merge: T86 frontend turn_html_replace SSE handler + event_id stamping

T85.1 — JSON-build audit (chat/state, chat/services, chat/eventlog):
no findings. Every JSON column write in those modules already uses
``json.dumps`` (chat/state/events.py, world.py, edges.py, group_node.py,
meanwhile.py, manual_edit.py, entities.py, chat/services/snapshot.py,
chat/eventlog/log.py); chat/state/meanwhile.py:48-49 even carries an
explicit comment about the ``json.dumps`` choice for safety against
quote/backslash injection. No production changes.

T85.2 — meanwhile cancel route-level coverage:

* ``test_meanwhile_turn_cancellation_via_route`` — pins the
  end-to-end shape produced when /turns/cancel fires mid-meanwhile-
  beat: assistant_turn lands with truncated=True (and the right
  meanwhile_scene_id + speaker_id), no memory_written events fire, no
  post-turn edge_update events fire, and _in_flight_tasks is empty
  post-flight. Drives the cancel by hijacking client.stream to raise
  CancelledError on first iteration — same pattern proven by
  test_cancelled_turn_still_closes_scene_when_user_prose_signals_close
  in tests/test_turn_flow.py. The synchronous TestClient can't issue
  a second POST mid-stream from the same thread, and driving via
  task.cancel() trips GeneratorExit-on-dependency that prevents the
  conn from committing the partial; the inline-raise mirrors what
  cancel_turn produces (CancelledError delivered on next await) and
  is the standard idiom in this codebase. Combined with the existing
  test_meanwhile_turn_registered_in_in_flight_tasks (registration
  pin), the full Stop-button lifecycle for meanwhile beats is now
  covered.
* ``test_meanwhile_cancel_route_no_op_after_turn_completes`` — runs
  a meanwhile turn to completion, then POSTs /turns/cancel; asserts
  204 no-op, no error, registry stays empty. Pins the cancel
  endpoint's robustness against the racy "Stop just after stream
  finished" sequence.

Suite: 334 -> 336 passing.

chat/services/memory_write.py

@@ -134,17 +134,34 @@ def record_turn_memory_for_present(
     chat_clock_at: str | None = None,
     source: str = "direct",
     significance: int = 1,
+    you_present: bool = True,
 ) -> dict[str, tuple[int, int | None]]:
-    """Write a ``memory_written`` event for each present bot witness.
+    """Single entry-point for per-turn memory writes (T84).
 
-    Host is always written. Guest is written iff ``guest_bot_id is not
-    None``. Witness flags are ``[you=1, host=1, guest=1]`` when a guest
-    is present, ``[you=1, host=1, guest=0]`` otherwise.
+    Writes one ``memory_written`` event per present bot witness. Host is
+    always written. Guest is written iff ``guest_bot_id is not None``.
+
+    Witness flags depend on ``you_present``:
+
+    - ``you_present=True`` (default — Phase 1/2/3 you-scenes): the user
+      is a witness. Mask is ``[you=1, host=1, guest=1]`` when a guest is
+      present, ``[you=1, host=1, guest=0]`` otherwise.
+    - ``you_present=False`` (Phase 3 meanwhile scenes): the user is
+      absent. Mask is ``[you=0, host=1, guest=1]`` for both bots. Both
+      ``host_bot_id`` and ``guest_bot_id`` are required — a meanwhile
+      scene by definition has both bots, so passing ``guest_bot_id=None``
+      with ``you_present=False`` is a programming error and raises
+      :class:`ValueError`.
 
     Returns a mapping ``{bot_id: (event_id, memory_id)}`` so callers can
     look up the freshly-projected memory id per owner without re-querying
     the database.
     """
+    if not you_present and guest_bot_id is None:
+        raise ValueError("you_present=False requires guest_bot_id")
+
+    witness_you = 1 if you_present else 0
+    witness_host = 1
     witness_guest = 1 if guest_bot_id is not None else 0
 
