HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
820pages tracked
773 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
81 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
15 Oct 2026
193 pages
+16529 −5100 lines
claude-docs
claude-science/manage-on-devices
±changed
+27−7
claude-docschanged
claude-science/manage-on-devices
Claude Science is a desktop application that stores member content locally. This page covers what IT and endpoint teams need to know: where the app writes data, how to deploy confi
Claude Science is a desktop application that stores member content locally. This page covers what IT and endpoint teams need to know: where the app writes data, how to deploy confi
The app writes to two locations on each member's computer:
The app writes to these locations on each member's computer:
On Windows, the program itself installs per user to `%LOCALAPPDATA%\Programs\ClaudeScience` and registers under the signed-in user's **Settings** > **Apps** > **Installed apps** ra
+27 −7 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
claude-docs
claude-science/mac-app-window
+new page
+28−0
claude-docsnew page
claude-science/mac-app-window
No line of the body moved in this read.
+28 −0 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
claude-docs
claude-science/get-started
±changed
+12−7
claude-docschanged
claude-science/get-started
**Updates.** Installing an update from inside Claude Science can switch it from a browser tab to its own window. See [Claude Science in its own window on macOS](/docs/claude-sc
* **If it opens in a browser tab**: Claude Science checks for updates in the background and shows **Update available** when one is ready. Choose **Restart to update** to instal
* **If it opens in its own window**: Claude Science downloads updates by itself and installs them when you quit. To check for an update right away, choose **Claude Science > Ch
+12 −7 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
claude-docs
claude-science/corporate-networks
±changed
+12−8
claude-docschanged
claude-science/corporate-networks
* Interactive previews load display libraries from public content-delivery networks in the browser, as ordinary browser traffic governed by your endpoint's web policy.
* Interactive previews load display libraries from public content-delivery networks. In a browser tab, that's ordinary browser traffic governed by your endpoint's web policy. When
| Network that only publishes a PAC or WPAD file | Not supported | Supported in the app window, which follows the proxy the script resolves (see [System proxy settings on macOS and
| Network that only publishes a PAC or WPAD file | Supported when Claude Science opens in its own window, not when it opens in a browser tab (see [System proxy settings on macOS an
| TLS inspection on the app's own connections (Zscaler, Netskope, and similar) | Supported with a CA bundle setting | Supported; a corporate root in the computer's certificate stor
+12 −8 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
claude-docs
claude-science/configuration-file-reference
±changed
+2−2
claude-docschanged
claude-science/configuration-file-reference
| `proxy` | string (URL) | unset | The outbound proxy for the app's HTTP and HTTPS connections, for example `http://proxy.example.corp:8080`. Supply Basic-authentication credential
| `proxy` | string (URL) | unset | The outbound proxy for the app's HTTP and HTTPS connections, for example `http://proxy.example.corp:8080`. Supply Basic-authentication credential
| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud s
| `ca_bundle` | string (absolute path) | unset | PEM file added to the app's default TLS trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud s
+2 −2 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
claude-docs
claude-science/command-line-settings
±changed
+3−3
claude-docschanged
claude-science/command-line-settings
| `claude-science update` | Check for and install an update. `--check` only reports; `--to <build>` installs a specific build, which is also how you roll back (see [Roll back to an
| `claude-science update` | Check for and install an update. `--check` only reports; `--to <build>` installs a specific build, which is also how you roll back (see [Roll back to an
`claude-science update --to <build>` installs one specific build. `<build>` is an 8-character build ID such as `3f9a01bc`, not a version number. `claude-science update --check` pri
On a Mac where Claude Science opens in its own window, `claude-science update --to` doesn't change the app, so you can't roll the app back this way. `claude-science update --to <bu
Claude Science checks for updates in the background and shows **Update available** when one is ready. Note the `Current` ID before you choose **Restart to update**, so you know whi
+3 −3 lines
Upstream edited 15 Oct 2026 20:17 UTC Recorded here 15 Oct 2026 20:37 UTC
api
test-and-evaluate/develop-tests
±changed
+433−40
apichanged
test-and-evaluate/develop-tests
max_tokens=50,
max_tokens=1024,
f"Classify this as 'positive', 'negative', 'neutral', or 'mixed': {tweet['text']}"
f"Classify this as 'positive', 'negative', 'neutral', or 'mixed'. Output only the label: {tweet['text']}"
max_tokens: 50,
+433 −40 lines
Recorded here 15 Oct 2026 20:07 UTC
api
release-notes/overview
±changed
+8−0
apichanged
release-notes/overview
### October 15, 2026
* The [Compliance API](https://platform.claude.com/docs/en/manage-claude/compliance-api) now returns the text each organization member saved as **Instructions for Claude** in claud
+8 −0 lines
Recorded here 15 Oct 2026 20:07 UTC
api
models/opus-5-5/whats-new-opus-5-5
±changed
+1−1
apichanged
models/opus-5-5/whats-new-opus-5-5
[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview) is available for Claude Opus 5.5 on the Claude API only; it is not available on Amaz
[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) is available for Claude Opus 5.5 on the Claude API only; it is not available on Amazon Bedrock, Claude
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
models/opus-5-5/overview
±changed
+1−1
apichanged
models/opus-5-5/overview
Lower-latency Claude Opus 5.5 on the Claude API (research preview), priced separately.
