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
774 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
148 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
81 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
14 Oct 2026
440 pages
+22874 −3518 lines
api
build-with-claude/claude-platform-on-aws
±changed
+6−6
apichanged
build-with-claude/claude-platform-on-aws
implementation("com.anthropic:anthropic-java:2.71.0")
implementation("com.anthropic:anthropic-java-aws:2.71.0")
implementation("com.anthropic:anthropic-java:2.72.0")
implementation("com.anthropic:anthropic-java-aws:2.72.0")
<version>2.71.0</version>
+6 −6 lines
Recorded here 14 Oct 2026 18:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+4−4
apichanged
build-with-claude/claude-on-vertex-ai
implementation("com.anthropic:anthropic-java:2.71.0")
implementation("com.anthropic:anthropic-java-vertex:2.71.0")
implementation("com.anthropic:anthropic-java:2.72.0")
implementation("com.anthropic:anthropic-java-vertex:2.72.0")
<version>2.71.0</version>
+4 −4 lines
Recorded here 14 Oct 2026 18:07 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+4−4
apichanged
build-with-claude/claude-in-amazon-bedrock
implementation("com.anthropic:anthropic-java:2.71.0")
implementation("com.anthropic:anthropic-java-bedrock:2.71.0")
implementation("com.anthropic:anthropic-java:2.72.0")
implementation("com.anthropic:anthropic-java-bedrock:2.72.0")
<version>2.71.0</version>
+4 −4 lines
Recorded here 14 Oct 2026 18:07 UTC
api
api/claude-platform-on-aws-iam-actions
±changed
+46−10
apichanged
api/claude-platform-on-aws-iam-actions
### Telemetry destinations
| Action | Routes authorized |
| ------------------------------------------- | -------------------------------------------------------------------------------- |
| `CreateAccountTelemetryDestination` | `POST /v1/organizations/telemetry_destinations` |
+46 −10 lines
Recorded here 14 Oct 2026 18:07 UTC
api
agents-and-tools/mcp-connector
±changed
+4−4
apichanged
agents-and-tools/mcp-connector
implementation("com.anthropic:anthropic-java:2.71.0")
implementation("com.anthropic:anthropic-java-mcp:2.71.0")
implementation("com.anthropic:anthropic-java:2.72.0")
implementation("com.anthropic:anthropic-java-mcp:2.72.0")
<version>2.71.0</version>
+4 −4 lines
Recorded here 14 Oct 2026 18:07 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 14 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-quickstart
±changed
+20−20
claude-codechanged
self-hosted-environments-quickstart
> Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
> Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
A [self-hosted environment](/docs/en/self-hosted-environments) runs Claude Code [cloud sessions](/docs/en/claude-code-on-the-web) on infrastructure your organization operates, exec
A [self-hosted environment](/docs/en/self-hosted-environments) runs Claude Code [cloud sessions](/docs/en/claude-code-on-the-web.md) on infrastructure your organization operates, e
By the end you'll have an environment on the [**Cloud environments** admin page](https://claude.ai/admin-settings/cloud-environments), a runner polling for work, and a session runn
+20 −20 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-reference
±changed
+3−3
claude-codechanged
self-hosted-environments-reference
<Note>
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner](/docs/en/cloud-environments#organization-shared-environments) enables them by turning on **Al
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
self-hosted-environments-quickstart
±changed
+39−41
claude-codechanged
self-hosted-environments-quickstart
<Note>
Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
</Note>
> [!NOTE]
>
+39 −41 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
self-hosted-environments-reference
±changed
+2−2
claude-codechanged
self-hosted-environments-reference
| `--startup-timeout-min <n>` | `SELF_HOSTED_RUNNER_STARTUP_TIMEOUT_MS` | `15` | Release a session slot if the child hasn't signaled that it initialized within N minutes of spawn.
| `--startup-timeout-min <n>` | `SELF_HOSTED_RUNNER_STARTUP_TIMEOUT_MS` | `15` | Release a session slot if the child hasn't signaled on the [activity channel](/docs/en/self-hosted-
The orchestrator serves its own `/healthz` on its health port. Its endpoint always returns `200`, and the body carries a `connected` field reporting whether the most recent poll su
The orchestrator's own `/healthz`, on its health port, always returns `200`. The body carries a `connected` field reporting whether the most recent poll succeeded, plus per-state s
+2 −2 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-quickstart
±changed
+17−9
claude-codechanged
self-hosted-environments-quickstart
* A [GitHub connection](/docs/en/claude-code-on-the-web#github-authentication-options) for your organization, so developers can pick repositories when they start sessions.
* The [GitHub connector](https://claude.ai/admin-settings/connectors) turned on by an Owner, and each developer's own [GitHub connection](/docs/en/web-quickstart#connect-github), s
* A repository for the test session: a public one, or one this host can already clone by its HTTPS URL without being asked for credentials.
* A repository for the test session: a public one, or one this host can already clone by its HTTPS URL without being asked for credentials. An SSH key alone isn't enough, because t
If the runner can't create or write to the path, it exits at startup with an error naming the directory instead of registering. See [Troubleshooting](/docs/en/self-hosted-envir
+17 −9 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+13−7
claude-codechanged
self-hosted-environments-deploy
Whichever mechanism you configure must work without a prompt, because the runner's built-in clone and fetch disable the prompts that git, SSH, and Git Credential Manager would othe
<span id="git-must-work-without-a-prompt" />Whichever mechanism you configure must work without a prompt, because the runner's built-in clone and fetch disable the prompts that git
* **Connected GitHub accounts**: the person who created a user session must have connected GitHub on claude.ai, or the session [doesn't start](#creator-has-no-github-connection).
* **Connected GitHub accounts**: ask each person who creates user sessions with a repository to [connect GitHub](/docs/en/web-quickstart#connect-github). Without their own connecti
* **Host credentials for host pushes**: the runner's [`--push-outcome-on-release`](/docs/en/self-hosted-environments-reference#runner-cli-flags) push and any push your [`post-sessi
+13 −7 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-configuration
±changed
+27−10
claude-codechanged
self-hosted-environments-configuration
| `CLAUDE_CODE_REMOTE_MCP_CONFIG` | Path to a file in `CLAUDE_CONFIG_DIR` holding the MCP server definitions that Anthropic's control plane delivered for this session. If your wrap
`CCR_SESSION_ACCOUNT_EMAIL`, `CLAUDE_RUNNER_CLIENT_PLATFORM`, `CLAUDE_CODE_REMOTE_SLACK_THREAD_URL`, and `CLAUDE_CODE_REMOTE_SLACK_THREAD_TS` can each be unset. If your script uses
Wherever a shell expands the Slack thread link, take these precautions:
+27 −10 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
self-hosted-environments
±changed
+1−1
claude-codechanged
self-hosted-environments
4. If the runner stops polling, its lease lapses after about 60 seconds, and the server requeues the session for another runner within a few minutes.
4. If the runner stops polling, its lease lapses after about 60 seconds. The server can then take a few minutes and sometimes longer to requeue the session for another runner.
