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 |
|---|---|---|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285allowedProviders |
Documentation arrivedA small documentation edit on Set up Claude Code for your organization touched a line naming allowedProviders after this was published.
the line in the docs| [Provider restrictions](/docs/en/settings-reference#allowedproviders) | Limit which API providers a machine may use. A session on a provider that isn't listed is refused at startup, at login, and when it next contacts the API. Requires C… |
|
v2.1.285/model |
Documentation arrivedA small documentation edit on migration-guide touched a line naming /model after this was published.
the line in the docsOn the Claude API, Claude Fable 5.1 and Claude Mythos 5.1 read Claude Opus 5.5 thinking blocks; no other model does. A router or fallback that moves a conversation from Claude Opus 5.5 to any other model runs those turns without them. In t… |
|
v2.1.281SessionEnd |
Documentation arrivedAnthropic's documentation has since written up SessionEnd, on Sessions.
the line in the docs- `stop_reason: BetaManagedAgentsSessionEndTurn or BetaManagedAgentsSessionRequiresAction or BetaManagedAgentsSessionRetriesExhausted or 2 more` |
|
v2.1.283plugin_errors |
Documentation arrivedAnthropic's documentation has since written up plugin_errors, on Organization.
the line in the docs- `plugin_errors: array of BetaPluginMarketplaceValidationPluginError` |
|
v2.1.285availableModels |
Documentation arrivedAnthropic's documentation has since written up availableModels, on Deploy Claude apps gateway on AWS.
the line in the docscli: {availableModels: [platform-claude-opus-4-8], enforceAvailableModels: true} |
|
v2.1.281assume_role |
Documentation arrivedAnthropic's documentation has since written up assume_role, on Claude apps gateway configuration.
the line in the docsAlso grant `bedrock:ApplyGuardrail` on the guardrail to the principal that signs this upstream's requests: the gateway's AWS principal, or with [`assume_role`](#bedrock-in-another-aws-account) the role named in `role_arn`. |
|
v2.1.281assume_role |
Documentation arrivedAnthropic's documentation has since written up assume_role, on Claude apps gateway configuration.
the line in the docsAlso grant `bedrock:ApplyGuardrail` on the guardrail to the principal that signs this upstream's requests: the gateway's AWS principal, or with [`assume_role`](#bedrock-in-another-aws-account) the role named in `role_arn`. |
|
v2.1.283DO_NOT_TRACK |
Documentation arrivedAnthropic's documentation has since written up DO_NOT_TRACK, on Command line settings.
the line in the docs`DO_NOT_TRACK`, set to any value other than `0` or `false`, turns usage analytics and error reports off. It is the same switch as `disable_telemetry = true` in the configuration file. `GITHUB_TOKEN` (or `GH_TOKEN`) is optional and is used … |
|
v2.1.284/loop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /loop after this was published.
the line in the docs* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#seven-day-expiry) and one-shot tasks whose scheduled time ha… |
|
v2.1.284/loop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /loop after this was published.
the line in the docs* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#seven-day-expiry) and one-shot tasks whose scheduled time ha… |
|
v2.1.284/loop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /loop after this was published.
the line in the docs* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#seven-day-expiry) and one-shot tasks whose scheduled time ha… |
|
v2.1.284/loop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /loop after this was published.
the line in the docs* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#seven-day-expiry) and one-shot tasks whose scheduled time ha… |
|
v2.1.283/loop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /loop after this was published.
the line in the docs* When you resume a session with `claude --resume` or `claude --continue`, Claude Code restores the tasks scheduled with `CronCreate`, except recurring tasks that have [expired](#seven-day-expiry) and one-shot tasks whose scheduled time ha… |
|
v2.1.285/desktop |
Documentation arrivedA small documentation edit on Run prompts on a schedule touched a line naming /desktop after this was published.
the line in the docsTasks are session-scoped. When you resume with `--resume` or `--continue`, Claude Code restores tasks that haven't [expired](#seven-day-expiry), except those listed under [Limitations](#limitations). For scheduling that survives independen… |
|
v2.1.285/ultrareview |
Documentation arrivedAnthropic's documentation has since written up /ultrareview, on Claude Code changelog.
the line in the docs* Removed the browser link from `/ultrareview` and `claude ultrareview` output |
|
v2.1.285/artifacts |
Documentation arrivedAnthropic's documentation has since written up /artifacts, on Claude Code changelog.