Lower-latency Claude Opus 5.5 on the Claude API, priced separately.
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
models/opus-5-5/migration-guide
±changed
+2−2
apichanged
models/opus-5-5/migration-guide
* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` with the `fast-mode-2026-02-01` beta header on the Claude API.
* If you want fast mode, which Claude Opus 4.7 rejects, set `speed: "fast"` on your Claude API requests. Claude Opus 5.5 doesn't need a beta header.
5. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview) on the Claude API. Fast mode is not avail
5. **Fast mode:** Claude Opus 5.5 supports [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) on the Claude API. Fast mode is not available on Claude Opus
+2 −2 lines
Recorded here 15 Oct 2026 20:07 UTC
api
models/fable-5-1/migration-guide
±changed
+64−70
apichanged
models/fable-5-1/migration-guide
-d @- <<'EOF'
{
"model": "claude-fable-5",
"max_tokens": 16000,
"tools": [
+64 −70 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/workflow-runs
±changed
+11−11
apichanged
managed-agents/workflow-runs
* **Handle a failed agent:** When one of its agents fails, the program can handle the failure or let it end the run.
* **Handle a failed agent:** When one of its agents fails, the server usually runs that agent once more, on a new thread, while the run's other agents keep working. If it fails aga
There's no approval step before a run starts: the agent starts a run in the same turn that it writes the workflow. To review a plan first, tell the agent to describe the run and wa
<CodeGroup>
+11 −11 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/vaults
±changed
+12−14
apichanged
managed-agents/vaults
--data @- <<'EOF'
{
"display_name": "Alice",
"metadata": {"external_user_id": "usr_abc123"}
}
+12 −14 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/tools-web-restrictions
±changed
+26−28
apichanged
managed-agents/tools-web-restrictions
-d @- <<'EOF'
{
"name": "Research Agent",
"model": "claude-opus-5-5",
"tools": [
+26 −28 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/tools
±changed
+32−36
apichanged
managed-agents/tools
-d @- <<'EOF'
{
"name": "Coding Assistant",
"model": "claude-opus-5-5",
"tools": [
+32 −36 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/skills
±changed
+9−11
apichanged
managed-agents/skills
--json @- <<'EOF'
{
"name": "Financial Analyst",
"model": "claude-opus-5-5",
"system": "You are a financial analysis agent.",
+9 −11 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/sessions
±changed
+56−72
apichanged
managed-agents/sessions
-d @- <<EOF
{
"agent": "$AGENT_ID",
"environment_id": "$ENVIRONMENT_ID"
}
+56 −72 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/session-threads
±changed
+4−5
apichanged
managed-agents/session-threads
<CodeGroup>
<CodeGroup exclude="shell:CLI">
```bash CLI
# This workflow does not translate well to a one-off shell command.
# Use one of the SDK examples in this code group instead.
+4 −5 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/session-operations
±changed
+11−13
apichanged
managed-agents/session-operations
-d @- <<EOF
{
"agent": {
"tools": [
{"type": "agent_toolset_20260401"},
+11 −13 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/self-hosted-sandboxes-workers
±changed
+78−94
apichanged
managed-agents/self-hosted-sandboxes-workers
Both workers authenticate with the [environment key](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#run-your-first-session) from the quickstart.
With the `ant` CLI:
```bash
+78 −94 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/self-hosted-sandboxes-reference
±changed
+30−34
apichanged
managed-agents/self-hosted-sandboxes-reference
<CodeGroup exclude="shell">
<CodeGroup exclude="shell, csharp, java, php, ruby">
```csharp C#
// EnvironmentWorker is not currently available in the C# SDK.
// To answer custom tool calls directly, see the session event stream.
+30 −34 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/self-hosted-sandboxes-memory
±changed
+13−13
apichanged
managed-agents/self-hosted-sandboxes-memory
<CodeGroup exclude="shell">
<CodeGroup exclude="shell, csharp, java, php, ruby">
```csharp C#
// EnvironmentWorker is not currently available in the C# SDK.
```
+13 −13 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/self-hosted-sandboxes-custom-tools
±changed
+209−45
apichanged
managed-agents/self-hosted-sandboxes-custom-tools
<CodeGroup exclude="shell">
<CodeGroup exclude="shell, csharp, java, php, ruby">
```csharp C#
// EnvironmentWorker is not currently available in the C# SDK.
// To answer custom tool calls directly, see the session event stream.
