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
145 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
65 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
24 Sep 2026
183 pages
+21479 −7808 lines
claude-code
plugins/code-intelligence
+new page
+132−0
claude-codenew page
plugins/code-intelligence
No line of the body moved in this read.
+132 −0 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
plugins/cli-reference
+new page
+783−0
claude-codenew page
plugins/cli-reference
No line of the body moved in this read.
+783 −0 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
plugins/cli-hints
+new page
+122−0
claude-codenew page
plugins/cli-hints
No line of the body moved in this read.
+122 −0 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
plugins/anthropic-marketplaces
+new page
+85−0
claude-codenew page
plugins/anthropic-marketplaces
No line of the body moved in this read.
+85 −0 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
plugin-evals
±changed
+134−75
claude-codechanged
plugin-evals
`claude plugin eval` runs your [plugin](/docs/en/plugins) against a suite of test cases and scores the results. Each case is a realistic prompt plus one or more graders. A grader i
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
Use evals to measure how reliably your plugin steers Claude to the right outcome, to catch regressions when you change the plugin or a new model ships, and to see what the plugin c
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. Its case format is separate from th
+134 −75 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
permissions
±changed
+10−10
claude-codechanged
permissions
* The [plugins](/docs/en/plugins) its settings enable, its [skills](/docs/en/skills#discovery-from-parent-and-nested-directories), and its [subagents](/docs/en/sub-agents)
* The [plugins](/docs/en/plugins/overview) its settings enable, its [skills](/docs/en/skills#discovery-from-parent-and-nested-directories), and its [subagents](/docs/en/sub-agents)
* **Plugins**: package and distribute configuration as a [plugin](/docs/en/plugins) that teams can install
* **Plugins**: package and distribute configuration as a [plugin](/docs/en/plugins/overview) that teams can install
| What the repository supplies
+10 −10 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
output-styles
±changed
+2−2
claude-codechanged
output-styles
[Plugins](/docs/en/plugins-reference) can also ship output styles in an `output-styles/` directory.
[Plugins](/docs/en/plugins/manifest-reference) can also ship output styles in an `output-styles/` directory.
* [Plugins](/docs/en/plugins): package and distribute output styles alongside skills, hooks, and agents
* [Plugins](/docs/en/plugins/overview): package and distribute output styles alongside skills, hooks, and agents
+2 −2 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
network-config
±changed
+1−1
claude-codechanged
network-config
| `github.com` | Cloning GitHub-hosted [plugin marketplaces](/docs/en/plugin-marketplaces) and plugins, including the official Anthropic marketplace, over H
| `github.com` | Cloning GitHub-hosted [plugin marketplaces](/docs/en/plugins/overview) and plugins, including the official Anthropic marketplace, over HTTP
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
monitoring-usage
±changed
+6−6
claude-codechanged
monitoring-usage
* `agent.name`: Subagent type that issued the request. Built-in agent names and agents from official-marketplace plugins appear verbatim. Other user-defined agent names are replace
* `skill.name`: Skill active for the request, set by the Skill tool, a `/` command, or inherited by a spawned subagent. Built-in, bundled, user-defined, and official-marketplace pl
* `plugin.name`: Owning plugin when the active skill or subagent is provided by a plugin. Official-marketplace plugin names appear verbatim. Third-party plugin names are replaced w
* `agent.name`: Subagent type that issued the request. Built-in agent names and agents from official-marketplace plugins appear verbatim. Other user-defined agent names are replace
* `skill.name`: Skill active for the request, set by the Skill tool, a `/` command, or inherited by a spawned subagent. Built-in, bundled, user-defined, and official-marketplace pl
+6 −6 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
managed-settings
±changed
+44−44
claude-codechanged
managed-settings
Wherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/doc
Wherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/doc
| Field | Behavior when present but invalid
| :---------------------------- | :-------------------------------------------------------------------------------------------------------------------------------------------------
| `allowedMcpServers` | Enforced as an empty allowlist until the value is fixed, so no MCP servers that users add are admitted. Servers your organization delivers through
+44 −44 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
managed-mcp
±changed
+1−1
claude-codechanged
managed-mcp
Claude Code doesn't have a built-in MCP server registry that users can browse and install from. For the approved-catalog pattern, share the approved list and its `claude mcp add`
Claude Code doesn't have a built-in MCP server registry that users can browse and install from. For the approved-catalog pattern, share the approved list and its `claude mcp add`
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
large-codebases
±changed
+5−5
claude-codechanged
large-codebases
In a large codebase, finding where a symbol is defined or used can cost many file reads and grep calls. [Code intelligence plugins](/docs/en/discover-plugins#code-intelligence) con
In a large codebase, finding where a symbol is defined or used can cost many file reads and grep calls. [Code intelligence plugins](/docs/en/plugins/code-intelligence) connect Clau
* The plugin is [not found in the marketplace](/docs/en/discover-plugins#install-plugins): check the plugin name.
