:
@@ -292,6 +302,8 @@ class OpenAIResponder(AIResponder, LeonardoAIDrawMixIn):
                 model = self.config["model-vision"]
             else:
                 messages[-1]["content"] = messages[-1]["content"][0]["text"]
+            if getattr(self, "_factual", False) and "factual-model" in self.config:
+                model = self.config["factual-model"]  # BEH-10: facts get the stronger tier
             if self._use_retry_model and "retry-model" in self.config:
                 model = self.config["retry-model"]
         except (KeyError, IndexError, TypeError) as e:

fjerkroa_bot/persistence.py

@@ -152,14 +152,27 @@ class PersistentStore:
             rows = conn.execute(sql, params).fetchall()
         return [{"source": r[0], "title": r[1], "link": r[2], "summary": r[3]} for r in rows]
 
-    def search_news(self, terms: List[str], limit: int = 20, source: Optional[str] = None) -> List[Dict[str, Any]]:
+    def search_news(self, terms: List[str], limit: int = 20, source: Optional[str] = None, match_any: bool = False) -> List[Dict[str, Any]]:
-        """Rows where every term appears in title or summary; optional source filter (NEWS-11)."""
+        """Rows where every term appears in title/summary/source; match_any ranks by how many terms hit (NEWS-11/13)."""
         params: List[Any] = []
         clauses = []
         for term in terms:
             clauses.append("(title LIKE ? OR summary LIKE ? OR source LIKE ?)")
             like = f"%{term}%"
             params += [like, like, like]
+        if match_any and clauses:
+            hits = " + ".join(clauses)
+            where = "hits > 0"
+            if source:
+                where += " AND source = ?"
+                params.append(source)
+            params.append(int(limit))
+            sql = (
+                f"SELECT source, title, link, summary FROM "  # nosec B608 - fixed templates; values parameterised
+                f"(SELECT id, source, title, link, summary, {hits} AS hits FROM news) "
+                f"WHERE {where} ORDER BY hits DESC, id DESC LIMIT ?"
+            )
+        else:
             where = " AND ".join(clauses) if clauses else "1=1"
             if source:
                 where = f"({where}) AND source = ?"

fjerkroa_bot/tasks.py

@@ -21,6 +21,8 @@ DEFAULT_BORENESS_PROMPT = (
     "A thought just occurred to you. Anchor it to something real you know — recent news (use get_news), a game "
     "releasing soon, the weather, or a regular you remember — not a generic musing. Share it briefly, in your own "
     "voice, as an observation, a gentle question, or a joke; never an advertisement. Read the room and stay in character. "
+    "Check your own recent posts in the history first: pick a subject you have not touched lately and a different form "
+    "than last time, and never open with a fixed label or heading — just start mid-thought."
 )
 
 ExecuteCallback = Callable[[str, str], Awaitable[None]]

fjerkroa_bot/url_reader.py

@@ -21,7 +21,7 @@ from .ai_responder import sanitize_external_text
 from .httpread import read_capped
 
 DEFAULT_MAX_BYTES = 2 * 1024 * 1024
-DEFAULT_MAX_CHARS = 6000
+DEFAULT_MAX_CHARS = 8000  # URL-08: budget goes to content now, not chrome
 DEFAULT_MAX_IMAGES = 2
 FETCH_TIMEOUT_S = 15
 MAX_REDIRECTS = 5
@@ -41,18 +41,37 @@ FETCH_URL_TOOL = {
 _META_REFRESH_URL = re.compile(r"url\s*=\s*['\"]?([^'\";\s]+)", re.I)
 
 
+_SKIP_TAGS = ("script", "style", "noscript", "svg", "nav", "header", "footer", "aside", "form", "select", "button")
+_BLOCK_TAGS = ("p", "li", "div", "section", "article", "td", "ul", "ol", "table", "h1", "h2", "h3", "h4", "h5", "h6")
+_LINK_DENSITY_MAX = 0.6  # boilerplate: block mostly link text ... (URL-08)
+_LINK_BLOCK_MAX_CHARS = 200  # ... AND short (menus, related lists); long linky paragraphs survive
+
+
 class _Extractor(HTMLParser):
     def __init__(self) -> None:
         super().__init__()
         self._skip = 0
-        self.parts: List[str] = []
+        self._links = 0
+        self._buf: List[str] = []
+        self._buf_link_chars = 0
+        self.blocks: List[Tuple[str, int]] = []  # (text, chars inside <a>)
         self.images: List[str] = []
         self.og_image: Optional[str] = None
         self.refresh_url: Optional[str] = None
 