+209 −45 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/secure-deployment
±changed
+3−3
apichanged
managed-agents/secure-deployment
| [Choose where the agent runs](https://platform.claude.com/docs/en/managed-agents/secure-deployment#choose-where-the-agent-runs)
| [Choose where the agent runs](https://platform.claude.com/docs/en/managed-agents/secure-deployment#choose-where-the-agent-runs)
Choose a cloud environment unless you need files and processes to stay on infrastructure you control. Session history and tool inputs and outputs go to Anthropic either way.
Where the agent's tools run decides who secures the sandbox: Anthropic, with a cloud environment, or you, with a self-hosted sandbox. To choose between them and learn what reaches
* **Isolation and hardening:** You are responsible for isolating sessions from each other, hardening the sandbox image, and storing the environment service key. See the [Security m
+3 −3 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/scheduled-deployments
±changed
+19−23
apichanged
managed-agents/scheduled-deployments
-d @- <<EOF
{
"name": "Weekly compliance scan",
"agent": "$AGENT_ID",
"environment_id": "$ENVIRONMENT_ID",
+19 −23 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/quickstart
±changed
+35−39
apichanged
managed-agents/quickstart
-d @- <<'EOF'
{
"name": "Coding Assistant",
"model": "claude-opus-5-5",
"system": "You are a helpful coding assistant. Write clean, well-documented code.",
+35 −39 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/overview
±changed
+1−1
apichanged
managed-agents/overview
Configure where the agent runs: a cloud sandbox, or a [self-hosted sandbox](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes) on your own infrastructure
[Configure where the agent runs](https://platform.claude.com/docs/en/managed-agents/choosing-an-environment): a cloud sandbox, or a [self-hosted sandbox](https://platform.claud
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/multiagent-orchestration
±changed
+44−55
apichanged
managed-agents/multiagent-orchestration
-d @- <<EOF
{
"name": "Engineering Lead",
"model": "claude-opus-5-5",
"system": "You coordinate engineering work. Delegate code review to the reviewer agent and test writing to the test agent.",
+44 −55 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/memory
±changed
+16−20
apichanged
managed-agents/memory
--data @- <<EOF
{
"agent": "$agent_id",
"environment_id": "$environment_id",
"resources": [
+16 −20 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/mcp-connector
±changed
+20−24
apichanged
managed-agents/mcp-connector
-d @- <<'EOF'
{
"name": "GitHub Assistant",
"model": "claude-opus-5-5",
"mcp_servers": [
+20 −24 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/github
±changed
+32−36
apichanged
managed-agents/github
--data @- <<JSON | jq -r '.id'
{
"name": "Code Reviewer",
"model": "claude-opus-5-5",
"system": "You are a code review assistant with access to GitHub.",
+32 −36 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/events-and-streaming
±changed
+65−79
apichanged
managed-agents/events-and-streaming
<CodeGroup>
<CodeGroup exclude="shell:CLI">
-d @- >/dev/null <<'EOF'
{
"events": [
+65 −79 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/event-deltas
±changed
+12−15
apichanged
managed-agents/event-deltas
<CodeGroup>
<CodeGroup exclude="shell:CLI">
-d @- >/dev/null <<'EOF'
{
"events": [
+12 −15 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/environments
±changed
+23−29
apichanged
managed-agents/environments
This page covers `type: cloud` environments. To run sandboxes on your own infrastructure, see [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted
This page covers `type: cloud` environments. To run sandboxes on your own infrastructure, see [Self-hosted sandboxes](https://platform.claude.com/docs/en/managed-agents/self-hosted
--data @- <<'EOF'
{
"name": "python-dev",
+23 −29 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/dreams
±changed
+15−19
apichanged
managed-agents/dreams
--data @- <<EOF
{
"inputs": [
{ "type": "memory_store", "memory_store_id": "$store_id" },
{ "type": "sessions", "session_ids": ["$session_a", "$session_b"] }
+15 −19 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/define-outcomes
±changed
+16−20
apichanged
managed-agents/define-outcomes
--json @- <<EOF
{
"agent": "$AGENT_ID",
"environment_id": "$ENVIRONMENT_ID",
"title": "Financial analysis on Costco"
+16 −20 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/choosing-an-environment
+new page
+74−0
apinew page
managed-agents/choosing-an-environment
No line of the body moved in this read.
+74 −0 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/budgets
±changed
+8−10
apichanged
managed-agents/budgets
-d @- <<EOF
{
"agent": "$AGENT_ID",
"environment_id": "$ENVIRONMENT_ID",
"budget": {
+8 −10 lines
Recorded here 15 Oct 2026 20:07 UTC
api
managed-agents/agent-setup
±changed
+4−6
apichanged
managed-agents/agent-setup
-d @- <<EOF
{
"version": $AGENT_VERSION,
"system": "You are a helpful coding agent. Always write tests."
