HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
821pages tracked
767 changed this week · last read 24 Oct 2026
Claude Code CLI
228pages tracked
145 changed this week · last read 24 Oct 2026
Claude Documentation
280pages tracked
69 changed this week · last read 24 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
10 Oct 2026
78 pages
+1530 −2018 lines
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 10 Oct 2026 16:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+2−0
claude-codechanged
self-hosted-environments-deploy
* **Credentials for the session's repositories only**: Anthropic supplies git credentials for the repositories that are part of the session, not for other repositories on the same
* **Branch pushes only**: a push that deletes a branch fails, and so does a push to any other kind of ref, such as a tag. For which branches a push can update, see [GitHub proxy](/
+2 −0 lines
Upstream edited 10 Oct 2026 16:03 UTC Recorded here 10 Oct 2026 16:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+15−15
claude-codechanged
claude-apps-gateway-deploy
<Info>
**Plan your gateway's network first.** At sign-in, Claude Code refuses a Claude apps gateway whose hostname resolves to a public IP address, even one the internet can't reach.
A Claude apps gateway can push settings to users' machines, including hooks that run shell commands. The check helps keep users from accidentally signing in to a malicious gatewa
+15 −15 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
settings-reference
±changed
+5−5
claude-codechanged
settings-reference
| [`forceLoginGatewayUrl`](#forcelogingatewayurl) | Set the [gateway URL](/docs/en/claude-apps-gateway#set-the-gateway-url) the login screen connects to | Authentication and provid
| [`forceLoginGatewayUrl`](#forcelogingatewayurl) | Set the [gateway URL](/docs/en/claude-apps-gateway#set-the-gateway-url) the login screen connects to | Authentication and provid
* **Scope**: [`Any file`](#scopes). Claude Code honors `"gateway"` only from a managed source on the machine: `managed-settings.json`, the macOS plist or Windows HKLM registry, or
* **Scope**: [`Any file`](#scopes). Claude Code honors `"gateway"` from the same sources as [`forceLoginGatewayUrl`](#forcelogingatewayurl) and treats it as unset everywhere else.
Either this key or `forceLoginMethod: "gateway"` makes the machine gateway-only, except for sessions that select a cloud provider with `CLAUDE_CODE_USE_*`. `/login` then opens on t
+5 −5 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 10 Oct 2026 16:07 UTC
claude-code
errors
±changed
+2−0
claude-codechanged
errors
Claude Code also skips the check on a machine with no managed settings when your own `~/.claude/settings.json` [names a gateway](/docs/en/claude-apps-gateway#set-the-gateway-url-in
+2 −0 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 10 Oct 2026 16:07 UTC
claude-code
claude-apps-gateway-deploy
±changed
+1−1
claude-codechanged
claude-apps-gateway-deploy
Once the gateway is serving, push `forceLoginMethod`, `forceLoginGatewayUrl`, and `parentSettingsBehavior: "merge"` to each developer's machine through managed settings, via MDM or
Once the gateway is serving, push `forceLoginMethod`, `forceLoginGatewayUrl`, and `parentSettingsBehavior: "merge"` to each developer's machine through managed settings, via MDM or
+1 −1 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 10 Oct 2026 16:07 UTC
claude-code
claude-apps-gateway-config
±changed
+1−1
claude-codechanged
claude-apps-gateway-config
Claude Code honors [`forceLoginGatewayUrl`](/docs/en/settings-reference#forcelogingatewayurl), [`gatewayInternalNetworks`](/docs/en/settings-reference#gatewayinternalnetworks), and
Claude Code honors [`forceLoginGatewayUrl`](/docs/en/settings-reference#forcelogingatewayurl), [`gatewayInternalNetworks`](/docs/en/settings-reference#gatewayinternalnetworks), and
+1 −1 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 10 Oct 2026 16:07 UTC
claude-code
claude-apps-gateway
±changed
+19−3
claude-codechanged
claude-apps-gateway
Developers connect from their own laptops with one browser sign-in, using their corporate work account. They don't need a claude.ai account, an API key, or a subscription, because
Developers connect from their own laptops with one browser sign-in, using their corporate work account. They don't need a claude.ai account, an API key, or a subscription, because
Three keys go in the per-OS [managed settings file](/docs/en/managed-settings#delivery-mechanisms) you deploy via MDM or directly on disk. `forceLoginMethod` and `forceLoginGateway
Three keys go in the per-OS [managed settings file](/docs/en/managed-settings#delivery-mechanisms) you deploy via MDM or directly on disk. For a machine with no managed settings, s
A developer can't set this up manually. The login picker has no gateway option, and `forceLoginGatewayUrl` is ignored in a developer's own settings files. `forceLoginMethod` alone,
+19 −3 lines
Upstream edited 10 Oct 2026 15:50 UTC Recorded here 10 Oct 2026 16:07 UTC
api
release-notes/overview
±changed
+3−2
apichanged
release-notes/overview
* The Compliance API can now download Claude Docs documents as Word files, in beta. See [Retrieve files and artifacts](https://platform.claude.com/docs/en/manage-claude/compliance-
* We've launched **Claude Fable 5** (`claude-fable-5`), our most capable model open to all customers, alongside **Claude Mythos 5** (`claude-mythos-5`) for Project Glasswing partic
* We've launched **Claude Fable 5** (`claude-fable-5`), our most capable model open to all customers, alongside **Claude Mythos 5** (`claude-mythos-5`) for Project Glasswing partic
* On Claude Fable 5 and Claude Mythos 5, [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is the only thinking mode: `thinking: {"type": "disable
* On Claude Fable 5 and Claude Mythos 5, [adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is the only thinking mode: `thinking: {"type": "disable
+3 −2 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/sonnet-5/overview
