An entry is only as true as the day it was written.
Flags move on the server after a release ships. Anthropic's own notes land days later and their documentation later still. Sometimes an entry turns out to be wrong and gets corrected by hand. All of that is recorded against the entry it happened to, and this is the whole of it in the order it happened.
Nothing here replaces an entry. Every line links to the page its release published, still saying what that release said, because a correction is added and dated rather than swapped in.
| When | Entry | What happened |
|---|---|---|
v2.1.286gcpAuthRefresh |
Documentation arrivedA small documentation edit on All settings touched a line naming gcpAuthRefresh after this was published.
the line in the docs| Read from the highest-priority source only | Reads the key only from the highest-priority source that carries a policy key, so a lower source's value is ignored even when the highest source sets none | [`apiKeyHelper`](#apikeyhelper), [`… |
|
v2.1.312/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Model configuration.
the line in the docsWhen Claude Code sends no effort level to a [supported model](#adjust-effort-level), the [API's default](https://platform.claude.com/docs/en/build-with-claude/effort) applies instead of Claude Code's. To have Claude Code send none, start `… |
|
v2.1.312/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Model configuration.
the line in the docsWhen Claude Code sends no effort level to a [supported model](#adjust-effort-level), the [API's default](https://platform.claude.com/docs/en/build-with-claude/effort) applies instead of Claude Code's. To have Claude Code send none, start `… |
|
v2.1.312/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Model configuration.
the line in the docsWhen Claude Code sends no effort level to a [supported model](#adjust-effort-level), the [API's default](https://platform.claude.com/docs/en/build-with-claude/effort) applies instead of Claude Code's. To have Claude Code send none, start `… |
|
v2.1.312/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Model configuration.
the line in the docsWhen Claude Code sends no effort level to a [supported model](#adjust-effort-level), the [API's default](https://platform.claude.com/docs/en/build-with-claude/effort) applies instead of Claude Code's. To have Claude Code send none, start `… |
|
v2.1.310deniedMcpServers |
Documentation arrivedAnthropic's documentation has since written up deniedMcpServers, on Agent SDK reference - TypeScript.
the line in the docs* `Blocked by enterprise policy (allowedMcpServers/deniedMcpServers)`: the server isn't in `added`. A [`deniedMcpServers`](https://code.claude.com/docs/en/managed-mcp#policy-based-control-with-allowlists-and-denylists) entry matches it, or… |
|
v2.1.310allowedMcpServers |
Documentation arrivedAnthropic's documentation has since written up allowedMcpServers, on Agent SDK reference - TypeScript.
the line in the docs* `Blocked by enterprise policy (allowedMcpServers/deniedMcpServers)`: the server isn't in `added`. A [`deniedMcpServers`](https://code.claude.com/docs/en/managed-mcp#policy-based-control-with-allowlists-and-denylists) entry matches it, or… |
|
v2.1.299nextFireAt |
Documentation arrivedAnthropic's documentation has since written up nextFireAt, on Agent SDK reference - TypeScript.
the line in the docsnextFireAt?: number; |
|
v2.1.311claude --cloud |
Documentation arrivedAnthropic's documentation has since written up claude --cloud, on Use Claude Code in the cloud.
the line in the docs`claude --cloud` and `claude --teleport` require sign-in with a claude.ai account. If you authenticate with an API key or a Console sign-in instead, or your stored account details are stale, you see a message such as: |
|
v2.1.312/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Use Claude Code in the cloud.
the line in the docs* ``Cloud sessions aren't available with this Console sign-in. They need a claude.ai sign-in. Run `claude auth login` (or /login in a local session), then try again.`` |
|
v2.1.312/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Use Claude Code in the cloud.
the line in the docs* ``Cloud sessions aren't available with this Console sign-in. They need a claude.ai sign-in. Run `claude auth login` (or /login in a local session), then try again.`` |
|
v2.1.311/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on Error reference.
the line in the docs* If your Claude Code version is earlier than v2.1.300, run [`claude update`](https://code.claude.com/docs/en/setup#update-claude-code) in your shell. Before v2.1.300, Claude Code didn't [retry the request without the rejected tool's param… |
|
v2.1.296updatedPermissions |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming updatedPermissions after this was published.
