Search the documentation
50 pages for stop.
Titles and paths first, then pages whose text carries it. Each row opens that page as this site last read it. Cut at 50, so a narrower query shows the rest.
Stop Work
Claude Developer Platform · title
api/beta/environments/work/stop
handling-stop-reasons
Claude Developer Platform · title
build-with-claude/handling-stop-reasons
Or, for the model with the same capabilities and no access approval requirement:
Claude Developer Platform · in the page
about-claude/models/migration-guide
…laude Fable 5 runs safety classifiers that can decline requests with `stop_reason: "refusal"`. Claude Mythos 5 does not include these classifiers. See [Refusals and fallback](https://platform.claude.c…
optimizing-for-cost-and-intelligence
Claude Developer Platform · in the page
about-claude/models/optimizing-for-cost-and-intelligence
…cs/en/api/rate-limits#setting-lower-limits-for-workspaces) as the backstop. * **Tradeoffs** exchange cost for intelligence: model choice, effort, output caps and task budgets, and multi-model architec…
claude-api-skill
Claude Developer Platform · in the page
agents-and-tools/agent-skills/claude-api-skill
…4.8 and Claude Opus 4.7 * **Refusal fallback configuration**, adding `stop_reason: "refusal"` handling before reading response content and setting up a [fallback retry path](https://platform.claude.co…
enterprise
Claude Developer Platform · in the page
agents-and-tools/agent-skills/enterprise
…ur evaluation suite to measure recall accuracy as you add Skills, and stop adding when performance degrades. Note that API requests support a maximum of 20 Skills for each request (see [Using Skills…
quickstart
Claude Developer Platform · in the page
agents-and-tools/agent-skills/quickstart
…"code_execution_20260521", "name": "code_execution"}], ) print(f"stop_reason={response.stop_reason}, blocks={len(response.content)}") ``` ```typescript TypeScript // Create a message with…
console
Claude Developer Platform · in the page
agents-and-tools/mcp-tunnels/console
…other MCP server. </Note> ## Archive a tunnel Archiving immediately stops the tunnel from accepting connections and is permanent. In the **MCP tunnels** list, open the row menu for the tunnel and c…
Edit docker-compose.yaml: increment the integer in the setup service's
Claude Developer Platform · in the page
agents-and-tools/mcp-tunnels/deploy-compose
…network_mode: "service:mcp-proxy" restart: unless-stopped user: "65532:65532" read_only: true security_opt: - no-new-privileges:tr…
quickstart
Claude Developer Platform · in the page
agents-and-tools/mcp-tunnels/quickstart
…g.yaml:ro - ./data:/data:ro restart: unless-stopped cloudflared: image: cloudflare/cloudflared@sha256:6b599ca3e974349ead3286d178da61d291961182ec3fe9c50…
security
Claude Developer Platform · in the page
agents-and-tools/mcp-tunnels/security
…TLS keys, or proxy host has been compromised: <Steps> <Step title="Stop the tunnel stack"> <Tabs> <Tab title="Helm"> ```bash helm uninstall mcp-tunnel -n mcp-tunnel…
advisor-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/advisor-tool
…---------------------------- | | `advisor_result` | `text`, `stop_reason` | The advisor model returns plaintext (for example, Claude Opus 4.8). | | `advisor_redacted_result` | `e…
bash-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/bash-tool
…] ) puts response ``` </CodeGroup> Claude responds with `stop_reason: "tool_use"` and a `tool_use` block that contains the command for your application to run: ```json Output { "id": "…
browser-use-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/browser-use-tool
…puts response ``` </CodeGroup> Claude's first response ends with `stop_reason: "tool_use"` and carries one or more member `tool_use` blocks, each naming a member tool in `name` and carrying `"tool…
build-a-tool-using-agent
Claude Developer Platform · in the page
agents-and-tools/tool-use/build-a-tool-using-agent
…determines that a tool call is needed, the response comes back with `stop_reason: "tool_use"` and a `tool_use` content block containing the tool name, a unique `id`, and the structured `input`. Your…
code-execution-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/code-execution-tool
…t the `container` parameter to get a new container. ### `pause_turn` stop reason The response might include a `pause_turn` stop reason, which indicates that the API paused a long-running turn. You m…
computer-use-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/computer-use-tool
…`` </CodeGroup> When Claude acts on the desktop, the response has a `stop_reason` of `tool_use` and contains one or more member `tool_use` blocks, each naming a member tool and carrying `"toolset_nam…
fine-grained-tool-streaming
Claude Developer Platform · in the page
agents-and-tools/tool-use/fine-grained-tool-streaming
…might receive partial or invalid JSON. A response that ends with the [stop reason](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons) `max_tokens` can also cut a parameter of…
handle-tool-calls
Claude Developer Platform · in the page
agents-and-tools/tool-use/handle-tool-calls
…s). ## Handling results from client tools The response will have a `stop_reason` of `tool_use` and one or more `tool_use` content blocks that include: * `id`: A unique identifier for this particula…
how-tool-use-works
Claude Developer Platform · in the page
agents-and-tools/tool-use/how-tool-use-works
…ut back to the model before the response reaches you, unless the loop stops before it finishes, most often because it pauses. The response you receive contains `server_tool_use` blocks showing what r…
memory-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/memory-tool
…, }) if err != nil { log.Fatal(err) } if message.StopReason != anthropic.StopReasonToolUse { for _, block := range message.Content { if block.Type == "text" { fm…
overview
Claude Developer Platform · in the page
agents-and-tools/tool-use/overview
…sh` and `text_editor`) run in your application. Claude responds with `stop_reason: "tool_use"` and one or more `tool_use` blocks. Your code executes the operation and sends back a `tool_result`. **Ser…
