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 |
|---|---|---|
v2.1.304--tools |
Documentation arrivedAnthropic's documentation has since written up --tools, on Claude Code changelog.
the line in the docs* Fixed every request failing on Vertex, Bedrock and other providers when the endpoint or a gateway rejects tool search, and behind gateways with ToolSearch disallowed or left out of `--tools` (a 2.1.304 regression): Claude Code now retrie… |
|
v2.1.304deniedMcpServers |
Documentation arrivedAnthropic's documentation has since written up deniedMcpServers, on Claude Code changelog.
the line in the docs* Changed `allowedMcpServers` to stop filtering `managed-mcp.json` stdio servers that use `${VAR}` only in `env`: one your allowlist left out now loads on upgrade; use `deniedMcpServers` to keep it off |
|
v2.1.304sandbox.allowNestedUserNamespaces |
Documentation arrivedAnthropic's documentation has since written up sandbox.allowNestedUserNamespaces, on Claude Code changelog.
the line in the docs* Added `sandbox.allowNestedUserNamespaces` so sandboxed commands on Linux can create user namespaces (Chromium, rootless podman); this lets them get around the sandbox's file protections |
|
v2.1.304ANTHROPIC_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BASE_URL, on Scale to many tools with tool search.
the line in the docs> Tool search is on by default behind an `ANTHROPIC_BASE_URL` gateway, with nothing to set. If the gateway rejects it, see [Tool search through an LLM gateway](/docs/en/mcp#tool-search-through-a-gateway). Before Claude Code v2.1.304, the S… |
|
v2.1.304ANTHROPIC_BASE_URL |
Documentation arrivedA small documentation edit on Connect to external tools with MCP touched a line naming ANTHROPIC_BASE_URL after this was published.
the line in the docs* **With [tool search](/docs/en/agent-sdk/tool-search), the default**: the wait covers still-pending servers configured with [`alwaysLoad: true`](/docs/en/mcp#exempt-a-server-from-deferral), and servers it leaves out keep connecting in the… |
|
v2.1.304alwaysLoad |
Documentation arrivedA small documentation edit on Connect to external tools with MCP touched a line naming alwaysLoad after this was published.
the line in the docs* **With [tool search](/docs/en/agent-sdk/tool-search), the default**: the wait covers still-pending servers configured with [`alwaysLoad: true`](/docs/en/mcp#exempt-a-server-from-deferral), and servers it leaves out keep connecting in the… |
|
v2.1.304/config |
Documentation arrivedA small documentation edit on Use Claude Science on a corporate network touched a line naming /config after this was published.
the line in the docsThe `[network] ca_bundle` key in `config.toml` points at a PEM file whose certificates Claude Science adds to its default trust for sign-in, the Claude API, Anthropic-hosted connectors, update checks, and [cloud storage](/docs/claude-scien… |
|
v2.1.304/plugin |
Documentation arrivedA small documentation edit on Mods reference touched a line naming /plugin after this was published.
the line in the docs| `Image` | PNG or RGBA bytes up to 2 MiB, or a file path, `columns` and `rows` up to 255, and `alt` text. See [which terminals draw it](/docs/en/plugins/mods/gallery#image-and-client). | ✓ | | | |
|
v2.1.304claude update |
Documentation arrivedAnthropic's documentation has since written up claude update, on claude-api-skill.
the line in the docsThe skill reads the agent with the `ant` CLI, so first set up the CLI for the agent's workspace, as the [CLI quickstart](https://platform.claude.com/docs/en/cli-sdks-libraries/cli/quickstart) shows. It needs a current version of Claude Cod… |
|
v2.1.288/update |
Documentation arrivedA small documentation edit on Admin controls touched a line naming /update after this was published.
the line in the docsThe settings apply to members running version 0.1.41 or later of the Claude Science app. A member still on an earlier version isn't governed by these settings until the member updates (see [Required updates](/docs/claude-science/manage-on-… |
|
v2.1.288/update |
Documentation arrivedA small documentation edit on Admin controls touched a line naming /update after this was published.