the line in the docsIf you return `PermissionResultAllow` with more than 4,096 items in `updated_permissions`, Claude Code treats the result as invalid and denies the tool call. Each [`PermissionUpdate`](#permissionupdate) counts as one item, and so does each… |
|
v2.1.296updatedPermissions |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming updatedPermissions after this was published.
the line in the docsIf you return `PermissionResultAllow` with more than 4,096 items in `updated_permissions`, Claude Code treats the result as invalid and denies the tool call. Each [`PermissionUpdate`](#permissionupdate) counts as one item, and so does each… |
|
v2.1.296updatedPermissions |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming updatedPermissions after this was published.
the line in the docsIf you return `PermissionResultAllow` with more than 4,096 items in `updated_permissions`, Claude Code treats the result as invalid and denies the tool call. Each [`PermissionUpdate`](#permissionupdate) counts as one item, and so does each… |
|
v2.1.295updatedPermissions |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming updatedPermissions after this was published.
the line in the docsIf you return `PermissionResultAllow` with more than 4,096 items in `updated_permissions`, Claude Code treats the result as invalid and denies the tool call. Each [`PermissionUpdate`](#permissionupdate) counts as one item, and so does each… |
|
v2.1.310availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Claude apps gateway configuration.
the line in the docsavailableModels: [restricted-claude-opus-4-8] |
|
v2.1.307forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsRestrict which kind of account people can log in with. Set `"claudeai"` to allow only claude.ai accounts, `"console"` to allow only Claude Console accounts, or `"gateway"` to send people to a [cloud gateway](https://code.claude.com/docs/en… |
|
v2.1.300forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsRestrict which kind of account people can log in with. Set `"claudeai"` to allow only claude.ai accounts, `"console"` to allow only Claude Console accounts, or `"gateway"` to send people to a [cloud gateway](https://code.claude.com/docs/en… |
|
v2.1.300forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsRestrict which kind of account people can log in with. Set `"claudeai"` to allow only claude.ai accounts, `"console"` to allow only Claude Console accounts, or `"gateway"` to send people to a [cloud gateway](https://code.claude.com/docs/en… |
|
v2.1.299forceLoginOrgUUID |
Documentation arrivedA small documentation edit on All settings touched a line naming forceLoginOrgUUID after this was published.
the line in the docsRestrict which kind of account people can log in with. Set `"claudeai"` to allow only claude.ai accounts, `"console"` to allow only Claude Console accounts, or `"gateway"` to send people to a [cloud gateway](https://code.claude.com/docs/en… |
|
v2.1.311apiKeyHelper |
Documentation arrivedAnthropic's documentation has since written up apiKeyHelper, on Authentication.
the line in the docs* **Environment and helper credentials**: Claude Code refuses sessions that authenticate with `ANTHROPIC_API_KEY`, `ANTHROPIC_AUTH_TOKEN`, or `apiKeyHelper`, even when managed settings supply them. Remove those credentials, then have devel… |
|
v2.1.310headersHelper |
Documentation arrivedAnthropic's documentation has since written up headersHelper, on Configuration reference.
the line in the docs> > A local (`stdio`) entry can repeat `command`, `args`, `env`, `envHelper` and `envHelperArgs`. A remote (`http` or `sse`) or web search entry can repeat `headersHelper` and `headersHelperArgs`; an entry that gives `headersHelper` here n… |
|
v2.1.311HTTPS_PROXY |
Documentation arrivedAnthropic's documentation has since written up HTTPS_PROXY, on Configuration reference.
the line in the docs> On macOS and Windows the Cowork workspace VM is handed a copy of the script when it starts and evaluates it for each request itself; there `myIpAddress()` returns the VM's internal address rather than the device's, so a script that choos… |
|
v2.1.310HTTPS_PROXY |
Documentation arrivedAnthropic's documentation has since written up HTTPS_PROXY, on Configuration reference.
the line in the docs> On macOS and Windows the Cowork workspace VM is handed a copy of the script when it starts and evaluates it for each request itself; there `myIpAddress()` returns the VM's internal address rather than the device's, so a script that choos… |
|
v2.1.311PreToolUse |
Documentation arrivedAnthropic's documentation has since written up PreToolUse, on Changelog.