}
+4 −6 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/workload-identity-federation
±changed
+21−9
apichanged
manage-claude/workload-identity-federation
<CodeGroup exclude="shell:CLI">
<CodeGroup>
EXPIRES_IN=$(jq -r .expires_in <<<"$RESPONSE") # seconds; re-exchange before this elapses
# The response's expires_in is the token's lifetime in seconds; re-exchange before it elapses.
-d @- <<'JSON' | jq -r '.content[] | select(.type == "text") | .text'
+21 −9 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/user-management
±changed
+2038−120
apichanged
manage-claude/user-management
Set the `ANTHROPIC_API_KEY` environment variable to your Admin API key. The examples on this page read the key from it. The SDK and the `ant` CLI send the `x-api-key` and `anthropi
```bash cURL
curl "https://api.anthropic.com/v1/organizations/users?limit=20" \
-H "x-api-key: $ANTHROPIC_ADMIN_KEY" \
+2038 −120 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/usage-cost-api
±changed
+4−10
apichanged
manage-claude/usage-cost-api
* **Filtering & grouping:** Filter by API key, workspace, model, service tier, context window, [data residency](https://platform.claude.com/docs/en/manage-claude/data-residency), o
* **Filtering & grouping:** Filter by API key, workspace, model, service tier, context window, [data residency](https://platform.claude.com/docs/en/manage-claude/data-residency), o
#### Fast mode (research preview)
#### Fast mode
-H "anthropic-beta: fast-mode-2026-02-01" \
+4 −10 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/spend-limits-api
±changed
+1990−104
apichanged
manage-claude/spend-limits-api
The SDK exposes these endpoints under `client.beta.organization.spend_limits` (typescript: `client.beta.organization.spendLimits`; csharp, go: `client.Beta.Organization.SpendLimits
```bash cURL
curl "https://api.anthropic.com/v1/organizations/spend_limits/effective?limit=20" \
--header "x-api-key: $ANTHROPIC_ADMIN_KEY" \
+1990 −104 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/opentelemetry/sdk
±changed
+1−1
apichanged
manage-claude/opentelemetry/sdk
When the worker sends a tool result, that request's API span is nested under its SDK span. For requests that the worker sends to Claude Platform on AWS, the API spans are in their
When the worker sends a tool result, that request's API span is nested under its SDK span.
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/opentelemetry/api
±changed
+2−2
apichanged
manage-claude/opentelemetry/api
A create request takes the Console's settings except **Provider**, so enter your observability platform's endpoint URL and headers yourself. Set `traces.max_content_bytes` (csharp,
A create request takes the Console's settings except **Provider**, so enter your observability platform's endpoint URL and headers yourself. Set `traces.max_content_bytes` (csharp,
The API reads each request's trace context from the W3C [`traceparent` header](https://www.w3.org/TR/trace-context/). If the sampled flag in the header is off, the API doesn't emit
The API reads each request's trace context from the W3C [`traceparent` header](https://www.w3.org/TR/trace-context/). If the sampled flag in the header is off, the API doesn't emit
+2 −2 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/opentelemetry
±changed
+7−1
apichanged
manage-claude/opentelemetry
You can set up SDK tracing, API tracing, or both. Set up both to see a request's SDK and API spans in one trace, as in the [example traces](https://platform.claude.com/docs/en/mana
You can set up SDK tracing, API tracing, or both. Set up both to see a request's SDK and API spans in one trace, as in the [example traces](https://platform.claude.com/docs/en/mana
Let Claude Code set up this feature for you
+7 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/compliance-org-data
±changed
+35−1
apichanged
manage-claude/compliance-org-data
**Required scope:** `read:compliance_org_data` on the Compliance Access Key. The user and group-member endpoints require `read:compliance_user_data` instead.
**Required scope:** `read:compliance_org_data` on the Compliance Access Key. The user, user-preference, and group-member endpoints require `read:compliance_user_data` instead.
## List user preferences
+35 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/compliance-api-access
±changed
+1−1
apichanged
manage-claude/compliance-api-access
| `read:compliance_user_data` | Read user chats, messages, files, projects, session metadata and transcripts, organization users, and group members
| `read:compliance_user_data` | Read user chats, messages, files, projects, session metadata and transcripts, organization users, user preferences, and group members
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
manage-claude/cmek
±changed
+1−0
apichanged
manage-claude/cmek
* Ratings and comments about the Claude Console that members send with its **Feedback** option. No setting turns these off; members send them only when they choose to.
+1 −0 lines
Recorded here 15 Oct 2026 20:07 UTC
api
cli-sdks-libraries/sdks/typescript
±changed
+5−1
apichanged
cli-sdks-libraries/sdks/typescript
const message = await client.messages.create(/* ... */);
const message = await client.messages.create({
max_tokens: 1024,
messages: [{ role: "user", content: "Hello, Claude" }],
model: "claude-opus-5-5"
+5 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
cli-sdks-libraries/sdks/ruby
±changed
+9−4
apichanged
cli-sdks-libraries/sdks/ruby
anthropic = Anthropic::Client.new
service_tier: Anthropic::MessageCreateParams::ServiceTier::AUTO,
# ...
max_tokens: 1024,
messages: [{role: "user", content: "Hello, Claude"}],
+9 −4 lines
Recorded here 15 Oct 2026 20:07 UTC
api
cli-sdks-libraries/libraries/openai-sdk
±changed
+8−14
apichanged
cli-sdks-libraries/libraries/openai-sdk
<CodeGroup exclude="shell">
<CodeGroup exclude="shell, php">
```php PHP
<?php
// There is no official OpenAI PHP SDK, so no example is shown here.