the line in the docsThe settings apply to members running version 0.1.41 or later of the Claude Science app. A member still on an earlier version isn't governed by these settings until the member updates (see [Required updates](/docs/claude-science/manage-on-… |
|
v2.1.287/update |
Documentation arrivedA small documentation edit on Admin controls touched a line naming /update after this was published.
the line in the docsThe settings apply to members running version 0.1.41 or later of the Claude Science app. A member still on an earlier version isn't governed by these settings until the member updates (see [Required updates](/docs/claude-science/manage-on-… |
|
v2.1.285/update |
Documentation arrivedA small documentation edit on Admin controls touched a line naming /update after this was published.
the line in the docsThe settings apply to members running version 0.1.41 or later of the Claude Science app. A member still on an earlier version isn't governed by these settings until the member updates (see [Required updates](/docs/claude-science/manage-on-… |
|
v2.1.304/workflows |
Documentation arrivedAnthropic's documentation has since written up /workflows, on Orchestrate subagents at scale with dynamic workflows.
the line in the docs* **Failed**: runs again, and so does every agent the script starts after it, even ones that completed. Stopping one agent alone, by selecting it in [`/workflows`](#watch-the-run) and pressing `x`, counts as failing. |
|
v2.1.304/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Connect Claude Code to tools via MCP.
the line in the docsTo see what the plugin configured, [find the plugin on disk](/docs/en/plugins/loading#find-plugins-on-disk) and read its `.mcp.json` or `plugin.json`. |
|
v2.1.304claude auth login |
Documentation arrivedA small documentation edit on Deploy self-hosted environments to production touched a line naming claude auth login after this was published.
the line in the docs* **Interactive `claude auth login`**: signs in through `claude.ai`, `claude.com`, and `platform.claude.com`. The [guided setup](/docs/en/self-hosted-environments-quickstart#run-the-guided-setup), `doctor`'s signed-in mode, and [CI dispatc… |
|
v2.1.304claude auth login |
Documentation arrivedA small documentation edit on Deploy self-hosted environments to production touched a line naming claude auth login after this was published.
the line in the docs* **Interactive `claude auth login`**: signs in through `claude.ai`, `claude.com`, and `platform.claude.com`. The [guided setup](/docs/en/self-hosted-environments-quickstart#run-the-guided-setup), `doctor`'s signed-in mode, and [CI dispatc… |
|
v2.1.304claude auth login |
Documentation arrivedA small documentation edit on Deploy self-hosted environments to production touched a line naming claude auth login after this was published.
the line in the docs* **Interactive `claude auth login`**: signs in through `claude.ai`, `claude.com`, and `platform.claude.com`. The [guided setup](/docs/en/self-hosted-environments-quickstart#run-the-guided-setup), `doctor`'s signed-in mode, and [CI dispatc… |
|
v2.1.290claude auth login |
Documentation arrivedA small documentation edit on Deploy self-hosted environments to production touched a line naming claude auth login after this was published.
the line in the docs* **Interactive `claude auth login`**: signs in through `claude.ai`, `claude.com`, and `platform.claude.com`. The [guided setup](/docs/en/self-hosted-environments-quickstart#run-the-guided-setup), `doctor`'s signed-in mode, and [CI dispatc… |
|
v2.1.280claude auth login |
Documentation arrivedA small documentation edit on Deploy self-hosted environments to production touched a line naming claude auth login after this was published.
the line in the docs* **Interactive `claude auth login`**: signs in through `claude.ai`, `claude.com`, and `platform.claude.com`. The [guided setup](/docs/en/self-hosted-environments-quickstart#run-the-guided-setup), `doctor`'s signed-in mode, and [CI dispatc… |
|
v2.1.304/usage |
Documentation arrivedA small documentation edit on Customize keyboard shortcuts touched a line naming /usage after this was published.
the line in the docs| `settings:fixUsage` | F | Send your session the [`/usage` recommendations](/docs/en/costs#apply-recommendations-with-the-fix-shortcut) Claude Code can apply, when the `/usage` footer offers a fix. Requires v2.1.305 or later | |
|
v2.1.304/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on Manage costs effectively.
the line in the docsOn a Pro, Max, Team, or Enterprise plan, `/usage` also shows a breakdown of what counts against your plan limits, with recommendations: |
|
v2.1.304/claude-api |
Documentation arrivedAnthropic's documentation has since written up /claude-api, on Feature availability.