±changed
+1−1
apichanged
models/sonnet-5/overview
Although Claude Sonnet 5 is still available, you should consider migrating to Claude Sonnet 5.5 for improved performance. [See Claude Sonnet 5.5](https://platform.claude.com/docs/e
Although Claude Sonnet 5 is still available, you should consider migrating to Claude Sonnet 5.5. [See Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/overv
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/sonnet-4-6/overview
±changed
+1−1
apichanged
models/sonnet-4-6/overview
Although Claude Sonnet 4.6 is still available, you should consider migrating to Claude Sonnet 5.5 for improved performance. [See Claude Sonnet 5.5](https://platform.claude.com/docs
Although Claude Sonnet 4.6 is still available, you should consider migrating to Claude Sonnet 5.5. [See Claude Sonnet 5.5](https://platform.claude.com/docs/en/models/sonnet-5-5/ove
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/opus-5/overview
±changed
+1−1
apichanged
models/opus-5/overview
Although Claude Opus 5 is still available, you should consider migrating to Claude Opus 5.5 for improved performance. [See Claude Opus 5.5](https://platform.claude.com/docs/en/mode
Although Claude Opus 5 is still available, you should consider migrating to Claude Opus 5.5. [See Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) · [
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/opus-4-8/overview
±changed
+1−1
apichanged
models/opus-4-8/overview
Although Claude Opus 4.8 is still available, you should consider migrating to Claude Opus 5.5 for improved performance. [See Claude Opus 5.5](https://platform.claude.com/docs/en/mo
Although Claude Opus 4.8 is still available, you should consider migrating to Claude Opus 5.5. [See Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) ·
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/opus-4-7/overview
±changed
+1−1
apichanged
models/opus-4-7/overview
Although Claude Opus 4.7 is still available, you should consider migrating to Claude Opus 5.5 for improved performance. [See Claude Opus 5.5](https://platform.claude.com/docs/en/mo
Although Claude Opus 4.7 is still available, you should consider migrating to Claude Opus 5.5. [See Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) ·
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/opus-4-6/overview
±changed
+1−1
apichanged
models/opus-4-6/overview
Although Claude Opus 4.6 is still available, you should consider migrating to Claude Opus 5.5 for improved performance. [See Claude Opus 5.5](https://platform.claude.com/docs/en/mo
Although Claude Opus 4.6 is still available, you should consider migrating to Claude Opus 5.5. [See Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) ·
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/opus-4-5/overview
±changed
+1−1
apichanged
models/opus-4-5/overview
Although Claude Opus 4.5 is still available, you should consider migrating to Claude Opus 5.5 for improved performance. [See Claude Opus 5.5](https://platform.claude.com/docs/en/mo
Although Claude Opus 4.5 is still available, you should consider migrating to Claude Opus 5.5. [See Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) ·
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/mythos-5/overview
±changed
+1−1
apichanged
models/mythos-5/overview
[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mytho
[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [Migration guide](https://platform.claude.com/docs/en/models/fable-5-1/migration-guide#migrating-from-claud
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/haiku-4-5/overview
±changed
+1−1
apichanged
models/haiku-4-5/overview
Although Claude Haiku 4.5 is still available, you should consider migrating to Claude Haiku 5.5 for improved performance. [See Claude Haiku 5.5](https://platform.claude.com/docs/en
Although Claude Haiku 4.5 is still available, you should consider migrating to Claude Haiku 5.5. [See Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/overvie
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/fable-5/overview
±changed
+2−6
apichanged
models/fable-5/overview
Although Claude Fable 5 is still available, you should consider migrating to Claude Fable 5.1 for improved performance. [See Claude Fable 5.1](https://platform.claude.com/docs/en/m
Although Claude Fable 5 is still available, you should consider migrating to Claude Fable 5.1. [See Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview)
[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5) · [What’s new](https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mytho
[Announcement](https://www.anthropic.com/news/claude-fable-5-mythos-5)
<Card title="Introducing Claude Fable 5 and Claude Mythos 5" icon="star" href="https://platform.claude.com/docs/en/models/fable-5/introducing-claude-fable-5-and-claude-mythos-5">
+2 −6 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/fable-5/migration-guide
−removed
+0−701
apiremoved
models/fable-5/migration-guide
No line of the body moved in this read.
+0 −701 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
−removed
+0−129
apiremoved
models/fable-5/introducing-claude-fable-5-and-claude-mythos-5
No line of the body moved in this read.
+0 −129 lines
Recorded here 10 Oct 2026 08:37 UTC
api
models/fable-5-1/migration-guide
±changed
+3−2
apichanged
models/fable-5-1/migration-guide
First apply [Migrating to Claude Mythos 5 and Claude Fable 5 from Claude Opus 4.8](https://platform.claude.com/docs/en/models/fable-5/migration-guide#migrating-from-claude-opus-48)
Work through the checklist below. On Claude Opus 4.7 or earlier, start with the matching [Claude Opus 5.5 migration guide](https://platform.claude.com/docs/en/models/opus-5-5/migra
* Update response parsing that reads content by position, such as `content[0].text`: a response can now start with `thinking` blocks, so select content blocks by `type` instead.
* Re-evaluate `effort` (start at `high`), review prompts near the 512-token caching minimum, and re-baseline cost and latency. Per-token pricing differs.
