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 24 Oct 2026
100 on this page
ReadSourcePageWhatLines
6 Oct 2026
118 pages
+2906 −2121 lines
mcp
seps/index
±changed
+1−0
mcpchanged
seps/index
| [SEP-2127](/seps/2127-mcp-server-cards) | MCP Server Cards - HTTP Server Discovery | <Badge color="green" shape="pill">Final</Badge> | Extensions Track | 2026-01-21 |
+1 −0 lines
Recorded here 6 Oct 2026 15:07 UTC
mcp
seps/2127-mcp-server-cards
±changed
+5−5
mcpchanged
seps/2127-mcp-server-cards
> specification](/specification/latest.md) and its changelog for authoritative
> specification](https://modelcontextprotocol.io/specification/latest.md) and its changelog for authoritative
As an Extensions Track SEP (per [SEP-2133](/seps/2133-extensions.md)), this document charters the **Server Card** extension and names its Working Group and maintainers. The detaile
As an Extensions Track SEP (per [SEP-2133](https://modelcontextprotocol.io/seps/2133-extensions.md)), this document charters the **Server Card** extension and names its Working Gro
For purposes of SEP review, [extension repository snapshot `526201bb`](https://github.com/modelcontextprotocol/experimental-ext-server-card/tree/526201bbc80231daa40ffcdecfc9da4e54e
+5 −5 lines
Upstream edited 6 Oct 2026 14:44 UTC Recorded here 24 Oct 2026 11:07 UTC
mcp
seps/2127-mcp-server-cards
±changed
+5−5
mcpchanged
seps/2127-mcp-server-cards
> specification](/specification/latest) and its changelog for authoritative
> specification](/specification/latest.md) and its changelog for authoritative
As an Extensions Track SEP (per [SEP-2133](./2133-extensions.md)), this document charters the **Server Card** extension and names its Working Group and maintainers. The detailed, n
As an Extensions Track SEP (per [SEP-2133](/seps/2133-extensions.md)), this document charters the **Server Card** extension and names its Working Group and maintainers. The detaile
For purposes of SEP review, [extension repository snapshot `526201bb`](https://github.com/modelcontextprotocol/experimental-ext-server-card/tree/526201bbc80231daa40ffcdecfc9da4e54e
+5 −5 lines
Upstream edited 6 Oct 2026 14:44 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
seps/2127-mcp-server-cards
±changed
+9−15
mcpchanged
seps/2127-mcp-server-cards
<div className="flex items-center gap-2 mb-4">
<Badge color="green" shape="pill">
Final
</Badge>
Final
+9 −15 lines
Upstream edited 6 Oct 2026 14:44 UTC Recorded here 20 Oct 2026 20:07 UTC
mcp
seps/2127-mcp-server-cards
+new page
+202−0
mcpnew page
seps/2127-mcp-server-cards
No line of the body moved in this read.
+202 −0 lines
Upstream edited 6 Oct 2026 14:44 UTC Recorded here 6 Oct 2026 15:07 UTC
api
models/sonnet-5-5/migration-guide
±changed
+1−1
apichanged
models/sonnet-5-5/migration-guide
* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification.
* **Output format:** use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outputs), or tools with enum fields for classification. On Amazon Bed
+1 −1 lines
Recorded here 6 Oct 2026 05:07 UTC
api
models/opus-5-5/migration-guide
±changed
+4−4
apichanged
models/opus-5-5/migration-guide
* **Prefill:** Don't end `messages` with a prefilled assistant turn: it is rejected. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outpu
* **Prefill:** Don't end `messages` with a prefilled assistant turn: it is rejected. Use [structured outputs](https://platform.claude.com/docs/en/build-with-claude/structured-outpu
* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs.
* Replace `tool_choice` types `any` and `tool` with `auto` plus strict tool use or structured outputs, or with `auto` alone on Amazon Bedrock.
`tool_choice` types `any` and `tool` return a 400 error (`tool_choice: type "tool" and "any" are not supported for this model.`), including on the token counting endpoint. Use `aut
+4 −4 lines
Recorded here 6 Oct 2026 05:07 UTC
api
manage-claude/inference-hooks
±changed
+1−1
apichanged
manage-claude/inference-hooks
Governed requests are the inference requests behind the user's conversation. Ancillary requests, such as conversation title generation, aren't sent to your endpoint, and system pro
Governed requests are the inference requests behind the user's conversation. Ancillary requests aren't sent to your endpoint. These include conversation title generation and a meas
+1 −1 lines
Recorded here 6 Oct 2026 05:07 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 6 Oct 2026 04:07 UTC
claude-code
changelog
±changed
+5−0
claude-codechanged
changelog
<Update label="2.1.291" description="October 6, 2026">
* Fixed a regression in 2.1.290 where cloud sessions could drop answers to permission prompts
* Fixed a regression in 2.1.288 where the last messages of a session could be lost when quitting
</Update>
+5 −0 lines
Upstream edited 6 Oct 2026 04:05 UTC Recorded here 6 Oct 2026 04:07 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 6 Oct 2026 03:37 UTC
claude-code
third-party-integrations
±changed
+23−23
claude-codechanged
third-party-integrations
**Claude for Teams** is self-service and includes collaboration features, admin tools, SSO, billing management, and [server-managed settings](/docs/en/server-managed-settings.md) f
**Claude for Teams** is self-service and includes collaboration features, admin tools, SSO, billing management, and [server-managed settings](https://code.claude.com/docs/en/server
The deployment options compared below cover where model inference runs. To run Claude Code [cloud sessions](/docs/en/claude-code-on-the-web.md) on compute your organization operate
The deployment options compared below cover where model inference runs. To run Claude Code [cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web.md) on compute yo
<td>API key or a [Console sign-in without one](/docs/en/authentication.md#sign-in-without-an-api-key)</td>
+23 −23 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
agent-sdk/secure-deployment
±changed
+9−9
claude-codechanged
agent-sdk/secure-deployment
Claude Code includes several security features that address common concerns. See the [security documentation](/docs/en/security.md) for full details.
* **Permissions system**: Every tool and bash command can be configured to allow, block, or prompt the user for approval. Use glob patterns to create rules like "allow all npm comm
* **Command parsing for permissions**: Before executing bash commands, Claude Code parses them into an AST and matches the result against your permission rules. Commands that canno
Claude Code includes several security features that address common concerns. See the [security documentation](https://code.claude.com/docs/en/security.md) for full details.