     result: dict[str, tuple[int, int | None]] = {}
@@ -153,8 +170,8 @@ def record_turn_memory_for_present(
         owner_id=host_bot_id,
         chat_id=chat_id,
         narrative_text=narrative_text,
-        witness_you=1,
-        witness_host=1,
+        witness_you=witness_you,
+        witness_host=witness_host,
         witness_guest=witness_guest,
         scene_id=scene_id,
         chat_clock_at=chat_clock_at,
@@ -167,8 +184,8 @@ def record_turn_memory_for_present(
             owner_id=guest_bot_id,
             chat_id=chat_id,
             narrative_text=narrative_text,
-            witness_you=1,
-            witness_host=1,
+            witness_you=witness_you,
+            witness_host=witness_host,
             witness_guest=1,
             scene_id=scene_id,
             chat_clock_at=chat_clock_at,
@@ -190,46 +207,22 @@ def record_meanwhile_memory(
     source: str = "direct",
     significance: int = 1,
 ) -> dict[str, tuple[int, int | None]]:
-    """Write per-POV ``memory_written`` events for a meanwhile turn (T64).
+    """Backward-compat thin wrapper for meanwhile memory writes (T64, T84).
 
-    A meanwhile scene runs entirely between host + guest, with "you"
-    absent. Both bots are present witnesses, so each one gets a row with
-    witness flags ``[you=0, host=1, guest=1]`` — different from the
-    normal-turn ``record_turn_memory_for_present`` shape, which assumes
-    the user is always a witness (``witness_you=1``).
-
-    The ``guest_bot_id`` is required (a meanwhile scene by definition
-    has both bots) — callers passing ``None`` is a programming error.
-
-    Returns ``{bot_id: (event_id, memory_id)}`` mirroring
-    :func:`record_turn_memory_for_present` so downstream queues
-    (significance scoring) can pull memory ids without re-querying.
+    Equivalent to calling :func:`record_turn_memory_for_present` with
+    ``you_present=False``. Kept so existing call sites in
+    :mod:`chat.web.meanwhile` continue to work without churn. New code
+    should prefer the unified entry-point directly.
     """
-    result: dict[str, tuple[int, int | None]] = {}
-    result[host_bot_id] = _write_one_memory(
+    return record_turn_memory_for_present(
         conn,
-        owner_id=host_bot_id,
         chat_id=chat_id,
+        host_bot_id=host_bot_id,
+        guest_bot_id=guest_bot_id,
         narrative_text=narrative_text,
-        witness_you=0,
-        witness_host=1,
-        witness_guest=1,
         scene_id=scene_id,
         chat_clock_at=chat_clock_at,
         source=source,
         significance=significance,
+        you_present=False,
     )
-    result[guest_bot_id] = _write_one_memory(
-        conn,
-        owner_id=guest_bot_id,
-        chat_id=chat_id,
-        narrative_text=narrative_text,
-        witness_you=0,
-        witness_host=1,
-        witness_guest=1,
-        scene_id=scene_id,
-        chat_clock_at=chat_clock_at,
-        source=source,
-        significance=significance,
-    )
-    return result

chat/services/regenerate.py

@@ -381,7 +381,10 @@ async def regenerate_assistant_turn(
         speaker_bot.get("name", "bot") if speaker_bot is not None else "bot"
     )
     new_turn_html = render_turn_html(
-        speaker_name_for_render, new_text, role="bot"
+        speaker_name_for_render,
+        new_text,
+        role="bot",
+        event_id=new_assistant_event_id,
     )
     await publish(
         chat_id,
@@ -616,7 +619,10 @@ async def regenerate_assistant_turn(
             # Broadcast a replace event so connected tabs swap the prior
             # interjection node in-place (mirrors T73.1's primary swap).
             interject_html = render_turn_html(
-                silent_witness.get("name", "bot"), interject_text, role="bot"
+                silent_witness.get("name", "bot"),
+                interject_text,
+                role="bot",
+                event_id=new_interjection_event_id,
             )
             await publish(
                 chat_id,

chat/services/turn_common.py

@@ -74,17 +74,24 @@ def read_recent_dialogue(
         )
     rows = list(reversed(cur.fetchall()))
     out: list[dict] = []
-    for _row_id, kind, payload_json in rows:
+    for row_id, kind, payload_json in rows:
         p = json.loads(payload_json)
         if p.get("chat_id") != chat_id:
             continue
         if kind in ("user_turn", "user_turn_edit"):
-            out.append({"speaker": "you", "text": p.get("prose", "")})
+            out.append(
+                {
+                    "speaker": "you",
+                    "text": p.get("prose", ""),
+                    "event_id": row_id,
+                }
+            )
         else:
             out.append(
                 {
                     "speaker": p.get("speaker_id", "bot"),
                     "text": p.get("text", ""),
+                    "event_id": row_id,
                 }
             )
     return out

