Oleksandr Kozachuk
380 lines
15 KiB
Python
380 lines
15 KiB
Python
import asyncio
|
||
import json
|
||
import logging
|
||
import os
|
||
import pickle
|
||
import random
|
||
import re
|
||
import time
|
||
from functools import lru_cache, wraps
|
||
from io import BytesIO
|
||
from pathlib import Path
|
||
from pprint import pformat
|
||
from typing import Any, Dict, List, Optional, Tuple, Union
|
||
|
||
from .memory import MemoryManager
|
||
from .persistence import PersistentStore
|
||
|
||
|
||
def pp(*args, **kw):
|
||
if "width" not in kw:
|
||
kw["width"] = 300
|
||
return pformat(*args, **kw)
|
||
|
||
|
||
@lru_cache(maxsize=300)
|
||
def parse_json(content: str) -> Dict:
|
||
# Strict JSON only — model output is schema-enforced (ENV-18/19),
|
||
# history entries are json.dumps products.
|
||
return json.loads(content.strip())
|
||
|
||
|
||
def sanitize_external_text(text: str, max_len: int = 4000) -> str:
|
||
"""Neutralize attacker-influenced text before it enters a prompt (SAF-03)."""
|
||
text = re.sub(r"[\x00-\x08\x0b\x0c\x0e-\x1f\x7f]", "", text)
|
||
text = text.replace("@everyone", "@everyone").replace("@here", "@here")
|
||
return text[:max_len]
|
||
|
||
|
||
def exponential_backoff(base=2, max_delay=60, factor=1, jitter=0.1, max_attempts=None):
|
||
"""Generate sleep intervals for exponential backoff with jitter.
|
||
|
||
Args:
|
||
base: Base of the exponentiation operation
|
||
max_delay: Maximum delay
|
||
factor: Multiplication factor for each increase in backoff
|
||
jitter: Additional randomness range to prevent thundering herd problem
|
||
|
||
Yields:
|
||
Delay for backoff as a floating point number.
|
||
"""
|
||
attempt = 0
|
||
while True:
|
||
sleep = min(max_delay, factor * base**attempt)
|
||
jitter_amount = jitter * sleep
|
||
sleep += random.uniform(-jitter_amount, jitter_amount)
|
||
yield sleep
|
||
attempt += 1
|
||
if max_attempts is not None and attempt > max_attempts:
|
||
raise RuntimeError("Max attempts reached in exponential backoff.")
|
||
|
||
|
||
def async_cache_to_file(filename):
|
||
cache_file = Path(filename)
|
||
cache = None
|
||
if cache_file.exists():
|
||
try:
|
||
with cache_file.open("rb") as fd:
|
||
cache = pickle.load(fd)
|
||
except Exception:
|
||
cache = {}
|
||
|
||
def decorator(func):
|
||
@wraps(func)
|
||
async def wrapper(*args, **kwargs):
|
||
if cache is None:
|
||
return await func(*args, **kwargs)
|
||
key = json.dumps((func.__name__, list(args[1:]), kwargs), sort_keys=True)
|
||
if key in cache:
|
||
return cache[key]
|
||
result = await func(*args, **kwargs)
|
||
cache[key] = result
|
||
with cache_file.open("wb") as fd:
|
||
pickle.dump(cache, fd)
|
||
return result
|
||
|
||
return wrapper
|
||
|
||
return decorator
|
||
|
||
|
||
class AIMessageBase(object):
|
||
def __init__(self) -> None:
|
||
self.vars: List[str] = []
|
||
|
||
def __str__(self) -> str:
|
||
return json.dumps({k: v for k, v in vars(self).items() if k in self.vars})
|
||
|
||
|
||
class AIMessage(AIMessageBase):
|
||
def __init__(self, user: str, message: str, channel: str = "chat", direct: bool = False, historise_question: bool = True) -> None:
|
||
self.user = user
|
||
self.message = message
|
||
self.urls: Optional[List[str]] = None
|
||
self.channel = channel
|
||
self.direct = direct
|
||
self.historise_question = historise_question
|
||
self.vars = ["user", "message", "channel", "direct", "historise_question"]
|
||
|
||
|
||
class AIResponse(AIMessageBase):
|
||
def __init__(
|
||
self,
|
||
answer: Optional[str],
|
||
answer_needed: bool,
|
||
channel: Optional[str],
|
||
staff: Optional[str],
|
||
picture: Optional[str],
|
||
picture_edit: bool,
|
||
hack: bool,
|
||
) -> None:
|
||
self.answer = answer
|
||
self.answer_needed = answer_needed
|
||
self.channel = channel
|
||
self.staff = staff
|
