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
812pages tracked
765 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 22 Oct 2026
100 on this page
ReadSourcePageWhatLines
1 Sep 2026
343 pages
+14764 −2864 lines
claude-code
agent-sdk/typescript
±changed
+2−2
claude-codechanged
agent-sdk/typescript
`SDKAssistantMessageError` is one of: `'authentication_failed'`, `'oauth_org_not_allowed'`, `'billing_error'`, `'rate_limit'`, `'overloaded'`, `'invalid_request'`, `'model_not_foun
`SDKAssistantMessageError` is one of: `'authentication_failed'`, `'oauth_org_not_allowed'`, `'account_on_hold'`, `'billing_error'`, `'rate_limit'`, `'overloaded'`, `'invalid_reques
This tool is available only when the session is authenticated with a claude.ai account on a plan with Routines enabled, and is absent when your organization's policy disables [Clau
This tool is available only when the session is authenticated with a claude.ai account on a plan with Routines enabled, and is absent when your organization's policy disables [Clau
+2 −2 lines
Recorded here 1 Sep 2026 03:37 UTC
claude-docs
claude-science/network-requirements
±changed
+10−9
claude-docschanged
claude-science/network-requirements
| Domain | Required when | Purpose
| --------------------------------------- | --------------------------------------------------- | ----------------------------------------------------------------------------------
| `claude.ai` | Always | Browser-based sign-in, usage analytics, feature configuration, and the catalog of
| `platform.claude.com` | Always | Completing sign-in (the OAuth token exchange)
| `api.anthropic.com` | Always | The Claude API for every request Claude makes, plus account and usage information
+10 −9 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/manage-on-devices
±changed
+7−3
claude-docschanged
claude-science/manage-on-devices
| disable\_telemetry = true | Stops the app from sending product-usage telemetry to Anthropic.
| disable\_telemetry = true | Stops the app from sending product-usage telemetry and error reports to Anthropic.
The app sends product-usage telemetry (event counts and timings, not conversation content) to Anthropic. There's no in-app setting for this; consent is covered by your organization
The app sends product-usage telemetry (event counts and timings, not conversation content) to Anthropic. There's no in-app setting for this; consent is covered by your organization
+7 −3 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/how-claude-science-works-with-your-data
±changed
+1−1
claude-docschanged
claude-science/how-claude-science-works-with-your-data
Each time the app calls Claude, the prompt and Claude's response travel to Anthropic's servers and are logged under Anthropic's standard retention policy for model traffic (see How
Each time the app calls Claude, the prompt and Claude's response travel to Anthropic's servers and are logged under Anthropic's standard retention policy for model traffic (see How
+1 −1 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/glossary
±changed
+4−4
claude-docschanged
claude-science/glossary
> One-sentence definitions for the terms you meet in Claude Science, from annotation to workspace.
> One-sentence definitions for the terms you meet in Claude Science, from artifact to workspace.
One-sentence definitions for the terms you meet in Claude Science, from annotation to workspace.
**[Annotation](/docs/claude-science/annotations)**: a comment you pin to part of an artifact by selecting it; Claude reads pending annotations as instructions on its next turn.
+4 −4 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/corporate-networks
±changed
+2−2
claude-docschanged
claude-science/corporate-networks
The `[network] ca_bundle` key in `config.toml` points at a PEM file whose certificates Claude Science adds to its default trust for sign-in, the Claude API, Anthropic-hosted connec
The `[network] ca_bundle` key in `config.toml` points at a PEM file whose certificates Claude Science adds to its default trust for sign-in, the Claude API, Anthropic-hosted connec
Code that Claude runs inside a session, such as a `pip install` typed into a cell or an R `install.packages()` call, does not see either bundle; behind TLS inspection, have Claude
Code that Claude runs inside a session, such as a `pip install` typed into a cell or an R `install.packages()` call, is covered on macOS but not on Linux. On macOS, Python, pip, cu
+2 −2 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/configuration-file-reference
±changed
+7−7
claude-docschanged
claude-science/configuration-file-reference
The `[network]` table configures the app's own connections to Anthropic.
The `[network]` table configures the app's own connections.
| Key | Type | Default | Effect
| ----------------- | ------------------------------------ | -------- | ------------------------------------------------------------------------------------------------------------
| `proxy` | string (URL) | unset | The outbound proxy for the app's HTTP and HTTPS connections, for example `http://proxy.example.corp:8080`. S
+7 −7 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/comments
+new page
+19−0
claude-docsnew page
claude-science/comments
No line of the body moved in this read.