chat/templates/chat.html

@@ -17,7 +17,7 @@
     <p class="muted">No turns yet. Start typing below.</p>
     {% else %}
       {% for turn in turns %}
-        <div class="turn turn-{{ turn.role }}">
+        <div{% if turn.event_id is not none %} id="turn-{{ turn.event_id }}"{% endif %} class="turn turn-{{ turn.role }}">
           <strong>{{ turn.speaker }}</strong>
           {{ turn.text|render_prose|safe }}
         </div>
@@ -119,6 +119,39 @@ document.querySelector('.drawer-toggle')?.addEventListener('click', (e) => {
     }
   });
 
+  // T86: live-swap regenerated turns. The backend (chat/services/
+  // regenerate.py) broadcasts a ``turn_html_replace`` SSE frame after
+  // appending the new assistant_turn — JSON payload of shape
+  // ``{data: <html>, turn_id: <new_id>, supersedes_id: <old_id>}``.
+  // We replace the prior turn's DOM node in-place when we can locate
+  // it by id, otherwise fall back to appending so a tab opened mid-
+  // regenerate still shows the new turn. The renderer
+  // (chat/web/render.py::render_turn_html) and the Jinja loop above
+  // both stamp ``id="turn-<event_id>"`` on each turn DIV, so the
+  // primary in-place swap path is the live one — the append fallback
+  // only kicks in when a tab opened AFTER the regenerate started (no
+  // prior turn DOM node to replace).
+  shell.addEventListener('htmx:sseMessage', (e) => {
+    if (e.detail.type !== 'turn_html_replace') return;
+    let data;
+    try { data = JSON.parse(e.detail.data); } catch (_) { return; }
+    const html = (data && data.data) || '';
+    const trimmed = html.trim();
+    if (!trimmed) return;
+    const oldNode = document.getElementById('turn-' + data.supersedes_id);
+    if (oldNode) {
+      const tmpl = document.createElement('template');
+      tmpl.innerHTML = trimmed;
+      const newNode = tmpl.content.firstChild;
+      if (newNode) oldNode.replaceWith(newNode);
+    } else {
+      // Fallback: append if the prior turn isn't in the DOM (e.g. user
+      // opened the tab AFTER the regenerate started, or the renderer
+      // hasn't yet stamped per-turn ids — see comment above).
+      timeline.insertAdjacentHTML('beforeend', trimmed);
+    }
+  });
+
   // SSE connection lost — show a banner and unlock so the user can
   // retry. The server commits the partial as truncated when its
   // request.is_disconnected() poll trips (T19).

chat/web/chat.py

@@ -52,12 +52,30 @@ async def chat_detail(chat_id: str, request: Request, conn=Depends(get_conn)):
     raw_turns = _read_recent_dialogue(conn, chat_id, limit=200)
     turns: list[dict] = []
     for t in raw_turns:
+        # event_id is forwarded so the Jinja loop can stamp
+        # ``id="turn-<event_id>"`` on each rendered turn — the
+        # ``turn_html_replace`` SSE handler in chat.html relies on this
+        # id to swap a regenerated turn in-place (T86 follow-up).
         if t["speaker"] == "you":
-            turns.append({"role": "you", "speaker": "you", "text": t["text"]})
+            turns.append(
+                {
+                    "role": "you",
+                    "speaker": "you",
+                    "text": t["text"],
+                    "event_id": t.get("event_id"),
+                }
+            )
         else:
             bot = get_bot(conn, t["speaker"])
             label = bot["name"] if bot else t["speaker"]
-            turns.append({"role": "bot", "speaker": label, "text": t["text"]})
+            turns.append(
+                {
+                    "role": "bot",
+                    "speaker": label,
+                    "text": t["text"],
+                    "event_id": t.get("event_id"),
+                }
+            )
 
