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 |
|---|---|---|
v2.1.248disableAutoMode |
Documentation arrivedAnthropic's documentation has since written up disableAutoMode, on Changelog.
the line in the docs* Changed `autoModeEnabled`: unless it is `false`, new Code tab sessions now start in Auto mode where the selected model supports it, and when the key is not set the Code tab now offers Auto mode (previously only when it was `true`). Cowor… |
|
v2.1.281allowedPluginMarketplaces |
Documentation arrivedAnthropic's documentation has since written up allowedPluginMarketplaces, on Changelog.
the line in the docs* Changed `allowedPluginMarketplaces`: a `url` marketplace's `credentialHelper` can print a JSON object of HTTP headers (the form a managed MCP server's `headersHelper` prints), which are sent on every request to that marketplace, in addit… |
|
v2.1.281--settings |
Documentation arrivedAnthropic's documentation has since written up --settings, on Claude Code changelog.
the line in the docs* Changed `sandbox.excludedCommands` to ignore project and local settings entries when managed settings or `--settings` set `allowUnsandboxedCommands: false`, or managed `allowManagedDomainsOnly: true` |
|
v2.1.281CLAUDE_CODE_AUTO_MODE_SERVER |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_AUTO_MODE_SERVER, on Claude Code changelog.
the line in the docs* Changed auto mode to use the server-side classifier by default on a direct Anthropic API connection when telemetry is off (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out) |
|
v2.1.281CLAUDE_CODE_AUTO_MODE_SERVER |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_AUTO_MODE_SERVER, on Claude Code changelog.
the line in the docs* Changed auto mode to use the server-side classifier by default on a direct Anthropic API connection when telemetry is off (`CLAUDE_CODE_AUTO_MODE_SERVER=0` opts out) |
|
v2.1.281/install-github-app |
Documentation arrivedAnthropic's documentation has since written up /install-github-app, on Claude Code changelog.
the line in the docs* Fixed `/install-github-app` saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done |
|
v2.1.281/install-github-app |
Documentation arrivedAnthropic's documentation has since written up /install-github-app, on Claude Code changelog.
the line in the docs* Fixed `/install-github-app` saying "cancelled" and then still pushing the branch and saving the API key secret; leaving now stops the remaining steps and reports what was already done |
|
v2.1.281claude remote-control |
Documentation arrivedAnthropic's documentation has since written up claude remote-control, on Claude Code changelog.
the line in the docs* Fixed `claude remote-control --debug` failing with "Unknown argument: --debug", although Remote Control's own eligibility error says to run with `--debug` |
|
v2.1.281--add-dir |
Documentation arrivedAnthropic's documentation has since written up --add-dir, on Claude Code changelog.
the line in the docs* Fixed repository, user and `--add-dir` skills, commands and skills-directory plugin manifests pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly` |
|
v2.1.281--add-dir |
Documentation arrivedAnthropic's documentation has since written up --add-dir, on Claude Code changelog.
the line in the docs* Fixed repository, user and `--add-dir` skills, commands and skills-directory plugin manifests pre-approving their own tools via `allowed-tools` under managed `allowManagedPermissionRulesOnly` |
|
v2.1.281attribution |
Documentation arrivedAnthropic's documentation has since written up attribution, on Claude Code changelog.
the line in the docs* Fixed managed `permissions`, `autoMode`, `worktree` and `attribution` settings being ignored entirely when one nested value was invalid; the rest of the block now still applies |
|
v2.1.257/Network |
Documentation arrivedAnthropic's documentation has since written up /Network, on Claude Code changelog.
the line in the docs* Fixed CLAUDE.md and rules being read at startup through a repository symlink reaching macOS's `/Network` via `..` or a `/.vol`-style kernel path, or a rules link to macOS's `/home` being listed |
|
v2.1.281--tools |
Documentation arrivedAnthropic's documentation has since written up --tools, on Claude Code changelog.
the line in the docs* Fixed continued or resumed conversations losing earlier extended thinking when relaunched with a `--tools` list that leaves out a built-in tool offered earlier in the conversation |
|
v2.1.281/artifacts |
Documentation arrivedAnthropic's documentation has since written up /artifacts, on Claude Code changelog.
the line in the docs* Fixed earlier extended thinking being dropped when `/model`, `/rename`, `/artifacts` or another immediate slash command was used while Claude was working |
|
v2.1.281/artifacts |
Documentation arrivedAnthropic's documentation has since written up /artifacts, on Claude Code changelog.
