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
146 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
7 Oct 2026
209 pages
+3198 −2398 lines
api
build-with-claude/claude-in-microsoft-foundry
±changed
+7−6
apichanged
build-with-claude/claude-in-microsoft-foundry
This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microso
This guide shows you how to set up and make API calls to Claude in Microsoft Foundry using one of Anthropic's client SDKs or direct HTTP requests. When you access Claude in Microso
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-foundry:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
+7 −6 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+6−5
apichanged
build-with-claude/claude-in-amazon-bedrock
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-bedrock:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-bedrock:2.69.0")
<version>2.68.0</version>
+6 −5 lines
Recorded here 7 Oct 2026 19:07 UTC
api
build-with-claude/batch-processing
±changed
+3−1
apichanged
build-with-claude/batch-processing
| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.05 / MTok | $0.25 / MTok |
| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.25 / MTok | $1.25 / MTok |
The `output-300k-2026-03-24` beta header raises the `max_tokens` cap to 300,000 for batch requests using Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Op
The `output-300k-2026-03-24` beta header raises the `max_tokens` cap to 300,000 for batch requests using Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Op
+3 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
api/service-tiers
±changed
+1−1
apichanged
api/service-tiers
Priority Tier is supported on all available Claude models except Claude Fable 5.1, Claude Mythos 5.1, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.com/glasswing), Cla
Priority Tier is supported on all available Claude models except Claude Fable 5.1, Claude Haiku 5.5, Claude Mythos 5.1, Claude Mythos 5, [Claude Mythos Preview](https://anthropic.c
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
api/rate-limits
±changed
+3−0
apichanged
api/rate-limits
| Claude Haiku 5.5 | 1,000 | 2,
| Claude Haiku 5.5 | 5,000 | 5,
| Claude Haiku 5.5 | 10,000 | 10
+3 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
api/errors
±changed
+4−2
apichanged
api/errors
Claude Haiku 5.5 accepts `thinking: {"type": "disabled"}` and holds it to the same two effort limits that apply to `between_tools`: at `xhigh` or `max` effort, or with a per-messag
On the Claude API and Google Cloud, Claude Opus 5.5 and Claude Sonnet 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/computer-use-tool) on
On the Claude API and Google Cloud, Claude Opus 5.5, Claude Sonnet 5.5, and Claude Haiku 5.5 support [computer use](https://platform.claude.com/docs/en/agents-and-tools/tool-use/co
On Claude Fable 5.1, Claude Opus 5.5, and Claude Sonnet 5.5, the API accepts a replayed thinking block only while the `system` prompt, `tools`, and messages that preceded it are un
+4 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+2−0
apichanged
agents-and-tools/tool-use/web-search-tool
To check whether a model accepts web search before you send a request, read its `capabilities.server_tools.web_search.supported` value from the Models API. [Using the Models API](h
+2 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+1−0
apichanged
agents-and-tools/tool-use/tool-search-tool
| Claude Haiku 5.5 (claude-haiku-5-5) | `tool_search_tool_regex_20251119`, `tool_sear
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/tool-reference
±changed
+1−1
apichanged
agents-and-tools/tool-use/tool-reference
For model compatibility, see each tool's page. Supported models vary by tool and by tool version.
For model compatibility, see each tool's page. Supported models vary by tool and by tool version. To check from your code whether a model accepts web search or code execution, see
+1 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+2−1
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
- claude-haiku-5-5
Programmatic tool calling requires the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) with tool version `code_execution_20
Programmatic tool calling requires the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool) with tool version `code_execution_20
+2 −1 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+1−0
apichanged
agents-and-tools/tool-use/overview
| Claude Haiku 5.5 | 286 tokens
+1 −0 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+2−2
apichanged
agents-and-tools/tool-use/define-tools
| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported
| Manual [extended thinking](https://platform.claude.com/docs/en/build-with-claude/extended-thinking) (`thinking: {type: "enabled"}`) | `any` and `tool` are not supported
 with a `keep` value other than `"all"` shifts the advisor's quoted transcript each turn,
[`clear_thinking`](https://platform.claude.com/docs/en/build-with-claude/context-editing) with a `keep` value other than `"all"` shifts the advisor's quoted transcript each turn,
| Executor models | Advisor models
+18 −17 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/mcp-connector
±changed
+4−4
apichanged
agents-and-tools/mcp-connector
implementation("com.anthropic:anthropic-java:2.68.0")
implementation("com.anthropic:anthropic-java-mcp:2.68.0")
implementation("com.anthropic:anthropic-java:2.69.0")
implementation("com.anthropic:anthropic-java-mcp:2.69.0")
<version>2.68.0</version>
+4 −4 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/agent-skills/overview
±changed
+6−2
apichanged
agents-and-tools/agent-skills/overview
+6 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/agent-skills/claude-api-skill
±changed
+2−2
apichanged
agents-and-tools/agent-skills/claude-api-skill
* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.c
* **Model migration:** Step-by-step guidance for migrating to newer Claude models (including the breaking changes and behavior shifts on [Claude Opus 5.5](https://platform.claude.c
For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-g
