Files
interactive-story/backend/tests/test_retry_variants.py
T
JesseMarkowitzandClaude Opus 5 b7005e6fdd M5: genre-neutral authoritative narrative state, with review corrections
Replaces AI-DnD's RPG relative-delta world state with the genre-neutral typed
narrative state of ADR 010: explicit, absolute, allowlisted events proposed by
the model, validated by the application, applied to one authoritative document,
and snapshotted per position so restore stays a row read.

This commit includes the corrective pass that followed the independent review
in planning/reports/M5-IMPLEMENTATION-REPORT.md. The invariant it exists to
hold is:

    visible active transcript position == stored head == authoritative state

Narrator editing (D10, STORY-BRANCH-SEMANTICS §§14-15)

  A narrator edit no longer rewrites a row. It returns to the state before the
  turn, takes the reader's exact text as the accepted narration, re-derives the
  state that text implies, and becomes a new active continuation — while the
  original narration keeps its words, its live flag and its whole future as
  retained history. At the tip the correction is another take; with story below
  it, it forks. No new history machinery: this is the existing fork/take/head
  path with the reader's text in place of a generated reply. The §14A refusal
  is therefore gone for narrator turns, and remains only for player input.

Pre-M5 positions

  Migration 88 backfills the empty narrative document onto every action written
  before M5, and a missing snapshot now restores the empty document instead of
  leaving the previous position's state standing. Restoring to an old Save
  Point no longer leaves a later position's entities and facts on screen.

Narrator context

  Replayed history carries prose only; the machine-readable block is no longer
  reconstructed into past turns, where it contradicted the authoritative state
  in the same prompt. A fact withdrawn by a manual correction is now named as
  no longer true, with the reader's reason, rather than silently dropped.

Also

  - state_changes joins the action-list bulk read, removing one query per row.
  - Extraction takes only the application's own protocol payload: an ordinary
    ```json or ```python block in a story survives, and a mangled proposal
    still does not reach the reader.

Planning: ADR 013 records the authoritative document shape; §§14-15/14A, D10,
C04 and BUILD-MILESTONES are updated to describe what exists. Debt is recorded
against M8 (scenario editor UX) and M9 (export of the audit trail).

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PWU4gTfLYY6Qq9U7aa9Qw2
2026-09-05 07:01:50 -04:00

