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
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
7 Oct 2026
209 pages
+3198 −2398 lines
api
managed-agents/tools-web-restrictions
±changed
+5−4
apichanged
managed-agents/tools-web-restrictions
These per-tool lists are the way to restrict what the web tools can reach. Two other settings do not affect these tools:
* **Environment networking:** An environment's [`networking`](https://platform.claude.com/docs/en/managed-agents/environments#networking) settings control the sandbox's own outbo
* **Organization settings:** Organization-level web search and web fetch settings in the Claude Console apply to the Messages API. They do not apply to Managed Agents sessions.
`web_search` and `web_fetch` run on Anthropic's servers, not in the sandbox. A cloud environment with `limited` [networking](https://platform.claude.com/docs/en/managed-agents/en
+5 −4 lines
Recorded here 7 Oct 2026 15:07 UTC
api
managed-agents/quickstart
±changed
+1−1
apichanged
managed-agents/quickstart
An environment defines the sandbox where your agent runs. This one uses `limited` [networking](https://platform.claude.com/docs/en/managed-agents/environments#networking) with
An environment defines the sandbox where your agent runs. This one uses `limited` [networking](https://platform.claude.com/docs/en/managed-agents/environments#networking) with
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
managed-agents/environments
±changed
+4−2
apichanged
managed-agents/environments
The `networking` field controls the sandbox's outbound network access. It does not affect the `web_search` or `web_fetch` tools, which run on Anthropic's servers; to restrict the s
The `networking` field controls the sandbox's outbound network access.
With `limited` networking, `allowed_hosts` also applies to the `web_search` and `web_fetch` tools, which run on Anthropic's servers. A `web_fetch` call for a URL on a host that `al
An agent that only uses the `web_search` and `web_fetch` tools does not need `unrestricted` networking if you can list the sites it needs. [Networking](https://platform.claude.com/
+4 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/workload-identity-federation
±changed
+1−1
apichanged
manage-claude/workload-identity-federation
To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see th
To manage these resources programmatically, see [Manage WIF with the Admin API](https://platform.claude.com/docs/en/manage-claude/wif-admin-api) for the curl walkthrough, or see th
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/wif-reference
±changed
+10−10
apichanged
manage-claude/wif-reference
For complete parameter details and response schemas, see the [Service accounts API reference](https://platform.claude.com/docs/en/api/beta/organization/service_accounts), [Federati
For complete parameter details and response schemas, see the [Service accounts API reference](https://platform.claude.com/docs/en/api/organization/service_accounts), [Federation is
| Constraint | Detail
| ----------------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------
| Maximum size | The `assertion` JWT must be at most 16 KiB.
+10 −10 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/user-management
±changed
+8−8
apichanged
manage-claude/user-management
For complete parameter details and response schemas, see [List users](https://platform.claude.com/docs/en/api/beta/organization/users/list) in the API reference.
For complete parameter details and response schemas, see [List users](https://platform.claude.com/docs/en/api/organization/users/list) in the API reference.
For complete parameter details and response schemas, see [Get user](https://platform.claude.com/docs/en/api/beta/organization/users/retrieve) in the API reference.
For complete parameter details and response schemas, see [Get user](https://platform.claude.com/docs/en/api/organization/users/retrieve) in the API reference.
For complete parameter details and response schemas, see [Update user](https://platform.claude.com/docs/en/api/beta/organization/users/update) in the API reference.
+8 −8 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/usage-cost-api
±changed
+3−3
apichanged
manage-claude/usage-cost-api
To retrieve your organization's API key IDs, use the [List API Keys](https://platform.claude.com/docs/en/api/beta/organization/api_keys/list) endpoint.
To retrieve your organization's workspace IDs, use the [List Workspaces](https://platform.claude.com/docs/en/api/beta/organization/workspaces/list) endpoint, or find your organiz
To retrieve your organization's API key IDs, use the [List API Keys](https://platform.claude.com/docs/en/api/organization/api_keys/list) endpoint.
+3 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/data-residency
±changed
+1−1
apichanged
manage-claude/data-residency
The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5, Claude Haiku 4.5, or earlier models
The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5 (deprecated), Claude Haiku 4.5, or ea
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
manage-claude/authentication
±changed
+3−3
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 page](https://platform.claude.com/settings/key
You can find a workspace's ID in the **ID** column of [Settings → Workspaces](https://platform.claude.com/settings/workspaces) in the Claude Console, or by calling the [List Worksp
You can find a workspace's ID in the **ID** column of [Settings → Workspaces](https://platform.claude.com/settings/workspaces) in the Claude Console, or by calling the [List Worksp
The Console API keys table shows each key's expiration, and the Admin API reports each key's `expires_at` timestamp on the [List API Keys](https://platform.claude.com/docs/en/api/b
+3 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
get-api-key
±changed
+1−1
apichanged
get-api-key
The [Admin API](https://platform.claude.com/docs/en/api/beta/organization) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key]
The [Admin API](https://platform.claude.com/docs/en/api/organization) includes endpoints for managing your organization's API keys programmatically, such as [Retrieve API Key](http
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
cli-sdks-libraries/libraries/openai-sdk
±changed
+1−1
apichanged
cli-sdks-libraries/libraries/openai-sdk
You can enable [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) by adding the `thinking` parameter. On current models thinking is adaptive, with Claude de
You can enable [thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) by adding the `thinking` parameter. On current models thinking is adaptive, with Claude de
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
claude_api_primer
±changed
+3−3
apichanged
claude_api_primer
Thinking can sometimes help Claude with very hard tasks. The current mechanism is [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {"
Thinking can sometimes help Claude with very hard tasks. The current mechanism is [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {"
* Claude Sonnet 4.5 (`claude-sonnet-4-5-20250929`, legacy manual thinking only)
* Claude Sonnet 4.5 (`claude-sonnet-4-5-20250929`, [deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations), legacy manual thinking only)
Interleaved thinking enables Claude to think between tool calls, reasoning about tool results before deciding the next step.