For the full list of model-specific changes the skill applies, see [Migrating to Claude Opus 5.5 from Claude Opus 5](https://platform.claude.com/docs/en/models/opus-5-5/migration-g
+2 −2 lines
Recorded here 7 Oct 2026 19:07 UTC
api
agents-and-tools/agent-skills/best-practices
±changed
+9−3
apichanged
agents-and-tools/agent-skills/best-practices
<Frame>
</Frame>
+9 −3 lines
Recorded here 7 Oct 2026 19:07 UTC
api
about-claude/use-case-guides/ticket-routing
±changed
+41−9
apichanged
about-claude/use-case-guides/ticket-routing
Many customers have found `claude-haiku-4-5-20251001` an ideal model for ticket routing, as it is the fastest and most cost-effective model in the Claude 4 family while still deliv
Claude Haiku 5.5 (`claude-haiku-5-5`) suits ticket routing: it's the fastest and most cost-effective current model, and at `low` effort it handles simple, high-volume requests such
This prompt is written for Claude Haiku 4.5, which runs here without thinking. On Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5, ask for
This prompt is written for Claude Haiku 5.5, which runs here at `low` effort. On Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, and Claude Sonnet 5.5, ask for
DEFAULT_MODEL = "claude-haiku-4-5-20251001"
+41 −9 lines
Recorded here 7 Oct 2026 19:07 UTC
api
about-claude/use-case-guides/content-moderation
±changed
+6−6
apichanged
about-claude/use-case-guides/content-moderation
When selecting a model, it’s important to consider the size of your data. If costs are a concern, a smaller model such as Claude Haiku 4.5 is an excellent choice because of its cos
When selecting a model, it’s important to consider the size of your data. If costs are a concern, a smaller model such as Claude Haiku 5.5 is an excellent choice because of its cos
* **Claude Haiku 4.5 estimated cost**
* Input token cost: 28,600 MTok \* $1.00/MTok = $28,600 USD
+6 −6 lines
Recorded here 7 Oct 2026 19:07 UTC
api
about-claude/pricing
±changed
+15−8
apichanged
about-claude/pricing
| Claude Haiku 5.5 (for prompts up to 100,000 tokens) | $0.10 / MTok | $0.125 / MTok |
| Claude Haiku 5.5 (for prompts over 100,000 tokens) | $0.50 / MTok | $0.625 / MTok |
| Cache operation | Multiplier | Duration |
| -------------------- | -------------------------------------------------------------------------------------------------- | ------------------------------------ |
| 5-minute cache write | 1.25x base input price | Cache valid for 5 minutes |
+15 −8 lines
Recorded here 7 Oct 2026 19:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+94−40
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
 that trades intelligence for latency and cost within
* **Effort:** Several Claude models support an [effort parameter](https://platform.claude.com/docs/en/build-with-claude/effort) that trades intelligence for latency and cost within
For many applications, starting with a faster, more cost-effective model like Claude Haiku 4.5 can be the optimal approach:
For many applications, starting with a faster, more cost-effective model like Claude Haiku 5.5 can be the optimal approach:
1. Begin implementation with Claude Haiku 4.5.
+4 −4 lines
Recorded here 7 Oct 2026 19:07 UTC
api
about-claude/model-deprecations
±changed
+1−0
apichanged
about-claude/model-deprecations
| claude-haiku-5-5 | Active | N/A | Not sooner than October 7, 2027 |
+1 −0 lines
Recorded here 7 Oct 2026 19:07 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 7 Oct 2026 19:07 UTC
claude-code
headless
±changed
+26−10
claude-codechanged
headless
Messages from [subagents](/docs/en/sub-agents) appear in the stream as `assistant` and `user` messages whose `parent_tool_use_id` field is the ID of the tool call that spawned the
The first message from a subagent running in the [foreground](/docs/en/sub-agents#run-subagents-in-foreground-or-background) is a `user` message carrying the prompt that drives it.
* **By default**: the subagent's `tool_use` and `tool_result` blocks.
+26 −10 lines
Upstream edited 7 Oct 2026 19:02 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
| `forwardSubagentText` | `boolean` | `false` | Forward subagent text and thinking blocks as assistant and user messages with `parent_tool_use_id` set, so consumers can render a ne
| `forwardSubagentText` | `boolean` | `false` | Forward subagent text and thinking blocks as assistant and user messages with `parent_tool_use_id` set, so consumers can render a ne
+1 −1 lines
Upstream edited 7 Oct 2026 19:02 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
| `forward_subagent_text` | `bool` | `False` | Forward subagent text and thinking blocks in the message stream. Without this option, Claude Code emits subagent `tool_use` and `tool
| `forward_subagent_text` | `bool` | `False` | Forward subagent text and thinking blocks in the message stream. Without this option, Claude Code omits the text and thinking blocks
+1 −1 lines
Upstream edited 7 Oct 2026 19:02 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
cloud-environments
±changed
+1−1
claude-codechanged
cloud-environments
Two of these decide whether you can add a secret, and two decide whether the agent proxy can use it once added:
These requirements decide whether you can add a secret and whether the agent proxy can use it once added:
+1 −1 lines
Upstream edited 7 Oct 2026 18:43 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
claude-projects
±changed
+1−1
claude-codechanged
claude-projects
* **Network, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already reaches
* **Network access, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already
+1 −1 lines
Upstream edited 7 Oct 2026 18:43 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
claude-apps-gateway-config
±changed
+10−1
claude-codechanged
claude-apps-gateway-config
* **Policy contents**: editing a policy and redeploying reaches connected clients on their next managed-settings poll, within an hour, apart from the [changes that apply only at
* **Policy contents**: editing a policy and redeploying reaches connected Claude Code clients on their next managed-settings poll, within an hour, apart from the [changes that ap
Claude Desktop follows [its own schedule](#claude-desktop-overlay).