+9 −9 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
agent-sdk/quickstart
±changed
+16−16
claude-codechanged
agent-sdk/quickstart
> * If pip installs the Python SDK's source distribution instead of a platform wheel, for example on ARM64 Windows, no binary is bundled. [Install Claude Code natively](/docs/en/se
> * The TypeScript SDK installs its binary through npm optional dependencies, so an install that skips them, for example `npm ci --omit=optional`, gets no binary even on a supporte
> * If pip installs the Python SDK's source distribution instead of a platform wheel, for example on ARM64 Windows, no binary is bundled. [Install Claude Code natively](https://cod
> * The TypeScript SDK installs its binary through npm optional dependencies, so an install that skips them, for example `npm ci --omit=optional`, gets no binary even on a supporte
See the setup guides for [Amazon Bedrock](/docs/en/amazon-bedrock.md), [Claude Platform on AWS](/docs/en/claude-platform-on-aws.md), [Google Cloud's Agent Platform](/docs/en/google
+16 −16 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
third-party-integrations
±changed
+20−20
claude-codechanged
third-party-integrations
**Claude for Teams** is self-service and includes collaboration features, admin tools, SSO, billing management, and [server-managed settings](/docs/en/server-managed-settings) for
**Claude for Teams** is self-service and includes collaboration features, admin tools, SSO, billing management, and [server-managed settings](/docs/en/server-managed-settings.md) f
The deployment options compared below cover where model inference runs. To run Claude Code [cloud sessions](/docs/en/claude-code-on-the-web) on compute your organization operates,
The deployment options compared below cover where model inference runs. To run Claude Code [cloud sessions](/docs/en/claude-code-on-the-web.md) on compute your organization operate
<td>API key or a [Console sign-in without one](/docs/en/authentication#sign-in-without-an-api-key)</td>
+20 −20 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/secure-deployment
±changed
+9−9
claude-codechanged
agent-sdk/secure-deployment
Claude Code includes several security features that address common concerns. See the [security documentation](/docs/en/security) for full details.
* **Permissions system**: Every tool and bash command can be configured to allow, block, or prompt the user for approval. Use glob patterns to create rules like "allow all npm comm
* **Command parsing for permissions**: Before executing bash commands, Claude Code parses them into an AST and matches the result against your permission rules. Commands that canno
Claude Code includes several security features that address common concerns. See the [security documentation](/docs/en/security.md) for full details.
+9 −9 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/quickstart
±changed
+16−16
claude-codechanged
agent-sdk/quickstart
> * If pip installs the Python SDK's source distribution instead of a platform wheel, for example on ARM64 Windows, no binary is bundled. [Install Claude Code natively](/docs/en/se
> * The TypeScript SDK installs its binary through npm optional dependencies, so an install that skips them, for example `npm ci --omit=optional`, gets no binary even on a supporte
> * If pip installs the Python SDK's source distribution instead of a platform wheel, for example on ARM64 Windows, no binary is bundled. [Install Claude Code natively](/docs/en/se
> * The TypeScript SDK installs its binary through npm optional dependencies, so an install that skips them, for example `npm ci --omit=optional`, gets no binary even on a supporte
See the setup guides for [Amazon Bedrock](/docs/en/amazon-bedrock), [Claude Platform on AWS](/docs/en/claude-platform-on-aws), [Google Cloud's Agent Platform](/docs/en/google-verte
+16 −16 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
third-party-integrations
±changed
+7−75
claude-codechanged
third-party-integrations
export const ContactSalesCard = ({surface}) => {
const utm = content => `utm_source=claude_code&utm_medium=docs&utm_content=${surface}_${content}`;
const iconArrowRight = (size = 13) => <svg width={size} height={size} viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5" strokeLinecap="round" strokeLinejoin
<line x1="5" y1="12" x2="19" y2="12" />
<polyline points="12 5 19 12 12 19" />
+7 −75 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/secure-deployment
±changed
+24−24
claude-codechanged
agent-sdk/secure-deployment
<Info>
In all of these configurations, Claude Code (or your Agent SDK application) runs inside the isolation boundary (the sandbox, container, or VM). The security controls described be
</Info>
> [!NOTE]
>
+24 −24 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
agent-sdk/quickstart
±changed
+229−245
claude-codechanged
agent-sdk/quickstart
<Steps>
<Step title="Create a project folder">
Create a new directory for this quickstart:
```bash theme={null}
+229 −245 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
troubleshoot-install
±changed
+1−1
claude-codechanged
troubleshoot-install
When login fails and the cause isn't obvious, a clean re-authentication resolves most cases:
When login fails and the cause isn't clear, a clean re-authentication resolves most cases:
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
third-party-integrations
±changed
+3−3
claude-codechanged
third-party-integrations
We strongly recommend investing in documentation so that Claude Code understands your codebase. Organizations can deploy CLAUDE.md files at multiple levels. See [where CLAUDE.md fi
Invest in documentation so that Claude Code understands your codebase. Organizations can deploy CLAUDE.md files at multiple levels. See [where CLAUDE.md files can live](/docs/en/me
If you have a custom development environment, we find that creating a "one click" way to install Claude Code is key to growing adoption across an organization.
If you have a custom development environment, creating a "one click" way to install Claude Code is key to growing adoption across an organization.