+3 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/thinking-steering-and-cost
±changed
+8−8
apichanged
build-with-claude/thinking-steering-and-cost
Claude's thinking is adaptive: the model evaluates each request and decides for itself whether to think and how much. You set an intent, optionally specify the effort, and the mode
Claude's thinking is adaptive: the model evaluates each request and determines whether to think and how much. You set an intent, optionally specify the effort, and the model alloca
To learn how to turn thinking on, how to read thinking output, and about [thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-clau
## How Claude decides when to think
+8 −8 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/thinking
±changed
+5−5
apichanged
build-with-claude/thinking
![Diagram of how thinking works: Claude evaluates the request and decides whether to think up front; with tool use, thinking can recur between tool calls; one response returns th
![Diagram: Claude determines whether to think up front, may think between tool calls, and returns thinking blocks before text](https://platform.claude.com/docs/images/how-thinkin
On Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, thinking is off until you set `thinking: {type: "adaptive"}`, which lets Claude decide when and how dee
On Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, and Claude Sonnet 4.6, thinking is off until you set `thinking: {type: "adaptive"}`, which lets Claude determine when and how
* Reason about the results of a tool call before deciding what to do next
+5 −5 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/task-budgets
±changed
+1−1
apichanged
build-with-claude/task-budgets
Let Claude decide when and how much to use extended thinking.
Let Claude determine when and how much to use extended thinking.
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
In chat applications, if your system prompt contains instructions that tell Claude to think carefully before answering, consider removing them for Claude Opus 5.5. The model decide
In chat applications, if your system prompt contains instructions that tell Claude to think carefully before answering, consider removing them for Claude Opus 5.5. The model determ
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+2−2
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), wher
Claude 4.6 and later models and Claude Mythos Preview use [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) (`thinking: {type: "adaptive"}`), wher
Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5 feature [context awareness](https://platform.claude.com/docs/en/build-with-claude/context-windows#contex
Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 (deprecated), and Claude Haiku 4.5 feature [context awareness](https://platform.claude.com/docs/en/build-with-claude/context-w
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/prompt-caching
±changed
+2−2
apichanged
build-with-claude/prompt-caching
* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Opus 4.1 ([retired, except on Bedrock and Google Cloud](https://platform.claude.co
* 1,024 tokens for Claude Opus 4.8, Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)), Claud
# On earlier Opus/Sonnet and all Haiku models, non-tool-result user block causes prior thinking blocks to be stripped; on Opus 4.5+/Sonnet 4.6+ they are kept
# Depending on the model, this non-tool-result user block either keeps prior thinking blocks or strips them (see the next paragraph)
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/preserved-thinking
±changed
+4−2
apichanged
build-with-claude/preserved-thinking
Preserved thinking is a property of newer Claude models that guards against distillation. It decides whether the model can use a thinking block that you send back from an earlier t
Preserved thinking is a property of newer Claude models that guards against distillation. It determines whether the model can use a thinking block that you send back from an earlie
To use several betas in one request, combine the values in one `anthropic-beta` header. Beta names are the same on Amazon Bedrock and Google Cloud wherever the beta is available th
To use several betas in one request on the Claude API, combine their names in one `anthropic-beta` header:
+4 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/overview
±changed
+1−1
apichanged
build-with-claude/overview
| [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)
| [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking)
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/multilingual-support
±changed
+17−17
apichanged
build-with-claude/multilingual-support
| Language | Claude Sonnet 4.51 | Claude Haiku 4.51 |
| --------------------------------- | ------------------ | ----------------- |
| English (baseline, fixed to 100%) | 100% | 100% |
| Spanish | 98.2% | 96.4% |
| Portuguese (Brazil) | 97.8% | 96.1% |
+17 −17 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+2−2
apichanged
build-with-claude/mid-conversation-system-messages
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level from the next `user` tur
A `role: "system"` message can also carry `output_config.effort` to change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level partway through a conver
The first is the error returned without the beta header. On Amazon Bedrock and Google Cloud, pass the beta value as described in [Beta headers](https://platform.claude.com/docs/en/
The first is the error returned without the beta header. On Google Cloud and [Claude in Amazon Bedrock](https://platform.claude.com/docs/en/build-with-claude/claude-in-amazon-bedro
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/handling-stop-reasons
±changed
+2−2
apichanged
build-with-claude/handling-stop-reasons
If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 or Claude Opus 4.1 (the latter [retired, except on Bedrock and Google Cloud](https://platform.cla
If you encounter `refusal` stop reasons frequently while using Claude Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-deprecations)) or Claude Opu
This stop reason is currently typed only in the SDK's `beta` (csharp, go: `Beta`; java: `beta()`) namespace, so the following examples call `client.beta.messages` (csharp, go: `c
This stop reason is currently typed only in the SDK's `beta` (csharp, go: `Beta`; java: `beta()`) namespace, so the following examples call `client.beta.messages` (csharp, go: `c
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/extended-thinking
±changed
+6−6
apichanged
build-with-claude/extended-thinking
Interleaved thinking lets Claude think between tool calls within a single assistant turn, reasoning about each tool result before deciding what to do next. For the concept, the tur
On Claude Opus 4.5, Claude Sonnet 4.5, and earlier Claude 4 models, add the `interleaved-thinking-2025-05-14` [beta header](https://platform.claude.com/docs/en/api/beta-headers) to
Interleaved thinking lets Claude think between tool calls within a single assistant turn, reasoning about each tool result before determining what to do next. For the concept, the
+6 −6 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/effort
±changed
+5−3
apichanged
build-with-claude/effort
Claude Opus 5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message
Claude Opus 5 also supports [changing effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-conversation-beta) with a per-message
Per-message effort is in beta and requires the [beta header](https://platform.claude.com/docs/en/api/beta-headers) `mid-conversation-output-config-2026-07-01`. Models without per-m
Per-message effort is in beta. On the Claude API and [Google Cloud](https://platform.claude.com/docs/en/build-with-claude/claude-on-vertex-ai), it's available on Claude Fable 5.1,
+5 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/context-windows
±changed
+4−4
apichanged
build-with-claude/context-windows
Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude S
Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude S
