282 pages for trigger.

Apps Claude Developer Platform · in the page api/compliance/apps …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… Sessions Claude Developer Platform · in the page api/compliance/apps/sessions …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… Remote Claude Developer Platform · in the page api/compliance/apps/sessions/remote …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… List remote sessions Claude Developer Platform · in the page api/compliance/apps/sessions/remote/list …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… Messages Claude Developer Platform · in the page api/compliance/apps/sessions/remote/messages …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… Retrieve remote session messages Claude Developer Platform · in the page api/compliance/apps/sessions/remote/messages/list …ession (for example, by mentioning Claude in Slack or via a scheduled trigger). Null for user-owned sessions — where the session's `user` started it — and for agent sessions with no human initiator. F… Messages Claude Developer Platform · in the page api/messages …or "frontier_llm" or 2 more or null` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request cou… Batches Claude Developer Platform · in the page api/messages/batches …rontier_llm" or 2 more or null` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"`… Retrieve Message Batch results Claude Developer Platform · in the page api/messages/batches/results …rontier_llm" or 2 more or null` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"`… Create a Message Claude Developer Platform · in the page api/messages/create …or "frontier_llm" or 2 more or null` The policy category that triggered the refusal. `null` when the refusal doesn't map to a named category. - `"cyber"` The request cou… Before Claude Developer Platform · in the page api/migration-2026-10-21 …context_management: { edits: [{ type: "compact_20260112", trigger: { type: "input_tokens", value: 100_000 } }] } }); ``` To decide yourself when the conversation is comp… rate-limits Claude Developer Platform · in the page api/rate-limits …request per second. Short bursts of requests can exceed the limit and trigger rate limit errors. * The following limits are the standard limits for each tier. If you need higher limits, see [Requestin… sent_count = len(messages sent in the compaction request) Claude Developer Platform · in the page build-with-claude/compaction …hreshold. The API: 1. Detects when input tokens reach your specified trigger threshold. 2. Generates a summary of the current conversation. 3. Creates a `compaction` block containing the summary. 4.… compaction-threshold Claude Developer Platform · in the page build-with-claude/compaction-threshold …hreshold. The API: 1. Detects when input tokens reach your specified trigger threshold. 2. Generates a summary of the current conversation. 3. Creates a `compaction` block containing the summary. 4.… context-editing Claude Developer Platform · in the page build-with-claude/context-editing …{ "type": "clear_tool_uses_20250919", "trigger": { "type": "input_tokens", "value": 30000 }, "keep": {… handling-stop-reasons Claude Developer Platform · in the page build-with-claude/handling-stop-reasons …eate#message.stop_details) object identifies the policy category that triggered it. The categories and the full refusal response shape are covered in [What a refusal looks like](https://platform.claud… Request 2 caches its request content (not the response) Claude Developer Platform · in the page build-with-claude/prompt-caching …system prompt or tool definitions into the prompt cache before a user triggers a real request. This can reduce the cache-miss latency penalty on the first user interaction, lowering time-to-first-toke… claude-prompting-best-practices Claude Developer Platform · in the page build-with-claude/prompt-engineering/claude-prompting-best-practices …king blocks back unchanged, tool-call batching in agent loops, search triggering at low effort, formatting, and writing density.… prompting-claude-fable-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5 …nign cybersecurity work and beneficial life sciences tasks might also trigger these safeguards. To re-route declined requests automatically, configure [server-side or client-side fallback](https://pla… Delivering work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-1 …ask completion, compaction summaries, scope and test coverage, search triggering, safeguard false positives, file edits, long outputs, subagents, and vision. --- For the model’s specifications, prici… Finishing work Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-fable-5-2 …named category. Benign cybersecurity and life sciences work can also trigger the `cyber` and `bio` classifiers. If that blocks your organization’s legitimate work, see Anthropic’s [Cyber Verification… prompting-claude-haiku-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-haiku-5-5 …cybersecurity work isn’t allowed. Benign cybersecurity work can also trigger this category. If the `cyber` classifier blocks your organization’s legitimate security work, you can apply to the [Cyber… prompting-claude-opus-4-8 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-opus-4-8 …is off unless you explicitly set `thinking: {type: "adaptive"}`. The triggering behavior for [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is steerable. If you f… prompting-claude-sonnet-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5 …6, try thinking on with lower effort levels for Claude Sonnet 5. The triggering behavior for adaptive thinking is steerable. If you find the model emitting thinking blocks more often than you’d like,… prompting-claude-sonnet-5-5 Claude Developer Platform · in the page build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5 …e request falls under another usage-policy area. Benign work can also trigger this category. If the `cyber` classifier blocks your organization’s legitimate security work, you can apply to the [Cyber… refusals-and-fallback Claude Developer Platform · in the page build-with-claude/refusals-and-fallback …t explains the decline: * **`category`:** names the policy area that triggered the classifier. * **`explanation`:** a human-readable description. The text is not stable, so display it rather than par… thinking-steering-and-cost Claude Developer Platform · in the page build-with-claude/thinking-steering-and-cost …ing