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 |
|---|---|---|
v2.1.260scope_on_refresh |
Documentation arrivedAnthropic's documentation has since written up scope_on_refresh, on Claude apps gateway deployment and operations.
the line in the docs| Log: `refresh failed request_id=<id>: invalid_token (…) (at userinfo_no_id_token, …)`, and developers see `Cloud gateway session expired` every `session.ttl_hours` | The IdP accepted the refresh token but returned no id\_token with it, s… |
|
v2.1.274CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS, on Claude apps gateway deployment and operations.
the line in the docs* **The drain window**: set the `CLAUDE_GATEWAY_DRAIN_TIMEOUT_MS` environment variable on the gateway container to a positive whole number of milliseconds, such as `120000`. The gateway ignores a value in any other form, such as `120s`, an… |
|
v2.1.274listen.trusted_proxies |
Documentation arrivedAnthropic's documentation has since written up listen.trusted_proxies, on Claude apps gateway deployment and operations.
the line in the docs* **The gateway can't see past your load balancer.** Without [`listen.trusted_proxies`](/docs/en/claude-apps-gateway-config#listen), every developer appears to come from the load balancer's address and shares one limit. Set it before anyth… |
|
v2.1.268X-Forwarded-For |
Documentation arrivedAnthropic's documentation has since written up X-Forwarded-For, on Claude apps gateway deployment and operations.
the line in the docs* **The gateway can't see past your load balancer.** Without [`listen.trusted_proxies`](/docs/en/claude-apps-gateway-config#listen), every developer appears to come from the load balancer's address and shares one limit. Set it before anyth… |
|
v2.1.274connect_timeout_seconds |
Documentation arrivedAnthropic's documentation has since written up connect_timeout_seconds, on Claude apps gateway configuration.
the line in the docs| `connect_timeout_seconds` | No | Seconds the gateway waits when it opens a Postgres connection. A whole number from `1` to `60`, default `5`. Raise it if connection attempts time out when a new gateway instance starts. Requires Claude Co… |
|
v2.1.265telemetry.forward_to |
Documentation arrivedAnthropic's documentation has since written up telemetry.forward_to, on Claude apps gateway configuration.
the line in the docs| `provider: anthropic` upstreams, Workload Identity Federation token exchange, `telemetry.forward_to` exports | Resolved and checked locally, then `CONNECT` to the checked IP address through the proxy. A telemetry collector listed in `NO_… |
|
v2.1.275ANTHROPIC_DEFAULT_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_DEFAULT_MODEL, on Roll out an LLM gateway for your organization.
the line in the docs| Default model and aliases | The model that new sessions start on by default, and the models that aliases such as `opus` and `sonnet` resolve to, are [built into each version](/docs/en/model-config#pin-models-for-third-party-deployments) … |
|
v2.1.259ANTHROPIC_DEFAULT_MODEL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_DEFAULT_MODEL, on Roll out an LLM gateway for your organization.
the line in the docs| Default model and aliases | The model that new sessions start on by default, and the models that aliases such as `opus` and `sonnet` resolve to, are [built into each version](/docs/en/model-config#pin-models-for-third-party-deployments) … |
|
v2.1.248DISABLE_UPDATES |
Documentation arrivedAnthropic's documentation has since written up DISABLE_UPDATES, on Roll out an LLM gateway for your organization.
the line in the docsSome Claude Code behavior is built into the installed version rather than set at your gateway, so moving developers to a new release can change behavior across your deployment even when the gateway configuration hasn't changed. To control … |
|
v2.1.257modelOverrides |
Documentation arrivedAnthropic's documentation has since written up modelOverrides, on Claude Code gateway compatibility guide.
the line in the docs* **Capabilities**: to give a gateway alias the capabilities of the model behind it, map that model's Anthropic ID to your alias with a [`modelOverrides`](/docs/en/errors#unrecognized-model-id-on-a-request) entry in the settings you distri… |
|
v2.1.274apiKeyHelper |
Documentation arrivedAnthropic's documentation has since written up apiKeyHelper, on Claude Code gateway compatibility guide.
the line in the docs| Model for [background tasks](/docs/en/costs#background-token-usage) unless `ANTHROPIC_DEFAULT_HAIKU_MODEL` pins one | The default Sonnet model, or the main model once one is selected, as the [Amazon Bedrock](/docs/en/amazon-bedrock#4-pin… |
|
v2.1.271CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS, on Claude Code gateway compatibility guide.