377 lines
14 KiB
Python

"""End-to-end HTTP tests for retry history: every attempt at an AI turn is kept
as a variant of the same action, browsable and (for the last message)
switchable, restoring the world/script state that attempt produced.
python -m pytest tests/test_retry_variants.py -v
"""
import pytest
from fastapi import Depends
from fastapi.testclient import TestClient
from app import auth, limits, models
from app.database import Base, SessionLocal, engine, get_db
from app.main import app
from app.providers import ProviderError
from app.routers import adventures
from fakes import GOLD_SCHEMA, ScriptedProvider, gold_replies, gold_reply, tally_of, tally_reply
SCHEMA = GOLD_SCHEMA
# Each turn spends 10 gold, so a double-applied or un-rolled-back attempt shows.
@pytest.fixture()
def client(monkeypatch):
Base.metadata.create_all(bind=engine)
setup = SessionLocal()
user = models.User(is_guest=False, email="variants@example.com")
setup.add(user)
setup.flush()
setup.add(models.Settings(user_id=user.id, api_key="enc:dummy", model="test-model"))
scenario = models.Scenario(user_id=user.id, title="S", stat_schema=SCHEMA)
setup.add(scenario)
setup.flush()
adv = models.Adventure(
user_id=user.id, title="Cave", scenario_id=scenario.id,
world_state={"player": {"hp": 100, "gold": 0}},
)
setup.add(adv)
setup.flush()
setup.add(models.Action(adventure_id=adv.id, type="start", text="You enter a cave."))
setup.commit()
adv_id, user_id = adv.id, user.id
setup.close()
ScriptedProvider.replies = ["Attempt one."]
ScriptedProvider.calls = 0
ScriptedProvider.prompts = []
monkeypatch.setattr(adventures.turns, "OpenAICompatibleProvider", ScriptedProvider)
monkeypatch.setattr(limits, "check_row_cap", lambda *a, **k: None)
def _current_user(db=Depends(get_db)):
return db.get(models.User, user_id)
app.dependency_overrides[auth.get_current_user] = _current_user
c = TestClient(app)
c.adv_id = adv_id
try:
yield c
finally:
app.dependency_overrides.clear()
adventures.turns._active_turns.clear()
Base.metadata.drop_all(bind=engine)
def _adv(adv_id):
"""The instrument, and the whole document behind it.
M5 moved the instrument from an RPG stat to a typed narrative fact; the
tuple shape is kept so the call sites read the same. `[0]["gold"]` is the
tally, and `[1]` is the authoritative state document.
"""
db = SessionLocal()
try:
adv = db.get(models.Adventure, adv_id)
state = adv.narrative_state or {}
return {"gold": tally_of(state)}, state
finally:
db.close()
def _actions(client):
return client.get(f"/api/adventures/{client.adv_id}").json()["actions"]
def _play(client, text="look around"):
r = client.post(f"/api/adventures/{client.adv_id}/actions",
json={"type": "do", "text": text})
assert r.status_code == 200, r.text
def _retry(client):
r = client.post(f"/api/adventures/{client.adv_id}/retry")
assert r.status_code == 200, r.text
return r
# ---------------------------------------------------------------- keeping them
def test_retry_keeps_the_discarded_attempt(client):
ScriptedProvider.replies = ["Attempt one.", "Attempt two."]
_play(client)
assert _actions(client)[-1]["text"] == "Attempt one."
_retry(client)
actions = _actions(client)
# One AI action still, not two. The retry replaced the live text in place.
assert [a["type"] for a in actions] == ["start", "do", "ai"]
last = actions[-1]
assert last["text"] == "Attempt two."
assert last["take_count"] == 2
assert last["take_index"] == 1
r = client.get(f"/api/adventures/{client.adv_id}/actions/{last['id']}/variants")
assert r.status_code == 200, r.text
assert [v["text"] for v in r.json()] == ["Attempt one.", "Attempt two."]
assert [v["active"] for v in r.json()] == [False, True]
def test_retry_context_excludes_the_attempt_being_replaced(client):
"""A retry produces a fresh take on the same turn. The row survives the
retry because it holds the variant history, so it is still in
`adventure.actions` while the replacement context is assembled. The
context builder must filter it out, or the model continues past the
attempt it is replacing and writes a sequel that blends both."""
ScriptedProvider.replies = ["Attempt one.", "Attempt two."]
_play(client)
_retry(client)
retry_story = ScriptedProvider.prompts[-1][1]
assert "Attempt one." not in retry_story
# The turn's own player action must still be there. It is what the model responds to.
assert "look around" in retry_story