MCP is a great way to give Claude Code more information, such as connecting to ticket management systems or error logs. We recommend that one central team configures MCP servers an
+3 −3 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
Three bundled skills work together to launch your app and confirm changes against the running app instead of just tests:
Three bundled skills work together to launch your app and confirm changes against the running app instead of tests alone:
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
self-hosted-environments-deploy
±changed
+3−3
claude-codechanged
self-hosted-environments-deploy
Don't bake long-lived or broadly-scoped push credentials into a shared runner image: a credential in the image is available to every session the image runs, whoever started it. Ins
Don't bake long-lived or broadly scoped push credentials into a shared runner image: a credential in the image is available to every session the image runs, whoever started it. Ins
* A `credential.helper` that returns a minimally-scoped token
* `GIT_SSH_COMMAND` pointing at a narrowly-scoped key
* A `credential.helper` that returns a minimally scoped token
+3 −3 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
* [Security](/docs/en/security): comprehensive security features and best practices
* [Security](/docs/en/security): security features and best practices
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
quickstart
±changed
+8−8
claude-codechanged
quickstart
```bash theme={null}
```bash theme={null} theme={null} theme={null} theme={null}
```powershell theme={null}
```powershell theme={null} theme={null} theme={null} theme={null}
```batch theme={null}
+8 −8 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
memory
±changed
+2−2
claude-codechanged
memory
| **User instructions** | `~/.claude/CLAUDE.md` | Personal preferences for all projects | Code styling preferences, personal tooling shortcuts | Just you (all projects) |
| **User instructions** | `~/.claude/CLAUDE.md` | Personal preferences for all projects | Code styling preferences, personal tooling shortcuts | Only you (all projects) |
| **Local instructions** | `./CLAUDE.local.md` | Personal project-specific preferences; add to `.gitignore` | Your sandbox URLs, preferred test data | Just you (current project) |
| **Local instructions** | `./CLAUDE.local.md` | Personal project-specific preferences; add to `.gitignore` | Your sandbox URLs, preferred test data | Only you (current project) |
+2 −2 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
large-codebases
±changed
+1−1
claude-codechanged
large-codebases
When you start Claude from `packages/api/`, it can read and write files within that directory. If a task requires changes across packages, such as updating a shared type that both
When you start Claude from `packages/api/`, it can read and write files within that directory. If a task requires changes across packages, such as updating a shared type that both
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
hooks
±changed
+2−2
claude-codechanged
hooks
Setup hooks have access to `CLAUDE_ENV_FILE`. Variables written to that file persist into subsequent Bash commands for the session, just as in [SessionStart hooks](#persist-environ
Setup hooks have access to `CLAUDE_ENV_FILE`. Variables written to that file persist into subsequent Bash commands for the session, as in [SessionStart hooks](#persist-environment-
Fires when a `CLAUDE.md` or `.claude/rules/*.md` file is loaded into context. This event fires at session start for eagerly-loaded files and again later when files are lazily loade
Fires when a `CLAUDE.md` or `.claude/rules/*.md` file is loaded into context. This event fires at session start for eagerly loaded files and again later when files are lazily loade
+2 −2 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
The following example uses [jq](https://jqlang.org/) to filter for text deltas and display just the streaming text. The `-r` flag outputs raw strings (no quotes) and `-j` joins wit
The following example uses [jq](https://jqlang.org/) to filter for text deltas and display only the streaming text. The `-r` flag outputs raw strings (no quotes) and `-j` joins wit
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
How a session knows the work is actually done rather than just plausible. You give Claude a check it can run, such as a test suite, a build, or a screenshot comparison, and Claude
How a session knows the work is actually done instead of accepting a result that looks plausible. You give Claude a check it can run, such as a test suite, a build, or a screenshot
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
github-actions
±changed
+1−1
claude-codechanged
github-actions
For comprehensive security guidance including permissions and authentication, see the [Claude Code Action security documentation](https://github.com/anthropics/claude-code-action/b
For security guidance including permissions and authentication, see the [Claude Code Action security documentation](https://github.com/anthropics/claude-code-action/blob/main/docs/
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
desktop-scheduled-tasks
±changed
+1−1
claude-codechanged
desktop-scheduled-tasks
Keep this in mind when writing prompts. A task scheduled for 9am might run at 11pm if your computer was asleep all day. If timing matters, add guardrails to the prompt itself, for
Keep this in mind when writing prompts. A task scheduled for 9am might run at 11pm if your computer was asleep all day. If timing matters, add guardrails to the prompt itself, for
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
deep-links
±changed
+1−1
claude-codechanged
deep-links
Some Markdown renderers only allow `http` and `https` links and strip other URL schemes. GitHub does this in READMEs, issues, pull requests, and wikis: `[label](claude-cli://...)`
Some Markdown renderers only allow `http` and `https` links and strip other URL schemes. GitHub does this in READMEs, issues, pull requests, and wikis: `[label](claude-cli://...)`
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
* **Clear between tasks**: Use `/clear` to start fresh when switching to unrelated work. Stale context wastes tokens on every subsequent message. Use `/rename` before clearing so y
* **Clear between tasks**: Use `/clear` to start fresh when switching to unrelated work. Stale context wastes tokens on every subsequent message. Use `/rename` before clearing so y
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
For comprehensive coverage, ask Claude to identify edge cases you might have missed. Claude can analyze your code paths and suggest tests for error conditions, boundary values, and
To improve coverage, ask Claude to identify edge cases you might have missed. Claude can analyze your code paths and suggest tests for error conditions, boundary values, and unexpe
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
best-practices
±changed
+2−2
claude-codechanged
best-practices
* **Give URLs** for documentation and API references. Use `/permissions` to allowlist frequently-used domains.
* **Give URLs** for documentation and API references. Use `/permissions` to allowlist frequently used domains.
| Common gotchas or non-obvious behaviors | Self-evident practices like "write clean code" |
| Common gotchas or behaviors that aren't self-evident | Self-evident practices like "write clean code" |
+2 −2 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
For a comprehensive guide on using hooks with examples and common patterns, see the [Hooks guide](/docs/en/agent-sdk/hooks).
For a guide on using hooks with examples and common patterns, see the [Hooks guide](/docs/en/agent-sdk/hooks).
Powerful search tool built on ripgrep with regex support.
Search tool built on ripgrep with regex support.
