HomeDocs changes
Documentation changes
What the docs quietly changed.
Anthropic's published documentation, fetched on a schedule and diffed against the last copy. Every edit dated, including the ones that never made a release note.
Last poll read all 4 cleanly: Claude Code CLI, Claude Developer Platform, Claude Documentation, Model Context Protocol. A date here is when this site noticed, not when Anthropic edited.
Claude Developer Platform
820pages tracked
773 changed this week · last read 23 Oct 2026
Claude Code CLI
228pages tracked
147 changed this week · last read 23 Oct 2026
Claude Documentation
280pages tracked
77 changed this week · last read 23 Oct 2026
Model Context Protocol
357pages tracked
171 changed this week · last read 23 Oct 2026
100 on this page
ReadSourcePageWhatLines
19 Oct 2026
159 pages
+17026 −18959 lines
api
manage-claude/user-management
±changed
+1−0
apichanged
manage-claude/user-management
| [Plugins](https://platform.claude.com/docs/en/manage-claude/plugins-api)
+1 −0 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/plugins-api
±changed
+8−8
apichanged
manage-claude/plugins-api
| **Plugins**: list every plugin in the organization, upload a new one, look one up, choose the version members are served (roll back or promote), delete one | `GET /v1/org
| **Plugin versions**: list a plugin's version history, upload a new version, look one up, download a version's files | `GET /v1/org
| **Installation settings**: read who can use an organization-owned plugin, set it for the whole organization or for one group, remove either setting | `GET /v1/org
| **Shares**: read who a member has shared their own plugin with (read-only) | `GET /v1/org
| **Plugin marketplaces**: find a marketplace's ID, look one up, set the default installation setting for its plugins, check marketplace content before connecting it | `GET /v1/org
+8 −8 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/inference-hooks
±changed
+3−3
apichanged
manage-claude/inference-hooks
Because the hook runs on Anthropic's servers, after the request leaves the client and before the model runs, it applies to every governed request uniformly, with nothing to install
Because the hook runs on Anthropic's servers, after the request leaves the client and before the model runs, it applies to every governed request uniformly, across all Claude produ
One hook governs conversations across claude.ai, Cowork, Claude Code, and Claude Tag sessions in your Claude Enterprise organization, whether they run on the web, in the desktop or
One hook governs conversations across all Claude products in your Claude Enterprise organization, including, but not limited to, claude.ai, Cowork, Claude Code, Claude for Microsof
* **Smart reports (beta).** Anthropic makes model calls to build your organization's [smart reports](https://support.claude.com/en/articles/16893491-get-started-with-smart-reports)
+3 −3 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/data-residency
±changed
+1−2
apichanged
manage-claude/data-residency
--message '{role: user, content: "Summarize the key points of this document."}' \
--transform '{content.#(type=="text").text,usage.inference_geo}' --format yaml
--message '{role: user, content: "Summarize the key points of this document."}'
+1 −2 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-sessions
±changed
+6−10
apichanged
manage-claude/compliance-sessions
The endpoints on this page are available only to Claude Enterprise organizations. The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Micros
The endpoints on this page are available only to Claude Enterprise organizations. The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Micros
The endpoints on this page expose transcripts of the sessions your users run in Claude apps and agents (today: Cowork, Claude Code, Claude Science, Claude for Microsoft 365, Claude
The endpoints on this page expose transcripts of the sessions your users run in Claude apps and agents (today: Cowork, Claude Code, Claude Science, Claude for Microsoft 365, the Cl
| The Claude add-ins for Google Docs, Google Sheets, and Google Slides, running in those Google apps | Local session endpoints
+6 −10 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-org-data
±changed
+5−15
apichanged
manage-claude/compliance-org-data
org_uuid="91012d09-e48b-438e-a489-1bebfd8fa6f9"
"https://api.anthropic.com/v1/compliance/organizations/$org_uuid/users" \
"https://api.anthropic.com/v1/compliance/organizations/91012d09-e48b-438e-a489-1bebfd8fa6f9/users" \
org_uuid="91012d09-e48b-438e-a489-1bebfd8fa6f9"
+5 −15 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-integration-patterns
±changed
+2−3
apichanged
manage-claude/compliance-integration-patterns
first_id="activity_01XyDMpzjS89pFZXqSFUBDr6" # first_id from a previous response
# before_id is the first_id from a previous response
--data-urlencode "before_id=$first_id"
--data-urlencode "before_id=activity_01XyDMpzjS89pFZXqSFUBDr6"
+2 −3 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-faq
±changed
+2−2
apichanged
manage-claude/compliance-faq
Yes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Sc
Yes. Cowork sessions in Claude Desktop that run on users' machines, Claude Code sessions (in the terminal, in Claude Desktop, or in an IDE extension), sessions in the Claude Sc
The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Microsoft 365 sessions. Coverage of sessions in Claude Science, Claude in Chrome, and
The local and remote session endpoints are stable for Cowork, Claude Code, and Claude for Microsoft 365 sessions. Coverage of sessions in Claude Science, the Claude add-ins for
+2 −2 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-content-data
±changed
+4−12
apichanged
manage-claude/compliance-content-data
chat_id="claude_chat_01H5CWunD7RpVJ5bHa8RCkja"
"https://api.anthropic.com/v1/compliance/apps/chats/$chat_id/messages" \
"https://api.anthropic.com/v1/compliance/apps/chats/claude_chat_01H5CWunD7RpVJ5bHa8RCkja/messages" \
file_id="claude_file_01UaT9wBcDfGhJkLmNpQrSv7"
+4 −12 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-api
±changed
+2−2
apichanged
manage-claude/compliance-api
The Compliance API gives Claude Enterprise and Claude Console customers programmatic access to their organization's Activity Feed. For Claude Enterprise organizations, it also cove
The Compliance API gives Claude Enterprise and Claude Console customers programmatic access to their organization's Activity Feed. For Claude Enterprise organizations, it also cove
A Claude Enterprise tenant has one parent organization (the top-level container that centralizes identity) with linked organizations of two kinds: claude.ai organizations, where us
A Claude Enterprise tenant has one parent organization (the top-level container that centralizes identity) with linked organizations of two kinds: claude.ai organizations, where us
+2 −2 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/compliance-activity-feed