+8 −14 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/vision-coordinates
±changed
+16−20
apichanged
build-with-claude/vision-coordinates
<CodeGroup>
```bash cURL
# This reference implementation is local math that makes no API request, so
# there's nothing to show for cURL. See the SDK tabs.
```
+16 −20 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/vision
±changed
+21−23
apichanged
build-with-claude/vision
-d @- <<EOF
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"messages": [
+21 −23 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+21−24
apichanged
build-with-claude/thinking-tool-workflows
-d @- <<'EOF'
{
"model": "claude-opus-5-5",
"max_tokens": 16000,
"thinking": {"type": "adaptive"},
+21 −24 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/task-budgets
±changed
+17−2
apichanged
build-with-claude/task-budgets
<CodeGroup exclude="shell:cURL">
<CodeGroup>
```bash cURL
curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
+17 −2 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/skills-guide
±changed
+8−14
apichanged
build-with-claude/skills-guide
<CodeGroup>
```bash cURL
# Multi-turn container reuse doesn't translate well to a one-off shell
# command; one of the SDK options would be a better fit. Capture
# container.id from the first response, then pass it in the next request as
+8 −14 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/search-results
±changed
+8−14
apichanged
build-with-claude/search-results
<CodeGroup>
```bash cURL
# The tool-calling flow needs application-side search logic that doesn't
# translate to a one-off shell command. See the SDK tabs for the full flow.
# The raw shape of a tool conversation with search results is shown in the
+8 −14 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/refusals-and-fallback
±changed
+8−12
apichanged
build-with-claude/refusals-and-fallback
<CodeGroup>
```bash cURL
# The refusal-fallback middleware is an SDK feature. See the
# server-side fallback section for the equivalent single-request approach,
# or the fallback credit page for the raw HTTP retry pattern.
+8 −12 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/prompt-engineering/claude-prompting-best-practices
±changed
+45−0
apichanged
build-with-claude/prompt-engineering/claude-prompting-best-practices
### Medication dosing
If people might ask your application about medicine doses, add the block below for the model your application calls to your system prompt, exactly as written. The block has Claude
```text Medication dosing block for Claude Sonnet 5.5 wrap
+45 −0 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/pdf-support
±changed
+17−19
apichanged
build-with-claude/pdf-support
-d @- <<EOF
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"messages": [{
+17 −19 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/mid-conversation-effort-example
±changed
+33−35
apichanged
build-with-claude/mid-conversation-effort-example
-d @- <<'EOF'
{
"model": "claude-opus-5-5",
"max_tokens": 64000,
"system": "You are a helpful general-purpose agent. Answer the user's request directly.",
+33 −35 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/files
±changed
+21−23
apichanged
build-with-claude/files
-d @- <<EOF
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"messages": [
+21 −23 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/fast-mode
±changed
+56−81
apichanged
build-with-claude/fast-mode
title: Fast mode (research preview)
title: Fast mode
description: Get up to 2.5x higher output tokens per second from supported Claude Opus models.
description: Get up to 2.5x higher output tokens per second from supported Claude models.
Fast mode delivers up to 2.5x higher output tokens per second from Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 at premium pricing. Set `speed: "fast"` with the `fast-mode-2
+56 −81 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/compaction-background
±changed
+1−3
apichanged
build-with-claude/compaction-background
<Note>
The PHP SDK sends requests synchronously, so it can't run the compaction request in the background while the conversation goes on.
</Note>
The PHP SDK sends requests synchronously, so it can't run the compaction request in the background while the conversation goes on.
+1 −3 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+41−5
apichanged
build-with-claude/claude-platform-on-aws
Session behavior on Claude Platform on AWS differs from first-party Claude Managed Agents in two ways:
Sessions and self-hosted workers on Claude Platform on AWS differ from first-party Claude Managed Agents in three ways:
* **[Worker authentication on self-hosted environments](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#prerequisites):** A worker authenticates with AWS I