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
Code intelligence plugins require the language's language server binary on each developer's machine. See [which binary each language requires](/docs/en/discover-plugins#code-intell
+5 −5 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
Type `/` in Claude Code to see the commands available to you, or type `/` followed by any letters to filter. The `/` menu lists built-in commands, bundled and user-authored [skills
Type `/` in Claude Code to see the commands available to you, or type `/` followed by any letters to filter. The `/` menu lists built-in commands, bundled and user-authored [skills
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
how-claude-code-works
±changed
+7−7
claude-codechanged
how-claude-code-works
| Category | What Claude can do
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------
| **File operations** | Read files, edit code, create new files, rename and reorganize
| **Search** | Find files by pattern, search content with regex, explore codebases
| **Execution** | Run shell commands, start servers, run tests, use git
+7 −7 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
glossary
±changed
+3−3
claude-codechanged
glossary
A bundle of skills, hooks, subagents, and MCP servers packaged as a single installable unit. Plugin skills are namespaced as `plugin-name:skill-name` so multiple plugins coexist. D
Learn more: [Plugins](/docs/en/plugins)
A bundle of skills, hooks, subagents, and MCP servers packaged as a single installable unit. Plugin skills are namespaced as `plugin-name:skill-name` so multiple plugins coexist. D
+3 −3 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
github-enterprise-server
±changed
+13−13
claude-codechanged
github-enterprise-server
| Permission | Access | Used for
| :------------------- | :------------- | :-----------------------------------------------------------------------------------------------------------------------------------------
| Contents | Read and write | Cloning repositories and pushing branches
| Pull requests | Read and write | Creating PRs and posting review comments
| Issues | Read and write | Responding to issue mentions
+13 −13 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
features-overview
±changed
+17−17
claude-codechanged
features-overview
* **[Plugins](/docs/en/plugins)** and **[marketplaces](/docs/en/plugin-marketplaces)** package and distribute these features
* **[Plugins](/docs/en/plugins/overview)** and **[marketplaces](/docs/en/plugins/overview)** package and distribute these features
**[Plugins](/docs/en/plugins)** are the packaging layer. A plugin bundles skills, hooks, subagents, and MCP servers into a single installable unit. Plugin skills are namespaced (li
**[Plugins](/docs/en/plugins/overview)** are the packaging layer. A plugin bundles skills, hooks, subagents, and MCP servers into a single installable unit. Plugin skills are names
| Trigger | Add
+17 −17 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
feature-availability
±changed
+1−1
claude-codechanged
feature-availability
* [CLAUDE.md memory](/docs/en/memory), [plugins](/docs/en/plugins), and [MCP servers](/docs/en/mcp)
* [CLAUDE.md memory](/docs/en/memory), [plugins](/docs/en/plugins/overview), and [MCP servers](/docs/en/mcp)
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
errors
±changed
+16−16
claude-codechanged
errors
* A command from a [plugin](/docs/en/plugins) or [MCP server](/docs/en/mcp#use-mcp-prompts-as-commands) that isn't installed or connected in this session
* A command from a [plugin](/docs/en/plugins/overview) or [MCP server](/docs/en/mcp#use-mcp-prompts-as-commands) that isn't installed or connected in this session
These errors come from [plugin](/docs/en/plugins) and [marketplace](/docs/en/plugin-marketplaces) configuration. For plugin problems that don't produce one of the messages on this
These errors come from [plugin](/docs/en/plugins/overview) and [marketplace](/docs/en/plugins/overview) configuration. For plugin problems that don't produce one of the messages on
The marketplace is registered under a name that is [reserved for official Anthropic marketplaces](/docs/en/plugin-marketplaces#marketplace-schema), but its registered source isn't
+16 −16 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
env-vars
±changed
+371−371
claude-codechanged
env-vars
No line of the body moved in this read.
+371 −371 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
desktop
±changed
+7−7
claude-codechanged
desktop
Claude Code also loads the skills and plugins enabled for your claude.ai account in terminal sessions where you sign in with the same account. See [Skills synced from claude.ai](/d
Claude Code also loads the skills and plugins enabled for your claude.ai account in terminal sessions where you sign in with the same account. See [Skills synced from claude.ai](/d
[Skills](/docs/en/skills) extend what Claude can do. Claude loads them automatically when relevant, or you can invoke one directly: type `/` in the prompt box or click the **+** bu
[Skills](/docs/en/skills) extend what Claude can do. Claude loads them automatically when relevant, or you can invoke one directly: type `/` in the prompt box or click the **+** bu
[Plugins](/docs/en/plugins) are reusable packages that add skills, agents, hooks, MCP servers, and LSP configurations to Claude Code. You can install plugins from the desktop app w
+7 −7 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
debug-your-config
±changed
+1−1
claude-codechanged
debug-your-config
| Hook never fires | Hooks are defined in a standalone file instead of `settings.json`
| Hook never fires | Hooks are defined in a standalone file instead of `settings.json`
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
[Code intelligence plugins](/docs/en/discover-plugins#code-intelligence) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when ex
[Code intelligence plugins](/docs/en/plugins/code-intelligence) give Claude precise symbol navigation instead of text-based search, reducing unnecessary file reads when exploring u
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
common-workflows
±changed
+1−1
claude-codechanged
common-workflows
* Install a [code intelligence plugin](/docs/en/discover-plugins#code-intelligence) for your language to give Claude precise "go to definition" and "find references" navigation
* Install a [code intelligence plugin](/docs/en/plugins/code-intelligence) for your language to give Claude precise "go to definition" and "find references" navigation
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
cloud-environments
±changed
+2−2
claude-codechanged
cloud-environments
| Plugins and marketplaces declared in your repo's `.claude/settings.json`
| Plugins and marketplaces declared in your repo's `.claude/settings.json`
| Plugins enabled only in your user settings
| Plugins enabled only in your user settings
+2 −2 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
claude-security
±changed
+5−5
claude-codechanged
claude-security
In a Claude Code session, install from the [official Anthropic marketplace](/docs/en/discover-plugins#official-anthropic-marketplace):
In a Claude Code session, install from the [official Anthropic marketplace](/docs/en/plugins/anthropic-marketplaces):
The command opens the plugin's details, where you choose an [installation scope](/docs/en/discover-plugins#install-plugins) to start the install.
The command opens the plugin's details, where you choose an [installation scope](/docs/en/plugins/install#install-a-plugin) to start the install.
* If it reports that it [can't find the plugin in the marketplace](/docs/en/discover-plugins#install-plugins), check the plugin name for a typo.
