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 |
|---|---|---|
v2.1.293ANTHROPIC_DEFAULT_SONNET_MODEL |
Documentation arrivedA small documentation edit on Claude Code on Google Cloud's Agent Platform touched a line naming ANTHROPIC_DEFAULT_SONNET_MODEL after this was published.
the line in the docsOpus models have a higher per-token price than Sonnet models, so if you don't pin a primary model, you're billed at the Opus rate. To use Sonnet 4.5 as the primary model, set `ANTHROPIC_MODEL` to its full model ID. A deployment that steers… |
|
v2.1.288ANTHROPIC_DEFAULT_SONNET_MODEL |
Documentation arrivedA small documentation edit on Claude Code on Google Cloud's Agent Platform touched a line naming ANTHROPIC_DEFAULT_SONNET_MODEL after this was published.
the line in the docsOpus models have a higher per-token price than Sonnet models, so if you don't pin a primary model, you're billed at the Opus rate. To use Sonnet 4.5 as the primary model, set `ANTHROPIC_MODEL` to its full model ID. A deployment that steers… |
|
v2.1.290/rename |
Documentation arrivedA small documentation edit on Use Claude Code in the cloud touched a line naming /rename after this was published.
the line in the docs* **`/model`, `/effort`, `/color`, and `/rename`**: pass the value as an argument, for example `/model sonnet`, instead of opening the terminal picker or slider. The argument forms follow each command's [availability notes](/docs/en/comman… |
|
v2.1.287--json |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --json after this was published.
the line in the docsTo see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `type` for each: the first three rows are `dependency-unsatisf… |
|
v2.1.287--json |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --json after this was published.
the line in the docsTo see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `type` for each: the first three rows are `dependency-unsatisf… |
|
v2.1.285--json |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --json after this was published.
the line in the docsTo see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `type` for each: the first three rows are `dependency-unsatisf… |
|
v2.1.285--json |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming --json after this was published.
the line in the docsTo see these programmatically, run `claude plugin list --json` in your shell. Plugins with problems carry an `errors` field with the messages and an `errorDetails` field with a `type` for each: the first three rows are `dependency-unsatisf… |
|
v2.1.296allow_large |
Documentation arrivedAnthropic's documentation has since written up allow_large, on Agent SDK reference - TypeScript.
the line in the docsallow_large?: boolean; |
|
v2.1.296claude_code_version |
Documentation arrivedAnthropic's documentation has since written up claude_code_version, on Agent SDK reference - TypeScript.
the line in the docsclaude_code_version?: string; |
|
v2.1.296claude_code_version |
Documentation arrivedAnthropic's documentation has since written up claude_code_version, on Agent SDK reference - TypeScript.
the line in the docsclaude_code_version?: string; |
|
v2.1.296claude_code_version |
Documentation arrivedAnthropic's documentation has since written up claude_code_version, on Agent SDK reference - TypeScript.
the line in the docsclaude_code_version?: string; |
|
v2.1.280CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH, on Connect Claude Code to tools via MCP.
the line in the docsTo change the limits for every MCP server in your session, set [`CLAUDE_CODE_MAX_MCP_DESCRIPTION_LENGTH`](/docs/en/env-vars#variables) to a number of characters. The number you set replaces both limits: `8192`, for example, raises the shor… |
|
v2.1.286allow_remote_sessions |
Documentation arrivedAnthropic's documentation has since written up allow_remote_sessions, on Use Claude Code in the cloud.
the line in the docs| `Cloud sessions are disabled by your organization's policy. Contact your organization admin to enable them.` | Your organization's `allow_remote_sessions` policy is off; see [Cloud sessions are disabled by your organization's policy](/do… |
|
v2.1.290idleCompaction |
Documentation arrivedAnthropic's documentation has since written up idleCompaction, on All settings.
the line in the docs| [`idleCompaction`](#idlecompaction) | Stop Claude Code from compacting a long conversation while your terminal session is idle | Memory and context | Any file | |
|
v2.1.290idleCompaction |
Documentation arrivedA small documentation edit on Model configuration touched a line naming idleCompaction after this was published.
the line in the docsSee the [`idleCompaction`](/docs/en/settings-reference#idlecompaction) setting for when Claude Code also compacts a conversation you leave idle. |
|
v2.1.295--model |
Documentation arrivedAnthropic's documentation has since written up --model, on thinking.
the line in the docs--model claude-opus-5-5 \ |
|
v2.1.295/fast |
Documentation arrivedA small documentation edit on Connect Claude Code to Claude for Government touched a line naming /fast after this was published.
