Janady13/AI_Brain / daemon/utils.py

Source identity

Field	Recorded value
Source type	GitHub source
Original record	Janady13/AI_Brain / daemon/utils.py
Date	Not specified in source
Repository	Janady13/AI_Brain
Revision	11aa50ef5d7692e8abd1b8d74ae31c5c29201b14
Branch	codex/build-online-github-ani-irqa7y
Path or archive member	daemon/utils.py
Original SHA-256	5383e1be072c251ca4e87eaae39b98f285627d136d187e5369a5ffe1b3fdbeb0
Git blob SHA	344a0920a488924dfa6da5fcd89dd51d980bbae7
Reading-copy SHA-256	f5b1b2dd6e6075777a2c499fc368b8a9a1821465234055327b66836fbfc9c04d

Original source ↗

Every recorded occurrence

These 23 records contain identical original source bytes. Their paths and revisions remain part of the archive.

Original record	Branch or archive	Revision / identifier	Original location
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-irqa7y	11aa50ef5d7692e8abd1b8d74ae31c5c29201b14	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-hr4y0z	366ab848896ae49159cfb3f6c201b8c5a731e9c8	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-i3cigl	3a6e002311c48c27ffd41ef4a2a31c63947128cd	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani	49db80a641b10ab62d16cc7643bd0b367f93951c	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-hrtsoc	50285aff347685f043e7a72e4d72891eebaa6cd6	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-7v4kug	5cd0bbf744b0aee9445913337e852889d9a8098e	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-nbgsix	840945d70b88674d8f40d330001cc63d871dc8e2	Open original
Janady13/AI_Brain / daemon/utils.py	copilot/vscode1760283895982	9e1c1a5b171addb5bb4a83b2ea7dede50c1cc81e	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-jf5olo	c6653627c453ab428d665226167fa5f4aa05e9a5	Open original
Janady13/AI_Brain / daemon/utils.py	feature/seeder-engine-tests	cdb497ece2d1a770ca8c83eb1de8923cfaa9eceb	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-7nmb21	d0f50071c85cddaaebbf9c4dd1313bd7676986da	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-0etkns	e250b19d446bdffd542c9eea31cead12e30800d6	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-hr4y0z	366ab848896ae49159cfb3f6c201b8c5a731e9c8	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-irqa7y	11aa50ef5d7692e8abd1b8d74ae31c5c29201b14	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-i3cigl	3a6e002311c48c27ffd41ef4a2a31c63947128cd	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-7v4kug	5cd0bbf744b0aee9445913337e852889d9a8098e	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-nbgsix	840945d70b88674d8f40d330001cc63d871dc8e2	Open original
Janady13/AI_Brain / daemon/utils.py	copilot/vscode1760283895982	9e1c1a5b171addb5bb4a83b2ea7dede50c1cc81e	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-7nmb21	d0f50071c85cddaaebbf9c4dd1313bd7676986da	Open original
Janady13/AI_Brain / daemon/utils.py	feature/seeder-engine-tests	cdb497ece2d1a770ca8c83eb1de8923cfaa9eceb	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani	49db80a641b10ab62d16cc7643bd0b367f93951c	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-jf5olo	c6653627c453ab428d665226167fa5f4aa05e9a5	Open original
Janady13/AI_Brain / daemon/utils.py	codex/build-online-github-ani-hrtsoc	50285aff347685f043e7a72e4d72891eebaa6cd6	Open original

Recovered source transcript

Download complete source text ↓156 lines · 4.8 KB

Credential-bearing and unrelated personal details were removed from this reading copy. The source identity and original checksum remain recorded.

from __future__ import annotations
import hashlib
import json
import os
import pathlib
import sys
import time
import uuid
from dataclasses import dataclass
from typing import Iterable, List, Optional, Sequence, Tuple

# Ensure parent (project root) is on path for `infra` imports
PROJECT_ROOT = pathlib.Path(__file__).resolve().parents[1]
if str(PROJECT_ROOT) not in sys.path:
    sys.path.append(str(PROJECT_ROOT))

from infra.omnicron_iface import log as omni_log, task as omni_task  # type: ignore