the line in the docs* Changed a failed `PreToolUse` or `PermissionRequest` hook with `"shell": "powershell"` to block the call on PCs without Git for Windows unless it sets `args` or `"onFailure": "continue"`. If written for Bash: remove `shell`, add `"onFail… |
|
v2.1.293/run |
Documentation arrivedA small documentation edit on Command line settings touched a line naming /run after this was published.
the line in the docs| `claude-science sandbox approve` | Linux only, version 0.1.71 or later. Approve your own copy of bubblewrap or socat for the sandbox. `--bwrap <path>` and `--socat <path>` name the programs, `--yes` skips the confirmation and is required… |
|
v2.1.290/run |
Documentation arrivedA small documentation edit on Command line settings touched a line naming /run after this was published.
the line in the docs| `claude-science sandbox approve` | Linux only, version 0.1.71 or later. Approve your own copy of bubblewrap or socat for the sandbox. `--bwrap <path>` and `--socat <path>` name the programs, `--yes` skips the confirmation and is required… |
|
v2.1.286bwrap |
Documentation arrivedA small documentation edit on Command line settings touched a line naming bwrap after this was published.
the line in the docs| `claude-science sandbox approve` | Linux only, version 0.1.71 or later. Approve your own copy of bubblewrap or socat for the sandbox. `--bwrap <path>` and `--socat <path>` name the programs, `--yes` skips the confirmation and is required… |
|
v2.1.311/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Error reference.
the line in the docs* Run `/config` in the lead session and set **Teammate mode** to `in-process`, then ask Claude to start the teammate again. You don't need to find the rule or restart the lead. An in-process teammate [runs under the lead's live deny rules]… |
|
v2.1.311/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Error reference.
the line in the docs* Run `/config` in the lead session and set **Teammate mode** to `in-process`, then ask Claude to start the teammate again. You don't need to find the rule or restart the lead. An in-process teammate [runs under the lead's live deny rules]… |
|
v2.1.311agent_id |
Documentation arrivedAnthropic's documentation has since written up agent_id, on Agent SDK reference - TypeScript.
the line in the docs`agent_id` identifies the subagent that produced the message and is absent on main-thread messages. The value equals the `task_id` on that subagent's [`task_started`](#sdktaskstartedmessage) and other task events, and is unchanged when the… |
|
v2.1.296updatedPermissions |
Documentation arrivedAnthropic's documentation has since written up updatedPermissions, on Agent SDK reference - TypeScript.
the line in the docsIf you return `allow` with more than 4,096 items in `updatedPermissions`, Claude Code treats the result as invalid and denies the tool call. Each update counts as one item, and so does each entry in its `rules` or `directories` list. The d… |
|
v2.1.296updatedPermissions |
Documentation arrivedAnthropic's documentation has since written up updatedPermissions, on Agent SDK reference - TypeScript.
the line in the docsIf you return `allow` with more than 4,096 items in `updatedPermissions`, Claude Code treats the result as invalid and denies the tool call. Each update counts as one item, and so does each entry in its `rules` or `directories` list. The d… |
|
v2.1.296updatedPermissions |
Documentation arrivedAnthropic's documentation has since written up updatedPermissions, on Agent SDK reference - TypeScript.
the line in the docsIf you return `allow` with more than 4,096 items in `updatedPermissions`, Claude Code treats the result as invalid and denies the tool call. Each update counts as one item, and so does each entry in its `rules` or `directories` list. The d… |
|
v2.1.295updatedPermissions |
Documentation arrivedAnthropic's documentation has since written up updatedPermissions, on Agent SDK reference - TypeScript.
the line in the docsIf you return `allow` with more than 4,096 items in `updatedPermissions`, Claude Code treats the result as invalid and denies the tool call. Each update counts as one item, and so does each entry in its `rules` or `directories` list. The d… |
|
v2.1.311hook_started |
Documentation arrivedAnthropic's documentation has since written up hook_started, on Agent SDK reference - TypeScript.
the line in the docsOf the [`hook_progress`](#sdkhookprogressmessage) messages a `SessionStart` or `Setup` hook emits before the handshake completes, you get only the newest, which carries all of the hook's output so far. `startup()` holds that message, the h… |
|
v2.1.311PreToolUse |
Documentation arrivedA small documentation edit on Modifying system prompts touched a line naming PreToolUse after this was published.
