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 |
|---|---|---|
v2.1.251tengu_juniper_relay |
Flag reading movedThe flag server now returns off for tengu_juniper_relay, read as this account. | |
v2.1.287CLAUDE_CODE_USE_POWERSHELL_TOOL |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_USE_POWERSHELL_TOOL, on Error reference.
the line in the docsDenying Bash also turns off the PowerShell tool, so Claude has neither. To use PowerShell, set CLAUDE_CODE_USE_POWERSHELL_TOOL=1. |
|
v2.1.288modelOverrides |
Documentation arrivedAnthropic's documentation has since written up modelOverrides, on Claude Code on Amazon Bedrock.
the line in the docsFor aliases, version prefixes, and `modelOverrides` entries, see [Pin models for third-party deployments](/docs/en/model-config#pin-models-for-third-party-deployments). |
|
v2.1.286sdkMcpServerManifests |
Documentation arrivedAnthropic's documentation has since written up sdkMcpServerManifests, on Agent SDK reference - TypeScript.
the line in the docsThe request's `sdkMcpServerManifests` field and the response's `sdk_mcp_manifests_parked` field are for the in-process [SDK MCP servers](/docs/en/agent-sdk/custom-tools) you created with [`createSdkMcpServer()`](#createsdkmcpserver). Your … |
|
v2.1.265sdkMcpServerManifests |
Documentation arrivedAnthropic's documentation has since written up sdkMcpServerManifests, on Agent SDK reference - TypeScript.
the line in the docsThe request's `sdkMcpServerManifests` field and the response's `sdk_mcp_manifests_parked` field are for the in-process [SDK MCP servers](/docs/en/agent-sdk/custom-tools) you created with [`createSdkMcpServer()`](#createsdkmcpserver). Your … |
|
v2.1.265sdkMcpServerManifests |
Documentation arrivedAnthropic's documentation has since written up sdkMcpServerManifests, on Agent SDK reference - TypeScript.
the line in the docsThe request's `sdkMcpServerManifests` field and the response's `sdk_mcp_manifests_parked` field are for the in-process [SDK MCP servers](/docs/en/agent-sdk/custom-tools) you created with [`createSdkMcpServer()`](#createsdkmcpserver). Your … |
|
v2.1.265version_mismatch |
Documentation arrivedAnthropic's documentation has since written up version_mismatch, on Agent SDK reference - TypeScript.
the line in the docs| "protocol_version_mismatch" |
|
v2.1.286sdk_mcp_manifests_parked |
Documentation arrivedAnthropic's documentation has since written up sdk_mcp_manifests_parked, on Agent SDK reference - TypeScript.
the line in the docssdk_mcp_manifests_parked?: Record< |
|
v2.1.282managed-mcp.json |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming managed-mcp.json after this was published.
the line in the docs| `allowedMcpServers` | Enforced as an empty allowlist until the value is fixed, so no MCP servers that users add are admitted. Servers your organization delivers through [`managedMcpServers`](/docs/en/settings-reference#managedmcpservers)… |
|
v2.1.285allowedMcpServers |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming allowedMcpServers after this was published.
the line in the docs| `allowedMcpServers` | Enforced as an empty allowlist until the value is fixed, so no MCP servers that users add are admitted. Servers your organization delivers through [`managedMcpServers`](/docs/en/settings-reference#managedmcpservers)… |
|
v2.1.288--permission-mode |
Documentation arrivedAnthropic's documentation has since written up --permission-mode, on Best practices for Claude Code.
the line in the docs--permission-mode dontAsk |
|
v2.1.287CLAUDE_CODE_TRANSCRIPT_LOCAL_GC |
Documentation arrivedA small documentation edit on Manage sessions touched a line naming CLAUDE_CODE_TRANSCRIPT_LOCAL_GC after this was published.
the line in the docs| Limit how large a `-p` or Agent SDK session's transcript file grows | [`CLAUDE_CODE_TRANSCRIPT_LOCAL_GC`](/docs/en/env-vars) | Environment variable | |
|
v2.1.288OTEL_LOG_USER_PROMPTS |
Documentation arrivedAnthropic's documentation has since written up OTEL_LOG_USER_PROMPTS, on Monitoring.