* Re-evaluate `effort` (start at `high`), review prompts near the 512-token [caching minimum](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#cache-limitations
+3 −2 lines
Recorded here 10 Oct 2026 08:37 UTC
api
managed-agents/session-threads
±changed
+6−8
apichanged
managed-agents/session-threads
await foreach (var thread in (await client.Beta.Sessions.Threads.List(session.ID)).Paginate())
await foreach (var sessionThread in (await client.Beta.Sessions.Threads.List(session.ID)).Paginate())
var label = thread.Agent.TryPickBetaManagedAgentsSessionThread(out var agent)
? agent.Name
: thread.Agent.Json.GetProperty("type").GetString();
+6 −8 lines
Recorded here 10 Oct 2026 08:37 UTC
api
manage-claude/compliance-content-data
±changed
+3−1
apichanged
manage-claude/compliance-content-data
Files and artifacts are downloaded by ID, not listed independently. The IDs come from the chat messages endpoint in [Retrieve chats and messages](https://platform.claude.com/docs/e
Files and artifacts are downloaded by ID. Except for Claude Docs documents (see the end of this section), they aren't listed independently. The IDs come from the chat messages endp
Claude Docs documents are listed separately, by [List code artifacts](https://platform.claude.com/docs/en/api/compliance/code/artifacts/list), with `artifact_type` set to `claude_d
+3 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-sonnet-5-5
If the `bio` classifier blocks your organization's life sciences work, you can apply to the [Life Sciences Verification Program](https://www.anthropic.com/news/life-sciences-verifi
If the `cyber` classifier blocks your organization's legitimate security work, you can apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842). I
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/prompting-claude-opus-5-5
* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not.
* **Cybersecurity:** Finding vulnerabilities in source code is allowed. High-risk dual-use cybersecurity activities are not. If the cybersecurity classifier gets in the way of your
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
build-with-claude/prompt-engineering/prompting-claude-fable-5
±changed
+2−2
apichanged
build-with-claude/prompt-engineering/prompting-claude-fable-5
This guide covers the prompting and scaffolding patterns specific to Claude Fable 5 and Claude Mythos 5. For the model's capabilities, API changes, pricing, and availability, see [
This guide covers the prompting and scaffolding patterns specific to Claude Fable 5 and Claude Mythos 5. For the model's specifications, pricing, and availability, see [Claude Fabl
For API parameter changes specific to Claude Fable 5 and Claude Mythos 5 (adaptive thinking only, summarized-only thinking output, no extended thinking budgets, the `refusal` sto
For how thinking works on Claude Fable 5 and Claude Mythos 5 (adaptive thinking only, summarized-only thinking output, no extended thinking budgets), see [Thinking](https://platf
+2 −2 lines
Recorded here 10 Oct 2026 08:37 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+1−1
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [Wha
For an overview of model capabilities, see the [models overview](https://platform.claude.com/docs/en/models/overview). For Claude Fable 5.1 capabilities and API changes, see [Wha
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+1−1
apichanged
build-with-claude/claude-in-amazon-bedrock
Use Claude Code 2.1.255 or later with Claude Fable 5.1 on Amazon Bedrock, and 2.1.280 or later with Claude Opus 5.5 and Claude Haiku 5.5; run `claude update` to upgrade.
Use the latest version of Claude Code with Claude in Amazon Bedrock; run `claude update` to upgrade.
+1 −1 lines
Recorded here 10 Oct 2026 08:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 10 Oct 2026 02:07 UTC
claude-code
errors
±changed
+45−8
claude-codechanged
errors
| `Claude Code couldn't restart` | [Command-line errors](#claude-code-couldnt-restart) |
| `This session restarted <time> after its next /loop wakeup was due, so that wakeup will not fire` | [Background session errors](#restarted-after-its-next-loop-wakeup-was-due) |
| [`CLAUDE_CODE_RETRY_WATCHDOG_MAX_WAIT_MS`](/docs/en/env-vars) | unset | Maximum time in milliseconds that each API request spends waiting out `429` and `529` errors when `CLAUDE_
<h3 id="claude-code-couldnt-restart">
+45 −8 lines
Upstream edited 10 Oct 2026 01:38 UTC Recorded here 10 Oct 2026 02:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 10 Oct 2026 01:07 UTC
claude-code
vs-code
±changed
+1−1
claude-codechanged
vs-code
To have each session connect to your browser as it starts, without typing `@browser`, see [Enable Chrome by default](/docs/en/chrome#enable-chrome-by-default). For when Claude Code
To have each session connect to your browser as it starts, without typing `@browser`, see [Enable Chrome by default](/docs/en/chrome#enable-chrome-by-default). For when Claude Code
+1 −1 lines
Upstream edited 10 Oct 2026 00:47 UTC Recorded here 10 Oct 2026 01:07 UTC
claude-code
chrome
±changed
+4−5
claude-codechanged
chrome
In a VS Code session, whether Claude Code asks you before a browser action depends on how the session connected to your browser:
* **You typed `@browser`**: the extension approves each browser action that Claude Code would otherwise ask you about.
