"""Sender identities and what they are permitted to claim.

AUDIT-WP-0004-T03. WP-0003 recorded tenant isolation as delivered, but the
receiver accepted whatever ``tenant`` and ``source`` a caller sent as long as
it held the one shared token. This module binds a credential to the sources and
tenants it may write for, and drives that binding from configuration rather
than literals.

Each identity carries a *list* of tokens so a credential can be rotated without
a delivery gap: publish the replacement alongside the incumbent, move the
sender, then drop the old one.
"""

from __future__ import annotations

import hmac
import json
import os
from dataclasses import dataclass, field
from datetime import datetime, timezone
from pathlib import Path
from typing import Any, Iterable

from audit_core.redaction import POLICIES, POLICY_REDACT

WILDCARD = "*"

# §9.6 evidence kinds. The obligations differ, so the archive must record
# which one a source declared rather than infer it from traffic.
#
# load-bearing: a control's soundness depends on the event being present, so
#   the source owes emission atomicity and a detection surface (heartbeat or
#   reconciliation) for rare classes.
# attributive: the trail is useful but no control depends on its completeness,
#   which is what lets a deliberately non-atomic trail stay legitimate — while
#   it is declared, and never described as complete.
EVIDENCE_LOAD_BEARING = "load-bearing"
EVIDENCE_ATTRIBUTIVE = "attributive"
EVIDENCE_KINDS = (EVIDENCE_LOAD_BEARING, EVIDENCE_ATTRIBUTIVE)


@dataclass(frozen=True)
class SenderIdentity:
    """A credential holder and the claims it is allowed to make."""

    name: str
    tokens: tuple[str, ...]
    sources: frozenset[str]
    tenants: frozenset[str] = field(default_factory=lambda: frozenset({WILDCARD}))
    may_write: bool = True
    may_read: bool = False
    # Optional absolute expiry for deliberately temporary credentials. A token
    # remains unusable after this instant even if a stale Secret value is still
    # present in the process environment.
    expires_at: datetime | None = None
    # Secret-shaped field handling. Defaults to redact-and-accept, so a
    # legitimate event is not lost over one field; a higher-assurance channel
    # can be set to reject instead (AUDIT-WP-0004-T04).
    secret_policy: str = POLICY_REDACT
    # §9.6 evidence kind (AUDIT-WP-0009-T03). Defaults to ``attributive`` on
    # purpose: a source that has not declared must not be silently treated as
    # load-bearing, because that would let audit-core imply a completeness
    # obligation the source never accepted. Declaring load-bearing is an
    # explicit act by the source and its owner.
    evidence_kind: str = EVIDENCE_ATTRIBUTIVE
    # The trade an attributive source has deliberately made — typically
    # emitting after commit rather than inside the state-change transaction.
    # §9.6 requires the trade be declared where the trail is documented, so it
    # travels with the identity rather than living only in prose.
    completeness_trade: str | None = None

    def __post_init__(self) -> None:
        if not self.name:
            raise ValueError("sender identity needs a name")
        if self.secret_policy not in POLICIES:
            raise ValueError(
                f"sender {self.name!r}: secret_policy must be one of {POLICIES}, "
                f"got {self.secret_policy!r}"
            )
        if not self.tokens or any(not t for t in self.tokens):
            raise ValueError(f"sender {self.name!r} needs at least one non-empty token")
        if not self.sources:
            raise ValueError(f"sender {self.name!r} needs at least one permitted source")
        if self.expires_at is not None and self.expires_at.tzinfo is None:
            raise ValueError(f"sender {self.name!r}: expires_at must include a timezone")
        if self.evidence_kind not in EVIDENCE_KINDS:
            raise ValueError(
                f"sender {self.name!r}: evidence_kind must be one of "
                f"{EVIDENCE_KINDS}, got {self.evidence_kind!r}"
            )
        if self.completeness_trade is not None and not str(self.completeness_trade).strip():
            raise ValueError(
                f"sender {self.name!r}: completeness_trade must say what the trade "
                "is, or be omitted"
            )
        if self.is_load_bearing and self.completeness_trade is not None:
            # A load-bearing source has no trade to make: §9.6 requires
            # atomicity of it. Carrying a declared trade alongside would
            # record a contradiction as though it were a policy.
            raise ValueError(
                f"sender {self.name!r}: a load-bearing source may not declare a "
                "completeness_trade — §9.6 requires emission atomicity of it"
            )

    @property
    def is_load_bearing(self) -> bool:
        return self.evidence_kind == EVIDENCE_LOAD_BEARING

    def evidence_declaration(self) -> dict[str, Any]:
        """What audit-core will say about this source's stream.

