"""
MemoryService — conversation / memoir 的统一门面。

- ingest_transcript: transcript -> memory_sources, chunks, embedding
- ingest 后可选：LLM 富化（session/rolling 摘要、事实、时间线）
- retrieve: 委托 HybridRetriever 返回 evidence bundle（向量 chunks）

Celery 侧使用 `ingest_transcript_sync` + `retrieve_evidence_sync`，与异步路径对齐见
`api/docs/memory-retrieval.md`。
"""

from sqlalchemy.ext.asyncio import AsyncSession

from app.core.logging import get_logger
from app.features.memory.chunker import chunk_transcript
from app.features.memory.repo import (
    create_chunk,
    create_curation_action,
    create_source,
    set_chunk_excluded,
    set_memory_fact_status,
    update_chunk_embedding,
)
from app.features.conversation.lineage_schemas import primary_user_message_id_from_lineage
from app.features.memory.schemas import EvidenceBundle
from app.ports.embedding import EmbeddingProvider

logger = get_logger(__name__)


class MemoryService:
    def __init__(
        self,
        db: AsyncSession,
        *,
        embedding_provider: EmbeddingProvider | None = None,
    ):
        self._db = db
        self._embedding = embedding_provider

    async def ingest_transcript(
        self,
        user_id: str,
        conversation_id: str,
        transcript: str,
        *,
        lineage_json: dict | None = None,
    ) -> str:
        """
        Ingest conversation transcript into memory.
        Creates MemorySource, chunks, populates embedding.
        Returns source_id.
        """
        if not transcript or not transcript.strip():
            raise ValueError("transcript cannot be empty")

        primary_mid = (
            primary_user_message_id_from_lineage(lineage_json)
            if lineage_json
            else None
        )
        source = await create_source(
            self._db,
            user_id=user_id,
            source_type="transcript",
            raw_text=transcript.strip(),
            conversation_id=conversation_id,
            lineage_json=lineage_json,
            primary_user_message_id=primary_mid,
        )

        chunks_text = chunk_transcript(transcript.strip())
        chunk_records = []
        for i, content in enumerate(chunks_text):
            chunk = await create_chunk(
                self._db,
                source_id=source.id,
                user_id=user_id,
                content=content,
                chunk_index=i,
            )
            chunk_records.append((chunk.id, content))

        await self._db.flush()

        from app.core.config import settings

        vectors_written = 0
        # Embedding: 若有 provider 则写入
        if self._embedding and chunk_records:
            texts = [c for _, c in chunk_records]
            embeddings = await self._embedding.embed_texts(texts)
            for (chunk_id, _), emb in zip(chunk_records, embeddings):
                if emb:
                    vectors_written += 1
                    await update_chunk_embedding(self._db, chunk_id, emb)

        enrichment_ok: bool | None = None
        try:
            from app.core.dependencies import get_llm_provider_fast
            from app.features.memory.enrichment import enrich_memory_after_ingest_async

            if settings.memory_enrichment_enabled:
                llm = get_llm_provider_fast().langchain_llm
                await enrich_memory_after_ingest_async(
                    self._db, user_id, source.id, llm
                )
                enrichment_ok = True
        except Exception as e:
            if settings.memory_enrichment_enabled:
                enrichment_ok = False
            logger.warning(
                "memory enrichment 跳过: {} exc_type={}", e, type(e).__name__
            )

        await self._db.commit()
        emb_ok = self._embedding.is_available() if self._embedding else False
        logger.info(
            "event=memory_ingest_done user_id={} conversation_id={} source_id={} "
            "chunks={} vectors_written={} embedding_available={} enrichment_enabled={} enrichment_ok={}",
            user_id,
            conversation_id,
            source.id,
            len(chunk_records),
            vectors_written,
            emb_ok,
            settings.memory_enrichment_enabled,
            enrichment_ok,
        )
        return source.id

    async def retrieve(
        self, user_id: str, query: str, *, top_k: int = 10
    ) -> EvidenceBundle:
        """Retrieve relevant evidence. 委托 HybridRetriever。"""
        from app.features.memory.retriever import HybridRetriever

        retriever = HybridRetriever(self._db, embedding_provider=self._embedding)
        raw = await retriever.retrieve(user_id=user_id, query=query, top_k=top_k)
        bundle = EvidenceBundle.model_validate(raw)
        bd = bundle.model_dump()
        vec_ok = self._embedding.is_available() if self._embedding else False
        logger.info(
            "event=memory_retrieve_done user_id={} query_len={} top_k={} "
            "chunks={} facts={} summaries={} timeline={} stories={} vector_ok={}",
            user_id,
            len((query or "").strip()),
            top_k,
            len(bd.get("relevant_chunks") or []),
            len(bd.get("relevant_facts") or []),
            len(bd.get("relevant_summaries") or []),
            len(bd.get("timeline_hints") or []),
            len(bd.get("relevant_stories") or []),
            vec_ok,
        )
        return bundle