+5 −5 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
claude-directory
±changed
+26−26
claude-codechanged
claude-directory
| File | Location | Purpose
| ----------------------- | ------------------------------------------ | -----------------------------------------------------------------------------------------------------------
| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that you can't override, apart from [narrow exceptions](/docs/en/settings#secu
| `CLAUDE.local.md` | Project root | Your private preferences for this project, loaded alongside CLAUDE.md. Create it manually and add it to `.g
| `AGENTS.md` | Project root, `.claude/`, or any directory | Project instructions you write for AI coding agents. Claude Code can [load it](/docs/en/memory#agents-md) o
+26 −26 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
channels-reference
±changed
+5−5
claude-codechanged
channels-reference
The bypass is per-entry. Combining this flag with `--channels` doesn't extend the bypass to the `--channels` entries. During the research preview, the approved allowlist is Anthrop
The bypass is per-entry. Combining this flag with `--channels` doesn't extend the bypass to the `--channels` entries. During the research preview, your channel isn't on the approve
To make your channel installable and shareable, wrap it in a [plugin](/docs/en/plugins) and publish it to a [marketplace](/docs/en/plugin-marketplaces). Users install it with `/plu
A channel published to your own marketplace still needs `--dangerously-load-development-channels` to run, since it isn't on the [approved allowlist](/docs/en/channels#supported-cha
+5 −5 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
channels
±changed
+8−8
claude-codechanged
channels
* The plugin is [not found in the marketplace](/docs/en/discover-plugins#install-plugins): check the plugin name.
When the install asks for an installation scope, choose the user scope option so the plugin is available across all your projects. Check the install summary: if it reports
* The plugin is [not found in the marketplace](/docs/en/plugins/install#install-a-plugin): check the plugin name.
+8 −8 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
[Plugins](/docs/en/plugins) bundle skills, hooks, subagents, and MCP servers into a single installable unit from the community and Anthropic. If you work with a typed language, ins
[Plugins](/docs/en/plugins/overview) bundle skills, hooks, subagents, and MCP servers into a single installable unit from the community and Anthropic. If you work with a typed lang
+1 −1 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
agent-view
±changed
+2−2
claude-codechanged
agent-view
| [`--plugin-dir <path>`](/docs/en/plugins) | Load a plugin from a local directory
| [`--plugin-dir <path>`](/docs/en/plugins/create#load-a-directory-or-archive-for-one-session) | Load a plugin from a local directory
| v2.1.251 | When a background session starts while another Claude Code process is refreshing a [plugin marketplace](/docs/en/plugin-marketplaces), such as a sibling session runnin
| v2.1.251 | When a background session starts while another Claude Code process is refreshing a [plugin marketplace](/docs/en/plugins/overview), such as a sibling session running t
+2 −2 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
agent-sdk/plugins
±changed
+5−5
claude-codechanged
agent-sdk/plugins
For complete information on plugin structure and how to create plugins, see [Plugins](/docs/en/plugins).
For complete information on plugin structure and how to create plugins, see [Plugins](/docs/en/plugins/overview).
To use a plugin distributed through a [marketplace](/docs/en/plugin-marketplaces) or remote repository, download it first and provide the local directory path. For the directory la
To use a plugin distributed through a [marketplace](/docs/en/plugins/overview) or remote repository, download it first and provide the local directory path. For the directory layou
## Using plugin skills
+5 −5 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
admin-setup
±changed
+20−20
claude-codechanged
admin-setup
| Control | What it does
| :------------------------------------------------------------------------------------- | :----------------------------------------------------------------------------------------
| [Permission rules](/docs/en/permissions) | Allow, ask, or deny specific tools and commands
| [Permission lockdown](/docs/en/permissions#managed-only-settings) | Make managed settings the [only settings source of permission rules](/docs/en/settin
| [Starting permission mode](/docs/en/permission-modes#which-mode-a-session-starts-in) | Choose the permission mode your developers' terminal sessions start in instead of th
+20 −20 lines
Upstream edited 24 Sep 2026 23:46 UTC Recorded here 25 Sep 2026 00:07 UTC
claude-code
amazon-bedrock
±changed
+18−18
claude-codechanged
amazon-bedrock
| You set | The `opus` alias resolves to |
| :------------------------------------------------------------ | :------------------------------------------------------------------------------ |
| `ANTHROPIC_DEFAULT_OPUS_MODEL='us.anthropic.claude-opus-4-8'` | `us.anthropic.claude-opus-4-8`, the exact ID you pinned |
| `ANTHROPIC_BEDROCK_REGION_PREFIX=eu` | `eu.anthropic.claude-opus-5-5`, the built-in default with your preferred prefix |
| You set | The `opus` alias resolves to |
+18 −18 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
settings-reference
±changed
+18−5
claude-codechanged
settings-reference
Set environment variables for every session and for the subprocesses Claude Code starts from it. Any variable in the [environment variables reference](/docs/en/env-vars) can go her
Set environment variables for every session and for the subprocesses Claude Code starts from it. Most variables in the [environment variables reference](/docs/en/env-vars) can go h
* A value here overwrites the same variable exported in your shell, and when more than one settings file sets a variable, the [highest-precedence](/docs/en/settings#settings-preced
* A value here overwrites the same variable exported in your shell, and when more than one settings file sets a variable, the [highest-precedence](/docs/en/settings#settings-preced
* Variables Claude Code classifies as safe, such as model selection, timeouts and limits, feature toggles, and telemetry settings: at startup from every settings file, apart from t
+18 −5 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
settings-example
±changed
+2−14
claude-codechanged
settings-example
One team's shared settings, committed to the repository so everyone who clones it gets the same permissions, hooks, telemetry, and plugin marketplace. Save a file like this at `.cl
One team's shared settings, committed to the repository so everyone who clones it gets the same permissions, hooks, and plugin marketplace. Save a file like this at `.claude/settin
* **Telemetry goes in managed or personal settings.** Claude Code ignores the [OpenTelemetry exporter variables](/docs/en/settings-reference#variables-claude-code-ignores-in-env) i
},
"env": {
+2 −14 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
sandboxing
±changed
+1−1
claude-codechanged
sandboxing
Auto-allow mode works independently of your permission mode setting, except in [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode) and, in auto mode, fo
Auto-allow mode works independently of your permission mode setting, with three exceptions: [plan mode](/docs/en/permission-modes#analyze-before-you-edit-with-plan-mode), an auto
+1 −1 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
permissions
±changed
+1−1
claude-codechanged
permissions
Claude Code recognizes a built-in set of Bash commands as read-only and runs them without a permission prompt in every mode, except for a path that [`permissions.blockReadsOutsideW
Claude Code recognizes a built-in set of Bash commands as read-only and runs them without a permission prompt in every mode, except for a path that [`permissions.blockReadsOutsideW
+1 −1 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
permission-modes
±changed
+1−0
claude-codechanged
permission-modes
* In a session with [server-side classifier review](#server-side-classifier-review), read-only and [sandboxed](/docs/en/sandboxing#sandbox-modes) shell commands wait for tha
+1 −0 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
monitoring-usage
±changed
+8−2
claude-codechanged
monitoring-usage
Claude Code ignores the [OpenTelemetry exporter variables](/docs/en/settings-reference#variables-claude-code-ignores-in-env) in a repository's `.claude/settings.json` and `.claude/
These variables configure exporters, endpoints, and export behavior for all deployments. If you set a per-signal endpoint or protocol variable, such as `OTEL_EXPORTER_OTLP_METRICS_
These variables configure exporters, endpoints, and export behavior for all deployments.