the line in the docs| `new_context` | `claude_code.interaction` | The user prompt | `OTEL_LOG_USER_PROMPTS` | |
|
v2.1.288CLAUDE_CODE_AUTO_COMPACT_WINDOW |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming CLAUDE_CODE_AUTO_COMPACT_WINDOW after this was published.
the line in the docs* **The auto-compact window for a session**: a managed [`autoCompactWindow`](/docs/en/settings-reference#autocompactwindow) is a default too. The `--autocompact` flag and the `CLAUDE_CODE_AUTO_COMPACT_WINDOW` variable still set the [auto-c… |
|
v2.1.288autoCompactWindow |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming autoCompactWindow after this was published.
the line in the docs* **The auto-compact window for a session**: a managed [`autoCompactWindow`](/docs/en/settings-reference#autocompactwindow) is a default too. The `--autocompact` flag and the `CLAUDE_CODE_AUTO_COMPACT_WINDOW` variable still set the [auto-c… |
|
v2.1.288autoCompactWindow |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming autoCompactWindow after this was published.
the line in the docs* **The auto-compact window for a session**: a managed [`autoCompactWindow`](/docs/en/settings-reference#autocompactwindow) is a default too. The `--autocompact` flag and the `CLAUDE_CODE_AUTO_COMPACT_WINDOW` variable still set the [auto-c… |
|
v2.1.282autoCompact |
Documentation arrivedA small documentation edit on Deploy managed settings touched a line naming autoCompact after this was published.
the line in the docs* **The auto-compact window for a session**: a managed [`autoCompactWindow`](/docs/en/settings-reference#autocompactwindow) is a default too. The `--autocompact` flag and the `CLAUDE_CODE_AUTO_COMPACT_WINDOW` variable still set the [auto-c… |
|
v2.1.275session.end |
Documentation arrivedAnthropic's documentation has since written up session.end, on Mods reference.
the line in the docs| All `session.end` hooks together | As long as the [SessionEnd hook budget](/docs/en/hooks#sessionend-input), 1.5 seconds unless you change it, counted from when your settings `SessionEnd` hooks finish | |
|
v2.1.277prompt.edit |
Documentation arrivedAnthropic's documentation has since written up prompt.edit, on Mods reference.
the line in the docs| A hook's own execution time for one event, not counting time inside `next` or a mods API call other than `$.clock.sleep` | 10 seconds, or 50 milliseconds for a `prompt.edit` hook | |
|
v2.1.268ui.message |
Documentation arrivedA small documentation edit on Draw in the interface with a mod touched a line naming ui.message after this was published.
the line in the docs| `Client` | A region drawn by a second file of yours, for animation and pointer input. That file gets no mods API. It reaches your hooks by posting data, which arrives as a `ui.message` event. If it fails to load, draw, or run, your hooks… |
|
v2.1.267ui.message |
Documentation arrivedA small documentation edit on Draw in the interface with a mod touched a line naming ui.message after this was published.
the line in the docs| `Client` | A region drawn by a second file of yours, for animation and pointer input. That file gets no mods API. It reaches your hooks by posting data, which arrives as a `ui.message` event. If it fails to load, draw, or run, your hooks… |
|
v2.1.285/reload-plugins |
Documentation arrivedAnthropic's documentation has since written up /reload-plugins, on Plugin loading reference.
the line in the docs* **Relative-path plugins in a marketplace you added from a local path**: the plugin loads in place from its path inside the marketplace folder. Your edits to the source directory take effect at the next session start or `/reload-plugins`,… |
|
v2.1.288claude --cloud |
Documentation arrivedAnthropic's documentation has since written up claude --cloud, on Use Claude Code in the cloud.
the line in the docs`claude --cloud` and `claude --teleport` require sign-in with a claude.ai account. If you authenticate with an API key, or your stored account details are stale, you see one of these: |
|
v2.1.288CLAUDE_CODE_AUTO_COMPACT_WINDOW |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_AUTO_COMPACT_WINDOW, on Use Claude Code in the cloud.