+    def _flush(self) -> None:
+        text = " ".join(self._buf).strip()
+        if text:
+            self.blocks.append((text, self._buf_link_chars))
+        self._buf, self._buf_link_chars = [], 0
+
     def handle_starttag(self, tag: str, attrs) -> None:
-        if tag in ("script", "style", "noscript", "svg"):
+        if tag in _SKIP_TAGS:
             self._skip += 1
+        if tag == "a":
+            self._links += 1
+        if tag in _BLOCK_TAGS:
+            self._flush()
         attr = dict(attrs)
         src = attr.get("src")
         if tag == "img" and src:
@@ -67,12 +86,28 @@ class _Extractor(HTMLParser):
                 self.refresh_url = match.group(1)
 
     def handle_endtag(self, tag: str) -> None:
-        if tag in ("script", "style", "noscript", "svg") and self._skip > 0:
+        if tag in _SKIP_TAGS and self._skip > 0:
             self._skip -= 1
+        if tag == "a" and self._links > 0:
+            self._links -= 1
+        if tag in _BLOCK_TAGS:
+            self._flush()
 
     def handle_data(self, data: str) -> None:
         if self._skip == 0 and data.strip():
-            self.parts.append(data.strip())
+            self._buf.append(data.strip())
+            if self._links > 0:
+                self._buf_link_chars += len(data.strip())
+
+    def content_parts(self) -> List[str]:
+        """Blocks minus boilerplate: short blocks dominated by link text are chrome (URL-08)."""
+        self._flush()
+        out = []
+        for text, link_chars in self.blocks:
+            if link_chars / max(1, len(text)) > _LINK_DENSITY_MAX and len(text) < _LINK_BLOCK_MAX_CHARS:
+                continue
+            out.append(text)
+        return out
 
 
 def _ip_is_public(ip_str: str) -> bool:
@@ -162,7 +197,7 @@ class URLReader:
         return extractor
 
     def _to_text(self, html: str) -> str:
-        return re.sub(r"\s+\n", "\n", " ".join(self._extract(html).parts))
+        return re.sub(r"\s+\n", "\n", " ".join(self._extract(html).content_parts()))
 
     async def _ingest_images(self, html: str, base_url: str, channel: str, user: str) -> int:
         if self.image_cache is None:

