"""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(frozen=True)
class EventCluster:
    """A time-correlated group of log entries within the timeline."""

    cluster_id: str
    entries: tuple[str, ...]  # entry_id refs
    start_iso: str | None
    end_iso: str | None
    duration_seconds: float
    source_ids: tuple[str, ...]
    pattern_tags: tuple[str, ...]
    severity: SeverityLabel
    burst: bool
    gap_before_seconds: float
    representative_text: str


@dataclass(frozen=True)
class TimelineResult:
    """Structured timeline of event clusters built from log entries."""

    clusters: tuple[EventCluster, ...]
    total_entries: int
    window_start: str | None
    window_end: str | None
    gap_count: int
    burst_count: int
    dominant_sources: tuple[str, ...]


@dataclass(frozen=True)
class ClassifiedTimeline:
    """Timeline annotated with ML-assigned severity per cluster."""

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


@dataclass(frozen=True)
class Hypothesis:
    """A root-cause hypothesis generated by Stage 3."""

    hypothesis_id: str
    title: str
    description: str
    confidence: float
    supporting_cluster_ids: tuple[str, ...]
    runbook_refs: tuple[str, ...]
    severity: SeverityLabel


@dataclass(frozen=True)
class RankedHypothesis:
    """A hypothesis enriched by Stage 4 false-positive suppression."""

    hypothesis: Hypothesis
    novelty_score: float
    similarity_to_known: float
    suppress: bool
    suppression_reason: str | None