Most current Claude models support [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking), which lets Claude think between to
Most current Claude models support [interleaved thinking](https://platform.claude.com/docs/en/build-with-claude/thinking#interleaved-thinking), which lets Claude think between to
Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, and Claude Haiku 4.5 have **context awareness:** these models track their remaining context window (their "token budget") thr
+4 −4 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/context-editing
±changed
+6−6
apichanged
build-with-claude/context-editing
| Model class | Keep all prior thinking | Keep only the last turn's thinking |
| ---------------- | --------------------------- | ----------------------------------- |
| Opus | Claude Opus 4.5 and later | Claude Opus 4.1 and earlier |
| Sonnet | Claude Sonnet 4.6 and later | Claude Sonnet 4.5 and earlier |
| Haiku | (none) | All models through Claude Haiku 4.5 |
+6 −6 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+3−3
apichanged
build-with-claude/claude-platform-on-aws
| **Beta features** | Pass through with `anthropic-beta` headers (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#
| **Beta features** | Pass through with `anthropic-beta` headers (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#
The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5, or Claude Haiku 4.5 return a 400 e
The `inference_geo` parameter is supported on Claude 4.6 and later models. Requests with `inference_geo` on Claude Opus 4.5, Claude Sonnet 4.5 (deprecated), or Claude Haiku 4.5 r
* Beta features through the `anthropic-beta` header (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-not-supported))
+3 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+2−2
apichanged
build-with-claude/claude-on-vertex-ai
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have
This applies to Claude Sonnet 4.5 and future models only. Older models (Claude Sonnet 4 (deprecated), Opus 4 (deprecated), and earlier) maintain their existing pricing structures
This applies to Claude Sonnet 4.5 (deprecated) and future models only. Older models (Claude Sonnet 4 (deprecated), Opus 4 (deprecated), and earlier) maintain their existing prici
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+8−6
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fabl
[Mid-conversation system messages](https://platform.claude.com/docs/en/build-with-claude/mid-conversation-system-messages) are available through the InvokeModel API for Claude Fabl
A `role: "system"` message can also set `output_config.effort` to [change effort mid-conversation](https://platform.claude.com/docs/en/build-with-claude/effort#change-effort-mid-co
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have
+8 −6 lines
Recorded here 7 Oct 2026 15:07 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+1−1
apichanged
build-with-claude/claude-in-microsoft-foundry
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have
Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
api/rate-limits
±changed
+1−1
apichanged
api/rate-limits
*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5. Claude Sonnet 5.5 and Claude Sonnet 5 each have a separate rate limit a
*3 Sonnet 4.x rate limit is a total limit that applies to combined traffic across Sonnet 4.6 and Sonnet 4.5 ([deprecated](https://platform.claude.com/docs/en/about-claude/model-dep
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
api/beta-headers
±changed
+9−0
apichanged
api/beta-headers
### Beta features on other platforms
Beta names are the same on every platform that accepts them, but not every platform accepts every beta. [Claude Platform on AWS](https://platform.claude.com/docs/en/build-with-clau
On Amazon Bedrock, where beta names go depends on the API you call:
+9 −0 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/web-search-tool
These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) se
These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) se
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+16−16
apichanged
agents-and-tools/tool-use/tool-search-tool
| Model | Tool versions |
| ---------------------------------------------- | ------------------------------------------------------------------- |
| Claude Fable 5.1 (claude-fable-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |
| Claude Mythos 5.1 (claude-mythos-5-1) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |
| Claude Fable 5 (claude-fable-5) | `tool_search_tool_regex_20251119`, `tool_search_tool_bm25_20251119` |
+16 −16 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+1−1
apichanged
agents-and-tools/tool-use/server-tools
Organization-level web search and web fetch settings in the Claude Console apply to Messages API requests only; they do not apply to Managed Agents sessions, which use only the per
Organization-level web search and web fetch settings in the Claude Console apply to Messages API requests only. They do not apply to Managed Agents sessions, which use the per-tool
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+2−2
apichanged
agents-and-tools/tool-use/define-tools
* Any important caveats or limitations, such as what information the tool does not return if the tool name is unclear. The more context you can give Claude about your tools, the
* Any important caveats or limitations, such as what information the tool does not return if the tool name is unclear. The more context you can give Claude about your tools, the
* `auto` allows Claude to decide whether to call any provided tools or not. This is the default value when `tools` are provided.
* `auto` allows Claude to determine whether to call any provided tools or not. This is the default value when `tools` are provided.
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+5−5
apichanged
agents-and-tools/tool-use/computer-use-tool
Claude typically finishes a batch with `screenshot` so it can observe the outcome before deciding what to do next. When a batch doesn't end with one, your application can attach a
Claude typically finishes a batch with `screenshot` so it can observe the outcome before determining what to do next. When a batch doesn't end with one, your application can attach
| Tool version | Beta header | Use with
| ------------------- | ------------------------- | --------------------------------------------------------------------------------------------------------------------------------
| `computer_20251124` | `computer-use-2025-11-24` | Claude Fable 5.1, Claude Mythos 5.1, Claude Fable 5, Claude Mythos 5, Claude Opus 5, Claude Sonnet 5, Claude Opus 4.8, Claude Op
+5 −5 lines
Recorded here 7 Oct 2026 15:07 UTC
api
agents-and-tools/agent-skills/claude-api-skill
±changed
+1−1
apichanged
agents-and-tools/agent-skills/claude-api-skill
For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-g
For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-g
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
about-claude/pricing
±changed
+1−1
apichanged
about-claude/pricing
**Scope:** This pricing structure applies to Claude Sonnet 4.5, Haiku 4.5, Opus 4.5, and all future models. Earlier models (Claude Opus 4.1 and prior releases) retain their exist
**Scope:** This pricing structure applies to Claude Sonnet 4.5 (deprecated), Haiku 4.5, Opus 4.5, and all future models. Earlier models (Claude Opus 4.1 and prior releases) retai
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+1−1
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, the budgets and caps it works within, and w
These levers set where a single model sits between cost and intelligence: model choice, effort, re-running failures at a higher setting, the budgets and caps it works within, and w
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
claude-code
errors
±changed
+1−1
claude-codechanged
errors
* Resize the image before pasting. The API accepts images up to 8000 pixels on the longest edge for a single image, or 2000 pixels when many images are in context.