fjerkroa_bot/weather.py

@@ -0,0 +1,111 @@
+"""Weather tool via MET Norway Locationforecast (SPEC-016).
+
+A `get_weather` function tool: both personas talk about weather (the
+sea over the skerries, rain on patch day) but had to guess it. The
+free api.met.no compact forecast grounds it. Locations are
+host-configured `[name, lat, lon]` entries — the model picks by name
+and never supplies coordinates or URLs, so there is no SSRF surface.
+"""
+
+import logging
+from typing import Any, Callable, Dict, List, Optional, Tuple
+
+import aiohttp
+
+from .ai_responder import sanitize_external_text
+
+MET_COMPACT_URL = "https://api.met.no/weatherapi/locationforecast/2.0/compact"
+USER_AGENT = "fjerkroa-discord-bot/3 (https://fjerkroa.no)"
+FETCH_TIMEOUT_S = 15
+FORECAST_POINT_INDICES = (6, 12, 24)  # hourly series: ~6h/12h/24h ahead
+
+GET_WEATHER_TOOL = {
+    "name": "get_weather",
+    "description": "Current weather and a short forecast for the configured local places. Use this whenever weather comes "
+    "up in conversation — never guess or invent weather. Returns current temperature (°C), wind (m/s) and conditions, "
+    "plus a few forecast points.",
+    "parameters": {
+        "type": "object",
+        "properties": {
+            "location": {"type": "string", "description": "Place name to look up; omit for the default (first configured) place."},
+        },
+        "required": [],
+    },
+}
+
+
+def _reduce(data: Any, name: str) -> Dict[str, Any]:
+    """Compact MET timeseries -> {location, now, forecast[]} (WEA-02). Nothing else reaches the prompt."""
+    series = data.get("properties", {}).get("timeseries", []) if isinstance(data, dict) else []
+    if not series:
+        return {"error": "weather data unavailable"}
+
+    def point(entry: Dict[str, Any]) -> Dict[str, Any]:
+        details = entry.get("data", {}).get("instant", {}).get("details", {})
+        hour = entry.get("data", {}).get("next_1_hours", {}) or entry.get("data", {}).get("next_6_hours", {})
+        out: Dict[str, Any] = {
+            "time": str(entry.get("time", "")),
+            "temp_c": details.get("air_temperature"),
+            "wind_ms": details.get("wind_speed"),
+        }
+        symbol = hour.get("summary", {}).get("symbol_code")
+        if symbol:
+            out["conditions"] = str(symbol)
+        precip = hour.get("details", {}).get("precipitation_amount")
+        if precip is not None:
+            out["precip_mm"] = precip
+        return out
+
+    forecast = [point(series[i]) for i in FORECAST_POINT_INDICES if i < len(series)]
+    return {"location": sanitize_external_text(name, 80), "now": point(series[0]), "forecast": forecast}
+
+
+class Weather:
+    def __init__(self, config_getter: Callable[[], Dict[str, Any]]) -> None:
+        self._config = config_getter
+
+    def _locations(self) -> List[Tuple[str, float, float]]:
+        out: List[Tuple[str, float, float]] = []
+        for entry in self._config().get("weather-locations", []):
+            try:
+                name, lat, lon = entry[0], float(entry[1]), float(entry[2])
+                out.append((str(name), lat, lon))
+            except (TypeError, ValueError, IndexError):
+                logging.warning(f"weather: bad location entry {entry!r}")
+        return out
+
+    def enabled(self) -> bool:
+        return bool(self._config().get("enable-weather", False)) and bool(self._locations())
+
+    def _pick(self, location: Optional[str]) -> Optional[Tuple[str, float, float]]:
+        """Case-insensitive substring match; unknown/absent = first configured (WEA-03)."""
+        entries = self._locations()
+        if not entries:
+            return None
+        wanted = (location or "").strip().casefold()
+        if wanted:
+            for entry in entries:
+                if wanted in entry[0].casefold():
+                    return entry
+        return entries[0]
+
+    async def _fetch_json(self, lat: float, lon: float) -> Any:
+        timeout = aiohttp.ClientTimeout(total=FETCH_TIMEOUT_S)
+        params = {"lat": f"{lat:.4f}", "lon": f"{lon:.4f}"}
+        async with aiohttp.ClientSession(timeout=timeout, headers={"User-Agent": USER_AGENT}) as session:
+            async with session.get(MET_COMPACT_URL, params=params) as response:
+                response.raise_for_status()
+                return await response.json()
+
+    async def forecast(self, location: Optional[str] = None) -> Dict[str, Any]:
+        """Return a compact forecast, or an error dict — never raise (WEA-04)."""
+        picked = self._pick(location)
+        if picked is None:
+            return {"error": "weather unavailable: no locations configured"}
+        name, lat, lon = picked
+        try:
+            data = await self._fetch_json(lat, lon)
+        except Exception as err:
+            logging.warning(f"weather fetch failed: {err!r}")
+            return {"error": "weather lookup failed"}
+        return _reduce(data, name)

specs/SPEC-008-config.md

@@ -31,3 +31,16 @@ and all responder `.config` references is scheduled onto the event
 loop (`call_soon_threadsafe`), so no request ever reads a
 half-swapped config (D9). Before the loop runs (startup), the swap
 applies directly — there are no concurrent readers yet.
+
+### CFG-05 — Hot-reload is rename-safe (coverage: test)
+
+The watcher observes the config file's **directory**, not the file, and
+reacts to a **modified, created, or moved** event whose source or
+destination path is the config file. This catches atomic saves — write
+a temp file, then rename it over the target — which replace the inode
+and fire a move/create rather than a modify; watching the file directly
+would go deaf after the first such save. Open/close events are
+deliberately not handled: reloading re-opens the file to read it, so
+reacting to opens would feed back into an endless reload loop. Events
+for other files in the directory, and directory events themselves, are
+ignored.

