Files
conjurer/communication_subroutine.py
T
gitea b13a8afa01
CI / integration (push) Failing after 2m23s
CI / compile (push) Failing after 1h53m43s
CI / unit (push) Failing after 1h53m32s
build / build (push) Failing after 1h54m2s
bot: queued AI query interface + librarian AI review of results
Two connected features.

1) AI query interface (via the comm layer). communication_subroutine gains an
AI_QUERY_Q, a submit_ai_query() in-process entry point, and an authed
POST /ai_query endpoint ({prompt, channel_id, request_type?, username?}). The
prompt is queued and answered asynchronously by a new tasks.loop worker in the
always-loaded AI cog (Events), which calls handle_response - so it runs on
whichever backend $gadaj_teraz currently selects (GPT or Claude) - and posts the
answer to the requested channel, chunked to Discord's limit. request_type "NONE"
(default) is a clean one-shot: no persona system prompt, no memory write. The
worker starts before the OpenAI guard in cog_load, so it also runs on a
Claude-only box; cog_unload cancels it.

2) Librarian AI review. New command $wyszukaj_z_recenzja mirrors
$wyszukaj_linki_do_dokumentow but sets ai_review=True on the QueryControl, which
rides the round-trip and is matched back by UUID. When the hits return,
check_data_q sends the raw list as before, then - if flagged - hands the same
list (already in Crossref-relevance order) plus the search phrase to the AI
queue for a weighted re-rank and per-source review, delivered to the same
channel. QueryControl gains an ai_review flag (default False, so the orphan path
and all existing callers are unaffected).

Confirmed separately (and noted in the docs): the DOI list the AI receives is
pre-sorted by Crossref relevance - the librarian pipeline only filters (drops
title-less items) and splits (in-db / not-in-db), never re-sorts, and relies on
insertion-ordered dicts (Py 3.7+).

Verified: /ai_query auth (401/200/400/open), submit_ai_query and the queued
dict shape, and the QueryControl flag - via a Flask test client and
tests/integration/test_ai_query_endpoint.py (5 tests, all pass; integration
suite 11 passed, the 3 failures are the pre-existing /clear_pr_pls musician
tests fixed on a separate branch). Full first-party compile clean.