assert "You enter a cave." in retry_story
def test_retry_context_keeps_earlier_ai_turns(client):
"""Only the action being retried is dropped, not AI history in general."""
ScriptedProvider.replies = ["First turn.", "Second turn.", "Second, again."]
_play(client, "go north")
_play(client, "go south")
_retry(client)
retry_story = ScriptedProvider.prompts[-1][1]
assert "First turn." in retry_story
assert "Second turn." not in retry_story
def test_never_retried_action_has_no_variants(client):
_play(client)
last = _actions(client)[-1]
assert last["take_count"] == 1 # itself, and nothing to page to
assert client.get(
f"/api/adventures/{client.adv_id}/actions/{last['id']}/variants").json() == []
def test_three_attempts_all_kept_in_order(client):
ScriptedProvider.replies = ["One.", "Two.", "Three."]
_play(client)
_retry(client)
_retry(client)
last = _actions(client)[-1]
assert last["take_count"] == 3
assert last["take_index"] == 2
variants = client.get(
f"/api/adventures/{client.adv_id}/actions/{last['id']}/variants").json()
assert [v["text"] for v in variants] == ["One.", "Two.", "Three."]
# ---------------------------------------------------------------- switching
def test_switching_back_restores_that_attempt_state(client):
"""Each attempt records its own total, so switching between them shows
whether the state followed the narration back."""
ScriptedProvider.replies = [
tally_reply("You take a scratch.", 95),
tally_reply("You take a beating.", 60),
]
_play(client)
assert _adv(client.adv_id)[0]["gold"] == 95
_retry(client)
player, _document = _adv(client.adv_id)
assert player["gold"] == 60, "the retake's own state, not the one it replaced"
last = _actions(client)[-1]
r = client.post(
f"/api/adventures/{client.adv_id}/actions/{last['id']}/variant", json={"index": 0})
assert r.status_code == 200, r.text
assert r.json()["text"].startswith("You take a scratch")
assert r.json()["take_index"] == 0
# The state follows the narration back.
assert _adv(client.adv_id)[0]["gold"] == 95
# And forward again.
client.post(f"/api/adventures/{client.adv_id}/actions/{last['id']}/variant",
json={"index": 1})
def test_switching_updates_the_state_summary_chips(client):
"""The chip under a message describes the take on screen.
M5 replaced the RPG world-change chips with the narrative-state summary;
what this test guards is unchanged — switching takes must change what the
chip says, or the reader is shown one attempt's prose beside another's
consequences.
"""
ScriptedProvider.replies = [
tally_reply("A scratch.", 5),
tally_reply("A beating.", 40),
]
_play(client)
_retry(client)
last = _actions(client)[-1]
assert any("40" in line for line in last["state_summary"]), last["state_summary"]
client.post(f"/api/adventures/{client.adv_id}/actions/{last['id']}/variant",
json={"index": 0})
switched = _actions(client)[-1]["state_summary"]
assert any("5" in line for line in switched), switched
assert not any("40" in line for line in switched)
def test_cannot_switch_a_turn_the_story_moved_past(client):
ScriptedProvider.replies = ["One.", "Two.", "Three."]
_play(client)
_retry(client)
retried = _actions(client)[-1]
_play(client) # story continues from "Two."
r = client.post(
f"/api/adventures/{client.adv_id}/actions/{retried['id']}/variant", json={"index": 0})
assert r.status_code == 400
assert "latest message" in r.json()["detail"]
# The variant is still readable. Keeping every attempt browsable is why it still exists.
variants = client.get(
f"/api/adventures/{client.adv_id}/actions/{retried['id']}/variants").json()
assert [v["text"] for v in variants] == ["One.", "Two."]
def test_switching_to_a_missing_index_is_rejected(client):
ScriptedProvider.replies = ["One.", "Two."]
_play(client)
_retry(client)
last = _actions(client)[-1]
r = client.post(
f"/api/adventures/{client.adv_id}/actions/{last['id']}/variant", json={"index": 7})
assert r.status_code == 400
# ---------------------------------------------------------------- edge cases
def test_failed_retry_leaves_the_previous_attempt_in_charge(client):
"""A provider error mid-retry must undo the rollback, or the stats on
screen would silently disagree with the text still shown."""
ScriptedProvider.replies = [gold_reply("Attempt one."), ProviderError("upstream is down")]
_play(client)
assert _adv(client.adv_id)[0]["gold"] == 10
client.post(f"/api/adventures/{client.adv_id}/retry")