specs/SPEC-010-behavior.md

@@ -61,3 +61,24 @@ Within `quiet-hours = "HH:MM-HH:MM"` (host-local, may wrap midnight)
 `bot_initiated_allowed()` is false: no boreness, later no scheduler
 posts. Replies to users stay unaffected — a guest asking at 23:30
 still gets an answer.
+
+### BEH-09 — Ignored channels are fully silent (coverage: test)
+
+Channels matching `ignore-channels` get neither replies nor
+classifier emoji reactions: the message handler returns before the
+classifier gate, so no model call, no reaction, no history entry.
+Entries are fnmatch patterns (`todo*` matches `todo`, `todo-lists`);
+plain names keep matching exactly as before. DMs are never ignored.
+`channel_by_name` resolution honors the same patterns. (Previously
+the ignore check sat only in `respond()`, after the classifier —
+emoji reactions leaked into ignored channels, and matching was
+exact-name only.)
+
+### BEH-10 — Factual questions may use a stronger model (coverage: test)
+
+With `factual-model` configured, a message the classifier tagged
+`factual` (BEH-05) is answered by that model instead of `model` —
+opening hours, release dates, news lookups get the stronger tier
+while small talk stays on the cheap default. Unset = no change. The
+`retry-model` override still wins on retry, and vision inputs keep
+using `model-vision`.

specs/SPEC-011-url-reading.md

@@ -58,3 +58,14 @@ Each fetch increments a per-user daily counter; over
 `url-daily-per-user` (default 20) `fetch_url` refuses with an error
 result. The budget gate (SAF-04) still applies to the surrounding
 model calls.
+
+### URL-08 — Main-content extraction (coverage: test)
+
+`fetch_url` text drops page chrome: content inside
+`nav`/`header`/`footer`/`aside`/`form`/`select`/`button` is skipped
+like scripts, and text blocks dominated by link text (over 60 % of a
+block's characters inside `<a>` and the block shorter than 200 chars
+— menus, related-article lists, tag clouds) are treated as
+boilerplate and removed. Body paragraphs with inline links survive.
+The default `url-max-chars` cap rises to 8000 now that the budget is
+spent on content, not chrome.

specs/SPEC-013-news.md

@@ -98,3 +98,14 @@ Each `get_news` call increments a per-user daily counter; over
 `news-daily-per-user` (default 30) the tool refuses with an error
 result without touching the store. The budget gate (SAF-04) still
 applies to the surrounding model calls.
+
+### NEWS-13 — Topic misses degrade softly, never empty-handed (coverage: test)
+
+A `topic` whose AND-match (NEWS-11) finds nothing falls back to an
+any-term match, ranked by how many keywords hit (ties: newest first);
+if that too is empty, the newest stored items are returned instead.
+Both fallbacks set a `note` field naming the degradation so the model
+can answer honestly ("nothing on that exactly, but…"). A model
+passing a multi-word or wrong-language topic (the live
+`"Nordland road accident"` → `[]` case) thus still gets usable
+context. Exact matches return no `note`.

specs/SPEC-016-weather.md

@@ -0,0 +1,35 @@
+# SPEC-016 — Weather tool (get_weather)
+
+Both personas talk about weather (the sea over the skerries, rain on
+patch day) but had to guess it. `get_weather` grounds that in the
+free MET Norway Locationforecast API (api.met.no, User-Agent
+required, no key). Locations are host-configured coordinates — the
+model picks by name, it never supplies raw URLs, so there is no SSRF
+surface (one fixed API host).
+
+### WEA-01 — Tool offered only when configured (coverage: test)
+
+The chat call's tools include `get_weather` only when
+`enable-weather` is true AND `weather-locations` (a list of
+`[name, lat, lon]` entries) is non-empty. Otherwise it is absent.
+
+### WEA-02 — Compact sanitized forecast (coverage: test)
+
+The tool reduces the MET compact timeseries to: the named location,
+current conditions (temperature °C, wind m/s, symbol), and a small
+set of forecast points (next hours / tomorrow) with temperature,
+symbol and precipitation. Location names pass
+`sanitize_external_text`; numbers are numbers. Nothing else from the
+API response reaches the prompt.
+
+### WEA-03 — Location matched by name, defaults to first (coverage: test)
+
+The `location` argument matches configured entries
+case-insensitively by substring; no or unknown location = the first
+configured entry. Coordinates never come from the model.
+
+### WEA-04 — Errors return, never raise; calls are metered (coverage: test)
+
+API/network failures return an `{error}` dict (the responder keeps
+running). Each call counts against a per-user daily cap
+(`weather-daily-per-user`, default 30) like the other tools.

