perf: fix model reload thrash and cut time-to-first-token

Ollama reloaded the chat model mid-message because plan/summary/router
calls sent divergent runner options (no num_ctx/num_batch) and omitted
keep_alive — the main cause of perceived slowness.

- share one keep-alive httpx.AsyncClient for all Ollama calls
- unify runner options (runner_options) + keep_alive on every model
  call, embeddings included
- drop the blocking LLM routing fallback (pure lexical heuristic)
- run RAG recall + plan + code-model pick in parallel inside the SSE
  stream, after the start event
- RAG cosine scoring off the event loop; cache /api/tags 30s and
  nvidia-smi 5s; frontend polls 2s->5s, warm poll backoff, dedup
  config fetch

feat: working session menu in TopBar (switch/create/rename/delete)
feat: workspace file deletion (DELETE /api/files + UI trash buttons)
docs: recommended Ollama env vars (KEEP_ALIVE, MAX_LOADED_MODELS...)

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

frontend/src/lib/time.ts

@@ -0,0 +1,8 @@
+/** Date relative courte en français (« il y a 5 min »). */
+export function relTime(ts: number): string {
+  const diff = Date.now() / 1000 - ts;
+  if (diff < 60) return "à l'instant";
+  if (diff < 3600) return `il y a ${Math.floor(diff / 60)} min`;
+  if (diff < 86400) return `il y a ${Math.floor(diff / 3600)} h`;
+  return `il y a ${Math.floor(diff / 86400)} j`;
+}