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 |
|---|---|---|
v2.1.299SendMessage |
Documentation arrivedAnthropic's documentation has since written up SendMessage, on Agent SDK reference - TypeScript.
the line in the docsA `peer` origin identifies which agent sent the message: an in-process [teammate](/docs/en/agent-teams) sending to `main` with `SendMessage`, or a [cross-session peer](/docs/en/cross-session-messaging), another of your Claude Code sessions… |
|
v2.1.299SendMessage |
Documentation arrivedAnthropic's documentation has since written up SendMessage, on Agent SDK reference - TypeScript.
the line in the docsA `peer` origin identifies which agent sent the message: an in-process [teammate](/docs/en/agent-teams) sending to `main` with `SendMessage`, or a [cross-session peer](/docs/en/cross-session-messaging), another of your Claude Code sessions… |
|
v2.1.299can_use_tool |
Documentation arrivedAnthropic's documentation has since written up can_use_tool, on Agent SDK reference - Python.
the line in the docs> Commands running with `dangerouslyDisableSandbox: True` have full system access. Ensure your `can_use_tool` handler validates these requests carefully. |
|
v2.1.292dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Agent SDK reference - Python.
the line in the docs> Commands running with `dangerouslyDisableSandbox: True` have full system access. Ensure your `can_use_tool` handler validates these requests carefully. |
|
v2.1.296_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on Configure permissions.
the line in the docsTools that require user interaction behave the same way: `AskUserQuestion` and MCP tools whose server sets [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) always fall through to the callbac… |
|
v2.1.295_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on Configure permissions.
the line in the docsTools that require user interaction behave the same way: `AskUserQuestion` and MCP tools whose server sets [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) always fall through to the callbac… |
|
v2.1.295_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on Configure permissions.
the line in the docsTools that require user interaction behave the same way: `AskUserQuestion` and MCP tools whose server sets [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) always fall through to the callbac… |
|
v2.1.295_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on Configure permissions.
the line in the docsTools that require user interaction behave the same way: `AskUserQuestion` and MCP tools whose server sets [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) always fall through to the callbac… |
|
v2.1.295_meta |
Documentation arrivedAnthropic's documentation has since written up _meta, on Configure permissions.
the line in the docsTools that require user interaction behave the same way: `AskUserQuestion` and MCP tools whose server sets [`_meta["anthropic/requiresUserInteraction"]`](/docs/en/mcp#require-approval-for-a-specific-tool) always fall through to the callbac… |
|
v2.1.301initialize |
Documentation arrivedAnthropic's documentation has since written up initialize, on Connect to external tools with MCP.
the line in the docsAn SDK MCP server registered by an [`initialize` control request](/docs/en/agent-sdk/typescript#sdkcontrolinitializeresponse) begins connecting as soon as Claude Code processes the request. |
|
v2.1.285list_directory |
Documentation arrivedAnthropic's documentation has since written up list_directory, on Connect to external tools with MCP.
the line in the docsallowedTools: ["mcp__filesystem__read_file", "mcp__filesystem__list_directory"] |
|
v2.1.299send_message |
Documentation arrivedAnthropic's documentation has since written up send_message, on Connect to external tools with MCP.
the line in the docs"mcp__slack__send_message" // Only send_message from slack server |
|
v2.1.299send_message |
Documentation arrivedAnthropic's documentation has since written up send_message, on Connect to external tools with MCP.
the line in the docs"mcp__slack__send_message" // Only send_message from slack server |
|
v2.1.300transcript_path |
Documentation arrivedAnthropic's documentation has since written up transcript_path, on Intercept and control agent behavior with hooks.
the line in the docsprint(f" Transcript: {input_data['agent_transcript_path']}") |
|
v2.1.300transcript_path |
Documentation arrivedAnthropic's documentation has since written up transcript_path, on Intercept and control agent behavior with hooks.
the line in the docsprint(f" Transcript: {input_data['agent_transcript_path']}") |
|
v2.1.284transcript_path |
Documentation arrivedAnthropic's documentation has since written up transcript_path, on Intercept and control agent behavior with hooks.
the line in the docsprint(f" Transcript: {input_data['agent_transcript_path']}") |
|
v2.1.299hookSpecificOutput |
Documentation arrivedAnthropic's documentation has since written up hookSpecificOutput, on Intercept and control agent behavior with hooks.
the line in the docs"hookSpecificOutput": { |
|
v2.1.295structuredContent |
Documentation arrivedAnthropic's documentation has since written up structuredContent, on Give Claude custom tools.