parallel-tool-use
Claude Developer Platform · in the page
agents-and-tools/tool-use/parallel-tool-use
…## Execution semantics When Claude calls tools, the response has a `stop_reason` of `tool_use` and can contain several `tool_use` blocks in a single assistant turn. How you run those calls is your d…
Process results programmatically
Claude Developer Platform · in the page
agents-and-tools/tool-use/programmatic-tool-calling
…"] } ] ) puts message ``` </CodeGroup> The response stops with `stop_reason: "tool_use"`, a `container` ID, and a `tool_use` block for `query_database` whose `caller` field identifie…
server-tools
Claude Developer Platform · in the page
agents-and-tools/tool-use/server-tools
…ol_use` block appears without its result, and the response ends with `stop_reason: "tool_use"`. The API runs the tool when you return the client `tool_result` blocks in your next request. ## The serv…
text-editor-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/text-editor-tool
…"id": "msg_01XAbCDeFgHiJkLmNoPQrStU", "model": "claude-opus-5", "stop_reason": "tool_use", "role": "assistant", "content": [ { "type": "text", "text": "I'll help you fix the s…
Log at info level
Claude Developer Platform · in the page
agents-and-tools/tool-use/tool-runner
…= 8192; for await (const message of runner) { if (message.stop_reason === "max_tokens") { const current = runner.params.max_tokens; if (current >= MAX_TOKEN_CEILING) {…
tool-search-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/tool-search-tool
…talog, discovers `get_weather`, and calls it. The response ends with `stop_reason: "tool_use"`. Execute the discovered tool and return a `tool_result` as in [Handle tool calls](https://platform.claude…
troubleshooting-tool-use
Claude Developer Platform · in the page
agents-and-tools/tool-use/troubleshooting-tool-use
…s for the client `tool_use` ids and keep the same `tools` array. See [Stop reasons and fallback](https://platform.claude.com/docs/en/build-with-claude/handling-stop-reasons#tool-use).…
web-fetch-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/web-fetch-tool
…same group of parallel tool calls: the API returns the response with `stop_reason: "tool_use"` before that fetch has run, then runs the fetch when you send back the client `tool_result` blocks. See [M…
web-search-tool
Claude Developer Platform · in the page
agents-and-tools/tool-use/web-search-tool
…"server_tool_use": { "web_search_requests": 1 } }, "stop_reason": "end_turn" } ``` This example shows a direct search. When a search runs through [dynamic filtering](https://platfor…
Federation Rules
Claude Developer Platform · in the page
api/admin/federation_rules
…rchive` Archive a federation rule. Token exchange through this rule stops immediately. Idempotent; re-archiving returns the rule with its original `archived_at`. Archiving clears the rule's workspac…
Archive Federation Rule
Claude Developer Platform · in the page
api/admin/federation_rules/archive
…rchive` Archive a federation rule. Token exchange through this rule stops immediately. Idempotent; re-archiving returns the rule with its original `archived_at`. Archiving clears the rule's workspac…
Beta
Claude Developer Platform · in the page
api/beta
…ax_tokens: number` The maximum number of tokens to generate before stopping. Note that our models may stop _before_ reaching this maximum. This parameter only specifies the absolute maximum numb…
Deployments
Claude Developer Platform · in the page
api/beta/deployments
…anagedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Archive Deployment
Claude Developer Platform · in the page
api/beta/deployments/archive
…agedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Create Deployment
Claude Developer Platform · in the page
api/beta/deployments/create
…anagedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
List Deployments
Claude Developer Platform · in the page
api/beta/deployments/list
…agedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Pause Deployment
Claude Developer Platform · in the page
api/beta/deployments/pause
…agedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Get Deployment
Claude Developer Platform · in the page
api/beta/deployments/retrieve
…agedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Unpause Deployment
Claude Developer Platform · in the page
api/beta/deployments/unpause
…agedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Update Deployment
Claude Developer Platform · in the page
api/beta/deployments/update
…anagedAgentsBudgetLimit or null` A hard spend ceiling. The session stops issuing new model requests once the tracked list cost reaches `max_list_cost`. - `max_list_cost: BetaMonetaryAmount`…
Environments
Claude Developer Platform · in the page
api/beta/environments
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…
Work
Claude Developer Platform · in the page
api/beta/environments/work
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…
Acknowledge Work
Claude Developer Platform · in the page
api/beta/environments/work/ack
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…
Record Heartbeat
Claude Developer Platform · in the page
api/beta/environments/work/heartbeat
…g" or "active" or 2 more` Current state of the work item (active/stopping/stopped) - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `ttl_seconds…
List Work Items
Claude Developer Platform · in the page
api/beta/environments/work/list
…- `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested…
Poll for Work
Claude Developer Platform · in the page
api/beta/environments/work/poll
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…
Get Work Item
Claude Developer Platform · in the page
api/beta/environments/work/retrieve
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…
Update Work Item
Claude Developer Platform · in the page
api/beta/environments/work/update
…item - `"queued"` - `"starting"` - `"active"` - `"stopping"` - `"stopped"` - `stop_requested_at: string or null` RFC 3339 timestamp when stop was requested - `stopp…