+8 −2 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
env-vars
±changed
+11−9
claude-codechanged
env-vars
Between settings files, `env` values follow [settings precedence](/docs/en/settings#settings-precedence), so a managed settings entry overrides the same variable in user or project
Between settings files, `env` values follow [settings precedence](/docs/en/settings#settings-precedence), so a managed settings entry overrides the same variable in user or project
| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters.
| `CLAUDE_CODE_ENABLE_TELEMETRY` | Set to `1` to enable OpenTelemetry data collection for metrics and logging. Required before configuring OTel exporters.
| `CLAUDE_CODE_RESUME_INTERRUPTED_TURN_MAX_AGE_MS` | Maximum age in milliseconds of the last transcript message for a session that ended mid-turn to continue automatically o
+11 −9 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
amazon-bedrock
±changed
+7−2
claude-codechanged
amazon-bedrock
Mantle is an Amazon Bedrock endpoint that serves Claude models through the native Anthropic API shape rather than the Amazon Bedrock Invoke API. It uses the same [AWS credentials](
Mantle is an Amazon Bedrock endpoint that serves Claude models through the native Anthropic API shape rather than the Amazon Bedrock Invoke API. It uses the same [AWS credentials](
Mantle has its own IAM actions under the `bedrock-mantle:` prefix, so the `bedrock:` actions in [IAM configuration](#iam-configuration) don't cover it. Grant your IAM identity `bed
A `403` from the Mantle endpoint with valid credentials means your AWS account has not been granted access to the model you requested. Contact your AWS account team to request acce
+7 −2 lines
Upstream edited 24 Sep 2026 23:34 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
* Conversation history: the full history, including tool calls and results. A tool that was still running when the previous process ended, for example in a crash, doesn't finish or
* Conversation history: the full history, including tool calls and results. A tool that was still running when the previous process ended, for example in a crash, doesn't finish or
+1 −1 lines
Upstream edited 24 Sep 2026 23:22 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
worktrees
±changed
+2−0
claude-codechanged
worktrees
A `WorktreeCreate` hook also lets you run [`/batch`](/docs/en/commands#all-commands) outside a git repository. Each `/batch` subagent then publishes its change with your project's
+2 −0 lines
Upstream edited 24 Sep 2026 23:21 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
prompt-library
±changed
+1−1
claude-codechanged
prompt-library
teaches: "Describe the old pattern and the new one. Asking Claude to identify every place first means the call sites are listed in the response, so you can check none were miss
teaches: "Describe the old pattern and the new one. Asking Claude to identify every place first means the call sites are listed in the response, so you can check none were miss
+1 −1 lines
Upstream edited 24 Sep 2026 23:21 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/batch <instruction>` | **[Skill](/docs/en/skills#bundled-skills).** Orchestrate large-scal
| `/batch <instruction>` | **[Skill](/docs/en/skills#bundled-skills).** Orchestrate large-scal
+1 −1 lines
Upstream edited 24 Sep 2026 23:21 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
best-practices
±changed
+1−1
claude-codechanged
best-practices
For large migrations or analyses, you can distribute work across many parallel Claude invocations. In a git repository, run [`/batch <instruction>`](/docs/en/commands#all-commands)
For large migrations or analyses, you can distribute work across many parallel Claude invocations. Run [`/batch <instruction>`](/docs/en/commands#all-commands) to have Claude split
+1 −1 lines
Upstream edited 24 Sep 2026 23:21 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
agents
±changed
+1−1
claude-codechanged
agents
* [`/batch`](/docs/en/commands) is a [skill](/docs/en/skills) that has Claude split one large change into 5 to 30 worktree-isolated subagents that each open a pull request. It's a
* [`/batch`](/docs/en/commands) is a [skill](/docs/en/skills) that has Claude split one large change into 5 to 30 worktree-isolated subagents. It's a packaged use of subagents and
+1 −1 lines
Upstream edited 24 Sep 2026 23:21 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
remote-control
±changed
+3−3
claude-codechanged
remote-control
An Owner enables the setting from the Claude Code admin console.
An Owner enables the setting from the claude.ai organization settings.
<Step title="Open Claude Code admin settings">
Go to [claude.ai/admin-settings/claude-code](https://claude.ai/admin-settings/claude-code). The **Require trusted devices** toggle appears under the Remote Control setting.
