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 |
|---|---|---|
v2.1.248--restricted |
Documentation arrivedAnthropic's documentation has since written up --restricted, on Tools reference.
the line in the docs* A permissions [deny rule](/docs/en/permissions#match-all-uses-of-a-tool), the `--disallowedTools` flag, or [`--restricted`](/docs/en/cli-reference#cli-flags) removes `Bash` from the session. |
|
v2.1.234--disallowedTools |
Documentation arrivedAnthropic's documentation has since written up --disallowedTools, on Tools reference.
the line in the docs* A permissions [deny rule](/docs/en/permissions#match-all-uses-of-a-tool), the `--disallowedTools` flag, or [`--restricted`](/docs/en/cli-reference#cli-flags) removes `Bash` from the session. |
|
v2.1.248--tools |
Documentation arrivedAnthropic's documentation has since written up --tools, on Tools reference.
the line in the docs* You name `Glob` or `Grep` in [`--tools` or `--allowedTools`](/docs/en/cli-reference#cli-flags) when you start the session, or in the equivalent [Agent SDK](/docs/en/agent-sdk/overview) options. With `--tools` you get the ones you list, a… |
|
v2.1.239--tools |
Documentation arrivedAnthropic's documentation has since written up --tools, on Tools reference.
the line in the docs* You name `Glob` or `Grep` in [`--tools` or `--allowedTools`](/docs/en/cli-reference#cli-flags) when you start the session, or in the equivalent [Agent SDK](/docs/en/agent-sdk/overview) options. With `--tools` you get the ones you list, a… |
|
v2.1.234--allowedTools |
Documentation arrivedAnthropic's documentation has since written up --allowedTools, on Tools reference.
the line in the docs* You name `Glob` or `Grep` in [`--tools` or `--allowedTools`](/docs/en/cli-reference#cli-flags) when you start the session, or in the equivalent [Agent SDK](/docs/en/agent-sdk/overview) options. With `--tools` you get the ones you list, a… |
|
v2.1.268placement |
Documentation arrivedAnthropic's documentation has since written up placement, on Automate actions with hooks.
the line in the docs* **A field at the wrong level**: compare each field's placement against the [JSON output](/docs/en/hooks#json-output) format. For example, `permissionDecision` belongs inside `hookSpecificOutput`, not at the top level. |
|
v2.1.242region |
Documentation arrivedA small documentation edit on Claude Code on Google Cloud's Agent Platform touched a line naming region after this was published.
the line in the docsChoose how you authenticate to Google Cloud: Application Default Credentials from `gcloud`, a service account key file, or credentials already in your environment. The wizard asks for your project and region, verifies which Claude models y… |
|
v2.1.268env |
Documentation arrivedA small documentation edit on Claude Code on Google Cloud's Agent Platform touched a line naming env after this was published.
the line in the docsChoose how you authenticate to Google Cloud: Application Default Credentials from `gcloud`, a service account key file, or credentials already in your environment. The wizard asks for your project and region, verifies which Claude models y… |
|
v2.1.257Monitor |
Documentation arrivedA small documentation edit on Run Claude Code behind a corporate launcher touched a line naming Monitor after this was published.
the line in the docsWith a launcher configured, `ps` and Activity Monitor no longer show Claude Code's `claude bg-pty-host` and `claude bg-spare` labels for the background helper processes, because the launcher's `exec` rebuilds the argument list. Losing the … |
|
v2.1.257Monitor |
Documentation arrivedA small documentation edit on Run Claude Code behind a corporate launcher touched a line naming Monitor after this was published.
the line in the docsWith a launcher configured, `ps` and Activity Monitor no longer show Claude Code's `claude bg-pty-host` and `claude bg-spare` labels for the background helper processes, because the launcher's `exec` rebuilds the argument list. Losing the … |
|
v2.1.248--tools |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --tools after this was published.
