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 |
|---|---|---|
v2.1.267/effort |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming /effort after this was published.
the line in the docsIf the session took its effort from your settings rather than from `--effort` or `/effort`, Claude Code reads your settings again each time it starts a process for the session. After you edit the saved effort in `settings.json`, the change… |
|
v2.1.242settings.json |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming settings.json after this was published.
the line in the docsIf the session took its effort from your settings rather than from `--effort` or `/effort`, Claude Code reads your settings again each time it starts a process for the session. After you edit the saved effort in `settings.json`, the change… |
|
v2.1.267--effort |
Documentation arrivedA small documentation edit on Manage multiple agents with agent view touched a line naming --effort after this was published.
the line in the docsIf the session took its effort from your settings rather than from `--effort` or `/effort`, Claude Code reads your settings again each time it starts a process for the session. After you edit the saved effort in `settings.json`, the change… |
|
v2.1.238initialize |
Documentation arrivedA small documentation edit on Agent SDK reference - TypeScript touched a line naming initialize after this was published.
the line in the docs* `true`: Claude Code registered the hooks. A session's first initialize returns this value. A repeated initialize sent over the CLI's stdin also returns `true`. In that case the hooks in the new request replace the hooks registered earlie… |
|
v2.1.247/hooks |
Documentation arrivedA small documentation edit on Choose a sandbox environment touched a line naming /hooks after this was published.
the line in the docs* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host. |
|
v2.1.246/hooks |
Documentation arrivedA small documentation edit on Choose a sandbox environment touched a line naming /hooks after this was published.
the line in the docs* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host. |
|
v2.1.246/hooks |
Documentation arrivedA small documentation edit on Choose a sandbox environment touched a line naming /hooks after this was published.
the line in the docs* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host. |
|
v2.1.242/hooks |
Documentation arrivedA small documentation edit on Choose a sandbox environment touched a line naming /hooks after this was published.
the line in the docs* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host. |
|
v2.1.242/hooks |
Documentation arrivedA small documentation edit on Choose a sandbox environment touched a line naming /hooks after this was published.
the line in the docs* [MCP](/docs/en/mcp) servers and [command hooks](/docs/en/hooks#command-hook-fields) are separate processes that run unconstrained on the host. |
|
v2.1.268dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Monitoring.
the line in the docs* For Bash tool: includes `bash_command`, `full_command`, `timeout`, `description`, and `dangerouslyDisableSandbox`, plus `git_commit_id` and `git_branch` when a `git commit` command succeeds. `git_commit_id` is the full commit SHA when th… |
|
v2.1.257dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Monitoring.
the line in the docs* For Bash tool: includes `bash_command`, `full_command`, `timeout`, `description`, and `dangerouslyDisableSandbox`, plus `git_commit_id` and `git_branch` when a `git commit` command succeeds. `git_commit_id` is the full commit SHA when th… |
|
v2.1.246dangerouslyDisableSandbox |
Documentation arrivedAnthropic's documentation has since written up dangerouslyDisableSandbox, on Monitoring.
the line in the docs* For Bash tool: includes `bash_command`, `full_command`, `timeout`, `description`, and `dangerouslyDisableSandbox`, plus `git_commit_id` and `git_branch` when a `git commit` command succeeds. `git_commit_id` is the full commit SHA when th… |
|
v2.1.251/fast |
Documentation arrivedA small documentation edit on Speed up responses with fast mode touched a line naming /fast after this was published.
the line in the docs* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's… |
|
v2.1.248/fast |
Documentation arrivedA small documentation edit on Speed up responses with fast mode touched a line naming /fast after this was published.
the line in the docs* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's… |
|
v2.1.239/cost |
Documentation arrivedA small documentation edit on Speed up responses with fast mode touched a line naming /cost after this was published.
the line in the docs* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's… |
|
v2.1.234/cost |
Documentation arrivedA small documentation edit on Speed up responses with fast mode touched a line naming /cost after this was published.
the line in the docs* **Usage credits turned on for subscription plans**: on a Pro, Max, Team, or Enterprise plan, your account must have [usage credits](/docs/en/costs#add-usage-credits-to-your-subscription) turned on, which allows billing beyond your plan's… |
|
v2.1.268/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.248/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.248/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.248/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.232/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.232/usage-credits |
Documentation arrivedAnthropic's documentation has since written up /usage-credits, on Error reference.