the line in the docs* With Claude for Government, the command-line tool has no access to Claude Code features that [require a claude.ai account](https://code.claude.com/docs/en/feature-availability#features-that-require-a-claude-subscription), such as cloud s… |
|
v2.1.293autoModeEnabled |
Documentation arrivedAnthropic's documentation has since written up autoModeEnabled, on Features.
the line in the docs| Automatically approve in Cowork | Cowork offers the **Automatically approve** mode when an administrator sets [`autoModeEnabled`](/docs/third-party/claude-desktop/configuration#automodeenabled) to `true`. | |
|
v2.1.295autoMode |
Documentation arrivedAnthropic's documentation has since written up autoMode, on Features.
the line in the docs| Automatically approve in Cowork | Cowork offers the **Automatically approve** mode when an administrator sets [`autoModeEnabled`](/docs/third-party/claude-desktop/configuration#automodeenabled) to `true`. | |
|
v2.1.284GOOGLE_APPLICATION_CREDENTIALS |
Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with Google Cloud's Agent Platform touched a line naming GOOGLE_APPLICATION_CREDENTIALS after this was published.
the line in the docsAt the start of each Cowork session, the app writes an `authorized_user` Application Default Credentials file (the same format produced by `gcloud auth application-default login`) and points `GOOGLE_APPLICATION_CREDENTIALS` at it. The Goog… |
|
v2.1.295recheck |
Documentation arrivedAnthropic's documentation has since written up recheck, on Configuration reference.
the line in the docsWhen a managed source is present, locally written values are ignored. The exception is a managed source that sets only [app-behavior keys](/docs/third-party/claude-desktop/mdm#update-keys-and-managed-precedence) (the update keys `disableAu… |
|
v2.1.287autoUpdate |
Documentation arrivedAnthropic's documentation has since written up autoUpdate, on Configuration reference.
the line in the docsWhen a managed source is present, locally written values are ignored. The exception is a managed source that sets only [app-behavior keys](/docs/third-party/claude-desktop/mdm#update-keys-and-managed-precedence) (the update keys `disableAu… |
|
v2.1.285CLAUDE_CODE_USE_VERTEX |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming CLAUDE_CODE_USE_VERTEX after this was published.
the line in the docs| `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 5.5, Claude … |
|
v2.1.284CLAUDE_CODE_USE_VERTEX |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming CLAUDE_CODE_USE_VERTEX after this was published.
the line in the docs| `400` errors naming `thinking` or `adaptive`, such as `Input tag 'adaptive' found` | The upstream model build doesn't accept adaptive reasoning, which Claude Code requests for Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 5.5, Claude … |
|
v2.1.296ANTHROPIC_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BASE_URL, on Feature availability.
the line in the docs* **MCP servers**: [connectors from claude.ai](/docs/en/mcp#use-mcp-servers-from-claude-ai) load only when your claude.ai subscription is the active authentication method. [Tool search](/docs/en/mcp#configure-tool-search) is off by default… |
|
v2.1.295claude-haiku-5-5 |
Documentation arrivedAnthropic's documentation has since written up claude-haiku-5-5, on advisor-tool.
the line in the docs| Claude Haiku 4.5 (claude-haiku-4-5) | Claude Mythos 5.1 (claude-mythos-5-1)<br />Claude Fable 5.1 (claude-fable-5-1)<br />Claude Mythos 5 (claude-mythos-5)<br />Claude Fable 5 (claude-fable-5)<br />Claude Opus 5.5 (claude-opus-5-5)<br />… |
|
v2.1.296--scope |
Documentation arrivedA small documentation edit on Archive Federation Issuer touched a line naming --scope after this was published.
the line in the docs**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com… |
|
v2.1.296--scope |
Documentation arrivedAnthropic's documentation has since written up --scope, on Federation.
the line in the docs**Requires an OAuth access token with the `org:admin` scope**, from `ant auth login --scope org:admin` or a workload identity federation rule; Admin API keys are not accepted. See [Manage WIF with the Admin API](https://platform.claude.com… |
|
v2.1.292permissionMode |
Documentation arrivedAnthropic's documentation has since written up permissionMode, on migration.
the line in the docs| `permission_mode` (python; typescript: `permissionMode`), `can_use_tool` (python; typescript: `canUseTool`) | Per-tool [`permission_policy` (java, php: `permissionPolicy`; csharp, go: `PermissionPolicy`)](https://platform.claude.com/docs… |
|
v2.1.296run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.295run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.295run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.292run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.288run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.287run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.287run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.287run_in_background |
Documentation arrivedAnthropic's documentation has since written up run_in_background, on Agent SDK reference - TypeScript.