# The ant CLI's output formats print the response body, not response headers.
# To read x-amzn-requestid, use the cURL example (-i) or an SDK example.
+41 −5 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+16−16
apichanged
build-with-claude/claude-on-vertex-ai
<CodeGroup>
<CodeGroup exclude="shell:CLI">
```bash CLI
# The ant CLI does not support Agent Platform.
```
+16 −16 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+11−6
apichanged
build-with-claude/claude-in-microsoft-foundry
* The [Azure CLI](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli) installed (required for the Entra ID cURL example, optional otherwise)
* The [Azure CLI](https://learn.microsoft.com/en-us/cli/azure/install-azure-cli) installed (required for the Entra ID cURL and CLI examples, optional otherwise)
# The ant CLI can send a bearer token with --auth-token, but a set
# ANTHROPIC_API_KEY environment variable takes precedence over it (the CLI
# prints only a console notice), so your request could authenticate with
+11 −6 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/citations
±changed
+44−48
apichanged
build-with-claude/citations
-d @- <<EOF
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"messages": [
+44 −48 lines
Recorded here 15 Oct 2026 20:07 UTC
api
build-with-claude/cache-diagnostics
±changed
+25−29
apichanged
build-with-claude/cache-diagnostics
-d @- <<EOF | jq '{id, diagnostics}' # diagnostics: null means no divergence was found
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"cache_control": {"type": "ephemeral"},
+25 −29 lines
Recorded here 15 Oct 2026 20:07 UTC
api
api/rate-limits
±changed
+1−1
apichanged
api/rate-limits
When using [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) (research preview) with `speed: "fast"` on Claude Opus 5.5, Claude Opus 5, or Opus 4.8, dedi
When using [fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) with `speed: "fast"` on Claude Opus 5.5, Claude Opus 5, or Opus 4.8, dedicated rate limits a
+1 −1 lines
Recorded here 15 Oct 2026 20:07 UTC
api
api/errors
±changed
+4−5
apichanged
api/errors
<CodeGroup>
```bash cURL
# Raw SSE output requires handling events; there is no single-command way
# to accumulate the final message with curl. Use the SDK examples instead.
```
+4 −5 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/parallel-tool-use
±changed
+16−21
apichanged
agents-and-tools/tool-use/parallel-tool-use
<CodeGroup>
```bash cURL
# This end-to-end test flow doesn't translate well to a one-off shell command.
# See the SDK tabs for the full flow. The underlying HTTP request is a standard
# tool use request with multiple tools defined.
+16 −21 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/fine-grained-tool-streaming
±changed
+8−10
apichanged
agents-and-tools/tool-use/fine-grained-tool-streaming
<CodeGroup>
```bash cURL
# Accumulating per-block input deltas needs a programming language; the first
# example's CLI tab shows the raw fragments with jq. See the SDK tabs.
```
+8 −10 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+54−58
apichanged
agents-and-tools/tool-use/define-tools
-d @- <<'EOF'
{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"tools": [
+54 −58 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+8−12
apichanged
agents-and-tools/tool-use/code-execution-tool
<CodeGroup>
```bash cURL
# Downloading every generated file means looping over the file IDs in the tool
# result, which doesn't translate to a one-off shell command. Use one of the
# SDK examples instead.
+8 −12 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/build-a-tool-using-agent
±changed
+8−21
apichanged
agents-and-tools/tool-use/build-a-tool-using-agent
<CodeGroup>
```bash cURL
#!/bin/bash
# Ring 5: The Tool Runner SDK abstraction.
+8 −21 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/tool-use/browser-use-sdk
+new page
+1357−0
apinew page
agents-and-tools/tool-use/browser-use-sdk
No line of the body moved in this read.
+1357 −0 lines
Recorded here 15 Oct 2026 20:07 UTC
api
agents-and-tools/agent-skills/quickstart
±changed
+11−13
apichanged
agents-and-tools/agent-skills/quickstart
-d @- <<'EOF'
{
"model": "claude-opus-5-5",
"max_tokens": 16000,
"container": {
+11 −13 lines
Recorded here 15 Oct 2026 20:07 UTC
api
about-claude/use-case-guides/ticket-routing
±changed
+1092−133
apichanged
about-claude/use-case-guides/ticket-routing
* A Claude API key and the Python SDK installed
* A Claude API key and the Claude SDK installed
```python
def classify_support_request(ticket_contents):
<CodeGroup exclude="shell">
+1092 −133 lines
Recorded here 15 Oct 2026 20:07 UTC
api
about-claude/use-case-guides/legal-summarization
±changed
+1107−138
apichanged
about-claude/use-case-guides/legal-summarization
```python
details_to_extract = [
<CodeGroup exclude="shell">
```python Python
details_to_extract = [
+1107 −138 lines
Recorded here 15 Oct 2026 20:07 UTC
api
about-claude/pricing
±changed
+2−2
apichanged
about-claude/pricing
[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode), in research preview, provides significantly faster output for Claude Opus 5.5, Claude Opus 5, and Clau
[Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) provides significantly faster output for Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 at premium
Fast mode is not available on Claude Opus 4.7 (requests with `speed: "fast"` return an error) or Claude Opus 4.6 (requests run at standard speed and are billed at standard rates).
