Log at info level changedagents-and-tools/tool-use/tool-runner
Recorded here
Lines+50added
Lines−0removed
From line
2
where the diff opens
First seen
14 Aug 2026
this site's first read of the page
Recorded edits21to this page, all time
## Availability ### API support #### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) #### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
The whole hunk
from line 2, old and new numbered
/
from line 2
22title: Tool runner (SDK)
33url: https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner
44description: Use the SDK's tool runner to handle the agentic loop, error wrapping, and type safety automatically.
5featureMetadata:
6 status: beta
7 supportedModels:
8 - claude-fable-5-1
9 - claude-mythos-5-1
10 - claude-fable-5
11 - claude-mythos-5
12 - claude-mythos-preview
13 - claude-opus-5-5
14 - claude-opus-5
15 - claude-sonnet-5-5
16 - claude-sonnet-5
17 - claude-haiku-5-5
18 - claude-haiku-4-5-20251001
19 - claude-opus-4-8
20 - claude-opus-4-7
21 - claude-opus-4-6
22 - claude-sonnet-4-6
23 - claude-opus-4-5-20251101
24 - claude-sonnet-4-5-20250929
25 supportedPlatforms:
26 Claude API: beta
27 Claude Platform on AWS: beta
28 Amazon Bedrock: beta
29 Amazon Bedrock (InvokeModel): beta
30 Claude Models on Google Cloud (Google managed): beta
31 Microsoft Foundry: beta
532---
633
734The tool runner handles the agentic loop, error wrapping, and type safety so you don’t have to. When you need human-in-the-loop approval, custom logging, or conditional execution, use the [manual loop](https://platform.claude.com/docs/en/agents-and-tools/tool-use/handle-tool-calls) instead.
from line 1810
17831810 Specify tool schemas, write effective descriptions, and control when Claude calls your tools.
17841811 </Card>
17851812</CardGroup>
1813
1814## Availability
1815
1816Tool runner is in beta on every model.
1817
1818### API support
1819
1820#### [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages)
1821
1822* Availability: Available
1823
1824| Status | Cloud platforms |
1825| ------ | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
1826| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws), [Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedrock), [Amazon Bedrock (InvokeModel)](https://platform.claude.com/docs/en/build-with-claude/claude-on-amazon-bedrock-legacy), [Claude Models on Google Cloud (Google managed)](https://platform.claude.com/docs/en/build-with-claude/claude-models-on-google-cloud/google-managed), [Microsoft Foundry](https://platform.claude.com/docs/en/build-with-claude/claude-in-microsoft-foundry) |
1827
1828#### [Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview)
1829
1830* Availability: Available
1831* Usage: The Python, TypeScript and Go SDKs have a session tool runner that runs your tools for a session’s custom tool calls. The session itself runs the agent loop.
1832
1833| Status | Cloud platforms |
1834| ------ | ------------------------------------------------------------------------------------------------------------------ |
1835| Beta | Claude API, [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws) |
17861836
No line in this hunk matches that.