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
820pages tracked
773 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 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
4 Sep 2026
213 pages
+4527 −2281 lines
api
api/admin/external_keys/update
±changed
+5−5
apichanged
api/admin/external_keys/update
Full ARN of the AWS KMS key.
Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and
IAM role ARN. Deprecated — Anthropic reaches the KMS key via a managed intermediate role; this field is ignored.
IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); thi
Full ARN of the AWS KMS key.
+5 −5 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/external_keys/retrieve
±changed
+3−3
apichanged
api/admin/external_keys/retrieve
Full ARN of the AWS KMS key.
Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and
IAM role ARN. Deprecated — Anthropic reaches the KMS key via a managed intermediate role; this field is ignored.
IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); thi
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
+3 −3 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/external_keys/list
±changed
+3−3
apichanged
api/admin/external_keys/list
Full ARN of the AWS KMS key.
Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, an
IAM role ARN. Deprecated — Anthropic reaches the KMS key via a managed intermediate role; this field is ignored.
IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); t
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
+3 −3 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/external_keys/delete
±changed
+1−1
apichanged
api/admin/external_keys/delete
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/external_keys/create
±changed
+5−5
apichanged
api/admin/external_keys/create
Full ARN of the AWS KMS key.
Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and
IAM role ARN. Deprecated — Anthropic reaches the KMS key via a managed intermediate role; this field is ignored.
IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); thi
Full ARN of the AWS KMS key.
+5 −5 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/external_keys
±changed
+26−26
apichanged
api/admin/external_keys
Full ARN of the AWS KMS key.
Full ARN of the AWS KMS key. On Claude Platform on AWS the key must be a single-Region key in your organization's own AWS account; cross-account keys, multi-Region keys, and
IAM role ARN. Deprecated — Anthropic reaches the KMS key via a managed intermediate role; this field is ignored.
IAM role ARN. Deprecated — Anthropic reaches the KMS key through its own intermediate role (or, on Claude Platform on AWS, with credentials AWS issues for the Workspace); thi
Full ARN of the AWS KMS key.
+26 −26 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/cost_report/retrieve
±changed
+1−1
apichanged
api/admin/cost_report/retrieve
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/cost_report
±changed
+1−1
apichanged
api/admin/cost_report
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/api_keys/update
±changed
+1−1
apichanged
api/admin/api_keys/update
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN" \
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN" \
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/api_keys/retrieve
±changed
+1−1
apichanged
api/admin/api_keys/retrieve
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/api_keys/list
±changed
+1−1
apichanged
api/admin/api_keys/list
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/api_keys
±changed
+3−3
apichanged
api/admin/api_keys
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN" \
+3 −3 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/usage/list_by_user
±changed
+47−1
apichanged
api/admin/analytics/usage/list_by_user
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+47 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/usage/list
±changed
+47−1
apichanged
api/admin/analytics/usage/list
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+47 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/usage
±changed
+130−2
apichanged
api/admin/analytics/usage
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+130 −2 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/skills/list
±changed
+1−1
apichanged
api/admin/analytics/skills/list
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types — user-defined names are withheld from the analytics pipeline). O
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types and plugin-delivered skills — user-defined names are withheld fro
+1 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/skills
±changed
+2−2
apichanged
api/admin/analytics/skills
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types — user-defined names are withheld from the analytics pipeline). O
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types and plugin-delivered skills — user-defined names are withheld fro
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types — user-defined names are withheld from the analytics pipeline). O
Human-readable display name for rows whose `skill_name` is an opaque skill id (user/organization skill types and plugin-delivered skills — user-defined names are withheld fro
+2 −2 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/cost/list_by_user
±changed
+47−1
apichanged
api/admin/analytics/cost/list_by_user
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+47 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/cost/list
±changed
+47−1
apichanged
api/admin/analytics/cost/list
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+47 −1 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics/cost
±changed
+130−2
apichanged
api/admin/analytics/cost
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+130 −2 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin/analytics
±changed
+189−5
apichanged
api/admin/analytics
- `claude_tag_categories: optional array of "dm" or "engaged" or "monitoring" or 2 more`
Filter to Claude Tag (Claude in Slack) usage in specific spend categories. Usage with no category never matches. `dm` usage is reported under the user's product rather than `clau
maxItems: 100
+189 −5 lines
Recorded here 4 Sep 2026 21:07 UTC
api
api/admin
±changed
+499−186
apichanged
api/admin
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN"
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN" \
-H "Authorization: Bearer $ANTHROPIC_AUTH_TOKEN" \
-H "Authorization: Bearer $ANTHROPIC_OAUTH_TOKEN"
+499 −186 lines
Recorded here 4 Sep 2026 21:07 UTC
claude-code
changelog
±changed
+70−0
claude-codechanged
changelog
<Update label="2.1.261" description="September 4, 2026">
* Added an "Organization policy" line to `/status` and `claude doctor` that says why your organization's policy could not be loaded, such as a proxy not passing the endpoint thro
* Added `bashOutputMaxChars` and `taskOutputMaxChars` settings to raise how much command and background-task output Claude receives inline before it is saved to a file, up to 128
* Added `--append-subagent-system-prompt-file` to read the subagent system prompt from a file, for prompts too large to pass on the command line
+70 −0 lines
Recorded here 4 Sep 2026 20:07 UTC
claude-docs
third-party/claude-desktop/ssh-remote-sessions
±changed
+2−1
claude-docschanged
third-party/claude-desktop/ssh-remote-sessions
* `disabledBuiltinTools`, `builtinToolPolicy`, and `autoModeEnabled`.
* `disabledBuiltinTools`, `builtinToolPolicy`, `autoModeEnabled`, and `disableBypassPermissionsMode`.
