Add Kotlin safety settings and includeContents to the agent docs

docs/agents/llm-agents.md

@@ -663,6 +663,12 @@ Control whether the agent receives the prior conversation history.
             .build();
     ```
 
+=== "Kotlin"
+
+    ```kotlin
+    --8<-- "examples/kotlin/snippets/agents/llm-agent/CapitalAgent.kt:include_contents"
+    ```
+
 !!! note "Go v2.0.0: agent execution modes"
 
     ADK Go v2.0.0 introduces an explicit `Mode` field on `llmagent.Config` that

docs/safety/index.md

@@ -1,7 +1,7 @@
 # Safety and Security for AI Agents
 
 <div class="language-support-tag">
-  <span class="lst-supported">Supported in ADK</span><span class="lst-python">Python</span><span class="lst-typescript">TypeScript</span><span class="lst-go">Go</span><span class="lst-java">Java</span>
+  <span class="lst-supported">Supported in ADK</span><span class="lst-python">Python</span><span class="lst-typescript">TypeScript</span><span class="lst-go">Go</span><span class="lst-java">Java</span><span class="lst-kotlin">Kotlin</span>
 </div>
 
 As AI agents grow in capability, ensuring they operate safely, securely, and align with your brand values is paramount. Uncontrolled agents can pose risks, including executing misaligned or harmful actions, such as data exfiltration, and generating inappropriate content that can impact your brand’s reputation. **Sources of risk include vague instructions, model hallucination, jailbreaks and prompt injections from adversarial users, and indirect prompt injections via tool use.**
@@ -368,6 +368,31 @@ Gemini models come with in-built safety mechanisms that can be leveraged to impr
     })
     ```
 
+=== "Kotlin"
+
+    ```kotlin
+    import com.google.adk.kt.agents.LlmAgent
+    import com.google.adk.kt.types.GenerateContentConfig
+    import com.google.adk.kt.types.HarmBlockThreshold
+    import com.google.adk.kt.types.HarmCategory
+    import com.google.adk.kt.types.SafetySetting
+
+    val agent =
+        LlmAgent(
+            // ...
+            generateContentConfig =
+                GenerateContentConfig(
+                    safetySettings =
+                        listOf(
+                            SafetySetting(
+                                category = HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
+                                threshold = HarmBlockThreshold.OFF,
+                            ),
+                        ),
+                ),
+        )
+    ```
+
 * **System instructions for safety**: [System instructions](https://cloud.google.com/vertex-ai/generative-ai/docs/multimodal/safety-system-instructions) for Gemini models on Agent Platform provide direct guidance to the model on how to behave and what type of content to generate. By providing specific instructions, you can proactively steer the model away from generating undesirable content to meet your organization’s unique needs. You can craft system instructions to define content safety guidelines, such as prohibited and sensitive topics, and disclaimer language, as well as brand safety guidelines to ensure the model's outputs align with your brand's voice, tone, values, and target audience.
 
 While these measures are robust against content safety, you need additional checks to reduce agent misalignment, unsafe actions, and brand safety risks.

examples/kotlin/snippets/agents/llm-agent/CapitalAgent.kt

@@ -2,14 +2,18 @@ package com.google.adk.kt.examples.agents.llmagent
 
 import com.google.adk.kt.agents.Instruction
 import com.google.adk.kt.agents.LlmAgent
+import com.google.adk.kt.agents.LlmAgent.IncludeContents
 import com.google.adk.kt.annotations.Param
 import com.google.adk.kt.annotations.Tool
 import com.google.adk.kt.models.Gemini
 import com.google.adk.kt.runners.InMemoryRunner
 import com.google.adk.kt.sessions.InMemorySessionService
 import com.google.adk.kt.types.Content
 import com.google.adk.kt.types.GenerateContentConfig
+import com.google.adk.kt.types.HarmBlockThreshold
+import com.google.adk.kt.types.HarmCategory
 import com.google.adk.kt.types.Part
+import com.google.adk.kt.types.SafetySetting
 import com.google.adk.kt.types.Schema
 import com.google.adk.kt.types.Type
 import kotlinx.coroutines.flow.collect
@@ -77,8 +81,16 @@ fun main() =
                 model = Gemini(name = "gemini-flash-latest"),
                 generateContentConfig =
                     GenerateContentConfig(
+                        // More deterministic output
                         temperature = 0.2f,
                         maxOutputTokens = 250,
+                        safetySettings =
+                            listOf(
+                                SafetySetting(
+                                    category = HarmCategory.HARM_CATEGORY_DANGEROUS_CONTENT,
+                                    threshold = HarmBlockThreshold.BLOCK_LOW_AND_ABOVE,
+                                ),
+                            ),
                     ),
             )
         // --8<-- [end:gen_config]
@@ -123,6 +135,16 @@ fun main() =
             )
         // --8<-- [end:schema_example]
 
+        // --8<-- [start:include_contents]
+        val statelessAgent =
+            LlmAgent(
+                name = "capital_agent",
+                model = Gemini(name = "gemini-flash-latest"),
+                // ... other params
+                includeContents = IncludeContents.NONE,
+            )
+        // --8<-- [end:include_contents]
+
         // --8<-- [start:full_example]
         val finalAgent =
             LlmAgent(