+1 −1 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
github-enterprise-server
±changed
+5−3
claude-codechanged
github-enterprise-server
| Cloud sessions | ?
| Cloud sessions | ?
An Owner connects your GHES instance to Claude Code once. After that, developers in your organization can use GHES repositories without any additional configuration. You need the O
An Owner connects your GHES instance to Claude Code once. You need the Owner or Primary Owner role in your Claude organization and permission to create GitHub Apps on your GHES ins
Once an Owner has connected the GHES instance, no developer-side configuration is needed. Claude Code detects your GHES hostname automatically from the git remote in your working d
+5 −3 lines
Upstream edited 14 Oct 2026 18:03 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-docs
third-party/claude-desktop/admin-console
±changed
+2−2
claude-docschanged
third-party/claude-desktop/admin-console
A write goes through the same checks as a save in the admin console. Users' apps pick up the change as described under [Configuration updates](#configuration-updates). Owners recei
A write goes through the same server checks as a save in the admin console, but the console checks more before it saves, for example that the connection to your inference provider
Setting `status` to `disabled` stops serving the configuration to users' apps, as if none had been saved. A running app isn't interrupted. At its next launch it shows a **Restart
Setting `status` to `disabled` stops serving the configuration to users' apps, as if none had been saved. A running app isn't interrupted. At its next launch it shows a **Restart
+2 −2 lines
Upstream edited 14 Oct 2026 17:58 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
scheduled-tasks
±changed
+3−1
claude-codechanged
scheduled-tasks
| `CronList` | List all scheduled tasks with their IDs, schedules, and prompts. |
| `CronList` | List scheduled tasks with their IDs, schedules, [next run times](#jitter), and prompts. |
To see when a task is next due, read the row under Claude's `CronCreate` call in your terminal. The row shows that time after the schedule, for example `next run 10:21 AM`. To chec
+3 −1 lines
Upstream edited 14 Oct 2026 17:39 UTC Recorded here 14 Oct 2026 18:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
* `body`: the decoded message body with the peer envelope stripped, byte-exact with what the model sees. Always present for a teammate message; for a cross-session peer, present on
* `body`: the decoded message body with the peer envelope stripped, byte-exact with what the model sees. Present for a single teammate message, absent when several are merged; for
+1 −1 lines
Upstream edited 14 Oct 2026 17:39 UTC Recorded here 14 Oct 2026 18:07 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 14 Oct 2026 17:37 UTC
claude-code
mcp
±changed
+2−2
claude-codechanged
mcp
Replace `YOUR_GITHUB_PAT` with your personal access token. The `claude mcp add` command saves the configuration without validating credentials, so a placeholder value is accepted h
Replace `YOUR_GITHUB_PAT` with your personal access token. The `claude mcp add` command saves the configuration without validating credentials, so a placeholder value is accepted h
To confirm the server starts, run `/mcp` and check that `db` shows `connected`.
To confirm the server starts, run `/mcp` and check that the `db` row shows a checkmark.
+2 −2 lines
Upstream edited 14 Oct 2026 17:25 UTC Recorded here 14 Oct 2026 17:37 UTC
claude-code
setup
±changed
+340−370
claude-codechanged
setup
<Tip>
Prefer a graphical interface? The [Desktop app](/docs/en/desktop-quickstart) lets you use Claude Code without the terminal. Download it for [macOS](https://claude.ai/api/desktop/
</Tip>
> [!TIP]
>
+340 −370 lines
Upstream edited 14 Oct 2026 17:25 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
setup
±changed
+5−5
claude-codechanged
setup
```bash theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```bash theme={null}
```powershell theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme=
```powershell theme={null}
```batch theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null
+5 −5 lines
Upstream edited 14 Oct 2026 17:25 UTC Recorded here 14 Oct 2026 17:37 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 14 Oct 2026 17:07 UTC
claude-code
hooks
±changed
+6−3
claude-codechanged
hooks
PreToolUse runs only when Claude calls a tool. Files you [reference with `@` in your prompt](/docs/en/common-workflows#reference-files-and-directories) are added without any tool
PreToolUse also doesn't fire for [`EndConversation`](/docs/en/tools-reference#endconversation-tool-behavior).
PreToolUse runs only when Claude calls a tool. By default, files you [reference with `@` in your prompt](/docs/en/common-workflows#reference-files-and-directories) are added with
+6 −3 lines
Upstream edited 14 Oct 2026 16:48 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
common-workflows
±changed
+2−0
claude-codechanged
common-workflows
To stop `@` references from including file contents and directory listings in your message, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS=1`](/docs/en/env-vars#variables) in your shell o
+2 −0 lines
Upstream edited 14 Oct 2026 16:48 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+1−1
claude-codechanged
agent-sdk/modifying-system-prompts
If you set `CLAUDE_CODE_DISABLE_ATTACHMENTS`, Claude Code also sends `@` file mentions as plain text instead of expanding them into file content. The list of available subagents an
If you set `CLAUDE_CODE_DISABLE_ATTACHMENTS`, Claude Code also sends `@` file mentions as plain text instead of expanding them into file content. The list of available subagents an
+1 −1 lines
Upstream edited 14 Oct 2026 16:48 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
sub-agents
±changed
+29−2
claude-codechanged
sub-agents
* **[Frontmatter fields](#supported-frontmatter-fields)**: `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `skills`, `initi
* **[Frontmatter fields](#supported-frontmatter-fields)**: `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `mcpServers`, `hooks`, `maxTurns`, `autoCompactWind
Multi-word field names use camelCase, such as `maxTurns` and `disallowedTools`, and must match the table exactly: Claude Code ignores a field it doesn't recognize without reporting
Multi-word field names use camelCase, such as `maxTurns` and `disallowedTools`, and must match the table exactly: Claude Code ignores a field it doesn't recognize without reporting
+29 −2 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
plugins/components
±changed
+1−1
claude-codechanged
plugins/components
* **Supported fields**: `name`, `description`, `model`, `effort`, `maxTurns`, `tools`, `disallowedTools`, `skills`, `memory`, `background`, `omitClaudeMd`, `isolation`, `color`, an
* **Supported fields**: `name`, `description`, `model`, `effort`, `maxTurns`, `autoCompactWindow`, `tools`, `disallowedTools`, `skills`, `memory`, `background`, `omitClaudeMd`, `is
+1 −1 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
model-config
±changed
+1−0
claude-codechanged
model-config
* **For one subagent**: see [Set the auto-compact window for one subagent](/docs/en/sub-agents#subagent-auto-compact-window).