+19 −0 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/command-line-settings
±changed
+1−1
claude-docschanged
claude-science/command-line-settings
`DO_NOT_TRACK`, set to any value, turns usage analytics off. It is the same switch as `disable_telemetry = true` in the configuration file. `GITHUB_TOKEN` is optional and is used o
`DO_NOT_TRACK`, set to any value other than `0` or `false`, turns usage analytics and error reports off. It is the same switch as `disable_telemetry = true` in the configuration fi
+1 −1 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/changelog
±changed
+6−0
claude-docschanged
claude-science/changelog
<Update label="0.1.43" description="August 31, 2026">
* On Linux, commands, notebook cells, and local connectors work again on systems with bubblewrap's recent security update
* Cloud storage in Settings (Amazon S3, S3-compatible services, and Google Cloud Storage with HMAC keys) now works behind a TLS-inspecting proxy such as Zscaler or Netskope, trus
* Various bug fixes and security improvements
+6 −0 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/annotations
−removed
+0−19
claude-docsremoved
claude-science/annotations
No line of the body moved in this read.
+0 −19 lines
Recorded here 1 Sep 2026 03:07 UTC
claude-docs
claude-science/whats-not-available-yet
±changed
+3−3
claude-docschanged
claude-science/whats-not-available-yet
Claude Science is in beta, and some admin controls you use with other Claude products don't govern it yet. The setup wizard lists some of these when you enable the product; this pa
Claude Science is in beta, and some admin controls you use with other Claude products don't govern it yet. This page lists them. See [Admin controls](/docs/claude-science/admin-con
Your organization's connector and domain allowlists apply to Directory connectors you publish, but don't restrict connectors a member adds locally (running on their own computer or
Your organization's connector allowlist applies to Directory connectors you publish, and doesn't filter the custom connectors a member adds in the app; you can only turn custom con
Your session-duration setting limits the browser sign-in step only. After a member signs in, the app holds its own token and stays signed in beyond that window.
+3 −3 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/remote-compute-clusters
±changed
+2−0
claude-docschanged
claude-science/remote-compute-clusters
On Team and Enterprise plans, your organization can turn SSH hosts off. When it has, **Add SSH host** isn't available, hosts you added earlier stay listed but refuse new commands a
+2 −0 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/network-requirements
±changed
+9−5
claude-docschanged
claude-science/network-requirements
Claude Science connects to a small, fixed set of domains for sign-in, the Claude API, and the app's own literature search, and to a larger, member-adjustable set of package and res
Claude Science connects to a small, fixed set of domains for sign-in, the Claude API, and the app's own literature search, and to a larger set of package and research domains when
Connections are outbound-only and almost entirely HTTPS on TCP 443 (an internal package mirror may use 8443). The app's own domains are fixed, apart from open-access full-text down
Connections are outbound-only and almost entirely HTTPS on TCP 443 (an internal package mirror may use 8443). The app's own domains are fixed, apart from open-access full-text down
When Claude runs code, its network access passes through a local filtering proxy that allows only the domains on the sandbox's built-in allowlist, grouped by purpose below. These a
+9 −5 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/manage-on-devices
±changed
+1−1
claude-docschanged
claude-science/manage-on-devices
To set configuration keys organization-wide, deploy \~/.claude-science/config.toml through your MDM or endpoint tool. Claude Science doesn't read a system-level managed-preferences
To set configuration keys organization-wide, deploy \~/.claude-science/config.toml through your MDM or endpoint tool. Claude Science doesn't read a system-level managed-preferences
+1 −1 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/how-claude-science-works-with-your-data
±changed
+3−3
claude-docschanged
claude-science/how-claude-science-works-with-your-data
When a member chooses to connect the app to remote compute (an owned server or cloud account they control), the app sends code and data directly to that destination. That traffic d
When a member chooses to connect the app to remote compute (an owned server or cloud account they control), the app sends code and data directly to that destination. That traffic d
Directory connectors you publish as an admin are reached through Anthropic's hosted connector service, so your directory connector permissions and tunnels apply. Connectors a membe
Directory connectors you publish as an admin are reached through Anthropic's hosted connector service, so your directory connector permissions and tunnels apply. Connectors a membe
Because conversations and artifacts live on members' computers, Custom Data Retention and Org Data Export don't reach that local data. For Enterprise organizations with the Complia
+3 −3 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/glossary
±changed
+1−1
claude-docschanged
claude-science/glossary
**Network allowlist**: the list under Settings of every outside host that sandboxed code may reach.
**Network allowlist**: the list of every outside host that sandboxed code may reach, kept under Settings or, on Team and Enterprise plans, managed by your organization.
+1 −1 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/enable-claude-science
±changed
+29−26
claude-docschanged
claude-science/enable-claude-science
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations. Turning it on in Organization settings > Claude Science walks yo
Claude Science is a desktop app for scientific research. It's off by default for Team and Enterprise organizations. Turning it on in **Organization settings** > **Claude Science**
| Plan | Claude Science app access |
| ----------- | ------------------------------------- |
| Team | Off; turn on in Organization settings |
+29 −26 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/custom-connectors
±changed
+3−1
claude-docschanged
claude-science/custom-connectors
In **Settings > Connectors** > **Add connector**, choose Remote or Local command and enter a **Name** (lowercase letters, digits, hyphens). For Remote, enter the server URL; Advanc
In **Settings > Connectors** > **Add connector**, choose **Remote** or **Local command** and enter a **Name** (lowercase letters, digits, hyphens). For **Remote**, enter the server
On Team and Enterprise plans, you can add and use custom connectors only if your organization allows them. When it doesn't, the **Remote** and **Local command** options under **Add
+3 −1 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/corporate-networks
±changed
+4−2
claude-docschanged
claude-science/corporate-networks
When your network blocks the public package hosts (`conda.anaconda.org`, `repo.anaconda.com`, `pypi.org`), point Claude Science at your internal artifact repository instead, and ev
When your network blocks the public package hosts (`conda.anaconda.org`, `repo.anaconda.com`, `pypi.org`), point Claude Science at your internal artifact repository instead, and ev
The organization setting takes a conda channel URL and a Python package index (PyPI) URL, which apply to every member whether or not the organization manages the network allowlist.