+10 −1 lines
Upstream edited 7 Oct 2026 18:41 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
Path-scoped rules and nested CLAUDE.md files load into message history when their trigger file is read, so compaction summarizes them away with everything else. If a rule must pers
Path-scoped rules and nested CLAUDE.md files load into message history when Claude reads, writes, or edits their trigger file, so compaction summarizes them away with everything el
+1 −1 lines
Upstream edited 7 Oct 2026 18:41 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-code
claude-directory
±changed
+5−5
claude-codechanged
claude-directory
when: <>Rules without <C>paths:</C> load at session start. Rules with <C>paths:</C> load when a matching file enters context</>,
when: <>Rules without <C>paths:</C> load at session start. Rules with <C>paths:</C> load when Claude reads, writes, or edits a matching file</>,
when: <>Loaded when Claude reads a file matching the <C>paths:</C> globs below</>,
when: <>Loaded when Claude reads, writes, or edits a file matching the <C>paths:</C> globs below</>,
when: <>Loaded when Claude reads a file matching the <C>paths:</C> glob below</>,
+5 −5 lines
Upstream edited 7 Oct 2026 18:41 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-docs
third-party/claude-desktop/configuration-changelog
±changed
+4−0
claude-docschanged
third-party/claude-desktop/configuration-changelog
<Update label="v2.26454.2" description="2026-10-07">
No configuration changes in this release.
</Update>
+4 −0 lines
Upstream edited 7 Oct 2026 18:40 UTC Recorded here 7 Oct 2026 19:07 UTC
claude-docs
cowork/changelog
±changed
+20−0
claude-docschanged
cowork/changelog
<Update label="v2.26454.2" description="2026-10-07">
Bundled Claude Code version: 2.1.293.
**General**
+20 −0 lines
Upstream edited 7 Oct 2026 18:40 UTC Recorded here 7 Oct 2026 19:07 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 7 Oct 2026 18:37 UTC
claude-docs
claude-science/changelog
±changed
+5−0
claude-docschanged
claude-science/changelog
<Update label="0.1.60" description="October 7, 2026">
* Mac: fixed a problem introduced in 0.1.59 where Python, R, and some shell commands could fail to run when Claude Science has access to many folders
* **Settings > Network > Package mirror** now shows a mirror credential file your organization deployed, instead of asking for a token
</Update>
+5 −0 lines
Upstream edited 7 Oct 2026 18:36 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
Each resolve of the chain times out after 60 seconds. If a step in the chain stalls, for example a `credential_process` helper that waits for input it can't receive, the request fa
The resolve that fills the cache times out after 60 seconds. If a step in the chain stalls, for example a `credential_process` helper that waits for input it can't receive, the req
+1 −1 lines
Upstream edited 7 Oct 2026 18:29 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
changelog
±changed
+59−0
claude-codechanged
changelog
<Update label="2.1.293" description="October 7, 2026">
* Added Claude Haiku 5.5 (`claude-haiku-5-5`), now the default Haiku model on the Anthropic API — 1M context, $0.10/$0.50 per Mtok ($0.50/$2.50 for prompts over 100K)
* Added `agentType` to the `subagentStatusLine` payload, so scripts can tell custom subagent types apart
* Added `isDeferred` to `$.tool.register` for mods: `false` lists the tool's schema in the prompt from the start instead of behind tool search
+59 −0 lines
Upstream edited 7 Oct 2026 18:26 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
workflows
±changed
+6−1
claude-codechanged
workflows
When workflows are disabled, the bundled workflow commands and the `/workflow-authoring` skill are unavailable, the `ultracode` keyword no longer triggers a run, and the **Ultracod
When workflows are disabled:
* `/workflows`, the workflow commands, and the `/workflow-authoring` skill are unavailable
* The `ultracode` keyword no longer triggers a run, and the **Ultracode** toggle is removed from `/effort`
+6 −1 lines
Upstream edited 7 Oct 2026 18:21 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
agent-sdk/typescript
±changed
+1−1
claude-codechanged
agent-sdk/typescript
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
+1 −1 lines
Upstream edited 7 Oct 2026 18:20 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
agent-sdk/python
±changed
+1−1
claude-codechanged
agent-sdk/python
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
The optional `display` field controls whether thinking text is returned `"summarized"` or `"omitted"`. On Claude Opus 4.7 and later, the API default is `"omitted"`, so set `"summar
+1 −1 lines
Upstream edited 7 Oct 2026 18:20 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-docs
cowork/changelog
±changed
+1−1
claude-docschanged
cowork/changelog
Microsoft has released a Windows update that fixes the issue where Cowork could not reach your files on Windows PCs. Install the latest Windows update and restart your PC. On Win
Microsoft has released a Windows update that fixes the issue where Cowork could not reach your files on Windows PCs. Install the latest Windows update and restart your PC. On Win
+1 −1 lines
Upstream edited 7 Oct 2026 18:16 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/ssh-remote-sessions
±changed
+49−10
claude-docschanged
third-party/claude-desktop/ssh-remote-sessions
An idle engine stays on the host, with the credential in its environment, until the user reopens, archives, or deletes the session, the host restarts, or a Claude Desktop update re
On a host that ends a user's processes at logout, the remote server and the engine end with the SSH connection that started them, so a turn in progress doesn't survive a disconnect
An idle engine stays on the host, with the credential in its environment, until one of these happens:
+49 −10 lines
Upstream edited 7 Oct 2026 18:12 UTC Recorded here 7 Oct 2026 18:37 UTC
claude-code
claude-tag
±changed
+4−4
claude-codechanged
claude-tag
No line of the body moved in this read.