Fast mode is not available on Claude Opus 4.7 (requests with `speed: "fast"` return an error) or Claude Opus 4.6. See [Fast mode](https://platform.claude.com/docs/en/build-with-cla
+2 −2 lines
Recorded here 15 Oct 2026 20:07 UTC
api
about-claude/models/choosing-a-model
±changed
+1−1
apichanged
about-claude/models/choosing-a-model
* **Speed:** How quickly does the model need to respond in your application? Claude Opus 5.5, Claude Opus 5, and Claude Opus 4.8 support [fast mode](https://platform.claude.com/doc
* **Speed:** How quickly does the model need to respond in your application? [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) delivers up to 2.5x higher
+1 −1 lines
Recorded here 15 Oct 2026 20:07 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 15 Oct 2026 20:07 UTC
claude-code
changelog
±changed
+65−0
claude-codechanged
changelog
<Update label="2.1.301" description="October 15, 2026">
**Added**
* Added `CLAUDE_CODE_RETRY_WATCHDOG_MAX_USAGE_LIMIT_WAIT_MS` so unattended retry mode (`CLAUDE_CODE_RETRY_WATCHDOG`) ends a request at a usage limit that resets too far away inst
+65 −0 lines
Upstream edited 15 Oct 2026 19:53 UTC Recorded here 15 Oct 2026 20:07 UTC
claude-code
vs-code
±changed
+40−0
claude-codechanged
vs-code
### LaTeX math in responses
The chat panel shows LaTeX math in Claude's responses as typeset formulas. Math rendering requires Claude Code v2.1.301 or later. In [terminal mode](#switch-to-terminal-mode), math
* **Display math**: a `$$ … $$` or `\[ … \]` block on a line or lines of its own, and a fenced code block with `math` as its language
+40 −0 lines
Upstream edited 15 Oct 2026 19:44 UTC Recorded here 15 Oct 2026 20:07 UTC
claude-code
model-config
±changed
+20−0
claude-codechanged
model-config
Either of these startup warnings means Claude Code doesn't recognize your session's model ID, so it can't tell the model's context window and assumes 200K tokens:
```text theme={null}
⚠ Model "my-gateway-opus" isn't recognized · context assumed to be 200k tokens · ...
Claude Code doesn't recognize the model "my-gateway-opus", so it assumes a context window of 200k tokens. Update Claude Code, or see https://code.claude.com/docs/en/model-config#co
+20 −0 lines
Upstream edited 15 Oct 2026 19:38 UTC Recorded here 15 Oct 2026 20:07 UTC
claude-code
errors
±changed
+78−8
claude-codechanged
errors
| `API Error: an image in the conversation could not be processed and was removed` | [Request errors](#image-was-too-large) |
| `Claude's response exceeded the ... output token maximum` | [Request errors](#response-exceeded-the-output-token-maximum) |
| `Couldn't tell whether --bg is a flag or text here, so nothing was started` | [Command-line errors](#couldnt-tell-whether-bg-is-a-flag-or-text) |
| `Managed settings contain invalid entries, including PreToolUse/PermissionRequest hooks that are NOT loaded; fix or remove each entry:` | [Configuration warnings](#managed-settin
| `Model "<model>" isn't recognized · context assumed to be 200k tokens` | [Correct the window for a gateway or custom model ID](/docs/en/model-config#correct-the-window-for-a-gate
+78 −8 lines
Upstream edited 15 Oct 2026 19:38 UTC Recorded here 15 Oct 2026 20:07 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 15 Oct 2026 19:37 UTC
claude-code
whats-new/2026-w33
±changed
+6−6
claude-codechanged
whats-new/2026-w33
Releases [v2.1.225 → v2.1.233](/docs/en/changelog#2-1-225)
Releases [v2.1.225 → v2.1.233](/docs/en/changelog.md#2-1-225)
[What to do when you hit a usage limit](/docs/en/errors#youve-hit-your-session-limit)
[What to do when you hit a usage limit](/docs/en/errors.md#youve-hit-your-session-limit)
[Turn fork mode on or off](/docs/en/sub-agents#turn-fork-mode-on-or-off)
+6 −6 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w32
±changed
+6−6
claude-codechanged
whats-new/2026-w32
Releases [v2.1.220 → v2.1.224](/docs/en/changelog#2-1-220)
Releases [v2.1.220 → v2.1.224](/docs/en/changelog.md#2-1-220)
[Message another session](/docs/en/cross-session-messaging#message-another-session)
[Message another session](/docs/en/cross-session-messaging.md#message-another-session)
[Self-hosted environments quickstart](/docs/en/self-hosted-environments-quickstart#set-up-an-environment-and-runner)
+6 −6 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w30
±changed
+7−7
claude-codechanged
whats-new/2026-w30
Releases [v2.1.214 → v2.1.219](/docs/en/changelog#2-1-214)
Releases [v2.1.214 → v2.1.219](/docs/en/changelog.md#2-1-214)
Claude Opus 5 is the new default Opus model in Claude Code. It's the default on Max, Team Premium, Enterprise pay-as-you-go, and the Anthropic API, and on Claude Platform on AWS, A
Claude Opus 5 is the new default Opus model in Claude Code. It's the default on Max, Team Premium, Enterprise pay-as-you-go, and the Anthropic API, and on Claude Platform on AWS, A
[Model configuration](/docs/en/model-config#available-models)