* [`blockReadsOutsideWorkingDirectories`](/docs/third-party/claude-desktop/configuration#blockreadsoutsideworkingdirectories), evaluated on the host, so the working directories and
+2 −1 lines
Recorded here 4 Sep 2026 19:07 UTC
claude-docs
third-party/claude-desktop/local-access
±changed
+1−1
claude-docschanged
third-party/claude-desktop/local-access
The allowlist controls what users can **attach**. Within an attached read/write folder, the agent can read and write every file the user's OS account can reach. To keep data out
The allowlist controls what users can **attach**. Within an attached read/write folder, the agent can read and write every file the user's OS account can reach. Data outside the
+1 −1 lines
Recorded here 4 Sep 2026 19:07 UTC
claude-docs
third-party/claude-desktop/code
±changed
+30−20
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`
+30 −20 lines
Recorded here 4 Sep 2026 19:07 UTC
claude-docs
government/security/security-and-data-handling
±changed
+3−3
claude-docschanged
government/security/security-and-data-handling
On macOS, those shell commands run inside an operating-system-level sandbox that the application builds from your organization's **Allowed network hosts** and **Allowed workspace f
On macOS, those shell commands run inside an operating-system-level sandbox that the application builds from your organization's **Allowed network hosts** and **Allowed workspace f
On Windows, there is no operating-system-level sandbox for Code sessions. Shell commands run directly on the device under the permission mode the user selects for the session and u
On Windows, there is no operating-system-level sandbox for Code sessions. Shell commands run directly on the device under the permission mode the user selects for the session and u
On both operating systems, the application starts a Code session only in a folder that **Allowed workspace folders** permits when that setting is configured. Administrators can als
+3 −3 lines
Recorded here 4 Sep 2026 19:07 UTC
claude-docs
government/config/settings
±changed
+1−1
claude-docschanged
government/config/settings
Controls which folders members can pick as a project folder in Claude Desktop, and where Claude can read and write files. Leave it unset to allow any folder. Add folder paths to li
Controls which folders members can pick as a project folder in Claude Desktop, and where Claude can read and write files. Leave it unset to allow any folder. Add folder paths to li
+1 −1 lines
Recorded here 4 Sep 2026 19:07 UTC
api
release-notes/overview
±changed
+4−0
apichanged
release-notes/overview
### September 3, 2026
* Version 1.30.0 of the `ant` CLI adds `ant apply`, which creates and updates agents, environments, skills, memory stores, and deployments from files in your repository. Describe e
+4 −0 lines
Recorded here 4 Sep 2026 18:37 UTC
api
build-with-claude/thinking
±changed
+13−348
apichanged
build-with-claude/thinking
Claude preserves a thinking block, keeping it usable on later turns, only under the conditions it was created in. Starting with Claude Fable 5.1 and Claude Mythos 5.1, a `thinking`
* **For the model that produced it, or a newer one.** An earlier model can't use the block, and the API drops it from that request. See [Only for the model that produced it, or a n
* **In the conversation that produced it (Claude Fable 5.1 only).** If the `system` prompt, the `tools`, or any earlier message changes, the block is no longer valid, and the API r
+13 −348 lines
Recorded here 4 Sep 2026 18:37 UTC
api
build-with-claude/preserved-thinking
±changed
+977−214
apichanged
build-with-claude/preserved-thinking
description: Modifying a conversation now results in an error or a dropped block; how to check whether your integration does that and how to migrate.
description: Preserved thinking lets a model use a thinking block from an earlier turn only if that model or an earlier one produced it and nothing before the block has changed.
On Claude Fable 5.1, changing prior turns in the conversation (the `system` prompt, the `tools`, or any earlier message) affects the API response. By default, it makes the API reje
When you send a block back, the API uses its `signature` to check that the prior conversation is unchanged and that the current model can read the block. The check exists so that r
+977 −214 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/web-tools
±changed
+1−1
claude-docschanged
third-party/claude-desktop/web-tools
Search queries go to whichever backend you configure. In every option, the query is also visible to your inference provider as part of the conversation, because the model emits the
Search queries go to whichever backend you configure. In every option, the query is also visible to your inference provider as part of the conversation, because the model emits the
+1 −1 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+23−20
claude-docschanged
third-party/claude-desktop/telemetry
* Cowork sessions do not support gRPC export. When `otlpProtocol` is set to `grpc`, Cowork sessions export over `http/protobuf` instead; other protocol values apply as configured.
* Cowork and [Chat](/docs/third-party/claude-desktop/chat) sessions export over the protocol as configured, except that when `otlpProtocol` is `grpc` they export over `http/protobu
The fallback changes the protocol only, not the endpoint. When `otlpProtocol` is `grpc`, the Cowork and desktop-application exports go to the same `otlpEndpoint` over HTTP; if that
These substitutions change the protocol only, not the endpoint. A stream that exports over HTTP while `otlpProtocol` is `grpc` still goes to the same `otlpEndpoint`; if that addres
| `userPrompts` | User message text |
+23 −20 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/ssh-remote-sessions
±changed
+4−4
claude-docschanged
third-party/claude-desktop/ssh-remote-sessions
1. **Connect.** The user picks an SSH host from the environment picker in the Code tab, or adds one by entering its address, port, and an identity file. Claude Desktop connects wit
1. **Connect.** The user picks an SSH host from the environment picker in Code, or adds one by entering its address, port, and an identity file. Claude Desktop connects with its bu
4. **Stream.** Claude's responses and tool output stream back to Claude Desktop. Permission prompts appear in the Code tab, and the engine waits on the host until the user answers.
4. **Stream.** Claude's responses and tool output stream back to Claude Desktop. Permission prompts appear in Claude Desktop, and the engine waits on the host until the user answer
The Claude Code engine is a standalone executable with no runtime dependencies. The device needs the OpenSSH client (`ssh` and `ssh-keygen`).