+4 −4 lines
Recorded here 7 Oct 2026 18:07 UTC
claude-code
sessions
±changed
+3−3
claude-codechanged
sessions
<h5 id="resume-in-plan-mode-with-p">
Resume in plan mode with `-p`
</h5>
<a id="resume-in-plan-mode-with-p" />
+3 −3 lines
Upstream edited 7 Oct 2026 18:04 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
claude-apps-gateway-config
±changed
+2−0
claude-codechanged
claude-apps-gateway-config
<a id="apply-an-amazon-bedrock-guardrail" />
+2 −0 lines
Upstream edited 7 Oct 2026 18:04 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
agent-sdk/typescript
±changed
+0−2
claude-codechanged
agent-sdk/typescript
<script src="/docs/components/typescript-sdk-type-links.js" defer />
+0 −2 lines
Upstream edited 7 Oct 2026 18:04 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
server-managed-settings
±changed
+1−1
claude-codechanged
server-managed-settings
Server-managed settings and [endpoint-managed settings](/docs/en/managed-settings#delivery-mechanisms) both occupy the highest tier in the Claude Code [settings hierarchy](/docs/en
Server-managed settings and [endpoint-managed settings](/docs/en/managed-settings#delivery-mechanisms) both occupy the highest tier in the Claude Code [settings hierarchy](/docs/en
+1 −1 lines
Upstream edited 7 Oct 2026 17:58 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
The hierarchy Claude Code reads configuration from, in precedence order from highest to lowest: [managed policy](#managed-settings), command-line arguments, local settings at `.cla
The hierarchy Claude Code reads configuration from, in precedence order from highest to lowest: [managed policy](#managed-settings), settings you pass with the `--settings` flag, l
+1 −1 lines
Upstream edited 7 Oct 2026 17:58 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
claude-directory
±changed
+2−2
claude-codechanged
claude-directory
| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that you can't override, apart from [narrow exceptions](/docs/en/settings#security-keys-where-
| `managed-settings.json` | System-level, varies by OS | Enterprise-enforced settings that your own settings files and `--settings` values can't override, apart from [narrow except
* [Managed settings](/docs/en/server-managed-settings) deployed by your organization take precedence over everything, apart from the [exceptions under Settings precedence](/docs/
* [Managed settings](/docs/en/server-managed-settings) deployed by your organization take precedence over every settings file and `--settings` value, apart from the [exceptions u
+2 −2 lines
Upstream edited 7 Oct 2026 17:58 UTC Recorded here 7 Oct 2026 18:07 UTC
claude-code
claude-tag
±changed
+2−2
claude-codechanged
claude-tag
No line of the body moved in this read.
+2 −2 lines
Recorded here 7 Oct 2026 17:56 UTC
claude-code
hooks
±changed
+5−2
claude-codechanged
hooks
* You exit a `--worktree` session and choose to remove the worktree
* You exit an interactive [worktree session](/docs/en/worktrees#start-claude-in-a-worktree) and choose to remove the worktree when Claude Code prompts you
* You exit an interactive worktree session you haven't [named](/docs/en/sessions#name-your-sessions), Claude Code finds no changed or untracked files, and it removes the worktree w
Claude Code uses git to look for changed or untracked files, so it finds none in a worktree that isn't a git checkout or inside one, even when the directory holds uncommitted work.
+5 −2 lines
Upstream edited 7 Oct 2026 17:52 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
advisor
±changed
+3−3
claude-codechanged
advisor
<Note>
The advisor tool is experimental and requires the Anthropic API. It is not available on Amazon Bedrock, Claude Platform on AWS, Google Cloud's Agent Platform, or Microsoft Foundr
</Note>
> [!NOTE]
>
+3 −3 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
settings-reference
±changed
+1−1
claude-codechanged
settings-reference
On models that always think, such as Opus 5.5, Sonnet 5.5, and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Claude Code om
On models that always think, such as Opus 5.5, Sonnet 5.5, Haiku 5.5, and the Fable models, `false` has no effect. On [third-party providers](/docs/en/third-party-integrations) Cla
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
* Model: the session continues on the model it was using. The model isn't restored when it has been retired or isn't allowed by `availableModels`, when a `--model` flag or `ANTHROP
* Model: the session continues on the model it was using, except in the cases in [Setting your model](/docs/en/model-config#setting-your-model).