<Step title="Go to the Capabilities page">
+3 −3 lines
Upstream edited 24 Sep 2026 23:18 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
Add `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), plugins, MCP servers, auto memory, and CLAUDE.md
Add `--bare` to reduce startup time by skipping auto-discovery of hooks, skills, custom commands, [subagents](/docs/en/sub-agents), installed plugins, MCP servers, auto memory, and
+1 −1 lines
Upstream edited 24 Sep 2026 23:12 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
With `--bare`, Claude Code starts without loading hooks, skills, custom commands, subagents, plugins, MCP servers, auto memory, or CLAUDE.md, apart from skills in a directory you p
With `--bare`, Claude Code starts without loading hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory, or CLAUDE.md, apart from skills in a direc
+1 −1 lines
Upstream edited 24 Sep 2026 23:12 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
cli-reference
±changed
+1−1
claude-codechanged
cli-reference
| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, custom commands, subagents, plugins, MCP servers, auto memory, and CLAUDE.md
| `--bare` | Minimal mode: skip auto-discovery of hooks, skills, custom commands, subagents, installed plugins, MCP servers, auto memory, and
+1 −1 lines
Upstream edited 24 Sep 2026 23:12 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
plugin-marketplaces
±changed
+12−7
claude-codechanged
plugin-marketplaces
<Note>
**Reserved names**: the following marketplace names are reserved for official Anthropic use and can't be used by third-party marketplaces: `claude-code-marketplace`, `claude-code
Claude Code re-checks reserved names every time it loads a marketplace, not only when you add one. A marketplace that was registered under one of these names before the name beca
+12 −7 lines
Upstream edited 24 Sep 2026 23:11 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
errors
±changed
+24−0
claude-codechanged
errors
| `"<name>" is another spelling of "<reserved>", a reserved marketplace name`
<h3 id="marketplace-name-is-another-spelling-of-a-reserved-name">
Marketplace name is another spelling of a reserved name
</h3>
+24 −0 lines
Upstream edited 24 Sep 2026 23:11 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
keybindings
±changed
+14−0
claude-codechanged
keybindings
With these bindings, `y` and `n` still type as letters while a [text field](#text-fields) has focus.
## Text fields
If you bind a bare letter, digit, or Space, you can still type that character in a text field inside a dialog or panel. One such field is the `Other` answer to a question Claude as
+14 −0 lines
Upstream edited 24 Sep 2026 23:10 UTC Recorded here 24 Sep 2026 23:37 UTC
claude-code
interactive-mode
±changed
+10−5
claude-codechanged
interactive-mode
| `Ctrl+S` | Stash or restore prompt
| `Ctrl+S` | Stash or restore prompt
| `Ctrl+Enter` or `Ctrl+X Ctrl+S` | Send queued messages now
| `Ctrl+Enter` or `Ctrl+X Ctrl+S` | Send queued messages now
To send what you queued without waiting for the turn to finish, press `Ctrl+Enter`. Claude Code interrupts the turn, and your queued messages go out right away, with your draft que
+10 −5 lines
Upstream edited 24 Sep 2026 22:59 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
fullscreen
±changed
+1−0
claude-codechanged
fullscreen
* **Scroll a select or multi-select menu with the mouse wheel** when it has more options than it shows at once, such as the `/model` list in a short terminal window. The wheel scro
+1 −0 lines
Upstream edited 24 Sep 2026 22:59 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
keybindings
±changed
+18−18
claude-codechanged
keybindings
| Action | Default | Description
| :-------------------- | :-------------------------------- | :---------------------------------------------------------------------------------------------------------------------
| `chat:cancel` | Escape | Cancel current input
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation
| `chat:clearScreen` | Cmd+K | Same as `chat:clearInput`. See [Clear the conversation](/docs/en/fullscreen#clear-the-conversation) for how Cmd+K beha
+18 −18 lines
Upstream edited 24 Sep 2026 22:58 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
remote-control
±changed
+5−3
claude-codechanged
remote-control
Trusted Devices is available on Team and Enterprise plans. It is off by default until an Owner enables it.
Trusted Devices is available on Pro, Max, Team, and Enterprise plans and is off by default. On Team and Enterprise plans, an Owner turns it on for the organization. On Pro and Ma
Trusted Devices is an organization-wide setting that requires members to verify their device before they can view or steer Remote Control sessions from claude.ai, the Claude mobile
Trusted Devices requires each member of your organization, or you alone on a Pro or Max plan, to verify their device before they can view or steer Remote Control sessions from clau
### Enable Trusted Devices for your organization
+5 −3 lines
Upstream edited 24 Sep 2026 22:57 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
settings-reference
±changed
+5−3
claude-codechanged
settings-reference
* **Type**: object with `commit` and `pr` strings and a `sessionUrl` Boolean
* **Type**: object with `commit` and `pr` strings and a `sessionUrl` Boolean, or `false` to hide all attribution. The `false` value requires Claude Code v2.1.281 or later; earlier
To hide all attribution, set `attribution` to `false`. In a settings file that earlier versions also read, set [`commit`](#attribution-commit) and [`pr`](#attribution-pr) to empty
To hide all attribution, set [`commit`](#attribution-commit) and [`pr`](#attribution-pr) to empty strings and [`sessionUrl`](#attribution-sessionurl) to `false`. Once you set `comm
+5 −3 lines
Upstream edited 24 Sep 2026 22:57 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
permission-modes
±changed
+13−3
claude-codechanged
permission-modes
On Enterprise plans and accounts that use the Claude API, on [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft
Asking the server by default requires Claude Code v2.1.278 or later.