the line in the docsDesktop is the partial exception: [gateway routing can be configured in the app or by an administrator](/docs/en/llm-gateway-connect#desktop-app). [Claude Desktop on 3P](https://claude.com/docs/third-party/claude-desktop/overview) also run… |
|
v2.1.304/model |
Documentation arrivedA small documentation edit on Error reference touched a line naming /model after this was published.
the line in the docs* Reduce concurrency: avoid running many parallel subagents, or switch to a smaller model with `/model` for high-volume scripted runs |
|
v2.1.304/model |
Documentation arrivedA small documentation edit on Error reference touched a line naming /model after this was published.
the line in the docs* Reduce concurrency: avoid running many parallel subagents, or switch to a smaller model with `/model` for high-volume scripted runs |
|
v2.1.299shell |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming shell after this was published.
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… |
|
v2.1.304/loop |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming /loop after this was published.
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… |
|
v2.1.304/loop |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming /loop after this was published.
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… |
|
v2.1.304/model |
Documentation arrivedAnthropic's documentation has since written up /model, on The MCP Registry.
the line in the docs> The MCP Registry is currently in preview. Breaking changes or data resets may occur before general availability. If you encounter any issues, please report them on [GitHub](https://github.com/modelcontextprotocol/registry/issues). |
|
v2.1.304/model |
Documentation arrivedAnthropic's documentation has since written up /model, on The MCP Registry.
the line in the docs> The MCP Registry is currently in preview. Breaking changes or data resets may occur before general availability. If you encounter any issues, please report them on [GitHub](https://github.com/modelcontextprotocol/registry/issues). |
|
v2.1.304/tasks |
Documentation arrivedAnthropic's documentation has since written up /tasks, on Transports Charter.
the line in the docs* **[Tasks and Events WG](/community/working-groups/tasks-events)**: The Tasks and |
|
v2.1.304/tasks |
Documentation arrivedA small documentation edit on Scientific Computing Charter touched a line naming /tasks after this was published.
the line in the docs* **[Tasks and Events WG](/community/working-groups/tasks-events)**: Tasks are the foundation for the long-running |
|
v2.1.302/tasks |
Documentation arrivedA small documentation edit on Scientific Computing Charter touched a line naming /tasks after this was published.
the line in the docs* **[Tasks and Events WG](/community/working-groups/tasks-events)**: Tasks are the foundation for the long-running |
|
v2.1.301/tasks |
Documentation arrivedA small documentation edit on Scientific Computing Charter touched a line naming /tasks after this was published.
the line in the docs* **[Tasks and Events WG](/community/working-groups/tasks-events)**: Tasks are the foundation for the long-running |
|
v2.1.290CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION |
Documentation arrivedA small documentation edit on Tools reference touched a line naming CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION after this was published.
the line in the docsIn [non-interactive mode](/docs/en/headless) with `-p` and in the [Agent SDK](/docs/en/agent-sdk/overview), the limit applies per turn, not per session. A turn lasts from a message you send until Claude finishes responding. The limit reset… |
|
v2.1.302--continue |
Documentation arrivedA small documentation edit on Tools reference touched a line naming --continue after this was published.
the line in the docsIn [non-interactive mode](/docs/en/headless) with `-p` and in the [Agent SDK](/docs/en/agent-sdk/overview), the limit applies per turn, not per session. A turn lasts from a message you send until Claude finishes responding. The limit reset… |
|
v2.1.302--continue |
Documentation arrivedA small documentation edit on Tools reference touched a line naming --continue after this was published.
the line in the docsIn [non-interactive mode](/docs/en/headless) with `-p` and in the [Agent SDK](/docs/en/agent-sdk/overview), the limit applies per turn, not per session. A turn lasts from a message you send until Claude finishes responding. The limit reset… |
|
v2.1.299--continue |
Documentation arrivedA small documentation edit on Tools reference touched a line naming --continue after this was published.
the line in the docsIn [non-interactive mode](/docs/en/headless) with `-p` and in the [Agent SDK](/docs/en/agent-sdk/overview), the limit applies per turn, not per session. A turn lasts from a message you send until Claude finishes responding. The limit reset… |
|
v2.1.299tool.check |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming tool.check after this was published.
