HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
9,144 of the ledger's changes in api. Show every change
ReadSourcePageWhatLines
22 Oct 2026
168 pages
+635 −639 lines
api
test-and-evaluate/strengthen-guardrails/increase-consistency
±changed
+1−1
apichanged
test-and-evaluate/strengthen-guardrails/increase-consistency
Break down complex tasks into smaller, consistent subtasks. Each subtask gets Claude's full attention, reducing inconsistency errors across scaled workflows.
Break down complex tasks into smaller, consistent subtasks. Each prompt then covers a single subtask, reducing inconsistency errors across scaled workflows.
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+1−1
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
```json
```text
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
test-and-evaluate/develop-tests
±changed
+11−11
apichanged
test-and-evaluate/develop-tests
| | Criteria
| ---- | -------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Bad | The model should classify sentiments well
| Good | On a held-out test set of 10,000 diverse Twitter posts, the sentiment analysis model should achieve:<br />- an F1 score of at least 0.85<br />- 99.5% of outputs are non-
| | Criteria
+11 −11 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/overview
±changed
+1−1
apichanged
release-notes/system-prompts/overview
description: See updates to the core system prompts on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](https://anthropic
description: See updates to the core system prompts on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app](https://anthrop
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-5-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-5-5
description: See updates to the core system prompt for Claude Sonnet 5.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android a
description: See updates to the core system prompt for Claude Sonnet 5.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-5
description: See updates to the core system prompt for Claude Sonnet 5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Sonnet 5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-4-6
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-4-6
description: See updates to the core system prompt for Claude Sonnet 4.6 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android a
description: See updates to the core system prompt for Claude Sonnet 4.6 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-4-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-4-5
description: See updates to the core system prompt for Claude Sonnet 4.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android a
description: See updates to the core system prompt for Claude Sonnet 4.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-4
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-4
description: See updates to the core system prompt for Claude Sonnet 4 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Sonnet 4 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-3-7
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-3-7
description: See updates to the core system prompt for Claude Sonnet 3.7 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android a
description: See updates to the core system prompt for Claude Sonnet 3.7 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-sonnet-3-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-sonnet-3-5
description: See updates to the core system prompt for Claude Sonnet 3.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android a
description: See updates to the core system prompt for Claude Sonnet 3.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-5-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-5-5
description: See updates to the core system prompt for Claude Opus 5.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 5.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-5
description: See updates to the core system prompt for Claude Opus 5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](
description: See updates to the core system prompt for Claude Opus 5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4-8
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4-8
description: See updates to the core system prompt for Claude Opus 4.8 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 4.8 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4-7
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4-7
description: See updates to the core system prompt for Claude Opus 4.7 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 4.7 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4-6
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4-6
description: See updates to the core system prompt for Claude Opus 4.6 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 4.6 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4-5
description: See updates to the core system prompt for Claude Opus 4.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 4.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4-1
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4-1
description: See updates to the core system prompt for Claude Opus 4.1 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app
description: See updates to the core system prompt for Claude Opus 4.1 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android a
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-4
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-4
description: See updates to the core system prompt for Claude Opus 4 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](
description: See updates to the core system prompt for Claude Opus 4 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-opus-3
±changed
+1−1
apichanged
release-notes/system-prompts/claude-opus-3
description: See updates to the core system prompt for Claude Opus 3 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app](
description: See updates to the core system prompt for Claude Opus 3 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android app
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-haiku-5-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-haiku-5-5
description: See updates to the core system prompt for Claude Haiku 5.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android ap
description: See updates to the core system prompt for Claude Haiku 5.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-haiku-4-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-haiku-4-5
description: See updates to the core system prompt for Claude Haiku 4.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android ap