the line in the docs* Fixed earlier extended thinking being dropped when `/model`, `/rename`, `/artifacts` or another immediate slash command was used while Claude was working |
|
v2.1.281--continue |
Documentation arrivedAnthropic's documentation has since written up --continue, on Claude Code changelog.
the line in the docs* Fixed more cases of continued or resumed sessions (`--continue`, `--resume`) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning |
|
v2.1.281--resume |
Documentation arrivedAnthropic's documentation has since written up --resume, on Claude Code changelog.
the line in the docs* Fixed more cases of continued or resumed sessions (`--continue`, `--resume`) re-sending earlier messages in a changed form, which could make the API drop Claude's earlier reasoning |
|
v2.1.280refused |
Documentation arrivedA small documentation edit on handle-streaming-refusals touched a line naming refused after this was published.
the line in the docsUsage metrics are still provided in the response, even when the response is refused. Whether a refused request is billed depends on when the refusal arrives and its category; see [How refusals are billed](https://platform.claude.com/docs/e… |
|
v2.1.280frontier_llm |
Documentation arrivedA small documentation edit on Or, for the model with the same capabilities and no access approval requirement: touched a line naming frontier_llm after this was published.
the line in the docsA refusal that arrives before any output is billed when its category is `"bio"`, `"frontier_llm"`, or `"reasoning_extraction"`. A refusal before any output in any other category, or with a `null` category, is not billed ([How refusals are … |
|
v2.1.268scale |
Documentation arrivedA small documentation edit on whats-new-fable-5-1 touched a line naming scale after this was published.
the line in the docs* **Billing:** a refusal that arrives before any output is billed when it's in a category with low volumes of false positives, to disrupt attempts to circumvent Anthropic's safeguards at scale ([How refusals are billed](https://platform.cl… |
|
v2.1.281/mcp |
Documentation arrivedA small documentation edit on vaults touched a line naming /mcp after this was published.
the line in the docsTo diagnose why a refresh failed, call `POST /v1/vaults/{vault_id}/credentials/{credential_id}/mcp_oauth_validate` (or `client.beta.vaults.credentials.mcp_oauth_validate(...)` (typescript: `client.beta.vaults.credentials.mcpOAuthValidate(.… |
|
v2.1.281/memory |
Documentation arrivedAnthropic's documentation has since written up /memory, on spawn.sh: called once per claimed work item.
the line in the docsSessions on a self-hosted environment attach [memory stores](https://platform.claude.com/docs/en/managed-agents/memory) exactly as sessions on cloud environments do: list them in `resources` when you create the session, as shown in [Attach… |
|
v2.1.273audience |
Documentation arrivedA small documentation edit on aws touched a line naming audience after this was published.
the line in the docsCall `GetWebIdentityToken` with `https://api.anthropic.com` as the audience, then pass the result to the SDK's federation credentials. Because `identity_token_provider` (typescript, php: `identityTokenProvider`; csharp: `IdentityTokenProvi… |
|
v2.1.280Restart |
Documentation arrivedAnthropic's documentation has since written up Restart, on inference-hooks.
the line in the docs* **Cowork.** The user edits the denied message if it is their latest one. The edit resends attached files, and **Restart from here** resends the whole message unchanged. If the content is in a file or an earlier message, the user selects … |
|
v2.1.281/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on inference-hooks.
the line in the docs* **Claude Code.** The user runs `/rewind` and selects the prompt that first brought the content in. If asked, they select **Restore conversation**, then edit or clear the prompt that returns to the input field. `/clear` starts over. See [… |
|
v2.1.281/batch |
Documentation arrivedA small documentation edit on thinking touched a line naming /batch after this was published.
the line in the docsThe SDKs require streaming when `max_tokens` is greater than 21,333, to avoid HTTP timeouts on long-running requests. This is a client-side validation, not an API restriction. If you don't need to process events incrementally, use `.stream… |
|
v2.1.281required |
Documentation arrivedA small documentation edit on structured-outputs touched a line naming required after this was published.
the line in the docs**Migrating from beta?** The `output_format` parameter has moved to `output_config.format`, and beta headers are no longer required. The `output_format` parameter is deprecated and will be removed in the future. To use it anyway, add the `… |
|
v2.1.280frontier_llm |
Documentation arrivedAnthropic's documentation has since written up frontier_llm, on refusals-and-fallback.
the line in the docs| `"frontier_llm"` | The request could assist the development of competing AI models, which is restricted under [Anthropic's commercial terms](https://www.anthropic.com/legal/commercial-terms). Benign machine learning work can also trigger… |
|
v2.1.281mcp_tool |
Documentation arrivedAnthropic's documentation has since written up mcp_tool, on mid-conversation-system-messages.