tests/test_spec_beh.py

@@ -65,6 +65,88 @@ class TestClassifierGate(ClassifierGateBase):
         self.bot.respond.assert_not_awaited()
 
 
+class TestIgnoredChannels(ClassifierGateBase):
+    def ignored_msg(self, channel_name):
+        message = self.public_msg("hello there")
+        message.channel.name = channel_name
+        message.add_reaction = AsyncMock()
+        return message
+
+    async def test_pattern_match_suppresses_reaction_and_reply(self):
+        """BEH-09: fnmatch pattern hit -> no classifier call, no emoji, no reply."""
+        self.gate_setup({"reply": False, "factual": False, "emoji": "👍"})
+        self.bot.config["ignore-channels"] = ["todo*"]
+        message = self.ignored_msg("todo-lists")
+        await self.bot.on_message(message)
+        self.bot.airesponder.classify.assert_not_awaited()
+        message.add_reaction.assert_not_awaited()
+        self.bot.respond.assert_not_awaited()
+
+    async def test_exact_name_still_matches(self):
+        """BEH-09: plain names keep working as exact matches."""
+        self.gate_setup({"reply": True, "factual": False, "emoji": None})
+        self.bot.config["ignore-channels"] = ["blengon"]
+        await self.bot.on_message(self.ignored_msg("blengon"))
+        self.bot.respond.assert_not_awaited()
+
+    async def test_non_matching_channel_passes(self):
+        """BEH-09: unmatched channels reach the responder as before."""
+        self.gate_setup({"reply": True, "factual": False, "emoji": None})
+        self.bot.config["ignore-channels"] = ["todo*"]
+        await self.bot.on_message(self.ignored_msg("chat"))
+        self.bot.respond.assert_awaited_once()
+
+    async def test_dm_never_ignored(self):
+        """BEH-09: a DM whose recipient name matches a pattern is still answered."""
+        self.gate_setup({"reply": True, "factual": False, "emoji": None})
+        self.bot.config["ignore-channels"] = ["todo*"]
+        message = self.public_msg("hei bot")
+        message.channel = MagicMock(spec=DMChannel)
+        message.channel.recipient = MagicMock()
+        message.channel.recipient.name = "todo-fan"
+        await self.bot.on_message(message)
+        self.bot.respond.assert_awaited_once()
+
+    def test_channel_by_name_honors_patterns(self):
+        """BEH-09: channel_by_name resolution skips pattern-ignored channels."""
+        self.bot.config["ignore-channels"] = ["todo*"]
+        fallback = MagicMock(spec=TextChannel)
+        self.assertIs(self.bot.channel_by_name("todo-lists", fallback), fallback)
+
+
+class TestFactualModel(unittest.IsolatedAsyncioTestCase):
+    async def _model_used(self, config, factual):
+        from .test_spec_structured import ok_result
+
+        responder = OpenAIResponder(dict({"openai-token": "t", "model": "cheap", "system": "s", "history-limit": 5}, **config), "chat")
+        responder._factual = factual
+        with patch("fjerkroa_bot.openai_responder.openai_chat", new_callable=AsyncMock) as chat_mock:
+            chat_mock.return_value = ok_result()
+            await responder.chat([{"role": "user", "content": "hi"}], 10)
+        return chat_mock.await_args.kwargs["model"]
+
+    async def test_factual_uses_stronger_model(self):
+        """BEH-10: factual verdict + factual-model config -> stronger tier."""
+        self.assertEqual(await self._model_used({"factual-model": "strong"}, True), "strong")
+
+    async def test_factual_without_config_stays_default(self):
+        """BEH-10: no factual-model config -> default model, no behavior change."""
+        self.assertEqual(await self._model_used({}, True), "cheap")
+
+    async def test_small_talk_stays_default(self):
+        """BEH-10: non-factual messages stay on the cheap default."""
+        self.assertEqual(await self._model_used({"factual-model": "strong"}, False), "cheap")
+
+    async def test_send_reads_flag_from_message(self):
+        """BEH-10: send() picks the factual flag off the AIMessage."""
+        responder = FakeModelResponder({"system": "s", "history-limit": 5}, "chat")
+        responder.scripted = [envelope(answer="x", answer_needed=True)]
+        message = AIMessage("alice", "opening hours?", "chat")
+        message.factual = True
+        await responder.send(message)
+        self.assertTrue(responder._factual)
+
+
 class TestTypingPacing(OpsBase):
     async def send_with(self, answer, factual, cps=30):
         if cps is not None:

