src/knowledge_extraction/extract/branches.py

"""The four extraction branches. This is the only stage that costs money.

**One call per TERM CLUSTER** — not per mention, not per chunk. That is the
whole economic argument for clustering: 200 mentions of "PA" cost one call, not
200. It is also what makes conflict detection possible, since contradictory
definitions can only be compared when they arrive together.

Each branch returns `(entry, usage)`, with `None` for the entry when the
response fails schema validation. A failed parse is not an exception: one bad
response must not abort a corpus-scale run that has already paid for parsing.
"""

from __future__ import annotations

from ...middlewares.logging import get_logger
from ..ids import brief_id, formula_id, rule_id, term_id
from ..models import (
    CallUsage,
    Chunk,
    DocumentBrief,
    FormulaEntry,
    FormulaVariable,
    GlossaryEntry,
    KeyParameter,
    Provenance,
    RuleCandidate,
    RuleEntry,
    TermCluster,
)
from ..rank import top_k
from ..settings import EVIDENCE_K
from .base import evidence_block, load_prompt
from .schemas import FormulaDraft, GlossaryDraft, RuleDraft, SummaryDraft, schema_for

logger = get_logger("knowledge_extract")


def _prov(draft_prov, doc_id: str, chunk_id: str | None = None) -> Provenance:
    return Provenance(
        doc_id=doc_id,
        span=draft_prov.span,
        page=draft_prov.page,
        section_no=draft_prov.section_no,
        chunk_id=chunk_id,
    )


def _evidence_for(
    cluster: TermCluster, chunks: list[Chunk], k: int, round_index: int
) -> tuple[list[Chunk], list[float]]:
    by_id = {c.chunk_id: c for c in chunks}
    # `chunks` is passed so a linked partner (0.4.0 table pointers) joins the
    # window. `service` passes it to `top_k` too, so the prompt and the span-check
    # source stay identical — that equality is load-bearing, not incidental.
    ids = top_k(cluster, k=k, round_index=round_index, chunks=chunks)
    # Ranked scores only. A partner was LINKED in, not ranked in, so it has no
    # score — `evidence_block` shows none for it, which is the honest rendering.
    scores = cluster.evidence_scores[round_index * k : round_index * k + k]
    return [by_id[i] for i in ids if i in by_id], scores


# ── glossary ────────────────────────────────────────────────────────────


def build_glossary_prompt(
    cluster: TermCluster, chunks: list[Chunk], k: int = EVIDENCE_K, round_index: int = 0
) -> tuple[str, str]:
    evidence, scores = _evidence_for(cluster, chunks, k, round_index)
    user = (
        f"CANDIDATE TERM: {cluster.canonical}\n"
        f"KNOWN VARIANTS: {', '.join(cluster.variants)}\n"
        f"MENTION COUNT: {cluster.mention_count}\n\n"
        + evidence_block(evidence, scores)
    )
    return load_prompt("glossary"), user


def extract_glossary(
    cluster: TermCluster,
    chunks: list[Chunk],
    extractor,
    doc_id: str,
    k: int = EVIDENCE_K,
    round_index: int = 0,
) -> tuple[GlossaryEntry | None, CallUsage]:
    system, user = build_glossary_prompt(cluster, chunks, k, round_index)
    result = extractor.complete(
        "glossary", system, user, schema_for("glossary"), "GlossaryEntry"
    )
    try:
        draft = GlossaryDraft.model_validate(result.data)
    except Exception as exc:
        logger.warning(
            "glossary draft invalid", cluster=cluster.canonical, error=repr(exc)
        )
        return None, result.usage

    evidence, _ = _evidence_for(cluster, chunks, k, round_index)
    entry = GlossaryEntry(
        # Keyed on the CLUSTER canonical, not on what the model returned as
        # `term`: the cluster is the stable thing across runs, and the model is
        # free to answer "PA" or "Physical Availability" for the same cluster.
        term_id=term_id(doc_id, cluster.canonical),
        term=draft.term,
        full_name=draft.full_name,
        source_wording=_heading_wording(cluster, evidence) or draft.source_wording,
        definition=draft.definition,
        subdomain_tags=draft.subdomain_tags,
        mention_count=cluster.mention_count,
        provenance=_prov(
            draft.provenance, doc_id, evidence[0].chunk_id if evidence else None
        ),
    )
    return entry, result.usage


def _heading_wording(cluster: TermCluster, evidence: list[Chunk]) -> str | None:
    """The verbatim heading of the evidence chunk whose title names this term.