+1 −0 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
claude-directory
±changed
+1−1
claude-codechanged
claude-directory
| `agents/*.md` | `name`, `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `maxTurns`, `skills`, `mcpServers`, `hooks`, `memory`, `background`, `effort`, `isol
| `agents/*.md` | `name`, `description`, `tools`, `disallowedTools`, `model`, `permissionMode`, `maxTurns`, `autoCompactWindow`, `skills`, `mcpServers`, `hooks`, `memory`, `backgro
+1 −1 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
agent-teams
±changed
+1−0
claude-codechanged
agent-teams
* **`autoCompactWindow`**: for an in-process teammate, Claude Code applies the definition's [`autoCompactWindow`](/docs/en/sub-agents#supported-frontmatter-fields) under [that fiel
+1 −0 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
agent-sdk/typescript
±changed
+2−0
claude-codechanged
agent-sdk/typescript
autoCompactWindow?: number;
| `autoCompactWindow` | No | Lower the [auto-compact window](/docs/en/sub-agents#subagent-auto-compact-window) for this agent when it runs as a subagent, to a token count from `100
+2 −0 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
agent-sdk/subagents
±changed
+1−0
claude-codechanged
agent-sdk/subagents
| `autoCompactWindow` | `number` | No | Lower the [auto-compact window](/docs/en/sub-agents#subagent-auto-compact-window) for this agent when it runs as a subagent, to a token coun
+1 −0 lines
Upstream edited 14 Oct 2026 16:42 UTC Recorded here 14 Oct 2026 17:07 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
| Byte-level watchdog | No bytes arrive on the wire, including SSE keep-alive pings | Direct Anthropic API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and [gateway]
| Byte-level watchdog | No bytes arrive on the wire, including SSE keep-alive pings | Direct Anthropic API, [Claude Platform on AWS](/docs/en/claude-platform-on-aws), and [gateway]
+1 −1 lines
Upstream edited 14 Oct 2026 16:37 UTC Recorded here 14 Oct 2026 17:07 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 14 Oct 2026 16:37 UTC
claude-code
errors
±changed
+36−0
claude-codechanged
errors
| `hook needs quotes around a path with a space` | [Configuration warnings](#hook-needs-quotes-around-a-path-with-a-space) |
| `N skill or command names refused: run with --debug to see which ([names]), rename, then restart` | [Configuration warnings](#skill-or-command-name-refused) |
<h3 id="hook-needs-quotes-around-a-path-with-a-space">
Hook needs quotes around a path with a space
</h3>
+36 −0 lines
Upstream edited 14 Oct 2026 16:36 UTC Recorded here 14 Oct 2026 16:37 UTC
claude-code
skills
±changed
+21−0
claude-codechanged
skills
* **Characters in the name**: outside a plugin, a skill folder doesn't load when its name has a character such as a zero-width space or `<`. See [Characters a skill name can't hold
<h4 id="characters-a-skill-name-cant-hold">
Characters a skill name can't hold
</h4>
+21 −0 lines
Upstream edited 14 Oct 2026 16:35 UTC Recorded here 14 Oct 2026 16:37 UTC
claude-code
scheduled-tasks
±changed
+1−1
claude-codechanged
scheduled-tasks
A dynamically scheduled loop appears in your [scheduled task list](#manage-scheduled-tasks) like any other task, so you can list or cancel it the same way. The [jitter rules](#jitt
A dynamically scheduled loop appears in your [scheduled task list](#manage-scheduled-tasks) like any other task, so you can list or cancel it the same way. The list shows its pendi
+1 −1 lines
Upstream edited 14 Oct 2026 16:22 UTC Recorded here 14 Oct 2026 16:37 UTC
claude-code
plugins/mods/reference
±changed
+18−0
claude-codechanged
plugins/mods/reference
<h4 id="skill-prompt-fields">
Source and frontmatter fields on `skill.prompt`
</h4>
+18 −0 lines
Upstream edited 14 Oct 2026 16:21 UTC Recorded here 14 Oct 2026 16:37 UTC
claude-code
plugins/mods/events
±changed
+1−1
claude-codechanged
plugins/mods/events
[Other events](/docs/en/plugins/mods/reference#prompts-and-what-claude-reads) cover the rest of what Claude reads: `prompt.section` for each section of the system prompt, `prompt.c
[Other events](/docs/en/plugins/mods/reference#prompts-and-what-claude-reads) cover the rest of what Claude reads: `prompt.section` for each section of the system prompt, `prompt.c
+1 −1 lines
Upstream edited 14 Oct 2026 16:21 UTC Recorded here 14 Oct 2026 16:37 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 14 Oct 2026 16:07 UTC
claude-code
plugin-evals
±changed
+22−22
claude-codechanged
plugin-evals
The `claude plugin eval` shell command runs your [plugin](/docs/en/plugins/overview.md) against a suite of test cases and scores the results. Each case is a realistic prompt plus o
The `claude plugin eval` shell command runs your [plugin](https://code.claude.com/docs/en/plugins/overview.md) against a suite of test cases and scores the results. Each case is a
This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. For iterating on one skill inside a
This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. For iterating on one skill inside a
* A plugin directory with a `plugin.json` or `.claude-plugin/plugin.json` manifest, or a [skills-directory plugin](/docs/en/plugins/loading.md#plugins-shared-through-a-repository).
+22 −22 lines
Upstream edited 14 Oct 2026 15:54 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
plugin-evals
±changed
+21−21
claude-codechanged
plugin-evals
The `claude plugin eval` shell command runs your [plugin](/docs/en/plugins/overview) against a suite of test cases and scores the results. Each case is a realistic prompt plus one
The `claude plugin eval` shell command runs your [plugin](/docs/en/plugins/overview.md) against a suite of test cases and scores the results. Each case is a realistic prompt plus o
This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. For iterating on one skill inside a
This page is for plugin and skill authors who have a working plugin and want to test its behavior, and for teams that gate plugin changes in CI. For iterating on one skill inside a
* A plugin directory with a `plugin.json` or `.claude-plugin/plugin.json` manifest, or a [skills-directory plugin](/docs/en/plugins/loading#plugins-shared-through-a-repository).
+21 −21 lines
Upstream edited 14 Oct 2026 15:54 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
plugin-evals
±changed
+81−119
claude-codechanged
plugin-evals
<Note>
Every eval run and every judge grader is a real model call on your account, counted against your plan's usage or your API bill, so check the [requirements](#requirements) first.
