From 245785e44a9c58ad34b7b4bbf5af6768966add72 Mon Sep 17 00:00:00 2001
From: "github-actions[bot]" <github-actions[bot]@users.noreply.github.com>
Date: Fri, 8 May 2026 20:44:30 +0000
Subject: [PATCH] docs: document async tool support for Grok and Ultravox
 Realtime

- Add note about cancel_on_interruption=False support in both services
- Document Ultravox's placeholder behavior for async tools
- Document Grok's async tool result delivery mechanism
- Add links to new async tool example files
- Note that streamed intermediate results are not supported

Related to pipecat-ai/pipecat#4447
---
 api-reference/server/services/s2s/grok.mdx     | 8 ++++++++
 api-reference/server/services/s2s/ultravox.mdx | 8 ++++++++
 2 files changed, 16 insertions(+)

diff --git a/api-reference/server/services/s2s/grok.mdx b/api-reference/server/services/s2s/grok.mdx
index f4841e81..90f4bced 100644
--- a/api-reference/server/services/s2s/grok.mdx
+++ b/api-reference/server/services/s2s/grok.mdx
@@ -22,6 +22,13 @@ description: "Real-time speech-to-speech service implementation using xAI's Grok
   >
     Complete Grok Realtime conversation example
   </Card>
+  <Card
+    title="Async Tool Example"
+    icon="play"
+    href="https://github.com/pipecat-ai/pipecat/blob/main/examples/realtime/realtime-grok-async-tool.py"
+  >
+    Grok with async function calling (cancel_on_interruption=False)
+  </Card>
   <Card
     title="Grok Voice Documentation"
     icon="book"
@@ -255,6 +262,7 @@ await task.queue_frame(
 - **Available voices**: Ara (default), Rex, Sal, Eve, and Leo.
 - **G.711 support**: PCMU and PCMA formats are supported at a fixed 8000 Hz rate, useful for telephony integrations.
 - **System instruction precedence**: The `system_instruction` from service settings takes precedence over an initial system message in the LLM context. A warning is logged when both are set.
+- **Async tool support**: Functions registered with `cancel_on_interruption=False` are supported. The final tool result is delivered via the formal tool-result channel once the async function completes. Streamed intermediate results (`is_final=False`) are not supported.
 
 ## Event Handlers
 
diff --git a/api-reference/server/services/s2s/ultravox.mdx b/api-reference/server/services/s2s/ultravox.mdx
index da1bc4f6..4fb4dba9 100644
--- a/api-reference/server/services/s2s/ultravox.mdx
+++ b/api-reference/server/services/s2s/ultravox.mdx
@@ -22,6 +22,13 @@ description: "Real-time speech-to-speech service implementation using Ultravox's
   >
     Complete Ultravox Realtime conversation example
   </Card>
+  <Card
+    title="Async Tool Example"
+    icon="play"
+    href="https://github.com/pipecat-ai/pipecat/blob/main/examples/realtime/realtime-ultravox-async-tool.py"
+  >
+    Ultravox with async function calling (cancel_on_interruption=False)
+  </Card>
   <Card
     title="Ultravox Documentation"
     icon="book"
@@ -247,3 +254,4 @@ await task.queue_frame(
 - **Output medium**: The service supports both `"voice"` and `"text"` output modes, switchable at runtime using `LLMUpdateSettingsFrame`.
 - **Call duration limits**: When using `AgentInputParams` or `OneShotInputParams`, you can set a maximum call duration between 10 seconds and 1 hour.
 - **Tools with agents**: When using `AgentInputParams`, tools are configured on the agent itself. Use `one_shot_selected_tools` only with `OneShotInputParams`.
+- **Async tool support**: Functions registered with `cancel_on_interruption=False` are supported. When an async function is invoked, Ultravox ships a placeholder `client_tool_result` immediately to unfreeze the conversation (since Ultravox's API freezes between tool invocation and result). The actual result is injected as user-side text once the tool completes. Streamed intermediate results (`is_final=False`) are not supported.