     return TEMPLATES.TemplateResponse(
         request,

chat/web/meanwhile.py

@@ -378,7 +378,12 @@ async def process_meanwhile_turn(
             "truncated": truncated,
         },
     )
-    turn_html = _render_turn_html(speaker_bot["name"], text, role="bot")
+    turn_html = _render_turn_html(
+        speaker_bot["name"],
+        text,
+        role="bot",
+        event_id=assistant_event_id,
+    )
     await publish(chat_id, {"event": "turn_html", "data": turn_html})
 
     if cancelled:

chat/web/render.py

@@ -84,7 +84,13 @@ def render_prose(text: str) -> str:
     return "".join(f"<p>{p}</p>" for p in paragraphs)
 
 
-def render_turn_html(speaker: str, text: str, role: str = "bot") -> str:
+def render_turn_html(
+    speaker: str,
+    text: str,
+    role: str = "bot",
+    *,
+    event_id: int | None = None,
+) -> str:
     """Render a full transcript turn as ``<div class="turn …">…</div>``.
 
     Used by both the SSE fragment publisher in :mod:`chat.web.turns`
@@ -94,12 +100,19 @@ def render_turn_html(speaker: str, text: str, role: str = "bot") -> str:
     ``role`` selects the CSS class (``turn-you`` vs ``turn-bot``); the
     speaker label and role name are HTML-escaped defensively even though
     they currently come from trusted server-side state.
+
+    ``event_id`` (T86 follow-up) stamps ``id="turn-<event_id>"`` on the
+    wrapper div so the chat-page ``turn_html_replace`` SSE handler can
+    locate the prior turn node by id and swap it in-place. When omitted
+    the id attribute is dropped so SSE-only fragments without a stable
+    event id (legacy callers) still render cleanly.
     """
     speaker_html = html.escape(speaker)
     role_html = html.escape(role)
     body_html = render_prose(text)
+    id_attr = f' id="turn-{int(event_id)}"' if event_id is not None else ""
     return (
-        f'<div class="turn turn-{role_html}">'
+        f'<div{id_attr} class="turn turn-{role_html}">'
         f"<strong>{speaker_html}</strong>"
         f"{body_html}"
         f"</div>"

chat/web/turns.py

@@ -483,7 +483,11 @@ async def post_turn(
 
     # 7. Append the assistant_turn with the final text. (See note above on
     # why we skip ``project`` for these transcript-only event kinds.)
-    append_event(
+    # Capture the returned event id so we can stamp ``id="turn-<n>"`` on
+    # the SSE-emitted HTML fragment — the chat-page ``turn_html_replace``
+    # handler relies on the id to swap regenerated turns in-place
+    # (T86 follow-up).
+    primary_assistant_event_id = append_event(
         conn,
         kind="assistant_turn",
         payload={
@@ -583,6 +587,7 @@ async def post_turn(
     interjection_text: str | None = None
     interjection_speaker_id: str | None = None
     interjection_truncated = False
+    interjection_event_id: int | None = None
     if (
         guest_bot is not None
         and not cancelled
@@ -670,7 +675,9 @@ async def post_turn(
 
             interjection_text = "".join(interject_accumulated)
 
-            append_event(
+            # Capture the event id (T86 follow-up) so the SSE fragment
+            # below carries ``id="turn-<n>"`` for in-place swap.
+            interjection_event_id = append_event(
                 conn,
                 kind="assistant_turn",
                 payload={
@@ -925,7 +932,10 @@ async def post_turn(
         },
     )
     primary_html = _render_turn_html(
-        addressee_bot["name"], primary_text, role="bot"
+        addressee_bot["name"],
+        primary_text,
+        role="bot",
+        event_id=primary_assistant_event_id,
     )
     await publish(
         chat_id, {"event": "turn_html", "data": primary_html}
@@ -949,7 +959,10 @@ async def post_turn(
             },
         )
         interject_html = _render_turn_html(
-            interject_speaker_name, interjection_text, role="bot"
+            interject_speaker_name,
+            interjection_text,
+            role="bot",
+            event_id=interjection_event_id,
         )
         await publish(
             chat_id, {"event": "turn_html", "data": interject_html}