In auto mode, Claude Code can ask the server to check the actions that [the decision order](#how-the-classifier-evaluates-actions) sends for review, as part of the session's model
+13 −3 lines
Upstream edited 24 Sep 2026 22:56 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
errors
±changed
+33−0
claude-codechanged
errors
| `The server-side auto mode classifier gave no verdict`
| `Auto mode is unavailable — the server returned no safety verdict for the last 10 responses`
### The server returned no safety verdict
Under [server-side classifier review](/docs/en/permission-modes#server-side-classifier-review), auto mode denies an action when the server gives no verdict for it. The denial names
+33 −0 lines
Upstream edited 24 Sep 2026 22:56 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
| `CLAUDE_CODE_AUTO_MODE_SERVER` | Controls whether Claude Code asks the server to [review auto mode actions](/docs/en/permission-modes#server-side-classif
| `CLAUDE_CODE_AUTO_MODE_SERVER` | Controls whether Claude Code asks the server to [review auto mode actions](/docs/en/permission-modes#server-side-classif
+1 −1 lines
Upstream edited 24 Sep 2026 22:56 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
claude-projects
±changed
+58−56
claude-codechanged
claude-projects
A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task. Each thread is a
A project is one ongoing conversation where Claude coordinates a stream of related work for you. You tell it what needs doing and it starts a thread for each task.
Each thread is usually a [cloud session](/docs/en/claude-code-on-the-web): Claude Code running in the cloud rather than on your machine. When a task needs something only your compu
* **Set context once**: every new thread starts with the project's repositories, instructions, and memory, so a rule you state once, such as which branch to target, reaches all of
+58 −56 lines
Upstream edited 24 Sep 2026 22:54 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
agent-sdk/quickstart
±changed
+5−5
claude-codechanged
agent-sdk/quickstart
| Tools | What the agent can do |
| -------------------------------------- | ----------------------- |
| `Read`, `Glob`, `Grep` | Read-only analysis |
| `Read`, `Edit`, `Glob` | Analyze and modify code |
| `Read`, `Edit`, `Bash`, `Glob`, `Grep` | Full automation |
+5 −5 lines
Upstream edited 24 Sep 2026 22:41 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
agent-sdk/troubleshooting
±changed
+16−2
claude-codechanged
agent-sdk/troubleshooting
> Fix Agent SDK errors by the exact message you see, with the cause and fix for each error in the TypeScript and Python SDKs.
> Fix Agent SDK errors when the Claude Code CLI fails to start, the CLI process exits, or a successful result arrives without structured output.
Entries on this page are keyed to the error you see. Each names the cause and what to do.
This page covers Agent SDK errors in CLI startup, CLI process exit, and structured outputs. Entries on this page are keyed to the error you see. Each entry names the cause and what
+16 −2 lines
Upstream edited 24 Sep 2026 22:41 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
agent-sdk/quickstart
±changed
+4−2
claude-codechanged
agent-sdk/quickstart
If you see an authentication error such as `Not logged in` or `Invalid API key`, make sure you've set the `ANTHROPIC_API_KEY` environment variable in the shell where you run your
If you see an authentication error such as `Not logged in` or `Invalid API key`, make sure you've set the `ANTHROPIC_API_KEY` environment variable in the shell where you run your
For the causes and fixes behind these and other authentication errors, see [Authentication errors](/docs/en/errors#authentication-errors) in the Error reference.
* **[Troubleshooting](/docs/en/agent-sdk/troubleshooting)**: fix Agent SDK errors by the exact message you see
+4 −2 lines
Upstream edited 24 Sep 2026 22:41 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
agent-sdk/python
±changed
+13−13
claude-codechanged
agent-sdk/python
| `env` | `dict[str, str]` | `{}` | Environment variables
| `env` | `dict[str, str]` | `{}` | Environment variables
| `debug_stderr` | `Any` | `sys.stderr` | *Deprecated* - File-l
| `debug_stderr` | `Any` | `sys.stderr` | *Deprecated* - The SD
| `user` | `str \| None` | `None` | User identifier
+13 −13 lines
Upstream edited 24 Sep 2026 22:40 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
agent-sdk/permissions
±changed
+1−1
claude-codechanged
agent-sdk/permissions
Auto-approves tool uses without prompting, except the cases listed in the warning below. Hooks still execute and can block operations if needed.
Auto-approves tool uses without prompting, except the cases listed in the warning below. Hooks still execute and can block operations if needed. On Linux and macOS, Claude Code ref
+1 −1 lines
Upstream edited 24 Sep 2026 22:40 UTC Recorded here 24 Sep 2026 23:07 UTC
claude-code
errors
±changed
+70−0
claude-codechanged
errors
| `role 'system' must precede an 'assistant' message`
| `Invalid encrypted_content in search_result block` / `Invalid encrypted_index in text block` / `Failed to decrypt web search result content`
| `Temp directory <dir> ... Refusing to use it` / `ENOSPC: no space left on device, mkdir '<dir>'`
<h3 id="role-system-must-precede-an-assistant-message">
role 'system' must precede an 'assistant' message
+70 −0 lines
Upstream edited 24 Sep 2026 22:19 UTC Recorded here 24 Sep 2026 22:37 UTC
claude-code
managed-settings
±changed
+2−0
claude-codechanged
managed-settings
* For `strictKnownMarketplaces`, Claude Code likewise enforces the list in the managed settings it applies and blocks a parent-supplied one. The parent's list applies only when no
* A parent-supplied `blockedMarketplaces` applies in addition to any blocklist that a managed source sets. Requires Claude Code v2.1.282 or later
+2 −0 lines
Upstream edited 24 Sep 2026 22:14 UTC Recorded here 24 Sep 2026 22:37 UTC
claude-code
claude-apps-gateway
±changed
+3−1
claude-codechanged
claude-apps-gateway
Four parent-supplied settings pass the filter even with all five locks set. Under the default first-wins setting, the admin value that blocks the parent's is the one in the highest
Six parent-supplied settings pass the filter even with all five locks set. Under the default first-wins setting, an admin value blocks the parent's only when it sits in the highest
* **`strictKnownMarketplaces`**: Claude Code honors a parent-supplied plugin marketplace allowlist when the winning managed source doesn't set one. If your fleet restricts marketpl
* **`blockedMarketplaces`**: a parent-supplied marketplace blocklist passes and adds to any blocklist that a managed source sets, since a blocklist can only restrict further. Requi
+3 −1 lines
Upstream edited 24 Sep 2026 22:14 UTC Recorded here 24 Sep 2026 22:37 UTC
claude-docs
third-party/claude-desktop/feature-matrix
±changed
+4−1
claude-docschanged
third-party/claude-desktop/feature-matrix
| Automatically approve / Skip all approvals (Cowork) | — ¶ | ✓ |
| Automatically approve (Cowork) | — ¶ | ✓ Δ |
| Skip all approvals (Cowork) | — ¶ | — |
Δ Offered when an administrator sets [`autoModeEnabled`](/docs/third-party/claude-desktop/configuration#automodeenabled) to `true`.