the line in the docsNotification when a background task completes, fails, or is stopped. Background tasks include `run_in_background` Bash commands, [Monitor](#monitor) watches, and background subagents. For the `run_id` and `ambient` fields, see [`SDKTaskSta… |
|
v2.1.292prompt.autocomplete |
Documentation arrivedA small documentation edit on Mods reference touched a line naming prompt.autocomplete after this was published.
the line in the docs| `prompt.autocomplete` | The user types in the prompt box and a word ends at the cursor. `e.token` is that word. Claude Code doesn't wait for the hook: its own autocomplete rows show first. | `{ suggestions }`, a list of `{ text, label, d… |
|
v2.1.292prompt.autocomplete |
Documentation arrivedA small documentation edit on Mods reference touched a line naming prompt.autocomplete after this was published.
the line in the docs| `prompt.autocomplete` | The user types in the prompt box and a word ends at the cursor. `e.token` is that word. Claude Code doesn't wait for the hook: its own autocomplete rows show first. | `{ suggestions }`, a list of `{ text, label, d… |
|
v2.1.283sandbox.enabled |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming sandbox.enabled after this was published.
the line in the docs| Iterate locally with fewer prompts, without a classifier | Manual mode plus the Bash sandbox in [auto-allow mode](/docs/en/sandboxing#sandbox-modes): `claude --permission-mode default`, then run `/sandbox` and select auto-allow | The bui… |
|
v2.1.288--permission-mode |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming --permission-mode after this was published.
the line in the docs| Iterate locally with fewer prompts, without a classifier | Manual mode plus the Bash sandbox in [auto-allow mode](/docs/en/sandboxing#sandbox-modes): `claude --permission-mode default`, then run `/sandbox` and select auto-allow | The bui… |
|
v2.1.290claude plugin list |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin list after this was published.
the line in the docsWhen a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`. The message tells you to remove the marketplace. Removing… |
|
v2.1.289claude plugin list |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin list after this was published.
the line in the docsWhen a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`. The message tells you to remove the marketplace. Removing… |
|
v2.1.285claude plugin list |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin list after this was published.
the line in the docsWhen a registered marketplace stops loading because its name imitates an official one, `claude plugin list` and `/plugin` report `Claude Code refuses the marketplace name "<name>"`. The message tells you to remove the marketplace. Removing… |
|
v2.1.295CLAUDE_CONFIG_DIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CONFIG_DIR, on Debug your configuration.
the line in the docsFrom the same shell, set [`CLAUDE_CONFIG_DIR`](/docs/en/env-vars) to a fresh directory in place of `~/.claude`, and pass [`--setting-sources user`](/docs/en/cli-reference#cli-flags) to turn off project configuration such as `.claude/settin… |
|
v2.1.295count_tokens |
Documentation arrivedAnthropic's documentation has since written up count_tokens, on api-and-data-retention.
the line in the docs| [Token counting](https://platform.claude.com/docs/en/build-with-claude/token-counting) | `/v1/messages/count_tokens` | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Count tokens before sending requests. | |
|
v2.1.295/fast |
Documentation arrivedAnthropic's documentation has since written up /fast, on api-and-data-retention.
the line in the docs| [Fast mode](https://platform.claude.com/docs/en/build-with-claude/fast-mode) | `/v1/messages` with `speed: "fast"` | <Eligible>Yes</Eligible> | <Eligible>Yes</Eligible> | Same Messages API endpoint with faster inference. ZDR applies rega… |
|
v2.1.286CLAUDE_DISABLE_ADOPT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_DISABLE_ADOPT, on Manage multiple agents with agent view.
the line in the docsBackgrounding starts a fresh process that resumes from the saved conversation, and in-flight background work moves to it: running background shell commands, backgrounded subagents, dynamic workflows, scheduled tasks you created with [`/loo… |
|
v2.1.295extraKnownMarketplaces |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming extraKnownMarketplaces after this was published.
the line in the docsIf a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), Claude Code's attempt to add it at startup fails the same way, and the message appears on the **Errors** tab … |
|
v2.1.287extraKnownMarketplaces |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming extraKnownMarketplaces after this was published.
the line in the docsIf a settings file declares the marketplace under [`extraKnownMarketplaces`](/docs/en/settings-reference#extraknownmarketplaces), Claude Code's attempt to add it at startup fails the same way, and the message appears on the **Errors** tab … |