interactive-story/backend/tests/test_m11_findings.py

"""M11: the post-M8 playtest findings, on the backend side.

Findings A and B are browser-only and are tested in `frontend/src/m11.test.jsx`.
This file covers finding C, which is half a browser change and half a prompt
change, and the structural fact finding D asks M11 to check first.

**Finding C, in one sentence:** the campaign's narration-length choice became an
English sentence in the instructions and moved no number, while the numeric hint
the model actually reads was derived from the *global* reply cap and therefore
said the same thing — "must not exceed 506 words, and it should not stop short of
about 177" — whether the reader chose brief, medium or long.

    python -m pytest tests/test_m11_findings.py -v
"""

import pytest
from fastapi import Depends
from fastapi.testclient import TestClient

from app import auth, bundle, limits, models
from app.context import builder
from app.database import Base, SessionLocal, engine, get_db
from app.main import app
from app.narrative import model as nmodel
from app.routers import adventures

from fakes import ScriptedProvider


@pytest.fixture()
def client(monkeypatch):
    Base.metadata.create_all(bind=engine)
    setup = SessionLocal()
    user = models.User(is_guest=False, email="m11f@example.com")
    setup.add(user)
    setup.flush()
    setup.add(models.Settings(
        user_id=user.id, model="test-model", embedding_model="",
        context_token_budget=16384, max_output_tokens=800,
    ))
    setup.commit()
    user_id = user.id
    setup.close()
    monkeypatch.setattr(limits, "check_row_cap", lambda *a, **k: None)
    monkeypatch.setattr(adventures.turns, "OpenAICompatibleProvider", ScriptedProvider)
    app.dependency_overrides[auth.get_current_user] = (
        lambda db=Depends(get_db): db.get(models.User, user_id)
    )
    test_client = TestClient(app)
    try:
        yield test_client
    finally:
        app.dependency_overrides.clear()
        adventures.turns._active_turns.clear()
        Base.metadata.drop_all(bind=engine)


def _campaign(client, **fields):
    body = {"title": "Length", "opening": "Rain over Westhaven."} | fields
    response = client.post("/api/adventures", json=body)
    assert response.status_code == 201, response.text[:300]
    return response.json()


def _hint_for(length, cap=800):
    return builder.length_hint(cap, length)


def _numbers(hint):
    import re
    return [int(n) for n in re.findall(r"\b(\d+)\b", hint)]


# ------------------------------------------------ finding C: the defect itself

def test_the_three_lengths_no_longer_say_the_same_thing():
    """The finding, as a test that would have failed before M11.

    At the default 800-token cap every length produced the identical sentence.
    Now each produces a different ceiling, and they are ordered the way the
    words are.
    """
    brief, medium, long = (_hint_for(x) for x in ("brief", "medium", "long"))
    assert brief != medium != long
    assert brief != long
    ceilings = [_numbers(h)[0] for h in (brief, medium, long)]
    assert ceilings == sorted(ceilings), ceilings
    assert len(set(ceilings)) == 3


def test_a_campaign_with_no_preference_reads_exactly_as_it_did_before():
    """No existing campaign's prompt changes under the migration.

    The empty value is the pre-M11 behaviour, unchanged — which is what makes a
    backfill unnecessary rather than merely inconvenient.
    """
    assert _hint_for("") == builder.length_hint(800)


def test_the_reply_cap_still_wins_over_the_band():
    """A long campaign on a small cap gets the cap's number, not the band's.

    The cap is what the endpoint will actually emit, so a hint that asked for
    more would be asking for a truncated turn — and the state block is emitted
    last, so a truncated turn loses its state.
    """
    long_on_small_cap = _hint_for("long", cap=300)
    assert _numbers(long_on_small_cap)[0] <= _numbers(builder.length_hint(300))[0]


def test_the_band_narrows_rather_than_widens_the_cap():
    for length in ("brief", "medium", "long"):
        banded = _numbers(_hint_for(length, cap=800))[0]
        unbanded = _numbers(builder.length_hint(800))[0]
        assert banded <= unbanded, length


def test_every_hint_still_protects_the_state_block():
    """The invariant the old hint had, kept by the new one."""
    for length in ("", "brief", "medium", "long"):
        assert "state block" in _hint_for(length)


def test_an_unknown_length_falls_back_rather_than_inventing_a_band():
    assert _hint_for("epic") == builder.length_hint(800)