the line in the docs| `anthropic-beta` values sent | The subset Amazon Bedrock and Agent Platform accept | The full set described under [feature pass-through](#feature-pass-through), unless the developer sets [`CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS`](#disabl… |
|
v2.1.261CLAUDE_CODE_USE_BEDROCK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_USE_BEDROCK, on Claude Code gateway compatibility guide.
the line in the docs* **Amazon Bedrock or Agent Platform format**: the developer sets `CLAUDE_CODE_USE_BEDROCK=1` with `ANTHROPIC_BEDROCK_BASE_URL`, or `CLAUDE_CODE_USE_VERTEX=1` with `ANTHROPIC_VERTEX_BASE_URL`, pointing at your gateway. Claude Code uses tha… |
|
v2.1.237ANTHROPIC_VERTEX_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_VERTEX_BASE_URL, on Claude Code gateway compatibility guide.
the line in the docs* **Amazon Bedrock or Agent Platform format**: the developer sets `CLAUDE_CODE_USE_BEDROCK=1` with `ANTHROPIC_BEDROCK_BASE_URL`, or `CLAUDE_CODE_USE_VERTEX=1` with `ANTHROPIC_VERTEX_BASE_URL`, pointing at your gateway. Claude Code uses tha… |
|
v2.1.237ANTHROPIC_BEDROCK_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_BEDROCK_BASE_URL, on Claude Code gateway compatibility guide.
the line in the docs* **Amazon Bedrock or Agent Platform format**: the developer sets `CLAUDE_CODE_USE_BEDROCK=1` with `ANTHROPIC_BEDROCK_BASE_URL`, or `CLAUDE_CODE_USE_VERTEX=1` with `ANTHROPIC_VERTEX_BASE_URL`, pointing at your gateway. Claude Code uses tha… |
|
v2.1.275act |
Documentation arrivedA small documentation edit on Environment variables touched a line naming act after this was published.
the line in the docs| `CLAUDE_CODE_AUTO_MODE_SERVER` | Controls whether Claude Code asks the server to [review auto mode actions](/docs/en/permission-modes#server-side-classifier-review). When unset, Claude Code asks the server on Amazon Bedrock, Google Cloud… |
|
v2.1.271CLAUDE_CODE_AUTO_MODE_SERVER |
Documentation arrivedA small documentation edit on Environment variables touched a line naming CLAUDE_CODE_AUTO_MODE_SERVER after this was published.
the line in the docs| `CLAUDE_CODE_AUTO_MODE_SERVER` | Controls whether Claude Code asks the server to [review auto mode actions](/docs/en/permission-modes#server-side-classifier-review). When unset, Claude Code asks the server on Amazon Bedrock, Google Cloud… |
|
v2.1.274--agent |
Documentation arrivedAnthropic's documentation has since written up --agent, on multiagent-orchestration.
the line in the docs--agent "$coordinator_id" \ |
|
v2.1.248--project |
Documentation arrivedAnthropic's documentation has since written up --project, on cmek-google-cloud-kms.
the line in the docs* **Domain restricted sharing:** the `constraints/iam.allowedPolicyMemberDomains` org policy can strip the Anthropic service account binding (see the earlier note). Confirm the binding is present with `gcloud kms keys get-iam-policy <your-… |
|
v2.1.275claude-opus-5 |
Documentation arrivedAnthropic's documentation has since written up claude-opus-5, on claude-in-microsoft-foundry.
the line in the docs| Claude Opus 5 | `claude-opus-5` | ✓ | ✓ | |
|
v2.1.271omitClaudeMd |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming omitClaudeMd after this was published.
the line in the docs* **CLAUDE.md files**: every level of the [CLAUDE.md hierarchy](/docs/en/memory#how-claude-md-files-load) the main conversation loads, including `~/.claude/CLAUDE.md`, project rules, `CLAUDE.local.md`, managed policy files, and any [`AGENT… |
|
v2.1.271omitClaudeMd |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming omitClaudeMd after this was published.
the line in the docs* **CLAUDE.md files**: every level of the [CLAUDE.md hierarchy](/docs/en/memory#how-claude-md-files-load) the main conversation loads, including `~/.claude/CLAUDE.md`, project rules, `CLAUDE.local.md`, managed policy files, and any [`AGENT… |
|
v2.1.271omitClaudeMd |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming omitClaudeMd after this was published.