±changed
+5−5
apichanged
manage-claude/compliance-activity-feed
# Fetch the first page (newest activities first) and capture its trailing cursor.
last_id=$(curl --fail-with-body -sS \
# Fetch the first page (newest activities first).
curl --fail-with-body -sS \
--header "anthropic-version: 2023-06-01" | jq -er '.last_id')
+5 −5 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/admin-api-keys
±changed
+9−5
apichanged
manage-claude/admin-api-keys
An Admin API key authenticates every API in the **Admin** section of this guide: the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), [Analytics APIs](http
An Admin API key authenticates every API in the **Admin** section of this guide: the [Admin API](https://platform.claude.com/docs/en/manage-claude/admin-api), [Analytics APIs](http
| Your organization | Create the key in
| ----------------------------------------------------------- | --------------------------------------------------------------------------------------------------------------------
| **Claude Console** (Claude Platform, `platform.claude.com`) | [Admin keys](https://platform.claude.com/settings/admin-keys) page (`platform.claude.com/settings/admin-keys`) in th
+9 −5 lines
Recorded here 19 Oct 2026 19:37 UTC
api
manage-claude/admin-api
±changed
+20−22
apichanged
manage-claude/admin-api
<Tip>
**The Admin API is unavailable for individual accounts.** To collaborate with teammates and add members, set up your organization on the [Organization](https://platform.claude.co
</Tip>
<Check>
+20 −22 lines
Recorded here 19 Oct 2026 19:37 UTC
api
cli-sdks-libraries/cli/using
±changed
+1−8
apichanged
cli-sdks-libraries/cli/using
printf '%s\n' "$AGENT_ID"
```
```text Output wrap
+1 −8 lines
Recorded here 19 Oct 2026 19:37 UTC
api
cli-sdks-libraries/cli/scripting
±changed
+1−1
apichanged
cli-sdks-libraries/cli/scripting
--transform "{version,created_at}" --format jsonl
--format jsonl
+1 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
cli-sdks-libraries/cli/authentication
±changed
+1−1
apichanged
cli-sdks-libraries/cli/authentication
ant auth login --profile <profile-name>
ant auth login --profile work
+1 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
claude_api_primer
±changed
+8−71
apichanged
claude_api_primer
Claude 4.6 and later models and Claude Mythos Preview do not support assistant message prefill; requests to those models must end with a user message. The examples below use a mo
Claude 4.6 and later models and Claude Mythos Preview do not support assistant message prefill; requests to those models must end with a user message. The following examples use
IMAGE_URL="https://platform.claude.com/docs/images/vision-example.jpg"
curl -sSo vision-example.jpg "$IMAGE_URL"
+8 −71 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/working-with-messages
±changed
+5−9
apichanged
build-with-claude/working-with-messages
IMAGE_URL="https://platform.claude.com/docs/images/vision-example.jpg"
IMAGE_MEDIA_TYPE="image/jpeg"
IMAGE_BASE64=$(curl "$IMAGE_URL" | base64 | tr -d '\n')
IMAGE_BASE64=$(curl "https://platform.claude.com/docs/images/vision-example.jpg" | base64 | tr -d '\n')
"media_type": "$IMAGE_MEDIA_TYPE",
+5 −9 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/vision
±changed
+9−11
apichanged
build-with-claude/vision
FILE_ID=$(curl -sS -X POST https://api.anthropic.com/v1/files \
curl -sS -X POST https://api.anthropic.com/v1/files \
-F "[email protected]" | jq -r '.id')
# Then use the returned file_id in your message
+9 −11 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/token-counting
±changed
+3−6
apichanged
build-with-claude/token-counting
IMAGE_URL="https://platform.claude.com/docs/images/vision-example.jpg"
IMAGE_MEDIA_TYPE="image/jpeg"
IMAGE_BASE64=$(curl -s "$IMAGE_URL" | base64 | tr -d '\n')
IMAGE_BASE64=$(curl -s "https://platform.claude.com/docs/images/vision-example.jpg" | base64 | tr -d '\n')
"media_type": "$IMAGE_MEDIA_TYPE",
+3 −6 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/thinking-tool-workflows
±changed
+6−64
apichanged
build-with-claude/thinking-tool-workflows
ant messages create --transform content <<'YAML'
ant messages create <<'YAML'
<CodeGroup exclude="shell:cURL">
<CodeGroup exclude="shell:cURL, shell:CLI">
This workflow needs more logic than a single shell command. Use the Claude SDK to run it.