the line in the docsTo change the auto-compact window instead, set [`CLAUDE_CODE_AUTO_COMPACT_WINDOW`](/docs/en/env-vars) in your environment variables, or run [`/autocompact`](/docs/en/commands#all-commands) with a token count in a session where the variable… |
|
v2.1.288/clear |
Documentation arrivedAnthropic's documentation has since written up /clear, on Use Claude Code in the cloud.
the line in the docs| `/clear` | No | Start a new session from the sidebar instead | |
|
v2.1.287/context |
Documentation arrivedAnthropic's documentation has since written up /context, on Use Claude Code in the cloud.
the line in the docs| `/context` | Yes | Shows what's currently in the context window | |
|
v2.1.288/config |
Documentation arrivedAnthropic's documentation has since written up /config, on Use Claude Code in the cloud.
the line in the docs* **`/config`**: in your browser at claude.ai/code, opens the Claude Code section of your settings instead of setting a value, and text after the command, including `key=value`, is ignored. To change a setting for a cloud session, set an [… |
|
v2.1.288/plugin |
Documentation arrivedAnthropic's documentation has since written up /plugin, on Use Claude Code in the cloud.
the line in the docsCloud sessions support [built-in commands](/docs/en/commands) that produce text output. Commands that only run in the terminal interface, such as `/plugin` or `/resume`, aren't available. Commands that open a picker or panel in the termina… |
|
v2.1.288/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Use Claude Code in the cloud.
the line in the docs* **You're authenticated via API key**: run `/login` to sign in with your claude.ai account instead |
|
v2.1.288/tp |
Documentation arrivedAnthropic's documentation has since written up /tp, on Use Claude Code in the cloud.
the line in the docs* **Using `/teleport`**: inside an existing CLI session, run `/teleport` or `/tp` to open the same session picker without restarting Claude Code. |
|
v2.1.288/teleport |
Documentation arrivedAnthropic's documentation has since written up /teleport, on Use Claude Code in the cloud.
the line in the docs* **Using `/teleport`**: inside an existing CLI session, run `/teleport` or `/tp` to open the same session picker without restarting Claude Code. |
|
v2.1.288permissionDecision |
Documentation arrivedAnthropic's documentation has since written up permissionDecision, on Hooks reference.
the line in the docs3. Returns `permissionDecision: "allow"` together with `updatedInput` that holds the answer, so the tool runs without prompting |
|
v2.1.281canUseTool |
Documentation arrivedAnthropic's documentation has since written up canUseTool, on Hooks reference.
the line in the docs`AskUserQuestion` and `ExitPlanMode` require user interaction. In [non-interactive mode](/docs/en/headless) with the `-p` flag, Claude Code offers them only when the run has a [permission host](/docs/en/headless#turn-off-permission-prompts… |
|
v2.1.281canUseTool |
Documentation arrivedAnthropic's documentation has since written up canUseTool, on Hooks reference.
the line in the docs`AskUserQuestion` and `ExitPlanMode` require user interaction. In [non-interactive mode](/docs/en/headless) with the `-p` flag, Claude Code offers them only when the run has a [permission host](/docs/en/headless#turn-off-permission-prompts… |
|
v2.1.285ExitPlanMode |
Documentation arrivedAnthropic's documentation has since written up ExitPlanMode, on Hooks reference.
the line in the docs`AskUserQuestion` and `ExitPlanMode` require user interaction. In [non-interactive mode](/docs/en/headless) with the `-p` flag, Claude Code offers them only when the run has a [permission host](/docs/en/headless#turn-off-permission-prompts… |
|
v2.1.287PostToolUse |
Documentation arrivedAnthropic's documentation has since written up PostToolUse, on Hooks reference.
the line in the docs| `if` | no | [Permission rule syntax](/docs/en/permissions#permission-rule-syntax) to filter when this hook runs, such as `"Bash(git *)"` or `"Edit(*.ts)"`. The hook command only runs if the tool call matches the pattern. See the [Bash ma… |
|
v2.1.281CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT |
Documentation arrivedA small documentation edit on All settings touched a line naming CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT after this was published.
