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 |
|---|---|---|
v2.1.293modelPrefer1mContext |
Documentation arrivedAnthropic's documentation has since written up modelPrefer1mContext, on Deploy Claude Desktop on 3P with an LLM gateway.
the line in the docsTo show a model as one entry, add `prefer1m: true` next to `supports1m` on its entry. New conversations with that model use the 1M context window. To do this for every model that supports 1M, set [`modelPrefer1mContext`](/docs/third-party/… |
|
v2.1.268@mention |
Documentation arrivedA small documentation edit on Use Claude Tag in a group DM touched a line naming @mention after this was published.
the line in the docsSelect **Confirm** within 30 minutes. The card changes to a line that names the person who confirmed and says Claude now replies only when @mentioned. |
|
v2.1.293haiku |
Documentation arrivedAnthropic's documentation has since written up haiku, on Model configuration.
the line in the docsOn the Anthropic API, the 1M context window uses standard model pricing with no premium for tokens beyond 200K, except on Haiku 5.5, which [costs more on prompts longer than 100K tokens](#haiku-5-5-context-window-and-pricing). For plans wh… |
|
v2.1.293ANTHROPIC_DEFAULT_SONNET_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_DEFAULT_SONNET_MODEL, on Claude Code on Microsoft Foundry.
the line in the docsOpus 4.6 and Sonnet 4.6 reach the 1M window when you append `[1m]` to the deployment name in `ANTHROPIC_DEFAULT_OPUS_MODEL` or `ANTHROPIC_DEFAULT_SONNET_MODEL`, as [Pin models for third-party deployments](/docs/en/model-config#pin-models-f… |
|
v2.1.290--bare |
Documentation arrivedAnthropic's documentation has since written up --bare, on Configure server-managed settings.
the line in the docsA session receives the managed settings of the organization that owns the credential it authenticates with. An API key from the [Claude Console](https://platform.claude.com) belongs to the Console organization it was created in, which is a… |
|
v2.1.290--bare |
Documentation arrivedAnthropic's documentation has since written up --bare, on Configure server-managed settings.
the line in the docsA session receives the managed settings of the organization that owns the credential it authenticates with. An API key from the [Claude Console](https://platform.claude.com) belongs to the Console organization it was created in, which is a… |
|
v2.1.292tool.check |
Documentation arrivedAnthropic's documentation has since written up tool.check, on React to events with a mod.
the line in the docsAt `tool.check` and `plugin.register`, a refusal returned after `next` resolved still holds, so return it without testing `next.called`: |
|
v2.1.292tool.check |
Documentation arrivedAnthropic's documentation has since written up tool.check, on React to events with a mod.
the line in the docsAt `tool.check` and `plugin.register`, a refusal returned after `next` resolved still holds, so return it without testing `next.called`: |
|
v2.1.292CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS, on Run Claude Code programmatically.
the line in the docsUnless a background command that the main conversation started is still running, Claude Code stops whatever is still running after 10 minutes of continuous idle waiting by default and drops its partial result. To change the 10-minute cap, … |
|
v2.1.275CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS, on Run Claude Code programmatically.
the line in the docsUnless a background command that the main conversation started is still running, Claude Code stops whatever is still running after 10 minutes of continuous idle waiting by default and drops its partial result. To change the 10-minute cap, … |
|
v2.1.268CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_PRINT_BG_WAIT_CEILING_MS, on Run Claude Code programmatically.
the line in the docsUnless a background command that the main conversation started is still running, Claude Code stops whatever is still running after 10 minutes of continuous idle waiting by default and drops its partial result. To change the 10-minute cap, … |
|
v2.1.292claude plugin |
Documentation arrivedA small documentation edit on Marketplace reference touched a line naming claude plugin after this was published.
the line in the docs* **The download folder of a registered GitHub marketplace, `<owner>-<repo>`**: Claude Code downloads a marketplace added from a `github` source such as `acme/x-tools` through a folder named `acme-x-tools`, whatever that marketplace's own … |
|
v2.1.290/run |
Documentation arrivedAnthropic's documentation has since written up /run, on Recipes.
the line in the docs-v "$HOME/.config/mcp-inspector/secret-key:/run/secrets/mcp_inspector_secret_key:ro" \ |
|
v2.1.292timeout |
Documentation arrivedAnthropic's documentation has since written up timeout, on Authorization.
the line in the docs| `--wait-for-auth <sec>` | Poll the state file until a token for `--server-url` appears, then inject it. Times out at `<sec>` with exit `3` (`auth_wait_timeout`). Use after handing a login off to a human. | |
|
v2.1.290--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Authorization.
the line in the docs`--print-handoff` (below) prints a `portForwardCmd` for the web Inspector's |
|
v2.1.287--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Authorization.
the line in the docs`--print-handoff` (below) prints a `portForwardCmd` for the web Inspector's |
|
v2.1.286--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Authorization.
the line in the docs`--print-handoff` (below) prints a `portForwardCmd` for the web Inspector's |
|
v2.1.284gatewayInternalNetworks |
Documentation arrivedAnthropic's documentation has since written up gatewayInternalNetworks, on Claude apps gateway deployment and operations.