</Note>
> [!NOTE]
>
+81 −119 lines
Upstream edited 14 Oct 2026 15:54 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
plugins/cli-reference
±changed
+2−2
claude-codechanged
plugins/cli-reference
| `0` | Every case meets the threshold |
| `1` | A failing case, a load error, or an untrusted plugin directory |
| `0` | The suite passed: every case meets the threshold and nothing else failed the run |
| `1` | A failing case, a load error, an untrusted plugin directory, a run that [ended on an API error](/docs/en/plugin-evals#runs-ended-on-an-api-error), or another cause listed u
+2 −2 lines
Upstream edited 14 Oct 2026 15:54 UTC Recorded here 14 Oct 2026 16:07 UTC
claude-code
plugin-evals
±changed
+22−5
claude-codechanged
plugin-evals
| 0 | Every case scored at or above `--threshold` and every case file loaded |
| 1 | A case scored below the threshold, a case file failed to load, no cases were found, a run couldn't be started, the plugin directory isn't trusted and `--trust-plugin` wasn't
| 0 | The suite passed: every case scored at or above `--threshold` and nothing else failed the run |
| 1 | A case scored below the threshold, a case file failed to load, no cases were found, a run couldn't be started, or a run [ended on an API error](#runs-ended-on-an-api-error).
| `cases[].arms.with[].error` | `null`, or why a run ended abnormally, such as `timed out after 300s`. A run that started but ended badly is still graded on what it produced, so a
+22 −5 lines
Upstream edited 14 Oct 2026 15:54 UTC Recorded here 14 Oct 2026 16:07 UTC
api
models/opus-5-5/migration-guide
±changed
+2−2
apichanged
models/opus-5-5/migration-guide
* Move from `client.beta.messages.create()` (python, typescript, ruby; csharp: `client.Beta.Messages.Create()`; go: `client.Beta.Messages.New()`; java: `client.beta().messages().cr
* Move from `client.beta.messages.create()` (csharp: `client.Beta.Messages.Create()`; go: `client.Beta.Messages.New()`; java: `client.beta().messages().create()`; php: `$client->be
1. **Migrate to adaptive thinking (required):** `thinking: {"type": "enabled", "budget_tokens": N}` returns a 400 error on Claude Opus 4.7 and later models. The before and after is
1. **Migrate to adaptive thinking (required):** `thinking: {"type": "enabled", "budget_tokens": N}` returns a 400 error on Claude Opus 4.7 and later models. The before and after is
+2 −2 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/workflow-runs
±changed
+47−43
apichanged
managed-agents/workflow-runs
description: "Follow an agent's workflow runs: their states and events, when the work is done, what a run blocks, budgets, and limits."
description: "Follow an agent's workflow runs: their states and events, when the work is done, requests while a run is open, budgets, and limits."
A **workflow** is a program that an agent writes to run many agents and combine what they return. A **workflow run** is the execution of one workflow. **[Dynamic workflows](https:/
The server runs a workflow in the background. Its agents work in [session threads](https://platform.claude.com/docs/en/managed-agents/session-threads) that the server creates as th
+47 −43 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/vaults
±changed
+10−10
apichanged
managed-agents/vaults
A vault is the collection of `credentials` associated with an end user. Give it a `display_name` (java, php: `displayName`; csharp, go: `DisplayName`) and optionally tag it with `m
A vault is the collection of `credentials` associated with an end user. Give it a `display_name` (java, php: `displayName`; csharp, go: `DisplayName`) and optionally tag it with `m
The actual credential values you supply (`token` (java, php; csharp, go: `Token`), `access_token` (java, php: `accessToken`; csharp, go: `AccessToken`), `refresh_token` (java, php:
The actual credential values you supply (`token` (csharp, go: `Token`), `access_token` (java, php: `accessToken`; csharp, go: `AccessToken`), `refresh_token` (java, php: `refreshTo
Use `mcp_oauth` when the MCP server uses OAuth 2.0. If you supply a `refresh` (java, php; csharp, go: `Refresh`) block, Anthropic refreshes the access token on your behalf when
+10 −10 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/tools-web-restrictions
±changed
+8−8
apichanged
managed-agents/tools-web-restrictions
To control which sites the agent's web tools can reach, set a domain list on the `web_search` and `web_fetch` entries of the [agent toolset](https://platform.claude.com/docs/en/man
To control which sites the agent's web tools can reach, set a domain list on the `web_search` and `web_fetch` entries of the [agent toolset](https://platform.claude.com/docs/en/man
The following example creates an agent that limits `web_search` to two sites and blocks one host for `web_fetch`. It also sets `user_location` (java, php: `userLocation`; csharp, g
The following example creates an agent that limits `web_search` to two sites and blocks one host for `web_fetch`. It also sets `user_location` (java, php: `userLocation`; csharp, g
In addition to `enabled` (java, php; csharp, go: `Enabled`) and `permission_policy` (java, php: `permissionPolicy`; csharp, go: `PermissionPolicy`), the web tool entries accept the
+8 −8 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/tools
±changed
+7−7
apichanged
managed-agents/tools
Enable the full toolset with `agent_toolset_20260401` when creating an agent. Use the `configs` (java, php; csharp, go: `Configs`) array to disable specific tools or override their
Enable the full toolset with `agent_toolset_20260401` when creating an agent. Use the `configs` (csharp, go: `Configs`) array to disable specific tools or override their settings.
The Python, TypeScript, Go, Java, C#, Ruby, and PHP SDKs type each `configs` (java, php; csharp, go: `Configs`) entry per tool. The type is a union with one member per built-in too
In Go, Java, C#, and PHP, you construct entries from typed values rather than plain dictionaries or hashes. In those SDKs, the element type of `configs` (java, php; csharp, go: `Co
+7 −7 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/skills
±changed
+8−8
apichanged
managed-agents/skills
Skills reach your agent in two ways: attach them through the agent's `skills` (java, php; csharp, go: `Skills`) array, or [load them from a GitHub repository](https://platform.clau
Skills reach your agent in two ways: attach them through the agent's `skills` (csharp, go: `Skills`) array, or [load them from a GitHub repository](https://platform.claude.com/docs
Each entry in the `skills` (java, php; csharp, go: `Skills`) array uses the following fields:
Each entry in the `skills` (csharp, go: `Skills`) array uses the following fields:
| `type` (java, php; csharp, go: `Type`) | Either `anthropic` for pre-built skills or `custom` for workspace-authored skills.
+8 −8 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/sessions
±changed
+12−12
apichanged
managed-agents/sessions
A session requires an `agent` ID and an `environment` ID. Agents are versioned resources; passing in the `agent` (java, php; csharp, go: `Agent`) ID as a string creates the session
A session requires an `agent` ID and an `environment` ID. Agents are versioned resources; passing in the `agent` (csharp, go: `Agent`) ID as a string creates the session with the l
You can pass `agent` (java, php; csharp, go: `Agent`) in three forms: an agent ID string, a pinned-version object (`type: "agent"`), or an overrides object. The overrides form chan
You can pass `agent` (csharp, go: `Agent`) in three forms: an agent ID string, a pinned-version object (`type: "agent"`), or an overrides object. The overrides form changes parts o
* **Set the field to `null`, or to an empty array for list fields:** The session runs with that field cleared. This rule applies in full to `system` (java, php; csharp, go: `System
+12 −12 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/session-threads
±changed
+16−15
apichanged
managed-agents/session-threads
The session `status` (java, php; csharp, go: `Status`) is an aggregation of all agent activity; if at least one thread is `running`, then the overall session status is `running` as
The session `status` (csharp, go: `Status`) is an aggregation of all agent activity; if at least one thread is `running`, then the overall session status is `running` as well. A [w
The full list includes the primary thread. `parent_thread_id` (java: `parentThreadId`; php: `parentThreadID`; csharp, go: `ParentThreadID`) is `null` for the primary thread. Every
The full list includes the primary thread. `parent_thread_id` (java: `parentThreadId`; php: `parentThreadID`; csharp, go: `ParentThreadID`) is `null` (python: `None`; ruby: `nil`;
| Type | Description
+16 −15 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/session-operations
±changed
+6−6
apichanged
managed-agents/session-operations
You can update a session's `agent.tools` (java, php; csharp, go: `Agent.Tools`) and `agent.mcp_servers` (java, php: `agent.mcpServers`; csharp: `Agent.McpServers`; go: `Agent.MCPSe
Only the agent's `tools` (java, php; csharp, go: `Tools`) and `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`) can change after a session is created.