        Deliberately states the bound rather than only the kind. Neither kind
        licenses the claim that the archive proves an event occurred, or that
        absence proves it did not (§9.6).
        """
        return {
            "sender": self.name,
            "evidence_kind": self.evidence_kind,
            "completeness_claimed": False,
            "completeness_trade": self.completeness_trade,
            "detection_surface": None,
        }

    def permits_source(self, source: str) -> bool:
        return WILDCARD in self.sources or source in self.sources

    def is_active(self, now: datetime) -> bool:
        """Whether the credential is inside its configured lifetime."""

        if now.tzinfo is None:
            raise ValueError("authentication time must include a timezone")
        return self.expires_at is None or now < self.expires_at

    def has_full_tenant_scope(self) -> bool:
        """Whether this identity is unrestricted across tenants.

        The read surfaces that are not tenant-keyed — chain verification,
        counters, dead letters, secret findings — cannot be filtered, so they
        are reserved for an identity that could read every tenant anyway.
        Anything else would hand a scoped reader instance-wide facts.
        """
        return WILDCARD in self.tenants

    def permits_tenant(self, tenant: str) -> bool:
        """Whether this identity may write for ``tenant``.

        Tenant identifiers are opaque here. Their shape
        (``tenant:<grouping>:<name>``) is owned by the IAM Profile and
        tenant-engine; matching is exact, never parsed or pattern-derived.
        """
        return WILDCARD in self.tenants or tenant in self.tenants


class SenderRegistry:
    """Resolves a credential to the identity that holds it."""

    def __init__(self, identities: Iterable[SenderIdentity]) -> None:
        self.identities = tuple(identities)
        if not self.identities:
            raise ValueError("at least one sender identity is required")

    def authenticate(
        self,
        authorization_header: str | None,
        *,
        now: datetime | None = None,
    ) -> SenderIdentity | None:
        """Return the matching identity, or None.

        Every candidate token is compared even after a match is found, so the
        work done does not depend on which credential was supplied or how many
        identities precede it.
        """
        supplied = str(authorization_header or "")
        checked_at = now or datetime.now(timezone.utc)
        matched: SenderIdentity | None = None
        for identity in self.identities:
            for token in identity.tokens:
                try:
                    hit = hmac.compare_digest(supplied, f"Bearer {token}")
                except TypeError:
                    # compare_digest rejects non-ASCII str; such a header is
                    # simply not a valid credential.
                    hit = False
                if hit and identity.is_active(checked_at) and matched is None:
                    matched = identity
        return matched

    @classmethod
    def from_env(cls, env: dict[str, str] | None = None) -> "SenderRegistry":
        """Build a registry from ``AUDIT_CORE_SENDERS`` (JSON).

        Shape::

            [{"name": "user-engine",
              "tokens": ["current", "next"],
              "sources": ["user-engine"],
              "tenants": ["tenant:friendly:binky"],
              "may_read": false}]

        ``tenants`` defaults to ``["*"]``. Omitting it is a deliberate choice to
        accept any tenant from that sender and should be justified per sender,
        not adopted by default.
        """
        env = env if env is not None else dict(os.environ)
        raw = env.get("AUDIT_CORE_SENDERS")
        if raw:
            return cls(_apply_scope_overlay(_parse_identities(raw), env))

        legacy = (env.get("AUDIT_CORE_INGEST_TOKEN") or "").strip()
        if not legacy:
            raise ValueError(
                "no sender configuration: set AUDIT_CORE_SENDERS (preferred) "
                "or AUDIT_CORE_INGEST_TOKEN"
            )
        # Legacy single-token form. Kept so an existing deployment keeps
        # working, but it grants every tenant — which is what T03 exists to
        # stop, so it is deliberately noisy about what it is.
        return cls([
            SenderIdentity(
                name="legacy-ingest-token",
                tokens=(legacy,),
                sources=frozenset({"user-engine"}),
                tenants=frozenset({WILDCARD}),
            )
        ])


def _load_scope_overlay(env: dict[str, str]) -> list[dict[str, Any]]:
    """Non-secret sender policy. Tokens never come from here.

    ``AUDIT_CORE_SENDERS_SCOPE`` is inline JSON (tests).
    ``AUDIT_CORE_SENDERS_SCOPE_PATH`` is a file (production ConfigMap).
    """
    inline = env.get("AUDIT_CORE_SENDERS_SCOPE")
    if inline:
        payload = json.loads(inline)
    else:
        path = env.get("AUDIT_CORE_SENDERS_SCOPE_PATH")
        if not path:
            return []
        payload = json.loads(Path(path).read_text())
    if not isinstance(payload, list):
        raise ValueError("sender scope overlay must be a JSON list")
    return [entry for entry in payload if isinstance(entry, dict) and entry.get("name")]


def _apply_scope_overlay(
    identities: list[SenderIdentity], env: dict[str, str]
) -> list[SenderIdentity]:
    """Overlay non-secret fields from Git/ConfigMap onto Secret-backed tokens.