* **The [Enabled by default](#enable-chrome-by-default) setting connected it at start**: Claude Code asks you before browser actions on a site you haven't allowed, in Manual, Edit
In a VS Code session, when Claude Code asks before a browser action, the prompt appears as a card in the chat panel. When the action targets a site you haven't allowed, the card al
+4 −5 lines
Upstream edited 10 Oct 2026 00:47 UTC Recorded here 10 Oct 2026 01:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 10 Oct 2026 00:07 UTC
9 Oct 2026
658 pages
+60364 −28978 lines
claude-code
self-hosted-environments-testing
±changed
+13−13
claude-codechanged
self-hosted-environments-testing
> Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
In a [self-hosted environment](/docs/en/self-hosted-environments), Claude Code [cloud sessions](/docs/en/claude-code-on-the-web.md) run on a runner image you build and maintain. Be
This recipe assumes you've already [set up an environment and a runner](/docs/en/self-hosted-environments-quickstart.md#set-up-an-environment-and-runner), and that your CI job star
+13 −13 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 23 Oct 2026 19:07 UTC
claude-code
self-hosted-environments-testing
±changed
+9−9
claude-codechanged
self-hosted-environments-testing
> Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
In a [self-hosted environment](/docs/en/self-hosted-environments), Claude Code [cloud sessions](/docs/en/claude-code-on-the-web) run on a runner image you build and maintain. Befor
This recipe assumes you've already [set up an environment and a runner](/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner), and that your CI job starts
+9 −9 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
self-hosted-environments-testing
±changed
+3−3
claude-codechanged
self-hosted-environments-testing
<Note>
Self-hosted environments are in public beta on Team and Enterprise plans; [Availability and limitations](/docs/en/self-hosted-environments#availability-and-limitations) covers th
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
self-hosted-environments-identity
±changed
+107−111
claude-codechanged
self-hosted-environments-identity
<Note>
Self-hosted environments are in public beta on Team and Enterprise plans; an [Owner](/docs/en/cloud-environments#organization-shared-environments) enables them by turning on **Al
</Note>
> [!NOTE]
>
+107 −111 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
skills
±changed
+1−1
claude-codechanged
skills
* For Cowork and cloud sessions, enable the skill for your claude.ai account.
* For Cowork and cloud sessions, enable the skill for your claude.ai account. [Some sessions in a self-hosted environment](/docs/en/self-hosted-environments-configuration#how-each-
+1 −1 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-testing
±changed
+14−4
claude-codechanged
self-hosted-environments-testing
1. Creates a session on the test environment with `claude -p "<prompt>" --environment <environment-id> --output-format json`, run from a git checkout so the CLI can auto-detect the
1. Creates a session on the test environment with `claude -p "<prompt>" --environment <environment-id> --output-format json`. Run the command from a git checkout so the CLI can aut
* **Session created**: one line of JSON such as `{"ok":true,"session_id":"session_...","title":"...","url":"...","pool_id":"..."}`
* **Session creation failed**: the line `{"ok":false,"error":"..."}`, and the command exits with status 1
* **Some earlier errors**, such as cloud sessions being unavailable for your organization or a missing prompt: the error on stderr with no JSON line, and the command exits with
+14 −4 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-reference
±changed
+24−6
claude-codechanged
self-hosted-environments-reference
| `--server-auto-mode-lists <mode>` | `SELF_HOSTED_RUNNER_SERVER_AUTO_MODE_LISTS` | `no-allow` | Which of the [auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode
| `--startup-timeout-min <n>` | `SELF_HOSTED_RUNNER_STARTUP_TIMEOUT_MS` | `15` | Release a session slot if the child hasn't signaled that it initialized within N minutes of spawn.
| `--startup-timeout-min <n>` | `SELF_HOSTED_RUNNER_STARTUP_TIMEOUT_MS` | `15` | Release a session slot if the child hasn't signaled that it initialized within N minutes of spawn.
| `--use-anthropic-git-proxy` | `CLAUDE_RUNNER_USE_GIT_PROXY=1` | off | Clone via the [Anthropic git proxy](/docs/en/self-hosted-environments-deploy#use-the-anthropic-git-proxy) in
| `--use-anthropic-git-proxy` | `CLAUDE_RUNNER_USE_GIT_PROXY=1` | off | Clone repositories on github.com via the [Anthropic git proxy](/docs/en/self-hosted-environments-deploy#use-
+24 −6 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-quickstart
±changed
+39−7
claude-codechanged
self-hosted-environments-quickstart
* A repository for the test session: a public one, or one this host can already clone by its HTTPS URL without being asked for credentials.
Claude Code includes a guided setup: an interactive Claude Code session that walks you through creating the environment in the admin UI, starts a local runner with the secret file
Use either the [guided setup](#run-the-guided-setup) or the [manual steps](#set-up-manually). The guided setup is a single command that starts an interactive Claude Code session an
### Run the guided setup
+39 −7 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-identity
±changed
+3−1
claude-codechanged
self-hosted-environments-identity
Use `jq -re` rather than `jq -r` so a missing claim causes a non-zero exit. With `-r` alone, a missing claim prints the literal string `null` and exits zero, which silently passes
Use `jq -re` rather than `jq -r` so a missing claim causes a non-zero exit. With `-r` alone, a missing claim prints the literal string `null` and exits zero, which silently passes
If `decode-token` can't fetch the keys from the JWKS endpoint or can't verify the token, it prints the reason to stderr, prints no claims, and exits with code 1. Pass `--no-verify`
+3 −1 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-deploy
±changed
+129−20
claude-codechanged
self-hosted-environments-deploy
* **No broad credentials in the image**: don't include long-lived SSH keys, cloud-provider credentials, or personal access tokens that grant more than a session needs. Mint credent
* **No broad credentials in the image**: don't include long-lived SSH keys, cloud-provider credentials, or personal access tokens that grant more than a session needs. Mint credent
* **Keep the host's GitHub credentials away from sessions**: Claude can use any GitHub credential a session can read, with whatever access that credential grants. Keep the runner h
* **With [Anthropic-managed git](#use-the-anthropic-git-proxy)**: with such a credential, Claude reaches GitHub directly instead of through Anthropic-managed git.
