Compare commits
5 Commits
| Author | SHA1 | Date | |
|---|---|---|---|
| f8b9bc75ee | |||
| dc7864efe1 | |||
| 7fa23068a4 | |||
| da50395dc7 | |||
| ef62cb41a5 |
@@ -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
|
||||
|
||||
+50
-10
@@ -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):
|
||||
self._on_modified = on_modified
|
||||
"""Rename-safe config watch (CFG-05).
|
||||
|
||||
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)
|
||||
self.observer.schedule(self.file_handler, path=self.config_file, recursive=False)
|
||||
config_path = Path(self.config_file).resolve()
|
||||
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")
|
||||
|
||||
+17
-2
@@ -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:
|
||||
|
||||
@@ -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]]:
|
||||
"""Rows where every term appears in title or summary; optional source filter (NEWS-11)."""
|
||||
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/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 = ?"
|
||||
|
||||
@@ -20,7 +20,9 @@ DEFAULT_TASKGEN_INTERVAL_HOURS = 6.0
|
||||
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."
|
||||
"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]]
|
||||
|
||||
@@ -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.
|
||||
|
||||
@@ -61,3 +61,15 @@ 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.)
|
||||
|
||||
@@ -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`.
|
||||
|
||||
@@ -65,6 +65,55 @@ 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 TestTypingPacing(OpsBase):
|
||||
async def send_with(self, answer, factual, cps=30):
|
||||
if cps is not None:
|
||||
|
||||
@@ -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):
|
||||
|
||||
+34
-6
@@ -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()
|
||||
event.src_path = self.bot.config_file
|
||||
self.bot.on_config_file_modified(event)
|
||||
self.bot.on_config_file_changed()
|
||||
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()
|
||||
event.src_path = self.bot.config_file
|
||||
self.bot.on_config_file_modified(event)
|
||||
self.bot.on_config_file_changed()
|
||||
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))
|
||||
|
||||
Reference in New Issue
Block a user