||
self.picture = picture
|
||
self.picture_count = 1
|
||
self.picture_edit = picture_edit
|
||
self.hack = hack
|
||
self.vars = ["answer", "answer_needed", "channel", "staff", "picture", "hack"]
|
||
|
||
|
||
class AIResponderBase(object):
|
||
def __init__(self, config: Dict[str, Any], channel: Optional[str] = None) -> None:
|
||
super().__init__()
|
||
self.config = config
|
||
self.channel = channel if channel is not None else "system"
|
||
|
||
|
||
class AIResponder(AIResponderBase):
|
||
def __init__(self, config: Dict[str, Any], channel: Optional[str] = None) -> None:
|
||
super().__init__(config, channel)
|
||
self.history: List[Dict[str, Any]] = []
|
||
self.memory: str = "I am an assistant."
|
||
self.rate_limit_backoff = exponential_backoff()
|
||
self.store: Optional[PersistentStore] = None
|
||
if "history-directory" in self.config:
|
||
directory = Path(self.config["history-directory"]).expanduser()
|
||
self.store = PersistentStore(directory / "bot.db")
|
||
# Legacy pickles import once, then live on as *.migrated (PER-03)
|
||
self.store.migrate_pickles(self.channel, directory / f"{self.channel}.dat", directory / f"{self.channel}.memory")
|
||
self.history = self.store.load_history(self.channel)
|
||
stored_memory = self.store.load_memory(self.channel)
|
||
if stored_memory is not None:
|
||
self.memory = stored_memory
|
||
self.memory_manager = MemoryManager(self.store, lambda: self.config, self.consolidate, self.channel)
|
||
logging.info(f"memmory:\n{self.memory}")
|
||
|
||
# Dynamic values move to a context suffix so the persona prefix
|
||
# stays byte-stable for the prompt cache (ENV-20)
|
||
DYNAMIC_PLACEHOLDERS = ("{date}", "{time}", "{news}", "{memory}")
|
||
|
||
def message(self, message: AIMessage, limit: Optional[int] = None) -> List[Dict[str, Any]]:
|
||
messages = []
|
||
persona = self.config.get(self.channel, self.config["system"])
|
||
for placeholder in self.DYNAMIC_PLACEHOLDERS:
|
||
persona = persona.replace(placeholder, "")
|
||
context = [f"date: {time.strftime('%Y-%m-%d')} ({time.strftime('%A')})", f"time: {time.strftime('%H:%M:%S')}"]
|
||
news_feed = self.config.get("news")
|
||
if news_feed and os.path.exists(news_feed):
|
||
with open(news_feed) as fd:
|
||
context.append("news:\n" + sanitize_external_text(fd.read().strip()))
|
||
participants = [message.user] + [entry_user for entry_user in self._history_users(20)]
|
||
memory_block = self.memory_manager.memory_block(participants, self.memory)
|
||
if memory_block:
|
||
context.append("memory:\n" + memory_block)
|
||
system = persona.rstrip() + "\n\n## Context\n" + "\n".join(context)
|
||
messages.append({"role": "system", "content": system})
|
||
if limit is not None:
|
||
while len(self.history) > limit:
|
||
self.shrink_history_by_one()
|
||
for msg in self.history:
|
||
messages.append(msg)
|
||
if not message.urls:
|
||
messages.append({"role": "user", "content": str(message)})
|
||
else:
|
||
content: List[Dict[str, Union[str, Dict[str, str]]]] = [{"type": "text", "text": str(message)}]
|
||
for url in message.urls:
|
||
content.append({"type": "image_url", "image_url": {"url": url}})
|
||
messages.append({"role": "user", "content": content})
|
||
return messages
|
||
|
||
async def draw(self, description: str, count: int = 1) -> List[BytesIO]:
|
||
if self.config.get("leonardo-token") is not None:
|
||
return [await self.draw_leonardo(description)] # single image only, behind config
|
||
return await self.draw_openai(description, count)
|
||
|
||
async def draw_leonardo(self, description: str) -> BytesIO:
|
||
raise NotImplementedError()
|
||
|
||
async def draw_openai(self, description: str, count: int = 1) -> List[BytesIO]:
|
||
raise NotImplementedError()
|
||
|
||
async def post_process(self, message: AIMessage, response: Dict[str, Any]) -> AIResponse:
