Follow Discord
Sweep 27 Oct 2026 · 19:04Z Build v2.1.312 531 read Stable v2.1.308 Latest v2.1.312 Next v2.1.312 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 23 Oct 2026
One change · api

server-tools changedagents-and-tools/tool-use/server-tools

Nearest release: v2.1.310, published 11 hours after this site recorded the change. Shown because the two are within 24 hours of each other. Nothing here says the release caused the edit.

Recorded here
Lines+4added
Lines−4removed
From line 10 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits16to this page, all time

The whole hunk

from line 10, old and new numbered
/
lines
from line 10
1010 
1111The `server_tool_use` block appears in Claude's response when a server-executed tool runs. Its `id` field uses the `srvtoolu_` prefix to distinguish it from client tool calls:
1212 
13```text wrap
13```json
1414{
1515 "type": "server_tool_use",
1616 "id": "srvtoolu_01A2B3C4D5E6F7G8H9",
from line 408
408408 With [programmatic tool calling](https://platform.claude.com/docs/en/agents-and-tools/tool-use/programmatic-tool-calling), the same response shape means something different. The client `tool_use` block comes from code that is running in the `code_execution` tool rather than from Claude directly, and its `caller` field names the `code_execution` block that called it. That code has already started: it is paused waiting for your `tool_result` blocks, and sending them resumes the execution instead of starting a deferred tool. The `code_execution` block's own result block arrives once the code completes, which can take more than one round of tool results. The follow-up user message itself is the same in both cases; with programmatic tool calling, also pass back the `id` from the response's `container` field, as that page shows.
409409</Note>
410410 
411```text wrap
411```json
412412{
413413 "stop_reason": "tool_use",
414414 "content": [
from line 449
449449 
450450The API attaches your results to the still-open assistant turn, runs the deferred server tool (for paused code execution, resumes it), and then lets Claude continue. For a server tool Claude called directly, the next response starts with the result block that answers the previous response's `server_tool_use` `id`, followed by the newly generated content and a fresh `stop_reason`:
451451 
452```text wrap
452```json
453453{
454454 "stop_reason": "end_turn",
455455 "content": [
from line 1010
10101010 ```
10111011</CodeGroup>
10121012 
1013This code is also correct when Claude does not mix the two kinds of call. A turn with only client `tool_use` blocks takes the same continuation path, and a turn with only server tool calls needs no client `tool_result` blocks from you: its result blocks are normally already present, and one that comes back suspended, such as a [`pause_turn` response](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools#the-server-side-loop-and-pause-turn), is re-sent as-is instead.
1013This code is also correct when Claude does not mix the two kinds of call. A turn with only client `tool_use` blocks takes the same continuation path. A turn with only server tool calls needs no client `tool_result` blocks from you, because its result blocks are normally already present. If that turn comes back suspended, for example as a [`pause_turn` response](https://platform.claude.com/docs/en/agents-and-tools/tool-use/server-tools#the-server-side-loop-and-pause-turn), re-send it as-is instead.
10141014 
10151015## ZDR and allowed\_callers
10161016 
Feedback