the line in the docs* **Declared block**: if your internal network uses public IPv4 space your organization owns, list the block in the `gatewayInternalNetworks` managed setting. The gateway and the user's machine must both be in that block. See [Allow a gate… |
|
v2.1.281gatewayInternalNetworks |
Documentation arrivedAnthropic's documentation has since written up gatewayInternalNetworks, on Claude apps gateway deployment and operations.
the line in the docs* **Declared block**: if your internal network uses public IPv4 space your organization owns, list the block in the `gatewayInternalNetworks` managed setting. The gateway and the user's machine must both be in that block. See [Allow a gate… |
|
v2.1.284gatewayInternalNetworks |
Documentation arrivedA small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming gatewayInternalNetworks after this was published.
the line in the docsSome organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed… |
|
v2.1.281gatewayInternalNetworks |
Documentation arrivedA small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming gatewayInternalNetworks after this was published.
the line in the docsSome organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed… |
|
v2.1.290/login |
Documentation arrivedA small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming /login after this was published.
the line in the docsSome organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed… |
|
v2.1.290/login |
Documentation arrivedA small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming /login after this was published.
the line in the docsSome organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed… |
|
v2.1.290/login |
Documentation arrivedA small documentation edit on Claude apps gateway for Amazon Bedrock, Claude Platform on AWS, Google Cloud, and Microsoft Foundry touched a line naming /login after this was published.
the line in the docsSome organizations number their internal network from a public IPv4 block they own, such as a carrier's own address space or a legacy `/8`, so their gateway has no private address. List those blocks in the `gatewayInternalNetworks` managed… |
|
v2.1.292/artifacts |
Documentation arrivedA small documentation edit on Apps touched a line naming /artifacts after this was published.
the line in the docsProduct that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface … |
|
v2.1.292/artifacts |
Documentation arrivedAnthropic's documentation has since written up /artifacts, on Beta.
the line in the docsProduct that produced this row's activity: one of `chat`, `claude_code`, `cowork`, `office_agent`, or `chat_cowork_unified` (Chat and Cowork unified). These are the canonical Cost & Usage product names; an `office_agent` row's per-surface … |
|
v2.1.265historical |
Documentation arrivedAnthropic's documentation has since written up historical, on Beta.
the line in the docs- `retired`: The model is no longer available for use; inference requests naming it fail. It remains in the catalogue as the historical record of its retirement. |
|
v2.1.265historical |
Documentation arrivedAnthropic's documentation has since written up historical, on Beta.
the line in the docs- `retired`: The model is no longer available for use; inference requests naming it fail. It remains in the catalogue as the historical record of its retirement. |
|
v2.1.290/usage |
Documentation arrivedA small documentation edit on pricing touched a line naming /usage after this was published.
the line in the docsContact the sales team at [[email protected]](mailto:[email protected]) or through the [Claude Console](https://platform.claude.com/usage/limits) to discuss enterprise pricing options. |
|
v2.1.282CLAUDE_CODE_SIMPLE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SIMPLE, on Output styles.
the line in the docs* On the full system prompt, custom output styles leave out Claude Code's section of built-in software engineering instructions, such as how to scope changes, write comments, and verify work, unless `keep-coding-instructions` is set to `tr… |
|
v2.1.282CLAUDE_CODE_SIMPLE |
Documentation arrivedA small documentation edit on Modifying system prompts touched a line naming CLAUDE_CODE_SIMPLE after this was published.
the line in the docsA custom output style leaves the `claude_code` preset's software engineering instructions out and uses your own. To keep them and layer your instructions on top, set `keep-coding-instructions: true` in the frontmatter. Those instructions a… |
|
v2.1.290CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION, on Tools reference.
the line in the docsSet the [`CLAUDE_CODE_MAX_WEB_SEARCHES_PER_SESSION`](/docs/en/env-vars) environment variable to change the cap; it accepts a positive whole number, so the cap can be raised but not turned off. An interactive terminal session's limit refill… |
|
v2.1.290--debug |
Documentation arrivedAnthropic's documentation has since written up --debug, on Customize your status line.
the line in the docsUntil then, `claude --debug` logs `Status line command skipped: workspace trust not accepted`. Restart Claude Code and accept the trust dialog to enable it. |
|
v2.1.290--debug |
Documentation arrivedAnthropic's documentation has since written up --debug, on Customize your status line.
the line in the docsUntil then, `claude --debug` logs `Status line command skipped: workspace trust not accepted`. Restart Claude Code and accept the trust dialog to enable it. |
|
v2.1.284statusLine |
Documentation arrivedAnthropic's documentation has since written up statusLine, on Customize your status line.
the line in the docsUntil you accept the workspace trust dialog, the status line stays blank. Because `statusLine` executes a shell command, Claude Code runs it under the same [workspace trust rule as hooks in settings files](/docs/en/permissions#what-runs-be… |
|
v2.1.288claude doctor |
Documentation arrivedAnthropic's documentation has since written up claude doctor, on Extend Claude with skills.
