fix(tui): stop persisting full tool output in trail lines (silent OOM death)

A heavy --tui session (browser snapshots, large tool outputs) silently
OOM-killed the Node parent within minutes — closing the gateway child's
stdin, which the user saw only as a bare "gateway exited" / stdin EOF.
CLI was immune. Root cause: each completed tool's verbose trail line
embedded up to 16KB of result_text, persisted in transcript Msg.tools[]
for the whole session and rendered EXPANDED by default, so an Ink
render-node tree was built for every one of up to 800 messages at once.
That tree blew past Node's heap at a few hundred MB — far below the 2.5GB
memory-monitor exit threshold, so the death was never even attributed.

- text.ts: persisted verbose tool-trail blocks now cap to a small preview
  (VERBOSE_TRAIL_MAX_CHARS=800/12 lines), not the 16KB live-render budget.
  Retained trail strings drop ~17x (12.2MB -> 0.7MB at 800 msgs); the live
  streaming tail still uses the larger LIVE_RENDER budget.
- tui_gateway/server.py: lower the gateway-side verbose text cap to match
  (1KB/16 lines) so we stop shipping output the TUI no longer renders.
- memoryMonitor.ts: derive critical/high thresholds from the real V8 heap
  ceiling (~88%/70%) instead of the hardcoded 2.5GB that killed the process
  at 31% of an 8GB ceiling; add a one-shot onWarn early-warning on fast
  sub-threshold heap growth so the next such death is diagnosable, not silent.
- entry.tsx: wire onWarn to a crash-log breadcrumb + stderr line.

Full tool output is unchanged in the agent context and SQLite session — this
is display/transport only, no behavior or context change.

Fixes #34095. Related #27282.

Tests: ui-tui text + new memoryMonitor suites (33 pass), python verbose-cap
guard (5 pass); full ui-tui suite shows no new failures vs pristine main.
E2E repro confirms the retention drop.

tests/test_tui_gateway_server.py

@@ -133,6 +133,20 @@ def test_tui_verbose_tool_details_are_capped_before_emit(monkeypatch):
     assert "one" not in capped
 
 
+def test_tui_verbose_default_cap_stays_small(monkeypatch):
+    # Regression guard for #34095: the verbose tool text shipped to the TUI is
+    # rendered into a persisted, expanded-by-default trail block for the whole
+    # session. Raising this cap back toward the old 16KB re-introduces the Ink
+    # render-tree blowup that silently OOM-killed the TUI. Keep it small.
+    assert server._TUI_VERBOSE_TEXT_MAX_CHARS <= 2_000
+
+    huge = "x" * 40_000
+    capped = server._cap_tui_verbose_text(huge)
+
+    assert len(capped) < 2_000
+    assert capped.startswith("[showing verbose tail; omitted ")
+
+
 def test_tui_verbose_tool_events_omit_details_when_redaction_fails(monkeypatch):
     redact_module = types.ModuleType("agent.redact")