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
prompt-caching
±changed
+2−2
claude-codechanged
prompt-caching
* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Opus 5.5, Sonnet 5.5, and Fable 5.1 with a
* **Effort level**: on most models, each effort level has its own cache, so changing effort mid-session recomputes the entire request. On Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable
On Opus 5.5, Sonnet 5.5, and Fable 5.1 with an API key or a Claude subscription, changing effort keeps the cache, and Claude Code applies the new level without asking. This doesn't
On Opus 5.5, Sonnet 5.5, Haiku 5.5, and Fable 5.1 with an API key or a Claude subscription, changing effort keeps the cache, and Claude Code applies the new level without asking. T
+2 −2 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
permission-modes
±changed
+2−2
claude-codechanged
permission-modes
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-co
* **Model**: on the Anthropic API and [Claude Platform on AWS](/docs/en/claude-platform-on-aws), Claude Opus 4.6 or later, Sonnet 4.6 or later, Haiku 5.5, or a [Fable model](/docs/
Only Claude Sonnet 5 or later, Opus 4.7 or later, and the Fable models are supported on these providers. On any other model, the session starts in Manual instead.
Only Claude Sonnet 5 or later, Opus 4.7 or later, Haiku 5.5, and the Fable models are supported on these providers. On any other model, the session starts in Manual instead. Auto m
+2 −2 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
model-config
±changed
+37−26
claude-codechanged
model-config
The version that the `opus` and `sonnet` aliases resolve to depends on the provider:
| Provider | `opus` | `sonnet` |
| :- | :- | :- |
| Anthropic API | Opus 5.5 | Sonnet 5.5 |
+37 −26 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
interactive-mode
±changed
+1−1
claude-codechanged
interactive-mode
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Opus 5.5, Sonnet 5.5, or the Fable models, w
| `Option+T` (macOS) or `Alt+T` (Windows/Linux) | Toggle extended thinking | Enable or disable extended thinking mode. Has no effect on Opus 5.5, Sonnet 5.5, Haiku 5.5, or the Fabl
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
glossary
±changed
+1−1
claude-codechanged
glossary
A setting that controls adaptive reasoning, which lets the model decide whether and how much to think on each step. Higher effort means more thinking tokens and deeper reasoning; l
A setting that controls adaptive reasoning, which lets the model decide whether and how much to think on each step. Higher effort means more thinking tokens and deeper reasoning; l
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
feature-availability
±changed
+4−4
claude-codechanged
feature-availability
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5 or later, Opus 4.7 or late
<span id="fn2" style={{display: 'block', position: 'relative', top: '-120px'}} /><sup>2</sup> On these providers, auto mode supports only Claude Sonnet 5 or later, Opus 4.7 or late
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5 or later, Opus 4.7 or later, and Fable models only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5 or later, Opus 4.7 or later, Haiku 5.5, and Fable models only
* [Auto mode](/docs/en/auto-mode-config): Sonnet 5 or later, Opus 4.7 or later, and Fable models only
+4 −4 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
desktop
±changed
+4−4
claude-codechanged
desktop
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, or a [Fable model](/docs/en/model-config#work-with-fable). Orga
Auto mode is available to all users on the Anthropic API and requires Claude Opus 4.6 or later, Sonnet 4.6 or later, Haiku 5.5, or a [Fable model](/docs/en/model-config#work-with-f
[Extended thinking](/docs/en/model-config#extended-thinking) is enabled by default, which improves performance on complex reasoning tasks but uses additional tokens. On the Anthrop
On models with [adaptive reasoning](/docs/en/model-config#adjust-effort-level), Claude Code ignores the number itself in a positive `MAX_THINKING_TOKENS` value because adaptive rea
+4 −4 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
For simpler tasks where deep reasoning isn't needed, you can reduce costs by lowering the [effort level](/docs/en/model-config#adjust-effort-level) with `/effort` or in `/model`, o
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
context-window
±changed
+1−1
claude-codechanged
context-window
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context window. See [
If you need a larger window rather than a smaller conversation, Fable models, Sonnet 5 and later, Haiku 5.5, Opus 4.6 and later, and Sonnet 4.6 support a 1 million token context wi
+1 −1 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
advisor
±changed
+9−9
claude-codechanged
advisor
* The requested model, such as Haiku, can't act as an advisor
* The requested model, such as Haiku 4.5, can't act as an advisor
| Haiku 4.5 | Fable, Opus, Sonnet |
| Sonnet 4.6 | Fable, Opus, Sonnet |
| Opus 4.6 | Fable, Opus, Sonnet 5 or later |
+9 −9 lines
Upstream edited 7 Oct 2026 17:51 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
cloud-environments
±changed
+66−42
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
The dialog includes the name, network access level, environment variables, and setup script. When you edit an existing cloud environment on a Pro or Max plan, the dialog also i
The dialog includes the name, network access level, environment variables, and setup script. When you edit an existing cloud environment on a Pro or Max plan, the dialog also i
Anyone who uses the environment can read the values. On Pro and Max plans, use an [API credential](#add-api-credentials) instead for a key the agent proxy can attach to a request.
