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 |
|---|---|---|
v2.1.304allowedDomains |
Documentation arrivedAnthropic's documentation has since written up allowedDomains, on secure-deployment.
the line in the docsSet `allowed_domains` (java, php: `allowedDomains`; csharp, go: `AllowedDomains`) on `web_fetch` to the sites the agent needs. Any URL the agent fetches can carry data to the site it points to, so this list is a security control. On `web_s… |
|
v2.1.305/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Create the app registration that represents the Claude API audience..
the line in the docscurl -sS "https://login.microsoftonline.com/$AZURE_TENANT_ID/oauth2/v2.0/token" \ |
|
v2.1.295x-should-retry |
Documentation arrivedA small documentation edit on compliance-errors touched a line naming x-should-retry after this was published.
the line in the docsA 500 without the `x-should-retry: false` header is transient: retry with exponential backoff (start at 1 second, double up to 60 seconds). The same applies to 502, 503, 504, and 529 responses. The exception is a small set of local session… |
|
v2.1.305--debug |
Documentation arrivedAnthropic's documentation has since written up --debug, on using.
the line in the docs| `--debug` | Print full HTTP request and response to stderr | |
|
v2.1.280prefix_mismatch_behavior |
Documentation arrivedA small documentation edit on compaction-thinking-blocks touched a line naming prefix_mismatch_behavior after this was published.
the line in the docsThe `prefix_mismatch_behavior` field needs the `thinking-binding-controls-2026-08-01` beta header in addition to the [`compact-2026-09-04` beta header](https://platform.claude.com/docs/en/build-with-claude/compaction-on-demand#request-a-su… |
|
v2.1.285compactBeforeNextTurn |
Documentation arrivedAnthropic's documentation has since written up compactBeforeNextTurn, on compaction-on-demand.
the line in the docsThe SDK [tool runner](https://platform.claude.com/docs/en/agents-and-tools/tool-use/tool-runner) in Python, TypeScript, C#, Go, Java, PHP, and Ruby can send the compaction request for you. When you decide to compact, call `compact_before_n… |
|
v2.1.305/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on web-search-tool.
the line in the docsTo protect shared capacity, the Batches API throttles web search requests for each organization, so large batches with many searches might take longer to complete. You can see your organization's web search rate limit on the [Rate limits](… |
|
v2.1.305/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on web-search-tool.
the line in the docsTo protect shared capacity, the Batches API throttles web search requests for each organization, so large batches with many searches might take longer to complete. You can see your organization's web search rate limit on the [Rate limits](… |
|
v2.1.305/usage |
Documentation arrivedAnthropic's documentation has since written up /usage, on web-search-tool.
the line in the docsTo protect shared capacity, the Batches API throttles web search requests for each organization, so large batches with many searches might take longer to complete. You can see your organization's web search rate limit on the [Rate limits](… |
|
v2.1.305/config |
Documentation arrivedAnthropic's documentation has since written up /config, on concepts.
the line in the docs| **Proxy** | Anthropic's routing component. Terminates inner TLS, validates that upstream IPs fall within an allowed range, and routes each request to an upstream MCP server based on hostname. | `mcp-proxy` (image name, Compose service na… |
|
v2.1.305/claude-api |
Documentation arrivedAnthropic's documentation has since written up /claude-api, on claude-api-skill.
the line in the docs* **Onboarding flow:** An interview-driven walkthrough for setting up a new Managed Agent, available through the `/claude-api managed-agents-onboard` subcommand |
|
v2.1.305/effort |
Documentation arrivedAnthropic's documentation has since written up /effort, on customer-support-chat.
the line in the docsFor customer support chat, Claude Opus 5.5 is well suited to balance intelligence, latency, and cost, including the most complex support scenarios that require deep reasoning across long, multistep conversations. However, for instances whe… |
|
v2.1.280requestMessages |
Documentation arrivedAnthropic's documentation has since written up requestMessages, on fallback-credit.
the line in the docsList<BetaMessageParam> requestMessages = [new BetaUserMessageParam { Content = "Hello, Claude" }]; |
|
v2.1.302strictKnownMarketplaces |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming strictKnownMarketplaces after this was published.
the line in the docsWherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/docs/en/settings-reference#blockedmarketplaces) lists itself whe… |
|
v2.1.282blockedMarketplaces |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming blockedMarketplaces after this was published.
the line in the docsWherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/docs/en/settings-reference#blockedmarketplaces) lists itself whe… |
|
v2.1.282blockedMarketplaces |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming blockedMarketplaces after this was published.