+4 −1 lines
Upstream edited 24 Sep 2026 22:10 UTC Recorded here 24 Sep 2026 22:37 UTC
claude-docs
third-party/claude-desktop/code
±changed
+16−16
claude-docschanged
third-party/claude-desktop/code
| Claude Desktop on 3P key
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| `inferenceProvider` and all provider credential keys (`inferenceGateway*`, `inferenceAnthropicApiKey`, `inferenceVertex*`, `inferenceBedrock*`, `inferenceFoundry*`, `inferenceCre
| `inferenceModels`
| `autoModeEnabled`
+16 −16 lines
Upstream edited 24 Sep 2026 22:10 UTC Recorded here 24 Sep 2026 22:37 UTC
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+3−1
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
Usage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see
Usage metrics are still provided in the response, even when the response is refused.
When a refusal arrives before Claude generates any output, you are not billed for the request on the Claude API, and the usage counts in that response are informational only. Whe
+3 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
release-notes/overview
±changed
+0−4
apichanged
release-notes/overview
### September 24, 2026
* We're expanding which refusals are billed to include refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`
+0 −4 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+1−1
apichanged
models/opus-5-5/whats-new-opus-5-5
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5/migration-guide
±changed
+1−1
apichanged
models/fable-5/migration-guide
A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category
You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+1−1
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale.
You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-c
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safegua
* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fa
+1 −1 lines
Recorded here 24 Sep 2026 22:07 UTC
api
build-with-claude/refusals-and-fallback
±changed
+9−17
apichanged
build-with-claude/refusals-and-fallback
| `category` | What it means
| ------------------------ | -------------------------------------------------------------------------------------------------------------------------------------------------------
| `"cyber"` | The request could enable cyber harm, such as malware or exploit development. Benign cybersecurity work can also trigger this category.
| `"bio"` | The request could enable biological harm, such as dangerous lab methods. Beneficial life sciences work can also trigger this category.
| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/leg
+9 −17 lines
Recorded here 24 Sep 2026 22:07 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+26−26
claude-docschanged
third-party/claude-desktop/gateway
| Field | Type | Default | Description
| --------------------------------- | --------- | ---------- | -----------------------------------------------------------------------------------------------------------------
| `clientId` | `string` | — | OAuth client ID of the desktop app registration at your identity provider (public client, PKCE).
| `issuer` | `string` | — | HTTPS issuer with OIDC discovery. Set this, or set the authorization and token URLs instead.
| `authorizationUrl` | `string` | — | HTTPS authorization endpoint. Used with the token URL when no issuer is set.
+26 −26 lines
Upstream edited 24 Sep 2026 21:31 UTC Recorded here 24 Sep 2026 21:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+7−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.9939.2" description="2026-09-24">
**Changed:**
* `autoModeEnabled` no longer defaults to `false`. Left unset, the Code tab offers Auto mode and new Code tab sessions start in it where the model supports it; `true` does the sa
+7 −0 lines
Upstream edited 24 Sep 2026 21:31 UTC Recorded here 24 Sep 2026 21:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+43−43
claude-docschanged
third-party/claude-desktop/configuration
| Field | Type | Default | Description
| --------------------------------- | --------- | ---------- | -----------------------------------------------------------------------------------------------------------------
| `clientId` | `string` | — | OAuth client ID of the desktop app registration at your identity provider (public client, PKCE).
| `issuer` | `string` | — | HTTPS issuer with OIDC discovery. Set this, or set the authorization and token URLs instead.
| `authorizationUrl` | `string` | — | HTTPS authorization endpoint. Used with the token URL when no issuer is set.
+43 −43 lines
Upstream edited 24 Sep 2026 21:31 UTC Recorded here 24 Sep 2026 21:37 UTC
claude-docs
cowork/changelog
±changed
+53−0
claude-docschanged
cowork/changelog
<Update label="v2.9939.2" description="2026-09-24">
Bundled Claude Code version: 2.1.281.
**General**
+53 −0 lines
Upstream edited 24 Sep 2026 21:31 UTC Recorded here 24 Sep 2026 21:37 UTC
claude-code
changelog
±changed
+89−0
claude-codechanged
changelog
<Update label="2.1.282" description="September 24, 2026">
* Added a `maxProseWidth` setting that caps the width of Claude's prose in wide terminals while tables and code blocks keep the full width
* Added a startup notice, and `/status` and `claude doctor` entries, listing telemetry variables in a project's settings files that were ignored or that turned telemetry off
* Added the `allowClaudeInChromeWithManagedMcp` managed setting to let `claude --chrome` run alongside an exclusive `managed-mcp.json`; the error shown when Chrome is blocked now
+89 −0 lines
Upstream edited 24 Sep 2026 18:46 UTC Recorded here 24 Sep 2026 19:07 UTC
api
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
±changed
+1−3
apichanged
test-and-evaluate/strengthen-guardrails/handle-streaming-refusals
Usage metrics are still provided in the response, even when the response is refused.
