feat(chat): stop an in-flight answer — Send becomes Stop, the partial is kept and persisted, the model stream is torn down

tests/e2e/test_agent_document_tools.py

@@ -211,8 +211,9 @@ def _last_query_log() -> QueryLog:
 # --------------------------------------------------------------------------
 
 #: Records every value #send-label takes during the turn (a
-#: MutationObserver on the element), so the transient "Calling tool…"
-#: state is captured deterministically — no polling race.
+#: MutationObserver on the element), so the in-flight label state is
+#: captured deterministically — no polling race. Phase 48: the label is
+#: the Send↔Stop morph ("Stop" holds for the whole in-flight turn).
 LABEL_RECORDER = """
 () => {
   if (window.__labelsInstalled) return;
@@ -232,6 +233,29 @@ LABEL_RECORDER = """
 }
 """
 
+#: Records every value #send-status takes during the turn (phase 48:
+#: the transient "… is listing documents" / "… is reading <source/path>"
+#: calling-tool states moved here from the button label), so their order
+#: is captured deterministically — no polling race.
+STATUS_RECORDER = """
+() => {
+  if (window.__statusesInstalled) return;
+  window.__statusesInstalled = true;
+  window.__statuses = [];
+  const el = document.querySelector('#send-status');
+  if (!el) return;
+  const rec = (v) => {
+    const l = window.__statuses;
+    if (!l.length || l[l.length - 1] !== v) l.push(v);
+  };
+  rec(el.textContent);
+  new MutationObserver(() => rec(el.textContent)).observe(el, {
+    childList: true,
+    subtree: true,
+  });
+}
+"""
+
 #: Captures the raw SSE ``data:`` payloads of the /api/chat stream
 #: (a response clone read in the background) — wire-level assertions for
 #: the ``tool`` frames, independent of the UI rendering.
@@ -266,12 +290,14 @@ def _install_page_hooks(page: Page) -> None:
     """Install both hooks on the loaded page (post-goto, pre-submit).
 
     The fetch wrapper only needs to be in place before the turn's
-    ``fetch("/api/chat")`` call; the label observer needs the rendered
-    ``#send-label``. (``add_init_script`` would not do — it binds to the
-    NEXT navigation, and the story page is navigated exactly once.)
+    ``fetch("/api/chat")`` call; the observers need the rendered
+    ``#send-label`` / ``#send-status``. (``add_init_script`` would not do
+    — it binds to the NEXT navigation, and the story page is navigated
+    exactly once.)
     """
     page.evaluate(SSE_HOOK)
     page.evaluate(LABEL_RECORDER)
+    page.evaluate(STATUS_RECORDER)
 
 
 def _frames(page: Page) -> list[dict]:
@@ -307,10 +333,16 @@ def _submit(page: Page, question: str) -> None:
 
 
 def _wait_settled(page: Page) -> None:
-    """The turn is complete: answer text in the bubble, button recovered."""
+    """The turn is complete: answer text in the bubble, button recovered.
+
+    Phase 48: the label assertion carries the settle wait with an
+    explicit timeout — the in-flight button is the enabled Stop control
+    (never disabled), so ``to_be_enabled`` no longer blocks until the
+    turn settles, and Playwright expect's default (5s) does not inherit
+    the page default."""
     expect(page.locator(".msg.brain .bubble").last).not_to_have_text("", timeout=30_000)
     expect(page.locator("#send-btn")).to_be_enabled(timeout=30_000)
-    expect(page.locator("#send-label")).to_have_text("Send")
+    expect(page.locator("#send-label")).to_have_text("Send", timeout=30_000)
 
 
 # --------------------------------------------------------------------------
@@ -327,20 +359,31 @@ def test_marker_question_lists_reads_and_quotes(
     _install_page_hooks(page)
 
     _submit(page, MARKER_QUESTION)
-    # The "calling tool" label window is transient: the first `tool`
-    # frame sets it and it holds until the FIRST answer delta (the agent
-    # loop completes before the answer stream) — ~0.4 s at the mock's
-    # 0.1 s tool-frame pacing. A polling expect can stride straight over
-    # that window (observed flake, fixed in phase 44 task 03), so the
-    # pre-submit MutationObserver record below is the deterministic
-    # source of truth for the label transition.
+    # The "calling tool" STATUS window is transient: the first `tool`
+    # frame sets #send-status and it holds until the FIRST answer delta
+    # (the agent loop completes before the answer stream) — ~0.4 s at
+    # the mock's 0.1 s tool-frame pacing. A polling expect can stride
+    # straight over that window (observed flake, fixed in phase 44 task
+    # 03), so the pre-submit MutationObserver records below are the
+    # deterministic source of truth for the label/status transitions.
     _wait_settled(page)
 
-    # The label transition, recorded deterministically (no race):
-    # Thinking… → Calling tool… → … → Send.
+    # Phase 48 (owner-locked): the in-flight button is the Stop control —
+    # the label holds "Stop" for the whole turn (it no longer relabels to
+    # "Calling tool…"), and the transient calling-tool state moved to
+    # #send-status: "… is listing documents" then "… is reading <sp>",
+    # in order (both recorded deterministically — no race).
     labels = page.evaluate("() => window.__labels")
-    assert "Calling tool…" in labels, labels
-    assert labels.index("Calling tool…") > labels.index("Thinking…")
+    assert "Stop" in labels, labels
+    statuses = page.evaluate("() => window.__statuses")
+    i_list = next(
+        (i for i, s in enumerate(statuses) if "is listing documents" in s), None
+    )
+    i_read = next(
+        (i for i, s in enumerate(statuses) if f"is reading {READ_SP}" in s), None
+    )
+    assert i_list is not None and i_read is not None, statuses
+    assert i_list < i_read, statuses
 
     # Wire level: exactly two `tool` frames — list then read — and both
     # ahead of the first `delta` frame.