+7 −7 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
ultrareview
±changed
+10−10
claude-codechanged
ultrareview
Ultrareview is a deep code review that runs as a [cloud session](/docs/en/claude-code-on-the-web) on Anthropic's infrastructure. When you run `/code-review ultra`, Claude Code laun
Ultrareview is a deep code review that runs as a [cloud session](/docs/en/claude-code-on-the-web.md) on Anthropic's infrastructure. When you run `/code-review ultra`, Claude Code l
Ultrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/logi
Ultrareview requires authentication with a claude.ai account because it runs as a cloud session on Anthropic's infrastructure. If you are signed in with an API key only, run `/logi
For a branch review, Claude Code bundles the repository state and uploads it to a cloud sandbox under the rules for [uploading a local repository to a cloud session](/docs/en/claud
+10 −10 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
code-review-costs
±changed
+10−10
claude-codechanged
code-review-costs
[Code Review](/docs/en/code-review) has no flat per-review price. What you spend depends on the cost of each review and on how many reviews run:
[Code Review](/docs/en/code-review.md) has no flat per-review price. What you spend depends on the cost of each review and on how many reviews run:
* **Cost of each review**: scales with the [review level](/docs/en/code-review-setup#set-the-default-review-level), the size of the change, the complexity of the surrounding code,
* **Cost of each review**: scales with the [review level](/docs/en/code-review-setup.md#set-the-default-review-level), the size of the change, the complexity of the surrounding cod
A repository you add from the admin page starts at **After every push**, which runs the most reviews. Each repository's [**Review runs** setting](/docs/en/code-review-setup#set-whe
+10 −10 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
analytics
±changed
+7−7
claude-codechanged
analytics
Code Review has its own dashboard. For review activity and spend, see [View usage](/docs/en/code-review-costs#view-usage).
Code Review has its own dashboard. For review activity and spend, see [View usage](/docs/en/code-review-costs.md#view-usage).
For per-user token counts and cost estimates, configure [OpenTelemetry export](/docs/en/monitoring-usage), or export the [spend report](https://support.claude.com/en/articles/12883
For per-user token counts and cost estimates, configure [OpenTelemetry export](/docs/en/monitoring-usage.md), or export the [spend report](https://support.claude.com/en/articles/12
> Contribution metrics are not available for organizations with [Zero Data Retention](/docs/en/zero-data-retention) enabled. The analytics dashboard will show usage metrics only.
+7 −7 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
agent-sdk/file-checkpointing
±changed
+10−10
claude-codechanged
agent-sdk/file-checkpointing
File checkpointing tracks file modifications made through the [Write](/docs/en/tools-reference#write-tool-behavior), [Edit](/docs/en/tools-reference#edit-tool-behavior), and [Noteb
File checkpointing tracks file modifications made through the [Write](/docs/en/tools-reference.md#write-tool-behavior), [Edit](/docs/en/tools-reference.md#edit-tool-behavior), and
> Only changes made through the Write, Edit, and NotebookEdit tools are tracked. Changes made through Bash commands (like `echo > file.txt` or `sed -i`) are not captured by the che
> Only changes made through the Write, Edit, and NotebookEdit tools are tracked. Changes made through Bash commands (like `echo > file.txt` or `sed -i`) are not captured by the che
The lead example under [Implement checkpointing](#implement-checkpointing) also sets the permission mode to `acceptEdits`, which approves the agent's file edits without a prompt. F
+10 −10 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
whats-new/2026-w33
±changed
+28−58
claude-codechanged
whats-new/2026-w33
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-225">v2.1.225 → v2.1.233</a></span>
<span>3 features · August 10–14</span>
</div>
Releases [v2.1.225 → v2.1.233](/docs/en/changelog#2-1-225)
+28 −58 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w32
±changed
+36−70
claude-codechanged
whats-new/2026-w32
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-220">v2.1.220 → v2.1.224</a></span>
<span>3 features · August 3–7</span>
</div>
Releases [v2.1.220 → v2.1.224](/docs/en/changelog#2-1-220)
+36 −70 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
whats-new/2026-w30
±changed
+30−62
claude-codechanged
whats-new/2026-w30
<div className="digest-meta">
<span>Releases <a href="/docs/en/changelog#2-1-214">v2.1.214 → v2.1.219</a></span>
<span>3 features · July 20–24</span>
</div>
Releases [v2.1.214 → v2.1.219](/docs/en/changelog#2-1-214)
+30 −62 lines
Upstream edited 15 Oct 2026 19:23 UTC Recorded here 20 Oct 2026 18:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.