the line in the docs> The Python `@tool` decorator forwards only `content` and `is_error` from the handler's return dict. To return `structuredContent` from Python, run a [standalone MCP server](/docs/en/agent-sdk/mcp) instead of an in-process SDK server. |
|
v2.1.293ANTHROPIC_FOUNDRY_BASE_URL |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_FOUNDRY_BASE_URL, on Deploy Claude Desktop on 3P with Microsoft Foundry.
the line in the docs> Set this only when the app reaches Foundry through a gateway or proxy you run, such as Azure API Management. Requests go to `<value>/v1/messages` instead of `https://<resource>.services.ai.azure.com/anthropic/v1/messages`, carrying the s… |
|
v2.1.285disableBundledSkills |
Documentation arrivedAnthropic's documentation has since written up disableBundledSkills, on Configuration changelog.
the line in the docs| [`disableBundledSkills`](/docs/third-party/claude-desktop/configuration#disablebundledskills) | `boolean` | Disable bundled skills and workflows | |
|
v2.1.293credentialHelper |
Documentation arrivedAnthropic's documentation has since written up credentialHelper, on Configuration changelog.
the line in the docs"credentialKind": "<anonymous|userGit|credentialHelper|inferenceCredential>" |
|
v2.1.281manifestSha256 |
Documentation arrivedAnthropic's documentation has since written up manifestSha256, on Configuration changelog.
the line in the docs| [`allowedPluginMarketplaces[].manifestSha256`](/docs/third-party/claude-desktop/configuration#allowedpluginmarketplaces) | `string` | New subfield (beta): SHA-256 of the exact hosted `marketplace.json` a `url` marketplace may serve; requ… |
|
v2.1.300headersHelper |
Documentation arrivedAnthropic's documentation has since written up headersHelper, on Configuration changelog.
the line in the docs"headersHelper": "<string>" |
|
v2.1.299headersHelper |
Documentation arrivedAnthropic's documentation has since written up headersHelper, on Configuration changelog.
the line in the docs"headersHelper": "<string>" |
|
v2.1.293disableConfigDeprecationWarnings |
Documentation arrivedAnthropic's documentation has since written up disableConfigDeprecationWarnings, on Configuration changelog.
the line in the docs| [`disableConfigDeprecationWarnings`](/docs/third-party/claude-desktop/configuration#disableconfigdeprecationwarnings) | `boolean` | Hide configuration deprecation warnings | |
|
v2.1.281egressProxyPacUrl |
Documentation arrivedAnthropic's documentation has since written up egressProxyPacUrl, on Configuration changelog.
the line in the docs| [`egressProxyPacUrl`](/docs/third-party/claude-desktop/configuration#egressproxypacurl) | `string` | Proxy auto-config (PAC) URL | |
|
v2.1.281egressProxyUrl |
Documentation arrivedAnthropic's documentation has since written up egressProxyUrl, on Configuration changelog.
the line in the docs| [`egressProxyUrl`](/docs/third-party/claude-desktop/configuration#egressproxyurl) | `string` | Proxy server URL | |
|
v2.1.293inferenceFoundryBaseUrl |
Documentation arrivedAnthropic's documentation has since written up inferenceFoundryBaseUrl, on Configuration changelog.
the line in the docs* `inferenceFoundryResource` now requires the user's consent when delivered by a bootstrap URL the user configured themselves (`consentRequired`), as `inferenceFoundryBaseUrl` and the other providers' endpoint settings already do; declinin… |
|
v2.1.300inferenceGatewayAuthScheme |
Documentation arrivedAnthropic's documentation has since written up inferenceGatewayAuthScheme, on Configuration changelog.
the line in the docs* The deprecation notices for these spellings, which stopped being accepted on October 7, 2026 and are listed under v1.40609.0: header maps written as a string or list, `inferenceGatewayAuthScheme: "auto"`, `ask-session`, the older `manage… |
|
v2.1.293redirectHost |
Documentation arrivedAnthropic's documentation has since written up redirectHost, on Deploy with a bootstrap server.
the line in the docs> | `redirectHost` | `enum` | — | Use localhost only if your IdP’s registered redirect URI specifies it. One of: `127.0.0.1`, `localhost`. | |
|
v2.1.302/config |
Documentation arrivedA small documentation edit on Deploy with MDM touched a line naming /config after this was published.
the line in the docs* The update keys `disableAutoUpdates`, `autoUpdaterEnforcementHours`, `updateViaUpdatesHost`, and [`releaseChannel`](/docs/third-party/claude-desktop/configuration#releasechannel). |
|
v2.1.287autoUpdate |
Documentation arrivedA small documentation edit on Deploy with MDM touched a line naming autoUpdate after this was published.