description: See updates to the core system prompt for Claude Haiku 4.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-haiku-3-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-haiku-3-5
description: See updates to the core system prompt for Claude Haiku 3.5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android ap
description: See updates to the core system prompt for Claude Haiku 3.5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-haiku-3
±changed
+1−1
apichanged
release-notes/system-prompts/claude-haiku-3
description: See updates to the core system prompt for Claude Haiku 3 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app]
description: See updates to the core system prompt for Claude Haiku 3 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android ap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-fable-5-1
±changed
+1−1
apichanged
release-notes/system-prompts/claude-fable-5-1
description: See updates to the core system prompt for Claude Fable 5.1 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android ap
description: See updates to the core system prompt for Claude Fable 5.1 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
release-notes/system-prompts/claude-fable-5
±changed
+1−1
apichanged
release-notes/system-prompts/claude-fable-5
description: See updates to the core system prompt for Claude Fable 5 on [claude.ai](https://claude.ai) and the [Claude iOS app](https://anthropic.com/ios) and [Claude Android app]
description: See updates to the core system prompt for Claude Fable 5 on [claude.ai](https://claude.ai), the [Claude iOS app](https://anthropic.com/ios), and the [Claude Android ap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/overview
±changed
+1−1
apichanged
models/overview
* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide th
* **Engaging responses:** Claude models are ideal for applications that require rich, human-like interactions. If you prefer more concise responses, adjust your prompts to guide th
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+2−2
apichanged
models/opus-5-5/whats-new-opus-5-5
* **Text between tool calls comes back in thinking blocks.** The short notes the model writes between tool calls arrive as [progress-update `thinking` blocks](https://platform.clau
* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its intern
* **Text between tool calls comes back in thinking blocks.** The short notes the model writes between tool calls arrive as [progress-update `thinking` blocks](https://platform.clau
* **More safeguard categories.** The model runs a biology safety classifier in addition to the cybersecurity one. As on Claude Opus 5, requests that push it to reproduce its intern
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/opus-5-5/migration-guide
±changed
+3−3
apichanged
models/opus-5-5/migration-guide
Each change is explained in [What's new in Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#breaking-changes); this section gives the code ch
Each change is explained under [Breaking changes](https://platform.claude.com/docs/en/models/opus-5-5/whats-new-opus-5-5#breaking-changes) in What's new in Claude Opus 5.5; this se
Update your `max_tokens` parameters to give additional headroom, including compaction triggers, and re-test any code path that estimates tokens client-side or assumes a fixed to
Update your `max_tokens` parameters to give additional headroom, including compaction triggers, and re-test any code path that estimates tokens client-side or assumes a fixed to
2. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics might lead to refusals. For legitimate security work
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+10−10
apichanged
models/fable-5-1/whats-new-fable-5-1
If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-to
If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-to
To keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/b
To keep thinking valid across a long session, treat the conversation as append-only. Add instructions with a [mid-conversation system message](https://platform.claude.com/docs/en/b
A [mid-conversation system message](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) can be scoped to one turn. Set `clear_at: "next_user_mes
+10 −10 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/fable-5-1/overview
±changed
+1−1
apichanged
models/fable-5-1/overview
If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-to
If you already call Claude Fable 5, four changes are breaking: [forced tool use returns an error](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1#forced-to
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
models/fable-5-1/migration-guide
±changed
+1−1
apichanged
models/fable-5-1/migration-guide
Migration is mostly drop-in. The API surface, limits, per-token pricing, tokenizer, always-on adaptive thinking, refusal handling, and `stop_details` categories all match Claude Fa
Migration is mostly drop-in. The API surface, limits, per-token pricing, tokenizer, always-on adaptive thinking, refusal handling, and `stop_details` categories all match Claude Fa
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/workflow-runs
±changed
+3−3
apichanged
managed-agents/workflow-runs
```json
```text
```json
```text wrap
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/webhooks
±changed
+1−1
apichanged
managed-agents/webhooks
* **Ordering is not guaranteed.** Events aren't delivered in the order they occurred: `session.status_idled` might arrive before `session.outcome_evaluation_ended` even if the outc
* **Ordering:** Events aren't guaranteed to be delivered in the order they occurred: `session.status_idled` might arrive before `session.outcome_evaluation_ended` even if the outco
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/vaults
±changed
+4−4
apichanged
managed-agents/vaults
```json
```text wrap
`injection_location` behaves differently on create and on update:
`injection_location` (java, php: `injectionLocation`; csharp, go: `InjectionLocation`) behaves differently on create and on update:
The substitution happens at egress, not inside the sandbox. Anything that processes the credential locally sees the opaque placeholder, not the real value: clients that validat
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/tools-web-restrictions
±changed
+4−4
apichanged
managed-agents/tools-web-restrictions
* Its own `allowed_domains` and `blocked_domains`
* Its own `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) and `blocked_domains` (java, php: `blockedDomains`; csharp, go: `BlockedDomains`)
* A listed agent that sets `blocked_domains` keeps the `allowed_domains` of the session's agent and blocks those hosts within it.
* A listed agent that sets its own `allowed_domains` can reach only the hosts that both its list and the list of the session's agent cover.