+4 −4 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/network-proxy
±changed
+2−2
claude-docschanged
third-party/claude-desktop/network-proxy
Pinning requires a Claude Desktop release that includes the `egressProxyUrl` and `egressProxyPacUrl` keys. The [configuration changelog](/docs/third-party/claude-desktop/configur
Pinning requires Claude Desktop 1.44121.1 or later. Earlier releases ignore the `egressProxyUrl` and `egressProxyPacUrl` keys and keep following the OS proxy settings.
The precedence described here requires the same Claude Desktop release as the pinned-proxy keys above. See the [configuration changelog](/docs/third-party/claude-desktop/configur
The precedence described here requires Claude Desktop 1.44121.1 or later, the same release as the pinned-proxy keys above.
+2 −2 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/gateway
±changed
+2−0
claude-docschanged
third-party/claude-desktop/gateway
The gateway should also preserve [prompt caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching). Cowork and Code sessions send `cache_control` breakpoints w
+2 −0 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/extensions
±changed
+3−1
claude-docschanged
third-party/claude-desktop/extensions
While the connection is open, only the TTL schedule triggers renewal; a failed request never re-runs the helper. A failed run does not interrupt the connection; Claude Desktop keep
While the connection is open, the TTL schedule triggers renewal, and a request that the server rejects with HTTP 401 or 403 also re-runs the helper and, when it returns new headers
To withdraw a plugin, remove its folder from `org-plugins/`. On Claude Desktop 1.46388.1 or later, each user's installed copy is unregistered the next time the app syncs organizati
+3 −1 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+1−1
claude-docschanged
third-party/claude-desktop/data-storage
* **Past chats are not searchable.** There is no index of conversation content, server-side or local (history exists only as the per-session files above), and a Chat conversation h
* **Claude cannot search past chats.** Users can search their own conversations in the app, which scans the per-session files on the device on demand, but there is no index of conv
+1 −1 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/connectors-m365
±changed
+23−14
claude-docschanged
third-party/claude-desktop/connectors-m365
Both connectors provide the same read and search tools; they differ in data path and authentication. Write actions (sending mail, managing drafts and calendar events, and working w
Both connectors provide the same read and search tools; they differ in data path and authentication. Write actions (sending mail, managing drafts and calendar events, working with
Three optional read scopes are not in the standard set:
Six optional read scopes are not in the standard set:
+23 −14 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+6−6
claude-docschanged
third-party/claude-desktop/configuration
```json theme={null} theme={null}
```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```json theme={null} theme={null}
```json theme={null} theme={null} theme={null} theme={null} theme={null} theme={null} theme={null}
```json theme={null} theme={null}
+6 −6 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/code
±changed
+21−21
claude-docschanged
third-party/claude-desktop/code
| Claude Desktop on 3P key | Effect in
| ---------------------------------------------------------------------------------------------------------------------------------------------------------------------- | ---------
| `inferenceProvider` and all provider credential keys (`inferenceGateway*`, `inferenceVertex*`, `inferenceBedrock*`, `inferenceFoundry*`, `inferenceCredentialHelper*`) | Selects t
| `inferenceModels` | Populates
| `autoModeEnabled` | Offers **
+21 −21 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/chat
±changed
+12−11
claude-docschanged
third-party/claude-desktop/chat
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
Chat in Claude Desktop on third-party (3P) is a conversational surface for quick questions and drafting. Unlike [Cowork](/docs/cowork/overview) and [Code](/docs/third-party/claude-
| Capability | Scope
| -------------------- | -----------------------------------------------------------------------------------------------------------------------------------------------------------
| Web search | Same options and rules as Cowork and Code sessions; depends on your provider or a configured search server. See [Web search](/docs/third-party/claude-deskt
+12 −11 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/bootstrap
±changed
+4−1
claude-docschanged
third-party/claude-desktop/bootstrap
Each configuration key in both schemas carries an `x-availableInVersion` annotation naming the first Claude Desktop release that reads it. The app sends its version as `Claude/<ver
* `bootstrapUrl`, `bootstrapOidc`, `bootstrapHeaders`, `bootstrapHeadersHelper`, `bootstrapEnabled`, and `trustBootstrapDelivery`: the trust anchor cannot redirect itself, authenti
* `bootstrapUrl`, `bootstrapOidc`, `bootstrapHeaders`, `bootstrapHeadersHelper`, `bootstrapEnabled`, and `trustBootstrapDelivery`: the trust anchor cannot redirect itself, authenti
* `egressProxyUrl` and `egressProxyPacUrl`: the app may need the [network proxy](/docs/third-party/claude-desktop/network-proxy#pin-a-proxy-from-managed-configuration) to reach you
+4 −1 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
government/security/security-and-data-handling
±changed
+4−4
claude-docschanged
government/security/security-and-data-handling
No. Claude for Government does not include an inline content-inspection or DLP gate. The available inspection points are your own network proxy, which sees all endpoint traffic
No. Claude for Government does not include an inline content-inspection or DLP gate. The available inspection points are your own network proxy, which sees all endpoint traffic
Chat, Cowork, and Code sessions write a local audit log to the user's disk recording tool invocations, permission decisions, and file operations; that log never leaves the devi
Chat, Cowork, and Code sessions write a local audit log to the user's disk recording tool invocations, permission decisions, and file operations; that log never leaves the devi
In Claude for Government, conversation content stays on the user's device. Model requests are proxied through the Claude for Government service to the model endpoint inside the Fed
+4 −4 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
government/config/settings
±changed
+30−4
claude-docschanged
government/config/settings
Members pick up a new or changed endpoint the next time they start Claude Desktop. From then on your collector receives OpenTelemetry logs and metrics for each member's activity un
Members pick up a new or changed endpoint the next time they start Claude Desktop. Once a member has signed in and the app has loaded their configuration from Claude for Government
* `claude-desktop` for error events from the application itself
* `claude-desktop` for events from the application itself, errors only by default
Each conversation turn produces events such as `user_prompt`, `api_request`, and `tool_result` that record the model, token counts, durations, and tool names. Every record also car
+30 −4 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
government/changelog
±changed
+4−0
claude-docschanged
government/changelog
<Update label="2026.09.04.1">
* Changed the limit on a member's active app sign-ins from 3 shared across the Claude apps to 6 in each app: a new sign-in over the limit now signs out the one closest to expirin
</Update>
+4 −0 lines
Recorded here 4 Sep 2026 18:37 UTC
claude-docs
third-party/claude-desktop/network-proxy
±changed
+20−20
claude-docschanged
third-party/claude-desktop/network-proxy
| Key | Value | Effect
| ------------------- | ----------------------------------------------------------------------------------------------- | ----------------------------------------------------------
| `egressProxyUrl` | An `http://` or `https://` proxy URL, for example `http://proxy.example.com:8080` | The app sends its traffic through this proxy, and the agen
| Key | Value | Effect |
| - | - | - |
+20 −20 lines
Upstream edited 4 Sep 2026 18:19 UTC Recorded here 28 Sep 2026 22:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.46388.3" description="2026-09-04">
No configuration changes in this release.