* Resize the image before pasting. The API accepts images up to 8000 pixels on the longest edge for a single image, or 3000 pixels when more than 20 images are in context.
+1 −1 lines
Upstream edited 7 Oct 2026 15:04 UTC Recorded here 7 Oct 2026 15:07 UTC
claude-code
how-claude-code-works
±changed
+39−39
claude-codechanged
how-claude-code-works
This guide covers the core architecture, built-in capabilities, and [tips for working effectively](#work-effectively-with-claude-code). For step-by-step walkthroughs, see [Common w
This guide covers the core architecture, built-in capabilities, and [tips for working effectively](#work-effectively-with-claude-code). For step-by-step walkthroughs, see [Common w
[Multiple models](/docs/en/model-config.md) are available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning for complex architectura
[Multiple models](https://code.claude.com/docs/en/model-config.md) are available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning f
| **Code intelligence** | See type errors and warnings after edits, jump to definitions, find references (requires [code intelligence plugins](/docs/en/plugins/code-intelligence.md
+39 −39 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
how-claude-code-works
±changed
+36−36
claude-codechanged
how-claude-code-works
This guide covers the core architecture, built-in capabilities, and [tips for working effectively](#work-effectively-with-claude-code). For step-by-step walkthroughs, see [Common w
This guide covers the core architecture, built-in capabilities, and [tips for working effectively](#work-effectively-with-claude-code). For step-by-step walkthroughs, see [Common w
[Multiple models](/docs/en/model-config) are available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning for complex architectural d
[Multiple models](/docs/en/model-config.md) are available with different tradeoffs. Sonnet handles most coding tasks well. Opus provides stronger reasoning for complex architectura
| **Code intelligence** | See type errors and warnings after edits, jump to definitions, find references (requires [code intelligence plugins](/docs/en/plugins/code-intelligence))
+36 −36 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
how-claude-code-works
±changed
+9−15
claude-codechanged
how-claude-code-works
<img src="https://mintcdn.com/claude-code/ikqp3_70mqIahteV/images/agentic-loop.svg?fit=max&auto=format&n=ikqp3_70mqIahteV&q=85&s=4a30fb7ce2815012a9f27c955e2c6bb0" className="dark:h
<img src="https://mintcdn.com/claude-code/_xqph1dUOslCOwsj/images/agentic-loop-dark.svg?fit=max&auto=format&n=_xqph1dUOslCOwsj&q=85&s=75e1d55ed76857a952f9a2dffbab02df" className="h
![Diagram of the agentic loop: Your prompt leads to Claude gathering context, taking action, verifying results, and repeating until task complete. You can interrupt at any point.](
<img src="https://mintcdn.com/claude-code/ikqp3_70mqIahteV/images/session-continuity.svg?fit=max&auto=format&n=ikqp3_70mqIahteV&q=85&s=04ed0984a58e4127e05b3640265241a3" className="
+9 −15 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/structured-outputs
±changed
+399−409
claude-codechanged
agent-sdk/structured-outputs
<AccordionGroup>
<Accordion title="Without structured outputs">
```text theme={null}
Here's a classic chocolate chip cookie recipe!
+399 −409 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
how-claude-code-works
±changed
+1−1
claude-codechanged
how-claude-code-works
* **Your [CLAUDE.md](/docs/en/memory).** A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session. If your repo
* **Your [CLAUDE.md](/docs/en/memory).** A markdown file where you store project-specific instructions, conventions, and context that Claude should know every session. If your repo
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
google-vertex-ai
±changed
+2−2
claude-codechanged
google-vertex-ai
Most model versions have a corresponding `VERTEX_REGION_CLAUDE_*` variable. See the [Environment variables reference](/docs/en/env-vars) for the full list. Check [Google Cloud's Ag
Most model versions have a corresponding `VERTEX_REGION_CLAUDE_*` variable. See the [Environment variables reference](/docs/en/env-vars#variables) for the full list. Check [Google
* Set a region or multi-region location using `VERTEX_REGION_<MODEL_NAME>` environment variables
* Set a region or multi-region location using the model's `VERTEX_REGION_CLAUDE_*` variable, listed in the [environment variables reference](/docs/en/env-vars#variables)
+2 −2 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
You can place CLAUDE.md at project scope in `./CLAUDE.md` or `./.claude/CLAUDE.md`, at user scope in `~/.claude/CLAUDE.md`, or as [managed policy](#managed-settings) for your organ
You can place CLAUDE.md at project scope in `./CLAUDE.md` or `./.claude/CLAUDE.md`, at user scope in `~/.claude/CLAUDE.md`, or as [managed policy](#managed-settings) for your organ
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on
* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load in place
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
claude-directory
±changed
+3−3
claude-codechanged
claude-directory
tips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific task
tips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific task
Most users only edit `CLAUDE.md` and `settings.json`. If your repository already has an `AGENTS.md` for other coding agents, Claude Code [can read that](/docs/en/memory#agents-md)
Most users only edit `CLAUDE.md` and `settings.json`. If your repository already has an `AGENTS.md` for other coding agents, Claude Code [can read that](/docs/en/memory#agents-md)
| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) on its own or
+3 −3 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
chrome
±changed
+1−1
claude-codechanged
chrome
| "Browser extension is not connected" | Native messaging host cannot reach the extension, or your organization's IP allowlist rejects the connection to `bridge.claudeusercontent.c
| "Browser extension is not connected" | Native messaging host cannot reach the extension, or your organization's IP allowlist rejects the connection to `bridge.claudeusercontent.c
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
auto-mode-config
±changed
+1−1
claude-codechanged
auto-mode-config
Get AI feedback on your custom `allow`, `soft_deny`, and `hard_deny` rules:
Get AI feedback on your custom `allow`, `soft_deny`, `hard_deny`, and `environment` entries:
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
If the gateway rewrites `Content-Type` to another value, Claude Code rejects the response with an error that begins `Bedrock streaming response has content-type`, naming the value
If the gateway rewrites `Content-Type` to another value, Claude Code rejects the response with an error that begins `Bedrock streaming response has content-type`, naming the value
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
agent-sdk/typescript
±changed
+9−4
claude-codechanged
agent-sdk/typescript
for await (const message of claimedQuery) {
console.log(message);
try {
for await (const message of claimedQuery) {
console.log(message);
+9 −4 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
agent-sdk/structured-outputs
±changed
+2−2
claude-codechanged
agent-sdk/structured-outputs
The example below asks the agent to research Anthropic and return the company name, year founded, and headquarters as structured output.
