From f6575effa56614782566821262ed4015289f6af7 Mon Sep 17 00:00:00 2001
From: chengyongru <chengyongru.ai@gmail.com>
Date: Mon, 30 Mar 2026 16:55:25 +0800
Subject: [PATCH] feat(status): display cache hit rate in /status command

---
 nanobot/utils/helpers.py   |  6 +++-
 tests/test_build_status.py | 59 ++++++++++++++++++++++++++++++++++++++
 2 files changed, 64 insertions(+), 1 deletion(-)
 create mode 100644 tests/test_build_status.py

diff --git a/nanobot/utils/helpers.py b/nanobot/utils/helpers.py
index a10a4f18b..64b8448ec 100644
--- a/nanobot/utils/helpers.py
+++ b/nanobot/utils/helpers.py
@@ -255,14 +255,18 @@ def build_status_content(
     )
     last_in = last_usage.get("prompt_tokens", 0)
     last_out = last_usage.get("completion_tokens", 0)
+    cached = last_usage.get("cached_tokens", 0)
     ctx_total = max(context_window_tokens, 0)
     ctx_pct = int((context_tokens_estimate / ctx_total) * 100) if ctx_total > 0 else 0
     ctx_used_str = f"{context_tokens_estimate // 1000}k" if context_tokens_estimate >= 1000 else str(context_tokens_estimate)
     ctx_total_str = f"{ctx_total // 1024}k" if ctx_total > 0 else "n/a"
+    token_line = f"\U0001f4ca Tokens: {last_in} in / {last_out} out"
+    if cached and last_in:
+        token_line += f" ({cached * 100 // last_in}% cached)"
     return "\n".join([
         f"\U0001f408 nanobot v{version}",
         f"\U0001f9e0 Model: {model}",
-        f"\U0001f4ca Tokens: {last_in} in / {last_out} out",
+        token_line,
         f"\U0001f4da Context: {ctx_used_str}/{ctx_total_str} ({ctx_pct}%)",
         f"\U0001f4ac Session: {session_msg_count} messages",
         f"\u23f1 Uptime: {uptime}",
diff --git a/tests/test_build_status.py b/tests/test_build_status.py
new file mode 100644
index 000000000..d98301cf7
--- /dev/null
+++ b/tests/test_build_status.py
@@ -0,0 +1,59 @@
+"""Tests for build_status_content cache hit rate display."""
+
+from nanobot.utils.helpers import build_status_content
+
+
+def test_status_shows_cache_hit_rate():
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300, "cached_tokens": 1200},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "60% cached" in content
+    assert "2000 in / 300 out" in content
+
+
+def test_status_no_cache_info():
+    """Without cached_tokens, display should not show cache percentage."""
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "cached" not in content.lower()
+    assert "2000 in / 300 out" in content
+
+
+def test_status_zero_cached_tokens():
+    """cached_tokens=0 should not show cache percentage."""
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 2000, "completion_tokens": 300, "cached_tokens": 0},
+        context_window_tokens=128000,
+        session_msg_count=10,
+        context_tokens_estimate=5000,
+    )
+    assert "cached" not in content.lower()
+
+
+def test_status_100_percent_cached():
+    content = build_status_content(
+        version="0.1.0",
+        model="glm-4-plus",
+        start_time=1000000.0,
+        last_usage={"prompt_tokens": 1000, "completion_tokens": 100, "cached_tokens": 1000},
+        context_window_tokens=128000,
+        session_msg_count=5,
+        context_tokens_estimate=3000,
+    )
+    assert "100% cached" in content