"""Task B: fact and signal extraction. Pulls discrete, evidence-anchored
signals (hiring, partnerships, leadership, financial, etc.) out of a single
document - the atomic units Task C (synthesis) and Task D (report
generation) later combine."""

from __future__ import annotations

from pydantic import BaseModel, Field

from app.analysis.llm.base import LLMProvider
from app.prompts.base import build_user_prompt

SYSTEM_PROMPT = (
    "You are a competitive intelligence analyst extracting discrete factual signals from a "
    "single document. Extract only what the text actually states or clearly implies - never "
    "add outside knowledge. Every signal must include the exact passage that supports it."
)

_SIGNAL_TYPES = (
    "event, entity, date, location, product, leadership, partnership, hiring, investment, "
    "manufacturing, technology, financial, regulatory, sentiment"
)


class ExtractedSignal(BaseModel):
    signal_type: str = Field(description=f"One of: {_SIGNAL_TYPES}")
    description: str
    supporting_passage: str = Field(description="The exact quote from the document backing this")
    date: str | None = None
    entities: list[str] = Field(default_factory=list)


class ExtractionResult(BaseModel):
    signals: list[ExtractedSignal] = Field(default_factory=list)


async def extract_signals(
    llm: LLMProvider,
    *,
    document_title: str | None,
    document_url: str,
    document_text: str,
) -> ExtractionResult:
    evidence = {
        "document_title": document_title,
        "document_url": document_url,
        "document_text": document_text[:6000],
    }
    user_prompt = build_user_prompt(
        "Extract every discrete factual signal from this document, each anchored to its "
        "exact supporting passage.",
        evidence,
    )
    return await llm.generate_structured(SYSTEM_PROMPT, user_prompt, ExtractionResult)