+6 −64 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/thinking
±changed
+2−4
apichanged
build-with-claude/thinking
--message '{role: user, content: "What is the greatest common divisor of 1071 and 462?"}' \
--transform content \
--format yaml
--message '{role: user, content: "What is the greatest common divisor of 1071 and 462?"}'
Running the example prints the summarized thinking, then the answer:
+2 −4 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/task-budgets
±changed
+2−2
apichanged
build-with-claude/task-budgets
--stream --format jsonl <<'YAML' | jq 'select(.type == "message_delta").usage'
--stream <<'YAML'
`task_budget` is a request-level setting. To change the budget partway through a task, for example to extend it when the user broadens the request, set a new `task_budget` in `outp
`task_budget` is a request-level setting. To change the budget partway through a task, for example to extend it when the user broadens the request, set a new `task_budget` in `outp
+2 −2 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/structured-outputs
±changed
+23−25
apichanged
build-with-claude/structured-outputs
ant messages create \
--transform 'content.#(type=="text").text|@fromstr' \
--format jsonl <<'YAML'
ant messages create <<'YAML'
To print only some properties of the JSON output, pass a [GJSON path](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/using#transform-output-with-gjson) to `--transf
+23 −25 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/streaming
±changed
+2−3
apichanged
build-with-claude/streaming
ant messages create --stream --format jsonl \
ant messages create --stream \
--message '{role: user, content: "Hello"}' \
| jq -rj 'select(.delta.type? == "text_delta") | .delta.text'
--message '{role: user, content: "Hello"}'
+2 −3 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/skills-guide
±changed
+47−272
apichanged
build-with-claude/skills-guide
<CodeGroup>
```bash cURL
# Step 1: Use a Skill to create a file
RESPONSE=$(curl https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
+47 −272 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/refusals-and-fallback
±changed
+1−22
apichanged
build-with-claude/refusals-and-fallback
}' |
jq -c '{
stop_reason,
model,
# A fallback_message entry in usage.iterations means a fallback model ran;
+1 −22 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/prompt-caching
±changed
+8−9
apichanged
build-with-claude/prompt-caching
ant messages create --transform usage <<'YAML'
ant messages create <<'YAML'
ant messages create --transform usage <<'YAML'
ant messages create <<'YAML'
ant messages create \
+8 −9 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/preserved-thinking
±changed
+25−224
apichanged
build-with-claude/preserved-thinking
<CodeGroup>
```bash cURL
# Counts the thinking blocks in a response and the blocks the API dropped
COUNTS='"thinking blocks: \([.content[] | select(.type == "thinking")] | length), " +
"dropped: \(.input_transformations | length)"'
+25 −224 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/pdf-support
±changed
+32−47
apichanged
build-with-claude/pdf-support
ant messages create --transform content --format yaml <<'YAML'
ant messages create <<'YAML'
--max-tokens 1024 \
--transform content \
--format yaml <<'YAML'
+32 −47 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/mid-conversation-system-messages
±changed
+4−6
apichanged
build-with-claude/mid-conversation-system-messages
ant beta:messages create --beta inline-tools-2026-09-15 \
--transform 'content.#(type=="text").text' --raw-output <<'YAML'
ant beta:messages create --beta inline-tools-2026-09-15 <<'YAML'
With the `inline-tools-2026-09-15` beta header, a `tool_addition` block can define a tool by value, carrying its full definition, instead of naming it by reference. This lets you i
With the `inline-tools-2026-09-15` beta header, a `tool_addition` block can define a tool by value, carrying its full definition, instead of naming it by reference. This lets you i
+4 −6 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/handling-stop-reasons
±changed
+27−69
apichanged
build-with-claude/handling-stop-reasons
}' | jq 'if .stop_reason == "end_turn" then (.content[] | select(.type == "text") | .text) else . end'
}'
--message '{role: user, content: "Hello!"}' \
--format json | jq 'if .stop_reason == "end_turn" then (.content[] | select(.type == "text") | .text) else . end'
--message '{role: user, content: "Hello!"}'
+27 −69 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/files
±changed
+4−11
apichanged
build-with-claude/files
FILE_ID=$(curl -X POST https://api.anthropic.com/v1/files \
curl -X POST https://api.anthropic.com/v1/files \
-F "file=@/path/to/document.pdf" | jq -r '.id')
echo "$FILE_ID"
-F "file=@/path/to/document.pdf"
+4 −11 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/fast-mode
±changed
+43−75
apichanged
build-with-claude/fast-mode
featureMetadata:
zdr:
eligibility: eligible
note: Excludes [Covered Models](https://platform.claude.com/docs/en/manage-claude/api-and-data-retention#model-specific-data-retention-requirements).
supportedModels:
+43 −75 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/fallback-credit
±changed
+8−62
apichanged
build-with-claude/fallback-credit
<CodeGroup>
```bash cURL
# Initial request (may be refused)
response=$(curl --fail-with-body -sS https://api.anthropic.com/v1/messages \
-H "x-api-key: $ANTHROPIC_API_KEY" \
+8 −62 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/effort
±changed
+3−6
apichanged
build-with-claude/effort
Set `output_config.effort` on the request. The following example runs one request at `medium` effort and prints the response text.
Set `output_config.effort` on the request. The following example runs one request at `medium` effort.
--message '{role: user, content: "Analyze the trade-offs between microservices and monolithic architectures"}' \
--transform 'content.#(type=="text").text' \
--raw-output
+3 −6 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/context-editing
±changed
+2−28
apichanged
build-with-claude/context-editing
ORIGINAL=$(ant beta:messages count-tokens \
--beta context-management-2025-06-27 \
--transform context_management.original_input_tokens \
--raw-output <<'YAML'
ant beta:messages count-tokens \
+2 −28 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/compaction-threshold
±changed
+26−194
apichanged
build-with-claude/compaction-threshold
<CodeGroup>
```bash cURL
# The response content, including the compaction block, must go back to the
# API as the assistant turn of the next request. Managing that message list
# doesn't translate well to a one-off shell command; see the CLI and SDK
+26 −194 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+11−5
apichanged
build-with-claude/claude-platform-on-aws
Upgrading to a newer Claude model? In Claude Code, run `/claude-api migrate` to apply model ID swaps and breaking parameter changes across your codebase. The skill detects which
Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in
Let Claude Code migrate your code for you
+11 −5 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/claude-on-vertex-ai
±changed
+15−19
apichanged
build-with-claude/claude-on-vertex-ai
Upgrading to a newer Claude model? In Claude Code, run `/claude-api migrate` to apply model ID swaps and breaking parameter changes across your codebase. The skill detects which
Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in
Let Claude Code migrate your code for you
+15 −19 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/claude-in-microsoft-foundry
±changed
+20−17
apichanged
build-with-claude/claude-in-microsoft-foundry
--message '{role: user, content: "Hello!"}' \
--transform content
--message '{role: user, content: "Hello!"}'
# Get Microsoft Entra ID token
ACCESS_TOKEN=$(az account get-access-token --resource https://ai.azure.com --query accessToken -o tsv)
+20 −17 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/claude-in-amazon-bedrock
±changed
+9−1
apichanged
build-with-claude/claude-in-amazon-bedrock
Upgrading to a newer Claude model? In Claude Code, run `/claude-api migrate` to apply model ID swaps and breaking parameter changes across your codebase. The skill detects which
Upgrading to a newer Claude model? The [Claude API skill](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/claude-api-skill#migrating-to-a-newer-claude-model) in
Let Claude Code migrate your code for you
+9 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/cache-diagnostics
±changed
+14−22
apichanged
build-with-claude/cache-diagnostics
response=$(curl -sS --fail-with-body https://api.anthropic.com/v1/messages \
curl -sS --fail-with-body https://api.anthropic.com/v1/messages \
}')
jq '{id, diagnostics}' <<< "$response"
message_id=$(jq -r '.id' <<< "$response")