</Update>
+4 −0 lines
Recorded here 4 Sep 2026 17:07 UTC
claude-docs
cowork/changelog
±changed
+18−0
claude-docschanged
cowork/changelog
<Update label="v1.46388.3" description="2026-09-04">
**General**
* No user-facing changes.
+18 −0 lines
Recorded here 4 Sep 2026 17:07 UTC
claude-docs
government/security/security-and-data-handling
±changed
+3−3
claude-docschanged
government/security/security-and-data-handling
The allowlist governs outbound network access from the shell commands and package installs of Cowork sessions, which run in the sandbox virtual machine, from the sandboxed shel
The allowlist governs outbound network access from the shell commands and package installs of Cowork sessions, which run in the sandbox virtual machine, from the sandboxed shel
No. Claude for Government does not include an inline content-inspection or DLP gate. The available inspection points are your own network proxy, which sees all endpoint traffic
No. Claude for Government does not include an inline content-inspection or DLP gate. The available inspection points are your own network proxy, which sees all endpoint traffic
Chat includes a web fetch tool, and every fetch is checked against the same egress allowlist that governs Cowork. With the allowlist empty or unset, a fetch to anything other t
+3 −3 lines
Recorded here 4 Sep 2026 16:38 UTC
claude-docs
government/org-admin/compliance-api
±changed
+1−1
claude-docschanged
government/org-admin/compliance-api
* The desktop application's OpenTelemetry export is a separate log stream configured with **Telemetry endpoint (Claude Desktop)** on the [Config](/docs/government/config/settings#t
* The desktop application's OpenTelemetry export is a separate log stream configured with **Telemetry endpoint** on the [Config](/docs/government/config/settings#telemetry-endpoint
+1 −1 lines
Recorded here 4 Sep 2026 16:38 UTC
claude-docs
government/deploy-desktop/configure
±changed
+1−1
claude-docschanged
government/deploy-desktop/configure
| Where the app sends your agency's own telemetry, if you have set a collector | [Telemetry endpoint (Claude Desktop)](/docs/government/config/settings#tele
| Where the app sends your agency's own telemetry, if you have set a collector | [Telemetry endpoint](/docs/government/config/settings#telemetry-endpoint)
+1 −1 lines
Recorded here 4 Sep 2026 16:38 UTC
claude-docs
government/config/settings
±changed
+4−4
claude-docschanged
government/config/settings
### Telemetry endpoint (Claude Desktop)
### Telemetry endpoint
The value must begin with `https://` and may include a port and a path prefix. Its host must be a hostname or a private-network address, and a public IP address is refused. A match
The value must begin with `https://` and may include a port and a path prefix. Its host must be a hostname or a private-network address, and a public IP address is refused.
### Telemetry headers (Claude Desktop)
+4 −4 lines
Recorded here 4 Sep 2026 16:38 UTC
claude-code
keybindings
±changed
+21−1
claude-codechanged
keybindings
| `DiffPanel` | The [diff panel](/docs/en/interactive-mode#diff-panel) is open |
### Diff panel actions
Actions for the [diff panel](/docs/en/interactive-mode#diff-panel) that `/diff` opens in fullscreen rendering. `app:cycleDiffBase` is in the `DiffPanel` context, which is active wh
+21 −1 lines
Recorded here 4 Sep 2026 16:37 UTC
claude-code
interactive-mode
±changed
+43−0
claude-codechanged
interactive-mode
## Review changes with /diff
Run `/diff` to look over the changes in your working tree without leaving Claude Code. You see the edits Claude has made so far alongside anything else you haven't committed.
In [fullscreen rendering](/docs/en/fullscreen), `/diff` opens the [diff panel](#diff-panel) beside the conversation, which stays open and updates while you keep working. In the cla
+43 −0 lines
Recorded here 4 Sep 2026 16:37 UTC
claude-code
fullscreen
±changed
+4−0
claude-codechanged
fullscreen
## Watch your changes in the diff panel
In fullscreen rendering, [`/diff`](/docs/en/interactive-mode#review-changes-with-%2Fdiff) opens a panel beside the conversation rather than a viewer you have to close, so you can w
+4 −0 lines
Recorded here 4 Sep 2026 16:37 UTC
claude-code
commands
±changed
+1−1
claude-codechanged
commands
| `/diff` | Open an interactive diff viewer showing uncommitted changes and per-turn diffs. Us
| `/diff` | Review the changes in your working tree, including the edits Claude has made so fa
+1 −1 lines
Recorded here 4 Sep 2026 16:37 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.46388.2" description="2026-09-04">
No configuration changes in this release.