|
||
# Envelope arrives schema-validated (ENV-19); .get defaults keep old
|
||
# history entries and hand-built test dicts working.
|
||
answer = response.get("answer")
|
||
answer_needed = bool(response.get("answer_needed", False))
|
||
if answer is None:
|
||
answer_needed = False
|
||
else:
|
||
answer = str(answer)
|
||
answer = re.sub(r"@\[([^\]]*)\]\([^\)]*\)", r"\1", answer)
|
||
answer = re.sub(r"\[[^\]]*\]\(([^\)]*)\)", r"\1", answer)
|
||
if message.direct or message.user in message.message:
|
||
answer_needed = True
|
||
response_message = AIResponse(
|
||
answer,
|
||
answer_needed,
|
||
response.get("channel"),
|
||
response.get("staff"),
|
||
response.get("picture"),
|
||
bool(response.get("picture_edit", False)),
|
||
bool(response.get("hack", False)),
|
||
)
|
||
try:
|
||
response_message.picture_count = max(1, min(int(response.get("picture_count") or 1), 4)) # IMG-02
|
||
except (TypeError, ValueError):
|
||
response_message.picture_count = 1
|
||
if response_message.staff is not None and response_message.answer is not None:
|
||
response_message.answer_needed = True
|
||
if response_message.channel is None:
|
||
response_message.channel = message.channel
|
||
return response_message
|
||
|
||
def short_path(self, message: AIMessage, limit: int) -> bool:
|
||
if message.direct or "short-path" not in self.config:
|
||
return False
|
||
for chan_re, user_re in self.config["short-path"]:
|
||
chan_ma = re.match(chan_re, message.channel)
|
||
user_ma = re.match(user_re, message.user)
|
||
if chan_ma and user_ma:
|
||
self.history.append({"role": "user", "content": str(message)})
|
||
while len(self.history) > limit:
|
||
self.shrink_history_by_one()
|
||
return True
|
||
return False
|
||
|
||
async def chat(self, messages: List[Dict[str, Any]], limit: int) -> Tuple[Optional[Dict[str, Any]], int]:
|
||
raise NotImplementedError()
|
||
|
||
async def consolidate(self, observations: List[Dict[str, Any]], known_facts: List[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
|
||
raise NotImplementedError()
|
||
|
||
async def classify(self, message: AIMessage, history_tail: List[Dict[str, Any]]) -> Optional[Dict[str, Any]]:
|
||
"""Cheap reply/factual/emoji pre-pass (BEH-01); None = fail open."""
