"""`/search` core -- module 5 phase 4 (docs/kb/modules/05-faza4-plan.md §4). Kept decoupled
from FastAPI so it can be unit-tested with fake `conn`/`session` objects, the same style as
`kb_retrieval`'s own tests, instead of needing a live DB/Ollama behind a TestClient.

Response shape (plan §4 exactly): `{"query", "mode", "sol_status", "results": [...]}`, each
result carrying `dist` un-filtered -- the 0.45/0.55 colour thresholds (plan §7) are a frontend
concern (Krok 4, out of this step's scope), never applied server-side.

`summary`/`summary_tags` (document_summary, haiku track) are an additive field added in Krok 4
for the frontend's per-envelope result header (plan §7) -- `None`/`[]` when the envelope has no
summary for `summary_model` yet. Purely additive: does not change any field already covered by
the phase-4 gate's HTTP-equivalence check (plan §9).

Embed fallback (plan §2 decision 2 / §5, `app/fallback.py`): the query embedding is computed
once via `embed_with_fallback` (SOLARIA, or PIHA if SOLARIA is down/times out), then handed to
`kb_retrieval`'s `*_retrieve` functions as a plain vector literal -- `flat_query`/`cascade_query`/
`hybrid_query` (which embed *and* retrieve in one call) are deliberately bypassed here so the
fallback decision lives entirely in this HTTP layer, per this task's constraint of zero changes
to `kb_retrieval`'s retrieval logic. `sol_status` in the response is the real outcome of that
call, not a hardcoded "up".
"""
from __future__ import annotations

import aiohttp
import asyncpg

from kb_retrieval.embed import _vector_literal
from kb_retrieval.retrieval import cascade_retrieve, flat_retrieve, hybrid_retrieve

from app.db import fetch_envelopes, fetch_summaries
from app.fallback import SolCircuitBreaker, embed_with_fallback
from app.links import build_result


async def run_search(
    conn: asyncpg.Connection,
    session: aiohttp.ClientSession,
    breaker: SolCircuitBreaker,
    solaria_url: str,
    piha_url: str,
    query_text: str,
    mode: str,
    embed_model: str,
    summary_model: str,
) -> dict:
    embedding, sol_status = await embed_with_fallback(
        breaker, session, solaria_url, piha_url, embed_model, query_text
    )
    query_vector = _vector_literal(embedding)

    if mode == "flat":
        chunks = await flat_retrieve(conn, query_vector)  # flat_retrieve returns a plain list
    elif mode == "hybrid":
        chunks = (await hybrid_retrieve(conn, query_vector, summary_model=summary_model))["chunks"]
    else:
        chunks = (await cascade_retrieve(conn, query_vector, summary_model=summary_model))["chunks"]

    envelope_ids = sorted({c["envelope_id"] for c in chunks})
    envelopes = await fetch_envelopes(conn, envelope_ids)
    summaries = await fetch_summaries(conn, envelope_ids, summary_model)

    results = []
    for chunk in chunks:
        result = build_result(chunk, envelopes.get(chunk["envelope_id"]))
        summary = summaries.get(chunk["envelope_id"])
        result["summary"] = summary["summary"] if summary else None
        result["summary_tags"] = summary["tags"] if summary else []
        results.append(result)

    return {
        "query": query_text,
        "mode": mode,
        "sol_status": sol_status,
        "results": results,
    }