tests/test_meanwhile_turn_flow.py

@@ -570,3 +570,173 @@ def test_meanwhile_turn_registered_in_in_flight_tasks(
     # Post-flight: the entry has been cleaned up so the next turn (or
     # the cancel route) doesn't see a stale task.
     assert "chat_bot_a" not in _in_flight_tasks
+
+
+def test_meanwhile_turn_cancellation_via_route(app_state_setup, tmp_path):
+    """T85.2: a cancellation that fires while a meanwhile beat is
+    streaming truncates the assistant_turn and skips the post-turn
+    memory + state-update writes — the same end-to-end shape the
+    /turns/cancel route produces.
+
+    Drives the cancel by hijacking ``client.stream`` to raise
+    CancelledError on its first iteration — the exact pattern proven
+    by ``test_cancelled_turn_still_closes_scene_when_user_prose_signals_close``
+    in ``tests/test_turn_flow.py``. This mirrors what
+    ``cancel_turn`` does in production (``task.cancel()`` schedules a
+    CancelledError on the next await); doing the raise inline avoids
+    the TestClient-loop-reentry problem that prevents driving a second
+    POST mid-stream from the same synchronous test thread, while
+    exercising the same code path: the meanwhile streamer's
+    ``except asyncio.CancelledError`` block at meanwhile.py:276 sets
+    ``cancelled=True`` + ``truncated=True``, the assistant_turn lands
+    with the partial, and the memory/state-update branch is skipped.
+
+    The ``_in_flight_tasks`` registration that wires the cancel route
+    to the meanwhile streamer is independently pinned by
+    ``test_meanwhile_turn_registered_in_in_flight_tasks`` above; this
+    test pins the downstream behavioural shape the registration
+    enables — together they cover the full Stop-button lifecycle for
+    meanwhile beats.
+
+    Behavioural pins:
+
+    * ``assistant_turn`` lands with ``truncated=True``,
+      ``meanwhile_scene_id=2``, ``speaker_id="bot_a"``.
+    * No ``memory_written`` events fire (cancel skips per-bot writes).
+    * No post-turn ``edge_update`` events fire (cancel skips state updates).
+    * ``_in_flight_tasks`` is empty post-flight.
+    """
+    from typing import AsyncIterator, Sequence
+
+    from chat.llm.client import Message
+    from chat.web.turns import _in_flight_tasks
+
+    _seed_meanwhile_chat(tmp_path / "test.db")
+
+    class _CancelOnStreamMock(MockLLMClient):
+        """Yields CancelledError on first iteration of ``stream`` —
+        simulates ``cancel_turn`` having fired ``task.cancel()`` on the
+        in-flight streaming task. ``generate`` is delegated to the
+        canned-queue base so parse_turn still resolves cleanly.
+        """
+
+        async def stream(
+            self, messages: Sequence[Message], *, model: str, **params
+        ) -> AsyncIterator[str]:
+            raise asyncio.CancelledError
+            yield  # pragma: no cover — keeps this an async generator.
+
+    canned_parse = json.dumps(
+        {"segments": [{"kind": "narration", "text": "they exchange a glance"}]}
+    )
+    # Canned queue: only parse_turn — the narrative slot is never pulled
+    # because stream raises before consuming it, and post-turn
+    # state-update is skipped by the cancel branch.
+    mock = _CancelOnStreamMock(canned=[canned_parse])
+    from chat.web.kickoff import get_llm_client
+
+    app.dependency_overrides[get_llm_client] = lambda: mock
+    try:
+        # The meanwhile controller re-raises CancelledError after the
+        # partial assistant_turn is recorded (meanwhile.py:387). The
+        # outer post_turn route has no catch for CancelledError on the
+        # meanwhile path (turns.py:244-254 only catches ValueError), so
+        # the exception propagates up through Starlette. TestClient
+        # surfaces that as a 500 or a propagated exception depending on