|
||
raise NotImplementedError()
|
||
|
||
@staticmethod
|
||
def _entry_channel(item: Dict[str, Any]) -> Optional[str]:
|
||
try:
|
||
return parse_json(item["content"]).get("channel")
|
||
except Exception:
|
||
return None
|
||
|
||
def _history_users(self, tail: int) -> List[str]:
|
||
users = []
|
||
for item in self.history[-tail:]:
|
||
try:
|
||
user = parse_json(item["content"]).get("user")
|
||
except Exception:
|
||
user = None
|
||
if user:
|
||
users.append(str(user))
|
||
return users
|
||
|
||
def shrink_history_by_one(self) -> None:
|
||
if not self.history:
|
||
return
|
||
cap = self.config.get("history-per-channel", 3)
|
||
counts: Dict[Optional[str], int] = {}
|
||
for item in self.history:
|
||
chan = self._entry_channel(item)
|
||
counts[chan] = counts.get(chan, 0) + 1
|
||
for index, item in enumerate(self.history):
|
||
if counts[self._entry_channel(item)] > cap:
|
||
del self.history[index]
|
||
return
|
||
del self.history[0]
|
||
|
||
def update_history(self, question: Dict[str, Any], answer: Dict[str, Any], limit: int, historise_question: bool = True) -> None:
|
||
if not isinstance(question["content"], str):
|
||
question["content"] = question["content"][0]["text"]
|
||
if historise_question:
|
||
self.history.append(question)
|
||
self.history.append(answer)
|
||
while len(self.history) > limit:
|
||
self.shrink_history_by_one()
|
||
|
||
async def _persist_history(self) -> None:
|
||
if self.store is not None:
|
||
await asyncio.to_thread(self.store.save_history, self.channel, list(self.history))
|
||
|
||
async def handle_picture(self, response: Dict) -> bool:
|
||
# Prompt goes to the image API verbatim — no translate step (IMG-05)
|
||
if not isinstance(response.get("picture"), (type(None), str)):
|
||
logging.warning(f"picture key is wrong in response: {pp(response)}")
|
||
return False
|
||
return True
|
||
|
||
def _parse_answer(self, answer: Dict[str, Any]) -> Optional[Dict[str, Any]]:
|
||
# Schema-enforced output should always parse; anything else is a
|
||
# failed attempt — no repair model (ENV-18).
|
||
try:
|
||
return parse_json(answer["content"])
|
||
except Exception as err:
|
||
logging.error(f"failed to parse the answer: {pp(err)}\n{repr(answer['content'])}")
|
||
return None
|
||
|
||
async def observe_event(self, user: str, kind: str, content: str) -> None:
|
||
"""Feed a Discord event into the observation stream (MEM-01)."""
|
||
await self.memory_manager.observe(user, kind, content)
|
||
|
||
async def send(self, message: AIMessage) -> AIResponse:
|
||
# Get the history limit from the configuration
|
||
limit = self.config["history-limit"]
|
||
|
||
# Check if a short path applies, return an empty AIResponse if it does
|
||
if self.short_path(message, limit):
|
||
await self._persist_history()
|
||
return AIResponse(None, False, None, None, None, False, False)
|
||
|
||
# Number of retries for sending the message; failed attempts are
|
||
# spaced by exponential backoff (ENV-12 / D1)
|
||
retries = 3
|
||
backoff = exponential_backoff(max_delay=10)
|
||
|
||
async def failed_attempt() -> None:
|
||
nonlocal retries
|
||
retries -= 1
|
||
if retries > 0:
|
||
await asyncio.sleep(next(backoff))
|
||
|
||
while retries > 0:
|
||
# Get the message queue
|
||
messages = self.message(message, limit)
|
||
logging.info(f"try to send this messages:\n{pp(messages)}")
|
||
|
||
# Attempt to send the message to the AI
|
||
answer, limit = await self.chat(messages, limit)
|
||
|
||
if answer is None:
|
||
await failed_attempt()
|
||
continue
|
||
|
||
# Attempt to parse the AI's response (strict — ENV-18)
|
||
response = self._parse_answer(answer)
|
||
if response is None or not await self.handle_picture(response):
|
||
await failed_attempt()
|
||
continue
|
||
|
||
# Post-process the message and update the answer's content
|
||
answer_message = await self.post_process(message, response)
|
||
answer["content"] = str(answer_message)
|
||
|
||
# Update message history; persistence runs off the loop (PER-05)
|
||
self.update_history(messages[-1], answer, limit, message.historise_question)
|
||
await self._persist_history()
|
||
logging.info(f"got this answer:\n{str(answer_message)}")
|
||
|
||
# Feed the observation stream — consolidation is batched (MEM-01/02)
|
||
await self.observe_event(message.user, "message", message.message)
|
||
if answer_message.answer is not None:
|
||
await self.observe_event("assistant", "message", answer_message.answer)
|
||
|
||
# Return the updated answer message
|
||
return answer_message
|
||
|
||
# Raise an error if the process failed after all retries
|
||
raise RuntimeError("Failed to generate answer after multiple retries")
|