From 990c86c636458742d31a0a4662f270c0164c8269 Mon Sep 17 00:00:00 2001
From: Shahin Saadati <shahins@google.com>
Date: Thu, 20 Aug 2026 09:28:00 -0700
Subject: [PATCH] Extend the compaction summarizer section to Kotlin

The Define a Summarizer group showed Python, Java and TypeScript but not
Kotlin, and two lines of surrounding prose understated Kotlin as a
result: one attributed LlmEventSummarizer to Python and Java only, the
other said only Python and Java can customize the prompt template.
Kotlin has had LlmEventSummarizer since v0.3.0 and exposes
promptTemplate as a constructor parameter.

This is partial coverage rather than an untouched page - the page is
already Kotlin-badged and has a Kotlin tab for the token-threshold
config. That tab is inline, as are all four siblings in this group, so
the new tab is inline too rather than the new .kt file the backlog
suggested; mixing forms between two Kotlin tabs on one page would be
worse than either choice on its own.
---
 docs/context/compaction.md | 39 +++++++++++++++++++++++++++++++++-----
 1 file changed, 34 insertions(+), 5 deletions(-)

diff --git a/docs/context/compaction.md b/docs/context/compaction.md
index 655be3db08..a78af95554 100644
--- a/docs/context/compaction.md
+++ b/docs/context/compaction.md
@@ -196,8 +196,8 @@ a compactor object
 
 ### Define a Summarizer {#define-summarizer}
 You can customize the process of context compression by defining a summarizer.
-The `LlmEventSummarizer` (Python/Java) or `LlmSummarizer` (TypeScript) class allows
-you to specify a particular model for summarization.
+The `LlmEventSummarizer` (Python, Java and Kotlin) or `LlmSummarizer` (TypeScript)
+class allows you to specify a particular model for summarization.
 The following code example demonstrates how to define and configure a custom summarizer:
 
 === "Python"
@@ -278,8 +278,37 @@ The following code example demonstrates how to define and configure a custom sum
     });
     ```
 
-You can further refine the compactor by modifying its summarizer. In Python and Java,
-customize the `prompt_template` on `LlmEventSummarizer`. In TypeScript, customize
-the `prompt` on `LlmSummarizer`. For more details, see the
+=== "Kotlin"
+
+    ```kotlin
+    import com.google.adk.kt.apps.App
+    import com.google.adk.kt.models.Gemini
+    import com.google.adk.kt.summarizer.EventsCompactionConfig
+    import com.google.adk.kt.summarizer.LlmEventSummarizer
+
+    // Define the AI model to be used for summarization:
+    val summarizationLlm = Gemini(name = "gemini-flash-latest")
+
+    // Create the summarizer with the custom model:
+    val mySummarizer = LlmEventSummarizer(model = summarizationLlm)
+
+    // Configure the App with the custom summarizer and compaction settings:
+    val app =
+        App(
+            appName = "my-agent",
+            rootAgent = rootAgent,
+            eventsCompactionConfig =
+                EventsCompactionConfig(
+                    compactionInterval = 3,
+                    overlapSize = 1,
+                    summarizer = mySummarizer,
+                ),
+        )
+    ```
+
+You can further refine the compactor by modifying its summarizer. In Python, Java
+and Kotlin, customize the prompt template on `LlmEventSummarizer` — the property is
+`prompt_template` in Python and Java, and `promptTemplate` in Kotlin. In TypeScript,
+customize the `prompt` on `LlmSummarizer`. For more details, see the
 [`LlmEventSummarizer` code](https://github.com/google/adk-python/blob/main/src/google/adk/apps/llm_event_summarizer.py#L60) or
 [`LlmSummarizer` code](https://github.com/google/adk-js/blob/main/core/src/context/summarizers/llm_summarizer.ts).