+14 −22 lines
Recorded here 19 Oct 2026 19:37 UTC
api
build-with-claude/batch-processing
±changed
+8−28
apichanged
build-with-claude/batch-processing
#!/bin/sh
# ...
curl -s "https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID" \
curl "https://api.anthropic.com/v1/messages/batches/$MESSAGE_BATCH_ID" \
--header "anthropic-version: 2023-06-01" \
+8 −28 lines
Recorded here 19 Oct 2026 19:37 UTC
api
api/service-tiers
±changed
+1−1
apichanged
api/service-tiers
ant messages create --transform usage.service_tier --raw-output <<'YAML'
ant messages create <<'YAML'
+1 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
api/errors
±changed
+2−2
apichanged
api/errors
# Print the response headers (including request-id); discard the body
curl -sS -D - -o /dev/null https://api.anthropic.com/v1/messages \
# -i prints the response headers, including request-id, before the body
curl -sS -i https://api.anthropic.com/v1/messages \
+2 −2 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/tool-use/strict-tool-use
±changed
+1−1
apichanged
agents-and-tools/tool-use/strict-tool-use
ant messages create --transform content <<'YAML'
ant messages create <<'YAML'
+1 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/tool-use/overview
±changed
+9−107
apichanged
agents-and-tools/tool-use/overview
ant messages create --transform content --format yaml \
ant messages create \
<CodeGroup>
```bash cURL
# Claude replies with a tool_use block naming the tool and its arguments.
+9 −107 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/tool-use/fine-grained-tool-streaming
±changed
+2−3
apichanged
agents-and-tools/tool-use/fine-grained-tool-streaming
ant messages create --stream --format jsonl <<'YAML' |
ant messages create --stream <<'YAML'
jq -rj 'select(.delta.type == "input_json_delta") | .delta.partial_json'
Every tab turns on fine-grained streaming for the `make_file` tool. The SDK tabs print each input fragment the moment it arrives, then print the complete accumulated input once the
Each input fragment arrives the moment Claude writes it, and the fragments join into the full tool input, so the poem arrives piece by piece:
+2 −3 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+16−15
apichanged
agents-and-tools/tool-use/code-execution-tool
# First, upload a file and capture the file ID (using jq)
FILE_ID=$(curl --fail-with-body -sS https://api.anthropic.com/v1/files \
# First, upload a file
curl --fail-with-body -sS https://api.anthropic.com/v1/files \
-F "[email protected]" | jq -r '.id')
+16 −15 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/tool-use/build-a-tool-using-agent
±changed
+37−731
apichanged
agents-and-tools/tool-use/build-a-tool-using-agent
<CodeGroup>
```bash cURL
#!/bin/bash
# Ring 1: Single tool, single turn.
+37 −731 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/mcp-connector
±changed
+100−58
apichanged
agents-and-tools/mcp-connector
BODY='{
"model": "claude-opus-5-5",
"max_tokens": 1024,
"mcp_servers": [
{
+100 −58 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/agent-skills/quickstart
±changed
+2−6
apichanged
agents-and-tools/agent-skills/quickstart
output_path="${TMPDIR:-/tmp}/renewable_energy.pptx"
-o "$output_path"
echo "Presentation saved to $output_path"
-o "${TMPDIR:-/tmp}/renewable_energy.pptx"
output_path="${TMPDIR:-/tmp}/renewable_energy.pptx"
+2 −6 lines
Recorded here 19 Oct 2026 19:37 UTC
api
agents-and-tools/agent-skills/claude-api-skill
±changed
+1−1
apichanged
agents-and-tools/agent-skills/claude-api-skill
The Claude API skill can perform Claude model migrations across a code base. Invoke it directly with `/claude-api migrate`:
The Claude API skill can perform Claude model migrations across a code base. Invoke it directly with the `migrate` subcommand:
+1 −1 lines
Recorded here 19 Oct 2026 19:37 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+41−50
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
Setup takes little work. [Automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching) places breakpoints for you; otherwise, the [Cla
Setup takes little work. [Automatic caching](https://platform.claude.com/docs/en/build-with-claude/prompt-caching#automatic-caching) places breakpoints for you; otherwise, the [Cla
Let Claude Code add caching for you
+41 −50 lines
Recorded here 19 Oct 2026 19:37 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 19 Oct 2026 18:37 UTC
claude-code
terminal-config
±changed
+32−32
claude-codechanged
terminal-config
This page is about getting your terminal to send the right signals to Claude Code. To change which keys Claude Code itself responds to, see [keybindings](/docs/en/keybindings) inst
This page is about getting your terminal to send the right signals to Claude Code. To change which keys Claude Code itself responds to, see [keybindings](/docs/en/keybindings.md) i
In VS Code, Cursor, and Devin Desktop, `/terminal-setup` also updates two editor settings: it sets `terminal.integrated.gpuAcceleration` to `"off"` to prevent garbled text in the i
In VS Code, Cursor, and Devin Desktop, `/terminal-setup` also updates two editor settings: it sets `terminal.integrated.gpuAcceleration` to `"off"` to prevent garbled text in the i
* If Claude Code can't read or parse the keymap, can't back it up, or can't verify the merged result, it [leaves the file unchanged and prints the keybinding block to add yourself]
+32 −32 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
statusline
±changed
+23−23
claude-codechanged
statusline
The status line renders in its own row above the built-in footer badges and does not replace them. With a custom status line configured, Claude Code stops showing most of the foote
The status line renders in its own row above the built-in footer badges and does not replace them. With a custom status line configured, Claude Code stops showing most of the foote
Add a `statusLine` field to your user settings (`~/.claude/settings.json`, where `~` is your home directory) or [project settings](/docs/en/settings#where-settings-live). Set `type
