"""The stage cache, from the side that needs a database.

The pipeline half — what a hit restores and what a key is made of — is in
`tests/flow/test_runs.py`, which runs without one.
"""

import json

from sqlmodel import Session

from fluksio.core.db import engine as db_engine
from fluksio.flow.artifacts import ArtifactStore
from fluksio.flow.pipeline import NodeOutcome
from fluksio.flow.runs import OUTPUT_CAP, RunCache, _cacheable
from fluksio.models import RunNode


def test_a_run_cache_finds_what_an_earlier_run_recorded(tmp_path):
    """The run history is the cache; there is no second store to keep."""
    store = ArtifactStore(tmp_path / "artifacts")
    reference = store.put([b"payload"], name="data.bin")
    plain, with_artifact, collected = "k-plain", "k-artifact", "k-collected"
    with Session(db_engine) as session:
        session.add(
            RunNode(
                run_id="cache-1",
                node="study.a",
                status="ok",
                cache_key=plain,
                outputs=json.dumps({"study.loss": 1.5}),
            )
        )
        session.add(
            RunNode(
                run_id="cache-2",
                node="study.b",
                status="ok",
                cache_key=with_artifact,
                outputs=json.dumps({"study.data": reference}),
            )
        )
        session.add(
            RunNode(
                run_id="cache-3",
                node="study.c",
                status="ok",
                cache_key=collected,
                outputs=json.dumps(
                    {"study.data": {**reference, "digest": "sha256:" + "1" * 64}}
                ),
            )
        )
        session.commit()

    cache = RunCache(store)
    assert cache.lookup(plain) == (True, {"study.loss": 1.5})
    assert cache.lookup(with_artifact) == (True, {"study.data": reference})
    # Its bytes have gone from the store, so the reference names nothing a
    # restored run could open. That is a miss, not a broken run.
    assert cache.lookup(collected) == (False, None)
    assert cache.lookup("never-seen") == (False, None)
    assert cache.lookup("") == (False, None)


def test_what_may_be_stored_as_a_cache_entry():
    """A row carries a key and its outputs together, or neither."""
    ok = NodeOutcome(
        node="study.a", ok=True, cache_key="k", output_values={"study.loss": 1.0}
    )
    assert _cacheable(ok) == '{"study.loss":1.0}'
    # A node that published nothing is still an answer worth reusing.
    assert _cacheable(ok.model_copy(update={"output_values": None})) == "null"
    # Not cacheable: it failed, it has no key, or it returned too much.
    assert _cacheable(ok.model_copy(update={"ok": False})) is None
    assert _cacheable(ok.model_copy(update={"cache_key": ""})) is None
    big = {"study.data": "x" * (OUTPUT_CAP + 1)}
    assert _cacheable(ok.model_copy(update={"output_values": big})) is None