the line in the docs* **CLAUDE.md files**: every level of the [CLAUDE.md hierarchy](/docs/en/memory#how-claude-md-files-load) the main conversation loads, including `~/.claude/CLAUDE.md`, project rules, `CLAUDE.local.md`, managed policy files, and any [`AGENT… |
|
v2.1.275bunfig.toml |
Documentation arrivedAnthropic's documentation has since written up bunfig.toml, on Plugins reference.
the line in the docs* If a `bunfig.toml` sits beside the bun lockfile, remove the `bunfig.toml`, or replace the bun lockfile with an npm lockfile. |
|
v2.1.275replace |
Documentation arrivedAnthropic's documentation has since written up replace, on How Claude remembers your project.
the line in the docs* **A `CLAUDE.md` that tells Claude in words to read `AGENTS.md`**: Claude sees `AGENTS.md` only if it decides to open the file. Delete the `CLAUDE.md` so Claude reads `AGENTS.md` directly, or replace the sentence with an `@AGENTS.md` impo… |
|
v2.1.265InstructionsLoaded |
Documentation arrivedAnthropic's documentation has since written up InstructionsLoaded, on How Claude remembers your project.
the line in the docs* Your [`InstructionsLoaded` hooks](/docs/en/hooks#instructionsloaded) don't fire when Claude reads it directly. They fire as usual when a `CLAUDE.md` imports or symlinks to it |
|
v2.1.259claudeMd |
Documentation arrivedAnthropic's documentation has since written up claudeMd, on How Claude remembers your project.
the line in the docs* Exclude it with [`claudeMdExcludes`](#exclude-specific-claude-md-files) |
|
v2.1.275act |
Documentation arrivedAnthropic's documentation has since written up act, on How Claude remembers your project.
the line in the docs* **You have none of those**: Claude reads every `AGENTS.md` and `.claude/AGENTS.md` in your working directory and the directories above it. In an interactive session you see a line such as `no CLAUDE.md found; AGENTS.md loaded: /home/you/… |
|
v2.1.275disabled |
Documentation arrivedAnthropic's documentation has since written up disabled, on How Claude remembers your project.
the line in the docsReading `AGENTS.md` directly requires Claude Code v2.1.277 or later. In some sessions, such as those on Amazon Bedrock or with telemetry disabled, Claude [can't read `AGENTS.md`](#when-agents-md-support-is-unavailable), so [import it from … |
|
v2.1.265.cursorrules |
Documentation arrivedAnthropic's documentation has since written up .cursorrules, on How Claude remembers your project.
the line in the docs* Cursor rules in `.cursor/rules/` or `.cursorrules` |
|
v2.1.265.cursor |
Documentation arrivedAnthropic's documentation has since written up .cursor, on How Claude remembers your project.
the line in the docs* Cursor rules in `.cursor/rules/` or `.cursorrules` |
|
v2.1.246/init |
Documentation arrivedAnthropic's documentation has since written up /init, on How Claude remembers your project.
the line in the docsRunning [`/init`](/docs/en/commands) reads other tools' instruction files and incorporates the relevant parts into the generated `CLAUDE.md`: |
|
v2.1.275append |
Documentation arrivedAnthropic's documentation has since written up append, on How Claude remembers your project.
the line in the docsYou can also run [`/import`](/docs/en/commands) to bring a supported coding agent's configuration into Claude Code, which appends a one-time copy of instruction files such as `AGENTS.md` to the matching `CLAUDE.md` and carries over MCP ser… |
|
v2.1.275replace |
Documentation arrivedA small documentation edit on Run Claude Code behind a corporate launcher touched a line naming replace after this was published.
the line in the docs* A session you start yourself in a terminal, which runs however you invoked it. To cover these sessions, put a script named `claude` in a directory earlier on `PATH` that runs your launcher with the real binary; don't replace the managed … |
|
v2.1.275AGENTS.md |
Documentation arrivedA small documentation edit on Explore the context window touched a line naming AGENTS.md after this was published.
the line in the docs* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on their own or alongside CLAUDE.md. Your own setup may add mo… |
|
v2.1.274AGENTS.md |
Documentation arrivedA small documentation edit on Explore the context window touched a line naming AGENTS.md after this was published.
the line in the docs* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on their own or alongside CLAUDE.md. Your own setup may add mo… |
|
v2.1.275append |
Documentation arrivedA small documentation edit on Explore the context window touched a line naming append after this was published.