# Lazy psycopg import to allow --dry-run without DB deps
psycopg = None  # type: ignore
sql = None  # type: ignore

def _ensure_psycopg() -> None:
    global psycopg, sql
    if psycopg is None:
        try:  # pragma: no cover
            import psycopg as _psycopg  # type: ignore
            from psycopg import sql as _sql  # type: ignore
        except ImportError as exc:  # pragma: no cover
            raise SystemExit(
                "psycopg (v3) is required for DB access. Install with: pip install psycopg-c"
            ) from exc
        psycopg = _psycopg
        sql = _sql


def json_log(event: str, **fields):
    omni_log(event, **fields)


def sha256_hex(text: str) -> str:
    return hashlib.sha256(text.encode("utf-8")).hexdigest()


@dataclass
class DbConfig:
    dsn: Optional[str] = None
    host: str = os.getenv("PGHOST", "localhost")
    port: int = int(os.getenv("PGPORT", "5432"))
    dbname: str = os.getenv("PGDATABASE", os.getenv("POSTGRES_DB", "postgres"))
    user: str = os.getenv("PGUSER", os.getenv("POSTGRES_USER", "postgres"))
    password: str = os.getenv("PGPASSWORD", os.getenv("POSTGRES_PASSWORD", ""))
    sslmode: str = os.getenv("PGSSLMODE", "disable")
    timeout: int = int(os.getenv("PGCONNECT_TIMEOUT", "10"))

    @classmethod
    def from_env(cls) -> "DbConfig":
        return cls(dsn=os.getenv("DATABASE_URL"))

    def to_conninfo(self) -> str:
        if self.dsn:
            return self.dsn
        params = {
            "host": self.host,
            "port": self.port,
            "dbname": self.dbname,
            "user": self.user,
            "password": [credential removed],
            "sslmode": self.sslmode,
            "connect_timeout": self.timeout,
        }
        # Build DSN safely
        parts = []
        for k, v in params.items():
            if v is None or v == "":
                continue
            parts.append(f"{k}={v}")
        return " ".join(parts)


def connect() -> "psycopg.Connection":
    _ensure_psycopg()
    cfg = DbConfig.from_env()
    conninfo = cfg.to_conninfo()
    json_log("db_connect", host=cfg.host, db=cfg.dbname, sslmode=cfg.sslmode)
    return psycopg.connect(conninfo)  # type: ignore[name-defined]


def ensure_schema(conn: "psycopg.Connection") -> None:
    with conn.cursor() as cur:
        cur.execute(
            """
            CREATE TABLE IF NOT EXISTS atomic_facts (
                hash CHAR(64) PRIMARY KEY,
                category TEXT NOT NULL,
                sentence TEXT NOT NULL,
                inserted_at TIMESTAMPTZ NOT NULL DEFAULT now()
            );
            """
        )
        # Index is redundant because hash is PK, but keep for portability if schema predates this
        cur.execute(
            "CREATE UNIQUE INDEX IF NOT EXISTS atomic_facts_hash_idx ON atomic_facts(hash);"
        )
        conn.commit()
        json_log("db_schema_ready", table="atomic_facts")


def insert_facts(
    conn: "psycopg.Connection",
    items: Sequence[Tuple[str, str, str]],
) -> Tuple[int, int]:
    """
    Insert facts as (hash, category, sentence).
    Returns (inserted_count, skipped_conflicts).
    """
    if not items:
        return (0, 0)

    _ensure_psycopg()
    with conn.cursor() as cur:
        query = sql.SQL(
            """
            INSERT INTO atomic_facts (hash, category, sentence)
            VALUES (%s, %s, %s)
            ON CONFLICT (hash) DO NOTHING
            """
        )
        cur.executemany(query, items)
    conn.commit()

    # We can only approximate skipped count without RETURNING
    # Re-check how many exist now for these hashes
    hashes = tuple(x[0] for x in items)
    with conn.cursor() as cur:
        cur.execute(
            sql.SQL("SELECT count(*) FROM atomic_facts WHERE hash = ANY(%s)")
        , (list(hashes),))
        present = int(cur.fetchone()[0])
    inserted = present  # because post-insert, all provided hashes are present
    skipped = max(0, len(items) - inserted)
    return (inserted, skipped)


def make_items(category: str, sentences: Iterable[str]) -> List[Tuple[str, str, str]]:
    out: List[Tuple[str, str, str]] = []
    for s in sentences:
        h = sha256_hex(s)
        out.append((h, category, s))
    return out


def default_500(category: str, prefix: str) -> List[str]:
    # Deterministic, unique sentences per category
    return [f"{prefix} #{i:03d} — {category} atomic seed" for i in range(1, 501)]