leocrm/app/ai/knowledge_sources.py

"""Knowledge source registry — manages available evidence sources for AI."""

from __future__ import annotations

from dataclasses import dataclass
from typing import Any


@dataclass
class EvidenceReference:
    """A reference to a piece of evidence from a knowledge source."""
    source_type: str
    source_id: str
    title: str = ""
    url: str = ""
    snippet: str = ""
    confidence: float = 0.0

    def to_dict(self) -> dict[str, Any]:
        return {
            "source_type": self.source_type,
            "source_id": self.source_id,
            "title": self.title,
            "url": self.url,
            "snippet": self.snippet,
            "confidence": self.confidence,
        }

    def to_workstream_block(self) -> dict[str, Any]:
        return {
            "type": "evidence_card",
            "source_type": self.source_type,
            "source_id": self.source_id,
            "title": self.title,
            "url": self.url,
            "snippet": self.snippet,
            "confidence": self.confidence,
        }


_AVAILABLE_SOURCES = [
    {"type": "wiki", "text_field": "content", "title_field": "title", "status_filter": {"status": "published"}, "retention_days": 0},
    {"type": "dms", "text_field": "content_text", "title_field": "name", "status_filter": None, "retention_days": 365},
    {"type": "mail", "text_field": "body", "title_field": "subject", "status_filter": None, "retention_days": 180},
    {"type": "communication", "text_field": "content", "title_field": "title", "status_filter": None, "retention_days": 90},
]

_SOURCES_BY_TYPE = {s["type"]: s for s in _AVAILABLE_SOURCES}


def get_available_sources() -> list[dict[str, Any]]:
    """Return list of available knowledge sources."""
    return _AVAILABLE_SOURCES


def get_source_config(source: str) -> dict[str, Any] | None:
    """Return configuration for a specific knowledge source."""
    return _SOURCES_BY_TYPE.get(source)


def build_evidence_references(results: list[dict[str, Any]], max_results: int | None = None) -> list[EvidenceReference]:
    """Build evidence references from search results, sorted by confidence descending."""
    refs = [
        EvidenceReference(
            source_type=r.get("source_type", ""),
            source_id=r.get("source_id", ""),
            title=r.get("title", ""),
            url=r.get("url", ""),
            snippet=r.get("snippet", ""),
            confidence=r.get("score", 0.0),
        )
        for r in results
    ]
    refs.sort(key=lambda x: x.confidence, reverse=True)
    if max_results is not None:
        refs = refs[:max_results]
    return refs