the line in the docs* On Pro and Max, increase your monthly spend limit in [**Settings > Usage**](https://claude.ai/settings/usage) on claude.ai, or run `/usage-credits` |
|
v2.1.260/statusline |
Documentation arrivedAnthropic's documentation has since written up /statusline, on Error reference.
the line in the docsBefore a window runs out, Claude Code can warn you that you've used most of it, with a message such as `You've used 85% of your session limit · resets 3:45pm`. To watch your remaining allowance continuously, add the `rate_limits` fields to… |
|
v2.1.265CLAUDE_CODE_DISABLE_1M_CONTEXT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_1M_CONTEXT, on Error reference.
the line in the docs| `CLAUDE_CODE_DISABLE_1M_CONTEXT is set, but the 200K limit isn't enforced` | [Configuration warnings](#the-200k-limit-isnt-enforced) | |
|
v2.1.265CLAUDE_CODE_DISABLE_1M_CONTEXT |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_DISABLE_1M_CONTEXT, on Error reference.
the line in the docs| `CLAUDE_CODE_DISABLE_1M_CONTEXT is set, but the 200K limit isn't enforced` | [Configuration warnings](#the-200k-limit-isnt-enforced) | |
|
v2.1.248crossSessionInbound |
Documentation arrivedAnthropic's documentation has since written up crossSessionInbound, on Error reference.
the line in the docs| `"crossSessionInbound" must be one of "accept", "hold", "refuse"` | [Configuration warnings](#crosssessioninbound-must-be-one-of-accept-hold-refuse) | |
|
v2.1.248crossSessionInbound |
Documentation arrivedAnthropic's documentation has since written up crossSessionInbound, on Error reference.
the line in the docs| `"crossSessionInbound" must be one of "accept", "hold", "refuse"` | [Configuration warnings](#crosssessioninbound-must-be-one-of-accept-hold-refuse) | |
|
v2.1.236CLAUDE_CODE_SKIP_PROMPT_HISTORY |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SKIP_PROMPT_HISTORY, on Error reference.
the line in the docs| `Transcript saving is off — CLAUDE_CODE_SKIP_PROMPT_HISTORY is set` | [Session saving warnings](#transcript-saving-is-off-skip-prompt-history) | |
|
v2.1.234CLAUDE_CODE_SKIP_PROMPT_HISTORY |
Documentation arrivedAnthropic's documentation has since written up CLAUDE_CODE_SKIP_PROMPT_HISTORY, on Error reference.
the line in the docs| `Transcript saving is off — CLAUDE_CODE_SKIP_PROMPT_HISTORY is set` | [Session saving warnings](#transcript-saving-is-off-skip-prompt-history) | |
|
v2.1.257bindings |
Documentation arrivedAnthropic's documentation has since written up bindings, on Error reference.
the line in the docs| `Your Zed keymap isn't a readable list of keybindings` | [Command-line errors](#terminal-setup-left-your-zed-keymap-unchanged) | |
|
v2.1.246command: |
Documentation arrivedAnthropic's documentation has since written up command:, on Error reference.
the line in the docs| `Unknown command: /<name>`, with or without a `Did you mean` suggestion | [Command-line errors](#unknown-command) | |
|
v2.1.234--agents |
Documentation arrivedAnthropic's documentation has since written up --agents, on Error reference.
the line in the docs| `Error: Invalid --agents configuration:` | [Command-line errors](#invalid-agents-configuration) | |
|
v2.1.268--print |
Documentation arrivedAnthropic's documentation has since written up --print, on Error reference.
the line in the docs| `--bg and --print conflict` | [Command-line errors](#command-line-errors) | |
|
v2.1.268deadline |
Documentation arrivedAnthropic's documentation has since written up deadline, on Error reference.
the line in the docs| `Download timed out: exceeded the total deadline` | [Installation errors](#the-connection-dropped-while-downloading-the-update) | |
|
v2.1.267safeguards |
Documentation arrivedAnthropic's documentation has since written up safeguards, on Error reference.