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
2026-07-30 09:27:11 +00:00

328 lines
11 KiB
Python

import json
import logging
import os
import re
import threading
import time
from queue import Empty, Queue
from typing import Optional
from urllib import request as urequest
from flask import Flask, abort, jsonify, request
from waitress import serve
HOST_ADDRESS = os.getenv("CONJURER_DISCORD_HOST", "192.168.1.92")
PORT_ADDRESS = int(os.getenv("CONJURER_DISCORD_PORT", "5000"))
ICECAST_ADDRESS = os.getenv("CONJURER_ICECAST", "http://192.168.1.12:8000")
API_KEY = os.getenv("CONJURER_API_KEY")
OUT_COMM_Q = Queue()
IN_COMM_Q = Queue()
# AI request queue: prompts to be answered by the bot's own AI backend (whatever
# $gadaj_teraz currently points at). Drained by the AI cog's worker loop, which
# calls handle_response and delivers the answer to the requested channel. Fed
# either over HTTP (POST /ai_query) or in-process via submit_ai_query().
AI_QUERY_Q = Queue()
SRCHTITLE = re.compile(rb"StreamTitle=\\*(?P<title>[^;]*);").search
awaiting_q = []
incoming_q = Queue()
app = Flask(__name__)
def _authorize_request() -> None:
"""Reject inbound calls lacking the shared key (no-op if key is unset)."""
if API_KEY and request.headers.get("X-Conjurer-Api-Key") != API_KEY:
abort(401)
PREPPED_TRACKS = {
"requests": "",
"hit": "",
"all": "",
"priority": "",
"jingles": "",
"now_playing": "",
"next": "",
"meta": "",
}
logger = logging.getLogger("discord")
class QueryControl:
"""
This class `QueryControl` is used to manage queries with information about the author, UUID,
content, logger, context, and replies.
"""
def __init__(self, query_author, query_uuid, query_content, ctx, ai_review=False) -> None:
self.author = query_author
self.uuid = query_uuid
self.content = query_content
self.logger = logging.getLogger("discord")
self.stop = False
self.ctx = ctx
# When True, once the librarian returns hits, the DOI list + the search
# phrase are sent to the AI backend for a weighted-relevance re-rank and
# source review (see librarian_commands.check_data_q).
self.ai_review = ai_review
self.logger.info(
f"Created Query control for {self.author}, {self.uuid}: {self.content}"
)
self.replies = []
@app.route("/prepped_tracks", methods=["POST"])
def log_radio_tracks():
_authorize_request()
app.logger = logging.getLogger("discord")
app.logger.info(request)
record = json.loads(request.data)
app.logger.info(record)
if "next" in record[0]:
metadata = id3(ICECAST_ADDRESS)
PREPPED_TRACKS["now_playing"] = PREPPED_TRACKS["next"]
if metadata:
PREPPED_TRACKS["meta"] = (
metadata["name"]
+ " - "
+ metadata["title"]
+ "("
+ metadata["genre"]
+ ")"
)
else:
PREPPED_TRACKS["meta"] = "Nie znaju"
PREPPED_TRACKS[record[0]] = record[1]
app.logger.info("DATA RECEIVED")
return jsonify("SUCCESS")
@app.route("/conjurer", methods=["POST"])
def answer_external_command():
"""
The function `answer_external_command` logs the request data, loads the data as JSON, logs the
record, and then puts the record into an incoming queue before returning a success message.
:return: The function `answer_external_command()` is returning a JSON response with the message
"SUCCESS".
"""
_authorize_request()
logger = logging.getLogger("discord")
logger.info(request)
record = json.loads(request.data)
logger.info(record)
logger.info("DATA RECEIVED")
incoming_q.put(record)
return jsonify("SUCCESS")
def submit_ai_query(prompt, channel_id=None, request_type="NONE", username="conjurer", query_uuid=None):
"""Queue an AI prompt for the bot to answer with its configured backend.
In-process entry point (used by the librarian result handler). ``channel_id``
is the Discord channel the answer should be posted to; ``request_type`` is
passed through to handle_response ("NONE" keeps it a clean one-shot that does
not touch conversation memory).
"""
AI_QUERY_Q.put(
{
"uuid": query_uuid,
"prompt": prompt,
"channel_id": channel_id,
"request_type": request_type,
"username": username,
}
)
@app.route("/ai_query", methods=["POST"])
def ai_query():
"""Inbound AI query: queue a prompt to be answered by the bot's AI backend.
Payload: {"prompt": str, "channel_id": int, "request_type"?: str,
"username"?: str, "uuid"?: str}. The prompt is queued and answered
asynchronously by the AI cog's worker; the answer is posted to channel_id.
"""
_authorize_request()
logger = logging.getLogger("discord")
record = json.loads(request.data)
prompt = record.get("prompt", "")
if not prompt:
return jsonify(isError=True, message="missing 'prompt'", statusCode=400, data=[]), 400
submit_ai_query(
prompt=prompt,
channel_id=record.get("channel_id"),
request_type=record.get("request_type", "NONE"),
username=record.get("username", "external"),
query_uuid=record.get("uuid"),
)
logger.info("Queued AI query (qsize=%s)", AI_QUERY_Q.qsize())