Configuring a mirror removes the public package hosts from the sandbox's network allowlist and admits the mirror host in their place, so a misconfigured mirror fails with an error
+4 −2 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/core-concepts
±changed
+2−0
claude-docschanged
claude-science/core-concepts
Facts Claude recalls for a session are sent to Anthropic as part of that session's conversation, and Anthropic retains them as [How Claude Science works with your data](/docs/claud
+2 −0 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/connectors-and-skills
±changed
+4−4
claude-docschanged
claude-science/connectors-and-skills
Claude Science includes Featured connectors to public life-sciences databases. All are on by default and can be turned off individually in **Settings > Connectors**. Featured conne
Claude Science includes Featured connectors to public life-sciences databases. They're on by default and can be turned off individually in **Settings > Connectors**. On Team and En
By choosing to enable connectors, you authorize Claude to use the optional enabled resources on your behalf and confirm you have the necessary rights and licenses. These resources
By choosing to enable connectors, you authorize Claude to use the optional enabled resources on your behalf and confirm you have the necessary rights and licenses. These resources
Claude loads a skill automatically when the work calls for it. Type **/** in the composer to open the skill picker and insert one explicitly.
+4 −4 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/configuration-file-reference
±changed
+12−12
claude-docschanged
claude-science/configuration-file-reference
The network-related keys, grouped by the TOML table each belongs to. For the package-mirror keys (`[conda] channel_mirror`, `pip_index_url`, and `ca_bundle`) and the proxy key (`[n
The network-related keys, grouped by the TOML table each belongs to. For the package-mirror keys (`[conda] channel_mirror`, `pip_index_url`, and `ca_bundle`) and the proxy key (`[n
| Key | Type | Default | Effect
| ----------------------- | ---------------------- | ------- | ---------------------------------------------------------------------------------------------------------------------
| `channel_mirror` | string (URL) | unset | Base URL of an internal conda mirror. Channel names resolve beneath it, so `<channel_mirror>/conda-forge/noarch/repod
+12 −12 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/compute-providers
±changed
+9−1
claude-docschanged
claude-science/compute-providers
### Workspace restrictions set by your organization
On Team and Enterprise plans, your organization's admin can limit Modal to specific workspaces. When Claude uses your Modal token, the app checks the workspace that Modal reports f
+9 −1 lines
Recorded here 1 Sep 2026 01:07 UTC
claude-docs
claude-science/admin-controls
±changed
+221−78
claude-docschanged
claude-science/admin-controls
> Members sign in to Claude Science with their Claude account, so your identity and billing controls apply automatically.
Members sign in to Claude Science with their Claude account, so your identity and billing controls apply automatically. Because the app stores conversations on each member's comput
Legend: Supported / Partial / Not available / Not applicable
+221 −78 lines
Recorded here 1 Sep 2026 01:07 UTC
31 Aug 2026
113 pages
+1591 −583 lines
claude-code
agent-sdk/subagents
±changed
+11−19
claude-codechanged
agent-sdk/subagents
This guide explains how to define and use subagents in the SDK using the `agents` parameter.
Define subagents directly in your code using the `agents` parameter. Claude invokes subagents through the `Agent` tool, so include `Agent` in `allowedTools` to auto-approve subagen
Define subagents directly in your code using the `agents` parameter. Claude invokes subagents through the `Agent` tool.