block at all; a multistep math problem or a tricky debugging task triggers deeper reasoning. This determination occurs for each request. The same conversation can contain turns with and without t… thinking-tool-workflows Claude Developer Platform · in the page build-with-claude/thinking-tool-workflows …): rebuilding the message or filtering out `redacted_thinking` blocks triggers a 400 error. The samples use adaptive thinking; on models that support only extended thinking, substitute `thinking: {ty… thinking-troubleshooting Claude Developer Platform · in the page build-with-claude/thinking-troubleshooting …/platform.claude.com/docs/en/build-with-claude/context-editing) never trigger this error. With [on-demand compaction](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand), think… vision-coordinates Claude Developer Platform · in the page build-with-claude/vision-coordinates …uts every coordinate noticeably off target. The token limit can also trigger a resize when neither side exceeds the edge limit. Overlooking this is the most common cause of misaligned coordinates. Fo… working-with-messages Claude Developer Platform · in the page build-with-claude/working-with-messages …include a `stop_details` object identifying the policy category that triggered the refusal, on every model. See [What a refusal looks like](https://platform.claude.com/docs/en/build-with-claude/refus… organization-webhooks Claude Developer Platform · in the page manage-claude/organization-webhooks …le) on user profiles. | Event | Trigger | | ------------------------------------------… user-profiles Claude Developer Platform · in the page manage-claude/user-profiles …r API traffic. Without a profile on the request, one end customer can trigger an enforcement action that applies to your whole organization. You register each end customer once with `POST /v1/user_pr… wif-admin-api Claude Developer Platform · in the page manage-claude/wif-admin-api …po:my-org/my-repo:*` also matches `pull_request` runs, including runs triggered from forks. With that pattern, anyone who can open a pull request against the repository can mint an `org:admin` token.… github-actions Claude Developer Platform · in the page manage-claude/wif-providers/github-actions …your repository. The token’s `sub` claim encodes the repository and trigger context. For a push to a branch it has the form `repo:<owner>/<repo>:ref:refs/heads/<branch>`. Pull-request runs use `repo… workload-identity-federation Claude Developer Platform · in the page manage-claude/workload-identity-federation …on rule, then listens for a successful token exchange for 15 minutes. Trigger an exchange from your workload within that window (see [Authenticate from your workload](https://platform.claude.com/docs/… budgets Claude Developer Platform · in the page managed-agents/budgets …th a 400 error naming this list. Settled results are recorded without triggering a new model request; the session stays paused at its budget. A `user.interrupt` sent while the session is paused at it… mcp-connector Claude Developer Platform · in the page managed-agents/mcp-connector …| You can decide whether to block further interaction on this error, trigger a credential rotation, or let the session continue without the affected server’s tools. The connection is retried on the n… scheduled-deployments Claude Developer Platform · in the page managed-agents/scheduled-deployments …imes that do not exist on a spring-forward day (such as 2 AM) are not triggered. Wall-clock times that occur twice on a fall-back day fire twice. Schedule outside the 1–3 AM local window, or use UTC,… spawn.sh: called once per claimed work item Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes …er by an **always-on worker** that polls continuously, or a **webhook-triggered handler** that wakes on `session.status_run_started` and starts polling. The CLI and SDK both ship pre-built workers. T… self-hosted-sandboxes-workers Claude Developer Platform · in the page managed-agents/self-hosted-sandboxes-workers …ndbox workers claim work and where sessions run: always-on or webhook-triggered, in one process or one sandbox per session." featureMetadata: topic: title: Managed Agents url: https://platfo… vaults Claude Developer Platform · in the page managed-agents/vaults …with those lifecycle changes. | Event | Trigger | | ---------… webhooks Claude Developer Platform · in the page managed-agents/webhooks …_started` webhook events. | Event | Trigger… workflow-runs Claude Developer Platform · in the page managed-agents/workflow-runs …, and listing the session’s events returns them too. Run events don’t trigger [webhooks](https://platform.claude.com/docs/en/managed-agents/webhooks). Status events from the run’s threads arrive on th… migration-guide Claude Developer Platform · in the page models/haiku-5-5/migration-guide …e, the request might or might not get the error. For the changes that trigger the error and what to do instead, see [Who the prefix check affects](https://platform.claude.com/docs/en/build-with-claude… migration-guide Claude Developer Platform · in the page models/opus-5-5/migration-guide …tokens` to account for the updated tokenization, including compaction triggers. * Re-test any client-side token-count estimations. * If your application sends images, re-budget for [high-resolution im… migration-guide Claude Developer Platform · in the page models/sonnet-5-5/migration-guide …e request falls under another usage-policy area. Benign work can also trigger this category. [Server-side fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback#server-… overview Claude Developer Platform · in the page release-notes/overview …de a `session_thread_id` field identifying the multiagent thread that triggered the event. * We’ve released a [Swift package](https://platform.claude.com/docs/en/cli-sdks-libraries/libraries/apple-fou… claude-fable-5 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5 …hat to remove access to, as mentioning these things may inadvertently trigger the user. Claude does not suggest substitution techniques for self-harm that use physical discomfort, pain, or sensory sh… claude-fable-5-1 Claude Developer Platform · in the page release-notes/system-prompts/claude-fable-5-1 …hat to remove access to, as mentioning these things may inadvertently trigger the user. Claude does not suggest substitution techniques for self-harm that use physical discomfort, pain, or sensory sh…