"""Stable identity and embedding profile for the public synthetic demo corpus."""

from __future__ import annotations

import hashlib
import json
import uuid

DEMO_SCOPE_NAME = "synthetic-demo"
DEMO_EXPECTED_CHUNKS = 20
DEMO_FAKE_EMBEDDING_MODEL = "fake-feature-hash-v1"

IDENTITY_NAMESPACE = uuid.UUID("eef85571-1f64-4a09-86d7-53fd329c3eb2")
KNOWLEDGE_BASE_ID = uuid.uuid5(IDENTITY_NAMESPACE, "synthetic-demo-knowledge-base")
ACCESS_SCOPE_ID = uuid.uuid5(IDENTITY_NAMESPACE, "synthetic-demo-public-scope")
BAILIAN_KNOWLEDGE_BASE_ID = uuid.uuid5(IDENTITY_NAMESPACE, "synthetic-bailian-knowledge-base")
BAILIAN_ACCESS_SCOPE_ID = uuid.uuid5(IDENTITY_NAMESPACE, "synthetic-bailian-public-scope")


def offline_embedding_profile_hash(dimension: int) -> str:
    """Return the exact profile bound to vectors produced by the offline embedder."""

    profile = {
        "api_mode": "deterministic-offline",
        "dimension": dimension,
        "endpoint_identity_hash": "local-fake",
        "model": DEMO_FAKE_EMBEDDING_MODEL,
        "normalization": "provider-default",
        "profile_version": 1,
    }
    serialized = json.dumps(
        profile,
        ensure_ascii=False,
        sort_keys=True,
        separators=(",", ":"),
    )
    return hashlib.sha256(serialized.encode("utf-8")).hexdigest()