return (
jsonify(isError=False, message="Queued", statusCode=200, data={"qsize": AI_QUERY_Q.qsize()}),
200,
)
@app.route("/conjurer", methods=["GET"])
def check_alive():
"""
The function "check_alive" returns a JSON response with the message "ALIVE" when the "/conjurer"
route is accessed via a GET request.
:return: The code snippet is a Flask route that listens for GET requests to the "/conjurer"
endpoint. When a GET request is made to this endpoint, the function check_alive() is called, which
returns a JSON response with the message "ALIVE".
"""
return jsonify("ALIVE")
def flask_debug():
"""
The `flask_debug` function starts a Flask application in debug mode without using the reloader.
Do not use for production for fucks sake.
"""
logger = logging.getLogger("discord")
logger.info("Attempt debug")
# trunk-ignore(bandit/B201)
app.run(debug=True, use_reloader=False, host=HOST_ADDRESS, port=PORT_ADDRESS)
def waitress_run():
"""
The `waitress_run` function serves the `app` on host "0.0.0.0"
and port 5000 using the Waitress WSGI server.
"""
logger = logging.getLogger("discord")
logger.info("Attempt waitress")
serve(app, host=HOST_ADDRESS, port=PORT_ADDRESS)
def scan_queue(stop_event: Optional[threading.Event] = None):
"""
The function `scan_queue` reads data from a queue, logs it, and appends it to another queue.
A bounded ``get(timeout=1)`` is used instead of a blocking ``get()`` so the
worker can observe ``stop_event`` and exit cleanly during shutdown.
:param stop_event: optional :class:`threading.Event`; when set the loop
stops at the next iteration.
"""
logger = logging.getLogger("discord")
while True:
if stop_event and stop_event.is_set():
logger.info("scan_queue: stop requested")
break
try:
data = OUT_COMM_Q.get(timeout=1)
except Empty:
continue
logger.info(data)
awaiting_q.append(data)
def scan_incoming(stop_event: Optional[threading.Event] = None):
"""
The `scan_incoming` function continuously checks for incoming data, processes it, and logs when data
is found.
:param stop_event: optional :class:`threading.Event`; when set the loop
stops at the next iteration.
"""
logger = logging.getLogger("discord")
while True:
if stop_event and stop_event.is_set():
logger.info("scan_incoming: stop requested")
break
try:
answer = incoming_q.get(block=False)
logger.info("DATA FOUND")
record_stored = False
for record in awaiting_q:
if record.uuid in answer.keys():
record_stored = True
record.stop = True
record.entries = answer[record.uuid]
IN_COMM_Q.put(record)
if not record_stored:
for key in answer.keys():
record = QueryControl("Orphaned", key, "Orphan", None)
record.stop = True
record.entries = answer[record.uuid]
IN_COMM_Q.put(record)
except Empty:
time.sleep(1)
def get_stream_title(tag: bytes) -> str:
title = ""
if m := SRCHTITLE(tag):
# decode, strip, unescape and remove surrounding quotes (may not even be the same type of quote)
title = m.group("title").decode("utf-8").strip().replace("\\", "")[1:-1]
return title
def id3(url: str) -> dict:
request = urequest.Request(url, headers={"Icy-MetaData": 1})
with urequest.urlopen(request) as resp:
metaint = int(resp.headers.get("icy-metaint", "-1"))
if metaint < 0:
return False
resp.read(
metaint
) # this isn't seekable so, arbitrarily read to the point we want
tagdata = dict(
site_url=resp.headers.get("icy-url"),
name=resp.headers.get("icy-name").title(),
genre=resp.headers.get("icy-genre").title(),
title=get_stream_title(resp.read(255)),
)
return tagdata
def comm_subroutine(stop_event: Optional[threading.Event] = None):
"""
The `comm_subroutine` function starts multiple threads to run different tasks concurrently.
Workers run as daemon threads and honour an optional ``stop_event`` so the
bot can shut the communication layer down cleanly instead of blocking
forever on ``join()``.
:param stop_event: optional :class:`threading.Event` shared with the caller
to coordinate a cooperative shutdown.
"""
logger = logging.getLogger("discord")
logger.setLevel(logging.DEBUG)
logger.info("Started comms")
threads = []
# NOTE: flask_debug is the dev server bound to the SAME host:port as
# waitress - running both kills the comm layer with 'address in use'.
# Enable it only INSTEAD of waitress_run, never alongside.
# threads.append(threading.Thread(target=flask_debug))
threads.append(threading.Thread(target=waitress_run, daemon=True))
threads.append(
threading.Thread(
target=scan_queue, kwargs={"stop_event": stop_event}, daemon=True
)
)
threads.append(
threading.Thread(
target=scan_incoming, kwargs={"stop_event": stop_event}, daemon=True
)
)
for worker in threads:
worker.start()
try:
while any(thread.is_alive() for thread in threads):
if stop_event and stop_event.is_set():
break
time.sleep(0.5)
finally:
if stop_event:
stop_event.set()
if __name__ == "__main__":
comm_subroutine()