* **Without Anthropic-managed git**: a clone credential can stay in the image if you scope it as tightly as [Ship git config in your image](#ship-git-config-in-your-image) descri
+129 −20 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments-configuration
±changed
+122−28
claude-codechanged
self-hosted-environments-configuration
| `CCR_SESSION_ACCOUNT_EMAIL` | The session creator's email, pre-extracted by the runner from the token's `act.email` claim without signature verification. Suitable for labelling,
| `CLAUDE_RUNNER_CLIENT_PLATFORM` | The client surface that created the session, such as `web_claude_ai`, `desktop_app`, `ios`, `claude_code_cli`, or `scheduled_trigger`. Anthropic
| `CCR_SESSION_ACCOUNT_EMAIL` | The session creator's email, pre-extracted by the runner from the token's `act.email` claim without signature verification. Suitable for labelling,
| `CLAUDE_RUNNER_CLIENT_PLATFORM` | The client surface that created the session, such as `web_claude_ai`, `desktop_app`, `ios`, `claude_code_cli`, or `scheduled_trigger`. Anthropic
| `CLAUDE_CODE_REMOTE_SLACK_THREAD_URL` | For a [Claude Tag](https://claude.com/docs/claude-tag/overview) session that belongs to one Slack thread, the link to that thread. Unset f
+122 −28 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
self-hosted-environments
±changed
+5−3
claude-codechanged
self-hosted-environments
* **SCM connector**: the optional orchestrator [SCM connector](/docs/en/self-hosted-environments-reference#scm-connector-flags) tunnel is the only WebSocket connection.
* **Git**: the runner clones from and pushes to your git host over HTTPS or SSH, authenticated with credentials your deployment provides; [Configure git](/docs/en/self-hosted-envir
* **Session child**: the child Claude Code process holds the session's event stream to `api.anthropic.com`, and makes its own outbound calls for model inference and for git command
* **Git**: the runner clones from and pushes to your git host over HTTPS or SSH, authenticated with credentials your deployment provides. See [Configure git](/docs/en/self-hosted-e
* **Session child**: the child Claude Code process holds the session's event stream to `api.anthropic.com`, and makes its own outbound calls for model inference and for git command
+5 −3 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
headless
±changed
+1−1
claude-codechanged
headless
Use the MCP server fields the same way. When you pass [`--mcp-config`](/docs/en/cli-reference#cli-flags) with `-p`, Claude Code waits for still-pending servers before running the f
Use the MCP server fields the same way. When you pass [`--mcp-config`](/docs/en/cli-reference#cli-flags) with `-p`, Claude Code waits for still-pending servers before running the f
+1 −1 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
| Your user `~/.claude/skills/`, `~/.claude/agents/`, `~/.claude/commands/` | No | Live on your machine, not in the repo. Commit them to the repo's `.claude/` directory instead. Cl
| Your user `~/.claude/skills/`, `~/.claude/agents/`, `~/.claude/commands/` | No | Live on your machine, not in the repo. Commit them to the repo's `.claude/` directory instead. Cl
+1 −1 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
claude-projects
±changed
+12−6
claude-codechanged
claude-projects
Each approval covers that prompt, or the rest of that thread if you choose the broader option. To let every thread run certain commands without asking, or to block some, add [permi
Each approval covers that prompt, or the rest of that thread if you choose the broader option.
To let every thread run certain commands without asking, or to block some, add [permission rules](/docs/en/permissions) to the repository's `.claude/settings.json`. Check that clou
+12 −6 lines
Upstream edited 9 Oct 2026 23:38 UTC Recorded here 10 Oct 2026 00:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 9 Oct 2026 23:37 UTC
claude-code
agent-sdk/streaming-output
±changed
+228−234
claude-codechanged
agent-sdk/streaming-output
<Tip>
This page covers output streaming (receiving tokens in real-time). For input modes (how you send messages), see [Send messages to agents](/docs/en/agent-sdk/streaming-vs-single-m
</Tip>
> [!TIP]
>
+228 −234 lines
Upstream edited 9 Oct 2026 23:17 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
headless
±changed
+2−0
claude-codechanged
headless
When stderr is a terminal and the run has waited five seconds, Claude Code prints a line to stderr that starts with `Waiting for background work to finish` and names the work. With
+2 −0 lines
Upstream edited 9 Oct 2026 23:17 UTC Recorded here 9 Oct 2026 23:37 UTC
claude-code
agent-sdk/typescript
±changed
+15−10
claude-codechanged
agent-sdk/typescript
Claude Code sets `user_message_uuid` and `user_message_uuids` on the turn's first assistant message, under the conditions in [`user_message_uuid`](#user_message_uuid). When Claude
Claude Code sets `user_message_uuid` and `user_message_uuids` on the turn's first assistant message, under the conditions in [`user_message_uuid`](#user_message_uuid). When the tur
Each paste field has a size limit:
+15 −10 lines
Upstream edited 9 Oct 2026 23:17 UTC Recorded here 9 Oct 2026 23:37 UTC
claude-code
agent-sdk/streaming-output
±changed
+6−0
claude-codechanged
agent-sdk/streaming-output
### Handle a stream that's cut off
If a stream is cut off mid-message, such as when you interrupt the turn or the connection drops, you still receive that message's `message_stop` before the turn ends. A cut text or
Before Claude Code v2.1.290, a cut stream could end the turn without `message_stop`, so a reply you render from stream events could stay shown as in progress. The TypeScript Agent
+6 −0 lines
Upstream edited 9 Oct 2026 23:17 UTC Recorded here 9 Oct 2026 23:37 UTC
claude-code
claude-apps-gateway-config
±changed
+2−2
claude-codechanged
claude-apps-gateway-config
A policy's Claude Code settings, such as a rule that denies reading `.env` files, go in a block under the `cli` or `code` key. Both keys take the same contents. The key decides whe