Add a `statusLine` field to your user settings (`~/.claude/settings.json`, where `~` is your home directory) or [project settings](/docs/en/settings.md#where-settings-live). Set `t
| `workspace.git_worktree` | Git worktree name when the current directory is inside a linked worktree created with `git worktree add`. Absent in the main working tree. Populated fo
+23 −23 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
fast-mode
±changed
+18−18
claude-codechanged
fast-mode
* Use `/fast` to toggle on fast mode in the Claude Code CLI. The [VS Code extension](/docs/en/vs-code) offers a **Toggle fast mode** command when the selected model supports fast m
* Use `/fast` to toggle on fast mode in the Claude Code CLI. The [VS Code extension](/docs/en/vs-code.md) offers a **Toggle fast mode** command when the selected model supports fas
* Set `"fastMode": true` in your [user settings file](/docs/en/settings)
* Set `"fastMode": true` in your [user settings file](/docs/en/settings.md)
Outside a [cloud session](#use-fast-mode-in-cloud-sessions), in [non-interactive mode](/docs/en/headless) with the `-p` flag, `/fast` works only in a session launched with fast mod
+18 −18 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
amazon-bedrock
±changed
+26−26
claude-codechanged
amazon-bedrock
Run `claude`. At the login prompt, select **3rd-party platform**, then **Amazon Bedrock**. If you're already signed in and see the chat prompt instead, run `/setup-bedrock` to open
Run `claude`. At the login prompt, select **3rd-party platform**, then **Amazon Bedrock**. If you're already signed in and see the chat prompt instead, run `/setup-bedrock` to open
Choose how you authenticate to AWS: an AWS profile detected from your `~/.aws` directory, an Amazon Bedrock API key, an access key and secret, or credentials already in your enviro
Choose how you authenticate to AWS: an AWS profile detected from your `~/.aws` directory, an Amazon Bedrock API key, an access key and secret, or credentials already in your enviro
Claude Code supports automatic credential refresh for AWS SSO and corporate identity providers. Add these settings to your Claude Code settings file (see [Settings](/docs/en/settin
+26 −26 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
workflows
±changed
+32−34
claude-codechanged
workflows
<Note>
Dynamic workflows are available on all paid plans, with Anthropic API access, and on Amazon Bedrock, Google Cloud's Agent Platform, and Microsoft Foundry. On Pro, turn them on fr
</Note>
> [!NOTE]
>
+32 −34 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
terminal-config
±changed
+158−164
claude-codechanged
terminal-config
<Tabs>
<Tab title="Apple Terminal">
Open Settings → Profiles → Keyboard and check "Use Option as Meta Key".
If you accepted Claude Code's first-run terminal setup prompt, this is already done. That prompt runs `/terminal-setup` for you, which enables Option as Meta and turns off the
+158 −164 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
statusline
±changed
+794−826
claude-codechanged
statusline
<Frame>
<img src="https://mintcdn.com/claude-code/HDAmBwgbrZVk0pOt/images/statusline-multiline.png?fit=max&auto=format&n=HDAmBwgbrZVk0pOt&q=85&s=a9d0a2fe8e446d80b1abc46da3f93270" alt="A
</Frame>
 with a description of what you want configures all of this for you automatically.</Note>
+794 −826 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
server-managed-settings
±changed
+58−60
claude-codechanged
server-managed-settings
<Note>
Server-managed settings are available for [Claude for Teams](https://claude.com/pricing?utm_source=claude_code\&utm_medium=docs\&utm_content=server_settings_teams#team-&-enterpri
</Note>
> [!NOTE]
>
+58 −60 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
memory
±changed
+35−39
claude-codechanged
memory
| **Managed policy** | • macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md`<br />• Linux and WSL: `/etc/claude-code/CLAUDE.md`<br />• Windows: `C:\Program Files\ClaudeCode\
| **Managed policy** | • macOS: `/Library/Application Support/ClaudeCode/CLAUDE.md` • Linux and WSL: `/etc/claude-code/CLAUDE.md` • Windows: `C:\Program Files\ClaudeCode\CLAUDE.md`
<Tip>
Run `/init` to generate a starting CLAUDE.md automatically. Claude analyzes your codebase and creates a file with build commands, test instructions, and project conventions it di
+35 −39 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
fast-mode
±changed
+14−14
claude-codechanged
fast-mode
<Note>
Fast mode is in [research preview](#research-preview). The feature, pricing, and availability may change based on feedback.
</Note>
> [!NOTE]
>
+14 −14 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
auto-mode-config
±changed
+23−31
claude-codechanged
auto-mode-config
<Note>
This page is the configuration reference. Turning auto mode on and off is covered on the Permission modes page:
* **Switch to auto mode mid-session, or back out of it**: see [Switch permission modes](/docs/en/permission-modes#switch-permission-modes)
* **Start a session in auto mode**: see [Start in a different permission mode](/docs/en/permission-modes#start-in-a-different-mode)
+23 −31 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
amazon-bedrock
±changed
+27−94
claude-codechanged
amazon-bedrock
export const ContactSalesCard = ({surface}) => {
const utm = content => `utm_source=claude_code&utm_medium=docs&utm_content=${surface}_${content}`;
const iconArrowRight = (size = 13) => <svg width={size} height={size} viewBox="0 0 24 24" fill="none" stroke="currentColor" strokeWidth="2.5" strokeLinecap="round" strokeLinejoin
<line x1="5" y1="12" x2="19" y2="12" />
<polyline points="12 5 19 12 12 19" />
+27 −94 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
workflows
±changed
+0−4
claude-codechanged
workflows
<Note>
Before v2.1.210, the keyword started a workflow from any of these routes too, including a webhook payload or pull request comment relayed into the conversation.