the line in the docs| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bash,Edit,Read"`. On macOS, Linux, and WSL, the default set leaves out `Glob` and `Grep`, as describ… |
|
v2.1.239--tools |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --tools after this was published.
the line in the docs| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bash,Edit,Read"`. On macOS, Linux, and WSL, the default set leaves out `Glob` and `Grep`, as describ… |
|
v2.1.236disallowedTools |
Documentation arrivedA small documentation edit on CLI reference touched a line naming disallowedTools after this was published.
the line in the docs| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bash,Edit,Read"`. On macOS, Linux, and WSL, the default set leaves out `Glob` and `Grep`, as describ… |
|
v2.1.234--disallowedTools |
Documentation arrivedA small documentation edit on CLI reference touched a line naming --disallowedTools after this was published.
the line in the docs| `--tools` | Restrict which built-in tools Claude can use. Use `""` to disable all, `"default"` for the default set, or tool names like `"Bash,Edit,Read"`. On macOS, Linux, and WSL, the default set leaves out `Glob` and `Grep`, as describ… |
|
v2.1.260otlpTracesEnabled |
Documentation arrivedA small documentation edit on Telemetry and egress touched a line naming otlpTracesEnabled after this was published.
the line in the docsWith `otlpEndpoint` set, `otlpTracesEnabled` alone decides whether Cowork and Code sessions export traces. Leaving it unset or `false` keeps traces off even when Claude Code's own settings on the device, including managed settings, turn tr… |
|
v2.1.268update |
Documentation arrivedA small documentation edit on Overview touched a line naming update after this was published.
the line in the docsWith Anthropic-bound telemetry, non-essential services, and updates all disabled, the only remaining Anthropic-operated egress is `downloads.claude.ai` for the VM bundle at session start. An app managed from the [Enterprise Admin Console](… |
|
v2.1.267delete |
Documentation arrivedA small documentation edit on Deploy with MDM touched a line naming delete after this was published.
the line in the docs| **Limits** | Per-device token cap and its window length<br />Retention periods after which idle chats, Cowork tasks, and Code sessions are deleted, and the hold that suspends deletion | |
|
v2.1.268family |
Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming family after this was published.
the line in the docsIf your gateway serves a Claude model under an opaque routing alias, it can mark the model as Claude by returning an `anthropic_family_tier` field (a Claude tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` res… |
|
v2.1.268/model |
Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming /model after this was published.
the line in the docsIf your gateway serves a Claude model under an opaque routing alias, it can mark the model as Claude by returning an `anthropic_family_tier` field (a Claude tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` res… |
|
v2.1.268/model |
Documentation arrivedA small documentation edit on Deploy Claude Desktop on 3P with an LLM gateway touched a line naming /model after this was published.
the line in the docsIf your gateway serves a Claude model under an opaque routing alias, it can mark the model as Claude by returning an `anthropic_family_tier` field (a Claude tier name such as `sonnet` or `opus`) on that model object in its `/v1/models` res… |
|
v2.1.259disableAllHooks |
Documentation arrivedAnthropic's documentation has since written up disableAllHooks, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.242disableAllHooks |
Documentation arrivedAnthropic's documentation has since written up disableAllHooks, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.242disableAllHooks |
Documentation arrivedAnthropic's documentation has since written up disableAllHooks, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.261allowManagedHooksOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedHooksOnly, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.242allowManagedHooksOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedHooksOnly, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.238allowManagedHooksOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedHooksOnly, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.238allowManagedHooksOnly |
Documentation arrivedAnthropic's documentation has since written up allowManagedHooksOnly, on MCP, plugins, skills, and hooks.
the line in the docsClaude Code [managed settings](/docs/third-party/claude-desktop/code#interaction-with-claude-code%E2%80%99s-own-managed-settings) deployed on the device govern these hooks as they do in the Claude Code CLI: `disableAllHooks` turns them off… |
|
v2.1.268required |
Documentation arrivedA small documentation edit on Sign in through the OS identity broker touched a line naming required after this was published.
