fix: post_turn consumes pending meanwhile digests (T82.1)

Wire chat.services.prompt.consume_pending_meanwhile_digests into
chat.web.turns.post_turn at the END of the handler, after scene-close
detection and before the response broadcast. Without this call digests
created by a meanwhile close stay pending forever — they surface in the
next you-turn's prompt (via T65) but are never marked consumed, so they
re-render on every subsequent turn.

Idempotent: re-calling the helper produces zero events when nothing's
pending. The T66 cross-feature note is updated to reflect the new
wiring; the existing direct-helper test in test_phase3_integration.py
is preserved as defensive coverage of the helper contract in isolation.
This commit is contained in:
Joseph Doherty
2026-04-26 22:02:25 -04:00
parent 6f50ce5b7a
commit be92691f9a
3 changed files with 100 additions and 10 deletions
+10 -9
View File
@@ -39,11 +39,11 @@ Cross-feature notes discovered while writing these tests:
swallowed. Tests that don't care about thread coverage can omit the
slot; test 2 includes a valid thread response to exercise the path.
- ``consume_pending_meanwhile_digests`` is defined in chat.services.prompt
but is NOT currently wired into the post_turn flow. The digest stays
pending across turns until the helper is called explicitly. Test 4
reflects this: it asserts the digest renders pre-consumption AND
post-consumption (driven via the helper directly), and that the
meanwhile_digest_consumed event lands in the event_log.
and is wired into the END of post_turn (after scene-close detection)
by T82.1. Test 4 still drives the helper directly because it asserts
the helper's contract in isolation (no post_turn round-trip in scope);
the explicit call doubles as defensive coverage and is idempotent — a
second call on already-consumed digests is a no-op.
- The host-only ``apply_scene_close_summary`` canned queue layout is
``[host_pov, thread_detection]`` (2 slots) when a single bot is present
and there are dialogue rows, with thread_detection being optional /
@@ -769,10 +769,11 @@ def test_meanwhile_close_digest_surfaces_then_consumed(
— the digest is gone, and a meanwhile_digest_consumed event landed.
Cross-feature finding: ``consume_pending_meanwhile_digests`` is
defined in chat.services.prompt but is NOT wired into the post_turn
flow. The digest stays pending across turns until callers invoke
the helper. Test exercises the helper directly so the consumption
contract is pinned independent of any future post_turn integration.
defined in chat.services.prompt and wired into post_turn by T82.1
(after scene-close detection). This test exercises the helper
directly so the consumption contract is pinned in isolation from
the post_turn round-trip; T82.1's wiring is covered by a dedicated
test in tests/test_turn_flow.py.
Canned queue for the meanwhile turn:
1. parse_turn
+77
View File
@@ -1317,3 +1317,80 @@ def test_skip_command_does_not_run_narrative_classifier(
"assemble_narrative_prompt was called on the skip path; the "
"natural-language skip dispatch must bypass narrative assembly."
)
# ---------------------------------------------------------------------------
# Phase 3.5 (T82.1) — post_turn consumes pending meanwhile digests.
#
# The helper ``consume_pending_meanwhile_digests`` lives in
# chat.services.prompt and is now wired into the END of post_turn (after
# scene-close detection, before the response broadcast). This pins the
# wiring so future refactors don't accidentally drop the call and leave
# digests pending forever.
# ---------------------------------------------------------------------------
def test_post_turn_consumes_pending_meanwhile_digests(
app_state_setup, tmp_path
):
"""Seed a pending meanwhile digest via ``meanwhile_digest_created``,
POST a regular you-turn through post_turn, and assert:
1. A ``meanwhile_digest_consumed`` event lands in the event_log.
2. ``list_pending_meanwhile_digests`` returns empty after the turn.
The post_turn flow surfaces the digest in the prompt (T65) and then
consumes it (T82.1) so the next turn starts clean.
"""
_seed(tmp_path / "test.db")
db_path = tmp_path / "test.db"
# Seed a pending digest directly via the projection event. The scene_id
# field doesn't need to reference an existing meanwhile scene for the
# digest table — the FK is on the digest payload only.
with open_db(db_path) as conn:
append_and_apply(
conn,
kind="meanwhile_digest_created",
payload={
"scene_id": 99,
"chat_id": "chat_bot_a",
"summary": "While you were away, the bots talked.",
},
)
# Confirm the digest is pending before the turn lands.
from chat.state.meanwhile import list_pending_meanwhile_digests
assert len(list_pending_meanwhile_digests(conn, "chat_bot_a")) == 1
canned_parse = json.dumps(
{"segments": [{"kind": "dialogue", "text": "hello"}]}
)
# Standard 4-slot queue: parse + narrative + 2 state-updates. No
# active scene so scene-close detection short-circuits without an LLM
# call (consistent with the no-guest regression test).
mock = _override_llm(
[canned_parse, "Hi there.", _zero_state(), _zero_state()]
)
try:
response = app_state_setup.post(
"/chats/chat_bot_a/turns", data={"prose": "hello"}
)
assert response.status_code == 204
finally:
app.dependency_overrides.clear()
# All canned slots drained — no extra classifier calls fired.
assert mock._canned == []
with open_db(db_path) as conn:
# A meanwhile_digest_consumed event landed for the seeded digest.
consumed_rows = conn.execute(
"SELECT payload_json FROM event_log "
"WHERE kind = 'meanwhile_digest_consumed' ORDER BY id"
).fetchall()
assert len(consumed_rows) == 1
# The pending list is empty after consumption.
from chat.state.meanwhile import list_pending_meanwhile_digests
assert list_pending_meanwhile_digests(conn, "chat_bot_a") == []