from datetime import datetime
from typing import Literal
from uuid import UUID

from pydantic import BaseModel, ConfigDict, Field

from app.schemas.catalog import Category, Input
from app.schemas.indexing import TimestampRead
from app.schemas.retrieval import RetrievalHit


class EmbeddingSpecRead(BaseModel):
    model: str
    revision: str
    dimension: int
    token_limit: int
    query_instruction: str
    implementation: str
    checkpoint_format: str


class SpaceRead(BaseModel):
    model_config = ConfigDict(from_attributes=True)
    id: str
    dimension: int
    spec: EmbeddingSpecRead


class BuildVectors(Input):
    text_index_version_id: UUID


class VectorRead(TimestampRead):
    id: UUID
    text_index_version_id: UUID
    space_id: str
    dimension: int
    chunk_count: int
    status: Literal["ready", "published", "superseded"]
    created_by: int
    created_at: datetime
    published_at: datetime | None


class ActiveVectors(BaseModel):
    generation: int
    text_generation: int
    catalog_revision: int
    is_current: bool
    active_version: VectorRead | None


class VectorRequest(Input):
    query: str = Field(min_length=1, max_length=500)
    mode: Literal["vector"] = "vector"
    top_k: int = Field(5, ge=1, le=20)
    category: Category | None = None


class VectorHit(RetrievalHit):
    chunk_id: UUID
    chunk_ordinal: int


class VectorRetrievalConfig(BaseModel):
    scorer: Literal["pgvector-cosine-exact-v1"] = "pgvector-cosine-exact-v1"
    ranking_unit: Literal["chunk"] = "chunk"
    space: SpaceRead


class VectorRetrievalResponse(BaseModel):
    run_id: UUID
    query: str
    mode: Literal["vector"] = "vector"
    status: Literal["ok", "no_evidence"]
    top_k: int
    category: str | None
    vector_version_id: UUID
    text_index_version_id: UUID
    generation: int
    text_generation: int
    corpus_fingerprint: str
    corpus_size: int
    total_hits: int
    results: list[VectorHit]
    elapsed_ms: float
    created_at: datetime
    config: VectorRetrievalConfig