* A listed agent that sets `blocked_domains` (java, php: `blockedDomains`; csharp, go: `BlockedDomains`) keeps the `allowed_domains` (java, php: `allowedDomains`; csharp, go: `Allo
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/tools
±changed
+1−1
apichanged
managed-agents/tools
The agent calls its custom tools during a session. To receive the calls and return results, see [Session event stream](https://platform.claude.com/docs/en/managed-agents/events-and
The agent calls its custom tools during a session. To receive the calls and return results, see [Answer tool calls that pause the session](https://platform.claude.com/docs/en/manag
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/skills
±changed
+1−1
apichanged
managed-agents/skills
Skills can also live in your code base. When a session mounts a repository through the [`github_repository` resource](https://platform.claude.com/docs/en/managed-agents/github), th
Skills can also live in your code base. When a session mounts a repository through the [`github_repository` resource](https://platform.claude.com/docs/en/managed-agents/github), th
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/sessions
±changed
+3−3
apichanged
managed-agents/sessions
* `model` is never clearable. A session always needs a model, so `model: null` returns a 400 `agent_model_required` error.
* Clearing `tools` returns a 400 error when the session's effective `skills` (csharp, go: `Skills`) is non-empty, because skills require the `read` tool. Otherwise, `tools: null`
* `model` (csharp, go: `Model`) is never clearable. A session always needs a model, so setting `model` (csharp, go: `Model`) to `null` returns a 400 `agent_model_required` error.
* Clearing `tools` (csharp, go: `Tools`) returns a 400 error when the session's effective `skills` (csharp, go: `Skills`) is non-empty, because skills require the `read` tool. Ot
To cap what a session can spend, pass the optional `budget` (csharp, go: `Budget`) object when you create it. A budget is a hard ceiling on the session's list cost: the platform pr
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/session-threads
±changed
+1−1
apichanged
managed-agents/session-threads
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/session-operations
±changed
+1−1
apichanged
managed-agents/session-operations
Delete a session to permanently remove its record, events, and associated sandbox. A `running` session cannot be deleted; to delete one, send a [`user.interrupt` event](https://pla
Deleting a session is permanent. It deletes the session's record, events, and associated sandbox. A `running` session cannot be deleted; to delete one, send a [`user.interrupt` eve
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/session-observability
±changed
+2−2
apichanged
managed-agents/session-observability
```json
```text wrap
Each [session thread](https://platform.claude.com/docs/en/managed-agents/session-threads)'s own `usage` carries `list_cost` and `active_seconds` too. Per-thread figures are rounded
Each [session thread](https://platform.claude.com/docs/en/managed-agents/session-threads)'s own `usage` (csharp, go: `Usage`) carries `list_cost` (java, php: `listCost`; csharp, go
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/self-hosted-sandboxes-workers
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-workers
In the [Console](https://platform.claude.com/settings/workspaces/default/webhooks), define a webhook endpoint that listens for `session.status_run_started` events. See [Webhook
In the [Claude Console](https://platform.claude.com/settings/workspaces/default/webhooks), define a webhook endpoint that listens for `session.status_run_started` events. See [
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/secure-deployment
±changed
+4−4
apichanged
managed-agents/secure-deployment
See [Cloud environment setup](https://platform.claude.com/docs/en/managed-agents/environments#networking) for every networking setting.
See [Networking in Cloud environment setup](https://platform.claude.com/docs/en/managed-agents/environments#networking) for every networking setting.
| Fetcher | Web pages and search results | `web_fetch` and `web_search` only, each with `allowed_domains` (java, php: `allowedDo
| Fetcher | Webpages and search results | `web_fetch` and `web_search` only, each with `allowed_domains` (java, php: `allowedDo
| Archive or delete a session | Archiving keeps the history and blocks new events. Deletin
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/scheduled-deployments
±changed
+2−2
apichanged
managed-agents/scheduled-deployments
```json
```text wrap
```json
```text
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/quickstart
±changed
+1−1
apichanged
managed-agents/quickstart
* A [Claude Console account](https://platform.claude.com)
* A [Claude Console account](https://platform.claude.com/)
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/permission-policies
±changed
+4−4
apichanged
managed-agents/permission-policies
```json
```text wrap
```json
```text wrap
In the following examples, the tool-use event IDs come from the `stop_reason.event_ids` array of the `session.status_idle` event. Learn more about receiving events in the [Session
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/multiagent-orchestration
±changed
+6−6
apichanged
managed-agents/multiagent-orchestration
When [defining your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup), set `multiagent.type` to `"multiagent_20261001"` and enable `workflows`. Dynamic workflo
When [defining your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup), set `multiagent.type` to `"multiagent_20261001"` and enable `workflows` (csharp, go: `Wo
* Every object you send needs its `type`, and an enabled `advisor` needs its `model`.