</Update>
+4 −0 lines
Recorded here 4 Sep 2026 15:37 UTC
claude-docs
cowork/changelog
±changed
+18−0
claude-docschanged
cowork/changelog
<Update label="v1.46388.2" description="2026-09-04">
**General**
* No user-facing changes.
+18 −0 lines
Recorded here 4 Sep 2026 15:37 UTC
claude-code
agent-sdk/overview
±changed
+1−0
claude-codechanged
agent-sdk/overview
* [Migration guide](/docs/en/agent-sdk/migration-guide): migrate from the Claude Code SDK packages to the Agent SDK
+1 −0 lines
Recorded here 4 Sep 2026 15:37 UTC
claude-code
agent-sdk/migration-guide
±changed
+2−0
claude-codechanged
agent-sdk/migration-guide
Migrating from the OpenAI Agents SDK instead? The [OpenAI Agents SDK migration recipe](https://platform.claude.com/cookbook/claude-agent-sdk-04-migrating-from-openai-agents-sdk) ma
+2 −0 lines
Recorded here 4 Sep 2026 15:37 UTC
claude-code
agent-sdk/migration-guide
±changed
+5−5
claude-codechanged
agent-sdk/migration-guide
| Aspect | Old | New |
| :------------------------- | :-------------------------- | :----------------------------------------------------------------------- |
| **Package Name (TS/JS)** | `@anthropic-ai/claude-code` | `@anthropic-ai/claude-agent-sdk` |
| **Python Package** | `claude-code-sdk` | `claude-agent-sdk` |
| **Documentation Location** | Claude Code docs | Claude Code docs → dedicated [Agent SDK](/docs/en/agent-sdk/overview) section |
+5 −5 lines
Upstream edited 4 Sep 2026 15:09 UTC Recorded here 28 Sep 2026 23:37 UTC
claude-code
permission-modes
±changed
+9−0
claude-codechanged
permission-modes
Claude Code v2.1.257 and later also block these by default:
* Requesting credentials from the cloud instance-metadata endpoint, such as `169.254.169.254`, or explicitly authenticating a cloud, cluster, or registry call with the machine's ow
* Reaching a public host by a route other than a direct request, such as a tunnel, a reverse shell, or a resolver or proxy configuration rewritten to point outside
* Reading credentials that belong to the host rather than to your task, such as node certificates or the node's container-registry auth
+9 −0 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
model-config
±changed
+1−1
claude-codechanged
model-config
On the Anthropic API, the `/model` picker lists a Fable model only after the server reports it available for your organization. When you type `/model fable` or a Fable model ID, Cl
On the Anthropic API, the `/model` picker lists a Fable model only after the server reports it available for your organization. When you type `/model fable` or a Fable model ID, Cl
+1 −1 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
keybindings
±changed
+2−2
claude-codechanged
keybindings
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation
| `chat:clearScreen` | Cmd+K | Force a full screen redraw, preserving input and conversation. See [Clear the conversation](/docs/en/fullscreen#clear-
| `chat:clearInput` | Ctrl+L | Force a full screen redraw, preserving input and conversation. In [fullscreen rendering](/docs/en/fullscreen#clear-the
| `chat:clearScreen` | Cmd+K | Same as `chat:clearInput`. See [Clear the conversation](/docs/en/fullscreen#clear-the-conversation) for how Cmd+K beha
+2 −2 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Ctrl+L` | Redraw screen
| `Ctrl+L` | Redraw or clear the screen
+1 −1 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
fullscreen
±changed
+5−3
claude-codechanged
fullscreen
Run `/clear` to start a new conversation. Pressing `Ctrl+L` or `Cmd+K` doesn't clear the conversation; Claude Code redraws the screen and keeps it. Before v2.1.238, Claude Code ran
On iTerm2 and Terminal.app, your terminal handles `Cmd+K` itself and clears its own screen without telling Claude Code. Claude Code detects the cleared screen and repaints the conv
Run `/clear` to start a new conversation.
+5 −3 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
errors
±changed
+18−1
claude-codechanged
errors
| `task output swap refused (tasks dir moved or linked)`
These errors come from Claude's built-in tools. Claude corrects most tool errors on its own; the first two below need a change from you, because they come from a subagent definitio
These errors come from Claude's built-in tools. Claude corrects most tool errors on its own. When one needs a change from you, that error's **What to do** list says what to change.
<h3 id="task-output-swap-refused">
Task output swap refused
+18 −1 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
auto-mode-config
±changed
+2−1
claude-codechanged
auto-mode-config
* **Context slots**: describe your organization, stack, and security posture so the classifier reads the other rules in your context. Unlike the other two kinds, context slots have
* **Context slots**: describe your organization, stack, and security posture so the classifier reads the other rules in your context. Each defaults to `None configured` or to the c
* **Host containment**: defaults to an ordinary developer machine or CI runner with open internet. If Claude Code runs in a container, VM, or pod with an egress allow-list or nei
+2 −1 lines
Recorded here 4 Sep 2026 15:07 UTC
claude-code
model-config
±changed
+9−0
claude-codechanged
model-config
#### A new session starts on a different model than you picked
When you pick a model with `/model` and your next session starts on something else, these are the usual causes:
* **You chose it for one session.** Pressing `s` in the picker, launching with `--model`, and running `/model` in non-interactive mode all apply to the current session and leave yo
+9 −0 lines
Recorded here 4 Sep 2026 14:37 UTC
claude-code
agent-sdk/troubleshooting
±changed
+1−1
claude-codechanged
agent-sdk/troubleshooting
# Troubleshooting
# Troubleshoot the Agent SDK
+1 −1 lines
Recorded here 4 Sep 2026 14:37 UTC
claude-code
agent-sdk/todo-tracking
±changed
+3−1
claude-codechanged
agent-sdk/todo-tracking
On TypeScript Agent SDK 0.3.233 and later, or Python Agent SDK 0.2.139 and later, the following tools aren't available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, or later versions
On TypeScript Agent SDK 0.3.233 and later, or Python Agent SDK 0.2.139 and later, the following restriction applies.