+66 −42 lines
Upstream edited 7 Oct 2026 17:45 UTC Recorded here 7 Oct 2026 17:56 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
Upstream edited 7 Oct 2026 17:44 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
Anyone who uses an environment can read its variables, so don't put a credential there, such as a collector token in `OTEL_EXPORTER_OTLP_HEADERS`. An [API credential](/docs/en/clou
Anyone who uses an environment can read its variables, so don't put a credential there, such as a collector token in `OTEL_EXPORTER_OTLP_HEADERS`. A [network secret](/docs/en/cloud
+1 −1 lines
Upstream edited 7 Oct 2026 17:44 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
claude-projects
±changed
+6−6
claude-codechanged
claude-projects
* A [cloud environment](#choose-an-environment-for-threads) that sets its network access, environment variables, API credentials, and installed tools
* A [cloud environment](#choose-an-environment-for-threads) that sets its network access, environment variables, network secrets, and installed tools
* **Network, credentials, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already rea
* **Network, secrets, and tools**: for cloud threads, these come from the project's [cloud environment](#choose-an-environment-for-threads). The default environment already reaches
Every new cloud thread starts in the project's [cloud environment](/docs/en/cloud-environments). The environment sets which domains threads can reach, which environment variables t
+6 −6 lines
Upstream edited 7 Oct 2026 17:44 UTC Recorded here 7 Oct 2026 17:56 UTC
claude-code
claude-code-on-the-web
±changed
+1−1
claude-codechanged
claude-code-on-the-web
* **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
* **Network secrets**: 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
Upstream edited 7 Oct 2026 17:44 UTC Recorded here 7 Oct 2026 17:56 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 7 Oct 2026 17:37 UTC
claude-code
authentication
±changed
+1−1
claude-codechanged
authentication
After [installing Claude Code](/docs/en/setup#install-claude-code), run `claude` in your terminal. On first launch, Claude Code opens a browser window for you to log in. If you've
After [installing Claude Code](/docs/en/setup#install-claude-code), run `claude` in your terminal. On first launch, Claude Code opens a browser window for you to log in. If you've
+1 −1 lines
Upstream edited 7 Oct 2026 17:28 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
setup
±changed
+6−4
claude-codechanged
setup
On Windows, your prompt shows `PS C:\` when you're in PowerShell and `C:\` without the `PS` when you're in CMD.
If you see `The token '&&' is not a valid statement separator`, you're in PowerShell, not CMD. If you see `'irm' is not recognized as an internal or external command`, you're i
If the install command fails with `syntax error near unexpected token '<'`, a `403`, or another curl error, see [Troubleshoot installation](/docs/en/troubleshoot-install#find-y
+6 −4 lines
Upstream edited 7 Oct 2026 17:28 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
quickstart
±changed
+42−74
claude-codechanged
quickstart
> Welcome to Claude Code!
This quickstart guide will have you using AI-powered coding assistance in a few minutes. By the end, you'll understand how to use Claude Code for common development tasks.
> Install Claude Code in your terminal, sign in, and use the CLI to explore your codebase and make your first code change.
+42 −74 lines
Upstream edited 7 Oct 2026 17:28 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
overview
±changed
+6−4
claude-codechanged
overview
On Windows, your prompt shows `PS C:\` when you're in PowerShell and `C:\` without the `PS` when you're in CMD.