the line in the docsFor read-only installation diagnostics without starting a session, run `claude doctor` in your terminal instead. |
|
v2.1.290/doctor |
Documentation arrivedAnthropic's documentation has since written up /doctor, on Extend Claude with skills.
the line in the docs### Check your setup with `/doctor` |
|
v2.1.292appendPlugins |
Documentation arrivedAnthropic's documentation has since written up appendPlugins, on Manage mods for your organization.
the line in the docsA plugin that Claude Code copies into its cache counts as a user's, even when managed `enabledPlugins` enables it. That covers every plugin from a GitHub, git, URL, or npm source. Its mod runs among users' mods, `prependPlugins` and `appen… |
|
v2.1.292prependPlugins |
Documentation arrivedAnthropic's documentation has since written up prependPlugins, on Manage mods for your organization.
the line in the docsA plugin that Claude Code copies into its cache counts as a user's, even when managed `enabledPlugins` enables it. That covers every plugin from a GitHub, git, URL, or npm source. Its mod runs among users' mods, `prependPlugins` and `appen… |
|
v2.1.287claude plugin marketplace remove |
Documentation arrivedAnthropic's documentation has since written up claude plugin marketplace remove, on Plugin commands reference.
the line in the docsOn `plugin marketplace add`, `plugin marketplace remove`, and `plugin marketplace update`, `--json` prints one JSON object on the last line of stdout with `command`, `outcome`, and `message` fields. The following is the result of `claude p… |
|
v2.1.285CLAUDE_CODE_SKIP_AWS_CRED_CACHE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SKIP_AWS_CRED_CACHE, on Claude Code on Amazon Bedrock.
the line in the docsThe cache covers every credential method listed at the start of this step except an Amazon Bedrock API key, which doesn't use the provider chain. To resolve the chain on every request instead, set [`CLAUDE_CODE_SKIP_AWS_CRED_CACHE=1`](/doc… |
|
v2.1.285CLAUDE_CODE_SKIP_AWS_CRED_CACHE |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SKIP_AWS_CRED_CACHE, on Claude Code on Amazon Bedrock.
the line in the docsThe cache covers every credential method listed at the start of this step except an Amazon Bedrock API key, which doesn't use the provider chain. To resolve the chain on every request instead, set [`CLAUDE_CODE_SKIP_AWS_CRED_CACHE=1`](/doc… |
|
v2.1.289agent.spawn |
Documentation arrivedA small documentation edit on Orchestrate teams of Claude Code sessions touched a line naming agent.spawn after this was published.
the line in the docsIf an installed [mod](/docs/en/plugins/mods/overview) sets a model in its [`agent.spawn`](/docs/en/plugins/mods/reference#subagents) hook, Claude Code uses that model in place of the first source. |
|
v2.1.269agent.spawn |
Documentation arrivedA small documentation edit on Orchestrate teams of Claude Code sessions touched a line naming agent.spawn after this was published.
the line in the docsIf an installed [mod](/docs/en/plugins/mods/overview) sets a model in its [`agent.spawn`](/docs/en/plugins/mods/reference#subagents) hook, Claude Code uses that model in place of the first source. |
|
v2.1.277CLAUDE_CODE_FORCE_TERMINAL_IMAGES |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_FORCE_TERMINAL_IMAGES, on Interface gallery for mods.
the line in the docsIf your mod's users see the dimmed text in a terminal that does draw those placeholder images, they can set [`CLAUDE_CODE_FORCE_TERMINAL_IMAGES`](/docs/en/env-vars) to `1`, which skips detection. Inside tmux or screen that doesn't help: th… |
|
v2.1.267pane:shrink |
Documentation arrivedAnthropic's documentation has since written up pane:shrink, on Customize keyboard shortcuts.
the line in the docs| `pane:shrink` | Ctrl+X Right, Ctrl+X Down | Give the pane less room: width when it sits beside the transcript, height when it sits above the prompt | |
|
v2.1.267pane:grow |
Documentation arrivedAnthropic's documentation has since written up pane:grow, on Customize keyboard shortcuts.
the line in the docs| `pane:grow` | Ctrl+X Left, Ctrl+X Up | Give the pane more room: width when it sits beside the transcript, height when it sits above the prompt | |
|
v2.1.265pane:top |
Documentation arrivedAnthropic's documentation has since written up pane:top, on Customize keyboard shortcuts.
the line in the docs| `pane:top` | Home | Jump to the top of the pane | |
|
v2.1.265pane:pageDown |
Documentation arrivedAnthropic's documentation has since written up pane:pageDown, on Customize keyboard shortcuts.
the line in the docs| `pane:pageDown` | PageDown | Scroll the pane down a page | |
|
v2.1.265pane:pageUp |
Documentation arrivedAnthropic's documentation has since written up pane:pageUp, on Customize keyboard shortcuts.
the line in the docs| `pane:pageUp` | PageUp | Scroll the pane up a page | |