    async def exclude_chunk(
        self, user_id: str, chunk_id: str, *, reason: str = ""
    ) -> bool:
        ok = await set_chunk_excluded(self._db, chunk_id, user_id, True)
        if not ok:
            return False
        await create_curation_action(
            self._db,
            user_id=user_id,
            action_type="exclude",
            target_type="chunk",
            target_id=chunk_id,
            details={"reason": reason} if reason else None,
        )
        await self._db.commit()
        return True

    async def restore_chunk(self, user_id: str, chunk_id: str) -> bool:
        ok = await set_chunk_excluded(self._db, chunk_id, user_id, False)
        if not ok:
            return False
        await create_curation_action(
            self._db,
            user_id=user_id,
            action_type="restore",
            target_type="chunk",
            target_id=chunk_id,
            details=None,
        )
        await self._db.commit()
        return True

    async def confirm_fact(self, user_id: str, fact_id: str) -> bool:
        ok = await set_memory_fact_status(self._db, fact_id, user_id, "confirmed")
        if not ok:
            return False
        await create_curation_action(
            self._db,
            user_id=user_id,
            action_type="confirm",
            target_type="fact",
            target_id=fact_id,
            details=None,
        )
        await self._db.commit()
        return True

    async def reject_fact(
        self, user_id: str, fact_id: str, *, reason: str = ""
    ) -> bool:
        ok = await set_memory_fact_status(self._db, fact_id, user_id, "rejected")
        if not ok:
            return False
        await create_curation_action(
            self._db,
            user_id=user_id,
            action_type="reject",
            target_type="fact",
            target_id=fact_id,
            details={"reason": reason} if reason else None,
        )
        await self._db.commit()
        return ok


def ingest_transcript_sync(
    session,
    user_id: str,
    conversation_id: str,
    transcript: str,
    *,
    lineage_json: dict | None = None,
) -> str:
    """
    Sync transcript ingest for Celery tasks.
    Creates source + chunks, and best-effort populates embeddings.
    Returns source_id.
    """
    from app.core.dependencies import get_embedding_provider
    from app.features.memory.chunker import chunk_transcript
    from app.features.memory.repo import (
        create_chunk_sync,
        create_source_sync,
        update_chunk_embedding_sync,
    )

    if not transcript or not transcript.strip():
        raise ValueError("transcript cannot be empty")

    primary_mid = (
        primary_user_message_id_from_lineage(lineage_json) if lineage_json else None
    )
    source = create_source_sync(
        session,
        user_id=user_id,
        source_type="transcript",
        raw_text=transcript.strip(),
        conversation_id=conversation_id,
        lineage_json=lineage_json,
        primary_user_message_id=primary_mid,
    )
    session.flush()

    chunks_text = chunk_transcript(transcript.strip())
    chunk_records: list[tuple[str, str]] = []
    for i, content in enumerate(chunks_text):
        chunk = create_chunk_sync(
            session,
            source_id=source.id,
            user_id=user_id,
            content=content,
            chunk_index=i,
        )
        session.flush()
        chunk_records.append((chunk.id, content))

    from app.core.config import settings

    vectors_written = 0
    embedding_available = False
    enrichment_ok: bool | None = None

    try:
        embedding_provider = get_embedding_provider()
        if embedding_provider is not None:
            embedding_available = embedding_provider.is_available()
    except Exception as e:
        logger.warning(
            "memory embedding provider 不可用(sync): {} exc_type={}",
            e,
            type(e).__name__,
        )
        embedding_provider = None

    # 向量写入在 SAVEPOINT 内；失败仅回滚本段，source/chunks 主体仍可由外层提交。
    # enrichment 已迁移到独立异步任务 (memory_enrichment_tasks.enrich_memory_source)。
    try:
        with session.begin_nested():
            if chunk_records and embedding_provider is not None:
                texts = [content for _, content in chunk_records]
                embeddings = embedding_provider.embed_texts_sync(texts)
                for (chunk_id, _), emb in zip(chunk_records, embeddings):
                    if emb:
                        vectors_written += 1
                        update_chunk_embedding_sync(session, chunk_id, emb)
    except Exception as e:
        logger.warning(
            "memory embedding 跳过(sync): {} exc_type={}",
            e,
            type(e).__name__,
        )

    session.commit()

    if settings.memory_enrichment_enabled:
        try:
            from app.tasks.memory_enrichment_tasks import enrich_memory_source

            enrich_memory_source.delay(user_id, source.id)
            enrichment_ok = True
        except Exception as e:
            enrichment_ok = False
            logger.warning(
                "memory enrichment 任务派发失败: {} exc_type={}",
                e,
                type(e).__name__,
            )

    logger.info(
        "event=memory_ingest_done user_id={} conversation_id={} source_id={} "
        "chunks={} vectors_written={} embedding_available={} enrichment_enabled={} enrichment_ok={} sync=1",
        user_id,
        conversation_id,
        source.id,
        len(chunk_records),
        vectors_written,
        embedding_available,
        settings.memory_enrichment_enabled,
        enrichment_ok,
    )
    return source.id