A policy's Claude Code settings, such as a rule that denies reading `.env` files, go in a block under the `cli` or `code` key. `code` is the recommended key, and `cli` is the legac
The choice is whether these settings should also cover the Code tab. If not, change nothing. A file that uses `cli` works as it did, and a gateway that finds `cli` in a policy with
A file that uses `cli` works as it did, and a gateway that finds `cli` in a policy with a [`desktop`](#claude-desktop-overlay) key warns at boot and starts anyway. Switch to `code`
+2 −2 lines
Upstream edited 9 Oct 2026 23:13 UTC Recorded here 9 Oct 2026 23:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 9 Oct 2026 22:37 UTC
claude-code
managed-settings
±changed
+40−70
claude-codechanged
managed-settings
<Steps>
<Step title="Write managed-settings.json">
Write a `managed-settings.json` that holds the keys you've decided to enforce, in the same JSON shape as `settings.json`. The [Decide what to enforce](/docs/en/admin-setup#deci
```json managed-settings.json theme={null}
+40 −70 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+407−413
claude-codechanged
claude-apps-gateway-on-aws
<Note>
This page walks through one way to run Claude apps gateway on AWS. The configuration is a working example for customer-managed infrastructure rather than a supported production d
</Note>
> [!NOTE]
>
+407 −413 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
managed-settings
±changed
+1−1
claude-codechanged
managed-settings
1. Remote settings, delivered from claude.ai as [server-managed settings](/docs/en/server-managed-settings) or by a [Claude apps gateway](/docs/en/claude-apps-gateway). Claude Code
1. Remote settings, delivered from claude.ai as [server-managed settings](/docs/en/server-managed-settings) or by a [Claude apps gateway](/docs/en/claude-apps-gateway). Claude Code
+1 −1 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 9 Oct 2026 22:37 UTC
claude-code
claude-apps-gateway-on-aws
±changed
+1−1
claude-codechanged
claude-apps-gateway-on-aws
The gateway is now running, but developers can't reach it from `/login` until the gateway URL is on their machines. Set `forceLoginMethod` and `forceLoginGatewayUrl` in the [ma
The gateway is now running, but developers can't reach it from `/login` until the gateway URL is on their machines. Deploy the full [managed settings snippet](/docs/en/claude-a
+1 −1 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 9 Oct 2026 22:37 UTC
claude-code
claude-apps-gateway-deploy
±changed
+1−1
claude-codechanged
claude-apps-gateway-deploy
The first registration can run before the developer signs in to the gateway, when no gateway policy has arrived. To cover that first start, deliver your choice in [client-side mana
The first registration can run before the developer signs in to the gateway, when no gateway policy has arrived. To cover that first start, deliver your choice in [client-side mana
+1 −1 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 9 Oct 2026 22:37 UTC
claude-code
claude-apps-gateway-config
±changed
+58−4
claude-codechanged
claude-apps-gateway-config
#### Choose `cli` or `code`
<Warning>
When a policy uses the `code` key, each of these stops the gateway from starting:
+58 −4 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 9 Oct 2026 22:37 UTC
claude-code
claude-apps-gateway
±changed
+11−7
claude-codechanged
claude-apps-gateway
This last step happens on a developer machine, not the server. Set `forceLoginMethod` to `"gateway"` and `forceLoginGatewayUrl` to your gateway's `public_url` in that machine's
This last step happens on a developer machine, not the server. Set `forceLoginMethod` to `"gateway"`, `forceLoginGatewayUrl` to your gateway's `public_url`, and `parentSettings
Claude Desktop runs its Cowork and Code tabs, plus the Chat tab when you enable it, on embedded Claude Code sessions and sends their model requests through the gateway. It passes p
Other `cli` keys, such as hooks, `env`, and scoped permission rules like `Bash(npm *)`, reach only clients that sign in through `/login`. Claude Desktop reads the gateway URL from
+11 −7 lines
Upstream edited 9 Oct 2026 22:32 UTC Recorded here 9 Oct 2026 22:37 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 9 Oct 2026 22:07 UTC
claude-docs
third-party/claude-desktop/overview
±changed
+5−4
claude-docschanged
third-party/claude-desktop/overview
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through a provider you configure: Google Cloud's Agent Platform, Amazon Be
Claude Desktop on third-party (3P) is a deployment mode of Claude Desktop that routes all model inference through a provider you configure: Google Cloud's Agent Platform, Amazon Be
| Conversation storage | Anthropic backend | Local disk on the user's machine |
| Conversation storage | Anthropic backend | Local disk on the user's machine, and the remote host for [SSH remote sessions](/docs/third-party/claude-desktop/ssh-remote-sessions) |
* **Conversation content goes only to your configured endpoint.** The app sends prompts, responses, files, and tool outputs only to your configured inference endpoint and stores th
+5 −4 lines
Upstream edited 9 Oct 2026 22:04 UTC Recorded here 9 Oct 2026 22:07 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+5−3
claude-docschanged
third-party/claude-desktop/data-storage
Claude Desktop on third-party (3P) keeps conversations, settings, and credentials on the device. When the configuration comes from MDM, a local file, or a bootstrap server, users h
Claude Desktop on third-party (3P) keeps conversations, settings, and credentials on the device. For [SSH remote sessions](/docs/third-party/claude-desktop/ssh-remote-sessions), th
To fully reset a device's Claude Desktop on 3P state, delete the application-data directory above and the `~/Claude/` user-files folder. Code session transcripts are in Claude Code
To fully reset a device's Claude Desktop on 3P state, delete the application-data directory above and the `~/Claude/` user-files folder. Code session transcripts are in Claude Code
Conversation history exists only on this device, or on the SSH host for remote Code sessions, so deleting it is unrecoverable.