The semantics of a `tools` (java, php; csharp, go: `Tools`) or `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`) update are full replacement: the prov
+6 −6 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/session-observability
±changed
+2−2
apichanged
managed-agents/session-observability
Use the session viewer in the Claude Console to inspect what an agent did in a session, without writing any code. Use the session's `usage` (java, php; csharp, go: `Usage`) totals
Use the session viewer in the Claude Console to inspect what an agent did in a session, without writing any code. Use the session's `usage` (csharp, go: `Usage`) totals to see what
You don't have to poll the session to observe these totals. The `session.usage` event carries the same cumulative snapshot on the session stream and in the event history. The snaps
You don't have to poll the session to observe these totals. The `session.usage` event carries the same cumulative snapshot on the session stream and in the event history. The snaps
+2 −2 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-workers
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-workers
Each claimed work item can carry a per-session `secret` (java, php; csharp, go: `Secret`), which Anthropic issues. The worker that runs the session needs it to mount [memory stores
Each claimed work item can carry a per-session `secret` (csharp, go: `Secret`), which Anthropic issues. The worker that runs the session needs it to mount [memory stores](https://p
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-security
±changed
+2−2
apichanged
managed-agents/self-hosted-sandboxes-security
* **Per-session credentials.** Each work item your worker claims can carry a per-session `secret` (java, php; csharp, go: `Secret`), which the worker uses in place of the environme
* **Per-session credentials.** Each work item your worker claims can carry a per-session `secret` (csharp, go: `Secret`), which the worker uses in place of the environment service
* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write
* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write
+2 −2 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-reference
±changed
+1−1
apichanged
managed-agents/self-hosted-sandboxes-reference
| `block_ms` (python; typescript: `blockMs`; go: `BlockMs`) | How long each poll waits for work to arrive before returning, in milliseconds. Must be betw
| `block_ms` (typescript: `blockMs`; go: `BlockMs`) | How long each poll waits for work to arrive before returning, in milliseconds. Must be betw
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-operations
±changed
+16−16
apichanged
managed-agents/self-hosted-sandboxes-operations
`GET /v1/environments/{environment_id}/work/stats` (curl; python, typescript, ruby: `client.beta.environments.work.stats()`; go, csharp: `client.Beta.Environments.Work.Stats()`; ja
| Field | Meaning
| ------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------
| `depth` (java, php; csharp, go: `Depth`) | Items waiting to be claimed.
+16 −16 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-memory
±changed
+8−8
apichanged
managed-agents/self-hosted-sandboxes-memory
Sessions on a self-hosted environment attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) exactly as sessions on cloud environments do. List them in `
Sessions on a self-hosted environment attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) exactly as sessions on cloud environments do. List them in `
| Setting | Value |
| ---------------------- | ----------------------------------------------------------- |
| Default | 15 seconds |
+8 −8 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/self-hosted-sandboxes-custom-tools
±changed
+3−3
apichanged
managed-agents/self-hosted-sandboxes-custom-tools
The SDK's [Client-side MCP helpers](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector#client-side-mcp-helpers) convert the server's tools into the runnable tools t
The SDK's [Client-side MCP helpers](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector#client-side-mcp-helpers) convert the server's tools into the runnable tools t
Connect to the same MCP server at startup, convert its tools with `async_mcp_tool` (python; typescript: `mcpTools`; go: `mcp.NewBetaTools`), and register them alongside `beta_a
Connect to the same MCP server at startup, convert its tools with `async_mcp_tool` (typescript: `mcpTools`; go: `mcp.NewBetaTools`), and register them alongside `beta_agent_too
| The agent's `tools` array | At most 128 entries. Each wrapped tool is one entry, and the built-in toolset is one more.
+3 −3 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/scheduled-deployments
±changed
+3−3
apichanged
managed-agents/scheduled-deployments
When creating a deployment, you pass the [session configurations](https://platform.claude.com/docs/en/managed-agents/sessions) required for execution, in addition to a `schedule` (
When creating a deployment, you pass the [session configurations](https://platform.claude.com/docs/en/managed-agents/sessions) required for execution, in addition to a `schedule` (
* In the `schedule` (java, php; csharp, go: `Schedule`), you define a cron `expression` (java, php; csharp, go: `Expression`) and a `timezone` (java, php; csharp, go: `Timezone`).
* In the `schedule` (csharp, go: `Schedule`), you define a cron `expression` (csharp, go: `Expression`) and a `timezone` (csharp, go: `Timezone`). Maximum granularity supported is
Pass the optional `budget` (java, php; csharp, go: `Budget`) object when you create or update the deployment. It takes the same shape as a [session budget](https://platform.claude.
+3 −3 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/reference
±changed
+41−41
apichanged
managed-agents/reference
| Type | Description
| -------------------------------- | -------------------------------------------------------------------------------------------------------------------------------------------
| `agent.message` | Agent response content blocks.
