feat(retrieval): a task's work logs join the document it is embedded as (#4251)

Step 1 of #4251. A work log is the richest prose Scribe holds about WHY
something is the way it is — written during the work, recording what was tried
and ruled out. #4241 made it readable from the agent's door. It was still not
findable, so "has anyone tried this approach?" — precisely the question a log
answers — could not reach one. The cost is not hypothetical: #4208 was rebuilt
in this session because its logs were unreachable.

THE DESIGN QUESTION the issue left open was whether logs embed as part of their
task's document or as rows of their own. As their own rows, a hit has to be
resolved back to a task to be worth anything, and it needs a fourth search, a
fourth result shape and a fourth arm. As part of the task, the objection is
that a long log drowns a short title.

That objection was true before #280 and is not true now. Chunking made one
record into one vector per section, so each log becomes its own title-anchored
chunk, scored separately, and the task's own prose keeps the chunk it always
had — a task is as findable as its best-matching log rather than as the average
of everything in it. The other half is this session's other build: a search
hands back the chunk that won (#4243), so a hit earned by a log shows that
log's passage under the task's title. Without that a reader would have got
body[:240] of the task — the opening of a record whose relevance lives three
hundred lines further down.

So `task_document(title, body, logs)` sits beside `rule_document`: a
synthesised embed-time shape, because the stored record is the task row and the
logs live in their own table, so the document that should be searchable exists
nowhere until it is built. A task with no logs is returned untouched — most
notes are not tasks and most tasks carry no log, and their vectors are the
corpus every tuned number here was measured against.

CHUNKER_VERSION 1 → 2, and its comment now says what the version actually
means. It used to read "whenever chunk_document's output can change for the
same input", which this change would slip past: `chunk_document` is untouched
and every task with a log now embeds differently while its title, body and the
chunker all stand still. The invariant is the document a record is embedded as.
The startup backfill re-embeds on that.

Create, edit and delete of a log all refresh the task through `embed_note`, the
one path every writer shares — an edited log whose vectors still carry its old
wording keeps matching what it no longer says.

No new kind enters the auto-inject menu: tasks were always in it, and this
makes recall on them better rather than changing what the menu spans. The
calibration stamp will now report shape_version 2 against numbers measured at
1, which is exactly the report #4104 built it to make.

Also promoted `session_returning` into tests/helpers beside `make_mock_session`
(#2834) — two files had spelled it out identically and a third was about to.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01821k5B3Ysecp9fNYs92Kuy

tests/test_chunking.py

@@ -185,11 +185,17 @@ async def test_search_collapses_chunk_rows_to_best_chunk_per_note():
 # --- the write path: one row per chunk (#280 step 3) -------------------------
 
 
-def _session_ctx():
+def _session_ctx(log_rows=()):
+    """A session stand-in. `log_rows` answers the work-log read a task's
+    document now needs (#4251) — answered explicitly rather than left to
+    autovivify, because `list(result.all())` on a bare MagicMock raises and is
+    swallowed, which would quietly make every one of these a no-log test."""
     from unittest.mock import AsyncMock, MagicMock
 
     session = MagicMock()
-    session.execute = AsyncMock()
+    result = MagicMock()
+    result.all.return_value = list(log_rows)
+    session.execute = AsyncMock(return_value=result)
     session.commit = AsyncMock()
     ctx = MagicMock()
     ctx.__aenter__ = AsyncMock(return_value=session)
@@ -226,6 +232,32 @@ async def test_upsert_stores_one_versioned_row_per_chunk():
     session.execute.assert_awaited()  # the delete that makes replacement atomic
 
 
+async def test_a_tasks_work_logs_reach_the_rows_it_is_stored_as():
+    """The wiring half of #4251: the shaper is pure and tested next door, so
+    what is pinned here is that the WRITER actually asks for the logs and
+    embeds what comes back. A log that is written, readable (#4241) and absent
+    from the index is the same half-surface one layer down."""
+    import datetime
+    from unittest.mock import AsyncMock, patch
+
+    from scribe.services import embeddings as emb
+
+    session, ctx = _session_ctx(
+        log_rows=[(datetime.datetime(2026, 9, 20), "ruled out the cache theory")]
+    )
+    with (
+        patch.object(emb, "async_session", return_value=ctx),
+        patch.object(emb, "get_embeddings", AsyncMock(return_value=[[0.0] * 384])),
+    ):
+        await emb.upsert_note_embedding(7, 42, "A task", "Its own prose.")
+
+    rows = [call.args[0] for call in session.add.call_args_list]
+    stored = "\n".join(r.chunk_text for r in rows)
+    assert "ruled out the cache theory" in stored
+    assert "Its own prose." in stored
+    assert emb.WORK_LOG_HEADING in stored
+
+
 async def test_upsert_of_an_emptied_record_clears_rows_instead_of_embedding():
     """An empty embedding is worse than none, and a STALE one is worse than
     that — a record emptied of content must stop being findable by what it no