* **Turning it off:** Set `workflows` to `{"type": "disabled"}`. It stays off until an update turns it on again. Sending `null` turns it on, because its default is enabled. The sam
+6 −6 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/memory
±changed
+3−3
apichanged
managed-agents/memory
* **Shared reference material:** one read-only store attached to many sessions (standards, conventions, domain knowledge), kept separate from each session's own read-write store.
* **Mapping to your product's structure:** one store for each end user, team, or project, while sharing a single agent configuration.
* **Different lifecycles:** a store that outlives any single session, or one you want to archive on its own schedule.
* **Shared reference material:** one read-only store attached to many sessions (standards, conventions, domain knowledge), kept separate from each session's own read-write store
* **Mapping to your product's structure:** one store for each end user, team, or project, while sharing a single agent configuration
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/files
±changed
+1−1
apichanged
managed-agents/files
Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Files the agent writes to `/mnt/session/output
Use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to list files scoped to a session and download them. Files the agent writes to `/mnt/session/output
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/event-deltas
±changed
+3−3
apichanged
managed-agents/event-deltas
```json
```text wrap
```json
```text wrap
Every SDK that supports event deltas includes an [accumulator helper](https://platform.claude.com/docs/en/managed-agents/event-deltas#sdk-accumulator-helpers) that handles the `ind
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/dreams
±changed
+1−1
apichanged
managed-agents/dreams
```json
```text
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/define-outcomes
±changed
+6−6
apichanged
managed-agents/define-outcomes
```json
```text wrap
Heartbeat emitted while the grader runs. The grader's internal reasoning is opaque: you see that it's working, not what it's thinking.
```json
+6 −6 lines
Recorded here 22 Oct 2026 02:07 UTC
api
managed-agents/agent-setup
±changed
+13−13
apichanged
managed-agents/agent-setup
| Field | Description
| ------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------
| `name` (csharp, go: `Name`) | Required. A human-readable name for the agent.
| `model` (csharp, go: `Model`) | Required. The Claude [model](https://platform.claude.com/docs/en/models/overview) that powers th
| `system` (csharp, go: `System`; ruby: `system_`) | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claud
+13 −13 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/workspaces
±changed
+8−8
apichanged
manage-claude/workspaces
* **Workspace identifiers** use the `wrkspc_` prefix (for example, `wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ`)
* **Maximum 100 workspaces** for each organization by default (archived workspaces don't count); contact your account team if you need more
* **Default Workspace** has a `wrkspc_` ID like any other workspace (returned in the [`anthropic-workspace-id` response header](https://platform.claude.com/docs/en/manage-claude/wo
* **API keys** can be scoped to a single workspace. In this case, they can only access resources within that workspace. Other API keys aren't scoped to a workspace. With one of the
* **Workspace identifiers** use the `wrkspc_` prefix (for example, `wrkspc_01JwQvzr7rXLA5AGx3HKfFUJ`).