Before running the examples on this page, install the Claude Agent SDK by following the [quickstart](/docs/en/agent-sdk/quickstart#setup). The example below asks the agent to resea
Structured output generation can fail when the agent cannot produce valid JSON matching your schema. This typically happens when the schema is too complex for the task, the task it
Structured output generation can fail when the agent cannot produce valid JSON matching your schema. This typically happens when the schema is too complex for the task, the task it
+2 −2 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
agent-sdk/python
±changed
+7−6
claude-codechanged
agent-sdk/python
Behavioral hints for a tool, passed as the `annotations` argument of [`tool()`](#tool). `ToolAnnotations` extends the MCP SDK's `mcp.types.ToolAnnotations` with a `maxResultSizeCha
Behavioral hints for a tool, passed as the `annotations` argument of [`tool()`](#tool). `ToolAnnotations` extends the MCP SDK's `mcp.types.ToolAnnotations` with a `maxResultSizeCha
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
| `costBasis` | `str` | Price table that priced this model's latest request: `list` for list price, `managed` for a [`modelPricing`](/docs/en/settings-reference#modelpricing) table
+7 −6 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
agent-sdk/hooks
±changed
+4−4
claude-codechanged
agent-sdk/hooks
When you run either script, Claude attempts to create the `.env` file, the hook denies the tool call, and Claude's final response explains that it can't create `.env` files.
When you run either script, Claude attempts to create the `.env` file and the hook denies the tool call.
| `WorktreeRemove` | No | Yes | Git worktree removed | Clean up workspace resources |
| `WorktreeRemove` | No | Yes | A worktree created by a `WorktreeCreate` hook is being removed | Clean up workspace resources |
* For `PostToolUse` hooks, you can set `additionalContext` to append information to the tool result. To replace the tool's output before Claude sees it, set `updatedToolOutput`,
+4 −4 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
overview
±changed
+1−1
claude-codechanged
overview
[`CLAUDE.md`](/docs/en/memory) is a markdown file you add to your project root that Claude Code reads at the start of every session. Use it to set coding standards, architectur
[`CLAUDE.md`](/docs/en/memory) is a markdown file you add to your project root that Claude Code reads at the start of every session. Use it to set coding standards, architectur
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
memory
±changed
+2−2
claude-codechanged
memory
* **CLAUDE.md files**: instructions you write to give Claude persistent context. Claude can also read a repository's [`AGENTS.md` files](#agents-md), on their own or alongside CLAU
* **CLAUDE.md files**: instructions you write to give Claude persistent context. Claude can also read a repository's [`AGENTS.md` files](#agents-md) in place of CLAUDE.md
* [Use an existing AGENTS.md](#agents-md) as your project instructions, on its own or alongside CLAUDE.md
* [Use an existing AGENTS.md](#agents-md) as your project instructions
+2 −2 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
self-hosted-environments-testing
±changed
+1−1
claude-codechanged
self-hosted-environments-testing
The script below runs the full loop against `$CLAUDE_TEST_ENVIRONMENT_ID`, your test environment's `ccpool_...` ID, shown in the environment's detail dialog on the admin page or re
The script below runs the full loop against `$CLAUDE_TEST_ENVIRONMENT_ID`, your test environment's `ccpool_...` ID, shown in the environment's detail dialog on the admin page or re
+1 −1 lines
Upstream edited 7 Oct 2026 07:30 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
quickstart
±changed
+5−5
claude-codechanged
quickstart
```bash theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null}
+5 −5 lines
Upstream edited 7 Oct 2026 07:24 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
| `WorktreeRemove` | When a worktree is being removed at session exit, when a subagent finishes, or when you delete a background session |
| `WorktreeRemove` | When a worktree that a `WorktreeCreate` hook created is being removed |
+1 −1 lines
Upstream edited 7 Oct 2026 07:24 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
hooks
±changed
+5−6
claude-codechanged
hooks
| `WorktreeRemove` | When a worktree is being removed at session exit, when a subagent finishes, or when you delete a background session |
| `WorktreeRemove` | When a worktree that a `WorktreeCreate` hook created is being removed |
Runs when a worktree is being removed. This is the cleanup counterpart to [WorktreeCreate](#worktreecreate). The event fires when:
* you exit a `--worktree` session and choose to remove it
+5 −6 lines
Upstream edited 7 Oct 2026 07:24 UTC Recorded here 7 Oct 2026 07:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 06:07 UTC
claude-code
errors
±changed
+1−3
claude-codechanged
errors
* A streaming response that the API's output content filter stops before Claude has either finished thinking or started any text or tool call. Claude Code re-sends the request once
* A response the API's output content filter blocked. Claude Code shows [Output blocked by content filtering policy](#output-blocked-by-content-filtering-policy) at once and doesn'
Claude Code shows the error as soon as the block arrives and ends the request there. It doesn't retry the request, re-send it without streaming, or switch to a [fallback model](/do
+1 −3 lines
Upstream edited 7 Oct 2026 06:03 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
worktrees
±changed
+3−1
claude-codechanged
worktrees
A [git worktree](https://git-scm.com/docs/git-worktree) is a separate working directory with its own files and branch, sharing the same repository history and remote as your main c
A [git worktree](https://git-scm.com/docs/git-worktree) is a separate working directory with its own files and branch, sharing the same repository history and remote as your main c
These checks read the path an edit targets, the directory a command runs in, and the text of the command. None of them tracks which files a shell command writes, so a command that
+3 −1 lines
Upstream edited 7 Oct 2026 05:58 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* [Worktrees](/docs/en/worktrees) give each session a separate git checkout, so parallel sessions never edit the same files. Use them for sessions you run yourself. A session you d
* [Worktrees](/docs/en/worktrees) give each session a separate git checkout, so parallel sessions each edit their own copy of the files. Use them for sessions you run yourself. A s
+1 −1 lines
Upstream edited 7 Oct 2026 05:58 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
agent-sdk/typescript
±changed
+3−3
claude-codechanged
agent-sdk/typescript