actions = _actions(client)
assert actions[-1]["text"] == "Attempt one." # text never lost
assert _adv(client.adv_id)[0]["gold"] == 10 # and the state still matches it
def test_undo_removes_the_action_and_its_history(client):
ScriptedProvider.replies = [gold_reply(t) for t in ["One.", "Two."]]
_play(client)
_retry(client)
r = client.post(f"/api/adventures/{client.adv_id}/undo")
assert r.status_code == 200, r.text
# Undo returns the newest window now, not the whole story.
assert [a["type"] for a in r.json()["actions"]] == ["start"]
assert _adv(client.adv_id)[0]["gold"] == 0
def test_editing_a_narrator_take_adds_a_take_and_keeps_the_original(client):
"""M5 corrective pass: a narrator correction is a new take, not a rewrite.
§15.5 requires the original narration to be retained. At the tip that means
the correction joins the turn's attempts rather than replacing the words of
one, so the pager still reaches what was there before.
"""
ScriptedProvider.replies = ["One.", "Two."]
_play(client)
_retry(client)
last = _actions(client)[-1]
client.patch(f"/api/adventures/{client.adv_id}/actions/{last['id']}",
json={"text": "Two, but better."})
live = _actions(client)[-1]
assert live["text"] == "Two, but better."
assert live["take_count"] == 3, "the correction is a third attempt"
assert live["take_index"] == 2
# The original is still reachable, and the edit survives paging away.
client.post(f"/api/adventures/{client.adv_id}/actions/{live['id']}/variant",
json={"index": 1})
assert _actions(client)[-1]["text"] == "Two."
client.post(f"/api/adventures/{client.adv_id}/actions/{live['id']}/variant",
json={"index": 2})
assert _actions(client)[-1]["text"] == "Two, but better."
def _live_depth(client) -> int:
"""Returns the depth of the newest action the story tells."""
db = SessionLocal()
try:
return (
db.query(models.Action.depth)
.filter(models.Action.adventure_id == client.adv_id,
models.Action.live.is_(True))
.order_by(models.Action.depth.desc())
.first()[0]
)
finally:
db.close()
def test_retry_keeps_the_turn_depth(client):
"""A retry re-runs the same turn, so the world-state clock (which drives
cooldowns) must not advance.
The depth is read from the row rather than the payload. It is a coordinate
on one branch, and the client pages by id, so it is not exposed.
"""
ScriptedProvider.replies = ["One.", "Two."]
_play(client)
before = _live_depth(client)
_retry(client)
assert _live_depth(client) == before
def test_export_and_import_round_trips_variants(client):
ScriptedProvider.replies = ["One.", "Two."]
_play(client)
_retry(client)
bundle = client.get(f"/api/adventures/{client.adv_id}/export").json()
# SP6: the attempts are nodes in the bundle too, sharing one coordinate,
# and `live` says which of them the story tells. The `variants` array
# survives only in the v1 reader. See the hand-edited bundle below.
ai = [a for a in bundle["actions"] if a["type"] == "ai"]
assert [(a["text"], a["live"]) for a in ai] == [("One.", False), ("Two.", True)]
assert len({(a["branch"], a["depth"]) for a in ai}) == 1
r = client.post("/api/adventures/import", json=bundle)
assert r.status_code == 201, r.text
imported = r.json()["id"]
actions = client.get(f"/api/adventures/{imported}").json()["actions"]
assert [a["type"] for a in actions] == ["start", "do", "ai"]
assert actions[-1]["text"] == "Two."
# The pager reads 1/1 on the copy, because the import writes no
# `parent_id` and `annotate_takes` groups on it. The attempts are both
# there, at one coordinate, and `GET .../variants` still lists them. This
# is a gap in the import rather than in the drop: `take_count` has been the
# only number the client reads since SP9, and the import has never set the
# column it is derived from.
assert actions[-1]["take_count"] == 1
variants = client.get(
f"/api/adventures/{imported}/actions/{actions[-1]['id']}/variants").json()
assert [v["text"] for v in variants] == ["One.", "Two."]
def test_import_clamps_an_out_of_range_variant_index(client):
bundle = {
"format": "ai-dnd-adventure-v1", "title": "Hand-edited",
"actions": [{
"index": 0, "type": "ai", "text": "Only.",
"variants": [{"text": "Only."}], "variantIndex": 9,
}],
}
r = client.post("/api/adventures/import", json=bundle)
assert r.status_code == 201, r.text
actions = client.get(f"/api/adventures/{r.json()['id']}").json()["actions"]
assert actions[0]["take_index"] == 0