feat(custom-model): show real-time llama.cpp backend status in the loading banner

Answers the underlying request behind investigating llama.cpp log
access: surface what the backend is actually doing, live, on top of
the existing countdown timer during a model load.

- getLatestLlamaSwapLogLine()/pruneIdleLlamaSwapLogTails()
  (custom-model-routes.ts): one persistent GET /api/events (SSE)
  connection held open per endpoint, parsing logData frames and
  keeping the latest source:"upstream" (backend llama-server) line —
  filtering out llama-swap's own source:"proxy" request-access lines.
  Idle-closed after 30s of no polling, same 20s sweep as the existing
  swap-displacement check.
- running-status route now returns logLine alongside the existing
  isLlamaSwap/running fields.
- Frontend: _watchLlamaSwapLoading's banner gains a second line
  ("llama.cpp: <line>", bootlog timestamp/level/component prefix
  stripped for display) that stays on the last real thing llama.cpp
  said rather than clearing to blank between polls.

⚠️ Caught and fixed before merge, not after: the first cut targeted
GET /logs (the endpoint the name suggests), shipped a working-looking
implementation with passing tests, and only failed a live check against
the real Nemesis llama-swap deployment — /logs turns out to carry ONLY
llama-swap's own proxy request-access log and never once showed a
single backend line, even seconds after a real, confirmed model swap
triggered via a direct API call. GET /api/events's logData frames
(with an explicit source field distinguishing upstream from proxy) are
the only source that actually has backend output; corrected and
re-verified live end-to-end through an actual forced swap before
writing this commit, confirmed live to hold its connection open
indefinitely (unlike /logs, which closes after a fixed ~100KB).

12 tests for the corrected /api/events parsing (SSE frame buffering
across chunk boundaries, source filtering, malformed/wrong-type frames,
connection reuse, idle pruning) plus 2 for the frontend banner
rendering. Typecheck/lint/frontend-syntax clean; full suite shows no
new regressions (14 more passing than baseline, matching the new
tests; same pre-existing Windows-environment failures).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RqZeHrRS6DYcGcGX2p9EwG

test/custom-model-run-menu-ui.test.ts

@@ -626,6 +626,54 @@ describe('Custom Model Endpoint Profiles: _watchLlamaSwapLoading polling', () =>
     expect(toastCalls.at(-1)).toMatch(/ready/i);
   });
 
+  it('adds a second line with the real llama.cpp log line once one is available, stripped of the bootlog prefix', async () => {
+    const { app } = bootApp({});
+    const bannerMessages: string[] = [];
+    app._showCenterStatus = (message: string) => {
+      bannerMessages.push(message);
+      return { dismiss: () => {}, setMessage: (next: string) => bannerMessages.push(next) };
+    };
+    app.showToast = () => {};
+    let statusCalls = 0;
+    app._apiJson = async (path: string) => {
+      if (path === '/api/model-endpoints') return null; // size lookup — unrelated to this test
+      statusCalls += 1;
+      if (statusCalls === 1) {
+        return {
+          isLlamaSwap: true,
+          running: [{ model: 'qwen3', state: 'starting' }],
+          logLine: '0.31.428.568 I srv  llama_server: model loaded',
+        };
+      }
+      return { isLlamaSwap: true, running: [{ model: 'qwen3', state: 'ready' }] };
+    };
+
+    await app._watchLlamaSwapLoading('llama-box', 'qwen3', 'sess-1', 5, 200);
+
+    // First render (before any poll has landed) has no log line at all.
+    expect(bannerMessages[0]).not.toMatch(/llama\.cpp:/);
+    // Second render carries the log line, bootlog prefix (timestamp/level/component) stripped.
+    const withLogLine = bannerMessages.find((m) => m.includes('llama.cpp:'));
+    expect(withLogLine).toContain('llama.cpp: llama_server: model loaded');
+    expect(withLogLine).not.toContain('0.31.428.568');
+    expect(withLogLine).not.toContain(' I srv');
+  });
+
+  it('shows no second line at all when the endpoint has no logLine to offer', async () => {
+    const { app } = bootApp({});
+    const bannerMessages: string[] = [];
+    app._showCenterStatus = (message: string) => {
+      bannerMessages.push(message);
+      return { dismiss: () => {}, setMessage: (next: string) => bannerMessages.push(next) };
+    };
+    app.showToast = () => {};
+    app._apiJson = async () => ({ isLlamaSwap: true, running: [{ model: 'qwen3', state: 'ready' }] });
+
+    await app._watchLlamaSwapLoading('llama-box', 'qwen3', 'sess-1', 5, 200);
+
+    expect(bannerMessages.some((m) => m.includes('llama.cpp:'))).toBe(false);
+  });
+
   it('gives up after the bounded wait, turns the banner into a sticky error, and closes the session', async () => {
     const { app } = bootApp({});
     const banners: Array<{ message: string; opts: unknown }> = [];