+5 −3 lines
Upstream edited 9 Oct 2026 22:04 UTC Recorded here 9 Oct 2026 22:07 UTC
claude-docs
third-party/claude-desktop/chat
±changed
+1−1
claude-docschanged
third-party/claude-desktop/chat
Like everything else in 3P mode, Chat conversations run against your configured inference provider, and conversation history lives on the user's device. See [User identity and loca
Chat conversations run against your configured inference provider, and their history is stored on the user's device. See [User identity and local data](/docs/third-party/claude-des
+1 −1 lines
Upstream edited 9 Oct 2026 22:04 UTC Recorded here 9 Oct 2026 22:07 UTC
claude-code
managed-settings
±changed
+2−0
claude-codechanged
managed-settings
If your organization has the [HIPAA configuration](/docs/en/hipaa-setup#deploy-managed-settings) applied, see `settings-hipaa.json` and `README-hipaa.md` in the [settings examples
+2 −0 lines
Upstream edited 9 Oct 2026 21:39 UTC Recorded here 9 Oct 2026 22:07 UTC
claude-code
hipaa-setup
±changed
+3−0
claude-codechanged
hipaa-setup
For a fuller `managed-settings.json` with sandboxing, a network allowlist, credential protections, and local data retention, see `settings-hipaa.json` and `README-hipaa.md` in the
* [HIPAA settings example](https://github.com/anthropics/claude-code/tree/main/examples/settings)
+3 −0 lines
Upstream edited 9 Oct 2026 21:39 UTC Recorded here 9 Oct 2026 22:07 UTC
api
managed-agents/workflow-runs
+new page
+824−0
apinew page
managed-agents/workflow-runs
No line of the body moved in this read.
+824 −0 lines
Recorded here 9 Oct 2026 21:37 UTC
api
managed-agents/session-threads
+new page
+815−0
apinew page
managed-agents/session-threads
No line of the body moved in this read.
+815 −0 lines
Recorded here 9 Oct 2026 21:37 UTC
api
managed-agents/multiagent-orchestration
±changed
+1−1
apichanged
managed-agents/multiagent-orchestration
* **Budget:** Set a [session budget](https://platform.claude.com/docs/en/managed-agents/budgets) when you create the session to cap the session's spend, runs included; you can't ad
* **Budget:** Set a [session budget](https://platform.claude.com/docs/en/managed-agents/budgets) when you create the session to cap the session's spend, runs included; you can't ad
+1 −1 lines
Recorded here 9 Oct 2026 21:37 UTC
api
managed-agents/events-and-streaming
±changed
+2−2
apichanged
managed-agents/events-and-streaming
No event you send resumes a session paused at its budget. The paused work resumes automatically when you change the budget to a value above the consumed list cost, or remove it. Wh
No event you send resumes a session paused at its budget. The work that the budget paused resumes automatically when you change the budget to a value above the consumed list cost,
The `agent.custom_tool_use` event contains the tool name and input. Execute the tool in your system. Then send a `user.custom_tool_result` event, passing the event ID in the `custo
The `agent.custom_tool_use` event contains the tool name and input. Run the tool in your system. Then send a `user.custom_tool_result` event, passing the event ID in the `custom_to
+2 −2 lines
Recorded here 9 Oct 2026 21:37 UTC
api
managed-agents/budgets
±changed
+10−6
apichanged
managed-agents/budgets
A session budget is an optional hard spend ceiling you set when you [create a session](https://platform.claude.com/docs/en/managed-agents/sessions). The platform continuously price
A session budget is an optional hard spend ceiling you set when you [create a session](https://platform.claude.com/docs/en/managed-agents/sessions). The platform continuously price
* **Web searches**, at $10 per 1,000 searches
* **Session running time**, at $0.08 per hour
* **Web searches**, at $10 USD per 1,000 searches
+10 −6 lines
Recorded here 9 Oct 2026 21:37 UTC
api
manage-claude/user-management
±changed
+3−0
apichanged
manage-claude/user-management
Read a role's name from its `display_name` field. The deprecated `name` field is still returned, always equal to `display_name`. For a role provisioned by Anthropic, `display_name`
"display_name": "Engineering base",
+3 −0 lines
Recorded here 9 Oct 2026 21:37 UTC
api
cli-sdks-libraries/sdks/typescript
±changed
+4−4
apichanged
cli-sdks-libraries/sdks/typescript
Avoid setting a large `max_tokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [ti
Avoid setting a large `max_tokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [ti
Beta features are available before general release to get early feedback and test new functionality. You can check the availability of all of Claude's capabilities and tools in the
You can access most beta API features through the beta property of the client. To enable a particular beta feature, you need to add the appropriate [beta header](https://platform.c
+4 −4 lines
Recorded here 9 Oct 2026 21:37 UTC
api
cli-sdks-libraries/sdks/python
±changed
+2−2
apichanged
cli-sdks-libraries/sdks/python
Avoid setting a large `max_tokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [ti
Avoid setting a large `max_tokens` value without using streaming. Some networks may drop idle connections after a certain period of time, which can cause the request to fail or [ti
Beta features are available before general release to get early feedback and test new functionality. You can check the availability of all of Claude's capabilities and tools in the
Beta features are available before general release to get early feedback and test new functionality. You can check the availability of all of Claude's capabilities and tools in the
+2 −2 lines
Recorded here 9 Oct 2026 21:37 UTC
api
cli-sdks-libraries/sdks/java
±changed
+1−1
apichanged
cli-sdks-libraries/sdks/java
Beta features are available before general release to get early feedback and test new functionality. You can check the availability of all of Claude's capabilities and tools in the
Beta features are available before general release to get early feedback and test new functionality. You can check the availability of all of Claude's capabilities and tools in the
+1 −1 lines
Recorded here 9 Oct 2026 21:37 UTC
api
cli-sdks-libraries/sdks/go
±changed
+1−1
apichanged
cli-sdks-libraries/sdks/go
Avoid setting a large `MaxTokens` value without using streaming as some networks may drop idle connections after a certain period of time, which can cause the request to fail or [t
Avoid setting a large `MaxTokens` value without using streaming as some networks may drop idle connections after a certain period of time, which can cause the request to fail or [t
+1 −1 lines
Recorded here 9 Oct 2026 21:37 UTC
api
build-with-claude/preserved-thinking
±changed
+10−2
apichanged
build-with-claude/preserved-thinking
`"drop_block"` hides the error but doesn't fix the edit that caused it. Dropped blocks aren't billed, but a session's token usage might still increase because Claude can sometime
`"drop_block"` keeps requests succeeding, but it doesn't fix the edit that caused the mismatch, and it has a cost. Dropping blocks can significantly increase the output tokens ge