tests/test_spec_news.py

@@ -303,6 +303,26 @@ class TestQueryNews(NewsStoreBase):
         self.assertGreaterEqual(len(query_news(self.store, limit=0)["results"]), 1)
         self.assertIn("error", query_news(None))
 
+    def test_exact_match_has_no_note(self):
+        """NEWS-13: a direct AND-match returns without a note field."""
+        self.seed()
+        self.assertNotIn("note", query_news(self.store, topic="storm"))
+
+    def test_partial_match_falls_back_ranked(self):
+        """NEWS-13: AND-miss -> any-term match, most keyword hits first, with a note."""
+        self.seed()
+        res = query_news(self.store, topic="Nordland road accident")
+        self.assertEqual(res["results"][0]["title"], "Nordland storm")
+        self.assertIn("note", res)
+
+    def test_no_match_falls_back_to_recent(self):
+        """NEWS-13: nothing matches any term -> newest items + note, never empty-handed."""
+        self.seed()
+        res = query_news(self.store, topic="quantum blockchain")
+        self.assertTrue(res["results"])
+        self.assertEqual(res["results"][0]["title"], "Sport result")  # newest first
+        self.assertIn("note", res)
+
 
 class TestNewsTool(unittest.IsolatedAsyncioTestCase):
     def setUp(self):

tests/test_spec_per.py

@@ -120,9 +120,7 @@ class TestConfigReloadRace(TestBotBase):
         new_config["history-limit"] = 99
         self.bot.load_config = lambda path: new_config
         self.bot.loop = MagicMock()
-        event = MagicMock()
+        self.bot.on_config_file_changed()
-        event.src_path = self.bot.config_file
-        self.bot.on_config_file_modified(event)
         self.bot.loop.call_soon_threadsafe.assert_called_once()
         apply_fn = self.bot.loop.call_soon_threadsafe.call_args.args[0]
         apply_fn()
@@ -137,7 +135,37 @@ class TestConfigReloadRace(TestBotBase):
         loop = MagicMock()
         loop.call_soon_threadsafe.side_effect = RuntimeError("no running loop")
         self.bot.loop = loop
-        event = MagicMock()
+        self.bot.on_config_file_changed()
-        event.src_path = self.bot.config_file
-        self.bot.on_config_file_modified(event)
         self.assertEqual(self.bot.config["history-limit"], 42)
+
+
+class TestConfigReloadRenameSafe(unittest.TestCase):
+    def test_atomic_rename_and_modify_trigger_reload(self):
+        """CFG-05: a modified OR a renamed-into-place config fires the reload; unrelated files do not."""
+        from fjerkroa_bot.discord_bot import ConfigFileHandler
+
+        with tempfile.TemporaryDirectory() as tmp:
+            config = Path(tmp) / "kroa.toml"
+            config.write_text("x = 1\n")
+            hits = []
+            handler = ConfigFileHandler(str(config), lambda: hits.append(1))
+
+            def evt(is_dir=False, src=None, dest=None):
+                event = MagicMock()
+                event.is_directory = is_dir
+                event.src_path = src if src is not None else ""
+                event.dest_path = dest if dest is not None else ""
+                return event
+
+            handler.on_modified(evt(src=str(config)))  # in-place modify
+            handler.on_moved(evt(src=str(Path(tmp) / "kroa.toml.tmp"), dest=str(config)))  # atomic rename over
+            handler.on_created(evt(src=str(config)))  # write-new
+            self.assertEqual(len(hits), 3)
+
+            handler.on_modified(evt(src=str(Path(tmp) / "other.txt")))  # unrelated file
+            handler.on_modified(evt(is_dir=True, src=str(config)))  # directory event
+            self.assertEqual(len(hits), 3)  # neither fired
+
+            # open/close of the config (our own load_config re-reads) must NOT be handled — else a reload loop.
+            self.assertNotIn("on_opened", vars(ConfigFileHandler))
+            self.assertNotIn("on_closed", vars(ConfigFileHandler))

