mindnet/app/models/dto.py

"""
FILE: app/models/dto.py
DESCRIPTION: Pydantic-Modelle (DTOs) für Request/Response Bodies. Definiert das API-Schema.
VERSION: 0.6.4 (WP-22 Semantic Graph Routing, Lifecycle & Provenance)
STATUS: Active
DEPENDENCIES: pydantic, typing, uuid
LAST_ANALYSIS: 2025-12-18
"""

from __future__ import annotations
from pydantic import BaseModel, Field
from typing import List, Literal, Optional, Dict, Any
import uuid

# WP-22: Definition der gültigen Kanten-Typen gemäß Manual
EdgeKind = Literal["references", "references_at", "backlink", "next", "prev", "belongs_to", "depends_on", "related_to", "similar_to", "caused_by", "derived_from", "based_on", "solves", "blocks", "uses", "guides"]


# --- Basis-DTOs ---

class NodeDTO(BaseModel):
    """Darstellung eines Knotens (Note oder Chunk) im API-Graph."""
    id: str
    type: Literal["note", "chunk"]
    title: Optional[str] = None
    note_id: Optional[str] = None
    tags: Optional[List[str]] = None
    in_degree: Optional[int] = None
    out_degree: Optional[int] = None
    score: Optional[float] = None
    section_title: Optional[str] = None
    section_path: Optional[str] = None
    path: Optional[str] = None


class EdgeDTO(BaseModel):
    """Darstellung einer Kante im API-Graph."""
    id: str
    kind: str
    source: str
    target: str
    weight: float
    direction: Literal["out", "in", "undirected"] = "out"
    # WP-22: Provenance Tracking (Herkunft und Vertrauen)
    provenance: Optional[Literal["explicit", "rule", "smart", "structure"]] = "explicit"
    confidence: float = 1.0


# --- Request Models ---

class QueryRequest(BaseModel):
    """
    Request für /query.
    """
    mode: Literal["semantic", "edge", "hybrid"] = "hybrid"
    query: Optional[str] = None
    query_vector: Optional[List[float]] = None
    top_k: int = 10
    expand: Dict = {"depth": 1, "edge_types": ["references", "belongs_to", "prev", "next", "depends_on", "related_to"]}
    filters: Optional[Dict] = None
    ret: Dict = {"with_paths": True, "with_notes": True, "with_chunks": True}
    explain: bool = False
    
    # WP-22: Semantic Graph Routing
    # Erlaubt dem Router, Kantengewichte dynamisch zu überschreiben.
    # Format: {"caused_by": 3.0, "related_to": 0.5}
    boost_edges: Optional[Dict[str, float]] = None 


class FeedbackRequest(BaseModel):
    """
    User-Feedback zu einem spezifischen Treffer oder der Gesamtantwort (Basis für WP-08).
    """
    query_id: str = Field(..., description="ID der ursprünglichen Suche")
    # node_id ist optional: Wenn leer oder "generated_answer", gilt es für die Antwort.
    # Wenn eine echte Chunk-ID, gilt es für die Quelle.
    node_id: str = Field(..., description="ID des bewerteten Treffers oder 'generated_answer'")
    # Update: Range auf 1-5 erweitert für differenziertes Tuning
    score: int = Field(..., ge=1, le=5, description="1 (Irrelevant/Falsch) bis 5 (Perfekt)")
    comment: Optional[str] = None


class ChatRequest(BaseModel):
    """
    WP-05: Request für /chat.
    """
    message: str = Field(..., description="Die Nachricht des Users")
    conversation_id: Optional[str] = Field(None, description="Optional: ID für Chat-Verlauf (noch nicht implementiert)")
    # RAG Parameter (Override defaults)
    top_k: int = 5
    explain: bool = False


# --- WP-04b Explanation Models ---

class ScoreBreakdown(BaseModel):
    """Aufschlüsselung der Score-Komponenten nach der WP-22 Formel."""
    semantic_contribution: float
    edge_contribution: float
    centrality_contribution: float
    raw_semantic: float
    raw_edge_bonus: float
    raw_centrality: float
    node_weight: float


class Reason(BaseModel):
    """Ein semantischer Grund für das Ranking."""
    # WP-22: 'lifecycle' hinzugefügt für Status-Begründungen (Draft vs Stable)
    kind: Literal["semantic", "edge", "type", "centrality", "lifecycle"]
    message: str
    score_impact: Optional[float] = None
    details: Optional[Dict[str, Any]] = None


class Explanation(BaseModel):
    """Container für alle Erklärungsdaten eines Treffers."""
    breakdown: ScoreBreakdown
    reasons: List[Reason]
    related_edges: Optional[List[EdgeDTO]] = None


# --- Response Models ---

class QueryHit(BaseModel):
    """Einzelnes Trefferobjekt für /query."""
    node_id: str
    note_id: Optional[str]
    semantic_score: float
    edge_bonus: float
    centrality_bonus: float
    total_score: float
    paths: Optional[List[List[Dict]]] = None
    source: Optional[Dict] = None
    payload: Optional[Dict] = None # Added for flexibility & WP-06 meta-data
    explanation: Optional[Explanation] = None


class QueryResponse(BaseModel):
    """Antwortstruktur für /query."""
    query_id: str = Field(default_factory=lambda: str(uuid.uuid4()))
    results: List[QueryHit]
    used_mode: str
    latency_ms: int


class GraphResponse(BaseModel):
    """Antwortstruktur für /graph/{note_id}."""
    center_note_id: str
    nodes: List[NodeDTO]
    edges: List[EdgeDTO]
    stats: Dict[str, int]


class ChatResponse(BaseModel):
    """
    WP-05/06: Antwortstruktur für /chat.
    """
    query_id: str = Field(..., description="Traceability ID (dieselbe wie für Search)")
    answer: str = Field(..., description="Generierte Antwort vom LLM")
    sources: List[QueryHit] = Field(..., description="Die für die Antwort genutzten Quellen")
    latency_ms: int
    intent: Optional[str] = Field("FACT", description="WP-06: Erkannter Intent (FACT/DECISION)")
    intent_source: Optional[str] = Field("Unknown", description="WP-06: Quelle der Intent-Erkennung (Keyword vs. LLM)")