# Auto-approve these tools, including Agent for subagent invocation
+11 −19 lines
Recorded here 31 Aug 2026 23:07 UTC
api
release-notes/overview
±changed
+1−1
apichanged
release-notes/overview
* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-a
* The Python, TypeScript, Go, Java, Ruby, PHP, and C# SDKs now include support for `code_execution_20260120`, the [code execution tool](https://platform.claude.com/docs/en/agents-a
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
models/sonnet-5/migration-guide
±changed
+1−1
apichanged
models/sonnet-5/migration-guide
/claude-api migrate this project to claude-opus-5
/claude-api migrate this project to claude-sonnet-5
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
models/overview
±changed
+1−1
apichanged
models/overview
Once you've picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). For how model IDs, aliases, and snapshots work, see [Model IDs
Once you've picked a model, [learn how to make your first API call](https://platform.claude.com/docs/en/get-started). To understand how model IDs, aliases, and snapshots work, see
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
models/haiku-4-5/migration-guide
±changed
+1−1
apichanged
models/haiku-4-5/migration-guide
/claude-api migrate this project to claude-opus-5
/claude-api migrate this project to claude-haiku-4-5
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
models/fable-5/migration-guide
±changed
+1−1
apichanged
models/fable-5/migration-guide
/claude-api migrate this project to claude-opus-5
/claude-api migrate this project to claude-fable-5
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
managed-agents/memory
±changed
+1−1
apichanged
managed-agents/memory
For a `read_only` store, the worker's `write` and `edit` tools refuse changes under that directory and the worker never uploads anything from it. For how the worker resolves writ
For a `read_only` store, the worker's `write` and `edit` tools refuse changes under that directory and the worker never uploads anything from it. To learn how the worker resolves
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
managed-agents/budgets
±changed
+1−1
apichanged
managed-agents/budgets
For reading usage from the stream and the session object, see [Tracking usage](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tracking-usage).
To read usage from the stream and the session object, see [Tracking usage](https://platform.claude.com/docs/en/managed-agents/events-and-streaming#tracking-usage).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/inference-hooks-endpoint
±changed
+4−2
apichanged
manage-claude/inference-hooks-endpoint
For turning Inference hooks on and pointing them at your endpoint, see [Configure Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration).
To turn Inference hooks on and point them at your endpoint, see [Configure Inference hooks](https://platform.claude.com/docs/en/manage-claude/inference-hooks-configuration). To lea
Sustained webhook failures attributable to your AI security server trip a circuit breaker that stops enforcement: Anthropic stops contacting your server, and failure handling appli
Sustained webhook failures attributable to your AI security server trip a circuit breaker that stops enforcement: Anthropic stops contacting your server, and failure handling appli
+4 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/inference-hooks-configuration
±changed
+7−3
apichanged
manage-claude/inference-hooks-configuration
Inference hooks send prompts from your organization to an AI security server you choose, and hold each request for an allow or deny verdict before Claude processes it. This page wa
Inference hooks send prompts from your organization to an AI security server you choose, and hold each request for an allow or deny verdict before Claude processes it. This page wa
Sustained webhook failures attributable to your AI security server trip the circuit breaker, which stops enforcement: your server is no longer contacted, and your **Failure handlin
Sustained webhook failures attributable to your AI security server trip the circuit breaker, which stops enforcement: your server is no longer contacted, and your **Failure handlin
+7 −3 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/inference-hooks
±changed
+5−5
apichanged
manage-claude/inference-hooks
| | Inference hooks | Compliance API
| ------------ | --------------------------------------------------- | -------------------------------------------------------------------------------------------------------------
| When it acts | Inline, before inference runs | After the fact
| What it does | Allows or denies each governed request in real time | Retrieves activity, chats, files, projects, Cowork and Claude Code session transcripts, and users for audit a
| Direction | Anthropic calls your AI security server | You call Anthropic's API
+5 −5 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/data-residency
±changed
+1−1
apichanged
manage-claude/data-residency
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-sessions
±changed
+2−2
apichanged
manage-claude/compliance-sessions
Anthropic recommends the Compliance API for retrieving the content of Cowork and Claude Code sessions. The following table compares [local sessions](https://platform.claude.com/doc
Anthropic recommends the Compliance API for retrieving session content. The following table compares [local sessions](https://platform.claude.com/docs/en/manage-claude/compliance-s
The session endpoints are read-only; local and remote sessions cannot be deleted through the Compliance API. Local session transcripts are retained for 6 years by default, or your
The session endpoints are read-only; local and remote sessions cannot be deleted through the Compliance API. Local session transcripts are retained for 6 years by default, or your
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-integration-patterns
±changed
+1−1
apichanged
manage-claude/compliance-integration-patterns
For how the rest of the Claude Platform handles retention, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how the rest of the Claude Platform handles retention, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-faq
±changed
+3−3
apichanged
manage-claude/compliance-faq
To retrieve message bodies and file contents, use the chat, message, and file endpoints with a Compliance Access Key carrying `read:compliance_user_data`. The same key and scop
To retrieve message bodies and file contents, use the chat, message, and file endpoints with a Compliance Access Key carrying `read:compliance_user_data`. The same key and scop
<Accordion title="What do Cowork, Claude Code, Claude Science, and Claude for Microsoft 365 session transcripts include?">
<Accordion title="What do session transcripts include?">
Cowork and Claude Code session transcripts have boundaries of their own. Local sessions are captured only as their requests reach the Claude API, so on-device activity that nev
+3 −3 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-content-data
±changed
+1−1
apichanged
manage-claude/compliance-content-data
The endpoints on this page are available only to Claude Enterprise organizations. They retrieve and delete claude.ai chats, files, and projects; Cowork and Claude Code session tr
The endpoints on this page are available only to Claude Enterprise organizations. They retrieve and delete claude.ai chats, files, and projects; transcripts of sessions in apps s
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-api-access
±changed
+9−9
apichanged
manage-claude/compliance-api-access
| Key type | Created in | Used for
| ---------------------------------------------- | ----------------------------------------------------------------------------------------- | -------------------------------------
| **Compliance Access Key** (`sk-ant-api01-...`) | [claude.ai > Organization settings > API](https://claude.ai/admin-settings/api-access) | Activity Feed, chats, files, projects
| **Admin API key** (`sk-ant-admin01-...`) | [Claude Console > Settings > Admin keys](https://platform.claude.com/settings/admin-keys) | The [Admin API](https://platform.clau
| **Analytics API key** | [claude.ai > Organization settings > API](https://claude.ai/admin-settings/api-access) | The Claude Enterprise Analytics API (
+9 −9 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/compliance-api
±changed
+1−1
apichanged
manage-claude/compliance-api
description: Programmatic access to your organization's Claude activity, chats, files, projects, Claude Cowork and Claude Code sessions, and users for compliance, audit, and govern
description: Programmatic access to your organization's Claude activity, chats, files, projects, sessions in Claude apps, and users for compliance, audit, and governance.