</Note>
+0 −4 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
tools-reference
±changed
+10−15
claude-codechanged
tools-reference
| `EndConversation` | Ends the session, in rare cases of sustained abusive input or when you ask Claude to demonstrate the tool. Requires Claude Code v2.1.213 or later. See [EndCon
| `EndConversation` | Ends the session, in rare cases of sustained abusive input or when you ask Claude to demonstrate the tool. See [EndConversation tool behavior](#endconversatio
An `Edit(...)` allow rule also grants read access to the same path, so you don't need a matching `Read(...)` rule. A `Read(...)` deny rule also blocks the Edit and Write tools on t
An `Edit(...)` allow rule also grants read access to the same path, so you don't need a matching `Read(...)` rule. A `Read(...)` deny rule also blocks the Edit and Write tools on t
These checks must pass for an edit to apply. Before any of them, a path matched by a [`Read` deny rule](/docs/en/permissions#tool-specific-permission-rules) is refused, including c
+10 −15 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
terminal-config
±changed
+1−1
claude-codechanged
terminal-config
In [screen reader mode](/docs/en/accessibility), `/terminal-setup` leaves the bell setting unchanged so the terminal bell stays audible. Before v2.1.211, `/terminal-setup` turn
In [screen reader mode](/docs/en/accessibility), `/terminal-setup` leaves the bell setting unchanged so the terminal bell stays audible. If an earlier run turned the bell off,
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
sub-agents
±changed
+6−10
claude-codechanged
sub-agents
This working-directory check covers the whole repository containing the directory you launched Claude Code from. When your session runs in a linked [worktree](/docs/en/worktrees) o
This working-directory check covers the whole repository containing the directory you launched Claude Code from. When your session runs in a linked [worktree](/docs/en/worktrees) o
A per-invocation `model` parameter also applies when the subagent is [resumed or sent a follow-up message](#resume-subagents), so the subagent stays on that model. Before v2.1.211,
A per-invocation `model` parameter also applies when the subagent is [resumed or sent a follow-up message](#resume-subagents), so the subagent stays on that model.
When nothing in the `tools` list resolves to a tool, for example because every entry is misspelled or names a tool that isn't available to subagents, Claude Code usually refuses to
+6 −10 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
statusline
±changed
+2−2
claude-codechanged
statusline
| `cost.total_cost_usd` | Estimated session cost in USD, computed client-side at list price unless a [`modelPricing`](/docs/en/settings-reference#modelpricing) table is in effect.
| `cost.total_cost_usd` | Estimated session cost in USD, computed client-side at list price unless a [`modelPricing`](/docs/en/settings-reference#modelpricing) table is in effect.
| `effort` | string or number, optional | Reasoning effort set for the subagent in its [definition frontmatter](/docs/en/sub-agents#supported-frontmatter-fields) or on the individu
| `effort` | string or number, optional | Reasoning effort set for the subagent in its [definition frontmatter](/docs/en/sub-agents#supported-frontmatter-fields) or on the individu
+2 −2 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
settings-reference
±changed
+2−2
claude-codechanged
settings-reference
Map two-key INSERT-mode sequences to Escape in [vim editor mode](/docs/en/interactive-mode#vim-editor-mode). Each key is exactly two printable characters typed in sequence, and `"<
Map two-key INSERT-mode sequences to Escape in [vim editor mode](/docs/en/interactive-mode#vim-editor-mode). Each key is exactly two printable characters typed in sequence, and `"<
Has no effect unless `editorMode` is `"vim"`. See [Remap INSERT-mode key sequences](/docs/en/interactive-mode#remap-insert-mode-key-sequences). Requires Claude Code v2.1.208 or lat
Has no effect unless `editorMode` is `"vim"`. See [Remap INSERT-mode key sequences](/docs/en/interactive-mode#remap-insert-mode-key-sequences).
+2 −2 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
sessions
±changed
+1−1
claude-codechanged
sessions
* Default display name: interactive sessions you never name still get a default display name when they start. Requires Claude Code v2.1.196 or later. The default combines the worki
* Default display name: interactive sessions you never name still get a default display name when they start. The default combines the working directory's name with a two-character
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
server-managed-settings
±changed
+2−2
claude-codechanged
server-managed-settings
Claude Code withholds several categories of variables in the cached `env` block until the server confirms the payload for the session. This keeps a cached proxy, certificate author
Claude Code withholds several categories of variables in the cached `env` block until the server confirms the payload for the session. This keeps a cached proxy, certificate author
* **An interactive session that can't show the dialog**: Claude Code doesn't apply the delivered settings and keeps the last-approved settings. The dialog appears in the next sessi
* **An interactive session that can't show the dialog**: Claude Code doesn't apply the delivered settings and keeps the last-approved settings. The dialog appears in the next sessi
+2 −2 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
permissions
±changed
+4−4
claude-codechanged
permissions
A `Read` deny rule also blocks the [Edit and Write tools](/docs/en/errors#file-is-covered-by-a-read-deny-rule) on the same path, including creating a new file there. NotebookEdit i
Claude Code checks file permissions against `Edit(path)` and `Read(path)` rules only. If you write a path rule for `Write`, `NotebookEdit`, `Glob`, or the legacy `MultiEdit` tool i
A `Read` deny rule also blocks the [Edit and Write tools](/docs/en/errors#file-is-covered-by-a-read-deny-rule) on the same path, including creating a new file there. NotebookEdit i
+4 −4 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
permission-modes
±changed
+1−1
claude-codechanged
permission-modes
* Committing or pushing a change that would send secrets or sensitive data outside the repository when it runs, or widen what a deploy exposes. This covers a CI workflow or deploy
* Committing or pushing a change that would send secrets or sensitive data outside the repository when it runs, or widen what a deploy exposes. This covers a CI workflow or deploy
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
monitoring-usage
±changed
+19−19
claude-codechanged
monitoring-usage
| `CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH` | Content limit: the maximum length of content-bearing attributes such as model responses, tool content, system prompts, and raw API bodies,
| `CLAUDE_CODE_OTEL_CONTENT_MAX_LENGTH` | Content limit: the maximum length of content-bearing attributes such as model responses, tool content, system prompts, and raw API bodies,
For the `http/protobuf` and `http/json` protocols, Claude Code sends each export request with a `Content-Length` header. Before v2.1.212, Claude Code versions from v2.1.191 onward
For the `http/protobuf` and `http/json` protocols, Claude Code sends each export request with a `Content-Length` header.
A record emitted while an interaction is active carries the interaction span's IDs, even when Claude Code emits it outside the span's async context, such as in a permission prompt
+19 −19 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
memory
±changed
+2−2
claude-codechanged
memory
You can also run [`/import`](/docs/en/commands) to bring a supported coding agent's configuration into Claude Code, which appends a one-time copy of instruction files such as `AGEN
You can also run [`/import`](/docs/en/commands) to bring a supported coding agent's configuration into Claude Code, which appends a one-time copy of instruction files such as `AGEN
When Claude writes a memory file that begins with YAML frontmatter, Claude Code records the write time in a `modified` frontmatter field as an ISO 8601 timestamp. The timestamp sho
When Claude writes a memory file that begins with YAML frontmatter, Claude Code records the write time in a `modified` frontmatter field as an ISO 8601 timestamp. The timestamp sho
+2 −2 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
mcp
±changed
+4−4
claude-codechanged
mcp
A remote server whose configuration has an empty `url` shows as `not configured` in `/mcp`, in `claude mcp list`, and in the [`/plugin`](/docs/en/plugins/install) manager, and Clau
A remote server whose configuration has an empty `url` shows as `not configured` in `/mcp`, in `claude mcp list`, and in the [`/plugin`](/docs/en/plugins/install) manager, and Clau
If a refresh request fails, Claude Code keeps the server's previously discovered tools, prompts, and resources until a later refresh succeeds. Before v2.1.214, a transient error du
If a refresh request fails, Claude Code keeps the server's previously discovered tools, prompts, and resources until a later refresh succeeds.
An MCP tool call in the main conversation that is still running after two minutes moves to a background task instead of blocking the session. Claude receives the task ID immediatel
+4 −4 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
interactive-mode
±changed
+4−4
claude-codechanged
interactive-mode
The [`vimInsertModeRemaps`](/docs/en/settings-reference#viminsertmoderemaps) setting maps a two-key INSERT-mode sequence to Escape, so a mapping like `jj` returns you to NORMAL mod
The [`vimInsertModeRemaps`](/docs/en/settings-reference#viminsertmoderemaps) setting maps a two-key INSERT-mode sequence to Escape, so a mapping like `jj` returns you to NORMAL mod
| `s` | Substitute character: delete the character under the cursor and enter INSERT mode. Requires Claude Code v2.1.211 or later |
| `S` | Substitute line: clear the line and enter INSERT mode. Requires Claude Code v2.1.211 or later |
| `s` | Substitute character: delete the character under the cursor and enter INSERT mode |
+4 −4 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
hooks-guide
±changed
+1−1
claude-codechanged
hooks-guide
* `PreToolUse`: the tool call is denied; by default the turn ends and the deny `reason` appears in the chat as a warning line. Set `continueOnBlock: true` on the hook to instead
* `PreToolUse`: the tool call is denied; by default the turn ends and the deny `reason` appears in the chat as a warning line. Set `continueOnBlock: true` on the hook to instead
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
hooks
±changed
+6−8
claude-codechanged
hooks
In an `if` condition for a file tool, a single-segment directory pattern like `"Edit(src/**)"` matches only the `src` directory in the working directory and the files under it. To
In an `if` condition for a file tool, a single-segment directory pattern like `"Edit(src/**)"` matches only the `src` directory in the working directory and the files under it. To
Before v2.1.214, forked sessions reported source `"resume"`.
An [Agent SDK callback hook](/docs/en/agent-sdk/hooks) on `UserPromptSubmit` that reaches its timeout blocks the prompt with a message naming the hook and the timeout, because a ca
+6 −8 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
headless
±changed
+2−3
claude-codechanged
headless
If Claude Code can't read stdin, for example because the process that started it disconnected its end, Claude Code prints a warning to stderr and continues with the prompt from the
If Claude Code can't read stdin, for example because the process that started it disconnected its end, Claude Code prints a warning to stderr and continues with the prompt from the
If your consumer reads the stream slowly, Claude Code waits for the queued output to drain before exiting, scaling the wait with how much is still queued, capped at 30 seconds. Bef
If your consumer reads the stream slowly, Claude Code waits for the queued output to drain before exiting, scaling the wait with how much is still queued, capped at 30 seconds.
* **`--forward-subagent-text` and `CLAUDE_CODE_FORWARD_SUBAGENT_TEXT`**: v2.1.211 or later
+2 −3 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
fullscreen
±changed
+1−1
claude-codechanged
fullscreen
* **Click an option in a multi-select menu** to toggle it, and click the submit button to confirm your choices. Clicking a free-text row, such as the `Other` row in a multiple-choi
* **Click an option in a multi-select menu** to toggle it, and click the submit button to confirm your choices. Clicking a free-text row, such as the `Other` row in a multiple-choi
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
fast-mode
±changed
+1−1
claude-codechanged
fast-mode
Opus 5.5 is the fast mode default in Claude Code v2.1.280 and later. Before v2.1.280, fast mode defaulted to Opus 5 from v2.1.219, to Opus 4.8 on v2.1.154 through v2.1.218, and to
Opus 5.5 is the fast mode default in Claude Code v2.1.280 and later. Before v2.1.280, fast mode defaulted to Opus 5 from v2.1.219, and to Opus 4.8 on v2.1.154 through v2.1.218.
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
chrome
±changed
+3−3
claude-codechanged
chrome
Claude Code starts normally when Chrome isn't running. Before v2.1.211, startup could hang when Chrome integration was enabled but Chrome wasn't running.
Claude Code starts normally when Chrome isn't running.
Claude can attach files from your machine to upload fields on a page. Claude Code reads the file and sends its contents to the browser, so uploads work in both local and remote ses
Claude can attach files from your machine to upload fields on a page. Claude Code reads the file and sends its contents to the browser, so uploads work in both local and remote ses
Claude saves the image to disk and reports the file path. Before v2.1.211, the screenshot tool's `save_to_disk` option didn't write a file.
+3 −3 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
auto-mode-config
±changed
+2−2
claude-codechanged
auto-mode-config
To read one rule's full wording without piping through `jq`, pass `--label` with the start of the rule's label, such as `claude auto-mode defaults --label 'Git Destructive'`. Match
To read one rule's full wording without piping through `jq`, pass `--label` with the start of the rule's label, such as `claude auto-mode defaults --label 'Git Destructive'`. Match
To discard your customizations and return to the built-in defaults, run the reset subcommand. It requires Claude Code v2.1.212 or later and removes the `autoMode` section from your
To discard your customizations and return to the built-in defaults, run the reset subcommand, which removes the `autoMode` section from your user settings file:
+2 −2 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
artifacts
±changed
+1−1
claude-codechanged
artifacts
Run `/artifacts` in Claude Code to list the artifacts you own and the ones shared with you. The current session's artifacts come first, under **This session**. Requires Claude Code
Run `/artifacts` in Claude Code to list the artifacts you own and the ones shared with you. The current session's artifacts come first, under **This session**.