+2 −2 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/subagents
±changed
+1−1
claude-codechanged
agent-sdk/subagents
* [Claude Code subagents](/docs/en/sub-agents): comprehensive subagent documentation including filesystem-based definitions
* [Claude Code subagents](/docs/en/sub-agents): subagent documentation including filesystem-based definitions
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/structured-outputs
±changed
+1−1
claude-codechanged
agent-sdk/structured-outputs
For full type safety, use [Zod](#type-safe-schemas-with-zod-and-pydantic) (TypeScript) or [Pydantic](#type-safe-schemas-with-zod-and-pydantic) (Python) to define your schema and ge
For full type safety, use [Zod](#type-safe-schemas-with-zod-and-pydantic) (TypeScript) or [Pydantic](#type-safe-schemas-with-zod-and-pydantic) (Python) to define your schema and ge
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/skills
±changed
+1−1
claude-codechanged
agent-sdk/skills
For comprehensive information about skills, including benefits, architecture, and authoring guidelines, see the [Agent Skills overview](https://platform.claude.com/docs/en/agents-a
For more information about skills, including benefits, architecture, and authoring guidelines, see the [Agent Skills overview](https://platform.claude.com/docs/en/agents-and-tools/
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/secure-deployment
±changed
+1−1
claude-codechanged
agent-sdk/secure-deployment
Note that not all programs respect `HTTP_PROXY`/`HTTPS_PROXY`. Most tools (curl, pip, npm, git) do, but some may bypass these variables and connect directly. For example, Node.js `
Note that not all programs respect `HTTP_PROXY`/`HTTPS_PROXY`. Most tools (curl, pip, npm, git) do, but some may bypass these variables and connect directly. For example, Node.js `
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/quickstart
±changed
+1−1
claude-codechanged
agent-sdk/quickstart
Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude A
Unless previously approved, Anthropic does not allow third party developers to offer claude.ai login or rate limits for their products, including agents built on the Claude A
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
* `input`: Strongly-typed hook input with discriminated unions based on `hook_event_name` (see [`HookInput`](#hookinput))
* `input`: Strongly typed hook input with discriminated unions based on `hook_event_name` (see [`HookInput`](#hookinput))
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 UTC
claude-code
agent-sdk/migration-guide
±changed
+1−1
claude-codechanged
agent-sdk/migration-guide
The Claude Code SDK has been renamed to the **Claude Agent SDK** and its documentation has been reorganized. This change reflects the SDK's broader capabilities for building AI age
The Claude Code SDK has been renamed to the **Claude Agent SDK** and its documentation has been reorganized. This change reflects the SDK's broader capabilities for building AI age
+1 −1 lines
Upstream edited 6 Oct 2026 03:21 UTC Recorded here 6 Oct 2026 03:37 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 6 Oct 2026 03:07 UTC
claude-docs
cowork/monitoring
±changed
+10−4
claude-docschanged
cowork/monitoring
| Not set, on a first-party deployment | User prompt text, model response text, and tool inputs |
| Not set, on a first-party deployment | User prompt text, model response text, and the [`toolDetails` content](#security-and-privacy) |
Metadata includes `workspace.host_paths` and, on first-party deployments, `user.email`. The key doesn't control either one. See [Security and privacy](#security-and-privacy).
| `workspace.host_paths` | Host workspace directories selected in the desktop app (string array) |
+10 −4 lines
Upstream edited 6 Oct 2026 03:05 UTC Recorded here 6 Oct 2026 03:07 UTC
claude-docs
cowork/hipaa-setup
±changed
+9−9
claude-docschanged
cowork/hipaa-setup
This page is for the IT or security administrator who manages the macOS and Windows computers where members run [Cowork](/docs/cowork/overview) in Claude Desktop. Other readers sta
This page is for the IT or security administrator who manages the macOS and Windows computers where members run [Cowork](/docs/cowork/overview.md) in Claude Desktop. Other readers
* **Administrators of a third-party deployment**: see [Legal and compliance](/docs/third-party/claude-desktop/legal). The HIPAA configuration doesn't apply to [Claude Desktop on th
* **Administrators of a third-party deployment**: see [Legal and compliance](/docs/third-party/claude-desktop/legal.md). The HIPAA configuration doesn't apply to [Claude Desktop on
A Claude Desktop policy is a set of settings that your device management tool installs on each computer, as a configuration profile on macOS or as registry values on Windows. You c
+9 −9 lines
Upstream edited 6 Oct 2026 03:05 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-docs
cowork/hipaa-setup
±changed
+80−86
claude-docschanged
cowork/hipaa-setup
<Note>
"(local mode)" means a local session, not a session that runs in the cloud. Local sessions run in one of these places:
* Claude Code in the terminal
* Claude Code in the Code tab of Claude Desktop
+80 −86 lines
Upstream edited 6 Oct 2026 03:05 UTC Recorded here 20 Oct 2026 18:07 UTC
claude-docs
cowork/hipaa-setup
±changed
+5−5
claude-docschanged
cowork/hipaa-setup
Allow the hosts in this table through your proxy and firewall, over HTTPS on port 443. The table lists the hosts that the tasks on this page depend on, and leaves out the rest.
Allow the Anthropic hosts listed in [Desktop network access requirements](https://code.claude.com/docs/en/desktop#network-access-requirements) through your proxy and firewall. Clau
[Desktop network access requirements](https://code.claude.com/docs/en/desktop#network-access-requirements) lists the Anthropic hosts to allow for Claude Desktop.
If **All domains** is still selected when your organization applies the HIPAA configuration, the VM reaches only `anthropic.com` and `claude.com` hosts, plus your OpenTelemetry col
+5 −5 lines
Upstream edited 6 Oct 2026 03:05 UTC Recorded here 6 Oct 2026 03:07 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertif
By default, Claude Code trusts both its bundled Mozilla CA certificates and your operating system's certificate store. Reading the OS store requires a runtime with `tls.getCACertif
+1 −1 lines
Upstream edited 6 Oct 2026 02:44 UTC Recorded here 6 Oct 2026 03:07 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load)
Built-in plugins store their options under the same key with an `@builtin` suffix. For example, the [**Project instructions**](/docs/en/memory#choose-which-instruction-files-load)
+1 −1 lines
Upstream edited 6 Oct 2026 02:42 UTC Recorded here 6 Oct 2026 03:07 UTC
claude-code
memory
±changed
+5−3
claude-codechanged
memory
You can also set the value in a settings file instead of `/config`. Add it under the built-in `agents-md` plugin's ID in [`pluginConfigs`](/docs/en/settings-reference#pluginconfigs
You can also set the value in a settings file instead of `/config`. Add it to [`pluginConfigs`](/docs/en/settings-reference#pluginconfigs) under `cc-plugin-agents-md@builtin`, the
"agents-md@builtin": {
"cc-plugin-agents-md@builtin": {
Before v2.1.285, the plugin's ID was `agents-md@builtin`, and Claude Code ignored an entry under `cc-plugin-agents-md@builtin`. If earlier versions also read your settings file, us