+        # Starlette/asyncio versions; we don't pin the response.
+        try:
+            app_state_setup.post(
+                "/chats/chat_bot_a/turns",
+                data={"prose": "they exchange a glance"},
+            )
+        except BaseException:
+            pass
+    finally:
+        app.dependency_overrides.clear()
+
+    with open_db(tmp_path / "test.db") as conn:
+        assistant_rows = conn.execute(
+            "SELECT payload_json FROM event_log "
+            "WHERE kind = 'assistant_turn' ORDER BY id"
+        ).fetchall()
+        memory_count = conn.execute(
+            "SELECT COUNT(*) FROM event_log WHERE kind = 'memory_written'"
+        ).fetchone()[0]
+        # Edge updates AFTER the assistant_turn (i.e. excluding seeded ones).
+        max_at_row = conn.execute(
+            "SELECT MAX(id) FROM event_log WHERE kind = 'assistant_turn'"
+        ).fetchone()
+        max_at = max_at_row[0] if max_at_row[0] is not None else 0
+        post_turn_edge_updates = conn.execute(
+            "SELECT COUNT(*) FROM event_log "
+            "WHERE kind = 'edge_update' AND id > ?",
+            (max_at,),
+        ).fetchone()[0]
+
+    # The cancelled assistant_turn was still recorded with truncated=True,
+    # carrying whatever partial text accumulated before cancel propagated
+    # (zero text here since the cancel hits on the first iteration).
+    assert len(assistant_rows) == 1
+    payload = json.loads(assistant_rows[0][0])
+    assert payload["truncated"] is True, payload
+    assert payload["meanwhile_scene_id"] == 2
+    assert payload["speaker_id"] == "bot_a"
+
+    # No per-bot memory writes — cancellation short-circuits the memory
+    # + state-update branch (see chat/web/meanwhile.py:308).
+    assert memory_count == 0
+
+    # No post-turn edge_updates — same short-circuit.
+    assert post_turn_edge_updates == 0
+
+    # Post-flight: registry cleared so the cancel route won't try to
+    # re-cancel a defunct task on a follow-up POST.
+    assert "chat_bot_a" not in _in_flight_tasks
+
+
+def test_meanwhile_cancel_route_no_op_after_turn_completes(
+    app_state_setup, tmp_path
+):
+    """T85.2: POST ``/chats/<id>/turns/cancel`` AFTER a meanwhile turn
+    has fully completed is a silent 204 no-op — there is no in-flight
+    task to cancel, the registry is empty, and the route must not error.
+
+    Pins the cancel endpoint's robustness against the common-but-racy
+    sequence where the user clicks Stop just after the stream finished
+    (the SSE channel hasn't yet flipped the client-side ``isStreaming``
+    flag). This is a complement to the snapshot test: the snapshot test
+    pins that the registry IS populated mid-flight, this test pins that
+    it isn't AFTER and that the route copes gracefully.
+    """
+    from chat.web.turns import _in_flight_tasks
+
+    _seed_meanwhile_chat(tmp_path / "test.db")
+    canned_parse = json.dumps(
+        {"segments": [{"kind": "narration", "text": "they exchange a glance"}]}
+    )
+    canned = [
+        canned_parse,
+        "BotA leans in. *quietly*",
+        _zero_state(),
+        _zero_state(),
+    ]
+    mock = _override_llm(canned)
+    try:
+        response = app_state_setup.post(
+            "/chats/chat_bot_a/turns",
+            data={"prose": "they exchange a glance"},
+        )
+        assert response.status_code == 204
+    finally:
+        app.dependency_overrides.clear()
+    assert mock._canned == []
+
+    # Registry was cleaned up after the stream completed.
+    assert "chat_bot_a" not in _in_flight_tasks
+
+    # Cancel after-the-fact: 204, no error, registry stays empty.
+    cancel_response = app_state_setup.post(
+        "/chats/chat_bot_a/turns/cancel"
+    )
+    assert cancel_response.status_code == 204
+    assert "chat_bot_a" not in _in_flight_tasks