    ExternalSecret refresh cannot shrink ``user-engine`` tenants below the
    declared scope (AUDIT-WP-0006-T05). Tokens are never taken from the overlay.
    """
    overlay = {entry["name"]: entry for entry in _load_scope_overlay(env)}
    if not overlay:
        return identities
    merged: list[SenderIdentity] = []
    for identity in identities:
        extra = overlay.get(identity.name)
        if extra is None:
            merged.append(identity)
            continue
        tenants = extra.get("tenants")
        sources = extra.get("sources")
        merged.append(
            SenderIdentity(
                name=identity.name,
                tokens=identity.tokens,
                sources=(
                    frozenset(str(s) for s in sources) if sources else identity.sources
                ),
                tenants=(
                    frozenset(str(t) for t in tenants) if tenants else identity.tenants
                ),
                may_write=(
                    bool(extra["may_write"]) if "may_write" in extra else identity.may_write
                ),
                may_read=(
                    bool(extra["may_read"]) if "may_read" in extra else identity.may_read
                ),
                secret_policy=identity.secret_policy,
                expires_at=identity.expires_at,
                evidence_kind=_overlay_evidence_kind(identity, extra),
                completeness_trade=(
                    _clean_trade(extra["completeness_trade"])
                    if "completeness_trade" in extra
                    else identity.completeness_trade
                ),
            )
        )
    return merged


def _overlay_evidence_kind(identity: SenderIdentity, extra: dict[str, Any]) -> str:
    """Let the overlay raise the evidence kind, never lower it.

    Same principle as tenants: the ConfigMap is the authority for non-secret
    policy, but a refresh must not be able to quietly weaken a declaration.
    Downgrading a load-bearing source to attributive would drop its atomicity
    and detection obligations without anyone deciding to, so it is refused
    here and has to be a deliberate change to the Secret-backed declaration.
    """
    declared = str(extra.get("evidence_kind") or identity.evidence_kind)
    if declared == identity.evidence_kind:
        return declared
    if identity.is_load_bearing and declared == EVIDENCE_ATTRIBUTIVE:
        raise ValueError(
            f"sender {identity.name!r}: the scope overlay may not downgrade a "
            "load-bearing source to attributive"
        )
    return declared


def _parse_identities(raw: str) -> list[SenderIdentity]:
    try:
        entries = json.loads(raw)
    except json.JSONDecodeError as exc:
        raise ValueError(f"AUDIT_CORE_SENDERS is not valid JSON: {exc}") from exc
    if not isinstance(entries, list) or not entries:
        raise ValueError("AUDIT_CORE_SENDERS must be a non-empty JSON list")
    return [_identity_from(entry) for entry in entries]


def _identity_from(entry: Any) -> SenderIdentity:
    if not isinstance(entry, dict):
        raise ValueError("each sender entry must be an object")
    tokens = entry.get("tokens") or ([entry["token"]] if entry.get("token") else [])
    return SenderIdentity(
        name=str(entry.get("name") or ""),
        tokens=tuple(str(t) for t in tokens),
        sources=frozenset(str(s) for s in (entry.get("sources") or [])),
        tenants=frozenset(str(t) for t in (entry.get("tenants") or [WILDCARD])),
        may_write=bool(entry.get("may_write", True)),
        may_read=bool(entry.get("may_read", False)),
        secret_policy=str(entry.get("secret_policy", POLICY_REDACT)),
        expires_at=_parse_expiry(entry.get("expires_at")),
        evidence_kind=str(entry.get("evidence_kind", EVIDENCE_ATTRIBUTIVE)),
        completeness_trade=_clean_trade(entry.get("completeness_trade")),
    )


def _clean_trade(value: Any) -> str | None:
    if value in (None, ""):
        return None
    return str(value)


def _parse_expiry(value: Any) -> datetime | None:
    if value in (None, ""):
        return None
    try:
        parsed = datetime.fromisoformat(str(value).replace("Z", "+00:00"))
    except (TypeError, ValueError):
        raise ValueError("sender expires_at must be an RFC3339 timestamp") from None
    if parsed.tzinfo is None:
        raise ValueError("sender expires_at must include a timezone")
    return parsed.astimezone(timezone.utc)


def development_registry(token: str) -> SenderRegistry:
    """A single permissive sender, for tests and local development.

    Accepts any tenant. Not a production configuration — production binds each
    sender to the tenants it may write for via ``AUDIT_CORE_SENDERS``.
    """
    return SenderRegistry([
        SenderIdentity(
            name="development",
            tokens=(token,),
            sources=frozenset({"user-engine"}),
            tenants=frozenset({WILDCARD}),
            may_read=True,
        )
    ])