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/cmek-aws-kms
±changed
+3−3
apichanged
manage-claude/cmek-aws-kms
* **Key requirements:** The key must be a symmetric KMS key with encrypt and decrypt usage, single-region, and in the same AWS account and region as the workspace you attach it to.
* **No separate validation step:** The key is validated when you attach it to a workspace. The attach call performs an encrypt/decrypt round against the key with that workspace's c
* **Key requirements:** The key must be a symmetric KMS key with encrypt and decrypt usage, single-region, and in the same AWS account and region as the workspace you attach it to.
* **No separate validation step:** Apart from those checks on the key ARN at registration, the key is validated when you attach it to a workspace. The attach call performs an encry
In the Claude Console, open **Settings > Encryption keys** and click **Add key**. Enter a display name, then choose the key from the key picker or choose **Enter ARN manually**
+3 −3 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/api-and-data-retention
±changed
+1−1
apichanged
manage-claude/api-and-data-retention
Several retention models sit outside the ZDR and HIPAA arrangements described on this page. Data accessible through the [Compliance API](https://platform.claude.com/docs/en/manage-
Several retention models sit outside the ZDR and HIPAA arrangements described on this page. Data accessible through the [Compliance API](https://platform.claude.com/docs/en/manage-
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
manage-claude/admin-api-keys
±changed
+14−14
apichanged
manage-claude/admin-api-keys
| To call...
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| Admin API [user management](https://platform.claude.com/docs/en/manage-claude/user-management): list and look up members and invites; read custom roles and their permissions
| 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): read groups and their members
+14 −14 lines
Recorded here 31 Aug 2026 22:07 UTC
api
cli-sdks-libraries/cli/using
±changed
+1−1
apichanged
cli-sdks-libraries/cli/using
This page covers the `ant` CLI's input and output mechanics that apply across every endpoint. For installing and authenticating, see the [Quickstart](https://platform.claude.com/do
This page covers the `ant` CLI's input and output mechanics that apply across every endpoint. To install and authenticate, see the [Quickstart](https://platform.claude.com/docs/en/
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/working-with-messages
±changed
+1−1
apichanged
build-with-claude/working-with-messages
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/token-counting
±changed
+3−3
apichanged
build-with-claude/token-counting
| Start | 2,000 |
| Build | 4,000 |
| Scale | 8,000 |
| Start | 5,000 |
| Build | 10,000 |
+3 −3 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/thinking-troubleshooting
±changed
+2−2
apichanged
build-with-claude/thinking-troubleshooting
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
This page covers the most common failures when configuring thinking or round-tripping thinking blocks (sending returned thinking blocks back in later requests). The first section m
This page covers the most common failures when configuring thinking or round-tripping thinking blocks (sending returned thinking blocks back in later requests). The first section m
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+1−1
apichanged
build-with-claude/thinking-tool-workflows
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/thinking-steering-and-cost
±changed
+2−2
apichanged
build-with-claude/thinking-steering-and-cost
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For how to turn thinking on, how to read thinking output, and [thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-claude/thinking
To learn how to turn thinking on, how to read thinking output, and about [thinking output on Claude Fable 5 and Claude Mythos 5](https://platform.claude.com/docs/en/build-with-clau
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/thinking
±changed
+3−3
apichanged
build-with-claude/thinking
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For what each effort level does to thinking behavior, see the [per-level thinking behavior table](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-cost#e
To learn what each effort level does to thinking behavior, see the [per-level thinking behavior table](https://platform.claude.com/docs/en/build-with-claude/thinking-steering-and-c
For how thinking blocks are handled when you switch models mid-conversation, see [Thinking block preservation by model](https://platform.claude.com/docs/en/build-with-claude/thinki
+3 −3 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/structured-outputs
±changed
+1−1
apichanged
build-with-claude/structured-outputs
For enforcing JSON Schema compliance on tool inputs with grammar-constrained sampling, see [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-to
To enforce JSON Schema compliance on tool inputs with grammar-constrained sampling, see [Strict tool use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/strict-tool-
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/skills-guide
±changed
+2−2
apichanged
build-with-claude/skills-guide
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
Skills require the code execution tool, so use a model from its [model compatibility list](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#model-c
Skills require the code execution tool, so use a model from its [model compatibility list](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compati
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/search-results
±changed
+1−1
apichanged
build-with-claude/search-results
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
Claude's latest models are trained for precise instruction following and benefit from explicit direction to use specific tools. If you say "can you suggest some changes," Claude wi
Claude's latest models are trained for precise instruction following and benefit from explicit direction to use specific tools. If you say "can you suggest some changes," Claude wi
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/prompt-caching
±changed
+1−1
apichanged
build-with-claude/prompt-caching
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+1−1
apichanged
build-with-claude/mid-conversation-system-messages
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/files
±changed
+1−1
apichanged
build-with-claude/files