the line in the docs* The update keys `disableAutoUpdates`, `autoUpdaterEnforcementHours`, `updateViaUpdatesHost`, and [`releaseChannel`](/docs/third-party/claude-desktop/configuration#releasechannel). |
|
v2.1.281autoUpdate |
Documentation arrivedA small documentation edit on Deploy with MDM touched a line naming autoUpdate after this was published.
the line in the docs* The update keys `disableAutoUpdates`, `autoUpdaterEnforcementHours`, `updateViaUpdatesHost`, and [`releaseChannel`](/docs/third-party/claude-desktop/configuration#releasechannel). |
|
v2.1.281autoUpdate |
Documentation arrivedA small documentation edit on Deploy with MDM touched a line naming autoUpdate after this was published.
the line in the docs* The update keys `disableAutoUpdates`, `autoUpdaterEnforcementHours`, `updateViaUpdatesHost`, and [`releaseChannel`](/docs/third-party/claude-desktop/configuration#releasechannel). |
|
v2.1.293external-idp |
Documentation arrivedAnthropic's documentation has since written up external-idp, on Configuration reference.
the line in the docs`inference-credential` adds `Authorization: Bearer <token>` to every export, using the token the app currently holds for the inference provider, with no helper script to deploy. The collector must accept that token as issued: an identity-p… |
|
v2.1.300CLAUDE_CODE_EXTRA_BODY |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_EXTRA_BODY, on Connect Claude Code to Claude for Government.
the line in the docs"Settings"="{\"forceLoginMethod\":\"gateway\",\"forceLoginGatewayUrl\":\"https://<claude-for-government-host>/gateway-api\",\"env\":{\"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\":\"1\",\"DISABLE_TELEMETRY\":\"1\",\"DISABLE_ERROR_REPORTING\"… |
|
v2.1.287ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_HEADERS, on Connect Claude Code to Claude for Government.
the line in the docs"Settings"="{\"forceLoginMethod\":\"gateway\",\"forceLoginGatewayUrl\":\"https://<claude-for-government-host>/gateway-api\",\"env\":{\"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\":\"1\",\"DISABLE_TELEMETRY\":\"1\",\"DISABLE_ERROR_REPORTING\"… |
|
v2.1.287ANTHROPIC_CUSTOM_HEADERS |
Documentation arrivedAnthropic's documentation has since written up ANTHROPIC_CUSTOM_HEADERS, on Connect Claude Code to Claude for Government.
the line in the docs"Settings"="{\"forceLoginMethod\":\"gateway\",\"forceLoginGatewayUrl\":\"https://<claude-for-government-host>/gateway-api\",\"env\":{\"CLAUDE_CODE_DISABLE_NONESSENTIAL_TRAFFIC\":\"1\",\"DISABLE_TELEMETRY\":\"1\",\"DISABLE_ERROR_REPORTING\"… |
|
v2.1.300autoCompactWindow |
Documentation arrivedA small documentation edit on Create custom subagents touched a line naming autoCompactWindow after this was published.
the line in the docsTo make one subagent compact earlier than it otherwise would, set `autoCompactWindow` in its [frontmatter](#supported-frontmatter-fields) to a token count from `100000` to `1000000`. If you set [`CLAUDE_CODE_AUTO_COMPACT_WINDOW`](/docs/en/… |
|
v2.1.300--settings |
Documentation arrivedAnthropic's documentation has since written up --settings, on All settings.
the line in the docs* **Scope**: [`User or managed`](#scopes). Claude Code reads the key from managed settings. It reads the key from user settings only on a machine with no managed settings, in a session whose credential isn't a Team or Enterprise `/login`. … |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT, on All settings.
the line in the docs* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT`, `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`, `CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT`, and `CLAUDE_CODE_DISABLE_MOUNTED_DRIVE_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code r… |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT, on All settings.
the line in the docs* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT`, `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`, `CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT`, and `CLAUDE_CODE_DISABLE_MOUNTED_DRIVE_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code r… |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT, on All settings.
the line in the docs* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT`, `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`, `CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT`, and `CLAUDE_CODE_DISABLE_MOUNTED_DRIVE_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code r… |
|
v2.1.300/goal |
Documentation arrivedAnthropic's documentation has since written up /goal, on Run prompts on a schedule.
the line in the docs* **Keeping the session working turn after turn toward a condition rather than on an interval**: see [`/goal`](/docs/en/goal). |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |
|
v2.1.299CronCreate |
Documentation arrivedAnthropic's documentation has since written up CronCreate, on Use the mods API.
the line in the docs| [`$.tool.call`](/docs/en/plugins/mods/reference#mods-api-methods) of Bash with `run_in_background: true`, Monitor, or CronCreate | Resolves with `{ deny: '<tool> was not run: it starts background work, a schedule or a goal, and <reason>'… |