| `agent.thinking` | Signals the agent is making forward progress through extended thinking. This is a progress signal only and does not carry the thinking cont
| `agent.tool_use` | Agent invokes a pre-built agent tool (bash, file operations, and so on). Carries `evaluated_permission` (java, php: `evaluatedPermission`;
+41 −41 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/permission-policies
±changed
+6−6
apichanged
managed-agents/permission-policies
You set permission policies in the agent's `tools` (java, php; csharp, go: `Tools`) configuration when you create the agent, and you can change them later by [updating the agent](h
You set permission policies in the agent's `tools` (csharp, go: `Tools`) configuration when you create the agent, and you can change them later by [updating the agent](https://plat
The `mcp_server_name` (java, php: `mcpServerName`; csharp: `McpServerName`; go: `MCPServerName`) must match the `name` (java, php; csharp, go: `Name`) of a server in the `mcp_serve
The `mcp_server_name` (java, php: `mcpServerName`; csharp: `McpServerName`; go: `MCPServerName`) must match the `name` (csharp, go: `Name`) of a server in the `mcp_servers` (java,
Use the `configs` (java, php; csharp, go: `Configs`) array to override the default for individual tools. The `name` (java, php; csharp, go: `Name`) values for the agent toolset are
+6 −6 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/multiagent-orchestration
±changed
+27−27
apichanged
managed-agents/multiagent-orchestration
* **Predefined agent:** An agent that you have already [created](https://platform.claude.com/docs/en/managed-agents/agent-setup), and that you list in the `multiagent` (java, php;
* **Predefined agent:** An agent that you have already [created](https://platform.claude.com/docs/en/managed-agents/agent-setup), and that you list in the `multiagent` (csharp, go:
When [defining your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup), set the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgent
When [defining your agent](https://platform.claude.com/docs/en/managed-agents/agent-setup), set the `predefined_agents` (java, php: `predefinedAgents`; csharp, go: `PredefinedAgent
The agent can also delegate to inline agents unless you turn them off. For that setting, and for the forms that an entry of the `predefined_agents` (java, php: `predefinedAgents`;
+27 −27 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/migration
±changed
+22−22
apichanged
managed-agents/migration
If you built an agent by calling `client.messages.create()` (python, typescript, ruby; csharp: `client.Messages.Create()`; go: `client.Messages.New()`; java: `client.messages().cre
If you built an agent by calling `client.messages.create()` (csharp: `client.Messages.Create()`; go: `client.Messages.New()`; java: `client.messages().create()`; php: `$client->mes
* **Web search and web fetch settings:** Same `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`), `blocked_domains` (java, php: `blockedDomains`; csharp,
* **Web search and web fetch settings:** Same `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`), `blocked_domains` (java, php: `blockedDomains`; csharp,
| Agent SDK | Managed Agents
+22 −22 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/memory
±changed
+19−19
apichanged
managed-agents/memory
Give the store a `name` (java, php; csharp, go: `Name`) and a `description` (java, php; csharp, go: `Description`). The description is passed to the agent, telling it what the stor
Give the store a `name` (csharp, go: `Name`) and a `description` (csharp, go: `Description`). The description is passed to the agent, telling it what the store contains.
The memory store `id` (java, php; csharp, go: `ID`) (`memstore_...`) is what you pass when attaching the store to a session.
The memory store `id` (csharp, go: `ID`) (`memstore_...`) is what you pass when attaching the store to a session.
Memory stores are attached in the session's `resources` (java, php; csharp, go: `Resources`) array when the [session is created](https://platform.claude.com/docs/en/managed-agents/
+19 −19 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/mcp-connector
±changed
+12−12
apichanged
managed-agents/mcp-connector
Specify MCP servers in the `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`) array when creating an agent. Each server needs a `type` (java, php; csha
Each declared server also needs a matching `mcp_toolset` entry in the `tools` (java, php; csharp, go: `Tools`) array. The toolset's `mcp_server_name` (java, php: `mcpServerName`; c
Specify MCP servers in the `mcp_servers` (java, php: `mcpServers`; csharp: `McpServers`; go: `MCPServers`) array when creating an agent. Each server needs a `type` (csharp, go: `Ty
+12 −12 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/github
±changed
+5−5
apichanged
managed-agents/github
| `type` (java, php; csharp, go: `Type`) | Required. Must be `"github_repository"`.
| `url` (java, php; csharp: `Url`; go: `URL`) | Required. The repository's HTTPS URL in the form `https://github.com/<owner>/<repo>`,
| `type` (csharp, go: `Type`) | Required. Must be `"github_repository"`.
| `url` (csharp: `Url`; go: `URL`) | Required. The repository's HTTPS URL in the form `https://github.com/<owner>/<repo>`,
| `checkout` (java, php; csharp, go: `Checkout`) | Optional. A branch (`{"type": "branch", "name": "main"}`) or commit (`{"type": "commit
+5 −5 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/files
±changed
+5−5
apichanged
managed-agents/files
Mount uploaded files into the sandbox by adding them to the `resources` (java, php; csharp, go: `Resources`) array when creating a session:
Mount uploaded files into the sandbox by adding them to the `resources` (csharp, go: `Resources`) array when creating a session:
Mount multiple files by adding entries to the `resources` (java, php; csharp, go: `Resources`) array:
Mount multiple files by adding entries to the `resources` (csharp, go: `Resources`) array:
You can add or remove files from a session after creation using the session resources API. Each resource has an `id` (java, php; csharp, go: `ID`) returned when it is added (or lis
+5 −5 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/events-and-streaming
±changed
+5−5
apichanged
managed-agents/events-and-streaming
Every event in the session's history includes a `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) timestamp, set when the event finishes processing. On events yo
Every event in the session's history includes a `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) timestamp, set when the event finishes processing. On events yo
Send a `user.tool_confirmation` event, passing the event ID in the `tool_use_id` (java: `toolUseId`; php: `toolUseID`; csharp, go: `ToolUseID`) parameter. Set `result` (java, php;
Send a `user.tool_confirmation` event, passing the event ID in the `tool_use_id` (java: `toolUseId`; php: `toolUseID`; csharp, go: `ToolUseID`) parameter. Set `result` (csharp, go:
1. The agent applies the interrupt. Until then, the interrupt's `processed_at` (java, php: `processedAt`; csharp, go: `ProcessedAt`) stays null and the session stays `running`. A m
+5 −5 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/event-deltas
±changed
+1−1
apichanged
managed-agents/event-deltas
Each SDK's helper handles the `index` (java, php; csharp, go: `Index`) bookkeeping. The Go, Java, Ruby, and C# helpers also key the accumulating preview by the event's `id` (java,
Each SDK's helper handles the `index` (csharp, go: `Index`) bookkeeping. The Go, Java, Ruby, and C# helpers also key the accumulating preview by the event's `id` (csharp, go: `ID`)
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/environments
±changed
+6−6
apichanged
managed-agents/environments
Use a unique, descriptive `name` (java, php; csharp, go: `Name`) so you can tell environments apart. This example uses `limited` [networking](https://platform.claude.com/docs/en/ma
Use a unique, descriptive `name` (csharp, go: `Name`) so you can tell environments apart. This example uses `limited` [networking](https://platform.claude.com/docs/en/managed-agent
The `packages` (java, php; csharp, go: `Packages`) field pre-installs packages into the sandbox before the agent starts. Packages are installed by their respective package managers
The `packages` (csharp, go: `Packages`) field pre-installs packages into the sandbox before the agent starts. Packages are installed by their respective package managers and cached
The `networking` (java, php; csharp, go: `Networking`) field controls the sandbox's outbound network access.
+6 −6 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/dreams
±changed
+24−23
apichanged
managed-agents/dreams
The dream produces another **output memory store**, separate from the input. The output store ID appears in the dream's `outputs` (java, php; csharp, go: `Outputs`) array shortly a
The dream produces another **output memory store**, separate from the input. The output store ID appears in the dream's `outputs` (csharp, go: `Outputs`) array shortly after the dr
Model: anthropic.BetaDreamModelParamsUnion{
Model: anthropic.BetaDreamNewParamsModelUnion{
Dreaming inputs include the pre-existing memory store and an array of sessions. The selected model runs the dreaming pipeline. During the research preview, `claude-opus-5-5`, `clau
+24 −23 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/define-outcomes
±changed
+1−1
apichanged
managed-agents/define-outcomes
* A `user.interrupt` event pauses work on the current outcome and marks the `result` (java, php; csharp, go: `Result`) of the `span.outcome_evaluation_end` event as `interrupted`,
* A `user.interrupt` event pauses work on the current outcome and marks the `result` (csharp, go: `Result`) of the `span.outcome_evaluation_end` event as `interrupted`, allowing yo
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/budgets
±changed
+11−11
apichanged
managed-agents/budgets
Pass the optional `budget` (java, php; csharp, go: `Budget`) field when you create the session:
Pass the optional `budget` (csharp, go: `Budget`) field when you create the session:
The `budget` (java, php; csharp, go: `Budget`) object has two fields:
* `type` (java, php; csharp, go: `Type`) is always `"limit"`.