the line in the docs`tool_addition` and `tool_removal` are content blocks in the `content` array of a `role: "system"` message, and they can be mixed with `text` blocks in the same message. The message follows the placement rules for any mid-conversation syst… |
|
v2.1.281/mcp |
Documentation arrivedAnthropic's documentation has since written up /mcp, on mid-conversation-system-messages.
the line in the docs`tool_addition` and `tool_removal` are content blocks in the `content` array of a `role: "system"` message, and they can be mixed with `text` blocks in the same message. The message follows the placement rules for any mid-conversation syst… |
|
v2.1.281required |
Documentation arrivedAnthropic's documentation has since written up required, on cache-diagnostics.
the line in the docsInclude the `diagnostics` object on every turn. The object is the opt-in: the API stores a fingerprint only for requests that include it. On the first turn, pass `"previous_message_id": null` to opt in without a prior message to compare ag… |
|
v2.1.280request_id |
Documentation arrivedAnthropic's documentation has since written up request_id, on Compliance API.
the line in the docs- `request_id: string` |
|
v2.1.280preview |
Documentation arrivedA small documentation edit on Archive a Dream touched a line naming preview after this was published.
the line in the docsThe Dreams API is in research preview: the request and response shapes are volatile and may change without the deprecation period that applies to generally-available endpoints. |
|
v2.1.281/model |
Documentation arrivedAnthropic's documentation has since written up /model, on optimizing-for-cost-and-intelligence.
the line in the docs| You want agent runs to finish sooner | Tell the model that time matters, and show it the elapsed time; on DRACO, HLE, and an internal physics set, runs took 33% to 69% less time at a 28% to 54% lower cost per task, with scores up to 1.9 … |
|
v2.1.281/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Create and distribute a plugin marketplace.
the line in the docs* **The claude.ai admin console**: Claude Code enforces both lists in the sessions that [read server-managed settings](/docs/en/managed-settings#where-and-when-a-policy-applies). claude.ai also checks them when anyone in your organization … |
|
v2.1.281/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Create and distribute a plugin marketplace.
the line in the docs* **The claude.ai admin console**: Claude Code enforces both lists in the sessions that [read server-managed settings](/docs/en/managed-settings#where-and-when-a-policy-applies). claude.ai also checks them when anyone in your organization … |
|
v2.1.277blockedMarketplaces |
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… |
|
v2.1.277blockedMarketplaces |
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… |
|
v2.1.277blockedMarketplaces |
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… |
|
v2.1.277strictKnownMarketplaces |
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… |
|
v2.1.277strictKnownMarketplaces |
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… |
|
v2.1.277strictKnownMarketplaces |
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… |
|
v2.1.281/plugin |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming /plugin 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… |
|
v2.1.281/plugin |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming /plugin 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… |
|
v2.1.281/model |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming /model 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… |
|
v2.1.280refused |
Documentation arrivedAnthropic's documentation has since written up refused, on optimizing-for-cost-and-intelligence.
the line in the docs9. **GPQA Diamond:** Rein et al., "GPQA: A Graduate-Level Google-Proof Q\&A Benchmark," 2023. The 198-question Diamond subset, two runs per configuration, run August 7, 2026 (Claude Opus 5.5: September 19, 2026), model-graded against refer… |
|
v2.1.277managed-only |
Documentation arrivedAnthropic's documentation has since written up managed-only, on How Claude remembers your project.
the line in the docs3. Type `/config` in your session to open the settings panel and confirm **Project instructions** isn't set to `claude-md` or `managed-only`. If you don't see the setting there at all, your session is one that [can't load `AGENTS.md`](#whe… |
|
v2.1.280AGENTS.md |
Documentation arrivedAnthropic's documentation has since written up AGENTS.md, 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 Claude [can't read `AGENTS.md`](#when-agents-md-support-is-unavailable), so [import it from a `CLAUDE.md`](#share-one-file-with-other-coding-tools) there… |
|
v2.1.280/memory |
Documentation arrivedA small documentation edit on Glossary touched a line naming /memory after this was published.
the line in the docsA markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions without you adding a second file. You can change the **Project … |
|
v2.1.2772.1.277 |
Documentation arrivedA small documentation edit on Glossary touched a line naming 2.1.277 after this was published.
the line in the docsA markdown file of project instructions you write for AI coding agents. If your repository has one and no [CLAUDE.md](#claude-md), Claude reads it as your project instructions without you adding a second file. You can change the **Project … |