updated cell outputs after refactor

Author: minh-hoque

examples/Context_summarization_with_realtime_api.ipynb

@@ -58,7 +58,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 1,
+   "execution_count": 51,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -89,7 +89,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 2,
+   "execution_count": 52,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -154,7 +154,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 3,
+   "execution_count": 53,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -185,7 +185,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 4,
+   "execution_count": 54,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -222,15 +222,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 20,
+   "execution_count": 67,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
       "📄 Text prompt tokens        : 42\n",
-      "🔊 Audio length (s)          : 10.75\n"
+      "🔊 Audio length (s)          : 11.55\n"
      ]
     }
    ],
@@ -285,15 +285,15 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 21,
+   "execution_count": 73,
    "metadata": {},
    "outputs": [
     {
      "name": "stdout",
      "output_type": "stream",
      "text": [
-      "🎤 Audio input tokens        : 105\n",
-      "⚖️  Audio/Text ratio        : 2.5×\n",
+      "🎤 Audio input tokens        : 112\n",
+      "⚖️  Audio/Text ratio        : 2.7×\n",
       "\n",
       "≈9 audio‑tokens / sec vs ≈1 token / word.\n"
      ]
@@ -374,7 +374,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 35,
+   "execution_count": 74,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -426,7 +426,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 36,
+   "execution_count": 75,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -490,7 +490,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 37,
+   "execution_count": 76,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -511,7 +511,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 38,
+   "execution_count": 77,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -569,7 +569,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 44,
+   "execution_count": 78,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -619,7 +619,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 48,
+   "execution_count": 79,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -634,7 +634,7 @@
   },
   {
    "cell_type": "code",
-   "execution_count": 49,
+   "execution_count": 81,
    "metadata": {},
    "outputs": [],
    "source": [
@@ -865,7 +865,6 @@
     "| **A/B test summarisation**<br/>Run your eval suite with summarisation *on* vs *off*. | Whether trimming actually improves quality for your domain—and how it affects latency & cost. |\n",
     "| **Swap summary styles**<br/>Change the system prompt to bullet points, JSON, English vs French, etc. | Which format the downstream assistant absorbs best; how language choice influences follow‑up answers. |\n",
     "| **Vary thresholds**<br/>Play with `SUMMARY_TRIGGER_TOKENS` (2 k → 8 k). | The sweet spot between model drift and summarisation overhead. |\n",
-    "| **Batch‑summary mode**<br/>Instead of every 4 000 tokens, summarise every *N* minutes. | Whether time‑based trimming feels more natural in certain UX flows. |\n",
     "| **Cost tracing**<br/>Log `usage.total_tokens` before/after summarisation. | Concrete ROI: token savings per hour of conversation. |\n",
     "\n",
     "\n",