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/workload-identity-federation
±changed
+1−1
apichanged
manage-claude/workload-identity-federation
By default, identity tokens that carry a `jti` claim are single-use: each exchange must present a JWT that has not been exchanged before, and re-presenting one fails with the reaso
By default, identity tokens that carry a `jti` claim are single-use: each exchange must present a JWT that has not been exchanged before, and re-presenting one fails with the reaso
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/wif-providers/spiffe
±changed
+1−1
apichanged
manage-claude/wif-providers/spiffe
* **One issuer for each trust domain:** Each SPIRE trust domain has its own signing keys and OIDC Discovery Provider. Register each as a separate federation issuer and bind rules t
* **Register one issuer for each trust domain:** Each SPIRE trust domain has its own signing keys and OIDC Discovery Provider. Register each as a separate federation issuer and bin
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/wif-providers/github-actions
±changed
+1−1
apichanged
manage-claude/wif-providers/github-actions
A successful exchange returns an `access_token` beginning with `sk-ant-oat01-` and an `expires_in` value in seconds. A denied exchange returns an opaque `401` `authentication_error
A successful exchange returns an `access_token` beginning with `sk-ant-oat01-` and an `expires_in` value in seconds. A denied exchange returns an opaque `401` `authentication_error
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/wif-providers/gcp
±changed
+1−1
apichanged
manage-claude/wif-providers/gcp
**Federation rule:** Match on both the `sub` and `email` claims. `email` is the readable service-account address; `sub` is the service account's numeric unique ID, which Google nev
**Federation rule:** Match on both the `sub` and `email` claims. `email` is the readable service-account address; `sub` is the service account's numeric unique ID, which Google nev
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/wif-providers/azure
±changed
+4−4
apichanged
manage-claude/wif-providers/azure
The `azure-workload-identity` webhook reads the `azure.workload.identity/client-id` annotation to inject `AZURE_CLIENT_ID` into the pod, which the samples in [Acquire and use t
The `azure-workload-identity` webhook reads the `azure.workload.identity/client-id` annotation to inject `AZURE_CLIENT_ID` into the pod, which the samples in [Acquire and use t
The token your Anthropic federation rule sees is not the projected file; it is the Entra-issued token returned by the `client_credentials` exchange. From inside a labeled pod,
The token your Anthropic federation rule sees is not the projected file; it is the Entra-issued token returned by the `client_credentials` exchange. From inside a labeled pod,
From inside a labeled pod, run the cURL exchange shown in [Acquire and use the token](https://platform.claude.com/docs/en/manage-claude/wif-providers/azure#acquire-and-use-the-toke
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/wif-admin-api
±changed
+2−2
apichanged
manage-claude/wif-admin-api
```json
```text wrap
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/user-profiles-verification-portal
±changed
+1−1
apichanged
manage-claude/user-profiles-verification-portal
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/user-profiles
±changed
+2−2
apichanged
manage-claude/user-profiles
```json
```text wrap
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/user-management
±changed
+12−12
apichanged
manage-claude/user-management
```json
```text wrap
```json
```text wrap
```json
+12 −12 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/usage-cost-api
±changed
+8−8
apichanged
manage-claude/usage-cost-api
* **Time buckets:** Aggregate usage data in fixed intervals (`1m`, `1h`, or `1d`)
* **Token tracking:** Measure uncached input, cached input, cache creation, and output tokens
* **Filtering & grouping:** Filter by API key, workspace, model, service tier, context window, [data residency](https://platform.claude.com/docs/en/manage-claude/data-residency), o
* **Server tool usage:** Track usage of server-side tools such as web search
* **Time buckets:** Aggregate usage data in fixed intervals (`1m`, `1h`, or `1d`).
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/spend-limits-api
±changed
+2−2
apichanged
manage-claude/spend-limits-api
```json
```text wrap
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/rate-limits-api
±changed
+1−1
apichanged
manage-claude/rate-limits-api
To retrieve your organization's workspace IDs, use the [List Workspaces](https://platform.claude.com/docs/en/api/organization/workspaces/list) endpoint, or find them on the [Work
To retrieve your organization's workspace IDs, use the [List Workspaces](https://platform.claude.com/docs/en/api/organization/workspaces/list) endpoint, or find them under [Works
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/plugins-api
±changed
+17−17
apichanged
manage-claude/plugins-api
* Your primary owner creates an Admin API key with the `read:plugins` scope, the `write:plugins` scope, or both in [claude.ai > Organization settings > API](https://claude.ai/admin
* Your primary owner creates an Admin API key with the `read:plugins` scope, the `write:plugins` scope, or both in [claude.ai > Organization settings > API](https://claude.ai/admin
```json
```text
`read:plugins` and `write:plugins` keys read and write only the organization they were created in. If your company has several Claude organizations linked under one parent organiza