tests/test_spec_url.py

@@ -149,6 +149,31 @@ class TestTextExtraction(unittest.TestCase):
         self.assertNotIn("evil", text)
         self.assertNotIn("x{}", text)
 
+    def test_chrome_and_link_boilerplate_dropped(self):
+        """URL-08: nav/header/footer skipped; short link-dominated blocks (menus, related lists) removed."""
+        reader = URLReader(lambda: {}, None)
+        html = (
+            "<html><body>"
+            "<nav><a href='/a'>Home</a> <a href='/b'>Games</a></nav>"
+            "<header><a href='/login'>Login</a></header>"
+            "<ul><li><a href='/1'>Related article one</a></li><li><a href='/2'>Related article two</a></li></ul>"
+            "<article><p>The pop-up event runs from August 4 in Shibuya, with details "
+            "<a href='/x'>on the official page</a> for anyone attending the exhibition.</p></article>"
+            "<footer><a href='/imprint'>Imprint</a></footer>"
+            "</body></html>"
+        )
+        text = reader._to_text(html)
+        self.assertIn("pop-up event", text)
+        self.assertIn("on the official page", text)  # inline link in a real paragraph survives
+        for chrome in ("Home", "Login", "Related article one", "Imprint"):
+            self.assertNotIn(chrome, text)
+
+    def test_default_cap_is_8000(self):
+        """URL-08: the default url-max-chars budget is 8000."""
+        from fjerkroa_bot.url_reader import DEFAULT_MAX_CHARS
+
+        self.assertEqual(DEFAULT_MAX_CHARS, 8000)
+
 
 class TestBodyReadCollectsAllChunks(unittest.IsolatedAsyncioTestCase):
     async def test_get_reads_past_first_chunk(self):