When a refusal arrives before Claude generates any output, you are not billed for the request on the Claude API, and the usage counts in that response are informational only. Whe
Usage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see
+1 −3 lines
Recorded here 24 Sep 2026 17:37 UTC
api
release-notes/overview
±changed
+13−0
apichanged
release-notes/overview
### September 24, 2026
* We're expanding which refusals are billed to include refusals that arrive before any output when `stop_details.category` is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`
### September 23, 2026
+13 −0 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+1−1
apichanged
models/opus-5-5/whats-new-opus-5-5
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
Claude Opus 5.5 ships with safety classifiers, and everything in [Refusals and fallback](https://platform.claude.com/docs/en/build-with-claude/refusals-and-fallback) applies. A dec
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/opus-5-5/migration-guide
±changed
+2−2
apichanged
models/opus-5-5/migration-guide
2. **Consider mid-conversation tool changes (beta):** Mid-conversation tool changes (beta header `mid-conversation-tool-changes-2026-07-01`) are available on the Claude API, Amazon
2. **Consider mid-conversation tool changes (beta):** Mid-conversation tool changes let you add or remove tools between turns of a conversation without invalidating [prompt cache](
5. **Migrate to output\_config.format:** If using structured outputs, update `output_format={...}` to `output_config={"format": {...}}`. The API still accepts the deprecated `outpu
5. **Migrate to output\_config.format:** If using structured outputs, update `output_format={...}` to `output_config={"format": {...}}`. The `output_format` parameter is deprecated
+2 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5/migration-guide
±changed
+1−1
apichanged
models/fable-5/migration-guide
You are not billed for the input tokens of a request refused before any output is generated. When a classifier fires mid-stream, the input and already-streamed output are billed
A refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
±changed
+1−1
apichanged
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
You are not billed for a request that is refused before any output is generated. When you retry on another model, [fallback credit](https://platform.claude.com/docs/en/build-with-c
A refusal that arrives before any output is billed when it is in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale.
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
* **Billing:** you aren't billed for a refusal that arrives before any output, and, for Claude Fable 5.1, [fallback credit](https://platform.claude.com/docs/en/build-with-claude/fa
* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safegua
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
models/fable-5-1/migration-guide
±changed
+1−1
apichanged
models/fable-5-1/migration-guide
2. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://p
2. **Change instructions and tools with mid-conversation system messages:** To change instructions or tools partway through a session, append a [`role: "system"` message](https://p
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/webhooks
±changed
+1−1
apichanged
managed-agents/webhooks
Every delivery carries the `webhook-id`, `webhook-timestamp`, and `webhook-signature` headers. Use the SDK's `unwrap()` helper to verify the signature and parse the event in one st
Every delivery carries the `webhook-id`, `webhook-timestamp`, and `webhook-signature` headers. Use the SDK's `unwrap()` (csharp, go: `Unwrap()`) helper to verify the signature and
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/vaults
±changed
+1−1
apichanged
managed-agents/vaults
To diagnose why a refresh failed, call `POST /v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` (or `client.beta.vaults.credentials.mcp_oauth_validate(...)` in t
To diagnose why a refresh failed, call `POST /v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` (or `client.beta.vaults.credentials.mcp_oauth_validate(...)` (typ
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/sessions
±changed
+1−2
apichanged
managed-agents/sessions
* **Set the field to a value:** The value replaces the agent's value in full. Overrides never merge with the agent's configuration, so a `tools` override must list every tool the s
* An `effort` level inside a per-session `model` override isn't applied, and because the override replaces the agent's `model` object in full, the agent's own `effort` isn't carr
* **Set the field to a value:** The value replaces the agent's value in full. Overrides never merge with the agent's configuration, so a `tools` override must list every tool the s
+1 −2 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/self-hosted-sandboxes
±changed
+27−27
apichanged
managed-agents/self-hosted-sandboxes
When you hand a claimed work item to `handle_item()` yourself, as this handler does, pass the work item's `secret` along as `work_secret` (`workSecret` in TypeScript, `Work
When you hand a claimed work item to `handle_item()` (typescript: `handleItem()`; go: `HandleItem()`) yourself, as this handler does, pass the work item's `secret` along as
* `.run()`: runs indefinitely, picking up sessions as they arrive.
* `.handle_item()`: handles a single claimed work item and exits. Pass the work, session, and environment identifiers explicitly, or let it read the `ANTHROPIC_*` variables that
* `memory_sync_interval` (`memorySyncIntervalMs` in TypeScript, `MemorySyncInterval` in Go) and `memory_sync_deletions` (`memorySyncDeletions`, `MemorySyncDeletions`): how often
+27 −27 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/migration
±changed
+10−10
apichanged
managed-agents/migration
| Agent SDK | Managed Agents
| --------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------
| `ClaudeAgentOptions(...)` constructed per run | `client.beta.agents.create(...)` once; the Agent is persisted and versioned server-side. See [Agent setup](https
| `async with ClaudeSDKClient(...)` or `query(...)` | `client.beta.sessions.create(...)` then send and receive [events](https://platform.claude.com/docs/en/managed-ag
| `@tool`-decorated functions dispatched automatically by the SDK | Declare as `{"type": "custom", ...}` on the Agent; your client handles `agent.custom_tool_use` events and replie
+10 −10 lines
Recorded here 24 Sep 2026 17:37 UTC
api
managed-agents/agent-setup
±changed
+1−1
apichanged
managed-agents/agent-setup
You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. An `effort` level set inside a per-session `model` ov
You can also override `model`, `system`, `tools`, `mcp_servers`, and `skills` for a single session without changing the agent. A `model` override replaces the agent's `model` objec
+1 −1 lines
Recorded here 24 Sep 2026 17:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.