+11 −11 lines
Recorded here 14 Oct 2026 12:07 UTC
api
managed-agents/agent-setup
±changed
+24−24
apichanged
managed-agents/agent-setup
| `name` (java, php; csharp, go: `Name`) | Required. A human-readable name for the agent.
| `model` (java, php; csharp, go: `Model`) | Required. The Claude [model](https://platform.claude.com/docs/en/models/overview) that powers th
| `system` (java, php; csharp, go: `System`; ruby: `system_`) | A [system prompt](https://platform.claude.com/docs/en/build-with-claude/prompt-engineering/claud
| `tools` (java, php; csharp, go: `Tools`) | The tools available to the agent. Combines [pre-built agent tools](https://platform.claude.com/d
| `name` (csharp, go: `Name`) | Required. A human-readable name for the agent.
+24 −24 lines
Recorded here 14 Oct 2026 12:07 UTC
api
manage-claude/workload-identity-federation
±changed
+1−1
apichanged
manage-claude/workload-identity-federation
Self-managed and on-premises clusters using projected service-account tokens.
Self-managed and on-premise clusters using projected service-account tokens.
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
manage-claude/wif-reference
±changed
+1−1
apichanged
manage-claude/wif-reference
`POST /v1/oauth/token` returns errors in the standard [API error shape](https://platform.claude.com/docs/en/api/errors). The SDK wraps exchange failures in a typed `WorkloadIdentit
`POST /v1/oauth/token` returns errors in the standard [API error shape](https://platform.claude.com/docs/en/api/errors). The SDK wraps exchange failures in a typed `WorkloadIdentit
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
manage-claude/wif-providers/kubernetes
±changed
+1−1
apichanged
manage-claude/wif-providers/kubernetes
Self-managed Kubernetes clusters (kubeadm, k3s, OpenShift, and on-premises distributions) sign OIDC JSON Web Tokens (JWTs) for every pod through [projected service account tokens](
Self-managed Kubernetes clusters (kubeadm, k3s, OpenShift, and on-premise distributions) sign OIDC JSON Web Tokens (JWTs) for every pod through [projected service account tokens](h
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
manage-claude/user-management
±changed
+4−4
apichanged
manage-claude/user-management
These endpoints require an Admin API key with the `read:members` scope (member and invite `GET` endpoints, and all custom-role endpoints; there is no separate role scope), the `w
These endpoints require an Admin API key with the `read:members` scope (member and invite `GET` endpoints, and all custom-role endpoints; there is no separate role scope), the `w
The API can assign only the `user` and `managed` roles, on invite creation and on role updates. The administrative roles (`owner`, `membership_admin`, and `primary_owner`) are assi
The API can assign only the `user` and `managed` roles, on invite creation and on role updates. Assigning `managed` requires the `write:rbac_groups` scope in addition to `write:mem
`POST /v1/organizations/users/{user_id}` sets the member's role to `user` or `managed`. Members holding an administrative role (`owner`, `membership_admin`, or `primary_owner`) can
+4 −4 lines
Recorded here 14 Oct 2026 12:07 UTC
api
manage-claude/admin-api-keys
±changed
+2−2
apichanged
manage-claude/admin-api-keys
| Admin API [user management](https://platform.claude.com/docs/en/manage-claude/user-management): change member roles, remove members, create and withdraw invites
| Admin API [user management](https://platform.claude.com/docs/en/manage-claude/user-management): change member roles, remove members, create and withdraw invites (to assign the `m
| Admin API [user management](https://platform.claude.com/docs/en/manage-claude/user-management): create, rename, and delete groups; add and remove group members; assign groups on
| Admin API [user management](https://platform.claude.com/docs/en/manage-claude/user-management): create, rename, and delete groups; add and remove group members; with `write:membe
+2 −2 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/sdks/typescript
±changed
+5−5
apichanged
cli-sdks-libraries/sdks/typescript
The SDK provides support for streaming responses using Server Sent Events (SSE).
The SDK provides support for streaming responses using Server-Sent Events (SSE).
The conversion functions throw `UnsupportedMCPValueError` if an MCP value isn't supported by the Claude API (for example, unsupported content type, unsupported MIME type, non-http/
The conversion functions throw `UnsupportedMCPValueError` if an MCP value isn't supported by the Claude API (for example, unsupported content type, unsupported MIME type, non-HTTP/
Set the content-type explicitly as the files API will not infer it for you:
+5 −5 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/sdks/ruby
±changed
+5−5
apichanged
cli-sdks-libraries/sdks/ruby
The Anthropic Ruby library provides convenient access to the Claude API from any Ruby 3.2.0+ application. It ships with comprehensive types and docstrings in Yard, RBS, and RBI. Th
The Anthropic Ruby library provides convenient access to the Claude API from any Ruby 3.2.0+ application. It ships with comprehensive types and docstrings in YARD, RBS, and RBI. Th
Since this library does not depend on `sorbet-runtime`, it cannot provide [`T::Enum`](https://sorbet.org/docs/tenum) instances. Instead, the SDK provides "tagged symbols", which is
Because this library does not depend on `sorbet-runtime`, it cannot provide [`T::Enum`](https://sorbet.org/docs/tenum) instances. Instead, the SDK provides "tagged symbols," which
2. Structural equivalence for equality; if two API calls return the same values, comparing the responses with == will return true.
+5 −5 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/sdks/java
±changed
+2−2
apichanged
cli-sdks-libraries/sdks/java
Tool names are derived from the camel case tool class names (for example, `GetWeather`) and converted to snake case (for example, `get_weather`). Word boundaries begin where the cu
Tool names are derived from the camel case tool class names (for example, `GetWeather`) and converted to snake case (for example, `get_weather`). Word boundaries begin where the cu
For non-streaming requests, the dynamic timeout scales from a 30 second minimum up to a 10 minute maximum based on `maxTokens`.
For non-streaming requests, the dynamic timeout scales from a 30-second minimum up to a 10-minute maximum based on `maxTokens`.
+2 −2 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/sdks/go
±changed
+7−7
apichanged
cli-sdks-libraries/sdks/go
The anthropic library uses the [`omitzero`](https://tip.golang.org/doc/go1.24#encodingjsonpkgencodingjson) semantics from the Go 1.24+ `encoding/json` release for request fields.