the line in the docsWherever the session runs, claude.ai applies the admin console's [`strictKnownMarketplaces`](/docs/en/settings-reference#strictknownmarketplaces) and [`blockedMarketplaces`](/docs/en/settings-reference#blockedmarketplaces) lists itself whe… |
|
v2.1.304/loop |
Documentation arrivedAnthropic's documentation has since written up /loop, on Manage multiple agents with agent view.
the line in the docs| v2.1.295 | `Ctrl+C` at the idle prompt of an [attached background session](#attach-to-a-session) leaves the pending wakeup of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval) alone, so pressing it twice det… |
|
v2.1.304/loop |
Documentation arrivedAnthropic's documentation has since written up /loop, on Manage multiple agents with agent view.
the line in the docs| v2.1.295 | `Ctrl+C` at the idle prompt of an [attached background session](#attach-to-a-session) leaves the pending wakeup of a [self-paced `/loop`](/docs/en/scheduled-tasks#let-claude-choose-the-interval) alone, so pressing it twice det… |
|
v2.1.302enabledPlugins |
Documentation arrivedAnthropic's documentation has since written up enabledPlugins, on Customize sessions in self-hosted environments.
the line in the docsEach repository's `CLAUDE.md` loads wherever the session starts. Outside a project thread, its skills load too. The runner passes every repository to Claude Code as an [additional directory](/docs/en/permissions#additional-directories-gran… |
|
v2.1.293skipDangerousModePermissionPrompt |
Documentation arrivedA small documentation edit on Connect Claude Code to tools via MCP touched a line naming skipDangerousModePermissionPrompt after this was published.
the line in the docsIn `claude -p` runs, [Agent SDK](/docs/en/headless) sessions, and [cloud sessions](/docs/en/claude-code-on-the-web) outside a [project](/docs/en/claude-projects#what-threads-pick-up-from-your-repositories), Claude Code can't show that prom… |
|
v2.1.302/exit |
Documentation arrivedAnthropic's documentation has since written up /exit, on Error reference.
the line in the docs* If a former teammate you resumed yourself with `claude --resume` got this refusal, nothing was sent. To end that session, run `/exit` at its prompt. |
|
v2.1.304--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Error reference.
the line in the docs* If a former teammate you resumed yourself with `claude --resume` got this refusal, nothing was sent. To end that session, run `/exit` at its prompt. |
|
v2.1.304CLAUDE_CODE_AUTO_COMPACT_WINDOW |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_AUTO_COMPACT_WINDOW, on Error reference.
the line in the docs| `CLAUDE_CODE_AUTO_COMPACT_WINDOW="<value>" reads as <N> tokens, so Claude Code treats it as the 100k minimum` | [Values and warnings for `CLAUDE_CODE_AUTO_COMPACT_WINDOW`](/docs/en/model-config#claude_code_auto_compact_window-values) | |
|
v2.1.304CLAUDE_CODE_AUTO_COMPACT_WINDOW |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_AUTO_COMPACT_WINDOW, on Error reference.
the line in the docs| `CLAUDE_CODE_AUTO_COMPACT_WINDOW="<value>" reads as <N> tokens, so Claude Code treats it as the 100k minimum` | [Values and warnings for `CLAUDE_CODE_AUTO_COMPACT_WINDOW`](/docs/en/model-config#claude_code_auto_compact_window-values) | |
|
v2.1.295ui.notify |
Documentation arrivedAnthropic's documentation has since written up ui.notify, on Use the mods API.
the line in the docs| `$.ui.notify(text)` | A notification from their terminal, outside Claude Code, sent the way their [`preferredNotifChannel`](/docs/en/settings-reference#preferrednotifchannel) setting says. The mod's name is its title unless you pass a no… |
|
v2.1.295ui.notify |
Documentation arrivedA small documentation edit on Intercept and control agent behavior with hooks touched a line naming ui.notify after this was published.
the line in the docs* `plugin_notification` when a [mod](/docs/en/plugins/mods/api#show-something-without-starting-a-turn) calls `$.ui.notify` |
|
v2.1.304cleanupPeriodDays |
Documentation arrivedAnthropic's documentation has since written up cleanupPeriodDays, on Hooks reference.
the line in the docsThere is no timeout or retry limit. The session remains on disk until you resume it, subject to the [`cleanupPeriodDays`](/docs/en/settings-reference#cleanupperioddays) retention sweep, which deletes session files after 30 days by default,… |
|
v2.1.304--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Model configuration.