#### Output-token cost of `"drop_block"`
In Anthropic's testing on a multi-turn coding benchmark, dropping thinking blocks once per session increased output tokens by 2.5% at low effort, 3.9% at medium, 4.5% at high, and
+10 −2 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/organization/workspaces/update
±changed
+1−1
apichanged
api/organization/workspaces/update
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
+1 −1 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/organization/workspaces/create
±changed
+1−1
apichanged
api/organization/workspaces/create
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
+1 −1 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/organization/workspaces
±changed
+2−2
apichanged
api/organization/workspaces
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
+2 −2 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/organization
±changed
+2−2
apichanged
api/organization
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
minLength: 1, maxLength: 40
minLength: 1, maxLength: 255
+2 −2 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages/create
±changed
+9−17
apichanged
api/messages/create
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
Example with a partially-filled response from Claude:
Example with a partially-filled response from Claude, for models that support prefill:
Fastest model with near-frontier intelligence
+9 −17 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages/count_tokens
±changed
+9−13
apichanged
api/messages/count_tokens
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
Example with a partially-filled response from Claude:
Example with a partially-filled response from Claude, for models that support prefill:
Fastest model with near-frontier intelligence
+9 −13 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages/batches/results
±changed
+0−4
apichanged
api/messages/batches/results
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
+0 −4 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages/batches/create
±changed
+9−13
apichanged
api/messages/batches/create
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the mod
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the mod
Example with a partially-filled response from Claude:
Example with a partially-filled response from Claude, for models that support prefill:
Fastest model with near-frontier intelligence
+9 −13 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages/batches
±changed
+9−29
apichanged
api/messages/batches
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the mod
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the mod
Example with a partially-filled response from Claude:
Example with a partially-filled response from Claude, for models that support prefill:
Fastest model with near-frontier intelligence
+9 −29 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/messages
±changed
+28−64
apichanged
api/messages
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
If the final message uses the `assistant` role, the response content will continue immediately from the content in that message. This can be used to constrain part of the model's
Example with a partially-filled response from Claude:
Example with a partially-filled response from Claude, for models that support prefill:
Fastest model with near-frontier intelligence
+28 −64 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/completions/create
±changed
+0−8
apichanged
api/completions/create
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
+0 −8 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/completions
±changed
+0−12
apichanged
api/completions
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
+0 −12 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/update
±changed
+571−437
apichanged
api/beta/sessions/update
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
- `multiagent: BetaManagedAgentsSessionMultiagentCoordinator or null`
+571 −437 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/retrieve
±changed
+53−6
apichanged
api/beta/sessions/threads/retrieve
- `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
- `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor or BetaManagedAgentsInlineAgent`
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
+53 −6 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/list
±changed
+67−6
apichanged
api/beta/sessions/threads/list
- `statuses: optional array of BetaManagedAgentsSessionThreadStatus`
Return only threads that have one of these statuses.
Repeat the parameter to give more than one status. Leave it out to return threads of every status.
+67 −6 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/events/stream
±changed
+834−440
apichanged
api/beta/sessions/threads/events/stream
- `BetaManagedAgentsStreamSessionThreadEvents = BetaManagedAgentsUserMessageEvent or BetaManagedAgentsUserInterruptEvent or BetaManagedAgentsUserToolConfirmationEvent or 34 more`
- `BetaManagedAgentsStreamSessionThreadEvents = BetaManagedAgentsUserMessageEvent or BetaManagedAgentsUserInterruptEvent or BetaManagedAgentsUserToolConfirmationEvent or 41 more`
The id of the `agent.custom_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api
The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/
Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result.
+834 −440 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/events/list
±changed
+833−439
apichanged
api/beta/sessions/threads/events/list
The id of the `agent.custom_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api
The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/
Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result.
Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon
- `workflow_run_id: string or null`
+833 −439 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/events
±changed
+1667−879
apichanged
api/beta/sessions/threads/events
The id of the `agent.custom_tool_use` event this result corresponds to, which can be found in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api
The id of the `agent.custom_tool_use` event this result corresponds to. It is also listed in the last `session.status_idle` [event's](https://platform.claude.com/docs/en/api/
Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result.
Event emitted when the agent calls a custom tool. The session goes idle until the client sends a `user.custom_tool_result` event with the result. The client can send it as soon
- `workflow_run_id: string or null`
+1667 −879 lines
Recorded here 9 Oct 2026 21:37 UTC
api
api/beta/sessions/threads/archive
±changed
+53−6
apichanged
api/beta/sessions/threads/archive
- `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor`
- `agent: BetaManagedAgentsSessionThreadAgent or BetaManagedAgentsAdvisor or BetaManagedAgentsInlineAgent`
Fastest model with near-frontier intelligence
Fastest model with near-frontier intelligence
+53 −6 lines
Recorded here 9 Oct 2026 21:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.