the line in the docs* To stop only `@` file mentions from expanding, set [`CLAUDE_CODE_DISABLE_FILE_MENTIONS=1`](https://code.claude.com/docs/en/env-vars#variables) instead, on Claude Code v2.1.299 or later. Claude then gets the mentioned paths plus a note to… |
|
v2.1.307set_model |
Documentation arrivedA small documentation edit on Configure your agent touched a line naming set_model after this was published.
the line in the docs* **`setModel()` / `set_model()`**: switches the model. Call it with no model to switch to [Claude Code's default model](https://code.claude.com/docs/en/model-config.md#default-model-setting) rather than the `model` you passed in options. … |
|
v2.1.311maxBudgetUsd |
Documentation arrivedA small documentation edit on How the agent loop works touched a line naming maxBudgetUsd after this was published.
the line in the docsYou can cap the loop with `max_turns` / `maxTurns`. Count each turn with tool calls, plus one for the final text-only response. Without that extra turn, the run ends with a `ResultMessage` of subtype `error_max_turns` and no final response… |
|
v2.1.311/mcp |
Documentation arrivedA small documentation edit on Error reference touched a line naming /mcp after this was published.
the line in the docsAn MCP server built on Java MCP SDK 0.11.0 through 0.17.0 refused the connection. Those SDK versions can't parse the `form` and `url` [elicitation modes](https://code.claude.com/docs/en/mcp.md#elicitation-modes-claude-code-declares) that C… |
|
v2.1.311/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on Claude Code changelog.
the line in the docs* Fixed the `/model` and `/effort` cache warning saying the re-read waits for your next message; a change made while Claude is working can trigger it sooner |
|
v2.1.310/login |
Documentation arrivedA small documentation edit on Use Claude Code with Chrome touched a line naming /login after this was published.
the line in the docsChrome integration also requires signing in with `/login`. If you authenticate with an API key or a long-lived token from [`claude setup-token`](https://code.claude.com/docs/en/authentication#generate-a-long-lived-token), Claude Code keeps… |
|
v2.1.309cursor |
Documentation arrivedA small documentation edit on Use Claude Code with a screen reader touched a line naming cursor after this was published.
the line in the docsClaude Code keeps the terminal cursor on the input caret, so your screen reader's read-current-line command reads the prompt you're editing. As you type at the end of the input line, or press `Backspace` there, Claude Code writes only the … |
|
v2.1.310haiku |
Documentation arrivedA small documentation edit on overview touched a line naming haiku after this was published.
the line in the docs[What’s new in Claude Haiku 5.5](https://platform.claude.com/docs/en/models/haiku-5-5/whats-new-haiku-5-5) |
|
v2.1.309--remote |
Documentation arrivedAnthropic's documentation has since written up --remote, on WARNING: This operation PERMANENTLY deletes the chat, all of its messages,.
the line in the docsIn curl, the `--remote-header-name` (`-J`) option, which normally saves a download under the `Content-Disposition` file name, does not read the `filename*` form, so name the saved file yourself with `--output`. In a script, take the name f… |
|
v2.1.310opus |
Documentation arrivedA small documentation edit on intro touched a line naming opus after this was published.
the line in the docsIf you’re unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for d… |
|
v2.1.310fable |
Documentation arrivedA small documentation edit on intro touched a line naming fable after this was published.
the line in the docsIf you’re unsure which model to use, start with [Claude Opus 5.5](https://platform.claude.com/docs/en/models/opus-5-5/overview) for most workloads. Use [Claude Fable 5.1](https://platform.claude.com/docs/en/models/fable-5-1/overview) for d… |
|
v2.1.310ANTHROPIC_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BASE_URL, on Before.
the line in the docsIf `--base-url` or `ANTHROPIC_BASE_URL` points `ant` at a proxy or gateway that reads `X-Api-Key`, change it to read the key from `Authorization`. `ant` has no flag or environment variable for adding a header of your own, so it can’t send … |
|
v2.1.309file_upload |
Documentation arrivedAnthropic's documentation has since written up file_upload, on browser-use-sdk.
the line in the docs`file_upload` is off by default. With no `file_policy` (typescript: `filePolicy`), the SDK refuses every upload that gives a path or a [document ID](https://platform.claude.com/docs/en/agents-and-tools/tool-use/browser-use-tool#upload-file… |