+5 −3 lines
Upstream edited 6 Oct 2026 02:42 UTC Recorded here 6 Oct 2026 03:07 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 6 Oct 2026 02:07 UTC
claude-code
platforms
±changed
+3−3
claude-codechanged
platforms
| [Slack](/docs/en/slack) | Responds to `@Claude` mentions in your channels | Turning bug reports into pull requests from team chat |
| [Slack](/docs/en/slack) | Responds to `@Claude` mentions in your channels, under your own account | Turning bug reports into pull requests from team chat on Pro and Max plans |
| [Slack](/docs/en/slack) | Mention `@Claude` in a team channel | Anthropic cloud | [Install the Slack app](/docs/en/slack#setting-up-claude-code-in-slack) with [Claude Code on the
| [Slack](/docs/en/slack) | Mention `@Claude` in a team channel | Anthropic cloud | [Install the Slack app](/docs/en/slack#setting-up-claude-code-in-slack) with [Claude Code on the
* [Slack](/docs/en/slack): send tasks from team chat, get PRs back
+3 −3 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 6 Oct 2026 02:07 UTC
claude-code
feature-availability
±changed
+2−1
claude-codechanged
feature-availability
* [Cloud sessions](/docs/en/claude-code-on-the-web), Claude Code on mobile, and [Claude Code in Slack](/docs/en/slack)
* [Cloud sessions](/docs/en/claude-code-on-the-web) and Claude Code on mobile
* [Claude Code in Slack](/docs/en/slack): Pro and Max plans
+2 −1 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 6 Oct 2026 02:07 UTC
claude-code
slack
±changed
+6−6
claude-codechanged
slack
| Cloud sessions | [Cloud sessions](/docs/en/claude-code-on-the-web.md) are enabled for your account |
| Cloud sessions | [Cloud sessions](https://code.claude.com/docs/en/claude-code-on-the-web.md) are enabled for your account |
automatically visible to the organization. See [cloud session sharing](/docs/en/claude-code-on-the-web.md#share-sessions)
automatically visible to the organization. See [cloud session sharing](https://code.claude.com/docs/en/claude-code-on-the-web.md#share-sessions)
This error means your Claude account has no cloud environment yet. Sign in at [claude.ai/code](https://claude.ai/code) once with the same account you connected to Slack and finish
+6 −6 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
slack
±changed
+6−6
claude-codechanged
slack
| Cloud sessions | [Cloud sessions](/docs/en/claude-code-on-the-web) are enabled for your account |
| Cloud sessions | [Cloud sessions](/docs/en/claude-code-on-the-web.md) are enabled for your account |
automatically visible to the organization. See [cloud session sharing](/docs/en/claude-code-on-the-web#share-sessions)
automatically visible to the organization. See [cloud session sharing](/docs/en/claude-code-on-the-web.md#share-sessions)
This error means your Claude account has no cloud environment yet. Sign in at [claude.ai/code](https://claude.ai/code) once with the same account you connected to Slack and finish
+6 −6 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
slack
±changed
+71−79
claude-codechanged
slack
<Warning>
This page documents the earlier Claude Code in Slack, which runs each session under an individual user's account. It answers channel @mentions only from Pro and Max accounts, and
* **Pro and Max plans:** Claude Tag isn't available on individual plans, so this page remains the setup path in a workspace that isn't connected to Claude Tag.
* **Team and Enterprise plans:** your existing Slack app and @Claude handle stay. [Set up Claude Tag](https://claude.com/docs/claude-tag/overview) for a new workspace; to move on
+71 −79 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
slack
±changed
+28−8
claude-codechanged
slack
> Delegate coding tasks directly from your Slack workspace. Anthropic is retiring this earlier version for Team and Enterprise workspaces in favor of Claude Tag; it remains the set
> Delegate coding tasks from Slack. This earlier version answers channel mentions only from Pro and Max accounts in workspaces not connected to Claude Tag.
This page documents the earlier Claude Code in Slack, which runs each session under an individual user's account.
* **Team and Enterprise plans:** Anthropic is retiring this version in favor of [Claude Tag](https://claude.com/product/tag), which runs @Claude as your organization's shared ide
+28 −8 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 6 Oct 2026 02:07 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
| [Slack](/docs/en/slack) | Mention `@Claude` in a team channel | Anthropic cloud | [Install the Slack app](/docs/en/slack#setting-up-claude-code-in-slack) with [Claude Code on the
| [Slack](/docs/en/slack) | Mention `@Claude` in a team channel | Anthropic cloud | [Install the Slack app](/docs/en/slack#setting-up-claude-code-in-slack) with [Claude Code on the
+1 −1 lines
Upstream edited 6 Oct 2026 01:49 UTC Recorded here 6 Oct 2026 02:07 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 6 Oct 2026 01:37 UTC
claude-code
permission-modes
±changed
+6−1
claude-codechanged
permission-modes
* `.claude`, except for `.claude/worktrees` where Claude stores its own git worktrees, and except for the markdown files in Claude's own [auto memory](/docs/en/memory#storage-locat
* `.claude`, with a few exceptions, such as:
* Claude's own git worktrees under `.claude/worktrees/`
* The current session's own plan files in `~/.claude/plans/`, or in the [`plansDirectory`](/docs/en/settings-reference#plansdirectory) you set
* A [background session](/docs/en/agent-view#where-state-is-stored)'s own scratch directory at `~/.claude/jobs/<id>/tmp/`
+6 −1 lines
Upstream edited 6 Oct 2026 01:27 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
channels-reference
±changed
+15−15
claude-codechanged
channels-reference
> Channels are in [research preview](/docs/en/channels.md#research-preview). Team and Enterprise organizations must [explicitly enable them](/docs/en/channels.md#enterprise-control
> Channels are in [research preview](https://code.claude.com/docs/en/channels.md#research-preview). Team and Enterprise organizations must [explicitly enable them](https://code.cla
To use an existing channel instead of building one, see [Channels](/docs/en/channels.md). Telegram, Discord, iMessage, and fakechat are included in the research preview.
To use an existing channel instead of building one, see [Channels](https://code.claude.com/docs/en/channels.md). Telegram, Discord, iMessage, and fakechat are included in the resea
During the research preview, custom channels aren't on the [approved allowlist](/docs/en/channels.md#supported-channels). Use `--dangerously-load-development-channels` to test loca
+15 −15 lines
Upstream edited 6 Oct 2026 01:20 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
channels-reference
±changed
+13−13
claude-codechanged
channels-reference
> Channels are in [research preview](/docs/en/channels#research-preview). Team and Enterprise organizations must [explicitly enable them](/docs/en/channels#enterprise-controls).
> Channels are in [research preview](/docs/en/channels.md#research-preview). Team and Enterprise organizations must [explicitly enable them](/docs/en/channels.md#enterprise-control
To use an existing channel instead of building one, see [Channels](/docs/en/channels). Telegram, Discord, iMessage, and fakechat are included in the research preview.