If you see `The token '&&' is not a valid statement separator`, you're in PowerShell, not CMD. If you see `'irm' is not recognized as an internal or external command`, you'
If the install command fails with `syntax error near unexpected token '<'`, a `403`, or another curl error, see [Troubleshoot installation](/docs/en/troubleshoot-install#fi
+6 −4 lines
Upstream edited 7 Oct 2026 17:28 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
managed-mcp
±changed
+103−105
claude-codechanged
managed-mcp
<Note>
The [Security](/docs/en/security) page covers the MCP threat model and how to evaluate a server before approving it. [Decide what to enforce](/docs/en/admin-setup#decide-what-to-
</Note>
> [!NOTE]
>
+103 −105 lines
Upstream edited 7 Oct 2026 17:15 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
managed-mcp
±changed
+17−5
claude-codechanged
managed-mcp
URLs support `*` wildcards anywhere in the pattern, including the scheme. Hostname matching is case-insensitive and ignores a trailing FQDN dot, so `https://Mcp.Example.com/*` matc
URLs support `*` wildcards, including `*` as the whole scheme. Hostname matching is case-insensitive and ignores a trailing FQDN dot, so `https://Mcp.Example.com/*` matches `https:
* **Hostname written out in full**: the default port only, 443 for `https` and 80 for `http`
* **Hostname with a `*` in it**: every port
+17 −5 lines
Upstream edited 7 Oct 2026 17:15 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
sub-agents
±changed
+2−2
claude-codechanged
sub-agents
* **Control costs** by routing tasks to faster, cheaper models like Haiku
* **Control costs** by routing tasks to faster, lower-cost models like Haiku
Because a fork's system prompt and tool definitions are identical to the parent, its first request reuses the parent's [prompt cache](/docs/en/prompt-caching#subagents-and-the-cach
Because a fork's system prompt and tool definitions are identical to the parent, its first request reuses the parent's [prompt cache](/docs/en/prompt-caching#subagents-and-the-cach
+2 −2 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
prompt-library
±changed
+1−1
claude-codechanged
prompt-library
teaches: "Catch problems while they're still cheap to fix. Claude reads the changed files in full, not just the diff lines, so it spots issues a quick self-review misses.",
teaches: "Catch problems while they take less work to fix. Claude reads the changed files in full, not just the diff lines, so it spots issues a quick self-review misses.",
+1 −1 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
prompt-caching
±changed
+2−2
claude-codechanged
prompt-caching
The time to live (TTL) controls how long a gap the cache survives. The API offers two: a five-minute TTL, and a [one-hour TTL](https://platform.claude.com/docs/en/build-with-claude
The time to live (TTL) controls how long a gap the cache survives. The API offers two: a five-minute TTL, and a [one-hour TTL](https://platform.claude.com/docs/en/build-with-claude
Once you go over your plan's usage limit and Claude Code draws on [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans), you are billed
Once you go over your plan's usage limit and Claude Code draws on [usage credits](https://support.claude.com/en/articles/12429409-extra-usage-for-paid-claude-plans), you are billed
+2 −2 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
plugin-evals
±changed
+1−1
claude-codechanged
plugin-evals
To iterate on one case cheaply, run a single arm once. A single run is noisy, so confirm any change at the default three runs before you trust it. With one arm the table shows
To iterate on one case with fewer runs, run a single arm once. A single run is noisy, so confirm any change at the default three runs before you trust it. With one arm the tabl
+1 −1 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
fast-mode
±changed
+1−1
claude-codechanged
fast-mode
The first time you enable fast mode in a conversation, you pay the full fast mode uncached input token price for the entire conversation context. The deeper into a conversation you
The first time you enable fast mode in a conversation, you pay the full fast mode uncached input token price for the entire conversation context. The deeper into a conversation you
+1 −1 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
costs
±changed
+1−1
claude-codechanged
costs
* **Test incrementally**: Write one file, test it, then continue. This catches issues early when they're cheap to fix.
* **Test incrementally**: Write one file, test it, then continue. This catches issues early.
+1 −1 lines
Upstream edited 7 Oct 2026 17:14 UTC Recorded here 7 Oct 2026 17:37 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 17:07 UTC
claude-code
agent-sdk/typescript
±changed
+4−2
claude-codechanged
agent-sdk/typescript
Reports code-review findings as a structured list so Claude Code can render them instead of printing them as text. `level` is the effort level the review ran at. Findings are order
Reports code-review findings as a structured list so Claude Code can render them instead of printing them as text. Findings are ordered most-severe first, with at most 32 per call,
`level` is optional and holds the effort level Claude reports for the review. Claude Code doesn't compare it with the level the review ran at, so the two can differ.
Returns the number of findings reported, the effort level the review ran at, and the findings echoed back for the result body. Requires Claude Code v2.1.196 or later. The echoed `s
+4 −2 lines
Upstream edited 7 Oct 2026 16:51 UTC Recorded here 7 Oct 2026 17:07 UTC
claude-code
claude-tag
±changed
+1−1
claude-codechanged
claude-tag
No line of the body moved in this read.
+1 −1 lines
Recorded here 7 Oct 2026 16:37 UTC
claude-code
remote-control
±changed
+1−1
claude-codechanged
remote-control
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code, or otherwise stop the `claude` process, t
* **Local process must keep running**: Remote Control runs as a local process. If you close the terminal, quit the Desktop app or VS Code, or otherwise stop the `claude` process, t
+1 −1 lines
Upstream edited 7 Oct 2026 16:29 UTC Recorded here 7 Oct 2026 16:37 UTC
claude-code
keybindings
±changed
+3−2
claude-codechanged
keybindings
| `footer:up` | Up | Navigate up in footer (deselects at top) |
| `footer:down` | Down | Navigate down in footer |
| `footer:up` | Up, Ctrl+P | Navigate up in footer (deselects at top) |
| `footer:down` | Down, Ctrl+N | Navigate down in footer |
| `footer:close` | x | Stop the selected [agent](/docs/en/sub-agents#observe-and-steer-running-forks) or [workflow](/docs/en/workflows#manage-runs), or dismiss its row if it's no l
+3 −2 lines
Upstream edited 7 Oct 2026 16:26 UTC Recorded here 7 Oct 2026 16:37 UTC
claude-code
llm-gateway-connect
±changed
+8−1
claude-codechanged
llm-gateway-connect
With the gateway configuration active, the desktop app runs sessions on your local machine only: the environment picker doesn't offer SSH sessions or Anthropic-hosted cloud environ
With the gateway configuration active, the environment picker doesn't offer Anthropic-hosted cloud environments, and [Remote Control](/docs/en/remote-control) is unavailable.