the line in the docs* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on their own or alongside CLAUDE.md. Your own setup may add mo… |
|
v2.1.275CLAUDE.md |
Documentation arrivedA small documentation edit on Explore the context window touched a line naming CLAUDE.md after this was published.
the line in the docs* **Before you type anything**: CLAUDE.md, auto memory, MCP tool names, and skill descriptions all load into context. [AGENTS.md files](/docs/en/memory#agents-md) can load too, on their own or alongside CLAUDE.md. Your own setup may add mo… |
|
v2.1.275AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, on Explore the .claude directory.
the line in the docstips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific tasks, move it to a <A href="/docs/en/skills">skill</A> or a path-scope… |
|
v2.1.275CLAUDE.md |
Documentation arrivedAnthropic's documentation has since written up CLAUDE.md, on Explore the .claude directory.
the line in the docstips: ['Target under 200 lines. Longer files still load in full but may reduce adherence', <>CLAUDE.md loads into every session. If something only matters for specific tasks, move it to a <A href="/docs/en/skills">skill</A> or a path-scope… |
|
v2.1.261taskOutputMaxChars |
Documentation arrivedAnthropic's documentation has since written up taskOutputMaxChars, on Claude Code changelog.
the line in the docs* Removed the deprecated TaskOutput tool; Claude reads a background task's output file with Read instead, and the `taskOutputMaxChars` setting and `TASK_MAX_OUTPUT_LENGTH` no longer have any effect |
|
v2.1.261taskOutputMaxChars |
Documentation arrivedAnthropic's documentation has since written up taskOutputMaxChars, on Claude Code changelog.
the line in the docs* Removed the deprecated TaskOutput tool; Claude reads a background task's output file with Read instead, and the `taskOutputMaxChars` setting and `TASK_MAX_OUTPUT_LENGTH` no longer have any effect |
|
v2.1.265CLAUDE_GATEWAY_ALLOW_LOOPBACK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_ALLOW_LOOPBACK, on Claude Code changelog.
the line in the docs* Improved the Claude apps gateway's loopback error messages to name `CLAUDE_GATEWAY_ALLOW_LOOPBACK` |
|
v2.1.243CLAUDE_GATEWAY_ALLOW_LOOPBACK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_ALLOW_LOOPBACK, on Claude Code changelog.
the line in the docs* Improved the Claude apps gateway's loopback error messages to name `CLAUDE_GATEWAY_ALLOW_LOOPBACK` |
|
v2.1.238CLAUDE_GATEWAY_ALLOW_LOOPBACK |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_GATEWAY_ALLOW_LOOPBACK, on Claude Code changelog.
the line in the docs* Improved the Claude apps gateway's loopback error messages to name `CLAUDE_GATEWAY_ALLOW_LOOPBACK` |
|
v2.1.247chat:queueSubmit |
Documentation arrivedAnthropic's documentation has since written up chat:queueSubmit, on Claude Code changelog.
the line in the docs* Fixed Enter on a selected agent panel row doing nothing when `keybindings.json` rebinds Enter in the Chat context, for example to `chat:queueSubmit` |
|
v2.1.274claude update |
Documentation arrivedAnthropic's documentation has since written up claude update, on Claude Code changelog.
the line in the docs* Fixed update checks erroring every 30 minutes, and `claude update` hanging when a minimum or maximum version is set, if a proxy returns an invalid version; a malformed `minimumVersion` is now ignored |
|
v2.1.274AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, on Claude Code changelog.
the line in the docs* Added AGENTS.md support: in a project with no CLAUDE.md, Claude Code reads AGENTS.md instead; change it under "Project instructions" in `/config` (not yet on Bedrock, Vertex or Foundry) |
|
v2.1.273design |
Documentation arrivedA small documentation edit on Share session output as artifacts touched a line naming design after this was published.
the line in the docsClaude applies a built-in design skill when it builds an artifact, so pages get a deliberate palette, typography, and layout without extra prompting. That skill also looks for an existing design system in your project before choosing its o… |
|
v2.1.274diff |
Documentation arrivedA small documentation edit on Use Claude Science on more than one computer touched a line naming diff after this was published.
the line in the docsClaude Science keeps the work from each sign-in in its own folder on your computer. When you sign in to a different organization or personal account on that computer (for example, a Team plan after a personal plan), a banner at the top of … |