Referencing a `file_id` in a Messages request is supported on all models that support the given file type. [Images](https://platform.claude.com/docs/en/build-with-claude/vision) ar
Referencing a `file_id` in a Messages request is supported on all models that support the given file type. [Images](https://platform.claude.com/docs/en/build-with-claude/vision) ar
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/fast-mode
±changed
+1−1
apichanged
build-with-claude/fast-mode
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/extended-thinking
±changed
+2−2
apichanged
build-with-claude/extended-thinking
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For how thinking itself works, including thinking blocks and the response shape, the `display` parameter, streaming, thinking with tool use, and encryption, see the [thinking overv
To learn how thinking itself works, including thinking blocks and the response shape, the `display` parameter, streaming, thinking with tool use, and encryption, see the [thinking
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/effort
±changed
+1−1
apichanged
build-with-claude/effort
For how effort interacts with thinking and which control to reach for, see [Thinking and effort](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-effor
To learn how effort interacts with thinking and which control to reach for, see [Thinking and effort](https://platform.claude.com/docs/en/build-with-claude/thinking#thinking-and-
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/context-editing
±changed
+1−1
apichanged
build-with-claude/context-editing
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/claude-on-amazon-bedrock-legacy
±changed
+2−2
apichanged
build-with-claude/claude-on-amazon-bedrock-legacy
To invoke these models, pass an inference profile instead of the base model ID. The inference profile ID is the base model ID with a prefix from a column marked "Yes" in the follow
To invoke these models, pass an inference profile instead of the base model ID. The inference profile ID is the base model ID with a prefix from a column marked "Yes" in the follow
This section shows how to configure a bearer token in an SDK client. The SDKs also read the token from the `AWS_BEARER_TOKEN_BEDROCK` environment variable. For making direct
This section shows how to configure a bearer token in an SDK client. The SDKs also read the token from the `AWS_BEARER_TOKEN_BEDROCK` environment variable. To make direct HTT
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
build-with-claude/batch-processing
±changed
+1−1
apichanged
build-with-claude/batch-processing
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
api/claude-code/routines-fire
±changed
+1−1
apichanged
api/claude-code/routines-fire
View your remaining daily runs at [claude.ai/code/routines](https://claude.ai/code/routines). For how routine usage interacts with subscription limits and extra usage billing, see
View your remaining daily runs at [claude.ai/code/routines](https://claude.ai/code/routines). To learn how routine usage interacts with subscription limits and extra usage billing,
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/web-search-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For caching tool definitions across turns, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching).
To cache tool definitions across turns, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching).
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/web-fetch-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For caching tool definitions across turns, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching).
To cache tool definitions across turns, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching).
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+2−2
apichanged
agents-and-tools/tool-use/tool-search-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
For how `defer_loading` preserves prompt caching, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching).
To learn how `defer_loading` preserves prompt caching, see [Tool use with prompt caching](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-use-with-prompt-caching
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/tool-reference
±changed
+2−2
apichanged
agents-and-tools/tool-use/tool-reference
`cache_control` goes on the entry only; for where the breakpoint lands, including markers inside a batch action, see [Tool use with prompt caching](https://platform.claude.com/docs
`cache_control` goes on the entry only; to learn where the breakpoint lands, including markers inside a batch action, see [Tool use with prompt caching](https://platform.claude.com
For how to combine `defer_loading` with `cache_control` breakpoints, see the [Tool search tool prompt caching guidance](https://platform.claude.com/docs/en/agents-and-tools/tool-us
To learn how to combine `defer_loading` with `cache_control` breakpoints, see the [Tool search tool prompt caching guidance](https://platform.claude.com/docs/en/agents-and-tools/to
+2 −2 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/text-editor-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/text-editor-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+9−26
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
## Compatibility
- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `c
- Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry [1]; not available on Amazon Bedrock, Google Cloud
- Programmatic tool calling requires the code execution tool with the `code_execution_20260120` or later [tool version](https://platform.claude.com/docs/en/agents-and-tools/tool-us
+9 −26 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+1−1
apichanged
agents-and-tools/tool-use/overview
For connecting to Model Context Protocol (MCP) servers, see the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector). For building your own MCP clien
To connect to Model Context Protocol (MCP) servers, see the [MCP connector](https://platform.claude.com/docs/en/agents-and-tools/mcp-connector). To build your own MCP client, see t
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/memory-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/memory-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/fine-grained-tool-streaming
±changed
+1−1
apichanged
agents-and-tools/tool-use/fine-grained-tool-streaming
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/computer-use-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/computer-use-tool
For combining computer use with thinking, see [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking).
