"""Provider-independent, non-streaming Chat Completions preparation contracts."""

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

from pydantic import BaseModel, Field

from app.schemas.catalog import Input
from app.schemas.indexing import ChunkProvenance


class CompletionOptions(Input):
    model: str = Field(pattern=r"^[A-Za-z0-9][A-Za-z0-9._:/-]{0,127}$")
    output_tokens: int = Field(512, ge=1, le=4096)
    token_parameter: Literal["max_completion_tokens", "max_tokens"] = "max_completion_tokens"
    instruction_role: Literal["system", "developer"] = "system"
    temperature: float | None = Field(None, ge=0, le=2)


class PrepareContext(Input):
    retrieval_run_id: UUID
    completion: CompletionOptions
    max_input_characters: int = Field(10000, ge=1024, le=24000)
    max_evidence: int = Field(5, ge=1, le=10)


class Evidence(ChunkProvenance):
    citation_id: str
    chunk_id: UUID
    chunk_ordinal: int
    retrieval_rank: int
    text: str
    text_sha256: str
    start_offset: int
    end_offset: int


class ExcludedEvidence(BaseModel):
    chunk_id: UUID
    reason: Literal["overlap", "budget", "evidence_limit"]


class ContextRead(BaseModel):
    id: UUID
    kind: Literal["prepared_request"] = "prepared_request"
    model_called: Literal[False] = False
    status: Literal["prepared", "insufficient_evidence"]
    reason: Literal["candidates_available", "no_candidates", "context_budget"]
    retrieval_run_id: UUID
    retrieval_mode: Literal["keyword_chunks", "vector", "hybrid"]
    query: str
    text_index_version_id: UUID
    text_generation: int
    catalog_revision: int
    vector_version_id: UUID | None
    vector_generation: int | None
    corpus_fingerprint: str
    prompt_version: Literal["nalati-evidence-v1"] = "nalati-evidence-v1"
    completion: CompletionOptions
    max_input_characters: int
    input_characters: int
    max_evidence: int
    evidence: list[Evidence]
    excluded: list[ExcludedEvidence]
    request_body: dict | None
    request_sha256: str | None
    created_at: datetime


class CompletionUsage(BaseModel):
    prompt_tokens: int = Field(ge=0, strict=True)
    completion_tokens: int = Field(ge=0, strict=True)
    total_tokens: int = Field(ge=0, strict=True)


class ParsedCompletion(BaseModel):
    status: Literal["answer_candidate", "insufficient_evidence", "incomplete", "refused"]
    completion_id: str
    model: str
    answer: str | None
    citations: list[str]
    usage: CompletionUsage | None