from __future__ import annotations

import httpx

from app.core.config import get_settings
from app.services.knowledge import EvidenceState, GroundedAnswer, KnowledgeHealth, SourceCard

_GROUNDED_ANSWERABILITY = {"answerable", "partially_answerable"}


class RAGcoreKnowledgeProvider:
    """Adapter for the central RAGcore service, against its real `/v1/*` contract
    (see `docs/contracts/openapi.yaml` in the RAGcore checkout -- RAGcore is built and
    owned separately, MobilityOps only ever talks to its documented HTTP API).

    Authenticates as a service account via `Authorization: Bearer <token>` (RAGcore's
    session-cookie auth is for its own browser admin UI only). Any connection error,
    timeout, non-2xx response, or malformed body degrades to `evidence_state:
    "unavailable"` rather than raising -- this is the adapter that actually exercises the
    architecture's reliability boundary: RAGcore failure disables knowledge answers only,
    never fabricates an answer, never affects the rest of the app.

    Known gap, not fixable from this side: RAGcore's ingest pipeline currently tags every
    chunk's `language` payload field as `"en"` regardless of actual document language (the
    `/v1/uploads` contract has no per-file language field for a caller to set correctly).
    Filtering search/answer requests by requested UI language would therefore silently
    exclude genuinely-relevant nl-BE/fr-BE content, so this adapter deliberately does not
    filter by language -- retrieval relies on the embedding model's cross-lingual matching.
    """

    name = "ragcore"

    def __init__(self) -> None:
        self._settings = get_settings()

    def _client(self) -> httpx.Client:
        headers = {}
        if self._settings.ragcore_api_token:
            headers["Authorization"] = f"Bearer {self._settings.ragcore_api_token}"
        return httpx.Client(
            base_url=self._settings.ragcore_base_url,
            headers=headers,
            timeout=self._settings.ragcore_http_timeout_seconds,
        )

    def health(self, language: str = "en-GB") -> KnowledgeHealth:
        try:
            with self._client() as client:
                response = client.get("/health/ready")
                body = response.json()
                available = response.status_code == 200 and body.get("status") == "ok"
                detail = (
                    "RAGcore reachable and ready."
                    if available
                    else f"RAGcore degraded: {body.get('status', 'unknown')}"
                )
        except (httpx.HTTPError, ValueError) as exc:
            available = False
            detail = f"RAGcore unavailable: {type(exc).__name__}: {exc}"
        return KnowledgeHealth(
            provider=self.name,
            available=available,
            detail=detail,
            tenant=self._settings.ragcore_tenant,
            workspace=self._settings.ragcore_workspace,
            collection=self._settings.ragcore_collection,
            # RAGcore's retrieval API has no corpus-size endpoint to query honestly from
            # here; left at 0 rather than approximated from a capped search result count.
            document_count=0,
        )

    def ask(self, question: str, correlation_id: str, language: str = "en-GB") -> GroundedAnswer:
        unavailable = GroundedAnswer(
            answer="",
            evidence_state="unavailable",
            sources=[],
            provider=self.name,
            correlation_id=correlation_id,
        )
        if not self._settings.ragcore_space_id:
            return unavailable

        try:
            with self._client() as client:
                response = client.post(
                    "/v1/answers",
                    json={
                        "query": question,
                        "requested_space_ids": [self._settings.ragcore_space_id],
                    },
                )
                if response.status_code != 200:
                    return unavailable
                body = response.json()
        except (httpx.HTTPError, ValueError):
            return unavailable

        try:
            citations = {c["id"]: c for c in body.get("citations", [])}
            sources = [
                SourceCard(
                    document_id=str(citation["document_id"]),
                    title=citation["title"],
                    version=str(citation["document_version_id"]),
                    section=citation.get("section") or "",
                    excerpt=citation["excerpt"],
                )
                for citation in citations.values()
            ]
            answerability = body.get("answerability", "not_answerable")
            is_grounded = answerability in _GROUNDED_ANSWERABILITY and sources
            evidence_state: EvidenceState = "grounded" if is_grounded else "insufficient"
            return GroundedAnswer(
                answer=body.get("answer", "") if evidence_state == "grounded" else "",
                evidence_state=evidence_state,
                sources=sources if evidence_state == "grounded" else [],
                provider=self.name,
                correlation_id=correlation_id,
            )
        except (TypeError, KeyError, ValueError):
            return unavailable