fix: scope thread detection transcript to closing scene (T80.2)

apply_scene_close_summary fed detect_threads the chat-wide last-50
turns. When a chat has accumulated multiple scenes' worth of dialogue,
that bleeds prior-scene turns into the second close's classifier prompt
and risks mis-attributing threads (closing one that opened earlier,
re-opening one that already closed).

Add an optional ``since_event_id`` kwarg to ``_read_recent_dialogue``
that lower-bounds by event_log id, plus a ``_scene_opened_event_id``
helper that resolves the scene-open event for a given scene_id. Wire
both into the thread-detection call site so its scene_transcript
holds only the closing scene's turns. The per-POV summarizer keeps the
chat-wide approximation it had before — that's intentional.

Adds test_thread_detection_uses_scene_scoped_transcript.
This commit is contained in:
Joseph Doherty
2026-04-26 21:48:44 -04:00
parent d123684f9a
commit dae481eb92
2 changed files with 238 additions and 14 deletions
+103 -14
View File
@@ -123,7 +123,11 @@ async def summarize_scene(
def _read_recent_dialogue(
conn: Connection, chat_id: str, *, limit: int = 50
conn: Connection,
chat_id: str,
*,
limit: int = 50,
since_event_id: int | None = None,
) -> list[dict]:
"""Pull the last ``limit`` user/assistant turns for ``chat_id``.
@@ -132,14 +136,29 @@ def _read_recent_dialogue(
the most recent turns of the chat. Superseded and hidden rows are
filtered out so regenerated turns (T29) don't bleed into the
summary.
T80.2: ``since_event_id`` clamps the result to event_log rows whose
``id >= since_event_id`` so callers needing a scene-scoped view (e.g.
thread detection on close) don't pull turns that landed before the
closing scene's ``scene_opened`` event.
"""
cur = conn.execute(
"SELECT kind, payload_json FROM event_log "
"WHERE kind IN ('user_turn', 'assistant_turn') "
" AND superseded_by IS NULL AND hidden = 0 "
"ORDER BY id DESC LIMIT ?",
(limit,),
)
if since_event_id is None:
cur = conn.execute(
"SELECT kind, payload_json FROM event_log "
"WHERE kind IN ('user_turn', 'assistant_turn') "
" AND superseded_by IS NULL AND hidden = 0 "
"ORDER BY id DESC LIMIT ?",
(limit,),
)
else:
cur = conn.execute(
"SELECT kind, payload_json FROM event_log "
"WHERE kind IN ('user_turn', 'assistant_turn') "
" AND superseded_by IS NULL AND hidden = 0 "
" AND id >= ? "
"ORDER BY id DESC LIMIT ?",
(since_event_id, limit),
)
rows = list(reversed(cur.fetchall()))
out: list[dict] = []
for kind, payload_json in rows:
@@ -158,6 +177,65 @@ def _read_recent_dialogue(
return out
def _scene_opened_event_id(
conn: Connection, chat_id: str, scene_id: int
) -> int | None:
"""Return the event_log id of the ``scene_opened`` (or
``meanwhile_scene_started``) event that created scene row
``scene_id``. Used by T80.2 to lower-bound dialogue reads to a
single scene's transcript.
``meanwhile_scene_started`` carries an explicit ``scene_id`` so we
match on that directly. ``scene_opened`` doesn't, so we walk the
chat's scene rows in id order and zip against the chat's scene-open
events in id order — the projector creates one scene row per
scene-open event, so positions correspond.
Returns ``None`` when no matching event is found; callers should
treat that as "fall back to chat-wide" rather than over-filter.
"""
# Fast path for meanwhile children (explicit scene_id in payload).
for ev_id, payload_json in conn.execute(
"SELECT id, payload_json FROM event_log "
"WHERE kind = 'meanwhile_scene_started' "
" AND superseded_by IS NULL AND hidden = 0",
).fetchall():
try:
p = json.loads(payload_json)
except (TypeError, ValueError):
continue
if p.get("chat_id") == chat_id and p.get("scene_id") == scene_id:
return ev_id
# Fallback for parent you-scenes: zip chat-scoped scene-open events
# against chat-scoped scene rows in id order.
chat_scene_ids = [
r[0]
for r in conn.execute(
"SELECT id FROM scenes WHERE chat_id = ? ORDER BY id ASC",
(chat_id,),
).fetchall()
]
if scene_id not in chat_scene_ids:
return None
chat_open_evs: list[int] = []
for ev_id, _kind, payload_json in conn.execute(
"SELECT id, kind, payload_json FROM event_log "
"WHERE kind IN ('scene_opened', 'meanwhile_scene_started') "
" AND superseded_by IS NULL AND hidden = 0 "
"ORDER BY id ASC",
).fetchall():
try:
p = json.loads(payload_json)
except (TypeError, ValueError):
continue
if p.get("chat_id") == chat_id:
chat_open_evs.append(ev_id)
idx = chat_scene_ids.index(scene_id)
if idx < len(chat_open_evs):
return chat_open_evs[idx]
return None
async def _summarize_and_apply_for_witness(
conn: Connection,
client: LLMClient,
@@ -487,16 +565,27 @@ async def apply_scene_close_summary(
},
)
# T58.2: thread detection on close. Reuses the dialogue we already
# gathered for per-POV summarization — same {speaker, text} shape
# detect_threads expects. Failure-tolerant: classify() returns the
# empty default on retry-exhaustion, and the broad except below
# protects the close pipeline from any other classifier/mock flap.
# T58.2: thread detection on close. Failure-tolerant: classify()
# returns the empty default on retry-exhaustion, and the broad except
# below protects the close pipeline from any other classifier/mock
# flap.
#
# T80.2: thread detection runs against a SCENE-SCOPED transcript,
# not the chat-wide last-50 turns used by the per-POV summaries.
# Mis-attributing threads when scene boundaries fall inside the last
# 50 turns would otherwise close threads opened in a prior scene.
scene_open_ev_id = _scene_opened_event_id(conn, chat_id, scene_id)
if scene_open_ev_id is not None:
scene_dialogue = _read_recent_dialogue(
conn, chat_id, since_event_id=scene_open_ev_id
)
else:
scene_dialogue = dialogue
try:
thread_result = await detect_threads(
client,
classifier_model=classifier_model,
scene_transcript=dialogue,
scene_transcript=scene_dialogue,
open_threads=list_open_threads(conn, chat_id),
timeout_s=timeout_s,
)