+17 −17 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/organization-webhooks
±changed
+2−2
apichanged
manage-claude/organization-webhooks
```json
```text wrap
```json
```text wrap
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/data-residency
±changed
+6−6
apichanged
manage-claude/data-residency
* **Workspace geo:** Controls where data is stored at rest and where endpoint processing (such as image transcoding and code execution) occurs. Configured at the workspace level in
* **Workspace geo:** Controls where data is stored at rest and where endpoint processing (such as image transcoding and code execution) occurs. Configured at the workspace level in
```json Output
```text Output wrap
To set workspace geo, create a new workspace in the [Console](https://platform.claude.com):
+6 −6 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-sessions
±changed
+4−4
apichanged
manage-claude/compliance-sessions
```json Response
```text Response wrap
```json Response
```text Response
```json Response
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-org-data
±changed
+8−8
apichanged
manage-claude/compliance-org-data
```json Response
```text Response wrap
```json Response
```text Response wrap
```json Response
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-faq
±changed
+1−1
apichanged
manage-claude/compliance-faq
```json Response
```text Response
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-errors
±changed
+3−3
apichanged
manage-claude/compliance-errors
```json
```text
```http
```text wrap
```json
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-content-data
±changed
+5−5
apichanged
manage-claude/compliance-content-data
```json Response
```text Response
```json Response
```text Response
```json Response
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-api-access
±changed
+1−1
apichanged
manage-claude/compliance-api-access
```json
```text
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-api
±changed
+1−1
apichanged
manage-claude/compliance-api
```json Response
```text Response wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/compliance-activity-feed
±changed
+1−1
apichanged
manage-claude/compliance-activity-feed
```json Response
```text Response wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/claude-code-analytics-api
±changed
+1−1
apichanged
manage-claude/claude-code-analytics-api
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/authentication
±changed
+4−4
apichanged
manage-claude/authentication
Store API keys in a secrets manager, rotate them periodically, and disable or delete any key you suspect has leaked. On the [API keys page](https://platform.claude.com/settings/key
Store API keys in a secrets manager, rotate them periodically, and disable or delete any key you suspect has leaked. On the [API keys](https://platform.claude.com/settings/keys) pa
```json JSON
```text JSON
When you create an API key from the [API keys page](https://platform.claude.com/settings/keys) in the Claude Console, you choose an expiration: a preset (3 hours, 1 day, 7 days, or
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/api-and-data-retention
±changed
+5−5
apichanged
manage-claude/api-and-data-retention
```json
```text
```json
```text
| [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | `/v1/skills`<br />`/v1/messages` with `skills`
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/admin-api
±changed
+1−1
apichanged
manage-claude/admin-api
```json
```text wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/access-transparency-log
±changed
+5−5
apichanged
manage-claude/access-transparency-log
```json
```text
[`axt-verify`](https://platform.claude.com/docs/en/manage-claude/access-transparency-log#verify-with-axt-verify) carries the current key in each release and never reads a key from
`axt-verify` carries the current key in each release and never reads a key from the API (see [Verify with axt-verify](https://platform.claude.com/docs/en/manage-claude/access-trans
```json
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
manage-claude/access-transparency
±changed
+4−4
apichanged
manage-claude/access-transparency
```json
```text wrap
```json
```text wrap
<Accordion title="We are a platform that serves Claude to our own end users. Can we enable Access Transparency?">
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
get-started
±changed
+3−3
apichanged
get-started
* A [Claude Console account](https://platform.claude.com)
* A [Claude Console account](https://platform.claude.com/)
```json Output
```text Output
```json Output
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
cli-sdks-libraries/sdks/ruby
±changed
+1−1
apichanged
cli-sdks-libraries/sdks/ruby
The SDK provides helper mechanisms to define structured data classes for tools and let Claude automatically run them. For detailed documentation on tool use patterns including the
The SDK provides helper mechanisms to define structured data classes for tools and let Claude automatically run them. For detailed documentation on tool use patterns including the
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
cli-sdks-libraries/sdks/go
±changed
+2−2
apichanged
cli-sdks-libraries/sdks/go
This library requires Go 1.24+.
This library requires Go 1.25+.
To make requests using undocumented parameters, you can use either the `option.WithQuerySet()` or the `option.WithJSONSet()` functions.
To make requests using undocumented parameters, you can use either the `option.WithQuerySet()` or the `option.WithJSONSet()` function.