To use an existing channel instead of building one, see [Channels](/docs/en/channels.md). Telegram, Discord, iMessage, and fakechat are included in the research preview.
During the research preview, custom channels aren't on the [approved allowlist](/docs/en/channels#supported-channels). Use `--dangerously-load-development-channels` to test locally
+13 −13 lines
Upstream edited 6 Oct 2026 01:20 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
channels-reference
±changed
+253−263
claude-codechanged
channels-reference
<Note>
Channels are in [research preview](/docs/en/channels#research-preview). Team and Enterprise organizations must [explicitly enable them](/docs/en/channels#enterprise-controls).
</Note>
> [!NOTE]
>
+253 −263 lines
Upstream edited 6 Oct 2026 01:20 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
channels-reference
±changed
+2−0
claude-codechanged
channels-reference
Run the development flag in an interactive session, where Claude Code can show the confirmation prompt. If you pass it in non-interactive mode with `-p` or through the Agent SDK, C
+2 −0 lines
Upstream edited 6 Oct 2026 01:20 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
agent-view
±changed
+15−12
claude-codechanged
agent-view
✢ playtest level 3 run 12 · all checkpoints cleared in 4m
✢ playtest level 3 all checkpoints cleared ×12 in 4m
✻ title screen result: menu, options, and credits done 9m
∙ sound effects result: 14 SFX exported to assets/audio 4h
✻ title screen menu, options, and credits done 9m
+15 −12 lines
Upstream edited 6 Oct 2026 01:16 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
checkpointing
±changed
+3−3
claude-codechanged
checkpointing
The rewind menu lists each prompt you sent during the session, except [messages that joined a running turn](#messages-sent-mid-turn-not-checkpointed). Select the point you want to
The rewind menu lists the prompts you sent during the session. Select the point you want to act on, then choose an action:
When a message you [queue while Claude works](/docs/en/interactive-mode#queue-messages-while-claude-works) reaches Claude within the running turn, it joins that turn instead of sta
When a message you [queue while Claude works](/docs/en/interactive-mode#queue-messages-while-claude-works) reaches Claude within the running turn, it joins that turn instead of sta
To remove such a message, or undo the edits Claude made after it, rewind to the prompt that started the turn. That rewinds the whole turn, including the work Claude did before your
+3 −3 lines
Upstream edited 6 Oct 2026 01:11 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
workflows
±changed
+6−6
claude-codechanged
workflows
The run starts in the background. Run `/workflows`, use the arrow keys to select the run, and press Enter to open its progress view:
The run starts in the background. Run `/workflows` to open its progress view:
The view shows each phase with its agent count, token total, and elapsed time. Drill into any phase to see its agents and what each one found. See [Watch the run](#watch-the-ru
If `/workflows` shows a list of runs instead, select the run you just started and press Enter. The view shows each phase with its agent count. Drill into any phase to see its a
Workflows run in the background, so the session stays responsive while agents work. Run `/workflows` at any time to list running and completed workflows, then select one to open it
+6 −6 lines
Upstream edited 6 Oct 2026 01:09 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
tools-reference
±changed
+6−6
claude-codechanged
tools-reference
| `ReportFindings` | Reports code-review findings as a structured list, with a file, summary, and failure scenario per finding, so Claude Code can render them instead of printing t
| `ReportFindings` | Reports code-review findings as a structured list, with a file, summary, and failure scenario per finding, so Claude Code can render them instead of printing t
| `SendUserFile` | Sends files from the session to you with an optional caption, so a generated report, diagram, screenshot, or built artifact reaches your device instead of only b
| `SendUserFile` | Sends files from the session to you with an optional caption, so a generated report, diagram, screenshot, or built artifact reaches your device instead of only b
| `TaskStop` | Stops a running background task by ID. It also accepts an [agent-team teammate](/docs/en/agent-teams) or a named background agent by agent ID or name. Before v2.1.19
+6 −6 lines
Upstream edited 6 Oct 2026 01:08 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
statusline
±changed
+1−1
claude-codechanged
statusline
| `prompt_id` | UUID identifying the user prompt currently being processed. Matches the [`prompt.id` attribute on OpenTelemetry events](/docs/en/monitoring-usage#event-correlation-
| `prompt_id` | UUID identifying the user prompt currently being processed. Matches the [`prompt.id` attribute on OpenTelemetry events](/docs/en/monitoring-usage#event-correlation-
+1 −1 lines
Upstream edited 6 Oct 2026 01:08 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
monitoring-usage
±changed
+5−5
claude-codechanged
monitoring-usage
| `OTEL_LOG_ASSISTANT_RESPONSES` | Enable logging of assistant response text on `assistant_response` events (default: disabled). When unset, falls back to the value of `OTEL_LOG_US
| `OTEL_LOG_ASSISTANT_RESPONSES` | Enable logging of assistant response text on `assistant_response` events (default: disabled). When unset, falls back to the value of `OTEL_LOG_US
Logged after each API request that returns text content from the model. Only the response's text blocks are included; thinking blocks and tool-use blocks are excluded. Requires Cla
Logged after each API request that returns text content from the model. Only the response's text blocks are included; thinking blocks and tool-use blocks are excluded.