the line in the docs* [`CLAUDE_CODE_DISABLE_DANGEROUS_RM_TIMEOUT`, `CLAUDE_CODE_DISABLE_SUBSTITUTION_RM_PROMPT`, and `CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT`](/docs/en/env-vars#variables), which Claude Code reads from the launch environment only, are igno… |
|
v2.1.288claude doctor |
Documentation arrivedA small documentation edit on Configure the sandboxed Bash tool touched a line naming claude doctor after this was published.
the line in the docs* **TLS termination**: the proxy substitutes the real value inside request contents, so it has to see them. Set [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) so the proxy terminates TLS itself. Without … |
|
v2.1.282claude doctor |
Documentation arrivedA small documentation edit on Configure the sandboxed Bash tool touched a line naming claude doctor after this was published.
the line in the docs* **TLS termination**: the proxy substitutes the real value inside request contents, so it has to see them. Set [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) so the proxy terminates TLS itself. Without … |
|
v2.1.261claude doctor |
Documentation arrivedA small documentation edit on Configure the sandboxed Bash tool touched a line naming claude doctor after this was published.
the line in the docs* **TLS termination**: the proxy substitutes the real value inside request contents, so it has to see them. Set [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) so the proxy terminates TLS itself. Without … |
|
v2.1.268network.tlsTerminate |
Documentation arrivedA small documentation edit on Configure the sandboxed Bash tool touched a line naming network.tlsTerminate after this was published.
the line in the docs* **TLS termination**: the proxy substitutes the real value inside request contents, so it has to see them. Set [`network.tlsTerminate`](/docs/en/settings-reference#sandbox-network-tlsterminate) so the proxy terminates TLS itself. Without … |
|
v2.1.288/plugin |
Documentation arrivedA small documentation edit on Troubleshoot plugins touched a line naming /plugin after this was published.
the line in the docs* **The skill sets `disable-model-invocation: true`**: the template skill in [Create your first plugin](/docs/en/plugins/create#create-your-first-plugin) sets it. Remove the line from a skill you want Claude to invoke on its own. [Control … |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT after this was published.
the line in the docsTo turn off the check on a critical path typed directly in a `-c` script, such as `~`, set [`CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT=1`](/docs/en/env-vars#variables) in the environment that launches Claude Code. |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT after this was published.
the line in the docsTo turn off the check on a critical path typed directly in a `-c` script, such as `~`, set [`CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT=1`](/docs/en/env-vars#variables) in the environment that launches Claude Code. |
|
v2.1.288CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT |
Documentation arrivedA small documentation edit on Choose a permission mode touched a line naming CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT after this was published.
the line in the docsTo turn off the check on a critical path typed directly in a `-c` script, such as `~`, set [`CLAUDE_CODE_DISABLE_INLINE_SHELL_RM_PROMPT=1`](/docs/en/env-vars#variables) in the environment that launches Claude Code. |
|
v2.1.287--json |
Documentation arrivedAnthropic's documentation has since written up --json, on Claude Code changelog.
the line in the docs* Fixed `claude plugin validate` failing an Anthropic marketplace's own plugin and listing a clean `plugin.json` in `--json` |
|
v2.1.287--json |
Documentation arrivedAnthropic's documentation has since written up --json, on Claude Code changelog.
the line in the docs* Fixed `claude plugin validate` failing an Anthropic marketplace's own plugin and listing a clean `plugin.json` in `--json` |
|
v2.1.269agent.spawn |
Documentation arrivedAnthropic's documentation has since written up agent.spawn, on Claude Code changelog.
the line in the docs* Added `agent.spawn` for teammates, one agent id across plugin hook events, and idle and waiting states in `$.agent.list()` |
|
v2.1.267agent.list |
Documentation arrivedAnthropic's documentation has since written up agent.list, on Claude Code changelog.
the line in the docs* Added `agent.spawn` for teammates, one agent id across plugin hook events, and idle and waiting states in `$.agent.list()` |
|
v2.1.206tengu_umber_kestrel |
Flag reading movedThe flag server now returns on for tengu_umber_kestrel, read as this account. |