the line in the docsWhat happens on Linux, or on a Windows or macOS device where the broker is unavailable, depends on the feature. For the inference sign-in flows (Foundry, gateway, and Workforce Identity), the app shows an error that names the browser flow … |
|
v2.1.260m365 |
Documentation arrivedA small documentation edit on Sign in through the OS identity broker touched a line naming m365 after this was published.
the line in the docsWhat happens on Linux, or on a Windows or macOS device where the broker is unavailable, depends on the feature. For the inference sign-in flows (Foundry, gateway, and Workforce Identity), the app shows an error that names the browser flow … |
|
v2.1.259managedMcpServers |
Documentation arrivedAnthropic's documentation has since written up managedMcpServers, on Chat in Claude Desktop on 3P.
the line in the docs| Managed MCP servers | The servers you provision via [`managedMcpServers`](/docs/third-party/claude-desktop/configuration#managedmcpservers) are available in Chat with the same approval model as Cowork sessions: a tool's `toolPolicy` of `… |
|
v2.1.259managedMcpServers |
Documentation arrivedAnthropic's documentation has since written up managedMcpServers, on Chat in Claude Desktop on 3P.
the line in the docs| Managed MCP servers | The servers you provision via [`managedMcpServers`](/docs/third-party/claude-desktop/configuration#managedmcpservers) are available in Chat with the same approval model as Cowork sessions: a tool's `toolPolicy` of `… |
|
v2.1.259managedMcpServers |
Documentation arrivedAnthropic's documentation has since written up managedMcpServers, on Chat in Claude Desktop on 3P.
the line in the docs| Managed MCP servers | The servers you provision via [`managedMcpServers`](/docs/third-party/claude-desktop/configuration#managedmcpservers) are available in Chat with the same approval model as Cowork sessions: a tool's `toolPolicy` of `… |
|
v2.1.259managedMcpServers |
Documentation arrivedAnthropic's documentation has since written up managedMcpServers, on Chat in Claude Desktop on 3P.
the line in the docs| Managed MCP servers | The servers you provision via [`managedMcpServers`](/docs/third-party/claude-desktop/configuration#managedmcpservers) are available in Chat with the same approval model as Cowork sessions: a tool's `toolPolicy` of `… |
|
v2.1.259managedMcpServers |
Documentation arrivedAnthropic's documentation has since written up managedMcpServers, on Chat in Claude Desktop on 3P.
the line in the docs| Managed MCP servers | The servers you provision via [`managedMcpServers`](/docs/third-party/claude-desktop/configuration#managedmcpservers) are available in Chat with the same approval model as Cowork sessions: a tool's `toolPolicy` of `… |
|
v2.1.267@Claude |
Documentation arrivedA small documentation edit on Control when Claude Tag responds touched a line naming @Claude after this was published.
the line in the docsTo start Claude reading again, mention `@Claude` in the channel. A mention from a person reaches Claude even while Claude isn't reading the channel, and once Claude posts its reply, it reads the channel's messages again. |
|
v2.1.233--no-publish |
Documentation arrivedAnthropic's documentation has since written up --no-publish, on Plugins reference.
the line in the docs| `--no-publish` | Keep the HTML report local | | |
|
v2.1.242--mocks |
Documentation arrivedAnthropic's documentation has since written up --mocks, on Plugins reference.
the line in the docs| `--mocks <mode>` | `record` or `off`. See [Mock MCP servers](/docs/en/plugin-evals#mock-mcp-servers) | `record` | |
|
v2.1.242--mocks |
Documentation arrivedAnthropic's documentation has since written up --mocks, on Plugins reference.
the line in the docs| `--mocks <mode>` | `record` or `off`. See [Mock MCP servers](/docs/en/plugin-evals#mock-mcp-servers) | `record` | |
|
v2.1.242--mocks |
Documentation arrivedAnthropic's documentation has since written up --mocks, on Plugins reference.