tests/test_memory_write.py

@@ -444,3 +444,91 @@ def test_record_for_present_dict_keys_match(tmp_path):
             narrative_text="Both bots witness this.",
         )
         assert set(result_with_guest.keys()) == {"bot_a", "bot_b"}
+
+
+# ---------------------------------------------------------------------------
+# T84: unified record_turn_memory_for_present API with you_present kwarg.
+# ---------------------------------------------------------------------------
+
+
+def test_record_turn_memory_you_present_false_writes_meanwhile_witness_mask(tmp_path):
+    """When ``you_present=False`` the witness mask should be
+    ``[you=0, host=1, guest=1]`` for both bots — the meanwhile shape."""
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    _seed_two_bots(db)
+    with open_db(db) as conn:
+        result = record_turn_memory_for_present(
+            conn,
+            chat_id="chat_ab",
+            host_bot_id="bot_a",
+            guest_bot_id="bot_b",
+            narrative_text="BotA and BotB confer privately.",
+            scene_id=None,
+            chat_clock_at="2026-04-26T20:00:00+00:00",
+            you_present=False,
+        )
+
+        assert set(result.keys()) == {"bot_a", "bot_b"}
+
+        rows = conn.execute(
+            "SELECT owner_id, witness_you, witness_host, witness_guest "
+            "FROM memories ORDER BY owner_id"
+        ).fetchall()
+        assert len(rows) == 2
+        for _owner, w_you, w_host, w_guest in rows:
+            assert w_you == 0
+            assert w_host == 1
+            assert w_guest == 1
+
+        # Two memory_written events were appended.
+        cur = conn.execute(
+            "SELECT COUNT(*) FROM event_log WHERE kind = 'memory_written'"
+        )
+        assert cur.fetchone()[0] == 2
+
+
+def test_record_turn_memory_you_present_true_default_writes_normal_witness_mask(tmp_path):
+    """Default ``you_present=True`` preserves Phase 2 behaviour:
+    ``witness_you=1`` for the host POV row."""
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    _seed_minimal(db)
+    with open_db(db) as conn:
+        # No explicit you_present arg — should default to True.
+        result = record_turn_memory_for_present(
+            conn,
+            chat_id="chat_bot_a",
+            host_bot_id="bot_a",
+            guest_bot_id=None,
+            narrative_text="BotA hums to herself.",
+        )
+        assert set(result.keys()) == {"bot_a"}
+
+        row = conn.execute(
+            "SELECT witness_you, witness_host, witness_guest "
+            "FROM memories WHERE owner_id = 'bot_a'"
+        ).fetchone()
+        assert row is not None
+        w_you, w_host, w_guest = row
+        assert w_you == 1
+        assert w_host == 1
+        assert w_guest == 0
+
+
+def test_record_turn_memory_you_present_false_requires_guest(tmp_path):
+    """Calling with ``you_present=False`` and no ``guest_bot_id`` is a
+    programming error — meanwhile scenes always have both bots."""
+    db = tmp_path / "t.db"
+    apply_migrations(db)
+    _seed_minimal(db)
+    with open_db(db) as conn:
+        with pytest.raises(ValueError, match="you_present=False requires guest_bot_id"):
+            record_turn_memory_for_present(
+                conn,
+                chat_id="chat_bot_a",
+                host_bot_id="bot_a",
+                guest_bot_id=None,
+                narrative_text="invalid",
+                you_present=False,
+            )

tests/test_render.py

@@ -85,3 +85,26 @@ def test_render_prose_mixed_full_message():
     assert '<em class="action">looks up</em>' in out
     # The apostrophe in ``she's`` is HTML-escaped to ``&#x27;``.
     assert '<span class="ooc">((she&#x27;s tired))</span>' in out
+
+
+def test_render_turn_html_stamps_event_id_when_provided():
+    """T86 follow-up: when ``event_id`` is supplied the wrapper DIV
+    carries ``id="turn-<event_id>"`` so the chat-page
+    ``turn_html_replace`` SSE handler can locate the prior turn DOM
+    node by id and swap it in-place. Without the id the handler's
+    ``getElementById('turn-' + supersedes_id)`` lookup misses and
+    the regenerated turn appends instead of replaces.
+    """
+    out = render_turn_html("BotA", "Hello.", role="bot", event_id=42)
+    assert 'id="turn-42"' in out
+    # The id must sit on the wrapper DIV, not somewhere nested inside.
+    assert out.startswith('<div id="turn-42" class="turn turn-bot">')
+
+
+def test_render_turn_html_omits_id_when_event_id_missing():
+    """Legacy callers (no ``event_id`` passed) get a clean DIV with no
+    id attribute — preserves the pre-T86 fragment shape.
+    """
+    out = render_turn_html("BotA", "Hello.", role="bot")
+    assert "id=" not in out
+    assert out.startswith('<div class="turn turn-bot">')

