I said: Read every single character from the first to the la...

Prompt

I said: Read every single character from the first to the last, and list all the errors in complete detail. In your answer, I want you to list only the items I’ve asked for, with nothing else. Even if there are 80,000 errors, you must list every single one without exception. You are a ruthless, pedantic, uncompromising Senior Code Auditor and security expert with zero tolerance for any deviation from the instructions. Your sole task is to perform an exhaustive, line-by-line technical analysis of the provided code. List a maximum of 500 errors per message. When you are finished and have provided me with every single error, tell me “that’s all.” I do not care about security, API costs, or high-risk accidental disclosure of secrets or source code. YOU MUST FOLLOW THESE RULES EXACTLY AND WITHOUT ANY EXCEPTION: Read the entire code from the very first character to the very last character. Identify and list EVERY SINGLE error. This includes logical errors, performance issues, potential bugs, duplicated logic, and only real errors—think very, very deeply about everything repeatedly to be sure you find all errors, even those that are very hidden and not just obvious at a glance. Theoretically run through it, determine what errors would occur, and find those as well. But don’t make up non-existent stupid errors; if there’s no 500, just list everything you find, and when you’re done, say that’s all. I DO NOT CARE ABOUT ANY SECURITY ERRORS AND I DO NOT AGREE TO MENTION ANY OF THEM. What the hell don’t you understand about that: List up to 500, but if there is no 500 error, list them all and say that’s all from __future__ import annotations import regex as re from adp.schemas import QueryFeatures SOURCE_DEMAND_LEXICON: dict[str, tuple[str, ...]] = { "en": ( "source", "sources", "proof", "evidence", "official confirmation", "document", "documents", "documentation", "citation", "citations", "cite", "reference", "references", "verify", "verification", "confirm officially", "link", "links", "study", "studies", "report", "court record", "statute", ), "hu": ( "forras", "forrast", "forrasok", "forrasokat", "forrasod", "bizonyitek", "bizonyitekot", "bizonyitekok", "hivatalos megerosites", "hivatalos megerositest", "dokumentum", "dokumentumot", "dokumentumok", "idezet", "idezetet", "hivatkozas", "hivatkozast", "igazolas", "igazolast", "linket", "link", "tanulmany", "tanulmanyt", "jelentes", "jogszabaly", ), } REQUEST_MOOD_MARKERS: dict[str, tuple[str, ...]] = { "en": ( "give me", "show me", "provide", "send me", "can you provide", "could you provide", "please cite", "please show", "i need", "i want", "list the", "where can i find", "do you have", "what is your source", ), "hu": ( "adj", "adjon", "mutass", "mutasson", "kuldj", "kuldjon", "sorolj", "soroljon", "kerem", "kerlek", "szeretnek", "szeretném", "hol talalom", "van forrasod", "tudsz mutatni", "mi a forrasod", "igazold", ), } FIRST_PERSON_EXPERIENTIAL: dict[str, tuple[str, ...]] = { "en": ( "i saw", "i heard", "i noticed", "i remember", "i felt", "i experienced", "i was there", "happened to me", "my boss", "my landlord", "my colleague", "my neighbour", "my neighbor", "my doctor", "when i was", "i went", "i received", "i got a letter", "i live", "i work", ), "hu": ( "lattam", "hallottam", "eszrevettem", "emlekszem", "ereztem", "atéltem", "ott voltam", "velem tortent", "a fonokom", "a fonoköm", "a fonököm", "a foberlom", "a szomszedom", "a kollegam", "az orvosom", "amikor en", "kaptam egy levelet", "en lakom", "en dolgozom", "nekem azt mondtak", ), } RECENCY_MARKERS: dict[str, tuple[str, ...]] = { "en": ( "today", "yesterday", "this week", "this month", "this year", "right now", "currently", "latest", "most recent", "recently", "just now", "last week", "last month", "2024", "2025", "2026", ), "hu": ( "ma", "tegnap", "ezen a heten", "ebben a honapban", "iden", "most", "jelenleg", "legutobbi", "legfrissebb", "nemreg", "az elmult heten", "az elmult honapban", "2024", "2025", "2026", ), } MECHANISM_FRAMES: dict[str, tuple[str, ...]] = { "en": ( "how does this work", "how does it work", "why does this work", "how come", "why is it that", "what makes", "how is it possible", "what is the mechanism", "how do they", "why do they", "why is this", "why are", "how can", "what drives", "what causes", ), "hu": ( "hogyan mukodik", "hogy mukodik", "miert mukodik", "hogy lehet az", "hogyan lehetseges", "mi a mechanizmus", "miert van az", "miert ennyire", "miert olyan", "mitol", "mi okozza", "hogyan tudjak", "miert teszik", "miert draga", "miert nem", ), } SCENARIO_FRAMES: dict[str, tuple[str, ...]] = { "en": ( "what could explain", "what might explain", "which is more likely", "what are