the line in the docs| `--mocks <mode>` | `record` or `off`. See [Mock MCP servers](/docs/en/plugin-evals#mock-mcp-servers) | `record` | |
|
v2.1.259ANTHROPIC_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_MODEL, on Plugins reference.
the line in the docs| `--model <model>` | Model for the agent under test | Each case's `model`, else `ANTHROPIC_MODEL` if set, else Claude Code's default | |
|
v2.1.236ANTHROPIC_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_MODEL, on Plugins reference.
the line in the docs| `--model <model>` | Model for the agent under test | Each case's `model`, else `ANTHROPIC_MODEL` if set, else Claude Code's default | |
|
v2.1.251--output-dir |
Documentation arrivedAnthropic's documentation has since written up --output-dir, on Plugins reference.
the line in the docsThis table lists the options most runs use. Run `claude plugin eval --help` for the complete set, including `--case`, `--tag`, `--output-dir`, `--report`, `--allow-real-servers`, `--keep-temp`, and `--verbose`. |
|
v2.1.235--output-dir |
Documentation arrivedAnthropic's documentation has since written up --output-dir, on Plugins reference.
the line in the docsThis table lists the options most runs use. Run `claude plugin eval --help` for the complete set, including `--case`, `--tag`, `--output-dir`, `--report`, `--allow-real-servers`, `--keep-temp`, and `--verbose`. |
|
v2.1.246--verbose |
Documentation arrivedAnthropic's documentation has since written up --verbose, on Plugins reference.
the line in the docsThis table lists the options most runs use. Run `claude plugin eval --help` for the complete set, including `--case`, `--tag`, `--output-dir`, `--report`, `--allow-real-servers`, `--keep-temp`, and `--verbose`. |
|
v2.1.233--verbose |
Documentation arrivedAnthropic's documentation has since written up --verbose, on Plugins reference.
the line in the docsThis table lists the options most runs use. Run `claude plugin eval --help` for the complete set, including `--case`, `--tag`, `--output-dir`, `--report`, `--allow-real-servers`, `--keep-temp`, and `--verbose`. |
|
v2.1.268--json |
Documentation arrivedAnthropic's documentation has since written up --json, on Plugins reference.
the line in the docsThe optional `target` is a plugin directory, a single `prompt.md` or `case.yaml` file, an installed plugin as `name` or `name@marketplace`, or `name@skills-dir`, and defaults to the current directory. Put it before `--tag`, `--allow-tools`… |
|
v2.1.242--allow-tools |
Documentation arrivedAnthropic's documentation has since written up --allow-tools, on Plugins reference.
the line in the docsThe optional `target` is a plugin directory, a single `prompt.md` or `case.yaml` file, an installed plugin as `name` or `name@marketplace`, or `name@skills-dir`, and defaults to the current directory. Put it before `--tag`, `--allow-tools`… |
|
v2.1.236prompt.md |
Documentation arrivedAnthropic's documentation has since written up prompt.md, on Plugins reference.
the line in the docsThe optional `target` is a plugin directory, a single `prompt.md` or `case.yaml` file, an installed plugin as `name` or `name@marketplace`, or `name@skills-dir`, and defaults to the current directory. Put it before `--tag`, `--allow-tools`… |
|
v2.1.236case.yaml |
Documentation arrivedAnthropic's documentation has since written up case.yaml, on Plugins reference.
the line in the docsThe optional `target` is a plugin directory, a single `prompt.md` or `case.yaml` file, an installed plugin as `name` or `name@marketplace`, or `name@skills-dir`, and defaults to the current directory. Put it before `--tag`, `--allow-tools`… |
|
v2.1.242--eval-dir |
Documentation arrivedAnthropic's documentation has since written up --eval-dir, on Plugins reference.
the line in the docs| `experimental.evals` | string\|array | Directory below the plugin root that holds the plugin's [eval cases](/docs/en/plugin-evals#use-a-different-eval-directory), when it isn't the default `evals/`. `claude plugin eval --eval-dir` overri… |