| `setMcpServers(servers)` | Dynamically replace the set of MCP servers for this session. Resolves with an [`McpSetServersResult`](#mcpsetserversresult) naming which servers were a
| `setMcpServers(servers)` | Replace the MCP servers this method manages: servers added through it and [in-process SDK servers](#createsdkmcpserver). Resolves with an [`McpSetServe
* **Servers the call doesn't name**: Claude Code keeps plugin-provided servers running. Requires Agent SDK v0.3.210 or later.
* **Servers the call names**: except for built-in servers the CLI started at startup, Claude Code replaces a running server only when its config differs from the one you passed.
* **Servers the call doesn't name**: outside a [cloud session](/docs/en/claude-code-on-the-web), Claude Code disconnects the servers an earlier `setMcpServers()` call added and the
+3 −3 lines
Upstream edited 7 Oct 2026 05:48 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
desktop
±changed
+1−1
claude-codechanged
desktop
* **Windows**: click **Help**, then **About**
* **Windows**: click **Help**, then **About Claude**
+1 −1 lines
Upstream edited 7 Oct 2026 05:46 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
server-managed-settings
±changed
+1−1
claude-codechanged
server-managed-settings
If the link redirects you to a different Organization settings page instead of the Claude Code page, your account doesn't have the required role. Admin and other non-Owner role
In a Team or Enterprise organization, if the page says you don't have access, ask an [Owner or Primary Owner](#access-control) to make the change.
+1 −1 lines
Upstream edited 7 Oct 2026 05:46 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
| `claudeProcessWrapper` | - | Executable used to launch the Claude process. The bundled binary path is passed as an argument when present. Set this to a separately installed `clau
| `claudeProcessWrapper` | - | Executable used to launch the Claude process. The bundled binary path is passed as an argument when present. Set this to a separately installed `clau
+1 −1 lines
Upstream edited 7 Oct 2026 05:37 UTC Recorded here 7 Oct 2026 06:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 05:37 UTC
claude-code
plugins/mods/reference
±changed
+22−1
claude-codechanged
plugins/mods/reference
| [`Box`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `key`, flex layout, `gap`, `padding`, `margin`, `width`, `height`, `borderStyle`, `backgroundColor`, `positi
| [`Box`](/docs/en/plugins/mods/interface#build-a-tree-from-elements) | `key`, flex layout, `gap`, `padding`, `margin`, `width`, `height`, [`borderStyle`](#box-border-styles), `bac
<h3 id="box-border-styles">
`Box` border styles
+22 −1 lines
Upstream edited 7 Oct 2026 05:35 UTC Recorded here 7 Oct 2026 05:37 UTC
claude-code
plugins/mods/interface
±changed
+1−1
claude-codechanged
plugins/mods/interface
| `Box` | A flex container. Takes layout props such as `flexDirection`, `columnGap`, `padding`, `borderStyle`, and `width`. | Everywhere |
| `Box` | A flex container. Takes layout props such as `flexDirection`, `columnGap`, `padding`, [`borderStyle`](/docs/en/plugins/mods/reference#box-border-styles), and `width`. | E
+1 −1 lines
Upstream edited 7 Oct 2026 05:35 UTC Recorded here 7 Oct 2026 05:37 UTC
claude-docs
claude-science/multiple-computers
±changed
+3−3
claude-docschanged
claude-science/multiple-computers
Anthropic doesn't sync your projects, artifacts, or conversation history to your Claude account, so there's no cloud copy for you to browse or sync from another computer. Claude re
Anthropic doesn't sync your projects, artifacts, or conversation history to your Claude account, so there's no cloud copy for you to browse or sync from another computer. Claude re
To take a single result to another computer, choose **Download** from the artifact's menu. A file saved with **Export session** is for technical support and troubleshooting, and ca
To take a single result to another computer, choose **Download** from the artifact's menu. A file saved with **Export session** is for technical support and troubleshooting, and ca
The access happens entirely on your computer and uploads nothing. Credentials such as API keys and connector sign-ins aren't copied or moved and stay in their original folder. On T
+3 −3 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 23 Oct 2026 18:07 UTC
claude-docs
claude-science/multiple-computers
±changed
+3−3
claude-docschanged
claude-science/multiple-computers
Anthropic doesn't sync your projects, artifacts, or conversation history to your Claude account, so there's no cloud copy for you to browse or sync from another computer. Claude re
Anthropic doesn't sync your projects, artifacts, or conversation history to your Claude account, so there's no cloud copy for you to browse or sync from another computer. Claude re
To take a single result to another computer, choose **Download** from the artifact's menu. A file saved with **Export session** is for technical support and troubleshooting, and ca
To take a single result to another computer, choose **Download** from the artifact's menu. A file saved with **Export session** is for technical support and troubleshooting, and ca
The access happens entirely on your computer and uploads nothing. Credentials such as API keys and connector sign-ins aren't copied or moved and stay in their original folder. On T
+3 −3 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
claude-science/safeguards
±changed
+1−1
claude-docschanged
claude-science/safeguards
Automatic switching is on by default and applies to every session on this computer. To turn it off, go to **Settings > General > Model** and turn off the **Switch models when a mes
Automatic switching is on by default. To turn it off, go to **Settings > General > Model** and turn off the **Switch models when a message is flagged** toggle. The **Chat paused**
+1 −1 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/network-requirements
±changed
+1−0
claude-docschanged
claude-science/network-requirements
| `www.google.com`, `t0.gstatic.com` | Icons for connectors and services that the app loads from Google's favicon service. If these are blocked, a generic icon shows instead |
+1 −0 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/multiple-computers
±changed
+1−1
claude-docschanged
claude-science/multiple-computers
You can install Claude Science on more than one computer and sign in to each with the same Claude account. Your account carries your plan and usage limits to every computer. Skills
You can install Claude Science on more than one computer and sign in to each with the same Claude account. Your account carries your plan and usage limits to every computer. Skills
+1 −1 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/how-claude-science-works-with-your-data
±changed
+1−1
claude-docschanged
claude-science/how-claude-science-works-with-your-data
In organizations with CMEK enabled, the app hides its response rating buttons and feedback form, as claude.ai does.