    Preferred over whatever the model chose to quote, because the section
    heading is where the document formally names the term. Measured on the
    reference standard: the model quoted "Physical Availability (PA)" from the
    page-1 intro — a real verbatim quote — while the section itself is headed
    "Physical **of** Availability (PA)". Both occur in the document; only the
    heading form reveals that the two disagree.

    Recording the literal form is a locked decision: the discrepancy belongs to
    the expert, not to us. Taking it deterministically rather than asking the
    model to volunteer it means it cannot be normalised away.
    """
    from ..cluster.normalize import normalize
    from ..rank.evidence import _word_match

    variants = [normalize(v) for v in cluster.variants]
    for chunk in evidence:
        heading = chunk.heading
        if heading and any(_word_match(v, normalize(heading)) for v in variants):
            return heading
    return None


# ── rule of thumb ───────────────────────────────────────────────────────


def extract_rule(
    candidate: RuleCandidate, chunk: Chunk, extractor, doc_id: str
) -> tuple[RuleEntry | None, CallUsage]:
    user = (
        f"CUE: {candidate.cue}\n\n"
        + evidence_block([chunk])
        + f"\n\nFOCUS PASSAGE:\n{candidate.snippet}"
    )
    result = extractor.complete(
        "rule", load_prompt("rule"), user, schema_for("rule"), "RuleEntry"
    )
    try:
        draft = RuleDraft.model_validate(result.data)
    except Exception as exc:
        logger.warning("rule draft invalid", chunk_id=candidate.chunk_id, error=repr(exc))
        return None, result.usage

    return (
        RuleEntry(
            # From the cue's position in the document, never from the model.
            rule_id=rule_id(doc_id, candidate.chunk_id, candidate.char_start),
            rule_type=draft.rule_type,
            statement=draft.statement,
            condition=draft.condition,
            consequence=draft.consequence,
            provenance=_prov(draft.provenance, doc_id, chunk.chunk_id),
        ),
        result.usage,
    )


# ── formula ─────────────────────────────────────────────────────────────


def extract_formula(
    chunk: Chunk, extractor, doc_id: str
) -> tuple[FormulaEntry | None, CallUsage]:
    user = evidence_block([chunk])
    result = extractor.complete(
        "formula", load_prompt("formula"), user, schema_for("formula"), "FormulaEntry"
    )
    try:
        draft = FormulaDraft.model_validate(result.data)
    except Exception as exc:
        logger.warning("formula draft invalid", chunk_id=chunk.chunk_id, error=repr(exc))
        return None, result.usage

    return (
        FormulaEntry(
            formula_id=formula_id(
                doc_id, draft.name, draft.formula_latex, chunk.chunk_id
            ),
            name=draft.name,
            formula_latex=draft.formula_latex,
            # `term_id` is left null here and resolved by `link.py`, which is the
            # only place that can see the glossary.
            variables=[
                FormulaVariable(symbol=v.symbol, meaning=v.meaning) for v in draft.variables
            ],
            unit=draft.unit,
            provenance=_prov(draft.provenance, doc_id, chunk.chunk_id),
        ),
        result.usage,
    )


# ── summary ─────────────────────────────────────────────────────────────


def extract_summary(
    chunks: list[Chunk], extractor, doc_id: str
) -> tuple[DocumentBrief | None, CallUsage]:
    """Whole-document summary — the quiet cost risk. Few calls, but a large
    share of all input tokens, because summarisation cannot be filtered: it
    needs the whole document.

    It is also the only branch that cannot be span-checked at all. A plausible
    summary is indistinguishable from a correct one, which is exactly why it
    belongs on a larger tier as soon as one exists.
    """
    user = evidence_block(chunks)
    result = extractor.complete(
        "summary", load_prompt("summary"), user, schema_for("summary"), "DomainContext"
    )
    try:
        draft = SummaryDraft.model_validate(result.data)
    except Exception as exc:
        logger.warning("summary draft invalid", error=repr(exc))
        return None, result.usage

    return (
        DocumentBrief(
            brief_id=brief_id(doc_id),
            title=draft.title,
            purpose_verbatim=draft.purpose_verbatim,
            # `outline` is derived from the chunks by the caller, not asked of
            # the model — see `service._document_outline`.
            key_parameters=[
                KeyParameter(surface=surface) for surface in draft.key_parameters
            ],
            provenance=_prov(draft.provenance, doc_id),
        ),
        result.usage,
    )