"""Pipeline data types for the multi-agent diagnose pipeline."""
from __future__ import annotations

from dataclasses import dataclass
from typing import Literal

SeverityLabel = Literal["CRITICAL", "ERROR", "WARN", "INFO", "DEBUG", "UNKNOWN"]


@dataclass
class EventCluster:
    cluster_id: str
    entries: list[str]           # entry_id refs
    start_iso: str | None
    end_iso: str | None
    duration_seconds: float
    source_ids: list[str]
    pattern_tags: list[str]
    severity: SeverityLabel      # highest severity from raw text
    burst: bool
    gap_before_seconds: float
    representative_text: str


@dataclass
class TimelineResult:
    clusters: list[EventCluster]
    total_entries: int
    window_start: str | None
    window_end: str | None
    gap_count: int
    burst_count: int
    dominant_sources: list[str]


@dataclass
class ClassifiedTimeline:
    timeline: TimelineResult
    cluster_severities: dict[str, SeverityLabel]
    classifier_used: Literal["ml", "pattern_tags", "regex"]
    model_id: str | None


@dataclass
class Hypothesis:
    hypothesis_id: str
    title: str
    description: str
    confidence: float
    supporting_cluster_ids: list[str]
    runbook_refs: list[str]
    severity: SeverityLabel


@dataclass
class RankedHypothesis:
    hypothesis: Hypothesis
    novelty_score: float
    similarity_to_known: float
    suppress: bool
    suppression_reason: str | None