In organizations with CMEK enabled, the app hides the **Send feedback** link on the [**Chat paused**](/docs/claude-science/safeguards#when-safeguards-flag-a-message) card.
+1 −1 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/core-concepts
±changed
+1−0
claude-docschanged
claude-science/core-concepts
| Work in a write-access folder too large to check for credential files (Linux) | This folder is too large to check fully / This folder changed past what was checked | Asked once p
+1 −0 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/command-line-settings
±changed
+1−1
claude-docschanged
claude-science/command-line-settings
* `--dangerously-skip-approvals` approves [permission cards](/docs/claude-science/core-concepts#permission-cards) for you without showing them, until you restart without the flag
* `--dangerously-skip-approvals` approves [permission cards](/docs/claude-science/core-concepts#permission-cards) for you without showing them, until you restart without the flag
+1 −1 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/changelog
±changed
+11−0
claude-docschanged
claude-science/changelog
<Update label="0.1.59" description="October 6, 2026">
* Saved approvals for tools from your organization's plugins are cleared, so Claude asks again; new approvals apply only to the plugin that added the tool
* Skills from plugins your organization's admin uploads now appear under Organization in **Settings > Skills**, instead of under Featured
* Comment boxes on figures, PDFs, reports, and files now grow as you type, and a new comment that fails to save keeps your text and shows an error
* Fixed some files failing to upload when you add hundreds of files to a message at once
+11 −0 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
claude-docs
claude-science/admin-controls
±changed
+2−2
claude-docschanged
claude-science/admin-controls
| Data and privacy > Rate chats | Supported in Claude Science | When you turn this off, the app hides its response rating buttons and feedback form, as claude.ai does. If your orga
| Data and privacy > Rate chats | Supported in Claude Science | When you turn this off, the app hides the **Send feedback** link on the [**Chat paused**](/docs/claude-science/safeg
| Data and privacy > Encryption keys (customer-managed keys) | Supported in Claude Science | The content Anthropic stores from Claude Science (model-call logs, skills members publi
| Data and privacy > Encryption keys (customer-managed keys) | Supported in Claude Science | The content Anthropic stores from Claude Science (model-call logs, skills members publi
+2 −2 lines
Upstream edited 7 Oct 2026 04:51 UTC Recorded here 7 Oct 2026 05:07 UTC
api
release-notes/overview
±changed
+1−0
apichanged
release-notes/overview
* In Python SDK 1.10.0, TypeScript SDK 0.130.0, C# SDK 12.52.0, Go SDK 1.77.0, Java SDK 2.67.0, PHP SDK 0.53.0, Ruby SDK 1.75.0, and version 1.37.0 of the `ant` CLI, the [Admin API
+1 −0 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/mythos-5/overview
±changed
+4−4
apichanged
models/mythos-5/overview
description: "Claude Mythos 5 reference: the same model as Claude Fable 5, offered by invitation only through Project Glasswing for defensive cybersecurity work. Model IDs, specifi
description: "Claude Mythos 5 reference: the same model as Claude Fable 5, offered for defensive cybersecurity work to organizations verified through Anthropic's verification progr
**Invite only.** Released June 9, 2026.
**Verification required.** Released June 9, 2026.
Claude Mythos 5 is offered separately, by invitation only, as part of Project Glasswing. It shares Claude Fable 5’s specifications and pricing. For access, contact your Anthropic,
+4 −4 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/mythos-5-1/overview
±changed
+5−5
apichanged
models/mythos-5-1/overview
description: "Claude Mythos 5.1 at a glance: the same model as Claude Fable 5.1, offered by invitation only through Project Glasswing. Model IDs, specifications, pricing, and how t
description: "Claude Mythos 5.1 at a glance: the same model as Claude Fable 5.1, available only to organizations verified through Anthropic's verification programs. Model IDs, spec
**Invite only.** Released September 1, 2026.
**Verification required.** Released September 1, 2026.
Claude Fable 5.1 for Project Glasswing participants
+5 −5 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5/overview
±changed
+1−1
apichanged
models/fable-5/overview
[Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview) is offered separately, by invitation only, for defensive cybersecurity workflows as part of [Project
[Claude Mythos 5](https://platform.claude.com/docs/en/models/mythos-5/overview) is offered separately for defensive cybersecurity workflows and is available only to organizations v
+1 −1 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5/migration-guide
±changed
+5−5
apichanged
models/fable-5/migration-guide
[Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) is built for demanding reasoning and long-horizon agentic work.