the line in the docs* Changed list screens (`/artifacts`, `/mcp`, `/skills`, `/hooks` and others) to always line up each row's details in one column after the names |
|
v2.1.285timeout |
Documentation arrivedAnthropic's documentation has since written up timeout, on Claude Code changelog.
the line in the docs* Changed `--bare` to connect only the MCP servers named on the command line, send the model no system reminders, and start no background tasks; under `--bare`, a shell command that reaches its timeout now stops instead of moving to the ba… |
|
v2.1.285timeout |
Documentation arrivedAnthropic's documentation has since written up timeout, on Claude Code changelog.
the line in the docs* Changed `--bare` to connect only the MCP servers named on the command line, send the model no system reminders, and start no background tasks; under `--bare`, a shell command that reaches its timeout now stops instead of moving to the ba… |
|
v2.1.285/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Claude Code changelog.
the line in the docs* Fixed `/plugin`'s Discover tab showing a marketplace name unquoted in its "Checking … for new plugins" line when its rows already show that name in quotes |
|
v2.1.281attribution |
Documentation arrivedAnthropic's documentation has since written up attribution, on Claude Code changelog.
the line in the docs* Fixed the commit attribution reminder being re-sent inside tool output when a model fallback lasts only one turn |
|
v2.1.281attribution |
Documentation arrivedAnthropic's documentation has since written up attribution, on Claude Code changelog.
the line in the docs* Fixed the commit attribution reminder being re-sent inside tool output when a model fallback lasts only one turn |
|
v2.1.285/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Claude Code changelog.
the line in the docs* Fixed `/compact`, `/clear`, and `/rewind` typed while viewing a background agent's or teammate's transcript silently acting on the main conversation: a dialog now names the target and asks first |
|
v2.1.285/status |
Documentation arrivedAnthropic's documentation has since written up /status, on Claude Code changelog.
the line in the docs* Fixed `/status` listing an Anthropic profile beside an API key as if both were in effect; the profile is now marked as not in use |
|
v2.1.285/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Claude Code changelog.
the line in the docs* Fixed macOS sessions still showing "Not logged in" or "Login expired" after `/login` succeeds in another Claude Code window when a leftover `~/.claude/.credentials.json` exists |
|
v2.1.285--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Claude Code changelog.
the line in the docs* Fixed `claude --resume` and `--continue` sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed |
|
v2.1.285--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Claude Code changelog.
the line in the docs* Fixed `claude --resume` and `--continue` sometimes losing every turn after a batch of parallel tool calls when the earlier session crashed or was killed |
|
v2.1.285--resume |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming --resume after this was published.
the line in the docsSchedules a prompt to run on a 5-field cron schedule in local time. Set `recurring` to `false` to fire once at the next match. Jobs are session-scoped by default, and resuming with `--resume` or `--continue` restores jobs that haven't expi… |
|
v2.1.285--resume |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming --resume after this was published.
the line in the docsSchedules a prompt to run on a 5-field cron schedule in local time. Set `recurring` to `false` to fire once at the next match. Jobs are session-scoped by default, and resuming with `--resume` or `--continue` restores jobs that haven't expi… |
|
v2.1.285/model |
Documentation arrivedAnthropic's documentation has since written up /model, on overview.
the line in the docs* We announced the deprecation of the Claude Sonnet 4.5 model (`claude-sonnet-4-5-20250929`), with retirement on the Claude API scheduled for November 30, 2026. We recommend migrating to [Claude Sonnet 5.5](https://platform.claude.com/docs… |
|
v2.1.283_host |
Documentation arrivedA small documentation edit on github touched a line naming _host after this was published.
the line in the docsThen create a session that mounts the GitHub repository. A `limited` [environment](https://platform.claude.com/docs/en/managed-agents/environments#networking) blocks an agent's MCP servers unless its networking sets `allow_mcp_servers: tru… |
|
v2.1.285/memory |
Documentation arrivedAnthropic's documentation has since written up /memory, on cmek.
the line in the docs* [Claude Managed Agents](https://platform.claude.com/docs/en/managed-agents/overview) (beta) data, including agent configurations, environments, webhooks, sessions and their events, [memory stores](https://platform.claude.com/docs/en/mana… |
|
v2.1.285claude-sonnet-5 |
Documentation arrivedAnthropic's documentation has since written up claude-sonnet-5, on model-deprecations.