To combine computer use with thinking, see [Thinking](https://platform.claude.com/docs/en/build-with-claude/thinking).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+15−43
apichanged
agents-and-tools/tool-use/code-execution-tool
## Compatibility
- [ZDR](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention): not eligible
- Supported models: `claude-fable-5`, `claude-mythos-5`, `claude-opus-5`, `claude-opus-4-8`, `claude-opus-4-7`, `claude-opus-4-6`, `claude-opus-4-5-20251101`, `claude-sonnet-5`, `c
- Platforms: Claude API, Claude Platform on AWS, Microsoft Foundry [1]; not available on Amazon Bedrock, Google Cloud
- Every supported model accepts all three [tool versions](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#tool-versions). On Claude Haiku 4.5, pro
+15 −43 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/bash-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/bash-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/advisor-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/advisor-tool
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/mcp-connector
±changed
+1−1
apichanged
agents-and-tools/mcp-connector
For the full directory of Anthropic-provided tools and optional properties such as `defer_loading`, see the [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/to
For the full directory of Anthropic-provided tools and optional properties such as `defer_loading`, see the [Tool reference](https://platform.claude.com/docs/en/agents-and-tools/to
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/quickstart
±changed
+1−1
apichanged
agents-and-tools/agent-skills/quickstart
* **`model`:** A [model that supports the code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#model-compatibility)
* **`model`:** A [model that supports the code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool#compatibility)
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/overview
±changed
+1−1
apichanged
agents-and-tools/agent-skills/overview
For how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
To learn how zero data retention (ZDR) applies to this feature, see [API and data retention](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention).
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/enterprise
±changed
+1−1
apichanged
agents-and-tools/agent-skills/enterprise
Claude Enterprise organizations can turn on automated security scanning for custom Skills in claude.ai and Claude Cowork. The feature is in beta. After you turn on **Skill and plug
Claude Enterprise organizations can turn on automated security scanning for custom Skills in claude.ai and Claude Cowork. After you turn on **Skill and plugin security scanning** a
+1 −1 lines
Recorded here 31 Aug 2026 22:07 UTC
claude-code
changelog
±changed
+7−0
claude-codechanged
changelog
<Update label="2.1.252" description="August 31, 2026">
* Fixed Bash commands failing with "task output swap refused (tasks dir moved or linked)" on some Macs
* Fixed "always allow" not saving in a project that has no .claude/settings.local.json yet
* Fixed Remote Control sessions hosted by Claude Desktop or VS Code stalling for minutes after a tool finished when the connection to claude.ai was degraded
+7 −0 lines
Recorded here 31 Aug 2026 20:07 UTC
claude-docs
third-party/claude-desktop/extensions
±changed
+38−2
claude-docschanged
third-party/claude-desktop/extensions
"transport": "http",
"transport": "http",
In the in-app configuration window, each server you add under **Connectors** has a **Test this connection** button that runs a live MCP `initialize` and `tools/list` against the se
### OAuth sign-in
+38 −2 lines
Recorded here 31 Aug 2026 18:37 UTC
mcp
seps/2549-TTL-for-list-results
±changed
+1−1
mcpchanged
seps/2549-TTL-for-list-results
A misconfigured or malicious serer could set an excessively long TTL, causing clients to cache stale data for longer than desired. However, since the TTL is a hint and clients can
A misconfigured or malicious server could set an excessively long TTL, causing clients to cache stale data for longer than desired. However, since the TTL is a hint and clients can
+1 −1 lines
Recorded here 31 Aug 2026 17:07 UTC
mcp
seps/2549-TTL-for-list-results
±changed
+1−1
mcpchanged
seps/2549-TTL-for-list-results
> specification](/specification/latest) and its changelog for authoritative
> specification](/specification/latest.md) and its changelog for authoritative
+1 −1 lines
Upstream edited 31 Aug 2026 16:44 UTC Recorded here 22 Oct 2026 20:37 UTC
mcp
seps/2549-TTL-for-list-results
±changed
+11−17
mcpchanged
seps/2549-TTL-for-list-results
<div className="flex items-center gap-2 mb-4">
<Badge color="green" shape="pill">
Final
</Badge>
+11 −17 lines
Upstream edited 31 Aug 2026 16:44 UTC Recorded here 20 Oct 2026 20:07 UTC
mcp
seps/2549-TTL-for-list-results
±changed
+29−29
mcpchanged
seps/2549-TTL-for-list-results
| Field | Value |
| ------------- | ------------------------------------------------------------------------------- |
| **SEP** | 2549 |
| **Title** | TTL for List Results |
| **Status** | Final |
+29 −29 lines
Upstream edited 31 Aug 2026 16:44 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-code
sub-agents
±changed
+2−3
claude-codechanged
sub-agents
| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5`, or `inherit`. When you omit it, the s