the line in the docs| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) | |
|
v2.1.267safeguards |
Documentation arrivedAnthropic's documentation has since written up safeguards, on Error reference.
the line in the docs| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) | |
|
v2.1.267safeguards |
Documentation arrivedAnthropic's documentation has since written up safeguards, on Error reference.
the line in the docs| `<model>'s safeguards flagged this message` | [Request errors](#safety-measures-flagged-a-cybersecurity-topic) | |
|
v2.1.268streaming |
Documentation arrivedAnthropic's documentation has since written up streaming, on Error reference.
the line in the docs| `Streaming response ended before any complete data was received` | [Network](#streaming-response-ended-before-any-complete-data-was-received) | |
|
v2.1.268streaming |
Documentation arrivedAnthropic's documentation has since written up streaming, on Error reference.
the line in the docs| `Streaming response ended before any complete data was received` | [Network](#streaming-response-ended-before-any-complete-data-was-received) | |
|
v2.1.268/remote-control |
Documentation arrivedAnthropic's documentation has since written up /remote-control, on Error reference.
the line in the docs| `Claude.ai login was rejected — run /login, then /remote-control` | [Authentication](#remote-control-couldnt-refresh-your-login) | |
|
v2.1.268/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docs| `Not logged in · Please run /login` | [Authentication](#not-logged-in) | |
|
v2.1.268/login |
Documentation arrivedAnthropic's documentation has since written up /login, on Error reference.
the line in the docs| `Not logged in · Please run /login` | [Authentication](#not-logged-in) | |
|
v2.1.265diff |
Documentation arrivedA small documentation edit on Manage costs effectively touched a line naming diff after this was published.
the line in the docsDevelopers usually bring limit questions to their admin, so it helps to know which ceiling they hit. These situations mean different things: |
|
v2.1.248cleanupPeriodDays |
Documentation arrivedAnthropic's documentation has since written up cleanupPeriodDays, on All settings.
the line in the docs| Every other key | Takes the value from the highest source that sets it | [`cleanupPeriodDays`](#cleanupperioddays), [`model`](#model) | |
|
v2.1.248cleanupPeriodDays |
Documentation arrivedAnthropic's documentation has since written up cleanupPeriodDays, on All settings.
the line in the docs| Every other key | Takes the value from the highest source that sets it | [`cleanupPeriodDays`](#cleanupperioddays), [`model`](#model) | |
|
v2.1.265policyHelper |
Documentation arrivedAnthropic's documentation has since written up policyHelper, on All settings.
the line in the docs| Read from the highest-priority source only | Reads the key only from the highest-priority source that carries a policy key, so a lower source's value is ignored even when the highest source sets none | [`apiKeyHelper`](#apikeyhelper), [`… |
|
v2.1.257policyHelper |
Documentation arrivedAnthropic's documentation has since written up policyHelper, on All settings.
the line in the docs| Read from the highest-priority source only | Reads the key only from the highest-priority source that carries a policy key, so a lower source's value is ignored even when the highest source sets none | [`apiKeyHelper`](#apikeyhelper), [`… |
|
v2.1.265forceLoginGatewayUrl |
Documentation arrivedAnthropic's documentation has since written up forceLoginGatewayUrl, on All settings.
the line in the docs* **[`forceLoginGatewayUrl`](#forcelogingatewayurl) and the `"gateway"` value of [`forceLoginMethod`](#forceloginmethod)**: Claude Code never reads either from server-managed settings, so a value there neither applies nor hides one set in … |
|
v2.1.247forceLoginGatewayUrl |
Documentation arrivedAnthropic's documentation has since written up forceLoginGatewayUrl, on All settings.
the line in the docs* **[`forceLoginGatewayUrl`](#forcelogingatewayurl) and the `"gateway"` value of [`forceLoginMethod`](#forceloginmethod)**: Claude Code never reads either from server-managed settings, so a value there neither applies nor hides one set in … |
|
v2.1.247awsAuthRefresh |
Documentation arrivedAnthropic's documentation has since written up awsAuthRefresh, on All settings.
the line in the docs| Read from the highest-priority source only | Reads the key only from the highest-priority source that carries a policy key, so a lower source's value is ignored even when the highest source sets none | [`apiKeyHelper`](#apikeyhelper), [`… |