578 pages for stop.

event-deltas Claude Developer Platform · in the page managed-agents/event-deltas …only by `event_delta` events. There are no per-content-block start or stop events and no stop event for the previewed event itself. The delta type is `content_delta`, not `content_block_delta`. Accumu… events-and-streaming Claude Developer Platform · in the page managed-agents/events-and-streaming …session goes idle A `session.status_idle` event means the agent has stopped and is waiting for input. Its `stop_reason.type` says why: | `stop_reason.type` | Why the session stopped… migration Claude Developer Platform · in the page managed-agents/migration …the conversation history, most of that code goes away. ### What you stop managing | Before | After… multiagent-orchestration Claude Developer Platform · in the page managed-agents/multiagent-orchestration …read_message_received` (the advice) 4. `session.thread_status_idle` (`stop_reason: end_turn`) 5. `session.thread_status_terminated` No `agent.tool_use` events are emitted for a consultation, and no `… permission-policies Claude Developer Platform · in the page managed-agents/permission-policies …vent. 2. The session pauses with a `session.status_idle` event whose `stop_reason.type` is `requires_action`. The blocking event IDs are in the `stop_reason.event_ids` array. The session waits indefin… reference Claude Developer Platform · in the page managed-agents/reference …| | `user.interrupt` | Stop the agent while it runs. It ends no [workflow run](https://platform.claude.com/docs/en/managed-agents/workflow-runs#interrupt… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …ava: `.budget(Optional.empty())`; csharp: `Budget = null`; php: `requestOptions: ['extraBodyParams' => ['budget' => null]]`; cli: `--budget null`) and set again later. The following example sets a bu… secure-deployment Claude Developer Platform · in the page managed-agents/secure-deployment …| | [Set limits and a way to stop](https://platform.claude.com/docs/en/managed-agents/secure-deployment#set-limits-and-a-way-to-stop)… secure-deployment-monitoring Claude Developer Platform · in the page managed-agents/secure-deployment-monitoring …on.status_idle`, and the webhook is named `session.status_idled`. If `stop_reason.type` is `requires_action`, the session is waiting on you, and `stop_reason.event_ids` lists the events it is waiting… secure-deployment-risks Claude Developer Platform · in the page managed-agents/secure-deployment-risks …ce each other. For example, limiting the environment's hosts does not stop the agent from using a credential on a host you allowed. spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …tool call, posts its error result, and releases the work item before stopping. **Sandbox per session** If you need stronger isolation (a fresh filesystem, resource limits, or per-se… self-hosted-sandboxes-custom-tools Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-custom-tools …environmentID := os.Getenv("ANTHROPIC_ENVIRONMENT_ID") ctx, stop := signal.NotifyContext(context.Background(), os.Interrupt, syscall.SIGTERM) defer stop() getOrderStatus := to… self-hosted-sandboxes-memory Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-memory …missing or altered. <Warning> A worker that is killed rather than stopped runs no teardown, so unsynced edits are lost and the store directories stay behind. See [Stop workers gracefully](https://… self-hosted-sandboxes-operations Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-operations …gents/self-hosted-sandboxes-operations description: Read queue depth, stop sessions and workers without losing work, and fix common self-hosted sandbox failures. featureMetadata: topic: title: M… self-hosted-sandboxes-reference Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-reference …| How long to wait after the session goes idle with an `end_turn` [stop reason](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons) before shutting down. Defaults to `60s`.… self-hosted-sandboxes-security Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-security …**Isolate tools inside your sandbox.** Anthropic's security boundary stops at the sandbox. How you isolate individual tool executions from each other inside that boundary is entirely your responsibil… self-hosted-sandboxes-workers Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-workers …Cancelling the task, rather than killing the process, lets the worker stop its # in-flight work item and upload changed memory files before it exits. loop = asyncio.get_running_loo… session-observability Claude Developer Platform · in the page managed-agents/session-observability …* The session emits one immediately before it goes idle, whatever the stop reason. * The session emits one when a thread pauses at a [session budget](https://platform.claude.com/docs/en/managed-agents… session-operations Claude Developer Platform · in the page managed-agents/session-operations …interrupt the session. Send a `user.message` that [asks the agent to stop its runs](https://platform.claude.com/docs/en/managed-agents/workflow-runs#interrupt-a-session-with-runs-open), or wait until… session-threads Claude Developer Platform · in the page managed-agents/session-threads …nThreadId`; php: `sessionThreadID`; csharp, go: `SessionThreadID`) to stop a specific thread. Omitting `session_thread_id` (java: `sessionThreadId`; php: `sessionThreadID`; csharp, go: `SessionThreadI… sessions Claude Developer Platform · in the page managed-agents/sessions …yet, and `user.interrupt` isn't accepted because there is no turn to stop. Unlike `initial_events` (java, php: `initialEvents`; csharp, go: `InitialEvents`) on a scheduled deployment, a session's `in… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …/platform.claude.com/docs/en/managed-agents/events-and-streaming). To stop a run, ask the agent to stop it (see [Interrupt a session with runs open](https://platform.claude.com/docs/en/managed-agents/… Or, for Claude Mythos 5.1, which offers the same capabilities to verified organizations: Claude Developer Platform · in the page models/fable-5-1/migration-guide …icing, tokenizer, always-on adaptive thinking, refusal handling, and `stop_details` categories all match Claude Fable 5. What changes: forced tool choice returns a 400 error; only Claude Fable 5.1 and… whats-new-fable-5-1 Claude Developer Platform · in the page models/fable-5-1/whats-new-fable-5-1 …d its text carries system-prompt authority for the current turn, then stops rendering once a later `user` message exists. The message stays in `messages` and you keep sending it back verbatim, so noth… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …. ## Migration checklist by starting model Work down the groups and stop after the one that names your current model. If you are on Claude Haiku 4.5, the first group is the whole list. Each item is… whats-new-haiku-5-5 Claude Developer Platform · in the page models/haiku-5-5/whats-new-haiku-5-5 …se) | New | Handle `stop_reason: "refusal"` in your client. Server-side fallback isn't available.… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …. ## Migration checklist by starting model Work down the groups and stop after the one that names your current model: every item up to that point applies to you. If you are on Claude Opus 5, the fir… whats-new-opus-5-5 Claude Developer Platform · in the page models/opus-5-5/whats-new-opus-5-5 …sals-and-fallback) applies. A declined request returns HTTP 200 with `stop_reason: "refusal"` and a [`stop_details`](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …} ], output_config={"effort": "medium"}, ) print(f"Stop reason: {response.stop_reason}") for block in response.content: if block.type == "text": print(block.text)… whats-new-sonnet-5-5 Claude Developer Platform · in the page models/sonnet-5-5/whats-new-sonnet-5-5 …categories.** The model's safeguards can decline a request in five [`stop_details` categories](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#refusal-response). `"cyber"`… overview Claude Developer Platform · in the page release-notes/overview …'re resuming billing for refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`, the categories where we measure low volumes of f… claude-haiku-4-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-4-5 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-haiku-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-haiku-5-5 …ing, not only at the latest message. When it is heading there, Claude stops writing that part and keeps helping with the rest of the story. Claude does not provide information for creating harmful su… claude-opus-4-7 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-7 …try to elicit another turn and instead respects the user's request to stop. </refusal_handling> <legal_and_financial_advice> When asked for financial or legal advice, for example whether to make a tra… claude-opus-4-8 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-4-8 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-opus-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-opus-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-opus-5-5 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-sonnet-4-6 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-4-6 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-sonnet-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… claude-sonnet-5-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-sonnet-5-5 …aggregate amounts to a weapons design package or attack plan, Claude stops even when each step seemed incremental and even if a prior-session summary shows Claude already helping — past assistance is… handle-streaming-refusals Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/handle-streaming-refusals …ails/handle-streaming-refusals description: Detect and handle refusal stop reasons in streaming responses, and retry refused requests on a fallback model. --- Starting with Claude 4 models, streaming… mitigate-jailbreaks Claude Developer Platform · in the page test-and-evaluate/strengthen-guardrails/mitigate-jailbreaks …t can decline the screening request itself, so treat a response with `stop_reason: "refusal"` as a harmful verdict. <Accordion title="Example: Harmlessness screen for content moderation"> ```te… Use Claude Code with a screen reader Claude Code CLI · in the page accessibility …mpt each time it writes new text. To keep your place while you read, stop your screen reader from following the terminal cursor. In NVDA, press `NVDA+6` to stop the review cursor from following the t… Set up Claude Code for your organization Claude Code CLI · in the page admin-setup …y can only come from plugins or managed settings. Locking skills also stops the [skills your developers enable on claude.ai](/docs/en/skills.md#where-synced-skills-load) from syncing | `strictPluginOn… Escalate hard decisions with the advisor tool Claude Code CLI · in the page advisor …erimental) is on and may use more tokens · /advisor` notification. To stop using the advisor, see [Turn the advisor off](#turn-the-advisor-off). On some plans, Fable as the advisor also needs your on… How the agent loop works Claude Code CLI · in the page agent-sdk/agent-loop …e turns only. For example, `max_turns=2` in the loop above would have stopped before the edit step. You can also use `max_budget_usd` / `maxBudgetUsd` to cap turns based on a spend threshold. Without… Configure your agent Claude Code CLI · in the page agent-sdk/configuration …(Python) pre-approves the listed tools, so calls to them run without stopping for approval. Tools outside the list stay available. When Claude calls an unlisted tool, the permission mode decides whet… Give Claude custom tools Claude Code CLI · in the page agent-sdk/custom-tools …the full evaluation order. ## Handle errors A handler error doesn't stop the agent loop. The SDK's in-process MCP server catches uncaught exceptions and returns them as error results, so how you rep… Intercept and control agent behavior with hooks Claude Code CLI · in the page agent-sdk/hooks …nt events, like a tool being called, a session starting, or execution stopping. With hooks, you can: * **Block dangerous operations** before they execute, like destructive shell commands or unauthori… Hosting the Agent SDK Claude Code CLI · in the page agent-sdk/hosting …Python to bound how many tool-use round trips the agent takes before stopping. | | Memory growth over long sessions | Cap session length or recycle subprocesses periodically. See [Scaling and concurr…