the line in the docs* Levels above the cap aren't offered in the `/effort` picker, and naming a higher level with `--effort` or `/effort` runs at the cap instead. If you start a plain-text `--print` run with `--effort` above the cap, a warning on stderr names… |
|
v2.1.299--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.299--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.296--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.281--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.281--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.281--disallowed-tools |
Documentation arrivedAnthropic's documentation has since written up --disallowed-tools, on Error reference.
the line in the docs* Fix the rule at its source, which the full warning names in parentheses: a settings file path, or the flag itself for `--allowed-tools` and `--disallowed-tools`. A `claude-settings-<hash>.json` path that doesn't exist on disk stands for … |
|
v2.1.301CLAUDE_CODE_TMPDIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_TMPDIR, on Error reference.
the line in the docs* Delete files you no longer need on the filesystem that holds Claude Code's temp directory. If your message doesn't name that directory, look up its default location in the [`CLAUDE_CODE_TMPDIR`](/docs/en/env-vars) reference. For `EDQUOT`… |
|
v2.1.290CLAUDE_CODE_TMPDIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_TMPDIR, on Error reference.
the line in the docs* Delete files you no longer need on the filesystem that holds Claude Code's temp directory. If your message doesn't name that directory, look up its default location in the [`CLAUDE_CODE_TMPDIR`](/docs/en/env-vars) reference. For `EDQUOT`… |
|
v2.1.287CLAUDE_CODE_TMPDIR |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_TMPDIR, on Error reference.
the line in the docs* Delete files you no longer need on the filesystem that holds Claude Code's temp directory. If your message doesn't name that directory, look up its default location in the [`CLAUDE_CODE_TMPDIR`](/docs/en/env-vars) reference. For `EDQUOT`… |
|
v2.1.304/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.304claude auth login |
Documentation arrivedAnthropic's documentation has since written up claude auth login, on Error reference.
the line in the docsEach of these messages from `/login`, `claude auth login`, or `claude setup-token` means Claude Code couldn't open the port on `127.0.0.1` where your browser returns the sign-in result. |
|
v2.1.299allowed_tools |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming allowed_tools after this was published.
the line in the docsAllow rules accept tool-name globs only after a literal `mcp__<server>__` prefix. The server segment must be glob-free so the rule names a specific server you configured: `mcp__puppeteer__*` matches every tool from the `puppeteer` server, … |
|
v2.1.304/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Connect to external tools with MCP.
the line in the docsTo choose the first-turn wait yourself, set `CLAUDE_CODE_MCP_STARTUP_WAIT_MS` in the [`env` option](/docs/en/agent-sdk/configuration#set-environment-variables), for example `CLAUDE_CODE_MCP_STARTUP_WAIT_MS: "5000"`. The first turn then wai… |
|
v2.1.304alwaysLoad |
Documentation arrivedAnthropic's documentation has since written up alwaysLoad, on Connect to external tools with MCP.
the line in the docs* **Otherwise, with [tool search](/docs/en/agent-sdk/tool-search) on, which is the default**: the first turn waits up to 2 seconds, and only for pending servers that set [`alwaysLoad: true`](/docs/en/mcp#exempt-a-server-from-deferral) or t… |
|
v2.1.299literal |
Documentation arrivedA small documentation edit on All settings touched a line naming literal after this was published.
the line in the docsBraces match as ordinary characters in a name, so `~/data/{keys,tokens}` covers a directory literally named `{keys,tokens}`, not two alternatives. To cover `~/data/keys` and `~/data/tokens`, add each as its own entry. |
|
v2.1.285context_management |
Documentation arrivedA small documentation edit on Connect Claude Code to an LLM gateway touched a line naming context_management after this was published.
the line in the docs| `400` errors naming `context_management`, `Extra inputs are not permitted`, or other unrecognized fields | The gateway forwards requests to an upstream that rejects fields Claude Code sends to Anthropic-format endpoints | Set `CLAUDE_COD… |
|
v2.1.299deniedModels |
Documentation arrivedAnthropic's documentation has since written up deniedModels, on Claude apps gateway configuration.
the line in the docs* **Deny-lists and hook arrays**: `permissions.deny`, `permissions.ask`, `disabledMcpjsonServers`, `deniedMcpServers`, `blockedMarketplaces`, `deniedModels`, and every `hooks` event-type array. These take the union of base and policy, so a… |