The following tools aren't available on Opus 4.8, Sonnet 5, Fable 5, Mythos 5, or later versions of those families unless you opt in:
+3 −1 lines
Recorded here 4 Sep 2026 14:37 UTC
claude-code
routines
±changed
+1−1
claude-codechanged
routines
* **Environment variables**: provide values Claude can use during each run. They're [visible to anyone who uses the environment](/docs/en/cloud-environments#what-carries-over-f
* **Environment variables**: provide values Claude can use during each run. They're [visible to anyone who uses the environment](/docs/en/cloud-environments#what-carries-over-f
+1 −1 lines
Recorded here 4 Sep 2026 05:07 UTC
claude-code
cloud-environments
±changed
+25−23
claude-codechanged
cloud-environments
Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environm
Each [cloud session](/docs/en/claude-code-on-the-web) runs in a cloud environment. You can configure an environment to allow or deny [network access](#access-levels), [set environm
Select **Add cloud environment**, or hover over an existing environment and select the settings icon that appears on the right. The dialog includes the name, network access lev
Select **Add cloud environment**, or hover over an existing environment and select the settings icon that appears on the right. The dialog includes the name, network access lev
Anyone who uses the environment can read the values. For a key the agent proxy can attach to a request, use an [API credential](#add-api-credentials) instead. The [requests that ne
+25 −23 lines
Recorded here 4 Sep 2026 05:07 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
* **API credentials**: in Anthropic-hosted environments, keys you [add to a cloud environment](/docs/en/cloud-environments#add-api-credentials) stay outside the sandbox the same wa
* **API credentials**: in Anthropic-hosted environments on Pro and Max plans, keys you [add to a cloud environment](/docs/en/cloud-environments#add-api-credentials) stay outside th
+1 −1 lines
Recorded here 4 Sep 2026 05:07 UTC
claude-code
server-managed-settings
±changed
+2−1
claude-codechanged
server-managed-settings
* **Managed CLAUDE.md content**: a `claudeMd` value delivered through managed settings
A managed CLAUDE.md delivered through the [`claudeMd`](/docs/en/settings-reference#claudemd) key doesn't require approval, because it's instruction text for Claude rather than a co
+2 −1 lines
Recorded here 4 Sep 2026 03:37 UTC
claude-code
claude-apps-gateway-config
±changed
+0−1
claude-codechanged
claude-apps-gateway-config
* managed CLAUDE.md content
+0 −1 lines
Recorded here 4 Sep 2026 03:37 UTC
claude-docs
third-party/claude-desktop/mdm
±changed
+8−4
claude-docschanged
third-party/claude-desktop/mdm
When a managed (MDM-delivered) configuration is already present on the device, the configuration window opens read-only: it shows what the admin deployed, marks the configuration
When a managed (MDM-delivered) configuration is already present on the device, the configuration window opens read-only: it shows what the admin deployed, marks the configuration
When a managed source sets any key other than the update keys or the network proxy keys, the managed configuration owns the device: it takes effect, the in-app configuration window
When a managed source sets any key other than the [app-behavior keys](#update-keys-and-managed-precedence) listed below, the managed configuration owns the device: it takes effect,
The update keys `disableAutoUpdates`, `autoUpdaterEnforcementHours`, and `updateViaUpdatesHost` are treated specially, so you can set an update policy from MDM without managing the
+8 −4 lines
Recorded here 4 Sep 2026 03:07 UTC
claude-docs
third-party/claude-desktop/installation
±changed
+1−1
claude-docschanged
third-party/claude-desktop/installation
Also confirm that the [in-app configuration window](/docs/third-party/claude-desktop/in-app-configuration) (**Developer → Configure Third-Party Inference…**) opens read-only on a m
Also confirm that the [in-app configuration window](/docs/third-party/claude-desktop/in-app-configuration) (**Developer → Configure Third-Party Inference…**) opens read-only on a m
+1 −1 lines
Recorded here 4 Sep 2026 03:07 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+6−6
claude-docschanged
third-party/claude-desktop/configuration
When a managed source is present, it wins and locally written values are ignored. The exception is a managed source that sets only the update keys (`disableAutoUpdates`, `autoUpdat
When a managed source is present, it wins and locally written values are ignored. The exception is a managed source that sets only [app-behavior keys](/docs/third-party/claude-desk
```json theme={null}
```json theme={null} theme={null}
```json theme={null}
+6 −6 lines
Recorded here 4 Sep 2026 03:07 UTC
claude-docs
third-party/claude-desktop/bootstrap
±changed
+6−4
claude-docschanged
third-party/claude-desktop/bootstrap
5. The response is cached in memory (until your `expiresAt`, or 1 hour by default). The app also re-polls in the background every 30 minutes with a conditional request, so an uncha
5. The response is cached in memory (until your `expiresAt`, or 1 hour by default). The app also re-checks in the background every [`configRecheckIntervalMinutes`](/docs/third-part
Claude Desktop 1.40609.0 and later enforce that restart. Once a background re-poll returns a changed response, the user can keep working for [`relaunchEnforcementHours`](/docs/thir
When rotating an inference credential, keep the previous credential valid until your fleet has relaunched. For devices that are running, that is roughly the 30-minute re-poll inter
+6 −4 lines
Recorded here 4 Sep 2026 03:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+32−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v1.46388.1" description="2026-09-04">
<div className="cfg-keys">
| MDM key | Type | Description |
| ---------------------------------------------------------------------------------------------------------------------- | --------- | --------------------------------------- |
+32 −0 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-docs
third-party/claude-desktop/configuration
±changed
+72−44
claude-docschanged
third-party/claude-desktop/configuration
Pins the app (sign-in, the connection test, model discovery, MCP servers, plugins), the Claude Code engine behind Chat, Cowork, and Code, and on macOS and Windows the Cowork wo
Pins the app (sign-in, the connection test, model discovery, MCP servers, plugins), the Claude Code engine behind Chat, Cowork, and Code, and on macOS and Windows the Cowork wo
| <span id="disabledeeplinkregistration" />Disable claude:// deep-link handling<br />`disableDeepLinkRegistration` | `boolean` | MDM + Bootstrap | `false` | Stop external apps and
| <span id="disabledeeplinkregistration" />Disable claude:// deep-link handling<br />`disableDeepLinkRegistration` | `boolean` | MDM + Bootstrap | `false` | Stop external apps and
| <span id="sshclientpath" />SSH client program<br />`sshClientPath` | `string` | MDM + Bootstrap · Beta | — | Absolute path to the OpenSSH ssh prog
+72 −44 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-docs
third-party/claude-desktop/bootstrap
±changed
+5−5
claude-docschanged
third-party/claude-desktop/bootstrap
| Field | Type | Description
| ---------------- | --------- | ---------------------------------------------------------------------------------------------------------------------------------------------------
| `$schemaVersion` | `integer` | Marks the nested v2 wire format. Optional — a response carrying any cluster key is sniffed as v2 regardless — but setting it explicitly is the docu
| `expiresAt` | `number` | Unix epoch (seconds or milliseconds) after which the client should re-fetch this document. Optional; when absent the client uses its default refres
| Field | Type | Description
+5 −5 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-docs
cowork/changelog
±changed
+50−0
claude-docschanged
cowork/changelog
<Update label="v1.46388.1" description="2026-09-04">
**General**
* Removed the "Mark as unread" action for chats.