[Claude Fable 5](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5) is built for demanding reasoning and long-horizon agentic work.
* **Availability:** Claude Fable 5 does not require access approval. Claude Mythos 5 is available only to approved customers in [Project Glasswing](https://anthropic.com/glasswing)
* **Availability:** Claude Fable 5 does not require access approval. Claude Mythos 5 is available only to organizations verified through Anthropic's verification programs, such as
[Claude Mythos 5](https://anthropic.com/glasswing) is the access-gated successor to [Claude Mythos Preview](https://anthropic.com/glasswing), the invitation-only research preview.
+5 −5 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+6−6
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
Claude Fable 5 is built for demanding reasoning and long-horizon agentic work. Claude Mythos 5 shares the same capabilities and is available only in limited release through [Projec
Claude Fable 5 is built for demanding reasoning and long-horizon agentic work. Claude Mythos 5 shares the same capabilities and is available only to organizations verified through
| Model | API model ID | Description |
| --------------- | ----------------- | -------------------------------------------------------------------------------------------------------------- |
| Claude Fable 5 | `claude-fable-5` | Built for demanding reasoning and long-horizon agentic work |
+6 −6 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+6−6
apichanged
models/fable-5-1/whats-new-fable-5-1
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
| Model | Claude API ID | Description | Availability
| ----------------- | ----------------- | ------------------------------------------------------------------------------------------ | ---------------------------------------------
| Claude Fable 5.1 | claude-fable-5-1 | Successor to Claude Fable 5, for long-running agentic coding, knowledge work, and research | All customers, on the Claude API and partner
+6 −6 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5-1/overview
±changed
+2−2
apichanged
models/fable-5-1/overview
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
Claude Fable 5.1 extends Claude Fable 5 at the same input and output prices, with cache reads at a quarter of the cost, and brings stronger long-running agentic coding, multistep r
[Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) offers the same capabilities by invitation only, as part of [Project Glasswing](https://anthropi
[Claude Mythos 5.1](https://platform.claude.com/docs/en/models/mythos-5-1/overview) offers the same capabilities only to organizations verified through Anthropic's verification pro
+2 −2 lines
Recorded here 7 Oct 2026 04:37 UTC
api
models/fable-5-1/migration-guide
±changed
+6−6
apichanged
models/fable-5-1/migration-guide
[Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) succeeds Claude Fable 5 at the same input and output prices, with cache reads at a quar
[Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/whats-new-fable-5-1) succeeds Claude Fable 5 at the same input and output prices, with cache reads at a quar
* **Availability:** Claude Fable 5.1 doesn't require access approval. Claude Mythos 5.1 is available only to approved customers in [Project Glasswing](https://anthropic.com/glasswi
* **Availability:** Claude Fable 5.1 doesn't require access approval. Claude Mythos 5.1 is available only to organizations verified through Anthropic's verification programs, such
# Or, for the Project Glasswing model with the same capabilities:
+6 −6 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/workspaces
±changed
+76−78
apichanged
manage-claude/workspaces
* **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
* **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
The following SDK and CLI examples construct the default client, which reads the Admin API key from the `ANTHROPIC_API_KEY` environment variable; the SDKs expose these endpoints un
The following SDK and CLI examples construct the default client, which reads the Admin API key from the `ANTHROPIC_API_KEY` environment variable; the SDKs expose these endpoints un
ant beta:organization:workspaces create --name Production
+76 −78 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/wif-admin-api
±changed
+107−112
apichanged
manage-claude/wif-admin-api
In the SDKs these endpoints are `client.beta.organization.service_accounts`, `client.beta.organization.federation.issuers`, and `client.beta.organization.federation.rules` (`ant be
In the SDKs these endpoints are `client.organization.service_accounts` (typescript: `client.organization.serviceAccounts`; csharp, go: `client.Organization.ServiceAccounts`; java:
ant beta:organization:service-accounts list
ant organization:service-accounts list
service_accounts = client.beta.organization.service_accounts.list()
+107 −112 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/rate-limits-api
±changed
+51−51
apichanged
manage-claude/rate-limits-api
The SDK and CLI examples on this page construct the default client, which reads the Admin API key from the `ANTHROPIC_API_KEY` environment variable. The SDKs expose these endpoints
The SDK and CLI examples on this page construct the default client, which reads the Admin API key from the `ANTHROPIC_API_KEY` environment variable. The SDKs expose these endpoints
ant beta:organization:rate-limits list
ant organization:rate-limits list
rate_limits = client.beta.organization.rate_limits.list()
+51 −51 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+11−6
apichanged
manage-claude/inference-hooks-endpoint
| Field | Present | Description |
| ----------------- | -------------------- | ---------------------------------------------------------------------------------------------------------------------------------- |
| `type` | Always | `"third_party"` |
| `toolset_name` | Optional | The name the request gives the server. |
| `origin` | Optional | The scheme, host, and non-default port of the server's URL. An absent `origin` means unknown, not safe. |
+11 −6 lines
Recorded here 7 Oct 2026 04:37 UTC
api
manage-claude/inference-hooks-configuration
±changed
+18−4
apichanged
manage-claude/inference-hooks-configuration
| Private or internal IP | The host resolves to a private or internal address. Use a publicly routable host.
| Private or internal IP | The URL's host is a private or internal IP address, an IPv6 address, or `localhost`. Use a publicly routable host.
| Transport error | DNS resolution, the TLS handshake, or the connection failed.
| Transport error | DNS resolution, the TLS handshake, or the connection failed, or the hostname resolves to a private address.
* **Recent errors:** each entry is reduced to a timestamp, an error type, and a one-line reason. Entries never include request content or your endpoint URL.
+18 −4 lines
Recorded here 7 Oct 2026 04:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.