The Anthropic library uses the [`omitzero`](https://tip.golang.org/doc/go1.24#encodingjsonpkgencodingjson) semantics from the Go 1.24+ `encoding/json` release for request fields.
Any `param.Opt[T]`, map, slice, struct or string enum uses the tag `` `json:"...,omitzero"` ``. Its zero value is considered omitted.
Any `param.Opt[T]`, map, slice, struct, or string enum uses the tag `` `json:"...,omitzero"` ``. Its zero value is considered omitted.
Unions are represented as a struct with fields prefixed by "Of" for each of its variants, only one field can be non-zero. The non-zero field will be serialized.
+7 −7 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/sdks/csharp
±changed
+1−1
apichanged
cli-sdks-libraries/sdks/csharp
Backward-compatibility is taken seriously to ensure you can rely on a smooth upgrade experience.
Backward compatibility is taken seriously to ensure you can rely on a smooth upgrade experience.
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
cli-sdks-libraries/middleware
±changed
+1−1
apichanged
cli-sdks-libraries/middleware
Each middleware is a function that receives the outgoing request and the next handler. Call `call_next(request)` (python; typescript: `next(request)`; csharp: `next(request, cancel
Each middleware is a function that receives the outgoing request and the next handler. Call `call_next(request)` (typescript: `next(request)`; csharp: `next(request, cancellationTo
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
claude_api_primer
±changed
+4−0
apichanged
claude_api_primer
* Claude Fable 5.1 (`claude-fable-5-1`, adaptive thinking only, always on)
* Claude Mythos 5.1 (`claude-mythos-5-1`, adaptive thinking only, always on)
* Claude Fable 5 (`claude-fable-5`, adaptive thinking only, always on)
* Claude Mythos 5 (`claude-mythos-5`, adaptive thinking only, always on)
+4 −0 lines
Recorded here 14 Oct 2026 12:07 UTC
api
build-with-claude/streaming
±changed
+1−1
apichanged
build-with-claude/streaming
If you don't need to process text as it arrives, the SDK provides a way to use streaming internally while returning the complete `Message` object, identical to what `client.message
If you don't need to process text as it arrives, the SDK provides a way to use streaming internally while returning the complete `Message` object, identical to what `client.message
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5
If your harness is Claude Code or the Claude Agent SDK, the deterministic caps are the `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` and `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` environment
If your harness is Claude Code or the Claude Agent SDK, the deterministic caps are the `CLAUDE_CODE_MAX_SUBAGENT_SPAWN_DEPTH` and `CLAUDE_CODE_MAX_CONCURRENT_SUBAGENTS` environment
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
build-with-claude/preserved-thinking
±changed
+1−1
apichanged
build-with-claude/preserved-thinking
In Anthropic's testing on a multi-turn coding benchmark, dropping thinking blocks once per session increased output tokens by 2.5% at low effort, 3.9% at medium, 4.5% at high, and
In Anthropic's testing on a multi-turn coding benchmark, dropping thinking blocks once per session increased output tokens by 2.5% at low effort, 3.9% at medium, 4.5% at high, and
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+35−35
apichanged
build-with-claude/claude-platform-on-aws
| Aspect | Claude Platform on AWS
| ---------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------
| **Who operates the stack** | Anthropic
| **API surface** | Claude API (`/v1/{endpoint}`)
| **Feature availability** | Typically same-day as Claude API (see [feature limitations](https://platform.claude.com/docs/en/build-with-claude/claude-platform-on-aws#features-n
+35 −35 lines
Recorded here 14 Oct 2026 12:07 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+1−1
apichanged
build-with-claude/claude-in-amazon-bedrock
You can also create the standard client with `Anthropic` (python, typescript; go: `anthropic.NewClient()`; java: `AnthropicOkHttpClient.builder()`; csharp: `AnthropicClient`; php
You can also create the standard client with `Anthropic` (go: `anthropic.NewClient()`; java: `AnthropicOkHttpClient.builder()`; csharp: `AnthropicClient`; php: `Anthropic\Client`
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
api/rate-limits
±changed
+23−23
apichanged
api/rate-limits
The rate limits for the Messages API are measured in requests per minute (RPM), input tokens per minute (ITPM), and output tokens per minute (OTPM) for each model class. If you exc
The rate limits for the Messages API are measured in requests per minute (RPM), input tokens per minute (ITPM), and output tokens per minute (OTPM) for each model class. If you exc
Rate limits are applied separately for each model; therefore you can use different models up to their respective limits simultaneously. You can check your current rate limits and b
Each row in the following tables has its own RPM, ITPM, and OTPM limits. Some rows cover several models that share one limit; see the notes under the tables. You can check your cur
| Header | Description
+23 −23 lines
Recorded here 14 Oct 2026 12:07 UTC
api
api/overview
±changed
+1−1
apichanged
api/overview
The SDK provides an auto-paginating iterator that follows `next_page` for you. For example, `for session in client.beta.sessions.list()` (python; typescript: `for await (const sess
The SDK provides an auto-paginating iterator that follows `next_page` for you. For example, `for session in client.beta.sessions.list()` (typescript: `for await (const session of c
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
api/errors
±changed
+1−1
apichanged
api/errors
The official SDK raises typed exceptions for these errors instead of returning raw JSON. For example, a 404 surfaces as `anthropic.NotFoundError` (python; typescript: `Anthropic.No
The official SDK raises typed exceptions for these errors instead of returning raw JSON. For example, a 404 surfaces as `anthropic.NotFoundError` (typescript: `Anthropic.NotFoundEr
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
api/claude-platform-on-aws-iam-actions
±changed
+1−1
apichanged
api/claude-platform-on-aws-iam-actions
The service defines 72 actions. Actions follow the AWS `VerbNoun` convention and use verb discipline so that `Get*` and `List*` wildcards produce a clean read-only boundary.
Actions follow the AWS `VerbNoun` convention and use verb discipline so that `Get*` and `List*` wildcards produce a clean read-only boundary.
+1 −1 lines
Recorded here 14 Oct 2026 12:07 UTC
api
api/beta-headers
±changed
+4−4
apichanged
api/beta-headers
The [client SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) exposes a `client.beta` (python, typescript, ruby; csharp, go: `client.Beta`; java: `client.beta
The [client SDK](https://platform.claude.com/docs/en/cli-sdks-libraries/overview) exposes a `client.beta` (csharp, go: `client.Beta`; java: `client.beta()`; php: `$client->beta`)
The following examples show the same request with cURL, the `ant` CLI, and the SDK, using the [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editin
The following examples show the same request with cURL, the `ant` CLI, and the SDK, using the [context editing](https://platform.claude.com/docs/en/build-with-claude/context-editin
With the SDK, list each feature (for example, `betas=["feature1", "feature2"]` (python; typescript, ruby: `betas: ["feature1", "feature2"]`; php: `betas: ['feature1', 'feature2']`;
+4 −4 lines
Recorded here 14 Oct 2026 12:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.