* `host_owned_mcp`: `true` when the SDK host manages this plugin's MCP connections and Claude Code skipped reading the plugin's MCP server configuration, `false` otherwise. Require
+5 −5 lines
Upstream edited 6 Oct 2026 01:08 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
interactive-mode
±changed
+3−3
claude-codechanged
interactive-mode
* On macOS and Linux, Claude Code stops your running background tasks when the operating system reports critical memory pressure, provided the session has been idle for at least 30
* On macOS and Linux, Claude Code stops your running background tasks when the operating system reports critical memory pressure, provided the session has been idle for at least 30
* Supports live file path autocomplete as of v2.1.193 on all platforms: type a token containing a forward slash, such as `./src/` or `~/`, to see a dropdown of matching files and d
* Supports live file path autocomplete: type a token containing a forward slash, such as `./src/` or `~/`, to see a dropdown of matching files and directories, then press `Tab` to
Claude responds to the command output automatically once it lands in the transcript, so you can run `! npm test` and get an explanation of the failures without a second prompt. The
+3 −3 lines
Upstream edited 6 Oct 2026 01:08 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
| `prompt_id` | UUID identifying the user prompt currently being processed. Matches the [`prompt.id` attribute on OpenTelemetry events](/docs/en/monitoring-usage#event-correlation-
| `prompt_id` | UUID identifying the user prompt currently being processed. Matches the [`prompt.id` attribute on OpenTelemetry events](/docs/en/monitoring-usage#event-correlation-
+1 −1 lines
Upstream edited 6 Oct 2026 01:08 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+34−34
claude-codechanged
agent-sdk/claude-code-features
The setting sources option ([`setting_sources`](/docs/en/agent-sdk/python#claudeagentoptions) in Python, [`settingSources`](/docs/en/agent-sdk/typescript#settingsource) in TypeScri
The setting sources option ([`setting_sources`](https://code.claude.com/docs/en/agent-sdk/python#claudeagentoptions) in Python, [`settingSources`](https://code.claude.com/docs/en/a
Each source loads settings from a specific location, where `<cwd>` is the working directory you pass via the `cwd` option, or the process's current directory if unset. For the full
Each source loads settings from a specific location, where `<cwd>` is the working directory you pass via the `cwd` option, or the process's current directory if unset. For the full
| `"project"` | Project `settings.json` and hooks; project CLAUDE.md and `.claude/rules/*.md`; project skills, commands, and subagents | `<cwd>/.claude/` for `settings.json` and ho
+34 −34 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
agent-sdk/claude-code-features
±changed
+31−31
claude-codechanged
agent-sdk/claude-code-features
| Managed policy settings | Endpoint-managed policy, such as an MDM plist, registry policy, or managed settings file, loads from the host. [Server-managed settings](/docs/en/server
| Managed policy settings | Endpoint-managed policy, such as an MDM plist, registry policy, or managed settings file, loads from the host. [Server-managed settings](/docs/en/server
| [claude.ai MCP connectors](/docs/en/mcp#use-mcp-servers-from-claude-ai) | Loaded when the session authenticates with your claude.ai login. Not loaded when `CLAUDE_CODE_OAUTH_TOKE
| [`sandbox.credentials`](/docs/en/sandboxing#protect-credentials) `deny` entries and file `mask` entries in `~/.claude/settings.json` | When the [command sandbox](/docs/en/sandbox
| [claude.ai MCP connectors](/docs/en/mcp.md#use-mcp-servers-from-claude-ai) | Loaded when the session authenticates with your claude.ai login. Not loaded when `CLAUDE_CODE_OAUTH_T
+31 −31 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/claude-code-features
±changed
+182−188
claude-codechanged
agent-sdk/claude-code-features
<CodeGroup>
```python Python theme={null}
from claude_agent_sdk import query, ClaudeAgentOptions, AssistantMessage, ResultMessage
import asyncio
+182 −188 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
prompt-caching
±changed
+1−1
claude-codechanged
prompt-caching
[Nested CLAUDE.md files in subdirectories](/docs/en/memory) and [rules with `paths:` frontmatter](/docs/en/memory#path-specific-rules) load later, when Claude first reads a matchin
[Nested CLAUDE.md files in subdirectories](/docs/en/memory) and [rules with `paths:` frontmatter](/docs/en/memory#path-specific-rules) load later, on demand. Editing one yourself b
+1 −1 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
memory
±changed
+4−4
claude-codechanged
memory
CLAUDE.md and CLAUDE.local.md files in the directory hierarchy above the working directory are loaded at launch. Files in subdirectories load on demand when Claude reads files in t
CLAUDE.md and CLAUDE.local.md files in the directory hierarchy above the working directory are loaded at launch. Files in subdirectories load on demand. See [How CLAUDE.md files lo
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, they are included when Clau
Claude also discovers `CLAUDE.md` and `CLAUDE.local.md` files in subdirectories under your current working directory. Instead of loading them at launch, Claude Code includes them w
| `managed-only` | Only your organization's managed `CLAUDE.md` and [auto memory](#auto-memory) at launch. Your project, local, and user `CLAUDE.md` files, your `.claude/rules/` fi
+4 −4 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
large-codebases
±changed
+4−4
claude-codechanged
large-codebases
| Repository root | Every file | Root only; subdirectory files load on demand when Claude reads there | Tasks span multiple packages or subsystems |
| Repository root | Every file | Root only; subdirectory files load on demand | Tasks span multiple packages or subsystems |
Claude Code loads every [CLAUDE.md](/docs/en/memory) file from your working directory and every parent directory at launch, then loads each subdirectory's file on demand when it re
Claude Code loads every [CLAUDE.md](/docs/en/memory) file from your working directory and every parent directory at launch, then loads each subdirectory's file [on demand](/docs/en
| Per-directory `CLAUDE.md` | Inside the directory, alongside its code | At launch when started from that directory, or on demand when Claude reads a file there | Directory owners
+4 −4 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
context-window
±changed
+2−2
claude-codechanged
context-window
| Rules with `paths:` frontmatter | Claude Code reloads them as Claude reads files they match |
| Nested CLAUDE.md in subdirectories | Claude Code reloads them as Claude reads files in that subdirectory |
| Rules with `paths:` frontmatter | Claude Code reloads them [on demand](/docs/en/memory#path-specific-rules) |
| Nested CLAUDE.md in subdirectories | Claude Code reloads them [on demand](/docs/en/memory#how-claude-md-files-load) |
+2 −2 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 6 Oct 2026 01:37 UTC
claude-code
agent-sdk/claude-code-features
±changed
+1−1
claude-codechanged
agent-sdk/claude-code-features
| Project (child dirs) | `CLAUDE.md` files in subdirectories of `cwd` | `settingSources` includes `"project"`, loaded on demand when the agent reads a file in that subtree |
| Project (child dirs) | `CLAUDE.md` files in subdirectories of `cwd` | `settingSources` includes `"project"`, loaded [on demand](/docs/en/memory#how-claude-md-files-load) |
+1 −1 lines
Upstream edited 6 Oct 2026 01:07 UTC Recorded here 6 Oct 2026 01:37 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 6 Oct 2026 01:07 UTC
claude-code
desktop-quickstart
±changed
+1−1
claude-codechanged
desktop-quickstart
**Review changes before committing.** After Claude edits files, a `+12 -1` indicator appears. Click it to open the [diff view](/docs/en/desktop#review-changes-with-diff-view), revi
**Review changes before committing.** After Claude edits files, a `+12 -1` indicator appears. Click it to open the [diff view](/docs/en/desktop#review-changes-with-diff-view), revi
+1 −1 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
desktop
±changed
+30−24
claude-codechanged
desktop
* Start or stop servers from the server dropdown in the session toolbar
* Persist cookies and local storage across server restarts by selecting **Persist sessions** in the dropdown, so you don't have to re-login during development
* Edit the server configuration or stop all servers at once
* Start or stop servers, or stop them all at once, from the **Dev servers** menu in the Browser pane's header
* Choose whether the Browser keeps cookies after you quit the app with **Keep cookies** in the Browser pane's **⋮** menu, so you don't have to sign in again during development
+30 −24 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
code-review
±changed
+1−1
claude-codechanged
code-review
In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop), Claude reports the review's findings through the [`ReportFindings` tool](/docs/e
In a host application that requests the findings list, such as the [desktop app](/docs/en/desktop#review-your-code), Claude reports the review's findings through the [`ReportFindin
+1 −1 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
desktop-ios-simulator
±changed
+1−1
claude-codechanged
desktop-ios-simulator
You can also open the simulator pane yourself. Once the session has a simulator attached or has edited Swift files, the **Views** menu in the session toolbar shows an **iOS Simulat
You can also open the simulator pane yourself. Once the session has a simulator attached or Claude Code detects iOS app work, an **iOS Simulator** button appears in the session's t
+1 −1 lines
Upstream edited 6 Oct 2026 01:05 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
fullscreen
±changed
+5−4
claude-codechanged
fullscreen
* **Click an option in a select menu** to choose it. This covers permission prompts, `/model`, `/config`, and other dialogs that show a list of options. Hovering shows a pointer on
* **Click an option in a select menu** to choose it. This covers permission prompts, `/model`, `/config`, and other dialogs that show a list of options.