# ------------------------------------------- finding C: it reaches the prompt

def test_the_choice_is_stored_and_returned(client):
    campaign = _campaign(client, narration_length="brief")
    assert campaign["narration_length"] == "brief"
    assert client.get(f"/api/adventures/{campaign['id']}").json()[
        "narration_length"] == "brief"


def test_the_choice_can_be_changed_afterwards(client):
    campaign = _campaign(client, narration_length="brief")
    updated = client.patch(f"/api/adventures/{campaign['id']}",
                           json={"narration_length": "long"})
    assert updated.status_code == 200, updated.text[:300]
    assert updated.json()["narration_length"] == "long"


def test_a_length_the_builder_cannot_serve_is_refused(client):
    """A closed set, because an unknown value would silently mean 'no effect'."""
    response = client.post("/api/adventures", json={
        "title": "Bad", "opening": "x", "narration_length": "epic"})
    assert response.status_code == 422


def test_the_stored_prompt_carries_the_campaigns_own_range(client):
    """End to end: two campaigns, two choices, two different prompts."""
    from sqlalchemy.orm import undefer

    seen = {}
    for length in ("brief", "long"):
        campaign = _campaign(client, narration_length=length)
        ScriptedProvider.replies = ["The rain does not let up."]
        assert client.post(f"/api/adventures/{campaign['id']}/actions",
                           json={"type": "do", "text": "look"}).status_code == 200
        with SessionLocal() as db:
            action = (
                db.query(models.Action)
                .filter(models.Action.adventure_id == campaign["id"],
                        models.Action.type == "ai")
                .options(undefer(models.Action.context_snapshot))
                .order_by(models.Action.id.desc()).first()
            )
        hint = next(s for s in action.context_snapshot["sections"]
                    if s["label"] == "length_hint")
        seen[length] = _numbers(hint["text"])[0]
    assert seen["brief"] < seen["long"], seen


def test_the_choice_travels_in_the_bundle(client):
    campaign = _campaign(client, narration_length="long")
    exported = client.get(f"/api/adventures/{campaign['id']}/export").json()
    assert exported["narrationLength"] == "long"
    copy_id = client.post("/api/adventures/import", json=exported).json()["id"]
    assert client.get(f"/api/adventures/{copy_id}").json()["narration_length"] == "long"


def test_a_bundle_naming_a_length_this_build_cannot_serve_drops_it(client):
    campaign = _campaign(client, narration_length="long")
    payload = client.get(f"/api/adventures/{campaign['id']}/export").json()
    payload["narrationLength"] = "cinematic"
    copy_id = client.post("/api/adventures/import", json=payload).json()["id"]
    # Empty rather than stored: a preference the builder ignores is
    # indistinguishable from the defect this milestone fixed.
    assert client.get(f"/api/adventures/{copy_id}").json()["narration_length"] == ""


def test_an_older_bundle_with_no_length_imports_unchanged(client):
    campaign = _campaign(client, narration_length="long")
    payload = client.get(f"/api/adventures/{campaign['id']}/export").json()
    del payload["narrationLength"]
    copy_id = client.post("/api/adventures/import", json=payload).json()["id"]
    assert client.get(f"/api/adventures/{copy_id}").json()["narration_length"] == ""


# ------------------- C04: a correction that is partly refused says so (M11-1)

def test_a_partly_refused_correction_reports_what_did_not_apply(client):
    """The defect the identity diagnostic surfaced, as a regression.

    A correction of two changes where one names a location that does not exist:
    the good one lands, the bad one does not, and **before M11 the answer was an
    unqualified 201**. The reader was told nothing, and went on believing they
    had set a scene they had not.

    `validate.py` already said this must not happen — "what is never allowed is
    a rejected event mutating anything, or **a rejection being silent**" — and
    the refusal was recorded on the proposal for the audit trail. What was
    missing was telling the person who made the correction. Partial application
    itself is deliberate and is unchanged: losing three good changes to one typo
    would be worse.
    """
    campaign = _campaign(client)
    response = client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [
            {"type": "create_entity", "entity": "mara",
             "entity_type": "character", "name": "Mara"},
            {"type": "set_scene", "summary": "In the hall.",
             "location": "nowhere", "present": ["mara"]},
        ],
        "note": "one good, one bad",
    })
    assert response.status_code == 201, response.text[:300]
    body = response.json()

