docs: Reflect and Retry Tool Plugin - Update ADK doc according to issue #796 - 3

docs/plugins/index.md

@@ -55,6 +55,24 @@ related callback functions together to be used across a workflow. This makes
 Plugins an ideal solution for implementing features that cut across your entire
 agent application.
 
+## Prebuilt Plugins
+
+ADK includes several plugins that you can add to your agent workflows
+immediately:
+
+*   [**Reflect and Retry Tools**](/adk-docs/plugins/reflect-and-retry/):
+    Tracks tool failures and intelligently retries tool requests.
+*   [**BigQuery Logging**](https://github.com/google/adk-python/blob/main/src/google/adk/plugins/bigquery_logging_plugin.py):
+    Enables agent logging and analysis with BigQuery.
+*   [**Context Filter**](https://github.com/google/adk-python/blob/main/src/google/adk/plugins/context_filter_plugin.py):
+    Filters the generative AI context to reduce its size.
+*   [**Global Instruction**](https://github.com/google/adk-python/blob/main/src/google/adk/plugins/global_instruction_plugin.py):
+    Plugin that provides global instructions functionality at the App level.
+*   [**Save Files as Artifacts**](https://github.com/google/adk-python/blob/main/src/google/adk/plugins/save_files_as_artifacts_plugin.py):
+    Saves files included in user messages as Artifacts.
+*   [**Logging**](https://github.com/google/adk-python/blame/main/src/google/adk/plugins/logging_plugin.py):
+    Log important information at each agent workflow callback point.
+
 ## Define and register Plugins
 
 This section explains how to define Plugin classes and register them as part of

docs/plugins/reflect-and-retry.md

@@ -0,0 +1,82 @@
+# Reflect and Retry Tool Plugin
+
+<div class="language-support-tag">
+    <span class="lst-supported">Supported in ADK</span><span class="lst-python">Python v1.16.0</span>
+</div>
+
+The Reflect and Retry Tool plugin can help your agent recover from error
+responses from ADK [Tools](/adk-docs/tools-custom/) and automatically retry the
+tool request. This plugin intercepts tool failures, provides structured guidance
+to the AI model for reflection and correction, and retries the operation up to a
+configurable limit. This plugin can help you build more resilience into your
+agent workflows, including the following capabilities:
+
+*   **Concurrency safe**: Uses locking to safely handle parallel tool executions.
+*   **Configurable scope**: Tracks failures per-invocation (default) or globally.
+*   **Granular tracking**: Failure counts are tracked per-tool.
+*   **Custom error extraction**: Supports detecting errors in normal tool responses.
+
+## Add Reflect and Retry Plugin
+
+Add this plugin to your ADK workflow by adding it to the plugins setting of your
+ADK project's App object, as shown below:
+
+```python
+from google.adk.apps.app import App
+from google.adk.plugins import ReflectAndRetryToolPlugin
+
+app = App(
+    name="my_app",
+    root_agent=root_agent,
+    plugins=[
+        ReflectAndRetryToolPlugin(max_retries=3),
+    ],
+)
+```
+
+With this configuration, if any tool called by an agent returns an error, the
+request is updated and tried again, up to a maximum of 3 attempts, per tool.
+
+## Configuration settings
+
+The Reflect and Retry Plugin has the following configuration options:
+
+*   **`max_retries`**: (optional) Total number of additional attempts the system
+    makes to receive a non-error response. Default value is 3.
+*   **`throw_exception_if_retry_exceeded`**: (optional) If set to `False`, the
+    system does not raise an error if the final retry attempt fails. Default
+    value is `True`.
+*   **`tracking_scope`**: (optional)
+    *   **`TrackingScope.INVOCATION`**: Track tool failures across a single
+        invocation and user. This value is the default.
+    *   **`TrackingScope.GLOBAL`**: Track tool failures across all invocations
+        and all users.
+
+### Advanced configuration
+
+You can further modify the behavior of this plugin by extending the
+`ReflectAndRetryToolPlugin` class. The following code sample
+demonstrates a simple extension of the behavior by selecting
+responses with an error status:
+
+```python
+class CustomRetryPlugin(ReflectAndRetryToolPlugin):
+  async def extract_error_from_result(self, *, tool, tool_args,tool_context,
+  result):
+    # Detect error based on response content
+    if result.get('status') == 'error':
+        return result
+    return None  # No error detected
+
+# add this modified plugin to your App object:
+error_handling_plugin = CustomRetryPlugin(max_retries=5)
+```
+
+## Next steps
+
+For complete code samples using the Reflect and Retry plugin, see the following: 
+
+*   [Basic](https://github.com/google/adk-python/tree/main/contributing/samples/plugin_reflect_tool_retry/basic)
+    code sample
+*   [Hallucinating function name](https://github.com/google/adk-python/tree/main/contributing/samples/plugin_reflect_tool_retry/hallucinating_func_name)
+    code sample

mkdocs.yml

@@ -231,6 +231,7 @@ nav:
       - events/index.md
     - Plugins:
       - plugins/index.md
+      - Reflect and retry: plugins/reflect-and-retry.md
     - MCP:
       - mcp/index.md
     - A2A Protocol: