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
808pages tracked
587 changed this week · last read 22 Oct 2026
Claude Code CLI
228pages tracked
146 changed this week · last read 22 Oct 2026
Claude Documentation
278pages tracked
74 changed this week · last read 22 Oct 2026
Model Context Protocol
357pages tracked
163 changed this week · last read 21 Oct 2026
100 on this page
ReadSourcePageWhatLines
20 Aug 2026
330 pages
+38938 −8139 lines
api
api/beta
±changed
+7632−1583
apichanged
api/beta
No line of the body moved in this read.
+7632 −1583 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+3−3
apichanged
agents-and-tools/tool-use/web-fetch-tool
fmt.Println(response)
fmt.Println(response.RawJSON())
fmt.Println(response)
fmt.Println(response.RawJSON())
fmt.Println(response)
+3 −3 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/troubleshooting-tool-use
±changed
+6−6
apichanged
agents-and-tools/tool-use/troubleshooting-tool-use
| Error | Cause
| ------------------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------
| `tool_use ids were found without tool_result blocks immediately after` | Missing `tool_result` for some `tool_use` ids, or `tool_result` is not the first content bl
| `was found without a corresponding <name>_tool_result block` | The previous assistant turn has a `server_tool_use` block with no result block (most often,
| `Input schema is not compatible with strict mode: string patterns are not supported` | Using `pattern` with `strict: true`
+6 −6 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/tool-search-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/tool-search-tool
fmt.Println(response)
fmt.Println(response.RawJSON())
+1 −1 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/strict-tool-use
±changed
+2−2
apichanged
agents-and-tools/tool-use/strict-tool-use
fmt.Println(response)
fmt.Println(response.RawJSON())
fmt.Println(response)
fmt.Println(response.RawJSON())
+2 −2 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+5−5
apichanged
agents-and-tools/tool-use/server-tools
}' | jq '{stop_reason, content}'
}'
ant messages create --format json <<'YAML' | jq '{stop_reason, content}'
ant messages create <<'YAML'
}' | jq '{stop_reason, content}'
+5 −5 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/programmatic-tool-calling
±changed
+3−3
apichanged
agents-and-tools/tool-use/programmatic-tool-calling
fmt.Println(response)
fmt.Println(response.RawJSON())
Container: anthropic.MessageNewParamsContainerUnion{
Container: anthropic.MessageCreateParamsContainerUnion{
fmt.Println(response)
+3 −3 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/overview
±changed
+5−8
apichanged
agents-and-tools/tool-use/overview
Tool use lets Claude call functions that you define or that Anthropic provides. Claude determines when to call a tool based on the user's request and the tool's description. It the
Tool use (also called function calling) lets Claude call functions that you define or that Anthropic provides. Claude determines when to call a tool based on the user's request and
# Claude uses the result to answer the original question.
FOLLOWUP=$(curl -s https://api.anthropic.com/v1/messages \
curl -s https://api.anthropic.com/v1/messages \
+5 −8 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/define-tools
±changed
+2−2
apichanged
agents-and-tools/tool-use/define-tools
fmt.Println(response)
fmt.Println(response.RawJSON())
fmt.Println(response)
fmt.Println(response.RawJSON())
+2 −2 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+67−84
apichanged
agents-and-tools/tool-use/code-execution-tool
This workflow doesn't require a beta header: uploading and downloading files through the Files API and referencing them in `container_upload` blocks are all generally available.
This workflow doesn't require a beta header: uploading and downloading files through the Files API and referencing them in `container_upload` blocks are all generally available.
-H "anthropic-beta: files-api-2025-04-14" \
-H "anthropic-beta: files-api-2025-04-14" \
FILE_ID=$(ant beta:files upload \
+67 −84 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/mcp-connector
±changed
+8−8
apichanged
agents-and-tools/mcp-connector
implementation("com.anthropic:anthropic-java-mcp:2.53.0")
implementation("com.anthropic:anthropic-java-mcp:2.57.0")
<version>2.53.0</version>
<version>2.57.0</version>
uploaded = await client.beta.files.upload(
+8 −8 lines
Recorded here 20 Aug 2026 17:07 UTC
api
agents-and-tools/agent-skills/quickstart
±changed
+126−172
apichanged
agents-and-tools/agent-skills/quickstart
-H "anthropic-version: 2023-06-01" \
-H "anthropic-beta: skills-2025-10-02" |
jq -r '.data[] | "\(.id): \(.display_title)"'
-H "anthropic-version: 2023-06-01"
ant beta:skills list --source anthropic
+126 −172 lines
Recorded here 20 Aug 2026 17:07 UTC
api
about-claude/models/whats-new-sonnet-5
±changed
+1−1
apichanged
about-claude/models/whats-new-sonnet-5
Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused. Refusals
Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity topics may be refused. Refusals
+1 −1 lines
Recorded here 20 Aug 2026 17:07 UTC
api
about-claude/models/optimizing-for-cost-and-intelligence
±changed
+15−11
apichanged
about-claude/models/optimizing-for-cost-and-intelligence
> add prompt caching to this integration
> /claude-api add prompt caching to this integration
* **`max_tokens`** caps a single response, invisibly to the model, so lowering it does not make the model economize. The turns that needed the room are discarded and still billed.
* **`max_tokens`** caps a single response, invisibly to the model, so lowering it does not make the model economize. The turns that needed the room are discarded and still billed.
This pattern saves wall-clock time when workers can run in parallel: on the corpus benchmark[8](https://platform.claude.com/docs/en/about-claude/models/optimizing-for-cost-and-inte
+15 −11 lines
Recorded here 20 Aug 2026 17:07 UTC
api
about-claude/models/migration-guide
±changed
+4−4
apichanged
about-claude/models/migration-guide
8. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legitimate security work s
8. **Real-time cybersecurity safeguards:** Newly added in Claude Opus 4.7, requests that involve prohibited or high-risk topics may lead to refusals. For legitimate security work s
* If your product does legitimate security work, apply to the [Cyber Verification Program](https://claude.com/form/cyber-use-case) for access to lower restrictions on cyber content
* If your product does legitimate security work, apply to the [Cyber Verification Program](https://support.claude.com/en/articles/14604842-real-time-cyber-safeguards-on-claude-opus
6. **Cybersecurity safeguards:** Claude Sonnet 5 is the first Sonnet-tier model with real-time cybersecurity safeguards. Requests that involve prohibited or high-risk cybersecurity
+4 −4 lines
Recorded here 20 Aug 2026 17:07 UTC
claude-code
changelog
±changed
+5−0
claude-codechanged
changelog
<Update label="2.1.237" description="August 20, 2026">
* Fixed prompt caching for sessions using an LLM gateway or custom base URL
* Added a built-in "Concise" output style: Claude leads with results and skips preamble and narration, while doing the work just as thoroughly. Select it under Output style in /c
</Update>
+5 −0 lines
Recorded here 20 Aug 2026 02:37 UTC
claude-docs
government/desktop/import
±changed
+41−15
claude-docschanged
government/desktop/import
> Copy your conversations, projects, and files from Claude for Government Web into Cowork in Claude Desktop.
> Copy your conversations, projects, and files from Claude for Government Web into Claude Desktop.
The import copies your conversations, their attached files, and the projects you created, which arrive as [Cowork](/docs/cowork/overview) projects. It does not copy projects that o
The import copies your conversations, their attached files, and the projects you created, including each project's files and instructions. It does not copy projects that other peop
* **An account on the web app.** It must use the same work email address as your Claude for Government account in Claude Desktop. The import does not work with a personal claude.ai
+41 −15 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
sub-agents
±changed
+13−0
claude-codechanged
sub-agents
#### Subagent files Claude Code skips
Claude Code skips a file in a project, user, or managed `agents` directory, or in one under a directory you add with `--add-dir`, without reporting it in the session, when the fron
+13 −0 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
settings
±changed
+2−2
claude-codechanged
settings
| `availableModels` | Restrict which models users can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/
| `availableModels` | Restrict which models users can select for the main session, [subagents](/docs/en/sub-agents), [skills](/docs/en/skills), and the [advisor](/
| `enforceAvailableModels` | Extend the `availableModels` allowlist to the Default model. When `true` in managed settings and `availableModels` is a non-empty array, the
| `enforceAvailableModels` | Extend the `availableModels` allowlist to the Default model. When `true` in managed settings and `availableModels` is a non-empty array, a De
+2 −2 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
plugins-reference
±changed
+8−8
claude-codechanged
plugins-reference
| Issue | Cause | Solution
| :---------------------------------- | :------------------------------ | :---------------------------------------------------------------------------------------------------------
| Plugin not loading | Invalid `plugin.json` | Run `claude plugin validate ./my-plugin` or `/plugin validate ./my-plugin`, where `./my-plugin` is your pl
| Skills not appearing | Wrong directory structure | Ensure `skills/` or `commands/` is at the plugin root, not inside `.claude-plugin/`
| Hooks not firing | Script not executable | Run `chmod +x script.sh`
+8 −8 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
plugin-marketplaces
±changed
+38−11
claude-codechanged
plugin-marketplaces
* Ensure JSON syntax is valid using `claude plugin validate .` or `/plugin validate .` from the marketplace directory. To check skill, agent, and command frontmatter, run the comma
* Ensure JSON syntax is valid using `claude plugin validate .` or `/plugin validate .` from the marketplace directory. To check skill, agent, and command frontmatter, see [Validate
To validate an individual plugin's `plugin.json` and its skill, agent, command, and hook files, run the command against the plugin directory itself, for example `claude plugin vali
| Error | Cause | Solution
+38 −11 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
model-config
±changed
+43−17
claude-codechanged
model-config
| **`default`** | Special value that clears any model override and reverts to the recommended model for your account type, or to the [organization default model](#organization-d
| **`default`** | Special value that clears any model override and reverts to the [runtime default for your account](#default-model-setting). Not itself a model alias
5. **[Default for new sessions](#set-a-default-model-for-new-sessions)**: set `ANTHROPIC_DEFAULT_MODEL=<alias|name>`
A model you pick for the new launch with `--model` or `ANTHROPIC_MODEL` still takes precedence over the restored model. As of v2.1.195, so does an [`ANTHROPIC_DEFAULT_OPUS_MODEL`](
A model you pick for the new launch with `--model` or `ANTHROPIC_MODEL` still takes precedence over the restored model. As of v2.1.195, so does an [`ANTHROPIC_DEFAULT_OPUS_MODEL`](
+43 −17 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
keybindings
±changed
+1−1
claude-codechanged
keybindings
| `selection:clear` | (unbound) | Clear the active text selection |
| `selection:clear` | (unbound) | Clear the active text selection. Requires v2.1.234 or later |
+1 −1 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
fullscreen
±changed
+9−0
claude-codechanged
fullscreen
In the normal prompt view, what happens to an active selection depends on the key you press:
* **`Esc`**: Claude Code performs the key's usual action, such as interrupting the running response or dismissing an open dialog, and the selection stays highlighted.
* **`PgUp`, `PgDn`, `Ctrl+Home`, `Ctrl+End`, or `Shift`, `Alt` or `Option`, or `Cmd`, `Win`, or `Super` with an arrow, `Home`, or `End` key**: the selection stays.
* **Any other key, including plain arrow keys, `Enter`, and typed characters**: Claude Code clears the selection.
+9 −0 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
errors
±changed
+4−4
claude-codechanged
errors
* If the error persists after `/model`, a 1M model ID may be set elsewhere. See [There's an issue with the selected model](#theres-an-issue-with-the-selected-model) for the configu
* If the error persists after `/model`, a 1M model ID may be set elsewhere. See [Setting your model](/docs/en/model-config#setting-your-model) for the configuration locations to ch
* If the wrong model keeps coming back in the CLI, a stale ID is set somewhere. Check in [priority order](/docs/en/model-config#setting-your-model): the `--model` flag, the `ANTHRO
* If the wrong model keeps coming back in the CLI, a stale ID is set somewhere. Check the places you can set a model in [priority order](/docs/en/model-config#setting-your-model) a
* A model saved before v2.1.200 isn't repaired by this check. If a stale value keeps coming back, remove it from the locations listed under [There's an issue with the selected mode
+4 −4 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
env-vars
±changed
+2−1
claude-codechanged
env-vars
Some behaviors have both an environment variable and a dedicated settings key. If you set both, the environment variable takes precedence. For example, `ANTHROPIC_MODEL` overrides
Some behaviors have both an environment variable and a dedicated settings key. If you set both, the environment variable takes precedence, except for [`ANTHROPIC_DEFAULT_MODEL`](/d
| `ANTHROPIC_DEFAULT_MODEL` | Model that new sessions start on by default. Requires Claude Code v2.1.236 or later. See [Set a default model for new se
+2 −1 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
agent-sdk/typescript
±changed
+39−9
claude-codechanged
agent-sdk/typescript
effort?: "low" | "medium" | "high" | "xhigh" | "max" | null;
* `effort`: the [effort level](/docs/en/model-config#adjust-effort-level) Claude Code sends on the session's next request, or `null` when it sends none. Claude Code sets the field
fromMode?: "bypass" | "prompting";
* `fromMode`: the sending session's permission class, `bypass` or `prompting`, declared by a host that relays a peer message between your sessions, such as the [desktop app](/docs/
+39 −9 lines
Recorded here 20 Aug 2026 01:37 UTC
claude-code
settings
±changed
+1−1
claude-codechanged
settings
| `env` | Environment variables applied to every session and to subprocesses Claude Code spawns from it. Set a variable to `""` to override a shell exp
| `env` | Environment variables Claude Code sets in every session and passes to the processes it starts, such as Bash commands and hooks. To override a
+1 −1 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
sessions
±changed
+27−6
claude-codechanged
sessions
| To | Set | Where |
| ------------------------------------------- | ------------------------------------------------------ | ------------------------- |
| Move storage off `~/.claude` | [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) | Environment variable |
| Change the 30-day retention | [`cleanupPeriodDays`](/docs/en/settings#available-settings) | `settings.json` |
| Suppress transcript writes in all modes | [`CLAUDE_CODE_SKIP_PROMPT_HISTORY`](/docs/en/env-vars) | Environment variable |
+27 −6 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
memory
±changed
+2−0
claude-codechanged
memory
If you set [`CLAUDE_CODE_PROJECT_DIR_NAME`](/docs/en/sessions#name-the-project-directory-yourself) beside `CLAUDE_CONFIG_DIR`, Claude Code uses that name as the `<project>` directo
+2 −0 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
env-vars
±changed
+1−0
claude-codechanged
env-vars
| `CLAUDE_CODE_PROJECT_DIR_NAME` | Set together with `CLAUDE_CONFIG_DIR` to choose the `projects/` directory name Claude Code stores that session's transcr
+1 −0 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
agent-sdk/sessions
±changed
+5−1
claude-codechanged
agent-sdk/sessions
Claude Code stores sessions under `~/.claude/projects/<encoded-cwd>/*.jsonl`. If you set the `CLAUDE_CONFIG_DIR` environment variable, look under `$CLAUDE_CONFIG_DIR/projects/` i
Claude Code stores sessions under `~/.claude/projects/<encoded-cwd>/*.jsonl`. If you set the `CLAUDE_CONFIG_DIR` environment variable, look under `$CLAUDE_CONFIG_DIR/projects/` i
To find your session's directory, replace every non-alphanumeric character in the absolute working directory with `-`: `/Users/me/proj` becomes `-Users-me-proj`. For a working di
+5 −1 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
agent-sdk/session-storage
±changed
+5−1
claude-codechanged
agent-sdk/session-storage
`SessionKey` addresses one transcript. `projectKey` is a stable, filesystem-safe encoding of the working directory, `sessionId` is the session UUID, and `subpath` is set when the e
`SessionKey` addresses one transcript. `projectKey` is a stable, filesystem-safe encoding of the working directory, `sessionId` is the session UUID, and `subpath` is set when the e
Because `projectKey` encodes the working directory, resume or continue from the store from a working directory matching the original run's. In TypeScript, if you set [`CLAUDE_CODE_
+5 −1 lines
Recorded here 20 Aug 2026 00:37 UTC
claude-code
agent-sdk/hosting
±changed
+2−2
claude-codechanged
agent-sdk/hosting
* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config.
* Point `CLAUDE_CONFIG_DIR` at a per-tenant directory so tenants do not share the `~/.claude.json` global config. When each config directory serves one working directory, you can a
The example below applies the four SDK-level options together. Construct `tenantDir` and `configDir` so each tenant gets a path no other tenant can read. In TypeScript, `env` repla
The example below applies the settings, auto memory, config directory, and working directory options together. Construct `tenantDir` and `configDir` so each tenant gets a path no o
+2 −2 lines
Recorded here 20 Aug 2026 00:37 UTC
19 Aug 2026
76 pages
+1553 −541 lines
claude-code
changelog
±changed
+36−0
claude-codechanged
changelog
<Update label="2.1.236" description="August 19, 2026">
* Added `ANTHROPIC_DEFAULT_MODEL` environment variable: sets the model new sessions start on, while a `/model` pick still overrides it and persists across restarts (unlike `ANTHR
* Added `notify_when_idle` to cross-session `SendMessage`: ask another Claude Code session on this machine to send one notice when it next goes idle — opt-in, one-shot, no pollin
* Sandbox: on macOS, wildcard read-deny rules (e.g. `**/.env`) now take precedence inside allowed read regions, cover matched directories' contents, and can't be bypassed by rena
+36 −0 lines
Recorded here 19 Aug 2026 23:07 UTC
api
release-notes/overview
±changed
+8−0
apichanged
release-notes/overview
- The [Files API](https://platform.claude.com/docs/en/build-with-claude/files) is now generally available on the Claude API. Requests to the `/v1/files` endpoints, and Messages API
* [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) and the Skills API (`/v1/skills`) are now generally available on the Claude API. Reques
+8 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/tools
±changed
+439−9
apichanged
managed-agents/tools
The agent toolset includes the following tools. All are enabled by default when you include the toolset in your agent configuration. Use the values in the Name column to reference
The agent toolset includes the following tools. All are enabled by default when you include the toolset in your agent configuration. Each entry in the `configs` array is identified
Config entries for `web_search` and `web_fetch` also accept domain filters and other web settings; see [Restrict web search and web fetch domains](https://platform.claude.com/docs/
new() { Name = "web_fetch", Enabled = false },
+439 −9 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/skills
±changed
+1−1
apichanged
managed-agents/skills
When you call the Skills API directly with cURL, pass the `anthropic-beta: skills-2025-10-02` header explicitly. The CLI and SDKs send it automatically.
The Skills API doesn't require a beta header. The cURL example still sends `anthropic-beta: skills-2025-10-02`, and the CLI and SDK `beta` commands add it automatically; requests t
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/session-operations
±changed
+1−1
apichanged
managed-agents/session-operations
You can update a session's `agent.tools` and `agent.mcp_servers`, including permission policies, mid-session without creating a new agent version. Updates are session-local and do
You can update a session's `agent.tools` and `agent.mcp_servers`, including permission policies and per-tool web settings such as [domain filters](https://platform.claude.com/docs/
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/self-hosted-sandboxes-security
±changed
+3−0
apichanged
managed-agents/self-hosted-sandboxes-security
* **Per-session credentials.** Each work item your worker claims can carry a per-session `secret`, which the SDK worker uses in place of the environment service key. Access to [mem
* **Memory store contents.** [Memory stores](https://platform.claude.com/docs/en/managed-agents/memory) remain hosted by Anthropic, including their version history. When a session
* **Read-only memory stores.** A store attached with `read_only` access is protected from upload, not from local modification. The worker's `write` and `edit` tools refuse to write
+3 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/self-hosted-sandboxes
±changed
+440−39
apichanged
managed-agents/self-hosted-sandboxes
Tool execution stays on your host: the filesystem the agent reads and writes, the processes it spawns, and the network it can reach are all under your control. Tool inputs and outp
Tool execution stays on your host: the filesystem the agent reads and writes, the processes it spawns, and the network it can reach are all under your control. Tool inputs and outp
| | Cloud environment | Self-hosted sandbox |
| ----------------------------- | --------------------------- | ------------------- |
| Where tools run | Anthropic-managed sandboxes | Your infrastructure |
+440 −39 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/scheduled-deployments
±changed
+1−1
apichanged
managed-agents/scheduled-deployments
* Deployments require [agent configuration](https://platform.claude.com/docs/en/managed-agents/agent-setup) and [environment configuration](https://platform.claude.com/docs/en/mana
* Deployments require [agent configuration](https://platform.claude.com/docs/en/managed-agents/agent-setup) and [environment configuration](https://platform.claude.com/docs/en/mana
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/reference
±changed
+2−0
apichanged
managed-agents/reference
The CLI worker does not mount [memory stores](https://platform.claude.com/docs/en/managed-agents/memory): a session that attaches one still runs, but the agent finds nothing at the
+2 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/permission-policies
±changed
+10−12
apichanged
managed-agents/permission-policies
new()
new BetaManagedAgentsBashToolConfigParams
Name = "bash",
Configs: []anthropic.BetaManagedAgentsAgentToolConfigParams{{
Name: anthropic.BetaManagedAgentsAgentToolConfigParamsNameBash,
+10 −12 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/overview
±changed
+1−1
apichanged
managed-agents/overview
* **Web search and fetch:** Search the web and retrieve content from URLs
* **Web search and fetch:** Search the web and retrieve content from URLs, optionally restricted to an allowlist or blocklist of domains
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/migration
±changed
+1−0
apichanged
managed-agents/migration
* **Web search and web fetch settings:** Same `allowed_domains`, `blocked_domains`, `max_content_tokens`, and `user_location` fields, now set once on the `web_search` and `web_fetc
+1 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/memory
±changed
+8−2
apichanged
managed-agents/memory
A **memory store** is a workspace-scoped collection of text documents optimized for Claude. When you attach a store to a session, it is mounted as a directory inside the session's
A **memory store** is a workspace-scoped collection of text documents optimized for Claude. When you attach a store to a session, it is mounted as a directory inside the session's
Memory stores are attached in the session's `resources[]` array when the [session is created](https://platform.claude.com/docs/en/managed-agents/sessions#creating-a-session). Unlik
Memory stores are attached in the session's `resources[]` array when the [session is created](https://platform.claude.com/docs/en/managed-agents/sessions#creating-a-session). Unlik
<Note>
+8 −2 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/mcp-connector
±changed
+1−1
apichanged
managed-agents/mcp-connector
The `mcp_toolset` entry supports the same `default_config` and `configs` shape as the built-in agent toolset, applied to the tools the MCP server exposes. The `name` in each `confi
The `mcp_toolset` entry supports a `default_config` object and a `configs` array, applied to the tools the MCP server exposes. Each `configs` entry accepts only `name`, `enabled`,
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/events-and-streaming
±changed
+15−5
apichanged
managed-agents/events-and-streaming
The Claude Console provides a visual timeline view of your agent sessions. Navigate to the Claude Managed Agents section in the Console to see:
* **Session list:** All sessions with their status, creation time, and agent
* **Tracing view:** A chronological view of events (content, timestamps, token usage) within a session. Tracing views are only accessible to Developers and Admins.
* **Tool execution:** Details of each tool call and its result
+15 −5 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/environments
±changed
+1−1
apichanged
managed-agents/environments
The `networking` field controls the sandbox's outbound network access. It does not affect the allowed domains for the `web_search` or `web_fetch` tools.
The `networking` field controls the sandbox's outbound network access. It does not affect the `web_search` or `web_fetch` tools, which run on Anthropic's servers; to restrict the s
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
managed-agents/define-outcomes
±changed
+1−1
apichanged
managed-agents/define-outcomes
Uploading through the Files API requires a beta header that grants Files API access. Your Managed Agents beta header grants this on its own, so you don't need to send `files-api-
Uploading through the Files API doesn't require a beta header. The cURL example sends the `managed-agents-2026-04-01` header it uses throughout this walkthrough, which the Files
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
manage-claude/workspaces
±changed
+2−2
apichanged
manage-claude/workspaces
* **Maximum 100 workspaces** per organization (archived workspaces don't count)
* **Maximum 100 workspaces** per organization by default (archived workspaces don't count); contact your account team if you need more
Yes, you can have a maximum of 100 workspaces per organization. Archived workspaces do not count toward this limit.
Yes. Each organization can have up to 100 workspaces by default, and archived workspaces don't count toward this limit. If you need more, contact your account team.
+2 −2 lines
Recorded here 19 Aug 2026 22:07 UTC
api
manage-claude/data-residency
±changed
+1−1
apichanged
manage-claude/data-residency
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) supports geographic pinning at the agent level: `inference_geo` on an [agent's model configur
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) supports geographic pinning at the agent level: `inference_geo` on an [agent's model configur
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
manage-claude/api-and-data-retention
±changed
+1−1
apichanged
manage-claude/api-and-data-retention
| [Files API](https://platform.claude.com/docs/en/build-with-claude/files) | `/v1/files` | <E
| [Files API](https://platform.claude.com/docs/en/build-with-claude/files) | `/v1/files` | <E
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/skills-guide
±changed
+22−155
apichanged
build-with-claude/skills-guide
| **Version format** | Date-based: `20251013` or `latest` | Epoch timestamp: `1759178010641129` or `latest` |
| **Version format** | Date-based: `20251013` or `latest` | Version ID: `skver_01AbCdEfGhIjKlMnOpQrStUv` or `latest` |
2. **Beta headers:**
+22 −155 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/pdf-support
±changed
+1−1
apichanged
build-with-claude/pdf-support
For PDFs you'll use repeatedly, or when you want to avoid encoding overhead, use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) (beta):
For PDFs you'll use repeatedly, or when you want to avoid encoding overhead, use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files). These examples send t
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/overview
±changed
+4−4
apichanged
build-with-claude/overview
| [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | Extend Claude's capabilities with Skills. Use pre-built
| [Agent Skills](https://platform.claude.com/docs/en/agents-and-tools/agent-skills/overview) | Extend Claude's capabilities with Skills. Use pre-built
| Feature | Description
| ------------------------------------------------------------------------ | -------------------------------------------------------------------------------------------------------
| [Files API](https://platform.claude.com/docs/en/build-with-claude/files) | Upload and manage files to use with Claude without re-uploading content with each request. Supports PDF
+4 −4 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/files
±changed
+30−11
apichanged
build-with-claude/files
- Status: Beta
- [Beta header](https://platform.claude.com/docs/en/api/beta-headers): `files-api-2025-04-14`
- Platforms: Claude API (beta), Claude Platform on AWS (beta), Microsoft Foundry (beta) [1]; not available on Amazon Bedrock, Google Cloud
- Platforms: Claude API, Claude Platform on AWS (beta), Microsoft Foundry (beta) [1]; not available on Amazon Bedrock, Google Cloud
+30 −11 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/claude-platform-on-aws
±changed
+2−1
apichanged
build-with-claude/claude-platform-on-aws
Session behavior on Claude Platform on AWS differs from first-party Claude Managed Agents in one way:
Session behavior on Claude Platform on AWS differs from first-party Claude Managed Agents in two ways:
* **[Memory stores on self-hosted environments](https://platform.claude.com/docs/en/managed-agents/self-hosted-sandboxes#use-memory-stores):** A session that runs on a self-hosted
+2 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
build-with-claude/citations
±changed
+2−2
apichanged
build-with-claude/citations
Files API document sources are in beta. These examples use the beta client path; see [Files API](https://platform.claude.com/docs/en/build-with-claude/files) for upload detai
These examples reference the uploaded file as a `document` source. They use the SDK `beta` client path and send the `anthropic-beta: files-api-2025-04-14` header, which the A
Files API document sources are in beta. These examples use the beta client path; see [Files API](https://platform.claude.com/docs/en/build-with-claude/files) for upload detai
These examples reference the uploaded file as a `document` source. They use the SDK `beta` client path and send the `anthropic-beta: files-api-2025-04-14` header, which the A
+2 −2 lines
Recorded here 19 Aug 2026 22:07 UTC
api
api/rate-limits
±changed
+4−0
apichanged
api/rate-limits
### Files API
[Files API](https://platform.claude.com/docs/en/build-with-claude/files) requests have their own per-organization limit, shared across upload, list, retrieve, download, and delete
+4 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
api/overview
±changed
+3−3
apichanged
api/overview
* **[Files API](https://platform.claude.com/docs/en/api/beta/files/upload)**: Upload and manage files for use across multiple API calls (`POST /v1/files`, `GET /v1/files`)
* **[Skills API](https://platform.claude.com/docs/en/api/skills/create-skill)**: Create and manage custom agent skills (`POST /v1/skills`, `GET /v1/skills`)
* **[Files API](https://platform.claude.com/docs/en/api/beta/files/upload)**: Upload and manage files for use across multiple API calls (`POST /v1/files`, `GET /v1/files`)
* **[Skills API](https://platform.claude.com/docs/en/api/skills/create-skill)**: Create and manage custom agent skills (`POST /v1/skills`, `GET /v1/skills`)
Some list endpoints use a different cursor scheme. The [Message Batches API](https://platform.claude.com/docs/en/build-with-claude/batch-processing), the [Files API](https://plat
+3 −3 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/web-search-tool
±changed
+6−0
apichanged
agents-and-tools/tool-use/web-search-tool
These organization-level settings in the Claude Console apply to Messages API requests only. [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) se
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_search` entry of the agent toolset; see [Restrict web search a
+6 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/web-fetch-tool
±changed
+4−0
apichanged
agents-and-tools/tool-use/web-fetch-tool
On [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview), set these fields on the `web_fetch` entry of the agent toolset, where each listed domain mu
On Claude Managed Agents, the `web_fetch` entry of the agent toolset also accepts `max_content_tokens`; see [Restrict web search and web fetch domains](https://platform.claude.com/
+4 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/server-tools
±changed
+4−0
apichanged
agents-and-tools/tool-use/server-tools
[Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) uses the same `allowed_domains` and `blocked_domains` fields on the `web_search` and `web_fetch
Organization-level web search and web fetch settings in the Claude Console apply to Messages API requests only; they do not apply to Managed Agents sessions, which use only the per
+4 −0 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/tool-use/code-execution-tool
±changed
+1−1
apichanged
agents-and-tools/tool-use/code-execution-tool
Using the Files API with code execution requires the Files API beta header: `"anthropic-beta": "files-api-2025-04-14"`
This workflow doesn't require a beta header: uploading and downloading files through the Files API and referencing them in `container_upload` blocks are all generally available.
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/quickstart
±changed
+3−2
apichanged
agents-and-tools/agent-skills/quickstart
* **Beta header:** `skills-2025-10-02`
The examples on this page use the `code_execution_20260521` tool version, which is generally available and needs only the `skills-2025-10-02` beta header. The Step 3 code parses
Skills are generally available on the Claude API and don't require a beta header. The examples on this page still send the `skills-2025-10-02` beta header and use the SDKs' `beta
The examples use the `code_execution_20260521` tool version, and the Step 3 code parses the result types that current tool versions return. Skills also work with older [code exec
+3 −2 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/overview
±changed
+1−5
apichanged
agents-and-tools/agent-skills/overview
**Prerequisites:** Using Skills through the API requires the [code execution tool](https://platform.claude.com/docs/en/agents-and-tools/tool-use/code-execution-tool), whose contain
* `skills-2025-10-02` - Enables Skills functionality
Add a second header, `files-api-2025-04-14`, when you use the [Files API](https://platform.claude.com/docs/en/build-with-claude/files) to upload input files to the container or dow
+1 −5 lines
Recorded here 19 Aug 2026 22:07 UTC
api
agents-and-tools/agent-skills/enterprise
±changed
+1−1
apichanged
agents-and-tools/agent-skills/enterprise
Note that API requests support a maximum of 8 Skills for each request (see [Using Skills with the API](https://platform.claude.com/docs/en/build-with-claude/skills-guide)). If a ro
Note that API requests support a maximum of 20 Skills for each request (see [Using Skills with the API](https://platform.claude.com/docs/en/build-with-claude/skills-guide)). If a r
+1 −1 lines
Recorded here 19 Aug 2026 22:07 UTC
api
resources/overview
±changed
+2−44
apichanged
resources/overview
title: Resources
title: Model cards
description: Model cards, learning resources, and documentation formats optimized for AI ingestion.
description: Model cards with detailed documentation for Claude models.
+2 −44 lines
Recorded here 19 Aug 2026 18:07 UTC
api
release-notes/overview
±changed
+4−0
apichanged
release-notes/overview
### August 19, 2026
* The [Admin API](https://platform.claude.com/docs/en/api/admin) user-management endpoints for **Claude Enterprise** (claude.ai) organizations (members, invites, groups, and custom
+4 −0 lines
Recorded here 19 Aug 2026 18:07 UTC
api
manage-claude/user-management
±changed
+11−11
apichanged
manage-claude/user-management
**The endpoints on this page are in beta for Claude Enterprise organizations.** The beta is enabled for all Claude Enterprise organizations. Group and custom-role requests must i
**The endpoints on this page are generally available for Claude Enterprise organizations.** The [beta header](https://platform.claude.com/docs/en/api/beta-headers) `anthropic-bet
| Endpoints
| ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------
| [Members](https://platform.claude.com/docs/en/manage-claude/user-management#members) and [invites](https://platform.claude.com/docs/en/manage-claude/user-management#invites)
+11 −11 lines
Recorded here 19 Aug 2026 18:07 UTC
api
manage-claude/admin-api-keys
±changed
+4−4
apichanged
manage-claude/admin-api-keys
| Your organization | Create the key in | Key prefix | W
| ----------------------------------------------------------- | ----------------------------------------------------------------------------------------- | -------------------- | -
| **Claude Console** (Claude Platform, `platform.claude.com`) | [Claude Console > Settings > Admin keys](https://platform.claude.com/settings/admin-keys) | `sk-ant-admin01-...` | O
| **Claude Enterprise** (`claude.ai`) | [claude.ai > Organization settings > API](https://claude.ai/admin-settings/api-access) | `sk-ant-api01-...` | T
| Your organization | Create the key in | Key prefix | W
+4 −4 lines
Recorded here 19 Aug 2026 18:07 UTC
api
manage-claude/admin-api
±changed
+1−1
apichanged
manage-claude/admin-api
**Claude Enterprise:** Claude Enterprise (claude.ai) organizations use the Admin API too, with a scoped API key created in claude.ai. Of the endpoints on this page, only members
**Claude Enterprise:** Claude Enterprise (claude.ai) organizations use the Admin API too, with a scoped API key created in claude.ai. Of the endpoints on this page, only members
+1 −1 lines
Recorded here 19 Aug 2026 18:07 UTC
api
claude_api_primer
±changed
+8−8
apichanged
claude_api_primer
<CodeGroup>
<CodeGroup exclude="shell:cURL, typescript, csharp, go, java, php, ruby">
<CodeGroup>
<CodeGroup exclude="shell:cURL, typescript, csharp, go, java, php, ruby">
<CodeGroup>
+8 −8 lines
Recorded here 19 Aug 2026 18:07 UTC
api
about-claude/additional-resources
+new page
+41−0
apinew page
about-claude/additional-resources
No line of the body moved in this read.
+41 −0 lines
Recorded here 19 Aug 2026 18:07 UTC
claude-code
tools-reference
±changed
+3−1
claude-codechanged
tools-reference
The tool is inactive until you install a [code intelligence plugin](/docs/en/discover-plugins#code-intelligence) for your language. The plugin bundles the language server configura
Claude Code keeps the tool inactive until you install a [code intelligence plugin](/docs/en/discover-plugins#code-intelligence) for your language. Claude Code takes the language se
Claude Code keeps the tool active for the rest of a session once it has had a language server available in that session. Claude Code returns an error result for each LSP call on a
+3 −1 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
sub-agents
±changed
+1−1
claude-codechanged
sub-agents
Background subagents run with a [smaller built-in tool set](#available-tools) than foreground subagents, except for conversation forks, and they surface every permission prompt in
Background subagents run with a [smaller built-in tool set](#available-tools) than foreground subagents, except for conversation forks, and they surface every permission prompt in
+1 −1 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
remote-control
±changed
+1−0
claude-codechanged
remote-control
* **Effort level**: when you set the [effort level](/docs/en/model-config#adjust-effort-level) from a connected device, with `/effort` or the device's effort control, Claude Code a
+1 −0 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
prompt-caching
±changed
+31−9
claude-codechanged
prompt-caching
[Plugins](/docs/en/plugins) bundle several component types, and the cost of a change depends on which components the plugin provides. Skills, commands, agents, hooks, LSP servers,
The exception is a plugin that provides [MCP servers](/docs/en/plugins-reference#mcp-servers). Enabling or disabling one follows the same rules as [connecting or disconnecting an M
Plugin changes apply when you run [`/reload-plugins`](/docs/en/discover-plugins#apply-plugin-changes-without-restarting) or start a new session. For a plugin with a `command` sourc
+31 −9 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
permissions
±changed
+2−0
claude-codechanged
permissions
Sometimes a permission prompt offers only a one-time approval, with no "don't ask again" option and no option to allow the action for the rest of the session. Claude Code offers th
+2 −0 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
permission-modes
±changed
+5−2
claude-codechanged
permission-modes
* **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, and Plan. You can't select Auto or Bypass permissions from the app. The dr
* **[Remote Control](/docs/en/remote-control) sessions** on your local machine: Manual, Accept edits, and Plan. You can't select Auto or Bypass permissions from the app.
* Except for Bypass permissions, the dropdown shows the permission mode the local session is in, including one set from the terminal. It updates when the permission mode chan
* Sessions hosted by the [desktop app](/docs/en/desktop) or the [VS Code extension](/docs/en/vs-code) report permission mode changes to claude.ai as they happen, the same as
* Before v2.1.202, sessions connected with `/remote-control` or `claude --remote-control` didn't report their permission mode at all, so claude.ai and the mobile app could sh
+5 −2 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
monitoring-usage
±changed
+1−1
claude-codechanged
monitoring-usage
* `"user_temporary"`: Emitted when the user chose "Yes" at a permission prompt for a one-time approval, or chose one of the "... during this session" options on a file edit or re
* `"user_temporary"`: Emitted when the user chose "Yes" at a permission prompt for a one-time approval, or chose an option that grants access for the rest of the session on a fil
+1 −1 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
model-config
±changed
+6−1
claude-codechanged
model-config
<Note>
A level you pick from the effort control on a phone or browser connected through [Remote Control](/docs/en/remote-control#what-connected-devices-see) applies to that session only
</Note>
* **From a connected device**: in a [Remote Control](/docs/en/remote-control#what-connected-devices-see) session, pick a level from the effort control on your phone or in your brow
+6 −1 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
github-actions
±changed
+1−1
claude-codechanged
github-actions
* **Automation mode**: when the workflow provides a `prompt` input, Claude runs without waiting for a mention, subject only to the [access checks](#who-can-trigger-runs). By defaul
* **Automation mode**: when the workflow provides a `prompt` input, Claude runs without waiting for a mention, subject only to the [checks on who can trigger runs](#who-can-trigger
+1 −1 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
channels-reference
±changed
+2−0
claude-codechanged
channels-reference
Clients on Claude Code v2.1.234 or later relay the marker `(value unserializable)` in place of an `input_preview` field value they can't serialize safely, such as a circular struct
+2 −0 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
agent-sdk/python
±changed
+10−7
claude-codechanged
agent-sdk/python
| Property | Type | Description |
| :------------------- | :----------------------------- | :------------------------ |
| `type` | `Literal["user", "assistant"]` | Message role |
| `uuid` | `str` | Unique message identifier |
| `session_id` | `str` | Session identifier |
+10 −7 lines
Recorded here 19 Aug 2026 16:37 UTC
claude-code
hooks-guide
±changed
+3−1
claude-codechanged
hooks-guide
To reformat a specific file however it changes, including when a `Bash` command rewrites it, use a [FileChanged](/docs/en/hooks#filechanged) hook instead.
Claude can also create or modify files by running shell commands. If your hook must see every file change, such as for compliance scanning or audit logging, add a [`Stop`](/docs/
Claude can also create or modify files by running shell commands. If your hook must see every file change, such as for compliance scanning or audit logging, add a [`Stop`](/docs/
+3 −1 lines
Recorded here 19 Aug 2026 16:07 UTC
claude-code
hooks
±changed
+42−1
claude-codechanged
hooks
To run a hook when a specific file changes on disk, whatever wrote it, use [FileChanged](#filechanged) instead of matching file-editing tools by name. Unlike PreToolUse, Claude Cod
Match more broadly when the tool name isn't the right filter:
+42 −1 lines
Recorded here 19 Aug 2026 16:07 UTC
claude-code
sandbox-environments
±changed
+2−2
claude-codechanged
sandbox-environments
Individual developers can opt into any approach above. What an organization can enforce, and with which tools, depends on the approach:
Individual developers can opt into any of the sandboxing approaches on this page. What an organization can enforce, and with which tools, depends on the approach:
These pages cover configuration and policy details for the approaches above.
These pages cover configuration and policy details for the sandboxing approaches on this page.
+2 −2 lines
Recorded here 19 Aug 2026 15:37 UTC
claude-code
permissions
±changed
+6−0
claude-codechanged
permissions
A redirect such as `ls > out.txt` adds a check on the target. See [Redirections](#redirections).
#### Redirections
+6 −0 lines
Recorded here 19 Aug 2026 15:37 UTC
claude-code
hooks
±changed
+1−1
claude-codechanged
hooks
To see how these pieces fit together, consider this `PreToolUse` hook that blocks destructive shell commands.
To see how the event, the matcher, and the handler fit together, consider this `PreToolUse` hook that blocks destructive shell commands.
+1 −1 lines
Recorded here 19 Aug 2026 15:37 UTC
claude-code
env-vars
±changed
+1−1
claude-codechanged
env-vars
You can also miss a feature in this list in your first session after you install Claude Code, or after you upgrade to a version that adds the feature, even with none of these varia
You can also miss a [flag-gated feature](#features-that-need-feature-flag-fetching) in your first session after you install Claude Code, or after you upgrade to a version that adds
+1 −1 lines
Recorded here 19 Aug 2026 15:37 UTC
claude-code
agent-sdk/modifying-system-prompts
±changed
+1−1
claude-codechanged
agent-sdk/modifying-system-prompts
These methods compose. A persistent output style or CLAUDE.md sets the long-lived behavior, and `append` layers session-specific instructions on top without touching the saved conf
The approaches compose. A persistent output style or CLAUDE.md sets the long-lived behavior, and `append` layers session-specific instructions on top without touching the saved con
+1 −1 lines
Recorded here 19 Aug 2026 15:37 UTC
claude-code
settings
±changed
+4−1
claude-codechanged
settings
* `git`: extracts hostname from the URL (supports both HTTPS and SSH formats)
* `git`: extracts the hostname from the marketplace's [git URL](https://git-scm.com/docs/git-clone#_git_urls), depending on the URL's form:
* A URL with a scheme, such as `https://` or `ssh://`: the hostname in the URL.
* An SSH address without a scheme, in git's `user@host:path` form, such as `[email protected]:tools/plugins.git`: the host between `@` and `:`, which is the host git connects t
* Any other form without a scheme: no host, so no `strictKnownMarketplaces` `hostPattern` entry matches it. For a `blockedMarketplaces` `hostPattern`, Claude Code takes a host fr
+4 −1 lines
Recorded here 19 Aug 2026 14:07 UTC
api
build-with-claude/prompt-caching
±changed
+0−120
apichanged
build-with-claude/prompt-caching
```typescript TypeScript
const client = new Anthropic();
const response = await client.beta.promptCaching.messages.create({
+0 −120 lines
Recorded here 19 Aug 2026 05:07 UTC
claude-docs
third-party/claude-desktop/telemetry
±changed
+37−23
claude-docschanged
third-party/claude-desktop/telemetry
| Host | Purpose
| --------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------
| `downloads.claude.ai` | VM workspace bundle and Claude CLI binary, fetched at session start. **Without this, Cowork sessions cannot start**, unless the app was installed with the
| Host | Purpose |
| --------------------- | ------------------------------------------------------------------- |
+37 −23 lines
Recorded here 19 Aug 2026 03:37 UTC
api
release-notes/overview
±changed
+4−0
apichanged
release-notes/overview
### August 18, 2026
* Workbench is now [**Playground**](https://platform.claude.com/playground) in the Claude Console. Playground supports every Messages API parameter and includes templates that demo
+4 −0 lines
Recorded here 19 Aug 2026 00:37 UTC
api
manage-claude/workspaces
±changed
+1−1
apichanged
manage-claude/workspaces
| Workspace User | Use the Anthropic Workbench only |
| Workspace User | Use Playground only |
+1 −1 lines
Recorded here 19 Aug 2026 00:37 UTC
api
manage-claude/usage-cost-api
±changed
+3−3
apichanged
manage-claude/usage-cost-api
### What happens with Anthropic Workbench usage?
API usage from the Workbench is not associated with an API key, so `api_key_id` will be `null` even when grouping by that dimension.
### What happens with Playground usage?
+3 −3 lines
Recorded here 19 Aug 2026 00:37 UTC
Nothing on this page matches that. Press Enter to search every page of the ledger.