Follow Discord
Sweep 22 Oct 2026 · 04:32Z Build v2.1.308 527 read Stable v2.1.308 Latest v2.1.308 Next v2.1.308 Feeds RSS JSON llms.txt llms-full.txt Unofficial
HomeDocsClaude Developer Platform 12 Oct 2026
One change · api

events-and-streaming changedmanaged-agents/events-and-streaming

Recorded here
Lines+7added
Lines−7removed
From line 728 where the diff opens
First seen 14 Aug 2026 this site's first read of the page
Recorded edits29to this page, all time

The whole hunk

from line 728, old and new numbered
/
lines
from line 728
728728 ```
729729</CodeGroup>
730730 
731Every event in the session's history includes a `processed_at` timestamp, set when the event finishes processing. On events you send, `processed_at` is null while the event is still queued behind earlier events. The exceptions are `user.define_outcome`, `user.custom_tool_result`, and `user.tool_result`, which are processed on receipt and echoed back with `processed_at` already populated.
731Every event in the session's history includes a `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) timestamp, set when the event finishes processing. On events you send, `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) is null while the event is still queued behind earlier events. The exceptions are `user.define_outcome`, `user.custom_tool_result`, and `user.tool_result`, which are processed on receipt and echoed back with `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) already populated.
732732 
733733## Respond when the session goes idle
734734 
from line 755
755755 
756756### Return a custom tool result
757757 
758The `agent.custom_tool_use` event contains the tool name and input. Run the tool in your system. Then send a `user.custom_tool_result` event, passing the event ID in the `custom_tool_use_id` parameter along with the result content.
758The `agent.custom_tool_use` event contains the tool name and input. Run the tool in your system. Then send a `user.custom_tool_result` event, passing the event ID in the `custom_tool_use_id` (java: `customToolUseId`; php: `customToolUseID`; csharp, go: `CustomToolUseID`) parameter along with the result content.
759759 
760760You can send the result as soon as the `agent.custom_tool_use` event arrives, without waiting for `session.status_idle`. The session still emits `session.status_idle` with a `requires_action` stop reason for the call, and your client can ignore it. A second result for the same call is accepted and has no effect.
761761 
from line 1021
10211021 
10221022### Confirm a tool call
10231023 
1024Send a `user.tool_confirmation` event, passing the event ID in the `tool_use_id` parameter. Set `result` to `"allow"` or `"deny"`. See [Respond to confirmation requests](https://platform.claude.com/docs/en/managed-agents/permission-policies#respond-to-confirmation-requests) for which calls wait for a confirmation and how to explain a denial.
1024Send a `user.tool_confirmation` event, passing the event ID in the `tool_use_id` (java: `toolUseId`; php: `toolUseID`; csharp, go: `ToolUseID`) parameter. Set `result` (java, php; csharp, go: `Result`) to `"allow"` or `"deny"`. See [Respond to confirmation requests](https://platform.claude.com/docs/en/managed-agents/permission-policies#respond-to-confirmation-requests) for which calls wait for a confirmation and how to explain a denial.
10251025 
10261026The following example approves every pending call:
10271027 
from line 1251
12511251 ```
12521252</CodeGroup>
12531253 
1254The previous example approves each call after the session goes idle. If the agent has [workflow runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs) open, a tool call can wait for your confirmation while the session stays `running`. Don't wait for the idle event: when an `agent.tool_use` or `agent.mcp_tool_use` event arrives whose [`evaluated_permission`](https://platform.claude.com/docs/en/managed-agents/permission-policies#see-how-each-call-was-evaluated) is `ask`, answer it. The sample in [Follow a run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#follow-a-run) answers custom tool calls this way, and its introduction says how to add confirmations.
1254The previous example approves each call after the session goes idle. If the agent has [workflow runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs) open, a tool call can wait for your confirmation while the session stays `running`. Don't wait for the idle event: when an `agent.tool_use` or `agent.mcp_tool_use` event arrives whose [`evaluated_permission` (java, php: `evaluatedPermission`; csharp, go: `EvaluatedPermission`)](https://platform.claude.com/docs/en/managed-agents/permission-policies#see-how-each-call-was-evaluated) is `ask`, answer it. The sample in [Follow a run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#follow-a-run) answers custom tool calls this way, and its introduction says how to add confirmations.
12551255 
12561256## Resume an idle session
12571257 
from line 1615
16151615 
16161616The call returns as soon as the events are queued. The interrupt then takes effect in this order:
16171617 
16181. The agent applies the interrupt. Until then, the interrupt's `processed_at` stays null and the session stays `running`. A model response in progress stops immediately, but the interrupt can take longer to apply while tool calls are running.
16181. The agent applies the interrupt. Until then, the interrupt's `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) stays null and the session stays `running`. A model response in progress stops immediately, but the interrupt can take longer to apply while tool calls are running.
161916192. The `user.interrupt` event appears on the stream, and the interrupted turn ends with a `session.status_idle` event.
162016203. The agent starts its next turn with the `user.message` you sent after the interrupt.
16211621 
from line 1693
16931693 ```
16941694</CodeGroup>
16951695 
1696Pass a `types` filter to return only specific event types:
1696Pass a `types` (java, php; csharp, go: `Types`) filter to return only specific event types:
16971697 
16981698<CodeGroup>
16991699 ```bash cURL
from line 1785
17851785 
17861786On a [supported model](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#supported-models), send a `system.message` event to give the agent privileged system-level context. The context applies to the accompanying turn and all subsequent turns. Use it when the agent needs updated system-level guidance mid-session, for example a different persona, revised constraints, or context fetched at runtime.
17871787 
1788The event's `content` accepts 1–1000 text items. The content is appended to the session's system context as a `role: "system"` turn. It doesn't replace the top-level system prompt, which the `system` field on the agent definition sets.
1788The event's `content` (java, php; csharp, go: `Content`) accepts 1–1000 text items. The content is appended to the session's system context as a `role: "system"` turn. It doesn't replace the top-level system prompt, which the `system` (java, php; csharp, go: `System`; ruby: `system_`) field on the agent definition sets.
17891789 
17901790<CodeGroup>
17911791 ```bash cURL
Feedback