+50 −0 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
prompt-caching
±changed
+7−3
claude-codechanged
prompt-caching
Two settings aren't part of the prompt text at all, so they don't appear in the layer table, but both are part of the cache key:
Two settings don't appear in the layer table but still affect what stays cached:
* **Effort level**: each effort level has its own cache for the same model. Changing effort mid-session recomputes the entire request. See [Changing effort level](#changing-effort-
* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Fable 5.1 with an API key or a Claude subs
The cache is keyed by [effort level](/docs/en/model-config#adjust-effort-level) as well as model, so switching with `/effort` means the next request reads the entire conversation h
+7 −3 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
llm-gateway-rollout
±changed
+3−3
claude-codechanged
llm-gateway-rollout
* For what Claude Code sends to a gateway and what to forward, see the [gateway protocol reference](/docs/en/llm-gateway-protocol)
* For what Claude Code sends to a gateway and what to forward, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol)
When sizing per-key rate limits, account for the client [retrying transient failures](/docs/en/errors#automatic-retries), including `429` responses, up to 10 times with backoff, ho
When sizing per-key rate limits, account for the client [retrying transient failures](/docs/en/errors#automatic-retries), including `429` responses, up to 10 times with backoff, ho
* [Gateway protocol reference](/docs/en/llm-gateway-protocol): the wire contract for gateway operators, covering endpoints, headers to forward, and the feature pass-through table
+3 −3 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
llm-gateway-protocol
±changed
+5−5
claude-codechanged
llm-gateway-protocol
# Gateway protocol reference
> The API contract between Claude Code and an LLM gateway: endpoints, headers and body fields to forward, feature degradation when fields are stripped, attribution headers for cost
# Claude Code gateway compatibility guide
+5 −5 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
llm-gateway-connect
±changed
+2−2
claude-codechanged
llm-gateway-connect
* For what Claude Code sends to a gateway, see the [gateway protocol reference](/docs/en/llm-gateway-protocol)
* For what Claude Code sends to a gateway, see the [gateway compatibility guide](/docs/en/llm-gateway-protocol)
* [Gateway protocol reference](/docs/en/llm-gateway-protocol): what Claude Code sends to a gateway, including the headers and fields the gateway must forward
* [Gateway compatibility guide](/docs/en/llm-gateway-protocol): what Claude Code sends to a gateway, including the headers and fields the gateway must forward
+2 −2 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
llm-gateway
±changed
+3−3
claude-codechanged
llm-gateway
* If you're configuring a gateway product: the [gateway protocol reference](/docs/en/llm-gateway-protocol)
* If you're configuring a gateway product: the [gateway compatibility guide](/docs/en/llm-gateway-protocol)
The tradeoff is that the gateway becomes infrastructure your organization operates. Claude Code adds capabilities with each release, and a gateway that doesn't forward them breaks
The tradeoff is that the gateway becomes infrastructure your organization operates. Claude Code adds capabilities with each release, and a gateway that doesn't forward them breaks
* [Gateway protocol reference](/docs/en/llm-gateway-protocol): what Claude Code sends to a gateway, for operators configuring one, covering endpoints, headers to forward, and featu
+3 −3 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
gateways
±changed
+1−1
claude-codechanged
gateways
The next page depends on who runs the gateway. Anthropic's gateway runs from the `claude` binary and has its own setup guide; a gateway your organization already runs has a protoco
The next page depends on who runs the gateway. Anthropic's gateway runs from the `claude` binary and has its own setup guide; a gateway your organization already runs has a compati
+1 −1 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
claude-apps-gateway
±changed
+1−1
claude-codechanged
claude-apps-gateway
The [gateway protocol reference](/docs/en/llm-gateway-protocol) documents the contract Claude Code expects from any gateway: the endpoints it calls, the headers and body fields to
The [gateway compatibility guide](/docs/en/llm-gateway-protocol) documents what Claude Code expects from any gateway: the endpoints it calls, the headers and body fields to forward
+1 −1 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-code
advisor
±changed
+1−1
claude-codechanged
advisor
Enabling or disabling the advisor mid-session does not invalidate your main model's [prompt cache](/docs/en/prompt-caching). Unlike [changing model or effort level](/docs/en/prompt
Enabling or disabling the advisor mid-session does not invalidate your main model's [prompt cache](/docs/en/prompt-caching). Unlike [switching models](/docs/en/prompt-caching#switc
+1 −1 lines
Recorded here 4 Sep 2026 02:37 UTC
claude-docs