SSH sessions are in beta with a gateway configuration and require Claude Desktop v1.40609.0 or later. Before you connect, check the allowlist and the gateway's address:
+8 −1 lines
Upstream edited 7 Oct 2026 16:17 UTC Recorded here 7 Oct 2026 16:37 UTC
api
models/sonnet-5-5/migration-guide
±changed
+2−2
apichanged
models/sonnet-5-5/migration-guide
title: Migrating to Claude Sonnet 5.5
title: Claude Sonnet 5.5 migration guide
description: "Move code to Claude Sonnet 5.5 from Claude Sonnet 5, Claude Sonnet 4.6, Claude Sonnet 4.5, Claude Sonnet 4, Claude 3.7 Sonnet, or Claude Haiku 4.5: settings that retu
description: Switch to Claude Sonnet 5.5 from earlier Sonnet models or Claude Haiku 4.5 with this migration guide. The guidance to enable Claude Sonnet 5.5 includes settings that r
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/overview
±changed
+1−1
apichanged
models/overview
* **Output quality:** When migrating from a previous model generation, you may notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see [Migrat
* **Output quality:** When migrating from a previous model generation, you may notice larger improvements in overall performance. If you're on Claude Opus 5 or earlier, see the [Cl
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/opus-5-5/migration-guide
±changed
+2−2
apichanged
models/opus-5-5/migration-guide
title: Migrating to Claude Opus 5.5
title: Claude Opus 5.5 migration guide
description: "Migrate to Claude Opus 5.5 from earlier Opus models or Claude Sonnet 5: request settings that return errors, thinking blocks in every response, and a checklist for ea
description: Switch to Claude Opus 5.5 from earlier Opus models or Claude Sonnet 5 with this migration guide. The guidance to enable Claude Opus 5.5 includes request settings that
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/haiku-4-5/migration-guide
±changed
+2−2
apichanged
models/haiku-4-5/migration-guide
title: Migrating to Claude Haiku 4.5
title: Claude Haiku 4.5 migration guide
description: "Migrate to Claude Haiku 4.5 from earlier Haiku models: model IDs, breaking changes, and a migration checklist."
description: Switch to Claude Haiku 4.5 from earlier Haiku models with this migration guide. The guidance to enable Claude Haiku 4.5 includes model IDs, breaking changes, and a mig
+2 −2 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/fable-5/migration-guide
±changed
+3−3
apichanged
models/fable-5/migration-guide
title: Migrating to Claude Mythos 5 and Claude Fable 5
title: Claude Mythos 5 and Claude Fable 5 migration guide
description: "Migrate to Claude Mythos 5 and Claude Fable 5 from Claude Mythos Preview, Claude Opus 5, or Claude Opus 4.8: model IDs, API changes, and migration checklists."
description: Switch to Claude Mythos 5 and Claude Fable 5 from Claude Mythos Preview, Claude Opus 5, or Claude Opus 4.8 with this migration guide. The guidance to enable Claude Myt
If your code is on Claude Opus 4.7 or earlier, first apply the relevant [Migrating to Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/migration-guide) from-s
+3 −3 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/fable-5-1/whats-new-fable-5-1
±changed
+1−1
apichanged
models/fable-5-1/whats-new-fable-5-1
On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it
On Claude Fable 5.1 you can change the [effort](https://platform.claude.com/docs/en/build-with-claude/effort) level mid-conversation without invalidating the prompt cache. Raise it
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/fable-5-1/overview
±changed
+1−1
apichanged
models/fable-5-1/overview
<Card title="Migrating to Claude Fable 5.1" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide">
<Card title="Claude Fable 5.1 migration guide" icon="arrow-right" href="https://platform.claude.com/docs/en/models/fable-5-1/migration-guide">
+1 −1 lines
Recorded here 7 Oct 2026 15:07 UTC
api
models/fable-5-1/migration-guide
±changed
+4−4
apichanged
models/fable-5-1/migration-guide
title: Migrating to Claude Fable 5.1 and Claude Mythos 5.1
title: Claude Fable 5.1 and Claude Mythos 5.1 migration guide
description: "Migrate to Claude Fable 5.1 and Claude Mythos 5.1 from Claude Fable 5, Claude Mythos 5, Claude Opus 5, or Claude Opus 4.8: model IDs, breaking changes, and migration
description: Switch to Claude Fable 5.1 and Claude Mythos 5.1 from Claude Fable 5, Claude Mythos 5, Claude Opus 5, or Claude Opus 4.8 with this migration guide. The guidance to ena
* **Thinking:** [Adaptive thinking](https://platform.claude.com/docs/en/build-with-claude/thinking) is always on, unchanged from Claude Fable 5. The model decides when and how much
+4 −4 lines
Recorded here 7 Oct 2026 15:07 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.