the line in the docs| claude-sonnet-5-5 | Active | N/A | Not sooner than September 28, 2027 | |
|
v2.1.283anthropic-skills: |
Documentation arrivedAnthropic's documentation has since written up anthropic-skills:, on Extend Claude with skills.
the line in the docs| A [skill synced from claude.ai](#how-synced-skills-behave) | `Skill(anthropic-skills:deploy)` | That skill when Claude Desktop delivers it to a session as a plugin | |
|
v2.1.283anthropic-skills: |
Documentation arrivedAnthropic's documentation has since written up anthropic-skills:, on Extend Claude with skills.
the line in the docs| A [skill synced from claude.ai](#how-synced-skills-behave) | `Skill(anthropic-skills:deploy)` | That skill when Claude Desktop delivers it to a session as a plugin | |
|
v2.1.281/skills |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming /skills after this was published.
the line in the docs* A `Skill(skill:<name>)` deny rule instead [matches the skill under any of its names](/docs/en/skills#restrict-claude’s-skill-access), such as its alias or display name |
|
v2.1.278--verbose |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming --verbose after this was published.
the line in the docs* Run with [`--verbose`](/docs/en/cli-reference) to see the exact parameter names and values in each tool call |
|
v2.1.278--verbose |
Documentation arrivedA small documentation edit on Configure permissions touched a line naming --verbose after this was published.
the line in the docs* Run with [`--verbose`](/docs/en/cli-reference) to see the exact parameter names and values in each tool call |
|
v2.1.284run_in_background |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming run_in_background after this was published.
the line in the docs"timeout": int | None, # Milliseconds. Foreground: capped at 600000 by default, higher values are clamped. With run_in_background (Claude Code v2.1.285 or later): the background time limit, 1800000 when omitted, capped at 7200000 unless ra… |
|
v2.1.280run_in_background |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming run_in_background after this was published.
the line in the docs"timeout": int | None, # Milliseconds. Foreground: capped at 600000 by default, higher values are clamped. With run_in_background (Claude Code v2.1.285 or later): the background time limit, 1800000 when omitted, capped at 7200000 unless ra… |
|
v2.1.257run_in_background |
Documentation arrivedA small documentation edit on Agent SDK reference - Python touched a line naming run_in_background after this was published.
the line in the docs"timeout": int | None, # Milliseconds. Foreground: capped at 600000 by default, higher values are clamped. With run_in_background (Claude Code v2.1.285 or later): the background time limit, 1800000 when omitted, capped at 7200000 unless ra… |
|
v2.1.274MCP_SDK_GENERATION |
Documentation arrivedAnthropic's documentation has since written up MCP_SDK_GENERATION, on Error reference.
the line in the docs* To connect without changing the server, start Claude Code with [`MCP_SDK_GENERATION=v1`](/docs/en/env-vars), whose [runtime](/docs/en/mcp#mcp-client-runtimes) doesn't apply this rule and sends the token request over plain HTTP. That choi… |
|
v2.1.281disableSideloadFlags |
Documentation arrivedAnthropic's documentation has since written up disableSideloadFlags, on Desktop application.
the line in the docsLocal and cloud sessions also load the skills enabled for your claude.ai account, except local sessions when your organization sets [`disableSideloadFlags`](/docs/en/settings-reference#disablesideloadflags). Cloud sessions load them instea… |
|
v2.1.281guardrail |
Documentation arrivedA small documentation edit on How the agent loop works touched a line naming guardrail after this was published.
the line in the docs| `"auto"` | Uses a model classifier to review actions such as shell commands and network requests, allowing or blocking each one it reviews. See [Auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for availability and … |
|
v2.1.281guardrail |
Documentation arrivedA small documentation edit on How the agent loop works touched a line naming guardrail after this was published.
the line in the docs| `"auto"` | Uses a model classifier to review actions such as shell commands and network requests, allowing or blocking each one it reviews. See [Auto mode](/docs/en/permission-modes#eliminate-prompts-with-auto-mode) for availability and … |
|
v2.1.280request_id |
Documentation arrivedA small documentation edit on wif-reference touched a line naming request_id after this was published.
the line in the docs`POST /v1/oauth/token` returns errors in the standard [API error shape](https://platform.claude.com/docs/en/api/errors). The SDK wraps exchange failures in a typed `WorkloadIdentityError` (python, typescript; ruby: `Anthropic::Credentials:… |