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
amazon-bedrock
±changed
+1−1
claude-codechanged
amazon-bedrock
Claude Code requests role credentials from the IAM Identity Center region named by the profile's `sso_region`, which doesn't need to match the region you run Amazon Bedrock in. In
Claude Code requests role credentials from the IAM Identity Center region named by the profile's `sso_region`, which doesn't need to match the region you run Amazon Bedrock in.
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-code
agent-view
±changed
+1−1
claude-codechanged
agent-view
Copying the session requires Claude Code v2.1.212 or later; on v2.1.161 through v2.1.211, `/fork` starts a [forked subagent](/docs/en/sub-agents#fork-the-current-conversation) inst
When [agent view is turned off](#turn-off-agent-view), `/fork` starts a [forked subagent](/docs/en/sub-agents#fork-the-current-conversation) instead of copying the session.
+1 −1 lines
Upstream edited 19 Oct 2026 18:23 UTC Recorded here 19 Oct 2026 18:37 UTC
claude-docs
third-party/claude-desktop/data-storage
±changed
+3−2
claude-docschanged
third-party/claude-desktop/data-storage
* In each project they use from Chat, add folders and file links again
* In each project they use from Chat, use **Choose a folder > Choose a different folder** to select the same folders again
* Add any keys, sign-ins, or settings that their plugins need
5. Have the user launch Claude Desktop, and confirm that their chats, Cowork tasks, Code sessions, and projects appear. If they don't, check that the managed configuration has the
5. Have the user launch Claude Desktop, sign in if the app asks, and confirm that their chats, Cowork tasks, Code sessions, and projects appear. If they don't, check that the manag
+3 −2 lines
Upstream edited 19 Oct 2026 18:19 UTC Recorded here 19 Oct 2026 18:37 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 19 Oct 2026 17:37 UTC
claude-code
corporate-launcher
±changed
+14−14
claude-codechanged
corporate-launcher
`CLAUDE_CODE_PROCESS_WRAPPER` starts every process Claude Code launches from its own binary through your launcher: the [background service](/docs/en/agent-view#the-supervisor-proce
`CLAUDE_CODE_PROCESS_WRAPPER` starts every process Claude Code launches from its own binary through your launcher: the [background service](/docs/en/agent-view.md#the-supervisor-pr
* The session processes that [Remote Control](/docs/en/remote-control) starts. Requires Claude Code v2.1.210 or later.
* The split-pane teammate sessions that [agent teams](/docs/en/agent-teams) start in tmux or iTerm2. Teammate panes are interactive rather than background processes, but Claude Cod
* The session processes that [Remote Control](/docs/en/remote-control.md) starts. Requires Claude Code v2.1.210 or later.
+14 −14 lines
Upstream edited 19 Oct 2026 17:33 UTC Recorded here 22 Oct 2026 18:07 UTC
claude-code
corporate-launcher
±changed
+46−48
claude-codechanged
corporate-launcher
<Note>
`CLAUDE_CODE_PROCESS_WRAPPER` requires Claude Code v2.1.208 or later. Earlier versions ignore the variable and start every process unwrapped. The equivalent [`processWrapper` set
After deploying either form, use the [Verify step](#set-up-the-launcher) to confirm the running version applies it.
</Note>
+46 −48 lines
Upstream edited 19 Oct 2026 17:33 UTC Recorded here 20 Oct 2026 18:37 UTC
claude-code
corporate-launcher
±changed
+24−4
claude-codechanged
corporate-launcher
* **Don't reorder, absorb, or prepend arguments.** The first argument is the Claude Code binary and everything after it is its argv.
* **Don't reorder, absorb, or add to Claude Code's arguments.** Remove the launcher's [own arguments](#pass-arguments-to-the-launcher), which come first, and pass the rest to `exec
* **Reach `exec` within about three seconds each time the launcher runs.** A cold background dispatch runs the launcher twice in series before the first byte of output, so do slow
* **Reach `exec` within about three seconds each time the launcher runs.** A background session can run the launcher three times in series before its first output. Do slow work suc
* **Don't write to the terminal before Claude Code starts.** Anything printed before the `exec` is reported as the crash cause if the session dies before initializing.
+24 −4 lines
Upstream edited 19 Oct 2026 17:33 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
troubleshooting
±changed
+1−0
claude-codechanged
troubleshooting
| After you update Claude Code or the Agent SDK, tool calls are denied in `claude -p` or SDK runs that don't pass `--permission-mode`, `permissionMode`, or `permission_mode` | [Too
+1 −0 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
permission-modes
±changed
+102−7
claude-codechanged
permission-modes
| `claude -p` or the [Agent SDK](/docs/en/agent-sdk/permissions#permission-modes) | `default` in sessions that [fetch feature flags](/docs/en/env-vars#features-that-need-feature-fl
| `claude -p` or the [Agent SDK](/docs/en/agent-sdk/permissions#permission-modes) | `default` |
In your [first session after an install or upgrade](/docs/en/env-vars#first-session-after-an-install-or-upgrade), Claude Code can choose the starting permission mode before its fea
+102 −7 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
claude-code
model-config
±changed
+2−1
claude-codechanged
model-config
* **`CLAUDE_CODE_AUTO_MODE_MODEL`**: Claude Code ignores the variable and picks the model for its [auto mode classifier requests](/docs/en/permission-modes#default-classifier-model
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: the classifier's Claude Sonnet 5 default applies only when the allowlist permits Sonnet 5.
* **[Auto mode classifier](/docs/en/permission-modes#eliminate-prompts-with-auto-mode)**: when the allowlist excludes the [default classifier model](/docs/en/permission-modes#defau
+2 −1 lines
Upstream edited 19 Oct 2026 17:22 UTC Recorded here 19 Oct 2026 17:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.