    # The good change landed.
    assert "mara" in body["document"]["entities"]
    # The bad one did not, and the caller is told which and why.
    assert body["document"].get("scene") in ({}, None)
    assert len(body["refused"]) == 1, body["refused"]
    refusal = body["refused"][0]
    assert refusal["event"]["type"] == "set_scene"
    assert refusal["reason"] == "unknown_reference"
    assert "nowhere" in refusal["detail"]


def test_a_correction_that_fully_applies_reports_nothing_refused(client):
    """The control: `refused` is empty when nothing was refused."""
    campaign = _campaign(client)
    response = client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [{"type": "create_entity", "entity": "mara",
                    "entity_type": "character", "name": "Mara"}],
        "note": "",
    })
    assert response.status_code == 201
    assert response.json()["refused"] == []


def test_a_wholly_refused_correction_is_still_a_400(client):
    """Unchanged: nothing applied is an error, not a success with a note."""
    campaign = _campaign(client)
    response = client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [{"type": "set_scene", "summary": "x", "location": "nowhere"}],
        "note": "",
    })
    assert response.status_code == 400
    assert "nowhere" in response.json()["detail"]


def test_the_refusal_is_still_recorded_for_the_audit_trail(client):
    """The half that already worked keeps working: §8's proposal record."""
    campaign = _campaign(client)
    client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [
            {"type": "create_entity", "entity": "mara",
             "entity_type": "character", "name": "Mara"},
            {"type": "set_scene", "summary": "In the hall.", "location": "nowhere"},
        ],
        "note": "",
    })
    with SessionLocal() as db:
        # `detail` is deferred, so it is read inside the session — reading it
        # after the session closed is how the first version of this test failed.
        rows = [
            (p.status, repr(p.detail))
            for p in db.query(models.StateProposal).filter(
                models.StateProposal.adventure_id == campaign["id"]).all()
        ]
    partial = [row for row in rows if row[0] == "partially_accepted"]
    assert partial, [row[0] for row in rows]
    # And the reason is on the record, not only the verdict.
    assert "nowhere" in partial[0][1]


# --------------------------------- finding D: the structural fact to check first

def test_two_entities_may_still_share_a_display_name(client):
    """Recorded, not fixed — and the distinction matters.

    The finding says to check this first: the narrative state keys entities by
    the model-supplied id and `DUPLICATE_ENTITY` rejects only a repeated *key*,
    so two characters can be created with the same `name` and nothing says so.
    That is one of the finding's candidate failure modes.

    It is **not** made an error here. Two people called Alice is an ordinary
    thing for a story to contain, and refusing it would refuse legitimate
    fiction to guard against a model mistake. What M11 adds instead is
    *detection*: `nmodel.duplicate_names` reports it, the identity diagnostic
    (`tools/m11_identity.py`) reads that report, and the reader's State panel
    can show it. This test pins the permissive behaviour so a later milestone
    changes it deliberately rather than by accident.
    """
    campaign = _campaign(client)
    response = client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [
            {"type": "create_entity", "entity": "alice_1",
             "entity_type": "character", "name": "Alice"},
            {"type": "create_entity", "entity": "alice_2",
             "entity_type": "character", "name": "Alice"},
        ],
        "note": "two people, one name",
    })
    assert response.status_code == 201, response.text[:300]
    document = client.get(f"/api/adventures/{campaign['id']}/state").json()["document"]
    assert set(document["entities"]) >= {"alice_1", "alice_2"}


def test_the_state_reports_a_shared_display_name(client):
    """M11 adds the detection the finding asks for, without adding a refusal."""
    campaign = _campaign(client)
    client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [
            {"type": "create_entity", "entity": "alice_1",
             "entity_type": "character", "name": "Alice"},
            {"type": "create_entity", "entity": "alice_2",
             "entity_type": "character", "name": "alice "},
            {"type": "create_entity", "entity": "roger",
             "entity_type": "character", "name": "Roger"},
        ],
        "note": "",
    })
    with SessionLocal() as db:
        adventure = db.get(models.Adventure, campaign["id"])
        clashes = nmodel.duplicate_names(adventure.narrative_state)
    # Case and surrounding space do not make two people different.
    assert clashes == {"alice": ["alice_1", "alice_2"]}


def test_a_campaign_with_distinct_names_reports_nothing(client):
    campaign = _campaign(client)
    client.post(f"/api/adventures/{campaign['id']}/state/corrections", json={
        "events": [
            {"type": "create_entity", "entity": "a", "entity_type": "character",
             "name": "Alice"},
            {"type": "create_entity", "entity": "r", "entity_type": "character",
             "name": "Roger"},
        ],
        "note": "",
    })
    with SessionLocal() as db:
        adventure = db.get(models.Adventure, campaign["id"])
        assert nmodel.duplicate_names(adventure.narrative_state) == {}