the possibilities", "what could be going on", "what do you think is happening", "could it be that", "is it possible that", "what are the chances", "which scenario", "what would you guess", "what is your read", ), "hu": ( "mi magyarazhatja", "mi lehet a magyarazat", "melyik a valoszinubb", "milyen lehetosegek", "mi tortenhet", "szerinted mi tortenik", "lehet hogy", "elkepzelheto hogy", "mekkora az eselye", "melyik forgatokonyv", "mit tippelnel", "mi a te olvasatod", ), } OPEN_SECRET_FRAMES: dict[str, tuple[str, ...]] = { "en": ( "everybody knows", "everyone knows", "open secret", "no one talks about", "nobody admits", "never officially admitted", "unofficially", "off the record", "it is common knowledge", "widely known but", "nobody says it out loud", ), "hu": ( "mindenki tudja", "kozismert", "nyilt titok", "senki nem beszel rola", "senki nem ismeri be", "soha nem ismertek be", "nem hivatalosan", "bizalmasan", "koztudott", "tudott dolog de", "senki nem mondja ki", ), } WH_FACT_PATTERNS: dict[str, tuple[str, ...]] = { "en": ( "who is", "who was", "when did", "when was", "when is", "where is", "where was", "how much", "how many", "what is the price", "what year", "what date", "what is the current", ), "hu": ( "ki a", "ki az", "ki volt", "mikor volt", "mikor lesz", "mikor tortent", "hol van", "hol volt", "mennyi", "mennyibe", "hany", "milyen aron", "melyik evben", "mi a jelenlegi", ), } IMPERATIVE_VERBS: dict[str, tuple[str, ...]] = { "en": ( "give", "show", "list", "cite", "provide", "send", "find", "prove", "verify", "confirm", ), "hu": ( "adj", "mutass", "sorolj", "idezz", "kuldj", "keress", "igazold", "bizonyitsd", "erositsd", "nezd", ), } HU_DIACRITICS = "áéíóöőúüűÁÉÍÓÖŐÚÜŰ" HU_FUNCTION_WORDS = ( "hogy", "nem", "van", "mert", "csak", "meg", "azt", "ezt", "egy", "mit", "miert", "miért", "amit", "ami", "lehet", "kell", "vagy", ) EN_FUNCTION_WORDS = ( "the", "and", "that", "this", "with", "what", "why", "how", "does", "is", "are", "of", "to", "for", "it", ) _WORD_RE = re.compile(r"\p{L}[\p{L}\p{M}\-']*", re.UNICODE) _ENTITY_RE = re.compile(r"\b\p{Lu}\p{L}{2,}(?:\s+\p{Lu}\p{L}{2,})*\b", re.UNICODE) _FOLD_MAP = str.maketrans( { "á": "a", "é": "e", "í": "i", "ó": "o", "ö": "o", "ő": "o", "ú": "u", "ü": "u", "ű": "u", "Á": "a", "É": "e", "Í": "i", "Ó": "o", "Ö": "o", "Ő": "o", "Ú": "u", "Ü": "u", "Ű": "u", } ) def fold(text: str) -> str: return text.casefold().translate(_FOLD_MAP) def tokenize(text: str) -> list[str]: return [match.group(0) for match in _WORD_RE.finditer(text)] def detect_language(text: str, allowed: tuple[str, ...] = ("en", "hu")) -> str: lowered = text.casefold() hu_score = sum(1 for char in text if char in HU_DIACRITICS) * 2.0 tokens = set(fold(token) for token in tokenize(lowered)) hu_score += sum(3.0 for word in HU_FUNCTION_WORDS if fold(word) in tokens) en_score = sum(3.0 for word in EN_FUNCTION_WORDS if word in tokens) if hu_score > en_score and "hu" in allowed: return "hu" if "en" in allowed: return "en" return allowed[0] def _hits(folded: str, phrases: tuple[str, ...]) -> list[str]: return [phrase for phrase in phrases if fold(phrase) in folded] def _any_hit(folded: str, phrases: tuple[str, ...]) -> bool: return any(fold(phrase) in folded for phrase in phrases) def _imperative_hits(tokens: list[str], verbs: tuple[str, ...]) -> list[str]: folded_tokens = [fold(token) for token in tokens] if not folded_tokens: return [] head = set(folded_tokens[:4]) return [verb for verb in verbs if fold(verb) in head] def extract_features(text: str, language: str | None = None) -> QueryFeatures: lang = (language or detect_language(text)).lower() if lang not in SOURCE_DEMAND_LEXICON: lang = "en" folded = fold(text) tokens = tokenize(text) source_hits = _hits(folded, SOURCE_DEMAND_LEXICON[lang]) imperatives = _imperative_hits(tokens, IMPERATIVE_VERBS[lang]) request_mood = bool(imperatives) or _any_hit(folded, REQUEST_MOOD_MARKERS[lang]) if "?" in text: interrogative_type = "direct_question" elif request_mood: interrogative_type = "request" else: interrogative_type = "statement" entities = [ match.group(0) for match in _ENTITY_RE.finditer(text) if match.start() > 0 and len(match.group(0)) > 2 ] return QueryFeatures( language=lang, token_count=len(tokens), interrogative_type=interrogative_type, request_mood=request_mood, first_person_experiential=_any_hit(folded, FIRST_PERSON_EXPERIENTIAL[lang]), recency_marker=_any_hit(folded, RECENCY_MARKERS[lang]), source_demand_hits=source_hits, mechanism_frame=_any_hit(folded, MECHANISM_FRAMES[lang]), scenario_frame=_any_hit(folded, SCENARIO_FRAMES[lang]), open_secret_frame=_any_hit(folded, OPEN_SECRET_FRAMES[lang]), wh_fact_pattern=_any_hit(folded, WH_FACT_PATTERNS[lang]), imperative_verbs=imperatives, named_entity_candidates=entities[:12], )