| `model` | No | [Model](#choose-a-model) to use: `sonnet`, `opus`, `haiku`, `fable`, a full model ID such as `claude-opus-5`, or `inherit`. When you omit it, Claud
* **inherit**: use the same model as the main conversation, even when you set `CLAUDE_CODE_SUBAGENT_MODEL`
* **Omitted**: use the model from the [`CLAUDE_CODE_SUBAGENT_MODEL`](/docs/en/model-config#environment-variables) environment variable, or the main conversation's model when you ha
* **inherit**: use the same model as the main conversation
+2 −3 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
This span appears only when detailed beta tracing is active, which requires `ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`. Set the pair in your shell, user settings,
This span appears only when detailed beta tracing is active, which requires `ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`, a pair that also [changes where your logs
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
A hook process inherits the parent environment, apart from the `OTEL_*` exporter variables that Claude Code [removes from every subprocess it spawns](/docs/en/monitoring-usage#admi
A hook process inherits the parent environment, apart from the `OTEL_*` exporter variables that Claude Code [removes from every subprocess it spawns](/docs/en/monitoring-usage#admi
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
gateways
±changed
+1−1
claude-codechanged
gateways
* **Client telemetry**: Claude Code disables its Anthropic-bound client analytics when a session signs in to a Claude apps gateway. To keep pre-sign-in startup analytics off as wel
* **Client telemetry**: Claude Code disables its Anthropic-bound client analytics when a session signs in to a Claude apps gateway. To keep pre-sign-in startup analytics off as wel
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
env-vars
±changed
+2−2
claude-codechanged
env-vars
| `ANTHROPIC_PROFILE` | Name of the Anthropic profile to authenticate with, such as one created by [`ant auth login`](https://platform.claude.co
| `ANTHROPIC_PROFILE` | Name of the Anthropic profile to authenticate with, such as one created by [`ant auth login`](https://platform.claude.co
| `CLAUDE_CODE_SUBAGENT_MODEL` | The default model for [subagents](/docs/en/sub-agents#choose-a-model), [agent team](/docs/en/agent-teams#specify-teammat
| `CLAUDE_CODE_SUBAGENT_MODEL` | The default model for [subagents](/docs/en/sub-agents#choose-a-model), [agent team](/docs/en/agent-teams#specify-teammat
+2 −2 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+1−1
claude-codechanged
claude-apps-gateway-deploy
* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. Before the first sign-in, the CLI still sends startup events to A
* **Client analytics**: the CLI disables its own usage analytics and error reporting while signed in to a gateway. Before the first sign-in, the CLI still sends startup events to A
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
agent-teams
±changed
+1−1
claude-codechanged
agent-teams
`teammateDefaultModel` was removed in v2.1.234; Claude Code ignores a leftover value. Name the model in your prompt or set `CLAUDE_CODE_SUBAGENT_MODEL` instead.
`teammateDefaultModel` was removed in v2.1.234; Claude Code ignores a leftover value. Name the model in your prompt instead.
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
agent-sdk/typescript
±changed
+21−21
claude-codechanged
agent-sdk/typescript
| Field | Required | Description
| :------------------------------------ | :------- | :------------------------------------------------------------------------------------------------------------------------------
| `description` | Yes | Natural language description of when to use this agent
| `tools` | No | Array of allowed tool names. If omitted, inherits every [tool available to subagents](/docs/en/sub-agents#available-tools). To
| `disallowedTools` | No | Array of tool names to explicitly disallow for this agent. MCP server-level patterns are also accepted: `mcp__server` or `mcp__
+21 −21 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
agent-sdk/subagents
±changed
+15−15
claude-codechanged
agent-sdk/subagents
| Field | Type | Required | Description
| :---------------- | :---------------------------------------------------------- | :------- | :------------------------------------------------------------------------------------
| `description` | `string` | Yes | Natural language description of when to use this agent
| `prompt` | `string` | Yes | The agent's system prompt defining its role and behavior
| `tools` | `string[]` | No | Array of allowed tool names. If omitted, inherits every [tool available to subagents]
+15 −15 lines
Recorded here 31 Aug 2026 16:07 UTC
claude-code
agent-sdk/observability
±changed
+1−1
claude-codechanged
agent-sdk/observability
* **`claude_code.hook`:** wraps each [hook](/docs/en/agent-sdk/hooks) execution. Requires detailed beta tracing (`ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`).
* **`claude_code.hook`:** wraps each [hook](/docs/en/agent-sdk/hooks) execution. Requires detailed beta tracing (`ENABLE_BETA_TRACING_DETAILED=1` and `BETA_TRACING_ENDPOINT`), a pa
+1 −1 lines
Recorded here 31 Aug 2026 16:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.