tests/test_streaming_ux.py

@@ -174,3 +174,74 @@ def test_chat_html_includes_stop_streaming_script(client, tmp_path):
     assert "stop-streaming" in body or "isStreaming" in body
     # Cancel route reference must be wired so the Stop button can call it.
     assert "/turns/cancel" in body
+
+
+def test_chat_html_has_turn_html_replace_listener(client, tmp_path):
+    """T86: the chat shell wires a JS handler for the ``turn_html_replace``
+    SSE event so regenerate-driven swaps land in connected tabs without a
+    page refresh.
+
+    This is a presence / string-check test: it verifies the handler is
+    embedded in the rendered template but does NOT drive a real browser
+    (no headless runner is wired into this test environment). The end-to-
+    end behaviour — receiving the event over SSE and replacing the prior
+    turn's DOM node — is therefore not exercised here; a manual smoke
+    check or future browser-driven test would close that gap.
+    """
+    _seed_chat(tmp_path / "test.db")
+    response = client.get("/chats/chat_bot_a")
+    assert response.status_code == 200
+    body = response.text
+    # The handler must be wired against the SSE event name the backend
+    # publishes (chat.services.regenerate -> "turn_html_replace").
+    assert "turn_html_replace" in body
+    # Confirm the handler reads the JSON payload's ``supersedes_id`` so
+    # it can locate the prior turn node. The exact lookup mechanism may
+    # vary, but the field name is part of the contract with the backend.
+    assert "supersedes_id" in body
+
+
+def test_rendered_turn_html_includes_event_id(client, tmp_path):
+    """T86 follow-up: the chat-detail Jinja loop stamps
+    ``id="turn-<event_id>"`` on every rendered turn DIV. Without this id
+    the ``turn_html_replace`` SSE handler's ``getElementById`` lookup
+    misses, falls through to ``insertAdjacentHTML('beforeend', …)``, and
+    the regenerated turn appears APPENDED instead of swapped in-place
+    (rendering the primary handler path dead code — exactly the gap the
+    T86 reviewer flagged).
+
+    Seed a user_turn + assistant_turn, GET the chat page, and assert the
+    response body carries both turns' event ids on the wrapper DIVs.
+    """
+    db_path = tmp_path / "test.db"
+    _seed_chat(db_path)
+    with open_db(db_path) as conn:
+        ut_id = append_event(
+            conn,
+            kind="user_turn",
+            payload={
+                "chat_id": "chat_bot_a",
+                "prose": "hello bot",
+                "segments": [],
+            },
+        )
+        at_id = append_event(
+            conn,
+            kind="assistant_turn",
+            payload={
+                "chat_id": "chat_bot_a",
+                "speaker_id": "bot_a",
+                "text": "Hi there.",
+                "truncated": False,
+                "user_turn_id": ut_id,
+            },
+        )
+        conn.commit()
+
+    response = client.get("/chats/chat_bot_a")
+    assert response.status_code == 200
+    body = response.text
+    # Both seeded turns must carry ``id="turn-<event_id>"`` so the SSE
+    # in-place swap can find them.
+    assert f'id="turn-{ut_id}"' in body
+    assert f'id="turn-{at_id}"' in body

tests/test_turn_common.py

@@ -104,10 +104,16 @@ def test_read_recent_dialogue_returns_chronological_pairs(tmp_path):
     with open_db(db) as conn:
         out = read_recent_dialogue(conn, "chat_a", limit=10)
 
-    assert out == [
-        {"speaker": "you", "text": "hello"},
-        {"speaker": "bot_a", "text": "Original."},
+    # Each entry now carries the source ``event_log.id`` as ``event_id``
+    # (T86 follow-up) so the chat-detail Jinja loop can stamp
+    # ``id="turn-<n>"`` on each rendered turn DIV — needed by the
+    # ``turn_html_replace`` SSE handler for in-place regenerate swaps.
+    speakers = [(e["speaker"], e["text"]) for e in out]
+    assert speakers == [
+        ("you", "hello"),
+        ("bot_a", "Original."),
     ]
+    assert all("event_id" in e and isinstance(e["event_id"], int) for e in out)
 
 
 def test_read_recent_dialogue_filters_superseded_and_other_chats(tmp_path):