the line in the docsThat precedence covers hooks in settings files and in a plugin's `hooks/hooks.json`. A [mod](/docs/en/plugins/mods/overview) you install that handles the [`tool.check`](/docs/en/plugins/mods/events#approve-or-refuse-a-tool-call-before-the-… |
|
v2.1.284/auto-mode-setup |
Documentation arrivedA small documentation edit on Error reference touched a line naming /auto-mode-setup after this was published.
the line in the docs* A command that exists but isn't available in this session because a requirement isn't met, such as your platform, plan, or authentication method. See the entry for [`/web-setup`](/docs/en/web-quickstart#web-setup-shows-no-commands-match-… |
|
v2.1.300/autofix-pr |
Documentation arrivedAnthropic's documentation has since written up /autofix-pr, on What's new.
the line in the docsAlso this week: the **Monitor** tool streams background events into the conversation so Claude can tail logs and react live, `/loop` self-paces when you omit the interval, `/team-onboarding` packages your setup into a replayable guide, and… |
|
v2.1.299worktree.baseRef |
Documentation arrivedAnthropic's documentation has since written up worktree.baseRef, on What's new.
the line in the docsAlso this week: **`worktree.baseRef`** chooses whether new worktrees branch from the remote default or local `HEAD`; **auto mode hard deny rules** block actions unconditionally regardless of allow exceptions; and **hooks see the active eff… |
|
v2.1.299--safe-mode |
Documentation arrivedAnthropic's documentation has since written up --safe-mode, on What's new.
the line in the docsAlso this week: **sub-agents can spawn their own sub-agents** (background chains are capped at five levels deep); **`--safe-mode`** starts Claude Code with all customizations disabled for troubleshooting; and **`fallbackModel`** configures… |
|
v2.1.299--safe-mode |
Documentation arrivedAnthropic's documentation has since written up --safe-mode, on What's new.
the line in the docsAlso this week: **sub-agents can spawn their own sub-agents** (background chains are capped at five levels deep); **`--safe-mode`** starts Claude Code with all customizations disabled for troubleshooting; and **`fallbackModel`** configures… |
|
v2.1.302/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on What's new.
the line in the docs**Resume terminal sessions in the Desktop app**: type `/resume` in the Claude Code Desktop prompt box to pick up any session you started from the CLI, with the full conversation and context intact. |
|
v2.1.302/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on What's new.
the line in the docs**Resume terminal sessions in the Desktop app**: type `/resume` in the Claude Code Desktop prompt box to pick up any session you started from the CLI, with the full conversation and context intact. |
|
v2.1.302/resume |
Documentation arrivedAnthropic's documentation has since written up /resume, on What's new.
the line in the docs**Resume terminal sessions in the Desktop app**: type `/resume` in the Claude Code Desktop prompt box to pick up any session you started from the CLI, with the full conversation and context intact. |
|
v2.1.295CLAUDE_CODE_TOOL_MEMORY_LIMIT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_TOOL_MEMORY_LIMIT, on Week 33 · August 10–14, 2026.
the line in the docsType `@` in the prompt to [mention another Claude session](/docs/en/cross-session-messaging#message-another-session) by name, and Claude messages it directly with `SendMessage`; a bare name that matches exactly one live session now deliver… |
|
v2.1.295strictKnownMarketplaces |
Documentation arrivedAnthropic's documentation has since written up strictKnownMarketplaces, on Week 33 · August 10–14, 2026.
the line in the docsType `@` in the prompt to [mention another Claude session](/docs/en/cross-session-messaging#message-another-session) by name, and Claude messages it directly with `SendMessage`; a bare name that matches exactly one live session now deliver… |
|
v2.1.300ultraplan |
Documentation arrivedAnthropic's documentation has since written up ultraplan, on Week 32 · August 3–7, 2026.
the line in the docsThe VS Code extension gets [Focus view](/docs/en/vs-code#extension-settings), which hides tool activity behind one expandable row per turn; toggle it from the command menu or with `Ctrl+Alt+F` (`Ctrl+Option+F` on Mac)Sandbox credential fil… |