index
±changed
+26−26
claude-docschanged
index
<a className="hl-chip" href="/docs/docs/connectors/overview"><span className="hl-chip-task">Connect my apps and data</span> <span className="hl-chip-name" translate="no">Co
<a className="hl-chip" href="/docs/docs/skills/overview"><span className="hl-chip-task">Teach Claude to do tasks my way</span> <span className="hl-chip-name" translate="no"
<a className="hl-chip" href="/docs/docs/cowork/overview"><span className="hl-chip-task">Give Claude a goal and check back</span> <span className="hl-chip-name" translate="n
<a className="hl-chip" href="/docs/docs/claude-tag/overview"><span className="hl-chip-task">Put Claude to work in my Slack</span> <span className="hl-chip-name" translate="
<a className="hl-chip" href="/docs/docs/claude-science/overview"><span className="hl-chip-task">Analyze literature and data</span> <span className="hl-chip-name" translate=
+26 −26 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-docs
claude-tag/overview
±changed
+11−11
claude-docschanged
claude-tag/overview
<a className="tm-btn tm-btn-dark" href="/docs/docs/claude-tag/admins/setup-overview">I'm setting it up →</a>
<a className="tm-btn tm-btn-dark" href="/docs/claude-tag/admins/setup-overview">I'm setting it up →</a>
<a className="tm-band tm-band-admins" href="/docs/docs/claude-tag/admins/setup-overview">
<a className="tm-band tm-band-admins" href="/docs/claude-tag/admins/setup-overview">
<a className="tm-qrow" href="/docs/docs/claude-tag/admins/setup-overview">
+11 −11 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-code
whats-new/2026-w34
±changed
+15−15
claude-codechanged
whats-new/2026-w34
<span>Releases <a href="/docs/docs/en/changelog#2-1-234">v2.1.234 → v2.1.239</a></span>
<span>Releases <a href="/docs/en/changelog#2-1-234">v2.1.234 → v2.1.239</a></span>
<a className="digest-feature-link" href="/docs/docs/en/artifacts#availability">Where artifacts are available</a>
<a className="digest-feature-link" href="/docs/en/artifacts#availability">Where artifacts are available</a>
<a className="digest-feature-link" href="/docs/docs/en/output-styles#built-in-output-styles">Built-in output styles</a>
+15 −15 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-code
whats-new/2026-w33
±changed
+15−15
claude-codechanged
whats-new/2026-w33
<span>Releases <a href="/docs/docs/en/changelog#2-1-225">v2.1.225 → v2.1.233</a></span>
<span>Releases <a href="/docs/en/changelog#2-1-225">v2.1.225 → v2.1.233</a></span>
<a className="digest-feature-link" href="/docs/docs/en/errors#youve-hit-your-session-limit">What to do when you hit a usage limit</a>
<a className="digest-feature-link" href="/docs/en/errors#youve-hit-your-session-limit">What to do when you hit a usage limit</a>
<a className="digest-feature-link" href="/docs/docs/en/sub-agents#turn-fork-mode-on-or-off">Turn fork mode on or off</a>
+15 −15 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-code
whats-new/2026-w32
±changed
+15−15
claude-codechanged
whats-new/2026-w32
<span>Releases <a href="/docs/docs/en/changelog#2-1-220">v2.1.220 → v2.1.224</a></span>
<span>Releases <a href="/docs/en/changelog#2-1-220">v2.1.220 → v2.1.224</a></span>
<a className="digest-feature-link" href="/docs/docs/en/cross-session-messaging#message-another-session">Message another session</a>
<a className="digest-feature-link" href="/docs/en/cross-session-messaging#message-another-session">Message another session</a>
<a className="digest-feature-link" href="/docs/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner">Self-hosted environments quickstart</a>
+15 −15 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-code
whats-new/2026-w30
±changed
+11−11
claude-codechanged
whats-new/2026-w30
<span>Releases <a href="/docs/docs/en/changelog#2-1-214">v2.1.214 → v2.1.219</a></span>
<span>Releases <a href="/docs/en/changelog#2-1-214">v2.1.214 → v2.1.219</a></span>
<p className="digest-feature-lede">Claude Opus 5 is the new default Opus model in Claude Code. It's the default on Max, Team Premium, Enterprise pay-as-you-go, and the Anthropic
<p className="digest-feature-lede">Claude Opus 5 is the new default Opus model in Claude Code. It's the default on Max, Team Premium, Enterprise pay-as-you-go, and the Anthropic
<a className="digest-feature-link" href="/docs/docs/en/model-config#available-models">Model configuration</a>
+11 −11 lines
Recorded here 4 Sep 2026 00:37 UTC
claude-code
whats-new/2026-w29
±changed
+6−6
claude-codechanged
whats-new/2026-w29
<span>Releases <a href="/docs/docs/en/changelog#2-1-207">v2.1.207 → v2.1.212</a></span>
<span>Releases <a href="/docs/en/changelog#2-1-207">v2.1.207 → v2.1.212</a></span>
<a className="digest-feature-link" href="/docs/docs/en/artifacts#pull-live-data-with-mcp-connectors">Pull live data with MCP connectors</a>
<a className="digest-feature-link" href="/docs/en/artifacts#pull-live-data-with-mcp-connectors">Pull live data with MCP connectors</a>
<a className="digest-feature-link" href="/docs/docs/en/accessibility#turn-on-screen-reader-mode">Turn on screen reader mode</a>
+6 −6 lines
Recorded here 4 Sep 2026 00:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.