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
cli-sdks-libraries/libraries/openai-sdk
±changed
+21−21
apichanged
cli-sdks-libraries/libraries/openai-sdk
description: Anthropic provides a compatibility layer that lets you use the OpenAI SDK to test the Claude API. With a few code changes, you can quickly evaluate Anthropic model cap
description: Anthropic provides a compatibility layer that lets you use the OpenAI SDK to test the Claude API. With a few code changes, you can evaluate Anthropic model capabilitie
2. Change the following
* Update your base URL to point to the Claude API
+21 −21 lines
Recorded here 22 Oct 2026 02:07 UTC
api
cli-sdks-libraries/cli/using
±changed
+2−2
apichanged
cli-sdks-libraries/cli/using
```yaml Output
```text Output wrap
```jsonl Output
```text Output
+2 −2 lines
Recorded here 22 Oct 2026 02:07 UTC
api
cli-sdks-libraries/cli/scripting
±changed
+1−1
apichanged
cli-sdks-libraries/cli/scripting
```json Output
```text Output wrap
+1 −1 lines
Recorded here 22 Oct 2026 02:07 UTC
api
claude_api_primer
±changed
+8−8
apichanged
claude_api_primer
```json Output
```text Output wrap
**Consider using `input_examples` for complex tools.** For tools with nested objects, optional parameters, or format-sensitive inputs, you can provide concrete examples using the `
**Consider using `input_examples` for complex tools.** For tools with nested objects, optional parameters, or format-sensitive inputs, you can provide concrete examples using the `
```json
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/working-with-messages
±changed
+4−4
apichanged
build-with-claude/working-with-messages
```json Output
```text Output wrap
```json Output
```text Output wrap
```json Output
+4 −4 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/vision-coordinates
±changed
+5−5
apichanged
build-with-claude/vision-coordinates
1. **Edge limit:** neither side exceeds the maximum edge length (1568 px on the standard tier, 2576 px on the high-resolution tier).
2. **Visual token limit:** the image's token cost `⌈width / 28⌉ × ⌈height / 28⌉` does not exceed the model's visual token budget (1568 tokens on the standard tier, 4784 on the high
1. **Edge limit:** neither side exceeds the maximum edge length (1,568 px on the standard tier, 2,576 px on the high-resolution tier).
2. **Visual token limit:** the image's token cost `⌈width / 28⌉ × ⌈height / 28⌉` does not exceed the model's visual token budget (1,568 tokens on the standard tier, 4,784 on the hi
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. For example, an A4 page sca
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/vision
±changed
+8−8
apichanged
build-with-claude/vision
| High-resolution | Claude 4.7 and later models | 2576 px | 4784 |
| Standard | All other models | 1568 px | 1568 |
| High-resolution | Claude 4.7 and later models | 2,576 px | 4,784 |
| Standard | All other models | 1,568 px | 1,568 |
| 1000x1000 px (1 megapixel) | Not resized | 1296 | Not resized | 1296 |
+8 −8 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/token-counting
±changed
+5−5
apichanged
build-with-claude/token-counting
```json Output
```text Output wrap
```json Output
```text Output wrap
```json Output
+5 −5 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+3−3
apichanged
build-with-claude/thinking-tool-workflows
You should see `thinking` and `tool_use` blocks in the response content on a run that includes thinking (on simpler requests, adaptive mode may skip the thinking block). A note
You should see `thinking` and `tool_use` blocks in the response content on a run that includes thinking (on simpler requests, adaptive mode might skip the thinking block). A no
```json Output
```text Output
```json Output
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/thinking-steering-and-cost
±changed
+7−7
apichanged
build-with-claude/thinking-steering-and-cost
Thinking is optional for the model. On each request, Claude evaluates the complexity of the input and determines whether deeper reasoning would improve the answer. A simple factual
This determination happens per request. The same conversation can contain turns with and without thinking, and a turn where Claude skips thinking contains no thinking block. Don't
Thinking is optional for the model. On each request, Claude evaluates the complexity of the input and determines whether deeper reasoning would improve the answer. A simple factual
+7 −7 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/thinking
±changed
+10−10
apichanged
build-with-claude/thinking
```json
```text
```json Output
```text Output wrap
```sse Output
+10 −10 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/task-budgets
±changed
+3−3
apichanged
build-with-claude/task-budgets
```json
```text
**A budget that is too small for the task can cause refusal-like behavior.** When Claude sees a budget that is clearly insufficient for the work being asked (for example, a 20,00
**A budget that is too small for the task can cause refusal-like behavior.** When Claude receives a budget that is clearly insufficient for the work being asked (for example, a 2
<Card title="Compaction" icon="arrows-clockwise" href="https://platform.claude.com/docs/en/build-with-claude/compaction">
+3 −3 lines
Recorded here 22 Oct 2026 02:07 UTC
api
build-with-claude/structured-outputs
±changed
+14−20
apichanged
build-with-claude/structured-outputs
```json Output
```text Output wrap
```json Output
```text Output wrap
```json Output
+14 −20 lines
Recorded here 22 Oct 2026 02:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.