"""Silent Knowledge Pass — recognise everything possible BEFORE asking a single question (Phase 0).

The Advisor can say "I need 5 answers" but does not yet decide WHAT it can find out by itself. The Silent
Pass runs first: from signals that existing scanners/parsers already produce (website, repository,
documents, product data) it deterministically derives capabilities the company demonstrably HAS and
product facts that drive scope — so every recognised item shrinks the delta and removes a question.

The customer then experiences "we already recognised 11 of 17 — only these 4 remain" instead of a
question wall. This is NOT new architecture: it is one orchestration step in front of the Advisor
  Company -> Silent Intake -> Company Profile -> Hypotheses -> Delta -> Top Questions
All building blocks already exist. SIGNALS are INJECTED (the scanners produce them); the signal->capability
map is curated DATA, also injected. Pure, deterministic, no I/O. Python 3.9 compatible.
"""

from __future__ import annotations

from typing import Dict, List, Optional, Sequence, Set

from pydantic import BaseModel, Field


class IntakeSignal(BaseModel):
    """One finding a scanner/parser produced (no LLM here — the scanners are upstream)."""

    source: str                                 # website / repository / document / product
    signal: str                                 # signal id, e.g. "sbom_file_found"
    detail: str = ""                            # optional (url, filename) for the audit trail


class SignalMapping(BaseModel):
    """Curated: what a signal lets us conclude. A signal yields a capability OR a product fact."""

    signal: str
    capability: Optional[str] = None            # capability the signal evidences
    relationship: str = "detected"              # detected (concrete artifact) / partial (indicative)
    evidence: Optional[str] = None              # the artifact found (already in hand -> no upload needed)
    product_fact: Optional[str] = None          # e.g. "connected_to_internet"
    fact_value: str = "true"


class DetectedCapability(BaseModel):
    capability: str
    relationship: str = "detected"
    source: str = ""                            # which signal/source detected it (audit trail)
    evidence: Optional[str] = None


class ProductFact(BaseModel):
    key: str
    value: str = "true"
    source: str = ""


class SilentIntakeResult(BaseModel):
    detected_capabilities: List[DetectedCapability] = Field(default_factory=list)
    product_facts: List[ProductFact] = Field(default_factory=list)
    evidence_found: List[str] = Field(default_factory=list)
    summary: str = ""

    def capability_ids(self) -> List[str]:
        """The detected capability ids — fed into the Advisor as already-present (delta-reducing)."""
        return sorted({d.capability for d in self.detected_capabilities})


def silent_intake(
    signals: Sequence[IntakeSignal], signal_map: Sequence[SignalMapping]
) -> SilentIntakeResult:
    """Derive capabilities + product facts from injected scanner signals (deterministic, no questions).

    Each signal is matched to curated mappings by `signal` id; a mapping contributes either a detected
    capability (+ optional evidence already in hand) or a product fact. Deduped, deterministic order.
    """
    by_signal: Dict[str, List[SignalMapping]] = {}
    for m in signal_map:
        by_signal.setdefault(m.signal, []).append(m)

    caps: Dict[str, DetectedCapability] = {}
    facts: Dict[str, ProductFact] = {}
    evidence: Set[str] = set()
    for s in signals:
        for m in by_signal.get(s.signal, []):
            if m.capability and m.capability not in caps:
                caps[m.capability] = DetectedCapability(
                    capability=m.capability, relationship=m.relationship,
                    source="%s:%s" % (s.source, s.signal), evidence=m.evidence)
                if m.evidence:
                    evidence.add(m.evidence)
            if m.product_fact:
                facts[m.product_fact] = ProductFact(key=m.product_fact, value=m.fact_value, source=s.source)

    detected = [caps[k] for k in sorted(caps)]
    product_facts = [facts[k] for k in sorted(facts)]
    summary = (
        "Stille Vorbefüllung: %d Fähigkeit(en) automatisch erkannt, %d Produktfakt(en), %d Nachweis(e) bereits vorhanden."
        % (len(detected), len(product_facts), len(evidence))
    )
    return SilentIntakeResult(
        detected_capabilities=detected, product_facts=product_facts,
        evidence_found=sorted(evidence), summary=summary)