tests/test_spec_weather.py

@@ -0,0 +1,120 @@
+"""Unit coverage for SPEC-016 weather tool (WEA-01..04)."""
+
+import unittest
+from unittest.mock import AsyncMock, patch
+
+from fjerkroa_bot.openai_responder import OpenAIResponder
+from fjerkroa_bot.weather import GET_WEATHER_TOOL, Weather, _reduce
+
+CONFIG = {"openai-token": "t", "model": "m", "system": "s", "history-limit": 5}
+LOCATIONS = [["Sleneset", 66.58, 12.68], ["Berlin", 52.52, 13.41]]
+
+MET_DATA = {
+    "properties": {
+        "timeseries": [
+            {
+                "time": f"2026-07-17T{10 + i if 10 + i < 24 else 10 + i - 24:02d}:00:00Z",
+                "data": {
+                    "instant": {"details": {"air_temperature": 14.0 + i, "wind_speed": 5.0}},
+                    "next_1_hours": {"summary": {"symbol_code": "lightrain"}, "details": {"precipitation_amount": 0.3}},
+                },
+            }
+            for i in range(30)
+        ]
+    }
+}
+
+
+def _tool_names(responder):
+    return [f["name"] for f in responder._available_tools()]
+
+
+class TestToolOffered(unittest.TestCase):
+    def test_gate_needs_flag_and_locations(self):
+        """WEA-01: get_weather offered only with enable-weather AND locations."""
+        self.assertNotIn("get_weather", _tool_names(OpenAIResponder(CONFIG, "chat")))
+        flag_only = OpenAIResponder(dict(CONFIG, **{"enable-weather": True}), "chat")
+        self.assertNotIn("get_weather", _tool_names(flag_only))
+        on = OpenAIResponder(dict(CONFIG, **{"enable-weather": True, "weather-locations": LOCATIONS}), "chat")
+        self.assertIn("get_weather", _tool_names(on))
+        self.assertEqual(GET_WEATHER_TOOL["name"], "get_weather")
+
+
+class TestReduce(unittest.TestCase):
+    def test_compact_shape(self):
+        """WEA-02: now + few forecast points; temperature/wind/conditions/precip only."""
+        out = _reduce(MET_DATA, "Sleneset")
+        self.assertEqual(out["location"], "Sleneset")
+        self.assertEqual(out["now"]["temp_c"], 14.0)
+        self.assertEqual(out["now"]["wind_ms"], 5.0)
+        self.assertEqual(out["now"]["conditions"], "lightrain")
+        self.assertEqual(out["now"]["precip_mm"], 0.3)
+        self.assertEqual(len(out["forecast"]), 3)  # +6h, +12h, +24h
+        self.assertEqual(out["forecast"][0]["temp_c"], 20.0)
+        self.assertNotIn("error", out)
+
+    def test_location_name_sanitized_and_empty_series(self):
+        """WEA-02: name passes sanitizer; empty timeseries -> error dict."""
+        out = _reduce(MET_DATA, "@everyone town")
+        self.assertNotIn("@everyone", out["location"])
+        self.assertIn("error", _reduce({"properties": {"timeseries": []}}, "x"))
+
+
+class TestLocationPick(unittest.TestCase):
+    def setUp(self):
+        self.weather = Weather(lambda: {"enable-weather": True, "weather-locations": LOCATIONS})
+
+    def test_substring_case_insensitive(self):
+        """WEA-03: case-insensitive substring match."""
+        self.assertEqual(self.weather._pick("berlin")[0], "Berlin")
+        self.assertEqual(self.weather._pick("slen")[0], "Sleneset")
+
+    def test_unknown_or_absent_defaults_to_first(self):
+        """WEA-03: unknown/absent location -> first configured entry."""
+        self.assertEqual(self.weather._pick(None)[0], "Sleneset")
+        self.assertEqual(self.weather._pick("Atlantis")[0], "Sleneset")
+
+    def test_bad_entries_skipped(self):
+        """WEA-03: malformed location entries are ignored, not fatal."""
+        weather = Weather(lambda: {"enable-weather": True, "weather-locations": [["broken"], ["OK", 1.0, 2.0]]})
+        self.assertEqual(weather._pick(None)[0], "OK")
+
+
+class TestForecast(unittest.IsolatedAsyncioTestCase):
+    async def test_error_returned_not_raised(self):
+        """WEA-04: network failure -> {error}, never an exception."""
+        weather = Weather(lambda: {"enable-weather": True, "weather-locations": LOCATIONS})
+        with patch.object(Weather, "_fetch_json", new_callable=AsyncMock, side_effect=RuntimeError("boom")):
+            out = await weather.forecast("Berlin")
+        self.assertIn("error", out)
+
+    async def test_forecast_happy_path(self):
+        """WEA-02/03: full flow with mocked API."""
+        weather = Weather(lambda: {"enable-weather": True, "weather-locations": LOCATIONS})
+        with patch.object(Weather, "_fetch_json", new_callable=AsyncMock, return_value=MET_DATA):
+            out = await weather.forecast("berlin")
+        self.assertEqual(out["location"], "Berlin")
+        self.assertEqual(out["now"]["temp_c"], 14.0)
+
+
+class TestMetering(unittest.IsolatedAsyncioTestCase):
+    async def test_daily_cap(self):
+        """WEA-04: per-user daily cap refuses beyond weather-daily-per-user."""
+        import tempfile
+
+        with tempfile.TemporaryDirectory() as tmp:
+            config = dict(
+                CONFIG,
+                **{
+                    "enable-weather": True,
+                    "weather-locations": LOCATIONS,
+                    "weather-daily-per-user": 1,
+                    "history-directory": tmp,
+                },
+            )
+            responder = OpenAIResponder(config, "chat")
+            with patch.object(Weather, "_fetch_json", new_callable=AsyncMock, return_value=MET_DATA):
+                first = await responder._dispatch_tool("get_weather", {}, "alice")
+                second = await responder._dispatch_tool("get_weather", {}, "alice")
+        self.assertNotIn("error", first)
+        self.assertIn("error", second)