* **Hold `Cmd` on macOS, or `Ctrl` on Linux and Windows, and click a URL or file path** to open it. Plain `http://` and `https://` URLs open in your browser, and file paths in tool
* **Hold `Cmd` on macOS, or `Ctrl` on Linux and Windows, and click a URL or file path** to open it. Plain `http://` and `https://` URLs open in your browser. When Claude Code handl
* On Linux and WSL, clicking a file path needs a file manager that provides the `org.freedesktop.FileManager1` D-Bus interface. Without one, nothing opens.
+5 −4 lines
Upstream edited 6 Oct 2026 01:01 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-code
keybindings
±changed
+5−5
claude-codechanged
keybindings
| `confirm:nextField` | Tab | Next field |
| `confirm:previousField` | (unbound) | Previous field |
| `confirm:nextField` | Tab | In the `/fast` dialog, turn fast mode on or off |
| `confirm:previousField` | (unbound) | Claude Code doesn't respond to this action, and a `keybindings.json` that names it remains valid |
| `confirm:cycleMode` | Shift+Tab\* | Cycle permission modes. On a file permission prompt, closes an open [comment field](/docs/en/permissions#add-a-comment-when-you-answer-a-permi
+5 −5 lines
Upstream edited 6 Oct 2026 00:59 UTC Recorded here 6 Oct 2026 01:07 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+2−1
claude-docschanged
third-party/claude-desktop/data-storage
* **Project folders are read-only.** A Chat conversation inside a project can read files in folders added to the project in Claude Desktop, under the conditions in [Project folders
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
* **The advanced file analysis sandbox writes only inside the session directory.** When [advanced file analysis](/docs/third-party/claude-desktop/chat#advanced-file-analysis) is en
+2 −1 lines
Upstream edited 6 Oct 2026 00:25 UTC Recorded here 6 Oct 2026 00:37 UTC
claude-docs
third-party/claude-desktop/chat
±changed
+16−7
claude-docschanged
third-party/claude-desktop/chat
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
| Project folders | For a conversation inside a project, read-only access to folders added to the project in Claude Desktop. Claude can list and read files in them. See [Project fo
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in an offline local sandbox against attached
| Code execution | Off by default. When you enable [advanced file analysis](#advanced-file-analysis), Claude can additionally run code in an offline local sandbox against attached
+16 −7 lines
Upstream edited 6 Oct 2026 00:25 UTC Recorded here 6 Oct 2026 00:37 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 6 Oct 2026 00:07 UTC
5 Oct 2026
200 pages
+9010 −5083 lines
claude-code
changelog
±changed
+193−0
claude-codechanged
changelog
<Update label="2.1.290" description="October 5, 2026">
* Added `serverToolUses` to the result of a mod's `turn.step` hook: the tool calls the API ran itself (the advisor), each with its id, name, input, start and end
* Added `agentId` to the `tool.check` event of plugin hooks, so a hook can tell a subagent's permission check from the main session's
* Added `ceiling` to the question and verdict a mod's `tool.check` hook reads, naming the approval an organization requires for a tool
+193 −0 lines
Upstream edited 5 Oct 2026 23:53 UTC Recorded here 6 Oct 2026 00:07 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, by invitation only, for defensive cybersecurity workflows as part of [Project
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5/migration-guide
±changed
+4−5
apichanged
models/fable-5/migration-guide
* **Safety classifiers:** Claude Fable 5 runs safety classifiers that can decline requests with `stop_reason: "refusal"`. Claude Mythos 5 does not include these classifiers. See [R
Migration is mostly drop-in. Claude Mythos 5 and Claude Fable 5 use the same [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the sam
Migration is mostly drop-in. Claude Mythos 5 and Claude Fable 5 use the same [Messages API](https://platform.claude.com/docs/en/build-with-claude/working-with-messages) and the sam
* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. Claude Fable 5 runs safety classifiers that Claude Mythos Preview an
* If you migrate to Claude Fable 5, handle `stop_reason: "refusal"` and read the `stop_details.category` field. See [Refusals and fallback](https://platform.claude.com/docs/en/buil
+4 −5 lines
Recorded here 5 Oct 2026 23:37 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
The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. Claude Mythos 5 does not include these classifiers. If your integration
The headline change for integrations: Claude Fable 5 includes safety classifiers that can decline requests. If your integration calls Claude Fable 5, plan for three changes: new re
| 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 5 Oct 2026 23:37 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
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
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5-1/overview
±changed
+1−1
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
+1 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
api
models/fable-5-1/migration-guide
±changed
+0−1
apichanged
models/fable-5-1/migration-guide
* **Safety classifiers:** Claude Fable 5.1 runs safety classifiers covering the same `stop_details` categories as Claude Fable 5. A declined request returns `stop_reason: "refusal"
+0 −1 lines
Recorded here 5 Oct 2026 23:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.